Merge 4.9.256 into android-4.9-q
Changes in 4.9.256
Linux 4.9.256
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I4f7bc2732a32f6a9eede516c7eab6f39094ad728
diff --git a/.gitignore b/.gitignore
index 0c39aa2..4105cfb 100644
--- a/.gitignore
+++ b/.gitignore
@@ -115,3 +115,6 @@
# Kdevelop4
*.kdev4
+
+# fetched Android config fragments
+kernel/configs/android-*.cfg
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 3acc4f1..4a5a887 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -436,6 +436,8 @@
- info on the magic SysRq key.
target/
- directory with info on generating TCM v4 fabric .ko modules
+tee.txt
+ - info on the TEE subsystem and drivers
this_cpu_ops.txt
- List rationale behind and the way to use this_cpu operations.
thermal/
diff --git a/Documentation/ABI/obsolete/sysfs-block-zram b/Documentation/ABI/obsolete/sysfs-block-zram
deleted file mode 100644
index 720ea92..0000000
--- a/Documentation/ABI/obsolete/sysfs-block-zram
+++ /dev/null
@@ -1,119 +0,0 @@
-What: /sys/block/zram<id>/num_reads
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The num_reads file is read-only and specifies the number of
- reads (failed or successful) done on this device.
- Now accessible via zram<id>/stat node.
-
-What: /sys/block/zram<id>/num_writes
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The num_writes file is read-only and specifies the number of
- writes (failed or successful) done on this device.
- Now accessible via zram<id>/stat node.
-
-What: /sys/block/zram<id>/invalid_io
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The invalid_io file is read-only and specifies the number of
- non-page-size-aligned I/O requests issued to this device.
- Now accessible via zram<id>/io_stat node.
-
-What: /sys/block/zram<id>/failed_reads
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The failed_reads file is read-only and specifies the number of
- failed reads happened on this device.
- Now accessible via zram<id>/io_stat node.
-
-What: /sys/block/zram<id>/failed_writes
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The failed_writes file is read-only and specifies the number of
- failed writes happened on this device.
- Now accessible via zram<id>/io_stat node.
-
-What: /sys/block/zram<id>/notify_free
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The notify_free file is read-only. Depending on device usage
- scenario it may account a) the number of pages freed because
- of swap slot free notifications or b) the number of pages freed
- because of REQ_DISCARD requests sent by bio. The former ones
- are sent to a swap block device when a swap slot is freed, which
- implies that this disk is being used as a swap disk. The latter
- ones are sent by filesystem mounted with discard option,
- whenever some data blocks are getting discarded.
- Now accessible via zram<id>/io_stat node.
-
-What: /sys/block/zram<id>/zero_pages
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The zero_pages file is read-only and specifies number of zero
- filled pages written to this disk. No memory is allocated for
- such pages.
- Now accessible via zram<id>/mm_stat node.
-
-What: /sys/block/zram<id>/orig_data_size
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The orig_data_size file is read-only and specifies uncompressed
- size of data stored in this disk. This excludes zero-filled
- pages (zero_pages) since no memory is allocated for them.
- Unit: bytes
- Now accessible via zram<id>/mm_stat node.
-
-What: /sys/block/zram<id>/compr_data_size
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The compr_data_size file is read-only and specifies compressed
- size of data stored in this disk. So, compression ratio can be
- calculated using orig_data_size and this statistic.
- Unit: bytes
- Now accessible via zram<id>/mm_stat node.
-
-What: /sys/block/zram<id>/mem_used_total
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The mem_used_total file is read-only and specifies the amount
- of memory, including allocator fragmentation and metadata
- overhead, allocated for this disk. So, allocator space
- efficiency can be calculated using compr_data_size and this
- statistic.
- Unit: bytes
- Now accessible via zram<id>/mm_stat node.
-
-What: /sys/block/zram<id>/mem_used_max
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The mem_used_max file is read/write and specifies the amount
- of maximum memory zram have consumed to store compressed data.
- For resetting the value, you should write "0". Otherwise,
- you could see -EINVAL.
- Unit: bytes
- Downgraded to write-only node: so it's possible to set new
- value only; its current value is stored in zram<id>/mm_stat
- node.
-
-What: /sys/block/zram<id>/mem_limit
-Date: August 2015
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The mem_limit file is read/write and specifies the maximum
- amount of memory ZRAM can use to store the compressed data.
- The limit could be changed in run time and "0" means disable
- the limit. No limit is the initial state. Unit: bytes
- Downgraded to write-only node: so it's possible to set new
- value only; its current value is stored in zram<id>/mm_stat
- node.
diff --git a/Documentation/ABI/testing/procfs-concurrent_time b/Documentation/ABI/testing/procfs-concurrent_time
new file mode 100644
index 0000000..55b4142
--- /dev/null
+++ b/Documentation/ABI/testing/procfs-concurrent_time
@@ -0,0 +1,16 @@
+What: /proc/uid_concurrent_active_time
+Date: December 2018
+Contact: Connor O'Brien <connoro@google.com>
+Description:
+ The /proc/uid_concurrent_active_time file displays aggregated cputime
+ numbers for each uid, broken down by the total number of cores that were
+ active while the uid's task was running.
+
+What: /proc/uid_concurrent_policy_time
+Date: December 2018
+Contact: Connor O'Brien <connoro@google.com>
+Description:
+ The /proc/uid_concurrent_policy_time file displays aggregated cputime
+ numbers for each uid, broken down based on the cpufreq policy
+ of the core used by the uid's task and the number of cores associated
+ with that policy that were active while the uid's task was running.
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup
new file mode 100644
index 0000000..0a54ed0
--- /dev/null
+++ b/Documentation/ABI/testing/procfs-smaps_rollup
@@ -0,0 +1,31 @@
+What: /proc/pid/smaps_rollup
+Date: August 2017
+Contact: Daniel Colascione <dancol@google.com>
+Description:
+ This file provides pre-summed memory information for a
+ process. The format is identical to /proc/pid/smaps,
+ except instead of an entry for each VMA in a process,
+ smaps_rollup has a single entry (tagged "[rollup]")
+ for which each field is the sum of the corresponding
+ fields from all the maps in /proc/pid/smaps.
+ For more details, see the procfs man page.
+
+ Typical output looks like this:
+
+ 00100000-ff709000 ---p 00000000 00:00 0 [rollup]
+ Rss: 884 kB
+ Pss: 385 kB
+ Shared_Clean: 696 kB
+ Shared_Dirty: 0 kB
+ Private_Clean: 120 kB
+ Private_Dirty: 68 kB
+ Referenced: 884 kB
+ Anonymous: 68 kB
+ LazyFree: 0 kB
+ AnonHugePages: 0 kB
+ ShmemPmdMapped: 0 kB
+ Shared_Hugetlb: 0 kB
+ Private_Hugetlb: 0 kB
+ Swap: 0 kB
+ SwapPss: 0 kB
+ Locked: 385 kB
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index 4518d30..14b2bf2 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -22,41 +22,6 @@
device. The reset operation frees all the memory associated
with this device.
-What: /sys/block/zram<id>/num_reads
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The num_reads file is read-only and specifies the number of
- reads (failed or successful) done on this device.
-
-What: /sys/block/zram<id>/num_writes
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The num_writes file is read-only and specifies the number of
- writes (failed or successful) done on this device.
-
-What: /sys/block/zram<id>/invalid_io
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The invalid_io file is read-only and specifies the number of
- non-page-size-aligned I/O requests issued to this device.
-
-What: /sys/block/zram<id>/failed_reads
-Date: February 2014
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The failed_reads file is read-only and specifies the number of
- failed reads happened on this device.
-
-What: /sys/block/zram<id>/failed_writes
-Date: February 2014
-Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
-Description:
- The failed_writes file is read-only and specifies the number of
- failed writes happened on this device.
-
What: /sys/block/zram<id>/max_comp_streams
Date: February 2014
Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
@@ -73,74 +38,24 @@
available and selected compression algorithms, change
compression algorithm selection.
-What: /sys/block/zram<id>/notify_free
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The notify_free file is read-only. Depending on device usage
- scenario it may account a) the number of pages freed because
- of swap slot free notifications or b) the number of pages freed
- because of REQ_DISCARD requests sent by bio. The former ones
- are sent to a swap block device when a swap slot is freed, which
- implies that this disk is being used as a swap disk. The latter
- ones are sent by filesystem mounted with discard option,
- whenever some data blocks are getting discarded.
-
-What: /sys/block/zram<id>/zero_pages
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The zero_pages file is read-only and specifies number of zero
- filled pages written to this disk. No memory is allocated for
- such pages.
-
-What: /sys/block/zram<id>/orig_data_size
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The orig_data_size file is read-only and specifies uncompressed
- size of data stored in this disk. This excludes zero-filled
- pages (zero_pages) since no memory is allocated for them.
- Unit: bytes
-
-What: /sys/block/zram<id>/compr_data_size
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The compr_data_size file is read-only and specifies compressed
- size of data stored in this disk. So, compression ratio can be
- calculated using orig_data_size and this statistic.
- Unit: bytes
-
-What: /sys/block/zram<id>/mem_used_total
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The mem_used_total file is read-only and specifies the amount
- of memory, including allocator fragmentation and metadata
- overhead, allocated for this disk. So, allocator space
- efficiency can be calculated using compr_data_size and this
- statistic.
- Unit: bytes
-
What: /sys/block/zram<id>/mem_used_max
Date: August 2014
Contact: Minchan Kim <minchan@kernel.org>
Description:
- The mem_used_max file is read/write and specifies the amount
- of maximum memory zram have consumed to store compressed data.
- For resetting the value, you should write "0". Otherwise,
- you could see -EINVAL.
+ The mem_used_max file is write-only and is used to reset
+ the counter of maximum memory zram have consumed to store
+ compressed data. For resetting the value, you should write
+ "0". Otherwise, you could see -EINVAL.
Unit: bytes
What: /sys/block/zram<id>/mem_limit
Date: August 2014
Contact: Minchan Kim <minchan@kernel.org>
Description:
- The mem_limit file is read/write and specifies the maximum
- amount of memory ZRAM can use to store the compressed data. The
- limit could be changed in run time and "0" means disable the
- limit. No limit is the initial state. Unit: bytes
+ The mem_limit file is write-only and specifies the maximum
+ amount of memory ZRAM can use to store the compressed data.
+ The limit could be changed in run time and "0" means disable
+ the limit. No limit is the initial state. Unit: bytes
What: /sys/block/zram<id>/compact
Date: August 2015
@@ -175,3 +90,50 @@
device's debugging info useful for kernel developers. Its
format is not documented intentionally and may change
anytime without any notice.
+
+What: /sys/block/zram<id>/backing_dev
+Date: June 2017
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The backing_dev file is read-write and set up backing
+ device for zram to write incompressible pages.
+ For using, user should enable CONFIG_ZRAM_WRITEBACK.
+
+What: /sys/block/zram<id>/idle
+Date: November 2018
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ idle file is write-only and mark zram slot as idle.
+ If system has mounted debugfs, user can see which slots
+ are idle via /sys/kernel/debug/zram/zram<id>/block_state
+
+What: /sys/block/zram<id>/writeback
+Date: November 2018
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The writeback file is write-only and trigger idle and/or
+ huge page writeback to backing device.
+
+What: /sys/block/zram<id>/bd_stat
+Date: November 2018
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The bd_stat file is read-only and represents backing device's
+ statistics (bd_count, bd_reads, bd_writes) in a format
+ similar to block layer statistics file format.
+
+What: /sys/block/zram<id>/writeback_limit_enable
+Date: November 2018
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The writeback_limit_enable file is read-write and specifies
+ eanbe of writeback_limit feature. "1" means eable the feature.
+ No limit "0" is the initial state.
+
+What: /sys/block/zram<id>/writeback_limit
+Date: November 2018
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The writeback_limit file is read-write and specifies the maximum
+ amount of writeback ZRAM can do. The limit could be changed
+ in run time.
diff --git a/Documentation/ABI/testing/sysfs-class-dual-role-usb b/Documentation/ABI/testing/sysfs-class-dual-role-usb
new file mode 100644
index 0000000..a900fd7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-dual-role-usb
@@ -0,0 +1,71 @@
+What: /sys/class/dual_role_usb/.../
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ Provide a generic interface to monitor and change
+ the state of dual role usb ports. The name here
+ refers to the name mentioned in the
+ dual_role_phy_desc that is passed while registering
+ the dual_role_phy_intstance through
+ devm_dual_role_instance_register.
+
+What: /sys/class/dual_role_usb/.../supported_modes
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ This is a static node, once initialized this
+ is not expected to change during runtime. "dfp"
+ refers to "downstream facing port" i.e. port can
+ only act as host. "ufp" refers to "upstream
+ facing port" i.e. port can only act as device.
+ "dfp ufp" refers to "dual role port" i.e. the port
+ can either be a host port or a device port.
+
+What: /sys/class/dual_role_usb/.../mode
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The mode node refers to the current mode in which the
+ port is operating. "dfp" for host ports. "ufp" for device
+ ports and "none" when cable is not connected.
+
+ On devices where the USB mode is software-controllable,
+ userspace can change the mode by writing "dfp" or "ufp".
+ On devices where the USB mode is fixed in hardware,
+ this attribute is read-only.
+
+What: /sys/class/dual_role_usb/.../power_role
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The power_role node mentions whether the port
+ is "sink"ing or "source"ing power. "none" if
+ they are not connected.
+
+ On devices implementing USB Power Delivery,
+ userspace can control the power role by writing "sink" or
+ "source". On devices without USB-PD, this attribute is
+ read-only.
+
+What: /sys/class/dual_role_usb/.../data_role
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The data_role node mentions whether the port
+ is acting as "host" or "device" for USB data connection.
+ "none" if there is no active data link.
+
+ On devices implementing USB Power Delivery, userspace
+ can control the data role by writing "host" or "device".
+ On devices without USB-PD, this attribute is read-only
+
+What: /sys/class/dual_role_usb/.../powers_vconn
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The powers_vconn node mentions whether the port
+ is supplying power for VCONN pin.
+
+ On devices with software control of VCONN,
+ userspace can disable the power supply to VCONN by writing "n",
+ or enable the power supply by writing "y".
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index a809f60..e916c1e 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -51,18 +51,63 @@
Controls the dirty page count condition for the in-place-update
policies.
+What: /sys/fs/f2fs/<disk>/min_seq_blocks
+Date: August 2018
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls the dirty page count condition for batched sequential
+ writes in ->writepages.
+
+
+What: /sys/fs/f2fs/<disk>/min_hot_blocks
+Date: March 2017
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls the dirty page count condition for redefining hot data.
+
+What: /sys/fs/f2fs/<disk>/min_ssr_sections
+Date: October 2017
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Controls the fee section threshold to trigger SSR allocation.
+
What: /sys/fs/f2fs/<disk>/max_small_discards
Date: November 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the issue rate of small discard commands.
+What: /sys/fs/f2fs/<disk>/discard_granularity
+Date: July 2017
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Controls discard granularity of inner discard thread, inner thread
+ will not issue discards with size that is smaller than granularity.
+ The unit size is one block, now only support configuring in range
+ of [1, 512].
+
+What: /sys/fs/f2fs/<disk>/umount_discard_timeout
+Date: January 2019
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Set timeout to issue discard commands during umount.
+ Default: 5 secs
+
What: /sys/fs/f2fs/<disk>/max_victim_search
Date: January 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the number of trials to find a victim segment.
+What: /sys/fs/f2fs/<disk>/migration_granularity
+Date: October 2018
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Controls migration granularity of garbage collection on large
+ section, it can let GC move partial segment{s} of one section
+ in one GC cycle, so that dispersing heavy overhead GC to
+ multiple lightweight one.
+
What: /sys/fs/f2fs/<disk>/dir_level
Date: March 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
@@ -80,6 +125,7 @@
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the trimming rate in batch mode.
+ <deprecated>
What: /sys/fs/f2fs/<disk>/cp_interval
Date: October 2015
@@ -91,7 +137,28 @@
Date: January 2016
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
- Controls the idle timing.
+ Controls the idle timing for all paths other than
+ discard and gc path.
+
+What: /sys/fs/f2fs/<disk>/discard_idle_interval
+Date: September 2018
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Contact: "Sahitya Tummala" <stummala@codeaurora.org>
+Description:
+ Controls the idle timing for discard path.
+
+What: /sys/fs/f2fs/<disk>/gc_idle_interval
+Date: September 2018
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Contact: "Sahitya Tummala" <stummala@codeaurora.org>
+Description:
+ Controls the idle timing for gc path.
+
+What: /sys/fs/f2fs/<disk>/iostat_enable
+Date: August 2017
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Controls to enable/disable IO stat.
What: /sys/fs/f2fs/<disk>/ra_nid_pages
Date: October 2015
@@ -112,3 +179,67 @@
Contact: "Shuoran Liu" <liushuoran@huawei.com>
Description:
Shows total written kbytes issued to disk.
+
+What: /sys/fs/f2fs/<disk>/feature
+Date: July 2017
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Shows all enabled features in current device.
+
+What: /sys/fs/f2fs/<disk>/inject_rate
+Date: May 2016
+Contact: "Sheng Yong" <shengyong1@huawei.com>
+Description:
+ Controls the injection rate.
+
+What: /sys/fs/f2fs/<disk>/inject_type
+Date: May 2016
+Contact: "Sheng Yong" <shengyong1@huawei.com>
+Description:
+ Controls the injection type.
+
+What: /sys/fs/f2fs/<disk>/reserved_blocks
+Date: June 2017
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Controls target reserved blocks in system, the threshold
+ is soft, it could exceed current available user space.
+
+What: /sys/fs/f2fs/<disk>/current_reserved_blocks
+Date: October 2017
+Contact: "Yunlong Song" <yunlong.song@huawei.com>
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Shows current reserved blocks in system, it may be temporarily
+ smaller than target_reserved_blocks, but will gradually
+ increase to target_reserved_blocks when more free blocks are
+ freed by user later.
+
+What: /sys/fs/f2fs/<disk>/gc_urgent
+Date: August 2017
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Do background GC agressively
+
+What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time
+Date: August 2017
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls sleep time of GC urgent mode
+
+What: /sys/fs/f2fs/<disk>/readdir_ra
+Date: November 2017
+Contact: "Sheng Yong" <shengyong1@huawei.com>
+Description:
+ Controls readahead inode block in readdir.
+
+What: /sys/fs/f2fs/<disk>/extension_list
+Date: Feburary 2018
+Contact: "Chao Yu" <yuchao0@huawei.com>
+Description:
+ Used to control configure extension list:
+ - Query: cat /sys/fs/f2fs/<disk>/extension_list
+ - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list
+ - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
+ - [h] means add/del hot file extension
+ - [c] means add/del cold file extension
diff --git a/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
new file mode 100644
index 0000000..acb19b9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
@@ -0,0 +1,16 @@
+What: /sys/kernel/wakeup_reasons/last_resume_reason
+Date: February 2014
+Contact: Ruchi Kandoi <kandoiruchi@google.com>
+Description:
+ The /sys/kernel/wakeup_reasons/last_resume_reason is
+ used to report wakeup reasons after system exited suspend.
+
+What: /sys/kernel/wakeup_reasons/last_suspend_time
+Date: March 2015
+Contact: jinqian <jinqian@google.com>
+Description:
+ The /sys/kernel/wakeup_reasons/last_suspend_time is
+ used to report time spent in last suspend cycle. It contains
+ two numbers (in seconds) separated by space. First number is
+ the time spent in suspend and resume processes. Second number
+ is the time spent in sleep state.
\ No newline at end of file
diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt
new file mode 100644
index 0000000..4fb40fe
--- /dev/null
+++ b/Documentation/accounting/psi.txt
@@ -0,0 +1,180 @@
+================================
+PSI - Pressure Stall Information
+================================
+
+:Date: April, 2018
+:Author: Johannes Weiner <hannes@cmpxchg.org>
+
+When CPU, memory or IO devices are contended, workloads experience
+latency spikes, throughput losses, and run the risk of OOM kills.
+
+Without an accurate measure of such contention, users are forced to
+either play it safe and under-utilize their hardware resources, or
+roll the dice and frequently suffer the disruptions resulting from
+excessive overcommit.
+
+The psi feature identifies and quantifies the disruptions caused by
+such resource crunches and the time impact it has on complex workloads
+or even entire systems.
+
+Having an accurate measure of productivity losses caused by resource
+scarcity aids users in sizing workloads to hardware--or provisioning
+hardware according to workload demand.
+
+As psi aggregates this information in realtime, systems can be managed
+dynamically using techniques such as load shedding, migrating jobs to
+other systems or data centers, or strategically pausing or killing low
+priority or restartable batch jobs.
+
+This allows maximizing hardware utilization without sacrificing
+workload health or risking major disruptions such as OOM kills.
+
+Pressure interface
+==================
+
+Pressure information for each resource is exported through the
+respective file in /proc/pressure/ -- cpu, memory, and io.
+
+The format for CPU is as such:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+and for memory and IO:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+full avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+The "some" line indicates the share of time in which at least some
+tasks are stalled on a given resource.
+
+The "full" line indicates the share of time in which all non-idle
+tasks are stalled on a given resource simultaneously. In this state
+actual CPU cycles are going to waste, and a workload that spends
+extended time in this state is considered to be thrashing. This has
+severe impact on performance, and it's useful to distinguish this
+situation from a state where some tasks are stalled but the CPU is
+still doing productive work. As such, time spent in this subset of the
+stall state is tracked separately and exported in the "full" averages.
+
+The ratios are tracked as recent trends over ten, sixty, and three
+hundred second windows, which gives insight into short term events as
+well as medium and long term trends. The total absolute stall time is
+tracked and exported as well, to allow detection of latency spikes
+which wouldn't necessarily make a dent in the time averages, or to
+average trends over custom time frames.
+
+Monitoring for pressure thresholds
+==================================
+
+Users can register triggers and use poll() to be woken up when resource
+pressure exceeds certain thresholds.
+
+A trigger describes the maximum cumulative stall time over a specific
+time window, e.g. 100ms of total stall time within any 500ms window to
+generate a wakeup event.
+
+To register a trigger user has to open psi interface file under
+/proc/pressure/ representing the resource to be monitored and write the
+desired threshold and time window. The open file descriptor should be
+used to wait for trigger events using select(), poll() or epoll().
+The following format is used:
+
+<some|full> <stall amount in us> <time window in us>
+
+For example writing "some 150000 1000000" into /proc/pressure/memory
+would add 150ms threshold for partial memory stall measured within
+1sec time window. Writing "full 50000 1000000" into /proc/pressure/io
+would add 50ms threshold for full io stall measured within 1sec time window.
+
+Triggers can be set on more than one psi metric and more than one trigger
+for the same psi metric can be specified. However for each trigger a separate
+file descriptor is required to be able to poll it separately from others,
+therefore for each trigger a separate open() syscall should be made even
+when opening the same psi interface file.
+
+Monitors activate only when system enters stall state for the monitored
+psi metric and deactivates upon exit from the stall state. While system is
+in the stall state psi signal growth is monitored at a rate of 10 times per
+tracking window.
+
+The kernel accepts window sizes ranging from 500ms to 10s, therefore min
+monitoring update interval is 50ms and max is 1s. Min limit is set to
+prevent overly frequent polling. Max limit is chosen as a high enough number
+after which monitors are most likely not needed and psi averages can be used
+instead.
+
+When activated, psi monitor stays active for at least the duration of one
+tracking window to avoid repeated activations/deactivations when system is
+bouncing in and out of the stall state.
+
+Notifications to the userspace are rate-limited to one per tracking window.
+
+The trigger will de-register when the file descriptor used to define the
+trigger is closed.
+
+Userspace monitor usage example
+===============================
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <poll.h>
+#include <string.h>
+#include <unistd.h>
+
+/*
+ * Monitor memory partial stall with 1s tracking window size
+ * and 150ms threshold.
+ */
+int main() {
+ const char trig[] = "some 150000 1000000";
+ struct pollfd fds;
+ int n;
+
+ fds.fd = open("/proc/pressure/memory", O_RDWR | O_NONBLOCK);
+ if (fds.fd < 0) {
+ printf("/proc/pressure/memory open error: %s\n",
+ strerror(errno));
+ return 1;
+ }
+ fds.events = POLLPRI;
+
+ if (write(fds.fd, trig, strlen(trig) + 1) < 0) {
+ printf("/proc/pressure/memory write error: %s\n",
+ strerror(errno));
+ return 1;
+ }
+
+ printf("waiting for events...\n");
+ while (1) {
+ n = poll(&fds, 1, -1);
+ if (n < 0) {
+ printf("poll error: %s\n", strerror(errno));
+ return 1;
+ }
+ if (fds.revents & POLLERR) {
+ printf("got POLLERR, event source is gone\n");
+ return 0;
+ }
+ if (fds.revents & POLLPRI) {
+ printf("event triggered!\n");
+ } else {
+ printf("unknown event received: 0x%x\n", fds.revents);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+Cgroup2 interface
+=================
+
+In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem
+mounted, pressure stall information is also tracked for tasks grouped
+into cgroups. Each subdirectory in the cgroupfs mountpoint contains
+cpu.pressure, memory.pressure, and io.pressure files; the format is
+the same as the /proc/pressure/ files.
+
+Per-cgroup psi monitors can be specified and used the same way as
+system-wide ones.
diff --git a/Documentation/android.txt b/Documentation/android.txt
new file mode 100644
index 0000000..0f40a78
--- /dev/null
+++ b/Documentation/android.txt
@@ -0,0 +1,121 @@
+ =============
+ A N D R O I D
+ =============
+
+Copyright (C) 2009 Google, Inc.
+Written by Mike Chan <mike@android.com>
+
+CONTENTS:
+---------
+
+1. Android
+ 1.1 Required enabled config options
+ 1.2 Required disabled config options
+ 1.3 Recommended enabled config options
+2. Contact
+
+
+1. Android
+==========
+
+Android (www.android.com) is an open source operating system for mobile devices.
+This document describes configurations needed to run the Android framework on
+top of the Linux kernel.
+
+To see a working defconfig look at msm_defconfig or goldfish_defconfig
+which can be found at http://android.git.kernel.org in kernel/common.git
+and kernel/msm.git
+
+
+1.1 Required enabled config options
+-----------------------------------
+After building a standard defconfig, ensure that these options are enabled in
+your .config or defconfig if they are not already. Based off the msm_defconfig.
+You should keep the rest of the default options enabled in the defconfig
+unless you know what you are doing.
+
+ANDROID_PARANOID_NETWORK
+ASHMEM
+CONFIG_FB_MODE_HELPERS
+CONFIG_FONT_8x16
+CONFIG_FONT_8x8
+CONFIG_YAFFS_SHORT_NAMES_IN_RAM
+DAB
+EARLYSUSPEND
+FB
+FB_CFB_COPYAREA
+FB_CFB_FILLRECT
+FB_CFB_IMAGEBLIT
+FB_DEFERRED_IO
+FB_TILEBLITTING
+HIGH_RES_TIMERS
+INOTIFY
+INOTIFY_USER
+INPUT_EVDEV
+INPUT_GPIO
+INPUT_MISC
+LEDS_CLASS
+LEDS_GPIO
+LOCK_KERNEL
+LkOGGER
+LOW_MEMORY_KILLER
+MISC_DEVICES
+NEW_LEDS
+NO_HZ
+POWER_SUPPLY
+PREEMPT
+RAMFS
+RTC_CLASS
+RTC_LIB
+SWITCH
+SWITCH_GPIO
+TMPFS
+UID_STAT
+UID16
+USB_FUNCTION
+USB_FUNCTION_ADB
+USER_WAKELOCK
+VIDEO_OUTPUT_CONTROL
+WAKELOCK
+YAFFS_AUTO_YAFFS2
+YAFFS_FS
+YAFFS_YAFFS1
+YAFFS_YAFFS2
+
+
+1.2 Required disabled config options
+------------------------------------
+CONFIG_YAFFS_DISABLE_LAZY_LOAD
+DNOTIFY
+
+
+1.3 Recommended enabled config options
+------------------------------
+ANDROID_PMEM
+PSTORE_CONSOLE
+PSTORE_RAM
+SCHEDSTATS
+DEBUG_PREEMPT
+DEBUG_MUTEXES
+DEBUG_SPINLOCK_SLEEP
+DEBUG_INFO
+FRAME_POINTER
+CPU_FREQ
+CPU_FREQ_TABLE
+CPU_FREQ_DEFAULT_GOV_ONDEMAND
+CPU_FREQ_GOV_ONDEMAND
+CRC_CCITT
+EMBEDDED
+INPUT_TOUCHSCREEN
+I2C
+I2C_BOARDINFO
+LOG_BUF_SHIFT=17
+SERIAL_CORE
+SERIAL_CORE_CONSOLE
+
+
+2. Contact
+==========
+website: http://android.git.kernel.org
+
+mailing-lists: android-kernel@googlegroups.com
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index e55103a..a542b9f 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -30,3 +30,9 @@
- Switching I/O schedulers at runtime
writeback_cache_control.txt
- Control of volatile write back caches
+mmc-max-speed.txt
+ - eMMC layer speed simulation, related to /sys/block/mmcblk*/
+ attributes:
+ max_read_speed
+ max_write_speed
+ cache_size
diff --git a/Documentation/block/mmc-max-speed.txt b/Documentation/block/mmc-max-speed.txt
new file mode 100644
index 0000000..3f052b9
--- /dev/null
+++ b/Documentation/block/mmc-max-speed.txt
@@ -0,0 +1,38 @@
+eMMC Block layer simulation speed controls in /sys/block/mmcblk*/
+===============================================
+
+Turned on with CONFIG_MMC_SIMULATE_MAX_SPEED which enables MMC device speed
+limiting. Used to test and simulate the behavior of the system when
+confronted with a slow MMC.
+
+Enables max_read_speed, max_write_speed and cache_size attributes and module
+default parameters to control the write or read maximum KB/second speed
+behaviors.
+
+NB: There is room for improving the algorithm for aspects tied directly to
+eMMC specific behavior. For instance, wear leveling and stalls from an
+exhausted erase pool. We would expect that if there was a need to provide
+similar speed simulation controls to other types of block devices, aspects of
+their behavior are modelled separately (e.g. head seek times, heat assist,
+shingling and rotational latency).
+
+/sys/block/mmcblk0/max_read_speed:
+
+Number of KB/second reads allowed to the block device. Used to test and
+simulate the behavior of the system when confronted with a slow reading MMC.
+Set to 0 or "off" to place no speed limit.
+
+/sys/block/mmcblk0/max_write_speed:
+
+Number of KB/second writes allowed to the block device. Used to test and
+simulate the behavior of the system when confronted with a slow writing MMC.
+Set to 0 or "off" to place no speed limit.
+
+/sys/block/mmcblk0/cache_size:
+
+Number of MB of high speed memory or high speed SLC cache expected on the
+eMMC device being simulated. Used to help simulate the write-back behavior
+more accurately. The assumption is the cache has no delay, but draws down
+in the background to the MLC/TLC primary store at the max_write_speed rate.
+Any write speed delays will show up when the cache is full, or when an I/O
+request to flush is issued.
diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
index 0535ae1..6e5c2bb 100644
--- a/Documentation/blockdev/zram.txt
+++ b/Documentation/blockdev/zram.txt
@@ -156,47 +156,24 @@
A brief description of exported device attributes. For more details please
read Documentation/ABI/testing/sysfs-block-zram.
-Name access description
----- ------ -----------
-disksize RW show and set the device's disk size
-initstate RO shows the initialization state of the device
-reset WO trigger device reset
-num_reads RO the number of reads
-failed_reads RO the number of failed reads
-num_write RO the number of writes
-failed_writes RO the number of failed writes
-invalid_io RO the number of non-page-size-aligned I/O requests
-max_comp_streams RW the number of possible concurrent compress operations
-comp_algorithm RW show and change the compression algorithm
-notify_free RO the number of notifications to free pages (either
- slot free notifications or REQ_DISCARD requests)
-zero_pages RO the number of zero filled pages written to this disk
-orig_data_size RO uncompressed size of data stored in this disk
-compr_data_size RO compressed size of data stored in this disk
-mem_used_total RO the amount of memory allocated for this disk
-mem_used_max RW the maximum amount of memory zram have consumed to
- store the data (to reset this counter to the actual
- current value, write 1 to this attribute)
-mem_limit RW the maximum amount of memory ZRAM can use to store
- the compressed data
-pages_compacted RO the number of pages freed during compaction
- (available only via zram<id>/mm_stat node)
-compact WO trigger memory compaction
-debug_stat RO this file is used for zram debugging purposes
+Name access description
+---- ------ -----------
+disksize RW show and set the device's disk size
+initstate RO shows the initialization state of the device
+reset WO trigger device reset
+mem_used_max WO reset the `mem_used_max' counter (see later)
+mem_limit WO specifies the maximum amount of memory ZRAM can use
+ to store the compressed data
+writeback_limit WO specifies the maximum amount of write IO zram can
+ write out to backing device as 4KB unit
+writeback_limit_enable RW show and set writeback_limit feature
+max_comp_streams RW the number of possible concurrent compress operations
+comp_algorithm RW show and change the compression algorithm
+compact WO trigger memory compaction
+debug_stat RO this file is used for zram debugging purposes
+backing_dev RW set up backend storage for zram to write out
+idle WO mark allocated slot as idle
-WARNING
-=======
-per-stat sysfs attributes are considered to be deprecated.
-The basic strategy is:
--- the existing RW nodes will be downgraded to WO nodes (in linux 4.11)
--- deprecated RO sysfs nodes will eventually be removed (in linux 4.11)
-
-The list of deprecated attributes can be found here:
-Documentation/ABI/obsolete/sysfs-block-zram
-
-Basically, every attribute that has its own read accessible sysfs node
-(e.g. num_reads) *AND* is accessible via one of the stat files (zram<id>/stat
-or zram<id>/io_stat or zram<id>/mm_stat) is considered to be deprecated.
User space is advised to use the following files to read the device statistics.
@@ -211,22 +188,52 @@
layer and, thus, not available in zram<id>/stat file. It consists of a
single line of text and contains the following stats separated by
whitespace:
- failed_reads
- failed_writes
- invalid_io
- notify_free
+ failed_reads the number of failed reads
+ failed_writes the number of failed writes
+ invalid_io the number of non-page-size-aligned I/O requests
+ notify_free Depending on device usage scenario it may account
+ a) the number of pages freed because of swap slot free
+ notifications or b) the number of pages freed because of
+ REQ_DISCARD requests sent by bio. The former ones are
+ sent to a swap block device when a swap slot is freed,
+ which implies that this disk is being used as a swap disk.
+ The latter ones are sent by filesystem mounted with
+ discard option, whenever some data blocks are getting
+ discarded.
File /sys/block/zram<id>/mm_stat
The stat file represents device's mm statistics. It consists of a single
line of text and contains the following stats separated by whitespace:
- orig_data_size
- compr_data_size
- mem_used_total
- mem_limit
- mem_used_max
- zero_pages
- num_migrated
+ orig_data_size uncompressed size of data stored in this disk.
+ This excludes same-element-filled pages (same_pages) since
+ no memory is allocated for them.
+ Unit: bytes
+ compr_data_size compressed size of data stored in this disk
+ mem_used_total the amount of memory allocated for this disk. This
+ includes allocator fragmentation and metadata overhead,
+ allocated for this disk. So, allocator space efficiency
+ can be calculated using compr_data_size and this statistic.
+ Unit: bytes
+ mem_limit the maximum amount of memory ZRAM can use to store
+ the compressed data
+ mem_used_max the maximum amount of memory zram have consumed to
+ store the data
+ same_pages the number of same element filled pages written to this disk.
+ No memory is allocated for such pages.
+ pages_compacted the number of pages freed during compaction
+ huge_pages the number of incompressible pages
+
+File /sys/block/zram<id>/bd_stat
+
+The stat file represents device's backing device statistics. It consists of
+a single line of text and contains the following stats separated by whitespace:
+ bd_count size of data written in backing device.
+ Unit: 4K bytes
+ bd_reads the number of reads from backing device
+ Unit: 4K bytes
+ bd_writes the number of writes to backing device
+ Unit: 4K bytes
9) Deactivate:
swapoff /dev/zram0
@@ -241,5 +248,108 @@
resets the disksize to zero. You must set the disksize again
before reusing the device.
+* Optional Feature
+
+= writeback
+
+With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page
+to backing storage rather than keeping it in memory.
+To use the feature, admin should set up backing device via
+
+ "echo /dev/sda5 > /sys/block/zramX/backing_dev"
+
+before disksize setting. It supports only partition at this moment.
+If admin want to use incompressible page writeback, they could do via
+
+ "echo huge > /sys/block/zramX/write"
+
+To use idle page writeback, first, user need to declare zram pages
+as idle.
+
+ "echo all > /sys/block/zramX/idle"
+
+From now on, any pages on zram are idle pages. The idle mark
+will be removed until someone request access of the block.
+IOW, unless there is access request, those pages are still idle pages.
+
+Admin can request writeback of those idle pages at right timing via
+
+ "echo idle > /sys/block/zramX/writeback"
+
+With the command, zram writeback idle pages from memory to the storage.
+
+If there are lots of write IO with flash device, potentially, it has
+flash wearout problem so that admin needs to design write limitation
+to guarantee storage health for entire product life.
+
+To overcome the concern, zram supports "writeback_limit" feature.
+The "writeback_limit_enable"'s default value is 0 so that it doesn't limit
+any writeback. IOW, if admin want to apply writeback budget, he should
+enable writeback_limit_enable via
+
+ $ echo 1 > /sys/block/zramX/writeback_limit_enable
+
+Once writeback_limit_enable is set, zram doesn't allow any writeback
+until admin set the budget via /sys/block/zramX/writeback_limit.
+
+(If admin doesn't enable writeback_limit_enable, writeback_limit's value
+assigned via /sys/block/zramX/writeback_limit is meaninless.)
+
+If admin want to limit writeback as per-day 400M, he could do it
+like below.
+
+ $ MB_SHIFT=20
+ $ 4K_SHIFT=12
+ $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \
+ /sys/block/zram0/writeback_limit.
+ $ echo 1 > /sys/block/zram0/writeback_limit_enable
+
+If admin want to allow further write again once the bugdet is exausted,
+he could do it like below
+
+ $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \
+ /sys/block/zram0/writeback_limit
+
+If admin want to see remaining writeback budget since he set,
+
+ $ cat /sys/block/zramX/writeback_limit
+
+If admin want to disable writeback limit, he could do
+
+ $ echo 0 > /sys/block/zramX/writeback_limit_enable
+
+The writeback_limit count will reset whenever you reset zram(e.g.,
+system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of
+writeback happened until you reset the zram to allocate extra writeback
+budget in next setting is user's job.
+
+If admin want to measure writeback count in a certain period, he could
+know it via /sys/block/zram0/bd_stat's 3rd column.
+
+= memory tracking
+
+With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the
+zram block. It could be useful to catch cold or incompressible
+pages of the process with*pagemap.
+If you enable the feature, you could see block state via
+/sys/kernel/debug/zram/zram0/block_state". The output is as follows,
+
+ 300 75.033841 .wh.
+ 301 63.806904 s...
+ 302 63.806919 ..hi
+
+First column is zram's block index.
+Second column is access time since the system was booted
+Third column is state of the block.
+(s: same page
+w: written page to backing store
+h: huge page
+i: idle page)
+
+First line of above example says 300th block is accessed at 75.033841sec
+and the block's state is huge so it is written back to the backing
+storage. It's a debugging feature so anyone shouldn't rely on it to work
+properly.
+
Nitin Gupta
ngupta@vflare.org
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 4cc07ce..73950fd 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -717,6 +717,12 @@
$PERIOD duration. If only one number is written, $MAX is
updated.
+ cpu.pressure
+ A read-only nested-key file which exists on non-root cgroups.
+
+ Shows pressure stall information for CPU. See
+ Documentation/accounting/psi.txt for details.
+
5-2. Memory
@@ -925,6 +931,12 @@
Swap usage hard limit. If a cgroup's swap usage reaches this
limit, anonymous meomry of the cgroup will not be swapped out.
+ memory.pressure
+ A read-only nested-key file which exists on non-root cgroups.
+
+ Shows pressure stall information for memory. See
+ Documentation/accounting/psi.txt for details.
+
5-2-2. Usage Guidelines
@@ -1055,6 +1067,12 @@
8:16 rbps=2097152 wbps=max riops=max wiops=max
+ io.pressure
+ A read-only nested-key file which exists on non-root cgroups.
+
+ Shows pressure stall information for IO. See
+ Documentation/accounting/psi.txt for details.
+
5-3-2. Writeback
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index c15aa75..0cf9a6b 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -28,6 +28,7 @@
2.3 Userspace
2.4 Ondemand
2.5 Conservative
+2.6 Interactive
3. The Governor Interface in the CPUfreq Core
@@ -218,6 +219,91 @@
speed. Load for frequency increase is still evaluated every
sampling rate.
+2.6 Interactive
+---------------
+
+The CPUfreq governor "interactive" is designed for latency-sensitive,
+interactive workloads. This governor sets the CPU speed depending on
+usage, similar to "ondemand" and "conservative" governors, but with a
+different set of configurable behaviors.
+
+The tunable values for this governor are:
+
+above_hispeed_delay: When speed is at or above hispeed_freq, wait for
+this long before raising speed in response to continued high load.
+The format is a single delay value, optionally followed by pairs of
+CPU speeds and the delay to use at or above those speeds. Colons can
+be used between the speeds and associated delays for readability. For
+example:
+
+ 80000 1300000:200000 1500000:40000
+
+uses delay 80000 uS until CPU speed 1.3 GHz, at which speed delay
+200000 uS is used until speed 1.5 GHz, at which speed (and above)
+delay 40000 uS is used. If speeds are specified these must appear in
+ascending order. Default is 20000 uS.
+
+boost: If non-zero, immediately boost speed of all CPUs to at least
+hispeed_freq until zero is written to this attribute. If zero, allow
+CPU speeds to drop below hispeed_freq according to load as usual.
+Default is zero.
+
+boostpulse: On each write, immediately boost speed of all CPUs to
+hispeed_freq for at least the period of time specified by
+boostpulse_duration, after which speeds are allowed to drop below
+hispeed_freq according to load as usual. Its a write-only file.
+
+boostpulse_duration: Length of time to hold CPU speed at hispeed_freq
+on a write to boostpulse, before allowing speed to drop according to
+load as usual. Default is 80000 uS.
+
+go_hispeed_load: The CPU load at which to ramp to hispeed_freq.
+Default is 99%.
+
+hispeed_freq: An intermediate "high speed" at which to initially ramp
+when CPU load hits the value specified in go_hispeed_load. If load
+stays high for the amount of time specified in above_hispeed_delay,
+then speed may be bumped higher. Default is the maximum speed allowed
+by the policy at governor initialization time.
+
+io_is_busy: If set, the governor accounts IO time as CPU busy time.
+
+min_sample_time: The minimum amount of time to spend at the current
+frequency before ramping down. Default is 80000 uS.
+
+target_loads: CPU load values used to adjust speed to influence the
+current CPU load toward that value. In general, the lower the target
+load, the more often the governor will raise CPU speeds to bring load
+below the target. The format is a single target load, optionally
+followed by pairs of CPU speeds and CPU loads to target at or above
+those speeds. Colons can be used between the speeds and associated
+target loads for readability. For example:
+
+ 85 1000000:90 1700000:99
+
+targets CPU load 85% below speed 1GHz, 90% at or above 1GHz, until
+1.7GHz and above, at which load 99% is targeted. If speeds are
+specified these must appear in ascending order. Higher target load
+values are typically specified for higher speeds, that is, target load
+values also usually appear in an ascending order. The default is
+target load 90% for all speeds.
+
+timer_rate: Sample rate for reevaluating CPU load when the CPU is not
+idle. A deferrable timer is used, such that the CPU will not be woken
+from idle to service this timer until something else needs to run.
+(The maximum time to allow deferring this timer when not running at
+minimum speed is configurable via timer_slack.) Default is 20000 uS.
+
+timer_slack: Maximum additional time to defer handling the governor
+sampling timer beyond timer_rate when running at speeds above the
+minimum. For platforms that consume additional power at idle when
+CPUs are running at speeds greater than minimum, this places an upper
+bound on how long the timer will be deferred prior to re-evaluating
+load and dropping speed. For example, if timer_rate is 20000uS and
+timer_slack is 10000uS then timers will be deferred for up to 30msec
+when not at lowest speed. A value of -1 means defer timers
+indefinitely at all speeds. Default is 80000 uS.
+
3. The Governor Interface in the CPUfreq Core
=============================================
diff --git a/Documentation/device-mapper/boot.txt b/Documentation/device-mapper/boot.txt
new file mode 100644
index 0000000..adcaad5
--- /dev/null
+++ b/Documentation/device-mapper/boot.txt
@@ -0,0 +1,42 @@
+Boot time creation of mapped devices
+===================================
+
+It is possible to configure a device mapper device to act as the root
+device for your system in two ways.
+
+The first is to build an initial ramdisk which boots to a minimal
+userspace which configures the device, then pivot_root(8) in to it.
+
+For simple device mapper configurations, it is possible to boot directly
+using the following kernel command line:
+
+dm="<name> <uuid> <ro>,table line 1,...,table line n"
+
+name = the name to associate with the device
+ after boot, udev, if used, will use that name to label
+ the device node.
+uuid = may be 'none' or the UUID desired for the device.
+ro = may be "ro" or "rw". If "ro", the device and device table will be
+ marked read-only.
+
+Each table line may be as normal when using the dmsetup tool except for
+two variations:
+1. Any use of commas will be interpreted as a newline
+2. Quotation marks cannot be escaped and cannot be used without
+ terminating the dm= argument.
+
+Unless renamed by udev, the device node created will be dm-0 as the
+first minor number for the device-mapper is used during early creation.
+
+Example
+=======
+
+- Booting to a linear array made up of user-mode linux block devices:
+
+ dm="lroot none 0, 0 4096 linear 98:16 0, 4096 4096 linear 98:32 0" \
+ root=/dev/dm-0
+
+Will boot to a rw dm-linear target of 8192 sectors split across two
+block devices identified by their major:minor numbers. After boot, udev
+will rename this target to /dev/mapper/lroot (depending on the rules).
+No uuid was assigned.
diff --git a/Documentation/device-mapper/dm-bow.txt b/Documentation/device-mapper/dm-bow.txt
new file mode 100644
index 0000000..e3fc4d2
--- /dev/null
+++ b/Documentation/device-mapper/dm-bow.txt
@@ -0,0 +1,99 @@
+dm_bow (backup on write)
+========================
+
+dm_bow is a device mapper driver that uses the free space on a device to back up
+data that is overwritten. The changes can then be committed by a simple state
+change, or rolled back by removing the dm_bow device and running a command line
+utility over the underlying device.
+
+dm_bow has three states, set by writing ‘1’ or ‘2’ to /sys/block/dm-?/bow/state.
+It is only possible to go from state 0 (initial state) to state 1, and then from
+state 1 to state 2.
+
+State 0: dm_bow collects all trims to the device and assumes that these mark
+free space on the overlying file system that can be safely used. Typically the
+mount code would create the dm_bow device, mount the file system, call the
+FITRIM ioctl on the file system then switch to state 1. These trims are not
+propagated to the underlying device.
+
+State 1: All writes to the device cause the underlying data to be backed up to
+the free (trimmed) area as needed in such a way as they can be restored.
+However, the writes, with one exception, then happen exactly as they would
+without dm_bow, so the device is always in a good final state. The exception is
+that sector 0 is used to keep a log of the latest changes, both to indicate that
+we are in this state and to allow rollback. See below for all details. If there
+isn't enough free space, writes are failed with -ENOSPC.
+
+State 2: The transition to state 2 triggers replacing the special sector 0 with
+the normal sector 0, and the freeing of all state information. dm_bow then
+becomes a pass-through driver, allowing the device to continue to be used with
+minimal performance impact.
+
+Usage
+=====
+dm-bow takes one command line parameter, the name of the underlying device.
+
+dm-bow will typically be used in the following way. dm-bow will be loaded with a
+suitable underlying device and the resultant device will be mounted. A file
+system trim will be issued via the FITRIM ioctl, then the device will be
+switched to state 1. The file system will now be used as normal. At some point,
+the changes can either be committed by switching to state 2, or rolled back by
+unmounting the file system, removing the dm-bow device and running the command
+line utility. Note that rebooting the device will be equivalent to unmounting
+and removing, but the command line utility must still be run
+
+Details of operation in state 1
+===============================
+
+dm_bow maintains a type for all sectors. A sector can be any of:
+
+SECTOR0
+SECTOR0_CURRENT
+UNCHANGED
+FREE
+CHANGED
+BACKUP
+
+SECTOR0 is the first sector on the device, and is used to hold the log of
+changes. This is the one exception.
+
+SECTOR0_CURRENT is a sector picked from the FREE sectors, and is where reads and
+writes from the true sector zero are redirected to. Note that like any backup
+sector, if the sector is written to directly, it must be moved again.
+
+UNCHANGED means that the sector has not been changed since we entered state 1.
+Thus if it is written to or trimmed, the contents must first be backed up.
+
+FREE means that the sector was trimmed in state 0 and has not yet been written
+to or used for backup. On being written to, a FREE sector is changed to CHANGED.
+
+CHANGED means that the sector has been modified, and can be further modified
+without further backup.
+
+BACKUP means that this is a free sector being used as a backup. On being written
+to, the contents must first be backed up again.
+
+All backup operations are logged to the first sector. The log sector has the
+format:
+--------------------------------------------------------
+| Magic | Count | Sequence | Log entry | Log entry | …
+--------------------------------------------------------
+
+Magic is a magic number. Count is the number of log entries. Sequence is 0
+initially. A log entry is
+
+-----------------------------------
+| Source | Dest | Size | Checksum |
+-----------------------------------
+
+When SECTOR0 is full, the log sector is backed up and another empty log sector
+created with sequence number one higher. The first entry in any log entry with
+sequence > 0 therefore must be the log of the backing up of the previous log
+sector. Note that sequence is not strictly needed, but is a useful sanity check
+and potentially limits the time spent trying to restore a corrupted snapshot.
+
+On entering state 1, dm_bow has a list of free sectors. All other sectors are
+unchanged. Sector0_current is selected from the free sectors and the contents of
+sector 0 are copied there. The sector 0 is backed up, which triggers the first
+log entry to be written.
+
diff --git a/Documentation/device-mapper/dm-crypt.txt b/Documentation/device-mapper/dm-crypt.txt
index 692171f..ae9a8f7 100644
--- a/Documentation/device-mapper/dm-crypt.txt
+++ b/Documentation/device-mapper/dm-crypt.txt
@@ -76,6 +76,20 @@
thread because it benefits CFQ to have writes submitted using the
same context.
+sector_size:<bytes>
+ Use <bytes> as the encryption unit instead of 512 bytes sectors.
+ This option can be in range 512 - 4096 bytes and must be power of two.
+ Virtual device will announce this size as a minimal IO and logical sector.
+
+iv_large_sectors
+ IV generators will use sector number counted in <sector_size> units
+ instead of default 512 bytes sectors.
+
+ For example, if <sector_size> is 4096 bytes, plain64 IV for the second
+ sector will be 8 (without flag) and 1 if iv_large_sectors is present.
+ The <iv_offset> must be multiple of <sector_size> (in 512 bytes units)
+ if this flag is specified.
+
Example scripts
===============
LUKS (Linux Unified Key Setup) is now the preferred way to set up disk
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
index 89fd8f9..b3d2e4a 100644
--- a/Documentation/device-mapper/verity.txt
+++ b/Documentation/device-mapper/verity.txt
@@ -109,6 +109,17 @@
This is the offset, in <data_block_size> blocks, from the start of the
FEC device to the beginning of the encoding data.
+check_at_most_once
+ Verify data blocks only the first time they are read from the data device,
+ rather than every time. This reduces the overhead of dm-verity so that it
+ can be used on systems that are memory and/or CPU constrained. However, it
+ provides a reduced level of security because only offline tampering of the
+ data device's content will be detected, not online tampering.
+
+ Hash blocks are still verified each time they are read from the hash device,
+ since verification of hash blocks is less performance critical than data
+ blocks, and a hash block will not be verified any more after all the data
+ blocks it covers have been verified anyway.
Theory of operation
===================
diff --git a/Documentation/devicetree/bindings/arm/firmware/linaro,optee-tz.txt b/Documentation/devicetree/bindings/arm/firmware/linaro,optee-tz.txt
new file mode 100644
index 0000000..d38834c
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/firmware/linaro,optee-tz.txt
@@ -0,0 +1,31 @@
+OP-TEE Device Tree Bindings
+
+OP-TEE is a piece of software using hardware features to provide a Trusted
+Execution Environment. The security can be provided with ARM TrustZone, but
+also by virtualization or a separate chip.
+
+We're using "linaro" as the first part of the compatible property for
+the reference implementation maintained by Linaro.
+
+* OP-TEE based on ARM TrustZone required properties:
+
+- compatible : should contain "linaro,optee-tz"
+
+- method : The method of calling the OP-TEE Trusted OS. Permitted
+ values are:
+
+ "smc" : SMC #0, with the register assignments specified
+ in drivers/tee/optee/optee_smc.h
+
+ "hvc" : HVC #0, with the register assignments specified
+ in drivers/tee/optee/optee_smc.h
+
+
+
+Example:
+ firmware {
+ optee {
+ compatible = "linaro,optee-tz";
+ method = "smc";
+ };
+ };
diff --git a/Documentation/devicetree/bindings/misc/memory-state-time.txt b/Documentation/devicetree/bindings/misc/memory-state-time.txt
new file mode 100644
index 0000000..c99a506
--- /dev/null
+++ b/Documentation/devicetree/bindings/misc/memory-state-time.txt
@@ -0,0 +1,8 @@
+Memory bandwidth and frequency state tracking
+
+Required properties:
+- compatible : should be:
+ "memory-state-time"
+- freq-tbl: Should contain entries with each frequency in Hz.
+- bw-buckets: Should contain upper-bound limits for each bandwidth bucket in Mbps.
+ Must match the framework power_profile.xml for the device.
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index bceffff..d0526e0 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -156,6 +156,7 @@
lantiq Lantiq Semiconductor
lenovo Lenovo Group Ltd.
lg LG Corporation
+linaro Linaro Limited
linux Linux-specific binding
lltc Linear Technology Corporation
lsi LSI Corp. (LSI Logic)
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index 753dd4f..564ccc6 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -125,6 +125,9 @@
disable_ext_identify Disable the extension list configured by mkfs, so f2fs
does not aware of cold files such as media files.
inline_xattr Enable the inline xattrs feature.
+noinline_xattr Disable the inline xattrs feature.
+inline_xattr_size=%u Support configuring inline xattr size, it depends on
+ flexible inline xattr feature.
inline_data Enable the inline data feature: New created small(<~3.4k)
files can be written into inode block.
inline_dentry Enable the inline dir feature: data in new created
@@ -154,9 +157,68 @@
enabled by default.
data_flush Enable data flushing before checkpoint in order to
persist data of regular and symlink.
+fault_injection=%d Enable fault injection in all supported types with
+ specified injection rate.
+fault_type=%d Support configuring fault injection type, should be
+ enabled with fault_injection option, fault type value
+ is shown below, it supports single or combined type.
+ Type_Name Type_Value
+ FAULT_KMALLOC 0x000000001
+ FAULT_KVMALLOC 0x000000002
+ FAULT_PAGE_ALLOC 0x000000004
+ FAULT_PAGE_GET 0x000000008
+ FAULT_ALLOC_BIO 0x000000010
+ FAULT_ALLOC_NID 0x000000020
+ FAULT_ORPHAN 0x000000040
+ FAULT_BLOCK 0x000000080
+ FAULT_DIR_DEPTH 0x000000100
+ FAULT_EVICT_INODE 0x000000200
+ FAULT_TRUNCATE 0x000000400
+ FAULT_READ_IO 0x000000800
+ FAULT_CHECKPOINT 0x000001000
+ FAULT_DISCARD 0x000002000
+ FAULT_WRITE_IO 0x000004000
mode=%s Control block allocation mode which supports "adaptive"
and "lfs". In "lfs" mode, there should be no random
writes towards main area.
+io_bits=%u Set the bit size of write IO requests. It should be set
+ with "mode=lfs".
+usrquota Enable plain user disk quota accounting.
+grpquota Enable plain group disk quota accounting.
+prjquota Enable plain project quota accounting.
+usrjquota=<file> Appoint specified file and type during mount, so that quota
+grpjquota=<file> information can be properly updated during recovery flow,
+prjjquota=<file> <quota file>: must be in root directory;
+jqfmt=<quota type> <quota type>: [vfsold,vfsv0,vfsv1].
+offusrjquota Turn off user journelled quota.
+offgrpjquota Turn off group journelled quota.
+offprjjquota Turn off project journelled quota.
+quota Enable plain user disk quota accounting.
+noquota Disable all plain disk quota option.
+whint_mode=%s Control which write hints are passed down to block
+ layer. This supports "off", "user-based", and
+ "fs-based". In "off" mode (default), f2fs does not pass
+ down hints. In "user-based" mode, f2fs tries to pass
+ down hints given by users. And in "fs-based" mode, f2fs
+ passes down hints with its policy.
+alloc_mode=%s Adjust block allocation policy, which supports "reuse"
+ and "default".
+fsync_mode=%s Control the policy of fsync. Currently supports "posix",
+ "strict", and "nobarrier". In "posix" mode, which is
+ default, fsync will follow POSIX semantics and does a
+ light operation to improve the filesystem performance.
+ In "strict" mode, fsync will be heavy and behaves in line
+ with xfs, ext4 and btrfs, where xfstest generic/342 will
+ pass, but the performance will regress. "nobarrier" is
+ based on "posix", but doesn't issue flush command for
+ non-atomic files likewise "nobarrier" mount option.
+test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt
+ context. The fake fscrypt context is used by xfstests.
+checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable"
+ to reenable checkpointing. Is enabled by default. While
+ disabled, any unmounting or unexpected shutdowns will cause
+ the filesystem contents to appear as they did when the
+ filesystem was mounted with that option.
================================================================================
DEBUGFS ENTRIES
@@ -202,6 +264,15 @@
gc_idle = 1 will select the Cost Benefit approach
& setting gc_idle = 2 will select the greedy approach.
+ gc_urgent This parameter controls triggering background GCs
+ urgently or not. Setting gc_urgent = 0 [default]
+ makes back to default behavior, while if it is set
+ to 1, background thread starts to do GC by given
+ gc_urgent_sleep_time interval.
+
+ gc_urgent_sleep_time This parameter controls sleep time for gc_urgent.
+ 500 ms is set by default. See above gc_urgent.
+
reclaim_segments This parameter controls the number of prefree
segments to be reclaimed. If the number of prefree
segments is larger than the number of segments
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
new file mode 100644
index 0000000..3a7b605
--- /dev/null
+++ b/Documentation/filesystems/fscrypt.rst
@@ -0,0 +1,641 @@
+=====================================
+Filesystem-level encryption (fscrypt)
+=====================================
+
+Introduction
+============
+
+fscrypt is a library which filesystems can hook into to support
+transparent encryption of files and directories.
+
+Note: "fscrypt" in this document refers to the kernel-level portion,
+implemented in ``fs/crypto/``, as opposed to the userspace tool
+`fscrypt <https://github.com/google/fscrypt>`_. This document only
+covers the kernel-level portion. For command-line examples of how to
+use encryption, see the documentation for the userspace tool `fscrypt
+<https://github.com/google/fscrypt>`_. Also, it is recommended to use
+the fscrypt userspace tool, or other existing userspace tools such as
+`fscryptctl <https://github.com/google/fscryptctl>`_ or `Android's key
+management system
+<https://source.android.com/security/encryption/file-based>`_, over
+using the kernel's API directly. Using existing tools reduces the
+chance of introducing your own security bugs. (Nevertheless, for
+completeness this documentation covers the kernel's API anyway.)
+
+Unlike dm-crypt, fscrypt operates at the filesystem level rather than
+at the block device level. This allows it to encrypt different files
+with different keys and to have unencrypted files on the same
+filesystem. This is useful for multi-user systems where each user's
+data-at-rest needs to be cryptographically isolated from the others.
+However, except for filenames, fscrypt does not encrypt filesystem
+metadata.
+
+Unlike eCryptfs, which is a stacked filesystem, fscrypt is integrated
+directly into supported filesystems --- currently ext4, F2FS, and
+UBIFS. This allows encrypted files to be read and written without
+caching both the decrypted and encrypted pages in the pagecache,
+thereby nearly halving the memory used and bringing it in line with
+unencrypted files. Similarly, half as many dentries and inodes are
+needed. eCryptfs also limits encrypted filenames to 143 bytes,
+causing application compatibility issues; fscrypt allows the full 255
+bytes (NAME_MAX). Finally, unlike eCryptfs, the fscrypt API can be
+used by unprivileged users, with no need to mount anything.
+
+fscrypt does not support encrypting files in-place. Instead, it
+supports marking an empty directory as encrypted. Then, after
+userspace provides the key, all regular files, directories, and
+symbolic links created in that directory tree are transparently
+encrypted.
+
+Threat model
+============
+
+Offline attacks
+---------------
+
+Provided that userspace chooses a strong encryption key, fscrypt
+protects the confidentiality of file contents and filenames in the
+event of a single point-in-time permanent offline compromise of the
+block device content. fscrypt does not protect the confidentiality of
+non-filename metadata, e.g. file sizes, file permissions, file
+timestamps, and extended attributes. Also, the existence and location
+of holes (unallocated blocks which logically contain all zeroes) in
+files is not protected.
+
+fscrypt is not guaranteed to protect confidentiality or authenticity
+if an attacker is able to manipulate the filesystem offline prior to
+an authorized user later accessing the filesystem.
+
+Online attacks
+--------------
+
+fscrypt (and storage encryption in general) can only provide limited
+protection, if any at all, against online attacks. In detail:
+
+fscrypt is only resistant to side-channel attacks, such as timing or
+electromagnetic attacks, to the extent that the underlying Linux
+Cryptographic API algorithms are. If a vulnerable algorithm is used,
+such as a table-based implementation of AES, it may be possible for an
+attacker to mount a side channel attack against the online system.
+Side channel attacks may also be mounted against applications
+consuming decrypted data.
+
+After an encryption key has been provided, fscrypt is not designed to
+hide the plaintext file contents or filenames from other users on the
+same system, regardless of the visibility of the keyring key.
+Instead, existing access control mechanisms such as file mode bits,
+POSIX ACLs, LSMs, or mount namespaces should be used for this purpose.
+Also note that as long as the encryption keys are *anywhere* in
+memory, an online attacker can necessarily compromise them by mounting
+a physical attack or by exploiting any kernel security vulnerability
+which provides an arbitrary memory read primitive.
+
+While it is ostensibly possible to "evict" keys from the system,
+recently accessed encrypted files will remain accessible at least
+until the filesystem is unmounted or the VFS caches are dropped, e.g.
+using ``echo 2 > /proc/sys/vm/drop_caches``. Even after that, if the
+RAM is compromised before being powered off, it will likely still be
+possible to recover portions of the plaintext file contents, if not
+some of the encryption keys as well. (Since Linux v4.12, all
+in-kernel keys related to fscrypt are sanitized before being freed.
+However, userspace would need to do its part as well.)
+
+Currently, fscrypt does not prevent a user from maliciously providing
+an incorrect key for another user's existing encrypted files. A
+protection against this is planned.
+
+Key hierarchy
+=============
+
+Master Keys
+-----------
+
+Each encrypted directory tree is protected by a *master key*. Master
+keys can be up to 64 bytes long, and must be at least as long as the
+greater of the key length needed by the contents and filenames
+encryption modes being used. For example, if AES-256-XTS is used for
+contents encryption, the master key must be 64 bytes (512 bits). Note
+that the XTS mode is defined to require a key twice as long as that
+required by the underlying block cipher.
+
+To "unlock" an encrypted directory tree, userspace must provide the
+appropriate master key. There can be any number of master keys, each
+of which protects any number of directory trees on any number of
+filesystems.
+
+Userspace should generate master keys either using a cryptographically
+secure random number generator, or by using a KDF (Key Derivation
+Function). Note that whenever a KDF is used to "stretch" a
+lower-entropy secret such as a passphrase, it is critical that a KDF
+designed for this purpose be used, such as scrypt, PBKDF2, or Argon2.
+
+Per-file keys
+-------------
+
+Since each master key can protect many files, it is necessary to
+"tweak" the encryption of each file so that the same plaintext in two
+files doesn't map to the same ciphertext, or vice versa. In most
+cases, fscrypt does this by deriving per-file keys. When a new
+encrypted inode (regular file, directory, or symlink) is created,
+fscrypt randomly generates a 16-byte nonce and stores it in the
+inode's encryption xattr. Then, it uses a KDF (Key Derivation
+Function) to derive the file's key from the master key and nonce.
+
+The Adiantum encryption mode (see `Encryption modes and usage`_) is
+special, since it accepts longer IVs and is suitable for both contents
+and filenames encryption. For it, a "direct key" option is offered
+where the file's nonce is included in the IVs and the master key is
+used for encryption directly. This improves performance; however,
+users must not use the same master key for any other encryption mode.
+
+Below, the KDF and design considerations are described in more detail.
+
+The current KDF works by encrypting the master key with AES-128-ECB,
+using the file's nonce as the AES key. The output is used as the
+derived key. If the output is longer than needed, then it is
+truncated to the needed length.
+
+Note: this KDF meets the primary security requirement, which is to
+produce unique derived keys that preserve the entropy of the master
+key, assuming that the master key is already a good pseudorandom key.
+However, it is nonstandard and has some problems such as being
+reversible, so it is generally considered to be a mistake! It may be
+replaced with HKDF or another more standard KDF in the future.
+
+Key derivation was chosen over key wrapping because wrapped keys would
+require larger xattrs which would be less likely to fit in-line in the
+filesystem's inode table, and there didn't appear to be any
+significant advantages to key wrapping. In particular, currently
+there is no requirement to support unlocking a file with multiple
+alternative master keys or to support rotating master keys. Instead,
+the master keys may be wrapped in userspace, e.g. as is done by the
+`fscrypt <https://github.com/google/fscrypt>`_ tool.
+
+Including the inode number in the IVs was considered. However, it was
+rejected as it would have prevented ext4 filesystems from being
+resized, and by itself still wouldn't have been sufficient to prevent
+the same key from being directly reused for both XTS and CTS-CBC.
+
+Encryption modes and usage
+==========================
+
+fscrypt allows one encryption mode to be specified for file contents
+and one encryption mode to be specified for filenames. Different
+directory trees are permitted to use different encryption modes.
+Currently, the following pairs of encryption modes are supported:
+
+- AES-256-XTS for contents and AES-256-CTS-CBC for filenames
+- AES-128-CBC for contents and AES-128-CTS-CBC for filenames
+- Adiantum for both contents and filenames
+
+If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair.
+
+AES-128-CBC was added only for low-powered embedded devices with
+crypto accelerators such as CAAM or CESA that do not support XTS.
+
+Adiantum is a (primarily) stream cipher-based mode that is fast even
+on CPUs without dedicated crypto instructions. It's also a true
+wide-block mode, unlike XTS. It can also eliminate the need to derive
+per-file keys. However, it depends on the security of two primitives,
+XChaCha12 and AES-256, rather than just one. See the paper
+"Adiantum: length-preserving encryption for entry-level processors"
+(https://eprint.iacr.org/2018/720.pdf) for more details. To use
+Adiantum, CONFIG_CRYPTO_ADIANTUM must be enabled. Also, fast
+implementations of ChaCha and NHPoly1305 should be enabled, e.g.
+CONFIG_CRYPTO_CHACHA20_NEON and CONFIG_CRYPTO_NHPOLY1305_NEON for ARM.
+
+New encryption modes can be added relatively easily, without changes
+to individual filesystems. However, authenticated encryption (AE)
+modes are not currently supported because of the difficulty of dealing
+with ciphertext expansion.
+
+Contents encryption
+-------------------
+
+For file contents, each filesystem block is encrypted independently.
+Currently, only the case where the filesystem block size is equal to
+the system's page size (usually 4096 bytes) is supported.
+
+Each block's IV is set to the logical block number within the file as
+a little endian number, except that:
+
+- With CBC mode encryption, ESSIV is also used. Specifically, each IV
+ is encrypted with AES-256 where the AES-256 key is the SHA-256 hash
+ of the file's data encryption key.
+
+- In the "direct key" configuration (FS_POLICY_FLAG_DIRECT_KEY set in
+ the fscrypt_policy), the file's nonce is also appended to the IV.
+ Currently this is only allowed with the Adiantum encryption mode.
+
+Filenames encryption
+--------------------
+
+For filenames, each full filename is encrypted at once. Because of
+the requirements to retain support for efficient directory lookups and
+filenames of up to 255 bytes, the same IV is used for every filename
+in a directory.
+
+However, each encrypted directory still uses a unique key; or
+alternatively (for the "direct key" configuration) has the file's
+nonce included in the IVs. Thus, IV reuse is limited to within a
+single directory.
+
+With CTS-CBC, the IV reuse means that when the plaintext filenames
+share a common prefix at least as long as the cipher block size (16
+bytes for AES), the corresponding encrypted filenames will also share
+a common prefix. This is undesirable. Adiantum does not have this
+weakness, as it is a wide-block encryption mode.
+
+All supported filenames encryption modes accept any plaintext length
+>= 16 bytes; cipher block alignment is not required. However,
+filenames shorter than 16 bytes are NUL-padded to 16 bytes before
+being encrypted. In addition, to reduce leakage of filename lengths
+via their ciphertexts, all filenames are NUL-padded to the next 4, 8,
+16, or 32-byte boundary (configurable). 32 is recommended since this
+provides the best confidentiality, at the cost of making directory
+entries consume slightly more space. Note that since NUL (``\0``) is
+not otherwise a valid character in filenames, the padding will never
+produce duplicate plaintexts.
+
+Symbolic link targets are considered a type of filename and are
+encrypted in the same way as filenames in directory entries, except
+that IV reuse is not a problem as each symlink has its own inode.
+
+User API
+========
+
+Setting an encryption policy
+----------------------------
+
+The FS_IOC_SET_ENCRYPTION_POLICY ioctl sets an encryption policy on an
+empty directory or verifies that a directory or regular file already
+has the specified encryption policy. It takes in a pointer to a
+:c:type:`struct fscrypt_policy`, defined as follows::
+
+ #define FS_KEY_DESCRIPTOR_SIZE 8
+
+ struct fscrypt_policy {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ };
+
+This structure must be initialized as follows:
+
+- ``version`` must be 0.
+
+- ``contents_encryption_mode`` and ``filenames_encryption_mode`` must
+ be set to constants from ``<linux/fs.h>`` which identify the
+ encryption modes to use. If unsure, use
+ FS_ENCRYPTION_MODE_AES_256_XTS (1) for ``contents_encryption_mode``
+ and FS_ENCRYPTION_MODE_AES_256_CTS (4) for
+ ``filenames_encryption_mode``.
+
+- ``flags`` must contain a value from ``<linux/fs.h>`` which
+ identifies the amount of NUL-padding to use when encrypting
+ filenames. If unsure, use FS_POLICY_FLAGS_PAD_32 (0x3).
+ In addition, if the chosen encryption modes are both
+ FS_ENCRYPTION_MODE_ADIANTUM, this can contain
+ FS_POLICY_FLAG_DIRECT_KEY to specify that the master key should be
+ used directly, without key derivation.
+
+- ``master_key_descriptor`` specifies how to find the master key in
+ the keyring; see `Adding keys`_. It is up to userspace to choose a
+ unique ``master_key_descriptor`` for each master key. The e4crypt
+ and fscrypt tools use the first 8 bytes of
+ ``SHA-512(SHA-512(master_key))``, but this particular scheme is not
+ required. Also, the master key need not be in the keyring yet when
+ FS_IOC_SET_ENCRYPTION_POLICY is executed. However, it must be added
+ before any files can be created in the encrypted directory.
+
+If the file is not yet encrypted, then FS_IOC_SET_ENCRYPTION_POLICY
+verifies that the file is an empty directory. If so, the specified
+encryption policy is assigned to the directory, turning it into an
+encrypted directory. After that, and after providing the
+corresponding master key as described in `Adding keys`_, all regular
+files, directories (recursively), and symlinks created in the
+directory will be encrypted, inheriting the same encryption policy.
+The filenames in the directory's entries will be encrypted as well.
+
+Alternatively, if the file is already encrypted, then
+FS_IOC_SET_ENCRYPTION_POLICY validates that the specified encryption
+policy exactly matches the actual one. If they match, then the ioctl
+returns 0. Otherwise, it fails with EEXIST. This works on both
+regular files and directories, including nonempty directories.
+
+Note that the ext4 filesystem does not allow the root directory to be
+encrypted, even if it is empty. Users who want to encrypt an entire
+filesystem with one key should consider using dm-crypt instead.
+
+FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
+
+- ``EACCES``: the file is not owned by the process's uid, nor does the
+ process have the CAP_FOWNER capability in a namespace with the file
+ owner's uid mapped
+- ``EEXIST``: the file is already encrypted with an encryption policy
+ different from the one specified
+- ``EINVAL``: an invalid encryption policy was specified (invalid
+ version, mode(s), or flags)
+- ``ENOTDIR``: the file is unencrypted and is a regular file, not a
+ directory
+- ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory
+- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``EOPNOTSUPP``: the kernel was not configured with encryption
+ support for this filesystem, or the filesystem superblock has not
+ had encryption enabled on it. (For example, to use encryption on an
+ ext4 filesystem, CONFIG_EXT4_ENCRYPTION must be enabled in the
+ kernel config, and the superblock must have had the "encrypt"
+ feature flag enabled using ``tune2fs -O encrypt`` or ``mkfs.ext4 -O
+ encrypt``.)
+- ``EPERM``: this directory may not be encrypted, e.g. because it is
+ the root directory of an ext4 filesystem
+- ``EROFS``: the filesystem is readonly
+
+Getting an encryption policy
+----------------------------
+
+The FS_IOC_GET_ENCRYPTION_POLICY ioctl retrieves the :c:type:`struct
+fscrypt_policy`, if any, for a directory or regular file. See above
+for the struct definition. No additional permissions are required
+beyond the ability to open the file.
+
+FS_IOC_GET_ENCRYPTION_POLICY can fail with the following errors:
+
+- ``EINVAL``: the file is encrypted, but it uses an unrecognized
+ encryption context format
+- ``ENODATA``: the file is not encrypted
+- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``EOPNOTSUPP``: the kernel was not configured with encryption
+ support for this filesystem
+
+Note: if you only need to know whether a file is encrypted or not, on
+most filesystems it is also possible to use the FS_IOC_GETFLAGS ioctl
+and check for FS_ENCRYPT_FL, or to use the statx() system call and
+check for STATX_ATTR_ENCRYPTED in stx_attributes.
+
+Getting the per-filesystem salt
+-------------------------------
+
+Some filesystems, such as ext4 and F2FS, also support the deprecated
+ioctl FS_IOC_GET_ENCRYPTION_PWSALT. This ioctl retrieves a randomly
+generated 16-byte value stored in the filesystem superblock. This
+value is intended to used as a salt when deriving an encryption key
+from a passphrase or other low-entropy user credential.
+
+FS_IOC_GET_ENCRYPTION_PWSALT is deprecated. Instead, prefer to
+generate and manage any needed salt(s) in userspace.
+
+Adding keys
+-----------
+
+To provide a master key, userspace must add it to an appropriate
+keyring using the add_key() system call (see:
+``Documentation/security/keys/core.rst``). The key type must be
+"logon"; keys of this type are kept in kernel memory and cannot be
+read back by userspace. The key description must be "fscrypt:"
+followed by the 16-character lower case hex representation of the
+``master_key_descriptor`` that was set in the encryption policy. The
+key payload must conform to the following structure::
+
+ #define FS_MAX_KEY_SIZE 64
+
+ struct fscrypt_key {
+ u32 mode;
+ u8 raw[FS_MAX_KEY_SIZE];
+ u32 size;
+ };
+
+``mode`` is ignored; just set it to 0. The actual key is provided in
+``raw`` with ``size`` indicating its size in bytes. That is, the
+bytes ``raw[0..size-1]`` (inclusive) are the actual key.
+
+The key description prefix "fscrypt:" may alternatively be replaced
+with a filesystem-specific prefix such as "ext4:". However, the
+filesystem-specific prefixes are deprecated and should not be used in
+new programs.
+
+There are several different types of keyrings in which encryption keys
+may be placed, such as a session keyring, a user session keyring, or a
+user keyring. Each key must be placed in a keyring that is "attached"
+to all processes that might need to access files encrypted with it, in
+the sense that request_key() will find the key. Generally, if only
+processes belonging to a specific user need to access a given
+encrypted directory and no session keyring has been installed, then
+that directory's key should be placed in that user's user session
+keyring or user keyring. Otherwise, a session keyring should be
+installed if needed, and the key should be linked into that session
+keyring, or in a keyring linked into that session keyring.
+
+Note: introducing the complex visibility semantics of keyrings here
+was arguably a mistake --- especially given that by design, after any
+process successfully opens an encrypted file (thereby setting up the
+per-file key), possessing the keyring key is not actually required for
+any process to read/write the file until its in-memory inode is
+evicted. In the future there probably should be a way to provide keys
+directly to the filesystem instead, which would make the intended
+semantics clearer.
+
+Access semantics
+================
+
+With the key
+------------
+
+With the encryption key, encrypted regular files, directories, and
+symlinks behave very similarly to their unencrypted counterparts ---
+after all, the encryption is intended to be transparent. However,
+astute users may notice some differences in behavior:
+
+- Unencrypted files, or files encrypted with a different encryption
+ policy (i.e. different key, modes, or flags), cannot be renamed or
+ linked into an encrypted directory; see `Encryption policy
+ enforcement`_. Attempts to do so will fail with EPERM. However,
+ encrypted files can be renamed within an encrypted directory, or
+ into an unencrypted directory.
+
+- Direct I/O is not supported on encrypted files. Attempts to use
+ direct I/O on such files will fall back to buffered I/O.
+
+- The fallocate operations FALLOC_FL_COLLAPSE_RANGE,
+ FALLOC_FL_INSERT_RANGE, and FALLOC_FL_ZERO_RANGE are not supported
+ on encrypted files and will fail with EOPNOTSUPP.
+
+- Online defragmentation of encrypted files is not supported. The
+ EXT4_IOC_MOVE_EXT and F2FS_IOC_MOVE_RANGE ioctls will fail with
+ EOPNOTSUPP.
+
+- The ext4 filesystem does not support data journaling with encrypted
+ regular files. It will fall back to ordered data mode instead.
+
+- DAX (Direct Access) is not supported on encrypted files.
+
+- The st_size of an encrypted symlink will not necessarily give the
+ length of the symlink target as required by POSIX. It will actually
+ give the length of the ciphertext, which will be slightly longer
+ than the plaintext due to NUL-padding and an extra 2-byte overhead.
+
+- The maximum length of an encrypted symlink is 2 bytes shorter than
+ the maximum length of an unencrypted symlink. For example, on an
+ EXT4 filesystem with a 4K block size, unencrypted symlinks can be up
+ to 4095 bytes long, while encrypted symlinks can only be up to 4093
+ bytes long (both lengths excluding the terminating null).
+
+Note that mmap *is* supported. This is possible because the pagecache
+for an encrypted file contains the plaintext, not the ciphertext.
+
+Without the key
+---------------
+
+Some filesystem operations may be performed on encrypted regular
+files, directories, and symlinks even before their encryption key has
+been provided:
+
+- File metadata may be read, e.g. using stat().
+
+- Directories may be listed, in which case the filenames will be
+ listed in an encoded form derived from their ciphertext. The
+ current encoding algorithm is described in `Filename hashing and
+ encoding`_. The algorithm is subject to change, but it is
+ guaranteed that the presented filenames will be no longer than
+ NAME_MAX bytes, will not contain the ``/`` or ``\0`` characters, and
+ will uniquely identify directory entries.
+
+ The ``.`` and ``..`` directory entries are special. They are always
+ present and are not encrypted or encoded.
+
+- Files may be deleted. That is, nondirectory files may be deleted
+ with unlink() as usual, and empty directories may be deleted with
+ rmdir() as usual. Therefore, ``rm`` and ``rm -r`` will work as
+ expected.
+
+- Symlink targets may be read and followed, but they will be presented
+ in encrypted form, similar to filenames in directories. Hence, they
+ are unlikely to point to anywhere useful.
+
+Without the key, regular files cannot be opened or truncated.
+Attempts to do so will fail with ENOKEY. This implies that any
+regular file operations that require a file descriptor, such as
+read(), write(), mmap(), fallocate(), and ioctl(), are also forbidden.
+
+Also without the key, files of any type (including directories) cannot
+be created or linked into an encrypted directory, nor can a name in an
+encrypted directory be the source or target of a rename, nor can an
+O_TMPFILE temporary file be created in an encrypted directory. All
+such operations will fail with ENOKEY.
+
+It is not currently possible to backup and restore encrypted files
+without the encryption key. This would require special APIs which
+have not yet been implemented.
+
+Encryption policy enforcement
+=============================
+
+After an encryption policy has been set on a directory, all regular
+files, directories, and symbolic links created in that directory
+(recursively) will inherit that encryption policy. Special files ---
+that is, named pipes, device nodes, and UNIX domain sockets --- will
+not be encrypted.
+
+Except for those special files, it is forbidden to have unencrypted
+files, or files encrypted with a different encryption policy, in an
+encrypted directory tree. Attempts to link or rename such a file into
+an encrypted directory will fail with EPERM. This is also enforced
+during ->lookup() to provide limited protection against offline
+attacks that try to disable or downgrade encryption in known locations
+where applications may later write sensitive data. It is recommended
+that systems implementing a form of "verified boot" take advantage of
+this by validating all top-level encryption policies prior to access.
+
+Implementation details
+======================
+
+Encryption context
+------------------
+
+An encryption policy is represented on-disk by a :c:type:`struct
+fscrypt_context`. It is up to individual filesystems to decide where
+to store it, but normally it would be stored in a hidden extended
+attribute. It should *not* be exposed by the xattr-related system
+calls such as getxattr() and setxattr() because of the special
+semantics of the encryption xattr. (In particular, there would be
+much confusion if an encryption policy were to be added to or removed
+from anything other than an empty directory.) The struct is defined
+as follows::
+
+ #define FS_KEY_DESCRIPTOR_SIZE 8
+ #define FS_KEY_DERIVATION_NONCE_SIZE 16
+
+ struct fscrypt_context {
+ u8 format;
+ u8 contents_encryption_mode;
+ u8 filenames_encryption_mode;
+ u8 flags;
+ u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+ };
+
+Note that :c:type:`struct fscrypt_context` contains the same
+information as :c:type:`struct fscrypt_policy` (see `Setting an
+encryption policy`_), except that :c:type:`struct fscrypt_context`
+also contains a nonce. The nonce is randomly generated by the kernel
+and is used to derive the inode's encryption key as described in
+`Per-file keys`_.
+
+Data path changes
+-----------------
+
+For the read path (->readpage()) of regular files, filesystems can
+read the ciphertext into the page cache and decrypt it in-place. The
+page lock must be held until decryption has finished, to prevent the
+page from becoming visible to userspace prematurely.
+
+For the write path (->writepage()) of regular files, filesystems
+cannot encrypt data in-place in the page cache, since the cached
+plaintext must be preserved. Instead, filesystems must encrypt into a
+temporary buffer or "bounce page", then write out the temporary
+buffer. Some filesystems, such as UBIFS, already use temporary
+buffers regardless of encryption. Other filesystems, such as ext4 and
+F2FS, have to allocate bounce pages specially for encryption.
+
+Filename hashing and encoding
+-----------------------------
+
+Modern filesystems accelerate directory lookups by using indexed
+directories. An indexed directory is organized as a tree keyed by
+filename hashes. When a ->lookup() is requested, the filesystem
+normally hashes the filename being looked up so that it can quickly
+find the corresponding directory entry, if any.
+
+With encryption, lookups must be supported and efficient both with and
+without the encryption key. Clearly, it would not work to hash the
+plaintext filenames, since the plaintext filenames are unavailable
+without the key. (Hashing the plaintext filenames would also make it
+impossible for the filesystem's fsck tool to optimize encrypted
+directories.) Instead, filesystems hash the ciphertext filenames,
+i.e. the bytes actually stored on-disk in the directory entries. When
+asked to do a ->lookup() with the key, the filesystem just encrypts
+the user-supplied name to get the ciphertext.
+
+Lookups without the key are more complicated. The raw ciphertext may
+contain the ``\0`` and ``/`` characters, which are illegal in
+filenames. Therefore, readdir() must base64-encode the ciphertext for
+presentation. For most filenames, this works fine; on ->lookup(), the
+filesystem just base64-decodes the user-supplied name to get back to
+the raw ciphertext.
+
+However, for very long filenames, base64 encoding would cause the
+filename length to exceed NAME_MAX. To prevent this, readdir()
+actually presents long filenames in an abbreviated form which encodes
+a strong "hash" of the ciphertext filename, along with the optional
+filesystem-specific hash(es) needed for directory lookups. This
+allows the filesystem to still, with a high degree of confidence, map
+the filename given in ->lookup() back to a particular directory entry
+that was previously listed by readdir(). See :c:type:`struct
+fscrypt_digested_name` in the source for more details.
+
+Note that the precise way that filenames are presented to userspace
+without the key is subject to change in the future. It is only meant
+as a way to temporarily present valid filenames so that commands like
+``rm -r`` work as expected on encrypted directories.
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index bcbf971..3ef8522 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -82,6 +82,29 @@
such as metadata and extended attributes are reported for the upper
directory only. These attributes of the lower directory are hidden.
+credentials
+-----------
+
+By default, all access to the upper, lower and work directories is the
+recorded mounter's MAC and DAC credentials. The incoming accesses are
+checked against the caller's credentials.
+
+In the case where caller MAC or DAC credentials do not overlap, a
+use case available in older versions of the driver, the
+override_creds mount flag can be turned off and help when the use
+pattern has caller with legitimate credentials where the mounter
+does not. Several unintended side effects will occur though. The
+caller without certain key capabilities or lower privilege will not
+always be able to delete files or directories, create nodes, or
+search some restricted directories. The ability to search and read
+a directory entry is spotty as a result of the cache mechanism not
+retesting the credentials because of the assumption, a privileged
+caller can fill cache, then a lower privilege can read the directory
+cache. The uneven security model where cache, upperdir and workdir
+are opened at privilege, but accessed without creating a form of
+privilege escalation, should only be used with strict understanding
+of the side effects and of the security policies.
+
whiteouts and opaque directories
--------------------------------
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 077c37e..843a4c8 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -392,6 +392,8 @@
[stack] = the stack of the main process
[vdso] = the "virtual dynamic shared object",
the kernel system call handler
+ [anon:<name>] = an anonymous mapping that has been
+ named by userspace
or if empty, the mapping is anonymous.
@@ -419,6 +421,7 @@
MMUPageSize: 4 kB
Locked: 0 kB
VmFlags: rd ex mr mw me dw
+Name: name from userspace
the first of these lines shows the same information as is displayed for the
mapping in /proc/PID/maps. The remaining lines show the size of the mapping
@@ -488,6 +491,9 @@
might change in future as well. So each consumer of these flags has to
follow each specific kernel version for the exact semantic.
+The "Name" field will only be present on a mapping that has been named by
+userspace, and will show the name passed in by userspace.
+
This file is only present if the CONFIG_MMU kernel configuration option is
enabled.
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 53b872c..db86cda 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -308,6 +308,12 @@
.. kernel-doc:: drivers/gpu/drm/drm_color_mgmt.c
:export:
+Explicit Fencing Properties
+---------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
+ :doc: explicit fencing properties
+
Existing KMS Properties
-----------------------
diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt
index 36ea940..575415f 100644
--- a/Documentation/input/event-codes.txt
+++ b/Documentation/input/event-codes.txt
@@ -301,7 +301,10 @@
INPUT_PROP_ACCELEROMETER
-------------------------
Directional axes on this device (absolute and/or relative x, y, z) represent
-accelerometer data. All other axes retain their meaning. A device must not mix
+accelerometer data. Some devices also report gyroscope data, which devices
+can report through the rotational axes (absolute and/or relative rx, ry, rz).
+
+All other axes retain their meaning. A device must not mix
regular directional axes and accelerometer axes on the same event node.
Guidelines:
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 81c7f2b..efb38da 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -308,6 +308,7 @@
0xA3 80-8F Port ACL in development:
<mailto:tlewis@mindspring.com>
0xA3 90-9F linux/dtlk.h
+0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem
0xAA 00-3F linux/uapi/linux/userfaultfd.h
0xAB 00-1F linux/nbd.h
0xAC 00-1F linux/raw.h
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7137655..0c59880 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -87,6 +87,7 @@
BLACKFIN Blackfin architecture is enabled.
CLK Common clock infrastructure is enabled.
CMA Contiguous Memory Area support is enabled.
+ DM Device mapper support is enabled.
DRM Direct Rendering Management support is enabled.
DYNAMIC_DEBUG Build in debug messages and enable them at runtime
EDD BIOS Enhanced Disk Drive Services (EDD) is enabled
@@ -1038,6 +1039,11 @@
dis_ucode_ldr [X86] Disable the microcode loader.
+ dm= [DM] Allows early creation of a device-mapper device.
+ See Documentation/device-mapper/boot.txt.
+
+ dmasound= [HW,OSS] Sound subsystem buff
+
dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
this option disables the debugging code at boot.
@@ -1900,6 +1906,12 @@
kernel and module base offset ASLR (Address Space
Layout Randomization).
+ kasan_multi_shot
+ [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
+ report on every invalid memory access. Without this
+ parameter KASAN will print report only for the first
+ invalid access.
+
keepinitrd [HW,ARM]
kernelcore= [KNL,X86,IA-64,PPC]
@@ -3503,6 +3515,10 @@
before loading.
See Documentation/blockdev/ramdisk.txt.
+ psi= [KNL] Enable or disable pressure stall information
+ tracking.
+ Format: <bool>
+
psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
probe for; one of (bare|imps|exps|lifebook|any).
psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
@@ -4090,6 +4106,14 @@
last alloc / free. For more information see
Documentation/vm/slub.txt.
+ slub_memcg_sysfs= [MM, SLUB]
+ Determines whether to enable sysfs directories for
+ memory cgroup sub-caches. 1 to enable, 0 to disable.
+ The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON.
+ Enabling this can lead to a very high number of debug
+ directories and files being created under
+ /sys/kernel/slub.
+
slub_max_order= [MM, SLUB]
Determines the maximum allowed order for slabs.
A high setting may cause OOMs due to memory
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a374412..95c7ac2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -609,6 +609,16 @@
Note that that additional client or server features are only
effective if the basic support (0x1 and 0x2) are enabled respectively.
+tcp_fwmark_accept - BOOLEAN
+ If set, incoming connections to listening sockets that do not have a
+ socket mark will set the mark of the accepting socket to the fwmark of
+ the incoming SYN packet. This will cause all packets on that connection
+ (starting from the first SYNACK) to be sent with that fwmark. The
+ listening socket's mark is unchanged. Listening sockets that already
+ have a fwmark set via setsockopt(SOL_SOCKET, SO_MARK, ...) are
+ unaffected.
+ Default: 0
+
tcp_syn_retries - INTEGER
Number of times initial SYNs for an active TCP connection attempt
will be retransmitted. Should not be higher than 127. Default value
@@ -1450,11 +1460,20 @@
Functional default: enabled if accept_ra is enabled.
disabled if accept_ra is disabled.
+accept_ra_rt_info_min_plen - INTEGER
+ Minimum prefix length of Route Information in RA.
+
+ Route Information w/ prefix smaller than this variable shall
+ be ignored.
+
+ Functional default: 0 if accept_ra_rtr_pref is enabled.
+ -1 if accept_ra_rtr_pref is disabled.
+
accept_ra_rt_info_max_plen - INTEGER
Maximum prefix length of Route Information in RA.
- Route Information w/ prefix larger than or equal to this
- variable shall be ignored.
+ Route Information w/ prefix larger than this variable shall
+ be ignored.
Functional default: 0 if accept_ra_rtr_pref is enabled.
-1 if accept_ra_rtr_pref is disabled.
@@ -1709,6 +1728,16 @@
By default the stable secret is unset.
+addr_gen_mode - INTEGER
+ Defines how link-local and autoconf addresses are generated.
+
+ 0: generate address based on EUI64 (default)
+ 1: do no generate a link-local address, use EUI64 for addresses generated
+ from autoconf
+ 2: generate stable privacy addresses, using the secret from
+ stable_secret (RFC7217)
+ 3: generate stable privacy addresses, using a random secret if unset
+
drop_unicast_in_l2_multicast - BOOLEAN
Drop any unicast IPv6 packets that are received in link-layer
multicast (or broadcast) frames.
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index d2fbeeb..54504c5 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -31,6 +31,15 @@
Raw pointer value SHOULD be printed with %p. The kernel supports
the following extended format specifiers for pointer types:
+Pointer Types:
+
+Pointers printed without a specifier extension (i.e unadorned %p) are
+hashed to give a unique identifier without leaking kernel addresses to user
+space. On 64 bit machines the first 32 bits are zeroed. If you _really_
+want the address see %px below.
+
+ %p abcdef12 or 00000000abcdef12
+
Symbols/Function Pointers:
%pF versatile_init+0x0/0x110
@@ -58,12 +67,24 @@
Kernel Pointers:
- %pK 0x01234567 or 0x0123456789abcdef
+ %pK 01234567 or 0123456789abcdef
For printing kernel pointers which should be hidden from unprivileged
users. The behaviour of %pK depends on the kptr_restrict sysctl - see
Documentation/sysctl/kernel.txt for more details.
+Unmodified Addresses:
+
+ %px 01234567 or 0123456789abcdef
+
+ For printing pointers when you _really_ want to print the address. Please
+ consider whether or not you are leaking sensitive information about the
+ Kernel layout in memory before printing pointers with %px. %px is
+ functionally equivalent to %lx. %px is preferred to %lx because it is more
+ uniquely grep'able. If, in the future, we need to modify the way the Kernel
+ handles printing pointers it will be nice to be able to find the call
+ sites.
+
Struct Resources:
%pr [mem 0x60000000-0x6fffffff flags 0x2200] or
diff --git a/Documentation/scheduler/sched-energy.txt b/Documentation/scheduler/sched-energy.txt
new file mode 100644
index 0000000..dab2f90
--- /dev/null
+++ b/Documentation/scheduler/sched-energy.txt
@@ -0,0 +1,362 @@
+Energy cost model for energy-aware scheduling (EXPERIMENTAL)
+
+Introduction
+=============
+
+The basic energy model uses platform energy data stored in sched_group_energy
+data structures attached to the sched_groups in the sched_domain hierarchy. The
+energy cost model offers two functions that can be used to guide scheduling
+decisions:
+
+1. static unsigned int sched_group_energy(struct energy_env *eenv)
+2. static int energy_diff(struct energy_env *eenv)
+
+sched_group_energy() estimates the energy consumed by all cpus in a specific
+sched_group including any shared resources owned exclusively by this group of
+cpus. Resources shared with other cpus are excluded (e.g. later level caches).
+
+energy_diff() estimates the total energy impact of a utilization change. That
+is, adding, removing, or migrating utilization (tasks).
+
+Both functions use a struct energy_env to specify the scenario to be evaluated:
+
+ struct energy_env {
+ struct sched_group *sg_top;
+ struct sched_group *sg_cap;
+ int cap_idx;
+ int util_delta;
+ int src_cpu;
+ int dst_cpu;
+ int energy;
+ };
+
+sg_top: sched_group to be evaluated. Not used by energy_diff().
+
+sg_cap: sched_group covering the cpus in the same frequency domain. Set by
+sched_group_energy().
+
+cap_idx: Capacity state to be used for energy calculations. Set by
+find_new_capacity().
+
+util_delta: Amount of utilization to be added, removed, or migrated.
+
+src_cpu: Source cpu from where 'util_delta' utilization is removed. Should be
+-1 if no source (e.g. task wake-up).
+
+dst_cpu: Destination cpu where 'util_delta' utilization is added. Should be -1
+if utilization is removed (e.g. terminating tasks).
+
+energy: Result of sched_group_energy().
+
+The metric used to represent utilization is the actual per-entity running time
+averaged over time using a geometric series. Very similar to the existing
+per-entity load-tracking, but _not_ scaled by task priority and capped by the
+capacity of the cpu. The latter property does mean that utilization may
+underestimate the compute requirements for task on fully/over utilized cpus.
+The greatest potential for energy savings without affecting performance too much
+is scenarios where the system isn't fully utilized. If the system is deemed
+fully utilized load-balancing should be done with task load (includes task
+priority) instead in the interest of fairness and performance.
+
+
+Background and Terminology
+===========================
+
+To make it clear from the start:
+
+energy = [joule] (resource like a battery on powered devices)
+power = energy/time = [joule/second] = [watt]
+
+The goal of energy-aware scheduling is to minimize energy, while still getting
+the job done. That is, we want to maximize:
+
+ performance [inst/s]
+ --------------------
+ power [W]
+
+which is equivalent to minimizing:
+
+ energy [J]
+ -----------
+ instruction
+
+while still getting 'good' performance. It is essentially an alternative
+optimization objective to the current performance-only objective for the
+scheduler. This alternative considers two objectives: energy-efficiency and
+performance. Hence, there needs to be a user controllable knob to switch the
+objective. Since it is early days, this is currently a sched_feature
+(ENERGY_AWARE).
+
+The idea behind introducing an energy cost model is to allow the scheduler to
+evaluate the implications of its decisions rather than applying energy-saving
+techniques blindly that may only have positive effects on some platforms. At
+the same time, the energy cost model must be as simple as possible to minimize
+the scheduler latency impact.
+
+Platform topology
+------------------
+
+The system topology (cpus, caches, and NUMA information, not peripherals) is
+represented in the scheduler by the sched_domain hierarchy which has
+sched_groups attached at each level that covers one or more cpus (see
+sched-domains.txt for more details). To add energy awareness to the scheduler
+we need to consider power and frequency domains.
+
+Power domain:
+
+A power domain is a part of the system that can be powered on/off
+independently. Power domains are typically organized in a hierarchy where you
+may be able to power down just a cpu or a group of cpus along with any
+associated resources (e.g. shared caches). Powering up a cpu means that all
+power domains it is a part of in the hierarchy must be powered up. Hence, it is
+more expensive to power up the first cpu that belongs to a higher level power
+domain than powering up additional cpus in the same high level domain. Two
+level power domain hierarchy example:
+
+ Power source
+ +-------------------------------+----...
+per group PD G G
+ | +----------+ |
+ +--------+-------| Shared | (other groups)
+per-cpu PD G G | resource |
+ | | +----------+
+ +-------+ +-------+
+ | CPU 0 | | CPU 1 |
+ +-------+ +-------+
+
+Frequency domain:
+
+Frequency domains (P-states) typically cover the same group of cpus as one of
+the power domain levels. That is, there might be several smaller power domains
+sharing the same frequency (P-state) or there might be a power domain spanning
+multiple frequency domains.
+
+From a scheduling point of view there is no need to know the actual frequencies
+[Hz]. All the scheduler cares about is the compute capacity available at the
+current state (P-state) the cpu is in and any other available states. For that
+reason, and to also factor in any cpu micro-architecture differences, compute
+capacity scaling states are called 'capacity states' in this document. For SMP
+systems this is equivalent to P-states. For mixed micro-architecture systems
+(like ARM big.LITTLE) it is P-states scaled according to the micro-architecture
+performance relative to the other cpus in the system.
+
+Energy modelling:
+------------------
+
+Due to the hierarchical nature of the power domains, the most obvious way to
+model energy costs is therefore to associate power and energy costs with
+domains (groups of cpus). Energy costs of shared resources are associated with
+the group of cpus that share the resources, only the cost of powering the
+cpu itself and any private resources (e.g. private L1 caches) is associated
+with the per-cpu groups (lowest level).
+
+For example, for an SMP system with per-cpu power domains and a cluster level
+(group of cpus) power domain we get the overall energy costs to be:
+
+ energy = energy_cluster + n * energy_cpu
+
+where 'n' is the number of cpus powered up and energy_cluster is the cost paid
+as soon as any cpu in the cluster is powered up.
+
+The power and frequency domains can naturally be mapped onto the existing
+sched_domain hierarchy and sched_groups by adding the necessary data to the
+existing data structures.
+
+The energy model considers energy consumption from two contributors (shown in
+the illustration below):
+
+1. Busy energy: Energy consumed while a cpu and the higher level groups that it
+belongs to are busy running tasks. Busy energy is associated with the state of
+the cpu, not an event. The time the cpu spends in this state varies. Thus, the
+most obvious platform parameter for this contribution is busy power
+(energy/time).
+
+2. Idle energy: Energy consumed while a cpu and higher level groups that it
+belongs to are idle (in a C-state). Like busy energy, idle energy is associated
+with the state of the cpu. Thus, the platform parameter for this contribution
+is idle power (energy/time).
+
+Energy consumed during transitions from an idle-state (C-state) to a busy state
+(P-state) or going the other way is ignored by the model to simplify the energy
+model calculations.
+
+
+ Power
+ ^
+ | busy->idle idle->busy
+ | transition transition
+ |
+ | _ __
+ | / \ / \__________________
+ |______________/ \ /
+ | \ /
+ | Busy \ Idle / Busy
+ | low P-state \____________/ high P-state
+ |
+ +------------------------------------------------------------> time
+
+Busy |--------------| |-----------------|
+
+Wakeup |------| |------|
+
+Idle |------------|
+
+
+The basic algorithm
+====================
+
+The basic idea is to determine the total energy impact when utilization is
+added or removed by estimating the impact at each level in the sched_domain
+hierarchy starting from the bottom (sched_group contains just a single cpu).
+The energy cost comes from busy time (sched_group is awake because one or more
+cpus are busy) and idle time (in an idle-state). Energy model numbers account
+for energy costs associated with all cpus in the sched_group as a group.
+
+ for_each_domain(cpu, sd) {
+ sg = sched_group_of(cpu)
+ energy_before = curr_util(sg) * busy_power(sg)
+ + (1-curr_util(sg)) * idle_power(sg)
+ energy_after = new_util(sg) * busy_power(sg)
+ + (1-new_util(sg)) * idle_power(sg)
+ energy_diff += energy_before - energy_after
+
+ }
+
+ return energy_diff
+
+{curr, new}_util: The cpu utilization at the lowest level and the overall
+non-idle time for the entire group for higher levels. Utilization is in the
+range 0.0 to 1.0 in the pseudo-code.
+
+busy_power: The power consumption of the sched_group.
+
+idle_power: The power consumption of the sched_group when idle.
+
+Note: It is a fundamental assumption that the utilization is (roughly) scale
+invariant. Task utilization tracking factors in any frequency scaling and
+performance scaling differences due to difference cpu microarchitectures such
+that task utilization can be used across the entire system.
+
+
+Platform energy data
+=====================
+
+struct sched_group_energy can be attached to sched_groups in the sched_domain
+hierarchy and has the following members:
+
+cap_states:
+ List of struct capacity_state representing the supported capacity states
+ (P-states). struct capacity_state has two members: cap and power, which
+ represents the compute capacity and the busy_power of the state. The
+ list must be ordered by capacity low->high.
+
+nr_cap_states:
+ Number of capacity states in cap_states list.
+
+idle_states:
+ List of struct idle_state containing idle_state power cost for each
+ idle-state supported by the system orderd by shallowest state first.
+ All states must be included at all level in the hierarchy, i.e. a
+ sched_group spanning just a single cpu must also include coupled
+ idle-states (cluster states). In addition to the cpuidle idle-states,
+ the list must also contain an entry for the idling using the arch
+ default idle (arch_idle_cpu()). Despite this state may not be a true
+ hardware idle-state it is considered the shallowest idle-state in the
+ energy model and must be the first entry. cpus may enter this state
+ (possibly 'active idling') if cpuidle decides not enter a cpuidle
+ idle-state. Default idle may not be used when cpuidle is enabled.
+ In this case, it should just be a copy of the first cpuidle idle-state.
+
+nr_idle_states:
+ Number of idle states in idle_states list.
+
+There are no unit requirements for the energy cost data. Data can be normalized
+with any reference, however, the normalization must be consistent across all
+energy cost data. That is, one bogo-joule/watt must be the same quantity for
+data, but we don't care what it is.
+
+A recipe for platform characterization
+=======================================
+
+Obtaining the actual model data for a particular platform requires some way of
+measuring power/energy. There isn't a tool to help with this (yet). This
+section provides a recipe for use as reference. It covers the steps used to
+characterize the ARM TC2 development platform. This sort of measurements is
+expected to be done anyway when tuning cpuidle and cpufreq for a given
+platform.
+
+The energy model needs two types of data (struct sched_group_energy holds
+these) for each sched_group where energy costs should be taken into account:
+
+1. Capacity state information
+
+A list containing the compute capacity and power consumption when fully
+utilized attributed to the group as a whole for each available capacity state.
+At the lowest level (group contains just a single cpu) this is the power of the
+cpu alone without including power consumed by resources shared with other cpus.
+It basically needs to fit the basic modelling approach described in "Background
+and Terminology" section:
+
+ energy_system = energy_shared + n * energy_cpu
+
+for a system containing 'n' busy cpus. Only 'energy_cpu' should be included at
+the lowest level. 'energy_shared' is included at the next level which
+represents the group of cpus among which the resources are shared.
+
+This model is, of course, a simplification of reality. Thus, power/energy
+attributions might not always exactly represent how the hardware is designed.
+Also, busy power is likely to depend on the workload. It is therefore
+recommended to use a representative mix of workloads when characterizing the
+capacity states.
+
+If the group has no capacity scaling support, the list will contain a single
+state where power is the busy power attributed to the group. The capacity
+should be set to a default value (1024).
+
+When frequency domains include multiple power domains, the group representing
+the frequency domain and all child groups share capacity states. This must be
+indicated by setting the SD_SHARE_CAP_STATES sched_domain flag. All groups at
+all levels that share the capacity state must have the list of capacity states
+with the power set to the contribution of the individual group.
+
+2. Idle power information
+
+Stored in the idle_states list. The power number is the group idle power
+consumption in each idle state as well when the group is idle but has not
+entered an idle-state ('active idle' as mentioned earlier). Due to the way the
+energy model is defined, the idle power of the deepest group idle state can
+alternatively be accounted for in the parent group busy power. In that case the
+group idle state power values are offset such that the idle power of the
+deepest state is zero. It is less intuitive, but it is easier to measure as
+idle power consumed by the group and the busy/idle power of the parent group
+cannot be distinguished without per group measurement points.
+
+Measuring capacity states and idle power:
+
+The capacity states' capacity and power can be estimated by running a benchmark
+workload at each available capacity state. By restricting the benchmark to run
+on subsets of cpus it is possible to extrapolate the power consumption of
+shared resources.
+
+ARM TC2 has two clusters of two and three cpus respectively. Each cluster has a
+shared L2 cache. TC2 has on-chip energy counters per cluster. Running a
+benchmark workload on just one cpu in a cluster means that power is consumed in
+the cluster (higher level group) and a single cpu (lowest level group). Adding
+another benchmark task to another cpu increases the power consumption by the
+amount consumed by the additional cpu. Hence, it is possible to extrapolate the
+cluster busy power.
+
+For platforms that don't have energy counters or equivalent instrumentation
+built-in, it may be possible to use an external DAQ to acquire similar data.
+
+If the benchmark includes some performance score (for example sysbench cpu
+benchmark), this can be used to record the compute capacity.
+
+Measuring idle power requires insight into the idle state implementation on the
+particular platform. Specifically, if the platform has coupled idle-states (or
+package states). To measure non-coupled per-cpu idle-states it is necessary to
+keep one cpu busy to keep any shared resources alive to isolate the idle power
+of the cpu from idle/busy power of the shared resources. The cpu can be tricked
+into different per-cpu idle states by disabling the other states. Based on
+various combinations of measurements with specific cpus busy and disabling
+idle-states it is possible to extrapolate the idle-state power.
diff --git a/Documentation/scheduler/sched-tune.txt b/Documentation/scheduler/sched-tune.txt
new file mode 100644
index 0000000..9bd2231
--- /dev/null
+++ b/Documentation/scheduler/sched-tune.txt
@@ -0,0 +1,366 @@
+ Central, scheduler-driven, power-performance control
+ (EXPERIMENTAL)
+
+Abstract
+========
+
+The topic of a single simple power-performance tunable, that is wholly
+scheduler centric, and has well defined and predictable properties has come up
+on several occasions in the past [1,2]. With techniques such as a scheduler
+driven DVFS [3], we now have a good framework for implementing such a tunable.
+This document describes the overall ideas behind its design and implementation.
+
+
+Table of Contents
+=================
+
+1. Motivation
+2. Introduction
+3. Signal Boosting Strategy
+4. OPP selection using boosted CPU utilization
+5. Per task group boosting
+6. Question and Answers
+ - What about "auto" mode?
+ - What about boosting on a congested system?
+ - How CPUs are boosted when we have tasks with multiple boost values?
+7. References
+
+
+1. Motivation
+=============
+
+Sched-DVFS [3] is a new event-driven cpufreq governor which allows the
+scheduler to select the optimal DVFS operating point (OPP) for running a task
+allocated to a CPU. The introduction of sched-DVFS enables running workloads at
+the most energy efficient OPPs.
+
+However, sometimes it may be desired to intentionally boost the performance of
+a workload even if that could imply a reasonable increase in energy
+consumption. For example, in order to reduce the response time of a task, we
+may want to run the task at a higher OPP than the one that is actually required
+by it's CPU bandwidth demand.
+
+This last requirement is especially important if we consider that one of the
+main goals of the sched-DVFS component is to replace all currently available
+CPUFreq policies. Since sched-DVFS is event based, as opposed to the sampling
+driven governors we currently have, it is already more responsive at selecting
+the optimal OPP to run tasks allocated to a CPU. However, just tracking the
+actual task load demand may not be enough from a performance standpoint. For
+example, it is not possible to get behaviors similar to those provided by the
+"performance" and "interactive" CPUFreq governors.
+
+This document describes an implementation of a tunable, stacked on top of the
+sched-DVFS which extends its functionality to support task performance
+boosting.
+
+By "performance boosting" we mean the reduction of the time required to
+complete a task activation, i.e. the time elapsed from a task wakeup to its
+next deactivation (e.g. because it goes back to sleep or it terminates). For
+example, if we consider a simple periodic task which executes the same workload
+for 5[s] every 20[s] while running at a certain OPP, a boosted execution of
+that task must complete each of its activations in less than 5[s].
+
+A previous attempt [5] to introduce such a boosting feature has not been
+successful mainly because of the complexity of the proposed solution. The
+approach described in this document exposes a single simple interface to
+user-space. This single tunable knob allows the tuning of system wide
+scheduler behaviours ranging from energy efficiency at one end through to
+incremental performance boosting at the other end. This first tunable affects
+all tasks. However, a more advanced extension of the concept is also provided
+which uses CGroups to boost the performance of only selected tasks while using
+the energy efficient default for all others.
+
+The rest of this document introduces in more details the proposed solution
+which has been named SchedTune.
+
+
+2. Introduction
+===============
+
+SchedTune exposes a simple user-space interface with a single power-performance
+tunable:
+
+ /proc/sys/kernel/sched_cfs_boost
+
+This permits expressing a boost value as an integer in the range [0..100].
+
+A value of 0 (default) configures the CFS scheduler for maximum energy
+efficiency. This means that sched-DVFS runs the tasks at the minimum OPP
+required to satisfy their workload demand.
+A value of 100 configures scheduler for maximum performance, which translates
+to the selection of the maximum OPP on that CPU.
+
+The range between 0 and 100 can be set to satisfy other scenarios suitably. For
+example to satisfy interactive response or depending on other system events
+(battery level etc).
+
+A CGroup based extension is also provided, which permits further user-space
+defined task classification to tune the scheduler for different goals depending
+on the specific nature of the task, e.g. background vs interactive vs
+low-priority.
+
+The overall design of the SchedTune module is built on top of "Per-Entity Load
+Tracking" (PELT) signals and sched-DVFS by introducing a bias on the Operating
+Performance Point (OPP) selection.
+Each time a task is allocated on a CPU, sched-DVFS has the opportunity to tune
+the operating frequency of that CPU to better match the workload demand. The
+selection of the actual OPP being activated is influenced by the global boost
+value, or the boost value for the task CGroup when in use.
+
+This simple biasing approach leverages existing frameworks, which means minimal
+modifications to the scheduler, and yet it allows to achieve a range of
+different behaviours all from a single simple tunable knob.
+The only new concept introduced is that of signal boosting.
+
+
+3. Signal Boosting Strategy
+===========================
+
+The whole PELT machinery works based on the value of a few load tracking signals
+which basically track the CPU bandwidth requirements for tasks and the capacity
+of CPUs. The basic idea behind the SchedTune knob is to artificially inflate
+some of these load tracking signals to make a task or RQ appears more demanding
+that it actually is.
+
+Which signals have to be inflated depends on the specific "consumer". However,
+independently from the specific (signal, consumer) pair, it is important to
+define a simple and possibly consistent strategy for the concept of boosting a
+signal.
+
+A boosting strategy defines how the "abstract" user-space defined
+sched_cfs_boost value is translated into an internal "margin" value to be added
+to a signal to get its inflated value:
+
+ margin := boosting_strategy(sched_cfs_boost, signal)
+ boosted_signal := signal + margin
+
+Different boosting strategies were identified and analyzed before selecting the
+one found to be most effective.
+
+Signal Proportional Compensation (SPC)
+--------------------------------------
+
+In this boosting strategy the sched_cfs_boost value is used to compute a
+margin which is proportional to the complement of the original signal.
+When a signal has a maximum possible value, its complement is defined as
+the delta from the actual value and its possible maximum.
+
+Since the tunable implementation uses signals which have SCHED_LOAD_SCALE as
+the maximum possible value, the margin becomes:
+
+ margin := sched_cfs_boost * (SCHED_LOAD_SCALE - signal)
+
+Using this boosting strategy:
+- a 100% sched_cfs_boost means that the signal is scaled to the maximum value
+- each value in the range of sched_cfs_boost effectively inflates the signal in
+ question by a quantity which is proportional to the maximum value.
+
+For example, by applying the SPC boosting strategy to the selection of the OPP
+to run a task it is possible to achieve these behaviors:
+
+- 0% boosting: run the task at the minimum OPP required by its workload
+- 100% boosting: run the task at the maximum OPP available for the CPU
+- 50% boosting: run at the half-way OPP between minimum and maximum
+
+Which means that, at 50% boosting, a task will be scheduled to run at half of
+the maximum theoretically achievable performance on the specific target
+platform.
+
+A graphical representation of an SPC boosted signal is represented in the
+following figure where:
+ a) "-" represents the original signal
+ b) "b" represents a 50% boosted signal
+ c) "p" represents a 100% boosted signal
+
+
+ ^
+ | SCHED_LOAD_SCALE
+ +-----------------------------------------------------------------+
+ |pppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppp
+ |
+ | boosted_signal
+ | bbbbbbbbbbbbbbbbbbbbbbbb
+ |
+ | original signal
+ | bbbbbbbbbbbbbbbbbbbbbbbb+----------------------+
+ | |
+ |bbbbbbbbbbbbbbbbbb |
+ | |
+ | |
+ | |
+ | +-----------------------+
+ | |
+ | |
+ | |
+ |------------------+
+ |
+ |
+ +----------------------------------------------------------------------->
+
+The plot above shows a ramped load signal (titled 'original_signal') and it's
+boosted equivalent. For each step of the original signal the boosted signal
+corresponding to a 50% boost is midway from the original signal and the upper
+bound. Boosting by 100% generates a boosted signal which is always saturated to
+the upper bound.
+
+
+4. OPP selection using boosted CPU utilization
+==============================================
+
+It is worth calling out that the implementation does not introduce any new load
+signals. Instead, it provides an API to tune existing signals. This tuning is
+done on demand and only in scheduler code paths where it is sensible to do so.
+The new API calls are defined to return either the default signal or a boosted
+one, depending on the value of sched_cfs_boost. This is a clean an non invasive
+modification of the existing existing code paths.
+
+The signal representing a CPU's utilization is boosted according to the
+previously described SPC boosting strategy. To sched-DVFS, this allows a CPU
+(ie CFS run-queue) to appear more used then it actually is.
+
+Thus, with the sched_cfs_boost enabled we have the following main functions to
+get the current utilization of a CPU:
+
+ cpu_util()
+ boosted_cpu_util()
+
+The new boosted_cpu_util() is similar to the first but returns a boosted
+utilization signal which is a function of the sched_cfs_boost value.
+
+This function is used in the CFS scheduler code paths where sched-DVFS needs to
+decide the OPP to run a CPU at.
+For example, this allows selecting the highest OPP for a CPU which has
+the boost value set to 100%.
+
+
+5. Per task group boosting
+==========================
+
+The availability of a single knob which is used to boost all tasks in the
+system is certainly a simple solution but it quite likely doesn't fit many
+utilization scenarios, especially in the mobile device space.
+
+For example, on battery powered devices there usually are many background
+services which are long running and need energy efficient scheduling. On the
+other hand, some applications are more performance sensitive and require an
+interactive response and/or maximum performance, regardless of the energy cost.
+To better service such scenarios, the SchedTune implementation has an extension
+that provides a more fine grained boosting interface.
+
+A new CGroup controller, namely "schedtune", could be enabled which allows to
+defined and configure task groups with different boosting values.
+Tasks that require special performance can be put into separate CGroups.
+The value of the boost associated with the tasks in this group can be specified
+using a single knob exposed by the CGroup controller:
+
+ schedtune.boost
+
+This knob allows the definition of a boost value that is to be used for
+SPC boosting of all tasks attached to this group.
+
+The current schedtune controller implementation is really simple and has these
+main characteristics:
+
+ 1) It is only possible to create 1 level depth hierarchies
+
+ The root control groups define the system-wide boost value to be applied
+ by default to all tasks. Its direct subgroups are named "boost groups" and
+ they define the boost value for specific set of tasks.
+ Further nested subgroups are not allowed since they do not have a sensible
+ meaning from a user-space standpoint.
+
+ 2) It is possible to define only a limited number of "boost groups"
+
+ This number is defined at compile time and by default configured to 16.
+ This is a design decision motivated by two main reasons:
+ a) In a real system we do not expect utilization scenarios with more then few
+ boost groups. For example, a reasonable collection of groups could be
+ just "background", "interactive" and "performance".
+ b) It simplifies the implementation considerably, especially for the code
+ which has to compute the per CPU boosting once there are multiple
+ RUNNABLE tasks with different boost values.
+
+Such a simple design should allow servicing the main utilization scenarios identified
+so far. It provides a simple interface which can be used to manage the
+power-performance of all tasks or only selected tasks.
+Moreover, this interface can be easily integrated by user-space run-times (e.g.
+Android, ChromeOS) to implement a QoS solution for task boosting based on tasks
+classification, which has been a long standing requirement.
+
+Setup and usage
+---------------
+
+0. Use a kernel with CGROUP_SCHEDTUNE support enabled
+
+1. Check that the "schedtune" CGroup controller is available:
+
+ root@linaro-nano:~# cat /proc/cgroups
+ #subsys_name hierarchy num_cgroups enabled
+ cpuset 0 1 1
+ cpu 0 1 1
+ schedtune 0 1 1
+
+2. Mount a tmpfs to create the CGroups mount point (Optional)
+
+ root@linaro-nano:~# sudo mount -t tmpfs cgroups /sys/fs/cgroup
+
+3. Mount the "schedtune" controller
+
+ root@linaro-nano:~# mkdir /sys/fs/cgroup/stune
+ root@linaro-nano:~# sudo mount -t cgroup -o schedtune stune /sys/fs/cgroup/stune
+
+4. Setup the system-wide boost value (Optional)
+
+ If not configured the root control group has a 0% boost value, which
+ basically disables boosting for all tasks in the system thus running in
+ an energy-efficient mode.
+
+ root@linaro-nano:~# echo $SYSBOOST > /sys/fs/cgroup/stune/schedtune.boost
+
+5. Create task groups and configure their specific boost value (Optional)
+
+ For example here we create a "performance" boost group configure to boost
+ all its tasks to 100%
+
+ root@linaro-nano:~# mkdir /sys/fs/cgroup/stune/performance
+ root@linaro-nano:~# echo 100 > /sys/fs/cgroup/stune/performance/schedtune.boost
+
+6. Move tasks into the boost group
+
+ For example, the following moves the tasks with PID $TASKPID (and all its
+ threads) into the "performance" boost group.
+
+ root@linaro-nano:~# echo "TASKPID > /sys/fs/cgroup/stune/performance/cgroup.procs
+
+This simple configuration allows only the threads of the $TASKPID task to run,
+when needed, at the highest OPP in the most capable CPU of the system.
+
+
+6. Question and Answers
+=======================
+
+What about "auto" mode?
+-----------------------
+
+The 'auto' mode as described in [5] can be implemented by interfacing SchedTune
+with some suitable user-space element. This element could use the exposed
+system-wide or cgroup based interface.
+
+How are multiple groups of tasks with different boost values managed?
+---------------------------------------------------------------------
+
+The current SchedTune implementation keeps track of the boosted RUNNABLE tasks
+on a CPU. Once sched-DVFS selects the OPP to run a CPU at, the CPU utilization
+is boosted with a value which is the maximum of the boost values of the
+currently RUNNABLE tasks in its RQ.
+
+This allows sched-DVFS to boost a CPU only while there are boosted tasks ready
+to run and switch back to the energy efficient mode as soon as the last boosted
+task is dequeued.
+
+
+7. References
+=============
+[1] http://lwn.net/Articles/552889
+[2] http://lkml.org/lkml/2012/5/18/91
+[3] http://lkml.org/lkml/2015/6/26/620
diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 3849814..0e03baf 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -1151,8 +1151,21 @@
usage. This is called key->payload.rcu_data0. The following accessors
wrap the RCU calls to this element:
- rcu_assign_keypointer(struct key *key, void *data);
- void *rcu_dereference_key(struct key *key);
+ (a) Set or change the first payload pointer:
+
+ rcu_assign_keypointer(struct key *key, void *data);
+
+ (b) Read the first payload pointer with the key semaphore held:
+
+ [const] void *dereference_key_locked([const] struct key *key);
+
+ Note that the return value will inherit its constness from the key
+ parameter. Static analysis will give an error if it things the lock
+ isn't held.
+
+ (c) Read the first payload pointer with the RCU read lock held:
+
+ const void *dereference_key_rcu(const struct key *key);
===================
diff --git a/Documentation/sync.txt b/Documentation/sync.txt
new file mode 100644
index 0000000..a2d05e7
--- /dev/null
+++ b/Documentation/sync.txt
@@ -0,0 +1,75 @@
+Motivation:
+
+In complicated DMA pipelines such as graphics (multimedia, camera, gpu, display)
+a consumer of a buffer needs to know when the producer has finished producing
+it. Likewise the producer needs to know when the consumer is finished with the
+buffer so it can reuse it. A particular buffer may be consumed by multiple
+consumers which will retain the buffer for different amounts of time. In
+addition, a consumer may consume multiple buffers atomically.
+The sync framework adds an API which allows synchronization between the
+producers and consumers in a generic way while also allowing platforms which
+have shared hardware synchronization primitives to exploit them.
+
+Goals:
+ * provide a generic API for expressing synchronization dependencies
+ * allow drivers to exploit hardware synchronization between hardware
+ blocks
+ * provide a userspace API that allows a compositor to manage
+ dependencies.
+ * provide rich telemetry data to allow debugging slowdowns and stalls of
+ the graphics pipeline.
+
+Objects:
+ * sync_timeline
+ * sync_pt
+ * sync_fence
+
+sync_timeline:
+
+A sync_timeline is an abstract monotonically increasing counter. In general,
+each driver/hardware block context will have one of these. They can be backed
+by the appropriate hardware or rely on the generic sw_sync implementation.
+Timelines are only ever created through their specific implementations
+(i.e. sw_sync.)
+
+sync_pt:
+
+A sync_pt is an abstract value which marks a point on a sync_timeline. Sync_pts
+have a single timeline parent. They have 3 states: active, signaled, and error.
+They start in active state and transition, once, to either signaled (when the
+timeline counter advances beyond the sync_pt’s value) or error state.
+
+sync_fence:
+
+Sync_fences are the primary primitives used by drivers to coordinate
+synchronization of their buffers. They are a collection of sync_pts which may
+or may not have the same timeline parent. A sync_pt can only exist in one fence
+and the fence's list of sync_pts is immutable once created. Fences can be
+waited on synchronously or asynchronously. Two fences can also be merged to
+create a third fence containing a copy of the two fences’ sync_pts. Fences are
+backed by file descriptors to allow userspace to coordinate the display pipeline
+dependencies.
+
+Use:
+
+A driver implementing sync support should have a work submission function which:
+ * takes a fence argument specifying when to begin work
+ * asynchronously queues that work to kick off when the fence is signaled
+ * returns a fence to indicate when its work will be done.
+ * signals the returned fence once the work is completed.
+
+Consider an imaginary display driver that has the following API:
+/*
+ * assumes buf is ready to be displayed.
+ * blocks until the buffer is on screen.
+ */
+ void display_buffer(struct dma_buf *buf);
+
+The new API will become:
+/*
+ * will display buf when fence is signaled.
+ * returns immediately with a fence that will signal when buf
+ * is no longer displayed.
+ */
+struct sync_fence* display_buffer(struct dma_buf *buf,
+ struct sync_fence *fence);
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ffab8b5..52daff6 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -659,12 +659,14 @@
perf_event_paranoid:
Controls use of the performance events system by unprivileged
-users (without CAP_SYS_ADMIN). The default value is 2.
+users (without CAP_SYS_ADMIN). The default value is 3 if
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 2 otherwise.
-1: Allow use of (almost) all events by all users
>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
>=1: Disallow CPU event access by users without CAP_SYS_ADMIN
>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+>=3: Disallow all event access by users without CAP_SYS_ADMIN
==============================================================
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 95ccbe6..206c9b0 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -30,6 +30,7 @@
- dirty_writeback_centisecs
- drop_caches
- extfrag_threshold
+- extra_free_kbytes
- hugepages_treat_as_movable
- hugetlb_shm_group
- laptop_mode
@@ -240,6 +241,21 @@
==============================================================
+extra_free_kbytes
+
+This parameter tells the VM to keep extra free memory between the threshold
+where background reclaim (kswapd) kicks in, and the threshold where direct
+reclaim (by allocating processes) kicks in.
+
+This is useful for workloads that require low latency memory allocations
+and have a bounded burstiness in memory allocations, for example a
+realtime application that receives and transmits network traffic
+(causing in-kernel memory allocations) with a maximum total message burst
+size of 200MB may need 200MB of extra free memory to avoid direct reclaim
+related latencies.
+
+==============================================================
+
hugepages_treat_as_movable
This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
diff --git a/Documentation/tee.txt b/Documentation/tee.txt
new file mode 100644
index 0000000..56ea85f
--- /dev/null
+++ b/Documentation/tee.txt
@@ -0,0 +1,127 @@
+=============
+TEE subsystem
+=============
+
+This document describes the TEE subsystem in Linux.
+
+A TEE (Trusted Execution Environment) is a trusted OS running in some
+secure environment, for example, TrustZone on ARM CPUs, or a separate
+secure co-processor etc. A TEE driver handles the details needed to
+communicate with the TEE.
+
+This subsystem deals with:
+
+- Registration of TEE drivers
+
+- Managing shared memory between Linux and the TEE
+
+- Providing a generic API to the TEE
+
+The TEE interface
+=================
+
+include/uapi/linux/tee.h defines the generic interface to a TEE.
+
+User space (the client) connects to the driver by opening /dev/tee[0-9]* or
+/dev/teepriv[0-9]*.
+
+- TEE_IOC_SHM_ALLOC allocates shared memory and returns a file descriptor
+ which user space can mmap. When user space doesn't need the file
+ descriptor any more, it should be closed. When shared memory isn't needed
+ any longer it should be unmapped with munmap() to allow the reuse of
+ memory.
+
+- TEE_IOC_VERSION lets user space know which TEE this driver handles and
+ the its capabilities.
+
+- TEE_IOC_OPEN_SESSION opens a new session to a Trusted Application.
+
+- TEE_IOC_INVOKE invokes a function in a Trusted Application.
+
+- TEE_IOC_CANCEL may cancel an ongoing TEE_IOC_OPEN_SESSION or TEE_IOC_INVOKE.
+
+- TEE_IOC_CLOSE_SESSION closes a session to a Trusted Application.
+
+There are two classes of clients, normal clients and supplicants. The latter is
+a helper process for the TEE to access resources in Linux, for example file
+system access. A normal client opens /dev/tee[0-9]* and a supplicant opens
+/dev/teepriv[0-9].
+
+Much of the communication between clients and the TEE is opaque to the
+driver. The main job for the driver is to receive requests from the
+clients, forward them to the TEE and send back the results. In the case of
+supplicants the communication goes in the other direction, the TEE sends
+requests to the supplicant which then sends back the result.
+
+OP-TEE driver
+=============
+
+The OP-TEE driver handles OP-TEE [1] based TEEs. Currently it is only the ARM
+TrustZone based OP-TEE solution that is supported.
+
+Lowest level of communication with OP-TEE builds on ARM SMC Calling
+Convention (SMCCC) [2], which is the foundation for OP-TEE's SMC interface
+[3] used internally by the driver. Stacked on top of that is OP-TEE Message
+Protocol [4].
+
+OP-TEE SMC interface provides the basic functions required by SMCCC and some
+additional functions specific for OP-TEE. The most interesting functions are:
+
+- OPTEE_SMC_FUNCID_CALLS_UID (part of SMCCC) returns the version information
+ which is then returned by TEE_IOC_VERSION
+
+- OPTEE_SMC_CALL_GET_OS_UUID returns the particular OP-TEE implementation, used
+ to tell, for instance, a TrustZone OP-TEE apart from an OP-TEE running on a
+ separate secure co-processor.
+
+- OPTEE_SMC_CALL_WITH_ARG drives the OP-TEE message protocol
+
+- OPTEE_SMC_GET_SHM_CONFIG lets the driver and OP-TEE agree on which memory
+ range to used for shared memory between Linux and OP-TEE.
+
+The GlobalPlatform TEE Client API [5] is implemented on top of the generic
+TEE API.
+
+Picture of the relationship between the different components in the
+OP-TEE architecture::
+
+ User space Kernel Secure world
+ ~~~~~~~~~~ ~~~~~~ ~~~~~~~~~~~~
+ +--------+ +-------------+
+ | Client | | Trusted |
+ +--------+ | Application |
+ /\ +-------------+
+ || +----------+ /\
+ || |tee- | ||
+ || |supplicant| \/
+ || +----------+ +-------------+
+ \/ /\ | TEE Internal|
+ +-------+ || | API |
+ + TEE | || +--------+--------+ +-------------+
+ | Client| || | TEE | OP-TEE | | OP-TEE |
+ | API | \/ | subsys | driver | | Trusted OS |
+ +-------+----------------+----+-------+----+-----------+-------------+
+ | Generic TEE API | | OP-TEE MSG |
+ | IOCTL (TEE_IOC_*) | | SMCCC (OPTEE_SMC_CALL_*) |
+ +-----------------------------+ +------------------------------+
+
+RPC (Remote Procedure Call) are requests from secure world to kernel driver
+or tee-supplicant. An RPC is identified by a special range of SMCCC return
+values from OPTEE_SMC_CALL_WITH_ARG. RPC messages which are intended for the
+kernel are handled by the kernel driver. Other RPC messages will be forwarded to
+tee-supplicant without further involvement of the driver, except switching
+shared memory buffer representation.
+
+References
+==========
+
+[1] https://github.com/OP-TEE/optee_os
+
+[2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+
+[3] drivers/tee/optee/optee_smc.h
+
+[4] drivers/tee/optee/optee_msg.h
+
+[5] http://www.globalplatform.org/specificationsdevice.asp look for
+ "TEE Client API Specification v1.0" and click download.
diff --git a/Documentation/trace/events-power.txt b/Documentation/trace/events-power.txt
index 21d514c..4d817d5 100644
--- a/Documentation/trace/events-power.txt
+++ b/Documentation/trace/events-power.txt
@@ -25,6 +25,7 @@
cpu_idle "state=%lu cpu_id=%lu"
cpu_frequency "state=%lu cpu_id=%lu"
+cpu_frequency_limits "min=%lu max=%lu cpu_id=%lu"
A suspend event is used to indicate the system going in and out of the
suspend mode:
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 185c39f..91723ed 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -362,6 +362,26 @@
to correlate events across hypervisor/guest if
tb_offset is known.
+ mono: This uses the fast monotonic clock (CLOCK_MONOTONIC)
+ which is monotonic and is subject to NTP rate adjustments.
+
+ mono_raw:
+ This is the raw monotonic clock (CLOCK_MONOTONIC_RAW)
+ which is montonic but is not subject to any rate adjustments
+ and ticks at the same rate as the hardware clocksource.
+
+ boot: This is the boot clock (CLOCK_BOOTTIME) and is based on the
+ fast monotonic clock, but also accounts for time spent in
+ suspend. Since the clock access is designed for use in
+ tracing in the suspend path, some side effects are possible
+ if clock is accessed after the suspend time is accounted before
+ the fast mono clock is updated. In this case, the clock update
+ appears to happen slightly sooner than it normally would have.
+ Also on 32-bit systems, it's possible that the 64-bit boot offset
+ sees a partial update. These effects are rare and post
+ processing should be able to handle them. See comments in the
+ ktime_get_boot_fast_ns() function for more information.
+
To set a clock, simply echo the clock name into this file.
echo global > trace_clock
@@ -2102,6 +2122,35 @@
1) 1.449 us | }
+You can disable the hierarchical function call formatting and instead print a
+flat list of function entry and return events. This uses the format described
+in the Output Formatting section and respects all the trace options that
+control that formatting. Hierarchical formatting is the default.
+
+ hierachical: echo nofuncgraph-flat > trace_options
+ flat: echo funcgraph-flat > trace_options
+
+ ie:
+
+ # tracer: function_graph
+ #
+ # entries-in-buffer/entries-written: 68355/68355 #P:2
+ #
+ # _-----=> irqs-off
+ # / _----=> need-resched
+ # | / _---=> hardirq/softirq
+ # || / _--=> preempt-depth
+ # ||| / delay
+ # TASK-PID CPU# |||| TIMESTAMP FUNCTION
+ # | | | |||| | |
+ sh-1806 [001] d... 198.843443: graph_ent: func=_raw_spin_lock
+ sh-1806 [001] d... 198.843445: graph_ent: func=__raw_spin_lock
+ sh-1806 [001] d..1 198.843447: graph_ret: func=__raw_spin_lock
+ sh-1806 [001] d..1 198.843449: graph_ret: func=_raw_spin_lock
+ sh-1806 [001] d..1 198.843451: graph_ent: func=_raw_spin_unlock_irqrestore
+ sh-1806 [001] d... 198.843453: graph_ret: func=_raw_spin_unlock_irqrestore
+
+
You might find other useful features for this tracer in the
following "dynamic ftrace" section such as tracing only specific
functions or tasks.
diff --git a/MAINTAINERS b/MAINTAINERS
index fcaab22..a77cae7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8606,6 +8606,12 @@
F: Documentation/scsi/NinjaSCSI.txt
F: drivers/scsi/nsp32*
+NINTENDO HID DRIVER
+M: Daniel J. Ogorchock <djogorchock@gmail.com>
+L: linux-input@vger.kernel.org
+S: Maintained
+F: drivers/hid/hid-nintendo*
+
NIOS2 ARCHITECTURE
M: Ley Foon Tan <lftan@altera.com>
L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
@@ -9010,6 +9016,11 @@
F: drivers/oprofile/
F: include/linux/oprofile.h
+OP-TEE DRIVER
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: drivers/tee/optee/
+
ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
M: Mark Fasheh <mfasheh@versity.com>
M: Joel Becker <jlbec@evilplan.org>
@@ -10655,6 +10666,14 @@
F: include/linux/stm.h
F: include/uapi/linux/stm.h
+TEE SUBSYSTEM
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: include/linux/tee_drv.h
+F: include/uapi/linux/tee.h
+F: drivers/tee/
+F: Documentation/tee.txt
+
THUNDERBOLT DRIVER
M: Andreas Noever <andreas.noever@gmail.com>
S: Maintained
diff --git a/Makefile b/Makefile
index 69af44d..3a32f94 100644
--- a/Makefile
+++ b/Makefile
@@ -339,6 +339,7 @@
# Make variables (CC, etc...)
AS = $(CROSS_COMPILE)as
LD = $(CROSS_COMPILE)ld
+LDGOLD = $(CROSS_COMPILE)ld.gold
CC = $(CROSS_COMPILE)gcc
CPP = $(CC) -E
AR = $(CROSS_COMPILE)ar
@@ -503,7 +504,11 @@
ifeq ($(cc-name),clang)
ifneq ($(CROSS_COMPILE),)
-CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%))
+CLANG_TRIPLE ?= $(CROSS_COMPILE)
+CLANG_FLAGS += --target=$(notdir $(CLANG_TRIPLE:%-=%))
+ifeq ($(shell $(srctree)/scripts/clang-android.sh $(CC) $(CLANG_FLAGS)), y)
+$(error "Clang with Android --target detected. Did you specify CLANG_TRIPLE?")
+endif
GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..)
@@ -633,6 +638,20 @@
CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
export CFLAGS_GCOV CFLAGS_KCOV
+# Make toolchain changes before including arch/$(SRCARCH)/Makefile to ensure
+# ar/cc/ld-* macros return correct values.
+ifdef CONFIG_LTO_CLANG
+# use GNU gold with LLVMgold for LTO linking, and LD for vmlinux_link
+LDFINAL_vmlinux := $(LD)
+LD := $(LDGOLD)
+LDFLAGS += -plugin LLVMgold.so
+# use llvm-ar for building symbol tables from IR files, and llvm-dis instead
+# of objdump for processing symbol versions and exports
+LLVM_AR := llvm-ar
+LLVM_DIS := llvm-dis
+export LLVM_AR LLVM_DIS
+endif
+
# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
# values of the respective KBUILD_* variables
ARCH_CPPFLAGS :=
@@ -653,6 +672,53 @@
KBUILD_CFLAGS += $(call cc-option,-fdata-sections,)
endif
+ifdef CONFIG_LTO_CLANG
+lto-clang-flags := -flto -fvisibility=hidden
+
+# allow disabling only clang LTO where needed
+DISABLE_LTO_CLANG := -fno-lto -fvisibility=default
+export DISABLE_LTO_CLANG
+endif
+
+ifdef CONFIG_LTO
+lto-flags := $(lto-clang-flags)
+KBUILD_CFLAGS += $(lto-flags)
+
+DISABLE_LTO := $(DISABLE_LTO_CLANG)
+export DISABLE_LTO
+
+# LDFINAL_vmlinux and LDFLAGS_FINAL_vmlinux can be set to override
+# the linker and flags for vmlinux_link.
+export LDFINAL_vmlinux LDFLAGS_FINAL_vmlinux
+endif
+
+ifdef CONFIG_CFI_CLANG
+cfi-clang-flags += -fsanitize=cfi
+DISABLE_CFI_CLANG := -fno-sanitize=cfi
+ifdef CONFIG_MODULES
+cfi-clang-flags += -fsanitize-cfi-cross-dso
+DISABLE_CFI_CLANG += -fno-sanitize-cfi-cross-dso
+endif
+ifdef CONFIG_CFI_PERMISSIVE
+cfi-clang-flags += -fsanitize-recover=cfi -fno-sanitize-trap=cfi
+endif
+
+# also disable CFI when LTO is disabled
+DISABLE_LTO_CLANG += $(DISABLE_CFI_CLANG)
+# allow disabling only clang CFI where needed
+export DISABLE_CFI_CLANG
+endif
+
+ifdef CONFIG_CFI
+# cfi-flags are re-tested in prepare-compiler-check
+cfi-flags := $(cfi-clang-flags)
+KBUILD_CFLAGS += $(cfi-flags)
+
+DISABLE_CFI := $(DISABLE_CFI_CLANG)
+DISABLE_LTO += $(DISABLE_CFI)
+export DISABLE_CFI
+endif
+
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
KBUILD_CFLAGS += -Os
else
@@ -711,6 +777,7 @@
KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, duplicate-decl-specifier)
# Quiet clang warning: comparison of unsigned expression < 0 is always false
KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
@@ -1108,6 +1175,22 @@
# CC_STACKPROTECTOR_STRONG! Why did it build with _REGULAR?!")
PHONY += prepare-compiler-check
prepare-compiler-check: FORCE
+# Make sure we're using a supported toolchain with LTO_CLANG
+ifdef CONFIG_LTO_CLANG
+ ifneq ($(call clang-ifversion, -ge, 0500, y), y)
+ @echo Cannot use CONFIG_LTO_CLANG: requires clang 5.0 or later >&2 && exit 1
+ endif
+ ifneq ($(call gold-ifversion, -ge, 112000000, y), y)
+ @echo Cannot use CONFIG_LTO_CLANG: requires GNU gold 1.12 or later >&2 && exit 1
+ endif
+endif
+# Make sure compiler supports LTO flags
+ifdef lto-flags
+ ifeq ($(call cc-option, $(lto-flags)),)
+ @echo Cannot use CONFIG_LTO: $(lto-flags) not supported by compiler \
+ >&2 && exit 1
+ endif
+endif
# Make sure compiler supports requested stack protector flag.
ifdef stackp-name
ifeq ($(call cc-option, $(stackp-flag)),)
@@ -1122,6 +1205,11 @@
$(stackp-flag) available but compiler is broken >&2 && exit 1
endif
endif
+ifdef cfi-flags
+ ifeq ($(call cc-option, $(cfi-flags)),)
+ @echo Cannot use CONFIG_CFI: $(cfi-flags) not supported by compiler >&2 && exit 1
+ endif
+endif
@:
# Generate some files
@@ -1131,12 +1219,17 @@
# needs to be updated, so this check is forced on all builds
uts_len := 64
+ifneq (,$(BUILD_NUMBER))
+ UTS_RELEASE=$(KERNELRELEASE)-ab$(BUILD_NUMBER)
+else
+ UTS_RELEASE=$(KERNELRELEASE)
+endif
define filechk_utsrelease.h
- if [ `echo -n "$(KERNELRELEASE)" | wc -c ` -gt $(uts_len) ]; then \
- echo '"$(KERNELRELEASE)" exceeds $(uts_len) characters' >&2; \
- exit 1; \
- fi; \
- (echo \#define UTS_RELEASE \"$(KERNELRELEASE)\";)
+ if [ `echo -n "$(UTS_RELEASE)" | wc -c ` -gt $(uts_len) ]; then \
+ echo '"$(UTS_RELEASE)" exceeds $(uts_len) characters' >&2; \
+ exit 1; \
+ fi; \
+ (echo \#define UTS_RELEASE \"$(UTS_RELEASE)\";)
endef
define filechk_version.h
@@ -1599,7 +1692,8 @@
-o -name modules.builtin -o -name '.tmp_*.o.*' \
-o -name '*.c.[012]*.*' \
-o -name '*.ll' \
- -o -name '*.gcno' \) -type f -print | xargs rm -f
+ -o -name '*.gcno' \
+ -o -name '*.*.symversions' \) -type f -print | xargs rm -f
# Generate tags for editors
# ---------------------------------------------------------------------------
diff --git a/arch/Kconfig b/arch/Kconfig
index b39d0f9..c8e6cdf 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -492,6 +492,75 @@
sections (e.g., '.text.init'). Typically '.' in section names
is used to distinguish them from label names / C identifiers.
+config LTO
+ def_bool n
+
+config ARCH_SUPPORTS_LTO_CLANG
+ bool
+ help
+ An architecture should select this option it supports:
+ - compiling with clang,
+ - compiling inline assembly with clang's integrated assembler,
+ - and linking with either lld or GNU gold w/ LLVMgold.
+
+choice
+ prompt "Link-Time Optimization (LTO) (EXPERIMENTAL)"
+ default LTO_NONE
+ help
+ This option turns on Link-Time Optimization (LTO).
+
+config LTO_NONE
+ bool "None"
+
+config LTO_CLANG
+ bool "Use clang Link Time Optimization (LTO) (EXPERIMENTAL)"
+ depends on ARCH_SUPPORTS_LTO_CLANG
+ depends on !FTRACE_MCOUNT_RECORD || HAVE_C_RECORDMCOUNT
+ depends on !KASAN
+ select LTO
+ select THIN_ARCHIVES
+ select LD_DEAD_CODE_DATA_ELIMINATION
+ help
+ This option enables clang's Link Time Optimization (LTO), which allows
+ the compiler to optimize the kernel globally at link time. If you
+ enable this option, the compiler generates LLVM IR instead of object
+ files, and the actual compilation from IR occurs at the LTO link step,
+ which may take several minutes.
+
+ If you select this option, you must compile the kernel with clang >=
+ 5.0 (make CC=clang) and GNU gold from binutils >= 2.27, and have the
+ LLVMgold plug-in in LD_LIBRARY_PATH.
+
+endchoice
+
+config CFI
+ bool
+
+config CFI_PERMISSIVE
+ bool "Use CFI in permissive mode"
+ depends on CFI
+ help
+ When selected, Control Flow Integrity (CFI) violations result in a
+ warning instead of a kernel panic. This option is useful for finding
+ CFI violations in drivers during development.
+
+config CFI_CLANG
+ bool "Use clang Control Flow Integrity (CFI) (EXPERIMENTAL)"
+ depends on LTO_CLANG
+ depends on KALLSYMS
+ select CFI
+ help
+ This option enables clang Control Flow Integrity (CFI), which adds
+ runtime checking for indirect function calls.
+
+config CFI_CLANG_SHADOW
+ bool "Use CFI shadow to speed up cross-module checks"
+ default y
+ depends on CFI_CLANG
+ help
+ If you select this option, the kernel builds a fast look-up table of
+ CFI check functions in loaded modules to reduce overhead.
+
config HAVE_ARCH_WITHIN_STACK_FRAMES
bool
help
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 9e46d6e..fa47df6a 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -97,4 +97,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ae55f5d..df6c167 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1839,6 +1839,15 @@
help
Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
+config ARM_FLUSH_CONSOLE_ON_RESTART
+ bool "Force flush the console on restart"
+ help
+ If the console is locked while the system is rebooted, the messages
+ in the temporary logbuffer would not have propogated to all the
+ console drivers. This option forces the console lock to be
+ released if it failed to be acquired, which will cause all the
+ pending messages to be flushed.
+
endmenu
menu "Boot options"
@@ -1867,6 +1876,21 @@
This was deprecated in 2001 and announced to live on for 5 years.
Some old boot loaders still use this way.
+config BUILD_ARM_APPENDED_DTB_IMAGE
+ bool "Build a concatenated zImage/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated zImage and list of
+ DTBs to be built by default (instead of a standalone zImage.)
+ The image will built in arch/arm/boot/zImage-dtb
+
+config BUILD_ARM_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated zImage-dtb.
+
# Compressed boot loader in ROM. Yes, we really want to ask about
# TEXT and BSS so we preserve their values in the config files.
config ZBOOT_ROM_TEXT
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index bb8f39f..05e791b 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1732,6 +1732,14 @@
kernel low-level debugging functions. Add earlyprintk to your
kernel parameters to enable this console.
+config EARLY_PRINTK_DIRECT
+ bool "Early printk direct"
+ depends on DEBUG_LL
+ help
+ Say Y here if you want to have an early console using the
+ kernel low-level debugging functions and EARLY_PRINTK is
+ not early enough.
+
config ARM_KPROBES_TEST
tristate "Kprobes test module"
depends on KPROBES && MODULES
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index e14ddca..9ced939 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -298,6 +298,8 @@
# Default target when executing plain make
ifeq ($(CONFIG_XIP_KERNEL),y)
KBUILD_IMAGE := xipImage
+else ifeq ($(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE := zImage-dtb
else
KBUILD_IMAGE := zImage
endif
@@ -349,6 +351,9 @@
$(Q)$(MAKE) $(build)=arch/arm/vdso $@
endif
+zImage-dtb: vmlinux scripts dtbs
+ $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
+
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arm/boot/.gitignore b/arch/arm/boot/.gitignore
index 3c79f85..ad7a025 100644
--- a/arch/arm/boot/.gitignore
+++ b/arch/arm/boot/.gitignore
@@ -4,3 +4,4 @@
bootpImage
uImage
*.dtb
+zImage-dtb
\ No newline at end of file
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 50f8d1b..da75630 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -16,6 +16,7 @@
ifneq ($(MACHINE),)
include $(MACHINE)/Makefile.boot
endif
+include $(srctree)/arch/arm/boot/dts/Makefile
# Note: the following conditions must always be true:
# ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET)
@@ -29,6 +30,14 @@
targets := Image zImage xipImage bootpImage uImage
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+
ifeq ($(CONFIG_XIP_KERNEL),y)
$(obj)/xipImage: vmlinux FORCE
@@ -55,6 +64,10 @@
$(obj)/zImage: $(obj)/compressed/vmlinux FORCE
$(call if_changed,objcopy)
+$(obj)/zImage-dtb: $(obj)/zImage $(DTB_OBJS) FORCE
+ $(call if_changed,cat)
+ @echo ' Kernel: $@ is ready'
+
endif
ifneq ($(LOADADDR),)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index a67ed74..98a87e9 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -784,6 +784,8 @@
bic r6, r6, #1 << 31 @ 32-bit translation system
bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
+ mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
mcrne p15, 0, r6, c2, c0, 2 @ load ttb control
#endif
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 7037201..54f95d3 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -960,5 +960,15 @@
dtstree := $(srctree)/$(src)
dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
-always := $(dtb-y)
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+
+targets += dtbs dtbs_install
+targets += $(DTB_LIST)
+
+always := $(DTB_LIST)
clean-files := *.dtb
diff --git a/arch/arm/configs/ranchu_defconfig b/arch/arm/configs/ranchu_defconfig
new file mode 100644
index 0000000..f59f38c
--- /dev/null
+++ b/arch/arm/configs/ranchu_defconfig
@@ -0,0 +1,315 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_ARCH_MMAP_RND_BITS=16
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARCH_VIRT=y
+CONFIG_ARM_KERNMEM_PERMS=y
+CONFIG_SMP=y
+CONFIG_PREEMPT=y
+CONFIG_AEABI=y
+CONFIG_HIGHMEM=y
+CONFIG_KSM=y
+CONFIG_SECCOMP=y
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_VFP=y
+CONFIG_NEON=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_LRO is not set
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_BRIDGE=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_NETDEVICES=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+CONFIG_SMSC911X=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_USB_USBNET=y
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_INPUT_TABLET=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_AMBAKMI=y
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_FB=y
+CONFIG_FB_GOLDFISH=y
+CONFIG_FB_SIMPLE=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION=y
+CONFIG_GOLDFISH_AUDIO=y
+CONFIG_GOLDFISH=y
+CONFIG_GOLDFISH_PIPE=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_FUSE_FS=y
+CONFIG_CUSE=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_DEBUG_INFO=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_PANIC_TIMEOUT=5
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_VIRTUALIZATION=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 27ed1b1..27e2309 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -62,34 +62,25 @@
using optimized ARM assembler and NEON, when available.
config CRYPTO_AES_ARM
- tristate "AES cipher algorithms (ARM-asm)"
- depends on ARM
+ tristate "Scalar AES cipher for ARM"
select CRYPTO_ALGAPI
select CRYPTO_AES
help
Use optimized AES assembler routines for ARM platforms.
- AES cipher algorithms (FIPS-197). AES uses the Rijndael
- algorithm.
+ On ARM processors without the Crypto Extensions, this is the
+ fastest AES implementation for single blocks. For multiple
+ blocks, the NEON bit-sliced implementation is usually faster.
- Rijndael appears to be consistently a very good performer in
- both hardware and software across a wide range of computing
- environments regardless of its use in feedback or non-feedback
- modes. Its key setup time is excellent, and its key agility is
- good. Rijndael's very low memory requirements make it very well
- suited for restricted-space environments, in which it also
- demonstrates excellent performance. Rijndael's operations are
- among the easiest to defend against power and timing attacks.
-
- The AES specifies three key sizes: 128, 192 and 256 bits
-
- See <http://csrc.nist.gov/encryption/aes/> for more information.
+ This implementation may be vulnerable to cache timing attacks,
+ since it uses lookup tables. However, as countermeasures it
+ disables IRQs and preloads the tables; it is hoped this makes
+ such attacks very difficult.
config CRYPTO_AES_ARM_BS
tristate "Bit sliced AES using NEON instructions"
depends on KERNEL_MODE_NEON
select CRYPTO_ALGAPI
- select CRYPTO_AES_ARM
select CRYPTO_ABLK_HELPER
help
Use a faster and more secure NEON based implementation of AES in CBC,
@@ -120,4 +111,15 @@
that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
that is part of the ARMv8 Crypto Extensions
+config CRYPTO_CHACHA20_NEON
+ tristate "NEON accelerated ChaCha stream cipher algorithms"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_CHACHA20
+
+config CRYPTO_NHPOLY1305_NEON
+ tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_NHPOLY1305
+
endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index fc51507..ae2480b 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -8,6 +8,8 @@
obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -24,8 +26,8 @@
endif
endif
-aes-arm-y := aes-armv4.o aes_glue.o
-aes-arm-bs-y := aesbs-core.o aesbs-glue.o
+aes-arm-y := aes-cipher-core.o aes-cipher-glue.o
+aes-arm-bs-y := aes-armv4.o aesbs-core.o aesbs-glue.o
sha1-arm-y := sha1-armv4-large.o sha1_glue.o
sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
@@ -36,6 +38,8 @@
sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o
aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o
ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o
+chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
new file mode 100644
index 0000000..f2d67c0
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -0,0 +1,264 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+ .text
+ .align 5
+
+ rk .req r0
+ rounds .req r1
+ in .req r2
+ out .req r3
+ ttab .req ip
+
+ t0 .req lr
+ t1 .req r2
+ t2 .req r3
+
+ .macro __select, out, in, idx
+ .if __LINUX_ARM_ARCH__ < 7
+ and \out, \in, #0xff << (8 * \idx)
+ .else
+ ubfx \out, \in, #(8 * \idx), #8
+ .endif
+ .endm
+
+ .macro __load, out, in, idx, sz, op
+ .if __LINUX_ARM_ARCH__ < 7 && \idx > 0
+ ldr\op \out, [ttab, \in, lsr #(8 * \idx) - \sz]
+ .else
+ ldr\op \out, [ttab, \in, lsl #\sz]
+ .endif
+ .endm
+
+ .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op, oldcpsr
+ __select \out0, \in0, 0
+ __select t0, \in1, 1
+ __load \out0, \out0, 0, \sz, \op
+ __load t0, t0, 1, \sz, \op
+
+ .if \enc
+ __select \out1, \in1, 0
+ __select t1, \in2, 1
+ .else
+ __select \out1, \in3, 0
+ __select t1, \in0, 1
+ .endif
+ __load \out1, \out1, 0, \sz, \op
+ __select t2, \in2, 2
+ __load t1, t1, 1, \sz, \op
+ __load t2, t2, 2, \sz, \op
+
+ eor \out0, \out0, t0, ror #24
+
+ __select t0, \in3, 3
+ .if \enc
+ __select \t3, \in3, 2
+ __select \t4, \in0, 3
+ .else
+ __select \t3, \in1, 2
+ __select \t4, \in2, 3
+ .endif
+ __load \t3, \t3, 2, \sz, \op
+ __load t0, t0, 3, \sz, \op
+ __load \t4, \t4, 3, \sz, \op
+
+ .ifnb \oldcpsr
+ /*
+ * This is the final round and we're done with all data-dependent table
+ * lookups, so we can safely re-enable interrupts.
+ */
+ restore_irqs \oldcpsr
+ .endif
+
+ eor \out1, \out1, t1, ror #24
+ eor \out0, \out0, t2, ror #16
+ ldm rk!, {t1, t2}
+ eor \out1, \out1, \t3, ror #16
+ eor \out0, \out0, t0, ror #8
+ eor \out1, \out1, \t4, ror #8
+ eor \out0, \out0, t1
+ eor \out1, \out1, t2
+ .endm
+
+ .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr
+ __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+ __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op, \oldcpsr
+ .endm
+
+ .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr
+ __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr
+ .endm
+
+ .macro __rev, out, in
+ .if __LINUX_ARM_ARCH__ < 6
+ lsl t0, \in, #24
+ and t1, \in, #0xff00
+ and t2, \in, #0xff0000
+ orr \out, t0, \in, lsr #24
+ orr \out, \out, t1, lsl #8
+ orr \out, \out, t2, lsr #8
+ .else
+ rev \out, \in
+ .endif
+ .endm
+
+ .macro __adrl, out, sym, c
+ .if __LINUX_ARM_ARCH__ < 7
+ ldr\c \out, =\sym
+ .else
+ movw\c \out, #:lower16:\sym
+ movt\c \out, #:upper16:\sym
+ .endif
+ .endm
+
+ .macro do_crypt, round, ttab, ltab, bsz
+ push {r3-r11, lr}
+
+ // Load keys first, to reduce latency in case they're not cached yet.
+ ldm rk!, {r8-r11}
+
+ ldr r4, [in]
+ ldr r5, [in, #4]
+ ldr r6, [in, #8]
+ ldr r7, [in, #12]
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ __rev r4, r4
+ __rev r5, r5
+ __rev r6, r6
+ __rev r7, r7
+#endif
+
+ eor r4, r4, r8
+ eor r5, r5, r9
+ eor r6, r6, r10
+ eor r7, r7, r11
+
+ __adrl ttab, \ttab
+ /*
+ * Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into
+ * L1 cache, assuming cacheline size >= 32. This is a hardening measure
+ * intended to make cache-timing attacks more difficult. They may not
+ * be fully prevented, however; see the paper
+ * https://cr.yp.to/antiforgery/cachetiming-20050414.pdf
+ * ("Cache-timing attacks on AES") for a discussion of the many
+ * difficulties involved in writing truly constant-time AES software.
+ */
+ save_and_disable_irqs t0
+ .set i, 0
+ .rept 1024 / 128
+ ldr r8, [ttab, #i + 0]
+ ldr r9, [ttab, #i + 32]
+ ldr r10, [ttab, #i + 64]
+ ldr r11, [ttab, #i + 96]
+ .set i, i + 128
+ .endr
+ push {t0} // oldcpsr
+
+ tst rounds, #2
+ bne 1f
+
+0: \round r8, r9, r10, r11, r4, r5, r6, r7
+ \round r4, r5, r6, r7, r8, r9, r10, r11
+
+1: subs rounds, rounds, #4
+ \round r8, r9, r10, r11, r4, r5, r6, r7
+ bls 2f
+ \round r4, r5, r6, r7, r8, r9, r10, r11
+ b 0b
+
+2: .ifb \ltab
+ add ttab, ttab, #1
+ .else
+ __adrl ttab, \ltab
+ // Prefetch inverse S-box for final round; see explanation above
+ .set i, 0
+ .rept 256 / 64
+ ldr t0, [ttab, #i + 0]
+ ldr t1, [ttab, #i + 32]
+ .set i, i + 64
+ .endr
+ .endif
+
+ pop {rounds} // oldcpsr
+ \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ __rev r4, r4
+ __rev r5, r5
+ __rev r6, r6
+ __rev r7, r7
+#endif
+
+ ldr out, [sp]
+
+ str r4, [out]
+ str r5, [out, #4]
+ str r6, [out, #8]
+ str r7, [out, #12]
+
+ pop {r3-r11, pc}
+
+ .align 3
+ .ltorg
+ .endm
+
+ENTRY(__aes_arm_encrypt)
+ do_crypt fround, crypto_ft_tab,, 2
+ENDPROC(__aes_arm_encrypt)
+
+ .align 5
+ENTRY(__aes_arm_decrypt)
+ do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
+ENDPROC(__aes_arm_decrypt)
+
+ .section ".rodata", "a"
+ .align L1_CACHE_SHIFT
+ .type __aes_arm_inverse_sbox, %object
+__aes_arm_inverse_sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+ .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+ .size __aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox
diff --git a/arch/arm/crypto/aes-cipher-glue.c b/arch/arm/crypto/aes-cipher-glue.c
new file mode 100644
index 0000000..c222f6e
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -0,0 +1,74 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm_encrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_encrypt);
+
+asmlinkage void __aes_arm_decrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_decrypt);
+
+static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int rounds = 6 + ctx->key_length / 4;
+
+ __aes_arm_encrypt(ctx->key_enc, rounds, in, out);
+}
+
+static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int rounds = 6 + ctx->key_length / 4;
+
+ __aes_arm_decrypt(ctx->key_dec, rounds, in, out);
+}
+
+static struct crypto_alg aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-arm",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_module = THIS_MODULE,
+
+ .cra_cipher.cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cra_cipher.cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cra_cipher.cia_setkey = crypto_aes_set_key,
+ .cra_cipher.cia_encrypt = aes_encrypt,
+ .cra_cipher.cia_decrypt = aes_decrypt,
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ .cra_alignmask = 3,
+#endif
+};
+
+static int __init aes_init(void)
+{
+ return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+ crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Scalar AES cipher for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
deleted file mode 100644
index 0409b8f..0000000
--- a/arch/arm/crypto/aes_glue.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Glue Code for the asm optimized version of the AES Cipher Algorithm
- */
-
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <crypto/aes.h>
-
-#include "aes_glue.h"
-
-EXPORT_SYMBOL(AES_encrypt);
-EXPORT_SYMBOL(AES_decrypt);
-EXPORT_SYMBOL(private_AES_set_encrypt_key);
-EXPORT_SYMBOL(private_AES_set_decrypt_key);
-
-static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
- struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
- AES_encrypt(src, dst, &ctx->enc_key);
-}
-
-static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
- struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
- AES_decrypt(src, dst, &ctx->dec_key);
-}
-
-static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
- unsigned int key_len)
-{
- struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-
- switch (key_len) {
- case AES_KEYSIZE_128:
- key_len = 128;
- break;
- case AES_KEYSIZE_192:
- key_len = 192;
- break;
- case AES_KEYSIZE_256:
- key_len = 256;
- break;
- default:
- tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
- return -EINVAL;
- }
-
- if (private_AES_set_encrypt_key(in_key, key_len, &ctx->enc_key) == -1) {
- tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
- return -EINVAL;
- }
- /* private_AES_set_decrypt_key expects an encryption key as input */
- ctx->dec_key = ctx->enc_key;
- if (private_AES_set_decrypt_key(in_key, key_len, &ctx->dec_key) == -1) {
- tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
- return -EINVAL;
- }
- return 0;
-}
-
-static struct crypto_alg aes_alg = {
- .cra_name = "aes",
- .cra_driver_name = "aes-asm",
- .cra_priority = 200,
- .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
- .cra_blocksize = AES_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct AES_CTX),
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(aes_alg.cra_list),
- .cra_u = {
- .cipher = {
- .cia_min_keysize = AES_MIN_KEY_SIZE,
- .cia_max_keysize = AES_MAX_KEY_SIZE,
- .cia_setkey = aes_set_key,
- .cia_encrypt = aes_encrypt,
- .cia_decrypt = aes_decrypt
- }
- }
-};
-
-static int __init aes_init(void)
-{
- return crypto_register_alg(&aes_alg);
-}
-
-static void __exit aes_fini(void)
-{
- crypto_unregister_alg(&aes_alg);
-}
-
-module_init(aes_init);
-module_exit(aes_fini);
-
-MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("aes");
-MODULE_ALIAS_CRYPTO("aes-asm");
-MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/chacha-neon-core.S b/arch/arm/crypto/chacha-neon-core.S
new file mode 100644
index 0000000..eb22926
--- /dev/null
+++ b/arch/arm/crypto/chacha-neon-core.S
@@ -0,0 +1,560 @@
+/*
+ * ChaCha/XChaCha NEON helper functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+ /*
+ * NEON doesn't have a rotate instruction. The alternatives are, more or less:
+ *
+ * (a) vshl.u32 + vsri.u32 (needs temporary register)
+ * (b) vshl.u32 + vshr.u32 + vorr (needs temporary register)
+ * (c) vrev32.16 (16-bit rotations only)
+ * (d) vtbl.8 + vtbl.8 (multiple of 8 bits rotations only,
+ * needs index vector)
+ *
+ * ChaCha has 16, 12, 8, and 7-bit rotations. For the 12 and 7-bit rotations,
+ * the only choices are (a) and (b). We use (a) since it takes two-thirds the
+ * cycles of (b) on both Cortex-A7 and Cortex-A53.
+ *
+ * For the 16-bit rotation, we use vrev32.16 since it's consistently fastest
+ * and doesn't need a temporary register.
+ *
+ * For the 8-bit rotation, we use vtbl.8 + vtbl.8. On Cortex-A7, this sequence
+ * is twice as fast as (a), even when doing (a) on multiple registers
+ * simultaneously to eliminate the stall between vshl and vsri. Also, it
+ * parallelizes better when temporary registers are scarce.
+ *
+ * A disadvantage is that on Cortex-A53, the vtbl sequence is the same speed as
+ * (a), so the need to load the rotation table actually makes the vtbl method
+ * slightly slower overall on that CPU (~1.3% slower ChaCha20). Still, it
+ * seems to be a good compromise to get a more significant speed boost on some
+ * CPUs, e.g. ~4.8% faster ChaCha20 on Cortex-A7.
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .fpu neon
+ .align 5
+
+/*
+ * chacha_permute - permute one block
+ *
+ * Permute one 64-byte block where the state matrix is stored in the four NEON
+ * registers q0-q3. It performs matrix operations on four words in parallel,
+ * but requires shuffling to rearrange the words after each round.
+ *
+ * The round count is given in r3.
+ *
+ * Clobbers: r3, ip, q4-q5
+ */
+chacha_permute:
+
+ adr ip, .Lrol8_table
+ vld1.8 {d10}, [ip, :64]
+
+.Ldoubleround:
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vrev32.16 q3, q3
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #12
+ vsri.u32 q1, q4, #20
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #7
+ vsri.u32 q1, q4, #25
+
+ // x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+ vext.8 q1, q1, q1, #4
+ // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+ vext.8 q2, q2, q2, #8
+ // x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+ vext.8 q3, q3, q3, #12
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vrev32.16 q3, q3
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #12
+ vsri.u32 q1, q4, #20
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #7
+ vsri.u32 q1, q4, #25
+
+ // x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+ vext.8 q1, q1, q1, #12
+ // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+ vext.8 q2, q2, q2, #8
+ // x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+ vext.8 q3, q3, q3, #4
+
+ subs r3, r3, #2
+ bne .Ldoubleround
+
+ bx lr
+ENDPROC(chacha_permute)
+
+ENTRY(chacha_block_xor_neon)
+ // r0: Input state matrix, s
+ // r1: 1 data block output, o
+ // r2: 1 data block input, i
+ // r3: nrounds
+ push {lr}
+
+ // x0..3 = s0..3
+ add ip, r0, #0x20
+ vld1.32 {q0-q1}, [r0]
+ vld1.32 {q2-q3}, [ip]
+
+ vmov q8, q0
+ vmov q9, q1
+ vmov q10, q2
+ vmov q11, q3
+
+ bl chacha_permute
+
+ add ip, r2, #0x20
+ vld1.8 {q4-q5}, [r2]
+ vld1.8 {q6-q7}, [ip]
+
+ // o0 = i0 ^ (x0 + s0)
+ vadd.i32 q0, q0, q8
+ veor q0, q0, q4
+
+ // o1 = i1 ^ (x1 + s1)
+ vadd.i32 q1, q1, q9
+ veor q1, q1, q5
+
+ // o2 = i2 ^ (x2 + s2)
+ vadd.i32 q2, q2, q10
+ veor q2, q2, q6
+
+ // o3 = i3 ^ (x3 + s3)
+ vadd.i32 q3, q3, q11
+ veor q3, q3, q7
+
+ add ip, r1, #0x20
+ vst1.8 {q0-q1}, [r1]
+ vst1.8 {q2-q3}, [ip]
+
+ pop {pc}
+ENDPROC(chacha_block_xor_neon)
+
+ENTRY(hchacha_block_neon)
+ // r0: Input state matrix, s
+ // r1: output (8 32-bit words)
+ // r2: nrounds
+ push {lr}
+
+ vld1.32 {q0-q1}, [r0]!
+ vld1.32 {q2-q3}, [r0]
+
+ mov r3, r2
+ bl chacha_permute
+
+ vst1.32 {q0}, [r1]!
+ vst1.32 {q3}, [r1]
+
+ pop {pc}
+ENDPROC(hchacha_block_neon)
+
+ .align 4
+.Lctrinc: .word 0, 1, 2, 3
+.Lrol8_table: .byte 3, 0, 1, 2, 7, 4, 5, 6
+
+ .align 5
+ENTRY(chacha_4block_xor_neon)
+ push {r4-r5}
+ mov r4, sp // preserve the stack pointer
+ sub ip, sp, #0x20 // allocate a 32 byte buffer
+ bic ip, ip, #0x1f // aligned to 32 bytes
+ mov sp, ip
+
+ // r0: Input state matrix, s
+ // r1: 4 data blocks output, o
+ // r2: 4 data blocks input, i
+ // r3: nrounds
+
+ //
+ // This function encrypts four consecutive ChaCha blocks by loading
+ // the state matrix in NEON registers four times. The algorithm performs
+ // each operation on the corresponding word of each state matrix, hence
+ // requires no word shuffling. The words are re-interleaved before the
+ // final addition of the original state and the XORing step.
+ //
+
+ // x0..15[0-3] = s0..15[0-3]
+ add ip, r0, #0x20
+ vld1.32 {q0-q1}, [r0]
+ vld1.32 {q2-q3}, [ip]
+
+ adr r5, .Lctrinc
+ vdup.32 q15, d7[1]
+ vdup.32 q14, d7[0]
+ vld1.32 {q4}, [r5, :128]
+ vdup.32 q13, d6[1]
+ vdup.32 q12, d6[0]
+ vdup.32 q11, d5[1]
+ vdup.32 q10, d5[0]
+ vadd.u32 q12, q12, q4 // x12 += counter values 0-3
+ vdup.32 q9, d4[1]
+ vdup.32 q8, d4[0]
+ vdup.32 q7, d3[1]
+ vdup.32 q6, d3[0]
+ vdup.32 q5, d2[1]
+ vdup.32 q4, d2[0]
+ vdup.32 q3, d1[1]
+ vdup.32 q2, d1[0]
+ vdup.32 q1, d0[1]
+ vdup.32 q0, d0[0]
+
+ adr ip, .Lrol8_table
+ b 1f
+
+.Ldoubleround4:
+ vld1.32 {q8-q9}, [sp, :256]
+1:
+ // x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+ // x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+ // x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+ // x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+ vadd.i32 q0, q0, q4
+ vadd.i32 q1, q1, q5
+ vadd.i32 q2, q2, q6
+ vadd.i32 q3, q3, q7
+
+ veor q12, q12, q0
+ veor q13, q13, q1
+ veor q14, q14, q2
+ veor q15, q15, q3
+
+ vrev32.16 q12, q12
+ vrev32.16 q13, q13
+ vrev32.16 q14, q14
+ vrev32.16 q15, q15
+
+ // x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+ // x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+ // x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+ // x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+ vadd.i32 q8, q8, q12
+ vadd.i32 q9, q9, q13
+ vadd.i32 q10, q10, q14
+ vadd.i32 q11, q11, q15
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q4, q8
+ veor q9, q5, q9
+ vshl.u32 q4, q8, #12
+ vshl.u32 q5, q9, #12
+ vsri.u32 q4, q8, #20
+ vsri.u32 q5, q9, #20
+
+ veor q8, q6, q10
+ veor q9, q7, q11
+ vshl.u32 q6, q8, #12
+ vshl.u32 q7, q9, #12
+ vsri.u32 q6, q8, #20
+ vsri.u32 q7, q9, #20
+
+ // x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+ // x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+ // x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+ // x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
+ vadd.i32 q0, q0, q4
+ vadd.i32 q1, q1, q5
+ vadd.i32 q2, q2, q6
+ vadd.i32 q3, q3, q7
+
+ veor q12, q12, q0
+ veor q13, q13, q1
+ veor q14, q14, q2
+ veor q15, q15, q3
+
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+ // x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+ // x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+ // x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+ vadd.i32 q8, q8, q12
+ vadd.i32 q9, q9, q13
+ vadd.i32 q10, q10, q14
+ vadd.i32 q11, q11, q15
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q4, q8
+ veor q9, q5, q9
+ vshl.u32 q4, q8, #7
+ vshl.u32 q5, q9, #7
+ vsri.u32 q4, q8, #25
+ vsri.u32 q5, q9, #25
+
+ veor q8, q6, q10
+ veor q9, q7, q11
+ vshl.u32 q6, q8, #7
+ vshl.u32 q7, q9, #7
+ vsri.u32 q6, q8, #25
+ vsri.u32 q7, q9, #25
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+ // x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+ // x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+ // x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+ vadd.i32 q0, q0, q5
+ vadd.i32 q1, q1, q6
+ vadd.i32 q2, q2, q7
+ vadd.i32 q3, q3, q4
+
+ veor q15, q15, q0
+ veor q12, q12, q1
+ veor q13, q13, q2
+ veor q14, q14, q3
+
+ vrev32.16 q15, q15
+ vrev32.16 q12, q12
+ vrev32.16 q13, q13
+ vrev32.16 q14, q14
+
+ // x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+ // x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+ // x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+ // x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+ vadd.i32 q10, q10, q15
+ vadd.i32 q11, q11, q12
+ vadd.i32 q8, q8, q13
+ vadd.i32 q9, q9, q14
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q7, q8
+ veor q9, q4, q9
+ vshl.u32 q7, q8, #12
+ vshl.u32 q4, q9, #12
+ vsri.u32 q7, q8, #20
+ vsri.u32 q4, q9, #20
+
+ veor q8, q5, q10
+ veor q9, q6, q11
+ vshl.u32 q5, q8, #12
+ vshl.u32 q6, q9, #12
+ vsri.u32 q5, q8, #20
+ vsri.u32 q6, q9, #20
+
+ // x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+ // x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+ // x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+ // x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
+ vadd.i32 q0, q0, q5
+ vadd.i32 q1, q1, q6
+ vadd.i32 q2, q2, q7
+ vadd.i32 q3, q3, q4
+
+ veor q15, q15, q0
+ veor q12, q12, q1
+ veor q13, q13, q2
+ veor q14, q14, q3
+
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+ // x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+ // x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+ // x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+ vadd.i32 q10, q10, q15
+ vadd.i32 q11, q11, q12
+ vadd.i32 q8, q8, q13
+ vadd.i32 q9, q9, q14
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q7, q8
+ veor q9, q4, q9
+ vshl.u32 q7, q8, #7
+ vshl.u32 q4, q9, #7
+ vsri.u32 q7, q8, #25
+ vsri.u32 q4, q9, #25
+
+ veor q8, q5, q10
+ veor q9, q6, q11
+ vshl.u32 q5, q8, #7
+ vshl.u32 q6, q9, #7
+ vsri.u32 q5, q8, #25
+ vsri.u32 q6, q9, #25
+
+ subs r3, r3, #2
+ bne .Ldoubleround4
+
+ // x0..7[0-3] are in q0-q7, x10..15[0-3] are in q10-q15.
+ // x8..9[0-3] are on the stack.
+
+ // Re-interleave the words in the first two rows of each block (x0..7).
+ // Also add the counter values 0-3 to x12[0-3].
+ vld1.32 {q8}, [r5, :128] // load counter values 0-3
+ vzip.32 q0, q1 // => (0 1 0 1) (0 1 0 1)
+ vzip.32 q2, q3 // => (2 3 2 3) (2 3 2 3)
+ vzip.32 q4, q5 // => (4 5 4 5) (4 5 4 5)
+ vzip.32 q6, q7 // => (6 7 6 7) (6 7 6 7)
+ vadd.u32 q12, q8 // x12 += counter values 0-3
+ vswp d1, d4
+ vswp d3, d6
+ vld1.32 {q8-q9}, [r0]! // load s0..7
+ vswp d9, d12
+ vswp d11, d14
+
+ // Swap q1 and q4 so that we'll free up consecutive registers (q0-q1)
+ // after XORing the first 32 bytes.
+ vswp q1, q4
+
+ // First two rows of each block are (q0 q1) (q2 q6) (q4 q5) (q3 q7)
+
+ // x0..3[0-3] += s0..3[0-3] (add orig state to 1st row of each block)
+ vadd.u32 q0, q0, q8
+ vadd.u32 q2, q2, q8
+ vadd.u32 q4, q4, q8
+ vadd.u32 q3, q3, q8
+
+ // x4..7[0-3] += s4..7[0-3] (add orig state to 2nd row of each block)
+ vadd.u32 q1, q1, q9
+ vadd.u32 q6, q6, q9
+ vadd.u32 q5, q5, q9
+ vadd.u32 q7, q7, q9
+
+ // XOR first 32 bytes using keystream from first two rows of first block
+ vld1.8 {q8-q9}, [r2]!
+ veor q8, q8, q0
+ veor q9, q9, q1
+ vst1.8 {q8-q9}, [r1]!
+
+ // Re-interleave the words in the last two rows of each block (x8..15).
+ vld1.32 {q8-q9}, [sp, :256]
+ vzip.32 q12, q13 // => (12 13 12 13) (12 13 12 13)
+ vzip.32 q14, q15 // => (14 15 14 15) (14 15 14 15)
+ vzip.32 q8, q9 // => (8 9 8 9) (8 9 8 9)
+ vzip.32 q10, q11 // => (10 11 10 11) (10 11 10 11)
+ vld1.32 {q0-q1}, [r0] // load s8..15
+ vswp d25, d28
+ vswp d27, d30
+ vswp d17, d20
+ vswp d19, d22
+
+ // Last two rows of each block are (q8 q12) (q10 q14) (q9 q13) (q11 q15)
+
+ // x8..11[0-3] += s8..11[0-3] (add orig state to 3rd row of each block)
+ vadd.u32 q8, q8, q0
+ vadd.u32 q10, q10, q0
+ vadd.u32 q9, q9, q0
+ vadd.u32 q11, q11, q0
+
+ // x12..15[0-3] += s12..15[0-3] (add orig state to 4th row of each block)
+ vadd.u32 q12, q12, q1
+ vadd.u32 q14, q14, q1
+ vadd.u32 q13, q13, q1
+ vadd.u32 q15, q15, q1
+
+ // XOR the rest of the data with the keystream
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q8
+ veor q1, q1, q12
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q2
+ veor q1, q1, q6
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q10
+ veor q1, q1, q14
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q4
+ veor q1, q1, q5
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q9
+ veor q1, q1, q13
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ veor q0, q0, q3
+ veor q1, q1, q7
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]
+ mov sp, r4 // restore original stack pointer
+ veor q0, q0, q11
+ veor q1, q1, q15
+ vst1.8 {q0-q1}, [r1]
+
+ pop {r4-r5}
+ bx lr
+ENDPROC(chacha_4block_xor_neon)
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
new file mode 100644
index 0000000..14cc6b0
--- /dev/null
+++ b/arch/arm/crypto/chacha-neon-glue.c
@@ -0,0 +1,226 @@
+/*
+ * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+ int nrounds);
+asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+ int nrounds);
+asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
+
+static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds)
+{
+ u8 buf[CHACHA_BLOCK_SIZE];
+
+ while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+ chacha_4block_xor_neon(state, dst, src, nrounds);
+ bytes -= CHACHA_BLOCK_SIZE * 4;
+ src += CHACHA_BLOCK_SIZE * 4;
+ dst += CHACHA_BLOCK_SIZE * 4;
+ state[12] += 4;
+ }
+ while (bytes >= CHACHA_BLOCK_SIZE) {
+ chacha_block_xor_neon(state, dst, src, nrounds);
+ bytes -= CHACHA_BLOCK_SIZE;
+ src += CHACHA_BLOCK_SIZE;
+ dst += CHACHA_BLOCK_SIZE;
+ state[12]++;
+ }
+ if (bytes) {
+ memcpy(buf, src, bytes);
+ chacha_block_xor_neon(state, buf, buf, nrounds);
+ memcpy(dst, buf, bytes);
+ }
+}
+
+static int chacha_neon_stream_xor(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src,
+ unsigned int nbytes,
+ struct chacha_ctx *ctx, u8 *iv)
+{
+ struct blkcipher_walk walk;
+ u32 state[16];
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, CHACHA_BLOCK_SIZE);
+
+ crypto_chacha_init(state, ctx, iv);
+
+ while (walk.nbytes >= CHACHA_BLOCK_SIZE) {
+ kernel_neon_begin();
+ chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
+ rounddown(walk.nbytes, CHACHA_BLOCK_SIZE),
+ ctx->nrounds);
+ kernel_neon_end();
+ err = blkcipher_walk_done(desc, &walk,
+ walk.nbytes % CHACHA_BLOCK_SIZE);
+ }
+
+ if (walk.nbytes) {
+ kernel_neon_begin();
+ chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes, ctx->nrounds);
+ kernel_neon_end();
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ return err;
+}
+
+static int chacha_neon(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct chacha_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ u8 *iv = desc->info;
+
+ if (nbytes <= CHACHA_BLOCK_SIZE || !may_use_simd())
+ return crypto_chacha_crypt(desc, dst, src, nbytes);
+
+ return chacha_neon_stream_xor(desc, dst, src, nbytes, ctx, iv);
+}
+
+static int xchacha_neon(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct chacha_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ u8 *iv = desc->info;
+ struct chacha_ctx subctx;
+ u32 state[16];
+ u8 real_iv[16];
+
+ if (nbytes <= CHACHA_BLOCK_SIZE || !may_use_simd())
+ return crypto_xchacha_crypt(desc, dst, src, nbytes);
+
+ crypto_chacha_init(state, ctx, iv);
+
+ kernel_neon_begin();
+ hchacha_block_neon(state, subctx.key, ctx->nrounds);
+ kernel_neon_end();
+ subctx.nrounds = ctx->nrounds;
+
+ memcpy(&real_iv[0], iv + 24, 8);
+ memcpy(&real_iv[8], iv + 16, 8);
+ return chacha_neon_stream_xor(desc, dst, src, nbytes, &subctx, real_iv);
+}
+
+static struct crypto_alg algs[] = {
+ {
+ .cra_name = "chacha20",
+ .cra_driver_name = "chacha20-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha20_setkey,
+ .encrypt = chacha_neon,
+ .decrypt = chacha_neon,
+ },
+ },
+ }, {
+ .cra_name = "xchacha20",
+ .cra_driver_name = "xchacha20-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha20_setkey,
+ .encrypt = xchacha_neon,
+ .decrypt = xchacha_neon,
+ },
+ },
+ }, {
+ .cra_name = "xchacha12",
+ .cra_driver_name = "xchacha12-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha12_setkey,
+ .encrypt = xchacha_neon,
+ .decrypt = xchacha_neon,
+ },
+ },
+ },
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ return crypto_register_algs(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+ crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm/crypto/nh-neon-core.S b/arch/arm/crypto/nh-neon-core.S
new file mode 100644
index 0000000..434d80a
--- /dev/null
+++ b/arch/arm/crypto/nh-neon-core.S
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, NEON accelerated version
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .fpu neon
+
+ KEY .req r0
+ MESSAGE .req r1
+ MESSAGE_LEN .req r2
+ HASH .req r3
+
+ PASS0_SUMS .req q0
+ PASS0_SUM_A .req d0
+ PASS0_SUM_B .req d1
+ PASS1_SUMS .req q1
+ PASS1_SUM_A .req d2
+ PASS1_SUM_B .req d3
+ PASS2_SUMS .req q2
+ PASS2_SUM_A .req d4
+ PASS2_SUM_B .req d5
+ PASS3_SUMS .req q3
+ PASS3_SUM_A .req d6
+ PASS3_SUM_B .req d7
+ K0 .req q4
+ K1 .req q5
+ K2 .req q6
+ K3 .req q7
+ T0 .req q8
+ T0_L .req d16
+ T0_H .req d17
+ T1 .req q9
+ T1_L .req d18
+ T1_H .req d19
+ T2 .req q10
+ T2_L .req d20
+ T2_H .req d21
+ T3 .req q11
+ T3_L .req d22
+ T3_H .req d23
+
+.macro _nh_stride k0, k1, k2, k3
+
+ // Load next message stride
+ vld1.8 {T3}, [MESSAGE]!
+
+ // Load next key stride
+ vld1.32 {\k3}, [KEY]!
+
+ // Add message words to key words
+ vadd.u32 T0, T3, \k0
+ vadd.u32 T1, T3, \k1
+ vadd.u32 T2, T3, \k2
+ vadd.u32 T3, T3, \k3
+
+ // Multiply 32x32 => 64 and accumulate
+ vmlal.u32 PASS0_SUMS, T0_L, T0_H
+ vmlal.u32 PASS1_SUMS, T1_L, T1_H
+ vmlal.u32 PASS2_SUMS, T2_L, T2_H
+ vmlal.u32 PASS3_SUMS, T3_L, T3_H
+.endm
+
+/*
+ * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ * u8 hash[NH_HASH_BYTES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+ENTRY(nh_neon)
+
+ vld1.32 {K0,K1}, [KEY]!
+ vmov.u64 PASS0_SUMS, #0
+ vmov.u64 PASS1_SUMS, #0
+ vld1.32 {K2}, [KEY]!
+ vmov.u64 PASS2_SUMS, #0
+ vmov.u64 PASS3_SUMS, #0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ blt .Lloop4_done
+.Lloop4:
+ _nh_stride K0, K1, K2, K3
+ _nh_stride K1, K2, K3, K0
+ _nh_stride K2, K3, K0, K1
+ _nh_stride K3, K0, K1, K2
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ bge .Lloop4
+
+.Lloop4_done:
+ ands MESSAGE_LEN, MESSAGE_LEN, #63
+ beq .Ldone
+ _nh_stride K0, K1, K2, K3
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K1, K2, K3, K0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K2, K3, K0, K1
+
+.Ldone:
+ // Sum the accumulators for each pass, then store the sums to 'hash'
+ vadd.u64 T0_L, PASS0_SUM_A, PASS0_SUM_B
+ vadd.u64 T0_H, PASS1_SUM_A, PASS1_SUM_B
+ vadd.u64 T1_L, PASS2_SUM_A, PASS2_SUM_B
+ vadd.u64 T1_H, PASS3_SUM_A, PASS3_SUM_B
+ vst1.8 {T0-T1}, [HASH]
+ bx lr
+ENDPROC(nh_neon)
diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c
new file mode 100644
index 0000000..49aae87
--- /dev/null
+++ b/arch/arm/crypto/nhpoly1305-neon-glue.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ * (NEON accelerated version)
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/hash.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/module.h>
+
+asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ u8 hash[NH_HASH_BYTES]);
+
+/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
+static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES])
+{
+ nh_neon(key, message, message_len, (u8 *)hash);
+}
+
+static int nhpoly1305_neon_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
+{
+ if (srclen < 64 || !may_use_simd())
+ return crypto_nhpoly1305_update(desc, src, srclen);
+
+ do {
+ unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+
+ kernel_neon_begin();
+ crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
+ kernel_neon_end();
+ src += n;
+ srclen -= n;
+ } while (srclen);
+ return 0;
+}
+
+static struct shash_alg nhpoly1305_alg = {
+ .base.cra_name = "nhpoly1305",
+ .base.cra_driver_name = "nhpoly1305-neon",
+ .base.cra_priority = 200,
+ .base.cra_ctxsize = sizeof(struct nhpoly1305_key),
+ .base.cra_module = THIS_MODULE,
+ .digestsize = POLY1305_DIGEST_SIZE,
+ .init = crypto_nhpoly1305_init,
+ .update = nhpoly1305_neon_update,
+ .final = crypto_nhpoly1305_final,
+ .setkey = crypto_nhpoly1305_setkey,
+ .descsize = sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+ crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-neon");
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index f13ae15..d2315ff 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -112,8 +112,12 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
-/* This is the base location for PIE (ET_DYN with INTERP) loads. */
-#define ELF_ET_DYN_BASE 0x400000UL
+/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ use of this is to invoke "./ld.so someprog" to test out a new version of
+ the loader. We need to make sure that it is out of the way of the program
+ that it will "exec", and that there is sufficient room for the brk. */
+
+#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
/* When the program starts, a1 contains a pointer to a function to be
registered with atexit, as per the SVR4 ABI. A value of 0 means we
diff --git a/arch/arm/include/asm/fiq_glue.h b/arch/arm/include/asm/fiq_glue.h
new file mode 100644
index 0000000..a9e244f9
--- /dev/null
+++ b/arch/arm/include/asm/fiq_glue.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_FIQ_GLUE_H
+#define __ASM_FIQ_GLUE_H
+
+struct fiq_glue_handler {
+ void (*fiq)(struct fiq_glue_handler *h, void *regs, void *svc_sp);
+ void (*resume)(struct fiq_glue_handler *h);
+};
+typedef void (*fiq_return_handler_t)(void);
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler);
+int fiq_glue_set_return_handler(fiq_return_handler_t fiq_return);
+int fiq_glue_clear_return_handler(fiq_return_handler_t fiq_return);
+
+#ifdef CONFIG_FIQ_GLUE
+void fiq_glue_resume(void);
+#else
+static inline void fiq_glue_resume(void) {}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 370f7a7..4e9b957 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -3,6 +3,7 @@
#ifdef CONFIG_ARM_CPU_TOPOLOGY
+#include <linux/cpufreq.h>
#include <linux/cpumask.h>
struct cputopo_arm {
@@ -24,6 +25,14 @@ void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
const struct cpumask *cpu_coregroup_mask(int cpu);
+#ifdef CONFIG_CPU_FREQ
+#define arch_scale_freq_capacity cpufreq_scale_freq_capacity
+#define arch_scale_max_freq_capacity cpufreq_scale_max_freq_capacity
+#define arch_scale_min_freq_capacity cpufreq_scale_min_freq_capacity
+#endif
+#define arch_scale_cpu_capacity scale_cpu_capacity
+extern unsigned long scale_cpu_capacity(struct sched_domain *sd, int cpu);
+
#else
static inline void init_cpu_topology(void) { }
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f555bb3..683d923 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -18,7 +18,6 @@ struct undef_hook {
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
extern char __irqentry_text_start[];
@@ -27,12 +26,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 314100a..d67def5 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -423,6 +423,8 @@
#define __NR_pkey_mprotect (__NR_SYSCALL_BASE+394)
#define __NR_pkey_alloc (__NR_SYSCALL_BASE+395)
#define __NR_pkey_free (__NR_SYSCALL_BASE+396)
+#define __NR_pidfd_send_signal (__NR_SYSCALL_BASE+424)
+#define __NR_pidfd_open (__NR_SYSCALL_BASE+434)
/*
* The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 08030b1..4585cdf 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -406,6 +406,8 @@
CALL(sys_pkey_mprotect)
/* 395 */ CALL(sys_pkey_alloc)
CALL(sys_pkey_free)
+ CALL(sys_pidfd_send_signal)
+ CALL(sys_pidfd_open)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 178a2a9..8d6c751 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -12,6 +12,7 @@
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
+#include <asm/memory.h>
#ifdef CONFIG_NEED_RET_TO_USER
#include <mach/entry-macro.S>
@@ -36,6 +37,9 @@
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
bne fast_work_pending
@@ -63,6 +67,9 @@
UNWIND(.cantunwind )
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
beq no_work_pending
@@ -95,6 +102,9 @@
ret_slow_syscall:
disable_irq_notrace @ disable interrupts
ENTRY(ret_to_user_from_irq)
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
bne slow_work_pending
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 9232cae..f3c6622 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -140,6 +140,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
{
+ if (user_mode(regs))
+ return -1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return 0;
@@ -147,6 +149,8 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
{
+ if (user_mode(regs))
+ return -1;
compiled_break = 1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 91d2d5b..aae93b4 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -80,6 +80,7 @@ void arch_cpu_idle_prepare(void)
void arch_cpu_idle_enter(void)
{
+ idle_notifier_call_chain(IDLE_START);
ledtrig_cpu(CPU_LED_IDLE_START);
#ifdef CONFIG_PL310_ERRATA_769419
wmb();
@@ -89,6 +90,7 @@ void arch_cpu_idle_enter(void)
void arch_cpu_idle_exit(void)
{
ledtrig_cpu(CPU_LED_IDLE_END);
+ idle_notifier_call_chain(IDLE_END);
}
void __show_regs(struct pt_regs *regs)
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 3fa867a..d704df8 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -6,6 +6,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/reboot.h>
@@ -122,6 +123,31 @@ void machine_power_off(void)
pm_power_off();
}
+#ifdef CONFIG_ARM_FLUSH_CONSOLE_ON_RESTART
+void arm_machine_flush_console(void)
+{
+ printk("\n");
+ pr_emerg("Restarting %s\n", linux_banner);
+ if (console_trylock()) {
+ console_unlock();
+ return;
+ }
+
+ mdelay(50);
+
+ local_irq_disable();
+ if (!console_trylock())
+ pr_emerg("arm_restart: Console was locked! Busting\n");
+ else
+ pr_emerg("arm_restart: Console was locked!\n");
+ console_unlock();
+}
+#else
+void arm_machine_flush_console(void)
+{
+}
+#endif
+
/*
* Restart requires that the secondary CPUs stop performing any activity
* while the primary CPU resets the system. Systems with a single CPU can
@@ -138,6 +164,10 @@ void machine_restart(char *cmd)
local_irq_disable();
smp_send_stop();
+ /* Flush the console to make sure all the relevant messages make it
+ * out to the console drivers */
+ arm_machine_flush_console();
+
if (arm_pm_restart)
arm_pm_restart(reboot_mode, cmd);
else
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 0a066f0..7abc908 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/tracehook.h>
#include <linux/uprobes.h>
+#include <linux/syscalls.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
@@ -640,3 +641,9 @@ struct page *get_signal_page(void)
return page;
}
+
+/* Defer to generic check */
+asmlinkage void addr_limit_check_failed(void)
+{
+ addr_limit_user_check();
+}
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index ec279d1..07b0812 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -42,7 +42,7 @@
*/
static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+unsigned long scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
return per_cpu(cpu_scale, cpu);
}
@@ -153,6 +153,8 @@ static void __init parse_dt_topology(void)
}
+static const struct sched_group_energy * const cpu_core_energy(int cpu);
+
/*
* Look for a customed capacity of a CPU in the cpu_capacity table during the
* boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
@@ -160,10 +162,14 @@ static void __init parse_dt_topology(void)
*/
static void update_cpu_capacity(unsigned int cpu)
{
- if (!cpu_capacity(cpu))
- return;
+ unsigned long capacity = SCHED_CAPACITY_SCALE;
- set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+ if (cpu_core_energy(cpu)) {
+ int max_cap_idx = cpu_core_energy(cpu)->nr_cap_states - 1;
+ capacity = cpu_core_energy(cpu)->cap_states[max_cap_idx].cap;
+ }
+
+ set_capacity_scale(cpu, capacity);
pr_info("CPU%u: update cpu_capacity %lu\n",
cpu, arch_scale_cpu_capacity(NULL, cpu));
@@ -275,17 +281,138 @@ void store_cpu_topology(unsigned int cpuid)
cpu_topology[cpuid].socket_id, mpidr);
}
+/*
+ * ARM TC2 specific energy cost model data. There are no unit requirements for
+ * the data. Data can be normalized to any reference point, but the
+ * normalization must be consistent. That is, one bogo-joule/watt must be the
+ * same quantity for all data, but we don't care what it is.
+ */
+static struct idle_state idle_states_cluster_a7[] = {
+ { .power = 25 }, /* arch_cpu_idle() (active idle) = WFI */
+ { .power = 25 }, /* WFI */
+ { .power = 10 }, /* cluster-sleep-l */
+ };
+
+static struct idle_state idle_states_cluster_a15[] = {
+ { .power = 70 }, /* arch_cpu_idle() (active idle) = WFI */
+ { .power = 70 }, /* WFI */
+ { .power = 25 }, /* cluster-sleep-b */
+ };
+
+static struct capacity_state cap_states_cluster_a7[] = {
+ /* Cluster only power */
+ { .cap = 150, .power = 2967, }, /* 350 MHz */
+ { .cap = 172, .power = 2792, }, /* 400 MHz */
+ { .cap = 215, .power = 2810, }, /* 500 MHz */
+ { .cap = 258, .power = 2815, }, /* 600 MHz */
+ { .cap = 301, .power = 2919, }, /* 700 MHz */
+ { .cap = 344, .power = 2847, }, /* 800 MHz */
+ { .cap = 387, .power = 3917, }, /* 900 MHz */
+ { .cap = 430, .power = 4905, }, /* 1000 MHz */
+ };
+
+static struct capacity_state cap_states_cluster_a15[] = {
+ /* Cluster only power */
+ { .cap = 426, .power = 7920, }, /* 500 MHz */
+ { .cap = 512, .power = 8165, }, /* 600 MHz */
+ { .cap = 597, .power = 8172, }, /* 700 MHz */
+ { .cap = 682, .power = 8195, }, /* 800 MHz */
+ { .cap = 768, .power = 8265, }, /* 900 MHz */
+ { .cap = 853, .power = 8446, }, /* 1000 MHz */
+ { .cap = 938, .power = 11426, }, /* 1100 MHz */
+ { .cap = 1024, .power = 15200, }, /* 1200 MHz */
+ };
+
+static struct sched_group_energy energy_cluster_a7 = {
+ .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a7),
+ .idle_states = idle_states_cluster_a7,
+ .nr_cap_states = ARRAY_SIZE(cap_states_cluster_a7),
+ .cap_states = cap_states_cluster_a7,
+};
+
+static struct sched_group_energy energy_cluster_a15 = {
+ .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a15),
+ .idle_states = idle_states_cluster_a15,
+ .nr_cap_states = ARRAY_SIZE(cap_states_cluster_a15),
+ .cap_states = cap_states_cluster_a15,
+};
+
+static struct idle_state idle_states_core_a7[] = {
+ { .power = 0 }, /* arch_cpu_idle (active idle) = WFI */
+ { .power = 0 }, /* WFI */
+ { .power = 0 }, /* cluster-sleep-l */
+ };
+
+static struct idle_state idle_states_core_a15[] = {
+ { .power = 0 }, /* arch_cpu_idle (active idle) = WFI */
+ { .power = 0 }, /* WFI */
+ { .power = 0 }, /* cluster-sleep-b */
+ };
+
+static struct capacity_state cap_states_core_a7[] = {
+ /* Power per cpu */
+ { .cap = 150, .power = 187, }, /* 350 MHz */
+ { .cap = 172, .power = 275, }, /* 400 MHz */
+ { .cap = 215, .power = 334, }, /* 500 MHz */
+ { .cap = 258, .power = 407, }, /* 600 MHz */
+ { .cap = 301, .power = 447, }, /* 700 MHz */
+ { .cap = 344, .power = 549, }, /* 800 MHz */
+ { .cap = 387, .power = 761, }, /* 900 MHz */
+ { .cap = 430, .power = 1024, }, /* 1000 MHz */
+ };
+
+static struct capacity_state cap_states_core_a15[] = {
+ /* Power per cpu */
+ { .cap = 426, .power = 2021, }, /* 500 MHz */
+ { .cap = 512, .power = 2312, }, /* 600 MHz */
+ { .cap = 597, .power = 2756, }, /* 700 MHz */
+ { .cap = 682, .power = 3125, }, /* 800 MHz */
+ { .cap = 768, .power = 3524, }, /* 900 MHz */
+ { .cap = 853, .power = 3846, }, /* 1000 MHz */
+ { .cap = 938, .power = 5177, }, /* 1100 MHz */
+ { .cap = 1024, .power = 6997, }, /* 1200 MHz */
+ };
+
+static struct sched_group_energy energy_core_a7 = {
+ .nr_idle_states = ARRAY_SIZE(idle_states_core_a7),
+ .idle_states = idle_states_core_a7,
+ .nr_cap_states = ARRAY_SIZE(cap_states_core_a7),
+ .cap_states = cap_states_core_a7,
+};
+
+static struct sched_group_energy energy_core_a15 = {
+ .nr_idle_states = ARRAY_SIZE(idle_states_core_a15),
+ .idle_states = idle_states_core_a15,
+ .nr_cap_states = ARRAY_SIZE(cap_states_core_a15),
+ .cap_states = cap_states_core_a15,
+};
+
+/* sd energy functions */
+static inline
+const struct sched_group_energy * const cpu_cluster_energy(int cpu)
+{
+ return cpu_topology[cpu].socket_id ? &energy_cluster_a7 :
+ &energy_cluster_a15;
+}
+
+static inline
+const struct sched_group_energy * const cpu_core_energy(int cpu)
+{
+ return cpu_topology[cpu].socket_id ? &energy_core_a7 :
+ &energy_core_a15;
+}
+
static inline int cpu_corepower_flags(void)
{
- return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN;
+ return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN | \
+ SD_SHARE_CAP_STATES;
}
static struct sched_domain_topology_level arm_topology[] = {
#ifdef CONFIG_SCHED_MC
- { cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
- { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+ { cpu_coregroup_mask, cpu_corepower_flags, cpu_core_energy, SD_INIT_NAME(MC) },
#endif
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { cpu_cpu_mask, NULL, cpu_cluster_energy, SD_INIT_NAME(DIE) },
{ NULL, },
};
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 3e1cd04..1a326b5 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -20,7 +20,6 @@
bool "Kernel-based Virtual Machine (KVM) support"
depends on MMU && OF
select PREEMPT_NOTIFIERS
- select ANON_INODES
select ARM_GIC
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 2465995..11da0f5 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -270,6 +270,11 @@
* - end - virtual end address of region
*/
ENTRY(v6_dma_flush_range)
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+ sub r2, r1, r0
+ cmp r2, #CONFIG_CACHE_FLUSH_RANGE_LIMIT
+ bhi v6_dma_flush_dcache_all
+#endif
#ifdef CONFIG_DMA_CACHE_RWFO
ldrb r2, [r0] @ read for ownership
strb r2, [r0] @ write for ownership
@@ -292,6 +297,18 @@
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
ret lr
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+v6_dma_flush_dcache_all:
+ mov r0, #0
+#ifdef HARVARD_CACHE
+ mcr p15, 0, r0, c7, c14, 0 @ D cache clean+invalidate
+#else
+ mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate
+#endif
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mov pc, lr
+#endif
+
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 2539c8f..9453c92 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -276,10 +276,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
local_irq_enable();
/*
- * If we're in an interrupt or have no user
+ * If we're in an interrupt, or have no irqs, or have no user
* context, we must not take the fault..
*/
- if (faulthandler_disabled() || !mm)
+ if (faulthandler_disabled() || irqs_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 2eb8ae1..70ae7f4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -15,6 +15,7 @@
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_USE_CMPXCHG_LOCKREF
+ select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
@@ -109,6 +110,7 @@
select POWER_SUPPLY
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
+ select THREAD_INFO_IN_TASK
help
ARM 64-bit (AArch64) Linux support.
@@ -417,7 +419,7 @@
config ARM64_ERRATUM_843419
bool "Cortex-A53: 843419: A load or store might access an incorrect address"
- default y
+ default y if !LTO_CLANG
select ARM64_MODULE_CMODEL_LARGE if MODULES
help
This option links the kernel with '--fix-cortex-a53-843419' and
@@ -852,6 +854,14 @@
If unsure, say Y
endif
+config ARM64_SW_TTBR0_PAN
+ bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+ help
+ Enabling this option prevents the kernel from accessing
+ user-space memory directly by pointing TTBR0_EL1 to a reserved
+ zeroed area and reserved ASID. The user access routines
+ restore the valid TTBR0_EL1 temporarily.
+
menu "ARMv8.1 architectural features"
config ARM64_HW_AFDBM
@@ -977,7 +987,7 @@
config RANDOMIZE_MODULE_REGION_FULL
bool "Randomize the module region independently from the core kernel"
- depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
+ depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE && !LTO_CLANG
default y
help
Randomizes the location of the module region without considering the
@@ -1011,6 +1021,23 @@
entering them here. As a minimum, you should specify the the
root device (e.g. root=/dev/nfs).
+choice
+ prompt "Kernel command line type" if CMDLINE != ""
+ default CMDLINE_FROM_BOOTLOADER
+
+config CMDLINE_FROM_BOOTLOADER
+ bool "Use bootloader kernel arguments if available"
+ help
+ Uses the command-line options passed by the boot loader. If
+ the boot loader doesn't provide any, the default kernel command
+ string provided in CMDLINE will be used.
+
+config CMDLINE_EXTEND
+ bool "Extend bootloader kernel arguments"
+ help
+ The command-line arguments provided by the boot loader will be
+ appended to the default kernel command string.
+
config CMDLINE_FORCE
bool "Always use the default kernel command string"
help
@@ -1018,6 +1045,7 @@
loader passes other arguments to the kernel.
This is useful if you cannot or don't want to change the
command-line options your boot loader passes to the kernel.
+endchoice
config EFI_STUB
bool
@@ -1050,6 +1078,41 @@
However, even with this option, the resultant kernel should
continue to boot on existing non-UEFI platforms.
+config BUILD_ARM64_APPENDED_DTB_IMAGE
+ bool "Build a concatenated Image.gz/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated Image.gz and list of
+ DTBs to be built by default (instead of a standalone Image.gz.)
+ The image will built in arch/arm64/boot/Image.gz-dtb
+
+choice
+ prompt "Appended DTB Kernel Image name"
+ depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+ help
+ Enabling this option will cause a specific kernel image Image or
+ Image.gz to be used for final image creation.
+ The image will built in arch/arm64/boot/IMAGE-NAME-dtb
+
+ config IMG_GZ_DTB
+ bool "Image.gz-dtb"
+ config IMG_DTB
+ bool "Image-dtb"
+endchoice
+
+config BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME
+ string
+ depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+ default "Image.gz-dtb" if IMG_GZ_DTB
+ default "Image-dtb" if IMG_DTB
+
+config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated Image.gz-dtb.
+
endmenu
menu "Userspace binary formats"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 8d469aa..3894c52 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -26,8 +26,17 @@
ifeq ($(call ld-option, --fix-cortex-a53-843419),)
$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
else
+ ifeq ($(call gold-ifversion, -lt, 114000000, y), y)
+$(warning This version of GNU gold may generate incorrect code with --fix-cortex-a53-843419;\
+ see https://sourceware.org/bugzilla/show_bug.cgi?id=21491)
+ endif
LDFLAGS_vmlinux += --fix-cortex-a53-843419
endif
+else
+ ifeq ($(ld-name),gold)
+# Pass --no-fix-cortex-a53-843419 to ensure the erratum fix is disabled
+LDFLAGS += --no-fix-cortex-a53-843419
+ endif
endif
KBUILD_DEFCONFIG := defconfig
@@ -41,9 +50,17 @@
endif
endif
-KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr)
+ifeq ($(cc-name),clang)
+# This is a workaround for https://bugs.llvm.org/show_bug.cgi?id=30792.
+# TODO: revert when this is fixed in LLVM.
+KBUILD_CFLAGS += -mno-implicit-float
+else
+KBUILD_CFLAGS += -mgeneral-regs-only
+endif
+KBUILD_CFLAGS += $(lseinstr)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads)
+KBUILD_CFLAGS += -fno-pic
KBUILD_AFLAGS += $(lseinstr)
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
@@ -62,6 +79,10 @@
ifeq ($(CONFIG_ARM64_MODULE_CMODEL_LARGE), y)
KBUILD_CFLAGS_MODULE += -mcmodel=large
+ifeq ($(CONFIG_LTO_CLANG), y)
+# Code model is not stored in LLVM IR, so we need to pass it also to LLVMgold
+KBUILD_LDFLAGS_MODULE += -plugin-opt=-code-model=large
+endif
endif
ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
@@ -80,6 +101,10 @@
TEXT_OFFSET := 0x00080000
endif
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS += $(call cc-disable-warning, asm-operand-widths)
+endif
+
# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61)
# in 32-bit arithmetic
KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \
@@ -98,7 +123,12 @@
core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
# Default target when executing plain make
+ifeq ($(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME))
+else
KBUILD_IMAGE := Image.gz
+endif
+
KBUILD_DTBS := dtbs
all: $(KBUILD_IMAGE) $(KBUILD_DTBS)
@@ -125,6 +155,9 @@
dtbs_install:
$(Q)$(MAKE) $(dtbinst)=$(boot)/dts
+Image-dtb Image.gz-dtb: vmlinux scripts dtbs
+ $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
PHONY += vdso_install
vdso_install:
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore
index 8dab0bb..34e3520 100644
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@@ -1,2 +1,4 @@
Image
+Image-dtb
Image.gz
+Image.gz-dtb
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index cd34148..0921d5e 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -14,16 +14,29 @@
# Based on the ia64 boot/Makefile.
#
+include $(srctree)/arch/arm64/boot/dts/Makefile
+
OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+
$(obj)/Image: vmlinux FORCE
$(call if_changed,objcopy)
$(obj)/Image.bz2: $(obj)/Image FORCE
$(call if_changed,bzip2)
+$(obj)/Image-dtb: $(obj)/Image $(DTB_OBJS) FORCE
+ $(call if_changed,cat)
+
$(obj)/Image.gz: $(obj)/Image FORCE
$(call if_changed,gzip)
@@ -36,6 +49,9 @@
$(obj)/Image.lzo: $(obj)/Image FORCE
$(call if_changed,lzo)
+$(obj)/Image.gz-dtb: $(obj)/Image.gz $(DTB_OBJS) FORCE
+ $(call if_changed,cat)
+
install:
$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
$(obj)/Image System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 6684f97..7ad2cf0 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -28,3 +28,17 @@
dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(foreach d,$(dts-dirs), $(wildcard $(dtstree)/$(d)/*.dts)))
always := $(dtb-y)
+
+targets += dtbs
+
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+targets += $(DTB_LIST)
+
+dtbs: $(addprefix $(obj)/, $(DTB_LIST))
+
+clean-files := dts/*.dtb *.dtb
diff --git a/arch/arm64/configs/cuttlefish_defconfig b/arch/arm64/configs/cuttlefish_defconfig
new file mode 100644
index 0000000..54b9b78
--- /dev/null
+++ b/arch/arm64/configs/cuttlefish_defconfig
@@ -0,0 +1,455 @@
+# CONFIG_FHANDLE is not set
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_PSI=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+# CONFIG_PROC_PID_CPUSET is not set
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_SCHEDTUNE=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_SCHED_TUNE=y
+CONFIG_DEFAULT_USE_ENERGY_AWARE=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+CONFIG_SGETMASK_SYSCALL=y
+# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_KALLSYMS_ALL=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
+CONFIG_CC_STACKPROTECTOR_STRONG=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_PCI=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PREEMPT=y
+CONFIG_HZ_100=y
+# CONFIG_SPARSEMEM_VMEMMAP is not set
+CONFIG_ZSMALLOC=y
+CONFIG_SECCOMP=y
+CONFIG_PARAVIRT=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_SWP_EMULATION=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_ARM64_SW_TTBR0_PAN=y
+CONFIG_ARM64_LSE_ATOMICS=y
+CONFIG_RANDOMIZE_BASE=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_COMPAT=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_CPU_IDLE=y
+CONFIG_ARM_CPUIDLE=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+CONFIG_CPUFREQ_DT=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM_SCPI_CPUFREQ=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_XFRM_INTERFACE=y
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPVTI=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
+CONFIG_INET_UDP_DIAG=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_VTI=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CT=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_RPFILTER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_L2TP=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_CLS_BPF=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_VSOCKETS=y
+CONFIG_VIRTIO_VSOCKETS=y
+CONFIG_BPF_JIT=y
+CONFIG_CFG80211=y
+# CONFIG_CFG80211_DEFAULT_PS is not set
+CONFIG_MAC80211=y
+# CONFIG_MAC80211_RC_MINSTREL is not set
+CONFIG_RFKILL=y
+# CONFIG_UEVENT_HELPER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+CONFIG_DEBUG_DEVRES=y
+CONFIG_OF_UNITTEST=y
+CONFIG_ZRAM=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_LOOP_MIN_COUNT=16
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_UID_SYS_STATS=y
+CONFIG_SCSI=y
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=y
+CONFIG_SCSI_VIRTIO=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_SNAPSHOT=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_DM_VERITY_AVB=y
+CONFIG_DM_BOW=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_NETCONSOLE_DYNAMIC=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_ETHERNET is not set
+CONFIG_PHYLIB=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPTP=y
+CONFIG_PPPOL2TP=y
+CONFIG_USB_RTL8152=y
+CONFIG_USB_USBNET=y
+# CONFIG_USB_NET_AX8817X is not set
+# CONFIG_USB_NET_AX88179_178A is not set
+# CONFIG_USB_NET_CDCETHER is not set
+# CONFIG_USB_NET_CDC_NCM is not set
+# CONFIG_USB_NET_NET1080 is not set
+# CONFIG_USB_NET_CDC_SUBSET is not set
+# CONFIG_USB_NET_ZAURUS is not set
+# CONFIG_WLAN_VENDOR_ADMTEK is not set
+# CONFIG_WLAN_VENDOR_ATH is not set
+# CONFIG_WLAN_VENDOR_ATMEL is not set
+# CONFIG_WLAN_VENDOR_BROADCOM is not set
+# CONFIG_WLAN_VENDOR_CISCO is not set
+# CONFIG_WLAN_VENDOR_INTEL is not set
+# CONFIG_WLAN_VENDOR_INTERSIL is not set
+# CONFIG_WLAN_VENDOR_MARVELL is not set
+# CONFIG_WLAN_VENDOR_MEDIATEK is not set
+# CONFIG_WLAN_VENDOR_RALINK is not set
+# CONFIG_WLAN_VENDOR_REALTEK is not set
+# CONFIG_WLAN_VENDOR_RSI is not set
+# CONFIG_WLAN_VENDOR_ST is not set
+# CONFIG_WLAN_VENDOR_TI is not set
+# CONFIG_WLAN_VENDOR_ZYDAS is not set
+CONFIG_VIRT_WIFI=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_INPUT_TABLET=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=48
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=y
+# CONFIG_HW_RANDOM_CAVIUM is not set
+# CONFIG_DEVPORT is not set
+# CONFIG_I2C_COMPAT is not set
+# CONFIG_I2C_HELPER_AUTO is not set
+# CONFIG_HWMON is not set
+CONFIG_THERMAL=y
+CONFIG_CPU_THERMAL=y
+CONFIG_MEDIA_SUPPORT=y
+# CONFIG_DVB_TUNER_DIB0070 is not set
+# CONFIG_DVB_TUNER_DIB0090 is not set
+# CONFIG_VGA_ARB is not set
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_HRTIMER=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_VERBOSE_PROCFS is not set
+# CONFIG_SND_DRIVERS is not set
+CONFIG_SND_INTEL8X0=y
+# CONFIG_SND_USB is not set
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_ACC=y
+CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y
+CONFIG_USB_CONFIGFS_UEVENT=y
+CONFIG_USB_CONFIGFS_F_MIDI=y
+CONFIG_MMC=y
+# CONFIG_PWRSEQ_EMMC is not set
+# CONFIG_PWRSEQ_SIMPLE is not set
+# CONFIG_MMC_BLOCK is not set
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_SYSTOHC is not set
+CONFIG_RTC_DRV_PL030=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_VIRTIO_PCI=y
+# CONFIG_VIRTIO_PCI_LEGACY is not set
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_INPUT=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_VSOC=y
+CONFIG_ION=y
+CONFIG_COMMON_CLK_SCPI=y
+# CONFIG_COMMON_CLK_XGENE is not set
+CONFIG_MAILBOX=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ARM_SCPI_PROTOCOL=y
+# CONFIG_ARM_SCPI_POWER_DOMAIN is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
+CONFIG_F2FS_FS=y
+CONFIG_F2FS_FS_SECURITY=y
+CONFIG_F2FS_FS_ENCRYPTION=y
+# CONFIG_DNOTIFY is not set
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_FUSE_FS=y
+CONFIG_OVERLAY_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+# CONFIG_EFIVAR_FS is not set
+CONFIG_SDCARD_FS=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=65536
+CONFIG_HARDENED_USERCOPY=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_CRYPTO_ADIANTUM=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_LZ4=y
+CONFIG_CRYPTO_ZSTD=y
+CONFIG_CRYPTO_ANSI_CPRNG=y
+CONFIG_XZ_DEC=y
diff --git a/arch/arm64/configs/ranchu64_defconfig b/arch/arm64/configs/ranchu64_defconfig
new file mode 100644
index 0000000..4195a35
--- /dev/null
+++ b/arch/arm64/configs/ranchu64_defconfig
@@ -0,0 +1,311 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_ARCH_MMAP_RND_BITS=24
+CONFIG_ARCH_MMAP_RND_COMPAT_BITS=16
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_NR_CPUS=4
+CONFIG_PREEMPT=y
+CONFIG_KSM=y
+CONFIG_SECCOMP=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_SWP_EMULATION=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_CMDLINE="console=ttyAMA0"
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_COMPAT=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_LRO is not set
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_RPFILTER=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_TARGET_ECN=y
+CONFIG_IP_NF_TARGET_TTL=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_AH=y
+CONFIG_IP6_NF_MATCH_EUI64=y
+CONFIG_IP6_NF_MATCH_FRAG=y
+CONFIG_IP6_NF_MATCH_OPTS=y
+CONFIG_IP6_NF_MATCH_HL=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_MATCH_MH=y
+CONFIG_IP6_NF_MATCH_RT=y
+CONFIG_IP6_NF_TARGET_HL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_BRIDGE=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_SCSI=y
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_NETDEVICES=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+CONFIG_SMC91X=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_SERIO_SERPORT is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_BATTERY_GOLDFISH=y
+# CONFIG_HWMON is not set
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_FB=y
+CONFIG_FB_GOLDFISH=y
+CONFIG_FB_SIMPLE=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+# CONFIG_USB_SUPPORT is not set
+CONFIG_RTC_CLASS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION=y
+CONFIG_GOLDFISH_AUDIO=y
+CONFIG_GOLDFISH=y
+CONFIG_GOLDFISH_PIPE=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_FUSE_FS=y
+CONFIG_CUSE=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_PANIC_TIMEOUT=5
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+# CONFIG_FTRACE is not set
+CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_DEBUG_RODATA=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index abb79b3..550e02a 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -18,7 +18,8 @@
ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
-CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+aes-ce-cipher-y := aes-ce-cipher-glue.o aes-ce-cipher-core.o
+CFLAGS_aes-ce-cipher-core.o += -march=armv8-a+crypto -Wa,-march=armv8-a+crypto $(DISABLE_LTO)
obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher-core.c
similarity index 77%
rename from arch/arm64/crypto/aes-ce-cipher.c
rename to arch/arm64/crypto/aes-ce-cipher-core.c
index 50d9fe1..9f41917 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher-core.c
@@ -1,5 +1,5 @@
/*
- * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ * aes-ce-cipher-core.c - core AES cipher using ARMv8 Crypto Extensions
*
* Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
*
@@ -10,16 +10,10 @@
#include <asm/neon.h>
#include <crypto/aes.h>
-#include <linux/cpufeature.h>
#include <linux/crypto.h>
-#include <linux/module.h>
#include "aes-ce-setkey.h"
-MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-
struct aes_block {
u8 b[AES_BLOCK_SIZE];
};
@@ -36,7 +30,7 @@ static int num_rounds(struct crypto_aes_ctx *ctx)
return 6 + ctx->key_length / 4;
}
-static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
{
struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
struct aes_block *out = (struct aes_block *)dst;
@@ -81,7 +75,7 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
kernel_neon_end();
}
-static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
{
struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
struct aes_block *out = (struct aes_block *)dst;
@@ -223,48 +217,3 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
return 0;
}
EXPORT_SYMBOL(ce_aes_expandkey);
-
-int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
- unsigned int key_len)
-{
- struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
- int ret;
-
- ret = ce_aes_expandkey(ctx, in_key, key_len);
- if (!ret)
- return 0;
-
- tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
- return -EINVAL;
-}
-EXPORT_SYMBOL(ce_aes_setkey);
-
-static struct crypto_alg aes_alg = {
- .cra_name = "aes",
- .cra_driver_name = "aes-ce",
- .cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
- .cra_blocksize = AES_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_module = THIS_MODULE,
- .cra_cipher = {
- .cia_min_keysize = AES_MIN_KEY_SIZE,
- .cia_max_keysize = AES_MAX_KEY_SIZE,
- .cia_setkey = ce_aes_setkey,
- .cia_encrypt = aes_cipher_encrypt,
- .cia_decrypt = aes_cipher_decrypt
- }
-};
-
-static int __init aes_mod_init(void)
-{
- return crypto_register_alg(&aes_alg);
-}
-
-static void __exit aes_mod_exit(void)
-{
- crypto_unregister_alg(&aes_alg);
-}
-
-module_cpu_feature_match(AES, aes_mod_init);
-module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce-cipher-glue.c b/arch/arm64/crypto/aes-ce-cipher-glue.c
new file mode 100644
index 0000000..442949e
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher-glue.c
@@ -0,0 +1,83 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+extern void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]);
+extern void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]);
+
+#ifdef CONFIG_CFI_CLANG
+static inline void __cfi_aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ aes_cipher_encrypt(tfm, dst, src);
+}
+
+static inline void __cfi_aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ aes_cipher_decrypt(tfm, dst, src);
+}
+
+#define aes_cipher_encrypt __cfi_aes_cipher_encrypt
+#define aes_cipher_decrypt __cfi_aes_cipher_decrypt
+#endif
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int ret;
+
+ ret = ce_aes_expandkey(ctx, in_key, key_len);
+ if (!ret)
+ return 0;
+
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+EXPORT_SYMBOL(ce_aes_setkey);
+
+static struct crypto_alg aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-ce",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_cipher = {
+ .cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = ce_aes_setkey,
+ .cia_encrypt = aes_cipher_encrypt,
+ .cia_decrypt = aes_cipher_decrypt
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 1b7b468..3431bb5 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -28,6 +28,14 @@ struct sha1_ce_state {
asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
int blocks);
+#ifdef CONFIG_CFI_CLANG
+static inline void __cfi_sha1_ce_transform(struct sha1_state *sst,
+ u8 const *src, int blocks)
+{
+ sha1_ce_transform((struct sha1_ce_state *)sst, src, blocks);
+}
+#define sha1_ce_transform __cfi_sha1_ce_transform
+#endif
const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize);
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 356ca93..42d96dd 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -28,6 +28,14 @@ struct sha256_ce_state {
asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
int blocks);
+#ifdef CONFIG_CFI_CLANG
+static inline void __cfi_sha2_ce_transform(struct sha256_state *sst,
+ u8 const *src, int blocks)
+{
+ sha2_ce_transform((struct sha256_ce_state *)sst, src, blocks);
+}
+#define sha2_ce_transform __cfi_sha2_ce_transform
+#endif
const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
sst.count);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 44e1d7f..28196b1 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += bugs.h
generic-y += clkdev.h
generic-y += cputime.h
-generic-y += current.h
generic-y += delay.h
generic-y += div64.h
generic-y += dma.h
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 3f85bbc..148849c 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -42,6 +42,15 @@
msr daifclr, #2
.endm
+ .macro save_and_disable_irq, flags
+ mrs \flags, daif
+ msr daifset, #2
+ .endm
+
+ .macro restore_irq, flags
+ msr daif, \flags
+ .endm
+
/*
* Enable and disable debug exceptions.
*/
@@ -451,6 +460,13 @@ alternative_endif
movk \reg, :abs_g0_nc:\val
.endm
+/*
+ * Return the current thread_info.
+ */
+ .macro get_thread_info, rd
+ mrs \rd, sp_el0
+ .endm
+
.macro pte_to_phys, phys, pte
and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
.endm
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e7bef3d..353e400 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -222,6 +222,12 @@ static inline bool system_supports_mixed_endian_el0(void)
return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
}
+static inline bool system_uses_ttbr0_pan(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
+ !cpus_have_cap(ARM64_HAS_PAN);
+}
+
#define ARM64_SSBD_UNKNOWN -1
#define ARM64_SSBD_FORCE_DISABLE 0
#define ARM64_SSBD_KERNEL 1
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
new file mode 100644
index 0000000..86c4041
--- /dev/null
+++ b/arch/arm64/include/asm/current.h
@@ -0,0 +1,30 @@
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+ unsigned long sp_el0;
+
+ asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+ return (struct task_struct *)sp_el0;
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
+
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 65db124..e589811 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -1,6 +1,7 @@
#ifndef _ASM_EFI_H
#define _ASM_EFI_H
+#include <asm/cpufeature.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/neon.h>
@@ -82,7 +83,30 @@ static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
static inline void efi_set_pgd(struct mm_struct *mm)
{
- switch_mm(NULL, mm, NULL);
+ __switch_mm(mm);
+
+ if (system_uses_ttbr0_pan()) {
+ if (mm != current->active_mm) {
+ /*
+ * Update the current thread's saved ttbr0 since it is
+ * restored as part of a return from exception. Enable
+ * access to the valid TTBR0_EL1 and invoke the errata
+ * workaround directly since there is no return from
+ * exception when invoking the EFI run-time services.
+ */
+ update_saved_ttbr0(current, mm);
+ uaccess_ttbr0_enable();
+ post_ttbr_update_workaround();
+ } else {
+ /*
+ * Defer the switch to the current thread's TTBR0_EL1
+ * until uaccess_enable(). Restore the current
+ * thread's saved ttbr0 corresponding to its active_mm
+ */
+ uaccess_ttbr0_disable();
+ update_saved_ttbr0(current, current->active_mm);
+ }
+ }
}
void efi_virtmap_load(void);
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 1fb0230..40a8a94 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -169,7 +169,7 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#ifdef CONFIG_COMPAT
/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
-#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL
+#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3)
/* AArch32 registers. */
#define COMPAT_ELF_NGREG 18
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d14c478..85997c0 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -175,6 +175,12 @@
#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
ESR_ELx_SYS64_ISS_DIR_READ)
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCT (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CNTFRQ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 0, 14, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 86a4345..e69df28 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -21,15 +21,12 @@
#include <linux/futex.h>
#include <linux/uaccess.h>
-#include <asm/alternative.h>
-#include <asm/cpufeature.h>
#include <asm/errno.h>
-#include <asm/sysreg.h>
#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
+do { \
+ uaccess_enable(); \
asm volatile( \
- ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \
- CONFIG_ARM64_PAN) \
" prfm pstl1strm, %2\n" \
"1: ldxr %w1, %2\n" \
insn "\n" \
@@ -44,11 +41,11 @@
" .popsection\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
- ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \
- CONFIG_ARM64_PAN) \
: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \
: "r" (oparg), "Ir" (-EFAULT) \
- : "memory")
+ : "memory"); \
+ uaccess_disable(); \
+} while (0)
static inline int
arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
@@ -102,8 +99,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
return -EFAULT;
uaddr = __uaccess_mask_ptr(_uaddr);
+ uaccess_enable();
asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
" prfm pstl1strm, %2\n"
"1: ldxr %w1, %2\n"
" sub %w3, %w1, %w4\n"
@@ -118,10 +115,10 @@ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
" .popsection\n"
_ASM_EXTABLE(1b, 4b)
_ASM_EXTABLE(2b, 4b)
-ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
: "memory");
+ uaccess_disable();
*uval = val;
return ret;
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9510ace..b6b167a 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -77,7 +77,11 @@ static inline void decode_ctrl_reg(u32 reg,
/* Lengths */
#define ARM_BREAKPOINT_LEN_1 0x1
#define ARM_BREAKPOINT_LEN_2 0x3
+#define ARM_BREAKPOINT_LEN_3 0x7
#define ARM_BREAKPOINT_LEN_4 0xf
+#define ARM_BREAKPOINT_LEN_5 0x1f
+#define ARM_BREAKPOINT_LEN_6 0x3f
+#define ARM_BREAKPOINT_LEN_7 0x7f
#define ARM_BREAKPOINT_LEN_8 0xff
/* Kernel stepping */
@@ -119,7 +123,7 @@ struct perf_event;
struct pmu;
extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
- int *gen_len, int *gen_type);
+ int *gen_len, int *gen_type, int *offset);
extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 7e51d1b..7803343 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -19,6 +19,7 @@
#ifndef __ASM_KERNEL_PGTABLE_H
#define __ASM_KERNEL_PGTABLE_H
+#include <asm/pgtable.h>
#include <asm/sparsemem.h>
/*
@@ -54,6 +55,12 @@
#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+#define RESERVED_TTBR0_SIZE (PAGE_SIZE)
+#else
+#define RESERVED_TTBR0_SIZE (0)
+#endif
+
/* Initial memory map size */
#if ARM64_SWAPPER_USES_SECTION_MAPS
#define SWAPPER_BLOCK_SHIFT SECTION_SHIFT
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index b18e852..36d6758 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -29,7 +29,9 @@
({ \
u64 reg; \
asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
- "mrs_s %0, " __stringify(r##vh),\
+ DEFINE_MRS_S \
+ "mrs_s %0, " __stringify(r##vh) "\n"\
+ UNDEFINE_MRS_S, \
ARM64_HAS_VIRT_HOST_EXTN) \
: "=r" (reg)); \
reg; \
@@ -39,7 +41,9 @@
do { \
u64 __val = (u64)(v); \
asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
- "msr_s " __stringify(r##vh) ", %x0",\
+ DEFINE_MSR_S \
+ "msr_s " __stringify(r##vh) ", %x0\n"\
+ UNDEFINE_MSR_S, \
ARM64_HAS_VIRT_HOST_EXTN) \
: : "rZ" (__val)); \
} while (0)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index ff72165..3ee30c5 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -47,7 +47,7 @@
* If the page is in the bottom half, we have to use the top half. If
* the page is in the top half, we have to use the bottom half:
*
- * T = __virt_to_phys(__hyp_idmap_text_start)
+ * T = __pa_symbol(__hyp_idmap_text_start)
* if (T & BIT(VA_BITS - 1))
* HYP_VA_MIN = 0 //idmap in upper half
* else
@@ -290,7 +290,7 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
}
-#define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x))
+#define kvm_virt_to_phys(x) __pa_symbol(x)
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index fc756e2..c5a0d2e 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -16,7 +16,12 @@
#else /* __ASSEMBLER__ */
+#ifdef CONFIG_LTO_CLANG
+#define __LSE_PREAMBLE ".arch armv8-a+lse\n"
+#else
__asm__(".arch_extension lse");
+#define __LSE_PREAMBLE
+#endif
/* Move the ll/sc atomics out-of-line */
#define __LL_SC_INLINE
@@ -29,7 +34,7 @@ __asm__(".arch_extension lse");
/* In-line patching at runtime */
#define ARM64_LSE_ATOMIC_INSN(llsc, lse) \
- ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+ ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS)
#endif /* __ASSEMBLER__ */
#else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ba917be..3450209 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -152,6 +152,11 @@ extern u64 kimage_vaddr;
/* the offset between the kernel virtual and physical mappings */
extern u64 kimage_voffset;
+static inline unsigned long kaslr_offset(void)
+{
+ return kimage_vaddr - KIMAGE_VADDR;
+}
+
/*
* Allow all memory at the discovery stage. We will clip it later.
*/
@@ -192,6 +197,7 @@ static inline void *phys_to_virt(phys_addr_t x)
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys(x))
+#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x))
/*
* virt_to_page(k) convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 6ac34c7..18b9f15 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -16,7 +16,9 @@
#ifndef __ASM_MMU_H
#define __ASM_MMU_H
+
#define USER_ASID_FLAG (UL(1) << 48)
+#define TTBR_ASID_MASK (UL(0xffff) << 48)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b96c4799..cb6902c 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -23,6 +23,7 @@
#include <linux/sched.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/proc-fns.h>
#include <asm-generic/mm_hooks.h>
#include <asm/cputype.h>
@@ -44,7 +45,7 @@ static inline void contextidr_thread_switch(struct task_struct *next)
*/
static inline void cpu_set_reserved_ttbr0(void)
{
- unsigned long ttbr = virt_to_phys(empty_zero_page);
+ unsigned long ttbr = __pa_symbol(empty_zero_page);
write_sysreg(ttbr, ttbr0_el1);
isb();
@@ -110,7 +111,7 @@ static inline void cpu_uninstall_idmap(void)
local_flush_tlb_all();
cpu_set_default_tcr_t0sz();
- if (mm != &init_mm)
+ if (mm != &init_mm && !system_uses_ttbr0_pan())
cpu_switch_mm(mm->pgd, mm);
}
@@ -120,14 +121,14 @@ static inline void cpu_install_idmap(void)
local_flush_tlb_all();
cpu_set_idmap_tcr_t0sz();
- cpu_switch_mm(idmap_pg_dir, &init_mm);
+ cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
}
/*
* Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
* avoiding the possibility of conflicting TLB entries being allocated.
*/
-static inline void cpu_replace_ttbr1(pgd_t *pgd)
+static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgd)
{
typedef void (ttbr_replace_func)(phys_addr_t);
extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -135,7 +136,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgd)
phys_addr_t pgd_phys = virt_to_phys(pgd);
- replace_phys = (void *)virt_to_phys(idmap_cpu_replace_ttbr1);
+ replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
cpu_install_idmap();
replace_phys(pgd_phys);
@@ -156,35 +157,43 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; })
-/*
- * This is called when "tsk" is about to enter lazy TLB mode.
- *
- * mm: describes the currently active mm context
- * tsk: task which is entering lazy tlb
- * cpu: cpu number which is entering lazy tlb
- *
- * tsk->mm will be NULL
- */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+ struct mm_struct *mm)
+{
+ u64 ttbr;
+
+ if (!system_uses_ttbr0_pan())
+ return;
+
+ if (mm == &init_mm)
+ ttbr = __pa_symbol(empty_zero_page);
+ else
+ ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
+
+ WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
+}
+#else
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+ struct mm_struct *mm)
+{
+}
+#endif
+
static inline void
enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
+ /*
+ * We don't actually care about the ttbr0 mapping, so point it at the
+ * zero page.
+ */
+ update_saved_ttbr0(tsk, &init_mm);
}
-/*
- * This is the actual mm switch as far as the scheduler
- * is concerned. No registers are touched. We avoid
- * calling the CPU specific function when the mm hasn't
- * actually changed.
- */
-static inline void
-switch_mm(struct mm_struct *prev, struct mm_struct *next,
- struct task_struct *tsk)
+static inline void __switch_mm(struct mm_struct *next)
{
unsigned int cpu = smp_processor_id();
- if (prev == next)
- return;
-
/*
* init_mm.pgd does not contain any user mappings and it is always
* active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -197,9 +206,26 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
check_and_switch_context(next, cpu);
}
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ if (prev != next)
+ __switch_mm(next);
+
+ /*
+ * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
+ * value may have not been initialised yet (activate_mm caller) or the
+ * ASID has changed since the last run (following the context switch
+ * of another thread of the same process).
+ */
+ update_saved_ttbr0(tsk, next);
+}
+
#define deactivate_mm(tsk,mm) do { } while (0)
-#define activate_mm(prev,next) switch_mm(prev, next, NULL)
+#define activate_mm(prev,next) switch_mm(prev, next, current)
void verify_cpu_asid_bits(void);
+void post_ttbr_update_workaround(void);
#endif
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 4724b8f..1abad23 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,7 @@
#ifndef __ASM_PERCPU_H
#define __ASM_PERCPU_H
+#include <asm/stack_pointer.h>
#include <asm/alternative.h>
static inline void set_my_cpu_offset(unsigned long off)
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 38b6a2b..8d5cbec 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -17,6 +17,8 @@
#ifndef __ASM_PERF_EVENT_H
#define __ASM_PERF_EVENT_H
+#include <asm/stack_pointer.h>
+
#define ARMV8_PMU_MAX_COUNTERS 32
#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 60e92da..4fb6ac9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -52,7 +52,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
* for zero-mapped memory areas etc..
*/
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) pfn_to_page(PHYS_PFN(__pa(empty_zero_page)))
+#define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page))
#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte))
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index eeaa975..81abea0 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -22,8 +22,6 @@
#define AARCH32_KERN_SIGRET_CODE_OFFSET 0x500
-extern const compat_ulong_t aarch32_sigret_code[6];
-
int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs);
int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 0226447..d050d72 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -29,11 +29,22 @@
#ifndef __ASSEMBLY__
+#include <asm/percpu.h>
+
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/thread_info.h>
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
+
+/*
+ * We don't use this_cpu_read(cpu_number) as that has implicit writes to
+ * preempt_count, and associated (compiler) barriers, that we'd like to avoid
+ * the expense of. If we're preemptible, the value can be stale at use anyway.
+ * And we can't use this_cpu_ptr() either, as that winds up recursing back
+ * here under CONFIG_DEBUG_PREEMPT=y.
+ */
+#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number))
struct seq_file;
@@ -73,6 +84,7 @@ asmlinkage void secondary_start_kernel(void);
*/
struct secondary_data {
void *stack;
+ struct task_struct *task;
long status;
};
diff --git a/arch/arm64/include/asm/stack_pointer.h b/arch/arm64/include/asm/stack_pointer.h
new file mode 100644
index 0000000..ffcdf74
--- /dev/null
+++ b/arch/arm64/include/asm/stack_pointer.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_STACK_POINTER_H
+#define __ASM_STACK_POINTER_H
+
+/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+#endif /* __ASM_STACK_POINTER_H */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index b8a313f..de5600f 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -1,7 +1,7 @@
#ifndef __ASM_SUSPEND_H
#define __ASM_SUSPEND_H
-#define NR_CTX_REGS 10
+#define NR_CTX_REGS 12
#define NR_CALLEE_SAVED_REGS 12
/*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 88bbe36..3ae4418 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -109,6 +109,10 @@
#define SCTLR_EL1_CP15BEN (1 << 5)
/* id_aa64isar0 */
+#define ID_AA64ISAR0_DP_SHIFT 44
+#define ID_AA64ISAR0_SM4_SHIFT 40
+#define ID_AA64ISAR0_SM3_SHIFT 36
+#define ID_AA64ISAR0_SHA3_SHIFT 32
#define ID_AA64ISAR0_RDM_SHIFT 28
#define ID_AA64ISAR0_ATOMICS_SHIFT 20
#define ID_AA64ISAR0_CRC32_SHIFT 16
@@ -246,20 +250,39 @@
#include <linux/types.h>
-asm(
-" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
-" .equ .L__reg_num_x\\num, \\num\n"
-" .endr\n"
+#define __DEFINE_MRS_MSR_S_REGNUM \
+" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+" .equ .L__reg_num_x\\num, \\num\n" \
+" .endr\n" \
" .equ .L__reg_num_xzr, 31\n"
-"\n"
-" .macro mrs_s, rt, sreg\n"
-" .inst 0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n"
+
+#define DEFINE_MRS_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro mrs_s, rt, sreg\n" \
+" .inst 0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n" \
" .endm\n"
-"\n"
-" .macro msr_s, sreg, rt\n"
-" .inst 0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n"
+
+#define DEFINE_MSR_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro msr_s, sreg, rt\n" \
+" .inst 0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n" \
" .endm\n"
-);
+
+#define UNDEFINE_MRS_S \
+" .purgem mrs_s\n"
+
+#define UNDEFINE_MSR_S \
+" .purgem msr_s\n"
+
+#define __mrs_s(r, v) \
+ DEFINE_MRS_S \
+" mrs_s %0, " __stringify(r) "\n" \
+ UNDEFINE_MRS_S : "=r" (v)
+
+#define __msr_s(r, v) \
+ DEFINE_MSR_S \
+" msr_s " __stringify(r) ", %x0\n" \
+ UNDEFINE_MSR_S : : "rZ" (v)
/*
* Unlike read_cpuid, calls to read_sysreg are never expected to be
@@ -285,15 +308,15 @@ asm(
* For registers without architectural names, or simply unsupported by
* GAS.
*/
-#define read_sysreg_s(r) ({ \
- u64 __val; \
- asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \
- __val; \
+#define read_sysreg_s(r) ({ \
+ u64 __val; \
+ asm volatile(__mrs_s(r, __val)); \
+ __val; \
})
-#define write_sysreg_s(v, r) do { \
- u64 __val = (u64)v; \
- asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
+#define write_sysreg_s(v, r) do { \
+ u64 __val = (u64)(v); \
+ asm volatile(__msr_s(r, __val)); \
} while (0)
static inline void config_sctlr_el1(u32 clear, u32 set)
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 0dd1bc1..bbd5dc7 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -36,58 +36,31 @@
struct task_struct;
+#include <asm/stack_pointer.h>
#include <asm/types.h>
typedef unsigned long mm_segment_t;
/*
* low level task data that entry.S needs immediate access to.
- * __switch_to() assumes cpu_context follows immediately after cpu_domain.
*/
struct thread_info {
unsigned long flags; /* low level flags */
mm_segment_t addr_limit; /* address limit */
- struct task_struct *task; /* main task structure */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ u64 ttbr0; /* saved TTBR0_EL1 */
+#endif
int preempt_count; /* 0 => preemptable, <0 => bug */
- int cpu; /* cpu */
};
#define INIT_THREAD_INFO(tsk) \
{ \
- .task = &tsk, \
- .flags = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
#define init_stack (init_thread_union.stack)
-/*
- * how to get the current stack pointer from C
- */
-register unsigned long current_stack_pointer asm ("sp");
-
-/*
- * how to get the thread information struct from C
- */
-static inline struct thread_info *current_thread_info(void) __attribute_const__;
-
-/*
- * struct thread_info can be accessed directly via sp_el0.
- *
- * We don't use read_sysreg() as we want the compiler to cache the value where
- * possible.
- */
-static inline struct thread_info *current_thread_info(void)
-{
- unsigned long sp_el0;
-
- asm ("mrs %0, sp_el0" : "=r" (sp_el0));
-
- return (struct thread_info *)sp_el0;
-}
-
#define thread_saved_pc(tsk) \
((unsigned long)(tsk->thread.cpu_context.pc))
#define thread_saved_sp(tsk) \
@@ -112,6 +85,7 @@ static inline struct thread_info *current_thread_info(void)
#define TIF_NEED_RESCHED 1
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
+#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */
#define TIF_NOHZ 7
#define TIF_SYSCALL_TRACE 8
#define TIF_SYSCALL_AUDIT 9
@@ -133,10 +107,12 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
+#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_32BIT (1 << TIF_32BIT)
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
+ _TIF_FSCHECK)
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 8b57339..a4f86ded 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -31,6 +31,17 @@ int pcibus_to_node(struct pci_bus *bus);
cpumask_of_node(pcibus_to_node(bus)))
#endif /* CONFIG_NUMA */
+struct sched_domain;
+#ifdef CONFIG_CPU_FREQ
+#define arch_scale_freq_capacity cpufreq_scale_freq_capacity
+extern unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu);
+#define arch_scale_max_freq_capacity cpufreq_scale_max_freq_capacity
+extern unsigned long cpufreq_scale_max_freq_capacity(struct sched_domain *sd, int cpu);
+#define arch_scale_min_freq_capacity cpufreq_scale_min_freq_capacity
+extern unsigned long cpufreq_scale_min_freq_capacity(struct sched_domain *sd, int cpu);
+#endif
+#define arch_scale_cpu_capacity scale_cpu_capacity
+extern unsigned long scale_cpu_capacity(struct sched_domain *sd, int cpu);
#include <asm-generic/topology.h>
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 02e9035..47a9066 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -37,18 +37,11 @@ void unregister_undef_hook(struct undef_hook *hook);
void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index f5cd96c6..2163279 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -18,6 +18,13 @@
#ifndef __ASM_UACCESS_H
#define __ASM_UACCESS_H
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/mmu.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
/*
* User space memory access functions
*/
@@ -26,11 +33,9 @@
#include <linux/string.h>
#include <linux/thread_info.h>
-#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
-#include <asm/sysreg.h>
#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/compiler.h>
@@ -67,6 +72,9 @@ static inline void set_fs(mm_segment_t fs)
{
current_thread_info()->addr_limit = fs;
+ /* On user-mode return, check fs is correct */
+ set_thread_flag(TIF_FSCHECK);
+
/*
* Prevent a mispredicted conditional call to set_fs from forwarding
* the wrong address limit to access_ok under speculation.
@@ -136,6 +144,115 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
" .popsection\n"
/*
+ * User access enabling/disabling.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void __uaccess_ttbr0_disable(void)
+{
+ unsigned long flags, ttbr;
+
+ local_irq_save(flags);
+ ttbr = read_sysreg(ttbr1_el1);
+ ttbr &= ~TTBR_ASID_MASK;
+ /* reserved_ttbr0 placed at the end of swapper_pg_dir */
+ write_sysreg(ttbr + SWAPPER_DIR_SIZE, ttbr0_el1);
+ isb();
+ /* Set reserved ASID */
+ write_sysreg(ttbr, ttbr1_el1);
+ isb();
+ local_irq_restore(flags);
+}
+
+static inline void __uaccess_ttbr0_enable(void)
+{
+ unsigned long flags, ttbr0, ttbr1;
+
+ /*
+ * Disable interrupts to avoid preemption between reading the 'ttbr0'
+ * variable and the MSR. A context switch could trigger an ASID
+ * roll-over and an update of 'ttbr0'.
+ */
+ local_irq_save(flags);
+ ttbr0 = READ_ONCE(current_thread_info()->ttbr0);
+
+ /* Restore active ASID */
+ ttbr1 = read_sysreg(ttbr1_el1);
+ ttbr1 &= ~TTBR_ASID_MASK; /* safety measure */
+ ttbr1 |= ttbr0 & TTBR_ASID_MASK;
+ write_sysreg(ttbr1, ttbr1_el1);
+ isb();
+
+ /* Restore user page table */
+ write_sysreg(ttbr0, ttbr0_el1);
+ isb();
+ local_irq_restore(flags);
+}
+
+static inline bool uaccess_ttbr0_disable(void)
+{
+ if (!system_uses_ttbr0_pan())
+ return false;
+ __uaccess_ttbr0_disable();
+ return true;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+ if (!system_uses_ttbr0_pan())
+ return false;
+ __uaccess_ttbr0_enable();
+ return true;
+}
+#else
+static inline bool uaccess_ttbr0_disable(void)
+{
+ return false;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+ return false;
+}
+#endif
+
+#define __uaccess_disable(alt) \
+do { \
+ if (!uaccess_ttbr0_disable()) \
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt, \
+ CONFIG_ARM64_PAN)); \
+} while (0)
+
+#define __uaccess_enable(alt) \
+do { \
+ if (!uaccess_ttbr0_enable()) \
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt, \
+ CONFIG_ARM64_PAN)); \
+} while (0)
+
+static inline void uaccess_disable(void)
+{
+ __uaccess_disable(ARM64_HAS_PAN);
+}
+
+static inline void uaccess_enable(void)
+{
+ __uaccess_enable(ARM64_HAS_PAN);
+}
+
+/*
+ * These functions are no-ops when UAO is present.
+ */
+static inline void uaccess_disable_not_uao(void)
+{
+ __uaccess_disable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+static inline void uaccess_enable_not_uao(void)
+{
+ __uaccess_enable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+/*
* Sanitise a uaccess pointer such that it becomes NULL if above the
* current addr_limit.
*/
@@ -182,8 +299,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
do { \
unsigned long __gu_val; \
__chk_user_ptr(ptr); \
- asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
- CONFIG_ARM64_PAN)); \
+ uaccess_enable_not_uao(); \
switch (sizeof(*(ptr))) { \
case 1: \
__get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr), \
@@ -204,9 +320,8 @@ do { \
default: \
BUILD_BUG(); \
} \
+ uaccess_disable_not_uao(); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
- asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
- CONFIG_ARM64_PAN)); \
} while (0)
#define __get_user_check(x, ptr, err) \
@@ -256,8 +371,7 @@ do { \
do { \
__typeof__(*(ptr)) __pu_val = (x); \
__chk_user_ptr(ptr); \
- asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
- CONFIG_ARM64_PAN)); \
+ uaccess_enable_not_uao(); \
switch (sizeof(*(ptr))) { \
case 1: \
__put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr), \
@@ -278,8 +392,7 @@ do { \
default: \
BUILD_BUG(); \
} \
- asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
- CONFIG_ARM64_PAN)); \
+ uaccess_disable_not_uao(); \
} while (0)
#define __put_user_check(x, ptr, err) \
@@ -379,4 +492,77 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
+#else /* __ASSEMBLY__ */
+
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ .macro __uaccess_ttbr0_disable, tmp1
+ mrs \tmp1, ttbr1_el1 // swapper_pg_dir
+ bic \tmp1, \tmp1, #TTBR_ASID_MASK
+ add \tmp1, \tmp1, #SWAPPER_DIR_SIZE // reserved_ttbr0 at the end of swapper_pg_dir
+ msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1
+ isb
+ sub \tmp1, \tmp1, #SWAPPER_DIR_SIZE
+ msr ttbr1_el1, \tmp1 // set reserved ASID
+ isb
+ .endm
+
+ .macro __uaccess_ttbr0_enable, tmp1, tmp2
+ get_thread_info \tmp1
+ ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1
+ mrs \tmp2, ttbr1_el1
+ extr \tmp2, \tmp2, \tmp1, #48
+ ror \tmp2, \tmp2, #16
+ msr ttbr1_el1, \tmp2 // set the active ASID
+ isb
+ msr ttbr0_el1, \tmp1 // set the non-PAN TTBR0_EL1
+ isb
+ .endm
+
+ .macro uaccess_ttbr0_disable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+ save_and_disable_irq \tmp2 // avoid preemption
+ __uaccess_ttbr0_disable \tmp1
+ restore_irq \tmp2
+alternative_else_nop_endif
+ .endm
+
+ .macro uaccess_ttbr0_enable, tmp1, tmp2, tmp3
+alternative_if_not ARM64_HAS_PAN
+ save_and_disable_irq \tmp3 // avoid preemption
+ __uaccess_ttbr0_enable \tmp1, \tmp2
+ restore_irq \tmp3
+alternative_else_nop_endif
+ .endm
+#else
+ .macro uaccess_ttbr0_disable, tmp1, tmp2
+ .endm
+
+ .macro uaccess_ttbr0_enable, tmp1, tmp2, tmp3
+ .endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+ .macro uaccess_disable_not_uao, tmp1, tmp2
+ uaccess_ttbr0_disable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+ SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+ .endm
+
+ .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3
+ uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3
+alternative_if ARM64_ALT_PAN_NOT_UAO
+ SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+ .endm
+
+#endif /* __ASSEMBLY__ */
+
#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e78ac26..63469ac 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
-#define __NR_compat_syscalls 394
+#define __NR_compat_syscalls 435
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index b7e8ef1..491a191 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -809,6 +809,10 @@ __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
__SYSCALL(__NR_preadv2, compat_sys_preadv2)
#define __NR_pwritev2 393
__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index a739287..1cc77c2 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -30,5 +30,10 @@
#define HWCAP_ATOMICS (1 << 8)
#define HWCAP_FPHP (1 << 9)
#define HWCAP_ASIMDHP (1 << 10)
+#define HWCAP_SHA3 (1 << 17)
+#define HWCAP_SM3 (1 << 18)
+#define HWCAP_SM4 (1 << 19)
+#define HWCAP_ASIMDDP (1 << 20)
+#define HWCAP_SHA512 (1 << 21)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index a32b401..1f5655c 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/acpi.h>
+#include <linux/mm.h>
#include <linux/types.h>
#include <asm/cpu_ops.h>
@@ -109,7 +110,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu)
* that read this address need to convert this address to the
* Boot-Loader's endianness before jumping.
*/
- writeq_relaxed(__pa(secondary_entry), &mailbox->entry_point);
+ writeq_relaxed(__pa_symbol(secondary_entry), &mailbox->entry_point);
writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id);
arch_send_wakeup_ipi_mask(cpumask_of(cpu));
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 4998920..e3e8f7d 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -14,7 +14,6 @@
#include <linux/slab.h>
#include <linux/sysctl.h>
-#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/insn.h>
#include <asm/opcodes.h>
@@ -285,10 +284,10 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
#define __SWP_LL_SC_LOOPS 4
#define __user_swpX_asm(data, addr, res, temp, temp2, B) \
+do { \
+ uaccess_enable(); \
__asm__ __volatile__( \
" mov %w3, %w7\n" \
- ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \
- CONFIG_ARM64_PAN) \
"0: ldxr"B" %w2, [%4]\n" \
"1: stxr"B" %w0, %w1, [%4]\n" \
" cbz %w0, 2f\n" \
@@ -306,13 +305,13 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
" .popsection" \
_ASM_EXTABLE(0b, 4b) \
_ASM_EXTABLE(1b, 4b) \
- ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \
- CONFIG_ARM64_PAN) \
: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2) \
: "r" ((unsigned long)addr), "i" (-EAGAIN), \
"i" (-EFAULT), \
"i" (__SWP_LL_SC_LOOPS) \
- : "memory")
+ : "memory"); \
+ uaccess_disable(); \
+} while (0)
#define __user_swp_asm(data, addr, res, temp, temp2) \
__user_swpX_asm(data, addr, res, temp, temp2, "")
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 95878be..b2debec 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -37,11 +37,13 @@ int main(void)
{
DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm));
BLANK();
- DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
- DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
- DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit));
- DEFINE(TI_TASK, offsetof(struct thread_info, task));
- DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
+ DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags));
+ DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count));
+ DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit));
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0));
+#endif
+ DEFINE(TSK_STACK, offsetof(struct task_struct, stack));
BLANK();
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
BLANK();
@@ -124,6 +126,7 @@ int main(void)
DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
BLANK();
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
+ DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
BLANK();
#ifdef CONFIG_KVM_ARM_HOST
DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt));
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index d4e9ecb..6c2b1b4 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -24,7 +24,7 @@ static inline void __noreturn cpu_soft_restart(unsigned long el2_switch,
el2_switch = el2_switch && !is_kernel_in_hyp_mode() &&
is_hyp_mode_available();
- restart = (void *)virt_to_phys(__cpu_soft_restart);
+ restart = (void *)__pa_symbol(__cpu_soft_restart);
cpu_install_idmap();
restart(el2_switch, entry, arg0, arg1, arg2);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 8cf001b..5608f95 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -23,6 +23,7 @@
#include <linux/sort.h>
#include <linux/stop_machine.h>
#include <linux/types.h>
+#include <linux/mm.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
@@ -81,7 +82,10 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
- ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_DP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SHA3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0),
@@ -745,7 +749,7 @@ static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused
static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
int __unused)
{
- phys_addr_t idmap_addr = virt_to_phys(__hyp_idmap_text_start);
+ phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
/*
* Activate the lower HYP offset only if:
@@ -802,7 +806,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
ID_AA64PFR0_CSV3_SHIFT);
}
-static int kpti_install_ng_mappings(void *__unused)
+static int __nocfi kpti_install_ng_mappings(void *__unused)
{
typedef void (kpti_remap_fn)(int, int, phys_addr_t);
extern kpti_remap_fn idmap_kpti_install_ng_mappings;
@@ -970,8 +974,13 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index b3d5b3e..0241857 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -63,6 +63,17 @@ static const char *const hwcap_str[] = {
"atomics",
"fphp",
"asimdhp",
+ "cpuid",
+ "asimdrdm",
+ "jscvt",
+ "fcma",
+ "lrcpc",
+ "dcpop",
+ "sha3",
+ "sm3",
+ "sm4",
+ "asimddp",
+ "sha512",
NULL
};
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index ca978d7..ecebb48c7 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -32,7 +32,9 @@
#include <asm/memory.h>
#include <asm/mmu.h>
#include <asm/processor.h>
+#include <asm/ptrace.h>
#include <asm/thread_info.h>
+#include <asm/uaccess.h>
#include <asm/asm-uaccess.h>
#include <asm/unistd.h>
#include <asm/kernel-pgtable.h>
@@ -105,7 +107,7 @@
alternative_cb_end
ldr_this_cpu \tmp2, arm64_ssbd_callback_required, \tmp1
cbz \tmp2, \targ
- ldr \tmp2, [tsk, #TI_FLAGS]
+ ldr \tmp2, [tsk, #TSK_TI_FLAGS]
tbnz \tmp2, #TIF_SSBD, \targ
mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2
mov w1, #\state
@@ -137,9 +139,8 @@
.if \el == 0
mrs x21, sp_el0
- mov tsk, sp
- and tsk, tsk, #~(THREAD_SIZE - 1) // Ensure MDSCR_EL1.SS is clear,
- ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug
+ ldr_this_cpu tsk, __entry_task, x20 // Ensure MDSCR_EL1.SS is clear,
+ ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug
disable_step_tsk x19, x20 // exceptions when scheduling.
apply_ssbd 1, 1f, x22, x23
@@ -155,15 +156,41 @@
add x21, sp, #S_FRAME_SIZE
get_thread_info tsk
/* Save the task's original addr_limit and set USER_DS */
- ldr x20, [tsk, #TI_ADDR_LIMIT]
+ ldr x20, [tsk, #TSK_TI_ADDR_LIMIT]
str x20, [sp, #S_ORIG_ADDR_LIMIT]
mov x20, #USER_DS
- str x20, [tsk, #TI_ADDR_LIMIT]
+ str x20, [tsk, #TSK_TI_ADDR_LIMIT]
/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
.endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
stp lr, x21, [sp, #S_LR]
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ /*
+ * Set the TTBR0 PAN bit in SPSR. When the exception is taken from
+ * EL0, there is no need to check the state of TTBR0_EL1 since
+ * accesses are always enabled.
+ * Note that the meaning of this bit differs from the ARMv8.1 PAN
+ * feature as all TTBR0_EL1 accesses are disabled, not just those to
+ * user mappings.
+ */
+alternative_if ARM64_HAS_PAN
+ b 1f // skip TTBR0 PAN
+alternative_else_nop_endif
+
+ .if \el != 0
+ mrs x21, ttbr0_el1
+ tst x21, #TTBR_ASID_MASK // Check for the reserved ASID
+ orr x23, x23, #PSR_PAN_BIT // Set the emulated PAN in the saved SPSR
+ b.eq 1f // TTBR0 access already disabled
+ and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR
+ .endif
+
+ __uaccess_ttbr0_disable x21
+1:
+#endif
+
stp x22, x23, [sp, #S_PC]
/*
@@ -194,7 +221,7 @@
.if \el != 0
/* Restore the task's original addr_limit. */
ldr x20, [sp, #S_ORIG_ADDR_LIMIT]
- str x20, [tsk, #TI_ADDR_LIMIT]
+ str x20, [tsk, #TSK_TI_ADDR_LIMIT]
/* No need to restore UAO, it will be restored from SPSR_EL1 */
.endif
@@ -202,6 +229,40 @@
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
.if \el == 0
ct_user_enter
+ .endif
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ /*
+ * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
+ * PAN bit checking.
+ */
+alternative_if ARM64_HAS_PAN
+ b 2f // skip TTBR0 PAN
+alternative_else_nop_endif
+
+ .if \el != 0
+ tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
+ .endif
+
+ __uaccess_ttbr0_enable x0, x1
+
+ .if \el == 0
+ /*
+ * Enable errata workarounds only if returning to user. The only
+ * workaround currently required for TTBR0_EL1 changes are for the
+ * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
+ * corruption).
+ */
+ bl post_ttbr_update_workaround
+ .endif
+1:
+ .if \el != 0
+ and x22, x22, #~PSR_PAN_BIT // ARMv8.0 CPUs do not understand this bit
+ .endif
+2:
+#endif
+
+ .if \el == 0
ldr x23, [sp, #S_SP] // load return stack pointer
msr sp_el0, x23
tst x22, #PSR_MODE32_BIT // native task?
@@ -221,6 +282,7 @@
apply_ssbd 0, 5f, x0, x1
5:
.endif
+
msr elr_el1, x21 // set up the return data
msr spsr_el1, x22
ldp x0, x1, [sp, #16 * 0]
@@ -257,21 +319,18 @@
.endif
.endm
- .macro get_thread_info, rd
- mrs \rd, sp_el0
- .endm
-
.macro irq_stack_entry
mov x19, sp // preserve the original sp
/*
- * Compare sp with the current thread_info, if the top
- * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and
- * should switch to the irq stack.
+ * Compare sp with the base of the task stack.
+ * If the top ~(THREAD_SIZE - 1) bits match, we are on a task stack,
+ * and should switch to the irq stack.
*/
- and x25, x19, #~(THREAD_SIZE - 1)
- cmp x25, tsk
- b.ne 9998f
+ ldr x25, [tsk, TSK_STACK]
+ eor x25, x25, x19
+ and x25, x25, #~(THREAD_SIZE - 1)
+ cbnz x25, 9998f
adr_this_cpu x25, irq_stack, x26
mov x26, #IRQ_STACK_START_SP
@@ -501,9 +560,9 @@
irq_handler
#ifdef CONFIG_PREEMPT
- ldr w24, [tsk, #TI_PREEMPT] // get preempt count
+ ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count
cbnz w24, 1f // preempt count != 0
- ldr x0, [tsk, #TI_FLAGS] // get flags
+ ldr x0, [tsk, #TSK_TI_FLAGS] // get flags
tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling?
bl el1_preempt
1:
@@ -518,7 +577,7 @@
el1_preempt:
mov x24, lr
1: bl preempt_schedule_irq // irq en/disable is done inside
- ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS
+ ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS
tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling?
ret x24
#endif
@@ -757,8 +816,7 @@
ldp x29, x9, [x8], #16
ldr lr, [x8]
mov sp, x9
- and x9, x9, #~(THREAD_SIZE - 1)
- msr sp_el0, x9
+ msr sp_el0, x1
ret
ENDPROC(cpu_switch_to)
@@ -769,7 +827,7 @@
ret_fast_syscall:
disable_irq // disable interrupts
str x0, [sp, #S_X0] // returned x0
- ldr x1, [tsk, #TI_FLAGS] // re-check for syscall tracing
+ ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for syscall tracing
and x2, x1, #_TIF_SYSCALL_WORK
cbnz x2, ret_fast_syscall_trace
and x2, x1, #_TIF_WORK_MASK
@@ -789,14 +847,14 @@
#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_on // enabled while in userspace
#endif
- ldr x1, [tsk, #TI_FLAGS] // re-check for single-step
+ ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step
b finish_ret_to_user
/*
* "slow" syscall return path.
*/
ret_to_user:
disable_irq // disable interrupts
- ldr x1, [tsk, #TI_FLAGS]
+ ldr x1, [tsk, #TSK_TI_FLAGS]
and x2, x1, #_TIF_WORK_MASK
cbnz x2, work_pending
finish_ret_to_user:
@@ -829,7 +887,7 @@
enable_dbg_and_irq
ct_user_exit 1
- ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks
+ ldr x16, [tsk, #TSK_TI_FLAGS] // check for syscall hooks
tst x16, #_TIF_SYSCALL_WORK
b.ne __sys_trace
cmp scno, sc_nr // check upper syscall limit
@@ -891,14 +949,24 @@
.macro tramp_map_kernel, tmp
mrs \tmp, ttbr1_el1
- sub \tmp, \tmp, #SWAPPER_DIR_SIZE
+ sub \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
bic \tmp, \tmp, #USER_ASID_FLAG
msr ttbr1_el1, \tmp
+#ifdef CONFIG_ARCH_MSM8996
+ /* ASID already in \tmp[63:48] */
+ movk \tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
+ movk \tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
+ /* 2MB boundary containing the vectors, so we nobble the walk cache */
+ movk \tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
+ isb
+ tlbi vae1, \tmp
+ dsb nsh
+#endif /* CONFIG_ARCH_MSM8996 */
.endm
.macro tramp_unmap_kernel, tmp
mrs \tmp, ttbr1_el1
- add \tmp, \tmp, #SWAPPER_DIR_SIZE
+ add \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
orr \tmp, \tmp, #USER_ASID_FLAG
msr ttbr1_el1, \tmp
/*
@@ -925,7 +993,9 @@
tramp_map_kernel x30
#ifdef CONFIG_RANDOMIZE_BASE
adr x30, tramp_vectors + PAGE_SIZE
+#ifndef CONFIG_ARCH_MSM8996
isb
+#endif
ldr x30, [x30]
#else
ldr x30, =vectors
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index aba5349..9c32d0e 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -326,14 +326,14 @@
* dirty cache lines being evicted.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
*/
adrp x0, idmap_pg_dir
- adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE
+ adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
@@ -412,7 +412,7 @@
* tables again to remove any speculatively loaded cache lines.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
dmb sy
bl __inval_cache_range
@@ -428,7 +428,8 @@
__primary_switched:
adrp x4, init_thread_union
add sp, x4, #THREAD_SIZE
- msr sp_el0, x4 // Save thread_info
+ adr_l x5, init_task
+ msr sp_el0, x5 // Save thread_info
adr_l x8, vectors // load VBAR_EL1 with virtual
msr vbar_el1, x8 // vector table address
@@ -699,10 +700,10 @@
isb
adr_l x0, secondary_data
- ldr x0, [x0, #CPU_BOOT_STACK] // get secondary_data.stack
- mov sp, x0
- and x0, x0, #~(THREAD_SIZE - 1)
- msr sp_el0, x0 // save thread_info
+ ldr x1, [x0, #CPU_BOOT_STACK] // get secondary_data.stack
+ mov sp, x1
+ ldr x2, [x0, #CPU_BOOT_TASK]
+ msr sp_el0, x2
mov x29, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index c4aec12..464fccc 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -50,9 +50,6 @@
*/
extern int in_suspend;
-/* Find a symbols alias in the linear map */
-#define LMADDR(x) phys_to_virt(virt_to_phys(x))
-
/* Do we need to reset el2? */
#define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode())
@@ -102,8 +99,8 @@ static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
int pfn_is_nosave(unsigned long pfn)
{
- unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
- unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);
+ unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin);
+ unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1);
return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
}
@@ -125,12 +122,12 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
return -EOVERFLOW;
arch_hdr_invariants(&hdr->invariants);
- hdr->ttbr1_el1 = virt_to_phys(swapper_pg_dir);
+ hdr->ttbr1_el1 = __pa_symbol(swapper_pg_dir);
hdr->reenter_kernel = _cpu_resume;
/* We can't use __hyp_get_vectors() because kvm may still be loaded */
if (el2_reset_needed())
- hdr->__hyp_stub_vectors = virt_to_phys(__hyp_stub_vectors);
+ hdr->__hyp_stub_vectors = __pa_symbol(__hyp_stub_vectors);
else
hdr->__hyp_stub_vectors = 0;
@@ -472,7 +469,6 @@ int swsusp_arch_resume(void)
void *zero_page;
size_t exit_size;
pgd_t *tmp_pg_dir;
- void *lm_restore_pblist;
phys_addr_t phys_hibernate_exit;
void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
void *, phys_addr_t, phys_addr_t);
@@ -493,12 +489,6 @@ int swsusp_arch_resume(void)
goto out;
/*
- * Since we only copied the linear map, we need to find restore_pblist's
- * linear map address.
- */
- lm_restore_pblist = LMADDR(restore_pblist);
-
- /*
* We need a zero page that is zero before & after resume in order to
* to break before make on the ttbr1 page tables.
*/
@@ -549,7 +539,7 @@ int swsusp_arch_resume(void)
}
hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
- resume_hdr.reenter_kernel, lm_restore_pblist,
+ resume_hdr.reenter_kernel, restore_pblist,
resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
out:
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index d168e52..f3b5cfb 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -318,9 +318,21 @@ static int get_hbp_len(u8 hbp_len)
case ARM_BREAKPOINT_LEN_2:
len_in_bytes = 2;
break;
+ case ARM_BREAKPOINT_LEN_3:
+ len_in_bytes = 3;
+ break;
case ARM_BREAKPOINT_LEN_4:
len_in_bytes = 4;
break;
+ case ARM_BREAKPOINT_LEN_5:
+ len_in_bytes = 5;
+ break;
+ case ARM_BREAKPOINT_LEN_6:
+ len_in_bytes = 6;
+ break;
+ case ARM_BREAKPOINT_LEN_7:
+ len_in_bytes = 7;
+ break;
case ARM_BREAKPOINT_LEN_8:
len_in_bytes = 8;
break;
@@ -350,7 +362,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
* to generic breakpoint descriptions.
*/
int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
- int *gen_len, int *gen_type)
+ int *gen_len, int *gen_type, int *offset)
{
/* Type */
switch (ctrl.type) {
@@ -370,17 +382,33 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
return -EINVAL;
}
+ if (!ctrl.len)
+ return -EINVAL;
+ *offset = __ffs(ctrl.len);
+
/* Len */
- switch (ctrl.len) {
+ switch (ctrl.len >> *offset) {
case ARM_BREAKPOINT_LEN_1:
*gen_len = HW_BREAKPOINT_LEN_1;
break;
case ARM_BREAKPOINT_LEN_2:
*gen_len = HW_BREAKPOINT_LEN_2;
break;
+ case ARM_BREAKPOINT_LEN_3:
+ *gen_len = HW_BREAKPOINT_LEN_3;
+ break;
case ARM_BREAKPOINT_LEN_4:
*gen_len = HW_BREAKPOINT_LEN_4;
break;
+ case ARM_BREAKPOINT_LEN_5:
+ *gen_len = HW_BREAKPOINT_LEN_5;
+ break;
+ case ARM_BREAKPOINT_LEN_6:
+ *gen_len = HW_BREAKPOINT_LEN_6;
+ break;
+ case ARM_BREAKPOINT_LEN_7:
+ *gen_len = HW_BREAKPOINT_LEN_7;
+ break;
case ARM_BREAKPOINT_LEN_8:
*gen_len = HW_BREAKPOINT_LEN_8;
break;
@@ -424,9 +452,21 @@ static int arch_build_bp_info(struct perf_event *bp)
case HW_BREAKPOINT_LEN_2:
info->ctrl.len = ARM_BREAKPOINT_LEN_2;
break;
+ case HW_BREAKPOINT_LEN_3:
+ info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+ break;
case HW_BREAKPOINT_LEN_4:
info->ctrl.len = ARM_BREAKPOINT_LEN_4;
break;
+ case HW_BREAKPOINT_LEN_5:
+ info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+ break;
+ case HW_BREAKPOINT_LEN_6:
+ info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+ break;
+ case HW_BREAKPOINT_LEN_7:
+ info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+ break;
case HW_BREAKPOINT_LEN_8:
info->ctrl.len = ARM_BREAKPOINT_LEN_8;
break;
@@ -519,18 +559,17 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
default:
return -EINVAL;
}
-
- info->address &= ~alignment_mask;
- info->ctrl.len <<= offset;
} else {
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
alignment_mask = 0x3;
else
alignment_mask = 0x7;
- if (info->address & alignment_mask)
- return -EINVAL;
+ offset = info->address & alignment_mask;
}
+ info->address &= ~alignment_mask;
+ info->ctrl.len <<= offset;
+
/*
* Disallow per-task kernel breakpoints since these would
* complicate the stepping code.
@@ -663,12 +702,47 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr,
}
NOKPROBE_SYMBOL(breakpoint_handler);
+/*
+ * Arm64 hardware does not always report a watchpoint hit address that matches
+ * one of the watchpoints set. It can also report an address "near" the
+ * watchpoint if a single instruction access both watched and unwatched
+ * addresses. There is no straight-forward way, short of disassembling the
+ * offending instruction, to map that address back to the watchpoint. This
+ * function computes the distance of the memory access from the watchpoint as a
+ * heuristic for the likelyhood that a given access triggered the watchpoint.
+ *
+ * See Section D2.10.5 "Determining the memory location that caused a Watchpoint
+ * exception" of ARMv8 Architecture Reference Manual for details.
+ *
+ * The function returns the distance of the address from the bytes watched by
+ * the watchpoint. In case of an exact match, it returns 0.
+ */
+static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
+ struct arch_hw_breakpoint_ctrl *ctrl)
+{
+ u64 wp_low, wp_high;
+ u32 lens, lene;
+
+ lens = __ffs(ctrl->len);
+ lene = __fls(ctrl->len);
+
+ wp_low = val + lens;
+ wp_high = val + lene;
+ if (addr < wp_low)
+ return wp_low - addr;
+ else if (addr > wp_high)
+ return addr - wp_high;
+ else
+ return 0;
+}
+
static int watchpoint_handler(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
- int i, step = 0, *kernel_step, access;
+ int i, step = 0, *kernel_step, access, closest_match = 0;
+ u64 min_dist = -1, dist;
u32 ctrl_reg;
- u64 val, alignment_mask;
+ u64 val;
struct perf_event *wp, **slots;
struct debug_info *debug_info;
struct arch_hw_breakpoint *info;
@@ -677,35 +751,15 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
slots = this_cpu_ptr(wp_on_reg);
debug_info = ¤t->thread.debug;
+ /*
+ * Find all watchpoints that match the reported address. If no exact
+ * match is found. Attribute the hit to the closest watchpoint.
+ */
+ rcu_read_lock();
for (i = 0; i < core_num_wrps; ++i) {
- rcu_read_lock();
-
wp = slots[i];
-
if (wp == NULL)
- goto unlock;
-
- info = counter_arch_bp(wp);
- /* AArch32 watchpoints are either 4 or 8 bytes aligned. */
- if (is_compat_task()) {
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
- alignment_mask = 0x7;
- else
- alignment_mask = 0x3;
- } else {
- alignment_mask = 0x7;
- }
-
- /* Check if the watchpoint value matches. */
- val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
- if (val != (untagged_addr(addr) & ~alignment_mask))
- goto unlock;
-
- /* Possible match, check the byte address select to confirm. */
- ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
- decode_ctrl_reg(ctrl_reg, &ctrl);
- if (!((1 << (addr & alignment_mask)) & ctrl.len))
- goto unlock;
+ continue;
/*
* Check that the access type matches.
@@ -714,18 +768,41 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W :
HW_BREAKPOINT_R;
if (!(access & hw_breakpoint_type(wp)))
- goto unlock;
+ continue;
+ /* Check if the watchpoint value and byte select match. */
+ val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
+ ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
+ decode_ctrl_reg(ctrl_reg, &ctrl);
+ dist = get_distance_from_watchpoint(addr, val, &ctrl);
+ if (dist < min_dist) {
+ min_dist = dist;
+ closest_match = i;
+ }
+ /* Is this an exact match? */
+ if (dist != 0)
+ continue;
+
+ info = counter_arch_bp(wp);
info->trigger = addr;
perf_bp_event(wp, regs);
/* Do we need to handle the stepping? */
if (is_default_overflow_handler(wp))
step = 1;
-
-unlock:
- rcu_read_unlock();
}
+ if (min_dist > 0 && min_dist != -1) {
+ /* No exact match found. */
+ wp = slots[closest_match];
+ info = counter_arch_bp(wp);
+ info->trigger = addr;
+ perf_bp_event(wp, regs);
+
+ /* Do we need to handle the stepping? */
+ if (is_default_overflow_handler(wp))
+ step = 1;
+ }
+ rcu_read_unlock();
if (!step)
return 0;
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 6f2ac4f..f607b38 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -97,7 +97,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
page = vmalloc_to_page(addr);
else if (!module)
- page = pfn_to_page(PHYS_PFN(__pa(addr)));
+ page = phys_to_page(__pa_symbol(addr));
else
return addr;
diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index 354be2a..79b1738 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -25,8 +25,7 @@
*/
void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
{
- while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
- !IS_ALIGNED((unsigned long)to, 8))) {
+ while (count && !IS_ALIGNED((unsigned long)from, 8)) {
*(u8 *)to = __raw_readb(from);
from++;
to++;
@@ -54,23 +53,22 @@ EXPORT_SYMBOL(__memcpy_fromio);
*/
void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
{
- while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
- !IS_ALIGNED((unsigned long)from, 8))) {
- __raw_writeb(*(volatile u8 *)from, to);
+ while (count && !IS_ALIGNED((unsigned long)to, 8)) {
+ __raw_writeb(*(u8 *)from, to);
from++;
to++;
count--;
}
while (count >= 8) {
- __raw_writeq(*(volatile u64 *)from, to);
+ __raw_writeq(*(u64 *)from, to);
from += 8;
to += 8;
count -= 8;
}
while (count) {
- __raw_writeb(*(volatile u8 *)from, to);
+ __raw_writeb(*(u8 *)from, to);
from++;
to++;
count--;
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
index 8949f6c..05881e2 100644
--- a/arch/arm64/kernel/module.lds
+++ b/arch/arm64/kernel/module.lds
@@ -1,3 +1,3 @@
SECTIONS {
- .plt (NOLOAD) : { BYTE(0) }
+ .plt : { BYTE(0) }
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index e917d11..ce1c933 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -45,6 +45,7 @@
#include <linux/personality.h>
#include <linux/notifier.h>
#include <trace/events/power.h>
+#include <linux/percpu.h>
#include <asm/alternative.h>
#include <asm/compat.h>
@@ -166,6 +167,70 @@ void machine_restart(char *cmd)
while (1);
}
+/*
+ * dump a block of kernel memory from around the given address
+ */
+static void show_data(unsigned long addr, int nbytes, const char *name)
+{
+ int i, j;
+ int nlines;
+ u32 *p;
+
+ /*
+ * don't attempt to dump non-kernel addresses or
+ * values that are probably just small negative numbers
+ */
+ if (addr < PAGE_OFFSET || addr > -256UL)
+ return;
+
+ printk("\n%s: %#lx:\n", name, addr);
+
+ /*
+ * round address down to a 32 bit boundary
+ * and always dump a multiple of 32 bytes
+ */
+ p = (u32 *)(addr & ~(sizeof(u32) - 1));
+ nbytes += (addr & (sizeof(u32) - 1));
+ nlines = (nbytes + 31) / 32;
+
+
+ for (i = 0; i < nlines; i++) {
+ /*
+ * just display low 16 bits of address to keep
+ * each line of the dump < 80 characters
+ */
+ printk("%04lx ", (unsigned long)p & 0xffff);
+ for (j = 0; j < 8; j++) {
+ u32 data;
+ if (probe_kernel_address(p, data)) {
+ pr_cont(" ********");
+ } else {
+ pr_cont(" %08x", data);
+ }
+ ++p;
+ }
+ pr_cont("\n");
+ }
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+ mm_segment_t fs;
+ unsigned int i;
+
+ fs = get_fs();
+ set_fs(KERNEL_DS);
+ show_data(regs->pc - nbytes, nbytes * 2, "PC");
+ show_data(regs->regs[30] - nbytes, nbytes * 2, "LR");
+ show_data(regs->sp - nbytes, nbytes * 2, "SP");
+ for (i = 0; i < 30; i++) {
+ char name[4];
+ snprintf(name, sizeof(name), "X%u", i);
+ show_data(regs->regs[i] - nbytes, nbytes * 2, name);
+ }
+ set_fs(fs);
+}
+
void __show_regs(struct pt_regs *regs)
{
int i, top_reg;
@@ -201,6 +266,8 @@ void __show_regs(struct pt_regs *regs)
pr_cont("\n");
}
+ if (!user_mode(regs))
+ show_extra_register_data(regs, 128);
printk("\n");
}
@@ -331,6 +398,20 @@ void uao_thread_switch(struct task_struct *next)
}
/*
+ * We store our current task in sp_el0, which is clobbered by userspace. Keep a
+ * shadow copy so that we can restore this upon entry from userspace.
+ *
+ * This is *only* for exception entry from EL0, and is not valid until we
+ * __switch_to() a user task.
+ */
+DEFINE_PER_CPU(struct task_struct *, __entry_task);
+
+static void entry_task_switch(struct task_struct *next)
+{
+ __this_cpu_write(__entry_task, next);
+}
+
+/*
* Thread switching.
*/
struct task_struct *__switch_to(struct task_struct *prev,
@@ -342,6 +423,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
tls_thread_switch(next);
hw_breakpoint_thread_switch(next);
contextidr_thread_switch(next);
+ entry_task_switch(next);
uao_thread_switch(next);
/*
@@ -359,27 +441,35 @@ struct task_struct *__switch_to(struct task_struct *prev,
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
- unsigned long stack_page;
+ unsigned long stack_page, ret = 0;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
+ stack_page = (unsigned long)try_get_task_stack(p);
+ if (!stack_page)
+ return 0;
+
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
frame.pc = thread_saved_pc(p);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = p->curr_ret_stack;
#endif
- stack_page = (unsigned long)task_stack_page(p);
do {
if (frame.sp < stack_page ||
frame.sp >= stack_page + THREAD_SIZE ||
unwind_frame(p, &frame))
- return 0;
- if (!in_sched_functions(frame.pc))
- return frame.pc;
+ goto out;
+ if (!in_sched_functions(frame.pc)) {
+ ret = frame.pc;
+ goto out;
+ }
} while (count ++ < 16);
- return 0;
+
+out:
+ put_task_stack(p);
+ return ret;
}
unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index bf6142a..3ebb2a5 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -20,6 +20,7 @@
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/psci.h>
+#include <linux/mm.h>
#include <uapi/linux/psci.h>
@@ -45,7 +46,7 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu)
static int cpu_psci_cpu_boot(unsigned int cpu)
{
- int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+ int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa_symbol(secondary_entry));
if (err)
pr_err("failed to boot CPU%d (%d)\n", cpu, err);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68af3f8..7990377 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -327,13 +327,13 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
struct arch_hw_breakpoint_ctrl ctrl,
struct perf_event_attr *attr)
{
- int err, len, type, disabled = !ctrl.enabled;
+ int err, len, type, offset, disabled = !ctrl.enabled;
attr->disabled = disabled;
if (disabled)
return 0;
- err = arch_bp_generic_fields(ctrl, &len, &type);
+ err = arch_bp_generic_fields(ctrl, &len, &type, &offset);
if (err)
return err;
@@ -352,6 +352,7 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
attr->bp_len = len;
attr->bp_type = type;
+ attr->bp_addr += offset;
return 0;
}
@@ -404,7 +405,7 @@ static int ptrace_hbp_get_addr(unsigned int note_type,
if (IS_ERR(bp))
return PTR_ERR(bp);
- *addr = bp ? bp->attr.bp_addr : 0;
+ *addr = bp ? counter_arch_bp(bp)->address : 0;
return 0;
}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 1718706..12a87f2 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -12,6 +12,7 @@
#include <linux/export.h>
#include <linux/ftrace.h>
+#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
struct return_address_data {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f534f492..b522209 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -42,6 +42,7 @@
#include <linux/of_fdt.h>
#include <linux/efi.h>
#include <linux/psci.h>
+#include <linux/mm.h>
#include <asm/acpi.h>
#include <asm/fixmap.h>
@@ -199,10 +200,10 @@ static void __init request_standard_resources(void)
struct memblock_region *region;
struct resource *res;
- kernel_code.start = virt_to_phys(_text);
- kernel_code.end = virt_to_phys(__init_begin - 1);
- kernel_data.start = virt_to_phys(_sdata);
- kernel_data.end = virt_to_phys(_end - 1);
+ kernel_code.start = __pa_symbol(_text);
+ kernel_code.end = __pa_symbol(__init_begin - 1);
+ kernel_data.start = __pa_symbol(_sdata);
+ kernel_data.end = __pa_symbol(_end - 1);
for_each_memblock(memory, region) {
res = alloc_bootmem_low(sizeof(*res));
@@ -291,6 +292,15 @@ void __init setup_arch(char **cmdline_p)
smp_init_cpus();
smp_build_mpidr_hash();
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ /*
+ * Make sure init_thread_info.ttbr0 always generates translation
+ * faults in case uaccess_enable() is inadvertently called by the init
+ * thread.
+ */
+ init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page);
+#endif
+
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
@@ -329,11 +339,11 @@ subsys_initcall(topology_init);
static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
void *p)
{
- u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR;
+ const unsigned long offset = kaslr_offset();
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) {
- pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n",
- kaslr_offset, KIMAGE_VADDR);
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+ offset, KIMAGE_VADDR);
} else {
pr_emerg("Kernel Offset: disabled\n");
}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 404dd67..c59e675 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -25,6 +25,7 @@
#include <linux/uaccess.h>
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
+#include <linux/syscalls.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
@@ -408,7 +409,11 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
* Update the trace code with the current status.
*/
trace_hardirqs_off();
+
do {
+ /* Check valid user FS if needed */
+ addr_limit_user_check();
+
if (thread_flags & _TIF_NEED_RESCHED) {
schedule();
} else {
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 0030d69..5a4fbcc 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -125,9 +125,6 @@
/* load sp from context */
ldr x2, [x0, #CPU_CTX_SP]
mov sp, x2
- /* save thread_info */
- and x2, x2, #~(THREAD_SIZE - 1)
- msr sp_el0, x2
/*
* cpu_do_resume expects x0 to contain context address pointer
*/
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 13b9c20..32b9539 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -58,6 +58,9 @@
#define CREATE_TRACE_POINTS
#include <trace/events/ipi.h>
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+
/*
* as from 2.5, kernels no longer have an init_tasks structure
* so we need some other way of telling a new secondary core
@@ -147,6 +150,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
* We need to tell the secondary core where to find its stack and the
* page tables.
*/
+ secondary_data.task = idle;
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
update_cpu_boot_status(CPU_MMU_OFF);
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
@@ -176,6 +180,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
return ret;
}
+ secondary_data.task = NULL;
secondary_data.stack = NULL;
status = READ_ONCE(secondary_data.status);
if (ret && status) {
@@ -214,7 +219,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
asmlinkage notrace void secondary_start_kernel(void)
{
struct mm_struct *mm = &init_mm;
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
+
+ cpu = task_cpu(current);
+ set_my_cpu_offset(per_cpu_offset(cpu));
/*
* All kernel threads share the same mm context; grab a
@@ -223,8 +231,6 @@ asmlinkage notrace void secondary_start_kernel(void)
atomic_inc(&mm->mm_count);
current->active_mm = mm;
- set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
@@ -724,6 +730,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
*/
for_each_possible_cpu(cpu) {
+ per_cpu(cpu_number, cpu) = cpu;
+
if (cpu == smp_processor_id())
continue;
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 9a00eee..9303465 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -21,6 +21,7 @@
#include <linux/of.h>
#include <linux/smp.h>
#include <linux/types.h>
+#include <linux/mm.h>
#include <asm/cacheflush.h>
#include <asm/cpu_ops.h>
@@ -98,7 +99,7 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
* boot-loader's endianess before jumping. This is mandated by
* the boot protocol.
*/
- writeq_relaxed(__pa(secondary_holding_pen), release_addr);
+ writeq_relaxed(__pa_symbol(secondary_holding_pen), release_addr);
__flush_dcache_area((__force void *)release_addr,
sizeof(*release_addr));
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 0cc01e0..5201beb 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -22,6 +22,7 @@
#include <linux/stacktrace.h>
#include <asm/irq.h>
+#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
/*
@@ -133,7 +134,6 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
break;
}
}
-EXPORT_SYMBOL(walk_stackframe);
#ifdef CONFIG_STACKTRACE
struct stack_trace_data {
@@ -186,6 +186,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
struct stack_trace_data data;
struct stackframe frame;
+ if (!try_get_task_stack(tsk))
+ return;
+
data.trace = trace;
data.skip = trace->skip;
@@ -207,6 +210,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
walk_stackframe(tsk, &frame, save_trace, &data);
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
+
+ put_task_stack(tsk);
}
void save_stack_trace(struct stack_trace *trace)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 1dbf609..e12f2d0 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -47,12 +47,6 @@ void notrace __cpu_suspend_exit(void)
cpu_uninstall_idmap();
/*
- * Restore per-cpu offset before any kernel
- * subsystem relying on it has a chance to run.
- */
- set_my_cpu_offset(per_cpu_offset(cpu));
-
- /*
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
*/
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 694f6de..ed73426 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -19,10 +19,24 @@
#include <linux/nodemask.h>
#include <linux/of.h>
#include <linux/sched.h>
+#include <linux/sched.h>
+#include <linux/sched_energy.h>
#include <asm/cputype.h>
#include <asm/topology.h>
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+
+unsigned long scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+ per_cpu(cpu_scale, cpu) = capacity;
+}
+
static int __init get_cpu_for_node(struct device_node *node)
{
struct device_node *cpu_node;
@@ -206,11 +220,72 @@ static int __init parse_dt_topology(void)
struct cpu_topology cpu_topology[NR_CPUS];
EXPORT_SYMBOL_GPL(cpu_topology);
+/* sd energy functions */
+static inline
+const struct sched_group_energy * const cpu_cluster_energy(int cpu)
+{
+ struct sched_group_energy *sge = sge_array[cpu][SD_LEVEL1];
+
+ if (!sge) {
+ pr_warn("Invalid sched_group_energy for Cluster%d\n", cpu);
+ return NULL;
+ }
+
+ return sge;
+}
+
+static inline
+const struct sched_group_energy * const cpu_core_energy(int cpu)
+{
+ struct sched_group_energy *sge = sge_array[cpu][SD_LEVEL0];
+
+ if (!sge) {
+ pr_warn("Invalid sched_group_energy for CPU%d\n", cpu);
+ return NULL;
+ }
+
+ return sge;
+}
+
const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_topology[cpu].core_sibling;
}
+static int cpu_cpu_flags(void)
+{
+ return SD_ASYM_CPUCAPACITY;
+}
+
+static inline int cpu_corepower_flags(void)
+{
+ return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN | \
+ SD_SHARE_CAP_STATES;
+}
+
+static struct sched_domain_topology_level arm64_topology[] = {
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, cpu_corepower_flags, cpu_core_energy, SD_INIT_NAME(MC) },
+#endif
+ { cpu_cpu_mask, cpu_cpu_flags, cpu_cluster_energy, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
+static void update_cpu_capacity(unsigned int cpu)
+{
+ unsigned long capacity = SCHED_CAPACITY_SCALE;
+
+ if (cpu_core_energy(cpu)) {
+ int max_cap_idx = cpu_core_energy(cpu)->nr_cap_states - 1;
+ capacity = cpu_core_energy(cpu)->cap_states[max_cap_idx].cap;
+ }
+
+ set_capacity_scale(cpu, capacity);
+
+ pr_info("CPU%d: update cpu_capacity %lu\n",
+ cpu, arch_scale_cpu_capacity(NULL, cpu));
+}
+
static void update_siblings_masks(unsigned int cpuid)
{
struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
@@ -272,6 +347,7 @@ void store_cpu_topology(unsigned int cpuid)
topology_populated:
update_siblings_masks(cpuid);
+ update_cpu_capacity(cpuid);
}
static void __init reset_cpu_topology(void)
@@ -302,4 +378,8 @@ void __init init_cpu_topology(void)
*/
if (of_have_populated_dt() && parse_dt_topology())
reset_cpu_topology();
+ else
+ set_sched_topology(arm64_topology);
+
+ init_sched_energy_costs();
}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5962bad..0586249 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -33,11 +33,13 @@
#include <linux/syscalls.h>
#include <asm/atomic.h>
+#include <asm/barrier.h>
#include <asm/bug.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/insn.h>
#include <asm/traps.h>
+#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
#include <asm/exception.h>
#include <asm/system_misc.h>
@@ -147,6 +149,9 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
if (!tsk)
tsk = current;
+ if (!try_get_task_stack(tsk))
+ return;
+
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
@@ -212,6 +217,8 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
stack + sizeof(struct pt_regs));
}
}
+
+ put_task_stack(tsk);
}
void show_stack(struct task_struct *tsk, unsigned long *sp)
@@ -227,10 +234,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
#endif
#define S_SMP " SMP"
-static int __die(const char *str, int err, struct thread_info *thread,
- struct pt_regs *regs)
+static int __die(const char *str, int err, struct pt_regs *regs)
{
- struct task_struct *tsk = thread->task;
+ struct task_struct *tsk = current;
static int die_counter;
int ret;
@@ -245,7 +251,8 @@ static int __die(const char *str, int err, struct thread_info *thread,
print_modules();
__show_regs(regs);
pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
- TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
+ TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
+ end_of_stack(tsk));
if (!user_mode(regs)) {
dump_mem(KERN_EMERG, "Stack: ", regs->sp,
@@ -264,7 +271,6 @@ static DEFINE_RAW_SPINLOCK(die_lock);
*/
void die(const char *str, struct pt_regs *regs, int err)
{
- struct thread_info *thread = current_thread_info();
int ret;
unsigned long flags;
@@ -274,9 +280,9 @@ void die(const char *str, struct pt_regs *regs, int err)
console_verbose();
bust_spinlocks(1);
- ret = __die(str, err, thread, regs);
+ ret = __die(str, err, regs);
- if (regs && kexec_should_crash(thread->task))
+ if (regs && kexec_should_crash(current))
crash_kexec(regs);
bust_spinlocks(0);
@@ -439,9 +445,10 @@ int cpu_enable_cache_maint_trap(void *__unused)
}
#define __user_cache_maint(insn, address, res) \
- if (address >= user_addr_max()) \
+ if (address >= user_addr_max()) { \
res = -EFAULT; \
- else \
+ } else { \
+ uaccess_ttbr0_enable(); \
asm volatile ( \
"1: " insn ", %1\n" \
" mov %w0, #0\n" \
@@ -453,7 +460,9 @@ int cpu_enable_cache_maint_trap(void *__unused)
" .popsection\n" \
_ASM_EXTABLE(1b, 3b) \
: "=r" (res) \
- : "r" (address), "i" (-EFAULT) )
+ : "r" (address), "i" (-EFAULT)); \
+ uaccess_ttbr0_disable(); \
+ }
static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
@@ -496,6 +505,25 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
regs->pc += 4;
}
+static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ isb();
+ if (rt != 31)
+ regs->regs[rt] = arch_counter_get_cntvct();
+ regs->pc += 4;
+}
+
+static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ if (rt != 31)
+ regs->regs[rt] = read_sysreg(cntfrq_el0);
+ regs->pc += 4;
+}
+
struct sys64_hook {
unsigned int esr_mask;
unsigned int esr_val;
@@ -514,6 +542,18 @@ static struct sys64_hook sys64_hooks[] = {
.esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
.handler = ctr_read_handler,
},
+ {
+ /* Trap read access to CNTVCT_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT,
+ .handler = cntvct_read_handler,
+ },
+ {
+ /* Trap read access to CNTFRQ_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ,
+ .handler = cntfrq_read_handler,
+ },
{},
};
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index c0f315e..56956a1 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -123,6 +123,7 @@ static int __init vdso_init(void)
{
int i;
struct page **vdso_pagelist;
+ unsigned long pfn;
if (memcmp(vdso_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
@@ -140,11 +141,14 @@ static int __init vdso_init(void)
return -ENOMEM;
/* Grab the vDSO data page. */
- vdso_pagelist[0] = pfn_to_page(PHYS_PFN(__pa(vdso_data)));
+ vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+
/* Grab the vDSO code pages. */
+ pfn = sym_to_pfn(vdso_start);
+
for (i = 0; i < vdso_pages; i++)
- vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(vdso_start)) + i);
+ vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
vdso_spec[0].pages = &vdso_pagelist[0];
vdso_spec[1].pages = &vdso_pagelist[1];
@@ -219,10 +223,8 @@ void update_vsyscall(struct timekeeper *tk)
if (!use_syscall) {
/* tkr_mono.cycle_last == tkr_raw.cycle_last */
vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last;
- vdso_data->raw_time_sec = tk->raw_time.tv_sec;
- vdso_data->raw_time_nsec = (tk->raw_time.tv_nsec <<
- tk->tkr_raw.shift) +
- tk->tkr_raw.xtime_nsec;
+ vdso_data->raw_time_sec = tk->raw_sec;
+ vdso_data->raw_time_nsec = tk->tkr_raw.xtime_nsec;
vdso_data->xtime_clock_sec = tk->xtime_sec;
vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
vdso_data->cs_mono_mult = tk->tkr_mono.mult;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 62c84f7..88fef38 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -14,6 +14,7 @@
ccflags-y := -shared -fno-common -fno-builtin
ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ccflags-y += $(DISABLE_LTO)
# Disable gcov profiling for VDSO code
GCOV_PROFILE := n
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index df829c4..21805e4 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -310,7 +310,7 @@
b.ne 4f
ldr x2, 5f
2:
- cbz w1, 3f
+ cbz x1, 3f
stp xzr, x2, [x1]
3: /* res == NULL. */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index fa3ffad..ad1142a 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -68,7 +68,7 @@
#define TRAMP_TEXT \
. = ALIGN(PAGE_SIZE); \
VMLINUX_SYMBOL(__entry_tramp_text_start) = .; \
- *(.entry.tramp.text) \
+ KEEP(*(.entry.tramp.text)) \
. = ALIGN(PAGE_SIZE); \
VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
#else
@@ -187,11 +187,11 @@
. = ALIGN(4);
.altinstructions : {
__alt_instructions = .;
- *(.altinstructions)
+ KEEP(*(.altinstructions))
__alt_instructions_end = .;
}
.altinstr_replacement : {
- *(.altinstr_replacement)
+ KEEP(*(.altinstr_replacement))
}
.rela : ALIGN(8) {
*(.rela .rela*)
@@ -236,6 +236,11 @@
swapper_pg_dir = .;
. += SWAPPER_DIR_SIZE;
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ reserved_ttbr0 = .;
+ . += RESERVED_TTBR0_SIZE;
+#endif
+
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
tramp_pg_dir = .;
. += PAGE_SIZE;
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 6eaf12c..55533f4 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -24,7 +24,6 @@
depends on OF
select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 48b0354..c470a7c 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -4,6 +4,10 @@
ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
+ifeq ($(cc-name),clang)
+ccflags-y += -fno-jump-tables
+endif
+
KVM=../../../../virt/kvm
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index a814f32..296afaf 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,10 +17,7 @@
*/
#include <linux/linkage.h>
-#include <asm/alternative.h>
-#include <asm/assembler.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
.text
@@ -33,8 +30,7 @@
* Alignment fixed up by hardware.
*/
ENTRY(__arch_clear_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_enable_not_uao x2, x3, x4
mov x2, x1 // save the size for fixup return
subs x1, x1, #8
b.mi 2f
@@ -54,8 +50,7 @@
b.mi 5f
uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
5: mov x0, #0
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_disable_not_uao x2, x3
ret
ENDPROC(__arch_clear_user)
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 580aca9..d0c356b 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -16,11 +16,8 @@
#include <linux/linkage.h>
-#include <asm/alternative.h>
-#include <asm/assembler.h>
#include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
/*
* Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -67,12 +64,10 @@
end .req x5
ENTRY(__arch_copy_from_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_disable_not_uao x3, x4
mov x0, #0 // Nothing to copy
ret
ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index d9ca6a4..026294e 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -18,11 +18,8 @@
#include <linux/linkage.h>
-#include <asm/alternative.h>
-#include <asm/assembler.h>
#include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
/*
* Copy from user space to user space (alignment handled by the hardware)
@@ -68,12 +65,10 @@
end .req x5
ENTRY(__arch_copy_in_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_disable_not_uao x3, x4
mov x0, #0
ret
ENDPROC(__arch_copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index e8bd40d..2d07da4 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -16,11 +16,8 @@
#include <linux/linkage.h>
-#include <asm/alternative.h>
-#include <asm/assembler.h>
#include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
/*
* Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -66,12 +63,10 @@
end .req x5
ENTRY(__arch_copy_to_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
- CONFIG_ARM64_PAN)
+ uaccess_disable_not_uao x3, x4
mov x0, #0
ret
ENDPROC(__arch_copy_to_user)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 58b5a90..82ecb6c 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -23,6 +23,7 @@
#include <asm/assembler.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
+#include <asm/uaccess.h>
/*
* flush_icache_range(start,end)
@@ -48,6 +49,7 @@
* - end - virtual end address of region
*/
ENTRY(__flush_cache_user_range)
+ uaccess_ttbr0_enable x2, x3, x4
dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x0, x3
@@ -69,10 +71,12 @@
dsb ish
isb
mov x0, #0
+1:
+ uaccess_ttbr0_disable x1, x2
ret
9:
mov x0, #-EFAULT
- ret
+ b 1b
ENDPROC(flush_icache_range)
ENDPROC(__flush_cache_user_range)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 62d976e..c841cce 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -233,7 +233,12 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
arm64_apply_bp_hardening();
- cpu_switch_mm(mm->pgd, mm);
+ /*
+ * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
+ * emulating PAN.
+ */
+ if (!system_uses_ttbr0_pan())
+ cpu_switch_mm(mm->pgd, mm);
}
/* Errata workaround post TTBRx_EL1 update. */
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index cab3574..6dda5ff 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -174,7 +174,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
/* create a coherent mapping */
page = virt_to_page(ptr);
coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
- prot, NULL);
+ prot, __builtin_return_address(0));
if (!coherent_ptr)
goto no_map;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f3d3f2e..2308508 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -299,13 +299,19 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
return fault;
}
-static inline bool is_permission_fault(unsigned int esr)
+static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs)
{
unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
- return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
- (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+ if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+ return false;
+
+ if (system_uses_ttbr0_pan())
+ return fsc_type == ESR_ELx_FSC_FAULT &&
+ (regs->pstate & PSR_PAN_BIT);
+ else
+ return fsc_type == ESR_ELx_FSC_PERM;
}
static bool is_el0_instruction_abort(unsigned int esr)
@@ -345,7 +351,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
mm_flags |= FAULT_FLAG_WRITE;
}
- if (is_permission_fault(esr) && (addr < TASK_SIZE)) {
+ if (addr < TASK_SIZE && is_permission_fault(esr, regs)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 5d3df68..c5c710d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -36,6 +36,7 @@
#include <linux/efi.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
+#include <linux/mm.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
@@ -213,8 +214,8 @@ void __init arm64_memblock_init(void)
* linear mapping. Take care not to clip the kernel which may be
* high in memory.
*/
- memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)),
- ULLONG_MAX);
+ memblock_remove(max_t(u64, memstart_addr + linear_region_size,
+ __pa_symbol(_end)), ULLONG_MAX);
if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
/* ensure that memstart_addr remains sufficiently aligned */
memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
@@ -229,7 +230,7 @@ void __init arm64_memblock_init(void)
*/
if (memory_limit != (phys_addr_t)ULLONG_MAX) {
memblock_mem_limit_remove_map(memory_limit);
- memblock_add(__pa(_text), (u64)(_end - _text));
+ memblock_add(__pa_symbol(_text), (u64)(_end - _text));
}
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) {
@@ -282,7 +283,7 @@ void __init arm64_memblock_init(void)
* Register the kernel text, kernel data, initrd, and initial
* pagetables with memblock.
*/
- memblock_reserve(__pa(_text), _end - _text);
+ memblock_reserve(__pa_symbol(_text), _end - _text);
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start) {
memblock_reserve(initrd_start, initrd_end - initrd_start);
@@ -492,7 +493,8 @@ void __init mem_init(void)
void free_initmem(void)
{
- free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
+ free_reserved_area(lm_alias(__init_begin),
+ lm_alias(__init_end),
0, "unused kernel");
/*
* Unmap the __init region but leave the VM area in place. This
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index ff43da2..ac31a2e 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -15,6 +15,7 @@
#include <linux/kernel.h>
#include <linux/memblock.h>
#include <linux/start_kernel.h>
+#include <linux/mm.h>
#include <asm/mmu_context.h>
#include <asm/kernel-pgtable.h>
@@ -26,6 +27,13 @@
static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). All the early functions are called too
+ * early to use lm_alias so __p*d_populate functions must be used to populate
+ * with the physical address from __pa_symbol.
+ */
+
static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
unsigned long end)
{
@@ -33,12 +41,12 @@ static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
unsigned long next;
if (pmd_none(*pmd))
- pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+ __pmd_populate(pmd, __pa_symbol(kasan_zero_pte), PMD_TYPE_TABLE);
pte = pte_offset_kimg(pmd, addr);
do {
next = addr + PAGE_SIZE;
- set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page),
+ set_pte(pte, pfn_pte(sym_to_pfn(kasan_zero_page),
PAGE_KERNEL));
} while (pte++, addr = next, addr != end && pte_none(*pte));
}
@@ -51,7 +59,7 @@ static void __init kasan_early_pmd_populate(pud_t *pud,
unsigned long next;
if (pud_none(*pud))
- pud_populate(&init_mm, pud, kasan_zero_pmd);
+ __pud_populate(pud, __pa_symbol(kasan_zero_pmd), PMD_TYPE_TABLE);
pmd = pmd_offset_kimg(pud, addr);
do {
@@ -68,7 +76,7 @@ static void __init kasan_early_pud_populate(pgd_t *pgd,
unsigned long next;
if (pgd_none(*pgd))
- pgd_populate(&init_mm, pgd, kasan_zero_pud);
+ __pgd_populate(pgd, __pa_symbol(kasan_zero_pud), PUD_TYPE_TABLE);
pud = pud_offset_kimg(pgd, addr);
do {
@@ -148,7 +156,7 @@ void __init kasan_init(void)
*/
memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
dsb(ishst);
- cpu_replace_ttbr1(tmp_pg_dir);
+ cpu_replace_ttbr1(lm_alias(tmp_pg_dir));
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
@@ -199,10 +207,10 @@ void __init kasan_init(void)
*/
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(&kasan_zero_pte[i],
- pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
+ pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
memset(kasan_zero_page, 0, PAGE_SIZE);
- cpu_replace_ttbr1(swapper_pg_dir);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
/* At this point kasan is fully initialized. Enable error messages */
init_task.kasan_depth = 0;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60be5bc..f1022a8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -28,6 +28,7 @@
#include <linux/memblock.h>
#include <linux/fs.h>
#include <linux/io.h>
+#include <linux/mm.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
@@ -332,8 +333,8 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
{
- unsigned long kernel_start = __pa(_text);
- unsigned long kernel_end = __pa(__init_begin);
+ unsigned long kernel_start = __pa_symbol(_text);
+ unsigned long kernel_end = __pa_symbol(__init_begin);
/*
* Take care not to create a writable alias for the
@@ -400,14 +401,14 @@ void mark_rodata_ro(void)
unsigned long section_size;
section_size = (unsigned long)_etext - (unsigned long)_text;
- create_mapping_late(__pa(_text), (unsigned long)_text,
+ create_mapping_late(__pa_symbol(_text), (unsigned long)_text,
section_size, PAGE_KERNEL_ROX);
/*
* mark .rodata as read only. Use __init_begin rather than __end_rodata
* to cover NOTES and EXCEPTION_TABLE.
*/
section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
- create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata,
+ create_mapping_late(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
section_size, PAGE_KERNEL_RO);
/* flush the TLBs after updating live kernel mappings */
@@ -417,7 +418,7 @@ void mark_rodata_ro(void)
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
pgprot_t prot, struct vm_struct *vma)
{
- phys_addr_t pa_start = __pa(va_start);
+ phys_addr_t pa_start = __pa_symbol(va_start);
unsigned long size = va_end - va_start;
BUG_ON(!PAGE_ALIGNED(pa_start));
@@ -527,7 +528,7 @@ void __init paging_init(void)
*/
cpu_replace_ttbr1(__va(pgd_phys));
memcpy(swapper_pg_dir, pgd, PGD_SIZE);
- cpu_replace_ttbr1(swapper_pg_dir);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
pgd_clear_fixmap();
memblock_free(pgd_phys, PAGE_SIZE);
@@ -536,7 +537,7 @@ void __init paging_init(void)
* We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
* allocated with it.
*/
- memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE,
+ memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
SWAPPER_DIR_SIZE - PAGE_SIZE);
}
@@ -647,6 +648,12 @@ static inline pte_t * fixmap_pte(unsigned long addr)
return &bm_pte[pte_index(addr)];
}
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). This function is called too early to use
+ * lm_alias so __p*d_populate functions must be used to populate with the
+ * physical address from __pa_symbol.
+ */
void __init early_fixmap_init(void)
{
pgd_t *pgd;
@@ -656,7 +663,7 @@ void __init early_fixmap_init(void)
pgd = pgd_offset_k(addr);
if (CONFIG_PGTABLE_LEVELS > 3 &&
- !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) {
+ !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) {
/*
* We only end up here if the kernel mapping and the fixmap
* share the top level pgd entry, which should only happen on
@@ -665,12 +672,14 @@ void __init early_fixmap_init(void)
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
pud = pud_offset_kimg(pgd, addr);
} else {
- pgd_populate(&init_mm, pgd, bm_pud);
+ if (pgd_none(*pgd))
+ __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
pud = fixmap_pud(addr);
}
- pud_populate(&init_mm, pud, bm_pmd);
+ if (pud_none(*pud))
+ __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
pmd = fixmap_pmd(addr);
- pmd_populate_kernel(&init_mm, pmd, bm_pte);
+ __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
/*
* The boot-ioremap range spans multiple pmds, for which
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 3b95e31..7df7082 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -64,18 +64,24 @@
mrs x2, tpidr_el0
mrs x3, tpidrro_el0
mrs x4, contextidr_el1
- mrs x5, osdlr_el1
- mrs x6, cpacr_el1
- mrs x7, tcr_el1
- mrs x8, vbar_el1
- mrs x9, mdscr_el1
- mrs x10, oslsr_el1
- mrs x11, sctlr_el1
+ mrs x5, cpacr_el1
+ mrs x6, tcr_el1
+ mrs x7, vbar_el1
+ mrs x8, mdscr_el1
+ mrs x9, oslsr_el1
+ mrs x10, sctlr_el1
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+ mrs x11, tpidr_el1
+alternative_else
+ mrs x11, tpidr_el2
+alternative_endif
+ mrs x12, sp_el0
stp x2, x3, [x0]
- stp x4, x5, [x0, #16]
- stp x6, x7, [x0, #32]
- stp x8, x9, [x0, #48]
- stp x10, x11, [x0, #64]
+ stp x4, xzr, [x0, #16]
+ stp x5, x6, [x0, #32]
+ stp x7, x8, [x0, #48]
+ stp x9, x10, [x0, #64]
+ stp x11, x12, [x0, #80]
ret
ENDPROC(cpu_do_suspend)
@@ -91,14 +97,15 @@
ldp x6, x8, [x0, #32]
ldp x9, x10, [x0, #48]
ldp x11, x12, [x0, #64]
+ ldp x13, x14, [x0, #80]
msr tpidr_el0, x2
msr tpidrro_el0, x3
msr contextidr_el1, x4
msr cpacr_el1, x6
/* Don't change t0sz here, mask those bits when restoring */
- mrs x7, tcr_el1
- bfi x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+ mrs x5, tcr_el1
+ bfi x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
msr tcr_el1, x8
msr vbar_el1, x9
@@ -113,10 +120,15 @@
msr mdscr_el1, x10
msr sctlr_el1, x12
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+ msr tpidr_el1, x13
+alternative_else
+ msr tpidr_el2, x13
+alternative_endif
+ msr sp_el0, x14
/*
* Restore oslsr_el1 by writing oslar_el1
*/
- msr osdlr_el1, x5
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
@@ -136,6 +148,9 @@
ENTRY(cpu_do_switch_mm)
mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ bfi x0, x1, #48, #16 // set the ASID field in TTBR0
+#endif
bfi x2, x1, #48, #16 // set the ASID
msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set)
isb
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 329c802..69711f2 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -49,6 +49,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/uaccess.h>
#include <xen/interface/xen.h>
@@ -91,6 +92,20 @@
mov x2, x3
mov x3, x4
mov x4, x5
+ /*
+ * Privcmd calls are issued by the userspace. The kernel needs to
+ * enable access to TTBR0_EL1 as the hypervisor would issue stage 1
+ * translations to user memory via AT instructions. Since AT
+ * instructions are not affected by the PAN bit (ARMv8.1), we only
+ * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
+ * is enabled (it implies that hardware UAO and PAN disabled).
+ */
+ uaccess_ttbr0_enable x6, x7, x8
hvc XEN_IMM
+
+ /*
+ * Disable userspace access from kernel once the hyp call completed.
+ */
+ uaccess_ttbr0_disable x6, x7
ret
ENDPROC(privcmd_call);
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 1fd147f..5f10f9b 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -90,4 +90,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index afbc98f0..ed960d3 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -90,5 +90,7 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 0018fad..9790d13 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -99,4 +99,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 5fe42fc..ad25676 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -90,4 +90,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 4e5aa2f..87160b4 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/module.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/kernel.h>
#include <linux/param.h>
#include <linux/string.h>
diff --git a/arch/microblaze/kernel/heartbeat.c b/arch/microblaze/kernel/heartbeat.c
index 4643e3a..2022130 100644
--- a/arch/microblaze/kernel/heartbeat.c
+++ b/arch/microblaze/kernel/heartbeat.c
@@ -9,6 +9,7 @@
*/
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/io.h>
#include <asm/setup.h>
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 2027240a..2f106d0 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -108,4 +108,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index 7c56d6b..0da0420 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -19,7 +19,6 @@
depends on HAVE_KVM
select EXPORT_UASM
select PREEMPT_NOTIFIERS
- select ANON_INODES
select KVM_MMIO
select SRCU
---help---
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 5129f23..69f9618 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -90,4 +90,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 9c935d7..b96a193 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -89,4 +89,6 @@
#define SO_CNX_ADVICE 0x402E
+#define SO_COOKIE 0x4032
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 1672e33..e78550f 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -97,4 +97,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 029be26..f2ef083 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -19,7 +19,6 @@
config KVM
bool
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_EVENTFD
select SRCU
select KVM_VFIO
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 88301e5..5d8e8b6 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -22,6 +22,7 @@
#include <linux/cpufreq.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
@@ -48,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info)
cpu = info->policy->cpu;
busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
- CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1);
+ info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1);
pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n",
cpu, busy_spus, info->busy_spus);
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 460f5f3..1149c34 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -24,6 +24,7 @@
#include <linux/errno.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/sched/rt.h>
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -986,9 +987,9 @@ static void spu_calc_load(void)
unsigned long active_tasks; /* fixed-point */
active_tasks = count_active_contexts() * FIXED_1;
- CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks);
- CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks);
- CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks);
+ spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks);
+ spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks);
+ spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks);
}
static void spusched_wake(unsigned long data)
@@ -1070,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx,
}
}
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
static int show_spu_loadavg(struct seq_file *s, void *private)
{
int a, b, c;
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index b5ff5ee..316eded 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -713,7 +713,7 @@ static void cmm_exit(void)
* Return value:
* 0 on success / other on failure
**/
-static int cmm_set_disable(const char *val, struct kernel_param *kp)
+static int cmm_set_disable(const char *val, const struct kernel_param *kp)
{
int disable = simple_strtoul(val, NULL, 10);
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 08b9e94..731dc7e 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -17,15 +17,12 @@
#include <linux/kernel_stat.h>
#include <linux/netdevice.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <asm/appldata.h>
#include <asm/smp.h>
#include "appldata.h"
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
/*
* OS data
*
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 41b51c2..04fe908 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -96,4 +96,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index b190023..f9b9d15 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -20,7 +20,6 @@
prompt "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_EVENTFD
select KVM_ASYNC_PF
diff --git a/arch/sh/drivers/heartbeat.c b/arch/sh/drivers/heartbeat.c
index 49bace4..c6d9604 100644
--- a/arch/sh/drivers/heartbeat.c
+++ b/arch/sh/drivers/heartbeat.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/timer.h>
#include <linux/io.h>
#include <linux/slab.h>
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 31aede3..de15f0a 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -86,6 +86,8 @@
#define SO_CNX_ADVICE 0x0037
+#define SO_COOKIE 0x003b
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c
index 3ae36f3..44a3ed9 100644
--- a/arch/sparc/kernel/led.c
+++ b/arch/sparc/kernel/led.c
@@ -8,6 +8,7 @@
#include <linux/jiffies.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
+#include <linux/sched/loadavg.h>
#include <asm/auxio.h>
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 4714061..0ae73ee 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -112,7 +112,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->pc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 643c149..8c85aaf 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -152,7 +152,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->tpc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ad8f206..68cf65f 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -149,7 +149,7 @@ static void show_segv_info(struct uml_pt_regs *regs)
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
(void *)UPT_IP(regs), (void *)UPT_SP(regs),
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 80636ca..c977d45 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,7 +19,6 @@
def_bool y
select ACPI_LEGACY_TABLES_LOOKUP if ACPI
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ANON_INODES
select ARCH_CLOCKSOURCE_DATA
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 940ed27..47be4f5 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -111,6 +111,8 @@
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
+ KBUILD_CFLAGS += -fno-pic
+
# By default gcc and clang use a stack alignment of 16 bytes for x86.
# However the standard kernel entry on x86-64 leaves the stack on an
# 8-byte boundary. If the compiler isn't informed about the actual
diff --git a/arch/x86/configs/i386_ranchu_defconfig b/arch/x86/configs/i386_ranchu_defconfig
new file mode 100644
index 0000000..f691e2e
--- /dev/null
+++ b/arch/x86/configs/i386_ranchu_defconfig
@@ -0,0 +1,423 @@
+# CONFIG_64BIT is not set
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ARCH_MMAP_RND_BITS=16
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_SMP=y
+CONFIG_X86_BIGSMP=y
+CONFIG_MCORE2=y
+CONFIG_X86_GENERIC=y
+CONFIG_HPET_TIMER=y
+CONFIG_NR_CPUS=512
+CONFIG_PREEMPT=y
+# CONFIG_X86_MCE is not set
+CONFIG_X86_REBOOTFIXUPS=y
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
+CONFIG_KSM=y
+CONFIG_CMA=y
+# CONFIG_MTRR_SANITIZER is not set
+CONFIG_EFI=y
+CONFIG_EFI_STUB=y
+CONFIG_HZ_100=y
+CONFIG_PHYSICAL_START=0x100000
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_CPU_FREQ=y
+# CONFIG_CPU_FREQ_STAT is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_PCIEASPM is not set
+CONFIG_PCCARD=y
+CONFIG_YENTA=y
+CONFIG_HOTPLUG_PCI=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_MAC80211_LEDS=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=16
+CONFIG_CONNECTOR=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_SPI_ATTRS=y
+CONFIG_SCSI_ISCSI_ATTRS=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_ATA_PIIX=y
+CONFIG_PATA_AMD=y
+CONFIG_PATA_OLDPIIX=y
+CONFIG_PATA_SCH=y
+CONFIG_PATA_MPIIX=y
+CONFIG_ATA_GENERIC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_DEBUG=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+CONFIG_BNX2=y
+CONFIG_TIGON3=y
+CONFIG_NET_TULIP=y
+CONFIG_E100=y
+CONFIG_E1000=y
+CONFIG_E1000E=y
+CONFIG_SKY2=y
+CONFIG_NE2K_PCI=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
+# CONFIG_8139TOO_PIO is not set
+CONFIG_R8169=y
+CONFIG_FDDI=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_USB_USBNET=y
+CONFIG_INPUT_POLLDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+# CONFIG_KEYBOARD_ATKBD is not set
+CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_INPUT_TABLET=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_NVRAM=y
+CONFIG_I2C_I801=y
+CONFIG_BATTERY_GOLDFISH=y
+CONFIG_WATCHDOG=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_AGP=y
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+CONFIG_DRM=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_FB_EFI=y
+CONFIG_FB_GOLDFISH=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_UHCI_HCD=y
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_EDAC=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+CONFIG_DMADEVICES=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SYNC_FILE=y
+CONFIG_ION=y
+CONFIG_GOLDFISH_AUDIO=y
+CONFIG_SND_HDA_INTEL=y
+CONFIG_GOLDFISH=y
+CONFIG_GOLDFISH_PIPE=y
+CONFIG_GOLDFISH_SYNC=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ISCSI_IBFT_FIND=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_FUSE_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=2048
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_SCHED_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+CONFIG_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_CRYPTO_AES_586=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_ASYMMETRIC_KEY_TYPE=y
+CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
+CONFIG_X509_CERTIFICATE_PARSER=y
+CONFIG_PKCS7_MESSAGE_PARSER=y
+CONFIG_PKCS7_TEST_KEY=y
+# CONFIG_VIRTUALIZATION is not set
+CONFIG_CRC_T10DIF=y
diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig
new file mode 100644
index 0000000..79dee74
--- /dev/null
+++ b/arch/x86/configs/x86_64_cuttlefish_defconfig
@@ -0,0 +1,507 @@
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_FHANDLE is not set
+# CONFIG_USELIB is not set
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_PSI=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_SCHEDTUNE=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_SCHED_TUNE=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_LZ4 is not set
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_PCSPKR_PLATFORM is not set
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_EMBEDDED=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
+CONFIG_CC_STACKPROTECTOR_STRONG=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_SMP=y
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
+CONFIG_PARAVIRT_SPINLOCKS=y
+CONFIG_MCORE2=y
+CONFIG_PROCESSOR_SELECT=y
+# CONFIG_CPU_SUP_CENTAUR is not set
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT=y
+# CONFIG_MICROCODE is not set
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
+CONFIG_DEFAULT_MMAP_MIN_ADDR=65536
+CONFIG_ZSMALLOC=y
+# CONFIG_MTRR is not set
+CONFIG_EFI=y
+CONFIG_HZ_100=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+CONFIG_PHYSICAL_START=0x200000
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_PHYSICAL_ALIGN=0x1000000
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="nopti"
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_ACPI_PROCFS_POWER=y
+# CONFIG_ACPI_FAN is not set
+# CONFIG_ACPI_THERMAL is not set
+# CONFIG_X86_PM_TIMER is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_X86_ACPI_CPUFREQ=y
+# CONFIG_X86_ACPI_CPUFREQ_CPB is not set
+CONFIG_PCI_MMCONFIG=y
+CONFIG_PCI_MSI=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=y
+CONFIG_IA32_EMULATION=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_XFRM_INTERFACE=y
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_NET_IPVTI=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
+CONFIG_INET_UDP_DIAG=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_VTI=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CT=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+# CONFIG_NETFILTER_XT_MATCH_L2TP is not set
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_MATCH_RPFILTER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_L2TP=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_CLS_BPF=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_VSOCKETS=y
+CONFIG_VIRTIO_VSOCKETS=y
+CONFIG_BPF_JIT=y
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_RFKILL=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEBUG_DEVRES=y
+CONFIG_OF=y
+CONFIG_OF_UNITTEST=y
+# CONFIG_PNP_DEBUG_MESSAGES is not set
+CONFIG_ZRAM=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_LOOP_MIN_COUNT=16
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_UID_SYS_STATS=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_SPI_ATTRS=y
+CONFIG_SCSI_VIRTIO=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_SNAPSHOT=y
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_DM_VERITY_AVB=y
+CONFIG_DM_BOW=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_NETCONSOLE_DYNAMIC=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_ETHERNET is not set
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPTP=y
+CONFIG_PPPOL2TP=y
+CONFIG_USB_RTL8152=y
+CONFIG_USB_USBNET=y
+# CONFIG_USB_NET_AX8817X is not set
+# CONFIG_USB_NET_AX88179_178A is not set
+# CONFIG_USB_NET_CDCETHER is not set
+# CONFIG_USB_NET_CDC_NCM is not set
+# CONFIG_USB_NET_NET1080 is not set
+# CONFIG_USB_NET_CDC_SUBSET is not set
+# CONFIG_USB_NET_ZAURUS is not set
+# CONFIG_WLAN_VENDOR_ADMTEK is not set
+# CONFIG_WLAN_VENDOR_ATH is not set
+# CONFIG_WLAN_VENDOR_ATMEL is not set
+# CONFIG_WLAN_VENDOR_BROADCOM is not set
+# CONFIG_WLAN_VENDOR_CISCO is not set
+# CONFIG_WLAN_VENDOR_INTEL is not set
+# CONFIG_WLAN_VENDOR_INTERSIL is not set
+# CONFIG_WLAN_VENDOR_MARVELL is not set
+# CONFIG_WLAN_VENDOR_MEDIATEK is not set
+# CONFIG_WLAN_VENDOR_RALINK is not set
+# CONFIG_WLAN_VENDOR_REALTEK is not set
+# CONFIG_WLAN_VENDOR_RSI is not set
+# CONFIG_WLAN_VENDOR_ST is not set
+# CONFIG_WLAN_VENDOR_TI is not set
+# CONFIG_WLAN_VENDOR_ZYDAS is not set
+CONFIG_MAC80211_HWSIM=y
+CONFIG_VIRT_WIFI=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_INPUT_TABLET=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_SERIO_I8042 is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=48
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
+# CONFIG_HW_RANDOM_VIA is not set
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_HPET=y
+# CONFIG_HPET_MMAP_DEFAULT is not set
+# CONFIG_DEVPORT is not set
+# CONFIG_ACPI_I2C_OPREGION is not set
+# CONFIG_I2C_COMPAT is not set
+# CONFIG_I2C_HELPER_AUTO is not set
+CONFIG_PTP_1588_CLOCK=y
+# CONFIG_HWMON is not set
+# CONFIG_X86_PKG_TEMP_THERMAL is not set
+CONFIG_WATCHDOG=y
+CONFIG_SOFT_WATCHDOG=y
+CONFIG_MEDIA_SUPPORT=y
+# CONFIG_DVB_TUNER_DIB0070 is not set
+# CONFIG_DVB_TUNER_DIB0090 is not set
+# CONFIG_VGA_ARB is not set
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_HRTIMER=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_VERBOSE_PROCFS is not set
+# CONFIG_SND_DRIVERS is not set
+CONFIG_SND_INTEL8X0=y
+# CONFIG_SND_USB is not set
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_DUMMY_HCD=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_MTP=y
+CONFIG_USB_CONFIGFS_F_PTP=y
+CONFIG_USB_CONFIGFS_F_ACC=y
+CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y
+CONFIG_USB_CONFIGFS_UEVENT=y
+CONFIG_USB_CONFIGFS_F_MIDI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_TEST=y
+CONFIG_SW_SYNC=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_INPUT=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_VSOC=y
+CONFIG_ION=y
+# CONFIG_X86_PLATFORM_DEVICES is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+# CONFIG_FIRMWARE_MEMMAP is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
+CONFIG_F2FS_FS=y
+CONFIG_F2FS_FS_SECURITY=y
+CONFIG_F2FS_FS_ENCRYPTION=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_QFMT_V2=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_FUSE_FS=y
+CONFIG_OVERLAY_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+# CONFIG_EFIVAR_FS is not set
+CONFIG_SDCARD_FS=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_UPROBE_EVENT=y
+CONFIG_DEBUG_SET_MODULE_RONX=y
+CONFIG_IO_DELAY_NONE=y
+CONFIG_DEBUG_BOOT_PARAMS=y
+CONFIG_OPTIMIZE_INLINING=y
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_PATH=y
+CONFIG_HARDENED_USERCOPY=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
+CONFIG_CRYPTO_RSA=y
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_ADIANTUM=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_AES_NI_INTEL=y
+CONFIG_CRYPTO_LZ4=y
+CONFIG_CRYPTO_ZSTD=y
+CONFIG_ASYMMETRIC_KEY_TYPE=y
+CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
+CONFIG_X509_CERTIFICATE_PARSER=y
+CONFIG_SYSTEM_TRUSTED_KEYRING=y
+CONFIG_SYSTEM_TRUSTED_KEYS="verity_dev_keys.x509"
diff --git a/arch/x86/configs/x86_64_ranchu_defconfig b/arch/x86/configs/x86_64_ranchu_defconfig
new file mode 100644
index 0000000..cafa3df
--- /dev/null
+++ b/arch/x86/configs/x86_64_ranchu_defconfig
@@ -0,0 +1,418 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_ARCH_MMAP_RND_BITS=32
+CONFIG_ARCH_MMAP_RND_COMPAT_BITS=16
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_SMP=y
+CONFIG_MCORE2=y
+CONFIG_MAXSMP=y
+CONFIG_PREEMPT=y
+# CONFIG_X86_MCE is not set
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
+CONFIG_KSM=y
+CONFIG_CMA=y
+# CONFIG_MTRR_SANITIZER is not set
+CONFIG_EFI=y
+CONFIG_EFI_STUB=y
+CONFIG_HZ_100=y
+CONFIG_PHYSICAL_START=0x100000
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_DEBUG=y
+CONFIG_CPU_FREQ=y
+# CONFIG_CPU_FREQ_STAT is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_PCI_MMCONFIG=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_PCIEASPM is not set
+CONFIG_PCCARD=y
+CONFIG_YENTA=y
+CONFIG_HOTPLUG_PCI=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=y
+CONFIG_IA32_EMULATION=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_ESP=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_OWNER=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_MAC80211_LEDS=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DMA_CMA=y
+CONFIG_CONNECTOR=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_SPI_ATTRS=y
+CONFIG_SCSI_ISCSI_ATTRS=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_ATA_PIIX=y
+CONFIG_PATA_AMD=y
+CONFIG_PATA_OLDPIIX=y
+CONFIG_PATA_SCH=y
+CONFIG_PATA_MPIIX=y
+CONFIG_ATA_GENERIC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_DEBUG=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
+CONFIG_BNX2=y
+CONFIG_TIGON3=y
+CONFIG_NET_TULIP=y
+CONFIG_E100=y
+CONFIG_E1000=y
+CONFIG_E1000E=y
+CONFIG_SKY2=y
+CONFIG_NE2K_PCI=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
+# CONFIG_8139TOO_PIO is not set
+CONFIG_R8169=y
+CONFIG_FDDI=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_USB_USBNET=y
+CONFIG_INPUT_POLLDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_KEYRESET=y
+# CONFIG_KEYBOARD_ATKBD is not set
+CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_INPUT_TABLET=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_DEVMEM is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_NVRAM=y
+CONFIG_I2C_I801=y
+CONFIG_BATTERY_GOLDFISH=y
+CONFIG_WATCHDOG=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_AGP=y
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+CONFIG_DRM=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_FB_EFI=y
+CONFIG_FB_GOLDFISH=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_HIDRAW=y
+CONFIG_UHID=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGIG940_FF=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_UHCI_HCD=y
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_EDAC=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+CONFIG_DMADEVICES=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_STAGING=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SYNC_FILE=y
+CONFIG_ION=y
+CONFIG_GOLDFISH_AUDIO=y
+CONFIG_SND_HDA_INTEL=y
+CONFIG_GOLDFISH=y
+CONFIG_GOLDFISH_PIPE=y
+CONFIG_GOLDFISH_SYNC=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ISCSI_IBFT_FIND=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_FUSE_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_SCHED_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+CONFIG_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_ASYMMETRIC_KEY_TYPE=y
+CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
+CONFIG_X509_CERTIFICATE_PARSER=y
+CONFIG_PKCS7_MESSAGE_PARSER=y
+CONFIG_PKCS7_TEST_KEY=y
+# CONFIG_VIRTUALIZATION is not set
+CONFIG_CRC_T10DIF=y
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 0a5fedf..4446688 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -10,7 +10,7 @@
*/
#include <crypto/algapi.h>
-#include <crypto/chacha20.h>
+#include <crypto/chacha.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
@@ -29,31 +29,31 @@ static bool chacha20_use_avx2;
static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes)
{
- u8 buf[CHACHA20_BLOCK_SIZE];
+ u8 buf[CHACHA_BLOCK_SIZE];
#ifdef CONFIG_AS_AVX2
if (chacha20_use_avx2) {
- while (bytes >= CHACHA20_BLOCK_SIZE * 8) {
+ while (bytes >= CHACHA_BLOCK_SIZE * 8) {
chacha20_8block_xor_avx2(state, dst, src);
- bytes -= CHACHA20_BLOCK_SIZE * 8;
- src += CHACHA20_BLOCK_SIZE * 8;
- dst += CHACHA20_BLOCK_SIZE * 8;
+ bytes -= CHACHA_BLOCK_SIZE * 8;
+ src += CHACHA_BLOCK_SIZE * 8;
+ dst += CHACHA_BLOCK_SIZE * 8;
state[12] += 8;
}
}
#endif
- while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+ while (bytes >= CHACHA_BLOCK_SIZE * 4) {
chacha20_4block_xor_ssse3(state, dst, src);
- bytes -= CHACHA20_BLOCK_SIZE * 4;
- src += CHACHA20_BLOCK_SIZE * 4;
- dst += CHACHA20_BLOCK_SIZE * 4;
+ bytes -= CHACHA_BLOCK_SIZE * 4;
+ src += CHACHA_BLOCK_SIZE * 4;
+ dst += CHACHA_BLOCK_SIZE * 4;
state[12] += 4;
}
- while (bytes >= CHACHA20_BLOCK_SIZE) {
+ while (bytes >= CHACHA_BLOCK_SIZE) {
chacha20_block_xor_ssse3(state, dst, src);
- bytes -= CHACHA20_BLOCK_SIZE;
- src += CHACHA20_BLOCK_SIZE;
- dst += CHACHA20_BLOCK_SIZE;
+ bytes -= CHACHA_BLOCK_SIZE;
+ src += CHACHA_BLOCK_SIZE;
+ dst += CHACHA_BLOCK_SIZE;
state[12]++;
}
if (bytes) {
@@ -70,24 +70,24 @@ static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
struct blkcipher_walk walk;
int err;
- if (nbytes <= CHACHA20_BLOCK_SIZE || !may_use_simd())
- return crypto_chacha20_crypt(desc, dst, src, nbytes);
+ if (nbytes <= CHACHA_BLOCK_SIZE || !may_use_simd())
+ return crypto_chacha_crypt(desc, dst, src, nbytes);
state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
blkcipher_walk_init(&walk, dst, src, nbytes);
- err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+ err = blkcipher_walk_virt_block(desc, &walk, CHACHA_BLOCK_SIZE);
desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
- crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+ crypto_chacha_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
kernel_fpu_begin();
- while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+ while (walk.nbytes >= CHACHA_BLOCK_SIZE) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
- rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+ rounddown(walk.nbytes, CHACHA_BLOCK_SIZE));
err = blkcipher_walk_done(desc, &walk,
- walk.nbytes % CHACHA20_BLOCK_SIZE);
+ walk.nbytes % CHACHA_BLOCK_SIZE);
}
if (walk.nbytes) {
@@ -108,14 +108,14 @@ static struct crypto_alg alg = {
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = 1,
.cra_type = &crypto_blkcipher_type,
- .cra_ctxsize = sizeof(struct chacha20_ctx),
+ .cra_ctxsize = sizeof(struct chacha_ctx),
.cra_alignmask = sizeof(u32) - 1,
.cra_module = THIS_MODULE,
.cra_u = {
.blkcipher = {
- .min_keysize = CHACHA20_KEY_SIZE,
- .max_keysize = CHACHA20_KEY_SIZE,
- .ivsize = CHACHA20_IV_SIZE,
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
.geniv = "seqiv",
.setkey = crypto_chacha20_setkey,
.encrypt = chacha20_simd,
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 28c3720..a69670b 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -83,35 +83,37 @@ static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) {
if (unlikely(!sctx->wset)) {
if (!sctx->uset) {
- memcpy(sctx->u, dctx->r, sizeof(sctx->u));
- poly1305_simd_mult(sctx->u, dctx->r);
+ memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
+ poly1305_simd_mult(sctx->u, dctx->r.r);
sctx->uset = true;
}
memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u));
- poly1305_simd_mult(sctx->u + 5, dctx->r);
+ poly1305_simd_mult(sctx->u + 5, dctx->r.r);
memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u));
- poly1305_simd_mult(sctx->u + 10, dctx->r);
+ poly1305_simd_mult(sctx->u + 10, dctx->r.r);
sctx->wset = true;
}
blocks = srclen / (POLY1305_BLOCK_SIZE * 4);
- poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u);
+ poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks,
+ sctx->u);
src += POLY1305_BLOCK_SIZE * 4 * blocks;
srclen -= POLY1305_BLOCK_SIZE * 4 * blocks;
}
#endif
if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
if (unlikely(!sctx->uset)) {
- memcpy(sctx->u, dctx->r, sizeof(sctx->u));
- poly1305_simd_mult(sctx->u, dctx->r);
+ memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
+ poly1305_simd_mult(sctx->u, dctx->r.r);
sctx->uset = true;
}
blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
- poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u);
+ poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks,
+ sctx->u);
src += POLY1305_BLOCK_SIZE * 2 * blocks;
srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
- poly1305_block_sse2(dctx->h, src, dctx->r, 1);
+ poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1);
srclen -= POLY1305_BLOCK_SIZE;
}
return srclen;
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 8841d01..ed319b0 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -22,6 +22,7 @@
#include <linux/user-return-notifier.h>
#include <linux/nospec.h>
#include <linux/uprobes.h>
+#include <linux/syscalls.h>
#include <asm/desc.h>
#include <asm/traps.h>
@@ -181,6 +182,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
struct thread_info *ti = current_thread_info();
u32 cached_flags;
+ addr_limit_user_check();
+
if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
local_irq_disable();
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c864245..cfb1f34 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -631,13 +631,8 @@
#endif
/* Make sure APIC interrupt handlers end up in the irqentry section: */
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
-# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
-# define POP_SECTION_IRQENTRY .popsection
-#else
-# define PUSH_SECTION_IRQENTRY
-# define POP_SECTION_IRQENTRY
-#endif
+#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+#define POP_SECTION_IRQENTRY .popsection
.macro apicinterrupt num sym do_sym
PUSH_SECTION_IRQENTRY
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2b36185..d2e3f29 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -389,3 +389,5 @@
380 i386 pkey_mprotect sys_pkey_mprotect
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
+424 i386 pidfd_send_signal sys_pidfd_send_signal
+434 i386 pidfd_open sys_pidfd_open
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index e93ef0b..db0315d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -338,6 +338,8 @@
329 common pkey_mprotect sys_pkey_mprotect
330 common pkey_alloc sys_pkey_alloc
331 common pkey_free sys_pkey_free
+424 common pidfd_send_signal sys_pidfd_send_signal
+434 common pidfd_open sys_pidfd_open
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index deca9b9..6665000 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -218,10 +218,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
{ \
- register void *__sp asm(_ASM_SP); \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
- : output, "+r" (__sp) \
+ : output, ASM_CALL_CONSTRAINT \
: [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input); \
}
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index c5d1785..02bab09 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -1,13 +1,6 @@
#ifndef _ASM_X86_IDLE_H
#define _ASM_X86_IDLE_H
-#define IDLE_START 1
-#define IDLE_END 2
-
-struct notifier_block;
-void idle_notifier_register(struct notifier_block *n);
-void idle_notifier_unregister(struct notifier_block *n);
-
#ifdef CONFIG_X86_64
void enter_idle(void);
void exit_idle(void);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 04b7971..98dbad6 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -462,8 +462,8 @@ int paravirt_disable_iospace(void);
*/
#ifdef CONFIG_X86_32
#define PVOP_VCALL_ARGS \
- unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \
- register void *__sp asm("esp")
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
@@ -483,8 +483,8 @@ int paravirt_disable_iospace(void);
/* [re]ax isn't an arg, but the return val */
#define PVOP_VCALL_ARGS \
unsigned long __edi = __edi, __esi = __esi, \
- __edx = __edx, __ecx = __ecx, __eax = __eax; \
- register void *__sp asm("rsp")
+ __edx = __edx, __ecx = __ecx, __eax = __eax;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
@@ -523,7 +523,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -533,7 +533,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -560,7 +560,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 17f2186..4939f6e 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -94,19 +94,14 @@ static __always_inline bool should_resched(int preempt_offset)
#ifdef CONFIG_PREEMPT
extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \
-})
+# define __preempt_schedule() \
+ asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT)
extern asmlinkage void preempt_schedule(void);
extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \
-})
+# define __preempt_schedule_notrace() \
+ asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT)
+
extern asmlinkage void preempt_schedule_notrace(void);
#endif
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index a34e0d4..7116b79 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -103,7 +103,6 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
({ \
long tmp; \
struct rw_semaphore* ret; \
- register void *__sp asm(_ASM_SP); \
\
asm volatile("# beginning down_write\n\t" \
LOCK_PREFIX " xadd %1,(%4)\n\t" \
@@ -114,7 +113,8 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
" call " slow_path "\n" \
"1:\n" \
"# ending down_write" \
- : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
+ : "+m" (sem->count), "=d" (tmp), \
+ "=a" (ret), ASM_CALL_CONSTRAINT \
: "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
: "memory", "cc"); \
ret; \
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 0438f7f..34191cf 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -103,6 +103,7 @@ struct thread_info {
#define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */
#define TIF_ADDR32 29 /* 32-bit address space on 64 bits */
#define TIF_X32 30 /* 32-bit native x86-64 binary */
+#define TIF_FSCHECK 31 /* Check FS is USER_DS on return */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
@@ -128,6 +129,7 @@ struct thread_info {
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
#define _TIF_ADDR32 (1 << TIF_ADDR32)
#define _TIF_X32 (1 << TIF_X32)
+#define _TIF_FSCHECK (1 << TIF_FSCHECK)
/*
* work to do in syscall_trace_enter(). Also includes TIF_NOHZ for
@@ -141,7 +143,7 @@ struct thread_info {
/* work to do on any return to user space */
#define _TIF_ALLWORK_MASK \
((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \
- _TIF_NOHZ)
+ _TIF_NOHZ | _TIF_FSCHECK)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW_BASE \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 9db8d87..d1ddcc0 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -8,6 +8,7 @@
#include <linux/kasan-checks.h>
#include <linux/thread_info.h>
#include <linux/string.h>
+#include <linux/sched.h>
#include <asm/asm.h>
#include <asm/page.h>
#include <asm/smap.h>
@@ -31,7 +32,12 @@
#define get_ds() (KERNEL_DS)
#define get_fs() (current->thread.addr_limit)
-#define set_fs(x) (current->thread.addr_limit = (x))
+static inline void set_fs(mm_segment_t fs)
+{
+ current->thread.addr_limit = fs;
+ /* On user-mode return, check fs is correct */
+ set_thread_flag(TIF_FSCHECK);
+}
#define segment_eq(a, b) ((a).seg == (b).seg)
@@ -171,11 +177,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
({ \
int __ret_gu; \
register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
- register void *__sp asm(_ASM_SP); \
__chk_user_ptr(ptr); \
might_fault(); \
asm volatile("call __get_user_%P4" \
- : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \
+ : "=a" (__ret_gu), "=r" (__val_gu), \
+ ASM_CALL_CONSTRAINT \
: "0" (ptr), "i" (sizeof(*(ptr)))); \
(x) = (__force __typeof__(*(ptr))) __val_gu; \
__builtin_expect(__ret_gu, 0); \
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 9f69453..79183bc 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -112,10 +112,9 @@ extern struct { char _entry[32]; } hypercall_page[];
register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
- register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
- register void *__sp asm(_ASM_SP);
+ register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
-#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp)
+#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT
#define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1)
#define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2)
#define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 03b6e5c..f7430d8 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -287,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
tgt_rip = next_rip + o_dspl;
n_dspl = tgt_rip - orig_insn;
- DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+ DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl);
if (tgt_rip - orig_insn >= 0) {
if (n_dspl - 2 <= 127)
@@ -341,7 +341,7 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
sync_core();
local_irq_restore(flags);
- DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+ DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
instr, a->instrlen - a->padlen, a->padlen);
}
@@ -359,7 +359,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
- DPRINTK("alt table %p -> %p", start, end);
+ DPRINTK("alt table %px, -> %px", start, end);
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
@@ -383,14 +383,14 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
continue;
}
- DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d",
+ DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
a->cpuid >> 5,
a->cpuid & 0x1f,
instr, a->instrlen,
replacement, a->replacementlen, a->padlen);
- DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
- DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
+ DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
+ DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
@@ -411,7 +411,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
a->instrlen - a->replacementlen);
insnbuf_sz += a->instrlen - a->replacementlen;
}
- DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
+ DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr);
text_poke_early(instr, insnbuf, insnbuf_sz);
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f58e4cc..fcc5dfb 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -70,19 +70,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_tss);
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
- atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
- atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
#endif
/*
@@ -452,14 +439,14 @@ static inline void play_dead(void)
void enter_idle(void)
{
this_cpu_write(is_idle, 1);
- atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+ idle_notifier_call_chain(IDLE_START);
}
static void __exit_idle(void)
{
if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
return;
- atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+ idle_notifier_call_chain(IDLE_END);
}
/* Called from interrupts to signify idle end */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 9150e09..9467d4f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -26,7 +26,6 @@
depends on X86_LOCAL_APIC
select PREEMPT_NOTIFIERS
select MMU_NOTIFIER
- select ANON_INODES
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQFD
select IRQ_BYPASS_MANAGER
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 622e5a7..da44308 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8887,7 +8887,6 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- register void *__sp asm(_ASM_SP);
/*
* If external interrupt exists, IF bit is set in rflags/eflags on the
@@ -8921,7 +8920,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
:
THUNK_TARGET(entry),
[ss]"i"(__KERNEL_DS),
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 102b4e7..fc841d9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -775,7 +775,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
if (is_vmalloc_addr((void *)address) &&
(((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
- register void *__sp asm("rsp");
unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
/*
* We're likely to be running with very little stack space
@@ -790,7 +789,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
asm volatile ("movq %[stack], %%rsp\n\t"
"call handle_stack_overflow\n\t"
"1: jmp 1b"
- : "+r" (__sp)
+ : ASM_CALL_CONSTRAINT
: "D" ("kernel stack overflow (page fault)"),
"S" (regs), "d" (address),
[stack] "rm" (stack));
@@ -854,7 +853,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->ip, (void *)regs->sp, error_code);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 842ca3c..18f9dad 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -615,7 +615,7 @@ enum __force_cpu_type {
static int force_cpu_type;
-static int set_cpu_type(const char *str, struct kernel_param *kp)
+static int set_cpu_type(const char *str, const struct kernel_param *kp)
{
if (!strcmp(str, "timer")) {
force_cpu_type = timer;
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 81435d9..fc7ca28 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -101,4 +101,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/block/bio.c b/block/bio.c
index 4c18a68..0c03c47 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -849,6 +849,9 @@ int bio_add_page(struct bio *bio, struct page *page,
bio->bi_vcnt++;
done:
bio->bi_iter.bi_size += len;
+
+ if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
+ bio_set_flag(bio, BIO_WORKINGSET);
return len;
}
EXPORT_SYMBOL(bio_add_page);
diff --git a/block/blk-core.c b/block/blk-core.c
index 4987f31..4eaa148 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,6 +33,7 @@
#include <linux/ratelimit.h>
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>
+#include <linux/psi.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
@@ -40,6 +41,8 @@
#include "blk.h"
#include "blk-mq.h"
+#include <linux/math64.h>
+
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
@@ -2092,6 +2095,10 @@ EXPORT_SYMBOL(generic_make_request);
*/
blk_qc_t submit_bio(struct bio *bio)
{
+ bool workingset_read = false;
+ unsigned long pflags;
+ blk_qc_t ret;
+
/*
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
@@ -2107,6 +2114,8 @@ blk_qc_t submit_bio(struct bio *bio)
if (op_is_write(bio_op(bio))) {
count_vm_events(PGPGOUT, count);
} else {
+ if (bio_flagged(bio, BIO_WORKINGSET))
+ workingset_read = true;
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
@@ -2122,7 +2131,21 @@ blk_qc_t submit_bio(struct bio *bio)
}
}
- return generic_make_request(bio);
+ /*
+ * If we're reading data that is part of the userspace
+ * workingset, count submission time as memory stall. When the
+ * device is congested, or the submitting cgroup IO-throttled,
+ * submission can be a significant part of overall IO time.
+ */
+ if (workingset_read)
+ psi_memstall_enter(&pflags);
+
+ ret = generic_make_request(bio);
+
+ if (workingset_read)
+ psi_memstall_leave(&pflags);
+
+ return ret;
}
EXPORT_SYMBOL(submit_bio);
@@ -3573,3 +3596,52 @@ int __init blk_dev_init(void)
return 0;
}
+
+/*
+ * Blk IO latency support. We want this to be as cheap as possible, so doing
+ * this lockless (and avoiding atomics), a few off by a few errors in this
+ * code is not harmful, and we don't want to do anything that is
+ * perf-impactful.
+ * TODO : If necessary, we can make the histograms per-cpu and aggregate
+ * them when printing them out.
+ */
+ssize_t
+blk_latency_hist_show(char* name, struct io_latency_state *s, char *buf,
+ int buf_size)
+{
+ int i;
+ int bytes_written = 0;
+ u_int64_t num_elem, elem;
+ int pct;
+ u_int64_t average;
+
+ num_elem = s->latency_elems;
+ if (num_elem > 0) {
+ average = div64_u64(s->latency_sum, s->latency_elems);
+ bytes_written += scnprintf(buf + bytes_written,
+ buf_size - bytes_written,
+ "IO svc_time %s Latency Histogram (n = %llu,"
+ " average = %llu):\n", name, num_elem, average);
+ for (i = 0;
+ i < ARRAY_SIZE(latency_x_axis_us);
+ i++) {
+ elem = s->latency_y_axis[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t< %6lluus%15llu%15d%%\n",
+ latency_x_axis_us[i],
+ elem, pct);
+ }
+ /* Last element in y-axis table is overflow */
+ elem = s->latency_y_axis[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t>=%6lluus%15llu%15d%%\n",
+ latency_x_axis_us[i - 1], elem, pct);
+ }
+
+ return bytes_written;
+}
+EXPORT_SYMBOL(blk_latency_hist_show);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0d644f3..df2e5eb 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -249,6 +249,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
limits->max_sectors = max_sectors;
+ q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL(blk_queue_max_hw_sectors);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9cc8d7c..ea374e8 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -212,6 +212,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
spin_lock_irq(q->queue_lock);
q->limits.max_sectors = max_sectors_kb << 1;
+ q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
spin_unlock_irq(q->queue_lock);
return ret;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index a4e2d01..650d69e 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -222,6 +222,7 @@ struct cfq_group_data {
unsigned int weight;
unsigned int leaf_weight;
+ u64 group_idle;
};
/* This is per cgroup per device grouping structure */
@@ -307,6 +308,7 @@ struct cfq_group {
struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
struct cfq_queue *async_idle_cfqq;
+ u64 group_idle;
};
struct cfq_io_cq {
@@ -803,6 +805,17 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
+static inline u64 get_group_idle(struct cfq_data *cfqd)
+{
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ struct cfq_queue *cfqq = cfqd->active_queue;
+
+ if (cfqq && cfqq->cfqg)
+ return cfqq->cfqg->group_idle;
+#endif
+ return cfqd->cfq_group_idle;
+}
+
#define cfq_log(cfqd, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -823,7 +836,7 @@ static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
if (!sample_valid(ttime->ttime_samples))
return false;
if (group_idle)
- slice = cfqd->cfq_group_idle;
+ slice = get_group_idle(cfqd);
else
slice = cfqd->cfq_slice_idle;
return ttime->ttime_mean > slice;
@@ -1626,6 +1639,7 @@ static void cfq_cpd_init(struct blkcg_policy_data *cpd)
cgd->weight = weight;
cgd->leaf_weight = weight;
+ cgd->group_idle = cfq_group_idle;
}
static void cfq_cpd_free(struct blkcg_policy_data *cpd)
@@ -1670,6 +1684,7 @@ static void cfq_pd_init(struct blkg_policy_data *pd)
cfqg->weight = cgd->weight;
cfqg->leaf_weight = cgd->leaf_weight;
+ cfqg->group_idle = cgd->group_idle;
}
static void cfq_pd_offline(struct blkg_policy_data *pd)
@@ -1791,6 +1806,19 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
return 0;
}
+static int cfq_print_group_idle(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+ u64 val = 0;
+
+ if (cgd)
+ val = cgd->group_idle;
+
+ seq_printf(sf, "%llu\n", div_u64(val, NSEC_PER_USEC));
+ return 0;
+}
+
static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off,
bool on_dfl, bool is_leaf_weight)
@@ -1912,6 +1940,37 @@ static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
return __cfq_set_weight(css, val, false, false, true);
}
+static int cfq_set_group_idle(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
+{
+ struct blkcg *blkcg = css_to_blkcg(css);
+ struct cfq_group_data *cfqgd;
+ struct blkcg_gq *blkg;
+ int ret = 0;
+
+ spin_lock_irq(&blkcg->lock);
+ cfqgd = blkcg_to_cfqgd(blkcg);
+ if (!cfqgd) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ cfqgd->group_idle = val * NSEC_PER_USEC;
+
+ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+ struct cfq_group *cfqg = blkg_to_cfqg(blkg);
+
+ if (!cfqg)
+ continue;
+
+ cfqg->group_idle = cfqgd->group_idle;
+ }
+
+out:
+ spin_unlock_irq(&blkcg->lock);
+ return ret;
+}
+
static int cfqg_print_stat(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
@@ -2057,6 +2116,11 @@ static struct cftype cfq_blkcg_legacy_files[] = {
.seq_show = cfq_print_leaf_weight,
.write_u64 = cfq_set_leaf_weight,
},
+ {
+ .name = "group_idle",
+ .seq_show = cfq_print_group_idle,
+ .write_u64 = cfq_set_group_idle,
+ },
/* statistics, covers only the tasks in the cfqg */
{
@@ -2952,7 +3016,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
* with sync vs async workloads.
*/
if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag &&
- !cfqd->cfq_group_idle)
+ !get_group_idle(cfqd))
return;
WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
@@ -2963,9 +3027,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
*/
if (!cfq_should_idle(cfqd, cfqq)) {
/* no queue idling. Check for group idling */
- if (cfqd->cfq_group_idle)
- group_idle = cfqd->cfq_group_idle;
- else
+ group_idle = get_group_idle(cfqd);
+ if (!group_idle)
return;
}
@@ -3006,7 +3069,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
cfq_mark_cfqq_wait_request(cfqq);
if (group_idle)
- sl = cfqd->cfq_group_idle;
+ sl = group_idle;
else
sl = cfqd->cfq_slice_idle;
@@ -3355,7 +3418,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
* this group, wait for requests to complete.
*/
check_group_idle:
- if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 &&
+ if (get_group_idle(cfqd) && cfqq->cfqg->nr_cfqq == 1 &&
cfqq->cfqg->dispatched &&
!cfq_io_thinktime_big(cfqd, &cfqq->cfqg->ttime, true)) {
cfqq = NULL;
@@ -3914,7 +3977,7 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
cfqd->cfq_slice_idle);
}
#ifdef CONFIG_CFQ_GROUP_IOSCHED
- __cfq_update_io_thinktime(&cfqq->cfqg->ttime, cfqd->cfq_group_idle);
+ __cfq_update_io_thinktime(&cfqq->cfqg->ttime, get_group_idle(cfqd));
#endif
}
@@ -4308,7 +4371,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
if (cfq_should_wait_busy(cfqd, cfqq)) {
u64 extend_sl = cfqd->cfq_slice_idle;
if (!cfqd->cfq_slice_idle)
- extend_sl = cfqd->cfq_group_idle;
+ extend_sl = get_group_idle(cfqd);
cfqq->slice_end = now + extend_sl;
cfq_mark_cfqq_wait_busy(cfqq);
cfq_log_cfqq(cfqd, cfqq, "will busy wait");
diff --git a/build.config.aarch64 b/build.config.aarch64
new file mode 100644
index 0000000..357db02
--- /dev/null
+++ b/build.config.aarch64
@@ -0,0 +1,12 @@
+ARCH=arm64
+
+CLANG_TRIPLE=aarch64-linux-gnu-
+CROSS_COMPILE=aarch64-linux-androidkernel-
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/aarch64/aarch64-linux-android-4.9/bin
+
+FILES="
+arch/arm64/boot/Image
+arch/arm64/boot/Image.gz
+vmlinux
+System.map
+"
diff --git a/build.config.common b/build.config.common
new file mode 100644
index 0000000..c9e1655
--- /dev/null
+++ b/build.config.common
@@ -0,0 +1,8 @@
+BRANCH=android-4.9-q
+KERNEL_DIR=common
+
+CC=clang
+CLANG_PREBUILT_BIN=prebuilts-master/clang/host/linux-x86/clang-r365631c/bin
+
+EXTRA_CMDS=''
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.cuttlefish.aarch64 b/build.config.cuttlefish.aarch64
new file mode 100644
index 0000000..0cb6019
--- /dev/null
+++ b/build.config.cuttlefish.aarch64
@@ -0,0 +1,5 @@
+. ${ROOT_DIR}/common/build.config.common
+. ${ROOT_DIR}/common/build.config.aarch64
+
+DEFCONFIG=cuttlefish_defconfig
+POST_DEFCONFIG_CMDS="check_defconfig"
diff --git a/build.config.cuttlefish.x86_64 b/build.config.cuttlefish.x86_64
new file mode 100644
index 0000000..fed773c
--- /dev/null
+++ b/build.config.cuttlefish.x86_64
@@ -0,0 +1,5 @@
+. ${ROOT_DIR}/common/build.config.common
+. ${ROOT_DIR}/common/build.config.x86_64
+
+DEFCONFIG=x86_64_cuttlefish_defconfig
+POST_DEFCONFIG_CMDS="check_defconfig"
diff --git a/build.config.goldfish.arm b/build.config.goldfish.arm
new file mode 100644
index 0000000..ff5646a
--- /dev/null
+++ b/build.config.goldfish.arm
@@ -0,0 +1,13 @@
+ARCH=arm
+BRANCH=android-4.4
+CROSS_COMPILE=arm-linux-androidkernel-
+DEFCONFIG=ranchu_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/arm/arm-linux-androideabi-4.9/bin
+FILES="
+arch/arm/boot/zImage
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.goldfish.arm64 b/build.config.goldfish.arm64
new file mode 100644
index 0000000..4c896a6
--- /dev/null
+++ b/build.config.goldfish.arm64
@@ -0,0 +1,13 @@
+ARCH=arm64
+BRANCH=android-4.4
+CROSS_COMPILE=aarch64-linux-android-
+DEFCONFIG=ranchu64_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/aarch64/aarch64-linux-android-4.9/bin
+FILES="
+arch/arm64/boot/Image
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.goldfish.mips b/build.config.goldfish.mips
new file mode 100644
index 0000000..9a14a44
--- /dev/null
+++ b/build.config.goldfish.mips
@@ -0,0 +1,12 @@
+ARCH=mips
+BRANCH=android-4.4
+CROSS_COMPILE=mips64el-linux-android-
+DEFCONFIG=ranchu_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/mips/mips64el-linux-android-4.9/bin
+FILES="
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.goldfish.mips64 b/build.config.goldfish.mips64
new file mode 100644
index 0000000..6ad9759
--- /dev/null
+++ b/build.config.goldfish.mips64
@@ -0,0 +1,12 @@
+ARCH=mips
+BRANCH=android-4.4
+CROSS_COMPILE=mips64el-linux-android-
+DEFCONFIG=ranchu64_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/mips/mips64el-linux-android-4.9/bin
+FILES="
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.goldfish.x86 b/build.config.goldfish.x86
new file mode 100644
index 0000000..2266c62
--- /dev/null
+++ b/build.config.goldfish.x86
@@ -0,0 +1,13 @@
+ARCH=x86
+BRANCH=android-4.4
+CROSS_COMPILE=x86_64-linux-android-
+DEFCONFIG=i386_ranchu_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin
+FILES="
+arch/x86/boot/bzImage
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.goldfish.x86_64 b/build.config.goldfish.x86_64
new file mode 100644
index 0000000..08c42c2
--- /dev/null
+++ b/build.config.goldfish.x86_64
@@ -0,0 +1,13 @@
+ARCH=x86_64
+BRANCH=android-4.4
+CROSS_COMPILE=x86_64-linux-android-
+DEFCONFIG=x86_64_ranchu_defconfig
+EXTRA_CMDS=''
+KERNEL_DIR=common
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin
+FILES="
+arch/x86/boot/bzImage
+vmlinux
+System.map
+"
+STOP_SHIP_TRACEPRINTK=1
diff --git a/build.config.x86_64 b/build.config.x86_64
new file mode 100644
index 0000000..df73a47
--- /dev/null
+++ b/build.config.x86_64
@@ -0,0 +1,11 @@
+ARCH=x86_64
+
+CLANG_TRIPLE=x86_64-linux-gnu-
+CROSS_COMPILE=x86_64-linux-androidkernel-
+LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin
+
+FILES="
+arch/x86/boot/bzImage
+vmlinux
+System.map
+"
diff --git a/certs/system_keyring.c b/certs/system_keyring.c
index 2476650..8cde8ea 100644
--- a/certs/system_keyring.c
+++ b/certs/system_keyring.c
@@ -241,5 +241,46 @@ int verify_pkcs7_signature(const void *data, size_t len,
return ret;
}
EXPORT_SYMBOL_GPL(verify_pkcs7_signature);
-
#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
+
+/**
+ * verify_signature_one - Verify a signature with keys from given keyring
+ * @sig: The signature to be verified
+ * @trusted_keys: Trusted keys to use (NULL for builtin trusted keys only,
+ * (void *)1UL for all trusted keys).
+ * @keyid: key description (not partial)
+ */
+int verify_signature_one(const struct public_key_signature *sig,
+ struct key *trusted_keys, const char *keyid)
+{
+ key_ref_t ref;
+ struct key *key;
+ int ret;
+
+ if (!sig)
+ return -EBADMSG;
+ if (!trusted_keys) {
+ trusted_keys = builtin_trusted_keys;
+ } else if (trusted_keys == (void *)1UL) {
+#ifdef CONFIG_SECONDARY_TRUSTED_KEYRING
+ trusted_keys = secondary_trusted_keys;
+#else
+ trusted_keys = builtin_trusted_keys;
+#endif
+ }
+
+ ref = keyring_search(make_key_ref(trusted_keys, 1),
+ &key_type_asymmetric, keyid);
+ if (IS_ERR(ref)) {
+ pr_err("Asymmetric key (%s) not found in keyring(%s)\n",
+ keyid, trusted_keys->description);
+ return -ENOKEY;
+ }
+
+ key = key_ref_to_ptr(ref);
+ ret = verify_signature(key, sig);
+ key_put(key);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(verify_signature_one);
+
diff --git a/crypto/Kconfig b/crypto/Kconfig
index ab0d93a..60ece1b 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -372,6 +372,34 @@
Support for key wrapping (NIST SP800-38F / RFC3394) without
padding.
+config CRYPTO_NHPOLY1305
+ tristate
+ select CRYPTO_HASH
+ select CRYPTO_POLY1305
+
+config CRYPTO_ADIANTUM
+ tristate "Adiantum support"
+ select CRYPTO_CHACHA20
+ select CRYPTO_POLY1305
+ select CRYPTO_NHPOLY1305
+ help
+ Adiantum is a tweakable, length-preserving encryption mode
+ designed for fast and secure disk encryption, especially on
+ CPUs without dedicated crypto instructions. It encrypts
+ each sector using the XChaCha12 stream cipher, two passes of
+ an ε-almost-∆-universal hash function, and an invocation of
+ the AES-256 block cipher on a single 16-byte block. On CPUs
+ without AES instructions, Adiantum is much faster than
+ AES-XTS.
+
+ Adiantum's security is provably reducible to that of its
+ underlying stream and block ciphers, subject to a security
+ bound. Unlike XTS, Adiantum is a true wide-block encryption
+ mode, so it actually provides an even stronger notion of
+ security than XTS, subject to the security bound.
+
+ If unsure, say N.
+
comment "Hash modes"
config CRYPTO_CMAC
@@ -1301,18 +1329,26 @@
Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
config CRYPTO_CHACHA20
- tristate "ChaCha20 cipher algorithm"
+ tristate "ChaCha stream cipher algorithms"
select CRYPTO_BLKCIPHER
help
- ChaCha20 cipher algorithm, RFC7539.
+ The ChaCha20, XChaCha20, and XChaCha12 stream cipher algorithms.
ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
Bernstein and further specified in RFC7539 for use in IETF protocols.
- This is the portable C implementation of ChaCha20.
-
- See also:
+ This is the portable C implementation of ChaCha20. See also:
<http://cr.yp.to/chacha/chacha-20080128.pdf>
+ XChaCha20 is the application of the XSalsa20 construction to ChaCha20
+ rather than to Salsa20. XChaCha20 extends ChaCha20's nonce length
+ from 64 bits (or 96 bits using the RFC7539 convention) to 192 bits,
+ while provably retaining ChaCha20's security. See also:
+ <https://cr.yp.to/snuffle/xsalsa-20081128.pdf>
+
+ XChaCha12 is XChaCha20 reduced to 12 rounds, with correspondingly
+ reduced security margin but increased performance. It can be needed
+ in some performance-sensitive scenarios.
+
config CRYPTO_CHACHA20_X86_64
tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)"
depends on X86 && 64BIT
@@ -1608,6 +1644,15 @@
help
This is the LZ4 high compression mode algorithm.
+config CRYPTO_ZSTD
+ tristate "Zstd compression algorithm"
+ select CRYPTO_ALGAPI
+ select CRYPTO_ACOMP2
+ select ZSTD_COMPRESS
+ select ZSTD_DECOMPRESS
+ help
+ This is the zstd algorithm.
+
comment "Random Number Generation"
config CRYPTO_ANSI_CPRNG
diff --git a/crypto/Makefile b/crypto/Makefile
index 9e52b3c..bb20d35 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -82,6 +82,8 @@
obj-$(CONFIG_CRYPTO_XTS) += xts.o
obj-$(CONFIG_CRYPTO_CTR) += ctr.o
obj-$(CONFIG_CRYPTO_KEYWRAP) += keywrap.o
+obj-$(CONFIG_CRYPTO_ADIANTUM) += adiantum.o
+obj-$(CONFIG_CRYPTO_NHPOLY1305) += nhpoly1305.o
obj-$(CONFIG_CRYPTO_GCM) += gcm.o
obj-$(CONFIG_CRYPTO_CCM) += ccm.o
obj-$(CONFIG_CRYPTO_CHACHA20POLY1305) += chacha20poly1305.o
@@ -107,7 +109,7 @@
obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
obj-$(CONFIG_CRYPTO_SEED) += seed.o
obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
-obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
+obj-$(CONFIG_CRYPTO_CHACHA20) += chacha_generic.o
obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
@@ -132,6 +134,7 @@
obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
obj-$(CONFIG_CRYPTO_USER_API_RNG) += algif_rng.o
obj-$(CONFIG_CRYPTO_USER_API_AEAD) += algif_aead.o
+obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o
#
# generic algorithms and the async_tx api
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
new file mode 100644
index 0000000..5564e73
--- /dev/null
+++ b/crypto/adiantum.c
@@ -0,0 +1,668 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Adiantum length-preserving encryption mode
+ *
+ * Copyright 2018 Google LLC
+ */
+
+/*
+ * Adiantum is a tweakable, length-preserving encryption mode designed for fast
+ * and secure disk encryption, especially on CPUs without dedicated crypto
+ * instructions. Adiantum encrypts each sector using the XChaCha12 stream
+ * cipher, two passes of an ε-almost-∆-universal (ε-∆U) hash function based on
+ * NH and Poly1305, and an invocation of the AES-256 block cipher on a single
+ * 16-byte block. See the paper for details:
+ *
+ * Adiantum: length-preserving encryption for entry-level processors
+ * (https://eprint.iacr.org/2018/720.pdf)
+ *
+ * For flexibility, this implementation also allows other ciphers:
+ *
+ * - Stream cipher: XChaCha12 or XChaCha20
+ * - Block cipher: any with a 128-bit block size and 256-bit key
+ *
+ * This implementation doesn't currently allow other ε-∆U hash functions, i.e.
+ * HPolyC is not supported. This is because Adiantum is ~20% faster than HPolyC
+ * but still provably as secure, and also the ε-∆U hash function of HBSH is
+ * formally defined to take two inputs (tweak, message) which makes it difficult
+ * to wrap with the crypto_shash API. Rather, some details need to be handled
+ * here. Nevertheless, if needed in the future, support for other ε-∆U hash
+ * functions could be added here.
+ */
+
+#include <crypto/b128ops.h>
+#include <crypto/chacha.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/nhpoly1305.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+/*
+ * Size of right-hand part of input data, in bytes; also the size of the block
+ * cipher's block size and the hash function's output.
+ */
+#define BLOCKCIPHER_BLOCK_SIZE 16
+
+/* Size of the block cipher key (K_E) in bytes */
+#define BLOCKCIPHER_KEY_SIZE 32
+
+/* Size of the hash key (K_H) in bytes */
+#define HASH_KEY_SIZE (POLY1305_BLOCK_SIZE + NHPOLY1305_KEY_SIZE)
+
+/*
+ * The specification allows variable-length tweaks, but Linux's crypto API
+ * currently only allows algorithms to support a single length. The "natural"
+ * tweak length for Adiantum is 16, since that fits into one Poly1305 block for
+ * the best performance. But longer tweaks are useful for fscrypt, to avoid
+ * needing to derive per-file keys. So instead we use two blocks, or 32 bytes.
+ */
+#define TWEAK_SIZE 32
+
+struct adiantum_instance_ctx {
+ struct crypto_skcipher_spawn streamcipher_spawn;
+ struct crypto_spawn blockcipher_spawn;
+ struct crypto_shash_spawn hash_spawn;
+};
+
+struct adiantum_tfm_ctx {
+ struct crypto_skcipher *streamcipher;
+ struct crypto_cipher *blockcipher;
+ struct crypto_shash *hash;
+ struct poly1305_key header_hash_key;
+};
+
+struct adiantum_request_ctx {
+
+ /*
+ * Buffer for right-hand part of data, i.e.
+ *
+ * P_L => P_M => C_M => C_R when encrypting, or
+ * C_R => C_M => P_M => P_L when decrypting.
+ *
+ * Also used to build the IV for the stream cipher.
+ */
+ union {
+ u8 bytes[XCHACHA_IV_SIZE];
+ __le32 words[XCHACHA_IV_SIZE / sizeof(__le32)];
+ le128 bignum; /* interpret as element of Z/(2^{128}Z) */
+ } rbuf;
+
+ bool enc; /* true if encrypting, false if decrypting */
+
+ /*
+ * The result of the Poly1305 ε-∆U hash function applied to
+ * (bulk length, tweak)
+ */
+ le128 header_hash;
+
+ /* Sub-requests, must be last */
+ union {
+ struct shash_desc hash_desc;
+ struct skcipher_request streamcipher_req;
+ } u;
+};
+
+/*
+ * Given the XChaCha stream key K_S, derive the block cipher key K_E and the
+ * hash key K_H as follows:
+ *
+ * K_E || K_H || ... = XChaCha(key=K_S, nonce=1||0^191)
+ *
+ * Note that this denotes using bits from the XChaCha keystream, which here we
+ * get indirectly by encrypting a buffer containing all 0's.
+ */
+static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct {
+ u8 iv[XCHACHA_IV_SIZE];
+ u8 derived_keys[BLOCKCIPHER_KEY_SIZE + HASH_KEY_SIZE];
+ struct scatterlist sg;
+ struct crypto_wait wait;
+ struct skcipher_request req; /* must be last */
+ } *data;
+ u8 *keyp;
+ int err;
+
+ /* Set the stream cipher key (K_S) */
+ crypto_skcipher_clear_flags(tctx->streamcipher, CRYPTO_TFM_REQ_MASK);
+ crypto_skcipher_set_flags(tctx->streamcipher,
+ crypto_skcipher_get_flags(tfm) &
+ CRYPTO_TFM_REQ_MASK);
+ err = crypto_skcipher_setkey(tctx->streamcipher, key, keylen);
+ crypto_skcipher_set_flags(tfm,
+ crypto_skcipher_get_flags(tctx->streamcipher) &
+ CRYPTO_TFM_RES_MASK);
+ if (err)
+ return err;
+
+ /* Derive the subkeys */
+ data = kzalloc(sizeof(*data) +
+ crypto_skcipher_reqsize(tctx->streamcipher), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ data->iv[0] = 1;
+ sg_init_one(&data->sg, data->derived_keys, sizeof(data->derived_keys));
+ crypto_init_wait(&data->wait);
+ skcipher_request_set_tfm(&data->req, tctx->streamcipher);
+ skcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+ CRYPTO_TFM_REQ_MAY_BACKLOG,
+ crypto_req_done, &data->wait);
+ skcipher_request_set_crypt(&data->req, &data->sg, &data->sg,
+ sizeof(data->derived_keys), data->iv);
+ err = crypto_wait_req(crypto_skcipher_encrypt(&data->req), &data->wait);
+ if (err)
+ goto out;
+ keyp = data->derived_keys;
+
+ /* Set the block cipher key (K_E) */
+ crypto_cipher_clear_flags(tctx->blockcipher, CRYPTO_TFM_REQ_MASK);
+ crypto_cipher_set_flags(tctx->blockcipher,
+ crypto_skcipher_get_flags(tfm) &
+ CRYPTO_TFM_REQ_MASK);
+ err = crypto_cipher_setkey(tctx->blockcipher, keyp,
+ BLOCKCIPHER_KEY_SIZE);
+ crypto_skcipher_set_flags(tfm,
+ crypto_cipher_get_flags(tctx->blockcipher) &
+ CRYPTO_TFM_RES_MASK);
+ if (err)
+ goto out;
+ keyp += BLOCKCIPHER_KEY_SIZE;
+
+ /* Set the hash key (K_H) */
+ poly1305_core_setkey(&tctx->header_hash_key, keyp);
+ keyp += POLY1305_BLOCK_SIZE;
+
+ crypto_shash_clear_flags(tctx->hash, CRYPTO_TFM_REQ_MASK);
+ crypto_shash_set_flags(tctx->hash, crypto_skcipher_get_flags(tfm) &
+ CRYPTO_TFM_REQ_MASK);
+ err = crypto_shash_setkey(tctx->hash, keyp, NHPOLY1305_KEY_SIZE);
+ crypto_skcipher_set_flags(tfm, crypto_shash_get_flags(tctx->hash) &
+ CRYPTO_TFM_RES_MASK);
+ keyp += NHPOLY1305_KEY_SIZE;
+ WARN_ON(keyp != &data->derived_keys[ARRAY_SIZE(data->derived_keys)]);
+out:
+ kzfree(data);
+ return err;
+}
+
+/* Addition in Z/(2^{128}Z) */
+static inline void le128_add(le128 *r, const le128 *v1, const le128 *v2)
+{
+ u64 x = le64_to_cpu(v1->b);
+ u64 y = le64_to_cpu(v2->b);
+
+ r->b = cpu_to_le64(x + y);
+ r->a = cpu_to_le64(le64_to_cpu(v1->a) + le64_to_cpu(v2->a) +
+ (x + y < x));
+}
+
+/* Subtraction in Z/(2^{128}Z) */
+static inline void le128_sub(le128 *r, const le128 *v1, const le128 *v2)
+{
+ u64 x = le64_to_cpu(v1->b);
+ u64 y = le64_to_cpu(v2->b);
+
+ r->b = cpu_to_le64(x - y);
+ r->a = cpu_to_le64(le64_to_cpu(v1->a) - le64_to_cpu(v2->a) -
+ (x - y > x));
+}
+
+/*
+ * Apply the Poly1305 ε-∆U hash function to (bulk length, tweak) and save the
+ * result to rctx->header_hash. This is the calculation
+ *
+ * H_T ← Poly1305_{K_T}(bin_{128}(|L|) || T)
+ *
+ * from the procedure in section 6.4 of the Adiantum paper. The resulting value
+ * is reused in both the first and second hash steps. Specifically, it's added
+ * to the result of an independently keyed ε-∆U hash function (for equal length
+ * inputs only) taken over the left-hand part (the "bulk") of the message, to
+ * give the overall Adiantum hash of the (tweak, left-hand part) pair.
+ */
+static void adiantum_hash_header(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct adiantum_request_ctx *rctx = skcipher_request_ctx(req);
+ const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+ struct {
+ __le64 message_bits;
+ __le64 padding;
+ } header = {
+ .message_bits = cpu_to_le64((u64)bulk_len * 8)
+ };
+ struct poly1305_state state;
+
+ poly1305_core_init(&state);
+
+ BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0);
+ poly1305_core_blocks(&state, &tctx->header_hash_key,
+ &header, sizeof(header) / POLY1305_BLOCK_SIZE);
+
+ BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0);
+ poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv,
+ TWEAK_SIZE / POLY1305_BLOCK_SIZE);
+
+ poly1305_core_emit(&state, &rctx->header_hash);
+}
+
+/* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */
+static int adiantum_hash_message(struct skcipher_request *req,
+ struct scatterlist *sgl, le128 *digest)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct adiantum_request_ctx *rctx = skcipher_request_ctx(req);
+ const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+ struct shash_desc *hash_desc = &rctx->u.hash_desc;
+ struct sg_mapping_iter miter;
+ unsigned int i, n;
+ int err;
+
+ hash_desc->tfm = tctx->hash;
+ hash_desc->flags = 0;
+
+ err = crypto_shash_init(hash_desc);
+ if (err)
+ return err;
+
+ sg_miter_start(&miter, sgl, sg_nents(sgl),
+ SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+ for (i = 0; i < bulk_len; i += n) {
+ sg_miter_next(&miter);
+ n = min_t(unsigned int, miter.length, bulk_len - i);
+ err = crypto_shash_update(hash_desc, miter.addr, n);
+ if (err)
+ break;
+ }
+ sg_miter_stop(&miter);
+ if (err)
+ return err;
+
+ return crypto_shash_final(hash_desc, (u8 *)digest);
+}
+
+/* Continue Adiantum encryption/decryption after the stream cipher step */
+static int adiantum_finish(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct adiantum_request_ctx *rctx = skcipher_request_ctx(req);
+ const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+ le128 digest;
+ int err;
+
+ /* If decrypting, decrypt C_M with the block cipher to get P_M */
+ if (!rctx->enc)
+ crypto_cipher_decrypt_one(tctx->blockcipher, rctx->rbuf.bytes,
+ rctx->rbuf.bytes);
+
+ /*
+ * Second hash step
+ * enc: C_R = C_M - H_{K_H}(T, C_L)
+ * dec: P_R = P_M - H_{K_H}(T, P_L)
+ */
+ err = adiantum_hash_message(req, req->dst, &digest);
+ if (err)
+ return err;
+ le128_add(&digest, &digest, &rctx->header_hash);
+ le128_sub(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest);
+ scatterwalk_map_and_copy(&rctx->rbuf.bignum, req->dst,
+ bulk_len, BLOCKCIPHER_BLOCK_SIZE, 1);
+ return 0;
+}
+
+static void adiantum_streamcipher_done(struct crypto_async_request *areq,
+ int err)
+{
+ struct skcipher_request *req = areq->data;
+
+ if (!err)
+ err = adiantum_finish(req);
+
+ skcipher_request_complete(req, err);
+}
+
+static int adiantum_crypt(struct skcipher_request *req, bool enc)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct adiantum_request_ctx *rctx = skcipher_request_ctx(req);
+ const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+ unsigned int stream_len;
+ le128 digest;
+ int err;
+
+ if (req->cryptlen < BLOCKCIPHER_BLOCK_SIZE)
+ return -EINVAL;
+
+ rctx->enc = enc;
+
+ /*
+ * First hash step
+ * enc: P_M = P_R + H_{K_H}(T, P_L)
+ * dec: C_M = C_R + H_{K_H}(T, C_L)
+ */
+ adiantum_hash_header(req);
+ err = adiantum_hash_message(req, req->src, &digest);
+ if (err)
+ return err;
+ le128_add(&digest, &digest, &rctx->header_hash);
+ scatterwalk_map_and_copy(&rctx->rbuf.bignum, req->src,
+ bulk_len, BLOCKCIPHER_BLOCK_SIZE, 0);
+ le128_add(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest);
+
+ /* If encrypting, encrypt P_M with the block cipher to get C_M */
+ if (enc)
+ crypto_cipher_encrypt_one(tctx->blockcipher, rctx->rbuf.bytes,
+ rctx->rbuf.bytes);
+
+ /* Initialize the rest of the XChaCha IV (first part is C_M) */
+ BUILD_BUG_ON(BLOCKCIPHER_BLOCK_SIZE != 16);
+ BUILD_BUG_ON(XCHACHA_IV_SIZE != 32); /* nonce || stream position */
+ rctx->rbuf.words[4] = cpu_to_le32(1);
+ rctx->rbuf.words[5] = 0;
+ rctx->rbuf.words[6] = 0;
+ rctx->rbuf.words[7] = 0;
+
+ /*
+ * XChaCha needs to be done on all the data except the last 16 bytes;
+ * for disk encryption that usually means 4080 or 496 bytes. But ChaCha
+ * implementations tend to be most efficient when passed a whole number
+ * of 64-byte ChaCha blocks, or sometimes even a multiple of 256 bytes.
+ * And here it doesn't matter whether the last 16 bytes are written to,
+ * as the second hash step will overwrite them. Thus, round the XChaCha
+ * length up to the next 64-byte boundary if possible.
+ */
+ stream_len = bulk_len;
+ if (round_up(stream_len, CHACHA_BLOCK_SIZE) <= req->cryptlen)
+ stream_len = round_up(stream_len, CHACHA_BLOCK_SIZE);
+
+ skcipher_request_set_tfm(&rctx->u.streamcipher_req, tctx->streamcipher);
+ skcipher_request_set_crypt(&rctx->u.streamcipher_req, req->src,
+ req->dst, stream_len, &rctx->rbuf);
+ skcipher_request_set_callback(&rctx->u.streamcipher_req,
+ req->base.flags,
+ adiantum_streamcipher_done, req);
+ return crypto_skcipher_encrypt(&rctx->u.streamcipher_req) ?:
+ adiantum_finish(req);
+}
+
+static int adiantum_encrypt(struct skcipher_request *req)
+{
+ return adiantum_crypt(req, true);
+}
+
+static int adiantum_decrypt(struct skcipher_request *req)
+{
+ return adiantum_crypt(req, false);
+}
+
+static int adiantum_init_tfm(struct crypto_skcipher *tfm)
+{
+ struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+ struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst);
+ struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+ struct crypto_skcipher *streamcipher;
+ struct crypto_cipher *blockcipher;
+ struct crypto_shash *hash;
+ unsigned int subreq_size;
+ int err;
+
+ streamcipher = crypto_spawn_skcipher(&ictx->streamcipher_spawn);
+ if (IS_ERR(streamcipher))
+ return PTR_ERR(streamcipher);
+
+ blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn);
+ if (IS_ERR(blockcipher)) {
+ err = PTR_ERR(blockcipher);
+ goto err_free_streamcipher;
+ }
+
+ hash = crypto_spawn_shash(&ictx->hash_spawn);
+ if (IS_ERR(hash)) {
+ err = PTR_ERR(hash);
+ goto err_free_blockcipher;
+ }
+
+ tctx->streamcipher = streamcipher;
+ tctx->blockcipher = blockcipher;
+ tctx->hash = hash;
+
+ BUILD_BUG_ON(offsetofend(struct adiantum_request_ctx, u) !=
+ sizeof(struct adiantum_request_ctx));
+ subreq_size = max(FIELD_SIZEOF(struct adiantum_request_ctx,
+ u.hash_desc) +
+ crypto_shash_descsize(hash),
+ FIELD_SIZEOF(struct adiantum_request_ctx,
+ u.streamcipher_req) +
+ crypto_skcipher_reqsize(streamcipher));
+
+ crypto_skcipher_set_reqsize(tfm,
+ offsetof(struct adiantum_request_ctx, u) +
+ subreq_size);
+ return 0;
+
+err_free_blockcipher:
+ crypto_free_cipher(blockcipher);
+err_free_streamcipher:
+ crypto_free_skcipher(streamcipher);
+ return err;
+}
+
+static void adiantum_exit_tfm(struct crypto_skcipher *tfm)
+{
+ struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_skcipher(tctx->streamcipher);
+ crypto_free_cipher(tctx->blockcipher);
+ crypto_free_shash(tctx->hash);
+}
+
+static void adiantum_free_instance(struct skcipher_instance *inst)
+{
+ struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst);
+
+ crypto_drop_skcipher(&ictx->streamcipher_spawn);
+ crypto_drop_spawn(&ictx->blockcipher_spawn);
+ crypto_drop_shash(&ictx->hash_spawn);
+ kfree(inst);
+}
+
+/*
+ * Check for a supported set of inner algorithms.
+ * See the comment at the beginning of this file.
+ */
+static bool adiantum_supported_algorithms(struct skcipher_alg *streamcipher_alg,
+ struct crypto_alg *blockcipher_alg,
+ struct shash_alg *hash_alg)
+{
+ if (strcmp(streamcipher_alg->base.cra_name, "xchacha12") != 0 &&
+ strcmp(streamcipher_alg->base.cra_name, "xchacha20") != 0)
+ return false;
+
+ if (blockcipher_alg->cra_cipher.cia_min_keysize > BLOCKCIPHER_KEY_SIZE ||
+ blockcipher_alg->cra_cipher.cia_max_keysize < BLOCKCIPHER_KEY_SIZE)
+ return false;
+ if (blockcipher_alg->cra_blocksize != BLOCKCIPHER_BLOCK_SIZE)
+ return false;
+
+ if (strcmp(hash_alg->base.cra_name, "nhpoly1305") != 0)
+ return false;
+
+ return true;
+}
+
+static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+ struct crypto_attr_type *algt;
+ const char *streamcipher_name;
+ const char *blockcipher_name;
+ const char *nhpoly1305_name;
+ struct skcipher_instance *inst;
+ struct adiantum_instance_ctx *ictx;
+ struct skcipher_alg *streamcipher_alg;
+ struct crypto_alg *blockcipher_alg;
+ struct crypto_alg *_hash_alg;
+ struct shash_alg *hash_alg;
+ int err;
+
+ algt = crypto_get_attr_type(tb);
+ if (IS_ERR(algt))
+ return PTR_ERR(algt);
+
+ if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
+ return -EINVAL;
+
+ streamcipher_name = crypto_attr_alg_name(tb[1]);
+ if (IS_ERR(streamcipher_name))
+ return PTR_ERR(streamcipher_name);
+
+ blockcipher_name = crypto_attr_alg_name(tb[2]);
+ if (IS_ERR(blockcipher_name))
+ return PTR_ERR(blockcipher_name);
+
+ nhpoly1305_name = crypto_attr_alg_name(tb[3]);
+ if (nhpoly1305_name == ERR_PTR(-ENOENT))
+ nhpoly1305_name = "nhpoly1305";
+ if (IS_ERR(nhpoly1305_name))
+ return PTR_ERR(nhpoly1305_name);
+
+ inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
+ if (!inst)
+ return -ENOMEM;
+ ictx = skcipher_instance_ctx(inst);
+
+ /* Stream cipher, e.g. "xchacha12" */
+ crypto_set_skcipher_spawn(&ictx->streamcipher_spawn,
+ skcipher_crypto_instance(inst));
+ err = crypto_grab_skcipher(&ictx->streamcipher_spawn, streamcipher_name,
+ 0, crypto_requires_sync(algt->type,
+ algt->mask));
+ if (err)
+ goto out_free_inst;
+ streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn);
+
+ /* Block cipher, e.g. "aes" */
+ crypto_set_spawn(&ictx->blockcipher_spawn,
+ skcipher_crypto_instance(inst));
+ err = crypto_grab_spawn(&ictx->blockcipher_spawn, blockcipher_name,
+ CRYPTO_ALG_TYPE_CIPHER, CRYPTO_ALG_TYPE_MASK);
+ if (err)
+ goto out_drop_streamcipher;
+ blockcipher_alg = ictx->blockcipher_spawn.alg;
+
+ /* NHPoly1305 ε-∆U hash function */
+ _hash_alg = crypto_alg_mod_lookup(nhpoly1305_name,
+ CRYPTO_ALG_TYPE_SHASH,
+ CRYPTO_ALG_TYPE_MASK);
+ if (IS_ERR(_hash_alg)) {
+ err = PTR_ERR(_hash_alg);
+ goto out_drop_blockcipher;
+ }
+ hash_alg = __crypto_shash_alg(_hash_alg);
+ err = crypto_init_shash_spawn(&ictx->hash_spawn, hash_alg,
+ skcipher_crypto_instance(inst));
+ if (err)
+ goto out_put_hash;
+
+ /* Check the set of algorithms */
+ if (!adiantum_supported_algorithms(streamcipher_alg, blockcipher_alg,
+ hash_alg)) {
+ pr_warn("Unsupported Adiantum instantiation: (%s,%s,%s)\n",
+ streamcipher_alg->base.cra_name,
+ blockcipher_alg->cra_name, hash_alg->base.cra_name);
+ err = -EINVAL;
+ goto out_drop_hash;
+ }
+
+ /* Instance fields */
+
+ err = -ENAMETOOLONG;
+ if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+ "adiantum(%s,%s)", streamcipher_alg->base.cra_name,
+ blockcipher_alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+ goto out_drop_hash;
+ if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+ "adiantum(%s,%s,%s)",
+ streamcipher_alg->base.cra_driver_name,
+ blockcipher_alg->cra_driver_name,
+ hash_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+ goto out_drop_hash;
+
+ inst->alg.base.cra_flags = streamcipher_alg->base.cra_flags &
+ CRYPTO_ALG_ASYNC;
+ inst->alg.base.cra_blocksize = BLOCKCIPHER_BLOCK_SIZE;
+ inst->alg.base.cra_ctxsize = sizeof(struct adiantum_tfm_ctx);
+ inst->alg.base.cra_alignmask = streamcipher_alg->base.cra_alignmask |
+ hash_alg->base.cra_alignmask;
+ /*
+ * The block cipher is only invoked once per message, so for long
+ * messages (e.g. sectors for disk encryption) its performance doesn't
+ * matter as much as that of the stream cipher and hash function. Thus,
+ * weigh the block cipher's ->cra_priority less.
+ */
+ inst->alg.base.cra_priority = (4 * streamcipher_alg->base.cra_priority +
+ 2 * hash_alg->base.cra_priority +
+ blockcipher_alg->cra_priority) / 7;
+
+ inst->alg.setkey = adiantum_setkey;
+ inst->alg.encrypt = adiantum_encrypt;
+ inst->alg.decrypt = adiantum_decrypt;
+ inst->alg.init = adiantum_init_tfm;
+ inst->alg.exit = adiantum_exit_tfm;
+ inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(streamcipher_alg);
+ inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(streamcipher_alg);
+ inst->alg.ivsize = TWEAK_SIZE;
+
+ inst->free = adiantum_free_instance;
+
+ err = skcipher_register_instance(tmpl, inst);
+ if (err)
+ goto out_drop_hash;
+
+ crypto_mod_put(_hash_alg);
+ return 0;
+
+out_drop_hash:
+ crypto_drop_shash(&ictx->hash_spawn);
+out_put_hash:
+ crypto_mod_put(_hash_alg);
+out_drop_blockcipher:
+ crypto_drop_spawn(&ictx->blockcipher_spawn);
+out_drop_streamcipher:
+ crypto_drop_skcipher(&ictx->streamcipher_spawn);
+out_free_inst:
+ kfree(inst);
+ return err;
+}
+
+/* adiantum(streamcipher_name, blockcipher_name [, nhpoly1305_name]) */
+static struct crypto_template adiantum_tmpl = {
+ .name = "adiantum",
+ .create = adiantum_create,
+ .module = THIS_MODULE,
+};
+
+static int __init adiantum_module_init(void)
+{
+ return crypto_register_template(&adiantum_tmpl);
+}
+
+static void __exit adiantum_module_exit(void)
+{
+ crypto_unregister_template(&adiantum_tmpl);
+}
+
+module_init(adiantum_module_init);
+module_exit(adiantum_module_exit);
+
+MODULE_DESCRIPTION("Adiantum length-preserving encryption mode");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("adiantum");
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index 3dd1011..956f8b8 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -62,7 +62,8 @@ static inline u8 byte(const u32 x, const unsigned n)
static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 };
-__visible const u32 crypto_ft_tab[4][256] = {
+/* cacheline-aligned to facilitate prefetching into cache */
+__visible const u32 crypto_ft_tab[4][256] __cacheline_aligned = {
{
0xa56363c6, 0x847c7cf8, 0x997777ee, 0x8d7b7bf6,
0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591,
@@ -326,7 +327,7 @@ __visible const u32 crypto_ft_tab[4][256] = {
}
};
-__visible const u32 crypto_fl_tab[4][256] = {
+__visible const u32 crypto_fl_tab[4][256] __cacheline_aligned = {
{
0x00000063, 0x0000007c, 0x00000077, 0x0000007b,
0x000000f2, 0x0000006b, 0x0000006f, 0x000000c5,
@@ -590,7 +591,7 @@ __visible const u32 crypto_fl_tab[4][256] = {
}
};
-__visible const u32 crypto_it_tab[4][256] = {
+__visible const u32 crypto_it_tab[4][256] __cacheline_aligned = {
{
0x50a7f451, 0x5365417e, 0xc3a4171a, 0x965e273a,
0xcb6bab3b, 0xf1459d1f, 0xab58faac, 0x9303e34b,
@@ -854,7 +855,7 @@ __visible const u32 crypto_it_tab[4][256] = {
}
};
-__visible const u32 crypto_il_tab[4][256] = {
+__visible const u32 crypto_il_tab[4][256] __cacheline_aligned = {
{
0x00000052, 0x00000009, 0x0000006a, 0x000000d5,
0x00000030, 0x00000036, 0x000000a5, 0x00000038,
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index c48ddeb..9fcd7f5 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -121,8 +121,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private)
int af_alg_release(struct socket *sock)
{
- if (sock->sk)
+ if (sock->sk) {
sock_put(sock->sk);
+ sock->sk = NULL;
+ }
return 0;
}
EXPORT_SYMBOL_GPL(af_alg_release);
diff --git a/crypto/api.c b/crypto/api.c
index b273b3a..b47796b 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -24,6 +24,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/string.h>
+#include <linux/completion.h>
#include "internal.h"
LIST_HEAD(crypto_alg_list);
@@ -610,5 +611,17 @@ int crypto_has_alg(const char *name, u32 type, u32 mask)
}
EXPORT_SYMBOL_GPL(crypto_has_alg);
+void crypto_req_done(struct crypto_async_request *req, int err)
+{
+ struct crypto_wait *wait = req->data;
+
+ if (err == -EINPROGRESS)
+ return;
+
+ wait->err = err;
+ complete(&wait->completion);
+}
+EXPORT_SYMBOL_GPL(crypto_req_done);
+
MODULE_DESCRIPTION("Cryptographic core API");
MODULE_LICENSE("GPL");
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
deleted file mode 100644
index 1cab831..0000000
--- a/crypto/chacha20_generic.c
+++ /dev/null
@@ -1,151 +0,0 @@
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <linux/crypto.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <crypto/chacha20.h>
-
-static inline u32 le32_to_cpuvp(const void *p)
-{
- return le32_to_cpup(p);
-}
-
-static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
- unsigned int bytes)
-{
- u8 stream[CHACHA20_BLOCK_SIZE];
-
- if (dst != src)
- memcpy(dst, src, bytes);
-
- while (bytes >= CHACHA20_BLOCK_SIZE) {
- chacha20_block(state, stream);
- crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
- bytes -= CHACHA20_BLOCK_SIZE;
- dst += CHACHA20_BLOCK_SIZE;
- }
- if (bytes) {
- chacha20_block(state, stream);
- crypto_xor(dst, stream, bytes);
- }
-}
-
-void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
-{
- static const char constant[16] = "expand 32-byte k";
-
- state[0] = le32_to_cpuvp(constant + 0);
- state[1] = le32_to_cpuvp(constant + 4);
- state[2] = le32_to_cpuvp(constant + 8);
- state[3] = le32_to_cpuvp(constant + 12);
- state[4] = ctx->key[0];
- state[5] = ctx->key[1];
- state[6] = ctx->key[2];
- state[7] = ctx->key[3];
- state[8] = ctx->key[4];
- state[9] = ctx->key[5];
- state[10] = ctx->key[6];
- state[11] = ctx->key[7];
- state[12] = le32_to_cpuvp(iv + 0);
- state[13] = le32_to_cpuvp(iv + 4);
- state[14] = le32_to_cpuvp(iv + 8);
- state[15] = le32_to_cpuvp(iv + 12);
-}
-EXPORT_SYMBOL_GPL(crypto_chacha20_init);
-
-int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
- unsigned int keysize)
-{
- struct chacha20_ctx *ctx = crypto_tfm_ctx(tfm);
- int i;
-
- if (keysize != CHACHA20_KEY_SIZE)
- return -EINVAL;
-
- for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
- ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32));
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(crypto_chacha20_setkey);
-
-int crypto_chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- struct scatterlist *src, unsigned int nbytes)
-{
- struct blkcipher_walk walk;
- u32 state[16];
- int err;
-
- blkcipher_walk_init(&walk, dst, src, nbytes);
- err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
-
- crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
-
- while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
- chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
- rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
- err = blkcipher_walk_done(desc, &walk,
- walk.nbytes % CHACHA20_BLOCK_SIZE);
- }
-
- if (walk.nbytes) {
- chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
- walk.nbytes);
- err = blkcipher_walk_done(desc, &walk, 0);
- }
-
- return err;
-}
-EXPORT_SYMBOL_GPL(crypto_chacha20_crypt);
-
-static struct crypto_alg alg = {
- .cra_name = "chacha20",
- .cra_driver_name = "chacha20-generic",
- .cra_priority = 100,
- .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
- .cra_blocksize = 1,
- .cra_type = &crypto_blkcipher_type,
- .cra_ctxsize = sizeof(struct chacha20_ctx),
- .cra_alignmask = sizeof(u32) - 1,
- .cra_module = THIS_MODULE,
- .cra_u = {
- .blkcipher = {
- .min_keysize = CHACHA20_KEY_SIZE,
- .max_keysize = CHACHA20_KEY_SIZE,
- .ivsize = CHACHA20_IV_SIZE,
- .geniv = "seqiv",
- .setkey = crypto_chacha20_setkey,
- .encrypt = crypto_chacha20_crypt,
- .decrypt = crypto_chacha20_crypt,
- },
- },
-};
-
-static int __init chacha20_generic_mod_init(void)
-{
- return crypto_register_alg(&alg);
-}
-
-static void __exit chacha20_generic_mod_fini(void)
-{
- crypto_unregister_alg(&alg);
-}
-
-module_init(chacha20_generic_mod_init);
-module_exit(chacha20_generic_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("chacha20 cipher algorithm");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-generic");
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 96d842a..e640da6 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -13,7 +13,7 @@
#include <crypto/internal/hash.h>
#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
-#include <crypto/chacha20.h>
+#include <crypto/chacha.h>
#include <crypto/poly1305.h>
#include <linux/err.h>
#include <linux/init.h>
@@ -51,7 +51,7 @@ struct poly_req {
};
struct chacha_req {
- u8 iv[CHACHA20_IV_SIZE];
+ u8 iv[CHACHA_IV_SIZE];
struct scatterlist src[1];
struct skcipher_request req; /* must be last member */
};
@@ -97,7 +97,7 @@ static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb)
memcpy(iv, &leicb, sizeof(leicb));
memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen);
memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv,
- CHACHA20_IV_SIZE - sizeof(leicb) - ctx->saltlen);
+ CHACHA_IV_SIZE - sizeof(leicb) - ctx->saltlen);
}
static int poly_verify_tag(struct aead_request *req)
@@ -502,7 +502,7 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key,
struct chachapoly_ctx *ctx = crypto_aead_ctx(aead);
int err;
- if (keylen != ctx->saltlen + CHACHA20_KEY_SIZE)
+ if (keylen != ctx->saltlen + CHACHA_KEY_SIZE)
return -EINVAL;
keylen -= ctx->saltlen;
@@ -647,7 +647,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
err = -EINVAL;
/* Need 16-byte IV size, including Initial Block Counter value */
- if (crypto_skcipher_alg_ivsize(chacha) != CHACHA20_IV_SIZE)
+ if (crypto_skcipher_alg_ivsize(chacha) != CHACHA_IV_SIZE)
goto out_drop_chacha;
/* Not a stream cipher? */
if (chacha->base.cra_blocksize != 1)
diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c
new file mode 100644
index 0000000..dda06a8f
--- /dev/null
+++ b/crypto/chacha_generic.c
@@ -0,0 +1,243 @@
+/*
+ * ChaCha and XChaCha stream ciphers, including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ * Copyright (C) 2018 Google LLC
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <crypto/chacha.h>
+
+static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds)
+{
+ /* aligned to potentially speed up crypto_xor() */
+ u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
+
+ if (dst != src)
+ memcpy(dst, src, bytes);
+
+ while (bytes >= CHACHA_BLOCK_SIZE) {
+ chacha_block(state, stream, nrounds);
+ crypto_xor(dst, stream, CHACHA_BLOCK_SIZE);
+ bytes -= CHACHA_BLOCK_SIZE;
+ dst += CHACHA_BLOCK_SIZE;
+ }
+ if (bytes) {
+ chacha_block(state, stream, nrounds);
+ crypto_xor(dst, stream, bytes);
+ }
+}
+
+static int chacha_stream_xor(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes,
+ struct chacha_ctx *ctx, u8 *iv)
+{
+ struct blkcipher_walk walk;
+ u32 state[16];
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, CHACHA_BLOCK_SIZE);
+
+ crypto_chacha_init(state, ctx, iv);
+
+ while (walk.nbytes >= CHACHA_BLOCK_SIZE) {
+ chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+ rounddown(walk.nbytes, CHACHA_BLOCK_SIZE),
+ ctx->nrounds);
+ err = blkcipher_walk_done(desc, &walk,
+ walk.nbytes % CHACHA_BLOCK_SIZE);
+ }
+
+ if (walk.nbytes) {
+ chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes, ctx->nrounds);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+
+ return err;
+}
+
+void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv)
+{
+ state[0] = 0x61707865; /* "expa" */
+ state[1] = 0x3320646e; /* "nd 3" */
+ state[2] = 0x79622d32; /* "2-by" */
+ state[3] = 0x6b206574; /* "te k" */
+ state[4] = ctx->key[0];
+ state[5] = ctx->key[1];
+ state[6] = ctx->key[2];
+ state[7] = ctx->key[3];
+ state[8] = ctx->key[4];
+ state[9] = ctx->key[5];
+ state[10] = ctx->key[6];
+ state[11] = ctx->key[7];
+ state[12] = get_unaligned_le32(iv + 0);
+ state[13] = get_unaligned_le32(iv + 4);
+ state[14] = get_unaligned_le32(iv + 8);
+ state[15] = get_unaligned_le32(iv + 12);
+}
+EXPORT_SYMBOL_GPL(crypto_chacha_init);
+
+static int chacha_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keysize, int nrounds)
+{
+ struct chacha_ctx *ctx = crypto_tfm_ctx(tfm);
+ int i;
+
+ if (keysize != CHACHA_KEY_SIZE)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+ ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
+
+ ctx->nrounds = nrounds;
+ return 0;
+}
+
+int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keysize)
+{
+ return chacha_setkey(tfm, key, keysize, 20);
+}
+EXPORT_SYMBOL_GPL(crypto_chacha20_setkey);
+
+int crypto_chacha12_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keysize)
+{
+ return chacha_setkey(tfm, key, keysize, 12);
+}
+EXPORT_SYMBOL_GPL(crypto_chacha12_setkey);
+
+int crypto_chacha_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct chacha_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ u8 *iv = desc->info;
+
+ return chacha_stream_xor(desc, dst, src, nbytes, ctx, iv);
+}
+EXPORT_SYMBOL_GPL(crypto_chacha_crypt);
+
+int crypto_xchacha_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct chacha_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ u8 *iv = desc->info;
+ struct chacha_ctx subctx;
+ u32 state[16];
+ u8 real_iv[16];
+
+ /* Compute the subkey given the original key and first 128 nonce bits */
+ crypto_chacha_init(state, ctx, iv);
+ hchacha_block(state, subctx.key, ctx->nrounds);
+ subctx.nrounds = ctx->nrounds;
+
+ /* Build the real IV */
+ memcpy(&real_iv[0], iv + 24, 8); /* stream position */
+ memcpy(&real_iv[8], iv + 16, 8); /* remaining 64 nonce bits */
+
+ /* Generate the stream and XOR it with the data */
+ return chacha_stream_xor(desc, dst, src, nbytes, &subctx, real_iv);
+}
+EXPORT_SYMBOL_GPL(crypto_xchacha_crypt);
+
+static struct crypto_alg algs[] = {
+ {
+ .cra_name = "chacha20",
+ .cra_driver_name = "chacha20-generic",
+ .cra_priority = 100,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha20_setkey,
+ .encrypt = crypto_chacha_crypt,
+ .decrypt = crypto_chacha_crypt,
+ },
+ },
+ }, {
+ .cra_name = "xchacha20",
+ .cra_driver_name = "xchacha20-generic",
+ .cra_priority = 100,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha20_setkey,
+ .encrypt = crypto_xchacha_crypt,
+ .decrypt = crypto_xchacha_crypt,
+ },
+ },
+ }, {
+ .cra_name = "xchacha12",
+ .cra_driver_name = "xchacha12-generic",
+ .cra_priority = 100,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct chacha_ctx),
+ .cra_alignmask = sizeof(u32) - 1,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .geniv = "seqiv",
+ .setkey = crypto_chacha12_setkey,
+ .encrypt = crypto_xchacha_crypt,
+ .decrypt = crypto_xchacha_crypt,
+ },
+ },
+ },
+};
+
+static int __init chacha_generic_mod_init(void)
+{
+ return crypto_register_algs(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit chacha_generic_mod_fini(void)
+{
+ crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+}
+
+module_init(chacha_generic_mod_init);
+module_exit(chacha_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (generic)");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-generic");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-generic");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-generic");
diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c
new file mode 100644
index 0000000..ec831a5
--- /dev/null
+++ b/crypto/nhpoly1305.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ *
+ * Copyright 2018 Google LLC
+ */
+
+/*
+ * "NHPoly1305" is the main component of Adiantum hashing.
+ * Specifically, it is the calculation
+ *
+ * H_L ← Poly1305_{K_L}(NH_{K_N}(pad_{128}(L)))
+ *
+ * from the procedure in section 6.4 of the Adiantum paper [1]. It is an
+ * ε-almost-∆-universal (ε-∆U) hash function for equal-length inputs over
+ * Z/(2^{128}Z), where the "∆" operation is addition. It hashes 1024-byte
+ * chunks of the input with the NH hash function [2], reducing the input length
+ * by 32x. The resulting NH digests are evaluated as a polynomial in
+ * GF(2^{130}-5), like in the Poly1305 MAC [3]. Note that the polynomial
+ * evaluation by itself would suffice to achieve the ε-∆U property; NH is used
+ * for performance since it's over twice as fast as Poly1305.
+ *
+ * This is *not* a cryptographic hash function; do not use it as such!
+ *
+ * [1] Adiantum: length-preserving encryption for entry-level processors
+ * (https://eprint.iacr.org/2018/720.pdf)
+ * [2] UMAC: Fast and Secure Message Authentication
+ * (https://fastcrypto.org/umac/umac_proc.pdf)
+ * [3] The Poly1305-AES message-authentication code
+ * (https://cr.yp.to/mac/poly1305-20050329.pdf)
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static void nh_generic(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES])
+{
+ u64 sums[4] = { 0, 0, 0, 0 };
+
+ BUILD_BUG_ON(NH_PAIR_STRIDE != 2);
+ BUILD_BUG_ON(NH_NUM_PASSES != 4);
+
+ while (message_len) {
+ u32 m0 = get_unaligned_le32(message + 0);
+ u32 m1 = get_unaligned_le32(message + 4);
+ u32 m2 = get_unaligned_le32(message + 8);
+ u32 m3 = get_unaligned_le32(message + 12);
+
+ sums[0] += (u64)(u32)(m0 + key[ 0]) * (u32)(m2 + key[ 2]);
+ sums[1] += (u64)(u32)(m0 + key[ 4]) * (u32)(m2 + key[ 6]);
+ sums[2] += (u64)(u32)(m0 + key[ 8]) * (u32)(m2 + key[10]);
+ sums[3] += (u64)(u32)(m0 + key[12]) * (u32)(m2 + key[14]);
+ sums[0] += (u64)(u32)(m1 + key[ 1]) * (u32)(m3 + key[ 3]);
+ sums[1] += (u64)(u32)(m1 + key[ 5]) * (u32)(m3 + key[ 7]);
+ sums[2] += (u64)(u32)(m1 + key[ 9]) * (u32)(m3 + key[11]);
+ sums[3] += (u64)(u32)(m1 + key[13]) * (u32)(m3 + key[15]);
+ key += NH_MESSAGE_UNIT / sizeof(key[0]);
+ message += NH_MESSAGE_UNIT;
+ message_len -= NH_MESSAGE_UNIT;
+ }
+
+ hash[0] = cpu_to_le64(sums[0]);
+ hash[1] = cpu_to_le64(sums[1]);
+ hash[2] = cpu_to_le64(sums[2]);
+ hash[3] = cpu_to_le64(sums[3]);
+}
+
+/* Pass the next NH hash value through Poly1305 */
+static void process_nh_hash_value(struct nhpoly1305_state *state,
+ const struct nhpoly1305_key *key)
+{
+ BUILD_BUG_ON(NH_HASH_BYTES % POLY1305_BLOCK_SIZE != 0);
+
+ poly1305_core_blocks(&state->poly_state, &key->poly_key, state->nh_hash,
+ NH_HASH_BYTES / POLY1305_BLOCK_SIZE);
+}
+
+/*
+ * Feed the next portion of the source data, as a whole number of 16-byte
+ * "NH message units", through NH and Poly1305. Each NH hash is taken over
+ * 1024 bytes, except possibly the final one which is taken over a multiple of
+ * 16 bytes up to 1024. Also, in the case where data is passed in misaligned
+ * chunks, we combine partial hashes; the end result is the same either way.
+ */
+static void nhpoly1305_units(struct nhpoly1305_state *state,
+ const struct nhpoly1305_key *key,
+ const u8 *src, unsigned int srclen, nh_t nh_fn)
+{
+ do {
+ unsigned int bytes;
+
+ if (state->nh_remaining == 0) {
+ /* Starting a new NH message */
+ bytes = min_t(unsigned int, srclen, NH_MESSAGE_BYTES);
+ nh_fn(key->nh_key, src, bytes, state->nh_hash);
+ state->nh_remaining = NH_MESSAGE_BYTES - bytes;
+ } else {
+ /* Continuing a previous NH message */
+ __le64 tmp_hash[NH_NUM_PASSES];
+ unsigned int pos;
+ int i;
+
+ pos = NH_MESSAGE_BYTES - state->nh_remaining;
+ bytes = min(srclen, state->nh_remaining);
+ nh_fn(&key->nh_key[pos / 4], src, bytes, tmp_hash);
+ for (i = 0; i < NH_NUM_PASSES; i++)
+ le64_add_cpu(&state->nh_hash[i],
+ le64_to_cpu(tmp_hash[i]));
+ state->nh_remaining -= bytes;
+ }
+ if (state->nh_remaining == 0)
+ process_nh_hash_value(state, key);
+ src += bytes;
+ srclen -= bytes;
+ } while (srclen);
+}
+
+int crypto_nhpoly1305_setkey(struct crypto_shash *tfm,
+ const u8 *key, unsigned int keylen)
+{
+ struct nhpoly1305_key *ctx = crypto_shash_ctx(tfm);
+ int i;
+
+ if (keylen != NHPOLY1305_KEY_SIZE)
+ return -EINVAL;
+
+ poly1305_core_setkey(&ctx->poly_key, key);
+ key += POLY1305_BLOCK_SIZE;
+
+ for (i = 0; i < NH_KEY_WORDS; i++)
+ ctx->nh_key[i] = get_unaligned_le32(key + i * sizeof(u32));
+
+ return 0;
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_setkey);
+
+int crypto_nhpoly1305_init(struct shash_desc *desc)
+{
+ struct nhpoly1305_state *state = shash_desc_ctx(desc);
+
+ poly1305_core_init(&state->poly_state);
+ state->buflen = 0;
+ state->nh_remaining = 0;
+ return 0;
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_init);
+
+int crypto_nhpoly1305_update_helper(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen,
+ nh_t nh_fn)
+{
+ struct nhpoly1305_state *state = shash_desc_ctx(desc);
+ const struct nhpoly1305_key *key = crypto_shash_ctx(desc->tfm);
+ unsigned int bytes;
+
+ if (state->buflen) {
+ bytes = min(srclen, (int)NH_MESSAGE_UNIT - state->buflen);
+ memcpy(&state->buffer[state->buflen], src, bytes);
+ state->buflen += bytes;
+ if (state->buflen < NH_MESSAGE_UNIT)
+ return 0;
+ nhpoly1305_units(state, key, state->buffer, NH_MESSAGE_UNIT,
+ nh_fn);
+ state->buflen = 0;
+ src += bytes;
+ srclen -= bytes;
+ }
+
+ if (srclen >= NH_MESSAGE_UNIT) {
+ bytes = round_down(srclen, NH_MESSAGE_UNIT);
+ nhpoly1305_units(state, key, src, bytes, nh_fn);
+ src += bytes;
+ srclen -= bytes;
+ }
+
+ if (srclen) {
+ memcpy(state->buffer, src, srclen);
+ state->buflen = srclen;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_update_helper);
+
+int crypto_nhpoly1305_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
+{
+ return crypto_nhpoly1305_update_helper(desc, src, srclen, nh_generic);
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_update);
+
+int crypto_nhpoly1305_final_helper(struct shash_desc *desc, u8 *dst, nh_t nh_fn)
+{
+ struct nhpoly1305_state *state = shash_desc_ctx(desc);
+ const struct nhpoly1305_key *key = crypto_shash_ctx(desc->tfm);
+
+ if (state->buflen) {
+ memset(&state->buffer[state->buflen], 0,
+ NH_MESSAGE_UNIT - state->buflen);
+ nhpoly1305_units(state, key, state->buffer, NH_MESSAGE_UNIT,
+ nh_fn);
+ }
+
+ if (state->nh_remaining)
+ process_nh_hash_value(state, key);
+
+ poly1305_core_emit(&state->poly_state, dst);
+ return 0;
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_final_helper);
+
+int crypto_nhpoly1305_final(struct shash_desc *desc, u8 *dst)
+{
+ return crypto_nhpoly1305_final_helper(desc, dst, nh_generic);
+}
+EXPORT_SYMBOL(crypto_nhpoly1305_final);
+
+static struct shash_alg nhpoly1305_alg = {
+ .base.cra_name = "nhpoly1305",
+ .base.cra_driver_name = "nhpoly1305-generic",
+ .base.cra_priority = 100,
+ .base.cra_ctxsize = sizeof(struct nhpoly1305_key),
+ .base.cra_module = THIS_MODULE,
+ .digestsize = POLY1305_DIGEST_SIZE,
+ .init = crypto_nhpoly1305_init,
+ .update = crypto_nhpoly1305_update,
+ .final = crypto_nhpoly1305_final,
+ .setkey = crypto_nhpoly1305_setkey,
+ .descsize = sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+ return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+ crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-generic");
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index bca9923..b60c1ee 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -17,6 +17,7 @@
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <asm/unaligned.h>
static inline u64 mlt(u64 a, u64 b)
{
@@ -33,16 +34,11 @@ static inline u32 and(u32 v, u32 mask)
return v & mask;
}
-static inline u32 le32_to_cpuvp(const void *p)
-{
- return le32_to_cpup(p);
-}
-
int crypto_poly1305_init(struct shash_desc *desc)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
- memset(dctx->h, 0, sizeof(dctx->h));
+ poly1305_core_init(&dctx->h);
dctx->buflen = 0;
dctx->rset = false;
dctx->sset = false;
@@ -51,23 +47,16 @@ int crypto_poly1305_init(struct shash_desc *desc)
}
EXPORT_SYMBOL_GPL(crypto_poly1305_init);
-static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key)
{
/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
- dctx->r[0] = (le32_to_cpuvp(key + 0) >> 0) & 0x3ffffff;
- dctx->r[1] = (le32_to_cpuvp(key + 3) >> 2) & 0x3ffff03;
- dctx->r[2] = (le32_to_cpuvp(key + 6) >> 4) & 0x3ffc0ff;
- dctx->r[3] = (le32_to_cpuvp(key + 9) >> 6) & 0x3f03fff;
- dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+ key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff;
+ key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03;
+ key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff;
+ key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff;
+ key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
}
-
-static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
-{
- dctx->s[0] = le32_to_cpuvp(key + 0);
- dctx->s[1] = le32_to_cpuvp(key + 4);
- dctx->s[2] = le32_to_cpuvp(key + 8);
- dctx->s[3] = le32_to_cpuvp(key + 12);
-}
+EXPORT_SYMBOL_GPL(poly1305_core_setkey);
/*
* Poly1305 requires a unique key for each tag, which implies that we can't set
@@ -79,13 +68,16 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
{
if (!dctx->sset) {
if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
- poly1305_setrkey(dctx, src);
+ poly1305_core_setkey(&dctx->r, src);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->rset = true;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
- poly1305_setskey(dctx, src);
+ dctx->s[0] = get_unaligned_le32(src + 0);
+ dctx->s[1] = get_unaligned_le32(src + 4);
+ dctx->s[2] = get_unaligned_le32(src + 8);
+ dctx->s[3] = get_unaligned_le32(src + 12);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->sset = true;
@@ -95,47 +87,43 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
}
EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey);
-static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
- const u8 *src, unsigned int srclen,
- u32 hibit)
+static void poly1305_blocks_internal(struct poly1305_state *state,
+ const struct poly1305_key *key,
+ const void *src, unsigned int nblocks,
+ u32 hibit)
{
u32 r0, r1, r2, r3, r4;
u32 s1, s2, s3, s4;
u32 h0, h1, h2, h3, h4;
u64 d0, d1, d2, d3, d4;
- unsigned int datalen;
- if (unlikely(!dctx->sset)) {
- datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
- src += srclen - datalen;
- srclen = datalen;
- }
+ if (!nblocks)
+ return;
- r0 = dctx->r[0];
- r1 = dctx->r[1];
- r2 = dctx->r[2];
- r3 = dctx->r[3];
- r4 = dctx->r[4];
+ r0 = key->r[0];
+ r1 = key->r[1];
+ r2 = key->r[2];
+ r3 = key->r[3];
+ r4 = key->r[4];
s1 = r1 * 5;
s2 = r2 * 5;
s3 = r3 * 5;
s4 = r4 * 5;
- h0 = dctx->h[0];
- h1 = dctx->h[1];
- h2 = dctx->h[2];
- h3 = dctx->h[3];
- h4 = dctx->h[4];
+ h0 = state->h[0];
+ h1 = state->h[1];
+ h2 = state->h[2];
+ h3 = state->h[3];
+ h4 = state->h[4];
- while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-
+ do {
/* h += m[i] */
- h0 += (le32_to_cpuvp(src + 0) >> 0) & 0x3ffffff;
- h1 += (le32_to_cpuvp(src + 3) >> 2) & 0x3ffffff;
- h2 += (le32_to_cpuvp(src + 6) >> 4) & 0x3ffffff;
- h3 += (le32_to_cpuvp(src + 9) >> 6) & 0x3ffffff;
- h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+ h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff;
+ h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff;
+ h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff;
+ h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff;
+ h4 += (get_unaligned_le32(src + 12) >> 8) | hibit;
/* h *= r */
d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
@@ -158,16 +146,36 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
h1 += h0 >> 26; h0 = h0 & 0x3ffffff;
src += POLY1305_BLOCK_SIZE;
- srclen -= POLY1305_BLOCK_SIZE;
+ } while (--nblocks);
+
+ state->h[0] = h0;
+ state->h[1] = h1;
+ state->h[2] = h2;
+ state->h[3] = h3;
+ state->h[4] = h4;
+}
+
+void poly1305_core_blocks(struct poly1305_state *state,
+ const struct poly1305_key *key,
+ const void *src, unsigned int nblocks)
+{
+ poly1305_blocks_internal(state, key, src, nblocks, 1 << 24);
+}
+EXPORT_SYMBOL_GPL(poly1305_core_blocks);
+
+static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
+ const u8 *src, unsigned int srclen, u32 hibit)
+{
+ unsigned int datalen;
+
+ if (unlikely(!dctx->sset)) {
+ datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+ src += srclen - datalen;
+ srclen = datalen;
}
- dctx->h[0] = h0;
- dctx->h[1] = h1;
- dctx->h[2] = h2;
- dctx->h[3] = h3;
- dctx->h[4] = h4;
-
- return srclen;
+ poly1305_blocks_internal(&dctx->h, &dctx->r,
+ src, srclen / POLY1305_BLOCK_SIZE, hibit);
}
int crypto_poly1305_update(struct shash_desc *desc,
@@ -191,9 +199,9 @@ int crypto_poly1305_update(struct shash_desc *desc,
}
if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
- bytes = poly1305_blocks(dctx, src, srclen, 1 << 24);
- src += srclen - bytes;
- srclen = bytes;
+ poly1305_blocks(dctx, src, srclen, 1 << 24);
+ src += srclen - (srclen % POLY1305_BLOCK_SIZE);
+ srclen %= POLY1305_BLOCK_SIZE;
}
if (unlikely(srclen)) {
@@ -205,31 +213,18 @@ int crypto_poly1305_update(struct shash_desc *desc,
}
EXPORT_SYMBOL_GPL(crypto_poly1305_update);
-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+void poly1305_core_emit(const struct poly1305_state *state, void *dst)
{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
- __le32 *mac = (__le32 *)dst;
u32 h0, h1, h2, h3, h4;
u32 g0, g1, g2, g3, g4;
u32 mask;
- u64 f = 0;
-
- if (unlikely(!dctx->sset))
- return -ENOKEY;
-
- if (unlikely(dctx->buflen)) {
- dctx->buf[dctx->buflen++] = 1;
- memset(dctx->buf + dctx->buflen, 0,
- POLY1305_BLOCK_SIZE - dctx->buflen);
- poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
- }
/* fully carry h */
- h0 = dctx->h[0];
- h1 = dctx->h[1];
- h2 = dctx->h[2];
- h3 = dctx->h[3];
- h4 = dctx->h[4];
+ h0 = state->h[0];
+ h1 = state->h[1];
+ h2 = state->h[2];
+ h3 = state->h[3];
+ h4 = state->h[4];
h2 += (h1 >> 26); h1 = h1 & 0x3ffffff;
h3 += (h2 >> 26); h2 = h2 & 0x3ffffff;
@@ -259,16 +254,40 @@ int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
h4 = (h4 & mask) | g4;
/* h = h % (2^128) */
- h0 = (h0 >> 0) | (h1 << 26);
- h1 = (h1 >> 6) | (h2 << 20);
- h2 = (h2 >> 12) | (h3 << 14);
- h3 = (h3 >> 18) | (h4 << 8);
+ put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0);
+ put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4);
+ put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8);
+ put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12);
+}
+EXPORT_SYMBOL_GPL(poly1305_core_emit);
+
+int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+ __le32 digest[4];
+ u64 f = 0;
+
+ if (unlikely(!dctx->sset))
+ return -ENOKEY;
+
+ if (unlikely(dctx->buflen)) {
+ dctx->buf[dctx->buflen++] = 1;
+ memset(dctx->buf + dctx->buflen, 0,
+ POLY1305_BLOCK_SIZE - dctx->buflen);
+ poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+ }
+
+ poly1305_core_emit(&dctx->h, digest);
/* mac = (h + s) % (2^128) */
- f = (f >> 32) + h0 + dctx->s[0]; mac[0] = cpu_to_le32(f);
- f = (f >> 32) + h1 + dctx->s[1]; mac[1] = cpu_to_le32(f);
- f = (f >> 32) + h2 + dctx->s[2]; mac[2] = cpu_to_le32(f);
- f = (f >> 32) + h3 + dctx->s[3]; mac[3] = cpu_to_le32(f);
+ f = (f >> 32) + le32_to_cpu(digest[0]) + dctx->s[0];
+ put_unaligned_le32(f, dst + 0);
+ f = (f >> 32) + le32_to_cpu(digest[1]) + dctx->s[1];
+ put_unaligned_le32(f, dst + 4);
+ f = (f >> 32) + le32_to_cpu(digest[2]) + dctx->s[2];
+ put_unaligned_le32(f, dst + 8);
+ f = (f >> 32) + le32_to_cpu(digest[3]) + dctx->s[3];
+ put_unaligned_le32(f, dst + 12);
return 0;
}
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index babbda2..fb79561 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1610,6 +1610,16 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
speed_template_32);
break;
+ case 219:
+ test_cipher_speed("adiantum(xchacha12,aes)", ENCRYPT, sec, NULL,
+ 0, speed_template_32);
+ test_cipher_speed("adiantum(xchacha12,aes)", DECRYPT, sec, NULL,
+ 0, speed_template_32);
+ test_cipher_speed("adiantum(xchacha20,aes)", ENCRYPT, sec, NULL,
+ 0, speed_template_32);
+ test_cipher_speed("adiantum(xchacha20,aes)", DECRYPT, sec, NULL,
+ 0, speed_template_32);
+ break;
case 300:
if (alg) {
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 62dffa0..898ef4d 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -62,7 +62,7 @@ int alg_test(const char *driver, const char *alg, u32 type, u32 mask)
*/
#define IDX1 32
#define IDX2 32400
-#define IDX3 1
+#define IDX3 1511
#define IDX4 8193
#define IDX5 22222
#define IDX6 17101
@@ -2173,6 +2173,36 @@ static const struct alg_test_desc alg_test_descs[] = {
.test = alg_test_null,
.fips_allowed = 1,
}, {
+ .alg = "adiantum(xchacha12,aes)",
+ .test = alg_test_skcipher,
+ .suite = {
+ .cipher = {
+ .enc = {
+ .vecs = adiantum_xchacha12_aes_enc_tv_template,
+ .count = ARRAY_SIZE(adiantum_xchacha12_aes_enc_tv_template),
+ },
+ .dec = {
+ .vecs = adiantum_xchacha12_aes_dec_tv_template,
+ .count = ARRAY_SIZE(adiantum_xchacha12_aes_dec_tv_template),
+ },
+ }
+ },
+ }, {
+ .alg = "adiantum(xchacha20,aes)",
+ .test = alg_test_skcipher,
+ .suite = {
+ .cipher = {
+ .enc = {
+ .vecs = adiantum_xchacha20_aes_enc_tv_template,
+ .count = ARRAY_SIZE(adiantum_xchacha20_aes_enc_tv_template),
+ },
+ .dec = {
+ .vecs = adiantum_xchacha20_aes_dec_tv_template,
+ .count = ARRAY_SIZE(adiantum_xchacha20_aes_dec_tv_template),
+ },
+ }
+ },
+ }, {
.alg = "ansi_cprng",
.test = alg_test_cprng,
.suite = {
@@ -3645,6 +3675,15 @@ static const struct alg_test_desc alg_test_descs[] = {
}
}
}, {
+ .alg = "nhpoly1305",
+ .test = alg_test_hash,
+ .suite = {
+ .hash = {
+ .vecs = nhpoly1305_tv_template,
+ .count = ARRAY_SIZE(nhpoly1305_tv_template),
+ }
+ }
+ }, {
.alg = "ofb(aes)",
.test = alg_test_skcipher,
.fips_allowed = 1,
@@ -3997,6 +4036,36 @@ static const struct alg_test_desc alg_test_descs[] = {
}
}
}, {
+ .alg = "xchacha12",
+ .test = alg_test_skcipher,
+ .suite = {
+ .cipher = {
+ .enc = {
+ .vecs = xchacha12_tv_template,
+ .count = ARRAY_SIZE(xchacha12_tv_template),
+ },
+ .dec = {
+ .vecs = xchacha12_tv_template,
+ .count = ARRAY_SIZE(xchacha12_tv_template),
+ },
+ }
+ },
+ }, {
+ .alg = "xchacha20",
+ .test = alg_test_skcipher,
+ .suite = {
+ .cipher = {
+ .enc = {
+ .vecs = xchacha20_tv_template,
+ .count = ARRAY_SIZE(xchacha20_tv_template),
+ },
+ .dec = {
+ .vecs = xchacha20_tv_template,
+ .count = ARRAY_SIZE(xchacha20_tv_template),
+ },
+ }
+ },
+ }, {
.alg = "xts(aes)",
.test = alg_test_skcipher,
.fips_allowed = 1,
@@ -4072,6 +4141,22 @@ static const struct alg_test_desc alg_test_descs[] = {
}
}
}
+ }, {
+ .alg = "zstd",
+ .test = alg_test_comp,
+ .fips_allowed = 1,
+ .suite = {
+ .comp = {
+ .comp = {
+ .vecs = zstd_comp_tv_template,
+ .count = ZSTD_COMP_TEST_VECTORS
+ },
+ .decomp = {
+ .vecs = zstd_decomp_tv_template,
+ .count = ZSTD_DECOMP_TEST_VECTORS
+ }
+ }
+ }
}
};
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index ebff337..125669f 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -29,7 +29,7 @@
#define MAX_DIGEST_SIZE 64
#define MAX_TAP 8
-#define MAX_KEYLEN 160
+#define MAX_KEYLEN 1088
#define MAX_IVLEN 32
struct hash_testvec {
@@ -37,10 +37,10 @@ struct hash_testvec {
char *key;
char *plaintext;
char *digest;
- unsigned char tap[MAX_TAP];
+ unsigned short tap[MAX_TAP];
unsigned short psize;
- unsigned char np;
- unsigned char ksize;
+ unsigned short np;
+ unsigned short ksize;
};
/*
@@ -4572,6 +4572,1237 @@ static struct hash_testvec poly1305_tv_template[] = {
}
};
+/* NHPoly1305 test vectors from https://github.com/google/adiantum */
+static struct hash_testvec nhpoly1305_tv_template[] = {
+ {
+ .key = "\xd2\x5d\x4c\xdd\x8d\x2b\x7f\x7a"
+ "\xd9\xbe\x71\xec\xd1\x83\x52\xe3"
+ "\xe1\xad\xd7\x5c\x0a\x75\x9d\xec"
+ "\x1d\x13\x7e\x5d\x71\x07\xc9\xe4"
+ "\x57\x2d\x44\x68\xcf\xd8\xd6\xc5"
+ "\x39\x69\x7d\x32\x75\x51\x4f\x7e"
+ "\xb2\x4c\xc6\x90\x51\x6e\xd9\xd6"
+ "\xa5\x8b\x2d\xf1\x94\xf9\xf7\x5e"
+ "\x2c\x84\x7b\x41\x0f\x88\x50\x89"
+ "\x30\xd9\xa1\x38\x46\x6c\xc0\x4f"
+ "\xe8\xdf\xdc\x66\xab\x24\x43\x41"
+ "\x91\x55\x29\x65\x86\x28\x5e\x45"
+ "\xd5\x2d\xb7\x80\x08\x9a\xc3\xd4"
+ "\x9a\x77\x0a\xd4\xef\x3e\xe6\x3f"
+ "\x6f\x2f\x9b\x3a\x7d\x12\x1e\x80"
+ "\x6c\x44\xa2\x25\xe1\xf6\x60\xe9"
+ "\x0d\xaf\xc5\x3c\xa5\x79\xae\x64"
+ "\xbc\xa0\x39\xa3\x4d\x10\xe5\x4d"
+ "\xd5\xe7\x89\x7a\x13\xee\x06\x78"
+ "\xdc\xa4\xdc\x14\x27\xe6\x49\x38"
+ "\xd0\xe0\x45\x25\x36\xc5\xf4\x79"
+ "\x2e\x9a\x98\x04\xe4\x2b\x46\x52"
+ "\x7c\x33\xca\xe2\x56\x51\x50\xe2"
+ "\xa5\x9a\xae\x18\x6a\x13\xf8\xd2"
+ "\x21\x31\x66\x02\xe2\xda\x8d\x7e"
+ "\x41\x19\xb2\x61\xee\x48\x8f\xf1"
+ "\x65\x24\x2e\x1e\x68\xce\x05\xd9"
+ "\x2a\xcf\xa5\x3a\x57\xdd\x35\x91"
+ "\x93\x01\xca\x95\xfc\x2b\x36\x04"
+ "\xe6\x96\x97\x28\xf6\x31\xfe\xa3"
+ "\x9d\xf6\x6a\x1e\x80\x8d\xdc\xec"
+ "\xaf\x66\x11\x13\x02\x88\xd5\x27"
+ "\x33\xb4\x1a\xcd\xa3\xf6\xde\x31"
+ "\x8e\xc0\x0e\x6c\xd8\x5a\x97\x5e"
+ "\xdd\xfd\x60\x69\x38\x46\x3f\x90"
+ "\x5e\x97\xd3\x32\x76\xc7\x82\x49"
+ "\xfe\xba\x06\x5f\x2f\xa2\xfd\xff"
+ "\x80\x05\x40\xe4\x33\x03\xfb\x10"
+ "\xc0\xde\x65\x8c\xc9\x8d\x3a\x9d"
+ "\xb5\x7b\x36\x4b\xb5\x0c\xcf\x00"
+ "\x9c\x87\xe4\x49\xad\x90\xda\x4a"
+ "\xdd\xbd\xff\xe2\x32\x57\xd6\x78"
+ "\x36\x39\x6c\xd3\x5b\x9b\x88\x59"
+ "\x2d\xf0\x46\xe4\x13\x0e\x2b\x35"
+ "\x0d\x0f\x73\x8a\x4f\x26\x84\x75"
+ "\x88\x3c\xc5\x58\x66\x18\x1a\xb4"
+ "\x64\x51\x34\x27\x1b\xa4\x11\xc9"
+ "\x6d\x91\x8a\xfa\x32\x60\x9d\xd7"
+ "\x87\xe5\xaa\x43\x72\xf8\xda\xd1"
+ "\x48\x44\x13\x61\xdc\x8c\x76\x17"
+ "\x0c\x85\x4e\xf3\xdd\xa2\x42\xd2"
+ "\x74\xc1\x30\x1b\xeb\x35\x31\x29"
+ "\x5b\xd7\x4c\x94\x46\x35\xa1\x23"
+ "\x50\xf2\xa2\x8e\x7e\x4f\x23\x4f"
+ "\x51\xff\xe2\xc9\xa3\x7d\x56\x8b"
+ "\x41\xf2\xd0\xc5\x57\x7e\x59\xac"
+ "\xbb\x65\xf3\xfe\xf7\x17\xef\x63"
+ "\x7c\x6f\x23\xdd\x22\x8e\xed\x84"
+ "\x0e\x3b\x09\xb3\xf3\xf4\x8f\xcd"
+ "\x37\xa8\xe1\xa7\x30\xdb\xb1\xa2"
+ "\x9c\xa2\xdf\x34\x17\x3e\x68\x44"
+ "\xd0\xde\x03\x50\xd1\x48\x6b\x20"
+ "\xe2\x63\x45\xa5\xea\x87\xc2\x42"
+ "\x95\x03\x49\x05\xed\xe0\x90\x29"
+ "\x1a\xb8\xcf\x9b\x43\xcf\x29\x7a"
+ "\x63\x17\x41\x9f\xe0\xc9\x10\xfd"
+ "\x2c\x56\x8c\x08\x55\xb4\xa9\x27"
+ "\x0f\x23\xb1\x05\x6a\x12\x46\xc7"
+ "\xe1\xfe\x28\x93\x93\xd7\x2f\xdc"
+ "\x98\x30\xdb\x75\x8a\xbe\x97\x7a"
+ "\x02\xfb\x8c\xba\xbe\x25\x09\xbe"
+ "\xce\xcb\xa2\xef\x79\x4d\x0e\x9d"
+ "\x1b\x9d\xb6\x39\x34\x38\xfa\x07"
+ "\xec\xe8\xfc\x32\x85\x1d\xf7\x85"
+ "\x63\xc3\x3c\xc0\x02\x75\xd7\x3f"
+ "\xb2\x68\x60\x66\x65\x81\xc6\xb1"
+ "\x42\x65\x4b\x4b\x28\xd7\xc7\xaa"
+ "\x9b\xd2\xdc\x1b\x01\xe0\x26\x39"
+ "\x01\xc1\x52\x14\xd1\x3f\xb7\xe6"
+ "\x61\x41\xc7\x93\xd2\xa2\x67\xc6"
+ "\xf7\x11\xb5\xf5\xea\xdd\x19\xfb"
+ "\x4d\x21\x12\xd6\x7d\xf1\x10\xb0"
+ "\x89\x07\xc7\x5a\x52\x73\x70\x2f"
+ "\x32\xef\x65\x2b\x12\xb2\xf0\xf5"
+ "\x20\xe0\x90\x59\x7e\x64\xf1\x4c"
+ "\x41\xb3\xa5\x91\x08\xe6\x5e\x5f"
+ "\x05\x56\x76\xb4\xb0\xcd\x70\x53"
+ "\x10\x48\x9c\xff\xc2\x69\x55\x24"
+ "\x87\xef\x84\xea\xfb\xa7\xbf\xa0"
+ "\x91\x04\xad\x4f\x8b\x57\x54\x4b"
+ "\xb6\xe9\xd1\xac\x37\x2f\x1d\x2e"
+ "\xab\xa5\xa4\xe8\xff\xfb\xd9\x39"
+ "\x2f\xb7\xac\xd1\xfe\x0b\x9a\x80"
+ "\x0f\xb6\xf4\x36\x39\x90\x51\xe3"
+ "\x0a\x2f\xb6\x45\x76\x89\xcd\x61"
+ "\xfe\x48\x5f\x75\x1d\x13\x00\x62"
+ "\x80\x24\x47\xe7\xbc\x37\xd7\xe3"
+ "\x15\xe8\x68\x22\xaf\x80\x6f\x4b"
+ "\xa8\x9f\x01\x10\x48\x14\xc3\x02"
+ "\x52\xd2\xc7\x75\x9b\x52\x6d\x30"
+ "\xac\x13\x85\xc8\xf7\xa3\x58\x4b"
+ "\x49\xf7\x1c\x45\x55\x8c\x39\x9a"
+ "\x99\x6d\x97\x27\x27\xe6\xab\xdd"
+ "\x2c\x42\x1b\x35\xdd\x9d\x73\xbb"
+ "\x6c\xf3\x64\xf1\xfb\xb9\xf7\xe6"
+ "\x4a\x3c\xc0\x92\xc0\x2e\xb7\x1a"
+ "\xbe\xab\xb3\x5a\xe5\xea\xb1\x48"
+ "\x58\x13\x53\x90\xfd\xc3\x8e\x54"
+ "\xf9\x18\x16\x73\xe8\xcb\x6d\x39"
+ "\x0e\xd7\xe0\xfe\xb6\x9f\x43\x97"
+ "\xe8\xd0\x85\x56\x83\x3e\x98\x68"
+ "\x7f\xbd\x95\xa8\x9a\x61\x21\x8f"
+ "\x06\x98\x34\xa6\xc8\xd6\x1d\xf3"
+ "\x3d\x43\xa4\x9a\x8c\xe5\xd3\x5a"
+ "\x32\xa2\x04\x22\xa4\x19\x1a\x46"
+ "\x42\x7e\x4d\xe5\xe0\xe6\x0e\xca"
+ "\xd5\x58\x9d\x2c\xaf\xda\x33\x5c"
+ "\xb0\x79\x9e\xc9\xfc\xca\xf0\x2f"
+ "\xa8\xb2\x77\xeb\x7a\xa2\xdd\x37"
+ "\x35\x83\x07\xd6\x02\x1a\xb6\x6c"
+ "\x24\xe2\x59\x08\x0e\xfd\x3e\x46"
+ "\xec\x40\x93\xf4\x00\x26\x4f\x2a"
+ "\xff\x47\x2f\xeb\x02\x92\x26\x5b"
+ "\x53\x17\xc2\x8d\x2a\xc7\xa3\x1b"
+ "\xcd\xbc\xa7\xe8\xd1\x76\xe3\x80"
+ "\x21\xca\x5d\x3b\xe4\x9c\x8f\xa9"
+ "\x5b\x7f\x29\x7f\x7c\xd8\xed\x6d"
+ "\x8c\xb2\x86\x85\xe7\x77\xf2\x85"
+ "\xab\x38\xa9\x9d\xc1\x4e\xc5\x64"
+ "\x33\x73\x8b\x59\x03\xad\x05\xdf"
+ "\x25\x98\x31\xde\xef\x13\xf1\x9b"
+ "\x3c\x91\x9d\x7b\xb1\xfa\xe6\xbf"
+ "\x5b\xed\xa5\x55\xe6\xea\x6c\x74"
+ "\xf4\xb9\xe4\x45\x64\x72\x81\xc2"
+ "\x4c\x28\xd4\xcd\xac\xe2\xde\xf9"
+ "\xeb\x5c\xeb\x61\x60\x5a\xe5\x28",
+ .ksize = 1088,
+ .plaintext = "",
+ .psize = 0,
+ .digest = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ }, {
+ .key = "\x29\x21\x43\xcb\xcb\x13\x07\xde"
+ "\xbf\x48\xdf\x8a\x7f\xa2\x84\xde"
+ "\x72\x23\x9d\xf5\xf0\x07\xf2\x4c"
+ "\x20\x3a\x93\xb9\xcd\x5d\xfe\xcb"
+ "\x99\x2c\x2b\x58\xc6\x50\x5f\x94"
+ "\x56\xc3\x7c\x0d\x02\x3f\xb8\x5e"
+ "\x7b\xc0\x6c\x51\x34\x76\xc0\x0e"
+ "\xc6\x22\xc8\x9e\x92\xa0\x21\xc9"
+ "\x85\x5c\x7c\xf8\xe2\x64\x47\xc9"
+ "\xe4\xa2\x57\x93\xf8\xa2\x69\xcd"
+ "\x62\x98\x99\xf4\xd7\x7b\x14\xb1"
+ "\xd8\x05\xff\x04\x15\xc9\xe1\x6e"
+ "\x9b\xe6\x50\x6b\x0b\x3f\x22\x1f"
+ "\x08\xde\x0c\x5b\x08\x7e\xc6\x2f"
+ "\x6c\xed\xd6\xb2\x15\xa4\xb3\xf9"
+ "\xa7\x46\x38\x2a\xea\x69\xa5\xde"
+ "\x02\xc3\x96\x89\x4d\x55\x3b\xed"
+ "\x3d\x3a\x85\x77\xbf\x97\x45\x5c"
+ "\x9e\x02\x69\xe2\x1b\x68\xbe\x96"
+ "\xfb\x64\x6f\x0f\xf6\x06\x40\x67"
+ "\xfa\x04\xe3\x55\xfa\xbe\xa4\x60"
+ "\xef\x21\x66\x97\xe6\x9d\x5c\x1f"
+ "\x62\x37\xaa\x31\xde\xe4\x9c\x28"
+ "\x95\xe0\x22\x86\xf4\x4d\xf3\x07"
+ "\xfd\x5f\x3a\x54\x2c\x51\x80\x71"
+ "\xba\x78\x69\x5b\x65\xab\x1f\x81"
+ "\xed\x3b\xff\x34\xa3\xfb\xbc\x73"
+ "\x66\x7d\x13\x7f\xdf\x6e\xe2\xe2"
+ "\xeb\x4f\x6c\xda\x7d\x33\x57\xd0"
+ "\xd3\x7c\x95\x4f\x33\x58\x21\xc7"
+ "\xc0\xe5\x6f\x42\x26\xc6\x1f\x5e"
+ "\x85\x1b\x98\x9a\xa2\x1e\x55\x77"
+ "\x23\xdf\x81\x5e\x79\x55\x05\xfc"
+ "\xfb\xda\xee\xba\x5a\xba\xf7\x77"
+ "\x7f\x0e\xd3\xe1\x37\xfe\x8d\x2b"
+ "\xd5\x3f\xfb\xd0\xc0\x3c\x0b\x3f"
+ "\xcf\x3c\x14\xcf\xfb\x46\x72\x4c"
+ "\x1f\x39\xe2\xda\x03\x71\x6d\x23"
+ "\xef\x93\xcd\x39\xd9\x37\x80\x4d"
+ "\x65\x61\xd1\x2c\x03\xa9\x47\x72"
+ "\x4d\x1e\x0e\x16\x33\x0f\x21\x17"
+ "\xec\x92\xea\x6f\x37\x22\xa4\xd8"
+ "\x03\x33\x9e\xd8\x03\x69\x9a\xe8"
+ "\xb2\x57\xaf\x78\x99\x05\x12\xab"
+ "\x48\x90\x80\xf0\x12\x9b\x20\x64"
+ "\x7a\x1d\x47\x5f\xba\x3c\xf9\xc3"
+ "\x0a\x0d\x8d\xa1\xf9\x1b\x82\x13"
+ "\x3e\x0d\xec\x0a\x83\xc0\x65\xe1"
+ "\xe9\x95\xff\x97\xd6\xf2\xe4\xd5"
+ "\x86\xc0\x1f\x29\x27\x63\xd7\xde"
+ "\xb7\x0a\x07\x99\x04\x2d\xa3\x89"
+ "\xa2\x43\xcf\xf3\xe1\x43\xac\x4a"
+ "\x06\x97\xd0\x05\x4f\x87\xfa\xf9"
+ "\x9b\xbf\x52\x70\xbd\xbc\x6c\xf3"
+ "\x03\x13\x60\x41\x28\x09\xec\xcc"
+ "\xb1\x1a\xec\xd6\xfb\x6f\x2a\x89"
+ "\x5d\x0b\x53\x9c\x59\xc1\x84\x21"
+ "\x33\x51\x47\x19\x31\x9c\xd4\x0a"
+ "\x4d\x04\xec\x50\x90\x61\xbd\xbc"
+ "\x7e\xc8\xd9\x6c\x98\x1d\x45\x41"
+ "\x17\x5e\x97\x1c\xc5\xa8\xe8\xea"
+ "\x46\x58\x53\xf7\x17\xd5\xad\x11"
+ "\xc8\x54\xf5\x7a\x33\x90\xf5\x19"
+ "\xba\x36\xb4\xfc\x52\xa5\x72\x3d"
+ "\x14\xbb\x55\xa7\xe9\xe3\x12\xf7"
+ "\x1c\x30\xa2\x82\x03\xbf\x53\x91"
+ "\x2e\x60\x41\x9f\x5b\x69\x39\xf6"
+ "\x4d\xc8\xf8\x46\x7a\x7f\xa4\x98"
+ "\x36\xff\x06\xcb\xca\xe7\x33\xf2"
+ "\xc0\x4a\xf4\x3c\x14\x44\x5f\x6b"
+ "\x75\xef\x02\x36\x75\x08\x14\xfd"
+ "\x10\x8e\xa5\x58\xd0\x30\x46\x49"
+ "\xaf\x3a\xf8\x40\x3d\x35\xdb\x84"
+ "\x11\x2e\x97\x6a\xb7\x87\x7f\xad"
+ "\xf1\xfa\xa5\x63\x60\xd8\x5e\xbf"
+ "\x41\x78\x49\xcf\x77\xbb\x56\xbb"
+ "\x7d\x01\x67\x05\x22\xc8\x8f\x41"
+ "\xba\x81\xd2\xca\x2c\x38\xac\x76"
+ "\x06\xc1\x1a\xc2\xce\xac\x90\x67"
+ "\x57\x3e\x20\x12\x5b\xd9\x97\x58"
+ "\x65\x05\xb7\x04\x61\x7e\xd8\x3a"
+ "\xbf\x55\x3b\x13\xe9\x34\x5a\x37"
+ "\x36\xcb\x94\x45\xc5\x32\xb3\xa0"
+ "\x0c\x3e\x49\xc5\xd3\xed\xa7\xf0"
+ "\x1c\x69\xcc\xea\xcc\x83\xc9\x16"
+ "\x95\x72\x4b\xf4\x89\xd5\xb9\x10"
+ "\xf6\x2d\x60\x15\xea\x3c\x06\x66"
+ "\x9f\x82\xad\x17\xce\xd2\xa4\x48"
+ "\x7c\x65\xd9\xf8\x02\x4d\x9b\x4c"
+ "\x89\x06\x3a\x34\x85\x48\x89\x86"
+ "\xf9\x24\xa9\x54\x72\xdb\x44\x95"
+ "\xc7\x44\x1c\x19\x11\x4c\x04\xdc"
+ "\x13\xb9\x67\xc8\xc3\x3a\x6a\x50"
+ "\xfa\xd1\xfb\xe1\x88\xb6\xf1\xa3"
+ "\xc5\x3b\xdc\x38\x45\x16\x26\x02"
+ "\x3b\xb8\x8f\x8b\x58\x7d\x23\x04"
+ "\x50\x6b\x81\x9f\xae\x66\xac\x6f"
+ "\xcf\x2a\x9d\xf1\xfd\x1d\x57\x07"
+ "\xbe\x58\xeb\x77\x0c\xe3\xc2\x19"
+ "\x14\x74\x1b\x51\x1c\x4f\x41\xf3"
+ "\x32\x89\xb3\xe7\xde\x62\xf6\x5f"
+ "\xc7\x6a\x4a\x2a\x5b\x0f\x5f\x87"
+ "\x9c\x08\xb9\x02\x88\xc8\x29\xb7"
+ "\x94\x52\xfa\x52\xfe\xaa\x50\x10"
+ "\xba\x48\x75\x5e\x11\x1b\xe6\x39"
+ "\xd7\x82\x2c\x87\xf1\x1e\xa4\x38"
+ "\x72\x3e\x51\xe7\xd8\x3e\x5b\x7b"
+ "\x31\x16\x89\xba\xd6\xad\x18\x5e"
+ "\xba\xf8\x12\xb3\xf4\x6c\x47\x30"
+ "\xc0\x38\x58\xb3\x10\x8d\x58\x5d"
+ "\xb4\xfb\x19\x7e\x41\xc3\x66\xb8"
+ "\xd6\x72\x84\xe1\x1a\xc2\x71\x4c"
+ "\x0d\x4a\x21\x7a\xab\xa2\xc0\x36"
+ "\x15\xc5\xe9\x46\xd7\x29\x17\x76"
+ "\x5e\x47\x36\x7f\x72\x05\xa7\xcc"
+ "\x36\x63\xf9\x47\x7d\xe6\x07\x3c"
+ "\x8b\x79\x1d\x96\x61\x8d\x90\x65"
+ "\x7c\xf5\xeb\x4e\x6e\x09\x59\x6d"
+ "\x62\x50\x1b\x0f\xe0\xdc\x78\xf2"
+ "\x5b\x83\x1a\xa1\x11\x75\xfd\x18"
+ "\xd7\xe2\x8d\x65\x14\x21\xce\xbe"
+ "\xb5\x87\xe3\x0a\xda\x24\x0a\x64"
+ "\xa9\x9f\x03\x8d\x46\x5d\x24\x1a"
+ "\x8a\x0c\x42\x01\xca\xb1\x5f\x7c"
+ "\xa5\xac\x32\x4a\xb8\x07\x91\x18"
+ "\x6f\xb0\x71\x3c\xc9\xb1\xa8\xf8"
+ "\x5f\x69\xa5\xa1\xca\x9e\x7a\xaa"
+ "\xac\xe9\xc7\x47\x41\x75\x25\xc3"
+ "\x73\xe2\x0b\xdd\x6d\x52\x71\xbe"
+ "\xc5\xdc\xb4\xe7\x01\x26\x53\x77"
+ "\x86\x90\x85\x68\x6b\x7b\x03\x53"
+ "\xda\x52\x52\x51\x68\xc8\xf3\xec"
+ "\x6c\xd5\x03\x7a\xa3\x0e\xb4\x02"
+ "\x5f\x1a\xab\xee\xca\x67\x29\x7b"
+ "\xbd\x96\x59\xb3\x8b\x32\x7a\x92"
+ "\x9f\xd8\x25\x2b\xdf\xc0\x4c\xda",
+ .ksize = 1088,
+ .plaintext = "\xbc\xda\x81\xa8\x78\x79\x1c\xbf"
+ "\x77\x53\xba\x4c\x30\x5b\xb8\x33",
+ .psize = 16,
+ .digest = "\x04\xbf\x7f\x6a\xce\x72\xea\x6a"
+ "\x79\xdb\xb0\xc9\x60\xf6\x12\xcc",
+ .np = 6,
+ .tap = { 4, 4, 1, 1, 1, 5 },
+ }, {
+ .key = "\x65\x4d\xe3\xf8\xd2\x4c\xac\x28"
+ "\x68\xf5\xb3\x81\x71\x4b\xa1\xfa"
+ "\x04\x0e\xd3\x81\x36\xbe\x0c\x81"
+ "\x5e\xaf\xbc\x3a\xa4\xc0\x8e\x8b"
+ "\x55\x63\xd3\x52\x97\x88\xd6\x19"
+ "\xbc\x96\xdf\x49\xff\x04\x63\xf5"
+ "\x0c\x11\x13\xaa\x9e\x1f\x5a\xf7"
+ "\xdd\xbd\x37\x80\xc3\xd0\xbe\xa7"
+ "\x05\xc8\x3c\x98\x1e\x05\x3c\x84"
+ "\x39\x61\xc4\xed\xed\x71\x1b\xc4"
+ "\x74\x45\x2c\xa1\x56\x70\x97\xfd"
+ "\x44\x18\x07\x7d\xca\x60\x1f\x73"
+ "\x3b\x6d\x21\xcb\x61\x87\x70\x25"
+ "\x46\x21\xf1\x1f\x21\x91\x31\x2d"
+ "\x5d\xcc\xb7\xd1\x84\x3e\x3d\xdb"
+ "\x03\x53\x2a\x82\xa6\x9a\x95\xbc"
+ "\x1a\x1e\x0a\x5e\x07\x43\xab\x43"
+ "\xaf\x92\x82\x06\x91\x04\x09\xf4"
+ "\x17\x0a\x9a\x2c\x54\xdb\xb8\xf4"
+ "\xd0\xf0\x10\x66\x24\x8d\xcd\xda"
+ "\xfe\x0e\x45\x9d\x6f\xc4\x4e\xf4"
+ "\x96\xaf\x13\xdc\xa9\xd4\x8c\xc4"
+ "\xc8\x57\x39\x3c\xc2\xd3\x0a\x76"
+ "\x4a\x1f\x75\x83\x44\xc7\xd1\x39"
+ "\xd8\xb5\x41\xba\x73\x87\xfa\x96"
+ "\xc7\x18\x53\xfb\x9b\xda\xa0\x97"
+ "\x1d\xee\x60\x85\x9e\x14\xc3\xce"
+ "\xc4\x05\x29\x3b\x95\x30\xa3\xd1"
+ "\x9f\x82\x6a\x04\xf5\xa7\x75\x57"
+ "\x82\x04\xfe\x71\x51\x71\xb1\x49"
+ "\x50\xf8\xe0\x96\xf1\xfa\xa8\x88"
+ "\x3f\xa0\x86\x20\xd4\x60\x79\x59"
+ "\x17\x2d\xd1\x09\xf4\xec\x05\x57"
+ "\xcf\x62\x7e\x0e\x7e\x60\x78\xe6"
+ "\x08\x60\x29\xd8\xd5\x08\x1a\x24"
+ "\xc4\x6c\x24\xe7\x92\x08\x3d\x8a"
+ "\x98\x7a\xcf\x99\x0a\x65\x0e\xdc"
+ "\x8c\x8a\xbe\x92\x82\x91\xcc\x62"
+ "\x30\xb6\xf4\x3f\xc6\x8a\x7f\x12"
+ "\x4a\x8a\x49\xfa\x3f\x5c\xd4\x5a"
+ "\xa6\x82\xa3\xe6\xaa\x34\x76\xb2"
+ "\xab\x0a\x30\xef\x6c\x77\x58\x3f"
+ "\x05\x6b\xcc\x5c\xae\xdc\xd7\xb9"
+ "\x51\x7e\x8d\x32\x5b\x24\x25\xbe"
+ "\x2b\x24\x01\xcf\x80\xda\x16\xd8"
+ "\x90\x72\x2c\xad\x34\x8d\x0c\x74"
+ "\x02\xcb\xfd\xcf\x6e\xef\x97\xb5"
+ "\x4c\xf2\x68\xca\xde\x43\x9e\x8a"
+ "\xc5\x5f\x31\x7f\x14\x71\x38\xec"
+ "\xbd\x98\xe5\x71\xc4\xb5\xdb\xef"
+ "\x59\xd2\xca\xc0\xc1\x86\x75\x01"
+ "\xd4\x15\x0d\x6f\xa4\xf7\x7b\x37"
+ "\x47\xda\x18\x93\x63\xda\xbe\x9e"
+ "\x07\xfb\xb2\x83\xd5\xc4\x34\x55"
+ "\xee\x73\xa1\x42\x96\xf9\x66\x41"
+ "\xa4\xcc\xd2\x93\x6e\xe1\x0a\xbb"
+ "\xd2\xdd\x18\x23\xe6\x6b\x98\x0b"
+ "\x8a\x83\x59\x2c\xc3\xa6\x59\x5b"
+ "\x01\x22\x59\xf7\xdc\xb0\x87\x7e"
+ "\xdb\x7d\xf4\x71\x41\xab\xbd\xee"
+ "\x79\xbe\x3c\x01\x76\x0b\x2d\x0a"
+ "\x42\xc9\x77\x8c\xbb\x54\x95\x60"
+ "\x43\x2e\xe0\x17\x52\xbd\x90\xc9"
+ "\xc2\x2c\xdd\x90\x24\x22\x76\x40"
+ "\x5c\xb9\x41\xc9\xa1\xd5\xbd\xe3"
+ "\x44\xe0\xa4\xab\xcc\xb8\xe2\x32"
+ "\x02\x15\x04\x1f\x8c\xec\x5d\x14"
+ "\xac\x18\xaa\xef\x6e\x33\x19\x6e"
+ "\xde\xfe\x19\xdb\xeb\x61\xca\x18"
+ "\xad\xd8\x3d\xbf\x09\x11\xc7\xa5"
+ "\x86\x0b\x0f\xe5\x3e\xde\xe8\xd9"
+ "\x0a\x69\x9e\x4c\x20\xff\xf9\xc5"
+ "\xfa\xf8\xf3\x7f\xa5\x01\x4b\x5e"
+ "\x0f\xf0\x3b\x68\xf0\x46\x8c\x2a"
+ "\x7a\xc1\x8f\xa0\xfe\x6a\x5b\x44"
+ "\x70\x5c\xcc\x92\x2c\x6f\x0f\xbd"
+ "\x25\x3e\xb7\x8e\x73\x58\xda\xc9"
+ "\xa5\xaa\x9e\xf3\x9b\xfd\x37\x3e"
+ "\xe2\x88\xa4\x7b\xc8\x5c\xa8\x93"
+ "\x0e\xe7\x9a\x9c\x2e\x95\x18\x9f"
+ "\xc8\x45\x0c\x88\x9e\x53\x4f\x3a"
+ "\x76\xc1\x35\xfa\x17\xd8\xac\xa0"
+ "\x0c\x2d\x47\x2e\x4f\x69\x9b\xf7"
+ "\xd0\xb6\x96\x0c\x19\xb3\x08\x01"
+ "\x65\x7a\x1f\xc7\x31\x86\xdb\xc8"
+ "\xc1\x99\x8f\xf8\x08\x4a\x9d\x23"
+ "\x22\xa8\xcf\x27\x01\x01\x88\x93"
+ "\x9c\x86\x45\xbd\xe0\x51\xca\x52"
+ "\x84\xba\xfe\x03\xf7\xda\xc5\xce"
+ "\x3e\x77\x75\x86\xaf\x84\xc8\x05"
+ "\x44\x01\x0f\x02\xf3\x58\xb0\x06"
+ "\x5a\xd7\x12\x30\x8d\xdf\x1f\x1f"
+ "\x0a\xe6\xd2\xea\xf6\x3a\x7a\x99"
+ "\x63\xe8\xd2\xc1\x4a\x45\x8b\x40"
+ "\x4d\x0a\xa9\x76\x92\xb3\xda\x87"
+ "\x36\x33\xf0\x78\xc3\x2f\x5f\x02"
+ "\x1a\x6a\x2c\x32\xcd\x76\xbf\xbd"
+ "\x5a\x26\x20\x28\x8c\x8c\xbc\x52"
+ "\x3d\x0a\xc9\xcb\xab\xa4\x21\xb0"
+ "\x54\x40\x81\x44\xc7\xd6\x1c\x11"
+ "\x44\xc6\x02\x92\x14\x5a\xbf\x1a"
+ "\x09\x8a\x18\xad\xcd\x64\x3d\x53"
+ "\x4a\xb6\xa5\x1b\x57\x0e\xef\xe0"
+ "\x8c\x44\x5f\x7d\xbd\x6c\xfd\x60"
+ "\xae\x02\x24\xb6\x99\xdd\x8c\xaf"
+ "\x59\x39\x75\x3c\xd1\x54\x7b\x86"
+ "\xcc\x99\xd9\x28\x0c\xb0\x94\x62"
+ "\xf9\x51\xd1\x19\x96\x2d\x66\xf5"
+ "\x55\xcf\x9e\x59\xe2\x6b\x2c\x08"
+ "\xc0\x54\x48\x24\x45\xc3\x8c\x73"
+ "\xea\x27\x6e\x66\x7d\x1d\x0e\x6e"
+ "\x13\xe8\x56\x65\x3a\xb0\x81\x5c"
+ "\xf0\xe8\xd8\x00\x6b\xcd\x8f\xad"
+ "\xdd\x53\xf3\xa4\x6c\x43\xd6\x31"
+ "\xaf\xd2\x76\x1e\x91\x12\xdb\x3c"
+ "\x8c\xc2\x81\xf0\x49\xdb\xe2\x6b"
+ "\x76\x62\x0a\x04\xe4\xaa\x8a\x7c"
+ "\x08\x0b\x5d\xd0\xee\x1d\xfb\xc4"
+ "\x02\x75\x42\xd6\xba\xa7\x22\xa8"
+ "\x47\x29\xb7\x85\x6d\x93\x3a\xdb"
+ "\x00\x53\x0b\xa2\xeb\xf8\xfe\x01"
+ "\x6f\x8a\x31\xd6\x17\x05\x6f\x67"
+ "\x88\x95\x32\xfe\x4f\xa6\x4b\xf8"
+ "\x03\xe4\xcd\x9a\x18\xe8\x4e\x2d"
+ "\xf7\x97\x9a\x0c\x7d\x9f\x7e\x44"
+ "\x69\x51\xe0\x32\x6b\x62\x86\x8f"
+ "\xa6\x8e\x0b\x21\x96\xe5\xaf\x77"
+ "\xc0\x83\xdf\xa5\x0e\xd0\xa1\x04"
+ "\xaf\xc1\x10\xcb\x5a\x40\xe4\xe3"
+ "\x38\x7e\x07\xe8\x4d\xfa\xed\xc5"
+ "\xf0\x37\xdf\xbb\x8a\xcf\x3d\xdc"
+ "\x61\xd2\xc6\x2b\xff\x07\xc9\x2f"
+ "\x0c\x2d\x5c\x07\xa8\x35\x6a\xfc"
+ "\xae\x09\x03\x45\x74\x51\x4d\xc4"
+ "\xb8\x23\x87\x4a\x99\x27\x20\x87"
+ "\x62\x44\x0a\x4a\xce\x78\x47\x22",
+ .ksize = 1088,
+ .plaintext = "\x8e\xb0\x4c\xde\x9c\x4a\x04\x5a"
+ "\xf6\xa9\x7f\x45\x25\xa5\x7b\x3a"
+ "\xbc\x4d\x73\x39\x81\xb5\xbd\x3d"
+ "\x21\x6f\xd7\x37\x50\x3c\x7b\x28"
+ "\xd1\x03\x3a\x17\xed\x7b\x7c\x2a"
+ "\x16\xbc\xdf\x19\x89\x52\x71\x31"
+ "\xb6\xc0\xfd\xb5\xd3\xba\x96\x99"
+ "\xb6\x34\x0b\xd0\x99\x93\xfc\x1a"
+ "\x01\x3c\x85\xc6\x9b\x78\x5c\x8b"
+ "\xfe\xae\xd2\xbf\xb2\x6f\xf9\xed"
+ "\xc8\x25\x17\xfe\x10\x3b\x7d\xda"
+ "\xf4\x8d\x35\x4b\x7c\x7b\x82\xe7"
+ "\xc2\xb3\xee\x60\x4a\x03\x86\xc9"
+ "\x4e\xb5\xc4\xbe\xd2\xbd\x66\xf1"
+ "\x13\xf1\x09\xab\x5d\xca\x63\x1f"
+ "\xfc\xfb\x57\x2a\xfc\xca\x66\xd8"
+ "\x77\x84\x38\x23\x1d\xac\xd3\xb3"
+ "\x7a\xad\x4c\x70\xfa\x9c\xc9\x61"
+ "\xa6\x1b\xba\x33\x4b\x4e\x33\xec"
+ "\xa0\xa1\x64\x39\x40\x05\x1c\xc2"
+ "\x3f\x49\x9d\xae\xf2\xc5\xf2\xc5"
+ "\xfe\xe8\xf4\xc2\xf9\x96\x2d\x28"
+ "\x92\x30\x44\xbc\xd2\x7f\xe1\x6e"
+ "\x62\x02\x8f\x3d\x1c\x80\xda\x0e"
+ "\x6a\x90\x7e\x75\xff\xec\x3e\xc4"
+ "\xcd\x16\x34\x3b\x05\x6d\x4d\x20"
+ "\x1c\x7b\xf5\x57\x4f\xfa\x3d\xac"
+ "\xd0\x13\x55\xe8\xb3\xe1\x1b\x78"
+ "\x30\xe6\x9f\x84\xd4\x69\xd1\x08"
+ "\x12\x77\xa7\x4a\xbd\xc0\xf2\xd2"
+ "\x78\xdd\xa3\x81\x12\xcb\x6c\x14"
+ "\x90\x61\xe2\x84\xc6\x2b\x16\xcc"
+ "\x40\x99\x50\x88\x01\x09\x64\x4f"
+ "\x0a\x80\xbe\x61\xae\x46\xc9\x0a"
+ "\x5d\xe0\xfb\x72\x7a\x1a\xdd\x61"
+ "\x63\x20\x05\xa0\x4a\xf0\x60\x69"
+ "\x7f\x92\xbc\xbf\x4e\x39\x4d\xdd"
+ "\x74\xd1\xb7\xc0\x5a\x34\xb7\xae"
+ "\x76\x65\x2e\xbc\x36\xb9\x04\x95"
+ "\x42\xe9\x6f\xca\x78\xb3\x72\x07"
+ "\xa3\xba\x02\x94\x67\x4c\xb1\xd7"
+ "\xe9\x30\x0d\xf0\x3b\xb8\x10\x6d"
+ "\xea\x2b\x21\xbf\x74\x59\x82\x97"
+ "\x85\xaa\xf1\xd7\x54\x39\xeb\x05"
+ "\xbd\xf3\x40\xa0\x97\xe6\x74\xfe"
+ "\xb4\x82\x5b\xb1\x36\xcb\xe8\x0d"
+ "\xce\x14\xd9\xdf\xf1\x94\x22\xcd"
+ "\xd6\x00\xba\x04\x4c\x05\x0c\xc0"
+ "\xd1\x5a\xeb\x52\xd5\xa8\x8e\xc8"
+ "\x97\xa1\xaa\xc1\xea\xc1\xbe\x7c"
+ "\x36\xb3\x36\xa0\xc6\x76\x66\xc5"
+ "\xe2\xaf\xd6\x5c\xe2\xdb\x2c\xb3"
+ "\x6c\xb9\x99\x7f\xff\x9f\x03\x24"
+ "\xe1\x51\x44\x66\xd8\x0c\x5d\x7f"
+ "\x5c\x85\x22\x2a\xcf\x6d\x79\x28"
+ "\xab\x98\x01\x72\xfe\x80\x87\x5f"
+ "\x46\xba\xef\x81\x24\xee\xbf\xb0"
+ "\x24\x74\xa3\x65\x97\x12\xc4\xaf"
+ "\x8b\xa0\x39\xda\x8a\x7e\x74\x6e"
+ "\x1b\x42\xb4\x44\x37\xfc\x59\xfd"
+ "\x86\xed\xfb\x8c\x66\x33\xda\x63"
+ "\x75\xeb\xe1\xa4\x85\x4f\x50\x8f"
+ "\x83\x66\x0d\xd3\x37\xfa\xe6\x9c"
+ "\x4f\x30\x87\x35\x18\xe3\x0b\xb7"
+ "\x6e\x64\x54\xcd\x70\xb3\xde\x54"
+ "\xb7\x1d\xe6\x4c\x4d\x55\x12\x12"
+ "\xaf\x5f\x7f\x5e\xee\x9d\xe8\x8e"
+ "\x32\x9d\x4e\x75\xeb\xc6\xdd\xaa"
+ "\x48\x82\xa4\x3f\x3c\xd7\xd3\xa8"
+ "\x63\x9e\x64\xfe\xe3\x97\x00\x62"
+ "\xe5\x40\x5d\xc3\xad\x72\xe1\x28"
+ "\x18\x50\xb7\x75\xef\xcd\x23\xbf"
+ "\x3f\xc0\x51\x36\xf8\x41\xc3\x08"
+ "\xcb\xf1\x8d\x38\x34\xbd\x48\x45"
+ "\x75\xed\xbc\x65\x7b\xb5\x0c\x9b"
+ "\xd7\x67\x7d\x27\xb4\xc4\x80\xd7"
+ "\xa9\xb9\xc7\x4a\x97\xaa\xda\xc8"
+ "\x3c\x74\xcf\x36\x8f\xe4\x41\xe3"
+ "\xd4\xd3\x26\xa7\xf3\x23\x9d\x8f"
+ "\x6c\x20\x05\x32\x3e\xe0\xc3\xc8"
+ "\x56\x3f\xa7\x09\xb7\xfb\xc7\xf7"
+ "\xbe\x2a\xdd\x0f\x06\x7b\x0d\xdd"
+ "\xb0\xb4\x86\x17\xfd\xb9\x04\xe5"
+ "\xc0\x64\x5d\xad\x2a\x36\x38\xdb"
+ "\x24\xaf\x5b\xff\xca\xf9\x41\xe8"
+ "\xf9\x2f\x1e\x5e\xf9\xf5\xd5\xf2"
+ "\xb2\x88\xca\xc9\xa1\x31\xe2\xe8"
+ "\x10\x95\x65\xbf\xf1\x11\x61\x7a"
+ "\x30\x1a\x54\x90\xea\xd2\x30\xf6"
+ "\xa5\xad\x60\xf9\x4d\x84\x21\x1b"
+ "\xe4\x42\x22\xc8\x12\x4b\xb0\x58"
+ "\x3e\x9c\x2d\x32\x95\x0a\x8e\xb0"
+ "\x0a\x7e\x77\x2f\xe8\x97\x31\x6a"
+ "\xf5\x59\xb4\x26\xe6\x37\x12\xc9"
+ "\xcb\xa0\x58\x33\x6f\xd5\x55\x55"
+ "\x3c\xa1\x33\xb1\x0b\x7e\x2e\xb4"
+ "\x43\x2a\x84\x39\xf0\x9c\xf4\x69"
+ "\x4f\x1e\x79\xa6\x15\x1b\x87\xbb"
+ "\xdb\x9b\xe0\xf1\x0b\xba\xe3\x6e"
+ "\xcc\x2f\x49\x19\x22\x29\xfc\x71"
+ "\xbb\x77\x38\x18\x61\xaf\x85\x76"
+ "\xeb\xd1\x09\xcc\x86\x04\x20\x9a"
+ "\x66\x53\x2f\x44\x8b\xc6\xa3\xd2"
+ "\x5f\xc7\x79\x82\x66\xa8\x6e\x75"
+ "\x7d\x94\xd1\x86\x75\x0f\xa5\x4f"
+ "\x3c\x7a\x33\xce\xd1\x6e\x9d\x7b"
+ "\x1f\x91\x37\xb8\x37\x80\xfb\xe0"
+ "\x52\x26\xd0\x9a\xd4\x48\x02\x41"
+ "\x05\xe3\x5a\x94\xf1\x65\x61\x19"
+ "\xb8\x88\x4e\x2b\xea\xba\x8b\x58"
+ "\x8b\x42\x01\x00\xa8\xfe\x00\x5c"
+ "\xfe\x1c\xee\x31\x15\x69\xfa\xb3"
+ "\x9b\x5f\x22\x8e\x0d\x2c\xe3\xa5"
+ "\x21\xb9\x99\x8a\x8e\x94\x5a\xef"
+ "\x13\x3e\x99\x96\x79\x6e\xd5\x42"
+ "\x36\x03\xa9\xe2\xca\x65\x4e\x8a"
+ "\x8a\x30\xd2\x7d\x74\xe7\xf0\xaa"
+ "\x23\x26\xdd\xcb\x82\x39\xfc\x9d"
+ "\x51\x76\x21\x80\xa2\xbe\x93\x03"
+ "\x47\xb0\xc1\xb6\xdc\x63\xfd\x9f"
+ "\xca\x9d\xa5\xca\x27\x85\xe2\xd8"
+ "\x15\x5b\x7e\x14\x7a\xc4\x89\xcc"
+ "\x74\x14\x4b\x46\xd2\xce\xac\x39"
+ "\x6b\x6a\x5a\xa4\x0e\xe3\x7b\x15"
+ "\x94\x4b\x0f\x74\xcb\x0c\x7f\xa9"
+ "\xbe\x09\x39\xa3\xdd\x56\x5c\xc7"
+ "\x99\x56\x65\x39\xf4\x0b\x7d\x87"
+ "\xec\xaa\xe3\x4d\x22\x65\x39\x4e",
+ .psize = 1024,
+ .digest = "\x64\x3a\xbc\xc3\x3f\x74\x40\x51"
+ "\x6e\x56\x01\x1a\x51\xec\x36\xde",
+ .np = 8,
+ .tap = { 64, 203, 267, 28, 263, 62, 54, 83 },
+ }, {
+ .key = "\x1b\x82\x2e\x1b\x17\x23\xb9\x6d"
+ "\xdc\x9c\xda\x99\x07\xe3\x5f\xd8"
+ "\xd2\xf8\x43\x80\x8d\x86\x7d\x80"
+ "\x1a\xd0\xcc\x13\xb9\x11\x05\x3f"
+ "\x7e\xcf\x7e\x80\x0e\xd8\x25\x48"
+ "\x8b\xaa\x63\x83\x92\xd0\x72\xf5"
+ "\x4f\x67\x7e\x50\x18\x25\xa4\xd1"
+ "\xe0\x7e\x1e\xba\xd8\xa7\x6e\xdb"
+ "\x1a\xcc\x0d\xfe\x9f\x6d\x22\x35"
+ "\xe1\xe6\xe0\xa8\x7b\x9c\xb1\x66"
+ "\xa3\xf8\xff\x4d\x90\x84\x28\xbc"
+ "\xdc\x19\xc7\x91\x49\xfc\xf6\x33"
+ "\xc9\x6e\x65\x7f\x28\x6f\x68\x2e"
+ "\xdf\x1a\x75\xe9\xc2\x0c\x96\xb9"
+ "\x31\x22\xc4\x07\xc6\x0a\x2f\xfd"
+ "\x36\x06\x5f\x5c\xc5\xb1\x3a\xf4"
+ "\x5e\x48\xa4\x45\x2b\x88\xa7\xee"
+ "\xa9\x8b\x52\xcc\x99\xd9\x2f\xb8"
+ "\xa4\x58\x0a\x13\xeb\x71\x5a\xfa"
+ "\xe5\x5e\xbe\xf2\x64\xad\x75\xbc"
+ "\x0b\x5b\x34\x13\x3b\x23\x13\x9a"
+ "\x69\x30\x1e\x9a\xb8\x03\xb8\x8b"
+ "\x3e\x46\x18\x6d\x38\xd9\xb3\xd8"
+ "\xbf\xf1\xd0\x28\xe6\x51\x57\x80"
+ "\x5e\x99\xfb\xd0\xce\x1e\x83\xf7"
+ "\xe9\x07\x5a\x63\xa9\xef\xce\xa5"
+ "\xfb\x3f\x37\x17\xfc\x0b\x37\x0e"
+ "\xbb\x4b\x21\x62\xb7\x83\x0e\xa9"
+ "\x9e\xb0\xc4\xad\x47\xbe\x35\xe7"
+ "\x51\xb2\xf2\xac\x2b\x65\x7b\x48"
+ "\xe3\x3f\x5f\xb6\x09\x04\x0c\x58"
+ "\xce\x99\xa9\x15\x2f\x4e\xc1\xf2"
+ "\x24\x48\xc0\xd8\x6c\xd3\x76\x17"
+ "\x83\x5d\xe6\xe3\xfd\x01\x8e\xf7"
+ "\x42\xa5\x04\x29\x30\xdf\xf9\x00"
+ "\x4a\xdc\x71\x22\x1a\x33\x15\xb6"
+ "\xd7\x72\xfb\x9a\xb8\xeb\x2b\x38"
+ "\xea\xa8\x61\xa8\x90\x11\x9d\x73"
+ "\x2e\x6c\xce\x81\x54\x5a\x9f\xcd"
+ "\xcf\xd5\xbd\x26\x5d\x66\xdb\xfb"
+ "\xdc\x1e\x7c\x10\xfe\x58\x82\x10"
+ "\x16\x24\x01\xce\x67\x55\x51\xd1"
+ "\xdd\x6b\x44\xa3\x20\x8e\xa9\xa6"
+ "\x06\xa8\x29\x77\x6e\x00\x38\x5b"
+ "\xde\x4d\x58\xd8\x1f\x34\xdf\xf9"
+ "\x2c\xac\x3e\xad\xfb\x92\x0d\x72"
+ "\x39\xa4\xac\x44\x10\xc0\x43\xc4"
+ "\xa4\x77\x3b\xfc\xc4\x0d\x37\xd3"
+ "\x05\x84\xda\x53\x71\xf8\x80\xd3"
+ "\x34\x44\xdb\x09\xb4\x2b\x8e\xe3"
+ "\x00\x75\x50\x9e\x43\x22\x00\x0b"
+ "\x7c\x70\xab\xd4\x41\xf1\x93\xcd"
+ "\x25\x2d\x84\x74\xb5\xf2\x92\xcd"
+ "\x0a\x28\xea\x9a\x49\x02\x96\xcb"
+ "\x85\x9e\x2f\x33\x03\x86\x1d\xdc"
+ "\x1d\x31\xd5\xfc\x9d\xaa\xc5\xe9"
+ "\x9a\xc4\x57\xf5\x35\xed\xf4\x4b"
+ "\x3d\x34\xc2\x29\x13\x86\x36\x42"
+ "\x5d\xbf\x90\x86\x13\x77\xe5\xc3"
+ "\x62\xb4\xfe\x0b\x70\x39\x35\x65"
+ "\x02\xea\xf6\xce\x57\x0c\xbb\x74"
+ "\x29\xe3\xfd\x60\x90\xfd\x10\x38"
+ "\xd5\x4e\x86\xbd\x37\x70\xf0\x97"
+ "\xa6\xab\x3b\x83\x64\x52\xca\x66"
+ "\x2f\xf9\xa4\xca\x3a\x55\x6b\xb0"
+ "\xe8\x3a\x34\xdb\x9e\x48\x50\x2f"
+ "\x3b\xef\xfd\x08\x2d\x5f\xc1\x37"
+ "\x5d\xbe\x73\xe4\xd8\xe9\xac\xca"
+ "\x8a\xaa\x48\x7c\x5c\xf4\xa6\x96"
+ "\x5f\xfa\x70\xa6\xb7\x8b\x50\xcb"
+ "\xa6\xf5\xa9\xbd\x7b\x75\x4c\x22"
+ "\x0b\x19\x40\x2e\xc9\x39\x39\x32"
+ "\x83\x03\xa8\xa4\x98\xe6\x8e\x16"
+ "\xb9\xde\x08\xc5\xfc\xbf\xad\x39"
+ "\xa8\xc7\x93\x6c\x6f\x23\xaf\xc1"
+ "\xab\xe1\xdf\xbb\x39\xae\x93\x29"
+ "\x0e\x7d\x80\x8d\x3e\x65\xf3\xfd"
+ "\x96\x06\x65\x90\xa1\x28\x64\x4b"
+ "\x69\xf9\xa8\x84\x27\x50\xfc\x87"
+ "\xf7\xbf\x55\x8e\x56\x13\x58\x7b"
+ "\x85\xb4\x6a\x72\x0f\x40\xf1\x4f"
+ "\x83\x81\x1f\x76\xde\x15\x64\x7a"
+ "\x7a\x80\xe4\xc7\x5e\x63\x01\x91"
+ "\xd7\x6b\xea\x0b\x9b\xa2\x99\x3b"
+ "\x6c\x88\xd8\xfd\x59\x3c\x8d\x22"
+ "\x86\x56\xbe\xab\xa1\x37\x08\x01"
+ "\x50\x85\x69\x29\xee\x9f\xdf\x21"
+ "\x3e\x20\x20\xf5\xb0\xbb\x6b\xd0"
+ "\x9c\x41\x38\xec\x54\x6f\x2d\xbd"
+ "\x0f\xe1\xbd\xf1\x2b\x6e\x60\x56"
+ "\x29\xe5\x7a\x70\x1c\xe2\xfc\x97"
+ "\x82\x68\x67\xd9\x3d\x1f\xfb\xd8"
+ "\x07\x9f\xbf\x96\x74\xba\x6a\x0e"
+ "\x10\x48\x20\xd8\x13\x1e\xb5\x44"
+ "\xf2\xcc\xb1\x8b\xfb\xbb\xec\xd7"
+ "\x37\x70\x1f\x7c\x55\xd2\x4b\xb9"
+ "\xfd\x70\x5e\xa3\x91\x73\x63\x52"
+ "\x13\x47\x5a\x06\xfb\x01\x67\xa5"
+ "\xc0\xd0\x49\x19\x56\x66\x9a\x77"
+ "\x64\xaf\x8c\x25\x91\x52\x87\x0e"
+ "\x18\xf3\x5f\x97\xfd\x71\x13\xf8"
+ "\x05\xa5\x39\xcc\x65\xd3\xcc\x63"
+ "\x5b\xdb\x5f\x7e\x5f\x6e\xad\xc4"
+ "\xf4\xa0\xc5\xc2\x2b\x4d\x97\x38"
+ "\x4f\xbc\xfa\x33\x17\xb4\x47\xb9"
+ "\x43\x24\x15\x8d\xd2\xed\x80\x68"
+ "\x84\xdb\x04\x80\xca\x5e\x6a\x35"
+ "\x2c\x2c\xe7\xc5\x03\x5f\x54\xb0"
+ "\x5e\x4f\x1d\x40\x54\x3d\x78\x9a"
+ "\xac\xda\x80\x27\x4d\x15\x4c\x1a"
+ "\x6e\x80\xc9\xc4\x3b\x84\x0e\xd9"
+ "\x2e\x93\x01\x8c\xc3\xc8\x91\x4b"
+ "\xb3\xaa\x07\x04\x68\x5b\x93\xa5"
+ "\xe7\xc4\x9d\xe7\x07\xee\xf5\x3b"
+ "\x40\x89\xcc\x60\x34\x9d\xb4\x06"
+ "\x1b\xef\x92\xe6\xc1\x2a\x7d\x0f"
+ "\x81\xaa\x56\xe3\xd7\xed\xa7\xd4"
+ "\xa7\x3a\x49\xc4\xad\x81\x5c\x83"
+ "\x55\x8e\x91\x54\xb7\x7d\x65\xa5"
+ "\x06\x16\xd5\x9a\x16\xc1\xb0\xa2"
+ "\x06\xd8\x98\x47\x73\x7e\x73\xa0"
+ "\xb8\x23\xb1\x52\xbf\x68\x74\x5d"
+ "\x0b\xcb\xfa\x8c\x46\xe3\x24\xe6"
+ "\xab\xd4\x69\x8d\x8c\xf2\x8a\x59"
+ "\xbe\x48\x46\x50\x8c\x9a\xe8\xe3"
+ "\x31\x55\x0a\x06\xed\x4f\xf8\xb7"
+ "\x4f\xe3\x85\x17\x30\xbd\xd5\x20"
+ "\xe7\x5b\xb2\x32\xcf\x6b\x16\x44"
+ "\xd2\xf5\x7e\xd7\xd1\x2f\xee\x64"
+ "\x3e\x9d\x10\xef\x27\x35\x43\x64"
+ "\x67\xfb\x7a\x7b\xe0\x62\x31\x9a"
+ "\x4d\xdf\xa5\xab\xc0\x20\xbb\x01"
+ "\xe9\x7b\x54\xf1\xde\xb2\x79\x50"
+ "\x6c\x4b\x91\xdb\x7f\xbb\x50\xc1"
+ "\x55\x44\x38\x9a\xe0\x9f\xe8\x29"
+ "\x6f\x15\xf8\x4e\xa6\xec\xa0\x60",
+ .ksize = 1088,
+ .plaintext = "\x15\x68\x9e\x2f\xad\x15\x52\xdf"
+ "\xf0\x42\x62\x24\x2a\x2d\xea\xbf"
+ "\xc7\xf3\xb4\x1a\xf5\xed\xb2\x08"
+ "\x15\x60\x1c\x00\x77\xbf\x0b\x0e"
+ "\xb7\x2c\xcf\x32\x3a\xc7\x01\x77"
+ "\xef\xa6\x75\xd0\x29\xc7\x68\x20"
+ "\xb2\x92\x25\xbf\x12\x34\xe9\xa4"
+ "\xfd\x32\x7b\x3f\x7c\xbd\xa5\x02"
+ "\x38\x41\xde\xc9\xc1\x09\xd9\xfc"
+ "\x6e\x78\x22\x83\x18\xf7\x50\x8d"
+ "\x8f\x9c\x2d\x02\xa5\x30\xac\xff"
+ "\xea\x63\x2e\x80\x37\x83\xb0\x58"
+ "\xda\x2f\xef\x21\x55\xba\x7b\xb1"
+ "\xb6\xed\xf5\xd2\x4d\xaa\x8c\xa9"
+ "\xdd\xdb\x0f\xb4\xce\xc1\x9a\xb1"
+ "\xc1\xdc\xbd\xab\x86\xc2\xdf\x0b"
+ "\xe1\x2c\xf9\xbe\xf6\xd8\xda\x62"
+ "\x72\xdd\x98\x09\x52\xc0\xc4\xb6"
+ "\x7b\x17\x5c\xf5\xd8\x4b\x88\xd6"
+ "\x6b\xbf\x84\x4a\x3f\xf5\x4d\xd2"
+ "\x94\xe2\x9c\xff\xc7\x3c\xd9\xc8"
+ "\x37\x38\xbc\x8c\xf3\xe7\xb7\xd0"
+ "\x1d\x78\xc4\x39\x07\xc8\x5e\x79"
+ "\xb6\x5a\x90\x5b\x6e\x97\xc9\xd4"
+ "\x82\x9c\xf3\x83\x7a\xe7\x97\xfc"
+ "\x1d\xbb\xef\xdb\xce\xe0\x82\xad"
+ "\xca\x07\x6c\x54\x62\x6f\x81\xe6"
+ "\x7a\x5a\x96\x6e\x80\x3a\xa2\x37"
+ "\x6f\xc6\xa4\x29\xc3\x9e\x19\x94"
+ "\x9f\xb0\x3e\x38\xfb\x3c\x2b\x7d"
+ "\xaa\xb8\x74\xda\x54\x23\x51\x12"
+ "\x4b\x96\x36\x8f\x91\x4f\x19\x37"
+ "\x83\xc9\xdd\xc7\x1a\x32\x2d\xab"
+ "\xc7\x89\xe2\x07\x47\x6c\xe8\xa6"
+ "\x70\x6b\x8e\x0c\xda\x5c\x6a\x59"
+ "\x27\x33\x0e\xe1\xe1\x20\xe8\xc8"
+ "\xae\xdc\xd0\xe3\x6d\xa8\xa6\x06"
+ "\x41\xb4\xd4\xd4\xcf\x91\x3e\x06"
+ "\xb0\x9a\xf7\xf1\xaa\xa6\x23\x92"
+ "\x10\x86\xf0\x94\xd1\x7c\x2e\x07"
+ "\x30\xfb\xc5\xd8\xf3\x12\xa9\xe8"
+ "\x22\x1c\x97\x1a\xad\x96\xb0\xa1"
+ "\x72\x6a\x6b\xb4\xfd\xf7\xe8\xfa"
+ "\xe2\x74\xd8\x65\x8d\x35\x17\x4b"
+ "\x00\x23\x5c\x8c\x70\xad\x71\xa2"
+ "\xca\xc5\x6c\x59\xbf\xb4\xc0\x6d"
+ "\x86\x98\x3e\x19\x5a\x90\x92\xb1"
+ "\x66\x57\x6a\x91\x68\x7c\xbc\xf3"
+ "\xf1\xdb\x94\xf8\x48\xf1\x36\xd8"
+ "\x78\xac\x1c\xa9\xcc\xd6\x27\xba"
+ "\x91\x54\x22\xf5\xe6\x05\x3f\xcc"
+ "\xc2\x8f\x2c\x3b\x2b\xc3\x2b\x2b"
+ "\x3b\xb8\xb6\x29\xb7\x2f\x94\xb6"
+ "\x7b\xfc\x94\x3e\xd0\x7a\x41\x59"
+ "\x7b\x1f\x9a\x09\xa6\xed\x4a\x82"
+ "\x9d\x34\x1c\xbd\x4e\x1c\x3a\x66"
+ "\x80\x74\x0e\x9a\x4f\x55\x54\x47"
+ "\x16\xba\x2a\x0a\x03\x35\x99\xa3"
+ "\x5c\x63\x8d\xa2\x72\x8b\x17\x15"
+ "\x68\x39\x73\xeb\xec\xf2\xe8\xf5"
+ "\x95\x32\x27\xd6\xc4\xfe\xb0\x51"
+ "\xd5\x0c\x50\xc5\xcd\x6d\x16\xb3"
+ "\xa3\x1e\x95\x69\xad\x78\x95\x06"
+ "\xb9\x46\xf2\x6d\x24\x5a\x99\x76"
+ "\x73\x6a\x91\xa6\xac\x12\xe1\x28"
+ "\x79\xbc\x08\x4e\x97\x00\x98\x63"
+ "\x07\x1c\x4e\xd1\x68\xf3\xb3\x81"
+ "\xa8\xa6\x5f\xf1\x01\xc9\xc1\xaf"
+ "\x3a\x96\xf9\x9d\xb5\x5a\x5f\x8f"
+ "\x7e\xc1\x7e\x77\x0a\x40\xc8\x8e"
+ "\xfc\x0e\xed\xe1\x0d\xb0\xe5\x5e"
+ "\x5e\x6f\xf5\x7f\xab\x33\x7d\xcd"
+ "\xf0\x09\x4b\xb2\x11\x37\xdc\x65"
+ "\x97\x32\x62\x71\x3a\x29\x54\xb9"
+ "\xc7\xa4\xbf\x75\x0f\xf9\x40\xa9"
+ "\x8d\xd7\x8b\xa7\xe0\x9a\xbe\x15"
+ "\xc6\xda\xd8\x00\x14\x69\x1a\xaf"
+ "\x5f\x79\xc3\xf5\xbb\x6c\x2a\x9d"
+ "\xdd\x3c\x5f\x97\x21\xe1\x3a\x03"
+ "\x84\x6a\xe9\x76\x11\x1f\xd3\xd5"
+ "\xf0\x54\x20\x4d\xc2\x91\xc3\xa4"
+ "\x36\x25\xbe\x1b\x2a\x06\xb7\xf3"
+ "\xd1\xd0\x55\x29\x81\x4c\x83\xa3"
+ "\xa6\x84\x1e\x5c\xd1\xd0\x6c\x90"
+ "\xa4\x11\xf0\xd7\x63\x6a\x48\x05"
+ "\xbc\x48\x18\x53\xcd\xb0\x8d\xdb"
+ "\xdc\xfe\x55\x11\x5c\x51\xb3\xab"
+ "\xab\x63\x3e\x31\x5a\x8b\x93\x63"
+ "\x34\xa9\xba\x2b\x69\x1a\xc0\xe3"
+ "\xcb\x41\xbc\xd7\xf5\x7f\x82\x3e"
+ "\x01\xa3\x3c\x72\xf4\xfe\xdf\xbe"
+ "\xb1\x67\x17\x2b\x37\x60\x0d\xca"
+ "\x6f\xc3\x94\x2c\xd2\x92\x6d\x9d"
+ "\x75\x18\x77\xaa\x29\x38\x96\xed"
+ "\x0e\x20\x70\x92\xd5\xd0\xb4\x00"
+ "\xc0\x31\xf2\xc9\x43\x0e\x75\x1d"
+ "\x4b\x64\xf2\x1f\xf2\x29\x6c\x7b"
+ "\x7f\xec\x59\x7d\x8c\x0d\xd4\xd3"
+ "\xac\x53\x4c\xa3\xde\x42\x92\x95"
+ "\x6d\xa3\x4f\xd0\xe6\x3d\xe7\xec"
+ "\x7a\x4d\x68\xf1\xfe\x67\x66\x09"
+ "\x83\x22\xb1\x98\x43\x8c\xab\xb8"
+ "\x45\xe6\x6d\xdf\x5e\x50\x71\xce"
+ "\xf5\x4e\x40\x93\x2b\xfa\x86\x0e"
+ "\xe8\x30\xbd\x82\xcc\x1c\x9c\x5f"
+ "\xad\xfd\x08\x31\xbe\x52\xe7\xe6"
+ "\xf2\x06\x01\x62\x25\x15\x99\x74"
+ "\x33\x51\x52\x57\x3f\x57\x87\x61"
+ "\xb9\x7f\x29\x3d\xcd\x92\x5e\xa6"
+ "\x5c\x3b\xf1\xed\x5f\xeb\x82\xed"
+ "\x56\x7b\x61\xe7\xfd\x02\x47\x0e"
+ "\x2a\x15\xa4\xce\x43\x86\x9b\xe1"
+ "\x2b\x4c\x2a\xd9\x42\x97\xf7\x9a"
+ "\xe5\x47\x46\x48\xd3\x55\x6f\x4d"
+ "\xd9\xeb\x4b\xdd\x7b\x21\x2f\xb3"
+ "\xa8\x36\x28\xdf\xca\xf1\xf6\xd9"
+ "\x10\xf6\x1c\xfd\x2e\x0c\x27\xe0"
+ "\x01\xb3\xff\x6d\x47\x08\x4d\xd4"
+ "\x00\x25\xee\x55\x4a\xe9\xe8\x5b"
+ "\xd8\xf7\x56\x12\xd4\x50\xb2\xe5"
+ "\x51\x6f\x34\x63\x69\xd2\x4e\x96"
+ "\x4e\xbc\x79\xbf\x18\xae\xc6\x13"
+ "\x80\x92\x77\xb0\xb4\x0f\x29\x94"
+ "\x6f\x4c\xbb\x53\x11\x36\xc3\x9f"
+ "\x42\x8e\x96\x8a\x91\xc8\xe9\xfc"
+ "\xfe\xbf\x7c\x2d\x6f\xf9\xb8\x44"
+ "\x89\x1b\x09\x53\x0a\x2a\x92\xc3"
+ "\x54\x7a\x3a\xf9\xe2\xe4\x75\x87"
+ "\xa0\x5e\x4b\x03\x7a\x0d\x8a\xf4"
+ "\x55\x59\x94\x2b\x63\x96\x0e\xf5",
+ .psize = 1040,
+ .digest = "\xb5\xb9\x08\xb3\x24\x3e\x03\xf0"
+ "\xd6\x0b\x57\xbc\x0a\x6d\x89\x59",
+ }, {
+ .key = "\xf6\x34\x42\x71\x35\x52\x8b\x58"
+ "\x02\x3a\x8e\x4a\x8d\x41\x13\xe9"
+ "\x7f\xba\xb9\x55\x9d\x73\x4d\xf8"
+ "\x3f\x5d\x73\x15\xff\xd3\x9e\x7f"
+ "\x20\x2a\x6a\xa8\xd1\xf0\x8f\x12"
+ "\x6b\x02\xd8\x6c\xde\xba\x80\x22"
+ "\x19\x37\xc8\xd0\x4e\x89\x17\x7c"
+ "\x7c\xdd\x88\xfd\x41\xc0\x04\xb7"
+ "\x1d\xac\x19\xe3\x20\xc7\x16\xcf"
+ "\x58\xee\x1d\x7a\x61\x69\xa9\x12"
+ "\x4b\xef\x4f\xb6\x38\xdd\x78\xf8"
+ "\x28\xee\x70\x08\xc7\x7c\xcc\xc8"
+ "\x1e\x41\xf5\x80\x86\x70\xd0\xf0"
+ "\xa3\x87\x6b\x0a\x00\xd2\x41\x28"
+ "\x74\x26\xf1\x24\xf3\xd0\x28\x77"
+ "\xd7\xcd\xf6\x2d\x61\xf4\xa2\x13"
+ "\x77\xb4\x6f\xa0\xf4\xfb\xd6\xb5"
+ "\x38\x9d\x5a\x0c\x51\xaf\xad\x63"
+ "\x27\x67\x8c\x01\xea\x42\x1a\x66"
+ "\xda\x16\x7c\x3c\x30\x0c\x66\x53"
+ "\x1c\x88\xa4\x5c\xb2\xe3\x78\x0a"
+ "\x13\x05\x6d\xe2\xaf\xb3\xe4\x75"
+ "\x00\x99\x58\xee\x76\x09\x64\xaa"
+ "\xbb\x2e\xb1\x81\xec\xd8\x0e\xd3"
+ "\x0c\x33\x5d\xb7\x98\xef\x36\xb6"
+ "\xd2\x65\x69\x41\x70\x12\xdc\x25"
+ "\x41\x03\x99\x81\x41\x19\x62\x13"
+ "\xd1\x0a\x29\xc5\x8c\xe0\x4c\xf3"
+ "\xd6\xef\x4c\xf4\x1d\x83\x2e\x6d"
+ "\x8e\x14\x87\xed\x80\xe0\xaa\xd3"
+ "\x08\x04\x73\x1a\x84\x40\xf5\x64"
+ "\xbd\x61\x32\x65\x40\x42\xfb\xb0"
+ "\x40\xf6\x40\x8d\xc7\x7f\x14\xd0"
+ "\x83\x99\xaa\x36\x7e\x60\xc6\xbf"
+ "\x13\x8a\xf9\x21\xe4\x7e\x68\x87"
+ "\xf3\x33\x86\xb4\xe0\x23\x7e\x0a"
+ "\x21\xb1\xf5\xad\x67\x3c\x9c\x9d"
+ "\x09\xab\xaf\x5f\xba\xe0\xd0\x82"
+ "\x48\x22\x70\xb5\x6d\x53\xd6\x0e"
+ "\xde\x64\x92\x41\xb0\xd3\xfb\xda"
+ "\x21\xfe\xab\xea\x20\xc4\x03\x58"
+ "\x18\x2e\x7d\x2f\x03\xa9\x47\x66"
+ "\xdf\x7b\xa4\x6b\x34\x6b\x55\x9c"
+ "\x4f\xd7\x9c\x47\xfb\xa9\x42\xec"
+ "\x5a\x12\xfd\xfe\x76\xa0\x92\x9d"
+ "\xfe\x1e\x16\xdd\x24\x2a\xe4\x27"
+ "\xd5\xa9\xf2\x05\x4f\x83\xa2\xaf"
+ "\xfe\xee\x83\x7a\xad\xde\xdf\x9a"
+ "\x80\xd5\x81\x14\x93\x16\x7e\x46"
+ "\x47\xc2\x14\xef\x49\x6e\xb9\xdb"
+ "\x40\xe8\x06\x6f\x9c\x2a\xfd\x62"
+ "\x06\x46\xfd\x15\x1d\x36\x61\x6f"
+ "\x77\x77\x5e\x64\xce\x78\x1b\x85"
+ "\xbf\x50\x9a\xfd\x67\xa6\x1a\x65"
+ "\xad\x5b\x33\x30\xf1\x71\xaa\xd9"
+ "\x23\x0d\x92\x24\x5f\xae\x57\xb0"
+ "\x24\x37\x0a\x94\x12\xfb\xb5\xb1"
+ "\xd3\xb8\x1d\x12\x29\xb0\x80\x24"
+ "\x2d\x47\x9f\x96\x1f\x95\xf1\xb1"
+ "\xda\x35\xf6\x29\xe0\xe1\x23\x96"
+ "\xc7\xe8\x22\x9b\x7c\xac\xf9\x41"
+ "\x39\x01\xe5\x73\x15\x5e\x99\xec"
+ "\xb4\xc1\xf4\xe7\xa7\x97\x6a\xd5"
+ "\x90\x9a\xa0\x1d\xf3\x5a\x8b\x5f"
+ "\xdf\x01\x52\xa4\x93\x31\x97\xb0"
+ "\x93\x24\xb5\xbc\xb2\x14\x24\x98"
+ "\x4a\x8f\x19\x85\xc3\x2d\x0f\x74"
+ "\x9d\x16\x13\x80\x5e\x59\x62\x62"
+ "\x25\xe0\xd1\x2f\x64\xef\xba\xac"
+ "\xcd\x09\x07\x15\x8a\xcf\x73\xb5"
+ "\x8b\xc9\xd8\x24\xb0\x53\xd5\x6f"
+ "\xe1\x2b\x77\xb1\xc5\xe4\xa7\x0e"
+ "\x18\x45\xab\x36\x03\x59\xa8\xbd"
+ "\x43\xf0\xd8\x2c\x1a\x69\x96\xbb"
+ "\x13\xdf\x6c\x33\x77\xdf\x25\x34"
+ "\x5b\xa5\x5b\x8c\xf9\x51\x05\xd4"
+ "\x8b\x8b\x44\x87\x49\xfc\xa0\x8f"
+ "\x45\x15\x5b\x40\x42\xc4\x09\x92"
+ "\x98\x0c\x4d\xf4\x26\x37\x1b\x13"
+ "\x76\x01\x93\x8d\x4f\xe6\xed\x18"
+ "\xd0\x79\x7b\x3f\x44\x50\xcb\xee"
+ "\xf7\x4a\xc9\x9e\xe0\x96\x74\xa7"
+ "\xe6\x93\xb2\x53\xca\x55\xa8\xdc"
+ "\x1e\x68\x07\x87\xb7\x2e\xc1\x08"
+ "\xb2\xa4\x5b\xaf\xc6\xdb\x5c\x66"
+ "\x41\x1c\x51\xd9\xb0\x07\x00\x0d"
+ "\xf0\x4c\xdc\x93\xde\xa9\x1e\x8e"
+ "\xd3\x22\x62\xd8\x8b\x88\x2c\xea"
+ "\x5e\xf1\x6e\x14\x40\xc7\xbe\xaa"
+ "\x42\x28\xd0\x26\x30\x78\x01\x9b"
+ "\x83\x07\xbc\x94\xc7\x57\xa2\x9f"
+ "\x03\x07\xff\x16\xff\x3c\x6e\x48"
+ "\x0a\xd0\xdd\x4c\xf6\x64\x9a\xf1"
+ "\xcd\x30\x12\x82\x2c\x38\xd3\x26"
+ "\x83\xdb\xab\x3e\xc6\xf8\xe6\xfa"
+ "\x77\x0a\x78\x82\x75\xf8\x63\x51"
+ "\x59\xd0\x8d\x24\x9f\x25\xe6\xa3"
+ "\x4c\xbc\x34\xfc\xe3\x10\xc7\x62"
+ "\xd4\x23\xc8\x3d\xa7\xc6\xa6\x0a"
+ "\x4f\x7e\x29\x9d\x6d\xbe\xb5\xf1"
+ "\xdf\xa4\x53\xfa\xc0\x23\x0f\x37"
+ "\x84\x68\xd0\xb5\xc8\xc6\xae\xf8"
+ "\xb7\x8d\xb3\x16\xfe\x8f\x87\xad"
+ "\xd0\xc1\x08\xee\x12\x1c\x9b\x1d"
+ "\x90\xf8\xd1\x63\xa4\x92\x3c\xf0"
+ "\xc7\x34\xd8\xf1\x14\xed\xa3\xbc"
+ "\x17\x7e\xd4\x62\x42\x54\x57\x2c"
+ "\x3e\x7a\x35\x35\x17\x0f\x0b\x7f"
+ "\x81\xa1\x3f\xd0\xcd\xc8\x3b\x96"
+ "\xe9\xe0\x4a\x04\xe1\xb6\x3c\xa1"
+ "\xd6\xca\xc4\xbd\xb6\xb5\x95\x34"
+ "\x12\x9d\xc5\x96\xf2\xdf\xba\x54"
+ "\x76\xd1\xb2\x6b\x3b\x39\xe0\xb9"
+ "\x18\x62\xfb\xf7\xfc\x12\xf1\x5f"
+ "\x7e\xc7\xe3\x59\x4c\xa6\xc2\x3d"
+ "\x40\x15\xf9\xa3\x95\x64\x4c\x74"
+ "\x8b\x73\x77\x33\x07\xa7\x04\x1d"
+ "\x33\x5a\x7e\x8f\xbd\x86\x01\x4f"
+ "\x3e\xb9\x27\x6f\xe2\x41\xf7\x09"
+ "\x67\xfd\x29\x28\xc5\xe4\xf6\x18"
+ "\x4c\x1b\x49\xb2\x9c\x5b\xf6\x81"
+ "\x4f\xbb\x5c\xcc\x0b\xdf\x84\x23"
+ "\x58\xd6\x28\x34\x93\x3a\x25\x97"
+ "\xdf\xb2\xc3\x9e\x97\x38\x0b\x7d"
+ "\x10\xb3\x54\x35\x23\x8c\x64\xee"
+ "\xf0\xd8\x66\xff\x8b\x22\xd2\x5b"
+ "\x05\x16\x3c\x89\xf7\xb1\x75\xaf"
+ "\xc0\xae\x6a\x4f\x3f\xaf\x9a\xf4"
+ "\xf4\x9a\x24\xd9\x80\x82\xc0\x12"
+ "\xde\x96\xd1\xbe\x15\x0b\x8d\x6a"
+ "\xd7\x12\xe4\x85\x9f\x83\xc9\xc3"
+ "\xff\x0b\xb5\xaf\x3b\xd8\x6d\x67"
+ "\x81\x45\xe6\xac\xec\xc1\x7b\x16"
+ "\x18\x0a\xce\x4b\xc0\x2e\x76\xbc"
+ "\x1b\xfa\xb4\x34\xb8\xfc\x3e\xc8"
+ "\x5d\x90\x71\x6d\x7a\x79\xef\x06",
+ .ksize = 1088,
+ .plaintext = "\xaa\x5d\x54\xcb\xea\x1e\x46\x0f"
+ "\x45\x87\x70\x51\x8a\x66\x7a\x33"
+ "\xb4\x18\xff\xa9\x82\xf9\x45\x4b"
+ "\x93\xae\x2e\x7f\xab\x98\xfe\xbf"
+ "\x01\xee\xe5\xa0\x37\x8f\x57\xa6"
+ "\xb0\x76\x0d\xa4\xd6\x28\x2b\x5d"
+ "\xe1\x03\xd6\x1c\x6f\x34\x0d\xe7"
+ "\x61\x2d\x2e\xe5\xae\x5d\x47\xc7"
+ "\x80\x4b\x18\x8f\xa8\x99\xbc\x28"
+ "\xed\x1d\x9d\x86\x7d\xd7\x41\xd1"
+ "\xe0\x2b\xe1\x8c\x93\x2a\xa7\x80"
+ "\xe1\x07\xa0\xa9\x9f\x8c\x8d\x1a"
+ "\x55\xfc\x6b\x24\x7a\xbd\x3e\x51"
+ "\x68\x4b\x26\x59\xc8\xa7\x16\xd9"
+ "\xb9\x61\x13\xde\x8b\x63\x1c\xf6"
+ "\x60\x01\xfb\x08\xb3\x5b\x0a\xbf"
+ "\x34\x73\xda\x87\x87\x3d\x6f\x97"
+ "\x4a\x0c\xa3\x58\x20\xa2\xc0\x81"
+ "\x5b\x8c\xef\xa9\xc2\x01\x1e\x64"
+ "\x83\x8c\xbc\x03\xb6\xd0\x29\x9f"
+ "\x54\xe2\xce\x8b\xc2\x07\x85\x78"
+ "\x25\x38\x96\x4c\xb4\xbe\x17\x4a"
+ "\x65\xa6\xfa\x52\x9d\x66\x9d\x65"
+ "\x4a\xd1\x01\x01\xf0\xcb\x13\xcc"
+ "\xa5\x82\xf3\xf2\x66\xcd\x3f\x9d"
+ "\xd1\xaa\xe4\x67\xea\xf2\xad\x88"
+ "\x56\x76\xa7\x9b\x59\x3c\xb1\x5d"
+ "\x78\xfd\x69\x79\x74\x78\x43\x26"
+ "\x7b\xde\x3f\xf1\xf5\x4e\x14\xd9"
+ "\x15\xf5\x75\xb5\x2e\x19\xf3\x0c"
+ "\x48\x72\xd6\x71\x6d\x03\x6e\xaa"
+ "\xa7\x08\xf9\xaa\x70\xa3\x0f\x4d"
+ "\x12\x8a\xdd\xe3\x39\x73\x7e\xa7"
+ "\xea\x1f\x6d\x06\x26\x2a\xf2\xc5"
+ "\x52\xb4\xbf\xfd\x52\x0c\x06\x60"
+ "\x90\xd1\xb2\x7b\x56\xae\xac\x58"
+ "\x5a\x6b\x50\x2a\xf5\xe0\x30\x3c"
+ "\x2a\x98\x0f\x1b\x5b\x0a\x84\x6c"
+ "\x31\xae\x92\xe2\xd4\xbb\x7f\x59"
+ "\x26\x10\xb9\x89\x37\x68\x26\xbf"
+ "\x41\xc8\x49\xc4\x70\x35\x7d\xff"
+ "\x2d\x7f\xf6\x8a\x93\x68\x8c\x78"
+ "\x0d\x53\xce\x7d\xff\x7d\xfb\xae"
+ "\x13\x1b\x75\xc4\x78\xd7\x71\xd8"
+ "\xea\xd3\xf4\x9d\x95\x64\x8e\xb4"
+ "\xde\xb8\xe4\xa6\x68\xc8\xae\x73"
+ "\x58\xaf\xa8\xb0\x5a\x20\xde\x87"
+ "\x43\xb9\x0f\xe3\xad\x41\x4b\xd5"
+ "\xb7\xad\x16\x00\xa6\xff\xf6\x74"
+ "\xbf\x8c\x9f\xb3\x58\x1b\xb6\x55"
+ "\xa9\x90\x56\x28\xf0\xb5\x13\x4e"
+ "\x9e\xf7\x25\x86\xe0\x07\x7b\x98"
+ "\xd8\x60\x5d\x38\x95\x3c\xe4\x22"
+ "\x16\x2f\xb2\xa2\xaf\xe8\x90\x17"
+ "\xec\x11\x83\x1a\xf4\xa9\x26\xda"
+ "\x39\x72\xf5\x94\x61\x05\x51\xec"
+ "\xa8\x30\x8b\x2c\x13\xd0\x72\xac"
+ "\xb9\xd2\xa0\x4c\x4b\x78\xe8\x6e"
+ "\x04\x85\xe9\x04\x49\x82\x91\xff"
+ "\x89\xe5\xab\x4c\xaa\x37\x03\x12"
+ "\xca\x8b\x74\x10\xfd\x9e\xd9\x7b"
+ "\xcb\xdb\x82\x6e\xce\x2e\x33\x39"
+ "\xce\xd2\x84\x6e\x34\x71\x51\x6e"
+ "\x0d\xd6\x01\x87\xc7\xfa\x0a\xd3"
+ "\xad\x36\xf3\x4c\x9f\x96\x5e\x62"
+ "\x62\x54\xc3\x03\x78\xd6\xab\xdd"
+ "\x89\x73\x55\x25\x30\xf8\xa7\xe6"
+ "\x4f\x11\x0c\x7c\x0a\xa1\x2b\x7b"
+ "\x3d\x0d\xde\x81\xd4\x9d\x0b\xae"
+ "\xdf\x00\xf9\x4c\xb6\x90\x8e\x16"
+ "\xcb\x11\xc8\xd1\x2e\x73\x13\x75"
+ "\x75\x3e\xaa\xf5\xee\x02\xb3\x18"
+ "\xa6\x2d\xf5\x3b\x51\xd1\x1f\x47"
+ "\x6b\x2c\xdb\xc4\x10\xe0\xc8\xba"
+ "\x9d\xac\xb1\x9d\x75\xd5\x41\x0e"
+ "\x7e\xbe\x18\x5b\xa4\x1f\xf8\x22"
+ "\x4c\xc1\x68\xda\x6d\x51\x34\x6c"
+ "\x19\x59\xec\xb5\xb1\xec\xa7\x03"
+ "\xca\x54\x99\x63\x05\x6c\xb1\xac"
+ "\x9c\x31\xd6\xdb\xba\x7b\x14\x12"
+ "\x7a\xc3\x2f\xbf\x8d\xdc\x37\x46"
+ "\xdb\xd2\xbc\xd4\x2f\xab\x30\xd5"
+ "\xed\x34\x99\x8e\x83\x3e\xbe\x4c"
+ "\x86\x79\x58\xe0\x33\x8d\x9a\xb8"
+ "\xa9\xa6\x90\x46\xa2\x02\xb8\xdd"
+ "\xf5\xf9\x1a\x5c\x8c\x01\xaa\x6e"
+ "\xb4\x22\x12\xf5\x0c\x1b\x9b\x7a"
+ "\xc3\x80\xf3\x06\x00\x5f\x30\xd5"
+ "\x06\xdb\x7d\x82\xc2\xd4\x0b\x4c"
+ "\x5f\xe9\xc5\xf5\xdf\x97\x12\xbf"
+ "\x56\xaf\x9b\x69\xcd\xee\x30\xb4"
+ "\xa8\x71\xff\x3e\x7d\x73\x7a\xb4"
+ "\x0d\xa5\x46\x7a\xf3\xf4\x15\x87"
+ "\x5d\x93\x2b\x8c\x37\x64\xb5\xdd"
+ "\x48\xd1\xe5\x8c\xae\xd4\xf1\x76"
+ "\xda\xf4\xba\x9e\x25\x0e\xad\xa3"
+ "\x0d\x08\x7c\xa8\x82\x16\x8d\x90"
+ "\x56\x40\x16\x84\xe7\x22\x53\x3a"
+ "\x58\xbc\xb9\x8f\x33\xc8\xc2\x84"
+ "\x22\xe6\x0d\xe7\xb3\xdc\x5d\xdf"
+ "\xd7\x2a\x36\xe4\x16\x06\x07\xd2"
+ "\x97\x60\xb2\xf5\x5e\x14\xc9\xfd"
+ "\x8b\x05\xd1\xce\xee\x9a\x65\x99"
+ "\xb7\xae\x19\xb7\xc8\xbc\xd5\xa2"
+ "\x7b\x95\xe1\xcc\xba\x0d\xdc\x8a"
+ "\x1d\x59\x52\x50\xaa\x16\x02\x82"
+ "\xdf\x61\x33\x2e\x44\xce\x49\xc7"
+ "\xe5\xc6\x2e\x76\xcf\x80\x52\xf0"
+ "\x3d\x17\x34\x47\x3f\xd3\x80\x48"
+ "\xa2\xba\xd5\xc7\x7b\x02\x28\xdb"
+ "\xac\x44\xc7\x6e\x05\x5c\xc2\x79"
+ "\xb3\x7d\x6a\x47\x77\x66\xf1\x38"
+ "\xf0\xf5\x4f\x27\x1a\x31\xca\x6c"
+ "\x72\x95\x92\x8e\x3f\xb0\xec\x1d"
+ "\xc7\x2a\xff\x73\xee\xdf\x55\x80"
+ "\x93\xd2\xbd\x34\xd3\x9f\x00\x51"
+ "\xfb\x2e\x41\xba\x6c\x5a\x7c\x17"
+ "\x7f\xe6\x70\xac\x8d\x39\x3f\x77"
+ "\xe2\x23\xac\x8f\x72\x4e\xe4\x53"
+ "\xcc\xf1\x1b\xf1\x35\xfe\x52\xa4"
+ "\xd6\xb8\x40\x6b\xc1\xfd\xa0\xa1"
+ "\xf5\x46\x65\xc2\x50\xbb\x43\xe2"
+ "\xd1\x43\x28\x34\x74\xf5\x87\xa0"
+ "\xf2\x5e\x27\x3b\x59\x2b\x3e\x49"
+ "\xdf\x46\xee\xaf\x71\xd7\x32\x36"
+ "\xc7\x14\x0b\x58\x6e\x3e\x2d\x41"
+ "\xfa\x75\x66\x3a\x54\xe0\xb2\xb9"
+ "\xaf\xdd\x04\x80\x15\x19\x3f\x6f"
+ "\xce\x12\xb4\xd8\xe8\x89\x3c\x05"
+ "\x30\xeb\xf3\x3d\xcd\x27\xec\xdc"
+ "\x56\x70\x12\xcf\x78\x2b\x77\xbf"
+ "\x22\xf0\x1b\x17\x9c\xcc\xd6\x1b"
+ "\x2d\x3d\xa0\x3b\xd8\xc9\x70\xa4"
+ "\x7a\x3e\x07\xb9\x06\xc3\xfa\xb0"
+ "\x33\xee\xc1\xd8\xf6\xe0\xf0\xb2"
+ "\x61\x12\x69\xb0\x5f\x28\x99\xda"
+ "\xc3\x61\x48\xfa\x07\x16\x03\xc4"
+ "\xa8\xe1\x3c\xe8\x0e\x64\x15\x30"
+ "\xc1\x9d\x84\x2f\x73\x98\x0e\x3a"
+ "\xf2\x86\x21\xa4\x9e\x1d\xb5\x86"
+ "\x16\xdb\x2b\x9a\x06\x64\x8e\x79"
+ "\x8d\x76\x3e\xc3\xc2\x64\x44\xe3"
+ "\xda\xbc\x1a\x52\xd7\x61\x03\x65"
+ "\x54\x32\x77\x01\xed\x9d\x8a\x43"
+ "\x25\x24\xe3\xc1\xbe\xb8\x2f\xcb"
+ "\x89\x14\x64\xab\xf6\xa0\x6e\x02"
+ "\x57\xe4\x7d\xa9\x4e\x9a\x03\x36"
+ "\xad\xf1\xb1\xfc\x0b\xe6\x79\x51"
+ "\x9f\x81\x77\xc4\x14\x78\x9d\xbf"
+ "\xb6\xd6\xa3\x8c\xba\x0b\x26\xe7"
+ "\xc8\xb9\x5c\xcc\xe1\x5f\xd5\xc6"
+ "\xc4\xca\xc2\xa3\x45\xba\x94\x13"
+ "\xb2\x8f\xc3\x54\x01\x09\xe7\x8b"
+ "\xda\x2a\x0a\x11\x02\x43\xcb\x57"
+ "\xc9\xcc\xb5\x5c\xab\xc4\xec\x54"
+ "\x00\x06\x34\xe1\x6e\x03\x89\x7c"
+ "\xc6\xfb\x6a\xc7\x60\x43\xd6\xc5"
+ "\xb5\x68\x72\x89\x8f\x42\xc3\x74"
+ "\xbd\x25\xaa\x9f\x67\xb5\xdf\x26"
+ "\x20\xe8\xb7\x01\x3c\xe4\x77\xce"
+ "\xc4\x65\xa7\x23\x79\xea\x33\xc7"
+ "\x82\x14\x5c\x82\xf2\x4e\x3d\xf6"
+ "\xc6\x4a\x0e\x29\xbb\xec\x44\xcd"
+ "\x2f\xd1\x4f\x21\x71\xa9\xce\x0f"
+ "\x5c\xf2\x72\x5c\x08\x2e\x21\xd2"
+ "\xc3\x29\x13\xd8\xac\xc3\xda\x13"
+ "\x1a\x9d\xa7\x71\x1d\x27\x1d\x27"
+ "\x1d\xea\xab\x44\x79\xad\xe5\xeb"
+ "\xef\x1f\x22\x0a\x44\x4f\xcb\x87"
+ "\xa7\x58\x71\x0e\x66\xf8\x60\xbf"
+ "\x60\x74\x4a\xb4\xec\x2e\xfe\xd3"
+ "\xf5\xb8\xfe\x46\x08\x50\x99\x6c"
+ "\x66\xa5\xa8\x34\x44\xb5\xe5\xf0"
+ "\xdd\x2c\x67\x4e\x35\x96\x8e\x67"
+ "\x48\x3f\x5f\x37\x44\x60\x51\x2e"
+ "\x14\x91\x5e\x57\xc3\x0e\x79\x77"
+ "\x2f\x03\xf4\xe2\x1c\x72\xbf\x85"
+ "\x5d\xd3\x17\xdf\x6c\xc5\x70\x24"
+ "\x42\xdf\x51\x4e\x2a\xb2\xd2\x5b"
+ "\x9e\x69\x83\x41\x11\xfe\x73\x22"
+ "\xde\x8a\x9e\xd8\x8a\xfb\x20\x38"
+ "\xd8\x47\x6f\xd5\xed\x8f\x41\xfd"
+ "\x13\x7a\x18\x03\x7d\x0f\xcd\x7d"
+ "\xa6\x7d\x31\x9e\xf1\x8f\x30\xa3"
+ "\x8b\x4c\x24\xb7\xf5\x48\xd7\xd9"
+ "\x12\xe7\x84\x97\x5c\x31\x6d\xfb"
+ "\xdf\xf3\xd3\xd1\xd5\x0c\x30\x06"
+ "\x01\x6a\xbc\x6c\x78\x7b\xa6\x50"
+ "\xfa\x0f\x3c\x42\x2d\xa5\xa3\x3b"
+ "\xcf\x62\x50\xff\x71\x6d\xe7\xda"
+ "\x27\xab\xc6\x67\x16\x65\x68\x64"
+ "\xc7\xd5\x5f\x81\xa9\xf6\x65\xb3"
+ "\x5e\x43\x91\x16\xcd\x3d\x55\x37"
+ "\x55\xb3\xf0\x28\xc5\x54\x19\xc0"
+ "\xe0\xd6\x2a\x61\xd4\xc8\x72\x51"
+ "\xe9\xa1\x7b\x48\x21\xad\x44\x09"
+ "\xe4\x01\x61\x3c\x8a\x5b\xf9\xa1"
+ "\x6e\x1b\xdf\xc0\x04\xa8\x8b\xf2"
+ "\x21\xbe\x34\x7b\xfc\xa1\xcd\xc9"
+ "\xa9\x96\xf4\xa4\x4c\xf7\x4e\x8f"
+ "\x84\xcc\xd3\xa8\x92\x77\x8f\x36"
+ "\xe2\x2e\x8c\x33\xe8\x84\xa6\x0c"
+ "\x6c\x8a\xda\x14\x32\xc2\x96\xff"
+ "\xc6\x4a\xc2\x9b\x30\x7f\xd1\x29"
+ "\xc0\xd5\x78\x41\x00\x80\x80\x03"
+ "\x2a\xb1\xde\x26\x03\x48\x49\xee"
+ "\x57\x14\x76\x51\x3c\x36\x5d\x0a"
+ "\x5c\x9f\xe8\xd8\x53\xdb\x4f\xd4"
+ "\x38\xbf\x66\xc9\x75\x12\x18\x75"
+ "\x34\x2d\x93\x22\x96\x51\x24\x6e"
+ "\x4e\xd9\x30\xea\x67\xff\x92\x1c"
+ "\x16\x26\xe9\xb5\x33\xab\x8c\x22"
+ "\x47\xdb\xa0\x2c\x08\xf0\x12\x69"
+ "\x7e\x93\x52\xda\xa5\xe5\xca\xc1"
+ "\x0f\x55\x2a\xbd\x09\x30\x88\x1b"
+ "\x9c\xc6\x9f\xe6\xdb\xa6\x92\xeb"
+ "\xf4\xbd\x5c\xc4\xdb\xc6\x71\x09"
+ "\xab\x5e\x48\x0c\xed\x6f\xda\x8e"
+ "\x8d\x0c\x98\x71\x7d\x10\xd0\x9c"
+ "\x20\x9b\x79\x53\x26\x5d\xb9\x85"
+ "\x8a\x31\xb8\xc5\x1c\x97\xde\x88"
+ "\x61\x55\x7f\x7c\x21\x06\xea\xc4"
+ "\x5f\xaf\xf2\xf0\xd5\x5e\x7d\xb4"
+ "\x6e\xcf\xe9\xae\x1b\x0e\x11\x80"
+ "\xc1\x9a\x74\x7e\x52\x6f\xa0\xb7"
+ "\x24\xcd\x8d\x0a\x11\x40\x63\x72"
+ "\xfa\xe2\xc5\xb3\x94\xef\x29\xa2"
+ "\x1a\x23\x43\x04\x37\x55\x0d\xe9"
+ "\x83\xb2\x29\x51\x49\x64\xa0\xbd"
+ "\xde\x73\xfd\xa5\x7c\x95\x70\x62"
+ "\x58\xdc\xe2\xd0\xbf\x98\xf5\x8a"
+ "\x6a\xfd\xce\xa8\x0e\x42\x2a\xeb"
+ "\xd2\xff\x83\x27\x53\x5c\xa0\x6e"
+ "\x93\xef\xe2\xb9\x5d\x35\xd6\x98"
+ "\xf6\x71\x19\x7a\x54\xa1\xa7\xe8"
+ "\x09\xfe\xf6\x9e\xc7\xbd\x3e\x29"
+ "\xbd\x6b\x17\xf4\xe7\x3e\x10\x5c"
+ "\xc1\xd2\x59\x4f\x4b\x12\x1a\x5b"
+ "\x50\x80\x59\xb9\xec\x13\x66\xa8"
+ "\xd2\x31\x7b\x6a\x61\x22\xdd\x7d"
+ "\x61\xee\x87\x16\x46\x9f\xf9\xc7"
+ "\x41\xee\x74\xf8\xd0\x96\x2c\x76"
+ "\x2a\xac\x7d\x6e\x9f\x0e\x7f\x95"
+ "\xfe\x50\x16\xb2\x23\xca\x62\xd5"
+ "\x68\xcf\x07\x3f\x3f\x97\x85\x2a"
+ "\x0c\x25\x45\xba\xdb\x32\xcb\x83"
+ "\x8c\x4f\xe0\x6d\x9a\x99\xf9\xc9"
+ "\xda\xd4\x19\x31\xc1\x7c\x6d\xd9"
+ "\x9c\x56\xd3\xec\xc1\x81\x4c\xed"
+ "\x28\x9d\x87\xeb\x19\xd7\x1a\x4f"
+ "\x04\x6a\xcb\x1f\xcf\x1f\xa2\x16"
+ "\xfc\x2a\x0d\xa1\x14\x2d\xfa\xc5"
+ "\x5a\xd2\xc5\xf9\x19\x7c\x20\x1f"
+ "\x2d\x10\xc0\x66\x7c\xd9\x2d\xe5"
+ "\x88\x70\x59\xa7\x85\xd5\x2e\x7c"
+ "\x5c\xe3\xb7\x12\xd6\x97\x3f\x29",
+ .psize = 2048,
+ .digest = "\x37\x90\x92\xc2\xeb\x01\x87\xd9"
+ "\x95\xc7\x91\xc3\x17\x8b\x38\x52",
+ }
+};
+
/*
* DES test vectors.
*/
@@ -33125,6 +34356,2108 @@ static struct cipher_testvec chacha20_enc_tv_template[] = {
},
};
+static struct cipher_testvec xchacha20_tv_template[] = {
+ { /* from libsodium test/default/xchacha20.c */
+ .key = "\x79\xc9\x97\x98\xac\x67\x30\x0b"
+ "\xbb\x27\x04\xc9\x5c\x34\x1e\x32"
+ "\x45\xf3\xdc\xb2\x17\x61\xb9\x8e"
+ "\x52\xff\x45\xb2\x4f\x30\x4f\xc4",
+ .klen = 32,
+ .iv = "\xb3\x3f\xfd\x30\x96\x47\x9b\xcf"
+ "\xbc\x9a\xee\x49\x41\x76\x88\xa0"
+ "\xa2\x55\x4f\x8d\x95\x38\x94\x19"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00",
+ .result = "\xc6\xe9\x75\x81\x60\x08\x3a\xc6"
+ "\x04\xef\x90\xe7\x12\xce\x6e\x75"
+ "\xd7\x79\x75\x90\x74\x4e\x0c\xf0"
+ "\x60\xf0\x13\x73\x9c",
+ .ilen = 29,
+ .rlen = 29,
+ }, { /* from libsodium test/default/xchacha20.c */
+ .key = "\x9d\x23\xbd\x41\x49\xcb\x97\x9c"
+ "\xcf\x3c\x5c\x94\xdd\x21\x7e\x98"
+ "\x08\xcb\x0e\x50\xcd\x0f\x67\x81"
+ "\x22\x35\xea\xaf\x60\x1d\x62\x32",
+ .klen = 32,
+ .iv = "\xc0\x47\x54\x82\x66\xb7\xc3\x70"
+ "\xd3\x35\x66\xa2\x42\x5c\xbf\x30"
+ "\xd8\x2d\x1e\xaf\x52\x94\x10\x9e"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00",
+ .result = "\xa2\x12\x09\x09\x65\x94\xde\x8c"
+ "\x56\x67\xb1\xd1\x3a\xd9\x3f\x74"
+ "\x41\x06\xd0\x54\xdf\x21\x0e\x47"
+ "\x82\xcd\x39\x6f\xec\x69\x2d\x35"
+ "\x15\xa2\x0b\xf3\x51\xee\xc0\x11"
+ "\xa9\x2c\x36\x78\x88\xbc\x46\x4c"
+ "\x32\xf0\x80\x7a\xcd\x6c\x20\x3a"
+ "\x24\x7e\x0d\xb8\x54\x14\x84\x68"
+ "\xe9\xf9\x6b\xee\x4c\xf7\x18\xd6"
+ "\x8d\x5f\x63\x7c\xbd\x5a\x37\x64"
+ "\x57\x78\x8e\x6f\xae\x90\xfc\x31"
+ "\x09\x7c\xfc",
+ .ilen = 91,
+ .rlen = 91,
+ }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes
+ to nonce, and recomputed the ciphertext with libsodium */
+ .key = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x67\xc6\x69\x73"
+ "\x51\xff\x4a\xec\x29\xcd\xba\xab"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .result = "\x9c\x49\x2a\xe7\x8a\x2f\x93\xc7"
+ "\xb3\x33\x6f\x82\x17\xd8\xc4\x1e"
+ "\xad\x80\x11\x11\x1d\x4c\x16\x18"
+ "\x07\x73\x9b\x4f\xdb\x7c\xcb\x47"
+ "\xfd\xef\x59\x74\xfa\x3f\xe5\x4c"
+ "\x9b\xd0\xea\xbc\xba\x56\xad\x32"
+ "\x03\xdc\xf8\x2b\xc1\xe1\x75\x67"
+ "\x23\x7b\xe6\xfc\xd4\x03\x86\x54",
+ .ilen = 64,
+ .rlen = 64,
+ }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes
+ to nonce, and recomputed the ciphertext with libsodium */
+ .key = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x01",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x02\xf2\xfb\xe3\x46"
+ "\x7c\xc2\x54\xf8\x1b\xe8\xe7\x8d"
+ "\x01\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+ "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+ "\x6f\x20\x74\x68\x65\x20\x49\x45"
+ "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+ "\x64\x65\x64\x20\x62\x79\x20\x74"
+ "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+ "\x69\x62\x75\x74\x6f\x72\x20\x66"
+ "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+ "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+ "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+ "\x20\x70\x61\x72\x74\x20\x6f\x66"
+ "\x20\x61\x6e\x20\x49\x45\x54\x46"
+ "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+ "\x74\x2d\x44\x72\x61\x66\x74\x20"
+ "\x6f\x72\x20\x52\x46\x43\x20\x61"
+ "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+ "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+ "\x20\x6d\x61\x64\x65\x20\x77\x69"
+ "\x74\x68\x69\x6e\x20\x74\x68\x65"
+ "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+ "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+ "\x45\x54\x46\x20\x61\x63\x74\x69"
+ "\x76\x69\x74\x79\x20\x69\x73\x20"
+ "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+ "\x65\x64\x20\x61\x6e\x20\x22\x49"
+ "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+ "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+ "\x22\x2e\x20\x53\x75\x63\x68\x20"
+ "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+ "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+ "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+ "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+ "\x74\x73\x20\x69\x6e\x20\x49\x45"
+ "\x54\x46\x20\x73\x65\x73\x73\x69"
+ "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+ "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+ "\x77\x72\x69\x74\x74\x65\x6e\x20"
+ "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+ "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+ "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+ "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+ "\x64\x65\x20\x61\x74\x20\x61\x6e"
+ "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+ "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+ "\x20\x77\x68\x69\x63\x68\x20\x61"
+ "\x72\x65\x20\x61\x64\x64\x72\x65"
+ "\x73\x73\x65\x64\x20\x74\x6f",
+ .result = "\xf9\xab\x7a\x4a\x60\xb8\x5f\xa0"
+ "\x50\xbb\x57\xce\xef\x8c\xc1\xd9"
+ "\x24\x15\xb3\x67\x5e\x7f\x01\xf6"
+ "\x1c\x22\xf6\xe5\x71\xb1\x43\x64"
+ "\x63\x05\xd5\xfc\x5c\x3d\xc0\x0e"
+ "\x23\xef\xd3\x3b\xd9\xdc\x7f\xa8"
+ "\x58\x26\xb3\xd0\xc2\xd5\x04\x3f"
+ "\x0a\x0e\x8f\x17\xe4\xcd\xf7\x2a"
+ "\xb4\x2c\x09\xe4\x47\xec\x8b\xfb"
+ "\x59\x37\x7a\xa1\xd0\x04\x7e\xaa"
+ "\xf1\x98\x5f\x24\x3d\x72\x9a\x43"
+ "\xa4\x36\x51\x92\x22\x87\xff\x26"
+ "\xce\x9d\xeb\x59\x78\x84\x5e\x74"
+ "\x97\x2e\x63\xc0\xef\x29\xf7\x8a"
+ "\xb9\xee\x35\x08\x77\x6a\x35\x9a"
+ "\x3e\xe6\x4f\x06\x03\x74\x1b\xc1"
+ "\x5b\xb3\x0b\x89\x11\x07\xd3\xb7"
+ "\x53\xd6\x25\x04\xd9\x35\xb4\x5d"
+ "\x4c\x33\x5a\xc2\x42\x4c\xe6\xa4"
+ "\x97\x6e\x0e\xd2\xb2\x8b\x2f\x7f"
+ "\x28\xe5\x9f\xac\x4b\x2e\x02\xab"
+ "\x85\xfa\xa9\x0d\x7c\x2d\x10\xe6"
+ "\x91\xab\x55\x63\xf0\xde\x3a\x94"
+ "\x25\x08\x10\x03\xc2\x68\xd1\xf4"
+ "\xaf\x7d\x9c\x99\xf7\x86\x96\x30"
+ "\x60\xfc\x0b\xe6\xa8\x80\x15\xb0"
+ "\x81\xb1\x0c\xbe\xb9\x12\x18\x25"
+ "\xe9\x0e\xb1\xe7\x23\xb2\xef\x4a"
+ "\x22\x8f\xc5\x61\x89\xd4\xe7\x0c"
+ "\x64\x36\x35\x61\xb6\x34\x60\xf7"
+ "\x7b\x61\x37\x37\x12\x10\xa2\xf6"
+ "\x7e\xdb\x7f\x39\x3f\xb6\x8e\x89"
+ "\x9e\xf3\xfe\x13\x98\xbb\x66\x5a"
+ "\xec\xea\xab\x3f\x9c\x87\xc4\x8c"
+ "\x8a\x04\x18\x49\xfc\x77\x11\x50"
+ "\x16\xe6\x71\x2b\xee\xc0\x9c\xb6"
+ "\x87\xfd\x80\xff\x0b\x1d\x73\x38"
+ "\xa4\x1d\x6f\xae\xe4\x12\xd7\x93"
+ "\x9d\xcd\x38\x26\x09\x40\x52\xcd"
+ "\x67\x01\x67\x26\xe0\x3e\x98\xa8"
+ "\xe8\x1a\x13\x41\xbb\x90\x4d\x87"
+ "\xbb\x42\x82\x39\xce\x3a\xd0\x18"
+ "\x6d\x7b\x71\x8f\xbb\x2c\x6a\xd1"
+ "\xbd\xf5\xc7\x8a\x7e\xe1\x1e\x0f"
+ "\x0d\x0d\x13\x7c\xd9\xd8\x3c\x91"
+ "\xab\xff\x1f\x12\xc3\xee\xe5\x65"
+ "\x12\x8d\x7b\x61\xe5\x1f\x98",
+ .ilen = 375,
+ .rlen = 375,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 375 - 20, 4, 16 },
+
+ }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes
+ to nonce, and recomputed the ciphertext with libsodium */
+ .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+ "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+ "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+ "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x02\x76\x5a\x2e\x63"
+ "\x33\x9f\xc9\x9a\x66\x32\x0d\xb7"
+ "\x2a\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x27\x54\x77\x61\x73\x20\x62\x72"
+ "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+ "\x6e\x64\x20\x74\x68\x65\x20\x73"
+ "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+ "\x76\x65\x73\x0a\x44\x69\x64\x20"
+ "\x67\x79\x72\x65\x20\x61\x6e\x64"
+ "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+ "\x69\x6e\x20\x74\x68\x65\x20\x77"
+ "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+ "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+ "\x65\x72\x65\x20\x74\x68\x65\x20"
+ "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+ "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+ "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+ "\x72\x61\x74\x68\x73\x20\x6f\x75"
+ "\x74\x67\x72\x61\x62\x65\x2e",
+ .result = "\x95\xb9\x51\xe7\x8f\xb4\xa4\x03"
+ "\xca\x37\xcc\xde\x60\x1d\x8c\xe2"
+ "\xf1\xbb\x8a\x13\x7f\x61\x85\xcc"
+ "\xad\xf4\xf0\xdc\x86\xa6\x1e\x10"
+ "\xbc\x8e\xcb\x38\x2b\xa5\xc8\x8f"
+ "\xaa\x03\x3d\x53\x4a\x42\xb1\x33"
+ "\xfc\xd3\xef\xf0\x8e\x7e\x10\x9c"
+ "\x6f\x12\x5e\xd4\x96\xfe\x5b\x08"
+ "\xb6\x48\xf0\x14\x74\x51\x18\x7c"
+ "\x07\x92\xfc\xac\x9d\xf1\x94\xc0"
+ "\xc1\x9d\xc5\x19\x43\x1f\x1d\xbb"
+ "\x07\xf0\x1b\x14\x25\x45\xbb\xcb"
+ "\x5c\xe2\x8b\x28\xf3\xcf\x47\x29"
+ "\x27\x79\x67\x24\xa6\x87\xc2\x11"
+ "\x65\x03\xfa\x45\xf7\x9e\x53\x7a"
+ "\x99\xf1\x82\x25\x4f\x8d\x07",
+ .ilen = 127,
+ .rlen = 127,
+ }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes
+ to nonce, and recomputed the ciphertext with libsodium */
+ .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+ "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+ "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+ "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x01\x31\x58\xa3\x5a"
+ "\x25\x5d\x05\x17\x58\xe9\x5e\xd4"
+ "\x1c\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x49\xee\xe0\xdc\x24\x90\x40\xcd"
+ "\xc5\x40\x8f\x47\x05\xbc\xdd\x81"
+ "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb"
+ "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8"
+ "\x5c\xf7\x1e\x8a\xc1\x23\xf2\xd4"
+ "\x19\x4b\x01\x0f\x4e\xa4\x43\xce"
+ "\x01\xc6\x67\xda\x03\x91\x18\x90"
+ "\xa5\xa4\x8e\x45\x03\xb3\x2d\xac"
+ "\x74\x92\xd3\x53\x47\xc8\xdd\x25"
+ "\x53\x6c\x02\x03\x87\x0d\x11\x0c"
+ "\x58\xe3\x12\x18\xfd\x2a\x5b\x40"
+ "\x0c\x30\xf0\xb8\x3f\x43\xce\xae"
+ "\x65\x3a\x7d\x7c\xf4\x54\xaa\xcc"
+ "\x33\x97\xc3\x77\xba\xc5\x70\xde"
+ "\xd7\xd5\x13\xa5\x65\xc4\x5f\x0f"
+ "\x46\x1a\x0d\x97\xb5\xf3\xbb\x3c"
+ "\x84\x0f\x2b\xc5\xaa\xea\xf2\x6c"
+ "\xc9\xb5\x0c\xee\x15\xf3\x7d\xbe"
+ "\x9f\x7b\x5a\xa6\xae\x4f\x83\xb6"
+ "\x79\x49\x41\xf4\x58\x18\xcb\x86"
+ "\x7f\x30\x0e\xf8\x7d\x44\x36\xea"
+ "\x75\xeb\x88\x84\x40\x3c\xad\x4f"
+ "\x6f\x31\x6b\xaa\x5d\xe5\xa5\xc5"
+ "\x21\x66\xe9\xa7\xe3\xb2\x15\x88"
+ "\x78\xf6\x79\xa1\x59\x47\x12\x4e"
+ "\x9f\x9f\x64\x1a\xa0\x22\x5b\x08"
+ "\xbe\x7c\x36\xc2\x2b\x66\x33\x1b"
+ "\xdd\x60\x71\xf7\x47\x8c\x61\xc3"
+ "\xda\x8a\x78\x1e\x16\xfa\x1e\x86"
+ "\x81\xa6\x17\x2a\xa7\xb5\xc2\xe7"
+ "\xa4\xc7\x42\xf1\xcf\x6a\xca\xb4"
+ "\x45\xcf\xf3\x93\xf0\xe7\xea\xf6"
+ "\xf4\xe6\x33\x43\x84\x93\xa5\x67"
+ "\x9b\x16\x58\x58\x80\x0f\x2b\x5c"
+ "\x24\x74\x75\x7f\x95\x81\xb7\x30"
+ "\x7a\x33\xa7\xf7\x94\x87\x32\x27"
+ "\x10\x5d\x14\x4c\x43\x29\xdd\x26"
+ "\xbd\x3e\x3c\x0e\xfe\x0e\xa5\x10"
+ "\xea\x6b\x64\xfd\x73\xc6\xed\xec"
+ "\xa8\xc9\xbf\xb3\xba\x0b\x4d\x07"
+ "\x70\xfc\x16\xfd\x79\x1e\xd7\xc5"
+ "\x49\x4e\x1c\x8b\x8d\x79\x1b\xb1"
+ "\xec\xca\x60\x09\x4c\x6a\xd5\x09"
+ "\x49\x46\x00\x88\x22\x8d\xce\xea"
+ "\xb1\x17\x11\xde\x42\xd2\x23\xc1"
+ "\x72\x11\xf5\x50\x73\x04\x40\x47"
+ "\xf9\x5d\xe7\xa7\x26\xb1\x7e\xb0"
+ "\x3f\x58\xc1\x52\xab\x12\x67\x9d"
+ "\x3f\x43\x4b\x68\xd4\x9c\x68\x38"
+ "\x07\x8a\x2d\x3e\xf3\xaf\x6a\x4b"
+ "\xf9\xe5\x31\x69\x22\xf9\xa6\x69"
+ "\xc6\x9c\x96\x9a\x12\x35\x95\x1d"
+ "\x95\xd5\xdd\xbe\xbf\x93\x53\x24"
+ "\xfd\xeb\xc2\x0a\x64\xb0\x77\x00"
+ "\x6f\x88\xc4\x37\x18\x69\x7c\xd7"
+ "\x41\x92\x55\x4c\x03\xa1\x9a\x4b"
+ "\x15\xe5\xdf\x7f\x37\x33\x72\xc1"
+ "\x8b\x10\x67\xa3\x01\x57\x94\x25"
+ "\x7b\x38\x71\x7e\xdd\x1e\xcc\x73"
+ "\x55\xd2\x8e\xeb\x07\xdd\xf1\xda"
+ "\x58\xb1\x47\x90\xfe\x42\x21\x72"
+ "\xa3\x54\x7a\xa0\x40\xec\x9f\xdd"
+ "\xc6\x84\x6e\xca\xae\xe3\x68\xb4"
+ "\x9d\xe4\x78\xff\x57\xf2\xf8\x1b"
+ "\x03\xa1\x31\xd9\xde\x8d\xf5\x22"
+ "\x9c\xdd\x20\xa4\x1e\x27\xb1\x76"
+ "\x4f\x44\x55\xe2\x9b\xa1\x9c\xfe"
+ "\x54\xf7\x27\x1b\xf4\xde\x02\xf5"
+ "\x1b\x55\x48\x5c\xdc\x21\x4b\x9e"
+ "\x4b\x6e\xed\x46\x23\xdc\x65\xb2"
+ "\xcf\x79\x5f\x28\xe0\x9e\x8b\xe7"
+ "\x4c\x9d\x8a\xff\xc1\xa6\x28\xb8"
+ "\x65\x69\x8a\x45\x29\xef\x74\x85"
+ "\xde\x79\xc7\x08\xae\x30\xb0\xf4"
+ "\xa3\x1d\x51\x41\xab\xce\xcb\xf6"
+ "\xb5\xd8\x6d\xe0\x85\xe1\x98\xb3"
+ "\x43\xbb\x86\x83\x0a\xa0\xf5\xb7"
+ "\x04\x0b\xfa\x71\x1f\xb0\xf6\xd9"
+ "\x13\x00\x15\xf0\xc7\xeb\x0d\x5a"
+ "\x9f\xd7\xb9\x6c\x65\x14\x22\x45"
+ "\x6e\x45\x32\x3e\x7e\x60\x1a\x12"
+ "\x97\x82\x14\xfb\xaa\x04\x22\xfa"
+ "\xa0\xe5\x7e\x8c\x78\x02\x48\x5d"
+ "\x78\x33\x5a\x7c\xad\xdb\x29\xce"
+ "\xbb\x8b\x61\xa4\xb7\x42\xe2\xac"
+ "\x8b\x1a\xd9\x2f\x0b\x8b\x62\x21"
+ "\x83\x35\x7e\xad\x73\xc2\xb5\x6c"
+ "\x10\x26\x38\x07\xe5\xc7\x36\x80"
+ "\xe2\x23\x12\x61\xf5\x48\x4b\x2b"
+ "\xc5\xdf\x15\xd9\x87\x01\xaa\xac"
+ "\x1e\x7c\xad\x73\x78\x18\x63\xe0"
+ "\x8b\x9f\x81\xd8\x12\x6a\x28\x10"
+ "\xbe\x04\x68\x8a\x09\x7c\x1b\x1c"
+ "\x83\x66\x80\x47\x80\xe8\xfd\x35"
+ "\x1c\x97\x6f\xae\x49\x10\x66\xcc"
+ "\xc6\xd8\xcc\x3a\x84\x91\x20\x77"
+ "\x72\xe4\x24\xd2\x37\x9f\xc5\xc9"
+ "\x25\x94\x10\x5f\x40\x00\x64\x99"
+ "\xdc\xae\xd7\x21\x09\x78\x50\x15"
+ "\xac\x5f\xc6\x2c\xa2\x0b\xa9\x39"
+ "\x87\x6e\x6d\xab\xde\x08\x51\x16"
+ "\xc7\x13\xe9\xea\xed\x06\x8e\x2c"
+ "\xf8\x37\x8c\xf0\xa6\x96\x8d\x43"
+ "\xb6\x98\x37\xb2\x43\xed\xde\xdf"
+ "\x89\x1a\xe7\xeb\x9d\xa1\x7b\x0b"
+ "\x77\xb0\xe2\x75\xc0\xf1\x98\xd9"
+ "\x80\x55\xc9\x34\x91\xd1\x59\xe8"
+ "\x4b\x0f\xc1\xa9\x4b\x7a\x84\x06"
+ "\x20\xa8\x5d\xfa\xd1\xde\x70\x56"
+ "\x2f\x9e\x91\x9c\x20\xb3\x24\xd8"
+ "\x84\x3d\xe1\x8c\x7e\x62\x52\xe5"
+ "\x44\x4b\x9f\xc2\x93\x03\xea\x2b"
+ "\x59\xc5\xfa\x3f\x91\x2b\xbb\x23"
+ "\xf5\xb2\x7b\xf5\x38\xaf\xb3\xee"
+ "\x63\xdc\x7b\xd1\xff\xaa\x8b\xab"
+ "\x82\x6b\x37\x04\xeb\x74\xbe\x79"
+ "\xb9\x83\x90\xef\x20\x59\x46\xff"
+ "\xe9\x97\x3e\x2f\xee\xb6\x64\x18"
+ "\x38\x4c\x7a\x4a\xf9\x61\xe8\x9a"
+ "\xa1\xb5\x01\xa6\x47\xd3\x11\xd4"
+ "\xce\xd3\x91\x49\x88\xc7\xb8\x4d"
+ "\xb1\xb9\x07\x6d\x16\x72\xae\x46"
+ "\x5e\x03\xa1\x4b\xb6\x02\x30\xa8"
+ "\x3d\xa9\x07\x2a\x7c\x19\xe7\x62"
+ "\x87\xe3\x82\x2f\x6f\xe1\x09\xd9"
+ "\x94\x97\xea\xdd\x58\x9e\xae\x76"
+ "\x7e\x35\xe5\xb4\xda\x7e\xf4\xde"
+ "\xf7\x32\x87\xcd\x93\xbf\x11\x56"
+ "\x11\xbe\x08\x74\xe1\x69\xad\xe2"
+ "\xd7\xf8\x86\x75\x8a\x3c\xa4\xbe"
+ "\x70\xa7\x1b\xfc\x0b\x44\x2a\x76"
+ "\x35\xea\x5d\x85\x81\xaf\x85\xeb"
+ "\xa0\x1c\x61\xc2\xf7\x4f\xa5\xdc"
+ "\x02\x7f\xf6\x95\x40\x6e\x8a\x9a"
+ "\xf3\x5d\x25\x6e\x14\x3a\x22\xc9"
+ "\x37\x1c\xeb\x46\x54\x3f\xa5\x91"
+ "\xc2\xb5\x8c\xfe\x53\x08\x97\x32"
+ "\x1b\xb2\x30\x27\xfe\x25\x5d\xdc"
+ "\x08\x87\xd0\xe5\x94\x1a\xd4\xf1"
+ "\xfe\xd6\xb4\xa3\xe6\x74\x81\x3c"
+ "\x1b\xb7\x31\xa7\x22\xfd\xd4\xdd"
+ "\x20\x4e\x7c\x51\xb0\x60\x73\xb8"
+ "\x9c\xac\x91\x90\x7e\x01\xb0\xe1"
+ "\x8a\x2f\x75\x1c\x53\x2a\x98\x2a"
+ "\x06\x52\x95\x52\xb2\xe9\x25\x2e"
+ "\x4c\xe2\x5a\x00\xb2\x13\x81\x03"
+ "\x77\x66\x0d\xa5\x99\xda\x4e\x8c"
+ "\xac\xf3\x13\x53\x27\x45\xaf\x64"
+ "\x46\xdc\xea\x23\xda\x97\xd1\xab"
+ "\x7d\x6c\x30\x96\x1f\xbc\x06\x34"
+ "\x18\x0b\x5e\x21\x35\x11\x8d\x4c"
+ "\xe0\x2d\xe9\x50\x16\x74\x81\xa8"
+ "\xb4\x34\xb9\x72\x42\xa6\xcc\xbc"
+ "\xca\x34\x83\x27\x10\x5b\x68\x45"
+ "\x8f\x52\x22\x0c\x55\x3d\x29\x7c"
+ "\xe3\xc0\x66\x05\x42\x91\x5f\x58"
+ "\xfe\x4a\x62\xd9\x8c\xa9\x04\x19"
+ "\x04\xa9\x08\x4b\x57\xfc\x67\x53"
+ "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f"
+ "\x92\xd6\x41\x7c\x5b\x2a\x00\x79"
+ "\x72",
+ .result = "\x3a\x92\xee\x53\x31\xaf\x2b\x60"
+ "\x5f\x55\x8d\x00\x5d\xfc\x74\x97"
+ "\x28\x54\xf4\xa5\x75\xf1\x9b\x25"
+ "\x62\x1c\xc0\xe0\x13\xc8\x87\x53"
+ "\xd0\xf3\xa7\x97\x1f\x3b\x1e\xea"
+ "\xe0\xe5\x2a\xd1\xdd\xa4\x3b\x50"
+ "\x45\xa3\x0d\x7e\x1b\xc9\xa0\xad"
+ "\xb9\x2c\x54\xa6\xc7\x55\x16\xd0"
+ "\xc5\x2e\x02\x44\x35\xd0\x7e\x67"
+ "\xf2\xc4\x9b\xcd\x95\x10\xcc\x29"
+ "\x4b\xfa\x86\x87\xbe\x40\x36\xbe"
+ "\xe1\xa3\x52\x89\x55\x20\x9b\xc2"
+ "\xab\xf2\x31\x34\x16\xad\xc8\x17"
+ "\x65\x24\xc0\xff\x12\x37\xfe\x5a"
+ "\x62\x3b\x59\x47\x6c\x5f\x3a\x8e"
+ "\x3b\xd9\x30\xc8\x7f\x2f\x88\xda"
+ "\x80\xfd\x02\xda\x7f\x9a\x7a\x73"
+ "\x59\xc5\x34\x09\x9a\x11\xcb\xa7"
+ "\xfc\xf6\xa1\xa0\x60\xfb\x43\xbb"
+ "\xf1\xe9\xd7\xc6\x79\x27\x4e\xff"
+ "\x22\xb4\x24\xbf\x76\xee\x47\xb9"
+ "\x6d\x3f\x8b\xb0\x9c\x3c\x43\xdd"
+ "\xff\x25\x2e\x6d\xa4\x2b\xfb\x5d"
+ "\x1b\x97\x6c\x55\x0a\x82\x7a\x7b"
+ "\x94\x34\xc2\xdb\x2f\x1f\xc1\xea"
+ "\xd4\x4d\x17\x46\x3b\x51\x69\x09"
+ "\xe4\x99\x32\x25\xfd\x94\xaf\xfb"
+ "\x10\xf7\x4f\xdd\x0b\x3c\x8b\x41"
+ "\xb3\x6a\xb7\xd1\x33\xa8\x0c\x2f"
+ "\x62\x4c\x72\x11\xd7\x74\xe1\x3b"
+ "\x38\x43\x66\x7b\x6c\x36\x48\xe7"
+ "\xe3\xe7\x9d\xb9\x42\x73\x7a\x2a"
+ "\x89\x20\x1a\x41\x80\x03\xf7\x8f"
+ "\x61\x78\x13\xbf\xfe\x50\xf5\x04"
+ "\x52\xf9\xac\x47\xf8\x62\x4b\xb2"
+ "\x24\xa9\xbf\x64\xb0\x18\x69\xd2"
+ "\xf5\xe4\xce\xc8\xb1\x87\x75\xd6"
+ "\x2c\x24\x79\x00\x7d\x26\xfb\x44"
+ "\xe7\x45\x7a\xee\x58\xa5\x83\xc1"
+ "\xb4\x24\xab\x23\x2f\x4d\xd7\x4f"
+ "\x1c\xc7\xaa\xa9\x50\xf4\xa3\x07"
+ "\x12\x13\x89\x74\xdc\x31\x6a\xb2"
+ "\xf5\x0f\x13\x8b\xb9\xdb\x85\x1f"
+ "\xf5\xbc\x88\xd9\x95\xea\x31\x6c"
+ "\x36\x60\xb6\x49\xdc\xc4\xf7\x55"
+ "\x3f\x21\xc1\xb5\x92\x18\x5e\xbc"
+ "\x9f\x87\x7f\xe7\x79\x25\x40\x33"
+ "\xd6\xb9\x33\xd5\x50\xb3\xc7\x89"
+ "\x1b\x12\xa0\x46\xdd\xa7\xd8\x3e"
+ "\x71\xeb\x6f\x66\xa1\x26\x0c\x67"
+ "\xab\xb2\x38\x58\x17\xd8\x44\x3b"
+ "\x16\xf0\x8e\x62\x8d\x16\x10\x00"
+ "\x32\x8b\xef\xb9\x28\xd3\xc5\xad"
+ "\x0a\x19\xa2\xe4\x03\x27\x7d\x94"
+ "\x06\x18\xcd\xd6\x27\x00\xf9\x1f"
+ "\xb6\xb3\xfe\x96\x35\x5f\xc4\x1c"
+ "\x07\x62\x10\x79\x68\x50\xf1\x7e"
+ "\x29\xe7\xc4\xc4\xe7\xee\x54\xd6"
+ "\x58\x76\x84\x6d\x8d\xe4\x59\x31"
+ "\xe9\xf4\xdc\xa1\x1f\xe5\x1a\xd6"
+ "\xe6\x64\x46\xf5\x77\x9c\x60\x7a"
+ "\x5e\x62\xe3\x0a\xd4\x9f\x7a\x2d"
+ "\x7a\xa5\x0a\x7b\x29\x86\x7a\x74"
+ "\x74\x71\x6b\xca\x7d\x1d\xaa\xba"
+ "\x39\x84\x43\x76\x35\xfe\x4f\x9b"
+ "\xbb\xbb\xb5\x6a\x32\xb5\x5d\x41"
+ "\x51\xf0\x5b\x68\x03\x47\x4b\x8a"
+ "\xca\x88\xf6\x37\xbd\x73\x51\x70"
+ "\x66\xfe\x9e\x5f\x21\x9c\xf3\xdd"
+ "\xc3\xea\x27\xf9\x64\x94\xe1\x19"
+ "\xa0\xa9\xab\x60\xe0\x0e\xf7\x78"
+ "\x70\x86\xeb\xe0\xd1\x5c\x05\xd3"
+ "\xd7\xca\xe0\xc0\x47\x47\x34\xee"
+ "\x11\xa3\xa3\x54\x98\xb7\x49\x8e"
+ "\x84\x28\x70\x2c\x9e\xfb\x55\x54"
+ "\x4d\xf8\x86\xf7\x85\x7c\xbd\xf3"
+ "\x17\xd8\x47\xcb\xac\xf4\x20\x85"
+ "\x34\x66\xad\x37\x2d\x5e\x52\xda"
+ "\x8a\xfe\x98\x55\x30\xe7\x2d\x2b"
+ "\x19\x10\x8e\x7b\x66\x5e\xdc\xe0"
+ "\x45\x1f\x7b\xb4\x08\xfb\x8f\xf6"
+ "\x8c\x89\x21\x34\x55\x27\xb2\x76"
+ "\xb2\x07\xd9\xd6\x68\x9b\xea\x6b"
+ "\x2d\xb4\xc4\x35\xdd\xd2\x79\xae"
+ "\xc7\xd6\x26\x7f\x12\x01\x8c\xa7"
+ "\xe3\xdb\xa8\xf4\xf7\x2b\xec\x99"
+ "\x11\x00\xf1\x35\x8c\xcf\xd5\xc9"
+ "\xbd\x91\x36\x39\x70\xcf\x7d\x70"
+ "\x47\x1a\xfc\x6b\x56\xe0\x3f\x9c"
+ "\x60\x49\x01\x72\xa9\xaf\x2c\x9c"
+ "\xe8\xab\xda\x8c\x14\x19\xf3\x75"
+ "\x07\x17\x9d\x44\x67\x7a\x2e\xef"
+ "\xb7\x83\x35\x4a\xd1\x3d\x1c\x84"
+ "\x32\xdd\xaa\xea\xca\x1d\xdc\x72"
+ "\x2c\xcc\x43\xcd\x5d\xe3\x21\xa4"
+ "\xd0\x8a\x4b\x20\x12\xa3\xd5\x86"
+ "\x76\x96\xff\x5f\x04\x57\x0f\xe6"
+ "\xba\xe8\x76\x50\x0c\x64\x1d\x83"
+ "\x9c\x9b\x9a\x9a\x58\x97\x9c\x5c"
+ "\xb4\xa4\xa6\x3e\x19\xeb\x8f\x5a"
+ "\x61\xb2\x03\x7b\x35\x19\xbe\xa7"
+ "\x63\x0c\xfd\xdd\xf9\x90\x6c\x08"
+ "\x19\x11\xd3\x65\x4a\xf5\x96\x92"
+ "\x59\xaa\x9c\x61\x0c\x29\xa7\xf8"
+ "\x14\x39\x37\xbf\x3c\xf2\x16\x72"
+ "\x02\xfa\xa2\xf3\x18\x67\x5d\xcb"
+ "\xdc\x4d\xbb\x96\xff\x70\x08\x2d"
+ "\xc2\xa8\x52\xe1\x34\x5f\x72\xfe"
+ "\x64\xbf\xca\xa7\x74\x38\xfb\x74"
+ "\x55\x9c\xfa\x8a\xed\xfb\x98\xeb"
+ "\x58\x2e\x6c\xe1\x52\x76\x86\xd7"
+ "\xcf\xa1\xa4\xfc\xb2\x47\x41\x28"
+ "\xa3\xc1\xe5\xfd\x53\x19\x28\x2b"
+ "\x37\x04\x65\x96\x99\x7a\x28\x0f"
+ "\x07\x68\x4b\xc7\x52\x0a\x55\x35"
+ "\x40\x19\x95\x61\xe8\x59\x40\x1f"
+ "\x9d\xbf\x78\x7d\x8f\x84\xff\x6f"
+ "\xd0\xd5\x63\xd2\x22\xbd\xc8\x4e"
+ "\xfb\xe7\x9f\x06\xe6\xe7\x39\x6d"
+ "\x6a\x96\x9f\xf0\x74\x7e\xc9\x35"
+ "\xb7\x26\xb8\x1c\x0a\xa6\x27\x2c"
+ "\xa2\x2b\xfe\xbe\x0f\x07\x73\xae"
+ "\x7f\x7f\x54\xf5\x7c\x6a\x0a\x56"
+ "\x49\xd4\x81\xe5\x85\x53\x99\x1f"
+ "\x95\x05\x13\x58\x8d\x0e\x1b\x90"
+ "\xc3\x75\x48\x64\x58\x98\x67\x84"
+ "\xae\xe2\x21\xa2\x8a\x04\x0a\x0b"
+ "\x61\xaa\xb0\xd4\x28\x60\x7a\xf8"
+ "\xbc\x52\xfb\x24\x7f\xed\x0d\x2a"
+ "\x0a\xb2\xf9\xc6\x95\xb5\x11\xc9"
+ "\xf4\x0f\x26\x11\xcf\x2a\x57\x87"
+ "\x7a\xf3\xe7\x94\x65\xc2\xb5\xb3"
+ "\xab\x98\xe3\xc1\x2b\x59\x19\x7c"
+ "\xd6\xf3\xf9\xbf\xff\x6d\xc6\x82"
+ "\x13\x2f\x4a\x2e\xcd\x26\xfe\x2d"
+ "\x01\x70\xf4\xc2\x7f\x1f\x4c\xcb"
+ "\x47\x77\x0c\xa0\xa3\x03\xec\xda"
+ "\xa9\xbf\x0d\x2d\xae\xe4\xb8\x7b"
+ "\xa9\xbc\x08\xb4\x68\x2e\xc5\x60"
+ "\x8d\x87\x41\x2b\x0f\x69\xf0\xaf"
+ "\x5f\xba\x72\x20\x0f\x33\xcd\x6d"
+ "\x36\x7d\x7b\xd5\x05\xf1\x4b\x05"
+ "\xc4\xfc\x7f\x80\xb9\x4d\xbd\xf7"
+ "\x7c\x84\x07\x01\xc2\x40\x66\x5b"
+ "\x98\xc7\x2c\xe3\x97\xfa\xdf\x87"
+ "\xa0\x1f\xe9\x21\x42\x0f\x3b\xeb"
+ "\x89\x1c\x3b\xca\x83\x61\x77\x68"
+ "\x84\xbb\x60\x87\x38\x2e\x25\xd5"
+ "\x9e\x04\x41\x70\xac\xda\xc0\x9c"
+ "\x9c\x69\xea\x8d\x4e\x55\x2a\x29"
+ "\xed\x05\x4b\x7b\x73\x71\x90\x59"
+ "\x4d\xc8\xd8\x44\xf0\x4c\xe1\x5e"
+ "\x84\x47\x55\xcc\x32\x3f\xe7\x97"
+ "\x42\xc6\x32\xac\x40\xe5\xa5\xc7"
+ "\x8b\xed\xdb\xf7\x83\xd6\xb1\xc2"
+ "\x52\x5e\x34\xb7\xeb\x6e\xd9\xfc"
+ "\xe5\x93\x9a\x97\x3e\xb0\xdc\xd9"
+ "\xd7\x06\x10\xb6\x1d\x80\x59\xdd"
+ "\x0d\xfe\x64\x35\xcd\x5d\xec\xf0"
+ "\xba\xd0\x34\xc9\x2d\x91\xc5\x17"
+ "\x11",
+ .ilen = 1281,
+ .rlen = 1281,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 1200, 1, 80 },
+ },
+};
+
+/*
+ * Same as XChaCha20 test vectors above, but recomputed the ciphertext with
+ * XChaCha12, using a modified libsodium.
+ */
+static struct cipher_testvec xchacha12_tv_template[] = {
+ {
+ .key = "\x79\xc9\x97\x98\xac\x67\x30\x0b"
+ "\xbb\x27\x04\xc9\x5c\x34\x1e\x32"
+ "\x45\xf3\xdc\xb2\x17\x61\xb9\x8e"
+ "\x52\xff\x45\xb2\x4f\x30\x4f\xc4",
+ .klen = 32,
+ .iv = "\xb3\x3f\xfd\x30\x96\x47\x9b\xcf"
+ "\xbc\x9a\xee\x49\x41\x76\x88\xa0"
+ "\xa2\x55\x4f\x8d\x95\x38\x94\x19"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00",
+ .result = "\x1b\x78\x7f\xd7\xa1\x41\x68\xab"
+ "\x3d\x3f\xd1\x7b\x69\x56\xb2\xd5"
+ "\x43\xce\xeb\xaf\x36\xf0\x29\x9d"
+ "\x3a\xfb\x18\xae\x1b",
+ .ilen = 29,
+ .rlen = 29,
+ }, {
+ .key = "\x9d\x23\xbd\x41\x49\xcb\x97\x9c"
+ "\xcf\x3c\x5c\x94\xdd\x21\x7e\x98"
+ "\x08\xcb\x0e\x50\xcd\x0f\x67\x81"
+ "\x22\x35\xea\xaf\x60\x1d\x62\x32",
+ .klen = 32,
+ .iv = "\xc0\x47\x54\x82\x66\xb7\xc3\x70"
+ "\xd3\x35\x66\xa2\x42\x5c\xbf\x30"
+ "\xd8\x2d\x1e\xaf\x52\x94\x10\x9e"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00",
+ .result = "\xfb\x32\x09\x1d\x83\x05\xae\x4c"
+ "\x13\x1f\x12\x71\xf2\xca\xb2\xeb"
+ "\x5b\x83\x14\x7d\x83\xf6\x57\x77"
+ "\x2e\x40\x1f\x92\x2c\xf9\xec\x35"
+ "\x34\x1f\x93\xdf\xfb\x30\xd7\x35"
+ "\x03\x05\x78\xc1\x20\x3b\x7a\xe3"
+ "\x62\xa3\x89\xdc\x11\x11\x45\xa8"
+ "\x82\x89\xa0\xf1\x4e\xc7\x0f\x11"
+ "\x69\xdd\x0c\x84\x2b\x89\x5c\xdc"
+ "\xf0\xde\x01\xef\xc5\x65\x79\x23"
+ "\x87\x67\xd6\x50\xd9\x8d\xd9\x92"
+ "\x54\x5b\x0e",
+ .ilen = 91,
+ .rlen = 91,
+ }, {
+ .key = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x67\xc6\x69\x73"
+ "\x51\xff\x4a\xec\x29\xcd\xba\xab"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00",
+ .result = "\xdf\x2d\xc6\x21\x2a\x9d\xa1\xbb"
+ "\xc2\x77\x66\x0c\x5c\x46\xef\xa7"
+ "\x79\x1b\xb9\xdf\x55\xe2\xf9\x61"
+ "\x4c\x7b\xa4\x52\x24\xaf\xa2\xda"
+ "\xd1\x8f\x8f\xa2\x9e\x53\x4d\xc4"
+ "\xb8\x55\x98\x08\x7c\x08\xd4\x18"
+ "\x67\x8f\xef\x50\xb1\x5f\xa5\x77"
+ "\x4c\x25\xe7\x86\x26\x42\xca\x44",
+ .ilen = 64,
+ .rlen = 64,
+ }, {
+ .key = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x00\x00\x00\x00\x01",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x02\xf2\xfb\xe3\x46"
+ "\x7c\xc2\x54\xf8\x1b\xe8\xe7\x8d"
+ "\x01\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+ "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+ "\x6f\x20\x74\x68\x65\x20\x49\x45"
+ "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+ "\x64\x65\x64\x20\x62\x79\x20\x74"
+ "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+ "\x69\x62\x75\x74\x6f\x72\x20\x66"
+ "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+ "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+ "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+ "\x20\x70\x61\x72\x74\x20\x6f\x66"
+ "\x20\x61\x6e\x20\x49\x45\x54\x46"
+ "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+ "\x74\x2d\x44\x72\x61\x66\x74\x20"
+ "\x6f\x72\x20\x52\x46\x43\x20\x61"
+ "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+ "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+ "\x20\x6d\x61\x64\x65\x20\x77\x69"
+ "\x74\x68\x69\x6e\x20\x74\x68\x65"
+ "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+ "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+ "\x45\x54\x46\x20\x61\x63\x74\x69"
+ "\x76\x69\x74\x79\x20\x69\x73\x20"
+ "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+ "\x65\x64\x20\x61\x6e\x20\x22\x49"
+ "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+ "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+ "\x22\x2e\x20\x53\x75\x63\x68\x20"
+ "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+ "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+ "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+ "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+ "\x74\x73\x20\x69\x6e\x20\x49\x45"
+ "\x54\x46\x20\x73\x65\x73\x73\x69"
+ "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+ "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+ "\x77\x72\x69\x74\x74\x65\x6e\x20"
+ "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+ "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+ "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+ "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+ "\x64\x65\x20\x61\x74\x20\x61\x6e"
+ "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+ "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+ "\x20\x77\x68\x69\x63\x68\x20\x61"
+ "\x72\x65\x20\x61\x64\x64\x72\x65"
+ "\x73\x73\x65\x64\x20\x74\x6f",
+ .result = "\xe4\xa6\xc8\x30\xc4\x23\x13\xd6"
+ "\x08\x4d\xc9\xb7\xa5\x64\x7c\xb9"
+ "\x71\xe2\xab\x3e\xa8\x30\x8a\x1c"
+ "\x4a\x94\x6d\x9b\xe0\xb3\x6f\xf1"
+ "\xdc\xe3\x1b\xb3\xa9\x6d\x0d\xd6"
+ "\xd0\xca\x12\xef\xe7\x5f\xd8\x61"
+ "\x3c\x82\xd3\x99\x86\x3c\x6f\x66"
+ "\x02\x06\xdc\x55\xf9\xed\xdf\x38"
+ "\xb4\xa6\x17\x00\x7f\xef\xbf\x4f"
+ "\xf8\x36\xf1\x60\x7e\x47\xaf\xdb"
+ "\x55\x9b\x12\xcb\x56\x44\xa7\x1f"
+ "\xd3\x1a\x07\x3b\x00\xec\xe6\x4c"
+ "\xa2\x43\x27\xdf\x86\x19\x4f\x16"
+ "\xed\xf9\x4a\xf3\x63\x6f\xfa\x7f"
+ "\x78\x11\xf6\x7d\x97\x6f\xec\x6f"
+ "\x85\x0f\x5c\x36\x13\x8d\x87\xe0"
+ "\x80\xb1\x69\x0b\x98\x89\x9c\x4e"
+ "\xf8\xdd\xee\x5c\x0a\x85\xce\xd4"
+ "\xea\x1b\x48\xbe\x08\xf8\xe2\xa8"
+ "\xa5\xb0\x3c\x79\xb1\x15\xb4\xb9"
+ "\x75\x10\x95\x35\x81\x7e\x26\xe6"
+ "\x78\xa4\x88\xcf\xdb\x91\x34\x18"
+ "\xad\xd7\x8e\x07\x7d\xab\x39\xf9"
+ "\xa3\x9e\xa5\x1d\xbb\xed\x61\xfd"
+ "\xdc\xb7\x5a\x27\xfc\xb5\xc9\x10"
+ "\xa8\xcc\x52\x7f\x14\x76\x90\xe7"
+ "\x1b\x29\x60\x74\xc0\x98\x77\xbb"
+ "\xe0\x54\xbb\x27\x49\x59\x1e\x62"
+ "\x3d\xaf\x74\x06\xa4\x42\x6f\xc6"
+ "\x52\x97\xc4\x1d\xc4\x9f\xe2\xe5"
+ "\x38\x57\x91\xd1\xa2\x28\xcc\x40"
+ "\xcc\x70\x59\x37\xfc\x9f\x4b\xda"
+ "\xa0\xeb\x97\x9a\x7d\xed\x14\x5c"
+ "\x9c\xb7\x93\x26\x41\xa8\x66\xdd"
+ "\x87\x6a\xc0\xd3\xc2\xa9\x3e\xae"
+ "\xe9\x72\xfe\xd1\xb3\xac\x38\xea"
+ "\x4d\x15\xa9\xd5\x36\x61\xe9\x96"
+ "\x6c\x23\xf8\x43\xe4\x92\x29\xd9"
+ "\x8b\x78\xf7\x0a\x52\xe0\x19\x5b"
+ "\x59\x69\x5b\x5d\xa1\x53\xc4\x68"
+ "\xe1\xbb\xac\x89\x14\xe2\xe2\x85"
+ "\x41\x18\xf5\xb3\xd1\xfa\x68\x19"
+ "\x44\x78\xdc\xcf\xe7\x88\x2d\x52"
+ "\x5f\x40\xb5\x7e\xf8\x88\xa2\xae"
+ "\x4a\xb2\x07\x35\x9d\x9b\x07\x88"
+ "\xb7\x00\xd0\x0c\xb6\xa0\x47\x59"
+ "\xda\x4e\xc9\xab\x9b\x8a\x7b",
+
+ .ilen = 375,
+ .rlen = 375,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 375 - 20, 4, 16 },
+
+ }, {
+ .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+ "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+ "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+ "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x02\x76\x5a\x2e\x63"
+ "\x33\x9f\xc9\x9a\x66\x32\x0d\xb7"
+ "\x2a\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x27\x54\x77\x61\x73\x20\x62\x72"
+ "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+ "\x6e\x64\x20\x74\x68\x65\x20\x73"
+ "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+ "\x76\x65\x73\x0a\x44\x69\x64\x20"
+ "\x67\x79\x72\x65\x20\x61\x6e\x64"
+ "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+ "\x69\x6e\x20\x74\x68\x65\x20\x77"
+ "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+ "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+ "\x65\x72\x65\x20\x74\x68\x65\x20"
+ "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+ "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+ "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+ "\x72\x61\x74\x68\x73\x20\x6f\x75"
+ "\x74\x67\x72\x61\x62\x65\x2e",
+ .result = "\xb9\x68\xbc\x6a\x24\xbc\xcc\xd8"
+ "\x9b\x2a\x8d\x5b\x96\xaf\x56\xe3"
+ "\x11\x61\xe7\xa7\x9b\xce\x4e\x7d"
+ "\x60\x02\x48\xac\xeb\xd5\x3a\x26"
+ "\x9d\x77\x3b\xb5\x32\x13\x86\x8e"
+ "\x20\x82\x26\x72\xae\x64\x1b\x7e"
+ "\x2e\x01\x68\xb4\x87\x45\xa1\x24"
+ "\xe4\x48\x40\xf0\xaa\xac\xee\xa9"
+ "\xfc\x31\xad\x9d\x89\xa3\xbb\xd2"
+ "\xe4\x25\x13\xad\x0f\x5e\xdf\x3c"
+ "\x27\xab\xb8\x62\x46\x22\x30\x48"
+ "\x55\x2c\x4e\x84\x78\x1d\x0d\x34"
+ "\x8d\x3c\x91\x0a\x7f\x5b\x19\x9f"
+ "\x97\x05\x4c\xa7\x62\x47\x8b\xc5"
+ "\x44\x2e\x20\x33\xdd\xa0\x82\xa9"
+ "\x25\x76\x37\xe6\x3c\x67\x5b",
+ .ilen = 127,
+ .rlen = 127,
+ }, {
+ .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+ "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+ "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+ "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+ .klen = 32,
+ .iv = "\x00\x00\x00\x00\x00\x00\x00\x00"
+ "\x00\x00\x00\x01\x31\x58\xa3\x5a"
+ "\x25\x5d\x05\x17\x58\xe9\x5e\xd4"
+ "\x1c\x00\x00\x00\x00\x00\x00\x00",
+ .input = "\x49\xee\xe0\xdc\x24\x90\x40\xcd"
+ "\xc5\x40\x8f\x47\x05\xbc\xdd\x81"
+ "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb"
+ "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8"
+ "\x5c\xf7\x1e\x8a\xc1\x23\xf2\xd4"
+ "\x19\x4b\x01\x0f\x4e\xa4\x43\xce"
+ "\x01\xc6\x67\xda\x03\x91\x18\x90"
+ "\xa5\xa4\x8e\x45\x03\xb3\x2d\xac"
+ "\x74\x92\xd3\x53\x47\xc8\xdd\x25"
+ "\x53\x6c\x02\x03\x87\x0d\x11\x0c"
+ "\x58\xe3\x12\x18\xfd\x2a\x5b\x40"
+ "\x0c\x30\xf0\xb8\x3f\x43\xce\xae"
+ "\x65\x3a\x7d\x7c\xf4\x54\xaa\xcc"
+ "\x33\x97\xc3\x77\xba\xc5\x70\xde"
+ "\xd7\xd5\x13\xa5\x65\xc4\x5f\x0f"
+ "\x46\x1a\x0d\x97\xb5\xf3\xbb\x3c"
+ "\x84\x0f\x2b\xc5\xaa\xea\xf2\x6c"
+ "\xc9\xb5\x0c\xee\x15\xf3\x7d\xbe"
+ "\x9f\x7b\x5a\xa6\xae\x4f\x83\xb6"
+ "\x79\x49\x41\xf4\x58\x18\xcb\x86"
+ "\x7f\x30\x0e\xf8\x7d\x44\x36\xea"
+ "\x75\xeb\x88\x84\x40\x3c\xad\x4f"
+ "\x6f\x31\x6b\xaa\x5d\xe5\xa5\xc5"
+ "\x21\x66\xe9\xa7\xe3\xb2\x15\x88"
+ "\x78\xf6\x79\xa1\x59\x47\x12\x4e"
+ "\x9f\x9f\x64\x1a\xa0\x22\x5b\x08"
+ "\xbe\x7c\x36\xc2\x2b\x66\x33\x1b"
+ "\xdd\x60\x71\xf7\x47\x8c\x61\xc3"
+ "\xda\x8a\x78\x1e\x16\xfa\x1e\x86"
+ "\x81\xa6\x17\x2a\xa7\xb5\xc2\xe7"
+ "\xa4\xc7\x42\xf1\xcf\x6a\xca\xb4"
+ "\x45\xcf\xf3\x93\xf0\xe7\xea\xf6"
+ "\xf4\xe6\x33\x43\x84\x93\xa5\x67"
+ "\x9b\x16\x58\x58\x80\x0f\x2b\x5c"
+ "\x24\x74\x75\x7f\x95\x81\xb7\x30"
+ "\x7a\x33\xa7\xf7\x94\x87\x32\x27"
+ "\x10\x5d\x14\x4c\x43\x29\xdd\x26"
+ "\xbd\x3e\x3c\x0e\xfe\x0e\xa5\x10"
+ "\xea\x6b\x64\xfd\x73\xc6\xed\xec"
+ "\xa8\xc9\xbf\xb3\xba\x0b\x4d\x07"
+ "\x70\xfc\x16\xfd\x79\x1e\xd7\xc5"
+ "\x49\x4e\x1c\x8b\x8d\x79\x1b\xb1"
+ "\xec\xca\x60\x09\x4c\x6a\xd5\x09"
+ "\x49\x46\x00\x88\x22\x8d\xce\xea"
+ "\xb1\x17\x11\xde\x42\xd2\x23\xc1"
+ "\x72\x11\xf5\x50\x73\x04\x40\x47"
+ "\xf9\x5d\xe7\xa7\x26\xb1\x7e\xb0"
+ "\x3f\x58\xc1\x52\xab\x12\x67\x9d"
+ "\x3f\x43\x4b\x68\xd4\x9c\x68\x38"
+ "\x07\x8a\x2d\x3e\xf3\xaf\x6a\x4b"
+ "\xf9\xe5\x31\x69\x22\xf9\xa6\x69"
+ "\xc6\x9c\x96\x9a\x12\x35\x95\x1d"
+ "\x95\xd5\xdd\xbe\xbf\x93\x53\x24"
+ "\xfd\xeb\xc2\x0a\x64\xb0\x77\x00"
+ "\x6f\x88\xc4\x37\x18\x69\x7c\xd7"
+ "\x41\x92\x55\x4c\x03\xa1\x9a\x4b"
+ "\x15\xe5\xdf\x7f\x37\x33\x72\xc1"
+ "\x8b\x10\x67\xa3\x01\x57\x94\x25"
+ "\x7b\x38\x71\x7e\xdd\x1e\xcc\x73"
+ "\x55\xd2\x8e\xeb\x07\xdd\xf1\xda"
+ "\x58\xb1\x47\x90\xfe\x42\x21\x72"
+ "\xa3\x54\x7a\xa0\x40\xec\x9f\xdd"
+ "\xc6\x84\x6e\xca\xae\xe3\x68\xb4"
+ "\x9d\xe4\x78\xff\x57\xf2\xf8\x1b"
+ "\x03\xa1\x31\xd9\xde\x8d\xf5\x22"
+ "\x9c\xdd\x20\xa4\x1e\x27\xb1\x76"
+ "\x4f\x44\x55\xe2\x9b\xa1\x9c\xfe"
+ "\x54\xf7\x27\x1b\xf4\xde\x02\xf5"
+ "\x1b\x55\x48\x5c\xdc\x21\x4b\x9e"
+ "\x4b\x6e\xed\x46\x23\xdc\x65\xb2"
+ "\xcf\x79\x5f\x28\xe0\x9e\x8b\xe7"
+ "\x4c\x9d\x8a\xff\xc1\xa6\x28\xb8"
+ "\x65\x69\x8a\x45\x29\xef\x74\x85"
+ "\xde\x79\xc7\x08\xae\x30\xb0\xf4"
+ "\xa3\x1d\x51\x41\xab\xce\xcb\xf6"
+ "\xb5\xd8\x6d\xe0\x85\xe1\x98\xb3"
+ "\x43\xbb\x86\x83\x0a\xa0\xf5\xb7"
+ "\x04\x0b\xfa\x71\x1f\xb0\xf6\xd9"
+ "\x13\x00\x15\xf0\xc7\xeb\x0d\x5a"
+ "\x9f\xd7\xb9\x6c\x65\x14\x22\x45"
+ "\x6e\x45\x32\x3e\x7e\x60\x1a\x12"
+ "\x97\x82\x14\xfb\xaa\x04\x22\xfa"
+ "\xa0\xe5\x7e\x8c\x78\x02\x48\x5d"
+ "\x78\x33\x5a\x7c\xad\xdb\x29\xce"
+ "\xbb\x8b\x61\xa4\xb7\x42\xe2\xac"
+ "\x8b\x1a\xd9\x2f\x0b\x8b\x62\x21"
+ "\x83\x35\x7e\xad\x73\xc2\xb5\x6c"
+ "\x10\x26\x38\x07\xe5\xc7\x36\x80"
+ "\xe2\x23\x12\x61\xf5\x48\x4b\x2b"
+ "\xc5\xdf\x15\xd9\x87\x01\xaa\xac"
+ "\x1e\x7c\xad\x73\x78\x18\x63\xe0"
+ "\x8b\x9f\x81\xd8\x12\x6a\x28\x10"
+ "\xbe\x04\x68\x8a\x09\x7c\x1b\x1c"
+ "\x83\x66\x80\x47\x80\xe8\xfd\x35"
+ "\x1c\x97\x6f\xae\x49\x10\x66\xcc"
+ "\xc6\xd8\xcc\x3a\x84\x91\x20\x77"
+ "\x72\xe4\x24\xd2\x37\x9f\xc5\xc9"
+ "\x25\x94\x10\x5f\x40\x00\x64\x99"
+ "\xdc\xae\xd7\x21\x09\x78\x50\x15"
+ "\xac\x5f\xc6\x2c\xa2\x0b\xa9\x39"
+ "\x87\x6e\x6d\xab\xde\x08\x51\x16"
+ "\xc7\x13\xe9\xea\xed\x06\x8e\x2c"
+ "\xf8\x37\x8c\xf0\xa6\x96\x8d\x43"
+ "\xb6\x98\x37\xb2\x43\xed\xde\xdf"
+ "\x89\x1a\xe7\xeb\x9d\xa1\x7b\x0b"
+ "\x77\xb0\xe2\x75\xc0\xf1\x98\xd9"
+ "\x80\x55\xc9\x34\x91\xd1\x59\xe8"
+ "\x4b\x0f\xc1\xa9\x4b\x7a\x84\x06"
+ "\x20\xa8\x5d\xfa\xd1\xde\x70\x56"
+ "\x2f\x9e\x91\x9c\x20\xb3\x24\xd8"
+ "\x84\x3d\xe1\x8c\x7e\x62\x52\xe5"
+ "\x44\x4b\x9f\xc2\x93\x03\xea\x2b"
+ "\x59\xc5\xfa\x3f\x91\x2b\xbb\x23"
+ "\xf5\xb2\x7b\xf5\x38\xaf\xb3\xee"
+ "\x63\xdc\x7b\xd1\xff\xaa\x8b\xab"
+ "\x82\x6b\x37\x04\xeb\x74\xbe\x79"
+ "\xb9\x83\x90\xef\x20\x59\x46\xff"
+ "\xe9\x97\x3e\x2f\xee\xb6\x64\x18"
+ "\x38\x4c\x7a\x4a\xf9\x61\xe8\x9a"
+ "\xa1\xb5\x01\xa6\x47\xd3\x11\xd4"
+ "\xce\xd3\x91\x49\x88\xc7\xb8\x4d"
+ "\xb1\xb9\x07\x6d\x16\x72\xae\x46"
+ "\x5e\x03\xa1\x4b\xb6\x02\x30\xa8"
+ "\x3d\xa9\x07\x2a\x7c\x19\xe7\x62"
+ "\x87\xe3\x82\x2f\x6f\xe1\x09\xd9"
+ "\x94\x97\xea\xdd\x58\x9e\xae\x76"
+ "\x7e\x35\xe5\xb4\xda\x7e\xf4\xde"
+ "\xf7\x32\x87\xcd\x93\xbf\x11\x56"
+ "\x11\xbe\x08\x74\xe1\x69\xad\xe2"
+ "\xd7\xf8\x86\x75\x8a\x3c\xa4\xbe"
+ "\x70\xa7\x1b\xfc\x0b\x44\x2a\x76"
+ "\x35\xea\x5d\x85\x81\xaf\x85\xeb"
+ "\xa0\x1c\x61\xc2\xf7\x4f\xa5\xdc"
+ "\x02\x7f\xf6\x95\x40\x6e\x8a\x9a"
+ "\xf3\x5d\x25\x6e\x14\x3a\x22\xc9"
+ "\x37\x1c\xeb\x46\x54\x3f\xa5\x91"
+ "\xc2\xb5\x8c\xfe\x53\x08\x97\x32"
+ "\x1b\xb2\x30\x27\xfe\x25\x5d\xdc"
+ "\x08\x87\xd0\xe5\x94\x1a\xd4\xf1"
+ "\xfe\xd6\xb4\xa3\xe6\x74\x81\x3c"
+ "\x1b\xb7\x31\xa7\x22\xfd\xd4\xdd"
+ "\x20\x4e\x7c\x51\xb0\x60\x73\xb8"
+ "\x9c\xac\x91\x90\x7e\x01\xb0\xe1"
+ "\x8a\x2f\x75\x1c\x53\x2a\x98\x2a"
+ "\x06\x52\x95\x52\xb2\xe9\x25\x2e"
+ "\x4c\xe2\x5a\x00\xb2\x13\x81\x03"
+ "\x77\x66\x0d\xa5\x99\xda\x4e\x8c"
+ "\xac\xf3\x13\x53\x27\x45\xaf\x64"
+ "\x46\xdc\xea\x23\xda\x97\xd1\xab"
+ "\x7d\x6c\x30\x96\x1f\xbc\x06\x34"
+ "\x18\x0b\x5e\x21\x35\x11\x8d\x4c"
+ "\xe0\x2d\xe9\x50\x16\x74\x81\xa8"
+ "\xb4\x34\xb9\x72\x42\xa6\xcc\xbc"
+ "\xca\x34\x83\x27\x10\x5b\x68\x45"
+ "\x8f\x52\x22\x0c\x55\x3d\x29\x7c"
+ "\xe3\xc0\x66\x05\x42\x91\x5f\x58"
+ "\xfe\x4a\x62\xd9\x8c\xa9\x04\x19"
+ "\x04\xa9\x08\x4b\x57\xfc\x67\x53"
+ "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f"
+ "\x92\xd6\x41\x7c\x5b\x2a\x00\x79"
+ "\x72",
+ .result = "\xe1\xb6\x8b\x5c\x80\xb8\xcc\x08"
+ "\x1b\x84\xb2\xd1\xad\xa4\x70\xac"
+ "\x67\xa9\x39\x27\xac\xb4\x5b\xb7"
+ "\x4c\x26\x77\x23\x1d\xce\x0a\xbe"
+ "\x18\x9e\x42\x8b\xbd\x7f\xd6\xf1"
+ "\xf1\x6b\xe2\x6d\x7f\x92\x0e\xcb"
+ "\xb8\x79\xba\xb4\xac\x7e\x2d\xc0"
+ "\x9e\x83\x81\x91\xd5\xea\xc3\x12"
+ "\x8d\xa4\x26\x70\xa4\xf9\x71\x0b"
+ "\xbd\x2e\xe1\xb3\x80\x42\x25\xb3"
+ "\x0b\x31\x99\xe1\x0d\xde\xa6\x90"
+ "\xf2\xa3\x10\xf7\xe5\xf3\x83\x1e"
+ "\x2c\xfb\x4d\xf0\x45\x3d\x28\x3c"
+ "\xb8\xf1\xcb\xbf\x67\xd8\x43\x5a"
+ "\x9d\x7b\x73\x29\x88\x0f\x13\x06"
+ "\x37\x50\x0d\x7c\xe6\x9b\x07\xdd"
+ "\x7e\x01\x1f\x81\x90\x10\x69\xdb"
+ "\xa4\xad\x8a\x5e\xac\x30\x72\xf2"
+ "\x36\xcd\xe3\x23\x49\x02\x93\xfa"
+ "\x3d\xbb\xe2\x98\x83\xeb\xe9\x8d"
+ "\xb3\x8f\x11\xaa\x53\xdb\xaf\x2e"
+ "\x95\x13\x99\x3d\x71\xbd\x32\x92"
+ "\xdd\xfc\x9d\x5e\x6f\x63\x2c\xee"
+ "\x91\x1f\x4c\x64\x3d\x87\x55\x0f"
+ "\xcc\x3d\x89\x61\x53\x02\x57\x8f"
+ "\xe4\x77\x29\x32\xaf\xa6\x2f\x0a"
+ "\xae\x3c\x3f\x3f\xf4\xfb\x65\x52"
+ "\xc5\xc1\x78\x78\x53\x28\xad\xed"
+ "\xd1\x67\x37\xc7\x59\x70\xcd\x0a"
+ "\xb8\x0f\x80\x51\x9f\xc0\x12\x5e"
+ "\x06\x0a\x7e\xec\x24\x5f\x73\x00"
+ "\xb1\x0b\x31\x47\x4f\x73\x8d\xb4"
+ "\xce\xf3\x55\x45\x6c\x84\x27\xba"
+ "\xb9\x6f\x03\x4a\xeb\x98\x88\x6e"
+ "\x53\xed\x25\x19\x0d\x8f\xfe\xca"
+ "\x60\xe5\x00\x93\x6e\x3c\xff\x19"
+ "\xae\x08\x3b\x8a\xa6\x84\x05\xfe"
+ "\x9b\x59\xa0\x8c\xc8\x05\x45\xf5"
+ "\x05\x37\xdc\x45\x6f\x8b\x95\x8c"
+ "\x4e\x11\x45\x7a\xce\x21\xa5\xf7"
+ "\x71\x67\xb9\xce\xd7\xf9\xe9\x5e"
+ "\x60\xf5\x53\x7a\xa8\x85\x14\x03"
+ "\xa0\x92\xec\xf3\x51\x80\x84\xc4"
+ "\xdc\x11\x9e\x57\xce\x4b\x45\xcf"
+ "\x90\x95\x85\x0b\x96\xe9\xee\x35"
+ "\x10\xb8\x9b\xf2\x59\x4a\xc6\x7e"
+ "\x85\xe5\x6f\x38\x51\x93\x40\x0c"
+ "\x99\xd7\x7f\x32\xa8\x06\x27\xd1"
+ "\x2b\xd5\xb5\x3a\x1a\xe1\x5e\xda"
+ "\xcd\x5a\x50\x30\x3c\xc7\xe7\x65"
+ "\xa6\x07\x0b\x98\x91\xc6\x20\x27"
+ "\x2a\x03\x63\x1b\x1e\x3d\xaf\xc8"
+ "\x71\x48\x46\x6a\x64\x28\xf9\x3d"
+ "\xd1\x1d\xab\xc8\x40\x76\xc2\x39"
+ "\x4e\x00\x75\xd2\x0e\x82\x58\x8c"
+ "\xd3\x73\x5a\xea\x46\x89\xbe\xfd"
+ "\x4e\x2c\x0d\x94\xaa\x9b\x68\xac"
+ "\x86\x87\x30\x7e\xa9\x16\xcd\x59"
+ "\xd2\xa6\xbe\x0a\xd8\xf5\xfd\x2d"
+ "\x49\x69\xd2\x1a\x90\xd2\x1b\xed"
+ "\xff\x71\x04\x87\x87\x21\xc4\xb8"
+ "\x1f\x5b\x51\x33\xd0\xd6\x59\x9a"
+ "\x03\x0e\xd3\x8b\xfb\x57\x73\xfd"
+ "\x5a\x52\x63\x82\xc8\x85\x2f\xcb"
+ "\x74\x6d\x4e\xd9\x68\x37\x85\x6a"
+ "\xd4\xfb\x94\xed\x8d\xd1\x1a\xaf"
+ "\x76\xa7\xb7\x88\xd0\x2b\x4e\xda"
+ "\xec\x99\x94\x27\x6f\x87\x8c\xdf"
+ "\x4b\x5e\xa6\x66\xdd\xcb\x33\x7b"
+ "\x64\x94\x31\xa8\x37\xa6\x1d\xdb"
+ "\x0d\x5c\x93\xa4\x40\xf9\x30\x53"
+ "\x4b\x74\x8d\xdd\xf6\xde\x3c\xac"
+ "\x5c\x80\x01\x3a\xef\xb1\x9a\x02"
+ "\x0c\x22\x8e\xe7\x44\x09\x74\x4c"
+ "\xf2\x9a\x27\x69\x7f\x12\x32\x36"
+ "\xde\x92\xdf\xde\x8f\x5b\x31\xab"
+ "\x4a\x01\x26\xe0\xb1\xda\xe8\x37"
+ "\x21\x64\xe8\xff\x69\xfc\x9e\x41"
+ "\xd2\x96\x2d\x18\x64\x98\x33\x78"
+ "\x24\x61\x73\x9b\x47\x29\xf1\xa7"
+ "\xcb\x27\x0f\xf0\x85\x6d\x8c\x9d"
+ "\x2c\x95\x9e\xe5\xb2\x8e\x30\x29"
+ "\x78\x8a\x9d\x65\xb4\x8e\xde\x7b"
+ "\xd9\x00\x50\xf5\x7f\x81\xc3\x1b"
+ "\x25\x85\xeb\xc2\x8c\x33\x22\x1e"
+ "\x68\x38\x22\x30\xd8\x2e\x00\x98"
+ "\x85\x16\x06\x56\xb4\x81\x74\x20"
+ "\x95\xdb\x1c\x05\x19\xe8\x23\x4d"
+ "\x65\x5d\xcc\xd8\x7f\xc4\x2d\x0f"
+ "\x57\x26\x71\x07\xad\xaa\x71\x9f"
+ "\x19\x76\x2f\x25\x51\x88\xe4\xc0"
+ "\x82\x6e\x08\x05\x37\x04\xee\x25"
+ "\x23\x90\xe9\x4e\xce\x9b\x16\xc1"
+ "\x31\xe7\x6e\x2c\x1b\xe1\x85\x9a"
+ "\x0c\x8c\xbb\x12\x1e\x68\x7b\x93"
+ "\xa9\x3c\x39\x56\x23\x3e\x6e\xc7"
+ "\x77\x84\xd3\xe0\x86\x59\xaa\xb9"
+ "\xd5\x53\x58\xc9\x0a\x83\x5f\x85"
+ "\xd8\x47\x14\x67\x8a\x3c\x17\xe0"
+ "\xab\x02\x51\xea\xf1\xf0\x4f\x30"
+ "\x7d\xe0\x92\xc2\x5f\xfb\x19\x5a"
+ "\x3f\xbd\xf4\x39\xa4\x31\x0c\x39"
+ "\xd1\xae\x4e\xf7\x65\x7f\x1f\xce"
+ "\xc2\x39\xd1\x84\xd4\xe5\x02\xe0"
+ "\x58\xaa\xf1\x5e\x81\xaf\x7f\x72"
+ "\x0f\x08\x99\x43\xb9\xd8\xac\x41"
+ "\x35\x55\xf2\xb2\xd4\x98\xb8\x3b"
+ "\x2b\x3c\x3e\x16\x06\x31\xfc\x79"
+ "\x47\x38\x63\x51\xc5\xd0\x26\xd7"
+ "\x43\xb4\x2b\xd9\xc5\x05\xf2\x9d"
+ "\x18\xc9\x26\x82\x56\xd2\x11\x05"
+ "\xb6\x89\xb4\x43\x9c\xb5\x9d\x11"
+ "\x6c\x83\x37\x71\x27\x1c\xae\xbf"
+ "\xcd\x57\xd2\xee\x0d\x5a\x15\x26"
+ "\x67\x88\x80\x80\x1b\xdc\xc1\x62"
+ "\xdd\x4c\xff\x92\x5c\x6c\xe1\xa0"
+ "\xe3\x79\xa9\x65\x8c\x8c\x14\x42"
+ "\xe5\x11\xd2\x1a\xad\xa9\x56\x6f"
+ "\x98\xfc\x8a\x7b\x56\x1f\xc6\xc1"
+ "\x52\x12\x92\x9b\x41\x0f\x4b\xae"
+ "\x1b\x4a\xbc\xfe\x23\xb6\x94\x70"
+ "\x04\x30\x9e\x69\x47\xbe\xb8\x8f"
+ "\xca\x45\xd7\x8a\xf4\x78\x3e\xaa"
+ "\x71\x17\xd8\x1e\xb8\x11\x8f\xbc"
+ "\xc8\x1a\x65\x7b\x41\x89\x72\xc7"
+ "\x5f\xbe\xc5\x2a\xdb\x5c\x54\xf9"
+ "\x25\xa3\x7a\x80\x56\x9c\x8c\xab"
+ "\x26\x19\x10\x36\xa6\xf3\x14\x79"
+ "\x40\x98\x70\x68\xb7\x35\xd9\xb9"
+ "\x27\xd4\xe7\x74\x5b\x3d\x97\xb4"
+ "\xd9\xaa\xd9\xf2\xb5\x14\x84\x1f"
+ "\xa9\xde\x12\x44\x5b\x00\xc0\xbc"
+ "\xc8\x11\x25\x1b\x67\x7a\x15\x72"
+ "\xa6\x31\x6f\xf4\x68\x7a\x86\x9d"
+ "\x43\x1c\x5f\x16\xd3\xad\x2e\x52"
+ "\xf3\xb4\xc3\xfa\x27\x2e\x68\x6c"
+ "\x06\xe7\x4c\x4f\xa2\xe0\xe4\x21"
+ "\x5d\x9e\x33\x58\x8d\xbf\xd5\x70"
+ "\xf8\x80\xa5\xdd\xe7\x18\x79\xfa"
+ "\x7b\xfd\x09\x69\x2c\x37\x32\xa8"
+ "\x65\xfa\x8d\x8b\x5c\xcc\xe8\xf3"
+ "\x37\xf6\xa6\xc6\x5c\xa2\x66\x79"
+ "\xfa\x8a\xa7\xd1\x0b\x2e\x1b\x5e"
+ "\x95\x35\x00\x76\xae\x42\xf7\x50"
+ "\x51\x78\xfb\xb4\x28\x24\xde\x1a"
+ "\x70\x8b\xed\xca\x3c\x5e\xe4\xbd"
+ "\x28\xb5\xf3\x76\x4f\x67\x5d\x81"
+ "\xb2\x60\x87\xd9\x7b\x19\x1a\xa7"
+ "\x79\xa2\xfa\x3f\x9e\xa9\xd7\x25"
+ "\x61\xe1\x74\x31\xa2\x77\xa0\x1b"
+ "\xf6\xf7\xcb\xc5\xaa\x9e\xce\xf9"
+ "\x9b\x96\xef\x51\xc3\x1a\x44\x96"
+ "\xae\x17\x50\xab\x29\x08\xda\xcc"
+ "\x1a\xb3\x12\xd0\x24\xe4\xe2\xe0"
+ "\xc6\xe3\xcc\x82\xd0\xba\x47\x4c"
+ "\x3f\x49\xd7\xe8\xb6\x61\xaa\x65"
+ "\x25\x18\x40\x2d\x62\x25\x02\x71"
+ "\x61\xa2\xc1\xb2\x13\xd2\x71\x3f"
+ "\x43\x1a\xc9\x09\x92\xff\xd5\x57"
+ "\xf0\xfc\x5e\x1c\xf1\xf5\xf9\xf3"
+ "\x5b",
+ .ilen = 1281,
+ .rlen = 1281,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 1200, 1, 80 },
+ },
+};
+
+/* Adiantum test vectors from https://github.com/google/adiantum */
+static struct cipher_testvec adiantum_xchacha12_aes_enc_tv_template[] = {
+ {
+ .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4"
+ "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd"
+ "\x75\x20\x57\xea\x2c\x4f\xcd\xb2"
+ "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f",
+ .klen = 32,
+ .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8"
+ "\x33\x81\x37\x60\x7d\xfa\x73\x08"
+ "\xd8\x49\x6d\x80\xe8\x2f\x62\x54"
+ "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a",
+ .input = "\x67\xc9\xf2\x30\x84\x41\x8e\x43"
+ "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8",
+ .result = "\x6d\x32\x86\x18\x67\x86\x0f\x3f"
+ "\x96\x7c\x9d\x28\x0d\x53\xec\x9f",
+ .ilen = 16,
+ .rlen = 16,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 14, 2 },
+ }, {
+ .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99"
+ "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27"
+ "\xcc\x16\xd7\x2b\x85\x63\x99\xd3"
+ "\xba\x96\xa1\xdb\xd2\x60\x68\xda",
+ .klen = 32,
+ .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47"
+ "\x24\xc1\xb1\x69\xe1\x12\x93\x8f"
+ "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9"
+ "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4",
+ .input = "\x5e\xa8\x68\x19\x85\x98\x12\x23"
+ "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf"
+ "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19"
+ "\x43\x5a\x46\x06\x94\x2d\xf2",
+ .result = "\xc7\xc6\xf1\x73\x8f\xc4\xff\x4a"
+ "\x39\xbe\x78\xbe\x8d\x28\xc8\x89"
+ "\x46\x63\xe7\x0c\x7d\x87\xe8\x4e"
+ "\xc9\x18\x7b\xbe\x18\x60\x50",
+ .ilen = 31,
+ .rlen = 31,
+ }, {
+ .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7"
+ "\x05\x91\x8f\xee\x85\x1f\x35\x7f"
+ "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e"
+ "\x19\x09\x00\xa9\x04\x31\x4f\x11",
+ .klen = 32,
+ .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8"
+ "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb"
+ "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62"
+ "\xac\xa9\x8c\x41\x42\x94\x75\xb7",
+ .input = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82"
+ "\xf1\xec\x5d\x04\xe5\x14\x91\x13"
+ "\xdf\xf2\x87\x1b\x69\x81\x1d\x71"
+ "\x70\x9e\x9c\x3b\xde\x49\x70\x11"
+ "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69"
+ "\xd7\xdb\x80\xa7\x70\x92\x68\xce"
+ "\x81\x04\x2c\xc6\xab\xae\xe5\x60"
+ "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7"
+ "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea"
+ "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f"
+ "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9"
+ "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e"
+ "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13"
+ "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8"
+ "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a"
+ "\x56\x65\xc5\x54\x23\x28\xb0\x03",
+ .result = "\x9e\x16\xab\xed\x4b\xa7\x42\x5a"
+ "\xc6\xfb\x4e\x76\xff\xbe\x03\xa0"
+ "\x0f\xe3\xad\xba\xe4\x98\x2b\x0e"
+ "\x21\x48\xa0\xb8\x65\x48\x27\x48"
+ "\x84\x54\x54\xb2\x9a\x94\x7b\xe6"
+ "\x4b\x29\xe9\xcf\x05\x91\x80\x1a"
+ "\x3a\xf3\x41\x96\x85\x1d\x9f\x74"
+ "\x51\x56\x63\xfa\x7c\x28\x85\x49"
+ "\xf7\x2f\xf9\xf2\x18\x46\xf5\x33"
+ "\x80\xa3\x3c\xce\xb2\x57\x93\xf5"
+ "\xae\xbd\xa9\xf5\x7b\x30\xc4\x93"
+ "\x66\xe0\x30\x77\x16\xe4\xa0\x31"
+ "\xba\x70\xbc\x68\x13\xf5\xb0\x9a"
+ "\xc1\xfc\x7e\xfe\x55\x80\x5c\x48"
+ "\x74\xa6\xaa\xa3\xac\xdc\xc2\xf5"
+ "\x8d\xde\x34\x86\x78\x60\x75\x8d",
+ .ilen = 128,
+ .rlen = 128,
+ .also_non_np = 1,
+ .np = 4,
+ .tap = { 104, 16, 4, 4 },
+ }, {
+ .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a"
+ "\x25\x74\x29\x0d\x51\x8a\x0e\x13"
+ "\xc1\x53\x5d\x30\x8d\xee\x75\x0d"
+ "\x14\xd6\x69\xc9\x15\xa9\x0c\x60",
+ .klen = 32,
+ .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4"
+ "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2"
+ "\x62\x81\x97\xc5\x81\xaa\xf9\x44"
+ "\xc1\x72\x59\x82\xaf\x16\xc8\x2c",
+ .input = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09"
+ "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5"
+ "\x05\xa3\x69\x60\x91\x36\x98\x57"
+ "\xba\x0c\x14\xcc\xf3\x2d\x73\x03"
+ "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d"
+ "\xd0\x0b\x87\xb2\x50\x94\x7b\x58"
+ "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9"
+ "\x41\x84\xc1\xb1\x7e\x4b\x91\x12"
+ "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9"
+ "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4"
+ "\xa5\x20\x98\xef\xb5\xda\xe5\xc0"
+ "\x8a\x6a\x83\x77\x15\x84\x1e\xae"
+ "\x78\x94\x9d\xdf\xb7\xd1\xea\x67"
+ "\xaa\xb0\x14\x15\xfa\x67\x21\x84"
+ "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8"
+ "\x95\x62\xa9\x55\xf0\x80\xad\xbd"
+ "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36"
+ "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0"
+ "\x88\x4e\xec\x2c\x88\x10\x5e\xea"
+ "\x12\xc0\x16\x01\x29\xa3\xa0\x55"
+ "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b"
+ "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d"
+ "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3"
+ "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e"
+ "\x9c\xac\xdb\x90\xbd\x83\x72\xba"
+ "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf"
+ "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5"
+ "\x1e\x19\x38\x09\x16\xd2\x82\x1f"
+ "\x75\x18\x56\xb8\x96\x0b\xa6\xf9"
+ "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d"
+ "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee"
+ "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d"
+ "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25"
+ "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30"
+ "\xae\x23\x4f\x0e\x13\x66\x4f\xe1"
+ "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e"
+ "\x15\x85\x6b\xe3\x60\x81\x1d\x68"
+ "\xd7\x31\x87\x89\x09\xab\xd5\x96"
+ "\x1d\xf3\x6d\x67\x80\xca\x07\x31"
+ "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33"
+ "\x52\x18\xc8\x30\xfe\x2d\xca\x1e"
+ "\x79\x92\x7a\x60\x5c\xb6\x58\x87"
+ "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7"
+ "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63"
+ "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96"
+ "\x47\xca\xb8\x91\xf9\xf7\x94\x21"
+ "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b"
+ "\x66\x69\x6a\x72\xd0\xcb\x70\xb7"
+ "\x93\xb5\x37\x96\x05\x37\x4f\xe5"
+ "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea"
+ "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac"
+ "\x18\x7d\x52\x3b\xb3\x34\x62\x99"
+ "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84"
+ "\x17\x7c\x25\x48\x52\x67\x11\x27"
+ "\x67\xbb\x5a\x85\xca\x56\xb2\x5c"
+ "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb"
+ "\x22\x25\xf4\x13\xe5\x93\x4b\x9a"
+ "\x77\xf1\x52\x18\xfa\x16\x5e\x49"
+ "\x03\x45\xa8\x08\xfa\xb3\x41\x92"
+ "\x79\x50\x33\xca\xd0\xd7\x42\x55"
+ "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86"
+ "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc"
+ "\xf1\x54\x6e\x93\xa4\x65\x99\x8e"
+ "\xdf\x29\xc0\x64\x63\x07\xbb\xea",
+ .result = "\x15\x97\xd0\x86\x18\x03\x9c\x51"
+ "\xc5\x11\x36\x62\x13\x92\xe6\x73"
+ "\x29\x79\xde\xa1\x00\x3e\x08\x64"
+ "\x17\x1a\xbc\xd5\xfe\x33\x0e\x0c"
+ "\x7c\x94\xa7\xc6\x3c\xbe\xac\xa2"
+ "\x89\xe6\xbc\xdf\x0c\x33\x27\x42"
+ "\x46\x73\x2f\xba\x4e\xa6\x46\x8f"
+ "\xe4\xee\x39\x63\x42\x65\xa3\x88"
+ "\x7a\xad\x33\x23\xa9\xa7\x20\x7f"
+ "\x0b\xe6\x6a\xc3\x60\xda\x9e\xb4"
+ "\xd6\x07\x8a\x77\x26\xd1\xab\x44"
+ "\x99\x55\x03\x5e\xed\x8d\x7b\xbd"
+ "\xc8\x21\xb7\x21\x30\x3f\xc0\xb5"
+ "\xc8\xec\x6c\x23\xa6\xa3\x6d\xf1"
+ "\x30\x0a\xd0\xa6\xa9\x28\x69\xae"
+ "\x2a\xe6\x54\xac\x82\x9d\x6a\x95"
+ "\x6f\x06\x44\xc5\x5a\x77\x6e\xec"
+ "\xf8\xf8\x63\xb2\xe6\xaa\xbd\x8e"
+ "\x0e\x8a\x62\x00\x03\xc8\x84\xdd"
+ "\x47\x4a\xc3\x55\xba\xb7\xe7\xdf"
+ "\x08\xbf\x62\xf5\xe8\xbc\xb6\x11"
+ "\xe4\xcb\xd0\x66\x74\x32\xcf\xd4"
+ "\xf8\x51\x80\x39\x14\x05\x12\xdb"
+ "\x87\x93\xe2\x26\x30\x9c\x3a\x21"
+ "\xe5\xd0\x38\x57\x80\x15\xe4\x08"
+ "\x58\x05\x49\x7d\xe6\x92\x77\x70"
+ "\xfb\x1e\x2d\x6a\x84\x00\xc8\x68"
+ "\xf7\x1a\xdd\xf0\x7b\x38\x1e\xd8"
+ "\x2c\x78\x78\x61\xcf\xe3\xde\x69"
+ "\x1f\xd5\x03\xd5\x1a\xb4\xcf\x03"
+ "\xc8\x7a\x70\x68\x35\xb4\xf6\xbe"
+ "\x90\x62\xb2\x28\x99\x86\xf5\x44"
+ "\x99\xeb\x31\xcf\xca\xdf\xd0\x21"
+ "\xd6\x60\xf7\x0f\x40\xb4\x80\xb7"
+ "\xab\xe1\x9b\x45\xba\x66\xda\xee"
+ "\xdd\x04\x12\x40\x98\xe1\x69\xe5"
+ "\x2b\x9c\x59\x80\xe7\x7b\xcc\x63"
+ "\xa6\xc0\x3a\xa9\xfe\x8a\xf9\x62"
+ "\x11\x34\x61\x94\x35\xfe\xf2\x99"
+ "\xfd\xee\x19\xea\x95\xb6\x12\xbf"
+ "\x1b\xdf\x02\x1a\xcc\x3e\x7e\x65"
+ "\x78\x74\x10\x50\x29\x63\x28\xea"
+ "\x6b\xab\xd4\x06\x4d\x15\x24\x31"
+ "\xc7\x0a\xc9\x16\xb6\x48\xf0\xbf"
+ "\x49\xdb\x68\x71\x31\x8f\x87\xe2"
+ "\x13\x05\x64\xd6\x22\x0c\xf8\x36"
+ "\x84\x24\x3e\x69\x5e\xb8\x9e\x16"
+ "\x73\x6c\x83\x1e\xe0\x9f\x9e\xba"
+ "\xe5\x59\x21\x33\x1b\xa9\x26\xc2"
+ "\xc7\xd9\x30\x73\xb6\xa6\x73\x82"
+ "\x19\xfa\x44\x4d\x40\x8b\x69\x04"
+ "\x94\x74\xea\x6e\xb3\x09\x47\x01"
+ "\x2a\xb9\x78\x34\x43\x11\xed\xd6"
+ "\x8c\x95\x65\x1b\x85\x67\xa5\x40"
+ "\xac\x9c\x05\x4b\x57\x4a\xa9\x96"
+ "\x0f\xdd\x4f\xa1\xe0\xcf\x6e\xc7"
+ "\x1b\xed\xa2\xb4\x56\x8c\x09\x6e"
+ "\xa6\x65\xd7\x55\x81\xb7\xed\x11"
+ "\x9b\x40\x75\xa8\x6b\x56\xaf\x16"
+ "\x8b\x3d\xf4\xcb\xfe\xd5\x1d\x3d"
+ "\x85\xc2\xc0\xde\x43\x39\x4a\x96"
+ "\xba\x88\x97\xc0\xd6\x00\x0e\x27"
+ "\x21\xb0\x21\x52\xba\xa7\x37\xaa"
+ "\xcc\xbf\x95\xa8\xf4\xd0\x91\xf6",
+ .ilen = 512,
+ .rlen = 512,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 144, 368 },
+ }
+};
+
+static struct cipher_testvec adiantum_xchacha12_aes_dec_tv_template[] = {
+ {
+ .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4"
+ "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd"
+ "\x75\x20\x57\xea\x2c\x4f\xcd\xb2"
+ "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f",
+ .klen = 32,
+ .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8"
+ "\x33\x81\x37\x60\x7d\xfa\x73\x08"
+ "\xd8\x49\x6d\x80\xe8\x2f\x62\x54"
+ "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a",
+ .result = "\x67\xc9\xf2\x30\x84\x41\x8e\x43"
+ "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8",
+ .input = "\x6d\x32\x86\x18\x67\x86\x0f\x3f"
+ "\x96\x7c\x9d\x28\x0d\x53\xec\x9f",
+ .ilen = 16,
+ .rlen = 16,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 14, 2 },
+ }, {
+ .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99"
+ "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27"
+ "\xcc\x16\xd7\x2b\x85\x63\x99\xd3"
+ "\xba\x96\xa1\xdb\xd2\x60\x68\xda",
+ .klen = 32,
+ .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47"
+ "\x24\xc1\xb1\x69\xe1\x12\x93\x8f"
+ "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9"
+ "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4",
+ .result = "\x5e\xa8\x68\x19\x85\x98\x12\x23"
+ "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf"
+ "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19"
+ "\x43\x5a\x46\x06\x94\x2d\xf2",
+ .input = "\xc7\xc6\xf1\x73\x8f\xc4\xff\x4a"
+ "\x39\xbe\x78\xbe\x8d\x28\xc8\x89"
+ "\x46\x63\xe7\x0c\x7d\x87\xe8\x4e"
+ "\xc9\x18\x7b\xbe\x18\x60\x50",
+ .ilen = 31,
+ .rlen = 31,
+ }, {
+ .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7"
+ "\x05\x91\x8f\xee\x85\x1f\x35\x7f"
+ "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e"
+ "\x19\x09\x00\xa9\x04\x31\x4f\x11",
+ .klen = 32,
+ .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8"
+ "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb"
+ "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62"
+ "\xac\xa9\x8c\x41\x42\x94\x75\xb7",
+ .result = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82"
+ "\xf1\xec\x5d\x04\xe5\x14\x91\x13"
+ "\xdf\xf2\x87\x1b\x69\x81\x1d\x71"
+ "\x70\x9e\x9c\x3b\xde\x49\x70\x11"
+ "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69"
+ "\xd7\xdb\x80\xa7\x70\x92\x68\xce"
+ "\x81\x04\x2c\xc6\xab\xae\xe5\x60"
+ "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7"
+ "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea"
+ "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f"
+ "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9"
+ "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e"
+ "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13"
+ "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8"
+ "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a"
+ "\x56\x65\xc5\x54\x23\x28\xb0\x03",
+ .input = "\x9e\x16\xab\xed\x4b\xa7\x42\x5a"
+ "\xc6\xfb\x4e\x76\xff\xbe\x03\xa0"
+ "\x0f\xe3\xad\xba\xe4\x98\x2b\x0e"
+ "\x21\x48\xa0\xb8\x65\x48\x27\x48"
+ "\x84\x54\x54\xb2\x9a\x94\x7b\xe6"
+ "\x4b\x29\xe9\xcf\x05\x91\x80\x1a"
+ "\x3a\xf3\x41\x96\x85\x1d\x9f\x74"
+ "\x51\x56\x63\xfa\x7c\x28\x85\x49"
+ "\xf7\x2f\xf9\xf2\x18\x46\xf5\x33"
+ "\x80\xa3\x3c\xce\xb2\x57\x93\xf5"
+ "\xae\xbd\xa9\xf5\x7b\x30\xc4\x93"
+ "\x66\xe0\x30\x77\x16\xe4\xa0\x31"
+ "\xba\x70\xbc\x68\x13\xf5\xb0\x9a"
+ "\xc1\xfc\x7e\xfe\x55\x80\x5c\x48"
+ "\x74\xa6\xaa\xa3\xac\xdc\xc2\xf5"
+ "\x8d\xde\x34\x86\x78\x60\x75\x8d",
+ .ilen = 128,
+ .rlen = 128,
+ .also_non_np = 1,
+ .np = 4,
+ .tap = { 104, 16, 4, 4 },
+ }, {
+ .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a"
+ "\x25\x74\x29\x0d\x51\x8a\x0e\x13"
+ "\xc1\x53\x5d\x30\x8d\xee\x75\x0d"
+ "\x14\xd6\x69\xc9\x15\xa9\x0c\x60",
+ .klen = 32,
+ .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4"
+ "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2"
+ "\x62\x81\x97\xc5\x81\xaa\xf9\x44"
+ "\xc1\x72\x59\x82\xaf\x16\xc8\x2c",
+ .result = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09"
+ "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5"
+ "\x05\xa3\x69\x60\x91\x36\x98\x57"
+ "\xba\x0c\x14\xcc\xf3\x2d\x73\x03"
+ "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d"
+ "\xd0\x0b\x87\xb2\x50\x94\x7b\x58"
+ "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9"
+ "\x41\x84\xc1\xb1\x7e\x4b\x91\x12"
+ "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9"
+ "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4"
+ "\xa5\x20\x98\xef\xb5\xda\xe5\xc0"
+ "\x8a\x6a\x83\x77\x15\x84\x1e\xae"
+ "\x78\x94\x9d\xdf\xb7\xd1\xea\x67"
+ "\xaa\xb0\x14\x15\xfa\x67\x21\x84"
+ "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8"
+ "\x95\x62\xa9\x55\xf0\x80\xad\xbd"
+ "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36"
+ "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0"
+ "\x88\x4e\xec\x2c\x88\x10\x5e\xea"
+ "\x12\xc0\x16\x01\x29\xa3\xa0\x55"
+ "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b"
+ "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d"
+ "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3"
+ "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e"
+ "\x9c\xac\xdb\x90\xbd\x83\x72\xba"
+ "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf"
+ "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5"
+ "\x1e\x19\x38\x09\x16\xd2\x82\x1f"
+ "\x75\x18\x56\xb8\x96\x0b\xa6\xf9"
+ "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d"
+ "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee"
+ "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d"
+ "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25"
+ "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30"
+ "\xae\x23\x4f\x0e\x13\x66\x4f\xe1"
+ "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e"
+ "\x15\x85\x6b\xe3\x60\x81\x1d\x68"
+ "\xd7\x31\x87\x89\x09\xab\xd5\x96"
+ "\x1d\xf3\x6d\x67\x80\xca\x07\x31"
+ "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33"
+ "\x52\x18\xc8\x30\xfe\x2d\xca\x1e"
+ "\x79\x92\x7a\x60\x5c\xb6\x58\x87"
+ "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7"
+ "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63"
+ "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96"
+ "\x47\xca\xb8\x91\xf9\xf7\x94\x21"
+ "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b"
+ "\x66\x69\x6a\x72\xd0\xcb\x70\xb7"
+ "\x93\xb5\x37\x96\x05\x37\x4f\xe5"
+ "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea"
+ "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac"
+ "\x18\x7d\x52\x3b\xb3\x34\x62\x99"
+ "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84"
+ "\x17\x7c\x25\x48\x52\x67\x11\x27"
+ "\x67\xbb\x5a\x85\xca\x56\xb2\x5c"
+ "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb"
+ "\x22\x25\xf4\x13\xe5\x93\x4b\x9a"
+ "\x77\xf1\x52\x18\xfa\x16\x5e\x49"
+ "\x03\x45\xa8\x08\xfa\xb3\x41\x92"
+ "\x79\x50\x33\xca\xd0\xd7\x42\x55"
+ "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86"
+ "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc"
+ "\xf1\x54\x6e\x93\xa4\x65\x99\x8e"
+ "\xdf\x29\xc0\x64\x63\x07\xbb\xea",
+ .input = "\x15\x97\xd0\x86\x18\x03\x9c\x51"
+ "\xc5\x11\x36\x62\x13\x92\xe6\x73"
+ "\x29\x79\xde\xa1\x00\x3e\x08\x64"
+ "\x17\x1a\xbc\xd5\xfe\x33\x0e\x0c"
+ "\x7c\x94\xa7\xc6\x3c\xbe\xac\xa2"
+ "\x89\xe6\xbc\xdf\x0c\x33\x27\x42"
+ "\x46\x73\x2f\xba\x4e\xa6\x46\x8f"
+ "\xe4\xee\x39\x63\x42\x65\xa3\x88"
+ "\x7a\xad\x33\x23\xa9\xa7\x20\x7f"
+ "\x0b\xe6\x6a\xc3\x60\xda\x9e\xb4"
+ "\xd6\x07\x8a\x77\x26\xd1\xab\x44"
+ "\x99\x55\x03\x5e\xed\x8d\x7b\xbd"
+ "\xc8\x21\xb7\x21\x30\x3f\xc0\xb5"
+ "\xc8\xec\x6c\x23\xa6\xa3\x6d\xf1"
+ "\x30\x0a\xd0\xa6\xa9\x28\x69\xae"
+ "\x2a\xe6\x54\xac\x82\x9d\x6a\x95"
+ "\x6f\x06\x44\xc5\x5a\x77\x6e\xec"
+ "\xf8\xf8\x63\xb2\xe6\xaa\xbd\x8e"
+ "\x0e\x8a\x62\x00\x03\xc8\x84\xdd"
+ "\x47\x4a\xc3\x55\xba\xb7\xe7\xdf"
+ "\x08\xbf\x62\xf5\xe8\xbc\xb6\x11"
+ "\xe4\xcb\xd0\x66\x74\x32\xcf\xd4"
+ "\xf8\x51\x80\x39\x14\x05\x12\xdb"
+ "\x87\x93\xe2\x26\x30\x9c\x3a\x21"
+ "\xe5\xd0\x38\x57\x80\x15\xe4\x08"
+ "\x58\x05\x49\x7d\xe6\x92\x77\x70"
+ "\xfb\x1e\x2d\x6a\x84\x00\xc8\x68"
+ "\xf7\x1a\xdd\xf0\x7b\x38\x1e\xd8"
+ "\x2c\x78\x78\x61\xcf\xe3\xde\x69"
+ "\x1f\xd5\x03\xd5\x1a\xb4\xcf\x03"
+ "\xc8\x7a\x70\x68\x35\xb4\xf6\xbe"
+ "\x90\x62\xb2\x28\x99\x86\xf5\x44"
+ "\x99\xeb\x31\xcf\xca\xdf\xd0\x21"
+ "\xd6\x60\xf7\x0f\x40\xb4\x80\xb7"
+ "\xab\xe1\x9b\x45\xba\x66\xda\xee"
+ "\xdd\x04\x12\x40\x98\xe1\x69\xe5"
+ "\x2b\x9c\x59\x80\xe7\x7b\xcc\x63"
+ "\xa6\xc0\x3a\xa9\xfe\x8a\xf9\x62"
+ "\x11\x34\x61\x94\x35\xfe\xf2\x99"
+ "\xfd\xee\x19\xea\x95\xb6\x12\xbf"
+ "\x1b\xdf\x02\x1a\xcc\x3e\x7e\x65"
+ "\x78\x74\x10\x50\x29\x63\x28\xea"
+ "\x6b\xab\xd4\x06\x4d\x15\x24\x31"
+ "\xc7\x0a\xc9\x16\xb6\x48\xf0\xbf"
+ "\x49\xdb\x68\x71\x31\x8f\x87\xe2"
+ "\x13\x05\x64\xd6\x22\x0c\xf8\x36"
+ "\x84\x24\x3e\x69\x5e\xb8\x9e\x16"
+ "\x73\x6c\x83\x1e\xe0\x9f\x9e\xba"
+ "\xe5\x59\x21\x33\x1b\xa9\x26\xc2"
+ "\xc7\xd9\x30\x73\xb6\xa6\x73\x82"
+ "\x19\xfa\x44\x4d\x40\x8b\x69\x04"
+ "\x94\x74\xea\x6e\xb3\x09\x47\x01"
+ "\x2a\xb9\x78\x34\x43\x11\xed\xd6"
+ "\x8c\x95\x65\x1b\x85\x67\xa5\x40"
+ "\xac\x9c\x05\x4b\x57\x4a\xa9\x96"
+ "\x0f\xdd\x4f\xa1\xe0\xcf\x6e\xc7"
+ "\x1b\xed\xa2\xb4\x56\x8c\x09\x6e"
+ "\xa6\x65\xd7\x55\x81\xb7\xed\x11"
+ "\x9b\x40\x75\xa8\x6b\x56\xaf\x16"
+ "\x8b\x3d\xf4\xcb\xfe\xd5\x1d\x3d"
+ "\x85\xc2\xc0\xde\x43\x39\x4a\x96"
+ "\xba\x88\x97\xc0\xd6\x00\x0e\x27"
+ "\x21\xb0\x21\x52\xba\xa7\x37\xaa"
+ "\xcc\xbf\x95\xa8\xf4\xd0\x91\xf6",
+ .ilen = 512,
+ .rlen = 512,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 144, 368 },
+ }
+};
+
+/* Adiantum with XChaCha20 instead of XChaCha12 */
+/* Test vectors from https://github.com/google/adiantum */
+static struct cipher_testvec adiantum_xchacha20_aes_enc_tv_template[] = {
+ {
+ .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4"
+ "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd"
+ "\x75\x20\x57\xea\x2c\x4f\xcd\xb2"
+ "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f",
+ .klen = 32,
+ .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8"
+ "\x33\x81\x37\x60\x7d\xfa\x73\x08"
+ "\xd8\x49\x6d\x80\xe8\x2f\x62\x54"
+ "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a",
+ .input = "\x67\xc9\xf2\x30\x84\x41\x8e\x43"
+ "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8",
+ .result = "\xf6\x78\x97\xd6\xaa\x94\x01\x27"
+ "\x2e\x4d\x83\xe0\x6e\x64\x9a\xdf",
+ .ilen = 16,
+ .rlen = 16,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 5, 2, 9 },
+ }, {
+ .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99"
+ "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27"
+ "\xcc\x16\xd7\x2b\x85\x63\x99\xd3"
+ "\xba\x96\xa1\xdb\xd2\x60\x68\xda",
+ .klen = 32,
+ .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47"
+ "\x24\xc1\xb1\x69\xe1\x12\x93\x8f"
+ "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9"
+ "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4",
+ .input = "\x5e\xa8\x68\x19\x85\x98\x12\x23"
+ "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf"
+ "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19"
+ "\x43\x5a\x46\x06\x94\x2d\xf2",
+ .result = "\x4b\xb8\x90\x10\xdf\x7f\x64\x08"
+ "\x0e\x14\x42\x5f\x00\x74\x09\x36"
+ "\x57\x72\xb5\xfd\xb5\x5d\xb8\x28"
+ "\x0c\x04\x91\x14\x91\xe9\x37",
+ .ilen = 31,
+ .rlen = 31,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 16, 15 },
+ }, {
+ .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7"
+ "\x05\x91\x8f\xee\x85\x1f\x35\x7f"
+ "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e"
+ "\x19\x09\x00\xa9\x04\x31\x4f\x11",
+ .klen = 32,
+ .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8"
+ "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb"
+ "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62"
+ "\xac\xa9\x8c\x41\x42\x94\x75\xb7",
+ .input = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82"
+ "\xf1\xec\x5d\x04\xe5\x14\x91\x13"
+ "\xdf\xf2\x87\x1b\x69\x81\x1d\x71"
+ "\x70\x9e\x9c\x3b\xde\x49\x70\x11"
+ "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69"
+ "\xd7\xdb\x80\xa7\x70\x92\x68\xce"
+ "\x81\x04\x2c\xc6\xab\xae\xe5\x60"
+ "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7"
+ "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea"
+ "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f"
+ "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9"
+ "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e"
+ "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13"
+ "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8"
+ "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a"
+ "\x56\x65\xc5\x54\x23\x28\xb0\x03",
+ .result = "\xb1\x8b\xa0\x05\x77\xa8\x4d\x59"
+ "\x1b\x8e\x21\xfc\x3a\x49\xfa\xd4"
+ "\xeb\x36\xf3\xc4\xdf\xdc\xae\x67"
+ "\x07\x3f\x70\x0e\xe9\x66\xf5\x0c"
+ "\x30\x4d\x66\xc9\xa4\x2f\x73\x9c"
+ "\x13\xc8\x49\x44\xcc\x0a\x90\x9d"
+ "\x7c\xdd\x19\x3f\xea\x72\x8d\x58"
+ "\xab\xe7\x09\x2c\xec\xb5\x44\xd2"
+ "\xca\xa6\x2d\x7a\x5c\x9c\x2b\x15"
+ "\xec\x2a\xa6\x69\x91\xf9\xf3\x13"
+ "\xf7\x72\xc1\xc1\x40\xd5\xe1\x94"
+ "\xf4\x29\xa1\x3e\x25\x02\xa8\x3e"
+ "\x94\xc1\x91\x14\xa1\x14\xcb\xbe"
+ "\x67\x4c\xb9\x38\xfe\xa7\xaa\x32"
+ "\x29\x62\x0d\xb2\xf6\x3c\x58\x57"
+ "\xc1\xd5\x5a\xbb\xd6\xa6\x2a\xe5",
+ .ilen = 128,
+ .rlen = 128,
+ .also_non_np = 1,
+ .np = 4,
+ .tap = { 112, 7, 8, 1 },
+ }, {
+ .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a"
+ "\x25\x74\x29\x0d\x51\x8a\x0e\x13"
+ "\xc1\x53\x5d\x30\x8d\xee\x75\x0d"
+ "\x14\xd6\x69\xc9\x15\xa9\x0c\x60",
+ .klen = 32,
+ .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4"
+ "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2"
+ "\x62\x81\x97\xc5\x81\xaa\xf9\x44"
+ "\xc1\x72\x59\x82\xaf\x16\xc8\x2c",
+ .input = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09"
+ "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5"
+ "\x05\xa3\x69\x60\x91\x36\x98\x57"
+ "\xba\x0c\x14\xcc\xf3\x2d\x73\x03"
+ "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d"
+ "\xd0\x0b\x87\xb2\x50\x94\x7b\x58"
+ "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9"
+ "\x41\x84\xc1\xb1\x7e\x4b\x91\x12"
+ "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9"
+ "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4"
+ "\xa5\x20\x98\xef\xb5\xda\xe5\xc0"
+ "\x8a\x6a\x83\x77\x15\x84\x1e\xae"
+ "\x78\x94\x9d\xdf\xb7\xd1\xea\x67"
+ "\xaa\xb0\x14\x15\xfa\x67\x21\x84"
+ "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8"
+ "\x95\x62\xa9\x55\xf0\x80\xad\xbd"
+ "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36"
+ "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0"
+ "\x88\x4e\xec\x2c\x88\x10\x5e\xea"
+ "\x12\xc0\x16\x01\x29\xa3\xa0\x55"
+ "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b"
+ "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d"
+ "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3"
+ "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e"
+ "\x9c\xac\xdb\x90\xbd\x83\x72\xba"
+ "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf"
+ "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5"
+ "\x1e\x19\x38\x09\x16\xd2\x82\x1f"
+ "\x75\x18\x56\xb8\x96\x0b\xa6\xf9"
+ "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d"
+ "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee"
+ "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d"
+ "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25"
+ "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30"
+ "\xae\x23\x4f\x0e\x13\x66\x4f\xe1"
+ "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e"
+ "\x15\x85\x6b\xe3\x60\x81\x1d\x68"
+ "\xd7\x31\x87\x89\x09\xab\xd5\x96"
+ "\x1d\xf3\x6d\x67\x80\xca\x07\x31"
+ "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33"
+ "\x52\x18\xc8\x30\xfe\x2d\xca\x1e"
+ "\x79\x92\x7a\x60\x5c\xb6\x58\x87"
+ "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7"
+ "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63"
+ "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96"
+ "\x47\xca\xb8\x91\xf9\xf7\x94\x21"
+ "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b"
+ "\x66\x69\x6a\x72\xd0\xcb\x70\xb7"
+ "\x93\xb5\x37\x96\x05\x37\x4f\xe5"
+ "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea"
+ "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac"
+ "\x18\x7d\x52\x3b\xb3\x34\x62\x99"
+ "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84"
+ "\x17\x7c\x25\x48\x52\x67\x11\x27"
+ "\x67\xbb\x5a\x85\xca\x56\xb2\x5c"
+ "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb"
+ "\x22\x25\xf4\x13\xe5\x93\x4b\x9a"
+ "\x77\xf1\x52\x18\xfa\x16\x5e\x49"
+ "\x03\x45\xa8\x08\xfa\xb3\x41\x92"
+ "\x79\x50\x33\xca\xd0\xd7\x42\x55"
+ "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86"
+ "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc"
+ "\xf1\x54\x6e\x93\xa4\x65\x99\x8e"
+ "\xdf\x29\xc0\x64\x63\x07\xbb\xea",
+ .result = "\xe0\x33\xf6\xe0\xb4\xa5\xdd\x2b"
+ "\xdd\xce\xfc\x12\x1e\xfc\x2d\xf2"
+ "\x8b\xc7\xeb\xc1\xc4\x2a\xe8\x44"
+ "\x0f\x3d\x97\x19\x2e\x6d\xa2\x38"
+ "\x9d\xa6\xaa\xe1\x96\xb9\x08\xe8"
+ "\x0b\x70\x48\x5c\xed\xb5\x9b\xcb"
+ "\x8b\x40\x88\x7e\x69\x73\xf7\x16"
+ "\x71\xbb\x5b\xfc\xa3\x47\x5d\xa6"
+ "\xae\x3a\x64\xc4\xe7\xb8\xa8\xe7"
+ "\xb1\x32\x19\xdb\xe3\x01\xb8\xf0"
+ "\xa4\x86\xb4\x4c\xc2\xde\x5c\xd2"
+ "\x6c\x77\xd2\xe8\x18\xb7\x0a\xc9"
+ "\x3d\x53\xb5\xc4\x5c\xf0\x8c\x06"
+ "\xdc\x90\xe0\x74\x47\x1b\x0b\xf6"
+ "\xd2\x71\x6b\xc4\xf1\x97\x00\x2d"
+ "\x63\x57\x44\x1f\x8c\xf4\xe6\x9b"
+ "\xe0\x7a\xdd\xec\x32\x73\x42\x32"
+ "\x7f\x35\x67\x60\x0d\xcf\x10\x52"
+ "\x61\x22\x53\x8d\x8e\xbb\x33\x76"
+ "\x59\xd9\x10\xce\xdf\xef\xc0\x41"
+ "\xd5\x33\x29\x6a\xda\x46\xa4\x51"
+ "\xf0\x99\x3d\x96\x31\xdd\xb5\xcb"
+ "\x3e\x2a\x1f\xc7\x5c\x79\xd3\xc5"
+ "\x20\xa1\xb1\x39\x1b\xc6\x0a\x70"
+ "\x26\x39\x95\x07\xad\x7a\xc9\x69"
+ "\xfe\x81\xc7\x88\x08\x38\xaf\xad"
+ "\x9e\x8d\xfb\xe8\x24\x0d\x22\xb8"
+ "\x0e\xed\xbe\x37\x53\x7c\xa6\xc6"
+ "\x78\x62\xec\xa3\x59\xd9\xc6\x9d"
+ "\xb8\x0e\x69\x77\x84\x2d\x6a\x4c"
+ "\xc5\xd9\xb2\xa0\x2b\xa8\x80\xcc"
+ "\xe9\x1e\x9c\x5a\xc4\xa1\xb2\x37"
+ "\x06\x9b\x30\x32\x67\xf7\xe7\xd2"
+ "\x42\xc7\xdf\x4e\xd4\xcb\xa0\x12"
+ "\x94\xa1\x34\x85\x93\x50\x4b\x0a"
+ "\x3c\x7d\x49\x25\x01\x41\x6b\x96"
+ "\xa9\x12\xbb\x0b\xc0\xd7\xd0\x93"
+ "\x1f\x70\x38\xb8\x21\xee\xf6\xa7"
+ "\xee\xeb\xe7\x81\xa4\x13\xb4\x87"
+ "\xfa\xc1\xb0\xb5\x37\x8b\x74\xa2"
+ "\x4e\xc7\xc2\xad\x3d\x62\x3f\xf8"
+ "\x34\x42\xe5\xae\x45\x13\x63\xfe"
+ "\xfc\x2a\x17\x46\x61\xa9\xd3\x1c"
+ "\x4c\xaf\xf0\x09\x62\x26\x66\x1e"
+ "\x74\xcf\xd6\x68\x3d\x7d\xd8\xb7"
+ "\xe7\xe6\xf8\xf0\x08\x20\xf7\x47"
+ "\x1c\x52\xaa\x0f\x3e\x21\xa3\xf2"
+ "\xbf\x2f\x95\x16\xa8\xc8\xc8\x8c"
+ "\x99\x0f\x5d\xfb\xfa\x2b\x58\x8a"
+ "\x7e\xd6\x74\x02\x60\xf0\xd0\x5b"
+ "\x65\xa8\xac\xea\x8d\x68\x46\x34"
+ "\x26\x9d\x4f\xb1\x9a\x8e\xc0\x1a"
+ "\xf1\xed\xc6\x7a\x83\xfd\x8a\x57"
+ "\xf2\xe6\xe4\xba\xfc\xc6\x3c\xad"
+ "\x5b\x19\x50\x2f\x3a\xcc\x06\x46"
+ "\x04\x51\x3f\x91\x97\xf0\xd2\x07"
+ "\xe7\x93\x89\x7e\xb5\x32\x0f\x03"
+ "\xe5\x58\x9e\x74\x72\xeb\xc2\x38"
+ "\x00\x0c\x91\x72\x69\xed\x7d\x6d"
+ "\xc8\x71\xf0\xec\xff\x80\xd9\x1c"
+ "\x9e\xd2\xfa\x15\xfc\x6c\x4e\xbc"
+ "\xb1\xa6\xbd\xbd\x70\x40\xca\x20"
+ "\xb8\x78\xd2\xa3\xc6\xf3\x79\x9c"
+ "\xc7\x27\xe1\x6a\x29\xad\xa4\x03",
+ .ilen = 512,
+ .rlen = 512,
+ }
+};
+
+static struct cipher_testvec adiantum_xchacha20_aes_dec_tv_template[] = {
+ {
+ .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4"
+ "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd"
+ "\x75\x20\x57\xea\x2c\x4f\xcd\xb2"
+ "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f",
+ .klen = 32,
+ .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8"
+ "\x33\x81\x37\x60\x7d\xfa\x73\x08"
+ "\xd8\x49\x6d\x80\xe8\x2f\x62\x54"
+ "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a",
+ .result = "\x67\xc9\xf2\x30\x84\x41\x8e\x43"
+ "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8",
+ .input = "\xf6\x78\x97\xd6\xaa\x94\x01\x27"
+ "\x2e\x4d\x83\xe0\x6e\x64\x9a\xdf",
+ .ilen = 16,
+ .rlen = 16,
+ .also_non_np = 1,
+ .np = 3,
+ .tap = { 5, 2, 9 },
+ }, {
+ .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99"
+ "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27"
+ "\xcc\x16\xd7\x2b\x85\x63\x99\xd3"
+ "\xba\x96\xa1\xdb\xd2\x60\x68\xda",
+ .klen = 32,
+ .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47"
+ "\x24\xc1\xb1\x69\xe1\x12\x93\x8f"
+ "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9"
+ "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4",
+ .result = "\x5e\xa8\x68\x19\x85\x98\x12\x23"
+ "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf"
+ "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19"
+ "\x43\x5a\x46\x06\x94\x2d\xf2",
+ .input = "\x4b\xb8\x90\x10\xdf\x7f\x64\x08"
+ "\x0e\x14\x42\x5f\x00\x74\x09\x36"
+ "\x57\x72\xb5\xfd\xb5\x5d\xb8\x28"
+ "\x0c\x04\x91\x14\x91\xe9\x37",
+ .ilen = 31,
+ .rlen = 31,
+ .also_non_np = 1,
+ .np = 2,
+ .tap = { 16, 15 },
+ }, {
+ .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7"
+ "\x05\x91\x8f\xee\x85\x1f\x35\x7f"
+ "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e"
+ "\x19\x09\x00\xa9\x04\x31\x4f\x11",
+ .klen = 32,
+ .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8"
+ "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb"
+ "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62"
+ "\xac\xa9\x8c\x41\x42\x94\x75\xb7",
+ .result = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82"
+ "\xf1\xec\x5d\x04\xe5\x14\x91\x13"
+ "\xdf\xf2\x87\x1b\x69\x81\x1d\x71"
+ "\x70\x9e\x9c\x3b\xde\x49\x70\x11"
+ "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69"
+ "\xd7\xdb\x80\xa7\x70\x92\x68\xce"
+ "\x81\x04\x2c\xc6\xab\xae\xe5\x60"
+ "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7"
+ "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea"
+ "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f"
+ "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9"
+ "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e"
+ "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13"
+ "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8"
+ "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a"
+ "\x56\x65\xc5\x54\x23\x28\xb0\x03",
+ .input = "\xb1\x8b\xa0\x05\x77\xa8\x4d\x59"
+ "\x1b\x8e\x21\xfc\x3a\x49\xfa\xd4"
+ "\xeb\x36\xf3\xc4\xdf\xdc\xae\x67"
+ "\x07\x3f\x70\x0e\xe9\x66\xf5\x0c"
+ "\x30\x4d\x66\xc9\xa4\x2f\x73\x9c"
+ "\x13\xc8\x49\x44\xcc\x0a\x90\x9d"
+ "\x7c\xdd\x19\x3f\xea\x72\x8d\x58"
+ "\xab\xe7\x09\x2c\xec\xb5\x44\xd2"
+ "\xca\xa6\x2d\x7a\x5c\x9c\x2b\x15"
+ "\xec\x2a\xa6\x69\x91\xf9\xf3\x13"
+ "\xf7\x72\xc1\xc1\x40\xd5\xe1\x94"
+ "\xf4\x29\xa1\x3e\x25\x02\xa8\x3e"
+ "\x94\xc1\x91\x14\xa1\x14\xcb\xbe"
+ "\x67\x4c\xb9\x38\xfe\xa7\xaa\x32"
+ "\x29\x62\x0d\xb2\xf6\x3c\x58\x57"
+ "\xc1\xd5\x5a\xbb\xd6\xa6\x2a\xe5",
+ .ilen = 128,
+ .rlen = 128,
+ .also_non_np = 1,
+ .np = 4,
+ .tap = { 112, 7, 8, 1 },
+ }, {
+ .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a"
+ "\x25\x74\x29\x0d\x51\x8a\x0e\x13"
+ "\xc1\x53\x5d\x30\x8d\xee\x75\x0d"
+ "\x14\xd6\x69\xc9\x15\xa9\x0c\x60",
+ .klen = 32,
+ .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4"
+ "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2"
+ "\x62\x81\x97\xc5\x81\xaa\xf9\x44"
+ "\xc1\x72\x59\x82\xaf\x16\xc8\x2c",
+ .result = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09"
+ "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5"
+ "\x05\xa3\x69\x60\x91\x36\x98\x57"
+ "\xba\x0c\x14\xcc\xf3\x2d\x73\x03"
+ "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d"
+ "\xd0\x0b\x87\xb2\x50\x94\x7b\x58"
+ "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9"
+ "\x41\x84\xc1\xb1\x7e\x4b\x91\x12"
+ "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9"
+ "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4"
+ "\xa5\x20\x98\xef\xb5\xda\xe5\xc0"
+ "\x8a\x6a\x83\x77\x15\x84\x1e\xae"
+ "\x78\x94\x9d\xdf\xb7\xd1\xea\x67"
+ "\xaa\xb0\x14\x15\xfa\x67\x21\x84"
+ "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8"
+ "\x95\x62\xa9\x55\xf0\x80\xad\xbd"
+ "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36"
+ "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0"
+ "\x88\x4e\xec\x2c\x88\x10\x5e\xea"
+ "\x12\xc0\x16\x01\x29\xa3\xa0\x55"
+ "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b"
+ "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d"
+ "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3"
+ "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e"
+ "\x9c\xac\xdb\x90\xbd\x83\x72\xba"
+ "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf"
+ "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5"
+ "\x1e\x19\x38\x09\x16\xd2\x82\x1f"
+ "\x75\x18\x56\xb8\x96\x0b\xa6\xf9"
+ "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d"
+ "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee"
+ "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d"
+ "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25"
+ "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30"
+ "\xae\x23\x4f\x0e\x13\x66\x4f\xe1"
+ "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e"
+ "\x15\x85\x6b\xe3\x60\x81\x1d\x68"
+ "\xd7\x31\x87\x89\x09\xab\xd5\x96"
+ "\x1d\xf3\x6d\x67\x80\xca\x07\x31"
+ "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33"
+ "\x52\x18\xc8\x30\xfe\x2d\xca\x1e"
+ "\x79\x92\x7a\x60\x5c\xb6\x58\x87"
+ "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7"
+ "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63"
+ "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96"
+ "\x47\xca\xb8\x91\xf9\xf7\x94\x21"
+ "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b"
+ "\x66\x69\x6a\x72\xd0\xcb\x70\xb7"
+ "\x93\xb5\x37\x96\x05\x37\x4f\xe5"
+ "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea"
+ "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac"
+ "\x18\x7d\x52\x3b\xb3\x34\x62\x99"
+ "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84"
+ "\x17\x7c\x25\x48\x52\x67\x11\x27"
+ "\x67\xbb\x5a\x85\xca\x56\xb2\x5c"
+ "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb"
+ "\x22\x25\xf4\x13\xe5\x93\x4b\x9a"
+ "\x77\xf1\x52\x18\xfa\x16\x5e\x49"
+ "\x03\x45\xa8\x08\xfa\xb3\x41\x92"
+ "\x79\x50\x33\xca\xd0\xd7\x42\x55"
+ "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86"
+ "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc"
+ "\xf1\x54\x6e\x93\xa4\x65\x99\x8e"
+ "\xdf\x29\xc0\x64\x63\x07\xbb\xea",
+ .input = "\xe0\x33\xf6\xe0\xb4\xa5\xdd\x2b"
+ "\xdd\xce\xfc\x12\x1e\xfc\x2d\xf2"
+ "\x8b\xc7\xeb\xc1\xc4\x2a\xe8\x44"
+ "\x0f\x3d\x97\x19\x2e\x6d\xa2\x38"
+ "\x9d\xa6\xaa\xe1\x96\xb9\x08\xe8"
+ "\x0b\x70\x48\x5c\xed\xb5\x9b\xcb"
+ "\x8b\x40\x88\x7e\x69\x73\xf7\x16"
+ "\x71\xbb\x5b\xfc\xa3\x47\x5d\xa6"
+ "\xae\x3a\x64\xc4\xe7\xb8\xa8\xe7"
+ "\xb1\x32\x19\xdb\xe3\x01\xb8\xf0"
+ "\xa4\x86\xb4\x4c\xc2\xde\x5c\xd2"
+ "\x6c\x77\xd2\xe8\x18\xb7\x0a\xc9"
+ "\x3d\x53\xb5\xc4\x5c\xf0\x8c\x06"
+ "\xdc\x90\xe0\x74\x47\x1b\x0b\xf6"
+ "\xd2\x71\x6b\xc4\xf1\x97\x00\x2d"
+ "\x63\x57\x44\x1f\x8c\xf4\xe6\x9b"
+ "\xe0\x7a\xdd\xec\x32\x73\x42\x32"
+ "\x7f\x35\x67\x60\x0d\xcf\x10\x52"
+ "\x61\x22\x53\x8d\x8e\xbb\x33\x76"
+ "\x59\xd9\x10\xce\xdf\xef\xc0\x41"
+ "\xd5\x33\x29\x6a\xda\x46\xa4\x51"
+ "\xf0\x99\x3d\x96\x31\xdd\xb5\xcb"
+ "\x3e\x2a\x1f\xc7\x5c\x79\xd3\xc5"
+ "\x20\xa1\xb1\x39\x1b\xc6\x0a\x70"
+ "\x26\x39\x95\x07\xad\x7a\xc9\x69"
+ "\xfe\x81\xc7\x88\x08\x38\xaf\xad"
+ "\x9e\x8d\xfb\xe8\x24\x0d\x22\xb8"
+ "\x0e\xed\xbe\x37\x53\x7c\xa6\xc6"
+ "\x78\x62\xec\xa3\x59\xd9\xc6\x9d"
+ "\xb8\x0e\x69\x77\x84\x2d\x6a\x4c"
+ "\xc5\xd9\xb2\xa0\x2b\xa8\x80\xcc"
+ "\xe9\x1e\x9c\x5a\xc4\xa1\xb2\x37"
+ "\x06\x9b\x30\x32\x67\xf7\xe7\xd2"
+ "\x42\xc7\xdf\x4e\xd4\xcb\xa0\x12"
+ "\x94\xa1\x34\x85\x93\x50\x4b\x0a"
+ "\x3c\x7d\x49\x25\x01\x41\x6b\x96"
+ "\xa9\x12\xbb\x0b\xc0\xd7\xd0\x93"
+ "\x1f\x70\x38\xb8\x21\xee\xf6\xa7"
+ "\xee\xeb\xe7\x81\xa4\x13\xb4\x87"
+ "\xfa\xc1\xb0\xb5\x37\x8b\x74\xa2"
+ "\x4e\xc7\xc2\xad\x3d\x62\x3f\xf8"
+ "\x34\x42\xe5\xae\x45\x13\x63\xfe"
+ "\xfc\x2a\x17\x46\x61\xa9\xd3\x1c"
+ "\x4c\xaf\xf0\x09\x62\x26\x66\x1e"
+ "\x74\xcf\xd6\x68\x3d\x7d\xd8\xb7"
+ "\xe7\xe6\xf8\xf0\x08\x20\xf7\x47"
+ "\x1c\x52\xaa\x0f\x3e\x21\xa3\xf2"
+ "\xbf\x2f\x95\x16\xa8\xc8\xc8\x8c"
+ "\x99\x0f\x5d\xfb\xfa\x2b\x58\x8a"
+ "\x7e\xd6\x74\x02\x60\xf0\xd0\x5b"
+ "\x65\xa8\xac\xea\x8d\x68\x46\x34"
+ "\x26\x9d\x4f\xb1\x9a\x8e\xc0\x1a"
+ "\xf1\xed\xc6\x7a\x83\xfd\x8a\x57"
+ "\xf2\xe6\xe4\xba\xfc\xc6\x3c\xad"
+ "\x5b\x19\x50\x2f\x3a\xcc\x06\x46"
+ "\x04\x51\x3f\x91\x97\xf0\xd2\x07"
+ "\xe7\x93\x89\x7e\xb5\x32\x0f\x03"
+ "\xe5\x58\x9e\x74\x72\xeb\xc2\x38"
+ "\x00\x0c\x91\x72\x69\xed\x7d\x6d"
+ "\xc8\x71\xf0\xec\xff\x80\xd9\x1c"
+ "\x9e\xd2\xfa\x15\xfc\x6c\x4e\xbc"
+ "\xb1\xa6\xbd\xbd\x70\x40\xca\x20"
+ "\xb8\x78\xd2\xa3\xc6\xf3\x79\x9c"
+ "\xc7\x27\xe1\x6a\x29\xad\xa4\x03",
+ .ilen = 512,
+ .rlen = 512,
+ }
+};
+
/*
* CTS (Cipher Text Stealing) mode tests
*/
@@ -34587,4 +37920,78 @@ static struct comp_testvec lz4hc_decomp_tv_template[] = {
},
};
+#define ZSTD_COMP_TEST_VECTORS 2
+#define ZSTD_DECOMP_TEST_VECTORS 2
+
+static struct comp_testvec zstd_comp_tv_template[] = {
+ {
+ .inlen = 68,
+ .outlen = 39,
+ .input = "The algorithm is zstd. "
+ "The algorithm is zstd. "
+ "The algorithm is zstd.",
+ .output = "\x28\xb5\x2f\xfd\x00\x50\xf5\x00\x00\xb8\x54\x68\x65"
+ "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73"
+ "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01"
+ ,
+ },
+ {
+ .inlen = 244,
+ .outlen = 151,
+ .input = "zstd, short for Zstandard, is a fast lossless "
+ "compression algorithm, targeting real-time "
+ "compression scenarios at zlib-level and better "
+ "compression ratios. The zstd compression library "
+ "provides in-memory compression and decompression "
+ "functions.",
+ .output = "\x28\xb5\x2f\xfd\x00\x50\x75\x04\x00\x42\x4b\x1e\x17"
+ "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32"
+ "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f"
+ "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad"
+ "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60"
+ "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86"
+ "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90"
+ "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64"
+ "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30"
+ "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc"
+ "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e"
+ "\x20\xa9\x0e\x82\xb9\x43\x45\x01",
+ },
+};
+
+static struct comp_testvec zstd_decomp_tv_template[] = {
+ {
+ .inlen = 43,
+ .outlen = 68,
+ .input = "\x28\xb5\x2f\xfd\x04\x50\xf5\x00\x00\xb8\x54\x68\x65"
+ "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73"
+ "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01"
+ "\x6b\xf4\x13\x35",
+ .output = "The algorithm is zstd. "
+ "The algorithm is zstd. "
+ "The algorithm is zstd.",
+ },
+ {
+ .inlen = 155,
+ .outlen = 244,
+ .input = "\x28\xb5\x2f\xfd\x04\x50\x75\x04\x00\x42\x4b\x1e\x17"
+ "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32"
+ "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f"
+ "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad"
+ "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60"
+ "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86"
+ "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90"
+ "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64"
+ "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30"
+ "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc"
+ "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e"
+ "\x20\xa9\x0e\x82\xb9\x43\x45\x01\xaa\x6d\xda\x0d",
+ .output = "zstd, short for Zstandard, is a fast lossless "
+ "compression algorithm, targeting real-time "
+ "compression scenarios at zlib-level and better "
+ "compression ratios. The zstd compression library "
+ "provides in-memory compression and decompression "
+ "functions.",
+ },
+};
#endif /* _CRYPTO_TESTMGR_H */
diff --git a/crypto/zstd.c b/crypto/zstd.c
new file mode 100644
index 0000000..9bfd28f
--- /dev/null
+++ b/crypto/zstd.c
@@ -0,0 +1,209 @@
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2017-present, Facebook, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/vmalloc.h>
+#include <linux/zstd.h>
+
+
+#define ZSTD_DEF_LEVEL 3
+
+struct zstd_ctx {
+ ZSTD_CCtx *cctx;
+ ZSTD_DCtx *dctx;
+ void *cwksp;
+ void *dwksp;
+};
+
+static ZSTD_parameters zstd_params(void)
+{
+ return ZSTD_getParams(ZSTD_DEF_LEVEL, 0, 0);
+}
+
+static int zstd_comp_init(struct zstd_ctx *ctx)
+{
+ int ret = 0;
+ const ZSTD_parameters params = zstd_params();
+ const size_t wksp_size = ZSTD_CCtxWorkspaceBound(params.cParams);
+
+ ctx->cwksp = vzalloc(wksp_size);
+ if (!ctx->cwksp) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ctx->cctx = ZSTD_initCCtx(ctx->cwksp, wksp_size);
+ if (!ctx->cctx) {
+ ret = -EINVAL;
+ goto out_free;
+ }
+out:
+ return ret;
+out_free:
+ vfree(ctx->cwksp);
+ goto out;
+}
+
+static int zstd_decomp_init(struct zstd_ctx *ctx)
+{
+ int ret = 0;
+ const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+
+ ctx->dwksp = vzalloc(wksp_size);
+ if (!ctx->dwksp) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ctx->dctx = ZSTD_initDCtx(ctx->dwksp, wksp_size);
+ if (!ctx->dctx) {
+ ret = -EINVAL;
+ goto out_free;
+ }
+out:
+ return ret;
+out_free:
+ vfree(ctx->dwksp);
+ goto out;
+}
+
+static void zstd_comp_exit(struct zstd_ctx *ctx)
+{
+ vfree(ctx->cwksp);
+ ctx->cwksp = NULL;
+ ctx->cctx = NULL;
+}
+
+static void zstd_decomp_exit(struct zstd_ctx *ctx)
+{
+ vfree(ctx->dwksp);
+ ctx->dwksp = NULL;
+ ctx->dctx = NULL;
+}
+
+static int __zstd_init(void *ctx)
+{
+ int ret;
+
+ ret = zstd_comp_init(ctx);
+ if (ret)
+ return ret;
+ ret = zstd_decomp_init(ctx);
+ if (ret)
+ zstd_comp_exit(ctx);
+ return ret;
+}
+
+static int zstd_init(struct crypto_tfm *tfm)
+{
+ struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return __zstd_init(ctx);
+}
+
+static void __zstd_exit(void *ctx)
+{
+ zstd_comp_exit(ctx);
+ zstd_decomp_exit(ctx);
+}
+
+static void zstd_exit(struct crypto_tfm *tfm)
+{
+ struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ __zstd_exit(ctx);
+}
+
+static int __zstd_compress(const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ size_t out_len;
+ struct zstd_ctx *zctx = ctx;
+ const ZSTD_parameters params = zstd_params();
+
+ out_len = ZSTD_compressCCtx(zctx->cctx, dst, *dlen, src, slen, params);
+ if (ZSTD_isError(out_len))
+ return -EINVAL;
+ *dlen = out_len;
+ return 0;
+}
+
+static int zstd_compress(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return __zstd_compress(src, slen, dst, dlen, ctx);
+}
+
+static int __zstd_decompress(const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ size_t out_len;
+ struct zstd_ctx *zctx = ctx;
+
+ out_len = ZSTD_decompressDCtx(zctx->dctx, dst, *dlen, src, slen);
+ if (ZSTD_isError(out_len))
+ return -EINVAL;
+ *dlen = out_len;
+ return 0;
+}
+
+static int zstd_decompress(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return __zstd_decompress(src, slen, dst, dlen, ctx);
+}
+
+static struct crypto_alg alg = {
+ .cra_name = "zstd",
+ .cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+ .cra_ctxsize = sizeof(struct zstd_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_init = zstd_init,
+ .cra_exit = zstd_exit,
+ .cra_u = { .compress = {
+ .coa_compress = zstd_compress,
+ .coa_decompress = zstd_decompress } }
+};
+
+static int __init zstd_mod_init(void)
+{
+ int ret;
+
+ ret = crypto_register_alg(&alg);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
+static void __exit zstd_mod_fini(void)
+{
+ crypto_unregister_alg(&alg);
+}
+
+module_init(zstd_mod_init);
+module_exit(zstd_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Zstd Compression Algorithm");
+MODULE_ALIAS_CRYPTO("zstd");
diff --git a/drivers/Kconfig b/drivers/Kconfig
index e1e2066..de581c1 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -202,4 +202,6 @@
source "drivers/fpga/Kconfig"
+source "drivers/tee/Kconfig"
+
endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 7c3d58d..dc932be 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -175,3 +175,4 @@
obj-$(CONFIG_ANDROID) += android/
obj-$(CONFIG_NVMEM) += nvmem/
obj-$(CONFIG_FPGA) += fpga/
+obj-$(CONFIG_TEE) += tee/
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index e19f530..f7c4301 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -556,7 +556,8 @@ static int acpi_button_remove(struct acpi_device *device)
return 0;
}
-static int param_set_lid_init_state(const char *val, struct kernel_param *kp)
+static int param_set_lid_init_state(const char *val,
+ const struct kernel_param *kp)
{
int result = 0;
@@ -574,7 +575,8 @@ static int param_set_lid_init_state(const char *val, struct kernel_param *kp)
return result;
}
-static int param_get_lid_init_state(char *buffer, struct kernel_param *kp)
+static int param_get_lid_init_state(char *buffer,
+ const struct kernel_param *kp)
{
switch (lid_init_state) {
case ACPI_BUTTON_LID_INIT_OPEN:
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 8781b5d..077cd0b 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1883,7 +1883,8 @@ static const struct dev_pm_ops acpi_ec_pm = {
SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume)
};
-static int param_set_event_clearing(const char *val, struct kernel_param *kp)
+static int param_set_event_clearing(const char *val,
+ const struct kernel_param *kp)
{
int result = 0;
@@ -1901,7 +1902,8 @@ static int param_set_event_clearing(const char *val, struct kernel_param *kp)
return result;
}
-static int param_get_event_clearing(char *buffer, struct kernel_param *kp)
+static int param_get_event_clearing(char *buffer,
+ const struct kernel_param *kp)
{
switch (ec_event_clearing) {
case ACPI_EC_EVT_TIMING_STATUS:
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 764786c..a3efff9 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -227,7 +227,8 @@ module_param_cb(trace_method_name, ¶m_ops_trace_method, &trace_method_name,
module_param_cb(trace_debug_layer, ¶m_ops_trace_attrib, &acpi_gbl_trace_dbg_layer, 0644);
module_param_cb(trace_debug_level, ¶m_ops_trace_attrib, &acpi_gbl_trace_dbg_level, 0644);
-static int param_set_trace_state(const char *val, struct kernel_param *kp)
+static int param_set_trace_state(const char *val,
+ const struct kernel_param *kp)
{
acpi_status status;
const char *method = trace_method_name;
@@ -263,7 +264,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp)
return 0;
}
-static int param_get_trace_state(char *buffer, struct kernel_param *kp)
+static int param_get_trace_state(char *buffer, const struct kernel_param *kp)
{
if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED))
return sprintf(buffer, "disable");
@@ -292,7 +293,8 @@ MODULE_PARM_DESC(aml_debug_output,
"To enable/disable the ACPI Debug Object output.");
/* /sys/module/acpi/parameters/acpica_version */
-static int param_get_acpica_version(char *buffer, struct kernel_param *kp)
+static int param_get_acpica_version(char *buffer,
+ const struct kernel_param *kp)
{
int result;
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
index bdfc6c6..63ed9ce 100644
--- a/drivers/android/Kconfig
+++ b/drivers/android/Kconfig
@@ -9,7 +9,7 @@
config ANDROID_BINDER_IPC
bool "Android Binder IPC Driver"
- depends on MMU
+ depends on MMU && !M68K
default n
---help---
Binder is used in Android for both communication between processes,
@@ -19,18 +19,27 @@
Android process, using Binder to identify, invoke and pass arguments
between said processes.
-config ANDROID_BINDER_IPC_32BIT
- bool
- depends on !64BIT && ANDROID_BINDER_IPC
- default y
+config ANDROID_BINDER_DEVICES
+ string "Android Binder devices"
+ depends on ANDROID_BINDER_IPC
+ default "binder,hwbinder,vndbinder"
---help---
- The Binder API has been changed to support both 32 and 64bit
- applications in a mixed environment.
+ Default value for the binder.devices parameter.
- Enable this to support an old 32-bit Android user-space (v4.4 and
- earlier).
+ The binder.devices parameter is a comma-separated list of strings
+ that specifies the names of the binder device nodes that will be
+ created. Each binder device has its own context manager, and is
+ therefore logically separated from the other devices.
- Note that enabling this will break newer Android user-space.
+config ANDROID_BINDER_IPC_SELFTEST
+ bool "Android Binder IPC Driver Selftest"
+ depends on ANDROID_BINDER_IPC
+ ---help---
+ This feature allows binder selftest to run.
+
+ Binder selftest checks the allocation and free of binder buffers
+ exhaustively with combinations of various buffer sizes and
+ alignments.
endif # if ANDROID
diff --git a/drivers/android/Makefile b/drivers/android/Makefile
index 3b7e4b0..a01254c 100644
--- a/drivers/android/Makefile
+++ b/drivers/android/Makefile
@@ -1,3 +1,4 @@
ccflags-y += -I$(src) # needed for trace events
-obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o
+obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o
+obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index f4c0b62..934ea39 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -15,6 +15,40 @@
*
*/
+/*
+ * Locking overview
+ *
+ * There are 3 main spinlocks which must be acquired in the
+ * order shown:
+ *
+ * 1) proc->outer_lock : protects binder_ref
+ * binder_proc_lock() and binder_proc_unlock() are
+ * used to acq/rel.
+ * 2) node->lock : protects most fields of binder_node.
+ * binder_node_lock() and binder_node_unlock() are
+ * used to acq/rel
+ * 3) proc->inner_lock : protects the thread and node lists
+ * (proc->threads, proc->waiting_threads, proc->nodes)
+ * and all todo lists associated with the binder_proc
+ * (proc->todo, thread->todo, proc->delivered_death and
+ * node->async_todo), as well as thread->transaction_stack
+ * binder_inner_proc_lock() and binder_inner_proc_unlock()
+ * are used to acq/rel
+ *
+ * Any lock under procA must never be nested under any lock at the same
+ * level or below on procB.
+ *
+ * Functions that require a lock held on entry indicate which lock
+ * in the suffix of the function name:
+ *
+ * foo_olocked() : requires node->outer_lock
+ * foo_nlocked() : requires node->lock
+ * foo_ilocked() : requires proc->inner_lock
+ * foo_oilocked(): requires proc->outer_lock and proc->inner_lock
+ * foo_nilocked(): requires node->lock and proc->inner_lock
+ * ...
+ */
+
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <asm/cacheflush.h>
@@ -24,7 +58,6 @@
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/miscdevice.h>
-#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
@@ -34,31 +67,27 @@
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include <linux/security.h>
-
-#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
-#define BINDER_IPC_32BIT 1
-#endif
+#include <linux/spinlock.h>
#include <uapi/linux/android/binder.h>
+#include "binder_alloc.h"
#include "binder_trace.h"
-static DEFINE_MUTEX(binder_main_lock);
-static DEFINE_MUTEX(binder_deferred_lock);
-static DEFINE_MUTEX(binder_mmap_lock);
-
-static HLIST_HEAD(binder_procs);
static HLIST_HEAD(binder_deferred_list);
+static DEFINE_MUTEX(binder_deferred_lock);
+
+static HLIST_HEAD(binder_devices);
+static HLIST_HEAD(binder_procs);
+static DEFINE_MUTEX(binder_procs_lock);
+
static HLIST_HEAD(binder_dead_nodes);
+static DEFINE_SPINLOCK(binder_dead_nodes_lock);
static struct dentry *binder_debugfs_dir_entry_root;
static struct dentry *binder_debugfs_dir_entry_proc;
-static struct binder_node *binder_context_mgr_node;
-static kuid_t binder_context_mgr_uid = INVALID_UID;
-static int binder_last_id;
+static atomic_t binder_last_id;
#define BINDER_DEBUG_ENTRY(name) \
static int binder_##name##_open(struct inode *inode, struct file *file) \
@@ -104,22 +133,21 @@ enum {
BINDER_DEBUG_TRANSACTION_COMPLETE = 1U << 10,
BINDER_DEBUG_FREE_BUFFER = 1U << 11,
BINDER_DEBUG_INTERNAL_REFS = 1U << 12,
- BINDER_DEBUG_BUFFER_ALLOC = 1U << 13,
- BINDER_DEBUG_PRIORITY_CAP = 1U << 14,
- BINDER_DEBUG_BUFFER_ALLOC_ASYNC = 1U << 15,
+ BINDER_DEBUG_PRIORITY_CAP = 1U << 13,
+ BINDER_DEBUG_SPINLOCKS = 1U << 14,
};
static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR |
BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION;
-module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO);
+module_param_named(debug_mask, binder_debug_mask, uint, 0644);
-static bool binder_debug_no_lock;
-module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO);
+static char *binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES;
+module_param_named(devices, binder_devices_param, charp, S_IRUGO);
static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait);
static int binder_stop_on_user_error;
static int binder_set_stop_on_user_error(const char *val,
- struct kernel_param *kp)
+ const struct kernel_param *kp)
{
int ret;
@@ -129,7 +157,7 @@ static int binder_set_stop_on_user_error(const char *val,
return ret;
}
module_param_call(stop_on_user_error, binder_set_stop_on_user_error,
- param_get_int, &binder_stop_on_user_error, S_IWUSR | S_IRUGO);
+ param_get_int, &binder_stop_on_user_error, 0644);
#define binder_debug(mask, x...) \
do { \
@@ -145,6 +173,17 @@ module_param_call(stop_on_user_error, binder_set_stop_on_user_error,
binder_stop_on_user_error = 2; \
} while (0)
+#define to_flat_binder_object(hdr) \
+ container_of(hdr, struct flat_binder_object, hdr)
+
+#define to_binder_fd_object(hdr) container_of(hdr, struct binder_fd_object, hdr)
+
+#define to_binder_buffer_object(hdr) \
+ container_of(hdr, struct binder_buffer_object, hdr)
+
+#define to_binder_fd_array_object(hdr) \
+ container_of(hdr, struct binder_fd_array_object, hdr)
+
enum binder_stat_types {
BINDER_STAT_PROC,
BINDER_STAT_THREAD,
@@ -157,26 +196,27 @@ enum binder_stat_types {
};
struct binder_stats {
- int br[_IOC_NR(BR_FAILED_REPLY) + 1];
- int bc[_IOC_NR(BC_DEAD_BINDER_DONE) + 1];
- int obj_created[BINDER_STAT_COUNT];
- int obj_deleted[BINDER_STAT_COUNT];
+ atomic_t br[_IOC_NR(BR_FAILED_REPLY) + 1];
+ atomic_t bc[_IOC_NR(BC_REPLY_SG) + 1];
+ atomic_t obj_created[BINDER_STAT_COUNT];
+ atomic_t obj_deleted[BINDER_STAT_COUNT];
};
static struct binder_stats binder_stats;
static inline void binder_stats_deleted(enum binder_stat_types type)
{
- binder_stats.obj_deleted[type]++;
+ atomic_inc(&binder_stats.obj_deleted[type]);
}
static inline void binder_stats_created(enum binder_stat_types type)
{
- binder_stats.obj_created[type]++;
+ atomic_inc(&binder_stats.obj_created[type]);
}
struct binder_transaction_log_entry {
int debug_id;
+ int debug_id_done;
int call_type;
int from_proc;
int from_thread;
@@ -186,10 +226,14 @@ struct binder_transaction_log_entry {
int to_node;
int data_size;
int offsets_size;
+ int return_error_line;
+ uint32_t return_error;
+ uint32_t return_error_param;
+ const char *context_name;
};
struct binder_transaction_log {
- int next;
- int full;
+ atomic_t cur;
+ bool full;
struct binder_transaction_log_entry entry[32];
};
static struct binder_transaction_log binder_transaction_log;
@@ -199,22 +243,50 @@ static struct binder_transaction_log_entry *binder_transaction_log_add(
struct binder_transaction_log *log)
{
struct binder_transaction_log_entry *e;
+ unsigned int cur = atomic_inc_return(&log->cur);
- e = &log->entry[log->next];
+ if (cur >= ARRAY_SIZE(log->entry))
+ log->full = true;
+ e = &log->entry[cur % ARRAY_SIZE(log->entry)];
+ WRITE_ONCE(e->debug_id_done, 0);
+ /*
+ * write-barrier to synchronize access to e->debug_id_done.
+ * We make sure the initialized 0 value is seen before
+ * memset() other fields are zeroed by memset.
+ */
+ smp_wmb();
memset(e, 0, sizeof(*e));
- log->next++;
- if (log->next == ARRAY_SIZE(log->entry)) {
- log->next = 0;
- log->full = 1;
- }
return e;
}
+struct binder_context {
+ struct binder_node *binder_context_mgr_node;
+ struct mutex context_mgr_node_lock;
+
+ kuid_t binder_context_mgr_uid;
+ const char *name;
+};
+
+struct binder_device {
+ struct hlist_node hlist;
+ struct miscdevice miscdev;
+ struct binder_context context;
+};
+
+/**
+ * struct binder_work - work enqueued on a worklist
+ * @entry: node enqueued on list
+ * @type: type of work to be performed
+ *
+ * There are separate work lists for proc, thread, and node (async).
+ */
struct binder_work {
struct list_head entry;
- enum {
+
+ enum binder_work_type {
BINDER_WORK_TRANSACTION = 1,
BINDER_WORK_TRANSACTION_COMPLETE,
+ BINDER_WORK_RETURN_ERROR,
BINDER_WORK_NODE,
BINDER_WORK_DEAD_BINDER,
BINDER_WORK_DEAD_BINDER_AND_CLEAR,
@@ -222,8 +294,77 @@ struct binder_work {
} type;
};
+struct binder_error {
+ struct binder_work work;
+ uint32_t cmd;
+};
+
+/**
+ * struct binder_node - binder node bookkeeping
+ * @debug_id: unique ID for debugging
+ * (invariant after initialized)
+ * @lock: lock for node fields
+ * @work: worklist element for node work
+ * (protected by @proc->inner_lock)
+ * @rb_node: element for proc->nodes tree
+ * (protected by @proc->inner_lock)
+ * @dead_node: element for binder_dead_nodes list
+ * (protected by binder_dead_nodes_lock)
+ * @proc: binder_proc that owns this node
+ * (invariant after initialized)
+ * @refs: list of references on this node
+ * (protected by @lock)
+ * @internal_strong_refs: used to take strong references when
+ * initiating a transaction
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @local_weak_refs: weak user refs from local process
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @local_strong_refs: strong user refs from local process
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @tmp_refs: temporary kernel refs
+ * (protected by @proc->inner_lock while @proc
+ * is valid, and by binder_dead_nodes_lock
+ * if @proc is NULL. During inc/dec and node release
+ * it is also protected by @lock to provide safety
+ * as the node dies and @proc becomes NULL)
+ * @ptr: userspace pointer for node
+ * (invariant, no lock needed)
+ * @cookie: userspace cookie for node
+ * (invariant, no lock needed)
+ * @has_strong_ref: userspace notified of strong ref
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @pending_strong_ref: userspace has acked notification of strong ref
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @has_weak_ref: userspace notified of weak ref
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @pending_weak_ref: userspace has acked notification of weak ref
+ * (protected by @proc->inner_lock if @proc
+ * and by @lock)
+ * @has_async_transaction: async transaction to node in progress
+ * (protected by @lock)
+ * @sched_policy: minimum scheduling policy for node
+ * (invariant after initialized)
+ * @accept_fds: file descriptor operations supported for node
+ * (invariant after initialized)
+ * @min_priority: minimum scheduling priority
+ * (invariant after initialized)
+ * @inherit_rt: inherit RT scheduling policy from caller
+ * @txn_security_ctx: require sender's security context
+ * (invariant after initialized)
+ * @async_todo: list of async work items
+ * (protected by @proc->inner_lock)
+ *
+ * Bookkeeping structure for binder nodes.
+ */
struct binder_node {
int debug_id;
+ spinlock_t lock;
struct binder_work work;
union {
struct rb_node rb_node;
@@ -234,98 +375,200 @@ struct binder_node {
int internal_strong_refs;
int local_weak_refs;
int local_strong_refs;
+ int tmp_refs;
binder_uintptr_t ptr;
binder_uintptr_t cookie;
- unsigned has_strong_ref:1;
- unsigned pending_strong_ref:1;
- unsigned has_weak_ref:1;
- unsigned pending_weak_ref:1;
- unsigned has_async_transaction:1;
- unsigned accept_fds:1;
- unsigned min_priority:8;
+ struct {
+ /*
+ * bitfield elements protected by
+ * proc inner_lock
+ */
+ u8 has_strong_ref:1;
+ u8 pending_strong_ref:1;
+ u8 has_weak_ref:1;
+ u8 pending_weak_ref:1;
+ };
+ struct {
+ /*
+ * invariant after initialization
+ */
+ u8 sched_policy:2;
+ u8 inherit_rt:1;
+ u8 accept_fds:1;
+ u8 txn_security_ctx:1;
+ u8 min_priority;
+ };
+ bool has_async_transaction;
struct list_head async_todo;
};
struct binder_ref_death {
+ /**
+ * @work: worklist element for death notifications
+ * (protected by inner_lock of the proc that
+ * this ref belongs to)
+ */
struct binder_work work;
binder_uintptr_t cookie;
};
+/**
+ * struct binder_ref_data - binder_ref counts and id
+ * @debug_id: unique ID for the ref
+ * @desc: unique userspace handle for ref
+ * @strong: strong ref count (debugging only if not locked)
+ * @weak: weak ref count (debugging only if not locked)
+ *
+ * Structure to hold ref count and ref id information. Since
+ * the actual ref can only be accessed with a lock, this structure
+ * is used to return information about the ref to callers of
+ * ref inc/dec functions.
+ */
+struct binder_ref_data {
+ int debug_id;
+ uint32_t desc;
+ int strong;
+ int weak;
+};
+
+/**
+ * struct binder_ref - struct to track references on nodes
+ * @data: binder_ref_data containing id, handle, and current refcounts
+ * @rb_node_desc: node for lookup by @data.desc in proc's rb_tree
+ * @rb_node_node: node for lookup by @node in proc's rb_tree
+ * @node_entry: list entry for node->refs list in target node
+ * (protected by @node->lock)
+ * @proc: binder_proc containing ref
+ * @node: binder_node of target node. When cleaning up a
+ * ref for deletion in binder_cleanup_ref, a non-NULL
+ * @node indicates the node must be freed
+ * @death: pointer to death notification (ref_death) if requested
+ * (protected by @node->lock)
+ *
+ * Structure to track references from procA to target node (on procB). This
+ * structure is unsafe to access without holding @proc->outer_lock.
+ */
struct binder_ref {
/* Lookups needed: */
/* node + proc => ref (transaction) */
/* desc + proc => ref (transaction, inc/dec ref) */
/* node => refs + procs (proc exit) */
- int debug_id;
+ struct binder_ref_data data;
struct rb_node rb_node_desc;
struct rb_node rb_node_node;
struct hlist_node node_entry;
struct binder_proc *proc;
struct binder_node *node;
- uint32_t desc;
- int strong;
- int weak;
struct binder_ref_death *death;
};
-struct binder_buffer {
- struct list_head entry; /* free and allocated entries by address */
- struct rb_node rb_node; /* free entry by size or allocated entry */
- /* by address */
- unsigned free:1;
- unsigned allow_user_free:1;
- unsigned async_transaction:1;
- unsigned debug_id:29;
-
- struct binder_transaction *transaction;
-
- struct binder_node *target_node;
- size_t data_size;
- size_t offsets_size;
- uint8_t data[0];
-};
-
enum binder_deferred_state {
BINDER_DEFERRED_PUT_FILES = 0x01,
BINDER_DEFERRED_FLUSH = 0x02,
BINDER_DEFERRED_RELEASE = 0x04,
};
+/**
+ * struct binder_priority - scheduler policy and priority
+ * @sched_policy scheduler policy
+ * @prio [100..139] for SCHED_NORMAL, [0..99] for FIFO/RT
+ *
+ * The binder driver supports inheriting the following scheduler policies:
+ * SCHED_NORMAL
+ * SCHED_BATCH
+ * SCHED_FIFO
+ * SCHED_RR
+ */
+struct binder_priority {
+ unsigned int sched_policy;
+ int prio;
+};
+
+/**
+ * struct binder_proc - binder process bookkeeping
+ * @proc_node: element for binder_procs list
+ * @threads: rbtree of binder_threads in this proc
+ * (protected by @inner_lock)
+ * @nodes: rbtree of binder nodes associated with
+ * this proc ordered by node->ptr
+ * (protected by @inner_lock)
+ * @refs_by_desc: rbtree of refs ordered by ref->desc
+ * (protected by @outer_lock)
+ * @refs_by_node: rbtree of refs ordered by ref->node
+ * (protected by @outer_lock)
+ * @waiting_threads: threads currently waiting for proc work
+ * (protected by @inner_lock)
+ * @pid PID of group_leader of process
+ * (invariant after initialized)
+ * @tsk task_struct for group_leader of process
+ * (invariant after initialized)
+ * @files files_struct for process
+ * (protected by @files_lock)
+ * @files_lock mutex to protect @files
+ * @deferred_work_node: element for binder_deferred_list
+ * (protected by binder_deferred_lock)
+ * @deferred_work: bitmap of deferred work to perform
+ * (protected by binder_deferred_lock)
+ * @is_dead: process is dead and awaiting free
+ * when outstanding transactions are cleaned up
+ * (protected by @inner_lock)
+ * @todo: list of work for this process
+ * (protected by @inner_lock)
+ * @stats: per-process binder statistics
+ * (atomics, no lock needed)
+ * @delivered_death: list of delivered death notification
+ * (protected by @inner_lock)
+ * @max_threads: cap on number of binder threads
+ * (protected by @inner_lock)
+ * @requested_threads: number of binder threads requested but not
+ * yet started. In current implementation, can
+ * only be 0 or 1.
+ * (protected by @inner_lock)
+ * @requested_threads_started: number binder threads started
+ * (protected by @inner_lock)
+ * @tmp_ref: temporary reference to indicate proc is in use
+ * (atomic since @proc->inner_lock cannot
+ * always be acquired)
+ * @default_priority: default scheduler priority
+ * (invariant after initialized)
+ * @debugfs_entry: debugfs node
+ * @alloc: binder allocator bookkeeping
+ * @context: binder_context for this proc
+ * (invariant after initialized)
+ * @inner_lock: can nest under outer_lock and/or node lock
+ * @outer_lock: no nesting under innor or node lock
+ * Lock order: 1) outer, 2) node, 3) inner
+ *
+ * Bookkeeping structure for binder processes
+ */
struct binder_proc {
struct hlist_node proc_node;
struct rb_root threads;
struct rb_root nodes;
struct rb_root refs_by_desc;
struct rb_root refs_by_node;
+ struct list_head waiting_threads;
int pid;
- struct vm_area_struct *vma;
- struct mm_struct *vma_vm_mm;
struct task_struct *tsk;
struct files_struct *files;
struct mutex files_lock;
struct hlist_node deferred_work_node;
int deferred_work;
- void *buffer;
- ptrdiff_t user_buffer_offset;
+ bool is_dead;
- struct list_head buffers;
- struct rb_root free_buffers;
- struct rb_root allocated_buffers;
- size_t free_async_space;
-
- struct page **pages;
- size_t buffer_size;
- uint32_t buffer_free;
struct list_head todo;
- wait_queue_head_t wait;
struct binder_stats stats;
struct list_head delivered_death;
int max_threads;
int requested_threads;
int requested_threads_started;
- int ready_threads;
- long default_priority;
+ atomic_t tmp_ref;
+ struct binder_priority default_priority;
struct dentry *debugfs_entry;
+ struct binder_alloc alloc;
+ struct binder_context *context;
+ spinlock_t inner_lock;
+ spinlock_t outer_lock;
};
enum {
@@ -334,23 +577,63 @@ enum {
BINDER_LOOPER_STATE_EXITED = 0x04,
BINDER_LOOPER_STATE_INVALID = 0x08,
BINDER_LOOPER_STATE_WAITING = 0x10,
- BINDER_LOOPER_STATE_NEED_RETURN = 0x20,
- BINDER_LOOPER_STATE_POLL = 0x40,
+ BINDER_LOOPER_STATE_POLL = 0x20,
};
+/**
+ * struct binder_thread - binder thread bookkeeping
+ * @proc: binder process for this thread
+ * (invariant after initialization)
+ * @rb_node: element for proc->threads rbtree
+ * (protected by @proc->inner_lock)
+ * @waiting_thread_node: element for @proc->waiting_threads list
+ * (protected by @proc->inner_lock)
+ * @pid: PID for this thread
+ * (invariant after initialization)
+ * @looper: bitmap of looping state
+ * (only accessed by this thread)
+ * @looper_needs_return: looping thread needs to exit driver
+ * (no lock needed)
+ * @transaction_stack: stack of in-progress transactions for this thread
+ * (protected by @proc->inner_lock)
+ * @todo: list of work to do for this thread
+ * (protected by @proc->inner_lock)
+ * @process_todo: whether work in @todo should be processed
+ * (protected by @proc->inner_lock)
+ * @return_error: transaction errors reported by this thread
+ * (only accessed by this thread)
+ * @reply_error: transaction errors reported by target thread
+ * (protected by @proc->inner_lock)
+ * @wait: wait queue for thread work
+ * @stats: per-thread statistics
+ * (atomics, no lock needed)
+ * @tmp_ref: temporary reference to indicate thread is in use
+ * (atomic since @proc->inner_lock cannot
+ * always be acquired)
+ * @is_dead: thread is dead and awaiting free
+ * when outstanding transactions are cleaned up
+ * (protected by @proc->inner_lock)
+ * @task: struct task_struct for this thread
+ *
+ * Bookkeeping structure for binder threads.
+ */
struct binder_thread {
struct binder_proc *proc;
struct rb_node rb_node;
+ struct list_head waiting_thread_node;
int pid;
- int looper;
+ int looper; /* only modified by this thread */
+ bool looper_need_return; /* can be written by other thread */
struct binder_transaction *transaction_stack;
struct list_head todo;
- uint32_t return_error; /* Write failed, return error code in read buf */
- uint32_t return_error2; /* Write failed, return error code in read */
- /* buffer. Used when sending a reply to a dead process that */
- /* we are also waiting on */
+ bool process_todo;
+ struct binder_error return_error;
+ struct binder_error reply_error;
wait_queue_head_t wait;
struct binder_stats stats;
+ atomic_t tmp_ref;
+ bool is_dead;
+ struct task_struct *task;
};
struct binder_transaction {
@@ -367,13 +650,301 @@ struct binder_transaction {
struct binder_buffer *buffer;
unsigned int code;
unsigned int flags;
- long priority;
- long saved_priority;
+ struct binder_priority priority;
+ struct binder_priority saved_priority;
+ bool set_priority_called;
kuid_t sender_euid;
+ binder_uintptr_t security_ctx;
+ /**
+ * @lock: protects @from, @to_proc, and @to_thread
+ *
+ * @from, @to_proc, and @to_thread can be set to NULL
+ * during thread teardown
+ */
+ spinlock_t lock;
};
+/**
+ * struct binder_object - union of flat binder object types
+ * @hdr: generic object header
+ * @fbo: binder object (nodes and refs)
+ * @fdo: file descriptor object
+ * @bbo: binder buffer pointer
+ * @fdao: file descriptor array
+ *
+ * Used for type-independent object copies
+ */
+struct binder_object {
+ union {
+ struct binder_object_header hdr;
+ struct flat_binder_object fbo;
+ struct binder_fd_object fdo;
+ struct binder_buffer_object bbo;
+ struct binder_fd_array_object fdao;
+ };
+};
+
+/**
+ * binder_proc_lock() - Acquire outer lock for given binder_proc
+ * @proc: struct binder_proc to acquire
+ *
+ * Acquires proc->outer_lock. Used to protect binder_ref
+ * structures associated with the given proc.
+ */
+#define binder_proc_lock(proc) _binder_proc_lock(proc, __LINE__)
+static void
+_binder_proc_lock(struct binder_proc *proc, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_lock(&proc->outer_lock);
+}
+
+/**
+ * binder_proc_unlock() - Release spinlock for given binder_proc
+ * @proc: struct binder_proc to acquire
+ *
+ * Release lock acquired via binder_proc_lock()
+ */
+#define binder_proc_unlock(_proc) _binder_proc_unlock(_proc, __LINE__)
+static void
+_binder_proc_unlock(struct binder_proc *proc, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_unlock(&proc->outer_lock);
+}
+
+/**
+ * binder_inner_proc_lock() - Acquire inner lock for given binder_proc
+ * @proc: struct binder_proc to acquire
+ *
+ * Acquires proc->inner_lock. Used to protect todo lists
+ */
+#define binder_inner_proc_lock(proc) _binder_inner_proc_lock(proc, __LINE__)
+static void
+_binder_inner_proc_lock(struct binder_proc *proc, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_lock(&proc->inner_lock);
+}
+
+/**
+ * binder_inner_proc_unlock() - Release inner lock for given binder_proc
+ * @proc: struct binder_proc to acquire
+ *
+ * Release lock acquired via binder_inner_proc_lock()
+ */
+#define binder_inner_proc_unlock(proc) _binder_inner_proc_unlock(proc, __LINE__)
+static void
+_binder_inner_proc_unlock(struct binder_proc *proc, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_unlock(&proc->inner_lock);
+}
+
+/**
+ * binder_node_lock() - Acquire spinlock for given binder_node
+ * @node: struct binder_node to acquire
+ *
+ * Acquires node->lock. Used to protect binder_node fields
+ */
+#define binder_node_lock(node) _binder_node_lock(node, __LINE__)
+static void
+_binder_node_lock(struct binder_node *node, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_lock(&node->lock);
+}
+
+/**
+ * binder_node_unlock() - Release spinlock for given binder_proc
+ * @node: struct binder_node to acquire
+ *
+ * Release lock acquired via binder_node_lock()
+ */
+#define binder_node_unlock(node) _binder_node_unlock(node, __LINE__)
+static void
+_binder_node_unlock(struct binder_node *node, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_unlock(&node->lock);
+}
+
+/**
+ * binder_node_inner_lock() - Acquire node and inner locks
+ * @node: struct binder_node to acquire
+ *
+ * Acquires node->lock. If node->proc also acquires
+ * proc->inner_lock. Used to protect binder_node fields
+ */
+#define binder_node_inner_lock(node) _binder_node_inner_lock(node, __LINE__)
+static void
+_binder_node_inner_lock(struct binder_node *node, int line)
+{
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ spin_lock(&node->lock);
+ if (node->proc)
+ binder_inner_proc_lock(node->proc);
+}
+
+/**
+ * binder_node_unlock() - Release node and inner locks
+ * @node: struct binder_node to acquire
+ *
+ * Release lock acquired via binder_node_lock()
+ */
+#define binder_node_inner_unlock(node) _binder_node_inner_unlock(node, __LINE__)
+static void
+_binder_node_inner_unlock(struct binder_node *node, int line)
+{
+ struct binder_proc *proc = node->proc;
+
+ binder_debug(BINDER_DEBUG_SPINLOCKS,
+ "%s: line=%d\n", __func__, line);
+ if (proc)
+ binder_inner_proc_unlock(proc);
+ spin_unlock(&node->lock);
+}
+
+static bool binder_worklist_empty_ilocked(struct list_head *list)
+{
+ return list_empty(list);
+}
+
+/**
+ * binder_worklist_empty() - Check if no items on the work list
+ * @proc: binder_proc associated with list
+ * @list: list to check
+ *
+ * Return: true if there are no items on list, else false
+ */
+static bool binder_worklist_empty(struct binder_proc *proc,
+ struct list_head *list)
+{
+ bool ret;
+
+ binder_inner_proc_lock(proc);
+ ret = binder_worklist_empty_ilocked(list);
+ binder_inner_proc_unlock(proc);
+ return ret;
+}
+
+/**
+ * binder_enqueue_work_ilocked() - Add an item to the work list
+ * @work: struct binder_work to add to list
+ * @target_list: list to add work to
+ *
+ * Adds the work to the specified list. Asserts that work
+ * is not already on a list.
+ *
+ * Requires the proc->inner_lock to be held.
+ */
+static void
+binder_enqueue_work_ilocked(struct binder_work *work,
+ struct list_head *target_list)
+{
+ BUG_ON(target_list == NULL);
+ BUG_ON(work->entry.next && !list_empty(&work->entry));
+ list_add_tail(&work->entry, target_list);
+}
+
+/**
+ * binder_enqueue_deferred_thread_work_ilocked() - Add deferred thread work
+ * @thread: thread to queue work to
+ * @work: struct binder_work to add to list
+ *
+ * Adds the work to the todo list of the thread. Doesn't set the process_todo
+ * flag, which means that (if it wasn't already set) the thread will go to
+ * sleep without handling this work when it calls read.
+ *
+ * Requires the proc->inner_lock to be held.
+ */
+static void
+binder_enqueue_deferred_thread_work_ilocked(struct binder_thread *thread,
+ struct binder_work *work)
+{
+ binder_enqueue_work_ilocked(work, &thread->todo);
+}
+
+/**
+ * binder_enqueue_thread_work_ilocked() - Add an item to the thread work list
+ * @thread: thread to queue work to
+ * @work: struct binder_work to add to list
+ *
+ * Adds the work to the todo list of the thread, and enables processing
+ * of the todo queue.
+ *
+ * Requires the proc->inner_lock to be held.
+ */
+static void
+binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
+ struct binder_work *work)
+{
+ binder_enqueue_work_ilocked(work, &thread->todo);
+ thread->process_todo = true;
+}
+
+/**
+ * binder_enqueue_thread_work() - Add an item to the thread work list
+ * @thread: thread to queue work to
+ * @work: struct binder_work to add to list
+ *
+ * Adds the work to the todo list of the thread, and enables processing
+ * of the todo queue.
+ */
+static void
+binder_enqueue_thread_work(struct binder_thread *thread,
+ struct binder_work *work)
+{
+ binder_inner_proc_lock(thread->proc);
+ binder_enqueue_thread_work_ilocked(thread, work);
+ binder_inner_proc_unlock(thread->proc);
+}
+
+static void
+binder_dequeue_work_ilocked(struct binder_work *work)
+{
+ list_del_init(&work->entry);
+}
+
+/**
+ * binder_dequeue_work() - Removes an item from the work list
+ * @proc: binder_proc associated with list
+ * @work: struct binder_work to remove from list
+ *
+ * Removes the specified work item from whatever list it is on.
+ * Can safely be called if work is not on any list.
+ */
+static void
+binder_dequeue_work(struct binder_proc *proc, struct binder_work *work)
+{
+ binder_inner_proc_lock(proc);
+ binder_dequeue_work_ilocked(work);
+ binder_inner_proc_unlock(proc);
+}
+
+static struct binder_work *binder_dequeue_work_head_ilocked(
+ struct list_head *list)
+{
+ struct binder_work *w;
+
+ w = list_first_entry_or_null(list, struct binder_work, entry);
+ if (w)
+ list_del_init(&w->entry);
+ return w;
+}
+
static void
binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer);
+static void binder_free_thread(struct binder_thread *thread);
+static void binder_free_proc(struct binder_proc *proc);
+static void binder_inc_node_tmpref_ilocked(struct binder_node *node);
static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
{
@@ -435,459 +1006,282 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
return retval;
}
-static inline void binder_lock(const char *tag)
+static bool binder_has_work_ilocked(struct binder_thread *thread,
+ bool do_proc_work)
{
- trace_binder_lock(tag);
- mutex_lock(&binder_main_lock);
- trace_binder_locked(tag);
+ return thread->process_todo ||
+ thread->looper_need_return ||
+ (do_proc_work &&
+ !binder_worklist_empty_ilocked(&thread->proc->todo));
}
-static inline void binder_unlock(const char *tag)
+static bool binder_has_work(struct binder_thread *thread, bool do_proc_work)
{
- trace_binder_unlock(tag);
- mutex_unlock(&binder_main_lock);
+ bool has_work;
+
+ binder_inner_proc_lock(thread->proc);
+ has_work = binder_has_work_ilocked(thread, do_proc_work);
+ binder_inner_proc_unlock(thread->proc);
+
+ return has_work;
}
-static void binder_set_nice(long nice)
+static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread)
{
- long min_nice;
+ return !thread->transaction_stack &&
+ binder_worklist_empty_ilocked(&thread->todo) &&
+ (thread->looper & (BINDER_LOOPER_STATE_ENTERED |
+ BINDER_LOOPER_STATE_REGISTERED));
+}
- if (can_nice(current, nice)) {
- set_user_nice(current, nice);
+static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc,
+ bool sync)
+{
+ struct rb_node *n;
+ struct binder_thread *thread;
+
+ for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) {
+ thread = rb_entry(n, struct binder_thread, rb_node);
+ if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+ binder_available_for_proc_work_ilocked(thread)) {
+ if (sync)
+ wake_up_interruptible_sync(&thread->wait);
+ else
+ wake_up_interruptible(&thread->wait);
+ }
+ }
+}
+
+/**
+ * binder_select_thread_ilocked() - selects a thread for doing proc work.
+ * @proc: process to select a thread from
+ *
+ * Note that calling this function moves the thread off the waiting_threads
+ * list, so it can only be woken up by the caller of this function, or a
+ * signal. Therefore, callers *should* always wake up the thread this function
+ * returns.
+ *
+ * Return: If there's a thread currently waiting for process work,
+ * returns that thread. Otherwise returns NULL.
+ */
+static struct binder_thread *
+binder_select_thread_ilocked(struct binder_proc *proc)
+{
+ struct binder_thread *thread;
+
+ assert_spin_locked(&proc->inner_lock);
+ thread = list_first_entry_or_null(&proc->waiting_threads,
+ struct binder_thread,
+ waiting_thread_node);
+
+ if (thread)
+ list_del_init(&thread->waiting_thread_node);
+
+ return thread;
+}
+
+/**
+ * binder_wakeup_thread_ilocked() - wakes up a thread for doing proc work.
+ * @proc: process to wake up a thread in
+ * @thread: specific thread to wake-up (may be NULL)
+ * @sync: whether to do a synchronous wake-up
+ *
+ * This function wakes up a thread in the @proc process.
+ * The caller may provide a specific thread to wake-up in
+ * the @thread parameter. If @thread is NULL, this function
+ * will wake up threads that have called poll().
+ *
+ * Note that for this function to work as expected, callers
+ * should first call binder_select_thread() to find a thread
+ * to handle the work (if they don't have a thread already),
+ * and pass the result into the @thread parameter.
+ */
+static void binder_wakeup_thread_ilocked(struct binder_proc *proc,
+ struct binder_thread *thread,
+ bool sync)
+{
+ assert_spin_locked(&proc->inner_lock);
+
+ if (thread) {
+ if (sync)
+ wake_up_interruptible_sync(&thread->wait);
+ else
+ wake_up_interruptible(&thread->wait);
return;
}
- min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur);
- binder_debug(BINDER_DEBUG_PRIORITY_CAP,
- "%d: nice value %ld not allowed use %ld instead\n",
- current->pid, nice, min_nice);
- set_user_nice(current, min_nice);
- if (min_nice <= MAX_NICE)
- return;
- binder_user_error("%d RLIMIT_NICE not set\n", current->pid);
+
+ /* Didn't find a thread waiting for proc work; this can happen
+ * in two scenarios:
+ * 1. All threads are busy handling transactions
+ * In that case, one of those threads should call back into
+ * the kernel driver soon and pick up this work.
+ * 2. Threads are using the (e)poll interface, in which case
+ * they may be blocked on the waitqueue without having been
+ * added to waiting_threads. For this case, we just iterate
+ * over all threads not handling transaction work, and
+ * wake them all up. We wake all because we don't know whether
+ * a thread that called into (e)poll is handling non-binder
+ * work currently.
+ */
+ binder_wakeup_poll_threads_ilocked(proc, sync);
}
-static size_t binder_buffer_size(struct binder_proc *proc,
- struct binder_buffer *buffer)
+static void binder_wakeup_proc_ilocked(struct binder_proc *proc)
{
- if (list_is_last(&buffer->entry, &proc->buffers))
- return proc->buffer + proc->buffer_size - (void *)buffer->data;
- return (size_t)list_entry(buffer->entry.next,
- struct binder_buffer, entry) - (size_t)buffer->data;
+ struct binder_thread *thread = binder_select_thread_ilocked(proc);
+
+ binder_wakeup_thread_ilocked(proc, thread, /* sync = */false);
}
-static void binder_insert_free_buffer(struct binder_proc *proc,
- struct binder_buffer *new_buffer)
+static bool is_rt_policy(int policy)
{
- struct rb_node **p = &proc->free_buffers.rb_node;
- struct rb_node *parent = NULL;
- struct binder_buffer *buffer;
- size_t buffer_size;
- size_t new_buffer_size;
-
- BUG_ON(!new_buffer->free);
-
- new_buffer_size = binder_buffer_size(proc, new_buffer);
-
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: add free buffer, size %zd, at %pK\n",
- proc->pid, new_buffer_size, new_buffer);
-
- while (*p) {
- parent = *p;
- buffer = rb_entry(parent, struct binder_buffer, rb_node);
- BUG_ON(!buffer->free);
-
- buffer_size = binder_buffer_size(proc, buffer);
-
- if (new_buffer_size < buffer_size)
- p = &parent->rb_left;
- else
- p = &parent->rb_right;
- }
- rb_link_node(&new_buffer->rb_node, parent, p);
- rb_insert_color(&new_buffer->rb_node, &proc->free_buffers);
+ return policy == SCHED_FIFO || policy == SCHED_RR;
}
-static void binder_insert_allocated_buffer(struct binder_proc *proc,
- struct binder_buffer *new_buffer)
+static bool is_fair_policy(int policy)
{
- struct rb_node **p = &proc->allocated_buffers.rb_node;
- struct rb_node *parent = NULL;
- struct binder_buffer *buffer;
-
- BUG_ON(new_buffer->free);
-
- while (*p) {
- parent = *p;
- buffer = rb_entry(parent, struct binder_buffer, rb_node);
- BUG_ON(buffer->free);
-
- if (new_buffer < buffer)
- p = &parent->rb_left;
- else if (new_buffer > buffer)
- p = &parent->rb_right;
- else
- BUG();
- }
- rb_link_node(&new_buffer->rb_node, parent, p);
- rb_insert_color(&new_buffer->rb_node, &proc->allocated_buffers);
+ return policy == SCHED_NORMAL || policy == SCHED_BATCH;
}
-static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc,
- uintptr_t user_ptr)
+static bool binder_supported_policy(int policy)
{
- struct rb_node *n = proc->allocated_buffers.rb_node;
- struct binder_buffer *buffer;
- struct binder_buffer *kern_ptr;
-
- kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset
- - offsetof(struct binder_buffer, data));
-
- while (n) {
- buffer = rb_entry(n, struct binder_buffer, rb_node);
- BUG_ON(buffer->free);
-
- if (kern_ptr < buffer)
- n = n->rb_left;
- else if (kern_ptr > buffer)
- n = n->rb_right;
- else
- return buffer;
- }
- return NULL;
+ return is_fair_policy(policy) || is_rt_policy(policy);
}
-static int binder_update_page_range(struct binder_proc *proc, int allocate,
- void *start, void *end,
- struct vm_area_struct *vma)
+static int to_userspace_prio(int policy, int kernel_priority)
{
- void *page_addr;
- unsigned long user_page_addr;
- struct page **page;
- struct mm_struct *mm;
-
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: %s pages %pK-%pK\n", proc->pid,
- allocate ? "allocate" : "free", start, end);
-
- if (end <= start)
- return 0;
-
- trace_binder_update_page_range(proc, allocate, start, end);
-
- if (vma)
- mm = NULL;
+ if (is_fair_policy(policy))
+ return PRIO_TO_NICE(kernel_priority);
else
- mm = get_task_mm(proc->tsk);
-
- if (mm) {
- down_write(&mm->mmap_sem);
- if (!mmget_still_valid(mm)) {
- if (allocate == 0)
- goto free_range;
- goto err_no_vma;
- }
-
- vma = proc->vma;
- if (vma && mm != proc->vma_vm_mm) {
- pr_err("%d: vma mm and task mm mismatch\n",
- proc->pid);
- vma = NULL;
- }
- }
-
- if (allocate == 0)
- goto free_range;
-
- if (vma == NULL) {
- pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
- proc->pid);
- goto err_no_vma;
- }
-
- for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
- int ret;
-
- page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
-
- BUG_ON(*page);
- *page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
- if (*page == NULL) {
- pr_err("%d: binder_alloc_buf failed for page at %pK\n",
- proc->pid, page_addr);
- goto err_alloc_page_failed;
- }
- ret = map_kernel_range_noflush((unsigned long)page_addr,
- PAGE_SIZE, PAGE_KERNEL, page);
- flush_cache_vmap((unsigned long)page_addr,
- (unsigned long)page_addr + PAGE_SIZE);
- if (ret != 1) {
- pr_err("%d: binder_alloc_buf failed to map page at %pK in kernel\n",
- proc->pid, page_addr);
- goto err_map_kernel_failed;
- }
- user_page_addr =
- (uintptr_t)page_addr + proc->user_buffer_offset;
- ret = vm_insert_page(vma, user_page_addr, page[0]);
- if (ret) {
- pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
- proc->pid, user_page_addr);
- goto err_vm_insert_page_failed;
- }
- /* vm_insert_page does not seem to increment the refcount */
- }
- if (mm) {
- up_write(&mm->mmap_sem);
- mmput(mm);
- }
- return 0;
-
-free_range:
- for (page_addr = end - PAGE_SIZE; page_addr >= start;
- page_addr -= PAGE_SIZE) {
- page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
- if (vma)
- zap_page_range(vma, (uintptr_t)page_addr +
- proc->user_buffer_offset, PAGE_SIZE, NULL);
-err_vm_insert_page_failed:
- unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
-err_map_kernel_failed:
- __free_page(*page);
- *page = NULL;
-err_alloc_page_failed:
- ;
- }
-err_no_vma:
- if (mm) {
- up_write(&mm->mmap_sem);
- mmput(mm);
- }
- return -ENOMEM;
+ return MAX_USER_RT_PRIO - 1 - kernel_priority;
}
-static struct binder_buffer *binder_alloc_buf(struct binder_proc *proc,
- size_t data_size,
- size_t offsets_size, int is_async)
+static int to_kernel_prio(int policy, int user_priority)
{
- struct rb_node *n = proc->free_buffers.rb_node;
- struct binder_buffer *buffer;
- size_t buffer_size;
- struct rb_node *best_fit = NULL;
- void *has_page_addr;
- void *end_page_addr;
- size_t size;
+ if (is_fair_policy(policy))
+ return NICE_TO_PRIO(user_priority);
+ else
+ return MAX_USER_RT_PRIO - 1 - user_priority;
+}
- if (proc->vma == NULL) {
- pr_err("%d: binder_alloc_buf, no vma\n",
- proc->pid);
- return NULL;
- }
+static void binder_do_set_priority(struct task_struct *task,
+ struct binder_priority desired,
+ bool verify)
+{
+ int priority; /* user-space prio value */
+ bool has_cap_nice;
+ unsigned int policy = desired.sched_policy;
- size = ALIGN(data_size, sizeof(void *)) +
- ALIGN(offsets_size, sizeof(void *));
+ if (task->policy == policy && task->normal_prio == desired.prio)
+ return;
- if (size < data_size || size < offsets_size) {
- binder_user_error("%d: got transaction with invalid size %zd-%zd\n",
- proc->pid, data_size, offsets_size);
- return NULL;
- }
+ has_cap_nice = has_capability_noaudit(task, CAP_SYS_NICE);
- if (is_async &&
- proc->free_async_space < size + sizeof(struct binder_buffer)) {
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: binder_alloc_buf size %zd failed, no async space left\n",
- proc->pid, size);
- return NULL;
- }
+ priority = to_userspace_prio(policy, desired.prio);
- while (n) {
- buffer = rb_entry(n, struct binder_buffer, rb_node);
- BUG_ON(!buffer->free);
- buffer_size = binder_buffer_size(proc, buffer);
+ if (verify && is_rt_policy(policy) && !has_cap_nice) {
+ long max_rtprio = task_rlimit(task, RLIMIT_RTPRIO);
- if (size < buffer_size) {
- best_fit = n;
- n = n->rb_left;
- } else if (size > buffer_size)
- n = n->rb_right;
- else {
- best_fit = n;
- break;
+ if (max_rtprio == 0) {
+ policy = SCHED_NORMAL;
+ priority = MIN_NICE;
+ } else if (priority > max_rtprio) {
+ priority = max_rtprio;
}
}
- if (best_fit == NULL) {
- pr_err("%d: binder_alloc_buf size %zd failed, no address space\n",
- proc->pid, size);
- return NULL;
- }
- if (n == NULL) {
- buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
- buffer_size = binder_buffer_size(proc, buffer);
- }
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
- proc->pid, size, buffer, buffer_size);
+ if (verify && is_fair_policy(policy) && !has_cap_nice) {
+ long min_nice = rlimit_to_nice(task_rlimit(task, RLIMIT_NICE));
- has_page_addr =
- (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
- if (n == NULL) {
- if (size + sizeof(struct binder_buffer) + 4 >= buffer_size)
- buffer_size = size; /* no room for other buffers */
- else
- buffer_size = size + sizeof(struct binder_buffer);
- }
- end_page_addr =
- (void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size);
- if (end_page_addr > has_page_addr)
- end_page_addr = has_page_addr;
- if (binder_update_page_range(proc, 1,
- (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL))
- return NULL;
-
- rb_erase(best_fit, &proc->free_buffers);
- buffer->free = 0;
- binder_insert_allocated_buffer(proc, buffer);
- if (buffer_size != size) {
- struct binder_buffer *new_buffer = (void *)buffer->data + size;
-
- list_add(&new_buffer->entry, &buffer->entry);
- new_buffer->free = 1;
- binder_insert_free_buffer(proc, new_buffer);
- }
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: binder_alloc_buf size %zd got %pK\n",
- proc->pid, size, buffer);
- buffer->data_size = data_size;
- buffer->offsets_size = offsets_size;
- buffer->async_transaction = is_async;
- if (is_async) {
- proc->free_async_space -= size + sizeof(struct binder_buffer);
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
- "%d: binder_alloc_buf size %zd async free %zd\n",
- proc->pid, size, proc->free_async_space);
- }
-
- return buffer;
-}
-
-static void *buffer_start_page(struct binder_buffer *buffer)
-{
- return (void *)((uintptr_t)buffer & PAGE_MASK);
-}
-
-static void *buffer_end_page(struct binder_buffer *buffer)
-{
- return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK);
-}
-
-static void binder_delete_free_buffer(struct binder_proc *proc,
- struct binder_buffer *buffer)
-{
- struct binder_buffer *prev, *next = NULL;
- int free_page_end = 1;
- int free_page_start = 1;
-
- BUG_ON(proc->buffers.next == &buffer->entry);
- prev = list_entry(buffer->entry.prev, struct binder_buffer, entry);
- BUG_ON(!prev->free);
- if (buffer_end_page(prev) == buffer_start_page(buffer)) {
- free_page_start = 0;
- if (buffer_end_page(prev) == buffer_end_page(buffer))
- free_page_end = 0;
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: merge free, buffer %pK share page with %pK\n",
- proc->pid, buffer, prev);
- }
-
- if (!list_is_last(&buffer->entry, &proc->buffers)) {
- next = list_entry(buffer->entry.next,
- struct binder_buffer, entry);
- if (buffer_start_page(next) == buffer_end_page(buffer)) {
- free_page_end = 0;
- if (buffer_start_page(next) ==
- buffer_start_page(buffer))
- free_page_start = 0;
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: merge free, buffer %pK share page with %pK\n",
- proc->pid, buffer, prev);
+ if (min_nice > MAX_NICE) {
+ binder_user_error("%d RLIMIT_NICE not set\n",
+ task->pid);
+ return;
+ } else if (priority < min_nice) {
+ priority = min_nice;
}
}
- list_del(&buffer->entry);
- if (free_page_start || free_page_end) {
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: merge free, buffer %pK do not share page%s%s with %pK or %pK\n",
- proc->pid, buffer, free_page_start ? "" : " end",
- free_page_end ? "" : " start", prev, next);
- binder_update_page_range(proc, 0, free_page_start ?
- buffer_start_page(buffer) : buffer_end_page(buffer),
- (free_page_end ? buffer_end_page(buffer) :
- buffer_start_page(buffer)) + PAGE_SIZE, NULL);
+
+ if (policy != desired.sched_policy ||
+ to_kernel_prio(policy, priority) != desired.prio)
+ binder_debug(BINDER_DEBUG_PRIORITY_CAP,
+ "%d: priority %d not allowed, using %d instead\n",
+ task->pid, desired.prio,
+ to_kernel_prio(policy, priority));
+
+ trace_binder_set_priority(task->tgid, task->pid, task->normal_prio,
+ to_kernel_prio(policy, priority),
+ desired.prio);
+
+ /* Set the actual priority */
+ if (task->policy != policy || is_rt_policy(policy)) {
+ struct sched_param params;
+
+ params.sched_priority = is_rt_policy(policy) ? priority : 0;
+
+ sched_setscheduler_nocheck(task,
+ policy | SCHED_RESET_ON_FORK,
+ ¶ms);
}
+ if (is_fair_policy(policy))
+ set_user_nice(task, priority);
}
-static void binder_free_buf(struct binder_proc *proc,
- struct binder_buffer *buffer)
+static void binder_set_priority(struct task_struct *task,
+ struct binder_priority desired)
{
- size_t size, buffer_size;
-
- buffer_size = binder_buffer_size(proc, buffer);
-
- size = ALIGN(buffer->data_size, sizeof(void *)) +
- ALIGN(buffer->offsets_size, sizeof(void *));
-
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: binder_free_buf %pK size %zd buffer_size %zd\n",
- proc->pid, buffer, size, buffer_size);
-
- BUG_ON(buffer->free);
- BUG_ON(size > buffer_size);
- BUG_ON(buffer->transaction != NULL);
- BUG_ON((void *)buffer < proc->buffer);
- BUG_ON((void *)buffer > proc->buffer + proc->buffer_size);
-
- if (buffer->async_transaction) {
- proc->free_async_space += size + sizeof(struct binder_buffer);
-
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
- "%d: binder_free_buf size %zd async free %zd\n",
- proc->pid, size, proc->free_async_space);
- }
-
- binder_update_page_range(proc, 0,
- (void *)PAGE_ALIGN((uintptr_t)buffer->data),
- (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK),
- NULL);
- rb_erase(&buffer->rb_node, &proc->allocated_buffers);
- buffer->free = 1;
- if (!list_is_last(&buffer->entry, &proc->buffers)) {
- struct binder_buffer *next = list_entry(buffer->entry.next,
- struct binder_buffer, entry);
-
- if (next->free) {
- rb_erase(&next->rb_node, &proc->free_buffers);
- binder_delete_free_buffer(proc, next);
- }
- }
- if (proc->buffers.next != &buffer->entry) {
- struct binder_buffer *prev = list_entry(buffer->entry.prev,
- struct binder_buffer, entry);
-
- if (prev->free) {
- binder_delete_free_buffer(proc, buffer);
- rb_erase(&prev->rb_node, &proc->free_buffers);
- buffer = prev;
- }
- }
- binder_insert_free_buffer(proc, buffer);
+ binder_do_set_priority(task, desired, /* verify = */ true);
}
-static struct binder_node *binder_get_node(struct binder_proc *proc,
- binder_uintptr_t ptr)
+static void binder_restore_priority(struct task_struct *task,
+ struct binder_priority desired)
+{
+ binder_do_set_priority(task, desired, /* verify = */ false);
+}
+
+static void binder_transaction_priority(struct task_struct *task,
+ struct binder_transaction *t,
+ struct binder_priority node_prio,
+ bool inherit_rt)
+{
+ struct binder_priority desired_prio = t->priority;
+
+ if (t->set_priority_called)
+ return;
+
+ t->set_priority_called = true;
+ t->saved_priority.sched_policy = task->policy;
+ t->saved_priority.prio = task->normal_prio;
+
+ if (!inherit_rt && is_rt_policy(desired_prio.sched_policy)) {
+ desired_prio.prio = NICE_TO_PRIO(0);
+ desired_prio.sched_policy = SCHED_NORMAL;
+ }
+
+ if (node_prio.prio < t->priority.prio ||
+ (node_prio.prio == t->priority.prio &&
+ node_prio.sched_policy == SCHED_FIFO)) {
+ /*
+ * In case the minimum priority on the node is
+ * higher (lower value), use that priority. If
+ * the priority is the same, but the node uses
+ * SCHED_FIFO, prefer SCHED_FIFO, since it can
+ * run unbounded, unlike SCHED_RR.
+ */
+ desired_prio = node_prio;
+ }
+
+ binder_set_priority(task, desired_prio);
+}
+
+static struct binder_node *binder_get_node_ilocked(struct binder_proc *proc,
+ binder_uintptr_t ptr)
{
struct rb_node *n = proc->nodes.rb_node;
struct binder_node *node;
+ assert_spin_locked(&proc->inner_lock);
+
while (n) {
node = rb_entry(n, struct binder_node, rb_node);
@@ -895,21 +1289,47 @@ static struct binder_node *binder_get_node(struct binder_proc *proc,
n = n->rb_left;
else if (ptr > node->ptr)
n = n->rb_right;
- else
+ else {
+ /*
+ * take an implicit weak reference
+ * to ensure node stays alive until
+ * call to binder_put_node()
+ */
+ binder_inc_node_tmpref_ilocked(node);
return node;
+ }
}
return NULL;
}
-static struct binder_node *binder_new_node(struct binder_proc *proc,
- binder_uintptr_t ptr,
- binder_uintptr_t cookie)
+static struct binder_node *binder_get_node(struct binder_proc *proc,
+ binder_uintptr_t ptr)
+{
+ struct binder_node *node;
+
+ binder_inner_proc_lock(proc);
+ node = binder_get_node_ilocked(proc, ptr);
+ binder_inner_proc_unlock(proc);
+ return node;
+}
+
+static struct binder_node *binder_init_node_ilocked(
+ struct binder_proc *proc,
+ struct binder_node *new_node,
+ struct flat_binder_object *fp)
{
struct rb_node **p = &proc->nodes.rb_node;
struct rb_node *parent = NULL;
struct binder_node *node;
+ binder_uintptr_t ptr = fp ? fp->binder : 0;
+ binder_uintptr_t cookie = fp ? fp->cookie : 0;
+ __u32 flags = fp ? fp->flags : 0;
+ s8 priority;
+
+ assert_spin_locked(&proc->inner_lock);
while (*p) {
+
parent = *p;
node = rb_entry(parent, struct binder_node, rb_node);
@@ -917,39 +1337,87 @@ static struct binder_node *binder_new_node(struct binder_proc *proc,
p = &(*p)->rb_left;
else if (ptr > node->ptr)
p = &(*p)->rb_right;
- else
- return NULL;
+ else {
+ /*
+ * A matching node is already in
+ * the rb tree. Abandon the init
+ * and return it.
+ */
+ binder_inc_node_tmpref_ilocked(node);
+ return node;
+ }
}
-
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- if (node == NULL)
- return NULL;
+ node = new_node;
binder_stats_created(BINDER_STAT_NODE);
+ node->tmp_refs++;
rb_link_node(&node->rb_node, parent, p);
rb_insert_color(&node->rb_node, &proc->nodes);
- node->debug_id = ++binder_last_id;
+ node->debug_id = atomic_inc_return(&binder_last_id);
node->proc = proc;
node->ptr = ptr;
node->cookie = cookie;
node->work.type = BINDER_WORK_NODE;
+ priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK;
+ node->sched_policy = (flags & FLAT_BINDER_FLAG_SCHED_POLICY_MASK) >>
+ FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT;
+ node->min_priority = to_kernel_prio(node->sched_policy, priority);
+ node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS);
+ node->inherit_rt = !!(flags & FLAT_BINDER_FLAG_INHERIT_RT);
+ node->txn_security_ctx = !!(flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX);
+ spin_lock_init(&node->lock);
INIT_LIST_HEAD(&node->work.entry);
INIT_LIST_HEAD(&node->async_todo);
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
"%d:%d node %d u%016llx c%016llx created\n",
proc->pid, current->pid, node->debug_id,
(u64)node->ptr, (u64)node->cookie);
+
return node;
}
-static int binder_inc_node(struct binder_node *node, int strong, int internal,
- struct list_head *target_list)
+static struct binder_node *binder_new_node(struct binder_proc *proc,
+ struct flat_binder_object *fp)
{
+ struct binder_node *node;
+ struct binder_node *new_node = kzalloc(sizeof(*node), GFP_KERNEL);
+
+ if (!new_node)
+ return NULL;
+ binder_inner_proc_lock(proc);
+ node = binder_init_node_ilocked(proc, new_node, fp);
+ binder_inner_proc_unlock(proc);
+ if (node != new_node)
+ /*
+ * The node was already added by another thread
+ */
+ kfree(new_node);
+
+ return node;
+}
+
+static void binder_free_node(struct binder_node *node)
+{
+ kfree(node);
+ binder_stats_deleted(BINDER_STAT_NODE);
+}
+
+static int binder_inc_node_nilocked(struct binder_node *node, int strong,
+ int internal,
+ struct list_head *target_list)
+{
+ struct binder_proc *proc = node->proc;
+
+ assert_spin_locked(&node->lock);
+ if (proc)
+ assert_spin_locked(&proc->inner_lock);
if (strong) {
if (internal) {
if (target_list == NULL &&
node->internal_strong_refs == 0 &&
- !(node == binder_context_mgr_node &&
- node->has_strong_ref)) {
+ !(node->proc &&
+ node == node->proc->context->
+ binder_context_mgr_node &&
+ node->has_strong_ref)) {
pr_err("invalid inc strong node for %d\n",
node->debug_id);
return -EINVAL;
@@ -958,8 +1426,19 @@ static int binder_inc_node(struct binder_node *node, int strong, int internal,
} else
node->local_strong_refs++;
if (!node->has_strong_ref && target_list) {
- list_del_init(&node->work.entry);
- list_add_tail(&node->work.entry, target_list);
+ binder_dequeue_work_ilocked(&node->work);
+ /*
+ * Note: this function is the only place where we queue
+ * directly to a thread->todo without using the
+ * corresponding binder_enqueue_thread_work() helper
+ * functions; in this case it's ok to not set the
+ * process_todo flag, since we know this node work will
+ * always be followed by other work that starts queue
+ * processing: in case of synchronous transactions, a
+ * BR_REPLY or BR_ERROR; in case of oneway
+ * transactions, a BR_TRANSACTION_COMPLETE.
+ */
+ binder_enqueue_work_ilocked(&node->work, target_list);
}
} else {
if (!internal)
@@ -970,58 +1449,172 @@ static int binder_inc_node(struct binder_node *node, int strong, int internal,
node->debug_id);
return -EINVAL;
}
- list_add_tail(&node->work.entry, target_list);
+ /*
+ * See comment above
+ */
+ binder_enqueue_work_ilocked(&node->work, target_list);
}
}
return 0;
}
-static int binder_dec_node(struct binder_node *node, int strong, int internal)
+static int binder_inc_node(struct binder_node *node, int strong, int internal,
+ struct list_head *target_list)
{
+ int ret;
+
+ binder_node_inner_lock(node);
+ ret = binder_inc_node_nilocked(node, strong, internal, target_list);
+ binder_node_inner_unlock(node);
+
+ return ret;
+}
+
+static bool binder_dec_node_nilocked(struct binder_node *node,
+ int strong, int internal)
+{
+ struct binder_proc *proc = node->proc;
+
+ assert_spin_locked(&node->lock);
+ if (proc)
+ assert_spin_locked(&proc->inner_lock);
if (strong) {
if (internal)
node->internal_strong_refs--;
else
node->local_strong_refs--;
if (node->local_strong_refs || node->internal_strong_refs)
- return 0;
+ return false;
} else {
if (!internal)
node->local_weak_refs--;
- if (node->local_weak_refs || !hlist_empty(&node->refs))
- return 0;
+ if (node->local_weak_refs || node->tmp_refs ||
+ !hlist_empty(&node->refs))
+ return false;
}
- if (node->proc && (node->has_strong_ref || node->has_weak_ref)) {
+
+ if (proc && (node->has_strong_ref || node->has_weak_ref)) {
if (list_empty(&node->work.entry)) {
- list_add_tail(&node->work.entry, &node->proc->todo);
- wake_up_interruptible(&node->proc->wait);
+ binder_enqueue_work_ilocked(&node->work, &proc->todo);
+ binder_wakeup_proc_ilocked(proc);
}
} else {
if (hlist_empty(&node->refs) && !node->local_strong_refs &&
- !node->local_weak_refs) {
- list_del_init(&node->work.entry);
- if (node->proc) {
- rb_erase(&node->rb_node, &node->proc->nodes);
+ !node->local_weak_refs && !node->tmp_refs) {
+ if (proc) {
+ binder_dequeue_work_ilocked(&node->work);
+ rb_erase(&node->rb_node, &proc->nodes);
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
"refless node %d deleted\n",
node->debug_id);
} else {
+ BUG_ON(!list_empty(&node->work.entry));
+ spin_lock(&binder_dead_nodes_lock);
+ /*
+ * tmp_refs could have changed so
+ * check it again
+ */
+ if (node->tmp_refs) {
+ spin_unlock(&binder_dead_nodes_lock);
+ return false;
+ }
hlist_del(&node->dead_node);
+ spin_unlock(&binder_dead_nodes_lock);
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
"dead node %d deleted\n",
node->debug_id);
}
- kfree(node);
- binder_stats_deleted(BINDER_STAT_NODE);
+ return true;
}
}
-
- return 0;
+ return false;
}
+static void binder_dec_node(struct binder_node *node, int strong, int internal)
+{
+ bool free_node;
-static struct binder_ref *binder_get_ref(struct binder_proc *proc,
- u32 desc, bool need_strong_ref)
+ binder_node_inner_lock(node);
+ free_node = binder_dec_node_nilocked(node, strong, internal);
+ binder_node_inner_unlock(node);
+ if (free_node)
+ binder_free_node(node);
+}
+
+static void binder_inc_node_tmpref_ilocked(struct binder_node *node)
+{
+ /*
+ * No call to binder_inc_node() is needed since we
+ * don't need to inform userspace of any changes to
+ * tmp_refs
+ */
+ node->tmp_refs++;
+}
+
+/**
+ * binder_inc_node_tmpref() - take a temporary reference on node
+ * @node: node to reference
+ *
+ * Take reference on node to prevent the node from being freed
+ * while referenced only by a local variable. The inner lock is
+ * needed to serialize with the node work on the queue (which
+ * isn't needed after the node is dead). If the node is dead
+ * (node->proc is NULL), use binder_dead_nodes_lock to protect
+ * node->tmp_refs against dead-node-only cases where the node
+ * lock cannot be acquired (eg traversing the dead node list to
+ * print nodes)
+ */
+static void binder_inc_node_tmpref(struct binder_node *node)
+{
+ binder_node_lock(node);
+ if (node->proc)
+ binder_inner_proc_lock(node->proc);
+ else
+ spin_lock(&binder_dead_nodes_lock);
+ binder_inc_node_tmpref_ilocked(node);
+ if (node->proc)
+ binder_inner_proc_unlock(node->proc);
+ else
+ spin_unlock(&binder_dead_nodes_lock);
+ binder_node_unlock(node);
+}
+
+/**
+ * binder_dec_node_tmpref() - remove a temporary reference on node
+ * @node: node to reference
+ *
+ * Release temporary reference on node taken via binder_inc_node_tmpref()
+ */
+static void binder_dec_node_tmpref(struct binder_node *node)
+{
+ bool free_node;
+
+ binder_node_inner_lock(node);
+ if (!node->proc)
+ spin_lock(&binder_dead_nodes_lock);
+ node->tmp_refs--;
+ BUG_ON(node->tmp_refs < 0);
+ if (!node->proc)
+ spin_unlock(&binder_dead_nodes_lock);
+ /*
+ * Call binder_dec_node() to check if all refcounts are 0
+ * and cleanup is needed. Calling with strong=0 and internal=1
+ * causes no actual reference to be released in binder_dec_node().
+ * If that changes, a change is needed here too.
+ */
+ free_node = binder_dec_node_nilocked(node, 0, 1);
+ binder_node_inner_unlock(node);
+ if (free_node)
+ binder_free_node(node);
+}
+
+static void binder_put_node(struct binder_node *node)
+{
+ binder_dec_node_tmpref(node);
+}
+
+static struct binder_ref *binder_get_ref_olocked(struct binder_proc *proc,
+ u32 desc, bool need_strong_ref)
{
struct rb_node *n = proc->refs_by_desc.rb_node;
struct binder_ref *ref;
@@ -1029,11 +1622,11 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc,
while (n) {
ref = rb_entry(n, struct binder_ref, rb_node_desc);
- if (desc < ref->desc) {
+ if (desc < ref->data.desc) {
n = n->rb_left;
- } else if (desc > ref->desc) {
+ } else if (desc > ref->data.desc) {
n = n->rb_right;
- } else if (need_strong_ref && !ref->strong) {
+ } else if (need_strong_ref && !ref->data.strong) {
binder_user_error("tried to use weak ref as strong ref\n");
return NULL;
} else {
@@ -1043,13 +1636,34 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc,
return NULL;
}
-static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc,
- struct binder_node *node)
+/**
+ * binder_get_ref_for_node_olocked() - get the ref associated with given node
+ * @proc: binder_proc that owns the ref
+ * @node: binder_node of target
+ * @new_ref: newly allocated binder_ref to be initialized or %NULL
+ *
+ * Look up the ref for the given node and return it if it exists
+ *
+ * If it doesn't exist and the caller provides a newly allocated
+ * ref, initialize the fields of the newly allocated ref and insert
+ * into the given proc rb_trees and node refs list.
+ *
+ * Return: the ref for node. It is possible that another thread
+ * allocated/initialized the ref first in which case the
+ * returned ref would be different than the passed-in
+ * new_ref. new_ref must be kfree'd by the caller in
+ * this case.
+ */
+static struct binder_ref *binder_get_ref_for_node_olocked(
+ struct binder_proc *proc,
+ struct binder_node *node,
+ struct binder_ref *new_ref)
{
- struct rb_node *n;
+ struct binder_context *context = proc->context;
struct rb_node **p = &proc->refs_by_node.rb_node;
struct rb_node *parent = NULL;
- struct binder_ref *ref, *new_ref;
+ struct binder_ref *ref;
+ struct rb_node *n;
while (*p) {
parent = *p;
@@ -1062,22 +1676,22 @@ static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc,
else
return ref;
}
- new_ref = kzalloc(sizeof(*ref), GFP_KERNEL);
- if (new_ref == NULL)
+ if (!new_ref)
return NULL;
+
binder_stats_created(BINDER_STAT_REF);
- new_ref->debug_id = ++binder_last_id;
+ new_ref->data.debug_id = atomic_inc_return(&binder_last_id);
new_ref->proc = proc;
new_ref->node = node;
rb_link_node(&new_ref->rb_node_node, parent, p);
rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node);
- new_ref->desc = (node == binder_context_mgr_node) ? 0 : 1;
+ new_ref->data.desc = (node == context->binder_context_mgr_node) ? 0 : 1;
for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
ref = rb_entry(n, struct binder_ref, rb_node_desc);
- if (ref->desc > new_ref->desc)
+ if (ref->data.desc > new_ref->data.desc)
break;
- new_ref->desc = ref->desc + 1;
+ new_ref->data.desc = ref->data.desc + 1;
}
p = &proc->refs_by_desc.rb_node;
@@ -1085,123 +1699,443 @@ static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc,
parent = *p;
ref = rb_entry(parent, struct binder_ref, rb_node_desc);
- if (new_ref->desc < ref->desc)
+ if (new_ref->data.desc < ref->data.desc)
p = &(*p)->rb_left;
- else if (new_ref->desc > ref->desc)
+ else if (new_ref->data.desc > ref->data.desc)
p = &(*p)->rb_right;
else
BUG();
}
rb_link_node(&new_ref->rb_node_desc, parent, p);
rb_insert_color(&new_ref->rb_node_desc, &proc->refs_by_desc);
- if (node) {
- hlist_add_head(&new_ref->node_entry, &node->refs);
- binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d new ref %d desc %d for node %d\n",
- proc->pid, new_ref->debug_id, new_ref->desc,
- node->debug_id);
- } else {
- binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d new ref %d desc %d for dead node\n",
- proc->pid, new_ref->debug_id, new_ref->desc);
- }
+ binder_node_lock(node);
+ hlist_add_head(&new_ref->node_entry, &node->refs);
+
+ binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+ "%d new ref %d desc %d for node %d\n",
+ proc->pid, new_ref->data.debug_id, new_ref->data.desc,
+ node->debug_id);
+ binder_node_unlock(node);
return new_ref;
}
-static void binder_delete_ref(struct binder_ref *ref)
+static void binder_cleanup_ref_olocked(struct binder_ref *ref)
{
+ bool delete_node = false;
+
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
"%d delete ref %d desc %d for node %d\n",
- ref->proc->pid, ref->debug_id, ref->desc,
+ ref->proc->pid, ref->data.debug_id, ref->data.desc,
ref->node->debug_id);
rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc);
rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node);
- if (ref->strong)
- binder_dec_node(ref->node, 1, 1);
+
+ binder_node_inner_lock(ref->node);
+ if (ref->data.strong)
+ binder_dec_node_nilocked(ref->node, 1, 1);
+
hlist_del(&ref->node_entry);
- binder_dec_node(ref->node, 0, 1);
+ delete_node = binder_dec_node_nilocked(ref->node, 0, 1);
+ binder_node_inner_unlock(ref->node);
+ /*
+ * Clear ref->node unless we want the caller to free the node
+ */
+ if (!delete_node) {
+ /*
+ * The caller uses ref->node to determine
+ * whether the node needs to be freed. Clear
+ * it since the node is still alive.
+ */
+ ref->node = NULL;
+ }
+
if (ref->death) {
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"%d delete ref %d desc %d has death notification\n",
- ref->proc->pid, ref->debug_id, ref->desc);
- list_del(&ref->death->work.entry);
- kfree(ref->death);
+ ref->proc->pid, ref->data.debug_id,
+ ref->data.desc);
+ binder_dequeue_work(ref->proc, &ref->death->work);
binder_stats_deleted(BINDER_STAT_DEATH);
}
- kfree(ref);
binder_stats_deleted(BINDER_STAT_REF);
}
-static int binder_inc_ref(struct binder_ref *ref, int strong,
- struct list_head *target_list)
+/**
+ * binder_inc_ref_olocked() - increment the ref for given handle
+ * @ref: ref to be incremented
+ * @strong: if true, strong increment, else weak
+ * @target_list: list to queue node work on
+ *
+ * Increment the ref. @ref->proc->outer_lock must be held on entry
+ *
+ * Return: 0, if successful, else errno
+ */
+static int binder_inc_ref_olocked(struct binder_ref *ref, int strong,
+ struct list_head *target_list)
{
int ret;
if (strong) {
- if (ref->strong == 0) {
+ if (ref->data.strong == 0) {
ret = binder_inc_node(ref->node, 1, 1, target_list);
if (ret)
return ret;
}
- ref->strong++;
+ ref->data.strong++;
} else {
- if (ref->weak == 0) {
+ if (ref->data.weak == 0) {
ret = binder_inc_node(ref->node, 0, 1, target_list);
if (ret)
return ret;
}
- ref->weak++;
+ ref->data.weak++;
}
return 0;
}
-
-static int binder_dec_ref(struct binder_ref *ref, int strong)
+/**
+ * binder_dec_ref() - dec the ref for given handle
+ * @ref: ref to be decremented
+ * @strong: if true, strong decrement, else weak
+ *
+ * Decrement the ref.
+ *
+ * Return: true if ref is cleaned up and ready to be freed
+ */
+static bool binder_dec_ref_olocked(struct binder_ref *ref, int strong)
{
if (strong) {
- if (ref->strong == 0) {
+ if (ref->data.strong == 0) {
binder_user_error("%d invalid dec strong, ref %d desc %d s %d w %d\n",
- ref->proc->pid, ref->debug_id,
- ref->desc, ref->strong, ref->weak);
- return -EINVAL;
+ ref->proc->pid, ref->data.debug_id,
+ ref->data.desc, ref->data.strong,
+ ref->data.weak);
+ return false;
}
- ref->strong--;
- if (ref->strong == 0) {
- int ret;
-
- ret = binder_dec_node(ref->node, strong, 1);
- if (ret)
- return ret;
- }
+ ref->data.strong--;
+ if (ref->data.strong == 0)
+ binder_dec_node(ref->node, strong, 1);
} else {
- if (ref->weak == 0) {
+ if (ref->data.weak == 0) {
binder_user_error("%d invalid dec weak, ref %d desc %d s %d w %d\n",
- ref->proc->pid, ref->debug_id,
- ref->desc, ref->strong, ref->weak);
- return -EINVAL;
+ ref->proc->pid, ref->data.debug_id,
+ ref->data.desc, ref->data.strong,
+ ref->data.weak);
+ return false;
}
- ref->weak--;
+ ref->data.weak--;
}
- if (ref->strong == 0 && ref->weak == 0)
- binder_delete_ref(ref);
- return 0;
+ if (ref->data.strong == 0 && ref->data.weak == 0) {
+ binder_cleanup_ref_olocked(ref);
+ return true;
+ }
+ return false;
}
-static void binder_pop_transaction(struct binder_thread *target_thread,
- struct binder_transaction *t)
+/**
+ * binder_get_node_from_ref() - get the node from the given proc/desc
+ * @proc: proc containing the ref
+ * @desc: the handle associated with the ref
+ * @need_strong_ref: if true, only return node if ref is strong
+ * @rdata: the id/refcount data for the ref
+ *
+ * Given a proc and ref handle, return the associated binder_node
+ *
+ * Return: a binder_node or NULL if not found or not strong when strong required
+ */
+static struct binder_node *binder_get_node_from_ref(
+ struct binder_proc *proc,
+ u32 desc, bool need_strong_ref,
+ struct binder_ref_data *rdata)
{
- if (target_thread) {
- BUG_ON(target_thread->transaction_stack != t);
- BUG_ON(target_thread->transaction_stack->from != target_thread);
- target_thread->transaction_stack =
- target_thread->transaction_stack->from_parent;
- t->from = NULL;
+ struct binder_node *node;
+ struct binder_ref *ref;
+
+ binder_proc_lock(proc);
+ ref = binder_get_ref_olocked(proc, desc, need_strong_ref);
+ if (!ref)
+ goto err_no_ref;
+ node = ref->node;
+ /*
+ * Take an implicit reference on the node to ensure
+ * it stays alive until the call to binder_put_node()
+ */
+ binder_inc_node_tmpref(node);
+ if (rdata)
+ *rdata = ref->data;
+ binder_proc_unlock(proc);
+
+ return node;
+
+err_no_ref:
+ binder_proc_unlock(proc);
+ return NULL;
+}
+
+/**
+ * binder_free_ref() - free the binder_ref
+ * @ref: ref to free
+ *
+ * Free the binder_ref. Free the binder_node indicated by ref->node
+ * (if non-NULL) and the binder_ref_death indicated by ref->death.
+ */
+static void binder_free_ref(struct binder_ref *ref)
+{
+ if (ref->node)
+ binder_free_node(ref->node);
+ kfree(ref->death);
+ kfree(ref);
+}
+
+/**
+ * binder_update_ref_for_handle() - inc/dec the ref for given handle
+ * @proc: proc containing the ref
+ * @desc: the handle associated with the ref
+ * @increment: true=inc reference, false=dec reference
+ * @strong: true=strong reference, false=weak reference
+ * @rdata: the id/refcount data for the ref
+ *
+ * Given a proc and ref handle, increment or decrement the ref
+ * according to "increment" arg.
+ *
+ * Return: 0 if successful, else errno
+ */
+static int binder_update_ref_for_handle(struct binder_proc *proc,
+ uint32_t desc, bool increment, bool strong,
+ struct binder_ref_data *rdata)
+{
+ int ret = 0;
+ struct binder_ref *ref;
+ bool delete_ref = false;
+
+ binder_proc_lock(proc);
+ ref = binder_get_ref_olocked(proc, desc, strong);
+ if (!ref) {
+ ret = -EINVAL;
+ goto err_no_ref;
}
- t->need_reply = 0;
- if (t->buffer)
- t->buffer->transaction = NULL;
+ if (increment)
+ ret = binder_inc_ref_olocked(ref, strong, NULL);
+ else
+ delete_ref = binder_dec_ref_olocked(ref, strong);
+
+ if (rdata)
+ *rdata = ref->data;
+ binder_proc_unlock(proc);
+
+ if (delete_ref)
+ binder_free_ref(ref);
+ return ret;
+
+err_no_ref:
+ binder_proc_unlock(proc);
+ return ret;
+}
+
+/**
+ * binder_dec_ref_for_handle() - dec the ref for given handle
+ * @proc: proc containing the ref
+ * @desc: the handle associated with the ref
+ * @strong: true=strong reference, false=weak reference
+ * @rdata: the id/refcount data for the ref
+ *
+ * Just calls binder_update_ref_for_handle() to decrement the ref.
+ *
+ * Return: 0 if successful, else errno
+ */
+static int binder_dec_ref_for_handle(struct binder_proc *proc,
+ uint32_t desc, bool strong, struct binder_ref_data *rdata)
+{
+ return binder_update_ref_for_handle(proc, desc, false, strong, rdata);
+}
+
+
+/**
+ * binder_inc_ref_for_node() - increment the ref for given proc/node
+ * @proc: proc containing the ref
+ * @node: target node
+ * @strong: true=strong reference, false=weak reference
+ * @target_list: worklist to use if node is incremented
+ * @rdata: the id/refcount data for the ref
+ *
+ * Given a proc and node, increment the ref. Create the ref if it
+ * doesn't already exist
+ *
+ * Return: 0 if successful, else errno
+ */
+static int binder_inc_ref_for_node(struct binder_proc *proc,
+ struct binder_node *node,
+ bool strong,
+ struct list_head *target_list,
+ struct binder_ref_data *rdata)
+{
+ struct binder_ref *ref;
+ struct binder_ref *new_ref = NULL;
+ int ret = 0;
+
+ binder_proc_lock(proc);
+ ref = binder_get_ref_for_node_olocked(proc, node, NULL);
+ if (!ref) {
+ binder_proc_unlock(proc);
+ new_ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+ if (!new_ref)
+ return -ENOMEM;
+ binder_proc_lock(proc);
+ ref = binder_get_ref_for_node_olocked(proc, node, new_ref);
+ }
+ ret = binder_inc_ref_olocked(ref, strong, target_list);
+ *rdata = ref->data;
+ binder_proc_unlock(proc);
+ if (new_ref && ref != new_ref)
+ /*
+ * Another thread created the ref first so
+ * free the one we allocated
+ */
+ kfree(new_ref);
+ return ret;
+}
+
+static void binder_pop_transaction_ilocked(struct binder_thread *target_thread,
+ struct binder_transaction *t)
+{
+ BUG_ON(!target_thread);
+ assert_spin_locked(&target_thread->proc->inner_lock);
+ BUG_ON(target_thread->transaction_stack != t);
+ BUG_ON(target_thread->transaction_stack->from != target_thread);
+ target_thread->transaction_stack =
+ target_thread->transaction_stack->from_parent;
+ t->from = NULL;
+}
+
+/**
+ * binder_thread_dec_tmpref() - decrement thread->tmp_ref
+ * @thread: thread to decrement
+ *
+ * A thread needs to be kept alive while being used to create or
+ * handle a transaction. binder_get_txn_from() is used to safely
+ * extract t->from from a binder_transaction and keep the thread
+ * indicated by t->from from being freed. When done with that
+ * binder_thread, this function is called to decrement the
+ * tmp_ref and free if appropriate (thread has been released
+ * and no transaction being processed by the driver)
+ */
+static void binder_thread_dec_tmpref(struct binder_thread *thread)
+{
+ /*
+ * atomic is used to protect the counter value while
+ * it cannot reach zero or thread->is_dead is false
+ */
+ binder_inner_proc_lock(thread->proc);
+ atomic_dec(&thread->tmp_ref);
+ if (thread->is_dead && !atomic_read(&thread->tmp_ref)) {
+ binder_inner_proc_unlock(thread->proc);
+ binder_free_thread(thread);
+ return;
+ }
+ binder_inner_proc_unlock(thread->proc);
+}
+
+/**
+ * binder_proc_dec_tmpref() - decrement proc->tmp_ref
+ * @proc: proc to decrement
+ *
+ * A binder_proc needs to be kept alive while being used to create or
+ * handle a transaction. proc->tmp_ref is incremented when
+ * creating a new transaction or the binder_proc is currently in-use
+ * by threads that are being released. When done with the binder_proc,
+ * this function is called to decrement the counter and free the
+ * proc if appropriate (proc has been released, all threads have
+ * been released and not currenly in-use to process a transaction).
+ */
+static void binder_proc_dec_tmpref(struct binder_proc *proc)
+{
+ binder_inner_proc_lock(proc);
+ atomic_dec(&proc->tmp_ref);
+ if (proc->is_dead && RB_EMPTY_ROOT(&proc->threads) &&
+ !atomic_read(&proc->tmp_ref)) {
+ binder_inner_proc_unlock(proc);
+ binder_free_proc(proc);
+ return;
+ }
+ binder_inner_proc_unlock(proc);
+}
+
+/**
+ * binder_get_txn_from() - safely extract the "from" thread in transaction
+ * @t: binder transaction for t->from
+ *
+ * Atomically return the "from" thread and increment the tmp_ref
+ * count for the thread to ensure it stays alive until
+ * binder_thread_dec_tmpref() is called.
+ *
+ * Return: the value of t->from
+ */
+static struct binder_thread *binder_get_txn_from(
+ struct binder_transaction *t)
+{
+ struct binder_thread *from;
+
+ spin_lock(&t->lock);
+ from = t->from;
+ if (from)
+ atomic_inc(&from->tmp_ref);
+ spin_unlock(&t->lock);
+ return from;
+}
+
+/**
+ * binder_get_txn_from_and_acq_inner() - get t->from and acquire inner lock
+ * @t: binder transaction for t->from
+ *
+ * Same as binder_get_txn_from() except it also acquires the proc->inner_lock
+ * to guarantee that the thread cannot be released while operating on it.
+ * The caller must call binder_inner_proc_unlock() to release the inner lock
+ * as well as call binder_dec_thread_txn() to release the reference.
+ *
+ * Return: the value of t->from
+ */
+static struct binder_thread *binder_get_txn_from_and_acq_inner(
+ struct binder_transaction *t)
+{
+ struct binder_thread *from;
+
+ from = binder_get_txn_from(t);
+ if (!from)
+ return NULL;
+ binder_inner_proc_lock(from->proc);
+ if (t->from) {
+ BUG_ON(from != t->from);
+ return from;
+ }
+ binder_inner_proc_unlock(from->proc);
+ binder_thread_dec_tmpref(from);
+ return NULL;
+}
+
+static void binder_free_transaction(struct binder_transaction *t)
+{
+ struct binder_proc *target_proc;
+
+ spin_lock(&t->lock);
+ target_proc = t->to_proc;
+ if (target_proc) {
+ atomic_inc(&target_proc->tmp_ref);
+ spin_unlock(&t->lock);
+
+ binder_inner_proc_lock(target_proc);
+ if (t->buffer)
+ t->buffer->transaction = NULL;
+ binder_inner_proc_unlock(target_proc);
+ binder_proc_dec_tmpref(target_proc);
+ } else {
+ /*
+ * If the transaction has no target_proc, then
+ * t->buffer->transaction * has already been cleared.
+ */
+ spin_unlock(&t->lock);
+ }
kfree(t);
binder_stats_deleted(BINDER_STAT_TRANSACTION);
}
@@ -1214,30 +2148,34 @@ static void binder_send_failed_reply(struct binder_transaction *t,
BUG_ON(t->flags & TF_ONE_WAY);
while (1) {
- target_thread = t->from;
+ target_thread = binder_get_txn_from_and_acq_inner(t);
if (target_thread) {
- if (target_thread->return_error != BR_OK &&
- target_thread->return_error2 == BR_OK) {
- target_thread->return_error2 =
- target_thread->return_error;
- target_thread->return_error = BR_OK;
- }
- if (target_thread->return_error == BR_OK) {
- binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
- "send failed reply for transaction %d to %d:%d\n",
- t->debug_id,
- target_thread->proc->pid,
- target_thread->pid);
+ binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+ "send failed reply for transaction %d to %d:%d\n",
+ t->debug_id,
+ target_thread->proc->pid,
+ target_thread->pid);
- binder_pop_transaction(target_thread, t);
- target_thread->return_error = error_code;
+ binder_pop_transaction_ilocked(target_thread, t);
+ if (target_thread->reply_error.cmd == BR_OK) {
+ target_thread->reply_error.cmd = error_code;
+ binder_enqueue_thread_work_ilocked(
+ target_thread,
+ &target_thread->reply_error.work);
wake_up_interruptible(&target_thread->wait);
} else {
- pr_err("reply failed, target thread, %d:%d, has error code %d already\n",
- target_thread->proc->pid,
- target_thread->pid,
- target_thread->return_error);
+ /*
+ * Cannot get here for normal operation, but
+ * we can if multiple synchronous transactions
+ * are sent without blocking for responses.
+ * Just ignore the 2nd error in this case.
+ */
+ pr_warn("Unexpected reply error: %u\n",
+ target_thread->reply_error.cmd);
}
+ binder_inner_proc_unlock(target_thread->proc);
+ binder_thread_dec_tmpref(target_thread);
+ binder_free_transaction(t);
return;
}
next = t->from_parent;
@@ -1246,7 +2184,7 @@ static void binder_send_failed_reply(struct binder_transaction *t,
"send failed reply for transaction %d, target dead\n",
t->debug_id);
- binder_pop_transaction(target_thread, t);
+ binder_free_transaction(t);
if (next == NULL) {
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"reply failed, no target thread at root\n");
@@ -1259,43 +2197,255 @@ static void binder_send_failed_reply(struct binder_transaction *t,
}
}
+/**
+ * binder_cleanup_transaction() - cleans up undelivered transaction
+ * @t: transaction that needs to be cleaned up
+ * @reason: reason the transaction wasn't delivered
+ * @error_code: error to return to caller (if synchronous call)
+ */
+static void binder_cleanup_transaction(struct binder_transaction *t,
+ const char *reason,
+ uint32_t error_code)
+{
+ if (t->buffer->target_node && !(t->flags & TF_ONE_WAY)) {
+ binder_send_failed_reply(t, error_code);
+ } else {
+ binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+ "undelivered transaction %d, %s\n",
+ t->debug_id, reason);
+ binder_free_transaction(t);
+ }
+}
+
+/**
+ * binder_get_object() - gets object and checks for valid metadata
+ * @proc: binder_proc owning the buffer
+ * @buffer: binder_buffer that we're parsing.
+ * @offset: offset in the @buffer at which to validate an object.
+ * @object: struct binder_object to read into
+ *
+ * Return: If there's a valid metadata object at @offset in @buffer, the
+ * size of that object. Otherwise, it returns zero. The object
+ * is read into the struct binder_object pointed to by @object.
+ */
+static size_t binder_get_object(struct binder_proc *proc,
+ struct binder_buffer *buffer,
+ unsigned long offset,
+ struct binder_object *object)
+{
+ size_t read_size;
+ struct binder_object_header *hdr;
+ size_t object_size = 0;
+
+ read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
+ if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
+ !IS_ALIGNED(offset, sizeof(u32)))
+ return 0;
+ binder_alloc_copy_from_buffer(&proc->alloc, object, buffer,
+ offset, read_size);
+
+ /* Ok, now see if we read a complete object. */
+ hdr = &object->hdr;
+ switch (hdr->type) {
+ case BINDER_TYPE_BINDER:
+ case BINDER_TYPE_WEAK_BINDER:
+ case BINDER_TYPE_HANDLE:
+ case BINDER_TYPE_WEAK_HANDLE:
+ object_size = sizeof(struct flat_binder_object);
+ break;
+ case BINDER_TYPE_FD:
+ object_size = sizeof(struct binder_fd_object);
+ break;
+ case BINDER_TYPE_PTR:
+ object_size = sizeof(struct binder_buffer_object);
+ break;
+ case BINDER_TYPE_FDA:
+ object_size = sizeof(struct binder_fd_array_object);
+ break;
+ default:
+ return 0;
+ }
+ if (offset <= buffer->data_size - object_size &&
+ buffer->data_size >= object_size)
+ return object_size;
+ else
+ return 0;
+}
+
+/**
+ * binder_validate_ptr() - validates binder_buffer_object in a binder_buffer.
+ * @proc: binder_proc owning the buffer
+ * @b: binder_buffer containing the object
+ * @object: struct binder_object to read into
+ * @index: index in offset array at which the binder_buffer_object is
+ * located
+ * @start_offset: points to the start of the offset array
+ * @object_offsetp: offset of @object read from @b
+ * @num_valid: the number of valid offsets in the offset array
+ *
+ * Return: If @index is within the valid range of the offset array
+ * described by @start and @num_valid, and if there's a valid
+ * binder_buffer_object at the offset found in index @index
+ * of the offset array, that object is returned. Otherwise,
+ * %NULL is returned.
+ * Note that the offset found in index @index itself is not
+ * verified; this function assumes that @num_valid elements
+ * from @start were previously verified to have valid offsets.
+ * If @object_offsetp is non-NULL, then the offset within
+ * @b is written to it.
+ */
+static struct binder_buffer_object *binder_validate_ptr(
+ struct binder_proc *proc,
+ struct binder_buffer *b,
+ struct binder_object *object,
+ binder_size_t index,
+ binder_size_t start_offset,
+ binder_size_t *object_offsetp,
+ binder_size_t num_valid)
+{
+ size_t object_size;
+ binder_size_t object_offset;
+ unsigned long buffer_offset;
+
+ if (index >= num_valid)
+ return NULL;
+
+ buffer_offset = start_offset + sizeof(binder_size_t) * index;
+ binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
+ b, buffer_offset, sizeof(object_offset));
+ object_size = binder_get_object(proc, b, object_offset, object);
+ if (!object_size || object->hdr.type != BINDER_TYPE_PTR)
+ return NULL;
+ if (object_offsetp)
+ *object_offsetp = object_offset;
+
+ return &object->bbo;
+}
+
+/**
+ * binder_validate_fixup() - validates pointer/fd fixups happen in order.
+ * @proc: binder_proc owning the buffer
+ * @b: transaction buffer
+ * @objects_start_offset: offset to start of objects buffer
+ * @buffer_obj_offset: offset to binder_buffer_object in which to fix up
+ * @fixup_offset: start offset in @buffer to fix up
+ * @last_obj_offset: offset to last binder_buffer_object that we fixed
+ * @last_min_offset: minimum fixup offset in object at @last_obj_offset
+ *
+ * Return: %true if a fixup in buffer @buffer at offset @offset is
+ * allowed.
+ *
+ * For safety reasons, we only allow fixups inside a buffer to happen
+ * at increasing offsets; additionally, we only allow fixup on the last
+ * buffer object that was verified, or one of its parents.
+ *
+ * Example of what is allowed:
+ *
+ * A
+ * B (parent = A, offset = 0)
+ * C (parent = A, offset = 16)
+ * D (parent = C, offset = 0)
+ * E (parent = A, offset = 32) // min_offset is 16 (C.parent_offset)
+ *
+ * Examples of what is not allowed:
+ *
+ * Decreasing offsets within the same parent:
+ * A
+ * C (parent = A, offset = 16)
+ * B (parent = A, offset = 0) // decreasing offset within A
+ *
+ * Referring to a parent that wasn't the last object or any of its parents:
+ * A
+ * B (parent = A, offset = 0)
+ * C (parent = A, offset = 0)
+ * C (parent = A, offset = 16)
+ * D (parent = B, offset = 0) // B is not A or any of A's parents
+ */
+static bool binder_validate_fixup(struct binder_proc *proc,
+ struct binder_buffer *b,
+ binder_size_t objects_start_offset,
+ binder_size_t buffer_obj_offset,
+ binder_size_t fixup_offset,
+ binder_size_t last_obj_offset,
+ binder_size_t last_min_offset)
+{
+ if (!last_obj_offset) {
+ /* Nothing to fix up in */
+ return false;
+ }
+
+ while (last_obj_offset != buffer_obj_offset) {
+ unsigned long buffer_offset;
+ struct binder_object last_object;
+ struct binder_buffer_object *last_bbo;
+ size_t object_size = binder_get_object(proc, b, last_obj_offset,
+ &last_object);
+ if (object_size != sizeof(*last_bbo))
+ return false;
+
+ last_bbo = &last_object.bbo;
+ /*
+ * Safe to retrieve the parent of last_obj, since it
+ * was already previously verified by the driver.
+ */
+ if ((last_bbo->flags & BINDER_BUFFER_FLAG_HAS_PARENT) == 0)
+ return false;
+ last_min_offset = last_bbo->parent_offset + sizeof(uintptr_t);
+ buffer_offset = objects_start_offset +
+ sizeof(binder_size_t) * last_bbo->parent,
+ binder_alloc_copy_from_buffer(&proc->alloc, &last_obj_offset,
+ b, buffer_offset,
+ sizeof(last_obj_offset));
+ }
+ return (fixup_offset >= last_min_offset);
+}
+
static void binder_transaction_buffer_release(struct binder_proc *proc,
struct binder_buffer *buffer,
- binder_size_t *failed_at)
+ binder_size_t failed_at,
+ bool is_failure)
{
- binder_size_t *offp, *off_end;
int debug_id = buffer->debug_id;
+ binder_size_t off_start_offset, buffer_offset, off_end_offset;
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d buffer release %d, size %zd-%zd, failed at %pK\n",
+ "%d buffer release %d, size %zd-%zd, failed at %llx\n",
proc->pid, buffer->debug_id,
- buffer->data_size, buffer->offsets_size, failed_at);
+ buffer->data_size, buffer->offsets_size,
+ (unsigned long long)failed_at);
if (buffer->target_node)
binder_dec_node(buffer->target_node, 1, 0);
- offp = (binder_size_t *)(buffer->data +
- ALIGN(buffer->data_size, sizeof(void *)));
- if (failed_at)
- off_end = failed_at;
- else
- off_end = (void *)offp + buffer->offsets_size;
- for (; offp < off_end; offp++) {
- struct flat_binder_object *fp;
+ off_start_offset = ALIGN(buffer->data_size, sizeof(void *));
+ off_end_offset = is_failure ? failed_at :
+ off_start_offset + buffer->offsets_size;
+ for (buffer_offset = off_start_offset; buffer_offset < off_end_offset;
+ buffer_offset += sizeof(binder_size_t)) {
+ struct binder_object_header *hdr;
+ size_t object_size;
+ struct binder_object object;
+ binder_size_t object_offset;
- if (*offp > buffer->data_size - sizeof(*fp) ||
- buffer->data_size < sizeof(*fp) ||
- !IS_ALIGNED(*offp, sizeof(u32))) {
- pr_err("transaction release %d bad offset %lld, size %zd\n",
- debug_id, (u64)*offp, buffer->data_size);
+ binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
+ buffer, buffer_offset,
+ sizeof(object_offset));
+ object_size = binder_get_object(proc, buffer,
+ object_offset, &object);
+ if (object_size == 0) {
+ pr_err("transaction release %d bad object at offset %lld, size %zd\n",
+ debug_id, (u64)object_offset, buffer->data_size);
continue;
}
- fp = (struct flat_binder_object *)(buffer->data + *offp);
- switch (fp->type) {
+ hdr = &object.hdr;
+ switch (hdr->type) {
case BINDER_TYPE_BINDER:
case BINDER_TYPE_WEAK_BINDER: {
- struct binder_node *node = binder_get_node(proc, fp->binder);
+ struct flat_binder_object *fp;
+ struct binder_node *node;
+ fp = to_flat_binder_object(hdr);
+ node = binder_get_node(proc, fp->binder);
if (node == NULL) {
pr_err("transaction release %d bad node %016llx\n",
debug_id, (u64)fp->binder);
@@ -1304,90 +2454,599 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
binder_debug(BINDER_DEBUG_TRANSACTION,
" node %d u%016llx\n",
node->debug_id, (u64)node->ptr);
- binder_dec_node(node, fp->type == BINDER_TYPE_BINDER, 0);
+ binder_dec_node(node, hdr->type == BINDER_TYPE_BINDER,
+ 0);
+ binder_put_node(node);
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref;
+ struct flat_binder_object *fp;
+ struct binder_ref_data rdata;
+ int ret;
- ref = binder_get_ref(proc, fp->handle,
- fp->type == BINDER_TYPE_HANDLE);
+ fp = to_flat_binder_object(hdr);
+ ret = binder_dec_ref_for_handle(proc, fp->handle,
+ hdr->type == BINDER_TYPE_HANDLE, &rdata);
- if (ref == NULL) {
- pr_err("transaction release %d bad handle %d\n",
- debug_id, fp->handle);
+ if (ret) {
+ pr_err("transaction release %d bad handle %d, ret = %d\n",
+ debug_id, fp->handle, ret);
break;
}
binder_debug(BINDER_DEBUG_TRANSACTION,
- " ref %d desc %d (node %d)\n",
- ref->debug_id, ref->desc, ref->node->debug_id);
- binder_dec_ref(ref, fp->type == BINDER_TYPE_HANDLE);
+ " ref %d desc %d\n",
+ rdata.debug_id, rdata.desc);
} break;
- case BINDER_TYPE_FD:
- binder_debug(BINDER_DEBUG_TRANSACTION,
- " fd %d\n", fp->handle);
- if (failed_at)
- task_close_fd(proc, fp->handle);
- break;
+ case BINDER_TYPE_FD: {
+ struct binder_fd_object *fp = to_binder_fd_object(hdr);
+ binder_debug(BINDER_DEBUG_TRANSACTION,
+ " fd %d\n", fp->fd);
+ if (failed_at)
+ task_close_fd(proc, fp->fd);
+ } break;
+ case BINDER_TYPE_PTR:
+ /*
+ * Nothing to do here, this will get cleaned up when the
+ * transaction buffer gets freed
+ */
+ break;
+ case BINDER_TYPE_FDA: {
+ struct binder_fd_array_object *fda;
+ struct binder_buffer_object *parent;
+ struct binder_object ptr_object;
+ binder_size_t fda_offset;
+ size_t fd_index;
+ binder_size_t fd_buf_size;
+ binder_size_t num_valid;
+
+ num_valid = (buffer_offset - off_start_offset) /
+ sizeof(binder_size_t);
+ fda = to_binder_fd_array_object(hdr);
+ parent = binder_validate_ptr(proc, buffer, &ptr_object,
+ fda->parent,
+ off_start_offset,
+ NULL,
+ num_valid);
+ if (!parent) {
+ pr_err("transaction release %d bad parent offset",
+ debug_id);
+ continue;
+ }
+ fd_buf_size = sizeof(u32) * fda->num_fds;
+ if (fda->num_fds >= SIZE_MAX / sizeof(u32)) {
+ pr_err("transaction release %d invalid number of fds (%lld)\n",
+ debug_id, (u64)fda->num_fds);
+ continue;
+ }
+ if (fd_buf_size > parent->length ||
+ fda->parent_offset > parent->length - fd_buf_size) {
+ /* No space for all file descriptors here. */
+ pr_err("transaction release %d not enough space for %lld fds in buffer\n",
+ debug_id, (u64)fda->num_fds);
+ continue;
+ }
+ /*
+ * the source data for binder_buffer_object is visible
+ * to user-space and the @buffer element is the user
+ * pointer to the buffer_object containing the fd_array.
+ * Convert the address to an offset relative to
+ * the base of the transaction buffer.
+ */
+ fda_offset =
+ (parent->buffer - (uintptr_t)buffer->user_data) +
+ fda->parent_offset;
+ for (fd_index = 0; fd_index < fda->num_fds;
+ fd_index++) {
+ u32 fd;
+ binder_size_t offset = fda_offset +
+ fd_index * sizeof(fd);
+
+ binder_alloc_copy_from_buffer(&proc->alloc,
+ &fd,
+ buffer,
+ offset,
+ sizeof(fd));
+ task_close_fd(proc, fd);
+ }
+ } break;
default:
pr_err("transaction release %d bad object type %x\n",
- debug_id, fp->type);
+ debug_id, hdr->type);
break;
}
}
}
+static int binder_translate_binder(struct flat_binder_object *fp,
+ struct binder_transaction *t,
+ struct binder_thread *thread)
+{
+ struct binder_node *node;
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+ struct binder_ref_data rdata;
+ int ret = 0;
+
+ node = binder_get_node(proc, fp->binder);
+ if (!node) {
+ node = binder_new_node(proc, fp);
+ if (!node)
+ return -ENOMEM;
+ }
+ if (fp->cookie != node->cookie) {
+ binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n",
+ proc->pid, thread->pid, (u64)fp->binder,
+ node->debug_id, (u64)fp->cookie,
+ (u64)node->cookie);
+ ret = -EINVAL;
+ goto done;
+ }
+ if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+ ret = -EPERM;
+ goto done;
+ }
+
+ ret = binder_inc_ref_for_node(target_proc, node,
+ fp->hdr.type == BINDER_TYPE_BINDER,
+ &thread->todo, &rdata);
+ if (ret)
+ goto done;
+
+ if (fp->hdr.type == BINDER_TYPE_BINDER)
+ fp->hdr.type = BINDER_TYPE_HANDLE;
+ else
+ fp->hdr.type = BINDER_TYPE_WEAK_HANDLE;
+ fp->binder = 0;
+ fp->handle = rdata.desc;
+ fp->cookie = 0;
+
+ trace_binder_transaction_node_to_ref(t, node, &rdata);
+ binder_debug(BINDER_DEBUG_TRANSACTION,
+ " node %d u%016llx -> ref %d desc %d\n",
+ node->debug_id, (u64)node->ptr,
+ rdata.debug_id, rdata.desc);
+done:
+ binder_put_node(node);
+ return ret;
+}
+
+static int binder_translate_handle(struct flat_binder_object *fp,
+ struct binder_transaction *t,
+ struct binder_thread *thread)
+{
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+ struct binder_node *node;
+ struct binder_ref_data src_rdata;
+ int ret = 0;
+
+ node = binder_get_node_from_ref(proc, fp->handle,
+ fp->hdr.type == BINDER_TYPE_HANDLE, &src_rdata);
+ if (!node) {
+ binder_user_error("%d:%d got transaction with invalid handle, %d\n",
+ proc->pid, thread->pid, fp->handle);
+ return -EINVAL;
+ }
+ if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+ ret = -EPERM;
+ goto done;
+ }
+
+ binder_node_lock(node);
+ if (node->proc == target_proc) {
+ if (fp->hdr.type == BINDER_TYPE_HANDLE)
+ fp->hdr.type = BINDER_TYPE_BINDER;
+ else
+ fp->hdr.type = BINDER_TYPE_WEAK_BINDER;
+ fp->binder = node->ptr;
+ fp->cookie = node->cookie;
+ if (node->proc)
+ binder_inner_proc_lock(node->proc);
+ binder_inc_node_nilocked(node,
+ fp->hdr.type == BINDER_TYPE_BINDER,
+ 0, NULL);
+ if (node->proc)
+ binder_inner_proc_unlock(node->proc);
+ trace_binder_transaction_ref_to_node(t, node, &src_rdata);
+ binder_debug(BINDER_DEBUG_TRANSACTION,
+ " ref %d desc %d -> node %d u%016llx\n",
+ src_rdata.debug_id, src_rdata.desc, node->debug_id,
+ (u64)node->ptr);
+ binder_node_unlock(node);
+ } else {
+ struct binder_ref_data dest_rdata;
+
+ binder_node_unlock(node);
+ ret = binder_inc_ref_for_node(target_proc, node,
+ fp->hdr.type == BINDER_TYPE_HANDLE,
+ NULL, &dest_rdata);
+ if (ret)
+ goto done;
+
+ fp->binder = 0;
+ fp->handle = dest_rdata.desc;
+ fp->cookie = 0;
+ trace_binder_transaction_ref_to_ref(t, node, &src_rdata,
+ &dest_rdata);
+ binder_debug(BINDER_DEBUG_TRANSACTION,
+ " ref %d desc %d -> ref %d desc %d (node %d)\n",
+ src_rdata.debug_id, src_rdata.desc,
+ dest_rdata.debug_id, dest_rdata.desc,
+ node->debug_id);
+ }
+done:
+ binder_put_node(node);
+ return ret;
+}
+
+static int binder_translate_fd(int fd,
+ struct binder_transaction *t,
+ struct binder_thread *thread,
+ struct binder_transaction *in_reply_to)
+{
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+ int target_fd;
+ struct file *file;
+ int ret;
+ bool target_allows_fd;
+
+ if (in_reply_to)
+ target_allows_fd = !!(in_reply_to->flags & TF_ACCEPT_FDS);
+ else
+ target_allows_fd = t->buffer->target_node->accept_fds;
+ if (!target_allows_fd) {
+ binder_user_error("%d:%d got %s with fd, %d, but target does not allow fds\n",
+ proc->pid, thread->pid,
+ in_reply_to ? "reply" : "transaction",
+ fd);
+ ret = -EPERM;
+ goto err_fd_not_accepted;
+ }
+
+ file = fget(fd);
+ if (!file) {
+ binder_user_error("%d:%d got transaction with invalid fd, %d\n",
+ proc->pid, thread->pid, fd);
+ ret = -EBADF;
+ goto err_fget;
+ }
+ ret = security_binder_transfer_file(proc->tsk, target_proc->tsk, file);
+ if (ret < 0) {
+ ret = -EPERM;
+ goto err_security;
+ }
+
+ target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
+ if (target_fd < 0) {
+ ret = -ENOMEM;
+ goto err_get_unused_fd;
+ }
+ task_fd_install(target_proc, target_fd, file);
+ trace_binder_transaction_fd(t, fd, target_fd);
+ binder_debug(BINDER_DEBUG_TRANSACTION, " fd %d -> %d\n",
+ fd, target_fd);
+
+ return target_fd;
+
+err_get_unused_fd:
+err_security:
+ fput(file);
+err_fget:
+err_fd_not_accepted:
+ return ret;
+}
+
+static int binder_translate_fd_array(struct binder_fd_array_object *fda,
+ struct binder_buffer_object *parent,
+ struct binder_transaction *t,
+ struct binder_thread *thread,
+ struct binder_transaction *in_reply_to)
+{
+ binder_size_t fdi, fd_buf_size, num_installed_fds;
+ binder_size_t fda_offset;
+ int target_fd;
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+
+ fd_buf_size = sizeof(u32) * fda->num_fds;
+ if (fda->num_fds >= SIZE_MAX / sizeof(u32)) {
+ binder_user_error("%d:%d got transaction with invalid number of fds (%lld)\n",
+ proc->pid, thread->pid, (u64)fda->num_fds);
+ return -EINVAL;
+ }
+ if (fd_buf_size > parent->length ||
+ fda->parent_offset > parent->length - fd_buf_size) {
+ /* No space for all file descriptors here. */
+ binder_user_error("%d:%d not enough space to store %lld fds in buffer\n",
+ proc->pid, thread->pid, (u64)fda->num_fds);
+ return -EINVAL;
+ }
+ /*
+ * the source data for binder_buffer_object is visible
+ * to user-space and the @buffer element is the user
+ * pointer to the buffer_object containing the fd_array.
+ * Convert the address to an offset relative to
+ * the base of the transaction buffer.
+ */
+ fda_offset = (parent->buffer - (uintptr_t)t->buffer->user_data) +
+ fda->parent_offset;
+ if (!IS_ALIGNED((unsigned long)fda_offset, sizeof(u32))) {
+ binder_user_error("%d:%d parent offset not aligned correctly.\n",
+ proc->pid, thread->pid);
+ return -EINVAL;
+ }
+ for (fdi = 0; fdi < fda->num_fds; fdi++) {
+ u32 fd;
+
+ binder_size_t offset = fda_offset + fdi * sizeof(fd);
+
+ binder_alloc_copy_from_buffer(&target_proc->alloc,
+ &fd, t->buffer,
+ offset, sizeof(fd));
+ target_fd = binder_translate_fd(fd, t, thread, in_reply_to);
+ if (target_fd < 0)
+ goto err_translate_fd_failed;
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, offset,
+ &target_fd, sizeof(fd));
+ }
+ return 0;
+
+err_translate_fd_failed:
+ /*
+ * Failed to allocate fd or security error, free fds
+ * installed so far.
+ */
+ num_installed_fds = fdi;
+ for (fdi = 0; fdi < num_installed_fds; fdi++) {
+ u32 fd;
+ binder_size_t offset = fda_offset + fdi * sizeof(fd);
+ binder_alloc_copy_from_buffer(&target_proc->alloc,
+ &fd, t->buffer,
+ offset, sizeof(fd));
+ task_close_fd(target_proc, fd);
+ }
+ return target_fd;
+}
+
+static int binder_fixup_parent(struct binder_transaction *t,
+ struct binder_thread *thread,
+ struct binder_buffer_object *bp,
+ binder_size_t off_start_offset,
+ binder_size_t num_valid,
+ binder_size_t last_fixup_obj_off,
+ binder_size_t last_fixup_min_off)
+{
+ struct binder_buffer_object *parent;
+ struct binder_buffer *b = t->buffer;
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+ struct binder_object object;
+ binder_size_t buffer_offset;
+ binder_size_t parent_offset;
+
+ if (!(bp->flags & BINDER_BUFFER_FLAG_HAS_PARENT))
+ return 0;
+
+ parent = binder_validate_ptr(target_proc, b, &object, bp->parent,
+ off_start_offset, &parent_offset,
+ num_valid);
+ if (!parent) {
+ binder_user_error("%d:%d got transaction with invalid parent offset or type\n",
+ proc->pid, thread->pid);
+ return -EINVAL;
+ }
+
+ if (!binder_validate_fixup(target_proc, b, off_start_offset,
+ parent_offset, bp->parent_offset,
+ last_fixup_obj_off,
+ last_fixup_min_off)) {
+ binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n",
+ proc->pid, thread->pid);
+ return -EINVAL;
+ }
+
+ if (parent->length < sizeof(binder_uintptr_t) ||
+ bp->parent_offset > parent->length - sizeof(binder_uintptr_t)) {
+ /* No space for a pointer here! */
+ binder_user_error("%d:%d got transaction with invalid parent offset\n",
+ proc->pid, thread->pid);
+ return -EINVAL;
+ }
+ buffer_offset = bp->parent_offset +
+ (uintptr_t)parent->buffer - (uintptr_t)b->user_data;
+ binder_alloc_copy_to_buffer(&target_proc->alloc, b, buffer_offset,
+ &bp->buffer, sizeof(bp->buffer));
+
+ return 0;
+}
+
+/**
+ * binder_proc_transaction() - sends a transaction to a process and wakes it up
+ * @t: transaction to send
+ * @proc: process to send the transaction to
+ * @thread: thread in @proc to send the transaction to (may be NULL)
+ *
+ * This function queues a transaction to the specified process. It will try
+ * to find a thread in the target process to handle the transaction and
+ * wake it up. If no thread is found, the work is queued to the proc
+ * waitqueue.
+ *
+ * If the @thread parameter is not NULL, the transaction is always queued
+ * to the waitlist of that specific thread.
+ *
+ * Return: true if the transactions was successfully queued
+ * false if the target process or thread is dead
+ */
+static bool binder_proc_transaction(struct binder_transaction *t,
+ struct binder_proc *proc,
+ struct binder_thread *thread)
+{
+ struct binder_node *node = t->buffer->target_node;
+ struct binder_priority node_prio;
+ bool oneway = !!(t->flags & TF_ONE_WAY);
+ bool pending_async = false;
+
+ BUG_ON(!node);
+ binder_node_lock(node);
+ node_prio.prio = node->min_priority;
+ node_prio.sched_policy = node->sched_policy;
+
+ if (oneway) {
+ BUG_ON(thread);
+ if (node->has_async_transaction) {
+ pending_async = true;
+ } else {
+ node->has_async_transaction = true;
+ }
+ }
+
+ binder_inner_proc_lock(proc);
+
+ if (proc->is_dead || (thread && thread->is_dead)) {
+ binder_inner_proc_unlock(proc);
+ binder_node_unlock(node);
+ return false;
+ }
+
+ if (!thread && !pending_async)
+ thread = binder_select_thread_ilocked(proc);
+
+ if (thread) {
+ binder_transaction_priority(thread->task, t, node_prio,
+ node->inherit_rt);
+ binder_enqueue_thread_work_ilocked(thread, &t->work);
+ } else if (!pending_async) {
+ binder_enqueue_work_ilocked(&t->work, &proc->todo);
+ } else {
+ binder_enqueue_work_ilocked(&t->work, &node->async_todo);
+ }
+
+ if (!pending_async)
+ binder_wakeup_thread_ilocked(proc, thread, !oneway /* sync */);
+
+ binder_inner_proc_unlock(proc);
+ binder_node_unlock(node);
+
+ return true;
+}
+
+/**
+ * binder_get_node_refs_for_txn() - Get required refs on node for txn
+ * @node: struct binder_node for which to get refs
+ * @proc: returns @node->proc if valid
+ * @error: if no @proc then returns BR_DEAD_REPLY
+ *
+ * User-space normally keeps the node alive when creating a transaction
+ * since it has a reference to the target. The local strong ref keeps it
+ * alive if the sending process dies before the target process processes
+ * the transaction. If the source process is malicious or has a reference
+ * counting bug, relying on the local strong ref can fail.
+ *
+ * Since user-space can cause the local strong ref to go away, we also take
+ * a tmpref on the node to ensure it survives while we are constructing
+ * the transaction. We also need a tmpref on the proc while we are
+ * constructing the transaction, so we take that here as well.
+ *
+ * Return: The target_node with refs taken or NULL if no @node->proc is NULL.
+ * Also sets @proc if valid. If the @node->proc is NULL indicating that the
+ * target proc has died, @error is set to BR_DEAD_REPLY
+ */
+static struct binder_node *binder_get_node_refs_for_txn(
+ struct binder_node *node,
+ struct binder_proc **procp,
+ uint32_t *error)
+{
+ struct binder_node *target_node = NULL;
+
+ binder_node_inner_lock(node);
+ if (node->proc) {
+ target_node = node;
+ binder_inc_node_nilocked(node, 1, 0, NULL);
+ binder_inc_node_tmpref_ilocked(node);
+ atomic_inc(&node->proc->tmp_ref);
+ *procp = node->proc;
+ } else
+ *error = BR_DEAD_REPLY;
+ binder_node_inner_unlock(node);
+
+ return target_node;
+}
+
static void binder_transaction(struct binder_proc *proc,
struct binder_thread *thread,
- struct binder_transaction_data *tr, int reply)
+ struct binder_transaction_data *tr, int reply,
+ binder_size_t extra_buffers_size)
{
+ int ret;
struct binder_transaction *t;
struct binder_work *tcomplete;
- binder_size_t *offp, *off_end;
+ binder_size_t buffer_offset = 0;
+ binder_size_t off_start_offset, off_end_offset;
binder_size_t off_min;
- struct binder_proc *target_proc;
+ binder_size_t sg_buf_offset, sg_buf_end_offset;
+ struct binder_proc *target_proc = NULL;
struct binder_thread *target_thread = NULL;
struct binder_node *target_node = NULL;
- struct list_head *target_list;
- wait_queue_head_t *target_wait;
struct binder_transaction *in_reply_to = NULL;
struct binder_transaction_log_entry *e;
- uint32_t return_error;
+ uint32_t return_error = 0;
+ uint32_t return_error_param = 0;
+ uint32_t return_error_line = 0;
+ binder_size_t last_fixup_obj_off = 0;
+ binder_size_t last_fixup_min_off = 0;
+ struct binder_context *context = proc->context;
+ int t_debug_id = atomic_inc_return(&binder_last_id);
+ char *secctx = NULL;
+ u32 secctx_sz = 0;
e = binder_transaction_log_add(&binder_transaction_log);
+ e->debug_id = t_debug_id;
e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY);
e->from_proc = proc->pid;
e->from_thread = thread->pid;
e->target_handle = tr->target.handle;
e->data_size = tr->data_size;
e->offsets_size = tr->offsets_size;
+ e->context_name = proc->context->name;
if (reply) {
+ binder_inner_proc_lock(proc);
in_reply_to = thread->transaction_stack;
if (in_reply_to == NULL) {
+ binder_inner_proc_unlock(proc);
binder_user_error("%d:%d got reply transaction with no transaction stack\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EPROTO;
+ return_error_line = __LINE__;
goto err_empty_call_stack;
}
- binder_set_nice(in_reply_to->saved_priority);
if (in_reply_to->to_thread != thread) {
+ spin_lock(&in_reply_to->lock);
binder_user_error("%d:%d got reply transaction with bad transaction stack, transaction %d has target %d:%d\n",
proc->pid, thread->pid, in_reply_to->debug_id,
in_reply_to->to_proc ?
in_reply_to->to_proc->pid : 0,
in_reply_to->to_thread ?
in_reply_to->to_thread->pid : 0);
+ spin_unlock(&in_reply_to->lock);
+ binder_inner_proc_unlock(proc);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EPROTO;
+ return_error_line = __LINE__;
in_reply_to = NULL;
goto err_bad_call_stack;
}
thread->transaction_stack = in_reply_to->to_parent;
- target_thread = in_reply_to->from;
+ binder_inner_proc_unlock(proc);
+ target_thread = binder_get_txn_from_and_acq_inner(in_reply_to);
if (target_thread == NULL) {
return_error = BR_DEAD_REPLY;
+ return_error_line = __LINE__;
goto err_dead_binder;
}
if (target_thread->transaction_stack != in_reply_to) {
@@ -1396,110 +3055,162 @@ static void binder_transaction(struct binder_proc *proc,
target_thread->transaction_stack ?
target_thread->transaction_stack->debug_id : 0,
in_reply_to->debug_id);
+ binder_inner_proc_unlock(target_thread->proc);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EPROTO;
+ return_error_line = __LINE__;
in_reply_to = NULL;
target_thread = NULL;
goto err_dead_binder;
}
target_proc = target_thread->proc;
+ atomic_inc(&target_proc->tmp_ref);
+ binder_inner_proc_unlock(target_thread->proc);
} else {
if (tr->target.handle) {
struct binder_ref *ref;
- ref = binder_get_ref(proc, tr->target.handle, true);
- if (ref == NULL) {
+ /*
+ * There must already be a strong ref
+ * on this node. If so, do a strong
+ * increment on the node to ensure it
+ * stays alive until the transaction is
+ * done.
+ */
+ binder_proc_lock(proc);
+ ref = binder_get_ref_olocked(proc, tr->target.handle,
+ true);
+ if (ref) {
+ target_node = binder_get_node_refs_for_txn(
+ ref->node, &target_proc,
+ &return_error);
+ } else {
binder_user_error("%d:%d got transaction to invalid handle\n",
- proc->pid, thread->pid);
+ proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
+ }
+ binder_proc_unlock(proc);
+ } else {
+ mutex_lock(&context->context_mgr_node_lock);
+ target_node = context->binder_context_mgr_node;
+ if (target_node)
+ target_node = binder_get_node_refs_for_txn(
+ target_node, &target_proc,
+ &return_error);
+ else
+ return_error = BR_DEAD_REPLY;
+ mutex_unlock(&context->context_mgr_node_lock);
+ if (target_node && target_proc == proc) {
+ binder_user_error("%d:%d got transaction to context manager from process owning it\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_invalid_target_handle;
}
- target_node = ref->node;
- } else {
- target_node = binder_context_mgr_node;
- if (target_node == NULL) {
- return_error = BR_DEAD_REPLY;
- goto err_no_context_mgr_node;
- }
}
- e->to_node = target_node->debug_id;
- target_proc = target_node->proc;
- if (target_proc == NULL) {
- return_error = BR_DEAD_REPLY;
+ if (!target_node) {
+ /*
+ * return_error is set above
+ */
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_dead_binder;
}
+ e->to_node = target_node->debug_id;
if (WARN_ON(proc == target_proc)) {
return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_invalid_target_handle;
}
if (security_binder_transaction(proc->tsk,
target_proc->tsk) < 0) {
return_error = BR_FAILED_REPLY;
+ return_error_param = -EPERM;
+ return_error_line = __LINE__;
goto err_invalid_target_handle;
}
+ binder_inner_proc_lock(proc);
if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) {
struct binder_transaction *tmp;
tmp = thread->transaction_stack;
if (tmp->to_thread != thread) {
+ spin_lock(&tmp->lock);
binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n",
proc->pid, thread->pid, tmp->debug_id,
tmp->to_proc ? tmp->to_proc->pid : 0,
tmp->to_thread ?
tmp->to_thread->pid : 0);
+ spin_unlock(&tmp->lock);
+ binder_inner_proc_unlock(proc);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EPROTO;
+ return_error_line = __LINE__;
goto err_bad_call_stack;
}
while (tmp) {
- if (tmp->from && tmp->from->proc == target_proc)
- target_thread = tmp->from;
+ struct binder_thread *from;
+
+ spin_lock(&tmp->lock);
+ from = tmp->from;
+ if (from && from->proc == target_proc) {
+ atomic_inc(&from->tmp_ref);
+ target_thread = from;
+ spin_unlock(&tmp->lock);
+ break;
+ }
+ spin_unlock(&tmp->lock);
tmp = tmp->from_parent;
}
}
+ binder_inner_proc_unlock(proc);
}
- if (target_thread) {
+ if (target_thread)
e->to_thread = target_thread->pid;
- target_list = &target_thread->todo;
- target_wait = &target_thread->wait;
- } else {
- target_list = &target_proc->todo;
- target_wait = &target_proc->wait;
- }
e->to_proc = target_proc->pid;
/* TODO: reuse incoming transaction for reply */
t = kzalloc(sizeof(*t), GFP_KERNEL);
if (t == NULL) {
return_error = BR_FAILED_REPLY;
+ return_error_param = -ENOMEM;
+ return_error_line = __LINE__;
goto err_alloc_t_failed;
}
binder_stats_created(BINDER_STAT_TRANSACTION);
+ spin_lock_init(&t->lock);
tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL);
if (tcomplete == NULL) {
return_error = BR_FAILED_REPLY;
+ return_error_param = -ENOMEM;
+ return_error_line = __LINE__;
goto err_alloc_tcomplete_failed;
}
binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE);
- t->debug_id = ++binder_last_id;
- e->debug_id = t->debug_id;
+ t->debug_id = t_debug_id;
if (reply)
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld\n",
+ "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld-%lld\n",
proc->pid, thread->pid, t->debug_id,
target_proc->pid, target_thread->pid,
(u64)tr->data.ptr.buffer,
(u64)tr->data.ptr.offsets,
- (u64)tr->data_size, (u64)tr->offsets_size);
+ (u64)tr->data_size, (u64)tr->offsets_size,
+ (u64)extra_buffers_size);
else
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld\n",
+ "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld-%lld\n",
proc->pid, thread->pid, t->debug_id,
target_proc->pid, target_node->debug_id,
(u64)tr->data.ptr.buffer,
(u64)tr->data.ptr.offsets,
- (u64)tr->data_size, (u64)tr->offsets_size);
+ (u64)tr->data_size, (u64)tr->offsets_size,
+ (u64)extra_buffers_size);
if (!reply && !(tr->flags & TF_ONE_WAY))
t->from = thread;
@@ -1510,265 +3221,390 @@ static void binder_transaction(struct binder_proc *proc,
t->to_thread = target_thread;
t->code = tr->code;
t->flags = tr->flags;
- t->priority = task_nice(current);
+ if (!(t->flags & TF_ONE_WAY) &&
+ binder_supported_policy(current->policy)) {
+ /* Inherit supported policies for synchronous transactions */
+ t->priority.sched_policy = current->policy;
+ t->priority.prio = current->normal_prio;
+ } else {
+ /* Otherwise, fall back to the default priority */
+ t->priority = target_proc->default_priority;
+ }
+
+ if (target_node && target_node->txn_security_ctx) {
+ u32 secid;
+ size_t added_size;
+
+ security_task_getsecid(proc->tsk, &secid);
+ ret = security_secid_to_secctx(secid, &secctx, &secctx_sz);
+ if (ret) {
+ return_error = BR_FAILED_REPLY;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_get_secctx_failed;
+ }
+ added_size = ALIGN(secctx_sz, sizeof(u64));
+ extra_buffers_size += added_size;
+ if (extra_buffers_size < added_size) {
+ /* integer overflow of extra_buffers_size */
+ return_error = BR_FAILED_REPLY;
+ return_error_param = EINVAL;
+ return_error_line = __LINE__;
+ goto err_bad_extra_size;
+ }
+ }
trace_binder_transaction(reply, t, target_node);
- t->buffer = binder_alloc_buf(target_proc, tr->data_size,
- tr->offsets_size, !reply && (t->flags & TF_ONE_WAY));
- if (t->buffer == NULL) {
- return_error = BR_FAILED_REPLY;
+ t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size,
+ tr->offsets_size, extra_buffers_size,
+ !reply && (t->flags & TF_ONE_WAY));
+ if (IS_ERR(t->buffer)) {
+ /*
+ * -ESRCH indicates VMA cleared. The target is dying.
+ */
+ return_error_param = PTR_ERR(t->buffer);
+ return_error = return_error_param == -ESRCH ?
+ BR_DEAD_REPLY : BR_FAILED_REPLY;
+ return_error_line = __LINE__;
+ t->buffer = NULL;
goto err_binder_alloc_buf_failed;
}
- t->buffer->allow_user_free = 0;
+ if (secctx) {
+ size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) +
+ ALIGN(tr->offsets_size, sizeof(void *)) +
+ ALIGN(extra_buffers_size, sizeof(void *)) -
+ ALIGN(secctx_sz, sizeof(u64));
+
+ t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset;
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, buf_offset,
+ secctx, secctx_sz);
+ security_release_secctx(secctx, secctx_sz);
+ secctx = NULL;
+ }
t->buffer->debug_id = t->debug_id;
t->buffer->transaction = t;
t->buffer->target_node = target_node;
trace_binder_transaction_alloc_buf(t->buffer);
- if (target_node)
- binder_inc_node(target_node, 1, 0, NULL);
- offp = (binder_size_t *)(t->buffer->data +
- ALIGN(tr->data_size, sizeof(void *)));
-
- if (copy_from_user(t->buffer->data, (const void __user *)(uintptr_t)
- tr->data.ptr.buffer, tr->data_size)) {
+ if (binder_alloc_copy_user_to_buffer(
+ &target_proc->alloc,
+ t->buffer, 0,
+ (const void __user *)
+ (uintptr_t)tr->data.ptr.buffer,
+ tr->data_size)) {
binder_user_error("%d:%d got transaction with invalid data ptr\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EFAULT;
+ return_error_line = __LINE__;
goto err_copy_data_failed;
}
- if (copy_from_user(offp, (const void __user *)(uintptr_t)
- tr->data.ptr.offsets, tr->offsets_size)) {
+ if (binder_alloc_copy_user_to_buffer(
+ &target_proc->alloc,
+ t->buffer,
+ ALIGN(tr->data_size, sizeof(void *)),
+ (const void __user *)
+ (uintptr_t)tr->data.ptr.offsets,
+ tr->offsets_size)) {
binder_user_error("%d:%d got transaction with invalid offsets ptr\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EFAULT;
+ return_error_line = __LINE__;
goto err_copy_data_failed;
}
if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) {
binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n",
proc->pid, thread->pid, (u64)tr->offsets_size);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_bad_offset;
}
- off_end = (void *)offp + tr->offsets_size;
+ if (!IS_ALIGNED(extra_buffers_size, sizeof(u64))) {
+ binder_user_error("%d:%d got transaction with unaligned buffers size, %lld\n",
+ proc->pid, thread->pid,
+ (u64)extra_buffers_size);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_bad_offset;
+ }
+ off_start_offset = ALIGN(tr->data_size, sizeof(void *));
+ buffer_offset = off_start_offset;
+ off_end_offset = off_start_offset + tr->offsets_size;
+ sg_buf_offset = ALIGN(off_end_offset, sizeof(void *));
+ sg_buf_end_offset = sg_buf_offset + extra_buffers_size -
+ ALIGN(secctx_sz, sizeof(u64));
off_min = 0;
- for (; offp < off_end; offp++) {
- struct flat_binder_object *fp;
+ for (buffer_offset = off_start_offset; buffer_offset < off_end_offset;
+ buffer_offset += sizeof(binder_size_t)) {
+ struct binder_object_header *hdr;
+ size_t object_size;
+ struct binder_object object;
+ binder_size_t object_offset;
- if (*offp > t->buffer->data_size - sizeof(*fp) ||
- *offp < off_min ||
- t->buffer->data_size < sizeof(*fp) ||
- !IS_ALIGNED(*offp, sizeof(u32))) {
- binder_user_error("%d:%d got transaction with invalid offset, %lld (min %lld, max %lld)\n",
- proc->pid, thread->pid, (u64)*offp,
+ binder_alloc_copy_from_buffer(&target_proc->alloc,
+ &object_offset,
+ t->buffer,
+ buffer_offset,
+ sizeof(object_offset));
+ object_size = binder_get_object(target_proc, t->buffer,
+ object_offset, &object);
+ if (object_size == 0 || object_offset < off_min) {
+ binder_user_error("%d:%d got transaction with invalid offset (%lld, min %lld max %lld) or object.\n",
+ proc->pid, thread->pid,
+ (u64)object_offset,
(u64)off_min,
- (u64)(t->buffer->data_size -
- sizeof(*fp)));
+ (u64)t->buffer->data_size);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_bad_offset;
}
- fp = (struct flat_binder_object *)(t->buffer->data + *offp);
- off_min = *offp + sizeof(struct flat_binder_object);
- switch (fp->type) {
+
+ hdr = &object.hdr;
+ off_min = object_offset + object_size;
+ switch (hdr->type) {
case BINDER_TYPE_BINDER:
case BINDER_TYPE_WEAK_BINDER: {
- struct binder_ref *ref;
- struct binder_node *node = binder_get_node(proc, fp->binder);
+ struct flat_binder_object *fp;
- if (node == NULL) {
- node = binder_new_node(proc, fp->binder, fp->cookie);
- if (node == NULL) {
- return_error = BR_FAILED_REPLY;
- goto err_binder_new_node_failed;
- }
- node->min_priority = fp->flags & FLAT_BINDER_FLAG_PRIORITY_MASK;
- node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS);
- }
- if (fp->cookie != node->cookie) {
- binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n",
- proc->pid, thread->pid,
- (u64)fp->binder, node->debug_id,
- (u64)fp->cookie, (u64)node->cookie);
+ fp = to_flat_binder_object(hdr);
+ ret = binder_translate_binder(fp, t, thread);
+ if (ret < 0) {
return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_for_node_failed;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
}
- if (security_binder_transfer_binder(proc->tsk,
- target_proc->tsk)) {
- return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_for_node_failed;
- }
- ref = binder_get_ref_for_node(target_proc, node);
- if (ref == NULL) {
- return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_for_node_failed;
- }
- if (fp->type == BINDER_TYPE_BINDER)
- fp->type = BINDER_TYPE_HANDLE;
- else
- fp->type = BINDER_TYPE_WEAK_HANDLE;
- fp->binder = 0;
- fp->handle = ref->desc;
- fp->cookie = 0;
- binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
- &thread->todo);
-
- trace_binder_transaction_node_to_ref(t, node, ref);
- binder_debug(BINDER_DEBUG_TRANSACTION,
- " node %d u%016llx -> ref %d desc %d\n",
- node->debug_id, (u64)node->ptr,
- ref->debug_id, ref->desc);
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, object_offset,
+ fp, sizeof(*fp));
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref;
+ struct flat_binder_object *fp;
- ref = binder_get_ref(proc, fp->handle,
- fp->type == BINDER_TYPE_HANDLE);
-
- if (ref == NULL) {
- binder_user_error("%d:%d got transaction with invalid handle, %d\n",
- proc->pid,
- thread->pid, fp->handle);
+ fp = to_flat_binder_object(hdr);
+ ret = binder_translate_handle(fp, t, thread);
+ if (ret < 0) {
return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_failed;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
}
- if (security_binder_transfer_binder(proc->tsk,
- target_proc->tsk)) {
- return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_failed;
- }
- if (ref->node->proc == target_proc) {
- if (fp->type == BINDER_TYPE_HANDLE)
- fp->type = BINDER_TYPE_BINDER;
- else
- fp->type = BINDER_TYPE_WEAK_BINDER;
- fp->binder = ref->node->ptr;
- fp->cookie = ref->node->cookie;
- binder_inc_node(ref->node, fp->type == BINDER_TYPE_BINDER, 0, NULL);
- trace_binder_transaction_ref_to_node(t, ref);
- binder_debug(BINDER_DEBUG_TRANSACTION,
- " ref %d desc %d -> node %d u%016llx\n",
- ref->debug_id, ref->desc, ref->node->debug_id,
- (u64)ref->node->ptr);
- } else {
- struct binder_ref *new_ref;
-
- new_ref = binder_get_ref_for_node(target_proc, ref->node);
- if (new_ref == NULL) {
- return_error = BR_FAILED_REPLY;
- goto err_binder_get_ref_for_node_failed;
- }
- fp->binder = 0;
- fp->handle = new_ref->desc;
- fp->cookie = 0;
- binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
- trace_binder_transaction_ref_to_ref(t, ref,
- new_ref);
- binder_debug(BINDER_DEBUG_TRANSACTION,
- " ref %d desc %d -> ref %d desc %d (node %d)\n",
- ref->debug_id, ref->desc, new_ref->debug_id,
- new_ref->desc, ref->node->debug_id);
- }
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, object_offset,
+ fp, sizeof(*fp));
} break;
case BINDER_TYPE_FD: {
- int target_fd;
- struct file *file;
+ struct binder_fd_object *fp = to_binder_fd_object(hdr);
+ int target_fd = binder_translate_fd(fp->fd, t, thread,
+ in_reply_to);
- if (reply) {
- if (!(in_reply_to->flags & TF_ACCEPT_FDS)) {
- binder_user_error("%d:%d got reply with fd, %d, but target does not allow fds\n",
- proc->pid, thread->pid, fp->handle);
- return_error = BR_FAILED_REPLY;
- goto err_fd_not_allowed;
- }
- } else if (!target_node->accept_fds) {
- binder_user_error("%d:%d got transaction with fd, %d, but target does not allow fds\n",
- proc->pid, thread->pid, fp->handle);
- return_error = BR_FAILED_REPLY;
- goto err_fd_not_allowed;
- }
-
- file = fget(fp->handle);
- if (file == NULL) {
- binder_user_error("%d:%d got transaction with invalid fd, %d\n",
- proc->pid, thread->pid, fp->handle);
- return_error = BR_FAILED_REPLY;
- goto err_fget_failed;
- }
- if (security_binder_transfer_file(proc->tsk,
- target_proc->tsk,
- file) < 0) {
- fput(file);
- return_error = BR_FAILED_REPLY;
- goto err_get_unused_fd_failed;
- }
- target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
if (target_fd < 0) {
- fput(file);
return_error = BR_FAILED_REPLY;
- goto err_get_unused_fd_failed;
+ return_error_param = target_fd;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
}
- task_fd_install(target_proc, target_fd, file);
- trace_binder_transaction_fd(t, fp->handle, target_fd);
- binder_debug(BINDER_DEBUG_TRANSACTION,
- " fd %d -> %d\n", fp->handle, target_fd);
- /* TODO: fput? */
- fp->binder = 0;
- fp->handle = target_fd;
+ fp->pad_binder = 0;
+ fp->fd = target_fd;
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, object_offset,
+ fp, sizeof(*fp));
} break;
+ case BINDER_TYPE_FDA: {
+ struct binder_object ptr_object;
+ binder_size_t parent_offset;
+ struct binder_fd_array_object *fda =
+ to_binder_fd_array_object(hdr);
+ size_t num_valid = (buffer_offset - off_start_offset) /
+ sizeof(binder_size_t);
+ struct binder_buffer_object *parent =
+ binder_validate_ptr(target_proc, t->buffer,
+ &ptr_object, fda->parent,
+ off_start_offset,
+ &parent_offset,
+ num_valid);
+ if (!parent) {
+ binder_user_error("%d:%d got transaction with invalid parent offset or type\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_bad_parent;
+ }
+ if (!binder_validate_fixup(target_proc, t->buffer,
+ off_start_offset,
+ parent_offset,
+ fda->parent_offset,
+ last_fixup_obj_off,
+ last_fixup_min_off)) {
+ binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_bad_parent;
+ }
+ ret = binder_translate_fd_array(fda, parent, t, thread,
+ in_reply_to);
+ if (ret < 0) {
+ return_error = BR_FAILED_REPLY;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
+ }
+ last_fixup_obj_off = parent_offset;
+ last_fixup_min_off =
+ fda->parent_offset + sizeof(u32) * fda->num_fds;
+ } break;
+ case BINDER_TYPE_PTR: {
+ struct binder_buffer_object *bp =
+ to_binder_buffer_object(hdr);
+ size_t buf_left = sg_buf_end_offset - sg_buf_offset;
+ size_t num_valid;
+ if (bp->length > buf_left) {
+ binder_user_error("%d:%d got transaction with too large buffer\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_bad_offset;
+ }
+ if (binder_alloc_copy_user_to_buffer(
+ &target_proc->alloc,
+ t->buffer,
+ sg_buf_offset,
+ (const void __user *)
+ (uintptr_t)bp->buffer,
+ bp->length)) {
+ binder_user_error("%d:%d got transaction with invalid offsets ptr\n",
+ proc->pid, thread->pid);
+ return_error_param = -EFAULT;
+ return_error = BR_FAILED_REPLY;
+ return_error_line = __LINE__;
+ goto err_copy_data_failed;
+ }
+ /* Fixup buffer pointer to target proc address space */
+ bp->buffer = (uintptr_t)
+ t->buffer->user_data + sg_buf_offset;
+ sg_buf_offset += ALIGN(bp->length, sizeof(u64));
+
+ num_valid = (buffer_offset - off_start_offset) /
+ sizeof(binder_size_t);
+ ret = binder_fixup_parent(t, thread, bp,
+ off_start_offset,
+ num_valid,
+ last_fixup_obj_off,
+ last_fixup_min_off);
+ if (ret < 0) {
+ return_error = BR_FAILED_REPLY;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
+ }
+ binder_alloc_copy_to_buffer(&target_proc->alloc,
+ t->buffer, object_offset,
+ bp, sizeof(*bp));
+ last_fixup_obj_off = object_offset;
+ last_fixup_min_off = 0;
+ } break;
default:
binder_user_error("%d:%d got transaction with invalid object type, %x\n",
- proc->pid, thread->pid, fp->type);
+ proc->pid, thread->pid, hdr->type);
return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
goto err_bad_object_type;
}
}
+ tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
+ t->work.type = BINDER_WORK_TRANSACTION;
+
if (reply) {
+ binder_enqueue_thread_work(thread, tcomplete);
+ binder_inner_proc_lock(target_proc);
+ if (target_thread->is_dead) {
+ binder_inner_proc_unlock(target_proc);
+ goto err_dead_proc_or_thread;
+ }
BUG_ON(t->buffer->async_transaction != 0);
- binder_pop_transaction(target_thread, in_reply_to);
+ binder_pop_transaction_ilocked(target_thread, in_reply_to);
+ binder_enqueue_thread_work_ilocked(target_thread, &t->work);
+ binder_inner_proc_unlock(target_proc);
+ wake_up_interruptible_sync(&target_thread->wait);
+ binder_restore_priority(current, in_reply_to->saved_priority);
+ binder_free_transaction(in_reply_to);
} else if (!(t->flags & TF_ONE_WAY)) {
BUG_ON(t->buffer->async_transaction != 0);
+ binder_inner_proc_lock(proc);
+ /*
+ * Defer the TRANSACTION_COMPLETE, so we don't return to
+ * userspace immediately; this allows the target process to
+ * immediately start processing this transaction, reducing
+ * latency. We will then return the TRANSACTION_COMPLETE when
+ * the target replies (or there is an error).
+ */
+ binder_enqueue_deferred_thread_work_ilocked(thread, tcomplete);
t->need_reply = 1;
t->from_parent = thread->transaction_stack;
thread->transaction_stack = t;
+ binder_inner_proc_unlock(proc);
+ if (!binder_proc_transaction(t, target_proc, target_thread)) {
+ binder_inner_proc_lock(proc);
+ binder_pop_transaction_ilocked(thread, t);
+ binder_inner_proc_unlock(proc);
+ goto err_dead_proc_or_thread;
+ }
} else {
BUG_ON(target_node == NULL);
BUG_ON(t->buffer->async_transaction != 1);
- if (target_node->has_async_transaction) {
- target_list = &target_node->async_todo;
- target_wait = NULL;
- } else
- target_node->has_async_transaction = 1;
+ binder_enqueue_thread_work(thread, tcomplete);
+ if (!binder_proc_transaction(t, target_proc, NULL))
+ goto err_dead_proc_or_thread;
}
- t->work.type = BINDER_WORK_TRANSACTION;
- list_add_tail(&t->work.entry, target_list);
- tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
- list_add_tail(&tcomplete->entry, &thread->todo);
- if (target_wait) {
- if (reply || !(t->flags & TF_ONE_WAY))
- wake_up_interruptible_sync(target_wait);
- else
- wake_up_interruptible(target_wait);
- }
+ if (target_thread)
+ binder_thread_dec_tmpref(target_thread);
+ binder_proc_dec_tmpref(target_proc);
+ if (target_node)
+ binder_dec_node_tmpref(target_node);
+ /*
+ * write barrier to synchronize with initialization
+ * of log entry
+ */
+ smp_wmb();
+ WRITE_ONCE(e->debug_id_done, t_debug_id);
return;
-err_get_unused_fd_failed:
-err_fget_failed:
-err_fd_not_allowed:
-err_binder_get_ref_for_node_failed:
-err_binder_get_ref_failed:
-err_binder_new_node_failed:
+err_dead_proc_or_thread:
+ return_error = BR_DEAD_REPLY;
+ return_error_line = __LINE__;
+ binder_dequeue_work(proc, tcomplete);
+err_translate_failed:
err_bad_object_type:
err_bad_offset:
+err_bad_parent:
err_copy_data_failed:
trace_binder_transaction_failed_buffer_release(t->buffer);
- binder_transaction_buffer_release(target_proc, t->buffer, offp);
+ binder_transaction_buffer_release(target_proc, t->buffer,
+ buffer_offset, true);
+ if (target_node)
+ binder_dec_node_tmpref(target_node);
+ target_node = NULL;
t->buffer->transaction = NULL;
- binder_free_buf(target_proc, t->buffer);
+ binder_alloc_free_buf(&target_proc->alloc, t->buffer);
err_binder_alloc_buf_failed:
+err_bad_extra_size:
+ if (secctx)
+ security_release_secctx(secctx, secctx_sz);
+err_get_secctx_failed:
kfree(tcomplete);
binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
err_alloc_tcomplete_failed:
@@ -1779,25 +3615,48 @@ static void binder_transaction(struct binder_proc *proc,
err_empty_call_stack:
err_dead_binder:
err_invalid_target_handle:
-err_no_context_mgr_node:
+ if (target_thread)
+ binder_thread_dec_tmpref(target_thread);
+ if (target_proc)
+ binder_proc_dec_tmpref(target_proc);
+ if (target_node) {
+ binder_dec_node(target_node, 1, 0);
+ binder_dec_node_tmpref(target_node);
+ }
+
binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
- "%d:%d transaction failed %d, size %lld-%lld\n",
- proc->pid, thread->pid, return_error,
- (u64)tr->data_size, (u64)tr->offsets_size);
+ "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n",
+ proc->pid, thread->pid, return_error, return_error_param,
+ (u64)tr->data_size, (u64)tr->offsets_size,
+ return_error_line);
{
struct binder_transaction_log_entry *fe;
+ e->return_error = return_error;
+ e->return_error_param = return_error_param;
+ e->return_error_line = return_error_line;
fe = binder_transaction_log_add(&binder_transaction_log_failed);
*fe = *e;
+ /*
+ * write barrier to synchronize with initialization
+ * of log entry
+ */
+ smp_wmb();
+ WRITE_ONCE(e->debug_id_done, t_debug_id);
+ WRITE_ONCE(fe->debug_id_done, t_debug_id);
}
- BUG_ON(thread->return_error != BR_OK);
+ BUG_ON(thread->return_error.cmd != BR_OK);
if (in_reply_to) {
- thread->return_error = BR_TRANSACTION_COMPLETE;
+ binder_restore_priority(current, in_reply_to->saved_priority);
+ thread->return_error.cmd = BR_TRANSACTION_COMPLETE;
+ binder_enqueue_thread_work(thread, &thread->return_error.work);
binder_send_failed_reply(in_reply_to, return_error);
- } else
- thread->return_error = return_error;
+ } else {
+ thread->return_error.cmd = return_error;
+ binder_enqueue_thread_work(thread, &thread->return_error.work);
+ }
}
static int binder_thread_write(struct binder_proc *proc,
@@ -1806,19 +3665,22 @@ static int binder_thread_write(struct binder_proc *proc,
binder_size_t *consumed)
{
uint32_t cmd;
+ struct binder_context *context = proc->context;
void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
void __user *ptr = buffer + *consumed;
void __user *end = buffer + size;
- while (ptr < end && thread->return_error == BR_OK) {
+ while (ptr < end && thread->return_error.cmd == BR_OK) {
+ int ret;
+
if (get_user(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
trace_binder_command(cmd);
if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) {
- binder_stats.bc[_IOC_NR(cmd)]++;
- proc->stats.bc[_IOC_NR(cmd)]++;
- thread->stats.bc[_IOC_NR(cmd)]++;
+ atomic_inc(&binder_stats.bc[_IOC_NR(cmd)]);
+ atomic_inc(&proc->stats.bc[_IOC_NR(cmd)]);
+ atomic_inc(&thread->stats.bc[_IOC_NR(cmd)]);
}
switch (cmd) {
case BC_INCREFS:
@@ -1826,58 +3688,68 @@ static int binder_thread_write(struct binder_proc *proc,
case BC_RELEASE:
case BC_DECREFS: {
uint32_t target;
- struct binder_ref *ref;
const char *debug_string;
+ bool strong = cmd == BC_ACQUIRE || cmd == BC_RELEASE;
+ bool increment = cmd == BC_INCREFS || cmd == BC_ACQUIRE;
+ struct binder_ref_data rdata;
if (get_user(target, (uint32_t __user *)ptr))
return -EFAULT;
+
ptr += sizeof(uint32_t);
- if (target == 0 && binder_context_mgr_node &&
- (cmd == BC_INCREFS || cmd == BC_ACQUIRE)) {
- if (binder_context_mgr_node->proc == proc) {
- binder_user_error("%d:%d context manager tried to acquire desc 0\n",
- proc->pid, thread->pid);
- return -EINVAL;
+ ret = -1;
+ if (increment && !target) {
+ struct binder_node *ctx_mgr_node;
+ mutex_lock(&context->context_mgr_node_lock);
+ ctx_mgr_node = context->binder_context_mgr_node;
+ if (ctx_mgr_node) {
+ if (ctx_mgr_node->proc == proc) {
+ binder_user_error("%d:%d context manager tried to acquire desc 0\n",
+ proc->pid, thread->pid);
+ mutex_unlock(&context->context_mgr_node_lock);
+ return -EINVAL;
+ }
+ ret = binder_inc_ref_for_node(
+ proc, ctx_mgr_node,
+ strong, NULL, &rdata);
}
- ref = binder_get_ref_for_node(proc,
- binder_context_mgr_node);
- if (ref->desc != target) {
- binder_user_error("%d:%d tried to acquire reference to desc 0, got %d instead\n",
- proc->pid, thread->pid,
- ref->desc);
- }
- } else
- ref = binder_get_ref(proc, target,
- cmd == BC_ACQUIRE ||
- cmd == BC_RELEASE);
- if (ref == NULL) {
- binder_user_error("%d:%d refcount change on invalid ref %d\n",
- proc->pid, thread->pid, target);
- break;
+ mutex_unlock(&context->context_mgr_node_lock);
+ }
+ if (ret)
+ ret = binder_update_ref_for_handle(
+ proc, target, increment, strong,
+ &rdata);
+ if (!ret && rdata.desc != target) {
+ binder_user_error("%d:%d tried to acquire reference to desc %d, got %d instead\n",
+ proc->pid, thread->pid,
+ target, rdata.desc);
}
switch (cmd) {
case BC_INCREFS:
debug_string = "IncRefs";
- binder_inc_ref(ref, 0, NULL);
break;
case BC_ACQUIRE:
debug_string = "Acquire";
- binder_inc_ref(ref, 1, NULL);
break;
case BC_RELEASE:
debug_string = "Release";
- binder_dec_ref(ref, 1);
break;
case BC_DECREFS:
default:
debug_string = "DecRefs";
- binder_dec_ref(ref, 0);
+ break;
+ }
+ if (ret) {
+ binder_user_error("%d:%d %s %d refcount change on invalid ref %d ret %d\n",
+ proc->pid, thread->pid, debug_string,
+ strong, target, ret);
break;
}
binder_debug(BINDER_DEBUG_USER_REFS,
- "%d:%d %s ref %d desc %d s %d w %d for node %d\n",
- proc->pid, thread->pid, debug_string, ref->debug_id,
- ref->desc, ref->strong, ref->weak, ref->node->debug_id);
+ "%d:%d %s ref %d desc %d s %d w %d\n",
+ proc->pid, thread->pid, debug_string,
+ rdata.debug_id, rdata.desc, rdata.strong,
+ rdata.weak);
break;
}
case BC_INCREFS_DONE:
@@ -1885,6 +3757,7 @@ static int binder_thread_write(struct binder_proc *proc,
binder_uintptr_t node_ptr;
binder_uintptr_t cookie;
struct binder_node *node;
+ bool free_node;
if (get_user(node_ptr, (binder_uintptr_t __user *)ptr))
return -EFAULT;
@@ -1909,13 +3782,17 @@ static int binder_thread_write(struct binder_proc *proc,
"BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
(u64)node_ptr, node->debug_id,
(u64)cookie, (u64)node->cookie);
+ binder_put_node(node);
break;
}
+ binder_node_inner_lock(node);
if (cmd == BC_ACQUIRE_DONE) {
if (node->pending_strong_ref == 0) {
binder_user_error("%d:%d BC_ACQUIRE_DONE node %d has no pending acquire request\n",
proc->pid, thread->pid,
node->debug_id);
+ binder_node_inner_unlock(node);
+ binder_put_node(node);
break;
}
node->pending_strong_ref = 0;
@@ -1924,16 +3801,23 @@ static int binder_thread_write(struct binder_proc *proc,
binder_user_error("%d:%d BC_INCREFS_DONE node %d has no pending increfs request\n",
proc->pid, thread->pid,
node->debug_id);
+ binder_node_inner_unlock(node);
+ binder_put_node(node);
break;
}
node->pending_weak_ref = 0;
}
- binder_dec_node(node, cmd == BC_ACQUIRE_DONE, 0);
+ free_node = binder_dec_node_nilocked(node,
+ cmd == BC_ACQUIRE_DONE, 0);
+ WARN_ON(free_node);
binder_debug(BINDER_DEBUG_USER_REFS,
- "%d:%d %s node %d ls %d lw %d\n",
+ "%d:%d %s node %d ls %d lw %d tr %d\n",
proc->pid, thread->pid,
cmd == BC_INCREFS_DONE ? "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
- node->debug_id, node->local_strong_refs, node->local_weak_refs);
+ node->debug_id, node->local_strong_refs,
+ node->local_weak_refs, node->tmp_refs);
+ binder_node_inner_unlock(node);
+ binder_put_node(node);
break;
}
case BC_ATTEMPT_ACQUIRE:
@@ -1951,15 +3835,20 @@ static int binder_thread_write(struct binder_proc *proc,
return -EFAULT;
ptr += sizeof(binder_uintptr_t);
- buffer = binder_buffer_lookup(proc, data_ptr);
- if (buffer == NULL) {
- binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n",
- proc->pid, thread->pid, (u64)data_ptr);
- break;
- }
- if (!buffer->allow_user_free) {
- binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n",
- proc->pid, thread->pid, (u64)data_ptr);
+ buffer = binder_alloc_prepare_to_free(&proc->alloc,
+ data_ptr);
+ if (IS_ERR_OR_NULL(buffer)) {
+ if (PTR_ERR(buffer) == -EPERM) {
+ binder_user_error(
+ "%d:%d BC_FREE_BUFFER u%016llx matched unreturned or currently freeing buffer\n",
+ proc->pid, thread->pid,
+ (u64)data_ptr);
+ } else {
+ binder_user_error(
+ "%d:%d BC_FREE_BUFFER u%016llx no match\n",
+ proc->pid, thread->pid,
+ (u64)data_ptr);
+ }
break;
}
binder_debug(BINDER_DEBUG_FREE_BUFFER,
@@ -1968,23 +3857,48 @@ static int binder_thread_write(struct binder_proc *proc,
buffer->debug_id,
buffer->transaction ? "active" : "finished");
+ binder_inner_proc_lock(proc);
if (buffer->transaction) {
buffer->transaction->buffer = NULL;
buffer->transaction = NULL;
}
+ binder_inner_proc_unlock(proc);
if (buffer->async_transaction && buffer->target_node) {
- BUG_ON(!buffer->target_node->has_async_transaction);
- if (list_empty(&buffer->target_node->async_todo))
- buffer->target_node->has_async_transaction = 0;
- else
- list_move_tail(buffer->target_node->async_todo.next, &thread->todo);
+ struct binder_node *buf_node;
+ struct binder_work *w;
+
+ buf_node = buffer->target_node;
+ binder_node_inner_lock(buf_node);
+ BUG_ON(!buf_node->has_async_transaction);
+ BUG_ON(buf_node->proc != proc);
+ w = binder_dequeue_work_head_ilocked(
+ &buf_node->async_todo);
+ if (!w) {
+ buf_node->has_async_transaction = false;
+ } else {
+ binder_enqueue_work_ilocked(
+ w, &proc->todo);
+ binder_wakeup_proc_ilocked(proc);
+ }
+ binder_node_inner_unlock(buf_node);
}
trace_binder_transaction_buffer_release(buffer);
- binder_transaction_buffer_release(proc, buffer, NULL);
- binder_free_buf(proc, buffer);
+ binder_transaction_buffer_release(proc, buffer, 0, false);
+ binder_alloc_free_buf(&proc->alloc, buffer);
break;
}
+ case BC_TRANSACTION_SG:
+ case BC_REPLY_SG: {
+ struct binder_transaction_data_sg tr;
+
+ if (copy_from_user(&tr, ptr, sizeof(tr)))
+ return -EFAULT;
+ ptr += sizeof(tr);
+ binder_transaction(proc, thread, &tr.transaction_data,
+ cmd == BC_REPLY_SG, tr.buffers_size);
+ break;
+ }
case BC_TRANSACTION:
case BC_REPLY: {
struct binder_transaction_data tr;
@@ -1992,7 +3906,8 @@ static int binder_thread_write(struct binder_proc *proc,
if (copy_from_user(&tr, ptr, sizeof(tr)))
return -EFAULT;
ptr += sizeof(tr);
- binder_transaction(proc, thread, &tr, cmd == BC_REPLY);
+ binder_transaction(proc, thread, &tr,
+ cmd == BC_REPLY, 0);
break;
}
@@ -2000,6 +3915,7 @@ static int binder_thread_write(struct binder_proc *proc,
binder_debug(BINDER_DEBUG_THREADS,
"%d:%d BC_REGISTER_LOOPER\n",
proc->pid, thread->pid);
+ binder_inner_proc_lock(proc);
if (thread->looper & BINDER_LOOPER_STATE_ENTERED) {
thread->looper |= BINDER_LOOPER_STATE_INVALID;
binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called after BC_ENTER_LOOPER\n",
@@ -2013,6 +3929,7 @@ static int binder_thread_write(struct binder_proc *proc,
proc->requested_threads_started++;
}
thread->looper |= BINDER_LOOPER_STATE_REGISTERED;
+ binder_inner_proc_unlock(proc);
break;
case BC_ENTER_LOOPER:
binder_debug(BINDER_DEBUG_THREADS,
@@ -2037,7 +3954,7 @@ static int binder_thread_write(struct binder_proc *proc,
uint32_t target;
binder_uintptr_t cookie;
struct binder_ref *ref;
- struct binder_ref_death *death;
+ struct binder_ref_death *death = NULL;
if (get_user(target, (uint32_t __user *)ptr))
return -EFAULT;
@@ -2045,7 +3962,28 @@ static int binder_thread_write(struct binder_proc *proc,
if (get_user(cookie, (binder_uintptr_t __user *)ptr))
return -EFAULT;
ptr += sizeof(binder_uintptr_t);
- ref = binder_get_ref(proc, target, false);
+ if (cmd == BC_REQUEST_DEATH_NOTIFICATION) {
+ /*
+ * Allocate memory for death notification
+ * before taking lock
+ */
+ death = kzalloc(sizeof(*death), GFP_KERNEL);
+ if (death == NULL) {
+ WARN_ON(thread->return_error.cmd !=
+ BR_OK);
+ thread->return_error.cmd = BR_ERROR;
+ binder_enqueue_thread_work(
+ thread,
+ &thread->return_error.work);
+ binder_debug(
+ BINDER_DEBUG_FAILED_TRANSACTION,
+ "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n",
+ proc->pid, thread->pid);
+ break;
+ }
+ }
+ binder_proc_lock(proc);
+ ref = binder_get_ref_olocked(proc, target, false);
if (ref == NULL) {
binder_user_error("%d:%d %s invalid ref %d\n",
proc->pid, thread->pid,
@@ -2053,6 +3991,8 @@ static int binder_thread_write(struct binder_proc *proc,
"BC_REQUEST_DEATH_NOTIFICATION" :
"BC_CLEAR_DEATH_NOTIFICATION",
target);
+ binder_proc_unlock(proc);
+ kfree(death);
break;
}
@@ -2062,21 +4002,18 @@ static int binder_thread_write(struct binder_proc *proc,
cmd == BC_REQUEST_DEATH_NOTIFICATION ?
"BC_REQUEST_DEATH_NOTIFICATION" :
"BC_CLEAR_DEATH_NOTIFICATION",
- (u64)cookie, ref->debug_id, ref->desc,
- ref->strong, ref->weak, ref->node->debug_id);
+ (u64)cookie, ref->data.debug_id,
+ ref->data.desc, ref->data.strong,
+ ref->data.weak, ref->node->debug_id);
+ binder_node_lock(ref->node);
if (cmd == BC_REQUEST_DEATH_NOTIFICATION) {
if (ref->death) {
binder_user_error("%d:%d BC_REQUEST_DEATH_NOTIFICATION death notification already set\n",
proc->pid, thread->pid);
- break;
- }
- death = kzalloc(sizeof(*death), GFP_KERNEL);
- if (death == NULL) {
- thread->return_error = BR_ERROR;
- binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
- "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n",
- proc->pid, thread->pid);
+ binder_node_unlock(ref->node);
+ binder_proc_unlock(proc);
+ kfree(death);
break;
}
binder_stats_created(BINDER_STAT_DEATH);
@@ -2085,17 +4022,19 @@ static int binder_thread_write(struct binder_proc *proc,
ref->death = death;
if (ref->node->proc == NULL) {
ref->death->work.type = BINDER_WORK_DEAD_BINDER;
- if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
- list_add_tail(&ref->death->work.entry, &thread->todo);
- } else {
- list_add_tail(&ref->death->work.entry, &proc->todo);
- wake_up_interruptible(&proc->wait);
- }
+
+ binder_inner_proc_lock(proc);
+ binder_enqueue_work_ilocked(
+ &ref->death->work, &proc->todo);
+ binder_wakeup_proc_ilocked(proc);
+ binder_inner_proc_unlock(proc);
}
} else {
if (ref->death == NULL) {
binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification not active\n",
proc->pid, thread->pid);
+ binder_node_unlock(ref->node);
+ binder_proc_unlock(proc);
break;
}
death = ref->death;
@@ -2104,22 +4043,35 @@ static int binder_thread_write(struct binder_proc *proc,
proc->pid, thread->pid,
(u64)death->cookie,
(u64)cookie);
+ binder_node_unlock(ref->node);
+ binder_proc_unlock(proc);
break;
}
ref->death = NULL;
+ binder_inner_proc_lock(proc);
if (list_empty(&death->work.entry)) {
death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
- if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
- list_add_tail(&death->work.entry, &thread->todo);
- } else {
- list_add_tail(&death->work.entry, &proc->todo);
- wake_up_interruptible(&proc->wait);
+ if (thread->looper &
+ (BINDER_LOOPER_STATE_REGISTERED |
+ BINDER_LOOPER_STATE_ENTERED))
+ binder_enqueue_thread_work_ilocked(
+ thread,
+ &death->work);
+ else {
+ binder_enqueue_work_ilocked(
+ &death->work,
+ &proc->todo);
+ binder_wakeup_proc_ilocked(
+ proc);
}
} else {
BUG_ON(death->work.type != BINDER_WORK_DEAD_BINDER);
death->work.type = BINDER_WORK_DEAD_BINDER_AND_CLEAR;
}
+ binder_inner_proc_unlock(proc);
}
+ binder_node_unlock(ref->node);
+ binder_proc_unlock(proc);
} break;
case BC_DEAD_BINDER_DONE: {
struct binder_work *w;
@@ -2130,8 +4082,13 @@ static int binder_thread_write(struct binder_proc *proc,
return -EFAULT;
ptr += sizeof(cookie);
- list_for_each_entry(w, &proc->delivered_death, entry) {
- struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
+ binder_inner_proc_lock(proc);
+ list_for_each_entry(w, &proc->delivered_death,
+ entry) {
+ struct binder_ref_death *tmp_death =
+ container_of(w,
+ struct binder_ref_death,
+ work);
if (tmp_death->cookie == cookie) {
death = tmp_death;
@@ -2145,19 +4102,25 @@ static int binder_thread_write(struct binder_proc *proc,
if (death == NULL) {
binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n",
proc->pid, thread->pid, (u64)cookie);
+ binder_inner_proc_unlock(proc);
break;
}
-
- list_del_init(&death->work.entry);
+ binder_dequeue_work_ilocked(&death->work);
if (death->work.type == BINDER_WORK_DEAD_BINDER_AND_CLEAR) {
death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
- if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
- list_add_tail(&death->work.entry, &thread->todo);
- } else {
- list_add_tail(&death->work.entry, &proc->todo);
- wake_up_interruptible(&proc->wait);
+ if (thread->looper &
+ (BINDER_LOOPER_STATE_REGISTERED |
+ BINDER_LOOPER_STATE_ENTERED))
+ binder_enqueue_thread_work_ilocked(
+ thread, &death->work);
+ else {
+ binder_enqueue_work_ilocked(
+ &death->work,
+ &proc->todo);
+ binder_wakeup_proc_ilocked(proc);
}
}
+ binder_inner_proc_unlock(proc);
} break;
default:
@@ -2175,23 +4138,73 @@ static void binder_stat_br(struct binder_proc *proc,
{
trace_binder_return(cmd);
if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) {
- binder_stats.br[_IOC_NR(cmd)]++;
- proc->stats.br[_IOC_NR(cmd)]++;
- thread->stats.br[_IOC_NR(cmd)]++;
+ atomic_inc(&binder_stats.br[_IOC_NR(cmd)]);
+ atomic_inc(&proc->stats.br[_IOC_NR(cmd)]);
+ atomic_inc(&thread->stats.br[_IOC_NR(cmd)]);
}
}
-static int binder_has_proc_work(struct binder_proc *proc,
- struct binder_thread *thread)
+static int binder_put_node_cmd(struct binder_proc *proc,
+ struct binder_thread *thread,
+ void __user **ptrp,
+ binder_uintptr_t node_ptr,
+ binder_uintptr_t node_cookie,
+ int node_debug_id,
+ uint32_t cmd, const char *cmd_name)
{
- return !list_empty(&proc->todo) ||
- (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
+ void __user *ptr = *ptrp;
+
+ if (put_user(cmd, (uint32_t __user *)ptr))
+ return -EFAULT;
+ ptr += sizeof(uint32_t);
+
+ if (put_user(node_ptr, (binder_uintptr_t __user *)ptr))
+ return -EFAULT;
+ ptr += sizeof(binder_uintptr_t);
+
+ if (put_user(node_cookie, (binder_uintptr_t __user *)ptr))
+ return -EFAULT;
+ ptr += sizeof(binder_uintptr_t);
+
+ binder_stat_br(proc, thread, cmd);
+ binder_debug(BINDER_DEBUG_USER_REFS, "%d:%d %s %d u%016llx c%016llx\n",
+ proc->pid, thread->pid, cmd_name, node_debug_id,
+ (u64)node_ptr, (u64)node_cookie);
+
+ *ptrp = ptr;
+ return 0;
}
-static int binder_has_thread_work(struct binder_thread *thread)
+static int binder_wait_for_work(struct binder_thread *thread,
+ bool do_proc_work)
{
- return !list_empty(&thread->todo) || thread->return_error != BR_OK ||
- (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
+ DEFINE_WAIT(wait);
+ struct binder_proc *proc = thread->proc;
+ int ret = 0;
+
+ freezer_do_not_count();
+ binder_inner_proc_lock(proc);
+ for (;;) {
+ prepare_to_wait(&thread->wait, &wait, TASK_INTERRUPTIBLE);
+ if (binder_has_work_ilocked(thread, do_proc_work))
+ break;
+ if (do_proc_work)
+ list_add(&thread->waiting_thread_node,
+ &proc->waiting_threads);
+ binder_inner_proc_unlock(proc);
+ schedule();
+ binder_inner_proc_lock(proc);
+ list_del_init(&thread->waiting_thread_node);
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+ }
+ finish_wait(&thread->wait, &wait);
+ binder_inner_proc_unlock(proc);
+ freezer_count();
+
+ return ret;
}
static int binder_thread_read(struct binder_proc *proc,
@@ -2213,37 +4226,15 @@ static int binder_thread_read(struct binder_proc *proc,
}
retry:
- wait_for_proc_work = thread->transaction_stack == NULL &&
- list_empty(&thread->todo);
-
- if (thread->return_error != BR_OK && ptr < end) {
- if (thread->return_error2 != BR_OK) {
- if (put_user(thread->return_error2, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- binder_stat_br(proc, thread, thread->return_error2);
- if (ptr == end)
- goto done;
- thread->return_error2 = BR_OK;
- }
- if (put_user(thread->return_error, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- binder_stat_br(proc, thread, thread->return_error);
- thread->return_error = BR_OK;
- goto done;
- }
-
+ binder_inner_proc_lock(proc);
+ wait_for_proc_work = binder_available_for_proc_work_ilocked(thread);
+ binder_inner_proc_unlock(proc);
thread->looper |= BINDER_LOOPER_STATE_WAITING;
- if (wait_for_proc_work)
- proc->ready_threads++;
-
- binder_unlock(__func__);
trace_binder_wait_for_work(wait_for_proc_work,
!!thread->transaction_stack,
- !list_empty(&thread->todo));
+ !binder_worklist_empty(proc, &thread->todo));
if (wait_for_proc_work) {
if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
BINDER_LOOPER_STATE_ENTERED))) {
@@ -2252,24 +4243,16 @@ static int binder_thread_read(struct binder_proc *proc,
wait_event_interruptible(binder_user_error_wait,
binder_stop_on_user_error < 2);
}
- binder_set_nice(proc->default_priority);
- if (non_block) {
- if (!binder_has_proc_work(proc, thread))
- ret = -EAGAIN;
- } else
- ret = wait_event_freezable_exclusive(proc->wait, binder_has_proc_work(proc, thread));
- } else {
- if (non_block) {
- if (!binder_has_thread_work(thread))
- ret = -EAGAIN;
- } else
- ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread));
+ binder_restore_priority(current, proc->default_priority);
}
- binder_lock(__func__);
+ if (non_block) {
+ if (!binder_has_work(thread, wait_for_proc_work))
+ ret = -EAGAIN;
+ } else {
+ ret = binder_wait_for_work(thread, wait_for_proc_work);
+ }
- if (wait_for_proc_work)
- proc->ready_threads--;
thread->looper &= ~BINDER_LOOPER_STATE_WAITING;
if (ret)
@@ -2277,32 +4260,58 @@ static int binder_thread_read(struct binder_proc *proc,
while (1) {
uint32_t cmd;
- struct binder_transaction_data tr;
- struct binder_work *w;
+ struct binder_transaction_data_secctx tr;
+ struct binder_transaction_data *trd = &tr.transaction_data;
+ struct binder_work *w = NULL;
+ struct list_head *list = NULL;
struct binder_transaction *t = NULL;
+ struct binder_thread *t_from;
+ size_t trsize = sizeof(*trd);
- if (!list_empty(&thread->todo)) {
- w = list_first_entry(&thread->todo, struct binder_work,
- entry);
- } else if (!list_empty(&proc->todo) && wait_for_proc_work) {
- w = list_first_entry(&proc->todo, struct binder_work,
- entry);
- } else {
+ binder_inner_proc_lock(proc);
+ if (!binder_worklist_empty_ilocked(&thread->todo))
+ list = &thread->todo;
+ else if (!binder_worklist_empty_ilocked(&proc->todo) &&
+ wait_for_proc_work)
+ list = &proc->todo;
+ else {
+ binder_inner_proc_unlock(proc);
+
/* no data added */
- if (ptr - buffer == 4 &&
- !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN))
+ if (ptr - buffer == 4 && !thread->looper_need_return)
goto retry;
break;
}
- if (end - ptr < sizeof(tr) + 4)
+ if (end - ptr < sizeof(tr) + 4) {
+ binder_inner_proc_unlock(proc);
break;
+ }
+ w = binder_dequeue_work_head_ilocked(list);
+ if (binder_worklist_empty_ilocked(&thread->todo))
+ thread->process_todo = false;
switch (w->type) {
case BINDER_WORK_TRANSACTION: {
+ binder_inner_proc_unlock(proc);
t = container_of(w, struct binder_transaction, work);
} break;
+ case BINDER_WORK_RETURN_ERROR: {
+ struct binder_error *e = container_of(
+ w, struct binder_error, work);
+
+ WARN_ON(e->cmd == BR_OK);
+ binder_inner_proc_unlock(proc);
+ if (put_user(e->cmd, (uint32_t __user *)ptr))
+ return -EFAULT;
+ cmd = e->cmd;
+ e->cmd = BR_OK;
+ ptr += sizeof(uint32_t);
+
+ binder_stat_br(proc, thread, e->cmd);
+ } break;
case BINDER_WORK_TRANSACTION_COMPLETE: {
+ binder_inner_proc_unlock(proc);
cmd = BR_TRANSACTION_COMPLETE;
if (put_user(cmd, (uint32_t __user *)ptr))
return -EFAULT;
@@ -2312,113 +4321,134 @@ static int binder_thread_read(struct binder_proc *proc,
binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE,
"%d:%d BR_TRANSACTION_COMPLETE\n",
proc->pid, thread->pid);
-
- list_del(&w->entry);
kfree(w);
binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
} break;
case BINDER_WORK_NODE: {
struct binder_node *node = container_of(w, struct binder_node, work);
- uint32_t cmd = BR_NOOP;
- const char *cmd_name;
- int strong = node->internal_strong_refs || node->local_strong_refs;
- int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong;
+ int strong, weak;
+ binder_uintptr_t node_ptr = node->ptr;
+ binder_uintptr_t node_cookie = node->cookie;
+ int node_debug_id = node->debug_id;
+ int has_weak_ref;
+ int has_strong_ref;
+ void __user *orig_ptr = ptr;
- if (weak && !node->has_weak_ref) {
- cmd = BR_INCREFS;
- cmd_name = "BR_INCREFS";
+ BUG_ON(proc != node->proc);
+ strong = node->internal_strong_refs ||
+ node->local_strong_refs;
+ weak = !hlist_empty(&node->refs) ||
+ node->local_weak_refs ||
+ node->tmp_refs || strong;
+ has_strong_ref = node->has_strong_ref;
+ has_weak_ref = node->has_weak_ref;
+
+ if (weak && !has_weak_ref) {
node->has_weak_ref = 1;
node->pending_weak_ref = 1;
node->local_weak_refs++;
- } else if (strong && !node->has_strong_ref) {
- cmd = BR_ACQUIRE;
- cmd_name = "BR_ACQUIRE";
+ }
+ if (strong && !has_strong_ref) {
node->has_strong_ref = 1;
node->pending_strong_ref = 1;
node->local_strong_refs++;
- } else if (!strong && node->has_strong_ref) {
- cmd = BR_RELEASE;
- cmd_name = "BR_RELEASE";
+ }
+ if (!strong && has_strong_ref)
node->has_strong_ref = 0;
- } else if (!weak && node->has_weak_ref) {
- cmd = BR_DECREFS;
- cmd_name = "BR_DECREFS";
+ if (!weak && has_weak_ref)
node->has_weak_ref = 0;
- }
- if (cmd != BR_NOOP) {
- if (put_user(cmd, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- if (put_user(node->ptr,
- (binder_uintptr_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(binder_uintptr_t);
- if (put_user(node->cookie,
- (binder_uintptr_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(binder_uintptr_t);
+ if (!weak && !strong) {
+ binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+ "%d:%d node %d u%016llx c%016llx deleted\n",
+ proc->pid, thread->pid,
+ node_debug_id,
+ (u64)node_ptr,
+ (u64)node_cookie);
+ rb_erase(&node->rb_node, &proc->nodes);
+ binder_inner_proc_unlock(proc);
+ binder_node_lock(node);
+ /*
+ * Acquire the node lock before freeing the
+ * node to serialize with other threads that
+ * may have been holding the node lock while
+ * decrementing this node (avoids race where
+ * this thread frees while the other thread
+ * is unlocking the node after the final
+ * decrement)
+ */
+ binder_node_unlock(node);
+ binder_free_node(node);
+ } else
+ binder_inner_proc_unlock(proc);
- binder_stat_br(proc, thread, cmd);
- binder_debug(BINDER_DEBUG_USER_REFS,
- "%d:%d %s %d u%016llx c%016llx\n",
- proc->pid, thread->pid, cmd_name,
- node->debug_id,
- (u64)node->ptr, (u64)node->cookie);
- } else {
- list_del_init(&w->entry);
- if (!weak && !strong) {
- binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d:%d node %d u%016llx c%016llx deleted\n",
- proc->pid, thread->pid,
- node->debug_id,
- (u64)node->ptr,
- (u64)node->cookie);
- rb_erase(&node->rb_node, &proc->nodes);
- kfree(node);
- binder_stats_deleted(BINDER_STAT_NODE);
- } else {
- binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d:%d node %d u%016llx c%016llx state unchanged\n",
- proc->pid, thread->pid,
- node->debug_id,
- (u64)node->ptr,
- (u64)node->cookie);
- }
- }
+ if (weak && !has_weak_ref)
+ ret = binder_put_node_cmd(
+ proc, thread, &ptr, node_ptr,
+ node_cookie, node_debug_id,
+ BR_INCREFS, "BR_INCREFS");
+ if (!ret && strong && !has_strong_ref)
+ ret = binder_put_node_cmd(
+ proc, thread, &ptr, node_ptr,
+ node_cookie, node_debug_id,
+ BR_ACQUIRE, "BR_ACQUIRE");
+ if (!ret && !strong && has_strong_ref)
+ ret = binder_put_node_cmd(
+ proc, thread, &ptr, node_ptr,
+ node_cookie, node_debug_id,
+ BR_RELEASE, "BR_RELEASE");
+ if (!ret && !weak && has_weak_ref)
+ ret = binder_put_node_cmd(
+ proc, thread, &ptr, node_ptr,
+ node_cookie, node_debug_id,
+ BR_DECREFS, "BR_DECREFS");
+ if (orig_ptr == ptr)
+ binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+ "%d:%d node %d u%016llx c%016llx state unchanged\n",
+ proc->pid, thread->pid,
+ node_debug_id,
+ (u64)node_ptr,
+ (u64)node_cookie);
+ if (ret)
+ return ret;
} break;
case BINDER_WORK_DEAD_BINDER:
case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: {
struct binder_ref_death *death;
uint32_t cmd;
+ binder_uintptr_t cookie;
death = container_of(w, struct binder_ref_death, work);
if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION)
cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE;
else
cmd = BR_DEAD_BINDER;
- if (put_user(cmd, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- if (put_user(death->cookie,
- (binder_uintptr_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(binder_uintptr_t);
- binder_stat_br(proc, thread, cmd);
+ cookie = death->cookie;
+
binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
"%d:%d %s %016llx\n",
proc->pid, thread->pid,
cmd == BR_DEAD_BINDER ?
"BR_DEAD_BINDER" :
"BR_CLEAR_DEATH_NOTIFICATION_DONE",
- (u64)death->cookie);
-
+ (u64)cookie);
if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) {
- list_del(&w->entry);
+ binder_inner_proc_unlock(proc);
kfree(death);
binder_stats_deleted(BINDER_STAT_DEATH);
- } else
- list_move(&w->entry, &proc->delivered_death);
+ } else {
+ binder_enqueue_work_ilocked(
+ w, &proc->delivered_death);
+ binder_inner_proc_unlock(proc);
+ }
+ if (put_user(cmd, (uint32_t __user *)ptr))
+ return -EFAULT;
+ ptr += sizeof(uint32_t);
+ if (put_user(cookie,
+ (binder_uintptr_t __user *)ptr))
+ return -EFAULT;
+ ptr += sizeof(binder_uintptr_t);
+ binder_stat_br(proc, thread, cmd);
if (cmd == BR_DEAD_BINDER)
goto done; /* DEAD_BINDER notifications can cause transactions */
} break;
@@ -2430,50 +4460,67 @@ static int binder_thread_read(struct binder_proc *proc,
BUG_ON(t->buffer == NULL);
if (t->buffer->target_node) {
struct binder_node *target_node = t->buffer->target_node;
+ struct binder_priority node_prio;
- tr.target.ptr = target_node->ptr;
- tr.cookie = target_node->cookie;
- t->saved_priority = task_nice(current);
- if (t->priority < target_node->min_priority &&
- !(t->flags & TF_ONE_WAY))
- binder_set_nice(t->priority);
- else if (!(t->flags & TF_ONE_WAY) ||
- t->saved_priority > target_node->min_priority)
- binder_set_nice(target_node->min_priority);
+ trd->target.ptr = target_node->ptr;
+ trd->cookie = target_node->cookie;
+ node_prio.sched_policy = target_node->sched_policy;
+ node_prio.prio = target_node->min_priority;
+ binder_transaction_priority(current, t, node_prio,
+ target_node->inherit_rt);
cmd = BR_TRANSACTION;
} else {
- tr.target.ptr = 0;
- tr.cookie = 0;
+ trd->target.ptr = 0;
+ trd->cookie = 0;
cmd = BR_REPLY;
}
- tr.code = t->code;
- tr.flags = t->flags;
- tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid);
+ trd->code = t->code;
+ trd->flags = t->flags;
+ trd->sender_euid = from_kuid(current_user_ns(), t->sender_euid);
- if (t->from) {
- struct task_struct *sender = t->from->proc->tsk;
+ t_from = binder_get_txn_from(t);
+ if (t_from) {
+ struct task_struct *sender = t_from->proc->tsk;
- tr.sender_pid = task_tgid_nr_ns(sender,
- task_active_pid_ns(current));
+ trd->sender_pid =
+ task_tgid_nr_ns(sender,
+ task_active_pid_ns(current));
} else {
- tr.sender_pid = 0;
+ trd->sender_pid = 0;
}
- tr.data_size = t->buffer->data_size;
- tr.offsets_size = t->buffer->offsets_size;
- tr.data.ptr.buffer = (binder_uintptr_t)(
- (uintptr_t)t->buffer->data +
- proc->user_buffer_offset);
- tr.data.ptr.offsets = tr.data.ptr.buffer +
+ trd->data_size = t->buffer->data_size;
+ trd->offsets_size = t->buffer->offsets_size;
+ trd->data.ptr.buffer = (uintptr_t)t->buffer->user_data;
+ trd->data.ptr.offsets = trd->data.ptr.buffer +
ALIGN(t->buffer->data_size,
sizeof(void *));
- if (put_user(cmd, (uint32_t __user *)ptr))
+ tr.secctx = t->security_ctx;
+ if (t->security_ctx) {
+ cmd = BR_TRANSACTION_SEC_CTX;
+ trsize = sizeof(tr);
+ }
+ if (put_user(cmd, (uint32_t __user *)ptr)) {
+ if (t_from)
+ binder_thread_dec_tmpref(t_from);
+
+ binder_cleanup_transaction(t, "put_user failed",
+ BR_FAILED_REPLY);
+
return -EFAULT;
+ }
ptr += sizeof(uint32_t);
- if (copy_to_user(ptr, &tr, sizeof(tr)))
+ if (copy_to_user(ptr, &tr, trsize)) {
+ if (t_from)
+ binder_thread_dec_tmpref(t_from);
+
+ binder_cleanup_transaction(t, "copy_to_user failed",
+ BR_FAILED_REPLY);
+
return -EFAULT;
- ptr += sizeof(tr);
+ }
+ ptr += trsize;
trace_binder_transaction_received(t);
binder_stat_br(proc, thread, cmd);
@@ -2481,22 +4528,25 @@ static int binder_thread_read(struct binder_proc *proc,
"%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n",
proc->pid, thread->pid,
(cmd == BR_TRANSACTION) ? "BR_TRANSACTION" :
- "BR_REPLY",
- t->debug_id, t->from ? t->from->proc->pid : 0,
- t->from ? t->from->pid : 0, cmd,
+ (cmd == BR_TRANSACTION_SEC_CTX) ?
+ "BR_TRANSACTION_SEC_CTX" : "BR_REPLY",
+ t->debug_id, t_from ? t_from->proc->pid : 0,
+ t_from ? t_from->pid : 0, cmd,
t->buffer->data_size, t->buffer->offsets_size,
- (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets);
+ (u64)trd->data.ptr.buffer,
+ (u64)trd->data.ptr.offsets);
- list_del(&t->work.entry);
+ if (t_from)
+ binder_thread_dec_tmpref(t_from);
t->buffer->allow_user_free = 1;
- if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) {
+ if (cmd != BR_REPLY && !(t->flags & TF_ONE_WAY)) {
+ binder_inner_proc_lock(thread->proc);
t->to_parent = thread->transaction_stack;
t->to_thread = thread;
thread->transaction_stack = t;
+ binder_inner_proc_unlock(thread->proc);
} else {
- t->buffer->transaction = NULL;
- kfree(t);
- binder_stats_deleted(BINDER_STAT_TRANSACTION);
+ binder_free_transaction(t);
}
break;
}
@@ -2504,45 +4554,56 @@ static int binder_thread_read(struct binder_proc *proc,
done:
*consumed = ptr - buffer;
- if (proc->requested_threads + proc->ready_threads == 0 &&
+ binder_inner_proc_lock(proc);
+ if (proc->requested_threads == 0 &&
+ list_empty(&thread->proc->waiting_threads) &&
proc->requested_threads_started < proc->max_threads &&
(thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
BINDER_LOOPER_STATE_ENTERED)) /* the user-space code fails to */
/*spawn a new thread if we leave this out */) {
proc->requested_threads++;
+ binder_inner_proc_unlock(proc);
binder_debug(BINDER_DEBUG_THREADS,
"%d:%d BR_SPAWN_LOOPER\n",
proc->pid, thread->pid);
if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer))
return -EFAULT;
binder_stat_br(proc, thread, BR_SPAWN_LOOPER);
- }
+ } else
+ binder_inner_proc_unlock(proc);
return 0;
}
-static void binder_release_work(struct list_head *list)
+static void binder_release_work(struct binder_proc *proc,
+ struct list_head *list)
{
struct binder_work *w;
+ enum binder_work_type wtype;
- while (!list_empty(list)) {
- w = list_first_entry(list, struct binder_work, entry);
- list_del_init(&w->entry);
- switch (w->type) {
+ while (1) {
+ binder_inner_proc_lock(proc);
+ w = binder_dequeue_work_head_ilocked(list);
+ wtype = w ? w->type : 0;
+ binder_inner_proc_unlock(proc);
+ if (!w)
+ return;
+
+ switch (wtype) {
case BINDER_WORK_TRANSACTION: {
struct binder_transaction *t;
t = container_of(w, struct binder_transaction, work);
- if (t->buffer->target_node &&
- !(t->flags & TF_ONE_WAY)) {
- binder_send_failed_reply(t, BR_DEAD_REPLY);
- } else {
- binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
- "undelivered transaction %d\n",
- t->debug_id);
- t->buffer->transaction = NULL;
- kfree(t);
- binder_stats_deleted(BINDER_STAT_TRANSACTION);
- }
+
+ binder_cleanup_transaction(t, "process died.",
+ BR_DEAD_REPLY);
+ } break;
+ case BINDER_WORK_RETURN_ERROR: {
+ struct binder_error *e = container_of(
+ w, struct binder_error, work);
+
+ binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+ "undelivered TRANSACTION_ERROR: %u\n",
+ e->cmd);
} break;
case BINDER_WORK_TRANSACTION_COMPLETE: {
binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
@@ -2561,16 +4622,19 @@ static void binder_release_work(struct list_head *list)
kfree(death);
binder_stats_deleted(BINDER_STAT_DEATH);
} break;
+ case BINDER_WORK_NODE:
+ break;
default:
pr_err("unexpected work type, %d, not freed\n",
- w->type);
+ wtype);
break;
}
}
}
-static struct binder_thread *binder_get_thread(struct binder_proc *proc)
+static struct binder_thread *binder_get_thread_ilocked(
+ struct binder_proc *proc, struct binder_thread *new_thread)
{
struct binder_thread *thread = NULL;
struct rb_node *parent = NULL;
@@ -2585,38 +4649,102 @@ static struct binder_thread *binder_get_thread(struct binder_proc *proc)
else if (current->pid > thread->pid)
p = &(*p)->rb_right;
else
- break;
+ return thread;
}
- if (*p == NULL) {
- thread = kzalloc(sizeof(*thread), GFP_KERNEL);
- if (thread == NULL)
+ if (!new_thread)
+ return NULL;
+ thread = new_thread;
+ binder_stats_created(BINDER_STAT_THREAD);
+ thread->proc = proc;
+ thread->pid = current->pid;
+ get_task_struct(current);
+ thread->task = current;
+ atomic_set(&thread->tmp_ref, 0);
+ init_waitqueue_head(&thread->wait);
+ INIT_LIST_HEAD(&thread->todo);
+ rb_link_node(&thread->rb_node, parent, p);
+ rb_insert_color(&thread->rb_node, &proc->threads);
+ thread->looper_need_return = true;
+ thread->return_error.work.type = BINDER_WORK_RETURN_ERROR;
+ thread->return_error.cmd = BR_OK;
+ thread->reply_error.work.type = BINDER_WORK_RETURN_ERROR;
+ thread->reply_error.cmd = BR_OK;
+ INIT_LIST_HEAD(&new_thread->waiting_thread_node);
+ return thread;
+}
+
+static struct binder_thread *binder_get_thread(struct binder_proc *proc)
+{
+ struct binder_thread *thread;
+ struct binder_thread *new_thread;
+
+ binder_inner_proc_lock(proc);
+ thread = binder_get_thread_ilocked(proc, NULL);
+ binder_inner_proc_unlock(proc);
+ if (!thread) {
+ new_thread = kzalloc(sizeof(*thread), GFP_KERNEL);
+ if (new_thread == NULL)
return NULL;
- binder_stats_created(BINDER_STAT_THREAD);
- thread->proc = proc;
- thread->pid = current->pid;
- init_waitqueue_head(&thread->wait);
- INIT_LIST_HEAD(&thread->todo);
- rb_link_node(&thread->rb_node, parent, p);
- rb_insert_color(&thread->rb_node, &proc->threads);
- thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
- thread->return_error = BR_OK;
- thread->return_error2 = BR_OK;
+ binder_inner_proc_lock(proc);
+ thread = binder_get_thread_ilocked(proc, new_thread);
+ binder_inner_proc_unlock(proc);
+ if (thread != new_thread)
+ kfree(new_thread);
}
return thread;
}
-static int binder_free_thread(struct binder_proc *proc,
- struct binder_thread *thread)
+static void binder_free_proc(struct binder_proc *proc)
+{
+ BUG_ON(!list_empty(&proc->todo));
+ BUG_ON(!list_empty(&proc->delivered_death));
+ binder_alloc_deferred_release(&proc->alloc);
+ put_task_struct(proc->tsk);
+ binder_stats_deleted(BINDER_STAT_PROC);
+ kfree(proc);
+}
+
+static void binder_free_thread(struct binder_thread *thread)
+{
+ BUG_ON(!list_empty(&thread->todo));
+ binder_stats_deleted(BINDER_STAT_THREAD);
+ binder_proc_dec_tmpref(thread->proc);
+ put_task_struct(thread->task);
+ kfree(thread);
+}
+
+static int binder_thread_release(struct binder_proc *proc,
+ struct binder_thread *thread)
{
struct binder_transaction *t;
struct binder_transaction *send_reply = NULL;
int active_transactions = 0;
+ struct binder_transaction *last_t = NULL;
+ binder_inner_proc_lock(thread->proc);
+ /*
+ * take a ref on the proc so it survives
+ * after we remove this thread from proc->threads.
+ * The corresponding dec is when we actually
+ * free the thread in binder_free_thread()
+ */
+ atomic_inc(&proc->tmp_ref);
+ /*
+ * take a ref on this thread to ensure it
+ * survives while we are releasing it
+ */
+ atomic_inc(&thread->tmp_ref);
rb_erase(&thread->rb_node, &proc->threads);
t = thread->transaction_stack;
- if (t && t->to_thread == thread)
- send_reply = t;
+ if (t) {
+ spin_lock(&t->lock);
+ if (t->to_thread == thread)
+ send_reply = t;
+ }
+ thread->is_dead = true;
+
while (t) {
+ last_t = t;
active_transactions++;
binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
"release %d:%d transaction %d %s, still active\n",
@@ -2637,19 +4765,24 @@ static int binder_free_thread(struct binder_proc *proc,
t = t->from_parent;
} else
BUG();
+ spin_unlock(&last_t->lock);
+ if (t)
+ spin_lock(&t->lock);
}
/*
* If this thread used poll, make sure we remove the waitqueue
* from any epoll data structures holding it with POLLFREE.
* waitqueue_active() is safe to use here because we're holding
- * the global lock.
+ * the inner lock.
*/
if ((thread->looper & BINDER_LOOPER_STATE_POLL) &&
waitqueue_active(&thread->wait)) {
wake_up_poll(&thread->wait, POLLHUP | POLLFREE);
}
+ binder_inner_proc_unlock(thread->proc);
+
/*
* This is needed to avoid races between wake_up_poll() above and
* and ep_remove_waitqueue() called for other reasons (eg the epoll file
@@ -2661,9 +4794,8 @@ static int binder_free_thread(struct binder_proc *proc,
if (send_reply)
binder_send_failed_reply(send_reply, BR_DEAD_REPLY);
- binder_release_work(&thread->todo);
- kfree(thread);
- binder_stats_deleted(BINDER_STAT_THREAD);
+ binder_release_work(proc, &thread->todo);
+ binder_thread_dec_tmpref(thread);
return active_transactions;
}
@@ -2672,36 +4804,23 @@ static unsigned int binder_poll(struct file *filp,
{
struct binder_proc *proc = filp->private_data;
struct binder_thread *thread = NULL;
- int wait_for_proc_work;
-
- binder_lock(__func__);
+ bool wait_for_proc_work;
thread = binder_get_thread(proc);
- if (!thread) {
- binder_unlock(__func__);
+ if (!thread)
return POLLERR;
- }
+ binder_inner_proc_lock(thread->proc);
thread->looper |= BINDER_LOOPER_STATE_POLL;
+ wait_for_proc_work = binder_available_for_proc_work_ilocked(thread);
- wait_for_proc_work = thread->transaction_stack == NULL &&
- list_empty(&thread->todo) && thread->return_error == BR_OK;
+ binder_inner_proc_unlock(thread->proc);
- binder_unlock(__func__);
+ poll_wait(filp, &thread->wait, wait);
- if (wait_for_proc_work) {
- if (binder_has_proc_work(proc, thread))
- return POLLIN;
- poll_wait(filp, &proc->wait, wait);
- if (binder_has_proc_work(proc, thread))
- return POLLIN;
- } else {
- if (binder_has_thread_work(thread))
- return POLLIN;
- poll_wait(filp, &thread->wait, wait);
- if (binder_has_thread_work(thread))
- return POLLIN;
- }
+ if (binder_has_work(thread, wait_for_proc_work))
+ return POLLIN;
+
return 0;
}
@@ -2748,8 +4867,10 @@ static int binder_ioctl_write_read(struct file *filp,
&bwr.read_consumed,
filp->f_flags & O_NONBLOCK);
trace_binder_read_done(ret);
- if (!list_empty(&proc->todo))
- wake_up_interruptible(&proc->wait);
+ binder_inner_proc_lock(proc);
+ if (!binder_worklist_empty_ilocked(&proc->todo))
+ binder_wakeup_proc_ilocked(proc);
+ binder_inner_proc_unlock(proc);
if (ret < 0) {
if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
ret = -EFAULT;
@@ -2769,13 +4890,17 @@ static int binder_ioctl_write_read(struct file *filp,
return ret;
}
-static int binder_ioctl_set_ctx_mgr(struct file *filp)
+static int binder_ioctl_set_ctx_mgr(struct file *filp,
+ struct flat_binder_object *fbo)
{
int ret = 0;
struct binder_proc *proc = filp->private_data;
+ struct binder_context *context = proc->context;
+ struct binder_node *new_node;
kuid_t curr_euid = current_euid();
- if (binder_context_mgr_node != NULL) {
+ mutex_lock(&context->context_mgr_node_lock);
+ if (context->binder_context_mgr_node) {
pr_err("BINDER_SET_CONTEXT_MGR already set\n");
ret = -EBUSY;
goto out;
@@ -2783,31 +4908,96 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp)
ret = security_binder_set_context_mgr(proc->tsk);
if (ret < 0)
goto out;
- if (uid_valid(binder_context_mgr_uid)) {
- if (!uid_eq(binder_context_mgr_uid, curr_euid)) {
+ if (uid_valid(context->binder_context_mgr_uid)) {
+ if (!uid_eq(context->binder_context_mgr_uid, curr_euid)) {
pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
from_kuid(&init_user_ns, curr_euid),
from_kuid(&init_user_ns,
- binder_context_mgr_uid));
+ context->binder_context_mgr_uid));
ret = -EPERM;
goto out;
}
} else {
- binder_context_mgr_uid = curr_euid;
+ context->binder_context_mgr_uid = curr_euid;
}
- binder_context_mgr_node = binder_new_node(proc, 0, 0);
- if (binder_context_mgr_node == NULL) {
+ new_node = binder_new_node(proc, fbo);
+ if (!new_node) {
ret = -ENOMEM;
goto out;
}
- binder_context_mgr_node->local_weak_refs++;
- binder_context_mgr_node->local_strong_refs++;
- binder_context_mgr_node->has_strong_ref = 1;
- binder_context_mgr_node->has_weak_ref = 1;
+ binder_node_lock(new_node);
+ new_node->local_weak_refs++;
+ new_node->local_strong_refs++;
+ new_node->has_strong_ref = 1;
+ new_node->has_weak_ref = 1;
+ context->binder_context_mgr_node = new_node;
+ binder_node_unlock(new_node);
+ binder_put_node(new_node);
out:
+ mutex_unlock(&context->context_mgr_node_lock);
return ret;
}
+static int binder_ioctl_get_node_info_for_ref(struct binder_proc *proc,
+ struct binder_node_info_for_ref *info)
+{
+ struct binder_node *node;
+ struct binder_context *context = proc->context;
+ __u32 handle = info->handle;
+
+ if (info->strong_count || info->weak_count || info->reserved1 ||
+ info->reserved2 || info->reserved3) {
+ binder_user_error("%d BINDER_GET_NODE_INFO_FOR_REF: only handle may be non-zero.",
+ proc->pid);
+ return -EINVAL;
+ }
+
+ /* This ioctl may only be used by the context manager */
+ mutex_lock(&context->context_mgr_node_lock);
+ if (!context->binder_context_mgr_node ||
+ context->binder_context_mgr_node->proc != proc) {
+ mutex_unlock(&context->context_mgr_node_lock);
+ return -EPERM;
+ }
+ mutex_unlock(&context->context_mgr_node_lock);
+
+ node = binder_get_node_from_ref(proc, handle, true, NULL);
+ if (!node)
+ return -EINVAL;
+
+ info->strong_count = node->local_strong_refs +
+ node->internal_strong_refs;
+ info->weak_count = node->local_weak_refs;
+
+ binder_put_node(node);
+
+ return 0;
+}
+
+static int binder_ioctl_get_node_debug_info(struct binder_proc *proc,
+ struct binder_node_debug_info *info) {
+ struct rb_node *n;
+ binder_uintptr_t ptr = info->ptr;
+
+ memset(info, 0, sizeof(*info));
+
+ binder_inner_proc_lock(proc);
+ for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) {
+ struct binder_node *node = rb_entry(n, struct binder_node,
+ rb_node);
+ if (node->ptr > ptr) {
+ info->ptr = node->ptr;
+ info->cookie = node->cookie;
+ info->has_strong_ref = node->has_strong_ref;
+ info->has_weak_ref = node->has_weak_ref;
+ break;
+ }
+ }
+ binder_inner_proc_unlock(proc);
+
+ return 0;
+}
+
static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
int ret;
@@ -2819,13 +5009,14 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
/*pr_info("binder_ioctl: %d:%d %x %lx\n",
proc->pid, current->pid, cmd, arg);*/
+ binder_selftest_alloc(&proc->alloc);
+
trace_binder_ioctl(cmd, arg);
ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
if (ret)
goto err_unlocked;
- binder_lock(__func__);
thread = binder_get_thread(proc);
if (thread == NULL) {
ret = -ENOMEM;
@@ -2838,21 +5029,40 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (ret)
goto err;
break;
- case BINDER_SET_MAX_THREADS:
- if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
+ case BINDER_SET_MAX_THREADS: {
+ int max_threads;
+
+ if (copy_from_user(&max_threads, ubuf,
+ sizeof(max_threads))) {
ret = -EINVAL;
goto err;
}
+ binder_inner_proc_lock(proc);
+ proc->max_threads = max_threads;
+ binder_inner_proc_unlock(proc);
break;
+ }
+ case BINDER_SET_CONTEXT_MGR_EXT: {
+ struct flat_binder_object fbo;
+
+ if (copy_from_user(&fbo, ubuf, sizeof(fbo))) {
+ ret = -EINVAL;
+ goto err;
+ }
+ ret = binder_ioctl_set_ctx_mgr(filp, &fbo);
+ if (ret)
+ goto err;
+ break;
+ }
case BINDER_SET_CONTEXT_MGR:
- ret = binder_ioctl_set_ctx_mgr(filp);
+ ret = binder_ioctl_set_ctx_mgr(filp, NULL);
if (ret)
goto err;
break;
case BINDER_THREAD_EXIT:
binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
proc->pid, thread->pid);
- binder_free_thread(proc, thread);
+ binder_thread_release(proc, thread);
thread = NULL;
break;
case BINDER_VERSION: {
@@ -2869,6 +5079,43 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
break;
}
+ case BINDER_GET_NODE_INFO_FOR_REF: {
+ struct binder_node_info_for_ref info;
+
+ if (copy_from_user(&info, ubuf, sizeof(info))) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ ret = binder_ioctl_get_node_info_for_ref(proc, &info);
+ if (ret < 0)
+ goto err;
+
+ if (copy_to_user(ubuf, &info, sizeof(info))) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ break;
+ }
+ case BINDER_GET_NODE_DEBUG_INFO: {
+ struct binder_node_debug_info info;
+
+ if (copy_from_user(&info, ubuf, sizeof(info))) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ ret = binder_ioctl_get_node_debug_info(proc, &info);
+ if (ret < 0)
+ goto err;
+
+ if (copy_to_user(ubuf, &info, sizeof(info))) {
+ ret = -EFAULT;
+ goto err;
+ }
+ break;
+ }
default:
ret = -EINVAL;
goto err;
@@ -2876,8 +5123,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
ret = 0;
err:
if (thread)
- thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
- binder_unlock(__func__);
+ thread->looper_need_return = false;
wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
if (ret && ret != -ERESTARTSYS)
pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
@@ -2906,8 +5152,7 @@ static void binder_vma_close(struct vm_area_struct *vma)
proc->pid, vma->vm_start, vma->vm_end,
(vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
(unsigned long)pgprot_val(vma->vm_page_prot));
- proc->vma = NULL;
- proc->vma_vm_mm = NULL;
+ binder_alloc_vma_close(&proc->alloc);
binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
}
@@ -2925,10 +5170,8 @@ static const struct vm_operations_struct binder_vm_ops = {
static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
{
int ret;
- struct vm_struct *area;
struct binder_proc *proc = filp->private_data;
const char *failure_string;
- struct binder_buffer *buffer;
if (proc->tsk != current->group_leader)
return -EINVAL;
@@ -2937,8 +5180,8 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
vma->vm_end = vma->vm_start + SZ_4M;
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
- "binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
- proc->pid, vma->vm_start, vma->vm_end,
+ "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
+ __func__, proc->pid, vma->vm_start, vma->vm_end,
(vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
(unsigned long)pgprot_val(vma->vm_page_prot));
@@ -2947,78 +5190,22 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
failure_string = "bad vm_flags";
goto err_bad_arg;
}
- vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
-
- mutex_lock(&binder_mmap_lock);
- if (proc->buffer) {
- ret = -EBUSY;
- failure_string = "already mapped";
- goto err_already_mapped;
- }
-
- area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP);
- if (area == NULL) {
- ret = -ENOMEM;
- failure_string = "get_vm_area";
- goto err_get_vm_area_failed;
- }
- proc->buffer = area->addr;
- proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
- mutex_unlock(&binder_mmap_lock);
-
-#ifdef CONFIG_CPU_CACHE_VIPT
- if (cache_is_vipt_aliasing()) {
- while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) {
- pr_info("binder_mmap: %d %lx-%lx maps %pK bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer);
- vma->vm_start += PAGE_SIZE;
- }
- }
-#endif
- proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL);
- if (proc->pages == NULL) {
- ret = -ENOMEM;
- failure_string = "alloc page array";
- goto err_alloc_pages_failed;
- }
- proc->buffer_size = vma->vm_end - vma->vm_start;
+ vma->vm_flags |= VM_DONTCOPY | VM_MIXEDMAP;
+ vma->vm_flags &= ~VM_MAYWRITE;
vma->vm_ops = &binder_vm_ops;
vma->vm_private_data = proc;
- if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) {
- ret = -ENOMEM;
- failure_string = "alloc small buf";
- goto err_alloc_small_buf_failed;
- }
- buffer = proc->buffer;
- INIT_LIST_HEAD(&proc->buffers);
- list_add(&buffer->entry, &proc->buffers);
- buffer->free = 1;
- binder_insert_free_buffer(proc, buffer);
- proc->free_async_space = proc->buffer_size / 2;
- barrier();
+ ret = binder_alloc_mmap_handler(&proc->alloc, vma);
+ if (ret)
+ return ret;
mutex_lock(&proc->files_lock);
proc->files = get_files_struct(current);
mutex_unlock(&proc->files_lock);
- proc->vma = vma;
- proc->vma_vm_mm = vma->vm_mm;
-
- /*pr_info("binder_mmap: %d %lx-%lx maps %p\n",
- proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
return 0;
-err_alloc_small_buf_failed:
- kfree(proc->pages);
- proc->pages = NULL;
-err_alloc_pages_failed:
- mutex_lock(&binder_mmap_lock);
- vfree(proc->buffer);
- proc->buffer = NULL;
-err_get_vm_area_failed:
-err_already_mapped:
- mutex_unlock(&binder_mmap_lock);
err_bad_arg:
- pr_err("binder_mmap: %d %lx-%lx %s failed %d\n",
+ pr_err("%s: %d %lx-%lx %s failed %d\n", __func__,
proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
return ret;
}
@@ -3026,36 +5213,59 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
static int binder_open(struct inode *nodp, struct file *filp)
{
struct binder_proc *proc;
+ struct binder_device *binder_dev;
- binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n",
+ binder_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d:%d\n", __func__,
current->group_leader->pid, current->pid);
proc = kzalloc(sizeof(*proc), GFP_KERNEL);
if (proc == NULL)
return -ENOMEM;
+ spin_lock_init(&proc->inner_lock);
+ spin_lock_init(&proc->outer_lock);
+ atomic_set(&proc->tmp_ref, 0);
get_task_struct(current->group_leader);
proc->tsk = current->group_leader;
mutex_init(&proc->files_lock);
INIT_LIST_HEAD(&proc->todo);
- init_waitqueue_head(&proc->wait);
- proc->default_priority = task_nice(current);
+ if (binder_supported_policy(current->policy)) {
+ proc->default_priority.sched_policy = current->policy;
+ proc->default_priority.prio = current->normal_prio;
+ } else {
+ proc->default_priority.sched_policy = SCHED_NORMAL;
+ proc->default_priority.prio = NICE_TO_PRIO(0);
+ }
- binder_lock(__func__);
+ binder_dev = container_of(filp->private_data, struct binder_device,
+ miscdev);
+ proc->context = &binder_dev->context;
+ binder_alloc_init(&proc->alloc);
binder_stats_created(BINDER_STAT_PROC);
- hlist_add_head(&proc->proc_node, &binder_procs);
proc->pid = current->group_leader->pid;
INIT_LIST_HEAD(&proc->delivered_death);
+ INIT_LIST_HEAD(&proc->waiting_threads);
filp->private_data = proc;
- binder_unlock(__func__);
+ mutex_lock(&binder_procs_lock);
+ hlist_add_head(&proc->proc_node, &binder_procs);
+ mutex_unlock(&binder_procs_lock);
if (binder_debugfs_dir_entry_proc) {
char strbuf[11];
snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
- proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
- binder_debugfs_dir_entry_proc, proc, &binder_proc_fops);
+ /*
+ * proc debug entries are shared between contexts, so
+ * this will fail if the process tries to open the driver
+ * again with a different context. The priting code will
+ * anyway print all contexts that a given PID has, so this
+ * is not a problem.
+ */
+ proc->debugfs_entry = debugfs_create_file(strbuf, 0444,
+ binder_debugfs_dir_entry_proc,
+ (void *)(unsigned long)proc->pid,
+ &binder_proc_fops);
}
return 0;
@@ -3075,16 +5285,17 @@ static void binder_deferred_flush(struct binder_proc *proc)
struct rb_node *n;
int wake_count = 0;
+ binder_inner_proc_lock(proc);
for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) {
struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node);
- thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
+ thread->looper_need_return = true;
if (thread->looper & BINDER_LOOPER_STATE_WAITING) {
wake_up_interruptible(&thread->wait);
wake_count++;
}
}
- wake_up_interruptible_all(&proc->wait);
+ binder_inner_proc_unlock(proc);
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
"binder_flush: %d woke %d threads\n", proc->pid,
@@ -3105,13 +5316,21 @@ static int binder_node_release(struct binder_node *node, int refs)
{
struct binder_ref *ref;
int death = 0;
+ struct binder_proc *proc = node->proc;
- list_del_init(&node->work.entry);
- binder_release_work(&node->async_todo);
+ binder_release_work(proc, &node->async_todo);
- if (hlist_empty(&node->refs)) {
- kfree(node);
- binder_stats_deleted(BINDER_STAT_NODE);
+ binder_node_lock(node);
+ binder_inner_proc_lock(proc);
+ binder_dequeue_work_ilocked(&node->work);
+ /*
+ * The caller must have taken a temporary ref on the node,
+ */
+ BUG_ON(!node->tmp_refs);
+ if (hlist_empty(&node->refs) && node->tmp_refs == 1) {
+ binder_inner_proc_unlock(proc);
+ binder_node_unlock(node);
+ binder_free_node(node);
return refs;
}
@@ -3119,59 +5338,84 @@ static int binder_node_release(struct binder_node *node, int refs)
node->proc = NULL;
node->local_strong_refs = 0;
node->local_weak_refs = 0;
+ binder_inner_proc_unlock(proc);
+
+ spin_lock(&binder_dead_nodes_lock);
hlist_add_head(&node->dead_node, &binder_dead_nodes);
+ spin_unlock(&binder_dead_nodes_lock);
hlist_for_each_entry(ref, &node->refs, node_entry) {
refs++;
-
- if (!ref->death)
+ /*
+ * Need the node lock to synchronize
+ * with new notification requests and the
+ * inner lock to synchronize with queued
+ * death notifications.
+ */
+ binder_inner_proc_lock(ref->proc);
+ if (!ref->death) {
+ binder_inner_proc_unlock(ref->proc);
continue;
+ }
death++;
- if (list_empty(&ref->death->work.entry)) {
- ref->death->work.type = BINDER_WORK_DEAD_BINDER;
- list_add_tail(&ref->death->work.entry,
- &ref->proc->todo);
- wake_up_interruptible(&ref->proc->wait);
- } else
- BUG();
+ BUG_ON(!list_empty(&ref->death->work.entry));
+ ref->death->work.type = BINDER_WORK_DEAD_BINDER;
+ binder_enqueue_work_ilocked(&ref->death->work,
+ &ref->proc->todo);
+ binder_wakeup_proc_ilocked(ref->proc);
+ binder_inner_proc_unlock(ref->proc);
}
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"node %d now dead, refs %d, death %d\n",
node->debug_id, refs, death);
+ binder_node_unlock(node);
+ binder_put_node(node);
return refs;
}
static void binder_deferred_release(struct binder_proc *proc)
{
- struct binder_transaction *t;
+ struct binder_context *context = proc->context;
struct rb_node *n;
- int threads, nodes, incoming_refs, outgoing_refs, buffers,
- active_transactions, page_count;
+ int threads, nodes, incoming_refs, outgoing_refs, active_transactions;
- BUG_ON(proc->vma);
BUG_ON(proc->files);
+ mutex_lock(&binder_procs_lock);
hlist_del(&proc->proc_node);
+ mutex_unlock(&binder_procs_lock);
- if (binder_context_mgr_node && binder_context_mgr_node->proc == proc) {
+ mutex_lock(&context->context_mgr_node_lock);
+ if (context->binder_context_mgr_node &&
+ context->binder_context_mgr_node->proc == proc) {
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"%s: %d context_mgr_node gone\n",
__func__, proc->pid);
- binder_context_mgr_node = NULL;
+ context->binder_context_mgr_node = NULL;
}
+ mutex_unlock(&context->context_mgr_node_lock);
+ binder_inner_proc_lock(proc);
+ /*
+ * Make sure proc stays alive after we
+ * remove all the threads
+ */
+ atomic_inc(&proc->tmp_ref);
+ proc->is_dead = true;
threads = 0;
active_transactions = 0;
while ((n = rb_first(&proc->threads))) {
struct binder_thread *thread;
thread = rb_entry(n, struct binder_thread, rb_node);
+ binder_inner_proc_unlock(proc);
threads++;
- active_transactions += binder_free_thread(proc, thread);
+ active_transactions += binder_thread_release(proc, thread);
+ binder_inner_proc_lock(proc);
}
nodes = 0;
@@ -3181,73 +5425,42 @@ static void binder_deferred_release(struct binder_proc *proc)
node = rb_entry(n, struct binder_node, rb_node);
nodes++;
+ /*
+ * take a temporary ref on the node before
+ * calling binder_node_release() which will either
+ * kfree() the node or call binder_put_node()
+ */
+ binder_inc_node_tmpref_ilocked(node);
rb_erase(&node->rb_node, &proc->nodes);
+ binder_inner_proc_unlock(proc);
incoming_refs = binder_node_release(node, incoming_refs);
+ binder_inner_proc_lock(proc);
}
+ binder_inner_proc_unlock(proc);
outgoing_refs = 0;
+ binder_proc_lock(proc);
while ((n = rb_first(&proc->refs_by_desc))) {
struct binder_ref *ref;
ref = rb_entry(n, struct binder_ref, rb_node_desc);
outgoing_refs++;
- binder_delete_ref(ref);
+ binder_cleanup_ref_olocked(ref);
+ binder_proc_unlock(proc);
+ binder_free_ref(ref);
+ binder_proc_lock(proc);
}
+ binder_proc_unlock(proc);
- binder_release_work(&proc->todo);
- binder_release_work(&proc->delivered_death);
-
- buffers = 0;
- while ((n = rb_first(&proc->allocated_buffers))) {
- struct binder_buffer *buffer;
-
- buffer = rb_entry(n, struct binder_buffer, rb_node);
-
- t = buffer->transaction;
- if (t) {
- t->buffer = NULL;
- buffer->transaction = NULL;
- pr_err("release proc %d, transaction %d, not freed\n",
- proc->pid, t->debug_id);
- /*BUG();*/
- }
-
- binder_free_buf(proc, buffer);
- buffers++;
- }
-
- binder_stats_deleted(BINDER_STAT_PROC);
-
- page_count = 0;
- if (proc->pages) {
- int i;
-
- for (i = 0; i < proc->buffer_size / PAGE_SIZE; i++) {
- void *page_addr;
-
- if (!proc->pages[i])
- continue;
-
- page_addr = proc->buffer + i * PAGE_SIZE;
- binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%s: %d: page %d at %pK not freed\n",
- __func__, proc->pid, i, page_addr);
- unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
- __free_page(proc->pages[i]);
- page_count++;
- }
- kfree(proc->pages);
- vfree(proc->buffer);
- }
-
- put_task_struct(proc->tsk);
+ binder_release_work(proc, &proc->todo);
+ binder_release_work(proc, &proc->delivered_death);
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
- "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d, buffers %d, pages %d\n",
+ "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d\n",
__func__, proc->pid, threads, nodes, incoming_refs,
- outgoing_refs, active_transactions, buffers, page_count);
+ outgoing_refs, active_transactions);
- kfree(proc);
+ binder_proc_dec_tmpref(proc);
}
static void binder_deferred_func(struct work_struct *work)
@@ -3258,7 +5471,6 @@ static void binder_deferred_func(struct work_struct *work)
int defer;
do {
- binder_lock(__func__);
mutex_lock(&binder_deferred_lock);
if (!hlist_empty(&binder_deferred_list)) {
proc = hlist_entry(binder_deferred_list.first,
@@ -3287,7 +5499,6 @@ static void binder_deferred_func(struct work_struct *work)
if (defer & BINDER_DEFERRED_RELEASE)
binder_deferred_release(proc); /* frees proc */
- binder_unlock(__func__);
if (files)
put_files_struct(files);
} while (proc);
@@ -3307,41 +5518,52 @@ binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer)
mutex_unlock(&binder_deferred_lock);
}
-static void print_binder_transaction(struct seq_file *m, const char *prefix,
- struct binder_transaction *t)
+static void print_binder_transaction_ilocked(struct seq_file *m,
+ struct binder_proc *proc,
+ const char *prefix,
+ struct binder_transaction *t)
{
+ struct binder_proc *to_proc;
+ struct binder_buffer *buffer = t->buffer;
+
+ spin_lock(&t->lock);
+ to_proc = t->to_proc;
seq_printf(m,
- "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d",
+ "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %d:%d r%d",
prefix, t->debug_id, t,
t->from ? t->from->proc->pid : 0,
t->from ? t->from->pid : 0,
- t->to_proc ? t->to_proc->pid : 0,
+ to_proc ? to_proc->pid : 0,
t->to_thread ? t->to_thread->pid : 0,
- t->code, t->flags, t->priority, t->need_reply);
- if (t->buffer == NULL) {
+ t->code, t->flags, t->priority.sched_policy,
+ t->priority.prio, t->need_reply);
+ spin_unlock(&t->lock);
+
+ if (proc != to_proc) {
+ /*
+ * Can only safely deref buffer if we are holding the
+ * correct proc inner lock for this node
+ */
+ seq_puts(m, "\n");
+ return;
+ }
+
+ if (buffer == NULL) {
seq_puts(m, " buffer free\n");
return;
}
- if (t->buffer->target_node)
- seq_printf(m, " node %d",
- t->buffer->target_node->debug_id);
+ if (buffer->target_node)
+ seq_printf(m, " node %d", buffer->target_node->debug_id);
seq_printf(m, " size %zd:%zd data %pK\n",
- t->buffer->data_size, t->buffer->offsets_size,
- t->buffer->data);
-}
-
-static void print_binder_buffer(struct seq_file *m, const char *prefix,
- struct binder_buffer *buffer)
-{
- seq_printf(m, "%s %d: %pK size %zd:%zd %s\n",
- prefix, buffer->debug_id, buffer->data,
buffer->data_size, buffer->offsets_size,
- buffer->transaction ? "active" : "delivered");
+ buffer->user_data);
}
-static void print_binder_work(struct seq_file *m, const char *prefix,
- const char *transaction_prefix,
- struct binder_work *w)
+static void print_binder_work_ilocked(struct seq_file *m,
+ struct binder_proc *proc,
+ const char *prefix,
+ const char *transaction_prefix,
+ struct binder_work *w)
{
struct binder_node *node;
struct binder_transaction *t;
@@ -3349,8 +5571,16 @@ static void print_binder_work(struct seq_file *m, const char *prefix,
switch (w->type) {
case BINDER_WORK_TRANSACTION:
t = container_of(w, struct binder_transaction, work);
- print_binder_transaction(m, transaction_prefix, t);
+ print_binder_transaction_ilocked(
+ m, proc, transaction_prefix, t);
break;
+ case BINDER_WORK_RETURN_ERROR: {
+ struct binder_error *e = container_of(
+ w, struct binder_error, work);
+
+ seq_printf(m, "%stransaction error: %u\n",
+ prefix, e->cmd);
+ } break;
case BINDER_WORK_TRANSACTION_COMPLETE:
seq_printf(m, "%stransaction complete\n", prefix);
break;
@@ -3375,40 +5605,46 @@ static void print_binder_work(struct seq_file *m, const char *prefix,
}
}
-static void print_binder_thread(struct seq_file *m,
- struct binder_thread *thread,
- int print_always)
+static void print_binder_thread_ilocked(struct seq_file *m,
+ struct binder_thread *thread,
+ int print_always)
{
struct binder_transaction *t;
struct binder_work *w;
size_t start_pos = m->count;
size_t header_pos;
- seq_printf(m, " thread %d: l %02x\n", thread->pid, thread->looper);
+ seq_printf(m, " thread %d: l %02x need_return %d tr %d\n",
+ thread->pid, thread->looper,
+ thread->looper_need_return,
+ atomic_read(&thread->tmp_ref));
header_pos = m->count;
t = thread->transaction_stack;
while (t) {
if (t->from == thread) {
- print_binder_transaction(m,
- " outgoing transaction", t);
+ print_binder_transaction_ilocked(m, thread->proc,
+ " outgoing transaction", t);
t = t->from_parent;
} else if (t->to_thread == thread) {
- print_binder_transaction(m,
+ print_binder_transaction_ilocked(m, thread->proc,
" incoming transaction", t);
t = t->to_parent;
} else {
- print_binder_transaction(m, " bad transaction", t);
+ print_binder_transaction_ilocked(m, thread->proc,
+ " bad transaction", t);
t = NULL;
}
}
list_for_each_entry(w, &thread->todo, entry) {
- print_binder_work(m, " ", " pending transaction", w);
+ print_binder_work_ilocked(m, thread->proc, " ",
+ " pending transaction", w);
}
if (!print_always && m->count == header_pos)
m->count = start_pos;
}
-static void print_binder_node(struct seq_file *m, struct binder_node *node)
+static void print_binder_node_nilocked(struct seq_file *m,
+ struct binder_node *node)
{
struct binder_ref *ref;
struct binder_work *w;
@@ -3418,27 +5654,35 @@ static void print_binder_node(struct seq_file *m, struct binder_node *node)
hlist_for_each_entry(ref, &node->refs, node_entry)
count++;
- seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d",
+ seq_printf(m, " node %d: u%016llx c%016llx pri %d:%d hs %d hw %d ls %d lw %d is %d iw %d tr %d",
node->debug_id, (u64)node->ptr, (u64)node->cookie,
+ node->sched_policy, node->min_priority,
node->has_strong_ref, node->has_weak_ref,
node->local_strong_refs, node->local_weak_refs,
- node->internal_strong_refs, count);
+ node->internal_strong_refs, count, node->tmp_refs);
if (count) {
seq_puts(m, " proc");
hlist_for_each_entry(ref, &node->refs, node_entry)
seq_printf(m, " %d", ref->proc->pid);
}
seq_puts(m, "\n");
- list_for_each_entry(w, &node->async_todo, entry)
- print_binder_work(m, " ",
- " pending async transaction", w);
+ if (node->proc) {
+ list_for_each_entry(w, &node->async_todo, entry)
+ print_binder_work_ilocked(m, node->proc, " ",
+ " pending async transaction", w);
+ }
}
-static void print_binder_ref(struct seq_file *m, struct binder_ref *ref)
+static void print_binder_ref_olocked(struct seq_file *m,
+ struct binder_ref *ref)
{
+ binder_node_lock(ref->node);
seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %pK\n",
- ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ",
- ref->node->debug_id, ref->strong, ref->weak, ref->death);
+ ref->data.debug_id, ref->data.desc,
+ ref->node->proc ? "" : "dead ",
+ ref->node->debug_id, ref->data.strong,
+ ref->data.weak, ref->death);
+ binder_node_unlock(ref->node);
}
static void print_binder_proc(struct seq_file *m,
@@ -3448,35 +5692,63 @@ static void print_binder_proc(struct seq_file *m,
struct rb_node *n;
size_t start_pos = m->count;
size_t header_pos;
+ struct binder_node *last_node = NULL;
seq_printf(m, "proc %d\n", proc->pid);
+ seq_printf(m, "context %s\n", proc->context->name);
header_pos = m->count;
+ binder_inner_proc_lock(proc);
for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
- print_binder_thread(m, rb_entry(n, struct binder_thread,
+ print_binder_thread_ilocked(m, rb_entry(n, struct binder_thread,
rb_node), print_all);
+
for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) {
struct binder_node *node = rb_entry(n, struct binder_node,
rb_node);
- if (print_all || node->has_async_transaction)
- print_binder_node(m, node);
+ if (!print_all && !node->has_async_transaction)
+ continue;
+
+ /*
+ * take a temporary reference on the node so it
+ * survives and isn't removed from the tree
+ * while we print it.
+ */
+ binder_inc_node_tmpref_ilocked(node);
+ /* Need to drop inner lock to take node lock */
+ binder_inner_proc_unlock(proc);
+ if (last_node)
+ binder_put_node(last_node);
+ binder_node_inner_lock(node);
+ print_binder_node_nilocked(m, node);
+ binder_node_inner_unlock(node);
+ last_node = node;
+ binder_inner_proc_lock(proc);
}
+ binder_inner_proc_unlock(proc);
+ if (last_node)
+ binder_put_node(last_node);
+
if (print_all) {
+ binder_proc_lock(proc);
for (n = rb_first(&proc->refs_by_desc);
n != NULL;
n = rb_next(n))
- print_binder_ref(m, rb_entry(n, struct binder_ref,
- rb_node_desc));
+ print_binder_ref_olocked(m, rb_entry(n,
+ struct binder_ref,
+ rb_node_desc));
+ binder_proc_unlock(proc);
}
- for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
- print_binder_buffer(m, " buffer",
- rb_entry(n, struct binder_buffer, rb_node));
+ binder_alloc_print_allocated(m, &proc->alloc);
+ binder_inner_proc_lock(proc);
list_for_each_entry(w, &proc->todo, entry)
- print_binder_work(m, " ", " pending transaction", w);
+ print_binder_work_ilocked(m, proc, " ",
+ " pending transaction", w);
list_for_each_entry(w, &proc->delivered_death, entry) {
seq_puts(m, " has delivered dead binder\n");
break;
}
+ binder_inner_proc_unlock(proc);
if (!print_all && m->count == header_pos)
m->count = start_pos;
}
@@ -3519,7 +5791,9 @@ static const char * const binder_command_strings[] = {
"BC_EXIT_LOOPER",
"BC_REQUEST_DEATH_NOTIFICATION",
"BC_CLEAR_DEATH_NOTIFICATION",
- "BC_DEAD_BINDER_DONE"
+ "BC_DEAD_BINDER_DONE",
+ "BC_TRANSACTION_SG",
+ "BC_REPLY_SG",
};
static const char * const binder_objstat_strings[] = {
@@ -3540,17 +5814,21 @@ static void print_binder_stats(struct seq_file *m, const char *prefix,
BUILD_BUG_ON(ARRAY_SIZE(stats->bc) !=
ARRAY_SIZE(binder_command_strings));
for (i = 0; i < ARRAY_SIZE(stats->bc); i++) {
- if (stats->bc[i])
+ int temp = atomic_read(&stats->bc[i]);
+
+ if (temp)
seq_printf(m, "%s%s: %d\n", prefix,
- binder_command_strings[i], stats->bc[i]);
+ binder_command_strings[i], temp);
}
BUILD_BUG_ON(ARRAY_SIZE(stats->br) !=
ARRAY_SIZE(binder_return_strings));
for (i = 0; i < ARRAY_SIZE(stats->br); i++) {
- if (stats->br[i])
+ int temp = atomic_read(&stats->br[i]);
+
+ if (temp)
seq_printf(m, "%s%s: %d\n", prefix,
- binder_return_strings[i], stats->br[i]);
+ binder_return_strings[i], temp);
}
BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
@@ -3558,11 +5836,15 @@ static void print_binder_stats(struct seq_file *m, const char *prefix,
BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
ARRAY_SIZE(stats->obj_deleted));
for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) {
- if (stats->obj_created[i] || stats->obj_deleted[i])
- seq_printf(m, "%s%s: active %d total %d\n", prefix,
+ int created = atomic_read(&stats->obj_created[i]);
+ int deleted = atomic_read(&stats->obj_deleted[i]);
+
+ if (created || deleted)
+ seq_printf(m, "%s%s: active %d total %d\n",
+ prefix,
binder_objstat_strings[i],
- stats->obj_created[i] - stats->obj_deleted[i],
- stats->obj_created[i]);
+ created - deleted,
+ created);
}
}
@@ -3570,50 +5852,61 @@ static void print_binder_proc_stats(struct seq_file *m,
struct binder_proc *proc)
{
struct binder_work *w;
+ struct binder_thread *thread;
struct rb_node *n;
- int count, strong, weak;
+ int count, strong, weak, ready_threads;
+ size_t free_async_space =
+ binder_alloc_get_free_async_space(&proc->alloc);
seq_printf(m, "proc %d\n", proc->pid);
+ seq_printf(m, "context %s\n", proc->context->name);
count = 0;
+ ready_threads = 0;
+ binder_inner_proc_lock(proc);
for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
count++;
+
+ list_for_each_entry(thread, &proc->waiting_threads, waiting_thread_node)
+ ready_threads++;
+
seq_printf(m, " threads: %d\n", count);
seq_printf(m, " requested threads: %d+%d/%d\n"
" ready threads %d\n"
" free async space %zd\n", proc->requested_threads,
proc->requested_threads_started, proc->max_threads,
- proc->ready_threads, proc->free_async_space);
+ ready_threads,
+ free_async_space);
count = 0;
for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n))
count++;
+ binder_inner_proc_unlock(proc);
seq_printf(m, " nodes: %d\n", count);
count = 0;
strong = 0;
weak = 0;
+ binder_proc_lock(proc);
for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
struct binder_ref *ref = rb_entry(n, struct binder_ref,
rb_node_desc);
count++;
- strong += ref->strong;
- weak += ref->weak;
+ strong += ref->data.strong;
+ weak += ref->data.weak;
}
+ binder_proc_unlock(proc);
seq_printf(m, " refs: %d s %d w %d\n", count, strong, weak);
- count = 0;
- for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
- count++;
+ count = binder_alloc_get_allocated_count(&proc->alloc);
seq_printf(m, " buffers: %d\n", count);
+ binder_alloc_print_pages(m, &proc->alloc);
+
count = 0;
+ binder_inner_proc_lock(proc);
list_for_each_entry(w, &proc->todo, entry) {
- switch (w->type) {
- case BINDER_WORK_TRANSACTION:
+ if (w->type == BINDER_WORK_TRANSACTION)
count++;
- break;
- default:
- break;
- }
}
+ binder_inner_proc_unlock(proc);
seq_printf(m, " pending transactions: %d\n", count);
print_binder_stats(m, " ", &proc->stats);
@@ -3624,107 +5917,131 @@ static int binder_state_show(struct seq_file *m, void *unused)
{
struct binder_proc *proc;
struct binder_node *node;
- int do_lock = !binder_debug_no_lock;
-
- if (do_lock)
- binder_lock(__func__);
+ struct binder_node *last_node = NULL;
seq_puts(m, "binder state:\n");
+ spin_lock(&binder_dead_nodes_lock);
if (!hlist_empty(&binder_dead_nodes))
seq_puts(m, "dead nodes:\n");
- hlist_for_each_entry(node, &binder_dead_nodes, dead_node)
- print_binder_node(m, node);
+ hlist_for_each_entry(node, &binder_dead_nodes, dead_node) {
+ /*
+ * take a temporary reference on the node so it
+ * survives and isn't removed from the list
+ * while we print it.
+ */
+ node->tmp_refs++;
+ spin_unlock(&binder_dead_nodes_lock);
+ if (last_node)
+ binder_put_node(last_node);
+ binder_node_lock(node);
+ print_binder_node_nilocked(m, node);
+ binder_node_unlock(node);
+ last_node = node;
+ spin_lock(&binder_dead_nodes_lock);
+ }
+ spin_unlock(&binder_dead_nodes_lock);
+ if (last_node)
+ binder_put_node(last_node);
+ mutex_lock(&binder_procs_lock);
hlist_for_each_entry(proc, &binder_procs, proc_node)
print_binder_proc(m, proc, 1);
- if (do_lock)
- binder_unlock(__func__);
+ mutex_unlock(&binder_procs_lock);
+
return 0;
}
static int binder_stats_show(struct seq_file *m, void *unused)
{
struct binder_proc *proc;
- int do_lock = !binder_debug_no_lock;
-
- if (do_lock)
- binder_lock(__func__);
seq_puts(m, "binder stats:\n");
print_binder_stats(m, "", &binder_stats);
+ mutex_lock(&binder_procs_lock);
hlist_for_each_entry(proc, &binder_procs, proc_node)
print_binder_proc_stats(m, proc);
- if (do_lock)
- binder_unlock(__func__);
+ mutex_unlock(&binder_procs_lock);
+
return 0;
}
static int binder_transactions_show(struct seq_file *m, void *unused)
{
struct binder_proc *proc;
- int do_lock = !binder_debug_no_lock;
-
- if (do_lock)
- binder_lock(__func__);
seq_puts(m, "binder transactions:\n");
+ mutex_lock(&binder_procs_lock);
hlist_for_each_entry(proc, &binder_procs, proc_node)
print_binder_proc(m, proc, 0);
- if (do_lock)
- binder_unlock(__func__);
+ mutex_unlock(&binder_procs_lock);
+
return 0;
}
static int binder_proc_show(struct seq_file *m, void *unused)
{
struct binder_proc *itr;
- struct binder_proc *proc = m->private;
- int do_lock = !binder_debug_no_lock;
- bool valid_proc = false;
+ int pid = (unsigned long)m->private;
- if (do_lock)
- binder_lock(__func__);
-
+ mutex_lock(&binder_procs_lock);
hlist_for_each_entry(itr, &binder_procs, proc_node) {
- if (itr == proc) {
- valid_proc = true;
- break;
+ if (itr->pid == pid) {
+ seq_puts(m, "binder proc state:\n");
+ print_binder_proc(m, itr, 1);
}
}
- if (valid_proc) {
- seq_puts(m, "binder proc state:\n");
- print_binder_proc(m, proc, 1);
- }
- if (do_lock)
- binder_unlock(__func__);
+ mutex_unlock(&binder_procs_lock);
+
return 0;
}
static void print_binder_transaction_log_entry(struct seq_file *m,
struct binder_transaction_log_entry *e)
{
+ int debug_id = READ_ONCE(e->debug_id_done);
+ /*
+ * read barrier to guarantee debug_id_done read before
+ * we print the log values
+ */
+ smp_rmb();
seq_printf(m,
- "%d: %s from %d:%d to %d:%d node %d handle %d size %d:%d\n",
+ "%d: %s from %d:%d to %d:%d context %s node %d handle %d size %d:%d ret %d/%d l=%d",
e->debug_id, (e->call_type == 2) ? "reply" :
((e->call_type == 1) ? "async" : "call "), e->from_proc,
- e->from_thread, e->to_proc, e->to_thread, e->to_node,
- e->target_handle, e->data_size, e->offsets_size);
+ e->from_thread, e->to_proc, e->to_thread, e->context_name,
+ e->to_node, e->target_handle, e->data_size, e->offsets_size,
+ e->return_error, e->return_error_param,
+ e->return_error_line);
+ /*
+ * read-barrier to guarantee read of debug_id_done after
+ * done printing the fields of the entry
+ */
+ smp_rmb();
+ seq_printf(m, debug_id && debug_id == READ_ONCE(e->debug_id_done) ?
+ "\n" : " (incomplete)\n");
}
static int binder_transaction_log_show(struct seq_file *m, void *unused)
{
struct binder_transaction_log *log = m->private;
+ unsigned int log_cur = atomic_read(&log->cur);
+ unsigned int count;
+ unsigned int cur;
int i;
- if (log->full) {
- for (i = log->next; i < ARRAY_SIZE(log->entry); i++)
- print_binder_transaction_log_entry(m, &log->entry[i]);
+ count = log_cur + 1;
+ cur = count < ARRAY_SIZE(log->entry) && !log->full ?
+ 0 : count % ARRAY_SIZE(log->entry);
+ if (count > ARRAY_SIZE(log->entry) || log->full)
+ count = ARRAY_SIZE(log->entry);
+ for (i = 0; i < count; i++) {
+ unsigned int index = cur++ % ARRAY_SIZE(log->entry);
+
+ print_binder_transaction_log_entry(m, &log->entry[index]);
}
- for (i = 0; i < log->next; i++)
- print_binder_transaction_log_entry(m, &log->entry[i]);
return 0;
}
@@ -3739,53 +6056,118 @@ static const struct file_operations binder_fops = {
.release = binder_release,
};
-static struct miscdevice binder_miscdev = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "binder",
- .fops = &binder_fops
-};
-
BINDER_DEBUG_ENTRY(state);
BINDER_DEBUG_ENTRY(stats);
BINDER_DEBUG_ENTRY(transactions);
BINDER_DEBUG_ENTRY(transaction_log);
+static int __init init_binder_device(const char *name)
+{
+ int ret;
+ struct binder_device *binder_device;
+
+ binder_device = kzalloc(sizeof(*binder_device), GFP_KERNEL);
+ if (!binder_device)
+ return -ENOMEM;
+
+ binder_device->miscdev.fops = &binder_fops;
+ binder_device->miscdev.minor = MISC_DYNAMIC_MINOR;
+ binder_device->miscdev.name = name;
+
+ binder_device->context.binder_context_mgr_uid = INVALID_UID;
+ binder_device->context.name = name;
+ mutex_init(&binder_device->context.context_mgr_node_lock);
+
+ ret = misc_register(&binder_device->miscdev);
+ if (ret < 0) {
+ kfree(binder_device);
+ return ret;
+ }
+
+ hlist_add_head(&binder_device->hlist, &binder_devices);
+
+ return ret;
+}
+
static int __init binder_init(void)
{
int ret;
+ char *device_name, *device_names, *device_tmp;
+ struct binder_device *device;
+ struct hlist_node *tmp;
+
+ ret = binder_alloc_shrinker_init();
+ if (ret)
+ return ret;
+
+ atomic_set(&binder_transaction_log.cur, ~0U);
+ atomic_set(&binder_transaction_log_failed.cur, ~0U);
binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL);
if (binder_debugfs_dir_entry_root)
binder_debugfs_dir_entry_proc = debugfs_create_dir("proc",
binder_debugfs_dir_entry_root);
- ret = misc_register(&binder_miscdev);
+
if (binder_debugfs_dir_entry_root) {
debugfs_create_file("state",
- S_IRUGO,
+ 0444,
binder_debugfs_dir_entry_root,
NULL,
&binder_state_fops);
debugfs_create_file("stats",
- S_IRUGO,
+ 0444,
binder_debugfs_dir_entry_root,
NULL,
&binder_stats_fops);
debugfs_create_file("transactions",
- S_IRUGO,
+ 0444,
binder_debugfs_dir_entry_root,
NULL,
&binder_transactions_fops);
debugfs_create_file("transaction_log",
- S_IRUGO,
+ 0444,
binder_debugfs_dir_entry_root,
&binder_transaction_log,
&binder_transaction_log_fops);
debugfs_create_file("failed_transaction_log",
- S_IRUGO,
+ 0444,
binder_debugfs_dir_entry_root,
&binder_transaction_log_failed,
&binder_transaction_log_fops);
}
+
+ /*
+ * Copy the module_parameter string, because we don't want to
+ * tokenize it in-place.
+ */
+ device_names = kzalloc(strlen(binder_devices_param) + 1, GFP_KERNEL);
+ if (!device_names) {
+ ret = -ENOMEM;
+ goto err_alloc_device_names_failed;
+ }
+ strcpy(device_names, binder_devices_param);
+
+ device_tmp = device_names;
+ while ((device_name = strsep(&device_tmp, ","))) {
+ ret = init_binder_device(device_name);
+ if (ret)
+ goto err_init_binder_device_failed;
+ }
+
+ return ret;
+
+err_init_binder_device_failed:
+ hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) {
+ misc_deregister(&device->miscdev);
+ hlist_del(&device->hlist);
+ kfree(device);
+ }
+
+ kfree(device_names);
+
+err_alloc_device_names_failed:
+ debugfs_remove_recursive(binder_debugfs_dir_entry_root);
+
return ret;
}
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
new file mode 100644
index 0000000..da28422
--- /dev/null
+++ b/drivers/android/binder_alloc.c
@@ -0,0 +1,1157 @@
+/* binder_alloc.c
+ *
+ * Android IPC Subsystem
+ *
+ * Copyright (C) 2007-2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <asm/cacheflush.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/rtmutex.h>
+#include <linux/rbtree.h>
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/list_lru.h>
+#include <linux/uaccess.h>
+#include <linux/highmem.h>
+#include "binder_alloc.h"
+#include "binder_trace.h"
+
+struct list_lru binder_alloc_lru;
+
+static DEFINE_MUTEX(binder_alloc_mmap_lock);
+
+enum {
+ BINDER_DEBUG_OPEN_CLOSE = 1U << 1,
+ BINDER_DEBUG_BUFFER_ALLOC = 1U << 2,
+ BINDER_DEBUG_BUFFER_ALLOC_ASYNC = 1U << 3,
+};
+static uint32_t binder_alloc_debug_mask;
+
+module_param_named(debug_mask, binder_alloc_debug_mask,
+ uint, 0644);
+
+#define binder_alloc_debug(mask, x...) \
+ do { \
+ if (binder_alloc_debug_mask & mask) \
+ pr_info(x); \
+ } while (0)
+
+static struct binder_buffer *binder_buffer_next(struct binder_buffer *buffer)
+{
+ return list_entry(buffer->entry.next, struct binder_buffer, entry);
+}
+
+static struct binder_buffer *binder_buffer_prev(struct binder_buffer *buffer)
+{
+ return list_entry(buffer->entry.prev, struct binder_buffer, entry);
+}
+
+static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
+ struct binder_buffer *buffer)
+{
+ if (list_is_last(&buffer->entry, &alloc->buffers))
+ return alloc->buffer + alloc->buffer_size - buffer->user_data;
+ return binder_buffer_next(buffer)->user_data - buffer->user_data;
+}
+
+static void binder_insert_free_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *new_buffer)
+{
+ struct rb_node **p = &alloc->free_buffers.rb_node;
+ struct rb_node *parent = NULL;
+ struct binder_buffer *buffer;
+ size_t buffer_size;
+ size_t new_buffer_size;
+
+ BUG_ON(!new_buffer->free);
+
+ new_buffer_size = binder_alloc_buffer_size(alloc, new_buffer);
+
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: add free buffer, size %zd, at %pK\n",
+ alloc->pid, new_buffer_size, new_buffer);
+
+ while (*p) {
+ parent = *p;
+ buffer = rb_entry(parent, struct binder_buffer, rb_node);
+ BUG_ON(!buffer->free);
+
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+ if (new_buffer_size < buffer_size)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+ }
+ rb_link_node(&new_buffer->rb_node, parent, p);
+ rb_insert_color(&new_buffer->rb_node, &alloc->free_buffers);
+}
+
+static void binder_insert_allocated_buffer_locked(
+ struct binder_alloc *alloc, struct binder_buffer *new_buffer)
+{
+ struct rb_node **p = &alloc->allocated_buffers.rb_node;
+ struct rb_node *parent = NULL;
+ struct binder_buffer *buffer;
+
+ BUG_ON(new_buffer->free);
+
+ while (*p) {
+ parent = *p;
+ buffer = rb_entry(parent, struct binder_buffer, rb_node);
+ BUG_ON(buffer->free);
+
+ if (new_buffer->user_data < buffer->user_data)
+ p = &parent->rb_left;
+ else if (new_buffer->user_data > buffer->user_data)
+ p = &parent->rb_right;
+ else
+ BUG();
+ }
+ rb_link_node(&new_buffer->rb_node, parent, p);
+ rb_insert_color(&new_buffer->rb_node, &alloc->allocated_buffers);
+}
+
+static struct binder_buffer *binder_alloc_prepare_to_free_locked(
+ struct binder_alloc *alloc,
+ uintptr_t user_ptr)
+{
+ struct rb_node *n = alloc->allocated_buffers.rb_node;
+ struct binder_buffer *buffer;
+ void __user *uptr;
+
+ uptr = (void __user *)user_ptr;
+
+ while (n) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+ BUG_ON(buffer->free);
+
+ if (uptr < buffer->user_data)
+ n = n->rb_left;
+ else if (uptr > buffer->user_data)
+ n = n->rb_right;
+ else {
+ /*
+ * Guard against user threads attempting to
+ * free the buffer when in use by kernel or
+ * after it's already been freed.
+ */
+ if (!buffer->allow_user_free)
+ return ERR_PTR(-EPERM);
+ buffer->allow_user_free = 0;
+ return buffer;
+ }
+ }
+ return NULL;
+}
+
+/**
+ * binder_alloc_buffer_lookup() - get buffer given user ptr
+ * @alloc: binder_alloc for this proc
+ * @user_ptr: User pointer to buffer data
+ *
+ * Validate userspace pointer to buffer data and return buffer corresponding to
+ * that user pointer. Search the rb tree for buffer that matches user data
+ * pointer.
+ *
+ * Return: Pointer to buffer or NULL
+ */
+struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
+ uintptr_t user_ptr)
+{
+ struct binder_buffer *buffer;
+
+ mutex_lock(&alloc->mutex);
+ buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
+ mutex_unlock(&alloc->mutex);
+ return buffer;
+}
+
+static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
+ void __user *start, void __user *end)
+{
+ void __user *page_addr;
+ unsigned long user_page_addr;
+ struct binder_lru_page *page;
+ struct vm_area_struct *vma = NULL;
+ struct mm_struct *mm = NULL;
+ bool need_mm = false;
+
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: %s pages %pK-%pK\n", alloc->pid,
+ allocate ? "allocate" : "free", start, end);
+
+ if (end <= start)
+ return 0;
+
+ trace_binder_update_page_range(alloc, allocate, start, end);
+
+ if (allocate == 0)
+ goto free_range;
+
+ for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+ page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
+ if (!page->page_ptr) {
+ need_mm = true;
+ break;
+ }
+ }
+
+ if (need_mm && mmget_not_zero(alloc->vma_vm_mm))
+ mm = alloc->vma_vm_mm;
+
+ if (mm) {
+ down_read(&mm->mmap_sem);
+ if (!mmget_still_valid(mm)) {
+ if (allocate == 0)
+ goto free_range;
+ goto err_no_vma;
+ }
+ vma = alloc->vma;
+ }
+
+ if (!vma && need_mm) {
+ pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
+ alloc->pid);
+ goto err_no_vma;
+ }
+
+ for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+ int ret;
+ bool on_lru;
+ size_t index;
+
+ index = (page_addr - alloc->buffer) / PAGE_SIZE;
+ page = &alloc->pages[index];
+
+ if (page->page_ptr) {
+ trace_binder_alloc_lru_start(alloc, index);
+
+ on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
+ WARN_ON(!on_lru);
+
+ trace_binder_alloc_lru_end(alloc, index);
+ continue;
+ }
+
+ if (WARN_ON(!vma))
+ goto err_page_ptr_cleared;
+
+ trace_binder_alloc_page_start(alloc, index);
+ page->page_ptr = alloc_page(GFP_KERNEL |
+ __GFP_HIGHMEM |
+ __GFP_ZERO);
+ if (!page->page_ptr) {
+ pr_err("%d: binder_alloc_buf failed for page at %pK\n",
+ alloc->pid, page_addr);
+ goto err_alloc_page_failed;
+ }
+ page->alloc = alloc;
+ INIT_LIST_HEAD(&page->lru);
+
+ user_page_addr = (uintptr_t)page_addr;
+ ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
+ if (ret) {
+ pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
+ alloc->pid, user_page_addr);
+ goto err_vm_insert_page_failed;
+ }
+
+ if (index + 1 > alloc->pages_high)
+ alloc->pages_high = index + 1;
+
+ trace_binder_alloc_page_end(alloc, index);
+ /* vm_insert_page does not seem to increment the refcount */
+ }
+ if (mm) {
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+ return 0;
+
+free_range:
+ for (page_addr = end - PAGE_SIZE; page_addr >= start;
+ page_addr -= PAGE_SIZE) {
+ bool ret;
+ size_t index;
+
+ index = (page_addr - alloc->buffer) / PAGE_SIZE;
+ page = &alloc->pages[index];
+
+ trace_binder_free_lru_start(alloc, index);
+
+ ret = list_lru_add(&binder_alloc_lru, &page->lru);
+ WARN_ON(!ret);
+
+ trace_binder_free_lru_end(alloc, index);
+ continue;
+
+err_vm_insert_page_failed:
+ __free_page(page->page_ptr);
+ page->page_ptr = NULL;
+err_alloc_page_failed:
+err_page_ptr_cleared:
+ ;
+ }
+err_no_vma:
+ if (mm) {
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+ return vma ? -ENOMEM : -ESRCH;
+}
+
+static struct binder_buffer *binder_alloc_new_buf_locked(
+ struct binder_alloc *alloc,
+ size_t data_size,
+ size_t offsets_size,
+ size_t extra_buffers_size,
+ int is_async)
+{
+ struct rb_node *n = alloc->free_buffers.rb_node;
+ struct binder_buffer *buffer;
+ size_t buffer_size;
+ struct rb_node *best_fit = NULL;
+ void __user *has_page_addr;
+ void __user *end_page_addr;
+ size_t size, data_offsets_size;
+ int ret;
+
+ if (alloc->vma == NULL) {
+ pr_err("%d: binder_alloc_buf, no vma\n",
+ alloc->pid);
+ return ERR_PTR(-ESRCH);
+ }
+
+ data_offsets_size = ALIGN(data_size, sizeof(void *)) +
+ ALIGN(offsets_size, sizeof(void *));
+
+ if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: got transaction with invalid size %zd-%zd\n",
+ alloc->pid, data_size, offsets_size);
+ return ERR_PTR(-EINVAL);
+ }
+ size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
+ if (size < data_offsets_size || size < extra_buffers_size) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: got transaction with invalid extra_buffers_size %zd\n",
+ alloc->pid, extra_buffers_size);
+ return ERR_PTR(-EINVAL);
+ }
+ if (is_async &&
+ alloc->free_async_space < size + sizeof(struct binder_buffer)) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: binder_alloc_buf size %zd failed, no async space left\n",
+ alloc->pid, size);
+ return ERR_PTR(-ENOSPC);
+ }
+
+ /* Pad 0-size buffers so they get assigned unique addresses */
+ size = max(size, sizeof(void *));
+
+ while (n) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+ BUG_ON(!buffer->free);
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+ if (size < buffer_size) {
+ best_fit = n;
+ n = n->rb_left;
+ } else if (size > buffer_size)
+ n = n->rb_right;
+ else {
+ best_fit = n;
+ break;
+ }
+ }
+ if (best_fit == NULL) {
+ size_t allocated_buffers = 0;
+ size_t largest_alloc_size = 0;
+ size_t total_alloc_size = 0;
+ size_t free_buffers = 0;
+ size_t largest_free_size = 0;
+ size_t total_free_size = 0;
+
+ for (n = rb_first(&alloc->allocated_buffers); n != NULL;
+ n = rb_next(n)) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+ allocated_buffers++;
+ total_alloc_size += buffer_size;
+ if (buffer_size > largest_alloc_size)
+ largest_alloc_size = buffer_size;
+ }
+ for (n = rb_first(&alloc->free_buffers); n != NULL;
+ n = rb_next(n)) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+ free_buffers++;
+ total_free_size += buffer_size;
+ if (buffer_size > largest_free_size)
+ largest_free_size = buffer_size;
+ }
+ pr_err("%d: binder_alloc_buf size %zd failed, no address space\n",
+ alloc->pid, size);
+ pr_err("allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
+ total_alloc_size, allocated_buffers, largest_alloc_size,
+ total_free_size, free_buffers, largest_free_size);
+ return ERR_PTR(-ENOSPC);
+ }
+ if (n == NULL) {
+ buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+ }
+
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
+ alloc->pid, size, buffer, buffer_size);
+
+ has_page_addr = (void __user *)
+ (((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK);
+ WARN_ON(n && buffer_size != size);
+ end_page_addr =
+ (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+ if (end_page_addr > has_page_addr)
+ end_page_addr = has_page_addr;
+ ret = binder_update_page_range(alloc, 1, (void __user *)
+ PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (buffer_size != size) {
+ struct binder_buffer *new_buffer;
+
+ new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+ if (!new_buffer) {
+ pr_err("%s: %d failed to alloc new buffer struct\n",
+ __func__, alloc->pid);
+ goto err_alloc_buf_struct_failed;
+ }
+ new_buffer->user_data = (u8 __user *)buffer->user_data + size;
+ list_add(&new_buffer->entry, &buffer->entry);
+ new_buffer->free = 1;
+ binder_insert_free_buffer(alloc, new_buffer);
+ }
+
+ rb_erase(best_fit, &alloc->free_buffers);
+ buffer->free = 0;
+ buffer->allow_user_free = 0;
+ binder_insert_allocated_buffer_locked(alloc, buffer);
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: binder_alloc_buf size %zd got %pK\n",
+ alloc->pid, size, buffer);
+ buffer->data_size = data_size;
+ buffer->offsets_size = offsets_size;
+ buffer->async_transaction = is_async;
+ buffer->extra_buffers_size = extra_buffers_size;
+ if (is_async) {
+ alloc->free_async_space -= size + sizeof(struct binder_buffer);
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
+ "%d: binder_alloc_buf size %zd async free %zd\n",
+ alloc->pid, size, alloc->free_async_space);
+ }
+ return buffer;
+
+err_alloc_buf_struct_failed:
+ binder_update_page_range(alloc, 0, (void __user *)
+ PAGE_ALIGN((uintptr_t)buffer->user_data),
+ end_page_addr);
+ return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * binder_alloc_new_buf() - Allocate a new binder buffer
+ * @alloc: binder_alloc for this proc
+ * @data_size: size of user data buffer
+ * @offsets_size: user specified buffer offset
+ * @extra_buffers_size: size of extra space for meta-data (eg, security context)
+ * @is_async: buffer for async transaction
+ *
+ * Allocate a new buffer given the requested sizes. Returns
+ * the kernel version of the buffer pointer. The size allocated
+ * is the sum of the three given sizes (each rounded up to
+ * pointer-sized boundary)
+ *
+ * Return: The allocated buffer or %NULL if error
+ */
+struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
+ size_t data_size,
+ size_t offsets_size,
+ size_t extra_buffers_size,
+ int is_async)
+{
+ struct binder_buffer *buffer;
+
+ mutex_lock(&alloc->mutex);
+ buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
+ extra_buffers_size, is_async);
+ mutex_unlock(&alloc->mutex);
+ return buffer;
+}
+
+static void __user *buffer_start_page(struct binder_buffer *buffer)
+{
+ return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK);
+}
+
+static void __user *prev_buffer_end_page(struct binder_buffer *buffer)
+{
+ return (void __user *)
+ (((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK);
+}
+
+static void binder_delete_free_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer)
+{
+ struct binder_buffer *prev, *next = NULL;
+ bool to_free = true;
+ BUG_ON(alloc->buffers.next == &buffer->entry);
+ prev = binder_buffer_prev(buffer);
+ BUG_ON(!prev->free);
+ if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
+ to_free = false;
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: merge free, buffer %pK share page with %pK\n",
+ alloc->pid, buffer->user_data,
+ prev->user_data);
+ }
+
+ if (!list_is_last(&buffer->entry, &alloc->buffers)) {
+ next = binder_buffer_next(buffer);
+ if (buffer_start_page(next) == buffer_start_page(buffer)) {
+ to_free = false;
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: merge free, buffer %pK share page with %pK\n",
+ alloc->pid,
+ buffer->user_data,
+ next->user_data);
+ }
+ }
+
+ if (PAGE_ALIGNED(buffer->user_data)) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: merge free, buffer start %pK is page aligned\n",
+ alloc->pid, buffer->user_data);
+ to_free = false;
+ }
+
+ if (to_free) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
+ alloc->pid, buffer->user_data,
+ prev->user_data,
+ next ? next->user_data : NULL);
+ binder_update_page_range(alloc, 0, buffer_start_page(buffer),
+ buffer_start_page(buffer) + PAGE_SIZE);
+ }
+ list_del(&buffer->entry);
+ kfree(buffer);
+}
+
+static void binder_free_buf_locked(struct binder_alloc *alloc,
+ struct binder_buffer *buffer)
+{
+ size_t size, buffer_size;
+
+ buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+ size = ALIGN(buffer->data_size, sizeof(void *)) +
+ ALIGN(buffer->offsets_size, sizeof(void *)) +
+ ALIGN(buffer->extra_buffers_size, sizeof(void *));
+
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: binder_free_buf %pK size %zd buffer_size %zd\n",
+ alloc->pid, buffer, size, buffer_size);
+
+ BUG_ON(buffer->free);
+ BUG_ON(size > buffer_size);
+ BUG_ON(buffer->transaction != NULL);
+ BUG_ON(buffer->user_data < alloc->buffer);
+ BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
+
+ if (buffer->async_transaction) {
+ alloc->free_async_space += size + sizeof(struct binder_buffer);
+
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
+ "%d: binder_free_buf size %zd async free %zd\n",
+ alloc->pid, size, alloc->free_async_space);
+ }
+
+ binder_update_page_range(alloc, 0,
+ (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data),
+ (void __user *)(((uintptr_t)
+ buffer->user_data + buffer_size) & PAGE_MASK));
+
+ rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
+ buffer->free = 1;
+ if (!list_is_last(&buffer->entry, &alloc->buffers)) {
+ struct binder_buffer *next = binder_buffer_next(buffer);
+
+ if (next->free) {
+ rb_erase(&next->rb_node, &alloc->free_buffers);
+ binder_delete_free_buffer(alloc, next);
+ }
+ }
+ if (alloc->buffers.next != &buffer->entry) {
+ struct binder_buffer *prev = binder_buffer_prev(buffer);
+
+ if (prev->free) {
+ binder_delete_free_buffer(alloc, buffer);
+ rb_erase(&prev->rb_node, &alloc->free_buffers);
+ buffer = prev;
+ }
+ }
+ binder_insert_free_buffer(alloc, buffer);
+}
+
+/**
+ * binder_alloc_free_buf() - free a binder buffer
+ * @alloc: binder_alloc for this proc
+ * @buffer: kernel pointer to buffer
+ *
+ * Free the buffer allocated via binder_alloc_new_buffer()
+ */
+void binder_alloc_free_buf(struct binder_alloc *alloc,
+ struct binder_buffer *buffer)
+{
+ mutex_lock(&alloc->mutex);
+ binder_free_buf_locked(alloc, buffer);
+ mutex_unlock(&alloc->mutex);
+}
+
+/**
+ * binder_alloc_mmap_handler() - map virtual address space for proc
+ * @alloc: alloc structure for this proc
+ * @vma: vma passed to mmap()
+ *
+ * Called by binder_mmap() to initialize the space specified in
+ * vma for allocating binder buffers
+ *
+ * Return:
+ * 0 = success
+ * -EBUSY = address space already mapped
+ * -ENOMEM = failed to map memory to given address space
+ */
+int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+ struct vm_area_struct *vma)
+{
+ int ret;
+ const char *failure_string;
+ struct binder_buffer *buffer;
+
+ mutex_lock(&binder_alloc_mmap_lock);
+ if (alloc->buffer) {
+ ret = -EBUSY;
+ failure_string = "already mapped";
+ goto err_already_mapped;
+ }
+
+ alloc->buffer = (void __user *)vma->vm_start;
+ mutex_unlock(&binder_alloc_mmap_lock);
+
+ alloc->pages = kzalloc(sizeof(alloc->pages[0]) *
+ ((vma->vm_end - vma->vm_start) / PAGE_SIZE),
+ GFP_KERNEL);
+ if (alloc->pages == NULL) {
+ ret = -ENOMEM;
+ failure_string = "alloc page array";
+ goto err_alloc_pages_failed;
+ }
+ alloc->buffer_size = vma->vm_end - vma->vm_start;
+
+ buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+ if (!buffer) {
+ ret = -ENOMEM;
+ failure_string = "alloc buffer struct";
+ goto err_alloc_buf_struct_failed;
+ }
+
+ buffer->user_data = alloc->buffer;
+ list_add(&buffer->entry, &alloc->buffers);
+ buffer->free = 1;
+ binder_insert_free_buffer(alloc, buffer);
+ alloc->free_async_space = alloc->buffer_size / 2;
+ barrier();
+ alloc->vma = vma;
+ alloc->vma_vm_mm = vma->vm_mm;
+ /* Same as mmgrab() in later kernel versions */
+ atomic_inc(&alloc->vma_vm_mm->mm_count);
+
+ return 0;
+
+err_alloc_buf_struct_failed:
+ kfree(alloc->pages);
+ alloc->pages = NULL;
+err_alloc_pages_failed:
+ mutex_lock(&binder_alloc_mmap_lock);
+ alloc->buffer = NULL;
+err_already_mapped:
+ mutex_unlock(&binder_alloc_mmap_lock);
+ pr_err("%s: %d %lx-%lx %s failed %d\n", __func__,
+ alloc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
+ return ret;
+}
+
+
+void binder_alloc_deferred_release(struct binder_alloc *alloc)
+{
+ struct rb_node *n;
+ int buffers, page_count;
+ struct binder_buffer *buffer;
+
+ BUG_ON(alloc->vma);
+
+ buffers = 0;
+ mutex_lock(&alloc->mutex);
+ while ((n = rb_first(&alloc->allocated_buffers))) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+
+ /* Transaction should already have been freed */
+ BUG_ON(buffer->transaction);
+
+ binder_free_buf_locked(alloc, buffer);
+ buffers++;
+ }
+
+ while (!list_empty(&alloc->buffers)) {
+ buffer = list_first_entry(&alloc->buffers,
+ struct binder_buffer, entry);
+ WARN_ON(!buffer->free);
+
+ list_del(&buffer->entry);
+ WARN_ON_ONCE(!list_empty(&alloc->buffers));
+ kfree(buffer);
+ }
+
+ page_count = 0;
+ if (alloc->pages) {
+ int i;
+
+ for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+ void __user *page_addr;
+ bool on_lru;
+
+ if (!alloc->pages[i].page_ptr)
+ continue;
+
+ on_lru = list_lru_del(&binder_alloc_lru,
+ &alloc->pages[i].lru);
+ page_addr = alloc->buffer + i * PAGE_SIZE;
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%s: %d: page %d at %pK %s\n",
+ __func__, alloc->pid, i, page_addr,
+ on_lru ? "on lru" : "active");
+ __free_page(alloc->pages[i].page_ptr);
+ page_count++;
+ }
+ kfree(alloc->pages);
+ }
+ mutex_unlock(&alloc->mutex);
+ if (alloc->vma_vm_mm)
+ mmdrop(alloc->vma_vm_mm);
+
+ binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
+ "%s: %d buffers %d, pages %d\n",
+ __func__, alloc->pid, buffers, page_count);
+}
+
+static void print_binder_buffer(struct seq_file *m, const char *prefix,
+ struct binder_buffer *buffer)
+{
+ seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
+ prefix, buffer->debug_id, buffer->user_data,
+ buffer->data_size, buffer->offsets_size,
+ buffer->extra_buffers_size,
+ buffer->transaction ? "active" : "delivered");
+}
+
+/**
+ * binder_alloc_print_allocated() - print buffer info
+ * @m: seq_file for output via seq_printf()
+ * @alloc: binder_alloc for this proc
+ *
+ * Prints information about every buffer associated with
+ * the binder_alloc state to the given seq_file
+ */
+void binder_alloc_print_allocated(struct seq_file *m,
+ struct binder_alloc *alloc)
+{
+ struct rb_node *n;
+
+ mutex_lock(&alloc->mutex);
+ for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
+ print_binder_buffer(m, " buffer",
+ rb_entry(n, struct binder_buffer, rb_node));
+ mutex_unlock(&alloc->mutex);
+}
+
+/**
+ * binder_alloc_print_pages() - print page usage
+ * @m: seq_file for output via seq_printf()
+ * @alloc: binder_alloc for this proc
+ */
+void binder_alloc_print_pages(struct seq_file *m,
+ struct binder_alloc *alloc)
+{
+ struct binder_lru_page *page;
+ int i;
+ int active = 0;
+ int lru = 0;
+ int free = 0;
+
+ mutex_lock(&alloc->mutex);
+ for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+ page = &alloc->pages[i];
+ if (!page->page_ptr)
+ free++;
+ else if (list_empty(&page->lru))
+ active++;
+ else
+ lru++;
+ }
+ mutex_unlock(&alloc->mutex);
+ seq_printf(m, " pages: %d:%d:%d\n", active, lru, free);
+ seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high);
+}
+
+/**
+ * binder_alloc_get_allocated_count() - return count of buffers
+ * @alloc: binder_alloc for this proc
+ *
+ * Return: count of allocated buffers
+ */
+int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
+{
+ struct rb_node *n;
+ int count = 0;
+
+ mutex_lock(&alloc->mutex);
+ for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
+ count++;
+ mutex_unlock(&alloc->mutex);
+ return count;
+}
+
+
+/**
+ * binder_alloc_vma_close() - invalidate address space
+ * @alloc: binder_alloc for this proc
+ *
+ * Called from binder_vma_close() when releasing address space.
+ * Clears alloc->vma to prevent new incoming transactions from
+ * allocating more buffers.
+ */
+void binder_alloc_vma_close(struct binder_alloc *alloc)
+{
+ WRITE_ONCE(alloc->vma, NULL);
+}
+
+/**
+ * binder_alloc_free_page() - shrinker callback to free pages
+ * @item: item to free
+ * @lock: lock protecting the item
+ * @cb_arg: callback argument
+ *
+ * Called from list_lru_walk() in binder_shrink_scan() to free
+ * up pages when the system is under memory pressure.
+ */
+enum lru_status binder_alloc_free_page(struct list_head *item,
+ struct list_lru_one *lru,
+ spinlock_t *lock,
+ void *cb_arg)
+{
+ struct mm_struct *mm = NULL;
+ struct binder_lru_page *page = container_of(item,
+ struct binder_lru_page,
+ lru);
+ struct binder_alloc *alloc;
+ uintptr_t page_addr;
+ size_t index;
+ struct vm_area_struct *vma;
+
+ alloc = page->alloc;
+ if (!mutex_trylock(&alloc->mutex))
+ goto err_get_alloc_mutex_failed;
+
+ if (!page->page_ptr)
+ goto err_page_already_freed;
+
+ index = page - alloc->pages;
+ page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+
+ mm = alloc->vma_vm_mm;
+ if (!mmget_not_zero(mm))
+ goto err_mmget;
+ if (!down_write_trylock(&mm->mmap_sem))
+ goto err_down_write_mmap_sem_failed;
+ vma = alloc->vma;
+
+ list_lru_isolate(lru, item);
+ spin_unlock(lock);
+
+ if (vma) {
+ trace_binder_unmap_user_start(alloc, index);
+
+ zap_page_range(vma, page_addr, PAGE_SIZE, NULL);
+
+ trace_binder_unmap_user_end(alloc, index);
+ }
+ up_write(&mm->mmap_sem);
+ mmput(mm);
+
+ trace_binder_unmap_kernel_start(alloc, index);
+
+ __free_page(page->page_ptr);
+ page->page_ptr = NULL;
+
+ trace_binder_unmap_kernel_end(alloc, index);
+
+ spin_lock(lock);
+ mutex_unlock(&alloc->mutex);
+ return LRU_REMOVED_RETRY;
+
+err_down_write_mmap_sem_failed:
+ mmput_async(mm);
+err_mmget:
+err_page_already_freed:
+ mutex_unlock(&alloc->mutex);
+err_get_alloc_mutex_failed:
+ return LRU_SKIP;
+}
+
+static unsigned long
+binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned long ret = list_lru_count(&binder_alloc_lru);
+ return ret;
+}
+
+static unsigned long
+binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned long ret;
+
+ ret = list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+ NULL, sc->nr_to_scan);
+ return ret;
+}
+
+static struct shrinker binder_shrinker = {
+ .count_objects = binder_shrink_count,
+ .scan_objects = binder_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
+/**
+ * binder_alloc_init() - called by binder_open() for per-proc initialization
+ * @alloc: binder_alloc for this proc
+ *
+ * Called from binder_open() to initialize binder_alloc fields for
+ * new binder proc
+ */
+void binder_alloc_init(struct binder_alloc *alloc)
+{
+ alloc->pid = current->group_leader->pid;
+ mutex_init(&alloc->mutex);
+ INIT_LIST_HEAD(&alloc->buffers);
+}
+
+int binder_alloc_shrinker_init(void)
+{
+ int ret = list_lru_init(&binder_alloc_lru);
+
+ if (ret == 0) {
+ ret = register_shrinker(&binder_shrinker);
+ if (ret)
+ list_lru_destroy(&binder_alloc_lru);
+ }
+ return ret;
+}
+
+/**
+ * check_buffer() - verify that buffer/offset is safe to access
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @offset: offset into @buffer data
+ * @bytes: bytes to access from offset
+ *
+ * Check that the @offset/@bytes are within the size of the given
+ * @buffer and that the buffer is currently active and not freeable.
+ * Offsets must also be multiples of sizeof(u32). The kernel is
+ * allowed to touch the buffer in two cases:
+ *
+ * 1) when the buffer is being created:
+ * (buffer->free == 0 && buffer->allow_user_free == 0)
+ * 2) when the buffer is being torn down:
+ * (buffer->free == 0 && buffer->transaction == NULL).
+ *
+ * Return: true if the buffer is safe to access
+ */
+static inline bool check_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t offset, size_t bytes)
+{
+ size_t buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+ return buffer_size >= bytes &&
+ offset <= buffer_size - bytes &&
+ IS_ALIGNED(offset, sizeof(u32)) &&
+ !buffer->free &&
+ (!buffer->allow_user_free || !buffer->transaction);
+}
+
+/**
+ * binder_alloc_get_page() - get kernel pointer for given buffer offset
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @buffer_offset: offset into @buffer data
+ * @pgoffp: address to copy final page offset to
+ *
+ * Lookup the struct page corresponding to the address
+ * at @buffer_offset into @buffer->user_data. If @pgoffp is not
+ * NULL, the byte-offset into the page is written there.
+ *
+ * The caller is responsible to ensure that the offset points
+ * to a valid address within the @buffer and that @buffer is
+ * not freeable by the user. Since it can't be freed, we are
+ * guaranteed that the corresponding elements of @alloc->pages[]
+ * cannot change.
+ *
+ * Return: struct page
+ */
+static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ pgoff_t *pgoffp)
+{
+ binder_size_t buffer_space_offset = buffer_offset +
+ (buffer->user_data - alloc->buffer);
+ pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
+ size_t index = buffer_space_offset >> PAGE_SHIFT;
+ struct binder_lru_page *lru_page;
+
+ lru_page = &alloc->pages[index];
+ *pgoffp = pgoff;
+ return lru_page->page_ptr;
+}
+
+/**
+ * binder_alloc_copy_user_to_buffer() - copy src user to tgt user
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @buffer_offset: offset into @buffer data
+ * @from: userspace pointer to source buffer
+ * @bytes: bytes to copy
+ *
+ * Copy bytes from source userspace to target buffer.
+ *
+ * Return: bytes remaining to be copied
+ */
+unsigned long
+binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ const void __user *from,
+ size_t bytes)
+{
+ if (!check_buffer(alloc, buffer, buffer_offset, bytes))
+ return bytes;
+
+ while (bytes) {
+ unsigned long size;
+ unsigned long ret;
+ struct page *page;
+ pgoff_t pgoff;
+ void *kptr;
+
+ page = binder_alloc_get_page(alloc, buffer,
+ buffer_offset, &pgoff);
+ size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
+ kptr = kmap(page) + pgoff;
+ ret = copy_from_user(kptr, from, size);
+ kunmap(page);
+ if (ret)
+ return bytes - size + ret;
+ bytes -= size;
+ from += size;
+ buffer_offset += size;
+ }
+ return 0;
+}
+
+static void binder_alloc_do_buffer_copy(struct binder_alloc *alloc,
+ bool to_buffer,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ void *ptr,
+ size_t bytes)
+{
+ /* All copies must be 32-bit aligned and 32-bit size */
+ BUG_ON(!check_buffer(alloc, buffer, buffer_offset, bytes));
+
+ while (bytes) {
+ unsigned long size;
+ struct page *page;
+ pgoff_t pgoff;
+ void *tmpptr;
+ void *base_ptr;
+
+ page = binder_alloc_get_page(alloc, buffer,
+ buffer_offset, &pgoff);
+ size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
+ base_ptr = kmap_atomic(page);
+ tmpptr = base_ptr + pgoff;
+ if (to_buffer)
+ memcpy(tmpptr, ptr, size);
+ else
+ memcpy(ptr, tmpptr, size);
+ /*
+ * kunmap_atomic() takes care of flushing the cache
+ * if this device has VIVT cache arch
+ */
+ kunmap_atomic(base_ptr);
+ bytes -= size;
+ pgoff = 0;
+ ptr = ptr + size;
+ buffer_offset += size;
+ }
+}
+
+void binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ void *src,
+ size_t bytes)
+{
+ binder_alloc_do_buffer_copy(alloc, true, buffer, buffer_offset,
+ src, bytes);
+}
+
+void binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
+ void *dest,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ size_t bytes)
+{
+ binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
+ dest, bytes);
+}
+
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
new file mode 100644
index 0000000..b60d161
--- /dev/null
+++ b/drivers/android/binder_alloc.h
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_BINDER_ALLOC_H
+#define _LINUX_BINDER_ALLOC_H
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/rtmutex.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/list_lru.h>
+#include <uapi/linux/android/binder.h>
+
+extern struct list_lru binder_alloc_lru;
+struct binder_transaction;
+
+/**
+ * struct binder_buffer - buffer used for binder transactions
+ * @entry: entry alloc->buffers
+ * @rb_node: node for allocated_buffers/free_buffers rb trees
+ * @free: %true if buffer is free
+ * @allow_user_free: %true if user is allowed to free buffer
+ * @async_transaction: %true if buffer is in use for an async txn
+ * @debug_id: unique ID for debugging
+ * @transaction: pointer to associated struct binder_transaction
+ * @target_node: struct binder_node associated with this buffer
+ * @data_size: size of @transaction data
+ * @offsets_size: size of array of offsets
+ * @extra_buffers_size: size of space for other objects (like sg lists)
+ * @user_data: user pointer to base of buffer space
+ *
+ * Bookkeeping structure for binder transaction buffers
+ */
+struct binder_buffer {
+ struct list_head entry; /* free and allocated entries by address */
+ struct rb_node rb_node; /* free entry by size or allocated entry */
+ /* by address */
+ unsigned free:1;
+ unsigned allow_user_free:1;
+ unsigned async_transaction:1;
+ unsigned debug_id:29;
+
+ struct binder_transaction *transaction;
+
+ struct binder_node *target_node;
+ size_t data_size;
+ size_t offsets_size;
+ size_t extra_buffers_size;
+ void __user *user_data;
+};
+
+/**
+ * struct binder_lru_page - page object used for binder shrinker
+ * @page_ptr: pointer to physical page in mmap'd space
+ * @lru: entry in binder_alloc_lru
+ * @alloc: binder_alloc for a proc
+ */
+struct binder_lru_page {
+ struct list_head lru;
+ struct page *page_ptr;
+ struct binder_alloc *alloc;
+};
+
+/**
+ * struct binder_alloc - per-binder proc state for binder allocator
+ * @vma: vm_area_struct passed to mmap_handler
+ * (invarient after mmap)
+ * @tsk: tid for task that called init for this proc
+ * (invariant after init)
+ * @vma_vm_mm: copy of vma->vm_mm (invarient after mmap)
+ * @buffer: base of per-proc address space mapped via mmap
+ * @buffers: list of all buffers for this proc
+ * @free_buffers: rb tree of buffers available for allocation
+ * sorted by size
+ * @allocated_buffers: rb tree of allocated buffers sorted by address
+ * @free_async_space: VA space available for async buffers. This is
+ * initialized at mmap time to 1/2 the full VA space
+ * @pages: array of binder_lru_page
+ * @buffer_size: size of address space specified via mmap
+ * @pid: pid for associated binder_proc (invariant after init)
+ * @pages_high: high watermark of offset in @pages
+ *
+ * Bookkeeping structure for per-proc address space management for binder
+ * buffers. It is normally initialized during binder_init() and binder_mmap()
+ * calls. The address space is used for both user-visible buffers and for
+ * struct binder_buffer objects used to track the user buffers
+ */
+struct binder_alloc {
+ struct mutex mutex;
+ struct vm_area_struct *vma;
+ struct mm_struct *vma_vm_mm;
+ void __user *buffer;
+ struct list_head buffers;
+ struct rb_root free_buffers;
+ struct rb_root allocated_buffers;
+ size_t free_async_space;
+ struct binder_lru_page *pages;
+ size_t buffer_size;
+ uint32_t buffer_free;
+ int pid;
+ size_t pages_high;
+};
+
+#ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST
+void binder_selftest_alloc(struct binder_alloc *alloc);
+#else
+static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
+#endif
+enum lru_status binder_alloc_free_page(struct list_head *item,
+ struct list_lru_one *lru,
+ spinlock_t *lock, void *cb_arg);
+extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
+ size_t data_size,
+ size_t offsets_size,
+ size_t extra_buffers_size,
+ int is_async);
+extern void binder_alloc_init(struct binder_alloc *alloc);
+extern int binder_alloc_shrinker_init(void);
+extern void binder_alloc_vma_close(struct binder_alloc *alloc);
+extern struct binder_buffer *
+binder_alloc_prepare_to_free(struct binder_alloc *alloc,
+ uintptr_t user_ptr);
+extern void binder_alloc_free_buf(struct binder_alloc *alloc,
+ struct binder_buffer *buffer);
+extern int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+ struct vm_area_struct *vma);
+extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
+extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
+extern void binder_alloc_print_allocated(struct seq_file *m,
+ struct binder_alloc *alloc);
+void binder_alloc_print_pages(struct seq_file *m,
+ struct binder_alloc *alloc);
+
+/**
+ * binder_alloc_get_free_async_space() - get free space available for async
+ * @alloc: binder_alloc for this proc
+ *
+ * Return: the bytes remaining in the address-space for async transactions
+ */
+static inline size_t
+binder_alloc_get_free_async_space(struct binder_alloc *alloc)
+{
+ size_t free_async_space;
+
+ mutex_lock(&alloc->mutex);
+ free_async_space = alloc->free_async_space;
+ mutex_unlock(&alloc->mutex);
+ return free_async_space;
+}
+
+unsigned long
+binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ const void __user *from,
+ size_t bytes);
+
+void binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ void *src,
+ size_t bytes);
+
+void binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
+ void *dest,
+ struct binder_buffer *buffer,
+ binder_size_t buffer_offset,
+ size_t bytes);
+
+#endif /* _LINUX_BINDER_ALLOC_H */
+
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
new file mode 100644
index 0000000..b727089
--- /dev/null
+++ b/drivers/android/binder_alloc_selftest.c
@@ -0,0 +1,311 @@
+/* binder_alloc_selftest.c
+ *
+ * Android IPC Subsystem
+ *
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm_types.h>
+#include <linux/err.h>
+#include "binder_alloc.h"
+
+#define BUFFER_NUM 5
+#define BUFFER_MIN_SIZE (PAGE_SIZE / 8)
+
+static bool binder_selftest_run = true;
+static int binder_selftest_failures;
+static DEFINE_MUTEX(binder_selftest_lock);
+
+/**
+ * enum buf_end_align_type - Page alignment of a buffer
+ * end with regard to the end of the previous buffer.
+ *
+ * In the pictures below, buf2 refers to the buffer we
+ * are aligning. buf1 refers to previous buffer by addr.
+ * Symbol [ means the start of a buffer, ] means the end
+ * of a buffer, and | means page boundaries.
+ */
+enum buf_end_align_type {
+ /**
+ * @SAME_PAGE_UNALIGNED: The end of this buffer is on
+ * the same page as the end of the previous buffer and
+ * is not page aligned. Examples:
+ * buf1 ][ buf2 ][ ...
+ * buf1 ]|[ buf2 ][ ...
+ */
+ SAME_PAGE_UNALIGNED = 0,
+ /**
+ * @SAME_PAGE_ALIGNED: When the end of the previous buffer
+ * is not page aligned, the end of this buffer is on the
+ * same page as the end of the previous buffer and is page
+ * aligned. When the previous buffer is page aligned, the
+ * end of this buffer is aligned to the next page boundary.
+ * Examples:
+ * buf1 ][ buf2 ]| ...
+ * buf1 ]|[ buf2 ]| ...
+ */
+ SAME_PAGE_ALIGNED,
+ /**
+ * @NEXT_PAGE_UNALIGNED: The end of this buffer is on
+ * the page next to the end of the previous buffer and
+ * is not page aligned. Examples:
+ * buf1 ][ buf2 | buf2 ][ ...
+ * buf1 ]|[ buf2 | buf2 ][ ...
+ */
+ NEXT_PAGE_UNALIGNED,
+ /**
+ * @NEXT_PAGE_ALIGNED: The end of this buffer is on
+ * the page next to the end of the previous buffer and
+ * is page aligned. Examples:
+ * buf1 ][ buf2 | buf2 ]| ...
+ * buf1 ]|[ buf2 | buf2 ]| ...
+ */
+ NEXT_PAGE_ALIGNED,
+ /**
+ * @NEXT_NEXT_UNALIGNED: The end of this buffer is on
+ * the page that follows the page after the end of the
+ * previous buffer and is not page aligned. Examples:
+ * buf1 ][ buf2 | buf2 | buf2 ][ ...
+ * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
+ */
+ NEXT_NEXT_UNALIGNED,
+ LOOP_END,
+};
+
+static void pr_err_size_seq(size_t *sizes, int *seq)
+{
+ int i;
+
+ pr_err("alloc sizes: ");
+ for (i = 0; i < BUFFER_NUM; i++)
+ pr_cont("[%zu]", sizes[i]);
+ pr_cont("\n");
+ pr_err("free seq: ");
+ for (i = 0; i < BUFFER_NUM; i++)
+ pr_cont("[%d]", seq[i]);
+ pr_cont("\n");
+}
+
+static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
+ struct binder_buffer *buffer,
+ size_t size)
+{
+ void __user *page_addr;
+ void __user *end;
+ int page_index;
+
+ end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+ page_addr = buffer->user_data;
+ for (; page_addr < end; page_addr += PAGE_SIZE) {
+ page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
+ if (!alloc->pages[page_index].page_ptr ||
+ !list_empty(&alloc->pages[page_index].lru)) {
+ pr_err("expect alloc but is %s at page index %d\n",
+ alloc->pages[page_index].page_ptr ?
+ "lru" : "free", page_index);
+ return false;
+ }
+ }
+ return true;
+}
+
+static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
+ struct binder_buffer *buffers[],
+ size_t *sizes, int *seq)
+{
+ int i;
+
+ for (i = 0; i < BUFFER_NUM; i++) {
+ buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0);
+ if (IS_ERR(buffers[i]) ||
+ !check_buffer_pages_allocated(alloc, buffers[i],
+ sizes[i])) {
+ pr_err_size_seq(sizes, seq);
+ binder_selftest_failures++;
+ }
+ }
+}
+
+static void binder_selftest_free_buf(struct binder_alloc *alloc,
+ struct binder_buffer *buffers[],
+ size_t *sizes, int *seq, size_t end)
+{
+ int i;
+
+ for (i = 0; i < BUFFER_NUM; i++)
+ binder_alloc_free_buf(alloc, buffers[seq[i]]);
+
+ for (i = 0; i < end / PAGE_SIZE; i++) {
+ /**
+ * Error message on a free page can be false positive
+ * if binder shrinker ran during binder_alloc_free_buf
+ * calls above.
+ */
+ if (list_empty(&alloc->pages[i].lru)) {
+ pr_err_size_seq(sizes, seq);
+ pr_err("expect lru but is %s at page index %d\n",
+ alloc->pages[i].page_ptr ? "alloc" : "free", i);
+ binder_selftest_failures++;
+ }
+ }
+}
+
+static void binder_selftest_free_page(struct binder_alloc *alloc)
+{
+ int i;
+ unsigned long count;
+
+ while ((count = list_lru_count(&binder_alloc_lru))) {
+ list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+ NULL, count);
+ }
+
+ for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
+ if (alloc->pages[i].page_ptr) {
+ pr_err("expect free but is %s at page index %d\n",
+ list_empty(&alloc->pages[i].lru) ?
+ "alloc" : "lru", i);
+ binder_selftest_failures++;
+ }
+ }
+}
+
+static void binder_selftest_alloc_free(struct binder_alloc *alloc,
+ size_t *sizes, int *seq, size_t end)
+{
+ struct binder_buffer *buffers[BUFFER_NUM];
+
+ binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+ binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+
+ /* Allocate from lru. */
+ binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+ if (list_lru_count(&binder_alloc_lru))
+ pr_err("lru list should be empty but is not\n");
+
+ binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+ binder_selftest_free_page(alloc);
+}
+
+static bool is_dup(int *seq, int index, int val)
+{
+ int i;
+
+ for (i = 0; i < index; i++) {
+ if (seq[i] == val)
+ return true;
+ }
+ return false;
+}
+
+/* Generate BUFFER_NUM factorial free orders. */
+static void binder_selftest_free_seq(struct binder_alloc *alloc,
+ size_t *sizes, int *seq,
+ int index, size_t end)
+{
+ int i;
+
+ if (index == BUFFER_NUM) {
+ binder_selftest_alloc_free(alloc, sizes, seq, end);
+ return;
+ }
+ for (i = 0; i < BUFFER_NUM; i++) {
+ if (is_dup(seq, index, i))
+ continue;
+ seq[index] = i;
+ binder_selftest_free_seq(alloc, sizes, seq, index + 1, end);
+ }
+}
+
+static void binder_selftest_alloc_size(struct binder_alloc *alloc,
+ size_t *end_offset)
+{
+ int i;
+ int seq[BUFFER_NUM] = {0};
+ size_t front_sizes[BUFFER_NUM];
+ size_t back_sizes[BUFFER_NUM];
+ size_t last_offset, offset = 0;
+
+ for (i = 0; i < BUFFER_NUM; i++) {
+ last_offset = offset;
+ offset = end_offset[i];
+ front_sizes[i] = offset - last_offset;
+ back_sizes[BUFFER_NUM - i - 1] = front_sizes[i];
+ }
+ /*
+ * Buffers share the first or last few pages.
+ * Only BUFFER_NUM - 1 buffer sizes are adjustable since
+ * we need one giant buffer before getting to the last page.
+ */
+ back_sizes[0] += alloc->buffer_size - end_offset[BUFFER_NUM - 1];
+ binder_selftest_free_seq(alloc, front_sizes, seq, 0,
+ end_offset[BUFFER_NUM - 1]);
+ binder_selftest_free_seq(alloc, back_sizes, seq, 0, alloc->buffer_size);
+}
+
+static void binder_selftest_alloc_offset(struct binder_alloc *alloc,
+ size_t *end_offset, int index)
+{
+ int align;
+ size_t end, prev;
+
+ if (index == BUFFER_NUM) {
+ binder_selftest_alloc_size(alloc, end_offset);
+ return;
+ }
+ prev = index == 0 ? 0 : end_offset[index - 1];
+ end = prev;
+
+ BUILD_BUG_ON(BUFFER_MIN_SIZE * BUFFER_NUM >= PAGE_SIZE);
+
+ for (align = SAME_PAGE_UNALIGNED; align < LOOP_END; align++) {
+ if (align % 2)
+ end = ALIGN(end, PAGE_SIZE);
+ else
+ end += BUFFER_MIN_SIZE;
+ end_offset[index] = end;
+ binder_selftest_alloc_offset(alloc, end_offset, index + 1);
+ }
+}
+
+/**
+ * binder_selftest_alloc() - Test alloc and free of buffer pages.
+ * @alloc: Pointer to alloc struct.
+ *
+ * Allocate BUFFER_NUM buffers to cover all page alignment cases,
+ * then free them in all orders possible. Check that pages are
+ * correctly allocated, put onto lru when buffers are freed, and
+ * are freed when binder_alloc_free_page is called.
+ */
+void binder_selftest_alloc(struct binder_alloc *alloc)
+{
+ size_t end_offset[BUFFER_NUM];
+
+ if (!binder_selftest_run)
+ return;
+ mutex_lock(&binder_selftest_lock);
+ if (!binder_selftest_run || !alloc->vma)
+ goto done;
+ pr_info("STARTED\n");
+ binder_selftest_alloc_offset(alloc, end_offset, 0);
+ binder_selftest_run = false;
+ if (binder_selftest_failures > 0)
+ pr_info("%d tests FAILED\n", binder_selftest_failures);
+ else
+ pr_info("PASSED\n");
+
+done:
+ mutex_unlock(&binder_selftest_lock);
+}
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
index 7f20f3d..7674231 100644
--- a/drivers/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -23,7 +23,8 @@
struct binder_buffer;
struct binder_node;
struct binder_proc;
-struct binder_ref;
+struct binder_alloc;
+struct binder_ref_data;
struct binder_thread;
struct binder_transaction;
@@ -84,6 +85,30 @@ DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_ioctl_done);
DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_write_done);
DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_read_done);
+TRACE_EVENT(binder_set_priority,
+ TP_PROTO(int proc, int thread, unsigned int old_prio,
+ unsigned int desired_prio, unsigned int new_prio),
+ TP_ARGS(proc, thread, old_prio, new_prio, desired_prio),
+
+ TP_STRUCT__entry(
+ __field(int, proc)
+ __field(int, thread)
+ __field(unsigned int, old_prio)
+ __field(unsigned int, new_prio)
+ __field(unsigned int, desired_prio)
+ ),
+ TP_fast_assign(
+ __entry->proc = proc;
+ __entry->thread = thread;
+ __entry->old_prio = old_prio;
+ __entry->new_prio = new_prio;
+ __entry->desired_prio = desired_prio;
+ ),
+ TP_printk("proc=%d thread=%d old=%d => new=%d desired=%d",
+ __entry->proc, __entry->thread, __entry->old_prio,
+ __entry->new_prio, __entry->desired_prio)
+);
+
TRACE_EVENT(binder_wait_for_work,
TP_PROTO(bool proc_work, bool transaction_stack, bool thread_todo),
TP_ARGS(proc_work, transaction_stack, thread_todo),
@@ -146,8 +171,8 @@ TRACE_EVENT(binder_transaction_received,
TRACE_EVENT(binder_transaction_node_to_ref,
TP_PROTO(struct binder_transaction *t, struct binder_node *node,
- struct binder_ref *ref),
- TP_ARGS(t, node, ref),
+ struct binder_ref_data *rdata),
+ TP_ARGS(t, node, rdata),
TP_STRUCT__entry(
__field(int, debug_id)
@@ -160,8 +185,8 @@ TRACE_EVENT(binder_transaction_node_to_ref,
__entry->debug_id = t->debug_id;
__entry->node_debug_id = node->debug_id;
__entry->node_ptr = node->ptr;
- __entry->ref_debug_id = ref->debug_id;
- __entry->ref_desc = ref->desc;
+ __entry->ref_debug_id = rdata->debug_id;
+ __entry->ref_desc = rdata->desc;
),
TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d",
__entry->debug_id, __entry->node_debug_id,
@@ -170,8 +195,9 @@ TRACE_EVENT(binder_transaction_node_to_ref,
);
TRACE_EVENT(binder_transaction_ref_to_node,
- TP_PROTO(struct binder_transaction *t, struct binder_ref *ref),
- TP_ARGS(t, ref),
+ TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+ struct binder_ref_data *rdata),
+ TP_ARGS(t, node, rdata),
TP_STRUCT__entry(
__field(int, debug_id)
@@ -182,10 +208,10 @@ TRACE_EVENT(binder_transaction_ref_to_node,
),
TP_fast_assign(
__entry->debug_id = t->debug_id;
- __entry->ref_debug_id = ref->debug_id;
- __entry->ref_desc = ref->desc;
- __entry->node_debug_id = ref->node->debug_id;
- __entry->node_ptr = ref->node->ptr;
+ __entry->ref_debug_id = rdata->debug_id;
+ __entry->ref_desc = rdata->desc;
+ __entry->node_debug_id = node->debug_id;
+ __entry->node_ptr = node->ptr;
),
TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx",
__entry->debug_id, __entry->node_debug_id,
@@ -194,9 +220,10 @@ TRACE_EVENT(binder_transaction_ref_to_node,
);
TRACE_EVENT(binder_transaction_ref_to_ref,
- TP_PROTO(struct binder_transaction *t, struct binder_ref *src_ref,
- struct binder_ref *dest_ref),
- TP_ARGS(t, src_ref, dest_ref),
+ TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+ struct binder_ref_data *src_ref,
+ struct binder_ref_data *dest_ref),
+ TP_ARGS(t, node, src_ref, dest_ref),
TP_STRUCT__entry(
__field(int, debug_id)
@@ -208,7 +235,7 @@ TRACE_EVENT(binder_transaction_ref_to_ref,
),
TP_fast_assign(
__entry->debug_id = t->debug_id;
- __entry->node_debug_id = src_ref->node->debug_id;
+ __entry->node_debug_id = node->debug_id;
__entry->src_ref_debug_id = src_ref->debug_id;
__entry->src_ref_desc = src_ref->desc;
__entry->dest_ref_debug_id = dest_ref->debug_id;
@@ -268,9 +295,9 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release,
TP_ARGS(buffer));
TRACE_EVENT(binder_update_page_range,
- TP_PROTO(struct binder_proc *proc, bool allocate,
- void *start, void *end),
- TP_ARGS(proc, allocate, start, end),
+ TP_PROTO(struct binder_alloc *alloc, bool allocate,
+ void __user *start, void __user *end),
+ TP_ARGS(alloc, allocate, start, end),
TP_STRUCT__entry(
__field(int, proc)
__field(bool, allocate)
@@ -278,9 +305,9 @@ TRACE_EVENT(binder_update_page_range,
__field(size_t, size)
),
TP_fast_assign(
- __entry->proc = proc->pid;
+ __entry->proc = alloc->pid;
__entry->allocate = allocate;
- __entry->offset = start - proc->buffer;
+ __entry->offset = start - alloc->buffer;
__entry->size = end - start;
),
TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
@@ -288,6 +315,61 @@ TRACE_EVENT(binder_update_page_range,
__entry->offset, __entry->size)
);
+DECLARE_EVENT_CLASS(binder_lru_page_class,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index),
+ TP_STRUCT__entry(
+ __field(int, proc)
+ __field(size_t, page_index)
+ ),
+ TP_fast_assign(
+ __entry->proc = alloc->pid;
+ __entry->page_index = page_index;
+ ),
+ TP_printk("proc=%d page_index=%zu",
+ __entry->proc, __entry->page_index)
+);
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_start,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_end,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_start,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_end,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_start,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_end,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_start,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_end,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_start,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_end,
+ TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+ TP_ARGS(alloc, page_index));
+
TRACE_EVENT(binder_command,
TP_PROTO(uint32_t cmd),
TP_ARGS(cmd),
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 0651010..c9f6bae 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -246,7 +246,6 @@
config DMA_SHARED_BUFFER
bool
default n
- select ANON_INODES
help
This option enables the framework for buffer-sharing between
multiple drivers. A buffer is associated with a file using driver
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index d707cd1..79d7d7b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -33,6 +33,7 @@
#include <linux/cpufreq.h>
#include <linux/cpuidle.h>
#include <linux/timer.h>
+#include <linux/wakeup_reason.h>
#include "../base.h"
#include "power.h"
@@ -1353,6 +1354,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
pm_callback_t callback = NULL;
char *info = NULL;
int error = 0;
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
DECLARE_DPM_WATCHDOG_ON_STACK(wd);
TRACE_DEVICE(dev);
@@ -1379,6 +1381,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
pm_runtime_barrier(dev);
if (pm_wakeup_pending()) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
dev->power.direct_complete = false;
async_error = -EBUSY;
goto Complete;
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 23ee46a..e494a93 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -708,7 +708,7 @@ static void _remove_opp_dev(struct opp_device *opp_dev,
struct opp_table *opp_table)
{
opp_debug_unregister(opp_dev, opp_table);
- list_del(&opp_dev->node);
+ list_del_rcu(&opp_dev->node);
call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head,
_kfree_opp_dev_rcu);
}
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 9f51a16..fd1b5c8 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -15,6 +15,7 @@
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pm_wakeirq.h>
+#include <linux/types.h>
#include <trace/events/power.h>
#include "power.h"
@@ -810,6 +811,37 @@ void pm_wakeup_event(struct device *dev, unsigned int msec)
}
EXPORT_SYMBOL_GPL(pm_wakeup_event);
+void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max)
+{
+ struct wakeup_source *ws, *last_active_ws = NULL;
+ int len = 0;
+ bool active = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+ if (ws->active && len < max) {
+ if (!active)
+ len += scnprintf(pending_wakeup_source, max,
+ "Pending Wakeup Sources: ");
+ len += scnprintf(pending_wakeup_source + len, max - len,
+ "%s ", ws->name);
+ active = true;
+ } else if (!active &&
+ (!last_active_ws ||
+ ktime_to_ns(ws->last_time) >
+ ktime_to_ns(last_active_ws->last_time))) {
+ last_active_ws = ws;
+ }
+ }
+ if (!active && last_active_ws) {
+ scnprintf(pending_wakeup_source, max,
+ "Last active Wakeup Source: %s",
+ last_active_ws->name);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources);
+
void pm_print_active_wakeup_sources(void)
{
struct wakeup_source *ws;
@@ -1017,7 +1049,7 @@ static int print_wakeup_source_stats(struct seq_file *m,
active_time = ktime_set(0, 0);
}
- seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
+ seq_printf(m, "%-32s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
ws->name, active_count, ws->event_count,
ws->wakeup_count, ws->expire_count,
ktime_to_ms(active_time), ktime_to_ms(total_time),
@@ -1038,7 +1070,7 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
struct wakeup_source *ws;
int srcuidx;
- seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+ seq_puts(m, "name\t\t\t\t\tactive_count\tevent_count\twakeup_count\t"
"expire_count\tactive_since\ttotal_time\tmax_time\t"
"last_change\tprevent_suspend_time\n");
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index 8d98a32..96c34a9 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/suspend.h>
#include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
static LIST_HEAD(syscore_ops_list);
static DEFINE_MUTEX(syscore_ops_lock);
@@ -75,6 +76,8 @@ int syscore_suspend(void)
return 0;
err_out:
+ log_suspend_abort_reason("System core suspend callback %pF failed",
+ ops->suspend);
pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
list_for_each_entry_continue(ops, &syscore_ops_list, node)
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index ab62b81..dece26f 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -1070,7 +1070,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
.done = 0,
.flags = flags,
.error = 0,
- .kref = { ATOMIC_INIT(2) },
+ .kref = KREF_INIT(2),
};
if (!get_ldev_if_state(device, D_ATTACHING)) { /* put is in drbd_bm_aio_ctx_destroy() */
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f236b79..8ceaec2 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -211,33 +211,46 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
* LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
* will get updated by ioctl(LOOP_GET_STATUS)
*/
- blk_mq_freeze_queue(lo->lo_queue);
+ if (lo->lo_state == Lo_bound)
+ blk_mq_freeze_queue(lo->lo_queue);
lo->use_dio = use_dio;
if (use_dio)
lo->lo_flags |= LO_FLAGS_DIRECT_IO;
else
lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
- blk_mq_unfreeze_queue(lo->lo_queue);
+ if (lo->lo_state == Lo_bound)
+ blk_mq_unfreeze_queue(lo->lo_queue);
}
+/**
+ * loop_validate_block_size() - validates the passed in block size
+ * @bsize: size to validate
+ */
static int
-figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
+loop_validate_block_size(unsigned short bsize)
{
- loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
- sector_t x = (sector_t)size;
+ if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * loop_set_size() - sets device size and notifies userspace
+ * @lo: struct loop_device to set the size for
+ * @size: new size of the loop device
+ *
+ * Callers must validate that the size passed into this function fits into
+ * a sector_t, eg using loop_validate_size()
+ */
+static void loop_set_size(struct loop_device *lo, loff_t size)
+{
struct block_device *bdev = lo->lo_device;
- if (unlikely((loff_t)x != size))
- return -EFBIG;
- if (lo->lo_offset != offset)
- lo->lo_offset = offset;
- if (lo->lo_sizelimit != sizelimit)
- lo->lo_sizelimit = sizelimit;
- set_capacity(lo->lo_disk, x);
- bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
+ set_capacity(lo->lo_disk, size);
+ bd_set_size(bdev, size << 9);
/* let user-space know about the new size */
kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
- return 0;
}
static inline int
@@ -883,98 +896,6 @@ static int loop_prepare_queue(struct loop_device *lo)
return 0;
}
-static int loop_set_fd(struct loop_device *lo, fmode_t mode,
- struct block_device *bdev, unsigned int arg)
-{
- struct file *file;
- struct inode *inode;
- struct address_space *mapping;
- unsigned lo_blocksize;
- int lo_flags = 0;
- int error;
- loff_t size;
-
- /* This is safe, since we have a reference from open(). */
- __module_get(THIS_MODULE);
-
- error = -EBADF;
- file = fget(arg);
- if (!file)
- goto out;
-
- error = -EBUSY;
- if (lo->lo_state != Lo_unbound)
- goto out_putf;
-
- error = loop_validate_file(file, bdev);
- if (error)
- goto out_putf;
-
- mapping = file->f_mapping;
- inode = mapping->host;
-
- if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
- !file->f_op->write_iter)
- lo_flags |= LO_FLAGS_READ_ONLY;
-
- lo_blocksize = S_ISBLK(inode->i_mode) ?
- inode->i_bdev->bd_block_size : PAGE_SIZE;
-
- error = -EFBIG;
- size = get_loop_size(lo, file);
- if ((loff_t)(sector_t)size != size)
- goto out_putf;
- error = loop_prepare_queue(lo);
- if (error)
- goto out_putf;
-
- error = 0;
-
- set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
-
- lo->use_dio = false;
- lo->lo_blocksize = lo_blocksize;
- lo->lo_device = bdev;
- lo->lo_flags = lo_flags;
- lo->lo_backing_file = file;
- lo->transfer = NULL;
- lo->ioctl = NULL;
- lo->lo_sizelimit = 0;
- lo->old_gfp_mask = mapping_gfp_mask(mapping);
- mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-
- if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
- blk_queue_write_cache(lo->lo_queue, true, false);
-
- loop_update_dio(lo);
- set_capacity(lo->lo_disk, size);
- bd_set_size(bdev, size << 9);
- loop_sysfs_init(lo);
- /* let user-space know about the new size */
- kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
-
- set_blocksize(bdev, lo_blocksize);
-
- lo->lo_state = Lo_bound;
- if (part_shift)
- lo->lo_flags |= LO_FLAGS_PARTSCAN;
- if (lo->lo_flags & LO_FLAGS_PARTSCAN)
- loop_reread_partitions(lo, bdev);
-
- /* Grab the block_device to prevent its destruction after we
- * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
- */
- bdgrab(bdev);
- return 0;
-
- out_putf:
- fput(file);
- out:
- /* This is safe: open() is still holding a reference. */
- module_put(THIS_MODULE);
- return error;
-}
-
static int
loop_release_xfer(struct loop_device *lo)
{
@@ -1012,6 +933,179 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
return err;
}
+/**
+ * loop_set_status_from_info - configure device from loop_info
+ * @lo: struct loop_device to configure
+ * @info: struct loop_info64 to configure the device with
+ *
+ * Configures the loop device parameters according to the passed
+ * in loop_info64 configuration.
+ */
+static int
+loop_set_status_from_info(struct loop_device *lo,
+ const struct loop_info64 *info)
+{
+ int err;
+ struct loop_func_table *xfer;
+ kuid_t uid = current_uid();
+
+ if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
+ return -EINVAL;
+
+ err = loop_release_xfer(lo);
+ if (err)
+ return err;
+
+ if (info->lo_encrypt_type) {
+ unsigned int type = info->lo_encrypt_type;
+
+ if (type >= MAX_LO_CRYPT)
+ return -EINVAL;
+ xfer = xfer_funcs[type];
+ if (xfer == NULL)
+ return -EINVAL;
+ } else
+ xfer = NULL;
+
+ err = loop_init_xfer(lo, xfer, info);
+ if (err)
+ return err;
+
+ lo->lo_offset = info->lo_offset;
+ lo->lo_sizelimit = info->lo_sizelimit;
+ memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
+ memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
+ lo->lo_file_name[LO_NAME_SIZE-1] = 0;
+ lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
+
+ if (!xfer)
+ xfer = &none_funcs;
+ lo->transfer = xfer->transfer;
+ lo->ioctl = xfer->ioctl;
+
+ lo->lo_flags = info->lo_flags;
+
+ lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
+ lo->lo_init[0] = info->lo_init[0];
+ lo->lo_init[1] = info->lo_init[1];
+ if (info->lo_encrypt_key_size) {
+ memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
+ info->lo_encrypt_key_size);
+ lo->lo_key_owner = uid;
+ }
+
+ return 0;
+}
+
+static int loop_configure(struct loop_device *lo, fmode_t mode,
+ struct block_device *bdev,
+ const struct loop_config *config)
+{
+ struct file *file;
+ struct inode *inode;
+ struct address_space *mapping;
+ int error;
+ loff_t size;
+ unsigned short bsize;
+
+ /* This is safe, since we have a reference from open(). */
+ __module_get(THIS_MODULE);
+
+ error = -EBADF;
+ file = fget(config->fd);
+ if (!file)
+ goto out;
+
+ error = -EBUSY;
+ if (lo->lo_state != Lo_unbound)
+ goto out_putf;
+
+ error = loop_validate_file(file, bdev);
+ if (error)
+ goto out_putf;
+
+ mapping = file->f_mapping;
+ inode = mapping->host;
+
+ size = get_loop_size(lo, file);
+
+ if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
+ error = -EINVAL;
+ goto out_putf;
+ }
+
+ if (config->block_size) {
+ error = loop_validate_block_size(config->block_size);
+ if (error)
+ goto out_putf;
+ }
+
+ error = loop_set_status_from_info(lo, &config->info);
+ if (error)
+ goto out_putf;
+
+ if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+ !file->f_op->write_iter)
+ lo->lo_flags |= LO_FLAGS_READ_ONLY;
+
+ error = loop_prepare_queue(lo);
+ if (error)
+ goto out_putf;
+
+ error = 0;
+
+ set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0);
+
+ lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
+ lo->lo_device = bdev;
+ lo->lo_backing_file = file;
+ lo->old_gfp_mask = mapping_gfp_mask(mapping);
+ mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+
+ if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
+ blk_queue_write_cache(lo->lo_queue, true, false);
+
+ if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) {
+ /* In case of direct I/O, match underlying block size */
+ unsigned short bsize = bdev_logical_block_size(
+ inode->i_sb->s_bdev);
+
+ blk_queue_logical_block_size(lo->lo_queue, bsize);
+ }
+
+ loop_update_dio(lo);
+ loop_sysfs_init(lo);
+ loop_set_size(lo, size);
+
+ if (config->block_size)
+ bsize = config->block_size;
+ else
+ bsize = S_ISBLK(inode->i_mode) ?
+ block_size(inode->i_bdev) : PAGE_SIZE;
+
+ lo->lo_blocksize = bsize;
+ set_blocksize(bdev, bsize);
+
+ lo->lo_state = Lo_bound;
+ if (part_shift)
+ lo->lo_flags |= LO_FLAGS_PARTSCAN;
+ if (lo->lo_flags & LO_FLAGS_PARTSCAN)
+ loop_reread_partitions(lo, bdev);
+
+ /* Grab the block_device to prevent its destruction after we
+ * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
+ */
+ bdgrab(bdev);
+ return 0;
+
+ out_putf:
+ fput(file);
+ out:
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+ return error;
+}
+
static int loop_clr_fd(struct loop_device *lo)
{
struct file *filp = lo->lo_backing_file;
@@ -1059,6 +1153,7 @@ static int loop_clr_fd(struct loop_device *lo)
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
+ blk_queue_logical_block_size(lo->lo_queue, 512);
if (bdev) {
bdput(bdev);
invalidate_bdev(bdev);
@@ -1097,85 +1192,65 @@ static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
- struct loop_func_table *xfer;
kuid_t uid = current_uid();
+ int prev_lo_flags;
+ bool size_changed = false;
if (lo->lo_encrypt_key_size &&
!uid_eq(lo->lo_key_owner, uid) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (lo->lo_state != Lo_bound)
+ if (lo->lo_state != Lo_bound) {
return -ENXIO;
- if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
- return -EINVAL;
+ }
+
+ if (lo->lo_offset != info->lo_offset ||
+ lo->lo_sizelimit != info->lo_sizelimit) {
+ size_changed = true;
+ sync_blockdev(lo->lo_device);
+ kill_bdev(lo->lo_device);
+ }
/* I/O need to be drained during transfer transition */
blk_mq_freeze_queue(lo->lo_queue);
- err = loop_release_xfer(lo);
+ if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) {
+ /* If any pages were dirtied after kill_bdev(), try again */
+ err = -EAGAIN;
+ pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+ __func__, lo->lo_number, lo->lo_file_name,
+ lo->lo_device->bd_inode->i_mapping->nrpages);
+ goto exit;
+ }
+
+ prev_lo_flags = lo->lo_flags;
+
+ err = loop_set_status_from_info(lo, info);
if (err)
goto exit;
- if (info->lo_encrypt_type) {
- unsigned int type = info->lo_encrypt_type;
-
- if (type >= MAX_LO_CRYPT) {
- err = -EINVAL;
- goto exit;
- }
- xfer = xfer_funcs[type];
- if (xfer == NULL) {
- err = -EINVAL;
- goto exit;
- }
- } else
- xfer = NULL;
-
- err = loop_init_xfer(lo, xfer, info);
- if (err)
- goto exit;
-
- if (lo->lo_offset != info->lo_offset ||
- lo->lo_sizelimit != info->lo_sizelimit)
- if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
- err = -EFBIG;
- goto exit;
- }
+ /* Mask out flags that can't be set using LOOP_SET_STATUS. */
+ lo->lo_flags &= LOOP_SET_STATUS_SETTABLE_FLAGS;
+ /* For those flags, use the previous values instead */
+ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS;
+ /* For flags that can't be cleared, use previous values too */
+ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
+ if (size_changed) {
+ loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+ lo->lo_backing_file);
+ loop_set_size(lo, new_size);
+ }
loop_config_discard(lo);
- memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
- memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
- lo->lo_file_name[LO_NAME_SIZE-1] = 0;
- lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
-
- if (!xfer)
- xfer = &none_funcs;
- lo->transfer = xfer->transfer;
- lo->ioctl = xfer->ioctl;
-
- if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
- (info->lo_flags & LO_FLAGS_AUTOCLEAR))
- lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
-
- lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
- lo->lo_init[0] = info->lo_init[0];
- lo->lo_init[1] = info->lo_init[1];
- if (info->lo_encrypt_key_size) {
- memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
- info->lo_encrypt_key_size);
- lo->lo_key_owner = uid;
- }
-
/* update dio if lo_offset or transfer is changed */
__loop_update_dio(lo, lo->use_dio);
exit:
blk_mq_unfreeze_queue(lo->lo_queue);
- if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
- !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
- lo->lo_flags |= LO_FLAGS_PARTSCAN;
+ if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
+ !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
loop_reread_partitions(lo, lo->lo_device);
}
@@ -1324,10 +1399,15 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
{
+ loff_t size;
+
if (unlikely(lo->lo_state != Lo_bound))
return -ENXIO;
- return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
+ size = get_loop_size(lo, lo->lo_backing_file);
+ loop_set_size(lo, size);
+
+ return 0;
}
static int loop_set_dio(struct loop_device *lo, unsigned long arg)
@@ -1344,17 +1424,74 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
return error;
}
+static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
+{
+ int err = 0;
+
+ if (lo->lo_state != Lo_bound)
+ return -ENXIO;
+
+ err = loop_validate_block_size(arg);
+ if (err)
+ return err;
+
+ if (lo->lo_queue->limits.logical_block_size == arg)
+ return 0;
+
+ sync_blockdev(lo->lo_device);
+ kill_bdev(lo->lo_device);
+
+ blk_mq_freeze_queue(lo->lo_queue);
+
+ /* kill_bdev should have truncated all the pages */
+ if (lo->lo_device->bd_inode->i_mapping->nrpages) {
+ err = -EAGAIN;
+ pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+ __func__, lo->lo_number, lo->lo_file_name,
+ lo->lo_device->bd_inode->i_mapping->nrpages);
+ goto out_unfreeze;
+ }
+
+ blk_queue_logical_block_size(lo->lo_queue, arg);
+ loop_update_dio(lo);
+out_unfreeze:
+ blk_mq_unfreeze_queue(lo->lo_queue);
+
+ return err;
+}
+
static int lo_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct loop_device *lo = bdev->bd_disk->private_data;
+ void __user *argp = (void __user *) arg;
int err;
mutex_lock_nested(&lo->lo_ctl_mutex, 1);
switch (cmd) {
- case LOOP_SET_FD:
- err = loop_set_fd(lo, mode, bdev, arg);
+ case LOOP_SET_FD: {
+ /*
+ * Legacy case - pass in a zeroed out struct loop_config with
+ * only the file descriptor set , which corresponds with the
+ * default parameters we'd have used otherwise.
+ */
+ struct loop_config config;
+
+ memset(&config, 0, sizeof(config));
+ config.fd = arg;
+
+ err = loop_configure(lo, mode, bdev, &config);
break;
+ }
+ case LOOP_CONFIGURE: {
+ struct loop_config config;
+
+ if (copy_from_user(&config, argp, sizeof(config)))
+ return -EFAULT;
+
+ err = loop_configure(lo, mode, bdev, &config);
+ break;
+ }
case LOOP_CHANGE_FD:
err = loop_change_fd(lo, bdev, arg);
break;
@@ -1367,20 +1504,18 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
case LOOP_SET_STATUS:
err = -EPERM;
if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
- err = loop_set_status_old(lo,
- (struct loop_info __user *)arg);
+ err = loop_set_status_old(lo, argp);
break;
case LOOP_GET_STATUS:
- err = loop_get_status_old(lo, (struct loop_info __user *) arg);
+ err = loop_get_status_old(lo, argp);
break;
case LOOP_SET_STATUS64:
err = -EPERM;
if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
- err = loop_set_status64(lo,
- (struct loop_info64 __user *) arg);
+ err = loop_set_status64(lo, argp);
break;
case LOOP_GET_STATUS64:
- err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
+ err = loop_get_status64(lo, argp);
break;
case LOOP_SET_CAPACITY:
err = -EPERM;
@@ -1392,6 +1527,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
err = loop_set_dio(lo, arg);
break;
+ case LOOP_SET_BLOCK_SIZE:
+ err = -EPERM;
+ if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+ err = loop_set_block_size(lo, arg);
+ break;
default:
err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
}
@@ -1543,10 +1683,12 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
case LOOP_CLR_FD:
case LOOP_GET_STATUS64:
case LOOP_SET_STATUS64:
+ case LOOP_CONFIGURE:
arg = (unsigned long) compat_ptr(arg);
case LOOP_SET_FD:
case LOOP_CHANGE_FD:
case LOOP_SET_DIRECT_IO:
+ case LOOP_SET_BLOCK_SIZE:
err = lo_ioctl(bdev, mode, cmd, arg);
break;
default:
@@ -1782,6 +1924,7 @@ static int loop_add(struct loop_device **l, int i)
}
lo->lo_queue->queuedata = lo;
+ blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS);
/*
* It doesn't make sense to enable merge because the I/O
* submitted to backing file is handled page by page.
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index b8ecba6..e8f2fa2 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -12,4 +12,29 @@
It has several use cases, for example: /tmp storage, use as swap
disks and maybe many more.
- See zram.txt for more information.
+ See Documentation/blockdev/zram.txt for more information.
+
+config ZRAM_WRITEBACK
+ bool "Write back incompressible or idle page to backing device"
+ depends on ZRAM
+ default n
+ help
+ With incompressible page, there is no memory saving to keep it
+ in memory. Instead, write it out to backing device.
+ For this feature, admin should set up backing device via
+ /sys/block/zramX/backing_dev.
+
+ With /sys/block/zramX/{idle,writeback}, application could ask
+ idle page's writeback to the backing device to save in memory.
+
+ See Documentation/blockdev/zram.txt for more information.
+
+config ZRAM_MEMORY_TRACKING
+ bool "Track zRam block status"
+ depends on ZRAM && DEBUG_FS
+ help
+ With this feature, admin can track the state of allocated blocks
+ of zRAM. Admin could see the information via
+ /sys/kernel/debug/zram/zramX/block_state.
+
+ See Documentation/blockdev/zram.txt for more information.
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 4b5cd3a..c084a7f 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -32,6 +32,9 @@ static const char * const backends[] = {
#if IS_ENABLED(CONFIG_CRYPTO_842)
"842",
#endif
+#if IS_ENABLED(CONFIG_CRYPTO_ZSTD)
+ "zstd",
+#endif
NULL
};
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d64a53d..7c23088 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -31,6 +31,7 @@
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/sysfs.h>
+#include <linux/debugfs.h>
#include "zram_drv.h"
@@ -43,27 +44,31 @@ static const char *default_compressor = "lzo";
/* Module params (documentation at end) */
static unsigned int num_devices = 1;
+/*
+ * Pages that compress to sizes equals or greater than this are stored
+ * uncompressed in memory.
+ */
+static size_t huge_class_size;
-static inline void deprecated_attr_warn(const char *name)
+static void zram_free_page(struct zram *zram, size_t index);
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio);
+
+
+static int zram_slot_trylock(struct zram *zram, u32 index)
{
- pr_warn_once("%d (%s) Attribute %s (and others) will be removed. %s\n",
- task_pid_nr(current),
- current->comm,
- name,
- "See zram documentation.");
+ return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags);
}
-#define ZRAM_ATTR_RO(name) \
-static ssize_t name##_show(struct device *d, \
- struct device_attribute *attr, char *b) \
-{ \
- struct zram *zram = dev_to_zram(d); \
- \
- deprecated_attr_warn(__stringify(name)); \
- return scnprintf(b, PAGE_SIZE, "%llu\n", \
- (u64)atomic64_read(&zram->stats.name)); \
-} \
-static DEVICE_ATTR_RO(name);
+static void zram_slot_lock(struct zram *zram, u32 index)
+{
+ bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags);
+}
+
+static void zram_slot_unlock(struct zram *zram, u32 index)
+{
+ bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags);
+}
static inline bool init_done(struct zram *zram)
{
@@ -75,50 +80,77 @@ static inline struct zram *dev_to_zram(struct device *dev)
return (struct zram *)dev_to_disk(dev)->private_data;
}
+static unsigned long zram_get_handle(struct zram *zram, u32 index)
+{
+ return zram->table[index].handle;
+}
+
+static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle)
+{
+ zram->table[index].handle = handle;
+}
+
/* flag operations require table entry bit_spin_lock() being held */
-static int zram_test_flag(struct zram_meta *meta, u32 index,
+static bool zram_test_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
- return meta->table[index].value & BIT(flag);
+ return zram->table[index].flags & BIT(flag);
}
-static void zram_set_flag(struct zram_meta *meta, u32 index,
+static void zram_set_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
- meta->table[index].value |= BIT(flag);
+ zram->table[index].flags |= BIT(flag);
}
-static void zram_clear_flag(struct zram_meta *meta, u32 index,
+static void zram_clear_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
- meta->table[index].value &= ~BIT(flag);
+ zram->table[index].flags &= ~BIT(flag);
}
-static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
+static inline void zram_set_element(struct zram *zram, u32 index,
+ unsigned long element)
{
- return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+ zram->table[index].element = element;
}
-static void zram_set_obj_size(struct zram_meta *meta,
+static unsigned long zram_get_element(struct zram *zram, u32 index)
+{
+ return zram->table[index].element;
+}
+
+static size_t zram_get_obj_size(struct zram *zram, u32 index)
+{
+ return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1);
+}
+
+static void zram_set_obj_size(struct zram *zram,
u32 index, size_t size)
{
- unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;
+ unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT;
- meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
+ zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size;
}
+static inline bool zram_allocated(struct zram *zram, u32 index)
+{
+ return zram_get_obj_size(zram, index) ||
+ zram_test_flag(zram, index, ZRAM_SAME) ||
+ zram_test_flag(zram, index, ZRAM_WB);
+}
+
+#if PAGE_SIZE != 4096
static inline bool is_partial_io(struct bio_vec *bvec)
{
return bvec->bv_len != PAGE_SIZE;
}
-
-static void zram_revalidate_disk(struct zram *zram)
+#else
+static inline bool is_partial_io(struct bio_vec *bvec)
{
- revalidate_disk(zram->disk);
- /* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
- zram->disk->queue->backing_dev_info.capabilities |=
- BDI_CAP_STABLE_WRITES;
+ return false;
}
+#endif
/*
* Check if request is within bounds and aligned on zram logical blocks.
@@ -146,8 +178,7 @@ static inline bool valid_io_request(struct zram *zram,
static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
{
- if (*offset + bvec->bv_len >= PAGE_SIZE)
- (*index)++;
+ *index += (*offset + bvec->bv_len) / PAGE_SIZE;
*offset = (*offset + bvec->bv_len) % PAGE_SIZE;
}
@@ -166,36 +197,41 @@ static inline void update_used_max(struct zram *zram,
} while (old_max != cur_max);
}
-static bool page_zero_filled(void *ptr)
+static inline void zram_fill_page(char *ptr, unsigned long len,
+ unsigned long value)
+{
+ int i;
+ unsigned long *page = (unsigned long *)ptr;
+
+ WARN_ON_ONCE(!IS_ALIGNED(len, sizeof(unsigned long)));
+
+ if (likely(value == 0)) {
+ memset(ptr, 0, len);
+ } else {
+ for (i = 0; i < len / sizeof(*page); i++)
+ page[i] = value;
+ }
+}
+
+static bool page_same_filled(void *ptr, unsigned long *element)
{
unsigned int pos;
unsigned long *page;
+ unsigned long val;
page = (unsigned long *)ptr;
+ val = page[0];
- for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
- if (page[pos])
+ for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
+ if (val != page[pos])
return false;
}
+ *element = val;
+
return true;
}
-static void handle_zero_page(struct bio_vec *bvec)
-{
- struct page *page = bvec->bv_page;
- void *user_mem;
-
- user_mem = kmap_atomic(page);
- if (is_partial_io(bvec))
- memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
- else
- clear_page(user_mem);
- kunmap_atomic(user_mem);
-
- flush_dcache_page(page);
-}
-
static ssize_t initstate_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -217,47 +253,6 @@ static ssize_t disksize_show(struct device *dev,
return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
}
-static ssize_t orig_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- deprecated_attr_warn("orig_data_size");
- return scnprintf(buf, PAGE_SIZE, "%llu\n",
- (u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
-}
-
-static ssize_t mem_used_total_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val = 0;
- struct zram *zram = dev_to_zram(dev);
-
- deprecated_attr_warn("mem_used_total");
- down_read(&zram->init_lock);
- if (init_done(zram)) {
- struct zram_meta *meta = zram->meta;
- val = zs_get_total_pages(meta->mem_pool);
- }
- up_read(&zram->init_lock);
-
- return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
-}
-
-static ssize_t mem_limit_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val;
- struct zram *zram = dev_to_zram(dev);
-
- deprecated_attr_warn("mem_limit");
- down_read(&zram->init_lock);
- val = zram->limit_pages;
- up_read(&zram->init_lock);
-
- return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
-}
-
static ssize_t mem_limit_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
@@ -276,21 +271,6 @@ static ssize_t mem_limit_store(struct device *dev,
return len;
}
-static ssize_t mem_used_max_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val = 0;
- struct zram *zram = dev_to_zram(dev);
-
- deprecated_attr_warn("mem_used_max");
- down_read(&zram->init_lock);
- if (init_done(zram))
- val = atomic_long_read(&zram->stats.max_used_pages);
- up_read(&zram->init_lock);
-
- return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
-}
-
static ssize_t mem_used_max_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
@@ -304,15 +284,700 @@ static ssize_t mem_used_max_store(struct device *dev,
down_read(&zram->init_lock);
if (init_done(zram)) {
- struct zram_meta *meta = zram->meta;
atomic_long_set(&zram->stats.max_used_pages,
- zs_get_total_pages(meta->mem_pool));
+ zs_get_total_pages(zram->mem_pool));
}
up_read(&zram->init_lock);
return len;
}
+static ssize_t idle_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ int index;
+ char mode_buf[8];
+ ssize_t sz;
+
+ sz = strscpy(mode_buf, buf, sizeof(mode_buf));
+ if (sz <= 0)
+ return -EINVAL;
+
+ /* ignore trailing new line */
+ if (mode_buf[sz - 1] == '\n')
+ mode_buf[sz - 1] = 0x00;
+
+ if (strcmp(mode_buf, "all"))
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ return -EINVAL;
+ }
+
+ for (index = 0; index < nr_pages; index++) {
+ /*
+ * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
+ * See the comment in writeback_store.
+ */
+ zram_slot_lock(zram, index);
+ if (zram_allocated(zram, index) &&
+ !zram_test_flag(zram, index, ZRAM_UNDER_WB))
+ zram_set_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ }
+
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
+#ifdef CONFIG_ZRAM_WRITEBACK
+static ssize_t writeback_limit_enable_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ u64 val;
+ ssize_t ret = -EINVAL;
+
+ if (kstrtoull(buf, 10, &val))
+ return ret;
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ zram->wb_limit_enable = val;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+ ret = len;
+
+ return ret;
+}
+
+static ssize_t writeback_limit_enable_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ bool val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ val = zram->wb_limit_enable;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t writeback_limit_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ u64 val;
+ ssize_t ret = -EINVAL;
+
+ if (kstrtoull(buf, 10, &val))
+ return ret;
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ zram->bd_wb_limit = val;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+ ret = len;
+
+ return ret;
+}
+
+static ssize_t writeback_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ val = zram->bd_wb_limit;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
+static void reset_bdev(struct zram *zram)
+{
+ struct block_device *bdev;
+
+ if (!zram->backing_dev)
+ return;
+
+ bdev = zram->bdev;
+ if (zram->old_block_size)
+ set_blocksize(bdev, zram->old_block_size);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ /* hope filp_close flush all of IO */
+ filp_close(zram->backing_dev, NULL);
+ zram->backing_dev = NULL;
+ zram->old_block_size = 0;
+ zram->bdev = NULL;
+
+ kvfree(zram->bitmap);
+ zram->bitmap = NULL;
+}
+
+static ssize_t backing_dev_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+ struct file *file = zram->backing_dev;
+ char *p;
+ ssize_t ret;
+
+ down_read(&zram->init_lock);
+ if (!zram->backing_dev) {
+ memcpy(buf, "none\n", 5);
+ up_read(&zram->init_lock);
+ return 5;
+ }
+
+ p = file_path(file, buf, PAGE_SIZE - 1);
+ if (IS_ERR(p)) {
+ ret = PTR_ERR(p);
+ goto out;
+ }
+
+ ret = strlen(p);
+ memmove(buf, p, ret);
+ buf[ret++] = '\n';
+out:
+ up_read(&zram->init_lock);
+ return ret;
+}
+
+static ssize_t backing_dev_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ char *file_name;
+ size_t sz;
+ struct file *backing_dev = NULL;
+ struct inode *inode;
+ struct address_space *mapping;
+ unsigned int bitmap_sz, old_block_size = 0;
+ unsigned long nr_pages, *bitmap = NULL;
+ struct block_device *bdev = NULL;
+ int err;
+ struct zram *zram = dev_to_zram(dev);
+ gfp_t kmalloc_flags;
+
+ file_name = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!file_name)
+ return -ENOMEM;
+
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ pr_info("Can't setup backing device for initialized device\n");
+ err = -EBUSY;
+ goto out;
+ }
+
+ strlcpy(file_name, buf, PATH_MAX);
+ /* ignore trailing newline */
+ sz = strlen(file_name);
+ if (sz > 0 && file_name[sz - 1] == '\n')
+ file_name[sz - 1] = 0x00;
+
+ backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0);
+ if (IS_ERR(backing_dev)) {
+ err = PTR_ERR(backing_dev);
+ backing_dev = NULL;
+ goto out;
+ }
+
+ mapping = backing_dev->f_mapping;
+ inode = mapping->host;
+
+ /* Support only block device in this moment */
+ if (!S_ISBLK(inode->i_mode)) {
+ err = -ENOTBLK;
+ goto out;
+ }
+
+ bdev = bdgrab(I_BDEV(inode));
+ err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
+ if (err < 0) {
+ bdev = NULL;
+ goto out;
+ }
+
+ nr_pages = i_size_read(inode) >> PAGE_SHIFT;
+ bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
+ kmalloc_flags = GFP_KERNEL | __GFP_ZERO;
+ if (bitmap_sz > PAGE_SIZE)
+ kmalloc_flags |= __GFP_NOWARN | __GFP_NORETRY;
+
+ bitmap = kmalloc_node(bitmap_sz, kmalloc_flags, NUMA_NO_NODE);
+ if (!bitmap && bitmap_sz > PAGE_SIZE)
+ bitmap = vzalloc(bitmap_sz);
+
+ if (!bitmap) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ old_block_size = block_size(bdev);
+ err = set_blocksize(bdev, PAGE_SIZE);
+ if (err)
+ goto out;
+
+ reset_bdev(zram);
+
+ zram->old_block_size = old_block_size;
+ zram->bdev = bdev;
+ zram->backing_dev = backing_dev;
+ zram->bitmap = bitmap;
+ zram->nr_pages = nr_pages;
+ up_write(&zram->init_lock);
+
+ pr_info("setup backing device %s\n", file_name);
+ kfree(file_name);
+
+ return len;
+out:
+ if (bitmap)
+ kvfree(bitmap);
+
+ if (bdev)
+ blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+
+ if (backing_dev)
+ filp_close(backing_dev, NULL);
+
+ up_write(&zram->init_lock);
+
+ kfree(file_name);
+
+ return err;
+}
+
+static unsigned long alloc_block_bdev(struct zram *zram)
+{
+ unsigned long blk_idx = 1;
+retry:
+ /* skip 0 bit to confuse zram.handle = 0 */
+ blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx);
+ if (blk_idx == zram->nr_pages)
+ return 0;
+
+ if (test_and_set_bit(blk_idx, zram->bitmap))
+ goto retry;
+
+ atomic64_inc(&zram->stats.bd_count);
+ return blk_idx;
+}
+
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
+{
+ int was_set;
+
+ was_set = test_and_clear_bit(blk_idx, zram->bitmap);
+ WARN_ON_ONCE(!was_set);
+ atomic64_dec(&zram->stats.bd_count);
+}
+
+static void zram_page_end_io(struct bio *bio)
+{
+ struct page *page = bio->bi_io_vec[0].bv_page;
+
+ page_endio(page, op_is_write(bio_op(bio)), bio->bi_error);
+ bio_put(bio);
+}
+
+/*
+ * Returns 1 if the submission is successful.
+ */
+static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *parent)
+{
+ struct bio *bio;
+
+ bio = bio_alloc(GFP_ATOMIC, 1);
+ if (!bio)
+ return -ENOMEM;
+
+ bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
+ bio->bi_bdev = zram->bdev;
+ if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
+ bio_put(bio);
+ return -EIO;
+ }
+
+ if (!parent) {
+ bio->bi_opf = REQ_OP_READ;
+ bio->bi_end_io = zram_page_end_io;
+ } else {
+ bio->bi_opf = parent->bi_opf;
+ bio_chain(bio, parent);
+ }
+
+ submit_bio(bio);
+ return 1;
+}
+
+#define HUGE_WRITEBACK 1
+#define IDLE_WRITEBACK 2
+
+static ssize_t writeback_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ unsigned long index;
+ struct bio bio;
+ struct page *page;
+ ssize_t ret, sz;
+ char mode_buf[8];
+ int mode = -1;
+ unsigned long blk_idx = 0;
+
+ sz = strscpy(mode_buf, buf, sizeof(mode_buf));
+ if (sz <= 0)
+ return -EINVAL;
+
+ /* ignore trailing newline */
+ if (mode_buf[sz - 1] == '\n')
+ mode_buf[sz - 1] = 0x00;
+
+ if (!strcmp(mode_buf, "idle"))
+ mode = IDLE_WRITEBACK;
+ else if (!strcmp(mode_buf, "huge"))
+ mode = HUGE_WRITEBACK;
+
+ if (mode == -1)
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ ret = -EINVAL;
+ goto release_init_lock;
+ }
+
+ if (!zram->backing_dev) {
+ ret = -ENODEV;
+ goto release_init_lock;
+ }
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ ret = -ENOMEM;
+ goto release_init_lock;
+ }
+
+ for (index = 0; index < nr_pages; index++) {
+ struct bio_vec bvec;
+
+ bvec.bv_page = page;
+ bvec.bv_len = PAGE_SIZE;
+ bvec.bv_offset = 0;
+
+ spin_lock(&zram->wb_limit_lock);
+ if (zram->wb_limit_enable && !zram->bd_wb_limit) {
+ spin_unlock(&zram->wb_limit_lock);
+ ret = -EIO;
+ break;
+ }
+ spin_unlock(&zram->wb_limit_lock);
+
+ if (!blk_idx) {
+ blk_idx = alloc_block_bdev(zram);
+ if (!blk_idx) {
+ ret = -ENOSPC;
+ break;
+ }
+ }
+
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index))
+ goto next;
+
+ if (zram_test_flag(zram, index, ZRAM_WB) ||
+ zram_test_flag(zram, index, ZRAM_SAME) ||
+ zram_test_flag(zram, index, ZRAM_UNDER_WB))
+ goto next;
+
+ if (mode == IDLE_WRITEBACK &&
+ !zram_test_flag(zram, index, ZRAM_IDLE))
+ goto next;
+ if (mode == HUGE_WRITEBACK &&
+ !zram_test_flag(zram, index, ZRAM_HUGE))
+ goto next;
+ /*
+ * Clearing ZRAM_UNDER_WB is duty of caller.
+ * IOW, zram_free_page never clear it.
+ */
+ zram_set_flag(zram, index, ZRAM_UNDER_WB);
+ /* Need for hugepage writeback racing */
+ zram_set_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ if (zram_bvec_read(zram, &bvec, index, 0, NULL)) {
+ zram_slot_lock(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ continue;
+ }
+
+ bio_init(&bio);
+
+ bio.bi_max_vecs = 1;
+ bio.bi_io_vec = &bvec;
+ bio.bi_bdev = zram->bdev;
+
+ bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
+ bio_set_op_attrs(&bio, REQ_OP_WRITE, REQ_SYNC);
+ bio_add_page(&bio, bvec.bv_page, bvec.bv_len,
+ bvec.bv_offset);
+ /*
+ * XXX: A single page IO would be inefficient for write
+ * but it would be not bad as starter.
+ */
+ ret = submit_bio_wait(&bio);
+ if (ret) {
+ zram_slot_lock(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ continue;
+ }
+
+ atomic64_inc(&zram->stats.bd_writes);
+ /*
+ * We released zram_slot_lock so need to check if the slot was
+ * changed. If there is freeing for the slot, we can catch it
+ * easily by zram_allocated.
+ * A subtle case is the slot is freed/reallocated/marked as
+ * ZRAM_IDLE again. To close the race, idle_store doesn't
+ * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB.
+ * Thus, we could close the race by checking ZRAM_IDLE bit.
+ */
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index) ||
+ !zram_test_flag(zram, index, ZRAM_IDLE)) {
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ goto next;
+ }
+
+ zram_free_page(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_set_flag(zram, index, ZRAM_WB);
+ zram_set_element(zram, index, blk_idx);
+ blk_idx = 0;
+ atomic64_inc(&zram->stats.pages_stored);
+ spin_lock(&zram->wb_limit_lock);
+ if (zram->wb_limit_enable && zram->bd_wb_limit > 0)
+ zram->bd_wb_limit -= 1UL << (PAGE_SHIFT - 12);
+ spin_unlock(&zram->wb_limit_lock);
+next:
+ zram_slot_unlock(zram, index);
+ }
+
+ if (blk_idx)
+ free_block_bdev(zram, blk_idx);
+ ret = len;
+ __free_page(page);
+release_init_lock:
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+
+struct zram_work {
+ struct work_struct work;
+ struct zram *zram;
+ unsigned long entry;
+ struct bio *bio;
+};
+
+#if PAGE_SIZE != 4096
+static void zram_sync_read(struct work_struct *work)
+{
+ struct bio_vec bvec;
+ struct zram_work *zw = container_of(work, struct zram_work, work);
+ struct zram *zram = zw->zram;
+ unsigned long entry = zw->entry;
+ struct bio *bio = zw->bio;
+
+ read_from_bdev_async(zram, &bvec, entry, bio);
+}
+
+/*
+ * Block layer want one ->make_request_fn to be active at a time
+ * so if we use chained IO with parent IO in same context,
+ * it's a deadlock. To avoid, it, it uses worker thread context.
+ */
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *bio)
+{
+ struct zram_work work;
+
+ work.zram = zram;
+ work.entry = entry;
+ work.bio = bio;
+
+ INIT_WORK_ONSTACK(&work.work, zram_sync_read);
+ queue_work(system_unbound_wq, &work.work);
+ flush_work(&work.work);
+ destroy_work_on_stack(&work.work);
+
+ return 1;
+}
+#else
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *bio)
+{
+ WARN_ON(1);
+ return -EIO;
+}
+#endif
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *parent, bool sync)
+{
+ atomic64_inc(&zram->stats.bd_reads);
+ if (sync)
+ return read_from_bdev_sync(zram, bvec, entry, parent);
+ else
+ return read_from_bdev_async(zram, bvec, entry, parent);
+}
+#else
+static inline void reset_bdev(struct zram *zram) {};
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *parent, bool sync)
+{
+ return -EIO;
+}
+
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {};
+#endif
+
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+
+static struct dentry *zram_debugfs_root;
+
+static void zram_debugfs_create(void)
+{
+ zram_debugfs_root = debugfs_create_dir("zram", NULL);
+}
+
+static void zram_debugfs_destroy(void)
+{
+ debugfs_remove_recursive(zram_debugfs_root);
+}
+
+static void zram_accessed(struct zram *zram, u32 index)
+{
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram->table[index].ac_time = ktime_get_boottime();
+}
+
+static ssize_t read_block_state(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ char *kbuf;
+ ssize_t index, written = 0;
+ struct zram *zram = file->private_data;
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ struct timespec64 ts;
+
+ gfp_t kmalloc_flags;
+
+ kmalloc_flags = GFP_KERNEL;
+ if (count > PAGE_SIZE)
+ kmalloc_flags |= __GFP_NOWARN | __GFP_NORETRY;
+
+ kbuf = kmalloc_node(count, kmalloc_flags, NUMA_NO_NODE);
+ if (!kbuf && count > PAGE_SIZE)
+ kbuf = vmalloc(count);
+ if (!kbuf)
+ return -ENOMEM;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ kvfree(kbuf);
+ return -EINVAL;
+ }
+
+ for (index = *ppos; index < nr_pages; index++) {
+ int copied;
+
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index))
+ goto next;
+
+ ts = ktime_to_timespec64(zram->table[index].ac_time);
+ copied = snprintf(kbuf + written, count,
+ "%12zd %12lld.%06lu %c%c%c%c\n",
+ index, (s64)ts.tv_sec,
+ ts.tv_nsec / NSEC_PER_USEC,
+ zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.',
+ zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.',
+ zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.',
+ zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.');
+
+ if (count < copied) {
+ zram_slot_unlock(zram, index);
+ break;
+ }
+ written += copied;
+ count -= copied;
+next:
+ zram_slot_unlock(zram, index);
+ *ppos += 1;
+ }
+
+ up_read(&zram->init_lock);
+ if (copy_to_user(buf, kbuf, written))
+ written = -EFAULT;
+ kvfree(kbuf);
+
+ return written;
+}
+
+static const struct file_operations proc_zram_block_state_op = {
+ .open = simple_open,
+ .read = read_block_state,
+ .llseek = default_llseek,
+};
+
+static void zram_debugfs_register(struct zram *zram)
+{
+ if (!zram_debugfs_root)
+ return;
+
+ zram->debugfs_dir = debugfs_create_dir(zram->disk->disk_name,
+ zram_debugfs_root);
+ debugfs_create_file("block_state", 0400, zram->debugfs_dir,
+ zram, &proc_zram_block_state_op);
+}
+
+static void zram_debugfs_unregister(struct zram *zram)
+{
+ debugfs_remove_recursive(zram->debugfs_dir);
+}
+#else
+static void zram_debugfs_create(void) {};
+static void zram_debugfs_destroy(void) {};
+static void zram_accessed(struct zram *zram, u32 index)
+{
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+};
+static void zram_debugfs_register(struct zram *zram) {};
+static void zram_debugfs_unregister(struct zram *zram) {};
+#endif
+
/*
* We switched to per-cpu streams and this attr is not needed anymore.
* However, we will keep it around for some time, because:
@@ -351,7 +1016,7 @@ static ssize_t comp_algorithm_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
- char compressor[CRYPTO_MAX_ALG_NAME];
+ char compressor[ARRAY_SIZE(zram->compressor)];
size_t sz;
strlcpy(compressor, buf, sizeof(compressor));
@@ -370,7 +1035,7 @@ static ssize_t comp_algorithm_store(struct device *dev,
return -EBUSY;
}
- strlcpy(zram->compressor, compressor, sizeof(compressor));
+ strcpy(zram->compressor, compressor);
up_write(&zram->init_lock);
return len;
}
@@ -379,7 +1044,6 @@ static ssize_t compact_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct zram *zram = dev_to_zram(dev);
- struct zram_meta *meta;
down_read(&zram->init_lock);
if (!init_done(zram)) {
@@ -387,8 +1051,7 @@ static ssize_t compact_store(struct device *dev,
return -EINVAL;
}
- meta = zram->meta;
- zs_compact(meta->mem_pool);
+ zs_compact(zram->mem_pool);
up_read(&zram->init_lock);
return len;
@@ -425,27 +1088,48 @@ static ssize_t mm_stat_show(struct device *dev,
down_read(&zram->init_lock);
if (init_done(zram)) {
- mem_used = zs_get_total_pages(zram->meta->mem_pool);
- zs_pool_stats(zram->meta->mem_pool, &pool_stats);
+ mem_used = zs_get_total_pages(zram->mem_pool);
+ zs_pool_stats(zram->mem_pool, &pool_stats);
}
orig_size = atomic64_read(&zram->stats.pages_stored);
max_used = atomic_long_read(&zram->stats.max_used_pages);
ret = scnprintf(buf, PAGE_SIZE,
- "%8llu %8llu %8llu %8lu %8ld %8llu %8lu\n",
+ "%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n",
orig_size << PAGE_SHIFT,
(u64)atomic64_read(&zram->stats.compr_data_size),
mem_used << PAGE_SHIFT,
zram->limit_pages << PAGE_SHIFT,
max_used << PAGE_SHIFT,
- (u64)atomic64_read(&zram->stats.zero_pages),
- pool_stats.pages_compacted);
+ (u64)atomic64_read(&zram->stats.same_pages),
+ pool_stats.pages_compacted,
+ (u64)atomic64_read(&zram->stats.huge_pages));
up_read(&zram->init_lock);
return ret;
}
+#ifdef CONFIG_ZRAM_WRITEBACK
+#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12)))
+static ssize_t bd_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+ ssize_t ret;
+
+ down_read(&zram->init_lock);
+ ret = scnprintf(buf, PAGE_SIZE,
+ "%8llu %8llu %8llu\n",
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_count)),
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)),
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_writes)));
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+#endif
+
static ssize_t debug_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -455,9 +1139,10 @@ static ssize_t debug_stat_show(struct device *dev,
down_read(&zram->init_lock);
ret = scnprintf(buf, PAGE_SIZE,
- "version: %d\n%8llu\n",
+ "version: %d\n%8llu %8llu\n",
version,
- (u64)atomic64_read(&zram->stats.writestall));
+ (u64)atomic64_read(&zram->stats.writestall),
+ (u64)atomic64_read(&zram->stats.miss_free));
up_read(&zram->init_lock);
return ret;
@@ -465,75 +1150,42 @@ static ssize_t debug_stat_show(struct device *dev,
static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
+#ifdef CONFIG_ZRAM_WRITEBACK
+static DEVICE_ATTR_RO(bd_stat);
+#endif
static DEVICE_ATTR_RO(debug_stat);
-ZRAM_ATTR_RO(num_reads);
-ZRAM_ATTR_RO(num_writes);
-ZRAM_ATTR_RO(failed_reads);
-ZRAM_ATTR_RO(failed_writes);
-ZRAM_ATTR_RO(invalid_io);
-ZRAM_ATTR_RO(notify_free);
-ZRAM_ATTR_RO(zero_pages);
-ZRAM_ATTR_RO(compr_data_size);
-static inline bool zram_meta_get(struct zram *zram)
-{
- if (atomic_inc_not_zero(&zram->refcount))
- return true;
- return false;
-}
-
-static inline void zram_meta_put(struct zram *zram)
-{
- atomic_dec(&zram->refcount);
-}
-
-static void zram_meta_free(struct zram_meta *meta, u64 disksize)
+static void zram_meta_free(struct zram *zram, u64 disksize)
{
size_t num_pages = disksize >> PAGE_SHIFT;
size_t index;
/* Free all pages that are still in this zram device */
- for (index = 0; index < num_pages; index++) {
- unsigned long handle = meta->table[index].handle;
+ for (index = 0; index < num_pages; index++)
+ zram_free_page(zram, index);
- if (!handle)
- continue;
-
- zs_free(meta->mem_pool, handle);
- }
-
- zs_destroy_pool(meta->mem_pool);
- vfree(meta->table);
- kfree(meta);
+ zs_destroy_pool(zram->mem_pool);
+ vfree(zram->table);
}
-static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
+static bool zram_meta_alloc(struct zram *zram, u64 disksize)
{
size_t num_pages;
- struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
-
- if (!meta)
- return NULL;
num_pages = disksize >> PAGE_SHIFT;
- meta->table = vzalloc(num_pages * sizeof(*meta->table));
- if (!meta->table) {
- pr_err("Error allocating zram address table\n");
- goto out_error;
+ zram->table = vzalloc(num_pages * sizeof(*zram->table));
+ if (!zram->table)
+ return false;
+
+ zram->mem_pool = zs_create_pool(zram->disk->disk_name);
+ if (!zram->mem_pool) {
+ vfree(zram->table);
+ return false;
}
- meta->mem_pool = zs_create_pool(pool_name);
- if (!meta->mem_pool) {
- pr_err("Error creating memory pool\n");
- goto out_error;
- }
-
- return meta;
-
-out_error:
- vfree(meta->table);
- kfree(meta);
- return NULL;
+ if (!huge_class_size)
+ huge_class_size = zs_huge_class_size(zram->mem_pool);
+ return true;
}
/*
@@ -543,193 +1195,183 @@ static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
*/
static void zram_free_page(struct zram *zram, size_t index)
{
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
+ unsigned long handle;
- if (unlikely(!handle)) {
- /*
- * No memory is allocated for zero filled pages.
- * Simply clear zero page flag.
- */
- if (zram_test_flag(meta, index, ZRAM_ZERO)) {
- zram_clear_flag(meta, index, ZRAM_ZERO);
- atomic64_dec(&zram->stats.zero_pages);
- }
- return;
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ zram->table[index].ac_time.tv64 = 0;
+#endif
+ if (zram_test_flag(zram, index, ZRAM_IDLE))
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+
+ if (zram_test_flag(zram, index, ZRAM_HUGE)) {
+ zram_clear_flag(zram, index, ZRAM_HUGE);
+ atomic64_dec(&zram->stats.huge_pages);
}
- zs_free(meta->mem_pool, handle);
+ if (zram_test_flag(zram, index, ZRAM_WB)) {
+ zram_clear_flag(zram, index, ZRAM_WB);
+ free_block_bdev(zram, zram_get_element(zram, index));
+ goto out;
+ }
- atomic64_sub(zram_get_obj_size(meta, index),
+ /*
+ * No memory is allocated for same element filled pages.
+ * Simply clear same page flag.
+ */
+ if (zram_test_flag(zram, index, ZRAM_SAME)) {
+ zram_clear_flag(zram, index, ZRAM_SAME);
+ atomic64_dec(&zram->stats.same_pages);
+ goto out;
+ }
+
+ handle = zram_get_handle(zram, index);
+ if (!handle)
+ return;
+
+ zs_free(zram->mem_pool, handle);
+
+ atomic64_sub(zram_get_obj_size(zram, index),
&zram->stats.compr_data_size);
+out:
atomic64_dec(&zram->stats.pages_stored);
-
- meta->table[index].handle = 0;
- zram_set_obj_size(meta, index, 0);
+ zram_set_handle(zram, index, 0);
+ zram_set_obj_size(zram, index, 0);
+ WARN_ON_ONCE(zram->table[index].flags &
+ ~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB));
}
-static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
+static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
+ struct bio *bio, bool partial_io)
{
- int ret = 0;
- unsigned char *cmem;
- struct zram_meta *meta = zram->meta;
+ int ret;
unsigned long handle;
unsigned int size;
+ void *src, *dst;
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- handle = meta->table[index].handle;
- size = zram_get_obj_size(meta, index);
+ zram_slot_lock(zram, index);
+ if (zram_test_flag(zram, index, ZRAM_WB)) {
+ struct bio_vec bvec;
- if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- memset(mem, 0, PAGE_SIZE);
+ zram_slot_unlock(zram, index);
+
+ bvec.bv_page = page;
+ bvec.bv_len = PAGE_SIZE;
+ bvec.bv_offset = 0;
+ return read_from_bdev(zram, &bvec,
+ zram_get_element(zram, index),
+ bio, partial_io);
+ }
+
+ handle = zram_get_handle(zram, index);
+ if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
+ unsigned long value;
+ void *mem;
+
+ value = handle ? zram_get_element(zram, index) : 0;
+ mem = kmap_atomic(page);
+ zram_fill_page(mem, PAGE_SIZE, value);
+ kunmap_atomic(mem);
+ zram_slot_unlock(zram, index);
return 0;
}
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
+ size = zram_get_obj_size(zram, index);
+
+ src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE) {
- memcpy(mem, cmem, PAGE_SIZE);
+ dst = kmap_atomic(page);
+ memcpy(dst, src, PAGE_SIZE);
+ kunmap_atomic(dst);
+ ret = 0;
} else {
struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
- ret = zcomp_decompress(zstrm, cmem, size, mem);
+ dst = kmap_atomic(page);
+ ret = zcomp_decompress(zstrm, src, size, dst);
+ kunmap_atomic(dst);
zcomp_stream_put(zram->comp);
}
- zs_unmap_object(meta->mem_pool, handle);
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ zs_unmap_object(zram->mem_pool, handle);
+ zram_slot_unlock(zram, index);
/* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret)) {
- pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
- return ret;
- }
-
- return 0;
-}
-
-static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset)
-{
- int ret;
- struct page *page;
- unsigned char *user_mem, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
- page = bvec->bv_page;
-
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- if (unlikely(!meta->table[index].handle) ||
- zram_test_flag(meta, index, ZRAM_ZERO)) {
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- handle_zero_page(bvec);
- return 0;
- }
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
-
- if (is_partial_io(bvec))
- /* Use a temporary buffer to decompress the page */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
-
- user_mem = kmap_atomic(page);
- if (!is_partial_io(bvec))
- uncmem = user_mem;
-
- if (!uncmem) {
- pr_err("Unable to allocate temp memory\n");
- ret = -ENOMEM;
- goto out_cleanup;
- }
-
- ret = zram_decompress_page(zram, uncmem, index);
- /* Should NEVER happen. Return bio error if it does. */
if (unlikely(ret))
- goto out_cleanup;
+ pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
- if (is_partial_io(bvec))
- memcpy(user_mem + bvec->bv_offset, uncmem + offset,
- bvec->bv_len);
-
- flush_dcache_page(page);
- ret = 0;
-out_cleanup:
- kunmap_atomic(user_mem);
- if (is_partial_io(bvec))
- kfree(uncmem);
return ret;
}
-static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset)
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio)
{
- int ret = 0;
- unsigned int clen;
- unsigned long handle = 0;
+ int ret;
struct page *page;
- unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
- struct zcomp_strm *zstrm = NULL;
- unsigned long alloced_pages;
page = bvec->bv_page;
if (is_partial_io(bvec)) {
- /*
- * This is a partial IO. We need to read the full page
- * before to write the changes.
- */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
- if (!uncmem) {
- ret = -ENOMEM;
- goto out;
- }
- ret = zram_decompress_page(zram, uncmem, index);
- if (ret)
- goto out;
+ /* Use a temporary buffer to decompress the page */
+ page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
+ if (!page)
+ return -ENOMEM;
}
+ ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
+ if (unlikely(ret))
+ goto out;
+
+ if (is_partial_io(bvec)) {
+ void *dst = kmap_atomic(bvec->bv_page);
+ void *src = kmap_atomic(page);
+
+ memcpy(dst + bvec->bv_offset, src + offset, bvec->bv_len);
+ kunmap_atomic(src);
+ kunmap_atomic(dst);
+ }
+out:
+ if (is_partial_io(bvec))
+ __free_page(page);
+
+ return ret;
+}
+
+static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
+ u32 index, struct bio *bio)
+{
+ int ret = 0;
+ unsigned long alloced_pages;
+ unsigned long handle = 0;
+ unsigned int comp_len = 0;
+ void *src, *dst, *mem;
+ struct zcomp_strm *zstrm;
+ struct page *page = bvec->bv_page;
+ unsigned long element = 0;
+ enum zram_pageflags flags = 0;
+
+ mem = kmap_atomic(page);
+ if (page_same_filled(mem, &element)) {
+ kunmap_atomic(mem);
+ /* Free memory associated with this sector now. */
+ flags = ZRAM_SAME;
+ atomic64_inc(&zram->stats.same_pages);
+ goto out;
+ }
+ kunmap_atomic(mem);
+
compress_again:
- user_mem = kmap_atomic(page);
- if (is_partial_io(bvec)) {
- memcpy(uncmem + offset, user_mem + bvec->bv_offset,
- bvec->bv_len);
- kunmap_atomic(user_mem);
- user_mem = NULL;
- } else {
- uncmem = user_mem;
- }
-
- if (page_zero_filled(uncmem)) {
- if (user_mem)
- kunmap_atomic(user_mem);
- /* Free memory associated with this sector now. */
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- zram_free_page(zram, index);
- zram_set_flag(meta, index, ZRAM_ZERO);
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
-
- atomic64_inc(&zram->stats.zero_pages);
- ret = 0;
- goto out;
- }
-
zstrm = zcomp_stream_get(zram->comp);
- ret = zcomp_compress(zstrm, uncmem, &clen);
- if (!is_partial_io(bvec)) {
- kunmap_atomic(user_mem);
- user_mem = NULL;
- uncmem = NULL;
- }
+ src = kmap_atomic(page);
+ ret = zcomp_compress(zstrm, src, &comp_len);
+ kunmap_atomic(src);
if (unlikely(ret)) {
+ zcomp_stream_put(zram->comp);
pr_err("Compression failed! err=%d\n", ret);
- goto out;
+ zs_free(zram->mem_pool, handle);
+ return ret;
}
- src = zstrm->buffer;
- if (unlikely(clen > max_zpage_size)) {
- clen = PAGE_SIZE;
- if (is_partial_io(bvec))
- src = uncmem;
- }
-
+ if (comp_len >= huge_class_size)
+ comp_len = PAGE_SIZE;
/*
* handle allocation has 2 paths:
* a) fast path is executed with preemption disabled (for
@@ -744,71 +1386,108 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
* from the slow path and handle has already been allocated.
*/
if (!handle)
- handle = zs_malloc(meta->mem_pool, clen,
+ handle = zs_malloc(zram->mem_pool, comp_len,
__GFP_KSWAPD_RECLAIM |
__GFP_NOWARN |
__GFP_HIGHMEM |
__GFP_MOVABLE);
if (!handle) {
zcomp_stream_put(zram->comp);
- zstrm = NULL;
-
atomic64_inc(&zram->stats.writestall);
-
- handle = zs_malloc(meta->mem_pool, clen,
+ handle = zs_malloc(zram->mem_pool, comp_len,
GFP_NOIO | __GFP_HIGHMEM |
__GFP_MOVABLE);
if (handle)
goto compress_again;
-
- pr_err("Error allocating memory for compressed page: %u, size=%u\n",
- index, clen);
- ret = -ENOMEM;
- goto out;
+ return -ENOMEM;
}
- alloced_pages = zs_get_total_pages(meta->mem_pool);
+ alloced_pages = zs_get_total_pages(zram->mem_pool);
update_used_max(zram, alloced_pages);
if (zram->limit_pages && alloced_pages > zram->limit_pages) {
- zs_free(meta->mem_pool, handle);
- ret = -ENOMEM;
- goto out;
+ zcomp_stream_put(zram->comp);
+ zs_free(zram->mem_pool, handle);
+ return -ENOMEM;
}
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
+ dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
+ src = zstrm->buffer;
+ if (comp_len == PAGE_SIZE)
src = kmap_atomic(page);
- memcpy(cmem, src, PAGE_SIZE);
+ memcpy(dst, src, comp_len);
+ if (comp_len == PAGE_SIZE)
kunmap_atomic(src);
- } else {
- memcpy(cmem, src, clen);
- }
zcomp_stream_put(zram->comp);
- zstrm = NULL;
- zs_unmap_object(meta->mem_pool, handle);
-
+ zs_unmap_object(zram->mem_pool, handle);
+ atomic64_add(comp_len, &zram->stats.compr_data_size);
+out:
/*
* Free memory associated with this sector
* before overwriting unused sectors.
*/
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_slot_lock(zram, index);
zram_free_page(zram, index);
- meta->table[index].handle = handle;
- zram_set_obj_size(meta, index, clen);
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ if (comp_len == PAGE_SIZE) {
+ zram_set_flag(zram, index, ZRAM_HUGE);
+ atomic64_inc(&zram->stats.huge_pages);
+ }
+
+ if (flags) {
+ zram_set_flag(zram, index, flags);
+ zram_set_element(zram, index, element);
+ } else {
+ zram_set_handle(zram, index, handle);
+ zram_set_obj_size(zram, index, comp_len);
+ }
+ zram_slot_unlock(zram, index);
/* Update stats */
- atomic64_add(clen, &zram->stats.compr_data_size);
atomic64_inc(&zram->stats.pages_stored);
+ return ret;
+}
+
+static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio)
+{
+ int ret;
+ struct page *page = NULL;
+ void *src;
+ struct bio_vec vec;
+
+ vec = *bvec;
+ if (is_partial_io(bvec)) {
+ void *dst;
+ /*
+ * This is a partial IO. We need to read the full page
+ * before to write the changes.
+ */
+ page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
+ if (!page)
+ return -ENOMEM;
+
+ ret = __zram_bvec_read(zram, page, index, bio, true);
+ if (ret)
+ goto out;
+
+ src = kmap_atomic(bvec->bv_page);
+ dst = kmap_atomic(page);
+ memcpy(dst + offset, src + bvec->bv_offset, bvec->bv_len);
+ kunmap_atomic(dst);
+ kunmap_atomic(src);
+
+ vec.bv_page = page;
+ vec.bv_len = PAGE_SIZE;
+ vec.bv_offset = 0;
+ }
+
+ ret = __zram_bvec_write(zram, &vec, index, bio);
out:
- if (zstrm)
- zcomp_stream_put(zram->comp);
if (is_partial_io(bvec))
- kfree(uncmem);
+ __free_page(page);
return ret;
}
@@ -821,7 +1500,6 @@ static void zram_bio_discard(struct zram *zram, u32 index,
int offset, struct bio *bio)
{
size_t n = bio->bi_iter.bi_size;
- struct zram_meta *meta = zram->meta;
/*
* zram manages data in physical block size units. Because logical block
@@ -842,17 +1520,22 @@ static void zram_bio_discard(struct zram *zram, u32 index,
}
while (n >= PAGE_SIZE) {
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_slot_lock(zram, index);
zram_free_page(zram, index);
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_slot_unlock(zram, index);
atomic64_inc(&zram->stats.notify_free);
index++;
n -= PAGE_SIZE;
}
}
+/*
+ * Returns errno if it has some problem. Otherwise return 0 or 1.
+ * Returns 0 if IO request was done synchronously
+ * Returns 1 if IO request was successfully submitted.
+ */
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, bool is_write)
+ int offset, bool is_write, struct bio *bio)
{
unsigned long start_time = jiffies;
int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
@@ -863,15 +1546,20 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
if (!is_write) {
atomic64_inc(&zram->stats.num_reads);
- ret = zram_bvec_read(zram, bvec, index, offset);
+ ret = zram_bvec_read(zram, bvec, index, offset, bio);
+ flush_dcache_page(bvec->bv_page);
} else {
atomic64_inc(&zram->stats.num_writes);
- ret = zram_bvec_write(zram, bvec, index, offset);
+ ret = zram_bvec_write(zram, bvec, index, offset, bio);
}
generic_end_io_acct(rw_acct, &zram->disk->part0, start_time);
- if (unlikely(ret)) {
+ zram_slot_lock(zram, index);
+ zram_accessed(zram, index);
+ zram_slot_unlock(zram, index);
+
+ if (unlikely(ret < 0)) {
if (!is_write)
atomic64_inc(&zram->stats.failed_reads);
else
@@ -899,34 +1587,21 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
}
bio_for_each_segment(bvec, bio, iter) {
- int max_transfer_size = PAGE_SIZE - offset;
+ struct bio_vec bv = bvec;
+ unsigned int unwritten = bvec.bv_len;
- if (bvec.bv_len > max_transfer_size) {
- /*
- * zram_bvec_rw() can only make operation on a single
- * zram page. Split the bio vector.
- */
- struct bio_vec bv;
-
- bv.bv_page = bvec.bv_page;
- bv.bv_len = max_transfer_size;
- bv.bv_offset = bvec.bv_offset;
-
+ do {
+ bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
+ unwritten);
if (zram_bvec_rw(zram, &bv, index, offset,
- op_is_write(bio_op(bio))) < 0)
+ op_is_write(bio_op(bio)), bio) < 0)
goto out;
- bv.bv_len = bvec.bv_len - max_transfer_size;
- bv.bv_offset += max_transfer_size;
- if (zram_bvec_rw(zram, &bv, index + 1, 0,
- op_is_write(bio_op(bio))) < 0)
- goto out;
- } else
- if (zram_bvec_rw(zram, &bvec, index, offset,
- op_is_write(bio_op(bio))) < 0)
- goto out;
+ bv.bv_offset += bv.bv_len;
+ unwritten -= bv.bv_len;
- update_position(&index, &offset, &bvec);
+ update_position(&index, &offset, &bv);
+ } while (unwritten);
}
bio_endio(bio);
@@ -943,22 +1618,15 @@ static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
{
struct zram *zram = queue->queuedata;
- if (unlikely(!zram_meta_get(zram)))
- goto error;
-
- blk_queue_split(queue, &bio, queue->bio_split);
-
if (!valid_io_request(zram, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size)) {
atomic64_inc(&zram->stats.invalid_io);
- goto put_zram;
+ goto error;
}
__zram_make_request(zram, bio);
- zram_meta_put(zram);
return BLK_QC_T_NONE;
-put_zram:
- zram_meta_put(zram);
+
error:
bio_io_error(bio);
return BLK_QC_T_NONE;
@@ -968,45 +1636,43 @@ static void zram_slot_free_notify(struct block_device *bdev,
unsigned long index)
{
struct zram *zram;
- struct zram_meta *meta;
zram = bdev->bd_disk->private_data;
- meta = zram->meta;
- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- zram_free_page(zram, index);
- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
atomic64_inc(&zram->stats.notify_free);
+ if (!zram_slot_trylock(zram, index)) {
+ atomic64_inc(&zram->stats.miss_free);
+ return;
+ }
+
+ zram_free_page(zram, index);
+ zram_slot_unlock(zram, index);
}
static int zram_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, bool is_write)
{
- int offset, err = -EIO;
+ int offset, ret;
u32 index;
struct zram *zram;
struct bio_vec bv;
zram = bdev->bd_disk->private_data;
- if (unlikely(!zram_meta_get(zram)))
- goto out;
if (!valid_io_request(zram, sector, PAGE_SIZE)) {
atomic64_inc(&zram->stats.invalid_io);
- err = -EINVAL;
- goto put_zram;
+ ret = -EINVAL;
+ goto out;
}
index = sector >> SECTORS_PER_PAGE_SHIFT;
- offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+ offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
bv.bv_offset = 0;
- err = zram_bvec_rw(zram, &bv, index, offset, is_write);
-put_zram:
- zram_meta_put(zram);
+ ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
out:
/*
* If I/O fails, just return error(ie, non-zero) without
@@ -1016,14 +1682,24 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
* bio->bi_end_io does things to handle the error
* (e.g., SetPageError, set_page_dirty and extra works).
*/
- if (err == 0)
+ if (unlikely(ret < 0))
+ return ret;
+
+ switch (ret) {
+ case 0:
page_endio(page, is_write, 0);
- return err;
+ break;
+ case 1:
+ ret = 0;
+ break;
+ default:
+ WARN_ON(1);
+ }
+ return ret;
}
static void zram_reset_device(struct zram *zram)
{
- struct zram_meta *meta;
struct zcomp *comp;
u64 disksize;
@@ -1036,23 +1712,8 @@ static void zram_reset_device(struct zram *zram)
return;
}
- meta = zram->meta;
comp = zram->comp;
disksize = zram->disksize;
- /*
- * Refcount will go down to 0 eventually and r/w handler
- * cannot handle further I/O so it will bail out by
- * check zram_meta_get.
- */
- zram_meta_put(zram);
- /*
- * We want to free zram_meta in process context to avoid
- * deadlock between reclaim path and any other locks.
- */
- wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
-
- /* Reset stats */
- memset(&zram->stats, 0, sizeof(zram->stats));
zram->disksize = 0;
set_capacity(zram->disk, 0);
@@ -1060,8 +1721,10 @@ static void zram_reset_device(struct zram *zram)
up_write(&zram->init_lock);
/* I/O operation under all of CPU are done so let's free */
- zram_meta_free(meta, disksize);
+ zram_meta_free(zram, disksize);
+ memset(&zram->stats, 0, sizeof(zram->stats));
zcomp_destroy(comp);
+ reset_bdev(zram);
}
static ssize_t disksize_store(struct device *dev,
@@ -1069,7 +1732,6 @@ static ssize_t disksize_store(struct device *dev,
{
u64 disksize;
struct zcomp *comp;
- struct zram_meta *meta;
struct zram *zram = dev_to_zram(dev);
int err;
@@ -1077,10 +1739,18 @@ static ssize_t disksize_store(struct device *dev,
if (!disksize)
return -EINVAL;
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ pr_info("Cannot change disksize for initialized device\n");
+ err = -EBUSY;
+ goto out_unlock;
+ }
+
disksize = PAGE_ALIGN(disksize);
- meta = zram_meta_alloc(zram->disk->disk_name, disksize);
- if (!meta)
- return -ENOMEM;
+ if (!zram_meta_alloc(zram, disksize)) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
comp = zcomp_create(zram->compressor);
if (IS_ERR(comp)) {
@@ -1090,29 +1760,19 @@ static ssize_t disksize_store(struct device *dev,
goto out_free_meta;
}
- down_write(&zram->init_lock);
- if (init_done(zram)) {
- pr_info("Cannot change disksize for initialized device\n");
- err = -EBUSY;
- goto out_destroy_comp;
- }
-
- init_waitqueue_head(&zram->io_done);
- atomic_set(&zram->refcount, 1);
- zram->meta = meta;
zram->comp = comp;
zram->disksize = disksize;
set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
- zram_revalidate_disk(zram);
+
+ revalidate_disk(zram->disk);
up_write(&zram->init_lock);
return len;
-out_destroy_comp:
- up_write(&zram->init_lock);
- zcomp_destroy(comp);
out_free_meta:
- zram_meta_free(meta, disksize);
+ zram_meta_free(zram, disksize);
+out_unlock:
+ up_write(&zram->init_lock);
return err;
}
@@ -1151,7 +1811,7 @@ static ssize_t reset_store(struct device *dev,
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
- zram_revalidate_disk(zram);
+ revalidate_disk(zram->disk);
bdput(bdev);
mutex_lock(&bdev->bd_mutex);
@@ -1187,39 +1847,44 @@ static DEVICE_ATTR_WO(compact);
static DEVICE_ATTR_RW(disksize);
static DEVICE_ATTR_RO(initstate);
static DEVICE_ATTR_WO(reset);
-static DEVICE_ATTR_RO(orig_data_size);
-static DEVICE_ATTR_RO(mem_used_total);
-static DEVICE_ATTR_RW(mem_limit);
-static DEVICE_ATTR_RW(mem_used_max);
+static DEVICE_ATTR_WO(mem_limit);
+static DEVICE_ATTR_WO(mem_used_max);
+static DEVICE_ATTR_WO(idle);
static DEVICE_ATTR_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);
+#ifdef CONFIG_ZRAM_WRITEBACK
+static DEVICE_ATTR_RW(backing_dev);
+static DEVICE_ATTR_WO(writeback);
+static DEVICE_ATTR_RW(writeback_limit);
+static DEVICE_ATTR_RW(writeback_limit_enable);
+#endif
static struct attribute *zram_disk_attrs[] = {
&dev_attr_disksize.attr,
&dev_attr_initstate.attr,
&dev_attr_reset.attr,
- &dev_attr_num_reads.attr,
- &dev_attr_num_writes.attr,
- &dev_attr_failed_reads.attr,
- &dev_attr_failed_writes.attr,
&dev_attr_compact.attr,
- &dev_attr_invalid_io.attr,
- &dev_attr_notify_free.attr,
- &dev_attr_zero_pages.attr,
- &dev_attr_orig_data_size.attr,
- &dev_attr_compr_data_size.attr,
- &dev_attr_mem_used_total.attr,
&dev_attr_mem_limit.attr,
&dev_attr_mem_used_max.attr,
+ &dev_attr_idle.attr,
&dev_attr_max_comp_streams.attr,
&dev_attr_comp_algorithm.attr,
+#ifdef CONFIG_ZRAM_WRITEBACK
+ &dev_attr_backing_dev.attr,
+ &dev_attr_writeback.attr,
+ &dev_attr_writeback_limit.attr,
+ &dev_attr_writeback_limit_enable.attr,
+#endif
&dev_attr_io_stat.attr,
&dev_attr_mm_stat.attr,
+#ifdef CONFIG_ZRAM_WRITEBACK
+ &dev_attr_bd_stat.attr,
+#endif
&dev_attr_debug_stat.attr,
NULL,
};
-static struct attribute_group zram_disk_attr_group = {
+static const struct attribute_group zram_disk_attr_group = {
.attrs = zram_disk_attrs,
};
@@ -1248,7 +1913,9 @@ static int zram_add(void)
device_id = ret;
init_rwsem(&zram->init_lock);
-
+#ifdef CONFIG_ZRAM_WRITEBACK
+ spin_lock_init(&zram->wb_limit_lock);
+#endif
queue = blk_alloc_queue(GFP_KERNEL);
if (!queue) {
pr_err("Error allocating disk queue for device %d\n",
@@ -1281,6 +1948,7 @@ static int zram_add(void)
/* zram devices sort of resembles non-rotational disks */
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
+
/*
* To ensure that we always get PAGE_SIZE aligned
* and n*PAGE_SIZED sized I/O requests.
@@ -1291,8 +1959,6 @@ static int zram_add(void)
blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
- zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
- zram->disk->queue->limits.chunk_sectors = 0;
blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
/*
* zram_bio_discard() will clear all logical blocks if logical block
@@ -1308,12 +1974,15 @@ static int zram_add(void)
zram->disk->queue->limits.discard_zeroes_data = 0;
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+ zram->disk->queue->backing_dev_info.capabilities |=
+ BDI_CAP_STABLE_WRITES;
+
disk_to_dev(zram->disk)->groups = zram_disk_attr_groups;
add_disk(zram->disk);
strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
- zram->meta = NULL;
+ zram_debugfs_register(zram);
pr_info("Added device: %s\n", zram->disk->disk_name);
return device_id;
@@ -1344,6 +2013,8 @@ static int zram_remove(struct zram *zram)
zram->claim = true;
mutex_unlock(&bdev->bd_mutex);
+ zram_debugfs_unregister(zram);
+
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
@@ -1351,8 +2022,8 @@ static int zram_remove(struct zram *zram)
pr_info("Removed device: %s\n", zram->disk->disk_name);
- blk_cleanup_queue(zram->disk->queue);
del_gendisk(zram->disk);
+ blk_cleanup_queue(zram->disk->queue);
put_disk(zram->disk);
kfree(zram);
return 0;
@@ -1432,6 +2103,7 @@ static void destroy_devices(void)
{
class_unregister(&zram_control_class);
idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
+ zram_debugfs_destroy();
idr_destroy(&zram_index_idr);
unregister_blkdev(zram_major, "zram");
}
@@ -1446,6 +2118,7 @@ static int __init zram_init(void)
return ret;
}
+ zram_debugfs_create();
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_err("Unable to get major number\n");
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 6d2475a..f2fd46d 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -21,22 +21,6 @@
#include "zcomp.h"
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
#define ZRAM_LOGICAL_BLOCK_SHIFT 12
@@ -46,7 +30,7 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
/*
- * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * The lower ZRAM_FLAG_SHIFT bits of table.flags is for
* object size (excluding header), the higher bits is for
* zram_pageflags.
*
@@ -57,11 +41,15 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
*/
#define ZRAM_FLAG_SHIFT 24
-/* Flags for zram pages (table[page_no].value) */
+/* Flags for zram pages (table[page_no].flags) */
enum zram_pageflags {
- /* Page consists entirely of zeros */
- ZRAM_ZERO = ZRAM_FLAG_SHIFT,
- ZRAM_ACCESS, /* page is now accessed */
+ /* zram slot is locked */
+ ZRAM_LOCK = ZRAM_FLAG_SHIFT,
+ ZRAM_SAME, /* Page consists the same element */
+ ZRAM_WB, /* page is stored on backing_device */
+ ZRAM_UNDER_WB, /* page is under writeback */
+ ZRAM_HUGE, /* Incompressible page */
+ ZRAM_IDLE, /* not accessed page since last idle marking */
__NR_ZRAM_PAGEFLAGS,
};
@@ -70,8 +58,14 @@ enum zram_pageflags {
/* Allocated for each disk page */
struct zram_table_entry {
- unsigned long handle;
- unsigned long value;
+ union {
+ unsigned long handle;
+ unsigned long element;
+ };
+ unsigned long flags;
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ ktime_t ac_time;
+#endif
};
struct zram_stats {
@@ -82,19 +76,22 @@ struct zram_stats {
atomic64_t failed_writes; /* can happen when memory is too low */
atomic64_t invalid_io; /* non-page-aligned I/O requests */
atomic64_t notify_free; /* no. of swap slot free notifications */
- atomic64_t zero_pages; /* no. of zero filled pages */
+ atomic64_t same_pages; /* no. of same element filled pages */
+ atomic64_t huge_pages; /* no. of huge pages */
atomic64_t pages_stored; /* no. of pages currently stored */
atomic_long_t max_used_pages; /* no. of maximum pages stored */
atomic64_t writestall; /* no. of write slow paths */
-};
-
-struct zram_meta {
- struct zram_table_entry *table;
- struct zs_pool *mem_pool;
+ atomic64_t miss_free; /* no. of missed free */
+#ifdef CONFIG_ZRAM_WRITEBACK
+ atomic64_t bd_count; /* no. of pages in backing device */
+ atomic64_t bd_reads; /* no. of reads from backing device */
+ atomic64_t bd_writes; /* no. of writes from backing device */
+#endif
};
struct zram {
- struct zram_meta *meta;
+ struct zram_table_entry *table;
+ struct zs_pool *mem_pool;
struct zcomp *comp;
struct gendisk *disk;
/* Prevent concurrent execution of device init */
@@ -105,9 +102,6 @@ struct zram {
unsigned long limit_pages;
struct zram_stats stats;
- atomic_t refcount; /* refcount for zram_meta */
- /* wait all IO under all of cpu are done */
- wait_queue_head_t io_done;
/*
* This is the limit on amount of *uncompressed* worth of data
* we can store in a disk.
@@ -118,5 +112,18 @@ struct zram {
* zram is claimed so open request will be failed
*/
bool claim; /* Protected by bdev->bd_mutex */
+ struct file *backing_dev;
+#ifdef CONFIG_ZRAM_WRITEBACK
+ spinlock_t wb_limit_lock;
+ bool wb_limit_enable;
+ u64 bd_wb_limit;
+ struct block_device *bdev;
+ unsigned int old_block_size;
+ unsigned long *bitmap;
+ unsigned long nr_pages;
+#endif
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ struct dentry *debugfs_dir;
+#endif
};
#endif
diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index 9f2e3be..676c910 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -66,7 +66,7 @@ static void (*specific_poweroff_func)(ipmi_user_t user);
/* Holds the old poweroff function so we can restore it on removal. */
static void (*old_poweroff_func)(void);
-static int set_param_ifnum(const char *val, struct kernel_param *kp)
+static int set_param_ifnum(const char *val, const struct kernel_param *kp)
{
int rv = param_set_int(val, kp);
if (rv)
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 82af658..eda67a6 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1358,7 +1358,7 @@ static unsigned int num_slave_addrs;
#define IPMI_MEM_ADDR_SPACE 1
static const char * const addr_space_to_str[] = { "i/o", "mem" };
-static int hotmod_handler(const char *val, struct kernel_param *kp);
+static int hotmod_handler(const char *val, const struct kernel_param *kp);
module_param_call(hotmod, hotmod_handler, NULL, NULL, 0200);
MODULE_PARM_DESC(hotmod, "Add and remove interfaces. See"
@@ -1828,7 +1828,7 @@ static struct smi_info *smi_info_alloc(void)
return info;
}
-static int hotmod_handler(const char *val, struct kernel_param *kp)
+static int hotmod_handler(const char *val, const struct kernel_param *kp)
{
char *str = kstrdup(val, GFP_KERNEL);
int rv;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4cbc731..1e764ce 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -263,7 +263,7 @@
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
-#include <crypto/chacha20.h>
+#include <crypto/chacha.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
@@ -438,11 +438,10 @@ static int crng_init = 0;
#define crng_ready() (likely(crng_init > 1))
static int crng_init_cnt = 0;
static unsigned long crng_global_init_time = 0;
-#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
-static void _extract_crng(struct crng_state *crng,
- __u8 out[CHACHA20_BLOCK_SIZE]);
+#define CRNG_INIT_CNT_THRESH (2*CHACHA_KEY_SIZE)
+static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]);
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA20_BLOCK_SIZE], int used);
+ __u8 tmp[CHACHA_BLOCK_SIZE], int used);
static void process_random_ready_list(void);
static struct ratelimit_state unseeded_warning =
@@ -818,7 +817,7 @@ static int crng_fast_load(const char *cp, size_t len)
}
p = (unsigned char *) &primary_crng.state[4];
while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) {
- p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp;
+ p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp;
cp++; crng_init_cnt++; len--;
}
if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
@@ -868,7 +867,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
unsigned long flags;
int i, num;
union {
- __u8 block[CHACHA20_BLOCK_SIZE];
+ __u8 block[CHACHA_BLOCK_SIZE];
__u32 key[8];
} buf;
@@ -879,7 +878,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
} else {
_extract_crng(&primary_crng, buf.block);
_crng_backtrack_protect(&primary_crng, buf.block,
- CHACHA20_KEY_SIZE);
+ CHACHA_KEY_SIZE);
}
spin_lock_irqsave(&crng->lock, flags);
for (i = 0; i < 8; i++) {
@@ -894,6 +893,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
if (crng == &primary_crng && crng_init < 2) {
numa_crng_init();
crng_init = 2;
+ spin_unlock_irqrestore(&crng->lock, flags);
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
pr_notice("random: crng init done\n");
@@ -909,8 +909,9 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
urandom_warning.missed);
urandom_warning.missed = 0;
}
+ } else {
+ spin_unlock_irqrestore(&crng->lock, flags);
}
- spin_unlock_irqrestore(&crng->lock, flags);
}
static inline void maybe_reseed_primary_crng(void)
@@ -926,7 +927,7 @@ static inline void crng_wait_ready(void)
}
static void _extract_crng(struct crng_state *crng,
- __u8 out[CHACHA20_BLOCK_SIZE])
+ __u8 out[CHACHA_BLOCK_SIZE])
{
unsigned long v, flags;
@@ -943,7 +944,7 @@ static void _extract_crng(struct crng_state *crng,
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE])
{
struct crng_state *crng = NULL;
@@ -961,14 +962,14 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
* enough) to mutate the CRNG key to provide backtracking protection.
*/
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+ __u8 tmp[CHACHA_BLOCK_SIZE], int used)
{
unsigned long flags;
__u32 *s, *d;
int i;
used = round_up(used, sizeof(__u32));
- if (used + CHACHA20_KEY_SIZE > CHACHA20_BLOCK_SIZE) {
+ if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) {
extract_crng(tmp);
used = 0;
}
@@ -980,7 +981,7 @@ static void _crng_backtrack_protect(struct crng_state *crng,
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used)
{
struct crng_state *crng = NULL;
@@ -995,8 +996,8 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
- ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
- __u8 tmp[CHACHA20_BLOCK_SIZE];
+ ssize_t ret = 0, i = CHACHA_BLOCK_SIZE;
+ __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
int large_request = (nbytes > 256);
while (nbytes) {
@@ -1010,7 +1011,7 @@ static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
}
extract_crng(tmp);
- i = min_t(int, nbytes, CHACHA20_BLOCK_SIZE);
+ i = min_t(int, nbytes, CHACHA_BLOCK_SIZE);
if (copy_to_user(buf, tmp, i)) {
ret = -EFAULT;
break;
@@ -1564,7 +1565,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
*/
void get_random_bytes(void *buf, int nbytes)
{
- __u8 tmp[CHACHA20_BLOCK_SIZE];
+ __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4);
#if DEBUG_RANDOM_BOOT > 0
if (!crng_ready())
@@ -1573,10 +1574,10 @@ void get_random_bytes(void *buf, int nbytes)
#endif
trace_get_random_bytes(nbytes, _RET_IP_);
- while (nbytes >= CHACHA20_BLOCK_SIZE) {
+ while (nbytes >= CHACHA_BLOCK_SIZE) {
extract_crng(buf);
- buf += CHACHA20_BLOCK_SIZE;
- nbytes -= CHACHA20_BLOCK_SIZE;
+ buf += CHACHA_BLOCK_SIZE;
+ nbytes -= CHACHA_BLOCK_SIZE;
}
if (nbytes > 0) {
@@ -1584,7 +1585,7 @@ void get_random_bytes(void *buf, int nbytes)
memcpy(buf, tmp, nbytes);
crng_backtrack_protect(tmp, nbytes);
} else
- crng_backtrack_protect(tmp, CHACHA20_BLOCK_SIZE);
+ crng_backtrack_protect(tmp, CHACHA_BLOCK_SIZE);
memzero_explicit(tmp, sizeof(tmp));
}
EXPORT_SYMBOL(get_random_bytes);
@@ -2110,8 +2111,8 @@ struct ctl_table random_table[] = {
struct batched_entropy {
union {
- unsigned long entropy_long[CHACHA20_BLOCK_SIZE / sizeof(unsigned long)];
- unsigned int entropy_int[CHACHA20_BLOCK_SIZE / sizeof(unsigned int)];
+ unsigned long entropy_long[CHACHA_BLOCK_SIZE / sizeof(unsigned long)];
+ unsigned int entropy_int[CHACHA_BLOCK_SIZE / sizeof(unsigned int)];
};
unsigned int position;
};
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index 9faa0b1..0f86d7e 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -144,7 +144,6 @@
config TCG_VTPM_PROXY
tristate "VTPM Proxy Interface"
depends on TCG_TPM
- select ANON_INODES
---help---
This driver proxies for an emulated TPM (vTPM) running in userspace.
A device /dev/vtpmx is provided that creates a device pair
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index e2c6e43..0bed22f 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -305,6 +305,14 @@
This must be disabled for hardware validation purposes to detect any
hardware anomalies of missing events.
+config ARM_ARCH_TIMER_VCT_ACCESS
+ bool "Support for ARM architected timer virtual counter access in userspace"
+ default !ARM64
+ depends on ARM_ARCH_TIMER
+ help
+ This option enables support for reading the ARM architected timer's
+ virtual counter in userspace.
+
config FSL_ERRATUM_A008585
bool "Workaround for Freescale/NXP Erratum A-008585"
default y
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 5d7f83d..7821378 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -458,7 +458,10 @@ static void arch_counter_set_user_access(void)
| ARCH_TIMER_USR_PCT_ACCESS_EN);
/* Enable user access to the virtual counter */
- cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+ if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_VCT_ACCESS))
+ cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+ else
+ cntkctl &= ~ARCH_TIMER_USR_VCT_ACCESS_EN;
arch_timer_set_cntkctl(cntkctl);
}
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index cac26fb..c70ed51 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -45,6 +45,15 @@
If in doubt, say N.
+config CPU_FREQ_TIMES
+ bool "CPU frequency time-in-state statistics"
+ default y
+ help
+ This driver exports CPU time-in-state information through procfs file
+ system.
+
+ If in doubt, say N.
+
choice
prompt "Default CPUFreq governor"
default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
@@ -102,6 +111,16 @@
governor. If unsure have a look at the help section of the
driver. Fallback governor will be the performance governor.
+config CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+ bool "interactive"
+ select CPU_FREQ_GOV_INTERACTIVE
+ select CPU_FREQ_GOV_PERFORMANCE
+ help
+ Use the CPUFreq governor 'interactive' as default. This allows
+ you to get a full dynamic cpu frequency capable system by simply
+ loading your cpufreq low-level hardware driver, using the
+ 'interactive' governor for latency-sensitive workloads.
+
config CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
bool "schedutil"
depends on SMP
@@ -193,6 +212,26 @@
If in doubt, say N.
+config CPU_FREQ_GOV_INTERACTIVE
+ tristate "'interactive' cpufreq policy governor"
+ depends on CPU_FREQ
+ select CPU_FREQ_GOV_ATTR_SET
+ select IRQ_WORK
+ help
+ 'interactive' - This driver adds a dynamic cpufreq policy governor
+ designed for latency-sensitive workloads.
+
+ This governor attempts to reduce the latency of clock
+ increases so that the system is more responsive to
+ interactive workloads.
+
+ To compile this driver as a module, choose M here: the
+ module will be called cpufreq_interactive.
+
+ For details, take a look at linux/Documentation/cpu-freq.
+
+ If in doubt, say N.
+
config CPU_FREQ_GOV_SCHEDUTIL
bool "'schedutil' cpufreq policy governor"
depends on CPU_FREQ && SMP
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 0a9b6a09..f10a18d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -4,12 +4,16 @@
# CPUfreq stats
obj-$(CONFIG_CPU_FREQ_STAT) += cpufreq_stats.o
-# CPUfreq governors
+# CPUfreq times
+obj-$(CONFIG_CPU_FREQ_TIMES) += cpufreq_times.o
+
+# CPUfreq governors
obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE) += cpufreq_performance.o
obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE) += cpufreq_powersave.o
obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE) += cpufreq_userspace.o
obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND) += cpufreq_ondemand.o
obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE) += cpufreq_conservative.o
+obj-$(CONFIG_CPU_FREQ_GOV_INTERACTIVE) += cpufreq_interactive.o
obj-$(CONFIG_CPU_FREQ_GOV_COMMON) += cpufreq_governor.o
obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET) += cpufreq_governor_attr_set.o
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 1496617..fbb278b 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -282,6 +282,13 @@ static int cpufreq_init(struct cpufreq_policy *policy)
policy->cpuinfo.transition_latency = transition_latency;
+ /*
+ * Android: set default parameters for parity between schedutil and
+ * schedfreq
+ */
+ policy->up_transition_delay_us = transition_latency / NSEC_PER_USEC;
+ policy->down_transition_delay_us = 50000; /* 50ms */
+
return 0;
out_free_cpufreq_table:
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 86d48f8..351080d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -19,6 +19,7 @@
#include <linux/cpu.h>
#include <linux/cpufreq.h>
+#include <linux/cpufreq_times.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/init.h>
@@ -29,6 +30,9 @@
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/tick.h>
+#ifdef CONFIG_SMP
+#include <linux/sched.h>
+#endif
#include <trace/events/power.h>
static LIST_HEAD(cpufreq_policy_list);
@@ -117,6 +121,12 @@ bool have_governor_per_policy(void)
}
EXPORT_SYMBOL_GPL(have_governor_per_policy);
+bool cpufreq_driver_is_slow(void)
+{
+ return !(cpufreq_driver->flags & CPUFREQ_DRIVER_FAST);
+}
+EXPORT_SYMBOL_GPL(cpufreq_driver_is_slow);
+
struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
{
if (have_governor_per_policy())
@@ -301,6 +311,92 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
#endif
}
+/*********************************************************************
+ * FREQUENCY INVARIANT CPU CAPACITY *
+ *********************************************************************/
+
+static DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
+static DEFINE_PER_CPU(unsigned long, max_freq_cpu);
+static DEFINE_PER_CPU(unsigned long, max_freq_scale) = SCHED_CAPACITY_SCALE;
+static DEFINE_PER_CPU(unsigned long, min_freq_scale);
+
+static void
+scale_freq_capacity(const cpumask_t *cpus, unsigned long cur_freq,
+ unsigned long max_freq)
+{
+ unsigned long scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
+ int cpu;
+
+ for_each_cpu(cpu, cpus) {
+ per_cpu(freq_scale, cpu) = scale;
+ per_cpu(max_freq_cpu, cpu) = max_freq;
+ }
+
+ pr_debug("cpus %*pbl cur freq/max freq %lu/%lu kHz freq scale %lu\n",
+ cpumask_pr_args(cpus), cur_freq, max_freq, scale);
+}
+
+unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(freq_scale, cpu);
+}
+
+static void
+scale_max_freq_capacity(const cpumask_t *cpus, unsigned long policy_max_freq)
+{
+ unsigned long scale, max_freq;
+ int cpu = cpumask_first(cpus);
+
+ if (cpu >= nr_cpu_ids)
+ return;
+
+ max_freq = per_cpu(max_freq_cpu, cpu);
+
+ if (!max_freq)
+ return;
+
+ scale = (policy_max_freq << SCHED_CAPACITY_SHIFT) / max_freq;
+
+ for_each_cpu(cpu, cpus)
+ per_cpu(max_freq_scale, cpu) = scale;
+
+ pr_debug("cpus %*pbl policy max freq/max freq %lu/%lu kHz max freq scale %lu\n",
+ cpumask_pr_args(cpus), policy_max_freq, max_freq, scale);
+}
+
+unsigned long cpufreq_scale_max_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(max_freq_scale, cpu);
+}
+
+static void
+scale_min_freq_capacity(const cpumask_t *cpus, unsigned long policy_min_freq)
+{
+ unsigned long scale, max_freq;
+ int cpu = cpumask_first(cpus);
+
+ if (cpu >= nr_cpu_ids)
+ return;
+
+ max_freq = per_cpu(max_freq_cpu, cpu);
+
+ if (!max_freq)
+ return;
+
+ scale = (policy_min_freq << SCHED_CAPACITY_SHIFT) / max_freq;
+
+ for_each_cpu(cpu, cpus)
+ per_cpu(min_freq_scale, cpu) = scale;
+
+ pr_debug("cpus %*pbl policy min freq/max freq %lu/%lu kHz min freq scale %lu\n",
+ cpumask_pr_args(cpus), policy_min_freq, max_freq, scale);
+}
+
+unsigned long cpufreq_scale_min_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(min_freq_scale, cpu);
+}
+
static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
struct cpufreq_freqs *freqs, unsigned int state)
{
@@ -339,6 +435,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
(unsigned long)freqs->new, (unsigned long)freqs->cpu);
trace_cpu_frequency(freqs->new, freqs->cpu);
cpufreq_stats_record_transition(policy, freqs->new);
+ cpufreq_times_record_transition(policy, freqs->new);
srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
CPUFREQ_POSTCHANGE, freqs);
if (likely(policy) && likely(policy->cpu == freqs->cpu))
@@ -378,6 +475,9 @@ static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
struct cpufreq_freqs *freqs)
{
+#ifdef CONFIG_SMP
+ int cpu;
+#endif
/*
* Catch double invocations of _begin() which lead to self-deadlock.
@@ -405,6 +505,12 @@ void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
spin_unlock(&policy->transition_lock);
+ scale_freq_capacity(policy->cpus, freqs->new, policy->cpuinfo.max_freq);
+#ifdef CONFIG_SMP
+ for_each_cpu(cpu, policy->cpus)
+ trace_cpu_capacity(capacity_curr_of(cpu), cpu);
+#endif
+
cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
}
EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin);
@@ -1264,6 +1370,7 @@ static int cpufreq_online(unsigned int cpu)
goto out_exit_policy;
cpufreq_stats_create_table(policy);
+ cpufreq_times_create_policy(policy);
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_CREATE_POLICY, policy);
@@ -1831,9 +1938,14 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq)
{
+ int ret;
target_freq = clamp_val(target_freq, policy->min, policy->max);
- return cpufreq_driver->fast_switch(policy, target_freq);
+ ret = cpufreq_driver->fast_switch(policy, target_freq);
+ if (ret)
+ cpufreq_times_record_transition(policy, ret);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
@@ -2210,8 +2322,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_NOTIFY, new_policy);
+ scale_max_freq_capacity(policy->cpus, policy->max);
+ scale_min_freq_capacity(policy->cpus, policy->min);
+
policy->min = new_policy->min;
policy->max = new_policy->max;
+ trace_cpu_frequency_limits(policy->max, policy->min, policy->cpu);
policy->cached_target_freq = UINT_MAX;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 00a7435..0fe2518 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -302,7 +302,10 @@ static void cs_start(struct cpufreq_policy *policy)
dbs_info->requested_freq = policy->cur;
}
-static struct dbs_governor cs_governor = {
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+static
+#endif
+struct dbs_governor cs_governor = {
.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
.kobj_type = { .default_attrs = cs_attributes },
.gov_dbs_timer = cs_dbs_timer,
diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c
new file mode 100644
index 0000000..5a77d91
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_interactive.c
@@ -0,0 +1,1411 @@
+/*
+ * drivers/cpufreq/cpufreq_interactive.c
+ *
+ * Copyright (C) 2010-2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/cpufreq.h>
+#include <linux/irq_work.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/tick.h>
+#include <linux/time.h>
+#include <linux/timer.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/cpufreq_interactive.h>
+
+#define gov_attr_ro(_name) \
+static struct governor_attr _name = \
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define gov_attr_wo(_name) \
+static struct governor_attr _name = \
+__ATTR(_name, 0200, NULL, store_##_name)
+
+#define gov_attr_rw(_name) \
+static struct governor_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+/* Separate instance required for each 'interactive' directory in sysfs */
+struct interactive_tunables {
+ struct gov_attr_set attr_set;
+
+ /* Hi speed to bump to from lo speed when load burst (default max) */
+ unsigned int hispeed_freq;
+
+ /* Go to hi speed when CPU load at or above this value. */
+#define DEFAULT_GO_HISPEED_LOAD 99
+ unsigned long go_hispeed_load;
+
+ /* Target load. Lower values result in higher CPU speeds. */
+ spinlock_t target_loads_lock;
+ unsigned int *target_loads;
+ int ntarget_loads;
+
+ /*
+ * The minimum amount of time to spend at a frequency before we can ramp
+ * down.
+ */
+#define DEFAULT_MIN_SAMPLE_TIME (80 * USEC_PER_MSEC)
+ unsigned long min_sample_time;
+
+ /* The sample rate of the timer used to increase frequency */
+ unsigned long sampling_rate;
+
+ /*
+ * Wait this long before raising speed above hispeed, by default a
+ * single timer interval.
+ */
+ spinlock_t above_hispeed_delay_lock;
+ unsigned int *above_hispeed_delay;
+ int nabove_hispeed_delay;
+
+ /* Non-zero means indefinite speed boost active */
+ int boost;
+ /* Duration of a boot pulse in usecs */
+ int boostpulse_duration;
+ /* End time of boost pulse in ktime converted to usecs */
+ u64 boostpulse_endtime;
+ bool boosted;
+
+ /*
+ * Max additional time to wait in idle, beyond sampling_rate, at speeds
+ * above minimum before wakeup to reduce speed, or -1 if unnecessary.
+ */
+#define DEFAULT_TIMER_SLACK (4 * DEFAULT_SAMPLING_RATE)
+ unsigned long timer_slack_delay;
+ unsigned long timer_slack;
+ bool io_is_busy;
+};
+
+/* Separate instance required for each 'struct cpufreq_policy' */
+struct interactive_policy {
+ struct cpufreq_policy *policy;
+ struct interactive_tunables *tunables;
+ struct list_head tunables_hook;
+};
+
+/* Separate instance required for each CPU */
+struct interactive_cpu {
+ struct update_util_data update_util;
+ struct interactive_policy *ipolicy;
+
+ struct irq_work irq_work;
+ u64 last_sample_time;
+ unsigned long next_sample_jiffies;
+ bool work_in_progress;
+
+ struct rw_semaphore enable_sem;
+ struct timer_list slack_timer;
+
+ spinlock_t load_lock; /* protects the next 4 fields */
+ u64 time_in_idle;
+ u64 time_in_idle_timestamp;
+ u64 cputime_speedadj;
+ u64 cputime_speedadj_timestamp;
+
+ spinlock_t target_freq_lock; /*protects target freq */
+ unsigned int target_freq;
+
+ unsigned int floor_freq;
+ u64 pol_floor_val_time; /* policy floor_validate_time */
+ u64 loc_floor_val_time; /* per-cpu floor_validate_time */
+ u64 pol_hispeed_val_time; /* policy hispeed_validate_time */
+ u64 loc_hispeed_val_time; /* per-cpu hispeed_validate_time */
+};
+
+static DEFINE_PER_CPU(struct interactive_cpu, interactive_cpu);
+
+/* Realtime thread handles frequency scaling */
+static struct task_struct *speedchange_task;
+static cpumask_t speedchange_cpumask;
+static spinlock_t speedchange_cpumask_lock;
+
+/* Target load. Lower values result in higher CPU speeds. */
+#define DEFAULT_TARGET_LOAD 90
+static unsigned int default_target_loads[] = {DEFAULT_TARGET_LOAD};
+
+#define DEFAULT_SAMPLING_RATE (20 * USEC_PER_MSEC)
+#define DEFAULT_ABOVE_HISPEED_DELAY DEFAULT_SAMPLING_RATE
+static unsigned int default_above_hispeed_delay[] = {
+ DEFAULT_ABOVE_HISPEED_DELAY
+};
+
+/* Iterate over interactive policies for tunables */
+#define for_each_ipolicy(__ip) \
+ list_for_each_entry(__ip, &tunables->attr_set.policy_list, tunables_hook)
+
+static struct interactive_tunables *global_tunables;
+static DEFINE_MUTEX(global_tunables_lock);
+
+static inline void update_slack_delay(struct interactive_tunables *tunables)
+{
+ tunables->timer_slack_delay = usecs_to_jiffies(tunables->timer_slack +
+ tunables->sampling_rate);
+}
+
+static bool timer_slack_required(struct interactive_cpu *icpu)
+{
+ struct interactive_policy *ipolicy = icpu->ipolicy;
+ struct interactive_tunables *tunables = ipolicy->tunables;
+
+ if (tunables->timer_slack < 0)
+ return false;
+
+ if (icpu->target_freq > ipolicy->policy->min)
+ return true;
+
+ return false;
+}
+
+static void gov_slack_timer_start(struct interactive_cpu *icpu, int cpu)
+{
+ struct interactive_tunables *tunables = icpu->ipolicy->tunables;
+
+ icpu->slack_timer.expires = jiffies + tunables->timer_slack_delay;
+ add_timer_on(&icpu->slack_timer, cpu);
+}
+
+static void gov_slack_timer_modify(struct interactive_cpu *icpu)
+{
+ struct interactive_tunables *tunables = icpu->ipolicy->tunables;
+
+ mod_timer(&icpu->slack_timer, jiffies + tunables->timer_slack_delay);
+}
+
+static void slack_timer_resched(struct interactive_cpu *icpu, int cpu,
+ bool modify)
+{
+ struct interactive_tunables *tunables = icpu->ipolicy->tunables;
+ unsigned long flags;
+
+ spin_lock_irqsave(&icpu->load_lock, flags);
+
+ icpu->time_in_idle = get_cpu_idle_time(cpu,
+ &icpu->time_in_idle_timestamp,
+ tunables->io_is_busy);
+ icpu->cputime_speedadj = 0;
+ icpu->cputime_speedadj_timestamp = icpu->time_in_idle_timestamp;
+
+ if (timer_slack_required(icpu)) {
+ if (modify)
+ gov_slack_timer_modify(icpu);
+ else
+ gov_slack_timer_start(icpu, cpu);
+ }
+
+ spin_unlock_irqrestore(&icpu->load_lock, flags);
+}
+
+static unsigned int
+freq_to_above_hispeed_delay(struct interactive_tunables *tunables,
+ unsigned int freq)
+{
+ unsigned long flags;
+ unsigned int ret;
+ int i;
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+ for (i = 0; i < tunables->nabove_hispeed_delay - 1 &&
+ freq >= tunables->above_hispeed_delay[i + 1]; i += 2)
+ ;
+
+ ret = tunables->above_hispeed_delay[i];
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+
+ return ret;
+}
+
+static unsigned int freq_to_targetload(struct interactive_tunables *tunables,
+ unsigned int freq)
+{
+ unsigned long flags;
+ unsigned int ret;
+ int i;
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+ for (i = 0; i < tunables->ntarget_loads - 1 &&
+ freq >= tunables->target_loads[i + 1]; i += 2)
+ ;
+
+ ret = tunables->target_loads[i];
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+ return ret;
+}
+
+/*
+ * If increasing frequencies never map to a lower target load then
+ * choose_freq() will find the minimum frequency that does not exceed its
+ * target load given the current load.
+ */
+static unsigned int choose_freq(struct interactive_cpu *icpu,
+ unsigned int loadadjfreq)
+{
+ struct cpufreq_policy *policy = icpu->ipolicy->policy;
+ struct cpufreq_frequency_table *freq_table = policy->freq_table;
+ unsigned int prevfreq, freqmin = 0, freqmax = UINT_MAX, tl;
+ unsigned int freq = policy->cur;
+ int index;
+
+ do {
+ prevfreq = freq;
+ tl = freq_to_targetload(icpu->ipolicy->tunables, freq);
+
+ /*
+ * Find the lowest frequency where the computed load is less
+ * than or equal to the target load.
+ */
+
+ index = cpufreq_frequency_table_target(policy, loadadjfreq / tl,
+ CPUFREQ_RELATION_L);
+
+ freq = freq_table[index].frequency;
+
+ if (freq > prevfreq) {
+ /* The previous frequency is too low */
+ freqmin = prevfreq;
+
+ if (freq < freqmax)
+ continue;
+
+ /* Find highest frequency that is less than freqmax */
+ index = cpufreq_frequency_table_target(policy,
+ freqmax - 1, CPUFREQ_RELATION_H);
+
+ freq = freq_table[index].frequency;
+
+ if (freq == freqmin) {
+ /*
+ * The first frequency below freqmax has already
+ * been found to be too low. freqmax is the
+ * lowest speed we found that is fast enough.
+ */
+ freq = freqmax;
+ break;
+ }
+ } else if (freq < prevfreq) {
+ /* The previous frequency is high enough. */
+ freqmax = prevfreq;
+
+ if (freq > freqmin)
+ continue;
+
+ /* Find lowest frequency that is higher than freqmin */
+ index = cpufreq_frequency_table_target(policy,
+ freqmin + 1, CPUFREQ_RELATION_L);
+
+ freq = freq_table[index].frequency;
+
+ /*
+ * If freqmax is the first frequency above
+ * freqmin then we have already found that
+ * this speed is fast enough.
+ */
+ if (freq == freqmax)
+ break;
+ }
+
+ /* If same frequency chosen as previous then done. */
+ } while (freq != prevfreq);
+
+ return freq;
+}
+
+static u64 update_load(struct interactive_cpu *icpu, int cpu)
+{
+ struct interactive_tunables *tunables = icpu->ipolicy->tunables;
+ u64 now_idle, now, active_time, delta_idle, delta_time;
+
+ now_idle = get_cpu_idle_time(cpu, &now, tunables->io_is_busy);
+ delta_idle = (now_idle - icpu->time_in_idle);
+ delta_time = (now - icpu->time_in_idle_timestamp);
+
+ if (delta_time <= delta_idle)
+ active_time = 0;
+ else
+ active_time = delta_time - delta_idle;
+
+ icpu->cputime_speedadj += active_time * icpu->ipolicy->policy->cur;
+
+ icpu->time_in_idle = now_idle;
+ icpu->time_in_idle_timestamp = now;
+
+ return now;
+}
+
+/* Re-evaluate load to see if a frequency change is required or not */
+static void eval_target_freq(struct interactive_cpu *icpu)
+{
+ struct interactive_tunables *tunables = icpu->ipolicy->tunables;
+ struct cpufreq_policy *policy = icpu->ipolicy->policy;
+ struct cpufreq_frequency_table *freq_table = policy->freq_table;
+ u64 cputime_speedadj, now, max_fvtime;
+ unsigned int new_freq, loadadjfreq, index, delta_time;
+ unsigned long flags;
+ int cpu_load;
+ int cpu = smp_processor_id();
+
+ spin_lock_irqsave(&icpu->load_lock, flags);
+ now = update_load(icpu, smp_processor_id());
+ delta_time = (unsigned int)(now - icpu->cputime_speedadj_timestamp);
+ cputime_speedadj = icpu->cputime_speedadj;
+ spin_unlock_irqrestore(&icpu->load_lock, flags);
+
+ if (WARN_ON_ONCE(!delta_time))
+ return;
+
+ spin_lock_irqsave(&icpu->target_freq_lock, flags);
+ do_div(cputime_speedadj, delta_time);
+ loadadjfreq = (unsigned int)cputime_speedadj * 100;
+ cpu_load = loadadjfreq / policy->cur;
+ tunables->boosted = tunables->boost ||
+ now < tunables->boostpulse_endtime;
+
+ if (cpu_load >= tunables->go_hispeed_load || tunables->boosted) {
+ if (policy->cur < tunables->hispeed_freq) {
+ new_freq = tunables->hispeed_freq;
+ } else {
+ new_freq = choose_freq(icpu, loadadjfreq);
+
+ if (new_freq < tunables->hispeed_freq)
+ new_freq = tunables->hispeed_freq;
+ }
+ } else {
+ new_freq = choose_freq(icpu, loadadjfreq);
+ if (new_freq > tunables->hispeed_freq &&
+ policy->cur < tunables->hispeed_freq)
+ new_freq = tunables->hispeed_freq;
+ }
+
+ if (policy->cur >= tunables->hispeed_freq &&
+ new_freq > policy->cur &&
+ now - icpu->pol_hispeed_val_time < freq_to_above_hispeed_delay(tunables, policy->cur)) {
+ trace_cpufreq_interactive_notyet(cpu, cpu_load,
+ icpu->target_freq, policy->cur, new_freq);
+ goto exit;
+ }
+
+ icpu->loc_hispeed_val_time = now;
+
+ index = cpufreq_frequency_table_target(policy, new_freq,
+ CPUFREQ_RELATION_L);
+ new_freq = freq_table[index].frequency;
+
+ /*
+ * Do not scale below floor_freq unless we have been at or above the
+ * floor frequency for the minimum sample time since last validated.
+ */
+ max_fvtime = max(icpu->pol_floor_val_time, icpu->loc_floor_val_time);
+ if (new_freq < icpu->floor_freq && icpu->target_freq >= policy->cur) {
+ if (now - max_fvtime < tunables->min_sample_time) {
+ trace_cpufreq_interactive_notyet(cpu, cpu_load,
+ icpu->target_freq, policy->cur, new_freq);
+ goto exit;
+ }
+ }
+
+ /*
+ * Update the timestamp for checking whether speed has been held at
+ * or above the selected frequency for a minimum of min_sample_time,
+ * if not boosted to hispeed_freq. If boosted to hispeed_freq then we
+ * allow the speed to drop as soon as the boostpulse duration expires
+ * (or the indefinite boost is turned off).
+ */
+
+ if (!tunables->boosted || new_freq > tunables->hispeed_freq) {
+ icpu->floor_freq = new_freq;
+ if (icpu->target_freq >= policy->cur || new_freq >= policy->cur)
+ icpu->loc_floor_val_time = now;
+ }
+
+ if (icpu->target_freq == new_freq &&
+ icpu->target_freq <= policy->cur) {
+ trace_cpufreq_interactive_already(cpu, cpu_load,
+ icpu->target_freq, policy->cur, new_freq);
+ goto exit;
+ }
+
+ trace_cpufreq_interactive_target(cpu, cpu_load, icpu->target_freq,
+ policy->cur, new_freq);
+
+ icpu->target_freq = new_freq;
+ spin_unlock_irqrestore(&icpu->target_freq_lock, flags);
+
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+ cpumask_set_cpu(cpu, &speedchange_cpumask);
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+
+ wake_up_process(speedchange_task);
+ return;
+
+exit:
+ spin_unlock_irqrestore(&icpu->target_freq_lock, flags);
+}
+
+static void cpufreq_interactive_update(struct interactive_cpu *icpu)
+{
+ eval_target_freq(icpu);
+ slack_timer_resched(icpu, smp_processor_id(), true);
+}
+
+static void cpufreq_interactive_idle_end(void)
+{
+ struct interactive_cpu *icpu = &per_cpu(interactive_cpu,
+ smp_processor_id());
+
+ if (!down_read_trylock(&icpu->enable_sem))
+ return;
+
+ if (icpu->ipolicy) {
+ /*
+ * We haven't sampled load for more than sampling_rate time, do
+ * it right now.
+ */
+ if (time_after_eq(jiffies, icpu->next_sample_jiffies))
+ cpufreq_interactive_update(icpu);
+ }
+
+ up_read(&icpu->enable_sem);
+}
+
+static void cpufreq_interactive_get_policy_info(struct cpufreq_policy *policy,
+ unsigned int *pmax_freq,
+ u64 *phvt, u64 *pfvt)
+{
+ struct interactive_cpu *icpu;
+ u64 hvt = ~0ULL, fvt = 0;
+ unsigned int max_freq = 0, i;
+
+ for_each_cpu(i, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, i);
+
+ fvt = max(fvt, icpu->loc_floor_val_time);
+ if (icpu->target_freq > max_freq) {
+ max_freq = icpu->target_freq;
+ hvt = icpu->loc_hispeed_val_time;
+ } else if (icpu->target_freq == max_freq) {
+ hvt = min(hvt, icpu->loc_hispeed_val_time);
+ }
+ }
+
+ *pmax_freq = max_freq;
+ *phvt = hvt;
+ *pfvt = fvt;
+}
+
+static void cpufreq_interactive_adjust_cpu(unsigned int cpu,
+ struct cpufreq_policy *policy)
+{
+ struct interactive_cpu *icpu;
+ u64 hvt, fvt;
+ unsigned int max_freq;
+ int i;
+
+ cpufreq_interactive_get_policy_info(policy, &max_freq, &hvt, &fvt);
+
+ for_each_cpu(i, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, i);
+ icpu->pol_floor_val_time = fvt;
+ }
+
+ if (max_freq != policy->cur) {
+ __cpufreq_driver_target(policy, max_freq, CPUFREQ_RELATION_H);
+ for_each_cpu(i, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, i);
+ icpu->pol_hispeed_val_time = hvt;
+ }
+ }
+
+ trace_cpufreq_interactive_setspeed(cpu, max_freq, policy->cur);
+}
+
+static int cpufreq_interactive_speedchange_task(void *data)
+{
+ unsigned int cpu;
+ cpumask_t tmp_mask;
+ unsigned long flags;
+
+again:
+ set_current_state(TASK_INTERRUPTIBLE);
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+
+ if (cpumask_empty(&speedchange_cpumask)) {
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+ schedule();
+
+ if (kthread_should_stop())
+ return 0;
+
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+ }
+
+ set_current_state(TASK_RUNNING);
+ tmp_mask = speedchange_cpumask;
+ cpumask_clear(&speedchange_cpumask);
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+
+ for_each_cpu(cpu, &tmp_mask) {
+ struct interactive_cpu *icpu = &per_cpu(interactive_cpu, cpu);
+ struct cpufreq_policy *policy;
+
+ if (unlikely(!down_read_trylock(&icpu->enable_sem)))
+ continue;
+
+ if (likely(icpu->ipolicy)) {
+ policy = icpu->ipolicy->policy;
+ cpufreq_interactive_adjust_cpu(cpu, policy);
+ }
+
+ up_read(&icpu->enable_sem);
+ }
+
+ goto again;
+}
+
+static void cpufreq_interactive_boost(struct interactive_tunables *tunables)
+{
+ struct interactive_policy *ipolicy;
+ struct cpufreq_policy *policy;
+ struct interactive_cpu *icpu;
+ unsigned long flags[2];
+ bool wakeup = false;
+ int i;
+
+ tunables->boosted = true;
+
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags[0]);
+
+ for_each_ipolicy(ipolicy) {
+ policy = ipolicy->policy;
+
+ for_each_cpu(i, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, i);
+
+ if (!down_read_trylock(&icpu->enable_sem))
+ continue;
+
+ if (!icpu->ipolicy) {
+ up_read(&icpu->enable_sem);
+ continue;
+ }
+
+ spin_lock_irqsave(&icpu->target_freq_lock, flags[1]);
+ if (icpu->target_freq < tunables->hispeed_freq) {
+ icpu->target_freq = tunables->hispeed_freq;
+ cpumask_set_cpu(i, &speedchange_cpumask);
+ icpu->pol_hispeed_val_time = ktime_to_us(ktime_get());
+ wakeup = true;
+ }
+ spin_unlock_irqrestore(&icpu->target_freq_lock, flags[1]);
+
+ up_read(&icpu->enable_sem);
+ }
+ }
+
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags[0]);
+
+ if (wakeup)
+ wake_up_process(speedchange_task);
+}
+
+static int cpufreq_interactive_notifier(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct cpufreq_freqs *freq = data;
+ struct interactive_cpu *icpu = &per_cpu(interactive_cpu, freq->cpu);
+ unsigned long flags;
+
+ if (val != CPUFREQ_POSTCHANGE)
+ return 0;
+
+ if (!down_read_trylock(&icpu->enable_sem))
+ return 0;
+
+ if (!icpu->ipolicy) {
+ up_read(&icpu->enable_sem);
+ return 0;
+ }
+
+ spin_lock_irqsave(&icpu->load_lock, flags);
+ update_load(icpu, freq->cpu);
+ spin_unlock_irqrestore(&icpu->load_lock, flags);
+
+ up_read(&icpu->enable_sem);
+
+ return 0;
+}
+
+static struct notifier_block cpufreq_notifier_block = {
+ .notifier_call = cpufreq_interactive_notifier,
+};
+
+static unsigned int *get_tokenized_data(const char *buf, int *num_tokens)
+{
+ const char *cp = buf;
+ int ntokens = 1, i = 0;
+ unsigned int *tokenized_data;
+ int err = -EINVAL;
+
+ while ((cp = strpbrk(cp + 1, " :")))
+ ntokens++;
+
+ if (!(ntokens & 0x1))
+ goto err;
+
+ tokenized_data = kcalloc(ntokens, sizeof(*tokenized_data), GFP_KERNEL);
+ if (!tokenized_data) {
+ err = -ENOMEM;
+ goto err;
+ }
+
+ cp = buf;
+ while (i < ntokens) {
+ if (kstrtouint(cp, 0, &tokenized_data[i++]) < 0)
+ goto err_kfree;
+
+ cp = strpbrk(cp, " :");
+ if (!cp)
+ break;
+ cp++;
+ }
+
+ if (i != ntokens)
+ goto err_kfree;
+
+ *num_tokens = ntokens;
+ return tokenized_data;
+
+err_kfree:
+ kfree(tokenized_data);
+err:
+ return ERR_PTR(err);
+}
+
+/* Interactive governor sysfs interface */
+static struct interactive_tunables *to_tunables(struct gov_attr_set *attr_set)
+{
+ return container_of(attr_set, struct interactive_tunables, attr_set);
+}
+
+#define show_one(file_name, type) \
+static ssize_t show_##file_name(struct gov_attr_set *attr_set, char *buf) \
+{ \
+ struct interactive_tunables *tunables = to_tunables(attr_set); \
+ return sprintf(buf, type "\n", tunables->file_name); \
+}
+
+static ssize_t show_target_loads(struct gov_attr_set *attr_set, char *buf)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long flags;
+ ssize_t ret = 0;
+ int i;
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+ for (i = 0; i < tunables->ntarget_loads; i++)
+ ret += sprintf(buf + ret, "%u%s", tunables->target_loads[i],
+ i & 0x1 ? ":" : " ");
+
+ sprintf(buf + ret - 1, "\n");
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+
+ return ret;
+}
+
+static ssize_t store_target_loads(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned int *new_target_loads;
+ unsigned long flags;
+ int ntokens;
+
+ new_target_loads = get_tokenized_data(buf, &ntokens);
+ if (IS_ERR(new_target_loads))
+ return PTR_ERR(new_target_loads);
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+ if (tunables->target_loads != default_target_loads)
+ kfree(tunables->target_loads);
+ tunables->target_loads = new_target_loads;
+ tunables->ntarget_loads = ntokens;
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+
+ return count;
+}
+
+static ssize_t show_above_hispeed_delay(struct gov_attr_set *attr_set,
+ char *buf)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long flags;
+ ssize_t ret = 0;
+ int i;
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+ for (i = 0; i < tunables->nabove_hispeed_delay; i++)
+ ret += sprintf(buf + ret, "%u%s",
+ tunables->above_hispeed_delay[i],
+ i & 0x1 ? ":" : " ");
+
+ sprintf(buf + ret - 1, "\n");
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+
+ return ret;
+}
+
+static ssize_t store_above_hispeed_delay(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned int *new_above_hispeed_delay = NULL;
+ unsigned long flags;
+ int ntokens;
+
+ new_above_hispeed_delay = get_tokenized_data(buf, &ntokens);
+ if (IS_ERR(new_above_hispeed_delay))
+ return PTR_ERR(new_above_hispeed_delay);
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+ if (tunables->above_hispeed_delay != default_above_hispeed_delay)
+ kfree(tunables->above_hispeed_delay);
+ tunables->above_hispeed_delay = new_above_hispeed_delay;
+ tunables->nabove_hispeed_delay = ntokens;
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+
+ return count;
+}
+
+static ssize_t store_hispeed_freq(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long int val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->hispeed_freq = val;
+
+ return count;
+}
+
+static ssize_t store_go_hispeed_load(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->go_hispeed_load = val;
+
+ return count;
+}
+
+static ssize_t store_min_sample_time(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->min_sample_time = val;
+
+ return count;
+}
+
+static ssize_t show_timer_rate(struct gov_attr_set *attr_set, char *buf)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+
+ return sprintf(buf, "%lu\n", tunables->sampling_rate);
+}
+
+static ssize_t store_timer_rate(struct gov_attr_set *attr_set, const char *buf,
+ size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val, val_round;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ val_round = jiffies_to_usecs(usecs_to_jiffies(val));
+ if (val != val_round)
+ pr_warn("timer_rate not aligned to jiffy. Rounded up to %lu\n",
+ val_round);
+
+ tunables->sampling_rate = val_round;
+
+ return count;
+}
+
+static ssize_t store_timer_slack(struct gov_attr_set *attr_set, const char *buf,
+ size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtol(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->timer_slack = val;
+ update_slack_delay(tunables);
+
+ return count;
+}
+
+static ssize_t store_boost(struct gov_attr_set *attr_set, const char *buf,
+ size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boost = val;
+
+ if (tunables->boost) {
+ trace_cpufreq_interactive_boost("on");
+ if (!tunables->boosted)
+ cpufreq_interactive_boost(tunables);
+ } else {
+ tunables->boostpulse_endtime = ktime_to_us(ktime_get());
+ trace_cpufreq_interactive_unboost("off");
+ }
+
+ return count;
+}
+
+static ssize_t store_boostpulse(struct gov_attr_set *attr_set, const char *buf,
+ size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boostpulse_endtime = ktime_to_us(ktime_get()) +
+ tunables->boostpulse_duration;
+ trace_cpufreq_interactive_boost("pulse");
+ if (!tunables->boosted)
+ cpufreq_interactive_boost(tunables);
+
+ return count;
+}
+
+static ssize_t store_boostpulse_duration(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boostpulse_duration = val;
+
+ return count;
+}
+
+static ssize_t store_io_is_busy(struct gov_attr_set *attr_set, const char *buf,
+ size_t count)
+{
+ struct interactive_tunables *tunables = to_tunables(attr_set);
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->io_is_busy = val;
+
+ return count;
+}
+
+show_one(hispeed_freq, "%u");
+show_one(go_hispeed_load, "%lu");
+show_one(min_sample_time, "%lu");
+show_one(timer_slack, "%lu");
+show_one(boost, "%u");
+show_one(boostpulse_duration, "%u");
+show_one(io_is_busy, "%u");
+
+gov_attr_rw(target_loads);
+gov_attr_rw(above_hispeed_delay);
+gov_attr_rw(hispeed_freq);
+gov_attr_rw(go_hispeed_load);
+gov_attr_rw(min_sample_time);
+gov_attr_rw(timer_rate);
+gov_attr_rw(timer_slack);
+gov_attr_rw(boost);
+gov_attr_wo(boostpulse);
+gov_attr_rw(boostpulse_duration);
+gov_attr_rw(io_is_busy);
+
+static struct attribute *interactive_attributes[] = {
+ &target_loads.attr,
+ &above_hispeed_delay.attr,
+ &hispeed_freq.attr,
+ &go_hispeed_load.attr,
+ &min_sample_time.attr,
+ &timer_rate.attr,
+ &timer_slack.attr,
+ &boost.attr,
+ &boostpulse.attr,
+ &boostpulse_duration.attr,
+ &io_is_busy.attr,
+ NULL
+};
+
+static struct kobj_type interactive_tunables_ktype = {
+ .default_attrs = interactive_attributes,
+ .sysfs_ops = &governor_sysfs_ops,
+};
+
+static int cpufreq_interactive_idle_notifier(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ if (val == IDLE_END)
+ cpufreq_interactive_idle_end();
+
+ return 0;
+}
+
+static struct notifier_block cpufreq_interactive_idle_nb = {
+ .notifier_call = cpufreq_interactive_idle_notifier,
+};
+
+/* Interactive Governor callbacks */
+struct interactive_governor {
+ struct cpufreq_governor gov;
+ unsigned int usage_count;
+};
+
+static struct interactive_governor interactive_gov;
+
+#define CPU_FREQ_GOV_INTERACTIVE (&interactive_gov.gov)
+
+static void irq_work(struct irq_work *irq_work)
+{
+ struct interactive_cpu *icpu = container_of(irq_work, struct
+ interactive_cpu, irq_work);
+
+ cpufreq_interactive_update(icpu);
+ icpu->work_in_progress = false;
+}
+
+static void update_util_handler(struct update_util_data *data, u64 time,
+ unsigned int flags)
+{
+ struct interactive_cpu *icpu = container_of(data,
+ struct interactive_cpu, update_util);
+ struct interactive_policy *ipolicy = icpu->ipolicy;
+ struct interactive_tunables *tunables = ipolicy->tunables;
+ u64 delta_ns;
+
+ /*
+ * The irq-work may not be allowed to be queued up right now.
+ * Possible reasons:
+ * - Work has already been queued up or is in progress.
+ * - It is too early (too little time from the previous sample).
+ */
+ if (icpu->work_in_progress)
+ return;
+
+ delta_ns = time - icpu->last_sample_time;
+ if ((s64)delta_ns < tunables->sampling_rate * NSEC_PER_USEC)
+ return;
+
+ icpu->last_sample_time = time;
+ icpu->next_sample_jiffies = usecs_to_jiffies(tunables->sampling_rate) +
+ jiffies;
+
+ icpu->work_in_progress = true;
+ irq_work_queue(&icpu->irq_work);
+}
+
+static void gov_set_update_util(struct interactive_policy *ipolicy)
+{
+ struct cpufreq_policy *policy = ipolicy->policy;
+ struct interactive_cpu *icpu;
+ int cpu;
+
+ for_each_cpu(cpu, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, cpu);
+
+ icpu->last_sample_time = 0;
+ icpu->next_sample_jiffies = 0;
+ cpufreq_add_update_util_hook(cpu, &icpu->update_util,
+ update_util_handler);
+ }
+}
+
+static inline void gov_clear_update_util(struct cpufreq_policy *policy)
+{
+ int i;
+
+ for_each_cpu(i, policy->cpus)
+ cpufreq_remove_update_util_hook(i);
+
+ synchronize_sched();
+}
+
+static void icpu_cancel_work(struct interactive_cpu *icpu)
+{
+ irq_work_sync(&icpu->irq_work);
+ icpu->work_in_progress = false;
+ del_timer_sync(&icpu->slack_timer);
+}
+
+static struct interactive_policy *
+interactive_policy_alloc(struct cpufreq_policy *policy)
+{
+ struct interactive_policy *ipolicy;
+
+ ipolicy = kzalloc(sizeof(*ipolicy), GFP_KERNEL);
+ if (!ipolicy)
+ return NULL;
+
+ ipolicy->policy = policy;
+
+ return ipolicy;
+}
+
+static void interactive_policy_free(struct interactive_policy *ipolicy)
+{
+ kfree(ipolicy);
+}
+
+static struct interactive_tunables *
+interactive_tunables_alloc(struct interactive_policy *ipolicy)
+{
+ struct interactive_tunables *tunables;
+
+ tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
+ if (!tunables)
+ return NULL;
+
+ gov_attr_set_init(&tunables->attr_set, &ipolicy->tunables_hook);
+ if (!have_governor_per_policy())
+ global_tunables = tunables;
+
+ ipolicy->tunables = tunables;
+
+ return tunables;
+}
+
+static void interactive_tunables_free(struct interactive_tunables *tunables)
+{
+ if (!have_governor_per_policy())
+ global_tunables = NULL;
+
+ kfree(tunables);
+}
+
+int cpufreq_interactive_init(struct cpufreq_policy *policy)
+{
+ struct interactive_policy *ipolicy;
+ struct interactive_tunables *tunables;
+ int ret;
+
+ /* State should be equivalent to EXIT */
+ if (policy->governor_data)
+ return -EBUSY;
+
+ ipolicy = interactive_policy_alloc(policy);
+ if (!ipolicy)
+ return -ENOMEM;
+
+ mutex_lock(&global_tunables_lock);
+
+ if (global_tunables) {
+ if (WARN_ON(have_governor_per_policy())) {
+ ret = -EINVAL;
+ goto free_int_policy;
+ }
+
+ policy->governor_data = ipolicy;
+ ipolicy->tunables = global_tunables;
+
+ gov_attr_set_get(&global_tunables->attr_set,
+ &ipolicy->tunables_hook);
+ goto out;
+ }
+
+ tunables = interactive_tunables_alloc(ipolicy);
+ if (!tunables) {
+ ret = -ENOMEM;
+ goto free_int_policy;
+ }
+
+ tunables->hispeed_freq = policy->max;
+ tunables->above_hispeed_delay = default_above_hispeed_delay;
+ tunables->nabove_hispeed_delay =
+ ARRAY_SIZE(default_above_hispeed_delay);
+ tunables->go_hispeed_load = DEFAULT_GO_HISPEED_LOAD;
+ tunables->target_loads = default_target_loads;
+ tunables->ntarget_loads = ARRAY_SIZE(default_target_loads);
+ tunables->min_sample_time = DEFAULT_MIN_SAMPLE_TIME;
+ tunables->boostpulse_duration = DEFAULT_MIN_SAMPLE_TIME;
+ tunables->sampling_rate = DEFAULT_SAMPLING_RATE;
+ tunables->timer_slack = DEFAULT_TIMER_SLACK;
+ update_slack_delay(tunables);
+
+ spin_lock_init(&tunables->target_loads_lock);
+ spin_lock_init(&tunables->above_hispeed_delay_lock);
+
+ policy->governor_data = ipolicy;
+
+ ret = kobject_init_and_add(&tunables->attr_set.kobj,
+ &interactive_tunables_ktype,
+ get_governor_parent_kobj(policy), "%s",
+ interactive_gov.gov.name);
+ if (ret)
+ goto fail;
+
+ /* One time initialization for governor */
+ if (!interactive_gov.usage_count++) {
+ idle_notifier_register(&cpufreq_interactive_idle_nb);
+ cpufreq_register_notifier(&cpufreq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ }
+
+ out:
+ mutex_unlock(&global_tunables_lock);
+ return 0;
+
+ fail:
+ policy->governor_data = NULL;
+ interactive_tunables_free(tunables);
+
+ free_int_policy:
+ mutex_unlock(&global_tunables_lock);
+
+ interactive_policy_free(ipolicy);
+ pr_err("governor initialization failed (%d)\n", ret);
+
+ return ret;
+}
+
+void cpufreq_interactive_exit(struct cpufreq_policy *policy)
+{
+ struct interactive_policy *ipolicy = policy->governor_data;
+ struct interactive_tunables *tunables = ipolicy->tunables;
+ unsigned int count;
+
+ mutex_lock(&global_tunables_lock);
+
+ /* Last policy using the governor ? */
+ if (!--interactive_gov.usage_count) {
+ cpufreq_unregister_notifier(&cpufreq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ idle_notifier_unregister(&cpufreq_interactive_idle_nb);
+ }
+
+ count = gov_attr_set_put(&tunables->attr_set, &ipolicy->tunables_hook);
+ policy->governor_data = NULL;
+ if (!count)
+ interactive_tunables_free(tunables);
+
+ mutex_unlock(&global_tunables_lock);
+
+ interactive_policy_free(ipolicy);
+}
+
+int cpufreq_interactive_start(struct cpufreq_policy *policy)
+{
+ struct interactive_policy *ipolicy = policy->governor_data;
+ struct interactive_cpu *icpu;
+ unsigned int cpu;
+
+ for_each_cpu(cpu, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, cpu);
+
+ icpu->target_freq = policy->cur;
+ icpu->floor_freq = icpu->target_freq;
+ icpu->pol_floor_val_time = ktime_to_us(ktime_get());
+ icpu->loc_floor_val_time = icpu->pol_floor_val_time;
+ icpu->pol_hispeed_val_time = icpu->pol_floor_val_time;
+ icpu->loc_hispeed_val_time = icpu->pol_floor_val_time;
+
+ down_write(&icpu->enable_sem);
+ icpu->ipolicy = ipolicy;
+ up_write(&icpu->enable_sem);
+
+ slack_timer_resched(icpu, cpu, false);
+ }
+
+ gov_set_update_util(ipolicy);
+ return 0;
+}
+
+void cpufreq_interactive_stop(struct cpufreq_policy *policy)
+{
+ struct interactive_policy *ipolicy = policy->governor_data;
+ struct interactive_cpu *icpu;
+ unsigned int cpu;
+
+ gov_clear_update_util(ipolicy->policy);
+
+ for_each_cpu(cpu, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, cpu);
+
+ icpu_cancel_work(icpu);
+
+ down_write(&icpu->enable_sem);
+ icpu->ipolicy = NULL;
+ up_write(&icpu->enable_sem);
+ }
+}
+
+void cpufreq_interactive_limits(struct cpufreq_policy *policy)
+{
+ struct interactive_cpu *icpu;
+ unsigned int cpu;
+ unsigned long flags;
+
+ cpufreq_policy_apply_limits(policy);
+
+ for_each_cpu(cpu, policy->cpus) {
+ icpu = &per_cpu(interactive_cpu, cpu);
+
+ spin_lock_irqsave(&icpu->target_freq_lock, flags);
+
+ if (policy->max < icpu->target_freq)
+ icpu->target_freq = policy->max;
+ else if (policy->min > icpu->target_freq)
+ icpu->target_freq = policy->min;
+
+ spin_unlock_irqrestore(&icpu->target_freq_lock, flags);
+ }
+}
+
+static struct interactive_governor interactive_gov = {
+ .gov = {
+ .name = "interactive",
+ .max_transition_latency = TRANSITION_LATENCY_LIMIT,
+ .owner = THIS_MODULE,
+ .init = cpufreq_interactive_init,
+ .exit = cpufreq_interactive_exit,
+ .start = cpufreq_interactive_start,
+ .stop = cpufreq_interactive_stop,
+ .limits = cpufreq_interactive_limits,
+ }
+};
+
+static void cpufreq_interactive_nop_timer(unsigned long data)
+{
+ /*
+ * The purpose of slack-timer is to wake up the CPU from IDLE, in order
+ * to decrease its frequency if it is not set to minimum already.
+ *
+ * This is important for platforms where CPU with higher frequencies
+ * consume higher power even at IDLE.
+ */
+}
+
+static int __init cpufreq_interactive_gov_init(void)
+{
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+ struct interactive_cpu *icpu;
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ icpu = &per_cpu(interactive_cpu, cpu);
+
+ init_irq_work(&icpu->irq_work, irq_work);
+ spin_lock_init(&icpu->load_lock);
+ spin_lock_init(&icpu->target_freq_lock);
+ init_rwsem(&icpu->enable_sem);
+
+ /* Initialize per-cpu slack-timer */
+ init_timer_pinned(&icpu->slack_timer);
+ icpu->slack_timer.function = cpufreq_interactive_nop_timer;
+ }
+
+ spin_lock_init(&speedchange_cpumask_lock);
+ speedchange_task = kthread_create(cpufreq_interactive_speedchange_task,
+ NULL, "cfinteractive");
+ if (IS_ERR(speedchange_task))
+ return PTR_ERR(speedchange_task);
+
+ sched_setscheduler_nocheck(speedchange_task, SCHED_FIFO, ¶m);
+ get_task_struct(speedchange_task);
+
+ /* wake up so the thread does not look hung to the freezer */
+ wake_up_process(speedchange_task);
+
+ return cpufreq_register_governor(CPU_FREQ_GOV_INTERACTIVE);
+}
+
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return CPU_FREQ_GOV_INTERACTIVE;
+}
+
+fs_initcall(cpufreq_interactive_gov_init);
+#else
+module_init(cpufreq_interactive_gov_init);
+#endif
+
+static void __exit cpufreq_interactive_gov_exit(void)
+{
+ cpufreq_unregister_governor(CPU_FREQ_GOV_INTERACTIVE);
+ kthread_stop(speedchange_task);
+ put_task_struct(speedchange_task);
+}
+module_exit(cpufreq_interactive_gov_exit);
+
+MODULE_AUTHOR("Mike Chan <mike@android.com>");
+MODULE_DESCRIPTION("'cpufreq_interactive' - A dynamic cpufreq governor for Latency sensitive workloads");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index dafb679..399428e 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -22,7 +22,10 @@ static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy)
__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
}
-static struct cpufreq_governor cpufreq_gov_performance = {
+#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_performance = {
.name = "performance",
.owner = THIS_MODULE,
.limits = cpufreq_gov_performance_limits,
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 78a6510..5daa500 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -22,7 +22,10 @@ static void cpufreq_gov_powersave_limits(struct cpufreq_policy *policy)
__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
}
-static struct cpufreq_governor cpufreq_gov_powersave = {
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_powersave = {
.name = "powersave",
.limits = cpufreq_gov_powersave_limits,
.owner = THIS_MODULE,
diff --git a/drivers/cpufreq/cpufreq_times.c b/drivers/cpufreq/cpufreq_times.c
new file mode 100644
index 0000000..f4574e9
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_times.c
@@ -0,0 +1,633 @@
+/* drivers/cpufreq/cpufreq_times.c
+ *
+ * Copyright (C) 2018 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/cpufreq_times.h>
+#include <linux/cputime.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+
+#define UID_HASH_BITS 10
+
+static DECLARE_HASHTABLE(uid_hash_table, UID_HASH_BITS);
+
+static DEFINE_SPINLOCK(task_time_in_state_lock); /* task->time_in_state */
+static DEFINE_SPINLOCK(uid_lock); /* uid_hash_table */
+
+struct concurrent_times {
+ atomic64_t active[NR_CPUS];
+ atomic64_t policy[NR_CPUS];
+};
+
+struct uid_entry {
+ uid_t uid;
+ unsigned int max_state;
+ struct hlist_node hash;
+ struct rcu_head rcu;
+ struct concurrent_times *concurrent_times;
+ u64 time_in_state[0];
+};
+
+/**
+ * struct cpu_freqs - per-cpu frequency information
+ * @offset: start of these freqs' stats in task time_in_state array
+ * @max_state: number of entries in freq_table
+ * @last_index: index in freq_table of last frequency switched to
+ * @freq_table: list of available frequencies
+ */
+struct cpu_freqs {
+ unsigned int offset;
+ unsigned int max_state;
+ unsigned int last_index;
+ unsigned int freq_table[0];
+};
+
+static struct cpu_freqs *all_freqs[NR_CPUS];
+
+static unsigned int next_offset;
+
+
+/* Caller must hold rcu_read_lock() */
+static struct uid_entry *find_uid_entry_rcu(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+
+ hash_for_each_possible_rcu(uid_hash_table, uid_entry, hash, uid) {
+ if (uid_entry->uid == uid)
+ return uid_entry;
+ }
+ return NULL;
+}
+
+/* Caller must hold uid lock */
+static struct uid_entry *find_uid_entry_locked(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+
+ hash_for_each_possible(uid_hash_table, uid_entry, hash, uid) {
+ if (uid_entry->uid == uid)
+ return uid_entry;
+ }
+ return NULL;
+}
+
+/* Caller must hold uid lock */
+static struct uid_entry *find_or_register_uid_locked(uid_t uid)
+{
+ struct uid_entry *uid_entry, *temp;
+ struct concurrent_times *times;
+ unsigned int max_state = READ_ONCE(next_offset);
+ size_t alloc_size = sizeof(*uid_entry) + max_state *
+ sizeof(uid_entry->time_in_state[0]);
+
+ uid_entry = find_uid_entry_locked(uid);
+ if (uid_entry) {
+ if (uid_entry->max_state == max_state)
+ return uid_entry;
+ /* uid_entry->time_in_state is too small to track all freqs, so
+ * expand it.
+ */
+ temp = __krealloc(uid_entry, alloc_size, GFP_ATOMIC);
+ if (!temp)
+ return uid_entry;
+ temp->max_state = max_state;
+ memset(temp->time_in_state + uid_entry->max_state, 0,
+ (max_state - uid_entry->max_state) *
+ sizeof(uid_entry->time_in_state[0]));
+ if (temp != uid_entry) {
+ hlist_replace_rcu(&uid_entry->hash, &temp->hash);
+ kfree_rcu(uid_entry, rcu);
+ }
+ return temp;
+ }
+
+ uid_entry = kzalloc(alloc_size, GFP_ATOMIC);
+ if (!uid_entry)
+ return NULL;
+ times = kzalloc(sizeof(*times), GFP_ATOMIC);
+ if (!times) {
+ kfree(uid_entry);
+ return NULL;
+ }
+
+ uid_entry->uid = uid;
+ uid_entry->max_state = max_state;
+ uid_entry->concurrent_times = times;
+
+ hash_add_rcu(uid_hash_table, &uid_entry->hash, uid);
+
+ return uid_entry;
+}
+
+static int single_uid_time_in_state_show(struct seq_file *m, void *ptr)
+{
+ struct uid_entry *uid_entry;
+ unsigned int i;
+ uid_t uid = from_kuid_munged(current_user_ns(), *(kuid_t *)m->private);
+
+ if (uid == overflowuid)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ uid_entry = find_uid_entry_rcu(uid);
+ if (!uid_entry) {
+ rcu_read_unlock();
+ return 0;
+ }
+
+ for (i = 0; i < uid_entry->max_state; ++i) {
+ u64 time = cputime_to_clock_t(uid_entry->time_in_state[i]);
+ seq_write(m, &time, sizeof(time));
+ }
+
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static void *uid_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ if (*pos >= HASH_SIZE(uid_hash_table))
+ return NULL;
+
+ return &uid_hash_table[*pos];
+}
+
+static void *uid_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ do {
+ (*pos)++;
+
+ if (*pos >= HASH_SIZE(uid_hash_table))
+ return NULL;
+ } while (hlist_empty(&uid_hash_table[*pos]));
+
+ return &uid_hash_table[*pos];
+}
+
+static void uid_seq_stop(struct seq_file *seq, void *v) { }
+
+static int uid_time_in_state_seq_show(struct seq_file *m, void *v)
+{
+ struct uid_entry *uid_entry;
+ struct cpu_freqs *freqs, *last_freqs = NULL;
+ int i, cpu;
+
+ if (v == uid_hash_table) {
+ seq_puts(m, "uid:");
+ for_each_possible_cpu(cpu) {
+ freqs = all_freqs[cpu];
+ if (!freqs || freqs == last_freqs)
+ continue;
+ last_freqs = freqs;
+ for (i = 0; i < freqs->max_state; i++) {
+ seq_put_decimal_ull(m, " ",
+ freqs->freq_table[i]);
+ }
+ }
+ seq_putc(m, '\n');
+ }
+
+ rcu_read_lock();
+
+ hlist_for_each_entry_rcu(uid_entry, (struct hlist_head *)v, hash) {
+ if (uid_entry->max_state) {
+ seq_put_decimal_ull(m, "", uid_entry->uid);
+ seq_putc(m, ':');
+ }
+ for (i = 0; i < uid_entry->max_state; ++i) {
+ u64 time =
+ cputime_to_clock_t(uid_entry->time_in_state[i]);
+ seq_put_decimal_ull(m, " ", time);
+ }
+ if (uid_entry->max_state)
+ seq_putc(m, '\n');
+ }
+
+ rcu_read_unlock();
+ return 0;
+}
+
+static int concurrent_time_seq_show(struct seq_file *m, void *v,
+ atomic64_t *(*get_times)(struct concurrent_times *))
+{
+ struct uid_entry *uid_entry;
+ int i, num_possible_cpus = num_possible_cpus();
+
+ rcu_read_lock();
+
+ hlist_for_each_entry_rcu(uid_entry, (struct hlist_head *)v, hash) {
+ atomic64_t *times = get_times(uid_entry->concurrent_times);
+
+ seq_put_decimal_ull(m, "", (u64)uid_entry->uid);
+ seq_putc(m, ':');
+
+ for (i = 0; i < num_possible_cpus; ++i) {
+ u64 time = cputime_to_clock_t(atomic64_read(×[i]));
+
+ seq_put_decimal_ull(m, " ", time);
+ }
+ seq_putc(m, '\n');
+ }
+
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static inline atomic64_t *get_active_times(struct concurrent_times *times)
+{
+ return times->active;
+}
+
+static int concurrent_active_time_seq_show(struct seq_file *m, void *v)
+{
+ if (v == uid_hash_table) {
+ seq_put_decimal_ull(m, "cpus: ", num_possible_cpus());
+ seq_putc(m, '\n');
+ }
+
+ return concurrent_time_seq_show(m, v, get_active_times);
+}
+
+static inline atomic64_t *get_policy_times(struct concurrent_times *times)
+{
+ return times->policy;
+}
+
+static int concurrent_policy_time_seq_show(struct seq_file *m, void *v)
+{
+ int i;
+ struct cpu_freqs *freqs, *last_freqs = NULL;
+
+ if (v == uid_hash_table) {
+ int cnt = 0;
+
+ for_each_possible_cpu(i) {
+ freqs = all_freqs[i];
+ if (!freqs)
+ continue;
+ if (freqs != last_freqs) {
+ if (last_freqs) {
+ seq_put_decimal_ull(m, ": ", cnt);
+ seq_putc(m, ' ');
+ cnt = 0;
+ }
+ seq_put_decimal_ull(m, "policy", i);
+
+ last_freqs = freqs;
+ }
+ cnt++;
+ }
+ if (last_freqs) {
+ seq_put_decimal_ull(m, ": ", cnt);
+ seq_putc(m, '\n');
+ }
+ }
+
+ return concurrent_time_seq_show(m, v, get_policy_times);
+}
+
+void cpufreq_task_times_init(struct task_struct *p)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&task_time_in_state_lock, flags);
+ p->time_in_state = NULL;
+ spin_unlock_irqrestore(&task_time_in_state_lock, flags);
+ p->max_state = 0;
+}
+
+void cpufreq_task_times_alloc(struct task_struct *p)
+{
+ void *temp;
+ unsigned long flags;
+ unsigned int max_state = READ_ONCE(next_offset);
+
+ /* We use one array to avoid multiple allocs per task */
+ temp = kcalloc(max_state, sizeof(p->time_in_state[0]), GFP_ATOMIC);
+ if (!temp)
+ return;
+
+ spin_lock_irqsave(&task_time_in_state_lock, flags);
+ p->time_in_state = temp;
+ spin_unlock_irqrestore(&task_time_in_state_lock, flags);
+ p->max_state = max_state;
+}
+
+/* Caller must hold task_time_in_state_lock */
+static int cpufreq_task_times_realloc_locked(struct task_struct *p)
+{
+ void *temp;
+ unsigned int max_state = READ_ONCE(next_offset);
+
+ temp = krealloc(p->time_in_state, max_state * sizeof(u64), GFP_ATOMIC);
+ if (!temp)
+ return -ENOMEM;
+ p->time_in_state = temp;
+ memset(p->time_in_state + p->max_state, 0,
+ (max_state - p->max_state) * sizeof(u64));
+ p->max_state = max_state;
+ return 0;
+}
+
+void cpufreq_task_times_exit(struct task_struct *p)
+{
+ unsigned long flags;
+ void *temp;
+
+ if (!p->time_in_state)
+ return;
+
+ spin_lock_irqsave(&task_time_in_state_lock, flags);
+ temp = p->time_in_state;
+ p->time_in_state = NULL;
+ spin_unlock_irqrestore(&task_time_in_state_lock, flags);
+ kfree(temp);
+}
+
+int proc_time_in_state_show(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *p)
+{
+ unsigned int cpu, i;
+ cputime_t cputime;
+ unsigned long flags;
+ struct cpu_freqs *freqs;
+ struct cpu_freqs *last_freqs = NULL;
+
+ spin_lock_irqsave(&task_time_in_state_lock, flags);
+ for_each_possible_cpu(cpu) {
+ freqs = all_freqs[cpu];
+ if (!freqs || freqs == last_freqs)
+ continue;
+ last_freqs = freqs;
+
+ seq_printf(m, "cpu%u\n", cpu);
+ for (i = 0; i < freqs->max_state; i++) {
+ cputime = 0;
+ if (freqs->offset + i < p->max_state &&
+ p->time_in_state)
+ cputime = p->time_in_state[freqs->offset + i];
+ seq_printf(m, "%u %lu\n", freqs->freq_table[i],
+ (unsigned long)cputime_to_clock_t(cputime));
+ }
+ }
+ spin_unlock_irqrestore(&task_time_in_state_lock, flags);
+ return 0;
+}
+
+void cpufreq_acct_update_power(struct task_struct *p, cputime_t cputime)
+{
+ unsigned long flags;
+ unsigned int state;
+ unsigned int active_cpu_cnt = 0;
+ unsigned int policy_cpu_cnt = 0;
+ unsigned int policy_first_cpu;
+ struct uid_entry *uid_entry;
+ struct cpu_freqs *freqs = all_freqs[task_cpu(p)];
+ struct cpufreq_policy *policy;
+ uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p));
+ int cpu = 0;
+
+ if (!freqs || is_idle_task(p) || p->flags & PF_EXITING)
+ return;
+
+ state = freqs->offset + READ_ONCE(freqs->last_index);
+
+ spin_lock_irqsave(&task_time_in_state_lock, flags);
+ if ((state < p->max_state || !cpufreq_task_times_realloc_locked(p)) &&
+ p->time_in_state)
+ p->time_in_state[state] += cputime;
+ spin_unlock_irqrestore(&task_time_in_state_lock, flags);
+
+ spin_lock_irqsave(&uid_lock, flags);
+ uid_entry = find_or_register_uid_locked(uid);
+ if (uid_entry && state < uid_entry->max_state)
+ uid_entry->time_in_state[state] += cputime;
+ spin_unlock_irqrestore(&uid_lock, flags);
+
+ rcu_read_lock();
+ uid_entry = find_uid_entry_rcu(uid);
+ if (!uid_entry) {
+ rcu_read_unlock();
+ return;
+ }
+
+ for_each_possible_cpu(cpu)
+ if (!idle_cpu(cpu))
+ ++active_cpu_cnt;
+
+ atomic64_add(cputime,
+ &uid_entry->concurrent_times->active[active_cpu_cnt - 1]);
+
+ policy = cpufreq_cpu_get(task_cpu(p));
+ if (!policy) {
+ /*
+ * This CPU may have just come up and not have a cpufreq policy
+ * yet.
+ */
+ rcu_read_unlock();
+ return;
+ }
+
+ for_each_cpu(cpu, policy->related_cpus)
+ if (!idle_cpu(cpu))
+ ++policy_cpu_cnt;
+
+ policy_first_cpu = cpumask_first(policy->related_cpus);
+ cpufreq_cpu_put(policy);
+
+ atomic64_add(cputime,
+ &uid_entry->concurrent_times->policy[policy_first_cpu +
+ policy_cpu_cnt - 1]);
+ rcu_read_unlock();
+}
+
+static int cpufreq_times_get_index(struct cpu_freqs *freqs, unsigned int freq)
+{
+ int index;
+ for (index = 0; index < freqs->max_state; ++index) {
+ if (freqs->freq_table[index] == freq)
+ return index;
+ }
+ return -1;
+}
+
+void cpufreq_times_create_policy(struct cpufreq_policy *policy)
+{
+ int cpu, index = 0;
+ unsigned int count = 0;
+ struct cpufreq_frequency_table *pos, *table;
+ struct cpu_freqs *freqs;
+ void *tmp;
+
+ if (all_freqs[policy->cpu])
+ return;
+
+ table = policy->freq_table;
+ if (!table)
+ return;
+
+ cpufreq_for_each_valid_entry(pos, table)
+ count++;
+
+ tmp = kzalloc(sizeof(*freqs) + sizeof(freqs->freq_table[0]) * count,
+ GFP_KERNEL);
+ if (!tmp)
+ return;
+
+ freqs = tmp;
+ freqs->max_state = count;
+
+ cpufreq_for_each_valid_entry(pos, table)
+ freqs->freq_table[index++] = pos->frequency;
+
+ index = cpufreq_times_get_index(freqs, policy->cur);
+ if (index >= 0)
+ WRITE_ONCE(freqs->last_index, index);
+
+ freqs->offset = next_offset;
+ WRITE_ONCE(next_offset, freqs->offset + count);
+ for_each_cpu(cpu, policy->related_cpus)
+ all_freqs[cpu] = freqs;
+}
+
+static void uid_entry_reclaim(struct rcu_head *rcu)
+{
+ struct uid_entry *uid_entry = container_of(rcu, struct uid_entry, rcu);
+
+ kfree(uid_entry->concurrent_times);
+ kfree(uid_entry);
+}
+
+void cpufreq_task_times_remove_uids(uid_t uid_start, uid_t uid_end)
+{
+ struct uid_entry *uid_entry;
+ struct hlist_node *tmp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&uid_lock, flags);
+
+ for (; uid_start <= uid_end; uid_start++) {
+ hash_for_each_possible_safe(uid_hash_table, uid_entry, tmp,
+ hash, uid_start) {
+ if (uid_start == uid_entry->uid) {
+ hash_del_rcu(&uid_entry->hash);
+ call_rcu(&uid_entry->rcu, uid_entry_reclaim);
+ }
+ }
+ }
+
+ spin_unlock_irqrestore(&uid_lock, flags);
+}
+
+void cpufreq_times_record_transition(struct cpufreq_policy *policy,
+ unsigned int new_freq)
+{
+ int index;
+ struct cpu_freqs *freqs = all_freqs[policy->cpu];
+ if (!freqs)
+ return;
+
+ index = cpufreq_times_get_index(freqs, new_freq);
+ if (index >= 0)
+ WRITE_ONCE(freqs->last_index, index);
+}
+
+static const struct seq_operations uid_time_in_state_seq_ops = {
+ .start = uid_seq_start,
+ .next = uid_seq_next,
+ .stop = uid_seq_stop,
+ .show = uid_time_in_state_seq_show,
+};
+
+static int uid_time_in_state_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &uid_time_in_state_seq_ops);
+}
+
+int single_uid_time_in_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, single_uid_time_in_state_show,
+ &(inode->i_uid));
+}
+
+static const struct file_operations uid_time_in_state_fops = {
+ .open = uid_time_in_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct seq_operations concurrent_active_time_seq_ops = {
+ .start = uid_seq_start,
+ .next = uid_seq_next,
+ .stop = uid_seq_stop,
+ .show = concurrent_active_time_seq_show,
+};
+
+static int concurrent_active_time_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &concurrent_active_time_seq_ops);
+}
+
+static const struct file_operations concurrent_active_time_fops = {
+ .open = concurrent_active_time_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct seq_operations concurrent_policy_time_seq_ops = {
+ .start = uid_seq_start,
+ .next = uid_seq_next,
+ .stop = uid_seq_stop,
+ .show = concurrent_policy_time_seq_show,
+};
+
+static int concurrent_policy_time_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &concurrent_policy_time_seq_ops);
+}
+
+static const struct file_operations concurrent_policy_time_fops = {
+ .open = concurrent_policy_time_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init cpufreq_times_init(void)
+{
+ proc_create_data("uid_time_in_state", 0444, NULL,
+ &uid_time_in_state_fops, NULL);
+
+ proc_create_data("uid_concurrent_active_time", 0444, NULL,
+ &concurrent_active_time_fops, NULL);
+
+ proc_create_data("uid_concurrent_policy_time", 0444, NULL,
+ &concurrent_policy_time_fops, NULL);
+
+ return 0;
+}
+
+early_initcall(cpufreq_times_init);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index bd897e3..765166d 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -118,7 +118,10 @@ static void cpufreq_userspace_policy_limits(struct cpufreq_policy *policy)
mutex_unlock(&userspace_mutex);
}
-static struct cpufreq_governor cpufreq_gov_userspace = {
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_userspace = {
.name = "userspace",
.init = cpufreq_userspace_policy_init,
.exit = cpufreq_userspace_policy_exit,
diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm
index 21340e0..f521448 100644
--- a/drivers/cpuidle/Kconfig.arm
+++ b/drivers/cpuidle/Kconfig.arm
@@ -4,6 +4,7 @@
config ARM_CPUIDLE
bool "Generic ARM/ARM64 CPU idle Driver"
select DT_IDLE_STATES
+ select CPU_IDLE_MULTIPLE_DRIVERS
help
Select this to enable generic cpuidle driver for ARM.
It provides a generic idle driver whose idle states are configured
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index f440d38..f47c545 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -18,6 +18,7 @@
#include <linux/module.h>
#include <linux/of.h>
#include <linux/slab.h>
+#include <linux/topology.h>
#include <asm/cpuidle.h>
@@ -44,7 +45,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev,
return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, idx);
}
-static struct cpuidle_driver arm_idle_driver = {
+static struct cpuidle_driver arm_idle_driver __initdata = {
.name = "arm_idle",
.owner = THIS_MODULE,
/*
@@ -80,30 +81,42 @@ static const struct of_device_id arm_idle_state_match[] __initconst = {
static int __init arm_idle_init(void)
{
int cpu, ret;
- struct cpuidle_driver *drv = &arm_idle_driver;
+ struct cpuidle_driver *drv;
struct cpuidle_device *dev;
- /*
- * Initialize idle states data, starting at index 1.
- * This driver is DT only, if no DT idle states are detected (ret == 0)
- * let the driver initialization fail accordingly since there is no
- * reason to initialize the idle driver if only wfi is supported.
- */
- ret = dt_init_idle_driver(drv, arm_idle_state_match, 1);
- if (ret <= 0)
- return ret ? : -ENODEV;
-
- ret = cpuidle_register_driver(drv);
- if (ret) {
- pr_err("Failed to register cpuidle driver\n");
- return ret;
- }
-
- /*
- * Call arch CPU operations in order to initialize
- * idle states suspend back-end specific data
- */
for_each_possible_cpu(cpu) {
+
+ drv = kmemdup(&arm_idle_driver, sizeof(*drv), GFP_KERNEL);
+ if (!drv) {
+ ret = -ENOMEM;
+ goto out_fail;
+ }
+
+ drv->cpumask = (struct cpumask *)cpumask_of(cpu);
+
+ /*
+ * Initialize idle states data, starting at index 1. This
+ * driver is DT only, if no DT idle states are detected (ret
+ * == 0) let the driver initialization fail accordingly since
+ * there is no reason to initialize the idle driver if only
+ * wfi is supported.
+ */
+ ret = dt_init_idle_driver(drv, arm_idle_state_match, 1);
+ if (ret <= 0) {
+ ret = ret ? : -ENODEV;
+ goto out_kfree_drv;
+ }
+
+ ret = cpuidle_register_driver(drv);
+ if (ret) {
+ pr_err("Failed to register cpuidle driver\n");
+ goto out_kfree_drv;
+ }
+
+ /*
+ * Call arch CPU operations in order to initialize
+ * idle states suspend back-end specific data
+ */
ret = arm_cpuidle_init(cpu);
/*
@@ -115,14 +128,14 @@ static int __init arm_idle_init(void)
if (ret) {
pr_err("CPU %d failed to init idle CPU ops\n", cpu);
- goto out_fail;
+ goto out_unregister_drv;
}
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev) {
pr_err("Failed to allocate cpuidle device\n");
ret = -ENOMEM;
- goto out_fail;
+ goto out_unregister_drv;
}
dev->cpu = cpu;
@@ -130,21 +143,28 @@ static int __init arm_idle_init(void)
if (ret) {
pr_err("Failed to register cpuidle device for CPU %d\n",
cpu);
- kfree(dev);
- goto out_fail;
+ goto out_kfree_dev;
}
}
return 0;
+
+out_kfree_dev:
+ kfree(dev);
+out_unregister_drv:
+ cpuidle_unregister_driver(drv);
+out_kfree_drv:
+ kfree(drv);
out_fail:
while (--cpu >= 0) {
dev = per_cpu(cpuidle_devices, cpu);
+ drv = cpuidle_get_cpu_driver(dev);
cpuidle_unregister_device(dev);
+ cpuidle_unregister_driver(drv);
kfree(dev);
+ kfree(drv);
}
- cpuidle_unregister_driver(drv);
-
return ret;
}
device_initcall(arm_idle_init);
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 35237c8..439f460 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -193,7 +193,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
}
/* Take note of the planned idle state. */
- sched_idle_set_state(target_state);
+ sched_idle_set_state(target_state, index);
trace_cpu_idle_rcuidle(index, dev->cpu);
time_start = ns_to_ktime(local_clock());
@@ -206,7 +206,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
/* The cpu is no longer idle or about to enter idle. */
- sched_idle_set_state(NULL);
+ sched_idle_set_state(NULL, -1);
if (broadcast) {
if (WARN_ON_ONCE(!irqs_disabled()))
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 03d38c2..72bc6e6 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -18,6 +18,7 @@
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/math64.h>
#include <linux/module.h>
@@ -130,10 +131,6 @@ struct menu_device {
int interval_ptr;
};
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
static inline int get_loadavg(unsigned long load)
{
return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;
@@ -178,7 +175,12 @@ static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned lo
/* for higher loadavg, we are more reluctant */
- mult += 2 * get_loadavg(load);
+ /*
+ * this doesn't work as intended - it is almost always 0, but can
+ * sometimes, depending on workload, spike very high into the hundreds
+ * even when the average cpu load is under 10%.
+ */
+ /* mult += 2 * get_loadavg(); */
/* for IO wait tasks (per cpu!) we add 5x each */
mult += 10 * nr_iowaiters;
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index 2585821..bf4f348 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -3,7 +3,6 @@
config SYNC_FILE
bool "Explicit Synchronization Framework"
default n
- select ANON_INODES
select DMA_SHARED_BUFFER
---help---
The Sync File Framework adds explicit syncronization via
diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c
index 04bf298..883b3be 100644
--- a/drivers/dma-buf/fence.c
+++ b/drivers/dma-buf/fence.c
@@ -68,6 +68,8 @@ int fence_signal_locked(struct fence *fence)
struct fence_cb *cur, *tmp;
int ret = 0;
+ lockdep_assert_held(fence->lock);
+
if (WARN_ON(!fence))
return -EINVAL;
@@ -159,9 +161,6 @@ fence_wait_timeout(struct fence *fence, bool intr, signed long timeout)
if (WARN_ON(timeout < 0))
return -EINVAL;
- if (timeout == 0)
- return fence_is_signaled(fence);
-
trace_fence_wait_start(fence);
ret = fence->ops->wait(fence, intr, timeout);
trace_fence_wait_end(fence);
@@ -329,8 +328,12 @@ fence_remove_callback(struct fence *fence, struct fence_cb *cb)
spin_lock_irqsave(fence->lock, flags);
ret = !list_empty(&cb->node);
- if (ret)
+ if (ret) {
list_del_init(&cb->node);
+ if (list_empty(&fence->cb_list))
+ if (fence->ops->disable_signaling)
+ fence->ops->disable_signaling(fence);
+ }
spin_unlock_irqrestore(fence->lock, flags);
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 723d8af..82f35a4 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -280,18 +280,24 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj,
unsigned *pshared_count,
struct fence ***pshared)
{
- unsigned shared_count = 0;
- unsigned retry = 1;
- struct fence **shared = NULL, *fence_excl = NULL;
- int ret = 0;
+ struct fence **shared = NULL;
+ struct fence *fence_excl;
+ unsigned int shared_count;
+ int ret = 1;
- while (retry) {
+ do {
struct reservation_object_list *fobj;
unsigned seq;
+ unsigned int i;
- seq = read_seqcount_begin(&obj->seq);
+ shared_count = i = 0;
rcu_read_lock();
+ seq = read_seqcount_begin(&obj->seq);
+
+ fence_excl = rcu_dereference(obj->fence_excl);
+ if (fence_excl && !fence_get_rcu(fence_excl))
+ goto unlock;
fobj = rcu_dereference(obj->fence);
if (fobj) {
@@ -309,52 +315,37 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj,
}
ret = -ENOMEM;
- shared_count = 0;
break;
}
shared = nshared;
- memcpy(shared, fobj->shared, sz);
shared_count = fobj->shared_count;
- } else
- shared_count = 0;
- fence_excl = rcu_dereference(obj->fence_excl);
-
- retry = read_seqcount_retry(&obj->seq, seq);
- if (retry)
- goto unlock;
-
- if (!fence_excl || fence_get_rcu(fence_excl)) {
- unsigned i;
for (i = 0; i < shared_count; ++i) {
- if (fence_get_rcu(shared[i]))
- continue;
-
- /* uh oh, refcount failed, abort and retry */
- while (i--)
- fence_put(shared[i]);
-
- if (fence_excl) {
- fence_put(fence_excl);
- fence_excl = NULL;
- }
-
- retry = 1;
- break;
+ shared[i] = rcu_dereference(fobj->shared[i]);
+ if (!fence_get_rcu(shared[i]))
+ break;
}
- } else
- retry = 1;
+ }
+ if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) {
+ while (i--)
+ fence_put(shared[i]);
+ fence_put(fence_excl);
+ goto unlock;
+ }
+
+ ret = 0;
unlock:
rcu_read_unlock();
- }
- *pshared_count = shared_count;
- if (shared_count)
- *pshared = shared;
- else {
- *pshared = NULL;
+ } while (ret);
+
+ if (!shared_count) {
kfree(shared);
+ shared = NULL;
}
+
+ *pshared_count = shared_count;
+ *pshared = shared;
*pfence_excl = fence_excl;
return ret;
@@ -379,10 +370,7 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
{
struct fence *fence;
unsigned seq, shared_count, i = 0;
- long ret = timeout;
-
- if (!timeout)
- return reservation_object_test_signaled_rcu(obj, wait_all);
+ long ret = timeout ? timeout : 1;
retry:
fence = NULL;
@@ -397,9 +385,6 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
if (fobj)
shared_count = fobj->shared_count;
- if (read_seqcount_retry(&obj->seq, seq))
- goto unlock_retry;
-
for (i = 0; i < shared_count; ++i) {
struct fence *lfence = rcu_dereference(fobj->shared[i]);
@@ -422,9 +407,6 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
if (!shared_count) {
struct fence *fence_excl = rcu_dereference(obj->fence_excl);
- if (read_seqcount_retry(&obj->seq, seq))
- goto unlock_retry;
-
if (fence_excl &&
!test_bit(FENCE_FLAG_SIGNALED_BIT, &fence_excl->flags)) {
if (!fence_get_rcu(fence_excl))
@@ -439,6 +421,11 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
rcu_read_unlock();
if (fence) {
+ if (read_seqcount_retry(&obj->seq, seq)) {
+ fence_put(fence);
+ goto retry;
+ }
+
ret = fence_wait_timeout(fence, intr, ret);
fence_put(fence);
if (ret > 0 && wait_all && (i + 1 < shared_count))
@@ -484,12 +471,13 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj,
bool test_all)
{
unsigned seq, shared_count;
- int ret = true;
+ int ret;
+ rcu_read_lock();
retry:
+ ret = true;
shared_count = 0;
seq = read_seqcount_begin(&obj->seq);
- rcu_read_lock();
if (test_all) {
unsigned i;
@@ -500,46 +488,35 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj,
if (fobj)
shared_count = fobj->shared_count;
- if (read_seqcount_retry(&obj->seq, seq))
- goto unlock_retry;
-
for (i = 0; i < shared_count; ++i) {
struct fence *fence = rcu_dereference(fobj->shared[i]);
ret = reservation_object_test_signaled_single(fence);
if (ret < 0)
- goto unlock_retry;
+ goto retry;
else if (!ret)
break;
}
- /*
- * There could be a read_seqcount_retry here, but nothing cares
- * about whether it's the old or newer fence pointers that are
- * signaled. That race could still have happened after checking
- * read_seqcount_retry. If you care, use ww_mutex_lock.
- */
+ if (read_seqcount_retry(&obj->seq, seq))
+ goto retry;
}
if (!shared_count) {
struct fence *fence_excl = rcu_dereference(obj->fence_excl);
- if (read_seqcount_retry(&obj->seq, seq))
- goto unlock_retry;
-
if (fence_excl) {
ret = reservation_object_test_signaled_single(
fence_excl);
if (ret < 0)
- goto unlock_retry;
+ goto retry;
+
+ if (read_seqcount_retry(&obj->seq, seq))
+ goto retry;
}
}
rcu_read_unlock();
return ret;
-
-unlock_retry:
- rcu_read_unlock();
- goto retry;
}
EXPORT_SYMBOL_GPL(reservation_object_test_signaled_rcu);
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 4f35114..9dc86d3 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -169,6 +169,13 @@ static bool timeline_fence_enable_signaling(struct fence *fence)
return true;
}
+static void timeline_fence_disable_signaling(struct fence *fence)
+{
+ struct sync_pt *pt = container_of(fence, struct sync_pt, base);
+
+ list_del_init(&pt->link);
+}
+
static void timeline_fence_value_str(struct fence *fence,
char *str, int size)
{
@@ -187,6 +194,7 @@ static const struct fence_ops timeline_fence_ops = {
.get_driver_name = timeline_fence_get_driver_name,
.get_timeline_name = timeline_fence_get_timeline_name,
.enable_signaling = timeline_fence_enable_signaling,
+ .disable_signaling = timeline_fence_disable_signaling,
.signaled = timeline_fence_signaled,
.wait = fence_default_wait,
.release = timeline_fence_release,
@@ -360,8 +368,8 @@ static long sw_sync_ioctl_create_fence(struct sync_timeline *obj,
}
sync_file = sync_file_create(&pt->base);
+ fence_put(&pt->base);
if (!sync_file) {
- fence_put(&pt->base);
err = -ENOMEM;
goto err;
}
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 05d66d4..cb4629f 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -279,7 +279,7 @@ static void sync_file_free(struct kref *kref)
struct sync_file *sync_file = container_of(kref, struct sync_file,
kref);
- if (test_bit(POLL_ENABLED, &sync_file->fence->flags))
+ if (test_bit(POLL_ENABLED, &sync_file->flags))
fence_remove_callback(sync_file->fence, &sync_file->cb);
fence_put(sync_file->fence);
kfree(sync_file);
@@ -299,10 +299,10 @@ static unsigned int sync_file_poll(struct file *file, poll_table *wait)
poll_wait(file, &sync_file->wq, wait);
- if (!poll_does_not_wait(wait) &&
- !test_and_set_bit(POLL_ENABLED, &sync_file->fence->flags)) {
+ if (list_empty(&sync_file->cb.node) &&
+ !test_and_set_bit(POLL_ENABLED, &sync_file->flags)) {
if (fence_add_callback(sync_file->fence, &sync_file->cb,
- fence_check_cb_func) < 0)
+ fence_check_cb_func) < 0)
wake_up_all(&sync_file->wq);
}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index d596411..3a8dfff 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -50,7 +50,7 @@ unsigned int edac_mc_get_poll_msec(void)
return edac_mc_poll_msec;
}
-static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
+static int edac_set_poll_msec(const char *val, const struct kernel_param *kp)
{
unsigned int i;
int ret;
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 5f8543b..b0d3284 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -19,7 +19,8 @@
#ifdef CONFIG_EDAC_DEBUG
-static int edac_set_debug_level(const char *buf, struct kernel_param *kp)
+static int edac_set_debug_level(const char *buf,
+ const struct kernel_param *kp)
{
unsigned long val;
int ret;
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 310f8fe..f82d11a 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -19,7 +19,8 @@
KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \
$(call cc-option,-ffreestanding) \
- $(call cc-option,-fno-stack-protector)
+ $(call cc-option,-fno-stack-protector) \
+ $(DISABLE_LTO)
GCOV_PROFILE := n
KASAN_SANITIZE := n
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 5d097d6..74dbdce 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -12,7 +12,6 @@
menuconfig GPIOLIB
bool "GPIO Support"
- select ANON_INODES
help
This enables GPIO support through the generic GPIO library.
You only need to enable this, if you also want to enable
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 483059a..43cb33d 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -12,6 +12,7 @@
select I2C
select I2C_ALGOBIT
select DMA_SHARED_BUFFER
+ select SYNC_FILE
help
Kernel-level support for the Direct Rendering Infrastructure (DRI)
introduced in XFree86 4.0. If you say Y here, you need to select
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index dd6fff1..4e4043f 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -30,6 +30,7 @@
#include <drm/drm_atomic.h>
#include <drm/drm_mode.h>
#include <drm/drm_plane_helper.h>
+#include <linux/sync_file.h>
#include "drm_crtc_internal.h"
@@ -292,6 +293,23 @@ drm_atomic_get_crtc_state(struct drm_atomic_state *state,
}
EXPORT_SYMBOL(drm_atomic_get_crtc_state);
+static void set_out_fence_for_crtc(struct drm_atomic_state *state,
+ struct drm_crtc *crtc, s32 __user *fence_ptr)
+{
+ state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr;
+}
+
+static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
+ struct drm_crtc *crtc)
+{
+ s32 __user *fence_ptr;
+
+ fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr;
+ state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL;
+
+ return fence_ptr;
+}
+
/**
* drm_atomic_set_mode_for_crtc - set mode for CRTC
* @state: the CRTC whose incoming state to update
@@ -496,6 +514,16 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
&replaced);
state->color_mgmt_changed |= replaced;
return ret;
+ } else if (property == config->prop_out_fence_ptr) {
+ s32 __user *fence_ptr = u64_to_user_ptr(val);
+
+ if (!fence_ptr)
+ return 0;
+
+ if (put_user(-1, fence_ptr))
+ return -EFAULT;
+
+ set_out_fence_for_crtc(state->state, crtc, fence_ptr);
} else if (crtc->funcs->atomic_set_property)
return crtc->funcs->atomic_set_property(crtc, state, property, val);
else
@@ -538,6 +566,8 @@ drm_atomic_crtc_get_property(struct drm_crtc *crtc,
*val = (state->ctm) ? state->ctm->base.id : 0;
else if (property == config->gamma_lut_property)
*val = (state->gamma_lut) ? state->gamma_lut->base.id : 0;
+ else if (property == config->prop_out_fence_ptr)
+ *val = 0;
else if (crtc->funcs->atomic_get_property)
return crtc->funcs->atomic_get_property(crtc, state, property, val);
else
@@ -693,6 +723,17 @@ int drm_atomic_plane_set_property(struct drm_plane *plane,
drm_atomic_set_fb_for_plane(state, fb);
if (fb)
drm_framebuffer_unreference(fb);
+ } else if (property == config->prop_in_fence_fd) {
+ if (state->fence)
+ return -EINVAL;
+
+ if (U642I64(val) == -1)
+ return 0;
+
+ state->fence = sync_file_get_fence(val);
+ if (!state->fence)
+ return -EINVAL;
+
} else if (property == config->prop_crtc_id) {
struct drm_crtc *crtc = drm_crtc_find(dev, val);
return drm_atomic_set_crtc_for_plane(state, crtc);
@@ -752,6 +793,8 @@ drm_atomic_plane_get_property(struct drm_plane *plane,
if (property == config->prop_fb_id) {
*val = (state->fb) ? state->fb->base.id : 0;
+ } else if (property == config->prop_in_fence_fd) {
+ *val = -1;
} else if (property == config->prop_crtc_id) {
*val = (state->crtc) ? state->crtc->base.id : 0;
} else if (property == config->prop_crtc_x) {
@@ -1154,6 +1197,36 @@ drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state,
EXPORT_SYMBOL(drm_atomic_set_fb_for_plane);
/**
+ * drm_atomic_set_fence_for_plane - set fence for plane
+ * @plane_state: atomic state object for the plane
+ * @fence: fence to use for the plane
+ *
+ * Helper to setup the plane_state fence in case it is not set yet.
+ * By using this drivers doesn't need to worry if the user choose
+ * implicit or explicit fencing.
+ *
+ * This function will not set the fence to the state if it was set
+ * via explicit fencing interfaces on the atomic ioctl. It will
+ * all drope the reference to the fence as we not storing it
+ * anywhere.
+ *
+ * Otherwise, if plane_state->fence is not set this function we
+ * just set it with the received implict fence.
+ */
+void
+drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
+ struct fence *fence)
+{
+ if (plane_state->fence) {
+ fence_put(fence);
+ return;
+ }
+
+ plane_state->fence = fence;
+}
+EXPORT_SYMBOL(drm_atomic_set_fence_for_plane);
+
+/**
* drm_atomic_set_crtc_for_connector - set crtc for connector
* @conn_state: atomic state object for the connector
* @crtc: crtc to use for the connector
@@ -1472,11 +1545,9 @@ EXPORT_SYMBOL(drm_atomic_nonblocking_commit);
*/
static struct drm_pending_vblank_event *create_vblank_event(
- struct drm_device *dev, struct drm_file *file_priv,
- struct fence *fence, uint64_t user_data)
+ struct drm_device *dev, uint64_t user_data)
{
struct drm_pending_vblank_event *e = NULL;
- int ret;
e = kzalloc(sizeof *e, GFP_KERNEL);
if (!e)
@@ -1486,17 +1557,6 @@ static struct drm_pending_vblank_event *create_vblank_event(
e->event.base.length = sizeof(e->event);
e->event.user_data = user_data;
- if (file_priv) {
- ret = drm_event_reserve_init(dev, file_priv, &e->base,
- &e->event.base);
- if (ret) {
- kfree(e);
- return NULL;
- }
- }
-
- e->base.fence = fence;
-
return e;
}
@@ -1601,6 +1661,206 @@ void drm_atomic_clean_old_fb(struct drm_device *dev,
}
EXPORT_SYMBOL(drm_atomic_clean_old_fb);
+/**
+ * DOC: explicit fencing properties
+ *
+ * Explicit fencing allows userspace to control the buffer synchronization
+ * between devices. A Fence or a group of fences are transfered to/from
+ * userspace using Sync File fds and there are two DRM properties for that.
+ * IN_FENCE_FD on each DRM Plane to send fences to the kernel and
+ * OUT_FENCE_PTR on each DRM CRTC to receive fences from the kernel.
+ *
+ * As a contrast, with implicit fencing the kernel keeps track of any
+ * ongoing rendering, and automatically ensures that the atomic update waits
+ * for any pending rendering to complete. For shared buffers represented with
+ * a struct &dma_buf this is tracked in &reservation_object structures.
+ * Implicit syncing is how Linux traditionally worked (e.g. DRI2/3 on X.org),
+ * whereas explicit fencing is what Android wants.
+ *
+ * "IN_FENCE_FD”:
+ * Use this property to pass a fence that DRM should wait on before
+ * proceeding with the Atomic Commit request and show the framebuffer for
+ * the plane on the screen. The fence can be either a normal fence or a
+ * merged one, the sync_file framework will handle both cases and use a
+ * fence_array if a merged fence is received. Passing -1 here means no
+ * fences to wait on.
+ *
+ * If the Atomic Commit request has the DRM_MODE_ATOMIC_TEST_ONLY flag
+ * it will only check if the Sync File is a valid one.
+ *
+ * On the driver side the fence is stored on the @fence parameter of
+ * struct &drm_plane_state. Drivers which also support implicit fencing
+ * should set the implicit fence using drm_atomic_set_fence_for_plane(),
+ * to make sure there's consistent behaviour between drivers in precedence
+ * of implicit vs. explicit fencing.
+ *
+ * "OUT_FENCE_PTR”:
+ * Use this property to pass a file descriptor pointer to DRM. Once the
+ * Atomic Commit request call returns OUT_FENCE_PTR will be filled with
+ * the file descriptor number of a Sync File. This Sync File contains the
+ * CRTC fence that will be signaled when all framebuffers present on the
+ * Atomic Commit * request for that given CRTC are scanned out on the
+ * screen.
+ *
+ * The Atomic Commit request fails if a invalid pointer is passed. If the
+ * Atomic Commit request fails for any other reason the out fence fd
+ * returned will be -1. On a Atomic Commit with the
+ * DRM_MODE_ATOMIC_TEST_ONLY flag the out fence will also be set to -1.
+ *
+ * Note that out-fences don't have a special interface to drivers and are
+ * internally represented by a struct &drm_pending_vblank_event in struct
+ * &drm_crtc_state, which is also used by the nonblocking atomic commit
+ * helpers and for the DRM event handling for existing userspace.
+ */
+
+struct drm_out_fence_state {
+ s32 __user *out_fence_ptr;
+ struct sync_file *sync_file;
+ int fd;
+};
+
+static int setup_out_fence(struct drm_out_fence_state *fence_state,
+ struct fence *fence)
+{
+ fence_state->fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fence_state->fd < 0)
+ return fence_state->fd;
+
+ if (put_user(fence_state->fd, fence_state->out_fence_ptr))
+ return -EFAULT;
+
+ fence_state->sync_file = sync_file_create(fence);
+ if (!fence_state->sync_file)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int prepare_crtc_signaling(struct drm_device *dev,
+ struct drm_atomic_state *state,
+ struct drm_mode_atomic *arg,
+ struct drm_file *file_priv,
+ struct drm_out_fence_state **fence_state,
+ unsigned int *num_fences)
+{
+ struct drm_crtc *crtc;
+ struct drm_crtc_state *crtc_state;
+ int i, ret;
+
+ if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)
+ return 0;
+
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ s32 __user *fence_ptr;
+
+ fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc);
+
+ if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT || fence_ptr) {
+ struct drm_pending_vblank_event *e;
+
+ e = create_vblank_event(dev, arg->user_data);
+ if (!e)
+ return -ENOMEM;
+
+ crtc_state->event = e;
+ }
+
+ if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
+ struct drm_pending_vblank_event *e = crtc_state->event;
+
+ if (!file_priv)
+ continue;
+
+ ret = drm_event_reserve_init(dev, file_priv, &e->base,
+ &e->event.base);
+ if (ret) {
+ kfree(e);
+ crtc_state->event = NULL;
+ return ret;
+ }
+ }
+
+ if (fence_ptr) {
+ struct fence *fence;
+ struct drm_out_fence_state *f;
+
+ f = krealloc(*fence_state, sizeof(**fence_state) *
+ (*num_fences + 1), GFP_KERNEL);
+ if (!f)
+ return -ENOMEM;
+
+ memset(&f[*num_fences], 0, sizeof(*f));
+
+ f[*num_fences].out_fence_ptr = fence_ptr;
+ *fence_state = f;
+
+ fence = drm_crtc_create_fence(crtc);
+ if (!fence)
+ return -ENOMEM;
+
+ ret = setup_out_fence(&f[(*num_fences)++], fence);
+ if (ret) {
+ fence_put(fence);
+ return ret;
+ }
+
+ crtc_state->event->base.fence = fence;
+ }
+ }
+
+ return 0;
+}
+
+static void complete_crtc_signaling(struct drm_device *dev,
+ struct drm_atomic_state *state,
+ struct drm_out_fence_state *fence_state,
+ unsigned int num_fences,
+ bool install_fds)
+{
+ struct drm_crtc *crtc;
+ struct drm_crtc_state *crtc_state;
+ int i;
+
+ if (install_fds) {
+ for (i = 0; i < num_fences; i++)
+ fd_install(fence_state[i].fd,
+ fence_state[i].sync_file->file);
+
+ kfree(fence_state);
+ return;
+ }
+
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ struct drm_pending_vblank_event *event = crtc_state->event;
+ /*
+ * Free the allocated event. drm_atomic_helper_setup_commit
+ * can allocate an event too, so only free it if it's ours
+ * to prevent a double free in drm_atomic_state_clear.
+ */
+ if (event && (event->base.fence || event->base.file_priv)) {
+ drm_event_cancel_free(dev, &event->base);
+ crtc_state->event = NULL;
+ }
+ }
+
+ if (!fence_state)
+ return;
+
+ for (i = 0; i < num_fences; i++) {
+ if (fence_state[i].sync_file)
+ fput(fence_state[i].sync_file->file);
+ if (fence_state[i].fd >= 0)
+ put_unused_fd(fence_state[i].fd);
+
+ /* If this fails log error to the user */
+ if (fence_state[i].out_fence_ptr &&
+ put_user(-1, fence_state[i].out_fence_ptr))
+ DRM_DEBUG_ATOMIC("Couldn't clear out_fence_ptr\n");
+ }
+
+ kfree(fence_state);
+}
+
int drm_mode_atomic_ioctl(struct drm_device *dev,
void *data, struct drm_file *file_priv)
{
@@ -1613,11 +1873,10 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
struct drm_atomic_state *state;
struct drm_modeset_acquire_ctx ctx;
struct drm_plane *plane;
- struct drm_crtc *crtc;
- struct drm_crtc_state *crtc_state;
+ struct drm_out_fence_state *fence_state;
unsigned plane_mask;
int ret = 0;
- unsigned int i, j;
+ unsigned int i, j, num_fences;
/* disallow for drivers not supporting atomic: */
if (!drm_core_check_feature(dev, DRIVER_ATOMIC))
@@ -1658,6 +1917,8 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
plane_mask = 0;
copied_objs = 0;
copied_props = 0;
+ fence_state = NULL;
+ num_fences = 0;
for (i = 0; i < arg->count_objs; i++) {
uint32_t obj_id, count_props;
@@ -1732,20 +1993,10 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
drm_mode_object_unreference(obj);
}
- if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- struct drm_pending_vblank_event *e;
-
- e = create_vblank_event(dev, file_priv, NULL,
- arg->user_data);
- if (!e) {
- ret = -ENOMEM;
- goto out;
- }
-
- crtc_state->event = e;
- }
- }
+ ret = prepare_crtc_signaling(dev, state, arg, file_priv, &fence_state,
+ &num_fences);
+ if (ret)
+ goto out;
if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY) {
/*
@@ -1762,20 +2013,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
out:
drm_atomic_clean_old_fb(dev, plane_mask, ret);
- if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
- /*
- * Free the allocated event. drm_atomic_helper_setup_commit
- * can allocate an event too, so only free it if it's ours
- * to prevent a double free in drm_atomic_state_clear.
- */
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- struct drm_pending_vblank_event *event = crtc_state->event;
- if (event && (event->base.fence || event->base.file_priv)) {
- drm_event_cancel_free(dev, &event->base);
- crtc_state->event = NULL;
- }
- }
- }
+ complete_crtc_signaling(dev, state, fence_state, num_fences, !ret);
if (ret == -EDEADLK) {
drm_atomic_state_clear(state);
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 50acd79..f34b4e8 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -3166,6 +3166,9 @@ void __drm_atomic_helper_plane_destroy_state(struct drm_plane_state *state)
{
if (state->fb)
drm_framebuffer_unreference(state->fb);
+
+ if (state->fence)
+ fence_put(state->fence);
}
EXPORT_SYMBOL(__drm_atomic_helper_plane_destroy_state);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 2d7bedf..79b3d52 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -33,6 +33,7 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/fence.h>
#include <drm/drmP.h>
#include <drm/drm_crtc.h>
#include <drm/drm_edid.h>
@@ -141,6 +142,54 @@ static void drm_crtc_unregister_all(struct drm_device *dev)
}
}
+static const struct fence_ops drm_crtc_fence_ops;
+
+static struct drm_crtc *fence_to_crtc(struct fence *fence)
+{
+ BUG_ON(fence->ops != &drm_crtc_fence_ops);
+ return container_of(fence->lock, struct drm_crtc, fence_lock);
+}
+
+static const char *drm_crtc_fence_get_driver_name(struct fence *fence)
+{
+ struct drm_crtc *crtc = fence_to_crtc(fence);
+
+ return crtc->dev->driver->name;
+}
+
+static const char *drm_crtc_fence_get_timeline_name(struct fence *fence)
+{
+ struct drm_crtc *crtc = fence_to_crtc(fence);
+
+ return crtc->timeline_name;
+}
+
+static bool drm_crtc_fence_enable_signaling(struct fence *fence)
+{
+ return true;
+}
+
+static const struct fence_ops drm_crtc_fence_ops = {
+ .get_driver_name = drm_crtc_fence_get_driver_name,
+ .get_timeline_name = drm_crtc_fence_get_timeline_name,
+ .enable_signaling = drm_crtc_fence_enable_signaling,
+ .wait = fence_default_wait,
+};
+
+struct fence *drm_crtc_create_fence(struct drm_crtc *crtc)
+{
+ struct fence *fence;
+
+ fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+ if (!fence)
+ return NULL;
+
+ fence_init(fence, &drm_crtc_fence_ops, &crtc->fence_lock,
+ crtc->fence_context, ++crtc->fence_seqno);
+
+ return fence;
+}
+
/**
* drm_crtc_init_with_planes - Initialise a new CRTC object with
* specified primary and cursor planes.
@@ -198,6 +247,11 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
return -ENOMEM;
}
+ crtc->fence_context = fence_context_alloc(1);
+ spin_lock_init(&crtc->fence_lock);
+ snprintf(crtc->timeline_name, sizeof(crtc->timeline_name),
+ "CRTC:%d-%s", crtc->base.id, crtc->name);
+
crtc->base.properties = &crtc->properties;
list_add_tail(&crtc->head, &config->crtc_list);
@@ -213,6 +267,8 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
if (drm_core_check_feature(dev, DRIVER_ATOMIC)) {
drm_object_attach_property(&crtc->base, config->prop_active, 0);
drm_object_attach_property(&crtc->base, config->prop_mode_id, 0);
+ drm_object_attach_property(&crtc->base,
+ config->prop_out_fence_ptr, 0);
}
return 0;
@@ -365,6 +421,18 @@ static int drm_mode_create_standard_properties(struct drm_device *dev)
return -ENOMEM;
dev->mode_config.prop_fb_id = prop;
+ prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC,
+ "IN_FENCE_FD", -1, INT_MAX);
+ if (!prop)
+ return -ENOMEM;
+ dev->mode_config.prop_in_fence_fd = prop;
+
+ prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC,
+ "OUT_FENCE_PTR", 0, U64_MAX);
+ if (!prop)
+ return -ENOMEM;
+ dev->mode_config.prop_out_fence_ptr = prop;
+
prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC,
"CRTC_ID", DRM_MODE_OBJECT_CRTC);
if (!prop)
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index c48ba02..df2b51a 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -41,6 +41,8 @@ int drm_crtc_check_viewport(const struct drm_crtc *crtc,
const struct drm_display_mode *mode,
const struct drm_framebuffer *fb);
+struct fence *drm_crtc_create_fence(struct drm_crtc *crtc);
+
void drm_fb_release(struct drm_file *file_priv);
/* dumb buffer support IOCTLs */
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 1fd6eac..52629b6 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -18,13 +18,16 @@
*/
#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
#include <drm/drm_crtc.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_fb_cma_helper.h>
+#include <linux/dma-buf.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
+#include <linux/reservation.h>
#define DEFAULT_FBDEFIO_DELAY_MS 50
@@ -265,6 +268,38 @@ struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb,
}
EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_obj);
+/**
+ * drm_fb_cma_prepare_fb() - Prepare CMA framebuffer
+ * @plane: Which plane
+ * @state: Plane state attach fence to
+ *
+ * This should be put into prepare_fb hook of struct &drm_plane_helper_funcs .
+ *
+ * This function checks if the plane FB has an dma-buf attached, extracts
+ * the exclusive fence and attaches it to plane state for the atomic helper
+ * to wait on.
+ *
+ * There is no need for cleanup_fb for CMA based framebuffer drivers.
+ */
+int drm_fb_cma_prepare_fb(struct drm_plane *plane,
+ struct drm_plane_state *state)
+{
+ struct dma_buf *dma_buf;
+ struct fence *fence;
+
+ if ((plane->state->fb == state->fb) || !state->fb)
+ return 0;
+
+ dma_buf = drm_fb_cma_get_gem_obj(state->fb, 0)->base.dma_buf;
+ if (dma_buf) {
+ fence = reservation_object_get_excl_rcu(dma_buf->resv);
+ drm_atomic_set_fence_for_plane(state, fence);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(drm_fb_cma_prepare_fb);
+
#ifdef CONFIG_DEBUG_FS
static void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
{
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 921f7f6..8d9c190 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -665,6 +665,10 @@ void drm_event_cancel_free(struct drm_device *dev,
list_del(&p->pending_link);
}
spin_unlock_irqrestore(&dev->event_lock, flags);
+
+ if (p->fence)
+ fence_put(p->fence);
+
kfree(p);
}
EXPORT_SYMBOL(drm_event_cancel_free);
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 249c0ae..3957ef8 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -137,6 +137,7 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
if (drm_core_check_feature(dev, DRIVER_ATOMIC)) {
drm_object_attach_property(&plane->base, config->prop_fb_id, 0);
+ drm_object_attach_property(&plane->base, config->prop_in_fence_fd, -1);
drm_object_attach_property(&plane->base, config->prop_crtc_id, 0);
drm_object_attach_property(&plane->base, config->prop_crtc_x, 0);
drm_object_attach_property(&plane->base, config->prop_crtc_y, 0);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 83bf997..5e67e8b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -218,9 +218,10 @@ mdp5_plane_duplicate_state(struct drm_plane *plane)
mdp5_state = kmemdup(to_mdp5_plane_state(plane->state),
sizeof(*mdp5_state), GFP_KERNEL);
+ if (!mdp5_state)
+ return NULL;
- if (mdp5_state && mdp5_state->base.fb)
- drm_framebuffer_reference(mdp5_state->base.fb);
+ __drm_atomic_helper_plane_duplicate_state(plane, &mdp5_state->base);
mdp5_state->mode_changed = false;
mdp5_state->pending = false;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 52a2a1a..5a18408 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1606,7 +1606,14 @@ EXPORT_SYMBOL(ttm_bo_unmap_virtual);
int ttm_bo_wait(struct ttm_buffer_object *bo,
bool interruptible, bool no_wait)
{
- long timeout = no_wait ? 0 : 15 * HZ;
+ long timeout = 15 * HZ;
+
+ if (no_wait) {
+ if (reservation_object_test_signaled_rcu(bo->resv, true))
+ return 0;
+ else
+ return -EBUSY;
+ }
timeout = reservation_object_wait_timeout_rcu(bo->resv, true,
interruptible, timeout);
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 8eed456..0613316 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -573,6 +573,17 @@
To compile this driver as a module, choose M here: the
module will be called hid-multitouch.
+config HID_NINTENDO
+ tristate "Nintendo Joy-Con and Pro Controller support"
+ depends on HID
+ help
+ Adds support for the Nintendo Switch Joy-Cons and Pro Controller.
+ All controllers support bluetooth, and the Pro Controller also supports
+ its USB mode.
+
+ To compile this driver as a module, choose M here: the
+ module will be called hid-nintendo.
+
config HID_NTRIG
tristate "N-Trig touch screen"
depends on USB_HID
@@ -763,6 +774,14 @@
---help---
Support for Speedlink Vicious and Divine Cezanne mouse.
+config HID_STEAM
+ tristate "Steam Controller support"
+ depends on HID
+ ---help---
+ Say Y here if you have a Steam Controller if you want to use it
+ without running the Steam Client. It supports both the wired and
+ the wireless adaptor.
+
config HID_STEELSERIES
tristate "Steelseries SRW-S1 steering wheel support"
depends on HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index 86b2b57..9fb5986 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -61,6 +61,7 @@
obj-$(CONFIG_HID_MICROSOFT) += hid-microsoft.o
obj-$(CONFIG_HID_MONTEREY) += hid-monterey.o
obj-$(CONFIG_HID_MULTITOUCH) += hid-multitouch.o
+obj-$(CONFIG_HID_NINTENDO) += hid-nintendo.o
obj-$(CONFIG_HID_NTRIG) += hid-ntrig.o
obj-$(CONFIG_HID_ORTEK) += hid-ortek.o
obj-$(CONFIG_HID_PRODIKEYS) += hid-prodikeys.o
@@ -88,6 +89,7 @@
obj-$(CONFIG_HID_SMARTJOYPLUS) += hid-sjoy.o
obj-$(CONFIG_HID_SONY) += hid-sony.o
obj-$(CONFIG_HID_SPEEDLINK) += hid-speedlink.o
+obj-$(CONFIG_HID_STEAM) += hid-steam.o
obj-$(CONFIG_HID_STEELSERIES) += hid-steelseries.o
obj-$(CONFIG_HID_SUNPLUS) += hid-sunplus.o
obj-$(CONFIG_HID_GREENASIA) += hid-gaff.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index d99c9ed..986ee8f 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2071,6 +2071,16 @@ static const struct hid_device_id hid_have_special_driver[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER) },
{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
{ HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) },
+#if IS_ENABLED(CONFIG_HID_NINTENDO)
+ { HID_USB_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_PROCON) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_PROCON) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_JOYCONL) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_JOYCONR) },
+#endif
{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) },
{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_2) },
@@ -2174,6 +2184,8 @@ static const struct hid_device_id hid_have_special_driver[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_VALVE, USB_DEVICE_ID_STEAM_CONTROLLER) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_VALVE, USB_DEVICE_ID_STEAM_CONTROLLER_WIRELESS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SMARTJOY_PLUS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SUPER_JOY_BOX_3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index c4a53fc..69c09de 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -781,6 +781,9 @@
#define USB_VENDOR_ID_NINTENDO 0x057e
#define USB_DEVICE_ID_NINTENDO_WIIMOTE 0x0306
#define USB_DEVICE_ID_NINTENDO_WIIMOTE2 0x0330
+#define USB_DEVICE_ID_NINTENDO_JOYCONL 0x2006
+#define USB_DEVICE_ID_NINTENDO_JOYCONR 0x2007
+#define USB_DEVICE_ID_NINTENDO_PROCON 0x2009
#define USB_VENDOR_ID_NOVATEK 0x0603
#define USB_DEVICE_ID_NOVATEK_PCT 0x0600
@@ -957,6 +960,10 @@
#define USB_VENDOR_ID_STANTUM_SITRONIX 0x1403
#define USB_DEVICE_ID_MTP_SITRONIX 0x5001
+#define USB_VENDOR_ID_VALVE 0x28de
+#define USB_DEVICE_ID_STEAM_CONTROLLER 0x1102
+#define USB_DEVICE_ID_STEAM_CONTROLLER_WIRELESS 0x1142
+
#define USB_VENDOR_ID_STEELSERIES 0x1038
#define USB_DEVICE_ID_STEELSERIES_SRWS1 0x1410
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 5e1a51b..d458202 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -342,13 +342,45 @@ static unsigned find_battery_quirk(struct hid_device *hdev)
return quirks;
}
+static int hidinput_scale_battery_capacity(struct hid_device *dev,
+ int value)
+{
+ if (dev->battery_min < dev->battery_max &&
+ value >= dev->battery_min && value <= dev->battery_max)
+ value = ((value - dev->battery_min) * 100) /
+ (dev->battery_max - dev->battery_min);
+
+ return value;
+}
+
+static int hidinput_query_battery_capacity(struct hid_device *dev)
+{
+ u8 *buf;
+ int ret;
+
+ buf = kmalloc(2, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
+ dev->battery_report_type, HID_REQ_GET_REPORT);
+ if (ret != 2) {
+ kfree(buf);
+ return -ENODATA;
+ }
+
+ ret = hidinput_scale_battery_capacity(dev, buf[1]);
+ kfree(buf);
+ return ret;
+}
+
static int hidinput_get_battery_property(struct power_supply *psy,
enum power_supply_property prop,
union power_supply_propval *val)
{
struct hid_device *dev = power_supply_get_drvdata(psy);
+ int value;
int ret = 0;
- __u8 *buf;
switch (prop) {
case POWER_SUPPLY_PROP_PRESENT:
@@ -357,29 +389,15 @@ static int hidinput_get_battery_property(struct power_supply *psy,
break;
case POWER_SUPPLY_PROP_CAPACITY:
-
- buf = kmalloc(2 * sizeof(__u8), GFP_KERNEL);
- if (!buf) {
- ret = -ENOMEM;
- break;
+ if (dev->battery_report_type == HID_FEATURE_REPORT) {
+ value = hidinput_query_battery_capacity(dev);
+ if (value < 0)
+ return value;
+ } else {
+ value = dev->battery_capacity;
}
- ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
- dev->battery_report_type,
- HID_REQ_GET_REPORT);
- if (ret != 2) {
- ret = -ENODATA;
- kfree(buf);
- break;
- }
- ret = 0;
-
- if (dev->battery_min < dev->battery_max &&
- buf[1] >= dev->battery_min &&
- buf[1] <= dev->battery_max)
- val->intval = (100 * (buf[1] - dev->battery_min)) /
- (dev->battery_max - dev->battery_min);
- kfree(buf);
+ val->intval = value;
break;
case POWER_SUPPLY_PROP_MODEL_NAME:
@@ -387,7 +405,22 @@ static int hidinput_get_battery_property(struct power_supply *psy,
break;
case POWER_SUPPLY_PROP_STATUS:
- val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+ if (!dev->battery_reported &&
+ dev->battery_report_type == HID_FEATURE_REPORT) {
+ value = hidinput_query_battery_capacity(dev);
+ if (value < 0)
+ return value;
+
+ dev->battery_capacity = value;
+ dev->battery_reported = true;
+ }
+
+ if (!dev->battery_reported)
+ val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+ else if (dev->battery_capacity == 100)
+ val->intval = POWER_SUPPLY_STATUS_FULL;
+ else
+ val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
break;
case POWER_SUPPLY_PROP_SCOPE:
@@ -402,18 +435,16 @@ static int hidinput_get_battery_property(struct power_supply *psy,
return ret;
}
-static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field)
+static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field)
{
- struct power_supply_desc *psy_desc = NULL;
+ struct power_supply_desc *psy_desc;
struct power_supply_config psy_cfg = { .drv_data = dev, };
unsigned quirks;
s32 min, max;
+ int error;
- if (field->usage->hid != HID_DC_BATTERYSTRENGTH)
- return false; /* no match */
-
- if (dev->battery != NULL)
- goto out; /* already initialized? */
+ if (dev->battery)
+ return 0; /* already initialized? */
quirks = find_battery_quirk(dev);
@@ -421,16 +452,16 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
dev->bus, dev->vendor, dev->product, dev->version, quirks);
if (quirks & HID_BATTERY_QUIRK_IGNORE)
- goto out;
+ return 0;
psy_desc = kzalloc(sizeof(*psy_desc), GFP_KERNEL);
- if (psy_desc == NULL)
- goto out;
+ if (!psy_desc)
+ return -ENOMEM;
psy_desc->name = kasprintf(GFP_KERNEL, "hid-%s-battery", dev->uniq);
- if (psy_desc->name == NULL) {
- kfree(psy_desc);
- goto out;
+ if (!psy_desc->name) {
+ error = -ENOMEM;
+ goto err_free_mem;
}
psy_desc->type = POWER_SUPPLY_TYPE_BATTERY;
@@ -457,17 +488,20 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg);
if (IS_ERR(dev->battery)) {
- hid_warn(dev, "can't register power supply: %ld\n",
- PTR_ERR(dev->battery));
- kfree(psy_desc->name);
- kfree(psy_desc);
- dev->battery = NULL;
- } else {
- power_supply_powers(dev->battery, &dev->dev);
+ error = PTR_ERR(dev->battery);
+ hid_warn(dev, "can't register power supply: %d\n", error);
+ goto err_free_name;
}
-out:
- return true;
+ power_supply_powers(dev->battery, &dev->dev);
+ return 0;
+
+err_free_name:
+ kfree(psy_desc->name);
+err_free_mem:
+ kfree(psy_desc);
+ dev->battery = NULL;
+ return error;
}
static void hidinput_cleanup_battery(struct hid_device *dev)
@@ -483,16 +517,33 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
kfree(psy_desc);
dev->battery = NULL;
}
-#else /* !CONFIG_HID_BATTERY_STRENGTH */
-static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
- struct hid_field *field)
+
+static void hidinput_update_battery(struct hid_device *dev, int value)
{
- return false;
+ if (!dev->battery)
+ return;
+
+ if (value == 0 || value < dev->battery_min || value > dev->battery_max)
+ return;
+
+ dev->battery_capacity = hidinput_scale_battery_capacity(dev, value);
+ dev->battery_reported = true;
+ power_supply_changed(dev->battery);
+}
+#else /* !CONFIG_HID_BATTERY_STRENGTH */
+static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
+ struct hid_field *field)
+{
+ return 0;
}
static void hidinput_cleanup_battery(struct hid_device *dev)
{
}
+
+static void hidinput_update_battery(struct hid_device *dev, int value)
+{
+}
#endif /* CONFIG_HID_BATTERY_STRENGTH */
static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_field *field,
@@ -711,6 +762,11 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
}
break;
+ case 0x3b: /* Battery Strength */
+ hidinput_setup_battery(device, HID_INPUT_REPORT, field);
+ usage->type = EV_PWR;
+ goto ignore;
+
case 0x3c: /* Invert */
map_key_clear(BTN_TOOL_RUBBER);
break;
@@ -951,11 +1007,13 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
break;
case HID_UP_GENDEVCTRLS:
- if (hidinput_setup_battery(device, HID_INPUT_REPORT, field))
+ switch (usage->hid) {
+ case HID_DC_BATTERYSTRENGTH:
+ hidinput_setup_battery(device, HID_INPUT_REPORT, field);
+ usage->type = EV_PWR;
goto ignore;
- else
- goto unknown;
- break;
+ }
+ goto unknown;
case HID_UP_HPVENDOR: /* Reported on a Dutch layout HP5308 */
set_bit(EV_REP, input->evbit);
@@ -1048,7 +1106,6 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
if (usage->code > max)
goto ignore;
-
if (usage->type == EV_ABS) {
int a = field->logical_minimum;
@@ -1109,14 +1166,19 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
struct input_dev *input;
unsigned *quirks = &hid->quirks;
+ if (!usage->type)
+ return;
+
+ if (usage->type == EV_PWR) {
+ hidinput_update_battery(hid, value);
+ return;
+ }
+
if (!field->hidinput)
return;
input = field->hidinput->input;
- if (!usage->type)
- return;
-
if (usage->hat_min < usage->hat_max || usage->hat_dir) {
int hat_dir = usage->hat_dir;
if (!hat_dir)
@@ -1393,6 +1455,7 @@ static void report_features(struct hid_device *hid)
struct hid_driver *drv = hid->driver;
struct hid_report_enum *rep_enum;
struct hid_report *rep;
+ struct hid_usage *usage;
int i, j;
rep_enum = &hid->report_enum[HID_FEATURE_REPORT];
@@ -1403,12 +1466,15 @@ static void report_features(struct hid_device *hid)
continue;
for (j = 0; j < rep->field[i]->maxusage; j++) {
+ usage = &rep->field[i]->usage[j];
+
/* Verify if Battery Strength feature is available */
- hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i]);
+ if (usage->hid == HID_DC_BATTERYSTRENGTH)
+ hidinput_setup_battery(hid, HID_FEATURE_REPORT,
+ rep->field[i]);
if (drv->feature_mapping)
- drv->feature_mapping(hid, rep->field[i],
- rep->field[i]->usage + j);
+ drv->feature_mapping(hid, rep->field[i], usage);
}
}
}
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 8c993f9..78e37bb 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -34,7 +34,8 @@ module_param(emulate_scroll_wheel, bool, 0644);
MODULE_PARM_DESC(emulate_scroll_wheel, "Emulate a scroll wheel");
static unsigned int scroll_speed = 32;
-static int param_set_scroll_speed(const char *val, struct kernel_param *kp) {
+static int param_set_scroll_speed(const char *val,
+ const struct kernel_param *kp) {
unsigned long speed;
if (!val || kstrtoul(val, 0, &speed) || speed > 63)
return -EINVAL;
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
new file mode 100644
index 0000000..3695b96
--- /dev/null
+++ b/drivers/hid/hid-nintendo.c
@@ -0,0 +1,820 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * HID driver for Nintendo Switch Joy-Cons and Pro Controllers
+ *
+ * Copyright (c) 2019 Daniel J. Ogorchock <djogorchock@gmail.com>
+ *
+ * The following resources/projects were referenced for this driver:
+ * https://github.com/dekuNukem/Nintendo_Switch_Reverse_Engineering
+ * https://gitlab.com/pjranki/joycon-linux-kernel (Peter Rankin)
+ * https://github.com/FrotBot/SwitchProConLinuxUSB
+ * https://github.com/MTCKC/ProconXInput
+ * hid-wiimote kernel hid driver
+ * hid-logitech-hidpp driver
+ *
+ * This driver supports the Nintendo Switch Joy-Cons and Pro Controllers. The
+ * Pro Controllers can either be used over USB or Bluetooth.
+ *
+ * The driver will retrieve the factory calibration info from the controllers,
+ * so little to no user calibration should be required.
+ *
+ */
+
+#include "hid-ids.h"
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+
+/*
+ * Reference the url below for the following HID report defines:
+ * https://github.com/dekuNukem/Nintendo_Switch_Reverse_Engineering
+ */
+
+/* Output Reports */
+static const u8 JC_OUTPUT_RUMBLE_AND_SUBCMD = 0x01;
+static const u8 JC_OUTPUT_FW_UPDATE_PKT = 0x03;
+static const u8 JC_OUTPUT_RUMBLE_ONLY = 0x10;
+static const u8 JC_OUTPUT_MCU_DATA = 0x11;
+static const u8 JC_OUTPUT_USB_CMD = 0x80;
+
+/* Subcommand IDs */
+static const u8 JC_SUBCMD_STATE /*= 0x00*/;
+static const u8 JC_SUBCMD_MANUAL_BT_PAIRING = 0x01;
+static const u8 JC_SUBCMD_REQ_DEV_INFO = 0x02;
+static const u8 JC_SUBCMD_SET_REPORT_MODE = 0x03;
+static const u8 JC_SUBCMD_TRIGGERS_ELAPSED = 0x04;
+static const u8 JC_SUBCMD_GET_PAGE_LIST_STATE = 0x05;
+static const u8 JC_SUBCMD_SET_HCI_STATE = 0x06;
+static const u8 JC_SUBCMD_RESET_PAIRING_INFO = 0x07;
+static const u8 JC_SUBCMD_LOW_POWER_MODE = 0x08;
+static const u8 JC_SUBCMD_SPI_FLASH_READ = 0x10;
+static const u8 JC_SUBCMD_SPI_FLASH_WRITE = 0x11;
+static const u8 JC_SUBCMD_RESET_MCU = 0x20;
+static const u8 JC_SUBCMD_SET_MCU_CONFIG = 0x21;
+static const u8 JC_SUBCMD_SET_MCU_STATE = 0x22;
+static const u8 JC_SUBCMD_SET_PLAYER_LIGHTS = 0x30;
+static const u8 JC_SUBCMD_GET_PLAYER_LIGHTS = 0x31;
+static const u8 JC_SUBCMD_SET_HOME_LIGHT = 0x38;
+static const u8 JC_SUBCMD_ENABLE_IMU = 0x40;
+static const u8 JC_SUBCMD_SET_IMU_SENSITIVITY = 0x41;
+static const u8 JC_SUBCMD_WRITE_IMU_REG = 0x42;
+static const u8 JC_SUBCMD_READ_IMU_REG = 0x43;
+static const u8 JC_SUBCMD_ENABLE_VIBRATION = 0x48;
+static const u8 JC_SUBCMD_GET_REGULATED_VOLTAGE = 0x50;
+
+/* Input Reports */
+static const u8 JC_INPUT_BUTTON_EVENT = 0x3F;
+static const u8 JC_INPUT_SUBCMD_REPLY = 0x21;
+static const u8 JC_INPUT_IMU_DATA = 0x30;
+static const u8 JC_INPUT_MCU_DATA = 0x31;
+static const u8 JC_INPUT_USB_RESPONSE = 0x81;
+
+/* Feature Reports */
+static const u8 JC_FEATURE_LAST_SUBCMD = 0x02;
+static const u8 JC_FEATURE_OTA_FW_UPGRADE = 0x70;
+static const u8 JC_FEATURE_SETUP_MEM_READ = 0x71;
+static const u8 JC_FEATURE_MEM_READ = 0x72;
+static const u8 JC_FEATURE_ERASE_MEM_SECTOR = 0x73;
+static const u8 JC_FEATURE_MEM_WRITE = 0x74;
+static const u8 JC_FEATURE_LAUNCH = 0x75;
+
+/* USB Commands */
+static const u8 JC_USB_CMD_CONN_STATUS = 0x01;
+static const u8 JC_USB_CMD_HANDSHAKE = 0x02;
+static const u8 JC_USB_CMD_BAUDRATE_3M = 0x03;
+static const u8 JC_USB_CMD_NO_TIMEOUT = 0x04;
+static const u8 JC_USB_CMD_EN_TIMEOUT = 0x05;
+static const u8 JC_USB_RESET = 0x06;
+static const u8 JC_USB_PRE_HANDSHAKE = 0x91;
+static const u8 JC_USB_SEND_UART = 0x92;
+
+/* SPI storage addresses of factory calibration data */
+static const u16 JC_CAL_DATA_START = 0x603d;
+static const u16 JC_CAL_DATA_END = 0x604e;
+#define JC_CAL_DATA_SIZE (JC_CAL_DATA_END - JC_CAL_DATA_START + 1)
+
+
+/* The raw analog joystick values will be mapped in terms of this magnitude */
+static const u16 JC_MAX_STICK_MAG = 32767;
+static const u16 JC_STICK_FUZZ = 250;
+static const u16 JC_STICK_FLAT = 500;
+
+/* States for controller state machine */
+enum joycon_ctlr_state {
+ JOYCON_CTLR_STATE_INIT,
+ JOYCON_CTLR_STATE_READ,
+};
+
+struct joycon_stick_cal {
+ s32 max;
+ s32 min;
+ s32 center;
+};
+
+/*
+ * All the controller's button values are stored in a u32.
+ * They can be accessed with bitwise ANDs.
+ */
+static const u32 JC_BTN_Y = BIT(0);
+static const u32 JC_BTN_X = BIT(1);
+static const u32 JC_BTN_B = BIT(2);
+static const u32 JC_BTN_A = BIT(3);
+static const u32 JC_BTN_SR_R = BIT(4);
+static const u32 JC_BTN_SL_R = BIT(5);
+static const u32 JC_BTN_R = BIT(6);
+static const u32 JC_BTN_ZR = BIT(7);
+static const u32 JC_BTN_MINUS = BIT(8);
+static const u32 JC_BTN_PLUS = BIT(9);
+static const u32 JC_BTN_RSTICK = BIT(10);
+static const u32 JC_BTN_LSTICK = BIT(11);
+static const u32 JC_BTN_HOME = BIT(12);
+static const u32 JC_BTN_CAP = BIT(13); /* capture button */
+static const u32 JC_BTN_DOWN = BIT(16);
+static const u32 JC_BTN_UP = BIT(17);
+static const u32 JC_BTN_RIGHT = BIT(18);
+static const u32 JC_BTN_LEFT = BIT(19);
+static const u32 JC_BTN_SR_L = BIT(20);
+static const u32 JC_BTN_SL_L = BIT(21);
+static const u32 JC_BTN_L = BIT(22);
+static const u32 JC_BTN_ZL = BIT(23);
+
+enum joycon_msg_type {
+ JOYCON_MSG_TYPE_NONE,
+ JOYCON_MSG_TYPE_USB,
+ JOYCON_MSG_TYPE_SUBCMD,
+};
+
+struct joycon_subcmd_request {
+ u8 output_id; /* must be 0x01 for subcommand, 0x10 for rumble only */
+ u8 packet_num; /* incremented every send */
+ u8 rumble_data[8];
+ u8 subcmd_id;
+ u8 data[0]; /* length depends on the subcommand */
+} __packed;
+
+struct joycon_subcmd_reply {
+ u8 ack; /* MSB 1 for ACK, 0 for NACK */
+ u8 id; /* id of requested subcmd */
+ u8 data[0]; /* will be at most 35 bytes */
+} __packed;
+
+struct joycon_input_report {
+ u8 id;
+ u8 timer;
+ u8 bat_con; /* battery and connection info */
+ u8 button_status[3];
+ u8 left_stick[3];
+ u8 right_stick[3];
+ u8 vibrator_report;
+
+ /*
+ * If support for firmware updates, gyroscope data, and/or NFC/IR
+ * are added in the future, this can be swapped for a union.
+ */
+ struct joycon_subcmd_reply reply;
+} __packed;
+
+#define JC_MAX_RESP_SIZE (sizeof(struct joycon_input_report) + 35)
+
+/* Each physical controller is associated with a joycon_ctlr struct */
+struct joycon_ctlr {
+ struct hid_device *hdev;
+ struct input_dev *input;
+ enum joycon_ctlr_state ctlr_state;
+
+ /* The following members are used for synchronous sends/receives */
+ enum joycon_msg_type msg_type;
+ u8 subcmd_num;
+ struct mutex output_mutex;
+ u8 input_buf[JC_MAX_RESP_SIZE];
+ wait_queue_head_t wait;
+ bool received_resp;
+ u8 usb_ack_match;
+ u8 subcmd_ack_match;
+
+ /* factory calibration data */
+ struct joycon_stick_cal left_stick_cal_x;
+ struct joycon_stick_cal left_stick_cal_y;
+ struct joycon_stick_cal right_stick_cal_x;
+ struct joycon_stick_cal right_stick_cal_y;
+
+};
+
+static int __joycon_hid_send(struct hid_device *hdev, u8 *data, size_t len)
+{
+ u8 *buf;
+ int ret;
+
+ buf = kmemdup(data, len, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+ ret = hid_hw_output_report(hdev, buf, len);
+ kfree(buf);
+ if (ret < 0)
+ hid_dbg(hdev, "Failed to send output report ret=%d\n", ret);
+ return ret;
+}
+
+static int joycon_hid_send_sync(struct joycon_ctlr *ctlr, u8 *data, size_t len)
+{
+ int ret;
+
+ ret = __joycon_hid_send(ctlr->hdev, data, len);
+ if (ret < 0) {
+ memset(ctlr->input_buf, 0, JC_MAX_RESP_SIZE);
+ return ret;
+ }
+
+ if (!wait_event_timeout(ctlr->wait, ctlr->received_resp, HZ)) {
+ hid_dbg(ctlr->hdev, "synchronous send/receive timed out\n");
+ memset(ctlr->input_buf, 0, JC_MAX_RESP_SIZE);
+ return -ETIMEDOUT;
+ }
+
+ ctlr->received_resp = false;
+ return 0;
+}
+
+static int joycon_send_usb(struct joycon_ctlr *ctlr, u8 cmd)
+{
+ int ret;
+ u8 buf[2] = {JC_OUTPUT_USB_CMD};
+
+ buf[1] = cmd;
+ ctlr->usb_ack_match = cmd;
+ ctlr->msg_type = JOYCON_MSG_TYPE_USB;
+ ret = joycon_hid_send_sync(ctlr, buf, sizeof(buf));
+ if (ret)
+ hid_dbg(ctlr->hdev, "send usb command failed; ret=%d\n", ret);
+ return ret;
+}
+
+static int joycon_send_subcmd(struct joycon_ctlr *ctlr,
+ struct joycon_subcmd_request *subcmd,
+ size_t data_len)
+{
+ int ret;
+
+ subcmd->output_id = JC_OUTPUT_RUMBLE_AND_SUBCMD;
+ subcmd->packet_num = ctlr->subcmd_num;
+ if (++ctlr->subcmd_num > 0xF)
+ ctlr->subcmd_num = 0;
+ ctlr->subcmd_ack_match = subcmd->subcmd_id;
+ ctlr->msg_type = JOYCON_MSG_TYPE_SUBCMD;
+
+ ret = joycon_hid_send_sync(ctlr, (u8 *)subcmd,
+ sizeof(*subcmd) + data_len);
+ if (ret < 0)
+ hid_dbg(ctlr->hdev, "send subcommand failed; ret=%d\n", ret);
+ else
+ ret = 0;
+ return ret;
+}
+
+/* Supply nibbles for flash and on. Ones correspond to active */
+static int joycon_set_player_leds(struct joycon_ctlr *ctlr, u8 flash, u8 on)
+{
+ struct joycon_subcmd_request *req;
+ u8 buffer[sizeof(*req) + 1] = { 0 };
+
+ req = (struct joycon_subcmd_request *)buffer;
+ req->subcmd_id = JC_SUBCMD_SET_PLAYER_LIGHTS;
+ req->data[0] = (flash << 4) | on;
+
+ hid_dbg(ctlr->hdev, "setting player leds\n");
+ return joycon_send_subcmd(ctlr, req, 1);
+}
+
+static const u16 DFLT_STICK_CAL_CEN = 2000;
+static const u16 DFLT_STICK_CAL_MAX = 3500;
+static const u16 DFLT_STICK_CAL_MIN = 500;
+static int joycon_request_calibration(struct joycon_ctlr *ctlr)
+{
+ struct joycon_subcmd_request *req;
+ u8 buffer[sizeof(*req) + 5] = { 0 };
+ struct joycon_input_report *report;
+ struct joycon_stick_cal *cal_x;
+ struct joycon_stick_cal *cal_y;
+ s32 x_max_above;
+ s32 x_min_below;
+ s32 y_max_above;
+ s32 y_min_below;
+ u8 *data;
+ u8 *raw_cal;
+ int ret;
+
+ req = (struct joycon_subcmd_request *)buffer;
+ req->subcmd_id = JC_SUBCMD_SPI_FLASH_READ;
+ data = req->data;
+ data[0] = 0xFF & JC_CAL_DATA_START;
+ data[1] = 0xFF & (JC_CAL_DATA_START >> 8);
+ data[2] = 0xFF & (JC_CAL_DATA_START >> 16);
+ data[3] = 0xFF & (JC_CAL_DATA_START >> 24);
+ data[4] = JC_CAL_DATA_SIZE;
+
+ hid_dbg(ctlr->hdev, "requesting cal data\n");
+ ret = joycon_send_subcmd(ctlr, req, 5);
+ if (ret) {
+ hid_warn(ctlr->hdev,
+ "Failed to read stick cal, using defaults; ret=%d\n",
+ ret);
+
+ ctlr->left_stick_cal_x.center = DFLT_STICK_CAL_CEN;
+ ctlr->left_stick_cal_x.max = DFLT_STICK_CAL_MAX;
+ ctlr->left_stick_cal_x.min = DFLT_STICK_CAL_MIN;
+
+ ctlr->left_stick_cal_y.center = DFLT_STICK_CAL_CEN;
+ ctlr->left_stick_cal_y.max = DFLT_STICK_CAL_MAX;
+ ctlr->left_stick_cal_y.min = DFLT_STICK_CAL_MIN;
+
+ ctlr->right_stick_cal_x.center = DFLT_STICK_CAL_CEN;
+ ctlr->right_stick_cal_x.max = DFLT_STICK_CAL_MAX;
+ ctlr->right_stick_cal_x.min = DFLT_STICK_CAL_MIN;
+
+ ctlr->right_stick_cal_y.center = DFLT_STICK_CAL_CEN;
+ ctlr->right_stick_cal_y.max = DFLT_STICK_CAL_MAX;
+ ctlr->right_stick_cal_y.min = DFLT_STICK_CAL_MIN;
+
+ return ret;
+ }
+
+ report = (struct joycon_input_report *)ctlr->input_buf;
+ raw_cal = &report->reply.data[5];
+
+ /* left stick calibration parsing */
+ cal_x = &ctlr->left_stick_cal_x;
+ cal_y = &ctlr->left_stick_cal_y;
+
+ x_max_above = hid_field_extract(ctlr->hdev, (raw_cal + 0), 0, 12);
+ y_max_above = hid_field_extract(ctlr->hdev, (raw_cal + 1), 4, 12);
+ cal_x->center = hid_field_extract(ctlr->hdev, (raw_cal + 3), 0, 12);
+ cal_y->center = hid_field_extract(ctlr->hdev, (raw_cal + 4), 4, 12);
+ x_min_below = hid_field_extract(ctlr->hdev, (raw_cal + 6), 0, 12);
+ y_min_below = hid_field_extract(ctlr->hdev, (raw_cal + 7), 4, 12);
+ cal_x->max = cal_x->center + x_max_above;
+ cal_x->min = cal_x->center - x_min_below;
+ cal_y->max = cal_y->center + y_max_above;
+ cal_y->min = cal_y->center - y_min_below;
+
+ /* right stick calibration parsing */
+ raw_cal += 9;
+ cal_x = &ctlr->right_stick_cal_x;
+ cal_y = &ctlr->right_stick_cal_y;
+
+ cal_x->center = hid_field_extract(ctlr->hdev, (raw_cal + 0), 0, 12);
+ cal_y->center = hid_field_extract(ctlr->hdev, (raw_cal + 1), 4, 12);
+ x_min_below = hid_field_extract(ctlr->hdev, (raw_cal + 3), 0, 12);
+ y_min_below = hid_field_extract(ctlr->hdev, (raw_cal + 4), 4, 12);
+ x_max_above = hid_field_extract(ctlr->hdev, (raw_cal + 6), 0, 12);
+ y_max_above = hid_field_extract(ctlr->hdev, (raw_cal + 7), 4, 12);
+ cal_x->max = cal_x->center + x_max_above;
+ cal_x->min = cal_x->center - x_min_below;
+ cal_y->max = cal_y->center + y_max_above;
+ cal_y->min = cal_y->center - y_min_below;
+
+ hid_dbg(ctlr->hdev, "calibration:\n"
+ "l_x_c=%d l_x_max=%d l_x_min=%d\n"
+ "l_y_c=%d l_y_max=%d l_y_min=%d\n"
+ "r_x_c=%d r_x_max=%d r_x_min=%d\n"
+ "r_y_c=%d r_y_max=%d r_y_min=%d\n",
+ ctlr->left_stick_cal_x.center,
+ ctlr->left_stick_cal_x.max,
+ ctlr->left_stick_cal_x.min,
+ ctlr->left_stick_cal_y.center,
+ ctlr->left_stick_cal_y.max,
+ ctlr->left_stick_cal_y.min,
+ ctlr->right_stick_cal_x.center,
+ ctlr->right_stick_cal_x.max,
+ ctlr->right_stick_cal_x.min,
+ ctlr->right_stick_cal_y.center,
+ ctlr->right_stick_cal_y.max,
+ ctlr->right_stick_cal_y.min);
+
+ return 0;
+}
+
+static int joycon_set_report_mode(struct joycon_ctlr *ctlr)
+{
+ struct joycon_subcmd_request *req;
+ u8 buffer[sizeof(*req) + 1] = { 0 };
+
+ req = (struct joycon_subcmd_request *)buffer;
+ req->subcmd_id = JC_SUBCMD_SET_REPORT_MODE;
+ req->data[0] = 0x30; /* standard, full report mode */
+
+ hid_dbg(ctlr->hdev, "setting controller report mode\n");
+ return joycon_send_subcmd(ctlr, req, 1);
+}
+
+static s32 joycon_map_stick_val(struct joycon_stick_cal *cal, s32 val)
+{
+ s32 center = cal->center;
+ s32 min = cal->min;
+ s32 max = cal->max;
+ s32 new_val;
+
+ if (val > center) {
+ new_val = (val - center) * JC_MAX_STICK_MAG;
+ new_val /= (max - center);
+ } else {
+ new_val = (center - val) * -JC_MAX_STICK_MAG;
+ new_val /= (center - min);
+ }
+ new_val = clamp(new_val, (s32)-JC_MAX_STICK_MAG, (s32)JC_MAX_STICK_MAG);
+ return new_val;
+}
+
+static void joycon_parse_report(struct joycon_ctlr *ctlr,
+ struct joycon_input_report *rep)
+{
+ struct input_dev *dev = ctlr->input;
+ u32 btns;
+ u32 id = ctlr->hdev->product;
+
+ btns = hid_field_extract(ctlr->hdev, rep->button_status, 0, 24);
+
+ if (id != USB_DEVICE_ID_NINTENDO_JOYCONR) {
+ u16 raw_x;
+ u16 raw_y;
+ s32 x;
+ s32 y;
+
+ /* get raw stick values */
+ raw_x = hid_field_extract(ctlr->hdev, rep->left_stick, 0, 12);
+ raw_y = hid_field_extract(ctlr->hdev,
+ rep->left_stick + 1, 4, 12);
+ /* map the stick values */
+ x = joycon_map_stick_val(&ctlr->left_stick_cal_x, raw_x);
+ y = -joycon_map_stick_val(&ctlr->left_stick_cal_y, raw_y);
+ /* report sticks */
+ input_report_abs(dev, ABS_X, x);
+ input_report_abs(dev, ABS_Y, y);
+
+ /* report buttons */
+ input_report_key(dev, BTN_TL, btns & JC_BTN_L);
+ input_report_key(dev, BTN_TL2, btns & JC_BTN_ZL);
+ if (id != USB_DEVICE_ID_NINTENDO_PROCON) {
+ /* Report the S buttons as the non-existent triggers */
+ input_report_key(dev, BTN_TR, btns & JC_BTN_SL_L);
+ input_report_key(dev, BTN_TR2, btns & JC_BTN_SR_L);
+ }
+ input_report_key(dev, BTN_SELECT, btns & JC_BTN_MINUS);
+ input_report_key(dev, BTN_THUMBL, btns & JC_BTN_LSTICK);
+ input_report_key(dev, BTN_Z, btns & JC_BTN_CAP);
+ input_report_key(dev, BTN_DPAD_DOWN, btns & JC_BTN_DOWN);
+ input_report_key(dev, BTN_DPAD_UP, btns & JC_BTN_UP);
+ input_report_key(dev, BTN_DPAD_RIGHT, btns & JC_BTN_RIGHT);
+ input_report_key(dev, BTN_DPAD_LEFT, btns & JC_BTN_LEFT);
+ }
+ if (id != USB_DEVICE_ID_NINTENDO_JOYCONL) {
+ u16 raw_x;
+ u16 raw_y;
+ s32 x;
+ s32 y;
+
+ /* get raw stick values */
+ raw_x = hid_field_extract(ctlr->hdev, rep->right_stick, 0, 12);
+ raw_y = hid_field_extract(ctlr->hdev,
+ rep->right_stick + 1, 4, 12);
+ /* map stick values */
+ x = joycon_map_stick_val(&ctlr->right_stick_cal_x, raw_x);
+ y = -joycon_map_stick_val(&ctlr->right_stick_cal_y, raw_y);
+ /* report sticks */
+ input_report_abs(dev, ABS_RX, x);
+ input_report_abs(dev, ABS_RY, y);
+
+ /* report buttons */
+ input_report_key(dev, BTN_TR, btns & JC_BTN_R);
+ input_report_key(dev, BTN_TR2, btns & JC_BTN_ZR);
+ if (id != USB_DEVICE_ID_NINTENDO_PROCON) {
+ /* Report the S buttons as the non-existent triggers */
+ input_report_key(dev, BTN_TL, btns & JC_BTN_SL_R);
+ input_report_key(dev, BTN_TL2, btns & JC_BTN_SR_R);
+ }
+ input_report_key(dev, BTN_START, btns & JC_BTN_PLUS);
+ input_report_key(dev, BTN_THUMBR, btns & JC_BTN_RSTICK);
+ input_report_key(dev, BTN_MODE, btns & JC_BTN_HOME);
+ input_report_key(dev, BTN_WEST, btns & JC_BTN_Y);
+ input_report_key(dev, BTN_NORTH, btns & JC_BTN_X);
+ input_report_key(dev, BTN_EAST, btns & JC_BTN_A);
+ input_report_key(dev, BTN_SOUTH, btns & JC_BTN_B);
+ }
+
+ input_sync(dev);
+}
+
+
+static const unsigned int joycon_button_inputs_l[] = {
+ BTN_SELECT, BTN_Z, BTN_THUMBL,
+ BTN_DPAD_UP, BTN_DPAD_DOWN, BTN_DPAD_LEFT, BTN_DPAD_RIGHT,
+ BTN_TL, BTN_TL2,
+ 0 /* 0 signals end of array */
+};
+
+static const unsigned int joycon_button_inputs_r[] = {
+ BTN_START, BTN_MODE, BTN_THUMBR,
+ BTN_SOUTH, BTN_EAST, BTN_NORTH, BTN_WEST,
+ BTN_TR, BTN_TR2,
+ 0 /* 0 signals end of array */
+};
+
+static DEFINE_MUTEX(joycon_input_num_mutex);
+static int joycon_input_create(struct joycon_ctlr *ctlr)
+{
+ struct hid_device *hdev;
+ static int input_num = 1;
+ const char *name;
+ int ret;
+ int i;
+
+ hdev = ctlr->hdev;
+
+ switch (hdev->product) {
+ case USB_DEVICE_ID_NINTENDO_PROCON:
+ name = "Nintendo Switch Pro Controller";
+ break;
+ case USB_DEVICE_ID_NINTENDO_JOYCONL:
+ name = "Nintendo Switch Left Joy-Con";
+ break;
+ case USB_DEVICE_ID_NINTENDO_JOYCONR:
+ name = "Nintendo Switch Right Joy-Con";
+ break;
+ default: /* Should be impossible */
+ hid_err(hdev, "Invalid hid product\n");
+ return -EINVAL;
+ }
+
+ ctlr->input = devm_input_allocate_device(&hdev->dev);
+ if (!ctlr->input)
+ return -ENOMEM;
+ ctlr->input->id.bustype = hdev->bus;
+ ctlr->input->id.vendor = hdev->vendor;
+ ctlr->input->id.product = hdev->product;
+ ctlr->input->id.version = hdev->version;
+ ctlr->input->name = name;
+ input_set_drvdata(ctlr->input, ctlr);
+
+
+ /* set up sticks */
+ if (hdev->product != USB_DEVICE_ID_NINTENDO_JOYCONR) {
+ input_set_abs_params(ctlr->input, ABS_X,
+ -JC_MAX_STICK_MAG, JC_MAX_STICK_MAG,
+ JC_STICK_FUZZ, JC_STICK_FLAT);
+ input_set_abs_params(ctlr->input, ABS_Y,
+ -JC_MAX_STICK_MAG, JC_MAX_STICK_MAG,
+ JC_STICK_FUZZ, JC_STICK_FLAT);
+ }
+ if (hdev->product != USB_DEVICE_ID_NINTENDO_JOYCONL) {
+ input_set_abs_params(ctlr->input, ABS_RX,
+ -JC_MAX_STICK_MAG, JC_MAX_STICK_MAG,
+ JC_STICK_FUZZ, JC_STICK_FLAT);
+ input_set_abs_params(ctlr->input, ABS_RY,
+ -JC_MAX_STICK_MAG, JC_MAX_STICK_MAG,
+ JC_STICK_FUZZ, JC_STICK_FLAT);
+ }
+
+ /* set up buttons */
+ if (hdev->product != USB_DEVICE_ID_NINTENDO_JOYCONR) {
+ for (i = 0; joycon_button_inputs_l[i] > 0; i++)
+ input_set_capability(ctlr->input, EV_KEY,
+ joycon_button_inputs_l[i]);
+ }
+ if (hdev->product != USB_DEVICE_ID_NINTENDO_JOYCONL) {
+ for (i = 0; joycon_button_inputs_r[i] > 0; i++)
+ input_set_capability(ctlr->input, EV_KEY,
+ joycon_button_inputs_r[i]);
+ }
+
+ ret = input_register_device(ctlr->input);
+ if (ret)
+ return ret;
+
+ /* Set the default controller player leds based on controller number */
+ mutex_lock(&joycon_input_num_mutex);
+ mutex_lock(&ctlr->output_mutex);
+ ret = joycon_set_player_leds(ctlr, 0, 0xF >> (4 - input_num));
+ if (ret)
+ hid_warn(ctlr->hdev, "Failed to set leds; ret=%d\n", ret);
+ mutex_unlock(&ctlr->output_mutex);
+ if (++input_num > 4)
+ input_num = 1;
+ mutex_unlock(&joycon_input_num_mutex);
+
+ return 0;
+}
+
+/* Common handler for parsing inputs */
+static int joycon_ctlr_read_handler(struct joycon_ctlr *ctlr, u8 *data,
+ int size)
+{
+ int ret = 0;
+
+ if (data[0] == JC_INPUT_SUBCMD_REPLY || data[0] == JC_INPUT_IMU_DATA ||
+ data[0] == JC_INPUT_MCU_DATA) {
+ if (size >= 12) /* make sure it contains the input report */
+ joycon_parse_report(ctlr,
+ (struct joycon_input_report *)data);
+ }
+
+ return ret;
+}
+
+static int joycon_ctlr_handle_event(struct joycon_ctlr *ctlr, u8 *data,
+ int size)
+{
+ int ret = 0;
+ bool match = false;
+ struct joycon_input_report *report;
+
+ if (unlikely(mutex_is_locked(&ctlr->output_mutex)) &&
+ ctlr->msg_type != JOYCON_MSG_TYPE_NONE) {
+ switch (ctlr->msg_type) {
+ case JOYCON_MSG_TYPE_USB:
+ if (size < 2)
+ break;
+ if (data[0] == JC_INPUT_USB_RESPONSE &&
+ data[1] == ctlr->usb_ack_match)
+ match = true;
+ break;
+ case JOYCON_MSG_TYPE_SUBCMD:
+ if (size < sizeof(struct joycon_input_report) ||
+ data[0] != JC_INPUT_SUBCMD_REPLY)
+ break;
+ report = (struct joycon_input_report *)data;
+ if (report->reply.id == ctlr->subcmd_ack_match)
+ match = true;
+ break;
+ default:
+ break;
+ }
+
+ if (match) {
+ memcpy(ctlr->input_buf, data,
+ min(size, (int)JC_MAX_RESP_SIZE));
+ ctlr->msg_type = JOYCON_MSG_TYPE_NONE;
+ ctlr->received_resp = true;
+ wake_up(&ctlr->wait);
+
+ /* This message has been handled */
+ return 1;
+ }
+ }
+
+ if (ctlr->ctlr_state == JOYCON_CTLR_STATE_READ)
+ ret = joycon_ctlr_read_handler(ctlr, data, size);
+
+ return ret;
+}
+
+static int nintendo_hid_event(struct hid_device *hdev,
+ struct hid_report *report, u8 *raw_data, int size)
+{
+ struct joycon_ctlr *ctlr = hid_get_drvdata(hdev);
+
+ if (size < 1)
+ return -EINVAL;
+
+ return joycon_ctlr_handle_event(ctlr, raw_data, size);
+}
+
+static int nintendo_hid_probe(struct hid_device *hdev,
+ const struct hid_device_id *id)
+{
+ int ret;
+ struct joycon_ctlr *ctlr;
+
+ hid_dbg(hdev, "probe - start\n");
+
+ ctlr = devm_kzalloc(&hdev->dev, sizeof(*ctlr), GFP_KERNEL);
+ if (!ctlr) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ ctlr->hdev = hdev;
+ ctlr->ctlr_state = JOYCON_CTLR_STATE_INIT;
+ hid_set_drvdata(hdev, ctlr);
+ mutex_init(&ctlr->output_mutex);
+ init_waitqueue_head(&ctlr->wait);
+
+ ret = hid_parse(hdev);
+ if (ret) {
+ hid_err(hdev, "HID parse failed\n");
+ goto err;
+ }
+
+ ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
+ if (ret) {
+ hid_err(hdev, "HW start failed\n");
+ goto err;
+ }
+
+ ret = hid_hw_open(hdev);
+ if (ret) {
+ hid_err(hdev, "cannot start hardware I/O\n");
+ goto err_stop;
+ }
+
+ hid_device_io_start(hdev);
+
+ /* Initialize the controller */
+ mutex_lock(&ctlr->output_mutex);
+ /* if handshake command fails, assume ble pro controller */
+ if (hdev->product == USB_DEVICE_ID_NINTENDO_PROCON &&
+ !joycon_send_usb(ctlr, JC_USB_CMD_HANDSHAKE)) {
+ hid_dbg(hdev, "detected USB controller\n");
+ /* set baudrate for improved latency */
+ ret = joycon_send_usb(ctlr, JC_USB_CMD_BAUDRATE_3M);
+ if (ret) {
+ hid_err(hdev, "Failed to set baudrate; ret=%d\n", ret);
+ goto err_mutex;
+ }
+ /* handshake */
+ ret = joycon_send_usb(ctlr, JC_USB_CMD_HANDSHAKE);
+ if (ret) {
+ hid_err(hdev, "Failed handshake; ret=%d\n", ret);
+ goto err_mutex;
+ }
+ /*
+ * Set no timeout (to keep controller in USB mode).
+ * This doesn't send a response, so ignore the timeout.
+ */
+ joycon_send_usb(ctlr, JC_USB_CMD_NO_TIMEOUT);
+ }
+
+ /* get controller calibration data, and parse it */
+ ret = joycon_request_calibration(ctlr);
+ if (ret) {
+ /*
+ * We can function with default calibration, but it may be
+ * inaccurate. Provide a warning, and continue on.
+ */
+ hid_warn(hdev, "Analog stick positions may be inaccurate\n");
+ }
+
+ /* Set the reporting mode to 0x30, which is the full report mode */
+ ret = joycon_set_report_mode(ctlr);
+ if (ret) {
+ hid_err(hdev, "Failed to set report mode; ret=%d\n", ret);
+ goto err_mutex;
+ }
+
+ mutex_unlock(&ctlr->output_mutex);
+
+ ret = joycon_input_create(ctlr);
+ if (ret) {
+ hid_err(hdev, "Failed to create input device; ret=%d\n", ret);
+ goto err_close;
+ }
+
+ ctlr->ctlr_state = JOYCON_CTLR_STATE_READ;
+
+ hid_dbg(hdev, "probe - success\n");
+ return 0;
+
+err_mutex:
+ mutex_unlock(&ctlr->output_mutex);
+err_close:
+ hid_hw_close(hdev);
+err_stop:
+ hid_hw_stop(hdev);
+err:
+ hid_err(hdev, "probe - fail = %d\n", ret);
+ return ret;
+}
+
+static void nintendo_hid_remove(struct hid_device *hdev)
+{
+ hid_dbg(hdev, "remove\n");
+ hid_hw_close(hdev);
+ hid_hw_stop(hdev);
+}
+
+static const struct hid_device_id nintendo_hid_devices[] = {
+ { HID_USB_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_PROCON) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_PROCON) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_JOYCONL) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO,
+ USB_DEVICE_ID_NINTENDO_JOYCONR) },
+ { }
+};
+MODULE_DEVICE_TABLE(hid, nintendo_hid_devices);
+
+static struct hid_driver nintendo_hid_driver = {
+ .name = "nintendo",
+ .id_table = nintendo_hid_devices,
+ .probe = nintendo_hid_probe,
+ .remove = nintendo_hid_remove,
+ .raw_event = nintendo_hid_event,
+};
+module_hid_driver(nintendo_hid_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel J. Ogorchock <djogorchock@gmail.com>");
+MODULE_DESCRIPTION("Driver for Nintendo Switch Controllers");
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 9633d7a..c8b07a1 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -36,6 +36,8 @@
#include <linux/list.h>
#include <linux/idr.h>
#include <linux/input/mt.h>
+#include <linux/crc32.h>
+#include <asm/unaligned.h>
#include "hid-ids.h"
@@ -46,19 +48,21 @@
#define PS3REMOTE BIT(4)
#define DUALSHOCK4_CONTROLLER_USB BIT(5)
#define DUALSHOCK4_CONTROLLER_BT BIT(6)
-#define MOTION_CONTROLLER_USB BIT(7)
-#define MOTION_CONTROLLER_BT BIT(8)
-#define NAVIGATION_CONTROLLER_USB BIT(9)
-#define NAVIGATION_CONTROLLER_BT BIT(10)
-#define SINO_LITE_CONTROLLER BIT(11)
-#define FUTUREMAX_DANCE_MAT BIT(12)
+#define DUALSHOCK4_DONGLE BIT(7)
+#define MOTION_CONTROLLER_USB BIT(8)
+#define MOTION_CONTROLLER_BT BIT(9)
+#define NAVIGATION_CONTROLLER_USB BIT(10)
+#define NAVIGATION_CONTROLLER_BT BIT(11)
+#define SINO_LITE_CONTROLLER BIT(12)
+#define FUTUREMAX_DANCE_MAT BIT(13)
#define SIXAXIS_CONTROLLER (SIXAXIS_CONTROLLER_USB | SIXAXIS_CONTROLLER_BT)
#define MOTION_CONTROLLER (MOTION_CONTROLLER_USB | MOTION_CONTROLLER_BT)
#define NAVIGATION_CONTROLLER (NAVIGATION_CONTROLLER_USB |\
NAVIGATION_CONTROLLER_BT)
#define DUALSHOCK4_CONTROLLER (DUALSHOCK4_CONTROLLER_USB |\
- DUALSHOCK4_CONTROLLER_BT)
+ DUALSHOCK4_CONTROLLER_BT | \
+ DUALSHOCK4_DONGLE)
#define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER | BUZZ_CONTROLLER |\
DUALSHOCK4_CONTROLLER | MOTION_CONTROLLER |\
NAVIGATION_CONTROLLER)
@@ -71,89 +75,6 @@
#define MAX_LEDS 4
-/*
- * The Sixaxis reports both digital and analog values for each button on the
- * controller except for Start, Select and the PS button. The controller ends
- * up reporting 27 axes which causes them to spill over into the multi-touch
- * axis values. Additionally, the controller only has 20 actual, physical axes
- * so there are several unused axes in between the used ones.
- */
-static u8 sixaxis_rdesc[] = {
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x04, /* Usage (Joystick), */
- 0xA1, 0x01, /* Collection (Application), */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0x01, /* Report ID (1), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x01, /* Report Count (1), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x81, 0x03, /* Input (Constant, Variable), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x13, /* Report Count (19), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x01, /* Logical Maximum (1), */
- 0x35, 0x00, /* Physical Minimum (0), */
- 0x45, 0x01, /* Physical Maximum (1), */
- 0x05, 0x09, /* Usage Page (Button), */
- 0x19, 0x01, /* Usage Minimum (01h), */
- 0x29, 0x13, /* Usage Maximum (13h), */
- 0x81, 0x02, /* Input (Variable), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x0D, /* Report Count (13), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x81, 0x03, /* Input (Constant, Variable), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xA1, 0x00, /* Collection (Physical), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x04, /* Report Count (4), */
- 0x35, 0x00, /* Physical Minimum (0), */
- 0x46, 0xFF, 0x00, /* Physical Maximum (255), */
- 0x09, 0x30, /* Usage (X), */
- 0x09, 0x31, /* Usage (Y), */
- 0x09, 0x32, /* Usage (Z), */
- 0x09, 0x35, /* Usage (Rz), */
- 0x81, 0x02, /* Input (Variable), */
- 0xC0, /* End Collection, */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x95, 0x13, /* Report Count (19), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0x81, 0x02, /* Input (Variable), */
- 0x95, 0x0C, /* Report Count (12), */
- 0x81, 0x01, /* Input (Constant), */
- 0x75, 0x10, /* Report Size (16), */
- 0x95, 0x04, /* Report Count (4), */
- 0x26, 0xFF, 0x03, /* Logical Maximum (1023), */
- 0x46, 0xFF, 0x03, /* Physical Maximum (1023), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0x81, 0x02, /* Input (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0x02, /* Report ID (2), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0xEE, /* Report ID (238), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0xEF, /* Report ID (239), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xC0 /* End Collection */
-};
/* PS/3 Motion controller */
static u8 motion_rdesc[] = {
@@ -252,567 +173,6 @@ static u8 motion_rdesc[] = {
0xC0 /* End Collection */
};
-/* PS/3 Navigation controller */
-static u8 navigation_rdesc[] = {
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x04, /* Usage (Joystick), */
- 0xA1, 0x01, /* Collection (Application), */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0x01, /* Report ID (1), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x01, /* Report Count (1), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x81, 0x03, /* Input (Constant, Variable), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x13, /* Report Count (19), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x01, /* Logical Maximum (1), */
- 0x35, 0x00, /* Physical Minimum (0), */
- 0x45, 0x01, /* Physical Maximum (1), */
- 0x05, 0x09, /* Usage Page (Button), */
- 0x19, 0x01, /* Usage Minimum (01h), */
- 0x29, 0x13, /* Usage Maximum (13h), */
- 0x81, 0x02, /* Input (Variable), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x0D, /* Report Count (13), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x81, 0x03, /* Input (Constant, Variable), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xA1, 0x00, /* Collection (Physical), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x02, /* Report Count (2), */
- 0x35, 0x00, /* Physical Minimum (0), */
- 0x46, 0xFF, 0x00, /* Physical Maximum (255), */
- 0x09, 0x30, /* Usage (X), */
- 0x09, 0x31, /* Usage (Y), */
- 0x81, 0x02, /* Input (Variable), */
- 0xC0, /* End Collection, */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x95, 0x06, /* Report Count (6), */
- 0x81, 0x03, /* Input (Constant, Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x05, /* Report Count (5), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x95, 0x01, /* Report Count (1), */
- 0x81, 0x02, /* Input (Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x95, 0x01, /* Report Count (1), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x95, 0x1E, /* Report Count (24), */
- 0x81, 0x02, /* Input (Variable), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0x91, 0x02, /* Output (Variable), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0x02, /* Report ID (2), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0xEE, /* Report ID (238), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xA1, 0x02, /* Collection (Logical), */
- 0x85, 0xEF, /* Report ID (239), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x30, /* Report Count (48), */
- 0x09, 0x01, /* Usage (Pointer), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0, /* End Collection, */
- 0xC0 /* End Collection */
-};
-
-/*
- * The default descriptor doesn't provide mapping for the accelerometers
- * or orientation sensors. This fixed descriptor maps the accelerometers
- * to usage values 0x40, 0x41 and 0x42 and maps the orientation sensors
- * to usage values 0x43, 0x44 and 0x45.
- */
-static u8 dualshock4_usb_rdesc[] = {
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x05, /* Usage (Gamepad), */
- 0xA1, 0x01, /* Collection (Application), */
- 0x85, 0x01, /* Report ID (1), */
- 0x09, 0x30, /* Usage (X), */
- 0x09, 0x31, /* Usage (Y), */
- 0x09, 0x32, /* Usage (Z), */
- 0x09, 0x35, /* Usage (Rz), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x04, /* Report Count (4), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x39, /* Usage (Hat Switch), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x07, /* Logical Maximum (7), */
- 0x35, 0x00, /* Physical Minimum (0), */
- 0x46, 0x3B, 0x01, /* Physical Maximum (315), */
- 0x65, 0x14, /* Unit (Degrees), */
- 0x75, 0x04, /* Report Size (4), */
- 0x95, 0x01, /* Report Count (1), */
- 0x81, 0x42, /* Input (Variable, Null State), */
- 0x65, 0x00, /* Unit, */
- 0x05, 0x09, /* Usage Page (Button), */
- 0x19, 0x01, /* Usage Minimum (01h), */
- 0x29, 0x0E, /* Usage Maximum (0Eh), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x01, /* Logical Maximum (1), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x0E, /* Report Count (14), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x20, /* Usage (20h), */
- 0x75, 0x06, /* Report Size (6), */
- 0x95, 0x01, /* Report Count (1), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x3F, /* Logical Maximum (63), */
- 0x81, 0x02, /* Input (Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x33, /* Usage (Rx), */
- 0x09, 0x34, /* Usage (Ry), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x02, /* Report Count (2), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x21, /* Usage (21h), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x19, 0x40, /* Usage Minimum (40h), */
- 0x29, 0x42, /* Usage Maximum (42h), */
- 0x16, 0x00, 0x80, /* Logical Minimum (-32768), */
- 0x26, 0x00, 0x7F, /* Logical Maximum (32767), */
- 0x75, 0x10, /* Report Size (16), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x19, 0x43, /* Usage Minimum (43h), */
- 0x29, 0x45, /* Usage Maximum (45h), */
- 0x16, 0x00, 0xE0, /* Logical Minimum (-8192), */
- 0x26, 0xFF, 0x1F, /* Logical Maximum (8191), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x21, /* Usage (21h), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x27, /* Report Count (39), */
- 0x81, 0x02, /* Input (Variable), */
- 0x85, 0x05, /* Report ID (5), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x1F, /* Report Count (31), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x04, /* Report ID (4), */
- 0x09, 0x23, /* Usage (23h), */
- 0x95, 0x24, /* Report Count (36), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x02, /* Report ID (2), */
- 0x09, 0x24, /* Usage (24h), */
- 0x95, 0x24, /* Report Count (36), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x08, /* Report ID (8), */
- 0x09, 0x25, /* Usage (25h), */
- 0x95, 0x03, /* Report Count (3), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x10, /* Report ID (16), */
- 0x09, 0x26, /* Usage (26h), */
- 0x95, 0x04, /* Report Count (4), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x11, /* Report ID (17), */
- 0x09, 0x27, /* Usage (27h), */
- 0x95, 0x02, /* Report Count (2), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x12, /* Report ID (18), */
- 0x06, 0x02, 0xFF, /* Usage Page (FF02h), */
- 0x09, 0x21, /* Usage (21h), */
- 0x95, 0x0F, /* Report Count (15), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x13, /* Report ID (19), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x16, /* Report Count (22), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x14, /* Report ID (20), */
- 0x06, 0x05, 0xFF, /* Usage Page (FF05h), */
- 0x09, 0x20, /* Usage (20h), */
- 0x95, 0x10, /* Report Count (16), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x15, /* Report ID (21), */
- 0x09, 0x21, /* Usage (21h), */
- 0x95, 0x2C, /* Report Count (44), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x06, 0x80, 0xFF, /* Usage Page (FF80h), */
- 0x85, 0x80, /* Report ID (128), */
- 0x09, 0x20, /* Usage (20h), */
- 0x95, 0x06, /* Report Count (6), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x81, /* Report ID (129), */
- 0x09, 0x21, /* Usage (21h), */
- 0x95, 0x06, /* Report Count (6), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x82, /* Report ID (130), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x05, /* Report Count (5), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x83, /* Report ID (131), */
- 0x09, 0x23, /* Usage (23h), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x84, /* Report ID (132), */
- 0x09, 0x24, /* Usage (24h), */
- 0x95, 0x04, /* Report Count (4), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x85, /* Report ID (133), */
- 0x09, 0x25, /* Usage (25h), */
- 0x95, 0x06, /* Report Count (6), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x86, /* Report ID (134), */
- 0x09, 0x26, /* Usage (26h), */
- 0x95, 0x06, /* Report Count (6), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x87, /* Report ID (135), */
- 0x09, 0x27, /* Usage (27h), */
- 0x95, 0x23, /* Report Count (35), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x88, /* Report ID (136), */
- 0x09, 0x28, /* Usage (28h), */
- 0x95, 0x22, /* Report Count (34), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x89, /* Report ID (137), */
- 0x09, 0x29, /* Usage (29h), */
- 0x95, 0x02, /* Report Count (2), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x90, /* Report ID (144), */
- 0x09, 0x30, /* Usage (30h), */
- 0x95, 0x05, /* Report Count (5), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x91, /* Report ID (145), */
- 0x09, 0x31, /* Usage (31h), */
- 0x95, 0x03, /* Report Count (3), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x92, /* Report ID (146), */
- 0x09, 0x32, /* Usage (32h), */
- 0x95, 0x03, /* Report Count (3), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x93, /* Report ID (147), */
- 0x09, 0x33, /* Usage (33h), */
- 0x95, 0x0C, /* Report Count (12), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA0, /* Report ID (160), */
- 0x09, 0x40, /* Usage (40h), */
- 0x95, 0x06, /* Report Count (6), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA1, /* Report ID (161), */
- 0x09, 0x41, /* Usage (41h), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA2, /* Report ID (162), */
- 0x09, 0x42, /* Usage (42h), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA3, /* Report ID (163), */
- 0x09, 0x43, /* Usage (43h), */
- 0x95, 0x30, /* Report Count (48), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA4, /* Report ID (164), */
- 0x09, 0x44, /* Usage (44h), */
- 0x95, 0x0D, /* Report Count (13), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA5, /* Report ID (165), */
- 0x09, 0x45, /* Usage (45h), */
- 0x95, 0x15, /* Report Count (21), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA6, /* Report ID (166), */
- 0x09, 0x46, /* Usage (46h), */
- 0x95, 0x15, /* Report Count (21), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF0, /* Report ID (240), */
- 0x09, 0x47, /* Usage (47h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF1, /* Report ID (241), */
- 0x09, 0x48, /* Usage (48h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF2, /* Report ID (242), */
- 0x09, 0x49, /* Usage (49h), */
- 0x95, 0x0F, /* Report Count (15), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA7, /* Report ID (167), */
- 0x09, 0x4A, /* Usage (4Ah), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA8, /* Report ID (168), */
- 0x09, 0x4B, /* Usage (4Bh), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA9, /* Report ID (169), */
- 0x09, 0x4C, /* Usage (4Ch), */
- 0x95, 0x08, /* Report Count (8), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAA, /* Report ID (170), */
- 0x09, 0x4E, /* Usage (4Eh), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAB, /* Report ID (171), */
- 0x09, 0x4F, /* Usage (4Fh), */
- 0x95, 0x39, /* Report Count (57), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAC, /* Report ID (172), */
- 0x09, 0x50, /* Usage (50h), */
- 0x95, 0x39, /* Report Count (57), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAD, /* Report ID (173), */
- 0x09, 0x51, /* Usage (51h), */
- 0x95, 0x0B, /* Report Count (11), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAE, /* Report ID (174), */
- 0x09, 0x52, /* Usage (52h), */
- 0x95, 0x01, /* Report Count (1), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xAF, /* Report ID (175), */
- 0x09, 0x53, /* Usage (53h), */
- 0x95, 0x02, /* Report Count (2), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xB0, /* Report ID (176), */
- 0x09, 0x54, /* Usage (54h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0 /* End Collection */
-};
-
-/*
- * The default behavior of the Dualshock 4 is to send reports using report
- * type 1 when running over Bluetooth. However, when feature report 2 is
- * requested during the controller initialization it starts sending input
- * reports in report 17. Since report 17 is undefined in the default HID
- * descriptor the button and axis definitions must be moved to report 17 or
- * the HID layer won't process the received input.
- */
-static u8 dualshock4_bt_rdesc[] = {
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x05, /* Usage (Gamepad), */
- 0xA1, 0x01, /* Collection (Application), */
- 0x85, 0x01, /* Report ID (1), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x0A, /* Report Count (9), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x04, 0xFF, /* Usage Page (FF04h), */
- 0x85, 0x02, /* Report ID (2), */
- 0x09, 0x24, /* Usage (24h), */
- 0x95, 0x24, /* Report Count (36), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA3, /* Report ID (163), */
- 0x09, 0x25, /* Usage (25h), */
- 0x95, 0x30, /* Report Count (48), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x05, /* Report ID (5), */
- 0x09, 0x26, /* Usage (26h), */
- 0x95, 0x28, /* Report Count (40), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x06, /* Report ID (6), */
- 0x09, 0x27, /* Usage (27h), */
- 0x95, 0x34, /* Report Count (52), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x07, /* Report ID (7), */
- 0x09, 0x28, /* Usage (28h), */
- 0x95, 0x30, /* Report Count (48), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x08, /* Report ID (8), */
- 0x09, 0x29, /* Usage (29h), */
- 0x95, 0x2F, /* Report Count (47), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x06, 0x03, 0xFF, /* Usage Page (FF03h), */
- 0x85, 0x03, /* Report ID (3), */
- 0x09, 0x21, /* Usage (21h), */
- 0x95, 0x26, /* Report Count (38), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x04, /* Report ID (4), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x2E, /* Report Count (46), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF0, /* Report ID (240), */
- 0x09, 0x47, /* Usage (47h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF1, /* Report ID (241), */
- 0x09, 0x48, /* Usage (48h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xF2, /* Report ID (242), */
- 0x09, 0x49, /* Usage (49h), */
- 0x95, 0x0F, /* Report Count (15), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x11, /* Report ID (17), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x20, /* Usage (20h), */
- 0x95, 0x02, /* Report Count (2), */
- 0x81, 0x02, /* Input (Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x30, /* Usage (X), */
- 0x09, 0x31, /* Usage (Y), */
- 0x09, 0x32, /* Usage (Z), */
- 0x09, 0x35, /* Usage (Rz), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x04, /* Report Count (4), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x39, /* Usage (Hat Switch), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x07, /* Logical Maximum (7), */
- 0x75, 0x04, /* Report Size (4), */
- 0x95, 0x01, /* Report Count (1), */
- 0x81, 0x42, /* Input (Variable, Null State), */
- 0x05, 0x09, /* Usage Page (Button), */
- 0x19, 0x01, /* Usage Minimum (01h), */
- 0x29, 0x0E, /* Usage Maximum (0Eh), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x25, 0x01, /* Logical Maximum (1), */
- 0x75, 0x01, /* Report Size (1), */
- 0x95, 0x0E, /* Report Count (14), */
- 0x81, 0x02, /* Input (Variable), */
- 0x75, 0x06, /* Report Size (6), */
- 0x95, 0x01, /* Report Count (1), */
- 0x81, 0x01, /* Input (Constant), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x09, 0x33, /* Usage (Rx), */
- 0x09, 0x34, /* Usage (Ry), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x02, /* Report Count (2), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x20, /* Usage (20h), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x05, 0x01, /* Usage Page (Desktop), */
- 0x19, 0x40, /* Usage Minimum (40h), */
- 0x29, 0x42, /* Usage Maximum (42h), */
- 0x16, 0x00, 0x80, /* Logical Minimum (-32768), */
- 0x26, 0x00, 0x7F, /* Logical Maximum (32767), */
- 0x75, 0x10, /* Report Size (16), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x19, 0x43, /* Usage Minimum (43h), */
- 0x29, 0x45, /* Usage Maximum (45h), */
- 0x16, 0x00, 0xE0, /* Logical Minimum (-8192), */
- 0x26, 0xFF, 0x1F, /* Logical Maximum (8191), */
- 0x95, 0x03, /* Report Count (3), */
- 0x81, 0x02, /* Input (Variable), */
- 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
- 0x09, 0x20, /* Usage (20h), */
- 0x15, 0x00, /* Logical Minimum (0), */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x31, /* Report Count (51), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x21, /* Usage (21h), */
- 0x75, 0x08, /* Report Size (8), */
- 0x95, 0x4D, /* Report Count (77), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x12, /* Report ID (18), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x8D, /* Report Count (141), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x23, /* Usage (23h), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x13, /* Report ID (19), */
- 0x09, 0x24, /* Usage (24h), */
- 0x95, 0xCD, /* Report Count (205), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x25, /* Usage (25h), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x14, /* Report ID (20), */
- 0x09, 0x26, /* Usage (26h), */
- 0x96, 0x0D, 0x01, /* Report Count (269), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x27, /* Usage (27h), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x15, /* Report ID (21), */
- 0x09, 0x28, /* Usage (28h), */
- 0x96, 0x4D, 0x01, /* Report Count (333), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x29, /* Usage (29h), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x16, /* Report ID (22), */
- 0x09, 0x2A, /* Usage (2Ah), */
- 0x96, 0x8D, 0x01, /* Report Count (397), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x2B, /* Usage (2Bh), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x17, /* Report ID (23), */
- 0x09, 0x2C, /* Usage (2Ch), */
- 0x96, 0xCD, 0x01, /* Report Count (461), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x2D, /* Usage (2Dh), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x18, /* Report ID (24), */
- 0x09, 0x2E, /* Usage (2Eh), */
- 0x96, 0x0D, 0x02, /* Report Count (525), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x2F, /* Usage (2Fh), */
- 0x91, 0x02, /* Output (Variable), */
- 0x85, 0x19, /* Report ID (25), */
- 0x09, 0x30, /* Usage (30h), */
- 0x96, 0x22, 0x02, /* Report Count (546), */
- 0x81, 0x02, /* Input (Variable), */
- 0x09, 0x31, /* Usage (31h), */
- 0x91, 0x02, /* Output (Variable), */
- 0x06, 0x80, 0xFF, /* Usage Page (FF80h), */
- 0x85, 0x82, /* Report ID (130), */
- 0x09, 0x22, /* Usage (22h), */
- 0x95, 0x3F, /* Report Count (63), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x83, /* Report ID (131), */
- 0x09, 0x23, /* Usage (23h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x84, /* Report ID (132), */
- 0x09, 0x24, /* Usage (24h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x90, /* Report ID (144), */
- 0x09, 0x30, /* Usage (30h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x91, /* Report ID (145), */
- 0x09, 0x31, /* Usage (31h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x92, /* Report ID (146), */
- 0x09, 0x32, /* Usage (32h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0x93, /* Report ID (147), */
- 0x09, 0x33, /* Usage (33h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA0, /* Report ID (160), */
- 0x09, 0x40, /* Usage (40h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0x85, 0xA4, /* Report ID (164), */
- 0x09, 0x44, /* Usage (44h), */
- 0xB1, 0x02, /* Feature (Variable), */
- 0xC0 /* End Collection */
-};
-
static u8 ps3remote_rdesc[] = {
0x05, 0x01, /* GUsagePage Generic Desktop */
0x09, 0x05, /* LUsage 0x05 [Game Pad] */
@@ -975,6 +335,97 @@ static const unsigned int buzz_keymap[] = {
[20] = BTN_TRIGGER_HAPPY20,
};
+/* The Navigation controller is a partial DS3 and uses the same HID report
+ * and hence the same keymap indices, however not not all axes/buttons
+ * are physically present. We use the same axis and button mapping as
+ * the DS3, which uses the Linux gamepad spec.
+ */
+static const unsigned int navigation_absmap[] = {
+ [0x30] = ABS_X,
+ [0x31] = ABS_Y,
+ [0x33] = ABS_Z, /* L2 */
+};
+
+/* Buttons not physically available on the device, but still available
+ * in the reports are explicitly set to 0 for documentation purposes.
+ */
+static const unsigned int navigation_keymap[] = {
+ [0x01] = 0, /* Select */
+ [0x02] = BTN_THUMBL, /* L3 */
+ [0x03] = 0, /* R3 */
+ [0x04] = 0, /* Start */
+ [0x05] = BTN_DPAD_UP, /* Up */
+ [0x06] = BTN_DPAD_RIGHT, /* Right */
+ [0x07] = BTN_DPAD_DOWN, /* Down */
+ [0x08] = BTN_DPAD_LEFT, /* Left */
+ [0x09] = BTN_TL2, /* L2 */
+ [0x0a] = 0, /* R2 */
+ [0x0b] = BTN_TL, /* L1 */
+ [0x0c] = 0, /* R1 */
+ [0x0d] = BTN_NORTH, /* Triangle */
+ [0x0e] = BTN_EAST, /* Circle */
+ [0x0f] = BTN_SOUTH, /* Cross */
+ [0x10] = BTN_WEST, /* Square */
+ [0x11] = BTN_MODE, /* PS */
+};
+
+static const unsigned int sixaxis_absmap[] = {
+ [0x30] = ABS_X,
+ [0x31] = ABS_Y,
+ [0x32] = ABS_RX, /* right stick X */
+ [0x35] = ABS_RY, /* right stick Y */
+};
+
+static const unsigned int sixaxis_keymap[] = {
+ [0x01] = BTN_SELECT, /* Select */
+ [0x02] = BTN_THUMBL, /* L3 */
+ [0x03] = BTN_THUMBR, /* R3 */
+ [0x04] = BTN_START, /* Start */
+ [0x05] = BTN_DPAD_UP, /* Up */
+ [0x06] = BTN_DPAD_RIGHT, /* Right */
+ [0x07] = BTN_DPAD_DOWN, /* Down */
+ [0x08] = BTN_DPAD_LEFT, /* Left */
+ [0x09] = BTN_TL2, /* L2 */
+ [0x0a] = BTN_TR2, /* R2 */
+ [0x0b] = BTN_TL, /* L1 */
+ [0x0c] = BTN_TR, /* R1 */
+ [0x0d] = BTN_NORTH, /* Triangle */
+ [0x0e] = BTN_EAST, /* Circle */
+ [0x0f] = BTN_SOUTH, /* Cross */
+ [0x10] = BTN_WEST, /* Square */
+ [0x11] = BTN_MODE, /* PS */
+};
+
+static const unsigned int ds4_absmap[] = {
+ [0x30] = ABS_X,
+ [0x31] = ABS_Y,
+ [0x32] = ABS_RX, /* right stick X */
+ [0x33] = ABS_Z, /* L2 */
+ [0x34] = ABS_RZ, /* R2 */
+ [0x35] = ABS_RY, /* right stick Y */
+};
+
+static const unsigned int ds4_keymap[] = {
+ [0x1] = BTN_WEST, /* Square */
+ [0x2] = BTN_SOUTH, /* Cross */
+ [0x3] = BTN_EAST, /* Circle */
+ [0x4] = BTN_NORTH, /* Triangle */
+ [0x5] = BTN_TL, /* L1 */
+ [0x6] = BTN_TR, /* R1 */
+ [0x7] = BTN_TL2, /* L2 */
+ [0x8] = BTN_TR2, /* R2 */
+ [0x9] = BTN_SELECT, /* Share */
+ [0xa] = BTN_START, /* Options */
+ [0xb] = BTN_THUMBL, /* L3 */
+ [0xc] = BTN_THUMBR, /* R3 */
+ [0xd] = BTN_MODE, /* PS */
+};
+
+static const struct {int x; int y; } ds4_hat_mapping[] = {
+ {0, -1}, {1, -1}, {1, 0}, {1, 1}, {0, 1}, {-1, 1}, {-1, 0}, {-1, -1},
+ {0, 0}
+};
+
static enum power_supply_property sony_battery_props[] = {
POWER_SUPPLY_PROP_PRESENT,
POWER_SUPPLY_PROP_CAPACITY,
@@ -1019,24 +470,75 @@ struct motion_output_report_02 {
u8 rumble;
};
-#define DS4_REPORT_0x02_SIZE 37
-#define DS4_REPORT_0x05_SIZE 32
-#define DS4_REPORT_0x11_SIZE 78
-#define DS4_REPORT_0x81_SIZE 7
+#define DS4_FEATURE_REPORT_0x02_SIZE 37
+#define DS4_FEATURE_REPORT_0x05_SIZE 41
+#define DS4_FEATURE_REPORT_0x81_SIZE 7
+#define DS4_INPUT_REPORT_0x11_SIZE 78
+#define DS4_OUTPUT_REPORT_0x05_SIZE 32
+#define DS4_OUTPUT_REPORT_0x11_SIZE 78
#define SIXAXIS_REPORT_0xF2_SIZE 17
#define SIXAXIS_REPORT_0xF5_SIZE 8
#define MOTION_REPORT_0x02_SIZE 49
+/* Offsets relative to USB input report (0x1). Bluetooth (0x11) requires an
+ * additional +2.
+ */
+#define DS4_INPUT_REPORT_AXIS_OFFSET 1
+#define DS4_INPUT_REPORT_BUTTON_OFFSET 5
+#define DS4_INPUT_REPORT_TIMESTAMP_OFFSET 10
+#define DS4_INPUT_REPORT_GYRO_X_OFFSET 13
+#define DS4_INPUT_REPORT_BATTERY_OFFSET 30
+#define DS4_INPUT_REPORT_TOUCHPAD_OFFSET 33
+
+#define SENSOR_SUFFIX " Motion Sensors"
+#define DS4_TOUCHPAD_SUFFIX " Touchpad"
+
+/* Default to 4ms poll interval, which is same as USB (not adjustable). */
+#define DS4_BT_DEFAULT_POLL_INTERVAL_MS 4
+#define DS4_BT_MAX_POLL_INTERVAL_MS 62
+#define DS4_GYRO_RES_PER_DEG_S 1024
+#define DS4_ACC_RES_PER_G 8192
+
+#define SIXAXIS_INPUT_REPORT_ACC_X_OFFSET 41
+#define SIXAXIS_ACC_RES_PER_G 113
+
static DEFINE_SPINLOCK(sony_dev_list_lock);
static LIST_HEAD(sony_device_list);
static DEFINE_IDA(sony_device_id_allocator);
+/* Used for calibration of DS4 accelerometer and gyro. */
+struct ds4_calibration_data {
+ int abs_code;
+ short bias;
+ /* Calibration requires scaling against a sensitivity value, which is a
+ * float. Store sensitivity as a fraction to limit floating point
+ * calculations until final calibration.
+ */
+ int sens_numer;
+ int sens_denom;
+};
+
+enum ds4_dongle_state {
+ DONGLE_DISCONNECTED,
+ DONGLE_CALIBRATING,
+ DONGLE_CONNECTED,
+ DONGLE_DISABLED
+};
+
+enum sony_worker {
+ SONY_WORKER_STATE,
+ SONY_WORKER_HOTPLUG
+};
+
struct sony_sc {
spinlock_t lock;
struct list_head list_node;
struct hid_device *hdev;
+ struct input_dev *touchpad;
+ struct input_dev *sensor_dev;
struct led_classdev *leds[MAX_LEDS];
unsigned long quirks;
+ struct work_struct hotplug_worker;
struct work_struct state_worker;
void (*send_output_report)(struct sony_sc *);
struct power_supply *battery;
@@ -1050,7 +552,8 @@ struct sony_sc {
#endif
u8 mac_address[6];
- u8 worker_initialized;
+ u8 hotplug_worker_initialized;
+ u8 state_worker_initialized;
u8 defer_initialization;
u8 cable_state;
u8 battery_charging;
@@ -1059,21 +562,76 @@ struct sony_sc {
u8 led_delay_on[MAX_LEDS];
u8 led_delay_off[MAX_LEDS];
u8 led_count;
+
+ bool timestamp_initialized;
+ u16 prev_timestamp;
+ unsigned int timestamp_us;
+
+ u8 ds4_bt_poll_interval;
+ enum ds4_dongle_state ds4_dongle_state;
+ /* DS4 calibration data */
+ struct ds4_calibration_data ds4_calib_data[6];
};
-static inline void sony_schedule_work(struct sony_sc *sc)
+static void sony_set_leds(struct sony_sc *sc);
+
+static inline void sony_schedule_work(struct sony_sc *sc,
+ enum sony_worker which)
{
- if (!sc->defer_initialization)
- schedule_work(&sc->state_worker);
+ unsigned long flags;
+
+ switch (which) {
+ case SONY_WORKER_STATE:
+ spin_lock_irqsave(&sc->lock, flags);
+ if (!sc->defer_initialization && sc->state_worker_initialized)
+ schedule_work(&sc->state_worker);
+ spin_unlock_irqrestore(&sc->lock, flags);
+ break;
+ case SONY_WORKER_HOTPLUG:
+ if (sc->hotplug_worker_initialized)
+ schedule_work(&sc->hotplug_worker);
+ break;
+ }
}
-static u8 *sixaxis_fixup(struct hid_device *hdev, u8 *rdesc,
- unsigned int *rsize)
+static ssize_t ds4_show_poll_interval(struct device *dev,
+ struct device_attribute
+ *attr, char *buf)
{
- *rsize = sizeof(sixaxis_rdesc);
- return sixaxis_rdesc;
+ struct hid_device *hdev = to_hid_device(dev);
+ struct sony_sc *sc = hid_get_drvdata(hdev);
+
+ return snprintf(buf, PAGE_SIZE, "%i\n", sc->ds4_bt_poll_interval);
}
+static ssize_t ds4_store_poll_interval(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hid_device *hdev = to_hid_device(dev);
+ struct sony_sc *sc = hid_get_drvdata(hdev);
+ unsigned long flags;
+ u8 interval;
+
+ if (kstrtou8(buf, 0, &interval))
+ return -EINVAL;
+
+ if (interval > DS4_BT_MAX_POLL_INTERVAL_MS)
+ return -EINVAL;
+
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->ds4_bt_poll_interval = interval;
+ spin_unlock_irqrestore(&sc->lock, flags);
+
+ sony_schedule_work(sc, SONY_WORKER_STATE);
+
+ return count;
+}
+
+static DEVICE_ATTR(bt_poll_interval, 0644, ds4_show_poll_interval,
+ ds4_store_poll_interval);
+
+
static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
unsigned int *rsize)
{
@@ -1081,13 +639,6 @@ static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
return motion_rdesc;
}
-static u8 *navigation_fixup(struct hid_device *hdev, u8 *rdesc,
- unsigned int *rsize)
-{
- *rsize = sizeof(navigation_rdesc);
- return navigation_rdesc;
-}
-
static u8 *ps3remote_fixup(struct hid_device *hdev, u8 *rdesc,
unsigned int *rsize)
{
@@ -1129,6 +680,133 @@ static int ps3remote_mapping(struct hid_device *hdev, struct hid_input *hi,
return 1;
}
+static int navigation_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+ unsigned int key = usage->hid & HID_USAGE;
+
+ if (key >= ARRAY_SIZE(sixaxis_keymap))
+ return -1;
+
+ key = navigation_keymap[key];
+ if (!key)
+ return -1;
+
+ hid_map_usage_clear(hi, usage, bit, max, EV_KEY, key);
+ return 1;
+ } else if (usage->hid == HID_GD_POINTER) {
+ /* See comment in sixaxis_mapping, basically the L2 (and R2)
+ * triggers are reported through GD Pointer.
+ * In addition we ignore any analog button 'axes' and only
+ * support digital buttons.
+ */
+ switch (usage->usage_index) {
+ case 8: /* L2 */
+ usage->hid = HID_GD_Z;
+ break;
+ default:
+ return -1;
+ }
+
+ hid_map_usage_clear(hi, usage, bit, max, EV_ABS, usage->hid & 0xf);
+ return 1;
+ } else if ((usage->hid & HID_USAGE_PAGE) == HID_UP_GENDESK) {
+ unsigned int abs = usage->hid & HID_USAGE;
+
+ if (abs >= ARRAY_SIZE(navigation_absmap))
+ return -1;
+
+ abs = navigation_absmap[abs];
+
+ hid_map_usage_clear(hi, usage, bit, max, EV_ABS, abs);
+ return 1;
+ }
+
+ return -1;
+}
+
+
+static int sixaxis_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+ unsigned int key = usage->hid & HID_USAGE;
+
+ if (key >= ARRAY_SIZE(sixaxis_keymap))
+ return -1;
+
+ key = sixaxis_keymap[key];
+ hid_map_usage_clear(hi, usage, bit, max, EV_KEY, key);
+ return 1;
+ } else if (usage->hid == HID_GD_POINTER) {
+ /* The DS3 provides analog values for most buttons and even
+ * for HAT axes through GD Pointer. L2 and R2 are reported
+ * among these as well instead of as GD Z / RZ. Remap L2
+ * and R2 and ignore other analog 'button axes' as there is
+ * no good way for reporting them.
+ */
+ switch (usage->usage_index) {
+ case 8: /* L2 */
+ usage->hid = HID_GD_Z;
+ break;
+ case 9: /* R2 */
+ usage->hid = HID_GD_RZ;
+ break;
+ default:
+ return -1;
+ }
+
+ hid_map_usage_clear(hi, usage, bit, max, EV_ABS, usage->hid & 0xf);
+ return 1;
+ } else if ((usage->hid & HID_USAGE_PAGE) == HID_UP_GENDESK) {
+ unsigned int abs = usage->hid & HID_USAGE;
+
+ if (abs >= ARRAY_SIZE(sixaxis_absmap))
+ return -1;
+
+ abs = sixaxis_absmap[abs];
+
+ hid_map_usage_clear(hi, usage, bit, max, EV_ABS, abs);
+ return 1;
+ }
+
+ return -1;
+}
+
+static int ds4_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+ unsigned int key = usage->hid & HID_USAGE;
+
+ if (key >= ARRAY_SIZE(ds4_keymap))
+ return -1;
+
+ key = ds4_keymap[key];
+ hid_map_usage_clear(hi, usage, bit, max, EV_KEY, key);
+ return 1;
+ } else if ((usage->hid & HID_USAGE_PAGE) == HID_UP_GENDESK) {
+ unsigned int abs = usage->hid & HID_USAGE;
+
+ /* Let the HID parser deal with the HAT. */
+ if (usage->hid == HID_GD_HATSWITCH)
+ return 0;
+
+ if (abs >= ARRAY_SIZE(ds4_absmap))
+ return -1;
+
+ abs = ds4_absmap[abs];
+ hid_map_usage_clear(hi, usage, bit, max, EV_ABS, abs);
+ return 1;
+ }
+
+ return 0;
+}
+
static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc,
unsigned int *rsize)
{
@@ -1153,30 +831,9 @@ static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc,
rdesc[55] = 0x06;
}
- /*
- * The default Dualshock 4 USB descriptor doesn't assign
- * the gyroscope values to corresponding axes so we need a
- * modified one.
- */
- if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
- hid_info(hdev, "Using modified Dualshock 4 report descriptor with gyroscope axes\n");
- rdesc = dualshock4_usb_rdesc;
- *rsize = sizeof(dualshock4_usb_rdesc);
- } else if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
- hid_info(hdev, "Using modified Dualshock 4 Bluetooth report descriptor\n");
- rdesc = dualshock4_bt_rdesc;
- *rsize = sizeof(dualshock4_bt_rdesc);
- }
-
- if (sc->quirks & SIXAXIS_CONTROLLER)
- return sixaxis_fixup(hdev, rdesc, rsize);
-
if (sc->quirks & MOTION_CONTROLLER)
return motion_fixup(hdev, rdesc, rsize);
- if (sc->quirks & NAVIGATION_CONTROLLER)
- return navigation_fixup(hdev, rdesc, rsize);
-
if (sc->quirks & PS3REMOTE)
return ps3remote_fixup(hdev, rdesc, rsize);
@@ -1214,6 +871,23 @@ static void sixaxis_parse_report(struct sony_sc *sc, u8 *rd, int size)
sc->battery_capacity = battery_capacity;
sc->battery_charging = battery_charging;
spin_unlock_irqrestore(&sc->lock, flags);
+
+ if (sc->quirks & SIXAXIS_CONTROLLER) {
+ int val;
+
+ offset = SIXAXIS_INPUT_REPORT_ACC_X_OFFSET;
+ val = ((rd[offset+1] << 8) | rd[offset]) - 511;
+ input_report_abs(sc->sensor_dev, ABS_X, val);
+
+ /* Y and Z are swapped and inversed */
+ val = 511 - ((rd[offset+5] << 8) | rd[offset+4]);
+ input_report_abs(sc->sensor_dev, ABS_Y, val);
+
+ val = 511 - ((rd[offset+3] << 8) | rd[offset+2]);
+ input_report_abs(sc->sensor_dev, ABS_Z, val);
+
+ input_sync(sc->sensor_dev);
+ }
}
static void dualshock4_parse_report(struct sony_sc *sc, u8 *rd, int size)
@@ -1222,19 +896,111 @@ static void dualshock4_parse_report(struct sony_sc *sc, u8 *rd, int size)
struct hid_input, list);
struct input_dev *input_dev = hidinput->input;
unsigned long flags;
- int n, offset;
+ int n, m, offset, num_touch_data, max_touch_data;
u8 cable_state, battery_capacity, battery_charging;
+ u16 timestamp;
+
+ /* When using Bluetooth the header is 2 bytes longer, so skip these. */
+ int data_offset = (sc->quirks & DUALSHOCK4_CONTROLLER_BT) ? 2 : 0;
+
+ /* Second bit of third button byte is for the touchpad button. */
+ offset = data_offset + DS4_INPUT_REPORT_BUTTON_OFFSET;
+ input_report_key(sc->touchpad, BTN_LEFT, rd[offset+2] & 0x2);
/*
- * Battery and touchpad data starts at byte 30 in the USB report and
- * 32 in Bluetooth report.
+ * The default behavior of the Dualshock 4 is to send reports using
+ * report type 1 when running over Bluetooth. However, when feature
+ * report 2 is requested during the controller initialization it starts
+ * sending input reports in report 17. Since report 17 is undefined
+ * in the default HID descriptor, the HID layer won't generate events.
+ * While it is possible (and this was done before) to fixup the HID
+ * descriptor to add this mapping, it was better to do this manually.
+ * The reason is there were various pieces software both open and closed
+ * source, relying on the descriptors to be the same across various
+ * operating systems. If the descriptors wouldn't match some
+ * applications e.g. games on Wine would not be able to function due
+ * to different descriptors, which such applications are not parsing.
*/
- offset = (sc->quirks & DUALSHOCK4_CONTROLLER_USB) ? 30 : 32;
+ if (rd[0] == 17) {
+ int value;
+
+ offset = data_offset + DS4_INPUT_REPORT_AXIS_OFFSET;
+ input_report_abs(input_dev, ABS_X, rd[offset]);
+ input_report_abs(input_dev, ABS_Y, rd[offset+1]);
+ input_report_abs(input_dev, ABS_RX, rd[offset+2]);
+ input_report_abs(input_dev, ABS_RY, rd[offset+3]);
+
+ value = rd[offset+4] & 0xf;
+ if (value > 7)
+ value = 8; /* Center 0, 0 */
+ input_report_abs(input_dev, ABS_HAT0X, ds4_hat_mapping[value].x);
+ input_report_abs(input_dev, ABS_HAT0Y, ds4_hat_mapping[value].y);
+
+ input_report_key(input_dev, BTN_WEST, rd[offset+4] & 0x10);
+ input_report_key(input_dev, BTN_SOUTH, rd[offset+4] & 0x20);
+ input_report_key(input_dev, BTN_EAST, rd[offset+4] & 0x40);
+ input_report_key(input_dev, BTN_NORTH, rd[offset+4] & 0x80);
+
+ input_report_key(input_dev, BTN_TL, rd[offset+5] & 0x1);
+ input_report_key(input_dev, BTN_TR, rd[offset+5] & 0x2);
+ input_report_key(input_dev, BTN_TL2, rd[offset+5] & 0x4);
+ input_report_key(input_dev, BTN_TR2, rd[offset+5] & 0x8);
+ input_report_key(input_dev, BTN_SELECT, rd[offset+5] & 0x10);
+ input_report_key(input_dev, BTN_START, rd[offset+5] & 0x20);
+ input_report_key(input_dev, BTN_THUMBL, rd[offset+5] & 0x40);
+ input_report_key(input_dev, BTN_THUMBR, rd[offset+5] & 0x80);
+
+ input_report_key(input_dev, BTN_MODE, rd[offset+6] & 0x1);
+
+ input_report_abs(input_dev, ABS_Z, rd[offset+7]);
+ input_report_abs(input_dev, ABS_RZ, rd[offset+8]);
+
+ input_sync(input_dev);
+ }
+
+ /* Convert timestamp (in 5.33us unit) to timestamp_us */
+ offset = data_offset + DS4_INPUT_REPORT_TIMESTAMP_OFFSET;
+ timestamp = get_unaligned_le16(&rd[offset]);
+ if (!sc->timestamp_initialized) {
+ sc->timestamp_us = ((unsigned int)timestamp * 16) / 3;
+ sc->timestamp_initialized = true;
+ } else {
+ u16 delta;
+
+ if (sc->prev_timestamp > timestamp)
+ delta = (U16_MAX - sc->prev_timestamp + timestamp + 1);
+ else
+ delta = timestamp - sc->prev_timestamp;
+ sc->timestamp_us += (delta * 16) / 3;
+ }
+ sc->prev_timestamp = timestamp;
+ input_event(sc->sensor_dev, EV_MSC, MSC_TIMESTAMP, sc->timestamp_us);
+
+ offset = data_offset + DS4_INPUT_REPORT_GYRO_X_OFFSET;
+ for (n = 0; n < 6; n++) {
+ /* Store data in int for more precision during mult_frac. */
+ int raw_data = (short)((rd[offset+1] << 8) | rd[offset]);
+ struct ds4_calibration_data *calib = &sc->ds4_calib_data[n];
+
+ /* High precision is needed during calibration, but the
+ * calibrated values are within 32-bit.
+ * Note: we swap numerator 'x' and 'numer' in mult_frac for
+ * precision reasons so we don't need 64-bit.
+ */
+ int calib_data = mult_frac(calib->sens_numer,
+ raw_data - calib->bias,
+ calib->sens_denom);
+
+ input_report_abs(sc->sensor_dev, calib->abs_code, calib_data);
+ offset += 2;
+ }
+ input_sync(sc->sensor_dev);
/*
- * The lower 4 bits of byte 30 contain the battery level
+ * The lower 4 bits of byte 30 (or 32 for BT) contain the battery level
* and the 5th bit contains the USB cable state.
*/
+ offset = data_offset + DS4_INPUT_REPORT_BATTERY_OFFSET;
cable_state = (rd[offset] >> 4) & 0x01;
battery_capacity = rd[offset] & 0x0F;
@@ -1261,30 +1027,52 @@ static void dualshock4_parse_report(struct sony_sc *sc, u8 *rd, int size)
sc->battery_charging = battery_charging;
spin_unlock_irqrestore(&sc->lock, flags);
- offset += 5;
-
/*
- * The Dualshock 4 multi-touch trackpad data starts at offset 35 on USB
- * and 37 on Bluetooth.
- * The first 7 bits of the first byte is a counter and bit 8 is a touch
- * indicator that is 0 when pressed and 1 when not pressed.
- * The next 3 bytes are two 12 bit touch coordinates, X and Y.
- * The data for the second touch is in the same format and immediatly
- * follows the data for the first.
+ * The Dualshock 4 multi-touch trackpad data starts at offset 33 on USB
+ * and 35 on Bluetooth.
+ * The first byte indicates the number of touch data in the report.
+ * Trackpad data starts 2 bytes later (e.g. 35 for USB).
*/
- for (n = 0; n < 2; n++) {
- u16 x, y;
+ offset = data_offset + DS4_INPUT_REPORT_TOUCHPAD_OFFSET;
+ max_touch_data = (sc->quirks & DUALSHOCK4_CONTROLLER_BT) ? 4 : 3;
+ if (rd[offset] > 0 && rd[offset] <= max_touch_data)
+ num_touch_data = rd[offset];
+ else
+ num_touch_data = 1;
+ offset += 1;
- x = rd[offset+1] | ((rd[offset+2] & 0xF) << 8);
- y = ((rd[offset+2] & 0xF0) >> 4) | (rd[offset+3] << 4);
+ for (m = 0; m < num_touch_data; m++) {
+ /* Skip past timestamp */
+ offset += 1;
- input_mt_slot(input_dev, n);
- input_mt_report_slot_state(input_dev, MT_TOOL_FINGER,
- !(rd[offset] >> 7));
- input_report_abs(input_dev, ABS_MT_POSITION_X, x);
- input_report_abs(input_dev, ABS_MT_POSITION_Y, y);
+ /*
+ * The first 7 bits of the first byte is a counter and bit 8 is
+ * a touch indicator that is 0 when pressed and 1 when not
+ * pressed.
+ * The next 3 bytes are two 12 bit touch coordinates, X and Y.
+ * The data for the second touch is in the same format and
+ * immediately follows the data for the first.
+ */
+ for (n = 0; n < 2; n++) {
+ u16 x, y;
+ bool active;
- offset += 4;
+ x = rd[offset+1] | ((rd[offset+2] & 0xF) << 8);
+ y = ((rd[offset+2] & 0xF0) >> 4) | (rd[offset+3] << 4);
+
+ active = !(rd[offset] >> 7);
+ input_mt_slot(sc->touchpad, n);
+ input_mt_report_slot_state(sc->touchpad, MT_TOOL_FINGER, active);
+
+ if (active) {
+ input_report_abs(sc->touchpad, ABS_MT_POSITION_X, x);
+ input_report_abs(sc->touchpad, ABS_MT_POSITION_Y, y);
+ }
+
+ offset += 4;
+ }
+ input_mt_sync_frame(sc->touchpad);
+ input_sync(sc->touchpad);
}
}
@@ -1320,15 +1108,87 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report,
} else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 &&
size == 49) {
sixaxis_parse_report(sc, rd, size);
- } else if (((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
- size == 64) || ((sc->quirks & DUALSHOCK4_CONTROLLER_BT)
- && rd[0] == 0x11 && size == 78)) {
+ } else if ((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
+ size == 64) {
+ dualshock4_parse_report(sc, rd, size);
+ } else if (((sc->quirks & DUALSHOCK4_CONTROLLER_BT) && rd[0] == 0x11 &&
+ size == 78)) {
+ /* CRC check */
+ u8 bthdr = 0xA1;
+ u32 crc;
+ u32 report_crc;
+
+ crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
+ crc = ~crc32_le(crc, rd, DS4_INPUT_REPORT_0x11_SIZE-4);
+ report_crc = get_unaligned_le32(&rd[DS4_INPUT_REPORT_0x11_SIZE-4]);
+ if (crc != report_crc) {
+ hid_dbg(sc->hdev, "DualShock 4 input report's CRC check failed, received crc 0x%0x != 0x%0x\n",
+ report_crc, crc);
+ return -EILSEQ;
+ }
+
+ dualshock4_parse_report(sc, rd, size);
+ } else if ((sc->quirks & DUALSHOCK4_DONGLE) && rd[0] == 0x01 &&
+ size == 64) {
+ unsigned long flags;
+ enum ds4_dongle_state dongle_state;
+
+ /*
+ * In the case of a DS4 USB dongle, bit[2] of byte 31 indicates
+ * if a DS4 is actually connected (indicated by '0').
+ * For non-dongle, this bit is always 0 (connected).
+ */
+ bool connected = (rd[31] & 0x04) ? false : true;
+
+ spin_lock_irqsave(&sc->lock, flags);
+ dongle_state = sc->ds4_dongle_state;
+ spin_unlock_irqrestore(&sc->lock, flags);
+
+ /*
+ * The dongle always sends input reports even when no
+ * DS4 is attached. When a DS4 is connected, we need to
+ * obtain calibration data before we can use it.
+ * The code below tracks dongle state and kicks of
+ * calibration when needed and only allows us to process
+ * input if a DS4 is actually connected.
+ */
+ if (dongle_state == DONGLE_DISCONNECTED && connected) {
+ hid_info(sc->hdev, "DualShock 4 USB dongle: controller connected\n");
+ sony_set_leds(sc);
+
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->ds4_dongle_state = DONGLE_CALIBRATING;
+ spin_unlock_irqrestore(&sc->lock, flags);
+
+ sony_schedule_work(sc, SONY_WORKER_HOTPLUG);
+
+ /* Don't process the report since we don't have
+ * calibration data, but let hidraw have it anyway.
+ */
+ return 0;
+ } else if ((dongle_state == DONGLE_CONNECTED ||
+ dongle_state == DONGLE_DISABLED) && !connected) {
+ hid_info(sc->hdev, "DualShock 4 USB dongle: controller disconnected\n");
+
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->ds4_dongle_state = DONGLE_DISCONNECTED;
+ spin_unlock_irqrestore(&sc->lock, flags);
+
+ /* Return 0, so hidraw can get the report. */
+ return 0;
+ } else if (dongle_state == DONGLE_CALIBRATING ||
+ dongle_state == DONGLE_DISABLED ||
+ dongle_state == DONGLE_DISCONNECTED) {
+ /* Return 0, so hidraw can get the report. */
+ return 0;
+ }
+
dualshock4_parse_report(sc, rd, size);
}
if (sc->defer_initialization) {
sc->defer_initialization = 0;
- sony_schedule_work(sc);
+ sony_schedule_work(sc, SONY_WORKER_STATE);
}
return 0;
@@ -1366,49 +1226,189 @@ static int sony_mapping(struct hid_device *hdev, struct hid_input *hi,
if (sc->quirks & PS3REMOTE)
return ps3remote_mapping(hdev, hi, field, usage, bit, max);
+ if (sc->quirks & NAVIGATION_CONTROLLER)
+ return navigation_mapping(hdev, hi, field, usage, bit, max);
+
+ if (sc->quirks & SIXAXIS_CONTROLLER)
+ return sixaxis_mapping(hdev, hi, field, usage, bit, max);
+
+ if (sc->quirks & DUALSHOCK4_CONTROLLER)
+ return ds4_mapping(hdev, hi, field, usage, bit, max);
+
+
/* Let hid-core decide for the others */
return 0;
}
-static int sony_register_touchpad(struct hid_input *hi, int touch_count,
+static int sony_register_touchpad(struct sony_sc *sc, int touch_count,
int w, int h)
{
- struct input_dev *input_dev = hi->input;
+ size_t name_sz;
+ char *name;
int ret;
- ret = input_mt_init_slots(input_dev, touch_count, 0);
- if (ret < 0)
- return ret;
+ sc->touchpad = input_allocate_device();
+ if (!sc->touchpad)
+ return -ENOMEM;
- input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0, w, 0, 0);
- input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0, h, 0, 0);
+ input_set_drvdata(sc->touchpad, sc);
+ sc->touchpad->dev.parent = &sc->hdev->dev;
+ sc->touchpad->phys = sc->hdev->phys;
+ sc->touchpad->uniq = sc->hdev->uniq;
+ sc->touchpad->id.bustype = sc->hdev->bus;
+ sc->touchpad->id.vendor = sc->hdev->vendor;
+ sc->touchpad->id.product = sc->hdev->product;
+ sc->touchpad->id.version = sc->hdev->version;
+
+ /* Append a suffix to the controller name as there are various
+ * DS4 compatible non-Sony devices with different names.
+ */
+ name_sz = strlen(sc->hdev->name) + sizeof(DS4_TOUCHPAD_SUFFIX);
+ name = kzalloc(name_sz, GFP_KERNEL);
+ if (!name) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ snprintf(name, name_sz, "%s" DS4_TOUCHPAD_SUFFIX, sc->hdev->name);
+ sc->touchpad->name = name;
+
+ ret = input_mt_init_slots(sc->touchpad, touch_count, INPUT_MT_POINTER);
+ if (ret < 0)
+ goto err;
+
+ /* We map the button underneath the touchpad to BTN_LEFT. */
+ __set_bit(EV_KEY, sc->touchpad->evbit);
+ __set_bit(BTN_LEFT, sc->touchpad->keybit);
+ __set_bit(INPUT_PROP_BUTTONPAD, sc->touchpad->propbit);
+
+ input_set_abs_params(sc->touchpad, ABS_MT_POSITION_X, 0, w, 0, 0);
+ input_set_abs_params(sc->touchpad, ABS_MT_POSITION_Y, 0, h, 0, 0);
+
+ ret = input_register_device(sc->touchpad);
+ if (ret < 0)
+ goto err;
return 0;
+
+err:
+ kfree(sc->touchpad->name);
+ sc->touchpad->name = NULL;
+
+ input_free_device(sc->touchpad);
+ sc->touchpad = NULL;
+
+ return ret;
}
-static int sony_input_configured(struct hid_device *hdev,
- struct hid_input *hidinput)
+static void sony_unregister_touchpad(struct sony_sc *sc)
{
- struct sony_sc *sc = hid_get_drvdata(hdev);
- int ret;
+ if (!sc->touchpad)
+ return;
- /*
- * The Dualshock 4 touchpad supports 2 touches and has a
- * resolution of 1920x942 (44.86 dots/mm).
+ kfree(sc->touchpad->name);
+ sc->touchpad->name = NULL;
+
+ input_unregister_device(sc->touchpad);
+ sc->touchpad = NULL;
+}
+
+static int sony_register_sensors(struct sony_sc *sc)
+{
+ size_t name_sz;
+ char *name;
+ int ret;
+ int range;
+
+ sc->sensor_dev = input_allocate_device();
+ if (!sc->sensor_dev)
+ return -ENOMEM;
+
+ input_set_drvdata(sc->sensor_dev, sc);
+ sc->sensor_dev->dev.parent = &sc->hdev->dev;
+ sc->sensor_dev->phys = sc->hdev->phys;
+ sc->sensor_dev->uniq = sc->hdev->uniq;
+ sc->sensor_dev->id.bustype = sc->hdev->bus;
+ sc->sensor_dev->id.vendor = sc->hdev->vendor;
+ sc->sensor_dev->id.product = sc->hdev->product;
+ sc->sensor_dev->id.version = sc->hdev->version;
+
+ /* Append a suffix to the controller name as there are various
+ * DS4 compatible non-Sony devices with different names.
*/
- if (sc->quirks & DUALSHOCK4_CONTROLLER) {
- ret = sony_register_touchpad(hidinput, 2, 1920, 942);
- if (ret) {
- hid_err(sc->hdev,
- "Unable to initialize multi-touch slots: %d\n",
- ret);
- return ret;
- }
+ name_sz = strlen(sc->hdev->name) + sizeof(SENSOR_SUFFIX);
+ name = kzalloc(name_sz, GFP_KERNEL);
+ if (!name) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ snprintf(name, name_sz, "%s" SENSOR_SUFFIX, sc->hdev->name);
+ sc->sensor_dev->name = name;
+
+ if (sc->quirks & SIXAXIS_CONTROLLER) {
+ /* For the DS3 we only support the accelerometer, which works
+ * quite well even without calibration. The device also has
+ * a 1-axis gyro, but it is very difficult to manage from within
+ * the driver even to get data, the sensor is inaccurate and
+ * the behavior is very different between hardware revisions.
+ */
+ input_set_abs_params(sc->sensor_dev, ABS_X, -512, 511, 4, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_Y, -512, 511, 4, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_Z, -512, 511, 4, 0);
+ input_abs_set_res(sc->sensor_dev, ABS_X, SIXAXIS_ACC_RES_PER_G);
+ input_abs_set_res(sc->sensor_dev, ABS_Y, SIXAXIS_ACC_RES_PER_G);
+ input_abs_set_res(sc->sensor_dev, ABS_Z, SIXAXIS_ACC_RES_PER_G);
+ } else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
+ range = DS4_ACC_RES_PER_G*4;
+ input_set_abs_params(sc->sensor_dev, ABS_X, -range, range, 16, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_Y, -range, range, 16, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_Z, -range, range, 16, 0);
+ input_abs_set_res(sc->sensor_dev, ABS_X, DS4_ACC_RES_PER_G);
+ input_abs_set_res(sc->sensor_dev, ABS_Y, DS4_ACC_RES_PER_G);
+ input_abs_set_res(sc->sensor_dev, ABS_Z, DS4_ACC_RES_PER_G);
+
+ range = DS4_GYRO_RES_PER_DEG_S*2048;
+ input_set_abs_params(sc->sensor_dev, ABS_RX, -range, range, 16, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_RY, -range, range, 16, 0);
+ input_set_abs_params(sc->sensor_dev, ABS_RZ, -range, range, 16, 0);
+ input_abs_set_res(sc->sensor_dev, ABS_RX, DS4_GYRO_RES_PER_DEG_S);
+ input_abs_set_res(sc->sensor_dev, ABS_RY, DS4_GYRO_RES_PER_DEG_S);
+ input_abs_set_res(sc->sensor_dev, ABS_RZ, DS4_GYRO_RES_PER_DEG_S);
+
+ __set_bit(EV_MSC, sc->sensor_dev->evbit);
+ __set_bit(MSC_TIMESTAMP, sc->sensor_dev->mscbit);
}
+ __set_bit(INPUT_PROP_ACCELEROMETER, sc->sensor_dev->propbit);
+
+ ret = input_register_device(sc->sensor_dev);
+ if (ret < 0)
+ goto err;
+
return 0;
+
+err:
+ kfree(sc->sensor_dev->name);
+ sc->sensor_dev->name = NULL;
+
+ input_free_device(sc->sensor_dev);
+ sc->sensor_dev = NULL;
+
+ return ret;
}
+static void sony_unregister_sensors(struct sony_sc *sc)
+{
+ if (!sc->sensor_dev)
+ return;
+
+ kfree(sc->sensor_dev->name);
+ sc->sensor_dev->name = NULL;
+
+ input_unregister_device(sc->sensor_dev);
+ sc->sensor_dev = NULL;
+}
+
+
/*
* Sending HID_REQ_GET_REPORT changes the operation mode of the ps3 controller
* to "operational". Without this, the ps3 controller will not report any
@@ -1474,26 +1474,176 @@ static int sixaxis_set_operational_bt(struct hid_device *hdev)
}
/*
- * Requesting feature report 0x02 in Bluetooth mode changes the state of the
- * controller so that it sends full input reports of type 0x11.
+ * Request DS4 calibration data for the motion sensors.
+ * For Bluetooth this also affects the operating mode (see below).
*/
-static int dualshock4_set_operational_bt(struct hid_device *hdev)
+static int dualshock4_get_calibration_data(struct sony_sc *sc)
{
u8 *buf;
int ret;
+ short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus;
+ short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus;
+ short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus;
+ short gyro_speed_plus, gyro_speed_minus;
+ short acc_x_plus, acc_x_minus;
+ short acc_y_plus, acc_y_minus;
+ short acc_z_plus, acc_z_minus;
+ int speed_2x;
+ int range_2g;
- buf = kmalloc(DS4_REPORT_0x02_SIZE, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
+ /* For Bluetooth we use a different request, which supports CRC.
+ * Note: in Bluetooth mode feature report 0x02 also changes the state
+ * of the controller, so that it sends input reports of type 0x11.
+ */
+ if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
+ buf = kmalloc(DS4_FEATURE_REPORT_0x02_SIZE, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
- ret = hid_hw_raw_request(hdev, 0x02, buf, DS4_REPORT_0x02_SIZE,
- HID_FEATURE_REPORT, HID_REQ_GET_REPORT);
+ ret = hid_hw_raw_request(sc->hdev, 0x02, buf,
+ DS4_FEATURE_REPORT_0x02_SIZE,
+ HID_FEATURE_REPORT,
+ HID_REQ_GET_REPORT);
+ if (ret < 0)
+ goto err_stop;
+ } else {
+ u8 bthdr = 0xA3;
+ u32 crc;
+ u32 report_crc;
+ int retries;
+ buf = kmalloc(DS4_FEATURE_REPORT_0x05_SIZE, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ for (retries = 0; retries < 3; retries++) {
+ ret = hid_hw_raw_request(sc->hdev, 0x05, buf,
+ DS4_FEATURE_REPORT_0x05_SIZE,
+ HID_FEATURE_REPORT,
+ HID_REQ_GET_REPORT);
+ if (ret < 0)
+ goto err_stop;
+
+ /* CRC check */
+ crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
+ crc = ~crc32_le(crc, buf, DS4_FEATURE_REPORT_0x05_SIZE-4);
+ report_crc = get_unaligned_le32(&buf[DS4_FEATURE_REPORT_0x05_SIZE-4]);
+ if (crc != report_crc) {
+ hid_warn(sc->hdev, "DualShock 4 calibration report's CRC check failed, received crc 0x%0x != 0x%0x\n",
+ report_crc, crc);
+ if (retries < 2) {
+ hid_warn(sc->hdev, "Retrying DualShock 4 get calibration report request\n");
+ continue;
+ } else {
+ ret = -EILSEQ;
+ goto err_stop;
+ }
+ } else {
+ break;
+ }
+ }
+ }
+
+ gyro_pitch_bias = get_unaligned_le16(&buf[1]);
+ gyro_yaw_bias = get_unaligned_le16(&buf[3]);
+ gyro_roll_bias = get_unaligned_le16(&buf[5]);
+ if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
+ gyro_pitch_plus = get_unaligned_le16(&buf[7]);
+ gyro_pitch_minus = get_unaligned_le16(&buf[9]);
+ gyro_yaw_plus = get_unaligned_le16(&buf[11]);
+ gyro_yaw_minus = get_unaligned_le16(&buf[13]);
+ gyro_roll_plus = get_unaligned_le16(&buf[15]);
+ gyro_roll_minus = get_unaligned_le16(&buf[17]);
+ } else {
+ /* BT + Dongle */
+ gyro_pitch_plus = get_unaligned_le16(&buf[7]);
+ gyro_yaw_plus = get_unaligned_le16(&buf[9]);
+ gyro_roll_plus = get_unaligned_le16(&buf[11]);
+ gyro_pitch_minus = get_unaligned_le16(&buf[13]);
+ gyro_yaw_minus = get_unaligned_le16(&buf[15]);
+ gyro_roll_minus = get_unaligned_le16(&buf[17]);
+ }
+ gyro_speed_plus = get_unaligned_le16(&buf[19]);
+ gyro_speed_minus = get_unaligned_le16(&buf[21]);
+ acc_x_plus = get_unaligned_le16(&buf[23]);
+ acc_x_minus = get_unaligned_le16(&buf[25]);
+ acc_y_plus = get_unaligned_le16(&buf[27]);
+ acc_y_minus = get_unaligned_le16(&buf[29]);
+ acc_z_plus = get_unaligned_le16(&buf[31]);
+ acc_z_minus = get_unaligned_le16(&buf[33]);
+
+ /* Set gyroscope calibration and normalization parameters.
+ * Data values will be normalized to 1/DS4_GYRO_RES_PER_DEG_S degree/s.
+ */
+ speed_2x = (gyro_speed_plus + gyro_speed_minus);
+ sc->ds4_calib_data[0].abs_code = ABS_RX;
+ sc->ds4_calib_data[0].bias = gyro_pitch_bias;
+ sc->ds4_calib_data[0].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+ sc->ds4_calib_data[0].sens_denom = gyro_pitch_plus - gyro_pitch_minus;
+
+ sc->ds4_calib_data[1].abs_code = ABS_RY;
+ sc->ds4_calib_data[1].bias = gyro_yaw_bias;
+ sc->ds4_calib_data[1].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+ sc->ds4_calib_data[1].sens_denom = gyro_yaw_plus - gyro_yaw_minus;
+
+ sc->ds4_calib_data[2].abs_code = ABS_RZ;
+ sc->ds4_calib_data[2].bias = gyro_roll_bias;
+ sc->ds4_calib_data[2].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+ sc->ds4_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+
+ /* Set accelerometer calibration and normalization parameters.
+ * Data values will be normalized to 1/DS4_ACC_RES_PER_G G.
+ */
+ range_2g = acc_x_plus - acc_x_minus;
+ sc->ds4_calib_data[3].abs_code = ABS_X;
+ sc->ds4_calib_data[3].bias = acc_x_plus - range_2g / 2;
+ sc->ds4_calib_data[3].sens_numer = 2*DS4_ACC_RES_PER_G;
+ sc->ds4_calib_data[3].sens_denom = range_2g;
+
+ range_2g = acc_y_plus - acc_y_minus;
+ sc->ds4_calib_data[4].abs_code = ABS_Y;
+ sc->ds4_calib_data[4].bias = acc_y_plus - range_2g / 2;
+ sc->ds4_calib_data[4].sens_numer = 2*DS4_ACC_RES_PER_G;
+ sc->ds4_calib_data[4].sens_denom = range_2g;
+
+ range_2g = acc_z_plus - acc_z_minus;
+ sc->ds4_calib_data[5].abs_code = ABS_Z;
+ sc->ds4_calib_data[5].bias = acc_z_plus - range_2g / 2;
+ sc->ds4_calib_data[5].sens_numer = 2*DS4_ACC_RES_PER_G;
+ sc->ds4_calib_data[5].sens_denom = range_2g;
+
+err_stop:
kfree(buf);
-
return ret;
}
+static void dualshock4_calibration_work(struct work_struct *work)
+{
+ struct sony_sc *sc = container_of(work, struct sony_sc, hotplug_worker);
+ unsigned long flags;
+ enum ds4_dongle_state dongle_state;
+ int ret;
+
+ ret = dualshock4_get_calibration_data(sc);
+ if (ret < 0) {
+ /* This call is very unlikely to fail for the dongle. When it
+ * fails we are probably in a very bad state, so mark the
+ * dongle as disabled. We will re-enable the dongle if a new
+ * DS4 hotplug is detect from sony_raw_event as any issues
+ * are likely resolved then (the dongle is quite stupid).
+ */
+ hid_err(sc->hdev, "DualShock 4 USB dongle: calibration failed, disabling device\n");
+ dongle_state = DONGLE_DISABLED;
+ } else {
+ hid_info(sc->hdev, "DualShock 4 USB dongle: calibration completed\n");
+ dongle_state = DONGLE_CONNECTED;
+ }
+
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->ds4_dongle_state = dongle_state;
+ spin_unlock_irqrestore(&sc->lock, flags);
+}
+
static void sixaxis_set_leds_from_id(struct sony_sc *sc)
{
static const u8 sixaxis_leds[10][4] = {
@@ -1524,10 +1674,10 @@ static void dualshock4_set_leds_from_id(struct sony_sc *sc)
{
/* The first 4 color/index entries match what the PS4 assigns */
static const u8 color_code[7][3] = {
- /* Blue */ { 0x00, 0x00, 0x01 },
- /* Red */ { 0x01, 0x00, 0x00 },
- /* Green */ { 0x00, 0x01, 0x00 },
- /* Pink */ { 0x02, 0x00, 0x01 },
+ /* Blue */ { 0x00, 0x00, 0x40 },
+ /* Red */ { 0x40, 0x00, 0x00 },
+ /* Green */ { 0x00, 0x40, 0x00 },
+ /* Pink */ { 0x20, 0x00, 0x20 },
/* Orange */ { 0x02, 0x01, 0x00 },
/* Teal */ { 0x00, 0x01, 0x01 },
/* White */ { 0x01, 0x01, 0x01 }
@@ -1568,7 +1718,7 @@ static void buzz_set_leds(struct sony_sc *sc)
static void sony_set_leds(struct sony_sc *sc)
{
if (!(sc->quirks & BUZZ_CONTROLLER))
- sony_schedule_work(sc);
+ sony_schedule_work(sc, SONY_WORKER_STATE);
else
buzz_set_leds(sc);
}
@@ -1679,7 +1829,7 @@ static int sony_led_blink_set(struct led_classdev *led, unsigned long *delay_on,
new_off != drv_data->led_delay_off[n]) {
drv_data->led_delay_on[n] = new_on;
drv_data->led_delay_off[n] = new_off;
- sony_schedule_work(drv_data);
+ sony_schedule_work(drv_data, SONY_WORKER_STATE);
}
return 0;
@@ -1881,26 +2031,24 @@ static void dualshock4_send_output_report(struct sony_sc *sc)
int offset;
/*
- * NOTE: The buf[1] field of the Bluetooth report controls
- * the Dualshock 4 reporting rate.
- *
- * Known values include:
- *
- * 0x80 - 1000hz (full speed)
- * 0xA0 - 31hz
- * 0xB0 - 20hz
- * 0xD0 - 66hz
+ * NOTE: The lower 6 bits of buf[1] field of the Bluetooth report
+ * control the interval at which Dualshock 4 reports data:
+ * 0x00 - 1ms
+ * 0x01 - 1ms
+ * 0x02 - 2ms
+ * 0x3E - 62ms
+ * 0x3F - disabled
*/
- if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
- memset(buf, 0, DS4_REPORT_0x05_SIZE);
+ if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
+ memset(buf, 0, DS4_OUTPUT_REPORT_0x05_SIZE);
buf[0] = 0x05;
- buf[1] = 0xFF;
+ buf[1] = 0x07; /* blink + LEDs + motor */
offset = 4;
} else {
- memset(buf, 0, DS4_REPORT_0x11_SIZE);
+ memset(buf, 0, DS4_OUTPUT_REPORT_0x11_SIZE);
buf[0] = 0x11;
- buf[1] = 0x80;
- buf[3] = 0x0F;
+ buf[1] = 0xC0 /* HID + CRC */ | sc->ds4_bt_poll_interval;
+ buf[3] = 0x07; /* blink + LEDs + motor */
offset = 6;
}
@@ -1924,11 +2072,18 @@ static void dualshock4_send_output_report(struct sony_sc *sc)
buf[offset++] = sc->led_delay_on[3];
buf[offset++] = sc->led_delay_off[3];
- if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
- hid_hw_output_report(hdev, buf, DS4_REPORT_0x05_SIZE);
- else
- hid_hw_raw_request(hdev, 0x11, buf, DS4_REPORT_0x11_SIZE,
- HID_OUTPUT_REPORT, HID_REQ_SET_REPORT);
+ if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE))
+ hid_hw_output_report(hdev, buf, DS4_OUTPUT_REPORT_0x05_SIZE);
+ else {
+ /* CRC generation */
+ u8 bthdr = 0xA2;
+ u32 crc;
+
+ crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
+ crc = ~crc32_le(crc, buf, DS4_OUTPUT_REPORT_0x11_SIZE-4);
+ put_unaligned_le32(crc, &buf[74]);
+ hid_hw_output_report(hdev, buf, DS4_OUTPUT_REPORT_0x11_SIZE);
+ }
}
static void motion_send_output_report(struct sony_sc *sc)
@@ -1972,10 +2127,10 @@ static int sony_allocate_output_report(struct sony_sc *sc)
kmalloc(sizeof(union sixaxis_output_report_01),
GFP_KERNEL);
else if (sc->quirks & DUALSHOCK4_CONTROLLER_BT)
- sc->output_report_dmabuf = kmalloc(DS4_REPORT_0x11_SIZE,
+ sc->output_report_dmabuf = kmalloc(DS4_OUTPUT_REPORT_0x11_SIZE,
GFP_KERNEL);
- else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
- sc->output_report_dmabuf = kmalloc(DS4_REPORT_0x05_SIZE,
+ else if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE))
+ sc->output_report_dmabuf = kmalloc(DS4_OUTPUT_REPORT_0x05_SIZE,
GFP_KERNEL);
else if (sc->quirks & MOTION_CONTROLLER)
sc->output_report_dmabuf = kmalloc(MOTION_REPORT_0x02_SIZE,
@@ -2002,7 +2157,7 @@ static int sony_play_effect(struct input_dev *dev, void *data,
sc->left = effect->u.rumble.strong_magnitude / 256;
sc->right = effect->u.rumble.weak_magnitude / 256;
- sony_schedule_work(sc);
+ sony_schedule_work(sc, SONY_WORKER_STATE);
return 0;
}
@@ -2225,8 +2380,8 @@ static int sony_check_add(struct sony_sc *sc)
hid_warn(sc->hdev, "UNIQ does not contain a MAC address; duplicate check skipped\n");
return 0;
}
- } else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
- buf = kmalloc(DS4_REPORT_0x81_SIZE, GFP_KERNEL);
+ } else if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
+ buf = kmalloc(DS4_FEATURE_REPORT_0x81_SIZE, GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -2236,16 +2391,22 @@ static int sony_check_add(struct sony_sc *sc)
* offset 1.
*/
ret = hid_hw_raw_request(sc->hdev, 0x81, buf,
- DS4_REPORT_0x81_SIZE, HID_FEATURE_REPORT,
+ DS4_FEATURE_REPORT_0x81_SIZE, HID_FEATURE_REPORT,
HID_REQ_GET_REPORT);
- if (ret != DS4_REPORT_0x81_SIZE) {
+ if (ret != DS4_FEATURE_REPORT_0x81_SIZE) {
hid_err(sc->hdev, "failed to retrieve feature report 0x81 with the DualShock 4 MAC address\n");
ret = ret < 0 ? ret : -EINVAL;
goto out_free;
}
memcpy(sc->mac_address, &buf[1], sizeof(sc->mac_address));
+
+ snprintf(sc->hdev->uniq, sizeof(sc->hdev->uniq),
+ "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+ sc->mac_address[5], sc->mac_address[4],
+ sc->mac_address[3], sc->mac_address[2],
+ sc->mac_address[1], sc->mac_address[0]);
} else if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
buf = kmalloc(SIXAXIS_REPORT_0xF2_SIZE, GFP_KERNEL);
@@ -2273,6 +2434,12 @@ static int sony_check_add(struct sony_sc *sc)
*/
for (n = 0; n < 6; n++)
sc->mac_address[5-n] = buf[4+n];
+
+ snprintf(sc->hdev->uniq, sizeof(sc->hdev->uniq),
+ "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+ sc->mac_address[5], sc->mac_address[4],
+ sc->mac_address[3], sc->mac_address[2],
+ sc->mac_address[1], sc->mac_address[0]);
} else {
return 0;
}
@@ -2323,57 +2490,32 @@ static inline void sony_init_output_report(struct sony_sc *sc,
{
sc->send_output_report = send_output_report;
- if (!sc->worker_initialized)
+ if (!sc->state_worker_initialized)
INIT_WORK(&sc->state_worker, sony_state_worker);
- sc->worker_initialized = 1;
+ sc->state_worker_initialized = 1;
}
static inline void sony_cancel_work_sync(struct sony_sc *sc)
{
- if (sc->worker_initialized)
+ unsigned long flags;
+
+ if (sc->hotplug_worker_initialized)
+ cancel_work_sync(&sc->hotplug_worker);
+ if (sc->state_worker_initialized) {
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->state_worker_initialized = 0;
+ spin_unlock_irqrestore(&sc->lock, flags);
cancel_work_sync(&sc->state_worker);
+ }
}
-static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
+static int sony_input_configured(struct hid_device *hdev,
+ struct hid_input *hidinput)
{
- int ret;
+ struct sony_sc *sc = hid_get_drvdata(hdev);
int append_dev_id;
- unsigned long quirks = id->driver_data;
- struct sony_sc *sc;
- unsigned int connect_mask = HID_CONNECT_DEFAULT;
-
- if (!strcmp(hdev->name, "FutureMax Dance Mat"))
- quirks |= FUTUREMAX_DANCE_MAT;
-
- sc = devm_kzalloc(&hdev->dev, sizeof(*sc), GFP_KERNEL);
- if (sc == NULL) {
- hid_err(hdev, "can't alloc sony descriptor\n");
- return -ENOMEM;
- }
-
- spin_lock_init(&sc->lock);
-
- sc->quirks = quirks;
- hid_set_drvdata(hdev, sc);
- sc->hdev = hdev;
-
- ret = hid_parse(hdev);
- if (ret) {
- hid_err(hdev, "parse failed\n");
- return ret;
- }
-
- if (sc->quirks & VAIO_RDESC_CONSTANT)
- connect_mask |= HID_CONNECT_HIDDEV_FORCE;
- else if (sc->quirks & SIXAXIS_CONTROLLER)
- connect_mask |= HID_CONNECT_HIDDEV_FORCE;
-
- ret = hid_hw_start(hdev, connect_mask);
- if (ret) {
- hid_err(hdev, "hw start failed\n");
- return ret;
- }
+ int ret;
ret = sony_set_device_id(sc);
if (ret < 0) {
@@ -2381,14 +2523,17 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
goto err_stop;
}
+ ret = append_dev_id = sony_check_add(sc);
+ if (ret < 0)
+ goto err_stop;
+
ret = sony_allocate_output_report(sc);
if (ret < 0) {
hid_err(hdev, "failed to allocate the output report buffer\n");
goto err_stop;
}
- if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
- (sc->quirks & NAVIGATION_CONTROLLER_USB)) {
+ if (sc->quirks & NAVIGATION_CONTROLLER_USB) {
/*
* The Sony Sixaxis does not handle HID Output Reports on the
* Interrupt EP like it could, so we need to force HID Output
@@ -2408,29 +2553,113 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
sc->defer_initialization = 1;
+
ret = sixaxis_set_operational_usb(hdev);
+ if (ret < 0) {
+ hid_err(hdev, "Failed to set controller into operational mode\n");
+ goto err_stop;
+ }
+
sony_init_output_report(sc, sixaxis_send_output_report);
- } else if ((sc->quirks & SIXAXIS_CONTROLLER_BT) ||
- (sc->quirks & NAVIGATION_CONTROLLER_BT)) {
+ } else if (sc->quirks & NAVIGATION_CONTROLLER_BT) {
+ /*
+ * The Navigation controller wants output reports sent on the ctrl
+ * endpoint when connected via Bluetooth.
+ */
+ hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+
+ ret = sixaxis_set_operational_bt(hdev);
+ if (ret < 0) {
+ hid_err(hdev, "Failed to set controller into operational mode\n");
+ goto err_stop;
+ }
+
+ sony_init_output_report(sc, sixaxis_send_output_report);
+ } else if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+ /*
+ * The Sony Sixaxis does not handle HID Output Reports on the
+ * Interrupt EP and the device only becomes active when the
+ * PS button is pressed. See comment for Navigation controller
+ * above for more details.
+ */
+ hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+ hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
+ sc->defer_initialization = 1;
+
+ ret = sixaxis_set_operational_usb(hdev);
+ if (ret < 0) {
+ hid_err(hdev, "Failed to set controller into operational mode\n");
+ goto err_stop;
+ }
+
+ ret = sony_register_sensors(sc);
+ if (ret) {
+ hid_err(sc->hdev,
+ "Unable to initialize motion sensors: %d\n", ret);
+ goto err_stop;
+ }
+
+ sony_init_output_report(sc, sixaxis_send_output_report);
+ } else if (sc->quirks & SIXAXIS_CONTROLLER_BT) {
/*
* The Sixaxis wants output reports sent on the ctrl endpoint
* when connected via Bluetooth.
*/
hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+
ret = sixaxis_set_operational_bt(hdev);
+ if (ret < 0) {
+ hid_err(hdev, "Failed to set controller into operational mode\n");
+ goto err_stop;
+ }
+
+ ret = sony_register_sensors(sc);
+ if (ret) {
+ hid_err(sc->hdev,
+ "Unable to initialize motion sensors: %d\n", ret);
+ goto err_stop;
+ }
+
sony_init_output_report(sc, sixaxis_send_output_report);
} else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
+ ret = dualshock4_get_calibration_data(sc);
+ if (ret < 0) {
+ hid_err(hdev, "Failed to get calibration data from Dualshock 4\n");
+ goto err_stop;
+ }
+
+ /*
+ * The Dualshock 4 touchpad supports 2 touches and has a
+ * resolution of 1920x942 (44.86 dots/mm).
+ */
+ ret = sony_register_touchpad(sc, 2, 1920, 942);
+ if (ret) {
+ hid_err(sc->hdev,
+ "Unable to initialize multi-touch slots: %d\n",
+ ret);
+ goto err_stop;
+ }
+
+ ret = sony_register_sensors(sc);
+ if (ret) {
+ hid_err(sc->hdev,
+ "Unable to initialize motion sensors: %d\n", ret);
+ goto err_stop;
+ }
+
if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
- /*
- * The DualShock 4 wants output reports sent on the ctrl
- * endpoint when connected via Bluetooth.
- */
- hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
- ret = dualshock4_set_operational_bt(hdev);
- if (ret < 0) {
- hid_err(hdev, "failed to set the Dualshock 4 operational mode\n");
- goto err_stop;
- }
+ sc->ds4_bt_poll_interval = DS4_BT_DEFAULT_POLL_INTERVAL_MS;
+ ret = device_create_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
+ if (ret)
+ hid_warn(sc->hdev,
+ "can't create sysfs bt_poll_interval attribute err: %d\n",
+ ret);
+ }
+
+ if (sc->quirks & DUALSHOCK4_DONGLE) {
+ INIT_WORK(&sc->hotplug_worker, dualshock4_calibration_work);
+ sc->hotplug_worker_initialized = 1;
+ sc->ds4_dongle_state = DONGLE_DISCONNECTED;
}
sony_init_output_report(sc, dualshock4_send_output_report);
@@ -2440,13 +2669,6 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
ret = 0;
}
- if (ret < 0)
- goto err_stop;
-
- ret = append_dev_id = sony_check_add(sc);
- if (ret < 0)
- goto err_stop;
-
if (sc->quirks & SONY_LED_SUPPORT) {
ret = sony_leds_init(sc);
if (ret < 0)
@@ -2476,15 +2698,89 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
err_close:
hid_hw_close(hdev);
err_stop:
+ /* Piggy back on the default ds4_bt_ poll_interval to determine
+ * if we need to remove the file as we don't know for sure if we
+ * executed that logic.
+ */
+ if (sc->ds4_bt_poll_interval)
+ device_remove_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
if (sc->quirks & SONY_LED_SUPPORT)
sony_leds_remove(sc);
if (sc->quirks & SONY_BATTERY_SUPPORT)
sony_battery_remove(sc);
+ if (sc->touchpad)
+ sony_unregister_touchpad(sc);
+ if (sc->sensor_dev)
+ sony_unregister_sensors(sc);
sony_cancel_work_sync(sc);
kfree(sc->output_report_dmabuf);
sony_remove_dev_list(sc);
sony_release_device_id(sc);
- hid_hw_stop(hdev);
+ return ret;
+}
+
+static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
+{
+ int ret;
+ unsigned long quirks = id->driver_data;
+ struct sony_sc *sc;
+ unsigned int connect_mask = HID_CONNECT_DEFAULT;
+
+ if (!strcmp(hdev->name, "FutureMax Dance Mat"))
+ quirks |= FUTUREMAX_DANCE_MAT;
+
+ sc = devm_kzalloc(&hdev->dev, sizeof(*sc), GFP_KERNEL);
+ if (sc == NULL) {
+ hid_err(hdev, "can't alloc sony descriptor\n");
+ return -ENOMEM;
+ }
+
+ spin_lock_init(&sc->lock);
+
+ sc->quirks = quirks;
+ hid_set_drvdata(hdev, sc);
+ sc->hdev = hdev;
+
+ ret = hid_parse(hdev);
+ if (ret) {
+ hid_err(hdev, "parse failed\n");
+ return ret;
+ }
+
+ if (sc->quirks & VAIO_RDESC_CONSTANT)
+ connect_mask |= HID_CONNECT_HIDDEV_FORCE;
+ else if (sc->quirks & SIXAXIS_CONTROLLER)
+ connect_mask |= HID_CONNECT_HIDDEV_FORCE;
+
+ /* Patch the hw version on DS3/4 compatible devices, so applications can
+ * distinguish between the default HID mappings and the mappings defined
+ * by the Linux game controller spec. This is important for the SDL2
+ * library, which has a game controller database, which uses device ids
+ * in combination with version as a key.
+ */
+ if (sc->quirks & (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER))
+ hdev->version |= 0x8000;
+
+ ret = hid_hw_start(hdev, connect_mask);
+ if (ret) {
+ hid_err(hdev, "hw start failed\n");
+ return ret;
+ }
+
+ /* sony_input_configured can fail, but this doesn't result
+ * in hid_hw_start failures (intended). Check whether
+ * the HID layer claimed the device else fail.
+ * We don't know the actual reason for the failure, most
+ * likely it is due to EEXIST in case of double connection
+ * of USB and Bluetooth, but could have been due to ENOMEM
+ * or other reasons as well.
+ */
+ if (!(hdev->claimed & HID_CLAIMED_INPUT)) {
+ hid_err(hdev, "failed to claim input\n");
+ hid_hw_stop(hdev);
+ return -ENODEV;
+ }
+
return ret;
}
@@ -2492,13 +2788,22 @@ static void sony_remove(struct hid_device *hdev)
{
struct sony_sc *sc = hid_get_drvdata(hdev);
+ hid_hw_close(hdev);
+
if (sc->quirks & SONY_LED_SUPPORT)
sony_leds_remove(sc);
- if (sc->quirks & SONY_BATTERY_SUPPORT) {
- hid_hw_close(hdev);
+ if (sc->quirks & SONY_BATTERY_SUPPORT)
sony_battery_remove(sc);
- }
+
+ if (sc->touchpad)
+ sony_unregister_touchpad(sc);
+
+ if (sc->sensor_dev)
+ sony_unregister_sensors(sc);
+
+ if (sc->quirks & DUALSHOCK4_CONTROLLER_BT)
+ device_remove_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
sony_cancel_work_sync(sc);
@@ -2592,7 +2897,7 @@ static const struct hid_device_id sony_devices[] = {
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2),
.driver_data = DUALSHOCK4_CONTROLLER_BT },
{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE),
- .driver_data = DUALSHOCK4_CONTROLLER_USB },
+ .driver_data = DUALSHOCK4_DONGLE },
/* Nyko Core Controller for PS3 */
{ HID_USB_DEVICE(USB_VENDOR_ID_SINO_LITE, USB_DEVICE_ID_SINO_LITE_CONTROLLER),
.driver_data = SIXAXIS_CONTROLLER_USB | SINO_LITE_CONTROLLER },
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
new file mode 100644
index 0000000..a4a6c90
--- /dev/null
+++ b/drivers/hid/hid-steam.c
@@ -0,0 +1,1145 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * HID driver for Valve Steam Controller
+ *
+ * Copyright (c) 2018 Rodrigo Rivas Costa <rodrigorivascosta@gmail.com>
+ *
+ * Supports both the wired and wireless interfaces.
+ *
+ * This controller has a builtin emulation of mouse and keyboard: the right pad
+ * can be used as a mouse, the shoulder buttons are mouse buttons, A and B
+ * buttons are ENTER and ESCAPE, and so on. This is implemented as additional
+ * HID interfaces.
+ *
+ * This is known as the "lizard mode", because apparently lizards like to use
+ * the computer from the coach, without a proper mouse and keyboard.
+ *
+ * This driver will disable the lizard mode when the input device is opened
+ * and re-enable it when the input device is closed, so as not to break user
+ * mode behaviour. The lizard_mode parameter can be used to change that.
+ *
+ * There are a few user space applications (notably Steam Client) that use
+ * the hidraw interface directly to create input devices (XTest, uinput...).
+ * In order to avoid breaking them this driver creates a layered hidraw device,
+ * so it can detect when the client is running and then:
+ * - it will not send any command to the controller.
+ * - this input device will be removed, to avoid double input of the same
+ * user action.
+ * When the client is closed, this input device will be created again.
+ *
+ * For additional functions, such as changing the right-pad margin or switching
+ * the led, you can use the user-space tool at:
+ *
+ * https://github.com/rodrigorc/steamctrl
+ */
+
+#include <linux/device.h>
+#include <linux/input.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+#include <linux/rcupdate.h>
+#include <linux/delay.h>
+#include <linux/power_supply.h>
+#include "hid-ids.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Rodrigo Rivas Costa <rodrigorivascosta@gmail.com>");
+
+static bool lizard_mode = true;
+
+static DEFINE_MUTEX(steam_devices_lock);
+static LIST_HEAD(steam_devices);
+
+#define STEAM_QUIRK_WIRELESS BIT(0)
+
+/* Touch pads are 40 mm in diameter and 65535 units */
+#define STEAM_PAD_RESOLUTION 1638
+/* Trigger runs are about 5 mm and 256 units */
+#define STEAM_TRIGGER_RESOLUTION 51
+/* Joystick runs are about 5 mm and 256 units */
+#define STEAM_JOYSTICK_RESOLUTION 51
+
+#define STEAM_PAD_FUZZ 256
+
+/*
+ * Commands that can be sent in a feature report.
+ * Thanks to Valve for some valuable hints.
+ */
+#define STEAM_CMD_SET_MAPPINGS 0x80
+#define STEAM_CMD_CLEAR_MAPPINGS 0x81
+#define STEAM_CMD_GET_MAPPINGS 0x82
+#define STEAM_CMD_GET_ATTRIB 0x83
+#define STEAM_CMD_GET_ATTRIB_LABEL 0x84
+#define STEAM_CMD_DEFAULT_MAPPINGS 0x85
+#define STEAM_CMD_FACTORY_RESET 0x86
+#define STEAM_CMD_WRITE_REGISTER 0x87
+#define STEAM_CMD_CLEAR_REGISTER 0x88
+#define STEAM_CMD_READ_REGISTER 0x89
+#define STEAM_CMD_GET_REGISTER_LABEL 0x8a
+#define STEAM_CMD_GET_REGISTER_MAX 0x8b
+#define STEAM_CMD_GET_REGISTER_DEFAULT 0x8c
+#define STEAM_CMD_SET_MODE 0x8d
+#define STEAM_CMD_DEFAULT_MOUSE 0x8e
+#define STEAM_CMD_FORCEFEEDBAK 0x8f
+#define STEAM_CMD_REQUEST_COMM_STATUS 0xb4
+#define STEAM_CMD_GET_SERIAL 0xae
+
+/* Some useful register ids */
+#define STEAM_REG_LPAD_MODE 0x07
+#define STEAM_REG_RPAD_MODE 0x08
+#define STEAM_REG_RPAD_MARGIN 0x18
+#define STEAM_REG_LED 0x2d
+#define STEAM_REG_GYRO_MODE 0x30
+
+/* Raw event identifiers */
+#define STEAM_EV_INPUT_DATA 0x01
+#define STEAM_EV_CONNECT 0x03
+#define STEAM_EV_BATTERY 0x04
+
+/* Values for GYRO_MODE (bitmask) */
+#define STEAM_GYRO_MODE_OFF 0x0000
+#define STEAM_GYRO_MODE_STEERING 0x0001
+#define STEAM_GYRO_MODE_TILT 0x0002
+#define STEAM_GYRO_MODE_SEND_ORIENTATION 0x0004
+#define STEAM_GYRO_MODE_SEND_RAW_ACCEL 0x0008
+#define STEAM_GYRO_MODE_SEND_RAW_GYRO 0x0010
+
+/* Other random constants */
+#define STEAM_SERIAL_LEN 10
+
+struct steam_device {
+ struct list_head list;
+ spinlock_t lock;
+ struct hid_device *hdev, *client_hdev;
+ struct mutex mutex;
+ bool client_opened;
+ struct input_dev __rcu *input;
+ unsigned long quirks;
+ struct work_struct work_connect;
+ bool connected;
+ char serial_no[STEAM_SERIAL_LEN + 1];
+ struct power_supply_desc battery_desc;
+ struct power_supply __rcu *battery;
+ u8 battery_charge;
+ u16 voltage;
+};
+
+static int steam_recv_report(struct steam_device *steam,
+ u8 *data, int size)
+{
+ struct hid_report *r;
+ u8 *buf;
+ int ret;
+
+ r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+ if (hid_report_len(r) < 64)
+ return -EINVAL;
+
+ buf = hid_alloc_report_buf(r, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ /*
+ * The report ID is always 0, so strip the first byte from the output.
+ * hid_report_len() is not counting the report ID, so +1 to the length
+ * or else we get a EOVERFLOW. We are safe from a buffer overflow
+ * because hid_alloc_report_buf() allocates +7 bytes.
+ */
+ ret = hid_hw_raw_request(steam->hdev, 0x00,
+ buf, hid_report_len(r) + 1,
+ HID_FEATURE_REPORT, HID_REQ_GET_REPORT);
+ if (ret > 0)
+ memcpy(data, buf + 1, min(size, ret - 1));
+ kfree(buf);
+ return ret;
+}
+
+static int steam_send_report(struct steam_device *steam,
+ u8 *cmd, int size)
+{
+ struct hid_report *r;
+ u8 *buf;
+ unsigned int retries = 50;
+ int ret;
+
+ r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+ if (hid_report_len(r) < 64)
+ return -EINVAL;
+
+ buf = hid_alloc_report_buf(r, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ /* The report ID is always 0 */
+ memcpy(buf + 1, cmd, size);
+
+ /*
+ * Sometimes the wireless controller fails with EPIPE
+ * when sending a feature report.
+ * Doing a HID_REQ_GET_REPORT and waiting for a while
+ * seems to fix that.
+ */
+ do {
+ ret = hid_hw_raw_request(steam->hdev, 0,
+ buf, size + 1,
+ HID_FEATURE_REPORT, HID_REQ_SET_REPORT);
+ if (ret != -EPIPE)
+ break;
+ msleep(20);
+ } while (--retries);
+
+ kfree(buf);
+ if (ret < 0)
+ hid_err(steam->hdev, "%s: error %d (%*ph)\n", __func__,
+ ret, size, cmd);
+ return ret;
+}
+
+static inline int steam_send_report_byte(struct steam_device *steam, u8 cmd)
+{
+ return steam_send_report(steam, &cmd, 1);
+}
+
+static int steam_write_registers(struct steam_device *steam,
+ /* u8 reg, u16 val */...)
+{
+ /* Send: 0x87 len (reg valLo valHi)* */
+ u8 reg;
+ u16 val;
+ u8 cmd[64] = {STEAM_CMD_WRITE_REGISTER, 0x00};
+ va_list args;
+
+ va_start(args, steam);
+ for (;;) {
+ reg = va_arg(args, int);
+ if (reg == 0)
+ break;
+ val = va_arg(args, int);
+ cmd[cmd[1] + 2] = reg;
+ cmd[cmd[1] + 3] = val & 0xff;
+ cmd[cmd[1] + 4] = val >> 8;
+ cmd[1] += 3;
+ }
+ va_end(args);
+
+ return steam_send_report(steam, cmd, 2 + cmd[1]);
+}
+
+static int steam_get_serial(struct steam_device *steam)
+{
+ /*
+ * Send: 0xae 0x15 0x01
+ * Recv: 0xae 0x15 0x01 serialnumber (10 chars)
+ */
+ int ret;
+ u8 cmd[] = {STEAM_CMD_GET_SERIAL, 0x15, 0x01};
+ u8 reply[3 + STEAM_SERIAL_LEN + 1];
+
+ ret = steam_send_report(steam, cmd, sizeof(cmd));
+ if (ret < 0)
+ return ret;
+ ret = steam_recv_report(steam, reply, sizeof(reply));
+ if (ret < 0)
+ return ret;
+ if (reply[0] != 0xae || reply[1] != 0x15 || reply[2] != 0x01)
+ return -EIO;
+ reply[3 + STEAM_SERIAL_LEN] = 0;
+ strlcpy(steam->serial_no, reply + 3, sizeof(steam->serial_no));
+ return 0;
+}
+
+/*
+ * This command requests the wireless adaptor to post an event
+ * with the connection status. Useful if this driver is loaded when
+ * the controller is already connected.
+ */
+static inline int steam_request_conn_status(struct steam_device *steam)
+{
+ return steam_send_report_byte(steam, STEAM_CMD_REQUEST_COMM_STATUS);
+}
+
+static void steam_set_lizard_mode(struct steam_device *steam, bool enable)
+{
+ if (enable) {
+ /* enable esc, enter, cursors */
+ steam_send_report_byte(steam, STEAM_CMD_DEFAULT_MAPPINGS);
+ /* enable mouse */
+ steam_send_report_byte(steam, STEAM_CMD_DEFAULT_MOUSE);
+ steam_write_registers(steam,
+ STEAM_REG_RPAD_MARGIN, 0x01, /* enable margin */
+ 0);
+ } else {
+ /* disable esc, enter, cursor */
+ steam_send_report_byte(steam, STEAM_CMD_CLEAR_MAPPINGS);
+ steam_write_registers(steam,
+ STEAM_REG_RPAD_MODE, 0x07, /* disable mouse */
+ STEAM_REG_RPAD_MARGIN, 0x00, /* disable margin */
+ 0);
+ }
+}
+
+static int steam_input_open(struct input_dev *dev)
+{
+ struct steam_device *steam = input_get_drvdata(dev);
+
+ mutex_lock(&steam->mutex);
+ if (!steam->client_opened && lizard_mode)
+ steam_set_lizard_mode(steam, false);
+ mutex_unlock(&steam->mutex);
+ return 0;
+}
+
+static void steam_input_close(struct input_dev *dev)
+{
+ struct steam_device *steam = input_get_drvdata(dev);
+
+ mutex_lock(&steam->mutex);
+ if (!steam->client_opened && lizard_mode)
+ steam_set_lizard_mode(steam, true);
+ mutex_unlock(&steam->mutex);
+}
+
+static enum power_supply_property steam_battery_props[] = {
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_SCOPE,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+};
+
+static int steam_battery_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct steam_device *steam = power_supply_get_drvdata(psy);
+ unsigned long flags;
+ s16 volts;
+ u8 batt;
+ int ret = 0;
+
+ spin_lock_irqsave(&steam->lock, flags);
+ volts = steam->voltage;
+ batt = steam->battery_charge;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_PRESENT:
+ val->intval = 1;
+ break;
+ case POWER_SUPPLY_PROP_SCOPE:
+ val->intval = POWER_SUPPLY_SCOPE_DEVICE;
+ break;
+ case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+ val->intval = volts * 1000; /* mV -> uV */
+ break;
+ case POWER_SUPPLY_PROP_CAPACITY:
+ val->intval = batt;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ return ret;
+}
+
+static int steam_battery_register(struct steam_device *steam)
+{
+ struct power_supply *battery;
+ struct power_supply_config battery_cfg = { .drv_data = steam, };
+ unsigned long flags;
+ int ret;
+
+ steam->battery_desc.type = POWER_SUPPLY_TYPE_BATTERY;
+ steam->battery_desc.properties = steam_battery_props;
+ steam->battery_desc.num_properties = ARRAY_SIZE(steam_battery_props);
+ steam->battery_desc.get_property = steam_battery_get_property;
+ steam->battery_desc.name = devm_kasprintf(&steam->hdev->dev,
+ GFP_KERNEL, "steam-controller-%s-battery",
+ steam->serial_no);
+ if (!steam->battery_desc.name)
+ return -ENOMEM;
+
+ /* avoid the warning of 0% battery while waiting for the first info */
+ spin_lock_irqsave(&steam->lock, flags);
+ steam->voltage = 3000;
+ steam->battery_charge = 100;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
+ battery = power_supply_register(&steam->hdev->dev,
+ &steam->battery_desc, &battery_cfg);
+ if (IS_ERR(battery)) {
+ ret = PTR_ERR(battery);
+ hid_err(steam->hdev,
+ "%s:power_supply_register failed with error %d\n",
+ __func__, ret);
+ return ret;
+ }
+ rcu_assign_pointer(steam->battery, battery);
+ power_supply_powers(battery, &steam->hdev->dev);
+ return 0;
+}
+
+static int steam_input_register(struct steam_device *steam)
+{
+ struct hid_device *hdev = steam->hdev;
+ struct input_dev *input;
+ int ret;
+
+ rcu_read_lock();
+ input = rcu_dereference(steam->input);
+ rcu_read_unlock();
+ if (input) {
+ dbg_hid("%s: already connected\n", __func__);
+ return 0;
+ }
+
+ input = input_allocate_device();
+ if (!input)
+ return -ENOMEM;
+
+ input_set_drvdata(input, steam);
+ input->dev.parent = &hdev->dev;
+ input->open = steam_input_open;
+ input->close = steam_input_close;
+
+ input->name = (steam->quirks & STEAM_QUIRK_WIRELESS) ?
+ "Wireless Steam Controller" :
+ "Steam Controller";
+ input->phys = hdev->phys;
+ input->uniq = steam->serial_no;
+ input->id.bustype = hdev->bus;
+ input->id.vendor = hdev->vendor;
+ input->id.product = hdev->product;
+ input->id.version = hdev->version;
+
+ input_set_capability(input, EV_KEY, BTN_TR2);
+ input_set_capability(input, EV_KEY, BTN_TL2);
+ input_set_capability(input, EV_KEY, BTN_TR);
+ input_set_capability(input, EV_KEY, BTN_TL);
+ input_set_capability(input, EV_KEY, BTN_Y);
+ input_set_capability(input, EV_KEY, BTN_B);
+ input_set_capability(input, EV_KEY, BTN_X);
+ input_set_capability(input, EV_KEY, BTN_A);
+ input_set_capability(input, EV_KEY, BTN_DPAD_UP);
+ input_set_capability(input, EV_KEY, BTN_DPAD_RIGHT);
+ input_set_capability(input, EV_KEY, BTN_DPAD_LEFT);
+ input_set_capability(input, EV_KEY, BTN_DPAD_DOWN);
+ input_set_capability(input, EV_KEY, BTN_SELECT);
+ input_set_capability(input, EV_KEY, BTN_MODE);
+ input_set_capability(input, EV_KEY, BTN_START);
+ input_set_capability(input, EV_KEY, BTN_GEAR_DOWN);
+ input_set_capability(input, EV_KEY, BTN_GEAR_UP);
+ input_set_capability(input, EV_KEY, BTN_THUMBR);
+ input_set_capability(input, EV_KEY, BTN_THUMBL);
+ input_set_capability(input, EV_KEY, BTN_THUMB);
+ input_set_capability(input, EV_KEY, BTN_THUMB2);
+
+ input_set_abs_params(input, ABS_HAT2Y, 0, 255, 0, 0);
+ input_set_abs_params(input, ABS_HAT2X, 0, 255, 0, 0);
+ input_set_abs_params(input, ABS_X, -32767, 32767, 0, 0);
+ input_set_abs_params(input, ABS_Y, -32767, 32767, 0, 0);
+ input_set_abs_params(input, ABS_RX, -32767, 32767,
+ STEAM_PAD_FUZZ, 0);
+ input_set_abs_params(input, ABS_RY, -32767, 32767,
+ STEAM_PAD_FUZZ, 0);
+ input_set_abs_params(input, ABS_HAT0X, -32767, 32767,
+ STEAM_PAD_FUZZ, 0);
+ input_set_abs_params(input, ABS_HAT0Y, -32767, 32767,
+ STEAM_PAD_FUZZ, 0);
+ input_abs_set_res(input, ABS_X, STEAM_JOYSTICK_RESOLUTION);
+ input_abs_set_res(input, ABS_Y, STEAM_JOYSTICK_RESOLUTION);
+ input_abs_set_res(input, ABS_RX, STEAM_PAD_RESOLUTION);
+ input_abs_set_res(input, ABS_RY, STEAM_PAD_RESOLUTION);
+ input_abs_set_res(input, ABS_HAT0X, STEAM_PAD_RESOLUTION);
+ input_abs_set_res(input, ABS_HAT0Y, STEAM_PAD_RESOLUTION);
+ input_abs_set_res(input, ABS_HAT2Y, STEAM_TRIGGER_RESOLUTION);
+ input_abs_set_res(input, ABS_HAT2X, STEAM_TRIGGER_RESOLUTION);
+
+ ret = input_register_device(input);
+ if (ret)
+ goto input_register_fail;
+
+ rcu_assign_pointer(steam->input, input);
+ return 0;
+
+input_register_fail:
+ input_free_device(input);
+ return ret;
+}
+
+static void steam_input_unregister(struct steam_device *steam)
+{
+ struct input_dev *input;
+ rcu_read_lock();
+ input = rcu_dereference(steam->input);
+ rcu_read_unlock();
+ if (!input)
+ return;
+ RCU_INIT_POINTER(steam->input, NULL);
+ synchronize_rcu();
+ input_unregister_device(input);
+}
+
+static void steam_battery_unregister(struct steam_device *steam)
+{
+ struct power_supply *battery;
+
+ rcu_read_lock();
+ battery = rcu_dereference(steam->battery);
+ rcu_read_unlock();
+
+ if (!battery)
+ return;
+ RCU_INIT_POINTER(steam->battery, NULL);
+ synchronize_rcu();
+ power_supply_unregister(battery);
+}
+
+static int steam_register(struct steam_device *steam)
+{
+ int ret;
+ bool client_opened;
+
+ /*
+ * This function can be called several times in a row with the
+ * wireless adaptor, without steam_unregister() between them, because
+ * another client send a get_connection_status command, for example.
+ * The battery and serial number are set just once per device.
+ */
+ if (!steam->serial_no[0]) {
+ /*
+ * Unlikely, but getting the serial could fail, and it is not so
+ * important, so make up a serial number and go on.
+ */
+ mutex_lock(&steam->mutex);
+ if (steam_get_serial(steam) < 0)
+ strlcpy(steam->serial_no, "XXXXXXXXXX",
+ sizeof(steam->serial_no));
+ mutex_unlock(&steam->mutex);
+
+ hid_info(steam->hdev, "Steam Controller '%s' connected",
+ steam->serial_no);
+
+ /* ignore battery errors, we can live without it */
+ if (steam->quirks & STEAM_QUIRK_WIRELESS)
+ steam_battery_register(steam);
+
+ mutex_lock(&steam_devices_lock);
+ list_add(&steam->list, &steam_devices);
+ mutex_unlock(&steam_devices_lock);
+ }
+
+ mutex_lock(&steam->mutex);
+ client_opened = steam->client_opened;
+ if (!client_opened)
+ steam_set_lizard_mode(steam, lizard_mode);
+ mutex_unlock(&steam->mutex);
+
+ if (!client_opened)
+ ret = steam_input_register(steam);
+ else
+ ret = 0;
+
+ return ret;
+}
+
+static void steam_unregister(struct steam_device *steam)
+{
+ steam_battery_unregister(steam);
+ steam_input_unregister(steam);
+ if (steam->serial_no[0]) {
+ hid_info(steam->hdev, "Steam Controller '%s' disconnected",
+ steam->serial_no);
+ mutex_lock(&steam_devices_lock);
+ list_del(&steam->list);
+ mutex_unlock(&steam_devices_lock);
+ steam->serial_no[0] = 0;
+ }
+}
+
+static void steam_work_connect_cb(struct work_struct *work)
+{
+ struct steam_device *steam = container_of(work, struct steam_device,
+ work_connect);
+ unsigned long flags;
+ bool connected;
+ int ret;
+
+ spin_lock_irqsave(&steam->lock, flags);
+ connected = steam->connected;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
+ if (connected) {
+ ret = steam_register(steam);
+ if (ret) {
+ hid_err(steam->hdev,
+ "%s:steam_register failed with error %d\n",
+ __func__, ret);
+ }
+ } else {
+ steam_unregister(steam);
+ }
+}
+
+static bool steam_is_valve_interface(struct hid_device *hdev)
+{
+ struct hid_report_enum *rep_enum;
+
+ /*
+ * The wired device creates 3 interfaces:
+ * 0: emulated mouse.
+ * 1: emulated keyboard.
+ * 2: the real game pad.
+ * The wireless device creates 5 interfaces:
+ * 0: emulated keyboard.
+ * 1-4: slots where up to 4 real game pads will be connected to.
+ * We know which one is the real gamepad interface because they are the
+ * only ones with a feature report.
+ */
+ rep_enum = &hdev->report_enum[HID_FEATURE_REPORT];
+ return !list_empty(&rep_enum->report_list);
+}
+
+static int steam_client_ll_parse(struct hid_device *hdev)
+{
+ struct steam_device *steam = hdev->driver_data;
+
+ return hid_parse_report(hdev, steam->hdev->dev_rdesc,
+ steam->hdev->dev_rsize);
+}
+
+static int steam_client_ll_start(struct hid_device *hdev)
+{
+ return 0;
+}
+
+static void steam_client_ll_stop(struct hid_device *hdev)
+{
+}
+
+static int steam_client_ll_open(struct hid_device *hdev)
+{
+ struct steam_device *steam = hdev->driver_data;
+
+ mutex_lock(&steam->mutex);
+ steam->client_opened = true;
+ mutex_unlock(&steam->mutex);
+
+ steam_input_unregister(steam);
+
+ return 0;
+}
+
+static void steam_client_ll_close(struct hid_device *hdev)
+{
+ struct steam_device *steam = hdev->driver_data;
+
+ unsigned long flags;
+ bool connected;
+
+ spin_lock_irqsave(&steam->lock, flags);
+ connected = steam->connected;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
+ mutex_lock(&steam->mutex);
+ steam->client_opened = false;
+ if (connected)
+ steam_set_lizard_mode(steam, lizard_mode);
+ mutex_unlock(&steam->mutex);
+
+ if (connected)
+ steam_input_register(steam);
+}
+
+static int steam_client_ll_raw_request(struct hid_device *hdev,
+ unsigned char reportnum, u8 *buf,
+ size_t count, unsigned char report_type,
+ int reqtype)
+{
+ struct steam_device *steam = hdev->driver_data;
+
+ return hid_hw_raw_request(steam->hdev, reportnum, buf, count,
+ report_type, reqtype);
+}
+
+static struct hid_ll_driver steam_client_ll_driver = {
+ .parse = steam_client_ll_parse,
+ .start = steam_client_ll_start,
+ .stop = steam_client_ll_stop,
+ .open = steam_client_ll_open,
+ .close = steam_client_ll_close,
+ .raw_request = steam_client_ll_raw_request,
+};
+
+static struct hid_device *steam_create_client_hid(struct hid_device *hdev)
+{
+ struct hid_device *client_hdev;
+
+ client_hdev = hid_allocate_device();
+ if (IS_ERR(client_hdev))
+ return client_hdev;
+
+ client_hdev->ll_driver = &steam_client_ll_driver;
+ client_hdev->dev.parent = hdev->dev.parent;
+ client_hdev->bus = hdev->bus;
+ client_hdev->vendor = hdev->vendor;
+ client_hdev->product = hdev->product;
+ client_hdev->version = hdev->version;
+ client_hdev->type = hdev->type;
+ client_hdev->country = hdev->country;
+ strlcpy(client_hdev->name, hdev->name,
+ sizeof(client_hdev->name));
+ strlcpy(client_hdev->phys, hdev->phys,
+ sizeof(client_hdev->phys));
+ /*
+ * Since we use the same device info than the real interface to
+ * trick userspace, we will be calling steam_probe recursively.
+ * We need to recognize the client interface somehow.
+ */
+ client_hdev->group = HID_GROUP_STEAM;
+ return client_hdev;
+}
+
+static int steam_probe(struct hid_device *hdev,
+ const struct hid_device_id *id)
+{
+ struct steam_device *steam;
+ int ret;
+
+ ret = hid_parse(hdev);
+ if (ret) {
+ hid_err(hdev,
+ "%s:parse of hid interface failed\n", __func__);
+ return ret;
+ }
+
+ /*
+ * The virtual client_dev is only used for hidraw.
+ * Also avoid the recursive probe.
+ */
+ if (hdev->group == HID_GROUP_STEAM)
+ return hid_hw_start(hdev, HID_CONNECT_HIDRAW);
+ /*
+ * The non-valve interfaces (mouse and keyboard emulation) are
+ * connected without changes.
+ */
+ if (!steam_is_valve_interface(hdev))
+ return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+
+ steam = devm_kzalloc(&hdev->dev, sizeof(*steam), GFP_KERNEL);
+ if (!steam) {
+ ret = -ENOMEM;
+ goto steam_alloc_fail;
+ }
+ steam->hdev = hdev;
+ hid_set_drvdata(hdev, steam);
+ spin_lock_init(&steam->lock);
+ mutex_init(&steam->mutex);
+ steam->quirks = id->driver_data;
+ INIT_WORK(&steam->work_connect, steam_work_connect_cb);
+
+ steam->client_hdev = steam_create_client_hid(hdev);
+ if (IS_ERR(steam->client_hdev)) {
+ ret = PTR_ERR(steam->client_hdev);
+ goto client_hdev_fail;
+ }
+ steam->client_hdev->driver_data = steam;
+
+ /*
+ * With the real steam controller interface, do not connect hidraw.
+ * Instead, create the client_hid and connect that.
+ */
+ ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_HIDRAW);
+ if (ret)
+ goto hid_hw_start_fail;
+
+ ret = hid_add_device(steam->client_hdev);
+ if (ret)
+ goto client_hdev_add_fail;
+
+ ret = hid_hw_open(hdev);
+ if (ret) {
+ hid_err(hdev,
+ "%s:hid_hw_open\n",
+ __func__);
+ goto hid_hw_open_fail;
+ }
+
+ if (steam->quirks & STEAM_QUIRK_WIRELESS) {
+ hid_info(hdev, "Steam wireless receiver connected");
+ /* If using a wireless adaptor ask for connection status */
+ steam->connected = false;
+ steam_request_conn_status(steam);
+ } else {
+ /* A wired connection is always present */
+ steam->connected = true;
+ ret = steam_register(steam);
+ if (ret) {
+ hid_err(hdev,
+ "%s:steam_register failed with error %d\n",
+ __func__, ret);
+ goto input_register_fail;
+ }
+ }
+
+ return 0;
+
+input_register_fail:
+hid_hw_open_fail:
+client_hdev_add_fail:
+ hid_hw_stop(hdev);
+hid_hw_start_fail:
+ hid_destroy_device(steam->client_hdev);
+client_hdev_fail:
+ cancel_work_sync(&steam->work_connect);
+steam_alloc_fail:
+ hid_err(hdev, "%s: failed with error %d\n",
+ __func__, ret);
+ return ret;
+}
+
+static void steam_remove(struct hid_device *hdev)
+{
+ struct steam_device *steam = hid_get_drvdata(hdev);
+
+ if (!steam || hdev->group == HID_GROUP_STEAM) {
+ hid_hw_stop(hdev);
+ return;
+ }
+
+ hid_destroy_device(steam->client_hdev);
+ steam->client_opened = false;
+ cancel_work_sync(&steam->work_connect);
+ if (steam->quirks & STEAM_QUIRK_WIRELESS) {
+ hid_info(hdev, "Steam wireless receiver disconnected");
+ }
+ hid_hw_close(hdev);
+ hid_hw_stop(hdev);
+ steam_unregister(steam);
+}
+
+static void steam_do_connect_event(struct steam_device *steam, bool connected)
+{
+ unsigned long flags;
+ bool changed;
+
+ spin_lock_irqsave(&steam->lock, flags);
+ changed = steam->connected != connected;
+ steam->connected = connected;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
+ if (changed && schedule_work(&steam->work_connect) == 0)
+ dbg_hid("%s: connected=%d event already queued\n",
+ __func__, connected);
+}
+
+/*
+ * Some input data in the protocol has the opposite sign.
+ * Clamp the values to 32767..-32767 so that the range is
+ * symmetrical and can be negated safely.
+ */
+static inline s16 steam_le16(u8 *data)
+{
+ s16 x = (s16) le16_to_cpup((__le16 *)data);
+
+ return x == -32768 ? -32767 : x;
+}
+
+/*
+ * The size for this message payload is 60.
+ * The known values are:
+ * (* values are not sent through wireless)
+ * (* accelerator/gyro is disabled by default)
+ * Offset| Type | Mapped to |Meaning
+ * -------+-------+-----------+--------------------------
+ * 4-7 | u32 | -- | sequence number
+ * 8-10 | 24bit | see below | buttons
+ * 11 | u8 | ABS_HAT2Y | left trigger
+ * 12 | u8 | ABS_HAT2X | right trigger
+ * 13-15 | -- | -- | always 0
+ * 16-17 | s16 | ABS_X/ABS_HAT0X | X value
+ * 18-19 | s16 | ABS_Y/ABS_HAT0Y | Y value
+ * 20-21 | s16 | ABS_RX | right-pad X value
+ * 22-23 | s16 | ABS_RY | right-pad Y value
+ * 24-25 | s16 | -- | * left trigger
+ * 26-27 | s16 | -- | * right trigger
+ * 28-29 | s16 | -- | * accelerometer X value
+ * 30-31 | s16 | -- | * accelerometer Y value
+ * 32-33 | s16 | -- | * accelerometer Z value
+ * 34-35 | s16 | -- | gyro X value
+ * 36-36 | s16 | -- | gyro Y value
+ * 38-39 | s16 | -- | gyro Z value
+ * 40-41 | s16 | -- | quaternion W value
+ * 42-43 | s16 | -- | quaternion X value
+ * 44-45 | s16 | -- | quaternion Y value
+ * 46-47 | s16 | -- | quaternion Z value
+ * 48-49 | -- | -- | always 0
+ * 50-51 | s16 | -- | * left trigger (uncalibrated)
+ * 52-53 | s16 | -- | * right trigger (uncalibrated)
+ * 54-55 | s16 | -- | * joystick X value (uncalibrated)
+ * 56-57 | s16 | -- | * joystick Y value (uncalibrated)
+ * 58-59 | s16 | -- | * left-pad X value
+ * 60-61 | s16 | -- | * left-pad Y value
+ * 62-63 | u16 | -- | * battery voltage
+ *
+ * The buttons are:
+ * Bit | Mapped to | Description
+ * ------+------------+--------------------------------
+ * 8.0 | BTN_TR2 | right trigger fully pressed
+ * 8.1 | BTN_TL2 | left trigger fully pressed
+ * 8.2 | BTN_TR | right shoulder
+ * 8.3 | BTN_TL | left shoulder
+ * 8.4 | BTN_Y | button Y
+ * 8.5 | BTN_B | button B
+ * 8.6 | BTN_X | button X
+ * 8.7 | BTN_A | button A
+ * 9.0 | BTN_DPAD_UP | lef-pad up
+ * 9.1 | BTN_DPAD_RIGHT | lef-pad right
+ * 9.2 | BTN_DPAD_LEFT | lef-pad left
+ * 9.3 | BTN_DPAD_DOWN | lef-pad down
+ * 9.4 | BTN_SELECT | menu left
+ * 9.5 | BTN_MODE | steam logo
+ * 9.6 | BTN_START | menu right
+ * 9.7 | BTN_GEAR_DOWN | left back lever
+ * 10.0 | BTN_GEAR_UP | right back lever
+ * 10.1 | -- | left-pad clicked
+ * 10.2 | BTN_THUMBR | right-pad clicked
+ * 10.3 | BTN_THUMB | left-pad touched (but see explanation below)
+ * 10.4 | BTN_THUMB2 | right-pad touched
+ * 10.5 | -- | unknown
+ * 10.6 | BTN_THUMBL | joystick clicked
+ * 10.7 | -- | lpad_and_joy
+ */
+
+static void steam_do_input_event(struct steam_device *steam,
+ struct input_dev *input, u8 *data)
+{
+ /* 24 bits of buttons */
+ u8 b8, b9, b10;
+ s16 x, y;
+ bool lpad_touched, lpad_and_joy;
+
+ b8 = data[8];
+ b9 = data[9];
+ b10 = data[10];
+
+ input_report_abs(input, ABS_HAT2Y, data[11]);
+ input_report_abs(input, ABS_HAT2X, data[12]);
+
+ /*
+ * These two bits tells how to interpret the values X and Y.
+ * lpad_and_joy tells that the joystick and the lpad are used at the
+ * same time.
+ * lpad_touched tells whether X/Y are to be read as lpad coord or
+ * joystick values.
+ * (lpad_touched || lpad_and_joy) tells if the lpad is really touched.
+ */
+ lpad_touched = b10 & BIT(3);
+ lpad_and_joy = b10 & BIT(7);
+ x = steam_le16(data + 16);
+ y = -steam_le16(data + 18);
+
+ input_report_abs(input, lpad_touched ? ABS_HAT0X : ABS_X, x);
+ input_report_abs(input, lpad_touched ? ABS_HAT0Y : ABS_Y, y);
+ /* Check if joystick is centered */
+ if (lpad_touched && !lpad_and_joy) {
+ input_report_abs(input, ABS_X, 0);
+ input_report_abs(input, ABS_Y, 0);
+ }
+ /* Check if lpad is untouched */
+ if (!(lpad_touched || lpad_and_joy)) {
+ input_report_abs(input, ABS_HAT0X, 0);
+ input_report_abs(input, ABS_HAT0Y, 0);
+ }
+
+ input_report_abs(input, ABS_RX, steam_le16(data + 20));
+ input_report_abs(input, ABS_RY, -steam_le16(data + 22));
+
+ input_event(input, EV_KEY, BTN_TR2, !!(b8 & BIT(0)));
+ input_event(input, EV_KEY, BTN_TL2, !!(b8 & BIT(1)));
+ input_event(input, EV_KEY, BTN_TR, !!(b8 & BIT(2)));
+ input_event(input, EV_KEY, BTN_TL, !!(b8 & BIT(3)));
+ input_event(input, EV_KEY, BTN_Y, !!(b8 & BIT(4)));
+ input_event(input, EV_KEY, BTN_B, !!(b8 & BIT(5)));
+ input_event(input, EV_KEY, BTN_X, !!(b8 & BIT(6)));
+ input_event(input, EV_KEY, BTN_A, !!(b8 & BIT(7)));
+ input_event(input, EV_KEY, BTN_SELECT, !!(b9 & BIT(4)));
+ input_event(input, EV_KEY, BTN_MODE, !!(b9 & BIT(5)));
+ input_event(input, EV_KEY, BTN_START, !!(b9 & BIT(6)));
+ input_event(input, EV_KEY, BTN_GEAR_DOWN, !!(b9 & BIT(7)));
+ input_event(input, EV_KEY, BTN_GEAR_UP, !!(b10 & BIT(0)));
+ input_event(input, EV_KEY, BTN_THUMBR, !!(b10 & BIT(2)));
+ input_event(input, EV_KEY, BTN_THUMBL, !!(b10 & BIT(6)));
+ input_event(input, EV_KEY, BTN_THUMB, lpad_touched || lpad_and_joy);
+ input_event(input, EV_KEY, BTN_THUMB2, !!(b10 & BIT(4)));
+ input_event(input, EV_KEY, BTN_DPAD_UP, !!(b9 & BIT(0)));
+ input_event(input, EV_KEY, BTN_DPAD_RIGHT, !!(b9 & BIT(1)));
+ input_event(input, EV_KEY, BTN_DPAD_LEFT, !!(b9 & BIT(2)));
+ input_event(input, EV_KEY, BTN_DPAD_DOWN, !!(b9 & BIT(3)));
+
+ input_sync(input);
+}
+
+/*
+ * The size for this message payload is 11.
+ * The known values are:
+ * Offset| Type | Meaning
+ * -------+-------+---------------------------
+ * 4-7 | u32 | sequence number
+ * 8-11 | -- | always 0
+ * 12-13 | u16 | voltage (mV)
+ * 14 | u8 | battery percent
+ */
+static void steam_do_battery_event(struct steam_device *steam,
+ struct power_supply *battery, u8 *data)
+{
+ unsigned long flags;
+
+ s16 volts = steam_le16(data + 12);
+ u8 batt = data[14];
+
+ /* Creating the battery may have failed */
+ rcu_read_lock();
+ battery = rcu_dereference(steam->battery);
+ if (likely(battery)) {
+ spin_lock_irqsave(&steam->lock, flags);
+ steam->voltage = volts;
+ steam->battery_charge = batt;
+ spin_unlock_irqrestore(&steam->lock, flags);
+ power_supply_changed(battery);
+ }
+ rcu_read_unlock();
+}
+
+static int steam_raw_event(struct hid_device *hdev,
+ struct hid_report *report, u8 *data,
+ int size)
+{
+ struct steam_device *steam = hid_get_drvdata(hdev);
+ struct input_dev *input;
+ struct power_supply *battery;
+
+ if (!steam)
+ return 0;
+
+ if (steam->client_opened)
+ hid_input_report(steam->client_hdev, HID_FEATURE_REPORT,
+ data, size, 0);
+ /*
+ * All messages are size=64, all values little-endian.
+ * The format is:
+ * Offset| Meaning
+ * -------+--------------------------------------------
+ * 0-1 | always 0x01, 0x00, maybe protocol version?
+ * 2 | type of message
+ * 3 | length of the real payload (not checked)
+ * 4-n | payload data, depends on the type
+ *
+ * There are these known types of message:
+ * 0x01: input data (60 bytes)
+ * 0x03: wireless connect/disconnect (1 byte)
+ * 0x04: battery status (11 bytes)
+ */
+
+ if (size != 64 || data[0] != 1 || data[1] != 0)
+ return 0;
+
+ switch (data[2]) {
+ case STEAM_EV_INPUT_DATA:
+ if (steam->client_opened)
+ return 0;
+ rcu_read_lock();
+ input = rcu_dereference(steam->input);
+ if (likely(input))
+ steam_do_input_event(steam, input, data);
+ rcu_read_unlock();
+ break;
+ case STEAM_EV_CONNECT:
+ /*
+ * The payload of this event is a single byte:
+ * 0x01: disconnected.
+ * 0x02: connected.
+ */
+ switch (data[4]) {
+ case 0x01:
+ steam_do_connect_event(steam, false);
+ break;
+ case 0x02:
+ steam_do_connect_event(steam, true);
+ break;
+ }
+ break;
+ case STEAM_EV_BATTERY:
+ if (steam->quirks & STEAM_QUIRK_WIRELESS) {
+ rcu_read_lock();
+ battery = rcu_dereference(steam->battery);
+ if (likely(battery)) {
+ steam_do_battery_event(steam, battery, data);
+ } else {
+ dbg_hid(
+ "%s: battery data without connect event\n",
+ __func__);
+ steam_do_connect_event(steam, true);
+ }
+ rcu_read_unlock();
+ }
+ break;
+ }
+ return 0;
+}
+
+static int steam_param_set_lizard_mode(const char *val,
+ const struct kernel_param *kp)
+{
+ struct steam_device *steam;
+ int ret;
+
+ ret = param_set_bool(val, kp);
+ if (ret)
+ return ret;
+
+ mutex_lock(&steam_devices_lock);
+ list_for_each_entry(steam, &steam_devices, list) {
+ mutex_lock(&steam->mutex);
+ if (!steam->client_opened)
+ steam_set_lizard_mode(steam, lizard_mode);
+ mutex_unlock(&steam->mutex);
+ }
+ mutex_unlock(&steam_devices_lock);
+ return 0;
+}
+
+static const struct kernel_param_ops steam_lizard_mode_ops = {
+ .set = steam_param_set_lizard_mode,
+ .get = param_get_bool,
+};
+
+module_param_cb(lizard_mode, &steam_lizard_mode_ops, &lizard_mode, 0644);
+MODULE_PARM_DESC(lizard_mode,
+ "Enable mouse and keyboard emulation (lizard mode) when the gamepad is not in use");
+
+static const struct hid_device_id steam_controllers[] = {
+ { /* Wired Steam Controller */
+ HID_USB_DEVICE(USB_VENDOR_ID_VALVE,
+ USB_DEVICE_ID_STEAM_CONTROLLER)
+ },
+ { /* Wireless Steam Controller */
+ HID_USB_DEVICE(USB_VENDOR_ID_VALVE,
+ USB_DEVICE_ID_STEAM_CONTROLLER_WIRELESS),
+ .driver_data = STEAM_QUIRK_WIRELESS
+ },
+ {}
+};
+
+MODULE_DEVICE_TABLE(hid, steam_controllers);
+
+static struct hid_driver steam_controller_driver = {
+ .name = "hid-steam",
+ .id_table = steam_controllers,
+ .probe = steam_probe,
+ .remove = steam_remove,
+ .raw_event = steam_raw_event,
+};
+
+module_hid_driver(steam_controller_driver);
\ No newline at end of file
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 731a7b3..f1d7bd4 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -31,6 +31,8 @@
#define UHID_NAME "uhid"
#define UHID_BUFSIZE 32
+static DEFINE_MUTEX(uhid_open_mutex);
+
struct uhid_device {
struct mutex devlock;
bool running;
@@ -145,15 +147,26 @@ static void uhid_hid_stop(struct hid_device *hid)
static int uhid_hid_open(struct hid_device *hid)
{
struct uhid_device *uhid = hid->driver_data;
+ int retval = 0;
- return uhid_queue_event(uhid, UHID_OPEN);
+ mutex_lock(&uhid_open_mutex);
+ if (!hid->open++) {
+ retval = uhid_queue_event(uhid, UHID_OPEN);
+ if (retval)
+ hid->open--;
+ }
+ mutex_unlock(&uhid_open_mutex);
+ return retval;
}
static void uhid_hid_close(struct hid_device *hid)
{
struct uhid_device *uhid = hid->driver_data;
- uhid_queue_event(uhid, UHID_CLOSE);
+ mutex_lock(&uhid_open_mutex);
+ if (!--hid->open)
+ uhid_queue_event(uhid, UHID_CLOSE);
+ mutex_unlock(&uhid_open_mutex);
}
static int uhid_hid_parse(struct hid_device *hid)
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 2cd7c71..df63315 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -201,9 +201,23 @@ static void *etm_setup_aux(int event_cpu, void **pages,
event_data = alloc_event_data(event_cpu);
if (!event_data)
return NULL;
-
INIT_WORK(&event_data->work, free_event_data);
+ /*
+ * In theory nothing prevent tracers in a trace session from being
+ * associated with different sinks, nor having a sink per tracer. But
+ * until we have HW with this kind of topology we need to assume tracers
+ * in a trace session are using the same sink. Therefore go through
+ * the coresight bus and pick the first enabled sink.
+ *
+ * When operated from sysFS users are responsible to enable the sink
+ * while from perf, the perf tools will do it based on the choice made
+ * on the cmd line. As such the "enable_sink" flag in sysFS is reset.
+ */
+ sink = coresight_get_enabled_sink(true);
+ if (!sink)
+ goto err;
+
mask = &event_data->mask;
/* Setup the path for each CPU in a trace session */
@@ -219,28 +233,15 @@ static void *etm_setup_aux(int event_cpu, void **pages,
* list of devices from source to sink that can be
* referenced later when the path is actually needed.
*/
- event_data->path[cpu] = coresight_build_path(csdev);
+ event_data->path[cpu] = coresight_build_path(csdev, sink);
if (IS_ERR(event_data->path[cpu]))
goto err;
}
- /*
- * In theory nothing prevent tracers in a trace session from being
- * associated with different sinks, nor having a sink per tracer. But
- * until we have HW with this kind of topology and a way to convey
- * sink assignement from the perf cmd line we need to assume tracers
- * in a trace session are using the same sink. Therefore pick the sink
- * found at the end of the first available path.
- */
- cpu = cpumask_first(mask);
- /* Grab the sink at the end of the path */
- sink = coresight_get_sink(event_data->path[cpu]);
- if (!sink)
- goto err;
-
if (!sink_ops(sink)->alloc_buffer)
goto err;
+ cpu = cpumask_first(mask);
/* Get the AUX specific data from the sink buffer */
event_data->snk_config =
sink_ops(sink)->alloc_buffer(sink, cpu, pages,
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 22079f8..44e1bc5 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -1037,7 +1037,8 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
}
pm_runtime_put(&adev->dev);
- dev_info(dev, "%s initialized\n", (char *)id->data);
+ dev_info(dev, "CPU%d: %s initialized\n",
+ drvdata->cpu, (char *)id->data);
if (boot_enable) {
coresight_enable(drvdata->csdev);
@@ -1056,20 +1057,25 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
}
static struct amba_id etm4_ids[] = {
- { /* ETM 4.0 - Cortex-A53 */
+ {
.id = 0x000bb95d,
.mask = 0x000fffff,
- .data = "ETM 4.0",
+ .data = "Cortex-A53 ETM v4.0",
},
- { /* ETM 4.0 - Cortex-A57 */
+ {
.id = 0x000bb95e,
.mask = 0x000fffff,
- .data = "ETM 4.0",
+ .data = "Cortex-A57 ETM v4.0",
},
- { /* ETM 4.0 - A72, Maia, HiSilicon */
+ {
.id = 0x000bb95a,
.mask = 0x000fffff,
- .data = "ETM 4.0",
+ .data = "Cortex-A72 ETM v4.0",
+ },
+ {
+ .id = 0x000bb959,
+ .mask = 0x000fffff,
+ .data = "Cortex-A73 ETM v4.0",
},
{ 0, 0},
};
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 196a14b..ef9d8e9 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -111,7 +111,9 @@ static inline void CS_UNLOCK(void __iomem *addr)
void coresight_disable_path(struct list_head *path);
int coresight_enable_path(struct list_head *path, u32 mode);
struct coresight_device *coresight_get_sink(struct list_head *path);
-struct list_head *coresight_build_path(struct coresight_device *csdev);
+struct coresight_device *coresight_get_enabled_sink(bool reset);
+struct list_head *coresight_build_path(struct coresight_device *csdev,
+ struct coresight_device *sink);
void coresight_release_path(struct list_head *path);
#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 03ce12ad..6c6ebd5 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -70,7 +70,7 @@ static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata)
* When operating in sysFS mode the content of the buffer needs to be
* read before the TMC is disabled.
*/
- if (local_read(&drvdata->mode) == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
tmc_etb_dump_hw(drvdata);
tmc_disable_hw(drvdata);
@@ -103,19 +103,14 @@ static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata)
CS_LOCK(drvdata->base);
}
-static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev)
{
int ret = 0;
bool used = false;
char *buf = NULL;
- long val;
unsigned long flags;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
- /* This shouldn't be happening */
- if (WARN_ON(mode != CS_MODE_SYSFS))
- return -EINVAL;
-
/*
* If we don't have a buffer release the lock and allocate memory.
* Otherwise keep the lock and move along.
@@ -138,13 +133,12 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev, u32 mode)
goto out;
}
- val = local_xchg(&drvdata->mode, mode);
/*
* In sysFS mode we can have multiple writers per sink. Since this
* sink is already enabled no memory is needed and the HW need not be
* touched.
*/
- if (val == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
goto out;
/*
@@ -163,6 +157,7 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev, u32 mode)
drvdata->buf = buf;
}
+ drvdata->mode = CS_MODE_SYSFS;
tmc_etb_enable_hw(drvdata);
out:
spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -177,34 +172,29 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev, u32 mode)
return ret;
}
-static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etf_sink_perf(struct coresight_device *csdev)
{
int ret = 0;
- long val;
unsigned long flags;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
- /* This shouldn't be happening */
- if (WARN_ON(mode != CS_MODE_PERF))
- return -EINVAL;
-
spin_lock_irqsave(&drvdata->spinlock, flags);
if (drvdata->reading) {
ret = -EINVAL;
goto out;
}
- val = local_xchg(&drvdata->mode, mode);
/*
* In Perf mode there can be only one writer per sink. There
* is also no need to continue if the ETB/ETR is already operated
* from sysFS.
*/
- if (val != CS_MODE_DISABLED) {
+ if (drvdata->mode != CS_MODE_DISABLED) {
ret = -EINVAL;
goto out;
}
+ drvdata->mode = CS_MODE_PERF;
tmc_etb_enable_hw(drvdata);
out:
spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -216,9 +206,9 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode)
{
switch (mode) {
case CS_MODE_SYSFS:
- return tmc_enable_etf_sink_sysfs(csdev, mode);
+ return tmc_enable_etf_sink_sysfs(csdev);
case CS_MODE_PERF:
- return tmc_enable_etf_sink_perf(csdev, mode);
+ return tmc_enable_etf_sink_perf(csdev);
}
/* We shouldn't be here */
@@ -227,7 +217,6 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode)
static void tmc_disable_etf_sink(struct coresight_device *csdev)
{
- long val;
unsigned long flags;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
@@ -237,10 +226,11 @@ static void tmc_disable_etf_sink(struct coresight_device *csdev)
return;
}
- val = local_xchg(&drvdata->mode, CS_MODE_DISABLED);
/* Disable the TMC only if it needs to */
- if (val != CS_MODE_DISABLED)
+ if (drvdata->mode != CS_MODE_DISABLED) {
tmc_etb_disable_hw(drvdata);
+ drvdata->mode = CS_MODE_DISABLED;
+ }
spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -260,7 +250,7 @@ static int tmc_enable_etf_link(struct coresight_device *csdev,
}
tmc_etf_enable_hw(drvdata);
- local_set(&drvdata->mode, CS_MODE_SYSFS);
+ drvdata->mode = CS_MODE_SYSFS;
spin_unlock_irqrestore(&drvdata->spinlock, flags);
dev_info(drvdata->dev, "TMC-ETF enabled\n");
@@ -280,7 +270,7 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
}
tmc_etf_disable_hw(drvdata);
- local_set(&drvdata->mode, CS_MODE_DISABLED);
+ drvdata->mode = CS_MODE_DISABLED;
spin_unlock_irqrestore(&drvdata->spinlock, flags);
dev_info(drvdata->dev, "TMC disabled\n");
@@ -381,7 +371,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
return;
/* This shouldn't happen */
- if (WARN_ON_ONCE(local_read(&drvdata->mode) != CS_MODE_PERF))
+ if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF))
return;
CS_UNLOCK(drvdata->base);
@@ -502,7 +492,6 @@ const struct coresight_ops tmc_etf_cs_ops = {
int tmc_read_prepare_etb(struct tmc_drvdata *drvdata)
{
- long val;
enum tmc_mode mode;
int ret = 0;
unsigned long flags;
@@ -526,9 +515,8 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata)
goto out;
}
- val = local_read(&drvdata->mode);
/* Don't interfere if operated from Perf */
- if (val == CS_MODE_PERF) {
+ if (drvdata->mode == CS_MODE_PERF) {
ret = -EINVAL;
goto out;
}
@@ -540,7 +528,7 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata)
}
/* Disable the TMC if need be */
- if (val == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
tmc_etb_disable_hw(drvdata);
drvdata->reading = true;
@@ -571,7 +559,7 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata)
}
/* Re-enable the TMC if need be */
- if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
+ if (drvdata->mode == CS_MODE_SYSFS) {
/*
* The trace run will continue with the same allocated trace
* buffer. As such zero-out the buffer so that we don't end
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 886ea83..2db4857 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -15,11 +15,30 @@
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/circ_buf.h>
#include <linux/coresight.h>
#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+
#include "coresight-priv.h"
#include "coresight-tmc.h"
+/**
+ * struct cs_etr_buffer - keep track of a recording session' specifics
+ * @tmc: generic portion of the TMC buffers
+ * @paddr: the physical address of a DMA'able contiguous memory area
+ * @vaddr: the virtual address associated to @paddr
+ * @size: how much memory we have, starting at @paddr
+ * @dev: the device @vaddr has been tied to
+ */
+struct cs_etr_buffers {
+ struct cs_buffers tmc;
+ dma_addr_t paddr;
+ void __iomem *vaddr;
+ u32 size;
+ struct device *dev;
+};
+
static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
{
u32 axictl;
@@ -86,26 +105,22 @@ static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
* When operating in sysFS mode the content of the buffer needs to be
* read before the TMC is disabled.
*/
- if (local_read(&drvdata->mode) == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
tmc_etr_dump_hw(drvdata);
tmc_disable_hw(drvdata);
CS_LOCK(drvdata->base);
}
-static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
{
int ret = 0;
bool used = false;
- long val;
unsigned long flags;
void __iomem *vaddr = NULL;
dma_addr_t paddr;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
- /* This shouldn't be happening */
- if (WARN_ON(mode != CS_MODE_SYSFS))
- return -EINVAL;
/*
* If we don't have a buffer release the lock and allocate memory.
@@ -134,13 +149,12 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev, u32 mode)
goto out;
}
- val = local_xchg(&drvdata->mode, mode);
/*
* In sysFS mode we can have multiple writers per sink. Since this
* sink is already enabled no memory is needed and the HW need not be
* touched.
*/
- if (val == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
goto out;
/*
@@ -155,8 +169,7 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev, u32 mode)
drvdata->buf = drvdata->vaddr;
}
- memset(drvdata->vaddr, 0, drvdata->size);
-
+ drvdata->mode = CS_MODE_SYSFS;
tmc_etr_enable_hw(drvdata);
out:
spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -171,34 +184,29 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev, u32 mode)
return ret;
}
-static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etr_sink_perf(struct coresight_device *csdev)
{
int ret = 0;
- long val;
unsigned long flags;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
- /* This shouldn't be happening */
- if (WARN_ON(mode != CS_MODE_PERF))
- return -EINVAL;
-
spin_lock_irqsave(&drvdata->spinlock, flags);
if (drvdata->reading) {
ret = -EINVAL;
goto out;
}
- val = local_xchg(&drvdata->mode, mode);
/*
* In Perf mode there can be only one writer per sink. There
* is also no need to continue if the ETR is already operated
* from sysFS.
*/
- if (val != CS_MODE_DISABLED) {
+ if (drvdata->mode != CS_MODE_DISABLED) {
ret = -EINVAL;
goto out;
}
+ drvdata->mode = CS_MODE_PERF;
tmc_etr_enable_hw(drvdata);
out:
spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -210,9 +218,9 @@ static int tmc_enable_etr_sink(struct coresight_device *csdev, u32 mode)
{
switch (mode) {
case CS_MODE_SYSFS:
- return tmc_enable_etr_sink_sysfs(csdev, mode);
+ return tmc_enable_etr_sink_sysfs(csdev);
case CS_MODE_PERF:
- return tmc_enable_etr_sink_perf(csdev, mode);
+ return tmc_enable_etr_sink_perf(csdev);
}
/* We shouldn't be here */
@@ -221,7 +229,6 @@ static int tmc_enable_etr_sink(struct coresight_device *csdev, u32 mode)
static void tmc_disable_etr_sink(struct coresight_device *csdev)
{
- long val;
unsigned long flags;
struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
@@ -231,19 +238,244 @@ static void tmc_disable_etr_sink(struct coresight_device *csdev)
return;
}
- val = local_xchg(&drvdata->mode, CS_MODE_DISABLED);
/* Disable the TMC only if it needs to */
- if (val != CS_MODE_DISABLED)
+ if (drvdata->mode != CS_MODE_DISABLED) {
tmc_etr_disable_hw(drvdata);
+ drvdata->mode = CS_MODE_DISABLED;
+ }
spin_unlock_irqrestore(&drvdata->spinlock, flags);
dev_info(drvdata->dev, "TMC-ETR disabled\n");
}
+static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, int cpu,
+ void **pages, int nr_pages, bool overwrite)
+{
+ int node;
+ struct cs_etr_buffers *buf;
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ if (cpu == -1)
+ cpu = smp_processor_id();
+ node = cpu_to_node(cpu);
+
+ /* Allocate memory structure for interaction with Perf */
+ buf = kzalloc_node(sizeof(struct cs_etr_buffers), GFP_KERNEL, node);
+ if (!buf)
+ return NULL;
+
+ buf->dev = drvdata->dev;
+ buf->size = drvdata->size;
+ buf->vaddr = dma_alloc_coherent(buf->dev, buf->size,
+ &buf->paddr, GFP_KERNEL);
+ if (!buf->vaddr) {
+ kfree(buf);
+ return NULL;
+ }
+
+ buf->tmc.snapshot = overwrite;
+ buf->tmc.nr_pages = nr_pages;
+ buf->tmc.data_pages = pages;
+
+ return buf;
+}
+
+static void tmc_free_etr_buffer(void *config)
+{
+ struct cs_etr_buffers *buf = config;
+
+ dma_free_coherent(buf->dev, buf->size, buf->vaddr, buf->paddr);
+ kfree(buf);
+}
+
+static int tmc_set_etr_buffer(struct coresight_device *csdev,
+ struct perf_output_handle *handle,
+ void *sink_config)
+{
+ int ret = 0;
+ unsigned long head;
+ struct cs_etr_buffers *buf = sink_config;
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ /* wrap head around to the amount of space we have */
+ head = handle->head & ((buf->tmc.nr_pages << PAGE_SHIFT) - 1);
+
+ /* find the page to write to */
+ buf->tmc.cur = head / PAGE_SIZE;
+
+ /* and offset within that page */
+ buf->tmc.offset = head % PAGE_SIZE;
+
+ local_set(&buf->tmc.data_size, 0);
+
+ /* Tell the HW where to put the trace data */
+ drvdata->vaddr = buf->vaddr;
+ drvdata->paddr = buf->paddr;
+ memset(drvdata->vaddr, 0, drvdata->size);
+
+ return ret;
+}
+
+static unsigned long tmc_reset_etr_buffer(struct coresight_device *csdev,
+ struct perf_output_handle *handle,
+ void *sink_config, bool *lost)
+{
+ long size = 0;
+ struct cs_etr_buffers *buf = sink_config;
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ if (buf) {
+ /*
+ * In snapshot mode ->data_size holds the new address of the
+ * ring buffer's head. The size itself is the whole address
+ * range since we want the latest information.
+ */
+ if (buf->tmc.snapshot) {
+ size = buf->tmc.nr_pages << PAGE_SHIFT;
+ handle->head = local_xchg(&buf->tmc.data_size, size);
+ }
+
+ /*
+ * Tell the tracer PMU how much we got in this run and if
+ * something went wrong along the way. Nobody else can use
+ * this cs_etr_buffers instance until we are done. As such
+ * resetting parameters here and squaring off with the ring
+ * buffer API in the tracer PMU is fine.
+ */
+ *lost = !!local_xchg(&buf->tmc.lost, 0);
+ size = local_xchg(&buf->tmc.data_size, 0);
+ }
+
+ /* Get ready for another run */
+ drvdata->vaddr = NULL;
+ drvdata->paddr = 0;
+
+ return size;
+}
+
+static void tmc_update_etr_buffer(struct coresight_device *csdev,
+ struct perf_output_handle *handle,
+ void *sink_config)
+{
+ int i, cur;
+ u32 *buf_ptr;
+ u32 read_ptr, write_ptr;
+ u32 status, to_read;
+ unsigned long offset;
+ struct cs_buffers *buf = sink_config;
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ if (!buf)
+ return;
+
+ /* This shouldn't happen */
+ if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF))
+ return;
+
+ CS_UNLOCK(drvdata->base);
+
+ tmc_flush_and_stop(drvdata);
+
+ read_ptr = readl_relaxed(drvdata->base + TMC_RRP);
+ write_ptr = readl_relaxed(drvdata->base + TMC_RWP);
+
+ /*
+ * Get a hold of the status register and see if a wrap around
+ * has occurred. If so adjust things accordingly.
+ */
+ status = readl_relaxed(drvdata->base + TMC_STS);
+ if (status & TMC_STS_FULL) {
+ local_inc(&buf->lost);
+ to_read = drvdata->size;
+ } else {
+ to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);
+ }
+
+ /*
+ * The TMC RAM buffer may be bigger than the space available in the
+ * perf ring buffer (handle->size). If so advance the RRP so that we
+ * get the latest trace data.
+ */
+ if (to_read > handle->size) {
+ u32 buffer_start, mask = 0;
+
+ /* Read buffer start address in system memory */
+ buffer_start = readl_relaxed(drvdata->base + TMC_DBALO);
+
+ /*
+ * The value written to RRP must be byte-address aligned to
+ * the width of the trace memory databus _and_ to a frame
+ * boundary (16 byte), whichever is the biggest. For example,
+ * for 32-bit, 64-bit and 128-bit wide trace memory, the four
+ * LSBs must be 0s. For 256-bit wide trace memory, the five
+ * LSBs must be 0s.
+ */
+ switch (drvdata->memwidth) {
+ case TMC_MEM_INTF_WIDTH_32BITS:
+ case TMC_MEM_INTF_WIDTH_64BITS:
+ case TMC_MEM_INTF_WIDTH_128BITS:
+ mask = GENMASK(31, 5);
+ break;
+ case TMC_MEM_INTF_WIDTH_256BITS:
+ mask = GENMASK(31, 6);
+ break;
+ }
+
+ /*
+ * Make sure the new size is aligned in accordance with the
+ * requirement explained above.
+ */
+ to_read = handle->size & mask;
+ /* Move the RAM read pointer up */
+ read_ptr = (write_ptr + drvdata->size) - to_read;
+ /* Make sure we are still within our limits */
+ if (read_ptr > (buffer_start + (drvdata->size - 1)))
+ read_ptr -= drvdata->size;
+ /* Tell the HW */
+ writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
+ local_inc(&buf->lost);
+ }
+
+ cur = buf->cur;
+ offset = buf->offset;
+
+ /* for every byte to read */
+ for (i = 0; i < to_read; i += 4) {
+ buf_ptr = buf->data_pages[cur] + offset;
+ *buf_ptr = readl_relaxed(drvdata->base + TMC_RRD);
+
+ offset += 4;
+ if (offset >= PAGE_SIZE) {
+ offset = 0;
+ cur++;
+ /* wrap around at the end of the buffer */
+ cur &= buf->nr_pages - 1;
+ }
+ }
+
+ /*
+ * In snapshot mode all we have to do is communicate to
+ * perf_aux_output_end() the address of the current head. In full
+ * trace mode the same function expects a size to move rb->aux_head
+ * forward.
+ */
+ if (buf->snapshot)
+ local_set(&buf->data_size, (cur * PAGE_SIZE) + offset);
+ else
+ local_add(to_read, &buf->data_size);
+
+ CS_LOCK(drvdata->base);
+}
+
static const struct coresight_ops_sink tmc_etr_sink_ops = {
.enable = tmc_enable_etr_sink,
.disable = tmc_disable_etr_sink,
+ .alloc_buffer = tmc_alloc_etr_buffer,
+ .free_buffer = tmc_free_etr_buffer,
+ .set_buffer = tmc_set_etr_buffer,
+ .reset_buffer = tmc_reset_etr_buffer,
+ .update_buffer = tmc_update_etr_buffer,
};
const struct coresight_ops tmc_etr_cs_ops = {
@@ -253,7 +485,6 @@ const struct coresight_ops tmc_etr_cs_ops = {
int tmc_read_prepare_etr(struct tmc_drvdata *drvdata)
{
int ret = 0;
- long val;
unsigned long flags;
/* config types are set a boot time and never change */
@@ -266,9 +497,8 @@ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata)
goto out;
}
- val = local_read(&drvdata->mode);
/* Don't interfere if operated from Perf */
- if (val == CS_MODE_PERF) {
+ if (drvdata->mode == CS_MODE_PERF) {
ret = -EINVAL;
goto out;
}
@@ -280,7 +510,7 @@ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata)
}
/* Disable the TMC if need be */
- if (val == CS_MODE_SYSFS)
+ if (drvdata->mode == CS_MODE_SYSFS)
tmc_etr_disable_hw(drvdata);
drvdata->reading = true;
@@ -303,7 +533,7 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
spin_lock_irqsave(&drvdata->spinlock, flags);
/* RE-enable the TMC if need be */
- if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
+ if (drvdata->mode == CS_MODE_SYSFS) {
/*
* The trace run will continue with the same allocated trace
* buffer. The trace buffer is cleared in tmc_etr_enable_hw(),
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 44b3ae3..51c0185 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -117,7 +117,7 @@ struct tmc_drvdata {
void __iomem *vaddr;
u32 size;
u32 len;
- local_t mode;
+ u32 mode;
enum tmc_config_type config_type;
enum tmc_mem_intf_width memwidth;
u32 trigger_cntr;
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 5ffabc3..d70085e 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -379,6 +379,52 @@ struct coresight_device *coresight_get_sink(struct list_head *path)
return csdev;
}
+static int coresight_enabled_sink(struct device *dev, void *data)
+{
+ bool *reset = data;
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+ csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) &&
+ csdev->activated) {
+ /*
+ * Now that we have a handle on the sink for this session,
+ * disable the sysFS "enable_sink" flag so that possible
+ * concurrent perf session that wish to use another sink don't
+ * trip on it. Doing so has no ramification for the current
+ * session.
+ */
+ if (*reset)
+ csdev->activated = false;
+
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
+ * coresight_get_enabled_sink - returns the first enabled sink found on the bus
+ * @deactivate: Whether the 'enable_sink' flag should be reset
+ *
+ * When operated from perf the deactivate parameter should be set to 'true'.
+ * That way the "enabled_sink" flag of the sink that was selected can be reset,
+ * allowing for other concurrent perf sessions to choose a different sink.
+ *
+ * When operated from sysFS users have full control and as such the deactivate
+ * parameter should be set to 'false', hence mandating users to explicitly
+ * clear the flag.
+ */
+struct coresight_device *coresight_get_enabled_sink(bool deactivate)
+{
+ struct device *dev = NULL;
+
+ dev = bus_find_device(&coresight_bustype, NULL, &deactivate,
+ coresight_enabled_sink);
+
+ return dev ? to_coresight_device(dev) : NULL;
+}
+
/**
* _coresight_build_path - recursively build a path from a @csdev to a sink.
* @csdev: The device to start from.
@@ -391,6 +437,7 @@ struct coresight_device *coresight_get_sink(struct list_head *path)
* last one.
*/
static int _coresight_build_path(struct coresight_device *csdev,
+ struct coresight_device *sink,
struct list_head *path)
{
int i;
@@ -398,15 +445,15 @@ static int _coresight_build_path(struct coresight_device *csdev,
struct coresight_node *node;
/* An activated sink has been found. Enqueue the element */
- if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
- csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && csdev->activated)
+ if (csdev == sink)
goto out;
/* Not a sink - recursively explore each port found on this element */
for (i = 0; i < csdev->nr_outport; i++) {
struct coresight_device *child_dev = csdev->conns[i].child_dev;
- if (child_dev && _coresight_build_path(child_dev, path) == 0) {
+ if (child_dev &&
+ _coresight_build_path(child_dev, sink, path) == 0) {
found = true;
break;
}
@@ -433,18 +480,22 @@ static int _coresight_build_path(struct coresight_device *csdev,
return 0;
}
-struct list_head *coresight_build_path(struct coresight_device *csdev)
+struct list_head *coresight_build_path(struct coresight_device *source,
+ struct coresight_device *sink)
{
struct list_head *path;
int rc;
+ if (!sink)
+ return ERR_PTR(-EINVAL);
+
path = kzalloc(sizeof(struct list_head), GFP_KERNEL);
if (!path)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(path);
- rc = _coresight_build_path(csdev, path);
+ rc = _coresight_build_path(source, sink, path);
if (rc) {
kfree(path);
return ERR_PTR(rc);
@@ -508,6 +559,7 @@ static int coresight_validate_source(struct coresight_device *csdev,
int coresight_enable(struct coresight_device *csdev)
{
int cpu, ret = 0;
+ struct coresight_device *sink;
struct list_head *path;
enum coresight_dev_subtype_source subtype;
@@ -530,7 +582,17 @@ int coresight_enable(struct coresight_device *csdev)
goto out;
}
- path = coresight_build_path(csdev);
+ /*
+ * Search for a valid sink for this session but don't reset the
+ * "enable_sink" flag in sysFS. Users get to do that explicitly.
+ */
+ sink = coresight_get_enabled_sink(false);
+ if (!sink) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ path = coresight_build_path(csdev, sink);
if (IS_ERR(path)) {
pr_err("building path(s) failed\n");
ret = PTR_ERR(path);
diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c
index d127ace..6ee866f 100644
--- a/drivers/ide/ide.c
+++ b/drivers/ide/ide.c
@@ -244,7 +244,7 @@ struct chs_geom {
static unsigned int ide_disks;
static struct chs_geom ide_disks_chs[MAX_HWIFS * MAX_DRIVES];
-static int ide_set_disk_chs(const char *str, struct kernel_param *kp)
+static int ide_set_disk_chs(const char *str, const struct kernel_param *kp)
{
unsigned int a, b, c = 0, h = 0, s = 0, i, j = 1;
@@ -328,7 +328,7 @@ static void ide_dev_apply_params(ide_drive_t *drive, u8 unit)
static unsigned int ide_ignore_cable;
-static int ide_set_ignore_cable(const char *s, struct kernel_param *kp)
+static int ide_set_ignore_cable(const char *s, const struct kernel_param *kp)
{
int i, j = 1;
diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index 6743b18..53b9557 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -4,7 +4,6 @@
menuconfig IIO
tristate "Industrial I/O support"
- select ANON_INODES
help
The industrial I/O subsystem provides a unified framework for
drivers for many different types of embedded sensors using a
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 5d5368a..0af2d78 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -24,7 +24,6 @@
config INFINIBAND_USER_ACCESS
tristate "InfiniBand userspace access (verbs and CM)"
- select ANON_INODES
---help---
Userspace InfiniBand access support. This enables the
kernel side of userspace verbs and the userspace
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index cedb447..228cb4c 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -150,7 +150,7 @@ static struct kparam_string kp_txselect = {
.string = txselect_list,
.maxlen = MAX_ATTEN_LEN
};
-static int setup_txselect(const char *, struct kernel_param *);
+static int setup_txselect(const char *, const struct kernel_param *);
module_param_call(txselect, setup_txselect, param_get_string,
&kp_txselect, S_IWUSR | S_IRUGO);
MODULE_PARM_DESC(txselect,
@@ -6177,7 +6177,7 @@ static void set_no_qsfp_atten(struct qib_devdata *dd, int change)
}
/* handle the txselect parameter changing */
-static int setup_txselect(const char *str, struct kernel_param *kp)
+static int setup_txselect(const char *str, const struct kernel_param *kp)
{
struct qib_devdata *dd;
unsigned long val;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 8acf337..d28e57c 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -80,7 +80,7 @@ module_param(srpt_srq_size, int, 0444);
MODULE_PARM_DESC(srpt_srq_size,
"Shared receive queue (SRQ) size.");
-static int srpt_get_u64_x(char *buffer, struct kernel_param *kp)
+static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp)
{
return sprintf(buffer, "0x%016llx", *(u64 *)kp->arg);
}
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 6261874..34ffa02 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -187,6 +187,19 @@
To compile this driver as a module, choose M here: the
module will be called apm-power.
+config INPUT_KEYRESET
+ bool "Reset key"
+ depends on INPUT
+ select INPUT_KEYCOMBO
+ ---help---
+ Say Y here if you want to reboot when some keys are pressed;
+
+config INPUT_KEYCOMBO
+ bool "Key combo"
+ depends on INPUT
+ ---help---
+ Say Y here if you want to take action when some keys are pressed;
+
comment "Input Device Drivers"
source "drivers/input/keyboard/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 595820b..6a3281c 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -26,5 +26,7 @@
obj-$(CONFIG_INPUT_MISC) += misc/
obj-$(CONFIG_INPUT_APMPOWER) += apm-power.o
+obj-$(CONFIG_INPUT_KEYRESET) += keyreset.o
+obj-$(CONFIG_INPUT_KEYCOMBO) += keycombo.o
obj-$(CONFIG_RMI4_CORE) += rmi4/
diff --git a/drivers/input/keyboard/goldfish_events.c b/drivers/input/keyboard/goldfish_events.c
index f6e643b..c877e56 100644
--- a/drivers/input/keyboard/goldfish_events.c
+++ b/drivers/input/keyboard/goldfish_events.c
@@ -17,6 +17,7 @@
#include <linux/interrupt.h>
#include <linux/types.h>
#include <linux/input.h>
+#include <linux/input/mt.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
@@ -24,6 +25,8 @@
#include <linux/io.h>
#include <linux/acpi.h>
+#define GOLDFISH_MAX_FINGERS 5
+
enum {
REG_READ = 0x00,
REG_SET_PAGE = 0x00,
@@ -52,7 +55,21 @@ static irqreturn_t events_interrupt(int irq, void *dev_id)
value = __raw_readl(edev->addr + REG_READ);
input_event(edev->input, type, code, value);
- input_sync(edev->input);
+ // Send an extra (EV_SYN, SYN_REPORT, 0x0) event
+ // if a key was pressed. Some keyboard device
+ // drivers may only send the EV_KEY event and
+ // not EV_SYN.
+ // Note that sending an extra SYN_REPORT is not
+ // necessary nor correct protocol with other
+ // devices such as touchscreens, which will send
+ // their own SYN_REPORT's when sufficient event
+ // information has been collected (e.g., for
+ // touchscreens, when pressure and X/Y coordinates
+ // have been received). Hence, we will only send
+ // this extra SYN_REPORT if type == EV_KEY.
+ if (type == EV_KEY) {
+ input_sync(edev->input);
+ }
return IRQ_HANDLED;
}
@@ -154,6 +171,15 @@ static int events_probe(struct platform_device *pdev)
input_dev->name = edev->name;
input_dev->id.bustype = BUS_HOST;
+ // Set the Goldfish Device to be multi-touch.
+ // In the Ranchu kernel, there is multi-touch-specific
+ // code for handling ABS_MT_SLOT events.
+ // See drivers/input/input.c:input_handle_abs_event.
+ // If we do not issue input_mt_init_slots,
+ // the kernel will filter out needed ABS_MT_SLOT
+ // events when we touch the screen in more than one place,
+ // preventing multi-touch with more than one finger from working.
+ input_mt_init_slots(input_dev, GOLDFISH_MAX_FINGERS, 0);
events_import_bits(edev, input_dev->evbit, EV_SYN, EV_MAX);
events_import_bits(edev, input_dev->keybit, EV_KEY, KEY_MAX);
diff --git a/drivers/input/keycombo.c b/drivers/input/keycombo.c
new file mode 100644
index 0000000..2fba451
--- /dev/null
+++ b/drivers/input/keycombo.c
@@ -0,0 +1,261 @@
+/* drivers/input/keycombo.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keycombo.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+struct keycombo_state {
+ struct input_handler input_handler;
+ unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+ unsigned long upbit[BITS_TO_LONGS(KEY_CNT)];
+ unsigned long key[BITS_TO_LONGS(KEY_CNT)];
+ spinlock_t lock;
+ struct workqueue_struct *wq;
+ int key_down_target;
+ int key_down;
+ int key_up;
+ struct delayed_work key_down_work;
+ int delay;
+ struct work_struct key_up_work;
+ void (*key_up_fn)(void *);
+ void (*key_down_fn)(void *);
+ void *priv;
+ int key_is_down;
+ struct wakeup_source combo_held_wake_source;
+ struct wakeup_source combo_up_wake_source;
+};
+
+static void do_key_down(struct work_struct *work)
+{
+ struct delayed_work *dwork = container_of(work, struct delayed_work,
+ work);
+ struct keycombo_state *state = container_of(dwork,
+ struct keycombo_state, key_down_work);
+ if (state->key_down_fn)
+ state->key_down_fn(state->priv);
+}
+
+static void do_key_up(struct work_struct *work)
+{
+ struct keycombo_state *state = container_of(work, struct keycombo_state,
+ key_up_work);
+ if (state->key_up_fn)
+ state->key_up_fn(state->priv);
+ __pm_relax(&state->combo_up_wake_source);
+}
+
+static void keycombo_event(struct input_handle *handle, unsigned int type,
+ unsigned int code, int value)
+{
+ unsigned long flags;
+ struct keycombo_state *state = handle->private;
+
+ if (type != EV_KEY)
+ return;
+
+ if (code >= KEY_MAX)
+ return;
+
+ if (!test_bit(code, state->keybit))
+ return;
+
+ spin_lock_irqsave(&state->lock, flags);
+ if (!test_bit(code, state->key) == !value)
+ goto done;
+ __change_bit(code, state->key);
+ if (test_bit(code, state->upbit)) {
+ if (value)
+ state->key_up++;
+ else
+ state->key_up--;
+ } else {
+ if (value)
+ state->key_down++;
+ else
+ state->key_down--;
+ }
+ if (state->key_down == state->key_down_target && state->key_up == 0) {
+ __pm_stay_awake(&state->combo_held_wake_source);
+ state->key_is_down = 1;
+ if (queue_delayed_work(state->wq, &state->key_down_work,
+ state->delay))
+ pr_debug("Key down work already queued!");
+ } else if (state->key_is_down) {
+ if (!cancel_delayed_work(&state->key_down_work)) {
+ __pm_stay_awake(&state->combo_up_wake_source);
+ queue_work(state->wq, &state->key_up_work);
+ }
+ __pm_relax(&state->combo_held_wake_source);
+ state->key_is_down = 0;
+ }
+done:
+ spin_unlock_irqrestore(&state->lock, flags);
+}
+
+static int keycombo_connect(struct input_handler *handler,
+ struct input_dev *dev,
+ const struct input_device_id *id)
+{
+ int i;
+ int ret;
+ struct input_handle *handle;
+ struct keycombo_state *state =
+ container_of(handler, struct keycombo_state, input_handler);
+ for (i = 0; i < KEY_MAX; i++) {
+ if (test_bit(i, state->keybit) && test_bit(i, dev->keybit))
+ break;
+ }
+ if (i == KEY_MAX)
+ return -ENODEV;
+
+ handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+ if (!handle)
+ return -ENOMEM;
+
+ handle->dev = dev;
+ handle->handler = handler;
+ handle->name = KEYCOMBO_NAME;
+ handle->private = state;
+
+ ret = input_register_handle(handle);
+ if (ret)
+ goto err_input_register_handle;
+
+ ret = input_open_device(handle);
+ if (ret)
+ goto err_input_open_device;
+
+ return 0;
+
+err_input_open_device:
+ input_unregister_handle(handle);
+err_input_register_handle:
+ kfree(handle);
+ return ret;
+}
+
+static void keycombo_disconnect(struct input_handle *handle)
+{
+ input_close_device(handle);
+ input_unregister_handle(handle);
+ kfree(handle);
+}
+
+static const struct input_device_id keycombo_ids[] = {
+ {
+ .flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+ .evbit = { BIT_MASK(EV_KEY) },
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(input, keycombo_ids);
+
+static int keycombo_probe(struct platform_device *pdev)
+{
+ int ret;
+ int key, *keyp;
+ struct keycombo_state *state;
+ struct keycombo_platform_data *pdata = pdev->dev.platform_data;
+
+ if (!pdata)
+ return -EINVAL;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ spin_lock_init(&state->lock);
+ keyp = pdata->keys_down;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ state->key_down_target++;
+ __set_bit(key, state->keybit);
+ }
+ if (pdata->keys_up) {
+ keyp = pdata->keys_up;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ __set_bit(key, state->keybit);
+ __set_bit(key, state->upbit);
+ }
+ }
+
+ state->wq = alloc_ordered_workqueue("keycombo", 0);
+ if (!state->wq)
+ return -ENOMEM;
+
+ state->priv = pdata->priv;
+
+ if (pdata->key_down_fn)
+ state->key_down_fn = pdata->key_down_fn;
+ INIT_DELAYED_WORK(&state->key_down_work, do_key_down);
+
+ if (pdata->key_up_fn)
+ state->key_up_fn = pdata->key_up_fn;
+ INIT_WORK(&state->key_up_work, do_key_up);
+
+ wakeup_source_init(&state->combo_held_wake_source, "key combo");
+ wakeup_source_init(&state->combo_up_wake_source, "key combo up");
+ state->delay = msecs_to_jiffies(pdata->key_down_delay);
+
+ state->input_handler.event = keycombo_event;
+ state->input_handler.connect = keycombo_connect;
+ state->input_handler.disconnect = keycombo_disconnect;
+ state->input_handler.name = KEYCOMBO_NAME;
+ state->input_handler.id_table = keycombo_ids;
+ ret = input_register_handler(&state->input_handler);
+ if (ret) {
+ kfree(state);
+ return ret;
+ }
+ platform_set_drvdata(pdev, state);
+ return 0;
+}
+
+int keycombo_remove(struct platform_device *pdev)
+{
+ struct keycombo_state *state = platform_get_drvdata(pdev);
+ input_unregister_handler(&state->input_handler);
+ destroy_workqueue(state->wq);
+ kfree(state);
+ return 0;
+}
+
+
+struct platform_driver keycombo_driver = {
+ .driver.name = KEYCOMBO_NAME,
+ .probe = keycombo_probe,
+ .remove = keycombo_remove,
+};
+
+static int __init keycombo_init(void)
+{
+ return platform_driver_register(&keycombo_driver);
+}
+
+static void __exit keycombo_exit(void)
+{
+ return platform_driver_unregister(&keycombo_driver);
+}
+
+module_init(keycombo_init);
+module_exit(keycombo_exit);
diff --git a/drivers/input/keyreset.c b/drivers/input/keyreset.c
new file mode 100644
index 0000000..7e5222a
--- /dev/null
+++ b/drivers/input/keyreset.c
@@ -0,0 +1,144 @@
+/* drivers/input/keyreset.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keyreset.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/keycombo.h>
+
+struct keyreset_state {
+ int restart_requested;
+ int (*reset_fn)(void);
+ struct platform_device *pdev_child;
+ struct work_struct restart_work;
+};
+
+static void do_restart(struct work_struct *unused)
+{
+ orderly_reboot();
+}
+
+static void do_reset_fn(void *priv)
+{
+ struct keyreset_state *state = priv;
+ if (state->restart_requested)
+ panic("keyboard reset failed, %d", state->restart_requested);
+ if (state->reset_fn) {
+ state->restart_requested = state->reset_fn();
+ } else {
+ pr_info("keyboard reset\n");
+ schedule_work(&state->restart_work);
+ state->restart_requested = 1;
+ }
+}
+
+static int keyreset_probe(struct platform_device *pdev)
+{
+ int ret = -ENOMEM;
+ struct keycombo_platform_data *pdata_child;
+ struct keyreset_platform_data *pdata = pdev->dev.platform_data;
+ int up_size = 0, down_size = 0, size;
+ int key, *keyp;
+ struct keyreset_state *state;
+
+ if (!pdata)
+ return -EINVAL;
+ state = devm_kzalloc(&pdev->dev, sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ state->pdev_child = platform_device_alloc(KEYCOMBO_NAME,
+ PLATFORM_DEVID_AUTO);
+ if (!state->pdev_child)
+ return -ENOMEM;
+ state->pdev_child->dev.parent = &pdev->dev;
+ INIT_WORK(&state->restart_work, do_restart);
+
+ keyp = pdata->keys_down;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ down_size++;
+ }
+ if (pdata->keys_up) {
+ keyp = pdata->keys_up;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ up_size++;
+ }
+ }
+ size = sizeof(struct keycombo_platform_data)
+ + sizeof(int) * (down_size + 1);
+ pdata_child = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+ if (!pdata_child)
+ goto error;
+ memcpy(pdata_child->keys_down, pdata->keys_down,
+ sizeof(int) * down_size);
+ if (up_size > 0) {
+ pdata_child->keys_up = devm_kzalloc(&pdev->dev, up_size + 1,
+ GFP_KERNEL);
+ if (!pdata_child->keys_up)
+ goto error;
+ memcpy(pdata_child->keys_up, pdata->keys_up,
+ sizeof(int) * up_size);
+ if (!pdata_child->keys_up)
+ goto error;
+ }
+ state->reset_fn = pdata->reset_fn;
+ pdata_child->key_down_fn = do_reset_fn;
+ pdata_child->priv = state;
+ pdata_child->key_down_delay = pdata->key_down_delay;
+ ret = platform_device_add_data(state->pdev_child, pdata_child, size);
+ if (ret)
+ goto error;
+ platform_set_drvdata(pdev, state);
+ return platform_device_add(state->pdev_child);
+error:
+ platform_device_put(state->pdev_child);
+ return ret;
+}
+
+int keyreset_remove(struct platform_device *pdev)
+{
+ struct keyreset_state *state = platform_get_drvdata(pdev);
+ platform_device_put(state->pdev_child);
+ return 0;
+}
+
+
+struct platform_driver keyreset_driver = {
+ .driver.name = KEYRESET_NAME,
+ .probe = keyreset_probe,
+ .remove = keyreset_remove,
+};
+
+static int __init keyreset_init(void)
+{
+ return platform_driver_register(&keyreset_driver);
+}
+
+static void __exit keyreset_exit(void)
+{
+ return platform_driver_unregister(&keyreset_driver);
+}
+
+module_init(keyreset_init);
+module_exit(keyreset_exit);
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 7ffb614..ea1b5e4 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -535,6 +535,11 @@
To compile this driver as a module, choose M here: the
module will be called sgi_btns.
+config INPUT_GPIO
+ tristate "GPIO driver support"
+ help
+ Say Y here if you want to support gpio based keys, wheels etc...
+
config HP_SDC_RTC
tristate "HP SDC Real Time Clock"
depends on (GSC || HP300) && SERIO
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 0b6d025..13bf7db 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -36,6 +36,7 @@
obj-$(CONFIG_INPUT_GPIO_BEEPER) += gpio-beeper.o
obj-$(CONFIG_INPUT_GPIO_TILT_POLLED) += gpio_tilt_polled.o
obj-$(CONFIG_INPUT_GPIO_DECODER) += gpio_decoder.o
+obj-$(CONFIG_INPUT_GPIO) += gpio_event.o gpio_matrix.o gpio_input.o gpio_output.o gpio_axis.o
obj-$(CONFIG_INPUT_HISI_POWERKEY) += hisi_powerkey.o
obj-$(CONFIG_HP_SDC_RTC) += hp_sdc_rtc.o
obj-$(CONFIG_INPUT_IMS_PCU) += ims-pcu.o
diff --git a/drivers/input/misc/gpio_axis.c b/drivers/input/misc/gpio_axis.c
new file mode 100644
index 0000000..0acf4a5
--- /dev/null
+++ b/drivers/input/misc/gpio_axis.c
@@ -0,0 +1,192 @@
+/* drivers/input/misc/gpio_axis.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+struct gpio_axis_state {
+ struct gpio_event_input_devs *input_devs;
+ struct gpio_event_axis_info *info;
+ uint32_t pos;
+};
+
+uint16_t gpio_axis_4bit_gray_map_table[] = {
+ [0x0] = 0x0, [0x1] = 0x1, /* 0000 0001 */
+ [0x3] = 0x2, [0x2] = 0x3, /* 0011 0010 */
+ [0x6] = 0x4, [0x7] = 0x5, /* 0110 0111 */
+ [0x5] = 0x6, [0x4] = 0x7, /* 0101 0100 */
+ [0xc] = 0x8, [0xd] = 0x9, /* 1100 1101 */
+ [0xf] = 0xa, [0xe] = 0xb, /* 1111 1110 */
+ [0xa] = 0xc, [0xb] = 0xd, /* 1010 1011 */
+ [0x9] = 0xe, [0x8] = 0xf, /* 1001 1000 */
+};
+uint16_t gpio_axis_4bit_gray_map(struct gpio_event_axis_info *info, uint16_t in)
+{
+ return gpio_axis_4bit_gray_map_table[in];
+}
+
+uint16_t gpio_axis_5bit_singletrack_map_table[] = {
+ [0x10] = 0x00, [0x14] = 0x01, [0x1c] = 0x02, /* 10000 10100 11100 */
+ [0x1e] = 0x03, [0x1a] = 0x04, [0x18] = 0x05, /* 11110 11010 11000 */
+ [0x08] = 0x06, [0x0a] = 0x07, [0x0e] = 0x08, /* 01000 01010 01110 */
+ [0x0f] = 0x09, [0x0d] = 0x0a, [0x0c] = 0x0b, /* 01111 01101 01100 */
+ [0x04] = 0x0c, [0x05] = 0x0d, [0x07] = 0x0e, /* 00100 00101 00111 */
+ [0x17] = 0x0f, [0x16] = 0x10, [0x06] = 0x11, /* 10111 10110 00110 */
+ [0x02] = 0x12, [0x12] = 0x13, [0x13] = 0x14, /* 00010 10010 10011 */
+ [0x1b] = 0x15, [0x0b] = 0x16, [0x03] = 0x17, /* 11011 01011 00011 */
+ [0x01] = 0x18, [0x09] = 0x19, [0x19] = 0x1a, /* 00001 01001 11001 */
+ [0x1d] = 0x1b, [0x15] = 0x1c, [0x11] = 0x1d, /* 11101 10101 10001 */
+};
+uint16_t gpio_axis_5bit_singletrack_map(
+ struct gpio_event_axis_info *info, uint16_t in)
+{
+ return gpio_axis_5bit_singletrack_map_table[in];
+}
+
+static void gpio_event_update_axis(struct gpio_axis_state *as, int report)
+{
+ struct gpio_event_axis_info *ai = as->info;
+ int i;
+ int change;
+ uint16_t state = 0;
+ uint16_t pos;
+ uint16_t old_pos = as->pos;
+ for (i = ai->count - 1; i >= 0; i--)
+ state = (state << 1) | gpio_get_value(ai->gpio[i]);
+ pos = ai->map(ai, state);
+ if (ai->flags & GPIOEAF_PRINT_RAW)
+ pr_info("axis %d-%d raw %x, pos %d -> %d\n",
+ ai->type, ai->code, state, old_pos, pos);
+ if (report && pos != old_pos) {
+ if (ai->type == EV_REL) {
+ change = (ai->decoded_size + pos - old_pos) %
+ ai->decoded_size;
+ if (change > ai->decoded_size / 2)
+ change -= ai->decoded_size;
+ if (change == ai->decoded_size / 2) {
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d unknown direction, "
+ "pos %d -> %d\n", ai->type,
+ ai->code, old_pos, pos);
+ change = 0; /* no closest direction */
+ }
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d change %d\n",
+ ai->type, ai->code, change);
+ input_report_rel(as->input_devs->dev[ai->dev],
+ ai->code, change);
+ } else {
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d now %d\n",
+ ai->type, ai->code, pos);
+ input_event(as->input_devs->dev[ai->dev],
+ ai->type, ai->code, pos);
+ }
+ input_sync(as->input_devs->dev[ai->dev]);
+ }
+ as->pos = pos;
+}
+
+static irqreturn_t gpio_axis_irq_handler(int irq, void *dev_id)
+{
+ struct gpio_axis_state *as = dev_id;
+ gpio_event_update_axis(as, 1);
+ return IRQ_HANDLED;
+}
+
+int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int ret;
+ int i;
+ int irq;
+ struct gpio_event_axis_info *ai;
+ struct gpio_axis_state *as;
+
+ ai = container_of(info, struct gpio_event_axis_info, info);
+ if (func == GPIO_EVENT_FUNC_SUSPEND) {
+ for (i = 0; i < ai->count; i++)
+ disable_irq(gpio_to_irq(ai->gpio[i]));
+ return 0;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME) {
+ for (i = 0; i < ai->count; i++)
+ enable_irq(gpio_to_irq(ai->gpio[i]));
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ *data = as = kmalloc(sizeof(*as), GFP_KERNEL);
+ if (as == NULL) {
+ ret = -ENOMEM;
+ goto err_alloc_axis_state_failed;
+ }
+ as->input_devs = input_devs;
+ as->info = ai;
+ if (ai->dev >= input_devs->count) {
+ pr_err("gpio_event_axis: bad device index %d >= %d "
+ "for %d:%d\n", ai->dev, input_devs->count,
+ ai->type, ai->code);
+ ret = -EINVAL;
+ goto err_bad_device_index;
+ }
+
+ input_set_capability(input_devs->dev[ai->dev],
+ ai->type, ai->code);
+ if (ai->type == EV_ABS) {
+ input_set_abs_params(input_devs->dev[ai->dev], ai->code,
+ 0, ai->decoded_size - 1, 0, 0);
+ }
+ for (i = 0; i < ai->count; i++) {
+ ret = gpio_request(ai->gpio[i], "gpio_event_axis");
+ if (ret < 0)
+ goto err_request_gpio_failed;
+ ret = gpio_direction_input(ai->gpio[i]);
+ if (ret < 0)
+ goto err_gpio_direction_input_failed;
+ ret = irq = gpio_to_irq(ai->gpio[i]);
+ if (ret < 0)
+ goto err_get_irq_num_failed;
+ ret = request_irq(irq, gpio_axis_irq_handler,
+ IRQF_TRIGGER_RISING |
+ IRQF_TRIGGER_FALLING,
+ "gpio_event_axis", as);
+ if (ret < 0)
+ goto err_request_irq_failed;
+ }
+ gpio_event_update_axis(as, 0);
+ return 0;
+ }
+
+ ret = 0;
+ as = *data;
+ for (i = ai->count - 1; i >= 0; i--) {
+ free_irq(gpio_to_irq(ai->gpio[i]), as);
+err_request_irq_failed:
+err_get_irq_num_failed:
+err_gpio_direction_input_failed:
+ gpio_free(ai->gpio[i]);
+err_request_gpio_failed:
+ ;
+ }
+err_bad_device_index:
+ kfree(as);
+ *data = NULL;
+err_alloc_axis_state_failed:
+ return ret;
+}
diff --git a/drivers/input/misc/gpio_event.c b/drivers/input/misc/gpio_event.c
new file mode 100644
index 0000000..90f07eb
--- /dev/null
+++ b/drivers/input/misc/gpio_event.c
@@ -0,0 +1,228 @@
+/* drivers/input/misc/gpio_event.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+struct gpio_event {
+ struct gpio_event_input_devs *input_devs;
+ const struct gpio_event_platform_data *info;
+ void *state[0];
+};
+
+static int gpio_input_event(
+ struct input_dev *dev, unsigned int type, unsigned int code, int value)
+{
+ int i;
+ int devnr;
+ int ret = 0;
+ int tmp_ret;
+ struct gpio_event_info **ii;
+ struct gpio_event *ip = input_get_drvdata(dev);
+
+ for (devnr = 0; devnr < ip->input_devs->count; devnr++)
+ if (ip->input_devs->dev[devnr] == dev)
+ break;
+ if (devnr == ip->input_devs->count) {
+ pr_err("gpio_input_event: unknown device %p\n", dev);
+ return -EIO;
+ }
+
+ for (i = 0, ii = ip->info->info; i < ip->info->info_count; i++, ii++) {
+ if ((*ii)->event) {
+ tmp_ret = (*ii)->event(ip->input_devs, *ii,
+ &ip->state[i],
+ devnr, type, code, value);
+ if (tmp_ret)
+ ret = tmp_ret;
+ }
+ }
+ return ret;
+}
+
+static int gpio_event_call_all_func(struct gpio_event *ip, int func)
+{
+ int i;
+ int ret;
+ struct gpio_event_info **ii;
+
+ if (func == GPIO_EVENT_FUNC_INIT || func == GPIO_EVENT_FUNC_RESUME) {
+ ii = ip->info->info;
+ for (i = 0; i < ip->info->info_count; i++, ii++) {
+ if ((*ii)->func == NULL) {
+ ret = -ENODEV;
+ pr_err("gpio_event_probe: Incomplete pdata, "
+ "no function\n");
+ goto err_no_func;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME && (*ii)->no_suspend)
+ continue;
+ ret = (*ii)->func(ip->input_devs, *ii, &ip->state[i],
+ func);
+ if (ret) {
+ pr_err("gpio_event_probe: function failed\n");
+ goto err_func_failed;
+ }
+ }
+ return 0;
+ }
+
+ ret = 0;
+ i = ip->info->info_count;
+ ii = ip->info->info + i;
+ while (i > 0) {
+ i--;
+ ii--;
+ if ((func & ~1) == GPIO_EVENT_FUNC_SUSPEND && (*ii)->no_suspend)
+ continue;
+ (*ii)->func(ip->input_devs, *ii, &ip->state[i], func & ~1);
+err_func_failed:
+err_no_func:
+ ;
+ }
+ return ret;
+}
+
+static void __maybe_unused gpio_event_suspend(struct gpio_event *ip)
+{
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_SUSPEND);
+ if (ip->info->power)
+ ip->info->power(ip->info, 0);
+}
+
+static void __maybe_unused gpio_event_resume(struct gpio_event *ip)
+{
+ if (ip->info->power)
+ ip->info->power(ip->info, 1);
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_RESUME);
+}
+
+static int gpio_event_probe(struct platform_device *pdev)
+{
+ int err;
+ struct gpio_event *ip;
+ struct gpio_event_platform_data *event_info;
+ int dev_count = 1;
+ int i;
+ int registered = 0;
+
+ event_info = pdev->dev.platform_data;
+ if (event_info == NULL) {
+ pr_err("gpio_event_probe: No pdata\n");
+ return -ENODEV;
+ }
+ if ((!event_info->name && !event_info->names[0]) ||
+ !event_info->info || !event_info->info_count) {
+ pr_err("gpio_event_probe: Incomplete pdata\n");
+ return -ENODEV;
+ }
+ if (!event_info->name)
+ while (event_info->names[dev_count])
+ dev_count++;
+ ip = kzalloc(sizeof(*ip) +
+ sizeof(ip->state[0]) * event_info->info_count +
+ sizeof(*ip->input_devs) +
+ sizeof(ip->input_devs->dev[0]) * dev_count, GFP_KERNEL);
+ if (ip == NULL) {
+ err = -ENOMEM;
+ pr_err("gpio_event_probe: Failed to allocate private data\n");
+ goto err_kp_alloc_failed;
+ }
+ ip->input_devs = (void*)&ip->state[event_info->info_count];
+ platform_set_drvdata(pdev, ip);
+
+ for (i = 0; i < dev_count; i++) {
+ struct input_dev *input_dev = input_allocate_device();
+ if (input_dev == NULL) {
+ err = -ENOMEM;
+ pr_err("gpio_event_probe: "
+ "Failed to allocate input device\n");
+ goto err_input_dev_alloc_failed;
+ }
+ input_set_drvdata(input_dev, ip);
+ input_dev->name = event_info->name ?
+ event_info->name : event_info->names[i];
+ input_dev->event = gpio_input_event;
+ ip->input_devs->dev[i] = input_dev;
+ }
+ ip->input_devs->count = dev_count;
+ ip->info = event_info;
+ if (event_info->power)
+ ip->info->power(ip->info, 1);
+
+ err = gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_INIT);
+ if (err)
+ goto err_call_all_func_failed;
+
+ for (i = 0; i < dev_count; i++) {
+ err = input_register_device(ip->input_devs->dev[i]);
+ if (err) {
+ pr_err("gpio_event_probe: Unable to register %s "
+ "input device\n", ip->input_devs->dev[i]->name);
+ goto err_input_register_device_failed;
+ }
+ registered++;
+ }
+
+ return 0;
+
+err_input_register_device_failed:
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+err_call_all_func_failed:
+ if (event_info->power)
+ ip->info->power(ip->info, 0);
+ for (i = 0; i < registered; i++)
+ input_unregister_device(ip->input_devs->dev[i]);
+ for (i = dev_count - 1; i >= registered; i--) {
+ input_free_device(ip->input_devs->dev[i]);
+err_input_dev_alloc_failed:
+ ;
+ }
+ kfree(ip);
+err_kp_alloc_failed:
+ return err;
+}
+
+static int gpio_event_remove(struct platform_device *pdev)
+{
+ struct gpio_event *ip = platform_get_drvdata(pdev);
+ int i;
+
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+ if (ip->info->power)
+ ip->info->power(ip->info, 0);
+ for (i = 0; i < ip->input_devs->count; i++)
+ input_unregister_device(ip->input_devs->dev[i]);
+ kfree(ip);
+ return 0;
+}
+
+static struct platform_driver gpio_event_driver = {
+ .probe = gpio_event_probe,
+ .remove = gpio_event_remove,
+ .driver = {
+ .name = GPIO_EVENT_DEV_NAME,
+ },
+};
+
+module_platform_driver(gpio_event_driver);
+
+MODULE_DESCRIPTION("GPIO Event Driver");
+MODULE_LICENSE("GPL");
+
diff --git a/drivers/input/misc/gpio_input.c b/drivers/input/misc/gpio_input.c
new file mode 100644
index 0000000..eefd027
--- /dev/null
+++ b/drivers/input/misc/gpio_input.c
@@ -0,0 +1,390 @@
+/* drivers/input/misc/gpio_input.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/pm_wakeup.h>
+
+enum {
+ DEBOUNCE_UNSTABLE = BIT(0), /* Got irq, while debouncing */
+ DEBOUNCE_PRESSED = BIT(1),
+ DEBOUNCE_NOTPRESSED = BIT(2),
+ DEBOUNCE_WAIT_IRQ = BIT(3), /* Stable irq state */
+ DEBOUNCE_POLL = BIT(4), /* Stable polling state */
+
+ DEBOUNCE_UNKNOWN =
+ DEBOUNCE_PRESSED | DEBOUNCE_NOTPRESSED,
+};
+
+struct gpio_key_state {
+ struct gpio_input_state *ds;
+ uint8_t debounce;
+};
+
+struct gpio_input_state {
+ struct gpio_event_input_devs *input_devs;
+ const struct gpio_event_input_info *info;
+ struct hrtimer timer;
+ int use_irq;
+ int debounce_count;
+ spinlock_t irq_lock;
+ struct wakeup_source *ws;
+ struct gpio_key_state key_state[0];
+};
+
+static enum hrtimer_restart gpio_event_input_timer_func(struct hrtimer *timer)
+{
+ int i;
+ int pressed;
+ struct gpio_input_state *ds =
+ container_of(timer, struct gpio_input_state, timer);
+ unsigned gpio_flags = ds->info->flags;
+ unsigned npolarity;
+ int nkeys = ds->info->keymap_size;
+ const struct gpio_event_direct_entry *key_entry;
+ struct gpio_key_state *key_state;
+ unsigned long irqflags;
+ uint8_t debounce;
+ bool sync_needed;
+
+#if 0
+ key_entry = kp->keys_info->keymap;
+ key_state = kp->key_state;
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++)
+ pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+ gpio_read_detect_status(key_entry->gpio));
+#endif
+ key_entry = ds->info->keymap;
+ key_state = ds->key_state;
+ sync_needed = false;
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+ debounce = key_state->debounce;
+ if (debounce & DEBOUNCE_WAIT_IRQ)
+ continue;
+ if (key_state->debounce & DEBOUNCE_UNSTABLE) {
+ debounce = key_state->debounce = DEBOUNCE_UNKNOWN;
+ enable_irq(gpio_to_irq(key_entry->gpio));
+ if (gpio_flags & GPIOEDF_PRINT_KEY_UNSTABLE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) continue debounce\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ }
+ npolarity = !(gpio_flags & GPIOEDF_ACTIVE_HIGH);
+ pressed = gpio_get_value(key_entry->gpio) ^ npolarity;
+ if (debounce & DEBOUNCE_POLL) {
+ if (pressed == !(debounce & DEBOUNCE_PRESSED)) {
+ ds->debounce_count++;
+ key_state->debounce = DEBOUNCE_UNKNOWN;
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-"
+ "%x, %d (%d) start debounce\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ }
+ continue;
+ }
+ if (pressed && (debounce & DEBOUNCE_NOTPRESSED)) {
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) debounce pressed 1\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ key_state->debounce = DEBOUNCE_PRESSED;
+ continue;
+ }
+ if (!pressed && (debounce & DEBOUNCE_PRESSED)) {
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) debounce pressed 0\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ key_state->debounce = DEBOUNCE_NOTPRESSED;
+ continue;
+ }
+ /* key is stable */
+ ds->debounce_count--;
+ if (ds->use_irq)
+ key_state->debounce |= DEBOUNCE_WAIT_IRQ;
+ else
+ key_state->debounce |= DEBOUNCE_POLL;
+ if (gpio_flags & GPIOEDF_PRINT_KEYS)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d (%d) "
+ "changed to %d\n", ds->info->type,
+ key_entry->code, i, key_entry->gpio, pressed);
+ input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+ key_entry->code, pressed);
+ sync_needed = true;
+ }
+ if (sync_needed) {
+ for (i = 0; i < ds->input_devs->count; i++)
+ input_sync(ds->input_devs->dev[i]);
+ }
+
+#if 0
+ key_entry = kp->keys_info->keymap;
+ key_state = kp->key_state;
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+ pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+ gpio_read_detect_status(key_entry->gpio));
+ }
+#endif
+
+ if (ds->debounce_count)
+ hrtimer_start(timer, ds->info->debounce_time, HRTIMER_MODE_REL);
+ else if (!ds->use_irq)
+ hrtimer_start(timer, ds->info->poll_time, HRTIMER_MODE_REL);
+ else
+ __pm_relax(ds->ws);
+
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+ return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_event_input_irq_handler(int irq, void *dev_id)
+{
+ struct gpio_key_state *ks = dev_id;
+ struct gpio_input_state *ds = ks->ds;
+ int keymap_index = ks - ds->key_state;
+ const struct gpio_event_direct_entry *key_entry;
+ unsigned long irqflags;
+ int pressed;
+
+ if (!ds->use_irq)
+ return IRQ_HANDLED;
+
+ key_entry = &ds->info->keymap[keymap_index];
+
+ if (ds->info->debounce_time.tv64) {
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ if (ks->debounce & DEBOUNCE_WAIT_IRQ) {
+ ks->debounce = DEBOUNCE_UNKNOWN;
+ if (ds->debounce_count++ == 0) {
+ __pm_stay_awake(ds->ws);
+ hrtimer_start(
+ &ds->timer, ds->info->debounce_time,
+ HRTIMER_MODE_REL);
+ }
+ if (ds->info->flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_event_input_irq_handler: "
+ "key %x-%x, %d (%d) start debounce\n",
+ ds->info->type, key_entry->code,
+ keymap_index, key_entry->gpio);
+ } else {
+ disable_irq_nosync(irq);
+ ks->debounce = DEBOUNCE_UNSTABLE;
+ }
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ } else {
+ pressed = gpio_get_value(key_entry->gpio) ^
+ !(ds->info->flags & GPIOEDF_ACTIVE_HIGH);
+ if (ds->info->flags & GPIOEDF_PRINT_KEYS)
+ pr_info("gpio_event_input_irq_handler: key %x-%x, %d "
+ "(%d) changed to %d\n",
+ ds->info->type, key_entry->code, keymap_index,
+ key_entry->gpio, pressed);
+ input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+ key_entry->code, pressed);
+ input_sync(ds->input_devs->dev[key_entry->dev]);
+ }
+ return IRQ_HANDLED;
+}
+
+static int gpio_event_input_request_irqs(struct gpio_input_state *ds)
+{
+ int i;
+ int err;
+ unsigned int irq;
+ unsigned long req_flags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+
+ for (i = 0; i < ds->info->keymap_size; i++) {
+ err = irq = gpio_to_irq(ds->info->keymap[i].gpio);
+ if (err < 0)
+ goto err_gpio_get_irq_num_failed;
+ err = request_irq(irq, gpio_event_input_irq_handler,
+ req_flags, "gpio_keys", &ds->key_state[i]);
+ if (err) {
+ pr_err("gpio_event_input_request_irqs: request_irq "
+ "failed for input %d, irq %d\n",
+ ds->info->keymap[i].gpio, irq);
+ goto err_request_irq_failed;
+ }
+ if (ds->info->info.no_suspend) {
+ err = enable_irq_wake(irq);
+ if (err) {
+ pr_err("gpio_event_input_request_irqs: "
+ "enable_irq_wake failed for input %d, "
+ "irq %d\n",
+ ds->info->keymap[i].gpio, irq);
+ goto err_enable_irq_wake_failed;
+ }
+ }
+ }
+ return 0;
+
+ for (i = ds->info->keymap_size - 1; i >= 0; i--) {
+ irq = gpio_to_irq(ds->info->keymap[i].gpio);
+ if (ds->info->info.no_suspend)
+ disable_irq_wake(irq);
+err_enable_irq_wake_failed:
+ free_irq(irq, &ds->key_state[i]);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+ ;
+ }
+ return err;
+}
+
+int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int ret;
+ int i;
+ unsigned long irqflags;
+ struct gpio_event_input_info *di;
+ struct gpio_input_state *ds = *data;
+ char *wlname;
+
+ di = container_of(info, struct gpio_event_input_info, info);
+
+ if (func == GPIO_EVENT_FUNC_SUSPEND) {
+ if (ds->use_irq)
+ for (i = 0; i < di->keymap_size; i++)
+ disable_irq(gpio_to_irq(di->keymap[i].gpio));
+ hrtimer_cancel(&ds->timer);
+ return 0;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME) {
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ if (ds->use_irq)
+ for (i = 0; i < di->keymap_size; i++)
+ enable_irq(gpio_to_irq(di->keymap[i].gpio));
+ hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ if (ktime_to_ns(di->poll_time) <= 0)
+ di->poll_time = ktime_set(0, 20 * NSEC_PER_MSEC);
+
+ *data = ds = kzalloc(sizeof(*ds) + sizeof(ds->key_state[0]) *
+ di->keymap_size, GFP_KERNEL);
+ if (ds == NULL) {
+ ret = -ENOMEM;
+ pr_err("gpio_event_input_func: "
+ "Failed to allocate private data\n");
+ goto err_ds_alloc_failed;
+ }
+ ds->debounce_count = di->keymap_size;
+ ds->input_devs = input_devs;
+ ds->info = di;
+ wlname = kasprintf(GFP_KERNEL, "gpio_input:%s%s",
+ input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "");
+
+ ds->ws = wakeup_source_register(wlname);
+ kfree(wlname);
+ if (!ds->ws) {
+ ret = -ENOMEM;
+ pr_err("gpio_event_input_func: "
+ "Failed to allocate wakeup source\n");
+ goto err_ws_failed;
+ }
+
+ spin_lock_init(&ds->irq_lock);
+
+ for (i = 0; i < di->keymap_size; i++) {
+ int dev = di->keymap[i].dev;
+ if (dev >= input_devs->count) {
+ pr_err("gpio_event_input_func: bad device "
+ "index %d >= %d for key code %d\n",
+ dev, input_devs->count,
+ di->keymap[i].code);
+ ret = -EINVAL;
+ goto err_bad_keymap;
+ }
+ input_set_capability(input_devs->dev[dev], di->type,
+ di->keymap[i].code);
+ ds->key_state[i].ds = ds;
+ ds->key_state[i].debounce = DEBOUNCE_UNKNOWN;
+ }
+
+ for (i = 0; i < di->keymap_size; i++) {
+ ret = gpio_request(di->keymap[i].gpio, "gpio_kp_in");
+ if (ret) {
+ pr_err("gpio_event_input_func: gpio_request "
+ "failed for %d\n", di->keymap[i].gpio);
+ goto err_gpio_request_failed;
+ }
+ ret = gpio_direction_input(di->keymap[i].gpio);
+ if (ret) {
+ pr_err("gpio_event_input_func: "
+ "gpio_direction_input failed for %d\n",
+ di->keymap[i].gpio);
+ goto err_gpio_configure_failed;
+ }
+ }
+
+ ret = gpio_event_input_request_irqs(ds);
+
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ ds->use_irq = ret == 0;
+
+ pr_info("GPIO Input Driver: Start gpio inputs for %s%s in %s "
+ "mode\n", input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "",
+ ret == 0 ? "interrupt" : "polling");
+
+ hrtimer_init(&ds->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ ds->timer.function = gpio_event_input_timer_func;
+ hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ return 0;
+ }
+
+ ret = 0;
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ hrtimer_cancel(&ds->timer);
+ if (ds->use_irq) {
+ for (i = di->keymap_size - 1; i >= 0; i--) {
+ int irq = gpio_to_irq(di->keymap[i].gpio);
+ if (ds->info->info.no_suspend)
+ disable_irq_wake(irq);
+ free_irq(irq, &ds->key_state[i]);
+ }
+ }
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+ for (i = di->keymap_size - 1; i >= 0; i--) {
+err_gpio_configure_failed:
+ gpio_free(di->keymap[i].gpio);
+err_gpio_request_failed:
+ ;
+ }
+err_bad_keymap:
+ wakeup_source_unregister(ds->ws);
+err_ws_failed:
+ kfree(ds);
+err_ds_alloc_failed:
+ return ret;
+}
diff --git a/drivers/input/misc/gpio_matrix.c b/drivers/input/misc/gpio_matrix.c
new file mode 100644
index 0000000..08769dd
--- /dev/null
+++ b/drivers/input/misc/gpio_matrix.c
@@ -0,0 +1,440 @@
+/* drivers/input/misc/gpio_matrix.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+struct gpio_kp {
+ struct gpio_event_input_devs *input_devs;
+ struct gpio_event_matrix_info *keypad_info;
+ struct hrtimer timer;
+ struct wakeup_source wake_src;
+ int current_output;
+ unsigned int use_irq:1;
+ unsigned int key_state_changed:1;
+ unsigned int last_key_state_changed:1;
+ unsigned int some_keys_pressed:2;
+ unsigned int disabled_irq:1;
+ unsigned long keys_pressed[0];
+};
+
+static void clear_phantom_key(struct gpio_kp *kp, int out, int in)
+{
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ int key_index = out * mi->ninputs + in;
+ unsigned short keyentry = mi->keymap[key_index];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+ if (!test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+ if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+ pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+ "cleared\n", keycode, out, in,
+ mi->output_gpios[out], mi->input_gpios[in]);
+ __clear_bit(key_index, kp->keys_pressed);
+ } else {
+ if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+ pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+ "not cleared\n", keycode, out, in,
+ mi->output_gpios[out], mi->input_gpios[in]);
+ }
+}
+
+static int restore_keys_for_input(struct gpio_kp *kp, int out, int in)
+{
+ int rv = 0;
+ int key_index;
+
+ key_index = out * kp->keypad_info->ninputs + in;
+ while (out < kp->keypad_info->noutputs) {
+ if (test_bit(key_index, kp->keys_pressed)) {
+ rv = 1;
+ clear_phantom_key(kp, out, in);
+ }
+ key_index += kp->keypad_info->ninputs;
+ out++;
+ }
+ return rv;
+}
+
+static void remove_phantom_keys(struct gpio_kp *kp)
+{
+ int out, in, inp;
+ int key_index;
+
+ if (kp->some_keys_pressed < 3)
+ return;
+
+ for (out = 0; out < kp->keypad_info->noutputs; out++) {
+ inp = -1;
+ key_index = out * kp->keypad_info->ninputs;
+ for (in = 0; in < kp->keypad_info->ninputs; in++, key_index++) {
+ if (test_bit(key_index, kp->keys_pressed)) {
+ if (inp == -1) {
+ inp = in;
+ continue;
+ }
+ if (inp >= 0) {
+ if (!restore_keys_for_input(kp, out + 1,
+ inp))
+ break;
+ clear_phantom_key(kp, out, inp);
+ inp = -2;
+ }
+ restore_keys_for_input(kp, out, in);
+ }
+ }
+ }
+}
+
+static void report_key(struct gpio_kp *kp, int key_index, int out, int in)
+{
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ int pressed = test_bit(key_index, kp->keys_pressed);
+ unsigned short keyentry = mi->keymap[key_index];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+ if (pressed != test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+ if (keycode == KEY_RESERVED) {
+ if (mi->flags & GPIOKPF_PRINT_UNMAPPED_KEYS)
+ pr_info("gpiomatrix: unmapped key, %d-%d "
+ "(%d-%d) changed to %d\n",
+ out, in, mi->output_gpios[out],
+ mi->input_gpios[in], pressed);
+ } else {
+ if (mi->flags & GPIOKPF_PRINT_MAPPED_KEYS)
+ pr_info("gpiomatrix: key %x, %d-%d (%d-%d) "
+ "changed to %d\n", keycode,
+ out, in, mi->output_gpios[out],
+ mi->input_gpios[in], pressed);
+ input_report_key(kp->input_devs->dev[dev], keycode, pressed);
+ }
+ }
+}
+
+static void report_sync(struct gpio_kp *kp)
+{
+ int i;
+
+ for (i = 0; i < kp->input_devs->count; i++)
+ input_sync(kp->input_devs->dev[i]);
+}
+
+static enum hrtimer_restart gpio_keypad_timer_func(struct hrtimer *timer)
+{
+ int out, in;
+ int key_index;
+ int gpio;
+ struct gpio_kp *kp = container_of(timer, struct gpio_kp, timer);
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ unsigned gpio_keypad_flags = mi->flags;
+ unsigned polarity = !!(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH);
+
+ out = kp->current_output;
+ if (out == mi->noutputs) {
+ out = 0;
+ kp->last_key_state_changed = kp->key_state_changed;
+ kp->key_state_changed = 0;
+ kp->some_keys_pressed = 0;
+ } else {
+ key_index = out * mi->ninputs;
+ for (in = 0; in < mi->ninputs; in++, key_index++) {
+ gpio = mi->input_gpios[in];
+ if (gpio_get_value(gpio) ^ !polarity) {
+ if (kp->some_keys_pressed < 3)
+ kp->some_keys_pressed++;
+ kp->key_state_changed |= !__test_and_set_bit(
+ key_index, kp->keys_pressed);
+ } else
+ kp->key_state_changed |= __test_and_clear_bit(
+ key_index, kp->keys_pressed);
+ }
+ gpio = mi->output_gpios[out];
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(gpio, !polarity);
+ else
+ gpio_direction_input(gpio);
+ out++;
+ }
+ kp->current_output = out;
+ if (out < mi->noutputs) {
+ gpio = mi->output_gpios[out];
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(gpio, polarity);
+ else
+ gpio_direction_output(gpio, polarity);
+ hrtimer_start(timer, mi->settle_time, HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+ if (gpio_keypad_flags & GPIOKPF_DEBOUNCE) {
+ if (kp->key_state_changed) {
+ hrtimer_start(&kp->timer, mi->debounce_delay,
+ HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+ kp->key_state_changed = kp->last_key_state_changed;
+ }
+ if (kp->key_state_changed) {
+ if (gpio_keypad_flags & GPIOKPF_REMOVE_SOME_PHANTOM_KEYS)
+ remove_phantom_keys(kp);
+ key_index = 0;
+ for (out = 0; out < mi->noutputs; out++)
+ for (in = 0; in < mi->ninputs; in++, key_index++)
+ report_key(kp, key_index, out, in);
+ report_sync(kp);
+ }
+ if (!kp->use_irq || kp->some_keys_pressed) {
+ hrtimer_start(timer, mi->poll_time, HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+
+ /* No keys are pressed, reenable interrupt */
+ for (out = 0; out < mi->noutputs; out++) {
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(mi->output_gpios[out], polarity);
+ else
+ gpio_direction_output(mi->output_gpios[out], polarity);
+ }
+ for (in = 0; in < mi->ninputs; in++)
+ enable_irq(gpio_to_irq(mi->input_gpios[in]));
+ __pm_relax(&kp->wake_src);
+ return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_keypad_irq_handler(int irq_in, void *dev_id)
+{
+ int i;
+ struct gpio_kp *kp = dev_id;
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ unsigned gpio_keypad_flags = mi->flags;
+
+ if (!kp->use_irq) {
+ /* ignore interrupt while registering the handler */
+ kp->disabled_irq = 1;
+ disable_irq_nosync(irq_in);
+ return IRQ_HANDLED;
+ }
+
+ for (i = 0; i < mi->ninputs; i++)
+ disable_irq_nosync(gpio_to_irq(mi->input_gpios[i]));
+ for (i = 0; i < mi->noutputs; i++) {
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(mi->output_gpios[i],
+ !(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH));
+ else
+ gpio_direction_input(mi->output_gpios[i]);
+ }
+ __pm_stay_awake(&kp->wake_src);
+ hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ return IRQ_HANDLED;
+}
+
+static int gpio_keypad_request_irqs(struct gpio_kp *kp)
+{
+ int i;
+ int err;
+ unsigned int irq;
+ unsigned long request_flags;
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+
+ switch (mi->flags & (GPIOKPF_ACTIVE_HIGH|GPIOKPF_LEVEL_TRIGGERED_IRQ)) {
+ default:
+ request_flags = IRQF_TRIGGER_FALLING;
+ break;
+ case GPIOKPF_ACTIVE_HIGH:
+ request_flags = IRQF_TRIGGER_RISING;
+ break;
+ case GPIOKPF_LEVEL_TRIGGERED_IRQ:
+ request_flags = IRQF_TRIGGER_LOW;
+ break;
+ case GPIOKPF_LEVEL_TRIGGERED_IRQ | GPIOKPF_ACTIVE_HIGH:
+ request_flags = IRQF_TRIGGER_HIGH;
+ break;
+ }
+
+ for (i = 0; i < mi->ninputs; i++) {
+ err = irq = gpio_to_irq(mi->input_gpios[i]);
+ if (err < 0)
+ goto err_gpio_get_irq_num_failed;
+ err = request_irq(irq, gpio_keypad_irq_handler, request_flags,
+ "gpio_kp", kp);
+ if (err) {
+ pr_err("gpiomatrix: request_irq failed for input %d, "
+ "irq %d\n", mi->input_gpios[i], irq);
+ goto err_request_irq_failed;
+ }
+ err = enable_irq_wake(irq);
+ if (err) {
+ pr_err("gpiomatrix: set_irq_wake failed for input %d, "
+ "irq %d\n", mi->input_gpios[i], irq);
+ }
+ disable_irq(irq);
+ if (kp->disabled_irq) {
+ kp->disabled_irq = 0;
+ enable_irq(irq);
+ }
+ }
+ return 0;
+
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+ free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+ ;
+ }
+ return err;
+}
+
+int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int i;
+ int err;
+ int key_count;
+ struct gpio_kp *kp;
+ struct gpio_event_matrix_info *mi;
+
+ mi = container_of(info, struct gpio_event_matrix_info, info);
+ if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME) {
+ /* TODO: disable scanning */
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ if (mi->keymap == NULL ||
+ mi->input_gpios == NULL ||
+ mi->output_gpios == NULL) {
+ err = -ENODEV;
+ pr_err("gpiomatrix: Incomplete pdata\n");
+ goto err_invalid_platform_data;
+ }
+ key_count = mi->ninputs * mi->noutputs;
+
+ *data = kp = kzalloc(sizeof(*kp) + sizeof(kp->keys_pressed[0]) *
+ BITS_TO_LONGS(key_count), GFP_KERNEL);
+ if (kp == NULL) {
+ err = -ENOMEM;
+ pr_err("gpiomatrix: Failed to allocate private data\n");
+ goto err_kp_alloc_failed;
+ }
+ kp->input_devs = input_devs;
+ kp->keypad_info = mi;
+ for (i = 0; i < key_count; i++) {
+ unsigned short keyentry = mi->keymap[i];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+ if (dev >= input_devs->count) {
+ pr_err("gpiomatrix: bad device index %d >= "
+ "%d for key code %d\n",
+ dev, input_devs->count, keycode);
+ err = -EINVAL;
+ goto err_bad_keymap;
+ }
+ if (keycode && keycode <= KEY_MAX)
+ input_set_capability(input_devs->dev[dev],
+ EV_KEY, keycode);
+ }
+
+ for (i = 0; i < mi->noutputs; i++) {
+ err = gpio_request(mi->output_gpios[i], "gpio_kp_out");
+ if (err) {
+ pr_err("gpiomatrix: gpio_request failed for "
+ "output %d\n", mi->output_gpios[i]);
+ goto err_request_output_gpio_failed;
+ }
+ if (gpio_cansleep(mi->output_gpios[i])) {
+ pr_err("gpiomatrix: unsupported output gpio %d,"
+ " can sleep\n", mi->output_gpios[i]);
+ err = -EINVAL;
+ goto err_output_gpio_configure_failed;
+ }
+ if (mi->flags & GPIOKPF_DRIVE_INACTIVE)
+ err = gpio_direction_output(mi->output_gpios[i],
+ !(mi->flags & GPIOKPF_ACTIVE_HIGH));
+ else
+ err = gpio_direction_input(mi->output_gpios[i]);
+ if (err) {
+ pr_err("gpiomatrix: gpio_configure failed for "
+ "output %d\n", mi->output_gpios[i]);
+ goto err_output_gpio_configure_failed;
+ }
+ }
+ for (i = 0; i < mi->ninputs; i++) {
+ err = gpio_request(mi->input_gpios[i], "gpio_kp_in");
+ if (err) {
+ pr_err("gpiomatrix: gpio_request failed for "
+ "input %d\n", mi->input_gpios[i]);
+ goto err_request_input_gpio_failed;
+ }
+ err = gpio_direction_input(mi->input_gpios[i]);
+ if (err) {
+ pr_err("gpiomatrix: gpio_direction_input failed"
+ " for input %d\n", mi->input_gpios[i]);
+ goto err_gpio_direction_input_failed;
+ }
+ }
+ kp->current_output = mi->noutputs;
+ kp->key_state_changed = 1;
+
+ hrtimer_init(&kp->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ kp->timer.function = gpio_keypad_timer_func;
+ wakeup_source_init(&kp->wake_src, "gpio_kp");
+ err = gpio_keypad_request_irqs(kp);
+ kp->use_irq = err == 0;
+
+ pr_info("GPIO Matrix Keypad Driver: Start keypad matrix for "
+ "%s%s in %s mode\n", input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "",
+ kp->use_irq ? "interrupt" : "polling");
+
+ if (kp->use_irq)
+ __pm_stay_awake(&kp->wake_src);
+ hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+
+ return 0;
+ }
+
+ err = 0;
+ kp = *data;
+
+ if (kp->use_irq)
+ for (i = mi->noutputs - 1; i >= 0; i--)
+ free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+
+ hrtimer_cancel(&kp->timer);
+ wakeup_source_trash(&kp->wake_src);
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+err_gpio_direction_input_failed:
+ gpio_free(mi->input_gpios[i]);
+err_request_input_gpio_failed:
+ ;
+ }
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+err_output_gpio_configure_failed:
+ gpio_free(mi->output_gpios[i]);
+err_request_output_gpio_failed:
+ ;
+ }
+err_bad_keymap:
+ kfree(kp);
+err_kp_alloc_failed:
+err_invalid_platform_data:
+ return err;
+}
diff --git a/drivers/input/misc/gpio_output.c b/drivers/input/misc/gpio_output.c
new file mode 100644
index 0000000..2aac2fa
--- /dev/null
+++ b/drivers/input/misc/gpio_output.c
@@ -0,0 +1,97 @@
+/* drivers/input/misc/gpio_output.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+
+int gpio_event_output_event(
+ struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+ void **data, unsigned int dev, unsigned int type,
+ unsigned int code, int value)
+{
+ int i;
+ struct gpio_event_output_info *oi;
+ oi = container_of(info, struct gpio_event_output_info, info);
+ if (type != oi->type)
+ return 0;
+ if (!(oi->flags & GPIOEDF_ACTIVE_HIGH))
+ value = !value;
+ for (i = 0; i < oi->keymap_size; i++)
+ if (dev == oi->keymap[i].dev && code == oi->keymap[i].code)
+ gpio_set_value(oi->keymap[i].gpio, value);
+ return 0;
+}
+
+int gpio_event_output_func(
+ struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+ void **data, int func)
+{
+ int ret;
+ int i;
+ struct gpio_event_output_info *oi;
+ oi = container_of(info, struct gpio_event_output_info, info);
+
+ if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME)
+ return 0;
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ int output_level = !(oi->flags & GPIOEDF_ACTIVE_HIGH);
+
+ for (i = 0; i < oi->keymap_size; i++) {
+ int dev = oi->keymap[i].dev;
+ if (dev >= input_devs->count) {
+ pr_err("gpio_event_output_func: bad device "
+ "index %d >= %d for key code %d\n",
+ dev, input_devs->count,
+ oi->keymap[i].code);
+ ret = -EINVAL;
+ goto err_bad_keymap;
+ }
+ input_set_capability(input_devs->dev[dev], oi->type,
+ oi->keymap[i].code);
+ }
+
+ for (i = 0; i < oi->keymap_size; i++) {
+ ret = gpio_request(oi->keymap[i].gpio,
+ "gpio_event_output");
+ if (ret) {
+ pr_err("gpio_event_output_func: gpio_request "
+ "failed for %d\n", oi->keymap[i].gpio);
+ goto err_gpio_request_failed;
+ }
+ ret = gpio_direction_output(oi->keymap[i].gpio,
+ output_level);
+ if (ret) {
+ pr_err("gpio_event_output_func: "
+ "gpio_direction_output failed for %d\n",
+ oi->keymap[i].gpio);
+ goto err_gpio_direction_output_failed;
+ }
+ }
+ return 0;
+ }
+
+ ret = 0;
+ for (i = oi->keymap_size - 1; i >= 0; i--) {
+err_gpio_direction_output_failed:
+ gpio_free(oi->keymap[i].gpio);
+err_gpio_request_failed:
+ ;
+ }
+err_bad_keymap:
+ return ret;
+}
+
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index e3fa1cd..a57b04f 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -156,7 +156,7 @@ _set_debug(struct fritzcard *card)
}
static int
-set_debug(const char *val, struct kernel_param *kp)
+set_debug(const char *val, const struct kernel_param *kp)
{
int ret;
struct fritzcard *card;
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index d5bdbaf..1fc2906 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -244,7 +244,7 @@ _set_debug(struct inf_hw *card)
}
static int
-set_debug(const char *val, struct kernel_param *kp)
+set_debug(const char *val, const struct kernel_param *kp)
{
int ret;
struct inf_hw *card;
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index afde4ed..e9fcae4 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -111,7 +111,7 @@ _set_debug(struct tiger_hw *card)
}
static int
-set_debug(const char *val, struct kernel_param *kp)
+set_debug(const char *val, const struct kernel_param *kp)
{
int ret;
struct tiger_hw *card;
diff --git a/drivers/isdn/hardware/mISDN/speedfax.c b/drivers/isdn/hardware/mISDN/speedfax.c
index 9815bb4..1f1446e 100644
--- a/drivers/isdn/hardware/mISDN/speedfax.c
+++ b/drivers/isdn/hardware/mISDN/speedfax.c
@@ -94,7 +94,7 @@ _set_debug(struct sfax_hw *card)
}
static int
-set_debug(const char *val, struct kernel_param *kp)
+set_debug(const char *val, const struct kernel_param *kp)
{
int ret;
struct sfax_hw *card;
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 3b067ea..0db6783 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -101,7 +101,7 @@ _set_debug(struct w6692_hw *card)
}
static int
-set_debug(const char *val, struct kernel_param *kp)
+set_debug(const char *val, const struct kernel_param *kp)
{
int ret;
struct w6692_hw *card;
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 410c39c..4600f95 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -17,6 +17,7 @@
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/leds.h>
#include <linux/reboot.h>
#include "../leds.h"
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 197e29d..0923239 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -501,4 +501,65 @@
If unsure, say N.
+config DM_VERITY_AVB
+ tristate "Support AVB specific verity error behavior"
+ depends on DM_VERITY
+ ---help---
+ Enables Android Verified Boot platform-specific error
+ behavior. In particular, it will modify the vbmeta partition
+ specified on the kernel command-line when non-transient error
+ occurs (followed by a panic).
+
+ If unsure, say N.
+
+config DM_ANDROID_VERITY
+ bool "Android verity target support"
+ depends on BLK_DEV_DM=y
+ depends on DM_VERITY=y
+ depends on X509_CERTIFICATE_PARSER
+ depends on SYSTEM_TRUSTED_KEYRING
+ depends on CRYPTO_RSA
+ depends on KEYS
+ depends on ASYMMETRIC_KEY_TYPE
+ depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+ ---help---
+ This device-mapper target is virtually a VERITY target. This
+ target is setup by reading the metadata contents piggybacked
+ to the actual data blocks in the block device. The signature
+ of the metadata contents are verified against the key included
+ in the system keyring. Upon success, the underlying verity
+ target is setup.
+
+config DM_ANDROID_VERITY_AT_MOST_ONCE_DEFAULT_ENABLED
+ bool "Verity will validate blocks at most once"
+ depends on DM_VERITY
+ ---help---
+ Default enables at_most_once option for dm-verity
+
+ Verify data blocks only the first time they are read from the
+ data device, rather than every time. This reduces the overhead
+ of dm-verity so that it can be used on systems that are memory
+ and/or CPU constrained. However, it provides a reduced level
+ of security because only offline tampering of the data device's
+ content will be detected, not online tampering.
+
+ Hash blocks are still verified each time they are read from the
+ hash device, since verification of hash blocks is less performance
+ critical than data blocks, and a hash block will not be verified
+ any more after all the data blocks it covers have been verified anyway.
+
+ If unsure, say N.
+
+config DM_BOW
+ tristate "Backup block device"
+ depends on BLK_DEV_DM
+ select DM_BUFIO
+ ---help---
+ This device-mapper target takes a device and keeps a log of all
+ changes using free blocks identified by issuing a trim command.
+ This can then be restored by running a command line utility,
+ or committed by simply replacing the target.
+
+ If unsure, say N.
+
endif # MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 3cbda1a..18d9238 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -59,6 +59,8 @@
obj-$(CONFIG_DM_CACHE_CLEANER) += dm-cache-cleaner.o
obj-$(CONFIG_DM_ERA) += dm-era.o
obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o
+obj-$(CONFIG_DM_ANDROID_VERITY) += dm-android-verity.o
+obj-$(CONFIG_DM_BOW) += dm-bow.o
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
@@ -67,3 +69,7 @@
ifeq ($(CONFIG_DM_VERITY_FEC),y)
dm-verity-objs += dm-verity-fec.o
endif
+
+ifeq ($(CONFIG_DM_VERITY_AVB),y)
+dm-verity-objs += dm-verity-avb.o
+endif
diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c
new file mode 100644
index 0000000..f9491de
--- /dev/null
+++ b/drivers/md/dm-android-verity.c
@@ -0,0 +1,923 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/device-mapper.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/fcntl.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/of.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include <asm/setup.h>
+#include <crypto/hash.h>
+#include <crypto/hash_info.h>
+#include <crypto/public_key.h>
+#include <crypto/sha.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+
+#include "dm-verity.h"
+#include "dm-android-verity.h"
+
+static char verifiedbootstate[VERITY_COMMANDLINE_PARAM_LENGTH];
+static char veritymode[VERITY_COMMANDLINE_PARAM_LENGTH];
+static char veritykeyid[VERITY_DEFAULT_KEY_ID_LENGTH];
+static char buildvariant[BUILD_VARIANT];
+
+static bool target_added;
+static bool verity_enabled = true;
+struct dentry *debug_dir;
+static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv);
+
+static struct target_type android_verity_target = {
+ .name = "android-verity",
+ .version = {1, 0, 0},
+ .module = THIS_MODULE,
+ .ctr = android_verity_ctr,
+ .dtr = verity_dtr,
+ .map = verity_map,
+ .status = verity_status,
+ .prepare_ioctl = verity_prepare_ioctl,
+ .iterate_devices = verity_iterate_devices,
+ .io_hints = verity_io_hints,
+};
+
+static int __init verified_boot_state_param(char *line)
+{
+ strlcpy(verifiedbootstate, line, sizeof(verifiedbootstate));
+ return 1;
+}
+
+__setup("androidboot.verifiedbootstate=", verified_boot_state_param);
+
+static int __init verity_mode_param(char *line)
+{
+ strlcpy(veritymode, line, sizeof(veritymode));
+ return 1;
+}
+
+__setup("androidboot.veritymode=", verity_mode_param);
+
+static int __init verity_keyid_param(char *line)
+{
+ strlcpy(veritykeyid, line, sizeof(veritykeyid));
+ return 1;
+}
+
+__setup("veritykeyid=", verity_keyid_param);
+
+static int __init verity_buildvariant(char *line)
+{
+ strlcpy(buildvariant, line, sizeof(buildvariant));
+ return 1;
+}
+
+__setup("buildvariant=", verity_buildvariant);
+
+static inline bool default_verity_key_id(void)
+{
+ return veritykeyid[0] != '\0';
+}
+
+static inline bool is_eng(void)
+{
+ static const char typeeng[] = "eng";
+
+ return !strncmp(buildvariant, typeeng, sizeof(typeeng));
+}
+
+static inline bool is_userdebug(void)
+{
+ static const char typeuserdebug[] = "userdebug";
+
+ return !strncmp(buildvariant, typeuserdebug, sizeof(typeuserdebug));
+}
+
+static inline bool is_unlocked(void)
+{
+ static const char unlocked[] = "orange";
+
+ return !strncmp(verifiedbootstate, unlocked, sizeof(unlocked));
+}
+
+static int read_block_dev(struct bio_read *payload, struct block_device *bdev,
+ sector_t offset, int length)
+{
+ struct bio *bio;
+ int err = 0, i;
+
+ payload->number_of_pages = DIV_ROUND_UP(length, PAGE_SIZE);
+
+ bio = bio_alloc(GFP_KERNEL, payload->number_of_pages);
+ if (!bio) {
+ DMERR("Error while allocating bio");
+ return -ENOMEM;
+ }
+
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = offset;
+ bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC);
+
+ payload->page_io = kzalloc(sizeof(struct page *) *
+ payload->number_of_pages, GFP_KERNEL);
+ if (!payload->page_io) {
+ DMERR("page_io array alloc failed");
+ err = -ENOMEM;
+ goto free_bio;
+ }
+
+ for (i = 0; i < payload->number_of_pages; i++) {
+ payload->page_io[i] = alloc_page(GFP_KERNEL);
+ if (!payload->page_io[i]) {
+ DMERR("alloc_page failed");
+ err = -ENOMEM;
+ goto free_pages;
+ }
+ if (!bio_add_page(bio, payload->page_io[i], PAGE_SIZE, 0)) {
+ DMERR("bio_add_page error");
+ err = -EIO;
+ goto free_pages;
+ }
+ }
+
+ if (!submit_bio_wait(bio))
+ /* success */
+ goto free_bio;
+ DMERR("bio read failed");
+ err = -EIO;
+
+free_pages:
+ for (i = 0; i < payload->number_of_pages; i++)
+ if (payload->page_io[i])
+ __free_page(payload->page_io[i]);
+ kfree(payload->page_io);
+free_bio:
+ bio_put(bio);
+ return err;
+}
+
+static inline u64 fec_div_round_up(u64 x, u64 y)
+{
+ u64 remainder;
+
+ return div64_u64_rem(x, y, &remainder) +
+ (remainder > 0 ? 1 : 0);
+}
+
+static inline void populate_fec_metadata(struct fec_header *header,
+ struct fec_ecc_metadata *ecc)
+{
+ ecc->blocks = fec_div_round_up(le64_to_cpu(header->inp_size),
+ FEC_BLOCK_SIZE);
+ ecc->roots = le32_to_cpu(header->roots);
+ ecc->start = le64_to_cpu(header->inp_size);
+}
+
+static inline int validate_fec_header(struct fec_header *header, u64 offset)
+{
+ /* move offset to make the sanity check work for backup header
+ * as well. */
+ offset -= offset % FEC_BLOCK_SIZE;
+ if (le32_to_cpu(header->magic) != FEC_MAGIC ||
+ le32_to_cpu(header->version) != FEC_VERSION ||
+ le32_to_cpu(header->size) != sizeof(struct fec_header) ||
+ le32_to_cpu(header->roots) == 0 ||
+ le32_to_cpu(header->roots) >= FEC_RSM)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int extract_fec_header(dev_t dev, struct fec_header *fec,
+ struct fec_ecc_metadata *ecc)
+{
+ u64 device_size;
+ struct bio_read payload;
+ int i, err = 0;
+ struct block_device *bdev;
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+
+ if (IS_ERR_OR_NULL(bdev)) {
+ DMERR("bdev get error");
+ return PTR_ERR(bdev);
+ }
+
+ device_size = i_size_read(bdev->bd_inode);
+
+ /* fec metadata size is a power of 2 and PAGE_SIZE
+ * is a power of 2 as well.
+ */
+ BUG_ON(FEC_BLOCK_SIZE > PAGE_SIZE);
+ /* 512 byte sector alignment */
+ BUG_ON(((device_size - FEC_BLOCK_SIZE) % (1 << SECTOR_SHIFT)) != 0);
+
+ err = read_block_dev(&payload, bdev, (device_size -
+ FEC_BLOCK_SIZE) / (1 << SECTOR_SHIFT), FEC_BLOCK_SIZE);
+ if (err) {
+ DMERR("Error while reading verity metadata");
+ goto error;
+ }
+
+ BUG_ON(sizeof(struct fec_header) > PAGE_SIZE);
+ memcpy(fec, page_address(payload.page_io[0]),
+ sizeof(*fec));
+
+ ecc->valid = true;
+ if (validate_fec_header(fec, device_size - FEC_BLOCK_SIZE)) {
+ /* Try the backup header */
+ memcpy(fec, page_address(payload.page_io[0]) + FEC_BLOCK_SIZE
+ - sizeof(*fec) ,
+ sizeof(*fec));
+ if (validate_fec_header(fec, device_size -
+ sizeof(struct fec_header)))
+ ecc->valid = false;
+ }
+
+ if (ecc->valid)
+ populate_fec_metadata(fec, ecc);
+
+ for (i = 0; i < payload.number_of_pages; i++)
+ __free_page(payload.page_io[i]);
+ kfree(payload.page_io);
+
+error:
+ blkdev_put(bdev, FMODE_READ);
+ return err;
+}
+static void find_metadata_offset(struct fec_header *fec,
+ struct block_device *bdev, u64 *metadata_offset)
+{
+ u64 device_size;
+
+ device_size = i_size_read(bdev->bd_inode);
+
+ if (le32_to_cpu(fec->magic) == FEC_MAGIC)
+ *metadata_offset = le64_to_cpu(fec->inp_size) -
+ VERITY_METADATA_SIZE;
+ else
+ *metadata_offset = device_size - VERITY_METADATA_SIZE;
+}
+
+static int find_size(dev_t dev, u64 *device_size)
+{
+ struct block_device *bdev;
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+ if (IS_ERR_OR_NULL(bdev)) {
+ DMERR("blkdev_get_by_dev failed");
+ return PTR_ERR(bdev);
+ }
+
+ *device_size = i_size_read(bdev->bd_inode);
+ *device_size >>= SECTOR_SHIFT;
+
+ DMINFO("blkdev size in sectors: %llu", *device_size);
+ blkdev_put(bdev, FMODE_READ);
+ return 0;
+}
+
+static int verify_header(struct android_metadata_header *header)
+{
+ int retval = -EINVAL;
+
+ if (is_userdebug() && le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_DISABLE)
+ return VERITY_STATE_DISABLE;
+
+ if (!(le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_NUMBER) ||
+ (le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_DISABLE)) {
+ DMERR("Incorrect magic number");
+ return retval;
+ }
+
+ if (le32_to_cpu(header->protocol_version) !=
+ VERITY_METADATA_VERSION) {
+ DMERR("Unsupported version %u",
+ le32_to_cpu(header->protocol_version));
+ return retval;
+ }
+
+ return 0;
+}
+
+static int extract_metadata(dev_t dev, struct fec_header *fec,
+ struct android_metadata **metadata,
+ bool *verity_enabled)
+{
+ struct block_device *bdev;
+ struct android_metadata_header *header;
+ int i;
+ u32 table_length, copy_length, offset;
+ u64 metadata_offset;
+ struct bio_read payload;
+ int err = 0;
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+
+ if (IS_ERR_OR_NULL(bdev)) {
+ DMERR("blkdev_get_by_dev failed");
+ return -ENODEV;
+ }
+
+ find_metadata_offset(fec, bdev, &metadata_offset);
+
+ /* Verity metadata size is a power of 2 and PAGE_SIZE
+ * is a power of 2 as well.
+ * PAGE_SIZE is also a multiple of 512 bytes.
+ */
+ if (VERITY_METADATA_SIZE > PAGE_SIZE)
+ BUG_ON(VERITY_METADATA_SIZE % PAGE_SIZE != 0);
+ /* 512 byte sector alignment */
+ BUG_ON(metadata_offset % (1 << SECTOR_SHIFT) != 0);
+
+ err = read_block_dev(&payload, bdev, metadata_offset /
+ (1 << SECTOR_SHIFT), VERITY_METADATA_SIZE);
+ if (err) {
+ DMERR("Error while reading verity metadata");
+ goto blkdev_release;
+ }
+
+ header = kzalloc(sizeof(*header), GFP_KERNEL);
+ if (!header) {
+ DMERR("kzalloc failed for header");
+ err = -ENOMEM;
+ goto free_payload;
+ }
+
+ memcpy(header, page_address(payload.page_io[0]),
+ sizeof(*header));
+
+ DMINFO("bio magic_number:%u protocol_version:%d table_length:%u",
+ le32_to_cpu(header->magic_number),
+ le32_to_cpu(header->protocol_version),
+ le32_to_cpu(header->table_length));
+
+ err = verify_header(header);
+
+ if (err == VERITY_STATE_DISABLE) {
+ DMERR("Mounting root with verity disabled");
+ *verity_enabled = false;
+ /* we would still have to read the metadata to figure out
+ * the data blocks size. Or may be could map the entire
+ * partition similar to mounting the device.
+ *
+ * Reset error as well as the verity_enabled flag is changed.
+ */
+ err = 0;
+ } else if (err)
+ goto free_header;
+
+ *metadata = kzalloc(sizeof(**metadata), GFP_KERNEL);
+ if (!*metadata) {
+ DMERR("kzalloc for metadata failed");
+ err = -ENOMEM;
+ goto free_header;
+ }
+
+ (*metadata)->header = header;
+ table_length = le32_to_cpu(header->table_length);
+
+ if (table_length == 0 ||
+ table_length > (VERITY_METADATA_SIZE -
+ sizeof(struct android_metadata_header))) {
+ DMERR("table_length too long");
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ (*metadata)->verity_table = kzalloc(table_length + 1, GFP_KERNEL);
+
+ if (!(*metadata)->verity_table) {
+ DMERR("kzalloc verity_table failed");
+ err = -ENOMEM;
+ goto free_metadata;
+ }
+
+ if (sizeof(struct android_metadata_header) +
+ table_length <= PAGE_SIZE) {
+ memcpy((*metadata)->verity_table,
+ page_address(payload.page_io[0])
+ + sizeof(struct android_metadata_header),
+ table_length);
+ } else {
+ copy_length = PAGE_SIZE -
+ sizeof(struct android_metadata_header);
+ memcpy((*metadata)->verity_table,
+ page_address(payload.page_io[0])
+ + sizeof(struct android_metadata_header),
+ copy_length);
+ table_length -= copy_length;
+ offset = copy_length;
+ i = 1;
+ while (table_length != 0) {
+ if (table_length > PAGE_SIZE) {
+ memcpy((*metadata)->verity_table + offset,
+ page_address(payload.page_io[i]),
+ PAGE_SIZE);
+ offset += PAGE_SIZE;
+ table_length -= PAGE_SIZE;
+ } else {
+ memcpy((*metadata)->verity_table + offset,
+ page_address(payload.page_io[i]),
+ table_length);
+ table_length = 0;
+ }
+ i++;
+ }
+ }
+ (*metadata)->verity_table[table_length] = '\0';
+
+ DMINFO("verity_table: %s", (*metadata)->verity_table);
+ goto free_payload;
+
+free_metadata:
+ kfree(*metadata);
+free_header:
+ kfree(header);
+free_payload:
+ for (i = 0; i < payload.number_of_pages; i++)
+ if (payload.page_io[i])
+ __free_page(payload.page_io[i]);
+ kfree(payload.page_io);
+blkdev_release:
+ blkdev_put(bdev, FMODE_READ);
+ return err;
+}
+
+/* helper functions to extract properties from dts */
+const char *find_dt_value(const char *name)
+{
+ struct device_node *firmware;
+ const char *value;
+
+ firmware = of_find_node_by_path("/firmware/android");
+ if (!firmware)
+ return NULL;
+ value = of_get_property(firmware, name, NULL);
+ of_node_put(firmware);
+
+ return value;
+}
+
+static int verity_mode(void)
+{
+ static const char enforcing[] = "enforcing";
+ static const char verified_mode_prop[] = "veritymode";
+ const char *value;
+
+ value = find_dt_value(verified_mode_prop);
+ if (!value)
+ value = veritymode;
+ if (!strncmp(value, enforcing, sizeof(enforcing) - 1))
+ return DM_VERITY_MODE_RESTART;
+
+ return DM_VERITY_MODE_EIO;
+}
+
+static void handle_error(void)
+{
+ int mode = verity_mode();
+ if (mode == DM_VERITY_MODE_RESTART) {
+ DMERR("triggering restart");
+ kernel_restart("dm-verity device corrupted");
+ } else {
+ DMERR("Mounting verity root failed");
+ }
+}
+
+static struct public_key_signature *table_make_digest(
+ enum hash_algo hash,
+ const void *table,
+ unsigned long table_len)
+{
+ struct public_key_signature *pks = NULL;
+ struct crypto_shash *tfm;
+ struct shash_desc *desc;
+ size_t digest_size, desc_size;
+ int ret;
+
+ /* Allocate the hashing algorithm we're going to need and find out how
+ * big the hash operational data will be.
+ */
+ tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0);
+ if (IS_ERR(tfm))
+ return ERR_CAST(tfm);
+
+ desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
+ digest_size = crypto_shash_digestsize(tfm);
+
+ /* We allocate the hash operational data storage on the end of out
+ * context data and the digest output buffer on the end of that.
+ */
+ ret = -ENOMEM;
+ pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL);
+ if (!pks)
+ goto error;
+
+ pks->pkey_algo = "rsa";
+ pks->hash_algo = hash_algo_name[hash];
+ pks->digest = (u8 *)pks + sizeof(*pks) + desc_size;
+ pks->digest_size = digest_size;
+
+ desc = (struct shash_desc *)(pks + 1);
+ desc->tfm = tfm;
+ desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ ret = crypto_shash_init(desc);
+ if (ret < 0)
+ goto error;
+
+ ret = crypto_shash_finup(desc, table, table_len, pks->digest);
+ if (ret < 0)
+ goto error;
+
+ crypto_free_shash(tfm);
+ return pks;
+
+error:
+ kfree(pks);
+ crypto_free_shash(tfm);
+ return ERR_PTR(ret);
+}
+
+
+static int verify_verity_signature(char *key_id,
+ struct android_metadata *metadata)
+{
+ struct public_key_signature *pks = NULL;
+ int retval = -EINVAL;
+
+ if (!key_id)
+ goto error;
+
+ pks = table_make_digest(HASH_ALGO_SHA256,
+ (const void *)metadata->verity_table,
+ le32_to_cpu(metadata->header->table_length));
+ if (IS_ERR(pks)) {
+ DMERR("hashing failed");
+ retval = PTR_ERR(pks);
+ pks = NULL;
+ goto error;
+ }
+
+ pks->s = kmemdup(&metadata->header->signature[0], RSANUMBYTES, GFP_KERNEL);
+ if (!pks->s) {
+ DMERR("Error allocating memory for signature");
+ goto error;
+ }
+ pks->s_size = RSANUMBYTES;
+
+ retval = verify_signature_one(pks, NULL, key_id);
+ kfree(pks->s);
+error:
+ kfree(pks);
+ return retval;
+}
+
+static inline bool test_mult_overflow(sector_t a, u32 b)
+{
+ sector_t r = (sector_t)~0ULL;
+
+ sector_div(r, b);
+ return a > r;
+}
+
+static int add_as_linear_device(struct dm_target *ti, char *dev)
+{
+ /*Move to linear mapping defines*/
+ char *linear_table_args[DM_LINEAR_ARGS] = {dev,
+ DM_LINEAR_TARGET_OFFSET};
+ int err = 0;
+
+ android_verity_target.dtr = dm_linear_dtr,
+ android_verity_target.map = dm_linear_map,
+ android_verity_target.status = dm_linear_status,
+ android_verity_target.prepare_ioctl = dm_linear_prepare_ioctl,
+ android_verity_target.iterate_devices = dm_linear_iterate_devices,
+ android_verity_target.direct_access = dm_linear_direct_access,
+ android_verity_target.io_hints = NULL;
+
+ set_disk_ro(dm_disk(dm_table_get_md(ti->table)), 0);
+
+ err = dm_linear_ctr(ti, DM_LINEAR_ARGS, linear_table_args);
+
+ if (!err) {
+ DMINFO("Added android-verity as a linear target");
+ target_added = true;
+ } else
+ DMERR("Failed to add android-verity as linear target");
+
+ return err;
+}
+
+static int create_linear_device(struct dm_target *ti, dev_t dev,
+ char *target_device)
+{
+ u64 device_size = 0;
+ int err = find_size(dev, &device_size);
+
+ if (err) {
+ DMERR("error finding bdev size");
+ handle_error();
+ return err;
+ }
+
+ ti->len = device_size;
+ err = add_as_linear_device(ti, target_device);
+ if (err) {
+ handle_error();
+ return err;
+ }
+ verity_enabled = false;
+ return 0;
+}
+
+/*
+ * Target parameters:
+ * <key id> Key id of the public key in the system keyring.
+ * Verity metadata's signature would be verified against
+ * this. If the key id contains spaces, replace them
+ * with '#'.
+ * <block device> The block device for which dm-verity is being setup.
+ */
+static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ dev_t uninitialized_var(dev);
+ struct android_metadata *metadata = NULL;
+ int err = 0, i, mode;
+ char *key_id = NULL, *table_ptr, dummy, *target_device;
+ char *verity_table_args[VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS];
+ /* One for specifying number of opt args and one for mode */
+ sector_t data_sectors;
+ u32 data_block_size;
+ unsigned int no_of_args = VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS;
+ struct fec_header uninitialized_var(fec);
+ struct fec_ecc_metadata uninitialized_var(ecc);
+ char buf[FEC_ARG_LENGTH], *buf_ptr;
+ unsigned long long tmpll;
+
+ if (argc == 1) {
+ /* Use the default keyid */
+ if (default_verity_key_id())
+ key_id = veritykeyid;
+ else if (!is_eng()) {
+ DMERR("veritykeyid= is not set");
+ handle_error();
+ return -EINVAL;
+ }
+ target_device = argv[0];
+ } else if (argc == 2) {
+ key_id = argv[0];
+ target_device = argv[1];
+ } else {
+ DMERR("Incorrect number of arguments");
+ handle_error();
+ return -EINVAL;
+ }
+
+ dev = name_to_dev_t(target_device);
+ if (!dev) {
+ DMERR("no dev found for %s", target_device);
+ handle_error();
+ return -EINVAL;
+ }
+
+ if (is_eng())
+ return create_linear_device(ti, dev, target_device);
+
+ strreplace(key_id, '#', ' ');
+
+ DMINFO("key:%s dev:%s", key_id, target_device);
+
+ if (extract_fec_header(dev, &fec, &ecc)) {
+ DMERR("Error while extracting fec header");
+ handle_error();
+ return -EINVAL;
+ }
+
+ err = extract_metadata(dev, &fec, &metadata, &verity_enabled);
+
+ if (err) {
+ /* Allow invalid metadata when the device is unlocked */
+ if (is_unlocked()) {
+ DMWARN("Allow invalid metadata when unlocked");
+ return create_linear_device(ti, dev, target_device);
+ }
+ DMERR("Error while extracting metadata");
+ handle_error();
+ goto free_metadata;
+ }
+
+ if (verity_enabled) {
+ err = verify_verity_signature(key_id, metadata);
+
+ if (err) {
+ DMERR("Signature verification failed");
+ handle_error();
+ goto free_metadata;
+ } else
+ DMINFO("Signature verification success");
+ }
+
+ table_ptr = metadata->verity_table;
+
+ for (i = 0; i < VERITY_TABLE_ARGS; i++) {
+ verity_table_args[i] = strsep(&table_ptr, " ");
+ if (verity_table_args[i] == NULL)
+ break;
+ }
+
+ if (i != VERITY_TABLE_ARGS) {
+ DMERR("Verity table not in the expected format");
+ err = -EINVAL;
+ handle_error();
+ goto free_metadata;
+ }
+
+ if (sscanf(verity_table_args[5], "%llu%c", &tmpll, &dummy)
+ != 1) {
+ DMERR("Verity table not in the expected format");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ if (tmpll > ULONG_MAX) {
+ DMERR("<num_data_blocks> too large. Forgot to turn on CONFIG_LBDAF?");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ data_sectors = tmpll;
+
+ if (sscanf(verity_table_args[3], "%u%c", &data_block_size, &dummy)
+ != 1) {
+ DMERR("Verity table not in the expected format");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ if (test_mult_overflow(data_sectors, data_block_size >>
+ SECTOR_SHIFT)) {
+ DMERR("data_sectors too large");
+ handle_error();
+ err = -EOVERFLOW;
+ goto free_metadata;
+ }
+
+ data_sectors *= data_block_size >> SECTOR_SHIFT;
+ DMINFO("Data sectors %llu", (unsigned long long)data_sectors);
+
+ /* update target length */
+ ti->len = data_sectors;
+
+ /* Setup linear target and free */
+ if (!verity_enabled) {
+ err = add_as_linear_device(ti, target_device);
+ goto free_metadata;
+ }
+
+ /*substitute data_dev and hash_dev*/
+ verity_table_args[1] = target_device;
+ verity_table_args[2] = target_device;
+
+ mode = verity_mode();
+
+ if (ecc.valid && IS_BUILTIN(CONFIG_DM_VERITY_FEC)) {
+ if (mode) {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "%u %s " VERITY_TABLE_OPT_FEC_FORMAT,
+ 1 + VERITY_TABLE_OPT_FEC_ARGS,
+ mode == DM_VERITY_MODE_RESTART ?
+ VERITY_TABLE_OPT_RESTART :
+ VERITY_TABLE_OPT_LOGGING,
+ target_device,
+ ecc.start / FEC_BLOCK_SIZE, ecc.blocks,
+ ecc.roots);
+ } else {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "%u " VERITY_TABLE_OPT_FEC_FORMAT,
+ VERITY_TABLE_OPT_FEC_ARGS, target_device,
+ ecc.start / FEC_BLOCK_SIZE, ecc.blocks,
+ ecc.roots);
+ }
+ } else if (mode) {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "2 " VERITY_TABLE_OPT_IGNZERO " %s",
+ mode == DM_VERITY_MODE_RESTART ?
+ VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING);
+ } else {
+ err = snprintf(buf, FEC_ARG_LENGTH, "1 %s",
+ "ignore_zero_blocks");
+ }
+
+ if (err < 0 || err >= FEC_ARG_LENGTH)
+ goto free_metadata;
+
+ buf_ptr = buf;
+
+ for (i = VERITY_TABLE_ARGS; i < (VERITY_TABLE_ARGS +
+ VERITY_TABLE_OPT_FEC_ARGS + 2); i++) {
+ verity_table_args[i] = strsep(&buf_ptr, " ");
+ if (verity_table_args[i] == NULL) {
+ no_of_args = i;
+ break;
+ }
+ }
+
+ err = verity_ctr(ti, no_of_args, verity_table_args);
+ if (err) {
+ DMERR("android-verity failed to create a verity target");
+ } else {
+ target_added = true;
+ DMINFO("android-verity created as verity target");
+ }
+
+free_metadata:
+ if (metadata) {
+ kfree(metadata->header);
+ kfree(metadata->verity_table);
+ }
+ kfree(metadata);
+ return err;
+}
+
+static int __init dm_android_verity_init(void)
+{
+ int r;
+ struct dentry *file;
+
+ r = dm_register_target(&android_verity_target);
+ if (r < 0)
+ DMERR("register failed %d", r);
+
+ /* Tracks the status of the last added target */
+ debug_dir = debugfs_create_dir("android_verity", NULL);
+
+ if (IS_ERR_OR_NULL(debug_dir)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ goto end;
+ }
+
+ file = debugfs_create_bool("target_added", S_IRUGO, debug_dir,
+ &target_added);
+
+ if (IS_ERR_OR_NULL(file)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ debugfs_remove_recursive(debug_dir);
+ goto end;
+ }
+
+ file = debugfs_create_bool("verity_enabled", S_IRUGO, debug_dir,
+ &verity_enabled);
+
+ if (IS_ERR_OR_NULL(file)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ debugfs_remove_recursive(debug_dir);
+ }
+
+end:
+ return r;
+}
+
+static void __exit dm_android_verity_exit(void)
+{
+ if (!IS_ERR_OR_NULL(debug_dir))
+ debugfs_remove_recursive(debug_dir);
+
+ dm_unregister_target(&android_verity_target);
+}
+
+module_init(dm_android_verity_init);
+module_exit(dm_android_verity_exit);
diff --git a/drivers/md/dm-android-verity.h b/drivers/md/dm-android-verity.h
new file mode 100644
index 0000000..c8d7ab64
--- /dev/null
+++ b/drivers/md/dm-android-verity.h
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef DM_ANDROID_VERITY_H
+#define DM_ANDROID_VERITY_H
+
+#include <crypto/sha.h>
+
+#define RSANUMBYTES 256
+#define VERITY_METADATA_MAGIC_NUMBER 0xb001b001
+#define VERITY_METADATA_MAGIC_DISABLE 0x46464f56
+#define VERITY_METADATA_VERSION 0
+#define VERITY_STATE_DISABLE 1
+#define DATA_BLOCK_SIZE (4 * 1024)
+#define VERITY_METADATA_SIZE (8 * DATA_BLOCK_SIZE)
+#define VERITY_TABLE_ARGS 10
+#define VERITY_COMMANDLINE_PARAM_LENGTH 20
+#define BUILD_VARIANT 20
+
+/*
+ * <subject>:<sha1-id> is the format for the identifier.
+ * subject can either be the Common Name(CN) + Organization Name(O) or
+ * just the CN if the it is prefixed with O
+ * From https://tools.ietf.org/html/rfc5280#appendix-A
+ * ub-organization-name-length INTEGER ::= 64
+ * ub-common-name-length INTEGER ::= 64
+ *
+ * http://lxr.free-electrons.com/source/crypto/asymmetric_keys/x509_cert_parser.c?v=3.9#L278
+ * ctx->o_size + 2 + ctx->cn_size + 1
+ * + 41 characters for ":" and sha1 id
+ * 64 + 2 + 64 + 1 + 1 + 40 (172)
+ * setting VERITY_DEFAULT_KEY_ID_LENGTH to 200 characters.
+ */
+#define VERITY_DEFAULT_KEY_ID_LENGTH 200
+
+#define FEC_MAGIC 0xFECFECFE
+#define FEC_BLOCK_SIZE (4 * 1024)
+#define FEC_VERSION 0
+#define FEC_RSM 255
+#define FEC_ARG_LENGTH 300
+
+#define VERITY_TABLE_OPT_RESTART "restart_on_corruption"
+#define VERITY_TABLE_OPT_LOGGING "ignore_corruption"
+#define VERITY_TABLE_OPT_IGNZERO "ignore_zero_blocks"
+
+#define VERITY_TABLE_OPT_FEC_FORMAT \
+ "use_fec_from_device %s fec_start %llu fec_blocks %llu fec_roots %u ignore_zero_blocks"
+#define VERITY_TABLE_OPT_FEC_ARGS 9
+
+#define VERITY_DEBUG 0
+
+#define DM_MSG_PREFIX "android-verity"
+
+#define DM_LINEAR_ARGS 2
+#define DM_LINEAR_TARGET_OFFSET "0"
+
+/*
+ * There can be two formats.
+ * if fec is present
+ * <data_blocks> <verity_tree> <verity_metdata_32K><fec_data><fec_data_4K>
+ * if fec is not present
+ * <data_blocks> <verity_tree> <verity_metdata_32K>
+ */
+struct fec_header {
+ __le32 magic;
+ __le32 version;
+ __le32 size;
+ __le32 roots;
+ __le32 fec_size;
+ __le64 inp_size;
+ u8 hash[SHA256_DIGEST_SIZE];
+} __attribute__((packed));
+
+struct android_metadata_header {
+ __le32 magic_number;
+ __le32 protocol_version;
+ char signature[RSANUMBYTES];
+ __le32 table_length;
+};
+
+struct android_metadata {
+ struct android_metadata_header *header;
+ char *verity_table;
+};
+
+struct fec_ecc_metadata {
+ bool valid;
+ u32 roots;
+ u64 blocks;
+ u64 rounds;
+ u64 start;
+};
+
+struct bio_read {
+ struct page **page_io;
+ int number_of_pages;
+};
+
+extern struct target_type linear_target;
+
+extern void dm_linear_dtr(struct dm_target *ti);
+extern int dm_linear_map(struct dm_target *ti, struct bio *bio);
+extern void dm_linear_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen);
+extern int dm_linear_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode);
+extern int dm_linear_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data);
+extern int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv);
+extern long dm_linear_direct_access(struct dm_target *ti, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size);
+#endif /* DM_ANDROID_VERITY_H */
diff --git a/drivers/md/dm-bow.c b/drivers/md/dm-bow.c
new file mode 100644
index 0000000..b45f0b2
--- /dev/null
+++ b/drivers/md/dm-bow.c
@@ -0,0 +1,1234 @@
+/*
+ * Copyright (C) 2018 Google Limited.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm.h"
+#include "dm-bufio.h"
+#include "dm-core.h"
+
+#include <linux/crc32.h>
+#include <linux/module.h>
+
+#define DM_MSG_PREFIX "bow"
+#define SECTOR_SIZE 512
+
+struct log_entry {
+ u64 source;
+ u64 dest;
+ u32 size;
+ u32 checksum;
+} __packed;
+
+struct log_sector {
+ u32 magic;
+ u16 header_version;
+ u16 header_size;
+ u32 block_size;
+ u32 count;
+ u32 sequence;
+ sector_t sector0;
+ struct log_entry entries[];
+} __packed;
+
+/*
+ * MAGIC is BOW in ascii
+ */
+#define MAGIC 0x00574f42
+#define HEADER_VERSION 0x0100
+
+/*
+ * A sorted set of ranges representing the state of the data on the device.
+ * Use an rb_tree for fast lookup of a given sector
+ * Consecutive ranges are always of different type - operations on this
+ * set must merge matching consecutive ranges.
+ *
+ * Top range is always of type TOP
+ */
+struct bow_range {
+ struct rb_node node;
+ sector_t sector;
+ enum {
+ INVALID, /* Type not set */
+ SECTOR0, /* First sector - holds log record */
+ SECTOR0_CURRENT,/* Live contents of sector0 */
+ UNCHANGED, /* Original contents */
+ TRIMMED, /* Range has been trimmed */
+ CHANGED, /* Range has been changed */
+ BACKUP, /* Range is being used as a backup */
+ TOP, /* Final range - sector is size of device */
+ } type;
+ struct list_head trimmed_list; /* list of TRIMMED ranges */
+};
+
+static const char * const readable_type[] = {
+ "Invalid",
+ "Sector0",
+ "Sector0_current",
+ "Unchanged",
+ "Free",
+ "Changed",
+ "Backup",
+ "Top",
+};
+
+enum state {
+ TRIM,
+ CHECKPOINT,
+ COMMITTED,
+};
+
+struct bow_context {
+ struct dm_dev *dev;
+ u32 block_size;
+ u32 block_shift;
+ struct workqueue_struct *workqueue;
+ struct dm_bufio_client *bufio;
+ struct mutex ranges_lock; /* Hold to access this struct and/or ranges */
+ struct rb_root ranges;
+ struct dm_kobject_holder kobj_holder; /* for sysfs attributes */
+ atomic_t state; /* One of the enum state values above */
+ u64 trims_total;
+ struct log_sector *log_sector;
+ struct list_head trimmed_list;
+ bool forward_trims;
+};
+
+sector_t range_top(struct bow_range *br)
+{
+ return container_of(rb_next(&br->node), struct bow_range, node)
+ ->sector;
+}
+
+u64 range_size(struct bow_range *br)
+{
+ return (range_top(br) - br->sector) * SECTOR_SIZE;
+}
+
+static sector_t bvec_top(struct bvec_iter *bi_iter)
+{
+ return bi_iter->bi_sector + bi_iter->bi_size / SECTOR_SIZE;
+}
+
+/*
+ * Find the first range that overlaps with bi_iter
+ * bi_iter is set to the size of the overlapping sub-range
+ */
+static struct bow_range *find_first_overlapping_range(struct rb_root *ranges,
+ struct bvec_iter *bi_iter)
+{
+ struct rb_node *node = ranges->rb_node;
+ struct bow_range *br;
+
+ while (node) {
+ br = container_of(node, struct bow_range, node);
+
+ if (br->sector <= bi_iter->bi_sector
+ && bi_iter->bi_sector < range_top(br))
+ break;
+
+ if (bi_iter->bi_sector < br->sector)
+ node = node->rb_left;
+ else
+ node = node->rb_right;
+ }
+
+ WARN_ON(!node);
+ if (!node)
+ return NULL;
+
+ if (range_top(br) - bi_iter->bi_sector
+ < bi_iter->bi_size >> SECTOR_SHIFT)
+ bi_iter->bi_size = (range_top(br) - bi_iter->bi_sector)
+ << SECTOR_SHIFT;
+
+ return br;
+}
+
+void add_before(struct rb_root *ranges, struct bow_range *new_br,
+ struct bow_range *existing)
+{
+ struct rb_node *parent = &(existing->node);
+ struct rb_node **link = &(parent->rb_left);
+
+ while (*link) {
+ parent = *link;
+ link = &((*link)->rb_right);
+ }
+
+ rb_link_node(&new_br->node, parent, link);
+ rb_insert_color(&new_br->node, ranges);
+}
+
+/*
+ * Given a range br returned by find_first_overlapping_range, split br into a
+ * leading range, a range matching the bi_iter and a trailing range.
+ * Leading and trailing may end up size 0 and will then be deleted. The
+ * new range matching the bi_iter is then returned and should have its type
+ * and type specific fields populated.
+ * If bi_iter runs off the end of the range, bi_iter is truncated accordingly
+ */
+static int split_range(struct bow_context *bc, struct bow_range **br,
+ struct bvec_iter *bi_iter)
+{
+ struct bow_range *new_br;
+
+ if (bi_iter->bi_sector < (*br)->sector) {
+ WARN_ON(true);
+ return -EIO;
+ }
+
+ if (bi_iter->bi_sector > (*br)->sector) {
+ struct bow_range *leading_br =
+ kzalloc(sizeof(*leading_br), GFP_KERNEL);
+
+ if (!leading_br)
+ return -ENOMEM;
+
+ *leading_br = **br;
+ if (leading_br->type == TRIMMED)
+ list_add(&leading_br->trimmed_list, &bc->trimmed_list);
+
+ add_before(&bc->ranges, leading_br, *br);
+ (*br)->sector = bi_iter->bi_sector;
+ }
+
+ if (bvec_top(bi_iter) >= range_top(*br)) {
+ bi_iter->bi_size = (range_top(*br) - (*br)->sector)
+ * SECTOR_SIZE;
+ return 0;
+ }
+
+ /* new_br will be the beginning, existing br will be the tail */
+ new_br = kzalloc(sizeof(*new_br), GFP_KERNEL);
+ if (!new_br)
+ return -ENOMEM;
+
+ new_br->sector = (*br)->sector;
+ (*br)->sector = bvec_top(bi_iter);
+ add_before(&bc->ranges, new_br, *br);
+ *br = new_br;
+
+ return 0;
+}
+
+/*
+ * Sets type of a range. May merge range into surrounding ranges
+ * Since br may be invalidated, always sets br to NULL to prevent
+ * usage after this is called
+ */
+static void set_type(struct bow_context *bc, struct bow_range **br, int type)
+{
+ struct bow_range *prev = container_of(rb_prev(&(*br)->node),
+ struct bow_range, node);
+ struct bow_range *next = container_of(rb_next(&(*br)->node),
+ struct bow_range, node);
+
+ if ((*br)->type == TRIMMED) {
+ bc->trims_total -= range_size(*br);
+ list_del(&(*br)->trimmed_list);
+ }
+
+ if (type == TRIMMED) {
+ bc->trims_total += range_size(*br);
+ list_add(&(*br)->trimmed_list, &bc->trimmed_list);
+ }
+
+ (*br)->type = type;
+
+ if (next->type == type) {
+ if (type == TRIMMED)
+ list_del(&next->trimmed_list);
+ rb_erase(&next->node, &bc->ranges);
+ kfree(next);
+ }
+
+ if (prev->type == type) {
+ if (type == TRIMMED)
+ list_del(&(*br)->trimmed_list);
+ rb_erase(&(*br)->node, &bc->ranges);
+ kfree(*br);
+ }
+
+ *br = NULL;
+}
+
+static struct bow_range *find_free_range(struct bow_context *bc)
+{
+ if (list_empty(&bc->trimmed_list)) {
+ DMERR("Unable to find free space to back up to");
+ return NULL;
+ }
+
+ return list_first_entry(&bc->trimmed_list, struct bow_range,
+ trimmed_list);
+}
+
+static sector_t sector_to_page(struct bow_context const *bc, sector_t sector)
+{
+ WARN_ON((sector & (((sector_t)1 << (bc->block_shift - SECTOR_SHIFT)) - 1))
+ != 0);
+ return sector >> (bc->block_shift - SECTOR_SHIFT);
+}
+
+static int copy_data(struct bow_context const *bc,
+ struct bow_range *source, struct bow_range *dest,
+ u32 *checksum)
+{
+ int i;
+
+ if (range_size(source) != range_size(dest)) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ if (checksum)
+ *checksum = sector_to_page(bc, source->sector);
+
+ for (i = 0; i < range_size(source) >> bc->block_shift; ++i) {
+ struct dm_buffer *read_buffer, *write_buffer;
+ u8 *read, *write;
+ sector_t page = sector_to_page(bc, source->sector) + i;
+
+ read = dm_bufio_read(bc->bufio, page, &read_buffer);
+ if (IS_ERR(read)) {
+ DMERR("Cannot read page %llu",
+ (unsigned long long)page);
+ return PTR_ERR(read);
+ }
+
+ if (checksum)
+ *checksum = crc32(*checksum, read, bc->block_size);
+
+ write = dm_bufio_new(bc->bufio,
+ sector_to_page(bc, dest->sector) + i,
+ &write_buffer);
+ if (IS_ERR(write)) {
+ DMERR("Cannot write sector");
+ dm_bufio_release(read_buffer);
+ return PTR_ERR(write);
+ }
+
+ memcpy(write, read, bc->block_size);
+
+ dm_bufio_mark_buffer_dirty(write_buffer);
+ dm_bufio_release(write_buffer);
+ dm_bufio_release(read_buffer);
+ }
+
+ dm_bufio_write_dirty_buffers(bc->bufio);
+ return 0;
+}
+
+/****** logging functions ******/
+
+static int add_log_entry(struct bow_context *bc, sector_t source, sector_t dest,
+ unsigned int size, u32 checksum);
+
+static int backup_log_sector(struct bow_context *bc)
+{
+ struct bow_range *first_br, *free_br;
+ struct bvec_iter bi_iter;
+ u32 checksum = 0;
+ int ret;
+
+ first_br = container_of(rb_first(&bc->ranges), struct bow_range, node);
+
+ if (first_br->type != SECTOR0) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ if (range_size(first_br) != bc->block_size) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ free_br = find_free_range(bc);
+ /* No space left - return this error to userspace */
+ if (!free_br)
+ return -ENOSPC;
+ bi_iter.bi_sector = free_br->sector;
+ bi_iter.bi_size = bc->block_size;
+ ret = split_range(bc, &free_br, &bi_iter);
+ if (ret)
+ return ret;
+ if (bi_iter.bi_size != bc->block_size) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ ret = copy_data(bc, first_br, free_br, &checksum);
+ if (ret)
+ return ret;
+
+ bc->log_sector->count = 0;
+ bc->log_sector->sequence++;
+ ret = add_log_entry(bc, first_br->sector, free_br->sector,
+ range_size(first_br), checksum);
+ if (ret)
+ return ret;
+
+ set_type(bc, &free_br, BACKUP);
+ return 0;
+}
+
+static int add_log_entry(struct bow_context *bc, sector_t source, sector_t dest,
+ unsigned int size, u32 checksum)
+{
+ struct dm_buffer *sector_buffer;
+ u8 *sector;
+
+ if (sizeof(struct log_sector)
+ + sizeof(struct log_entry) * (bc->log_sector->count + 1)
+ > bc->block_size) {
+ int ret = backup_log_sector(bc);
+
+ if (ret)
+ return ret;
+ }
+
+ sector = dm_bufio_new(bc->bufio, 0, §or_buffer);
+ if (IS_ERR(sector)) {
+ DMERR("Cannot write boot sector");
+ dm_bufio_release(sector_buffer);
+ return -ENOSPC;
+ }
+
+ bc->log_sector->entries[bc->log_sector->count].source = source;
+ bc->log_sector->entries[bc->log_sector->count].dest = dest;
+ bc->log_sector->entries[bc->log_sector->count].size = size;
+ bc->log_sector->entries[bc->log_sector->count].checksum = checksum;
+ bc->log_sector->count++;
+
+ memcpy(sector, bc->log_sector, bc->block_size);
+ dm_bufio_mark_buffer_dirty(sector_buffer);
+ dm_bufio_release(sector_buffer);
+ dm_bufio_write_dirty_buffers(bc->bufio);
+ return 0;
+}
+
+static int prepare_log(struct bow_context *bc)
+{
+ struct bow_range *free_br, *first_br;
+ struct bvec_iter bi_iter;
+ u32 checksum = 0;
+ int ret;
+
+ /* Carve out first sector as log sector */
+ first_br = container_of(rb_first(&bc->ranges), struct bow_range, node);
+ if (first_br->type != UNCHANGED) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ if (range_size(first_br) < bc->block_size) {
+ WARN_ON(1);
+ return -EIO;
+ }
+ bi_iter.bi_sector = 0;
+ bi_iter.bi_size = bc->block_size;
+ ret = split_range(bc, &first_br, &bi_iter);
+ if (ret)
+ return ret;
+ first_br->type = SECTOR0;
+ if (range_size(first_br) != bc->block_size) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+ /* Find free sector for active sector0 reads/writes */
+ free_br = find_free_range(bc);
+ if (!free_br)
+ return -ENOSPC;
+ bi_iter.bi_sector = free_br->sector;
+ bi_iter.bi_size = bc->block_size;
+ ret = split_range(bc, &free_br, &bi_iter);
+ if (ret)
+ return ret;
+ free_br->type = SECTOR0_CURRENT;
+
+ /* Copy data */
+ ret = copy_data(bc, first_br, free_br, NULL);
+ if (ret)
+ return ret;
+
+ bc->log_sector->sector0 = free_br->sector;
+
+ /* Find free sector to back up original sector zero */
+ free_br = find_free_range(bc);
+ if (!free_br)
+ return -ENOSPC;
+ bi_iter.bi_sector = free_br->sector;
+ bi_iter.bi_size = bc->block_size;
+ ret = split_range(bc, &free_br, &bi_iter);
+ if (ret)
+ return ret;
+
+ /* Back up */
+ ret = copy_data(bc, first_br, free_br, &checksum);
+ if (ret)
+ return ret;
+
+ /*
+ * Set up our replacement boot sector - it will get written when we
+ * add the first log entry, which we do immediately
+ */
+ bc->log_sector->magic = MAGIC;
+ bc->log_sector->header_version = HEADER_VERSION;
+ bc->log_sector->header_size = sizeof(*bc->log_sector);
+ bc->log_sector->block_size = bc->block_size;
+ bc->log_sector->count = 0;
+ bc->log_sector->sequence = 0;
+
+ /* Add log entry */
+ ret = add_log_entry(bc, first_br->sector, free_br->sector,
+ range_size(first_br), checksum);
+ if (ret)
+ return ret;
+
+ set_type(bc, &free_br, BACKUP);
+ return 0;
+}
+
+static struct bow_range *find_sector0_current(struct bow_context *bc)
+{
+ struct bvec_iter bi_iter;
+
+ bi_iter.bi_sector = bc->log_sector->sector0;
+ bi_iter.bi_size = bc->block_size;
+ return find_first_overlapping_range(&bc->ranges, &bi_iter);
+}
+
+/****** sysfs interface functions ******/
+
+static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct bow_context *bc = container_of(kobj, struct bow_context,
+ kobj_holder.kobj);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&bc->state));
+}
+
+static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct bow_context *bc = container_of(kobj, struct bow_context,
+ kobj_holder.kobj);
+ enum state state, original_state;
+ int ret;
+
+ state = buf[0] - '0';
+ if (state < TRIM || state > COMMITTED) {
+ DMERR("State value %d out of range", state);
+ return -EINVAL;
+ }
+
+ mutex_lock(&bc->ranges_lock);
+ original_state = atomic_read(&bc->state);
+ if (state != original_state + 1) {
+ DMERR("Invalid state change from %d to %d",
+ original_state, state);
+ ret = -EINVAL;
+ goto bad;
+ }
+
+ DMINFO("Switching to state %s", state == CHECKPOINT ? "Checkpoint"
+ : state == COMMITTED ? "Committed" : "Unknown");
+
+ if (state == CHECKPOINT) {
+ ret = prepare_log(bc);
+ if (ret) {
+ DMERR("Failed to switch to checkpoint state");
+ goto bad;
+ }
+ } else if (state == COMMITTED) {
+ struct bow_range *br = find_sector0_current(bc);
+ struct bow_range *sector0_br =
+ container_of(rb_first(&bc->ranges), struct bow_range,
+ node);
+
+ ret = copy_data(bc, br, sector0_br, 0);
+ if (ret) {
+ DMERR("Failed to switch to committed state");
+ goto bad;
+ }
+ }
+ atomic_inc(&bc->state);
+ ret = count;
+
+bad:
+ mutex_unlock(&bc->ranges_lock);
+ return ret;
+}
+
+static ssize_t free_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct bow_context *bc = container_of(kobj, struct bow_context,
+ kobj_holder.kobj);
+ u64 trims_total;
+
+ mutex_lock(&bc->ranges_lock);
+ trims_total = bc->trims_total;
+ mutex_unlock(&bc->ranges_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", trims_total);
+}
+
+static struct kobj_attribute attr_state = __ATTR_RW(state);
+static struct kobj_attribute attr_free = __ATTR_RO(free);
+
+static struct attribute *bow_attrs[] = {
+ &attr_state.attr,
+ &attr_free.attr,
+ NULL
+};
+
+static struct kobj_type bow_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_attrs = bow_attrs,
+ .release = dm_kobject_release
+};
+
+/****** constructor/destructor ******/
+
+static void dm_bow_dtr(struct dm_target *ti)
+{
+ struct bow_context *bc = (struct bow_context *) ti->private;
+ struct kobject *kobj;
+
+ while (rb_first(&bc->ranges)) {
+ struct bow_range *br = container_of(rb_first(&bc->ranges),
+ struct bow_range, node);
+
+ rb_erase(&br->node, &bc->ranges);
+ kfree(br);
+ }
+ if (bc->workqueue)
+ destroy_workqueue(bc->workqueue);
+ if (bc->bufio)
+ dm_bufio_client_destroy(bc->bufio);
+
+ kobj = &bc->kobj_holder.kobj;
+ if (kobj->state_initialized) {
+ kobject_put(kobj);
+ wait_for_completion(dm_get_completion_from_kobject(kobj));
+ }
+
+ kfree(bc->log_sector);
+ kfree(bc);
+}
+
+static int dm_bow_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+{
+ struct bow_context *bc;
+ struct bow_range *br;
+ int ret;
+ struct mapped_device *md = dm_table_get_md(ti->table);
+
+ if (argc != 1) {
+ ti->error = "Invalid argument count";
+ return -EINVAL;
+ }
+
+ bc = kzalloc(sizeof(*bc), GFP_KERNEL);
+ if (!bc) {
+ ti->error = "Cannot allocate bow context";
+ return -ENOMEM;
+ }
+
+ ti->num_flush_bios = 1;
+ ti->num_discard_bios = 1;
+ ti->num_write_same_bios = 1;
+ ti->private = bc;
+
+ ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
+ &bc->dev);
+ if (ret) {
+ ti->error = "Device lookup failed";
+ goto bad;
+ }
+
+ if (bc->dev->bdev->bd_queue->limits.max_discard_sectors == 0) {
+ bc->dev->bdev->bd_queue->limits.discard_granularity = 1 << 12;
+ bc->dev->bdev->bd_queue->limits.max_hw_discard_sectors = 1 << 15;
+ bc->dev->bdev->bd_queue->limits.max_discard_sectors = 1 << 15;
+ bc->forward_trims = false;
+ } else {
+ bc->forward_trims = true;
+ }
+
+ bc->block_size = bc->dev->bdev->bd_queue->limits.logical_block_size;
+ bc->block_shift = ilog2(bc->block_size);
+ bc->log_sector = kzalloc(bc->block_size, GFP_KERNEL);
+ if (!bc->log_sector) {
+ ti->error = "Cannot allocate log sector";
+ goto bad;
+ }
+
+ init_completion(&bc->kobj_holder.completion);
+ ret = kobject_init_and_add(&bc->kobj_holder.kobj, &bow_ktype,
+ &disk_to_dev(dm_disk(md))->kobj, "%s",
+ "bow");
+ if (ret) {
+ ti->error = "Cannot create sysfs node";
+ goto bad;
+ }
+
+ mutex_init(&bc->ranges_lock);
+ bc->ranges = RB_ROOT;
+ bc->bufio = dm_bufio_client_create(bc->dev->bdev, bc->block_size, 1, 0,
+ NULL, NULL);
+ if (IS_ERR(bc->bufio)) {
+ ti->error = "Cannot initialize dm-bufio";
+ ret = PTR_ERR(bc->bufio);
+ bc->bufio = NULL;
+ goto bad;
+ }
+
+ bc->workqueue = alloc_workqueue("dm-bow",
+ WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM
+ | WQ_UNBOUND, num_online_cpus());
+ if (!bc->workqueue) {
+ ti->error = "Cannot allocate workqueue";
+ ret = -ENOMEM;
+ goto bad;
+ }
+
+ INIT_LIST_HEAD(&bc->trimmed_list);
+
+ br = kzalloc(sizeof(*br), GFP_KERNEL);
+ if (!br) {
+ ti->error = "Cannot allocate ranges";
+ ret = -ENOMEM;
+ goto bad;
+ }
+
+ br->sector = ti->len;
+ br->type = TOP;
+ rb_link_node(&br->node, NULL, &bc->ranges.rb_node);
+ rb_insert_color(&br->node, &bc->ranges);
+
+ br = kzalloc(sizeof(*br), GFP_KERNEL);
+ if (!br) {
+ ti->error = "Cannot allocate ranges";
+ ret = -ENOMEM;
+ goto bad;
+ }
+
+ br->sector = 0;
+ br->type = UNCHANGED;
+ rb_link_node(&br->node, bc->ranges.rb_node,
+ &bc->ranges.rb_node->rb_left);
+ rb_insert_color(&br->node, &bc->ranges);
+
+ ti->discards_supported = true;
+
+ return 0;
+
+bad:
+ dm_bow_dtr(ti);
+ return ret;
+}
+
+/****** Handle writes ******/
+
+static int prepare_unchanged_range(struct bow_context *bc, struct bow_range *br,
+ struct bvec_iter *bi_iter,
+ bool record_checksum)
+{
+ struct bow_range *backup_br;
+ struct bvec_iter backup_bi;
+ sector_t log_source, log_dest;
+ unsigned int log_size;
+ u32 checksum = 0;
+ int ret;
+ int original_type;
+ sector_t sector0;
+
+ /* Find a free range */
+ backup_br = find_free_range(bc);
+ if (!backup_br)
+ return -ENOSPC;
+
+ /* Carve out a backup range. This may be smaller than the br given */
+ backup_bi.bi_sector = backup_br->sector;
+ backup_bi.bi_size = min(range_size(backup_br), (u64) bi_iter->bi_size);
+ ret = split_range(bc, &backup_br, &backup_bi);
+ if (ret)
+ return ret;
+
+ /*
+ * Carve out a changed range. This will not be smaller than the backup
+ * br since the backup br is smaller than the source range and iterator
+ */
+ bi_iter->bi_size = backup_bi.bi_size;
+ ret = split_range(bc, &br, bi_iter);
+ if (ret)
+ return ret;
+ if (range_size(br) != range_size(backup_br)) {
+ WARN_ON(1);
+ return -EIO;
+ }
+
+
+ /* Copy data over */
+ ret = copy_data(bc, br, backup_br, record_checksum ? &checksum : NULL);
+ if (ret)
+ return ret;
+
+ /* Add an entry to the log */
+ log_source = br->sector;
+ log_dest = backup_br->sector;
+ log_size = range_size(br);
+
+ /*
+ * Set the types. Note that since set_type also amalgamates ranges
+ * we have to set both sectors to their final type before calling
+ * set_type on either
+ */
+ original_type = br->type;
+ sector0 = backup_br->sector;
+ bc->trims_total -= range_size(backup_br);
+ if (backup_br->type == TRIMMED)
+ list_del(&backup_br->trimmed_list);
+ backup_br->type = br->type == SECTOR0_CURRENT ? SECTOR0_CURRENT
+ : BACKUP;
+ br->type = CHANGED;
+ set_type(bc, &backup_br, backup_br->type);
+
+ /*
+ * Add the log entry after marking the backup sector, since adding a log
+ * can cause another backup
+ */
+ ret = add_log_entry(bc, log_source, log_dest, log_size, checksum);
+ if (ret) {
+ br->type = original_type;
+ return ret;
+ }
+
+ /* Now it is safe to mark this backup successful */
+ if (original_type == SECTOR0_CURRENT)
+ bc->log_sector->sector0 = sector0;
+
+ set_type(bc, &br, br->type);
+ return ret;
+}
+
+static int prepare_free_range(struct bow_context *bc, struct bow_range *br,
+ struct bvec_iter *bi_iter)
+{
+ int ret;
+
+ ret = split_range(bc, &br, bi_iter);
+ if (ret)
+ return ret;
+ set_type(bc, &br, CHANGED);
+ return 0;
+}
+
+static int prepare_changed_range(struct bow_context *bc, struct bow_range *br,
+ struct bvec_iter *bi_iter)
+{
+ /* Nothing to do ... */
+ return 0;
+}
+
+static int prepare_one_range(struct bow_context *bc,
+ struct bvec_iter *bi_iter)
+{
+ struct bow_range *br = find_first_overlapping_range(&bc->ranges,
+ bi_iter);
+ switch (br->type) {
+ case CHANGED:
+ return prepare_changed_range(bc, br, bi_iter);
+
+ case TRIMMED:
+ return prepare_free_range(bc, br, bi_iter);
+
+ case UNCHANGED:
+ case BACKUP:
+ return prepare_unchanged_range(bc, br, bi_iter, true);
+
+ /*
+ * We cannot track the checksum for the active sector0, since it
+ * may change at any point.
+ */
+ case SECTOR0_CURRENT:
+ return prepare_unchanged_range(bc, br, bi_iter, false);
+
+ case SECTOR0: /* Handled in the dm_bow_map */
+ case TOP: /* Illegal - top is off the end of the device */
+ default:
+ WARN_ON(1);
+ return -EIO;
+ }
+}
+
+struct write_work {
+ struct work_struct work;
+ struct bow_context *bc;
+ struct bio *bio;
+};
+
+static void bow_write(struct work_struct *work)
+{
+ struct write_work *ww = container_of(work, struct write_work, work);
+ struct bow_context *bc = ww->bc;
+ struct bio *bio = ww->bio;
+ struct bvec_iter bi_iter = bio->bi_iter;
+ int ret = 0;
+
+ kfree(ww);
+
+ mutex_lock(&bc->ranges_lock);
+ do {
+ ret = prepare_one_range(bc, &bi_iter);
+ bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE;
+ bi_iter.bi_size = bio->bi_iter.bi_size
+ - (bi_iter.bi_sector - bio->bi_iter.bi_sector)
+ * SECTOR_SIZE;
+ } while (!ret && bi_iter.bi_size);
+
+ mutex_unlock(&bc->ranges_lock);
+
+ if (!ret) {
+ bio->bi_bdev = bc->dev->bdev;
+ submit_bio(bio);
+ } else {
+ DMERR("Write failure with error %d", -ret);
+ bio->bi_error = ret;
+ bio_endio(bio);
+ }
+}
+
+static int queue_write(struct bow_context *bc, struct bio *bio)
+{
+ struct write_work *ww = kmalloc(sizeof(*ww), GFP_NOIO | __GFP_NORETRY
+ | __GFP_NOMEMALLOC | __GFP_NOWARN);
+ if (!ww) {
+ DMERR("Failed to allocate write_work");
+ return -ENOMEM;
+ }
+
+ INIT_WORK(&ww->work, bow_write);
+ ww->bc = bc;
+ ww->bio = bio;
+ queue_work(bc->workqueue, &ww->work);
+ return DM_MAPIO_SUBMITTED;
+}
+
+static int handle_sector0(struct bow_context *bc, struct bio *bio)
+{
+ int ret = DM_MAPIO_REMAPPED;
+
+ if (bio->bi_iter.bi_size > bc->block_size) {
+ struct bio * split = bio_split(bio,
+ bc->block_size >> SECTOR_SHIFT,
+ GFP_NOIO,
+ fs_bio_set);
+ if (!split) {
+ DMERR("Failed to split bio");
+ bio->bi_error = -ENOMEM;
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+ }
+
+ bio_chain(split, bio);
+ split->bi_iter.bi_sector = bc->log_sector->sector0;
+ split->bi_bdev = bc->dev->bdev;
+ submit_bio(split);
+
+ if (bio_data_dir(bio) == WRITE)
+ ret = queue_write(bc, bio);
+ } else {
+ bio->bi_iter.bi_sector = bc->log_sector->sector0;
+ }
+
+ return ret;
+}
+
+static int add_trim(struct bow_context *bc, struct bio *bio)
+{
+ struct bow_range *br;
+ struct bvec_iter bi_iter = bio->bi_iter;
+
+ DMDEBUG("add_trim: %llu, %u",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size);
+
+ do {
+ br = find_first_overlapping_range(&bc->ranges, &bi_iter);
+
+ switch (br->type) {
+ case UNCHANGED:
+ if (!split_range(bc, &br, &bi_iter))
+ set_type(bc, &br, TRIMMED);
+ break;
+
+ case TRIMMED:
+ /* Nothing to do */
+ break;
+
+ default:
+ /* No other case is legal in TRIM state */
+ WARN_ON(true);
+ break;
+ }
+
+ bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE;
+ bi_iter.bi_size = bio->bi_iter.bi_size
+ - (bi_iter.bi_sector - bio->bi_iter.bi_sector)
+ * SECTOR_SIZE;
+
+ } while (bi_iter.bi_size);
+
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+}
+
+static int remove_trim(struct bow_context *bc, struct bio *bio)
+{
+ struct bow_range *br;
+ struct bvec_iter bi_iter = bio->bi_iter;
+
+ DMDEBUG("remove_trim: %llu, %u",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size);
+
+ do {
+ br = find_first_overlapping_range(&bc->ranges, &bi_iter);
+
+ switch (br->type) {
+ case UNCHANGED:
+ /* Nothing to do */
+ break;
+
+ case TRIMMED:
+ if (!split_range(bc, &br, &bi_iter))
+ set_type(bc, &br, UNCHANGED);
+ break;
+
+ default:
+ /* No other case is legal in TRIM state */
+ WARN_ON(true);
+ break;
+ }
+
+ bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE;
+ bi_iter.bi_size = bio->bi_iter.bi_size
+ - (bi_iter.bi_sector - bio->bi_iter.bi_sector)
+ * SECTOR_SIZE;
+
+ } while (bi_iter.bi_size);
+
+ return DM_MAPIO_REMAPPED;
+}
+
+int remap_unless_illegal_trim(struct bow_context *bc, struct bio *bio)
+{
+ if (!bc->forward_trims && bio_op(bio) == REQ_OP_DISCARD) {
+ bio->bi_error = -EINVAL;
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+ } else {
+ bio->bi_bdev = bc->dev->bdev;
+ return DM_MAPIO_REMAPPED;
+ }
+}
+
+/****** dm interface ******/
+
+static int dm_bow_map(struct dm_target *ti, struct bio *bio)
+{
+ int ret = DM_MAPIO_REMAPPED;
+ struct bow_context *bc = ti->private;
+
+ if (likely(bc->state.counter == COMMITTED))
+ return remap_unless_illegal_trim(bc, bio);
+
+ if (bio_data_dir(bio) == READ && bio->bi_iter.bi_sector != 0)
+ return remap_unless_illegal_trim(bc, bio);
+
+ if (atomic_read(&bc->state) != COMMITTED) {
+ enum state state;
+
+ mutex_lock(&bc->ranges_lock);
+ state = atomic_read(&bc->state);
+ if (state == TRIM) {
+ if (bio_op(bio) == REQ_OP_DISCARD)
+ ret = add_trim(bc, bio);
+ else if (bio_data_dir(bio) == WRITE)
+ ret = remove_trim(bc, bio);
+ else
+ /* pass-through */;
+ } else if (state == CHECKPOINT) {
+ if (bio->bi_iter.bi_sector == 0)
+ ret = handle_sector0(bc, bio);
+ else if (bio_data_dir(bio) == WRITE)
+ ret = queue_write(bc, bio);
+ else
+ /* pass-through */;
+ } else {
+ /* pass-through */
+ }
+ mutex_unlock(&bc->ranges_lock);
+ }
+
+ if (ret == DM_MAPIO_REMAPPED)
+ return remap_unless_illegal_trim(bc, bio);
+
+ return ret;
+}
+
+static void dm_bow_tablestatus(struct dm_target *ti, char *result,
+ unsigned int maxlen)
+{
+ char *end = result + maxlen;
+ struct bow_context *bc = ti->private;
+ struct rb_node *i;
+ int trimmed_list_length = 0;
+ int trimmed_range_count = 0;
+ struct bow_range *br;
+
+ if (maxlen == 0)
+ return;
+ result[0] = 0;
+
+ list_for_each_entry(br, &bc->trimmed_list, trimmed_list)
+ if (br->type == TRIMMED) {
+ ++trimmed_list_length;
+ } else {
+ scnprintf(result, end - result,
+ "ERROR: non-trimmed entry in trimmed_list");
+ return;
+ }
+
+ if (!rb_first(&bc->ranges)) {
+ scnprintf(result, end - result, "ERROR: Empty ranges");
+ return;
+ }
+
+ if (container_of(rb_first(&bc->ranges), struct bow_range, node)
+ ->sector) {
+ scnprintf(result, end - result,
+ "ERROR: First range does not start at sector 0");
+ return;
+ }
+
+ for (i = rb_first(&bc->ranges); i; i = rb_next(i)) {
+ struct bow_range *br = container_of(i, struct bow_range, node);
+
+ result += scnprintf(result, end - result, "%s: %llu",
+ readable_type[br->type],
+ (unsigned long long)br->sector);
+ if (result >= end)
+ return;
+
+ result += scnprintf(result, end - result, "\n");
+ if (result >= end)
+ return;
+
+ if (br->type == TRIMMED)
+ ++trimmed_range_count;
+
+ if (br->type == TOP) {
+ if (br->sector != ti->len) {
+ scnprintf(result, end - result,
+ "\nERROR: Top sector is incorrect");
+ }
+
+ if (&br->node != rb_last(&bc->ranges)) {
+ scnprintf(result, end - result,
+ "\nERROR: Top sector is not last");
+ }
+
+ break;
+ }
+
+ if (!rb_next(i)) {
+ scnprintf(result, end - result,
+ "\nERROR: Last range not of type TOP");
+ return;
+ }
+
+ if (br->sector > range_top(br)) {
+ scnprintf(result, end - result,
+ "\nERROR: sectors out of order");
+ return;
+ }
+ }
+
+ if (trimmed_range_count != trimmed_list_length)
+ scnprintf(result, end - result,
+ "\nERROR: not all trimmed ranges in trimmed list");
+}
+
+static void dm_bow_status(struct dm_target *ti, status_type_t type,
+ unsigned int status_flags, char *result,
+ unsigned int maxlen)
+{
+ switch (type) {
+ case STATUSTYPE_INFO:
+ if (maxlen)
+ result[0] = 0;
+ break;
+
+ case STATUSTYPE_TABLE:
+ dm_bow_tablestatus(ti, result, maxlen);
+ break;
+ }
+}
+
+int dm_bow_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+ fmode_t *mode)
+{
+ struct bow_context *bc = ti->private;
+ struct dm_dev *dev = bc->dev;
+
+ *bdev = dev->bdev;
+ /* Only pass ioctls through if the device sizes match exactly. */
+ return ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+static int dm_bow_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data)
+{
+ struct bow_context *bc = ti->private;
+
+ return fn(ti, bc->dev, 0, ti->len, data);
+}
+
+static struct target_type bow_target = {
+ .name = "bow",
+ .version = {1, 1, 1},
+ .module = THIS_MODULE,
+ .ctr = dm_bow_ctr,
+ .dtr = dm_bow_dtr,
+ .map = dm_bow_map,
+ .status = dm_bow_status,
+ .prepare_ioctl = dm_bow_prepare_ioctl,
+ .iterate_devices = dm_bow_iterate_devices,
+};
+
+int __init dm_bow_init(void)
+{
+ int r = dm_register_target(&bow_target);
+
+ if (r < 0)
+ DMERR("registering bow failed %d", r);
+ return r;
+}
+
+void dm_bow_exit(void)
+{
+ dm_unregister_target(&bow_target);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(dm_bow_init);
+module_exit(dm_bow_exit);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index c837def..48bb5a8 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -32,7 +32,8 @@
#define DM_BUFIO_MEMORY_PERCENT 2
#define DM_BUFIO_VMALLOC_PERCENT 25
-#define DM_BUFIO_WRITEBACK_PERCENT 75
+#define DM_BUFIO_WRITEBACK_RATIO 3
+#define DM_BUFIO_LOW_WATERMARK_RATIO 16
/*
* Check buffer ages in this interval (seconds)
@@ -137,10 +138,12 @@ enum data_mode {
struct dm_buffer {
struct rb_node node;
struct list_head lru_list;
+ struct list_head global_list;
sector_t block;
void *data;
enum data_mode data_mode;
unsigned char list_mode; /* LIST_* */
+ unsigned accessed;
unsigned hold_count;
int read_error;
int write_error;
@@ -209,7 +212,11 @@ static unsigned long dm_bufio_cache_size;
*/
static unsigned long dm_bufio_cache_size_latch;
-static DEFINE_SPINLOCK(param_spinlock);
+static DEFINE_SPINLOCK(global_spinlock);
+
+static LIST_HEAD(global_queue);
+
+static unsigned long global_num = 0;
/*
* Buffers are freed after this timeout
@@ -226,11 +233,6 @@ static unsigned long dm_bufio_current_allocated;
/*----------------------------------------------------------------*/
/*
- * Per-client cache: dm_bufio_cache_size / dm_bufio_client_count
- */
-static unsigned long dm_bufio_cache_size_per_client;
-
-/*
* The current number of clients.
*/
static int dm_bufio_client_count;
@@ -241,11 +243,15 @@ static int dm_bufio_client_count;
static LIST_HEAD(dm_bufio_all_clients);
/*
- * This mutex protects dm_bufio_cache_size_latch,
- * dm_bufio_cache_size_per_client and dm_bufio_client_count
+ * This mutex protects dm_bufio_cache_size_latch and dm_bufio_client_count
*/
static DEFINE_MUTEX(dm_bufio_clients_lock);
+static struct workqueue_struct *dm_bufio_wq;
+static struct delayed_work dm_bufio_cleanup_old_work;
+static struct work_struct dm_bufio_replacement_work;
+
+
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
static void buffer_record_stack(struct dm_buffer *b)
{
@@ -306,15 +312,23 @@ static void __remove(struct dm_bufio_client *c, struct dm_buffer *b)
/*----------------------------------------------------------------*/
-static void adjust_total_allocated(enum data_mode data_mode, long diff)
+static void adjust_total_allocated(struct dm_buffer *b, bool unlink)
{
+ enum data_mode data_mode;
+ long diff;
+
static unsigned long * const class_ptr[DATA_MODE_LIMIT] = {
&dm_bufio_allocated_kmem_cache,
&dm_bufio_allocated_get_free_pages,
&dm_bufio_allocated_vmalloc,
};
- spin_lock(¶m_spinlock);
+ data_mode = b->data_mode;
+ diff = (long)b->c->block_size;
+ if (unlink)
+ diff = -diff;
+
+ spin_lock(&global_spinlock);
*class_ptr[data_mode] += diff;
@@ -323,7 +337,19 @@ static void adjust_total_allocated(enum data_mode data_mode, long diff)
if (dm_bufio_current_allocated > dm_bufio_peak_allocated)
dm_bufio_peak_allocated = dm_bufio_current_allocated;
- spin_unlock(¶m_spinlock);
+ b->accessed = 1;
+
+ if (!unlink) {
+ list_add(&b->global_list, &global_queue);
+ global_num++;
+ if (dm_bufio_current_allocated > dm_bufio_cache_size)
+ queue_work(dm_bufio_wq, &dm_bufio_replacement_work);
+ } else {
+ list_del(&b->global_list);
+ global_num--;
+ }
+
+ spin_unlock(&global_spinlock);
}
/*
@@ -344,9 +370,6 @@ static void __cache_size_refresh(void)
dm_bufio_default_cache_size);
dm_bufio_cache_size_latch = dm_bufio_default_cache_size;
}
-
- dm_bufio_cache_size_per_client = dm_bufio_cache_size_latch /
- (dm_bufio_client_count ? : 1);
}
/*
@@ -453,8 +476,6 @@ static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask)
return NULL;
}
- adjust_total_allocated(b->data_mode, (long)c->block_size);
-
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
memset(&b->stack_trace, 0, sizeof(b->stack_trace));
#endif
@@ -468,8 +489,6 @@ static void free_buffer(struct dm_buffer *b)
{
struct dm_bufio_client *c = b->c;
- adjust_total_allocated(b->data_mode, -(long)c->block_size);
-
free_buffer_data(c, b->data, b->data_mode);
kfree(b);
}
@@ -487,6 +506,8 @@ static void __link_buffer(struct dm_buffer *b, sector_t block, int dirty)
list_add(&b->lru_list, &c->lru[dirty]);
__insert(b->c, b);
b->last_accessed = jiffies;
+
+ adjust_total_allocated(b, false);
}
/*
@@ -501,6 +522,8 @@ static void __unlink_buffer(struct dm_buffer *b)
c->n_buffers[b->list_mode]--;
__remove(b->c, b);
list_del(&b->lru_list);
+
+ adjust_total_allocated(b, true);
}
/*
@@ -510,6 +533,8 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
{
struct dm_bufio_client *c = b->c;
+ b->accessed = 1;
+
BUG_ON(!c->n_buffers[b->list_mode]);
c->n_buffers[b->list_mode]--;
@@ -923,33 +948,6 @@ static void __write_dirty_buffers_async(struct dm_bufio_client *c, int no_wait,
}
/*
- * Get writeback threshold and buffer limit for a given client.
- */
-static void __get_memory_limit(struct dm_bufio_client *c,
- unsigned long *threshold_buffers,
- unsigned long *limit_buffers)
-{
- unsigned long buffers;
-
- if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) {
- if (mutex_trylock(&dm_bufio_clients_lock)) {
- __cache_size_refresh();
- mutex_unlock(&dm_bufio_clients_lock);
- }
- }
-
- buffers = dm_bufio_cache_size_per_client >>
- (c->sectors_per_block_bits + SECTOR_SHIFT);
-
- if (buffers < c->minimum_buffers)
- buffers = c->minimum_buffers;
-
- *limit_buffers = buffers;
- *threshold_buffers = mult_frac(buffers,
- DM_BUFIO_WRITEBACK_PERCENT, 100);
-}
-
-/*
* Check if we're over watermark.
* If we are over threshold_buffers, start freeing buffers.
* If we're over "limit_buffers", block until we get under the limit.
@@ -957,23 +955,7 @@ static void __get_memory_limit(struct dm_bufio_client *c,
static void __check_watermark(struct dm_bufio_client *c,
struct list_head *write_list)
{
- unsigned long threshold_buffers, limit_buffers;
-
- __get_memory_limit(c, &threshold_buffers, &limit_buffers);
-
- while (c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY] >
- limit_buffers) {
-
- struct dm_buffer *b = __get_unclaimed_buffer(c);
-
- if (!b)
- return;
-
- __free_buffer_wake(b);
- cond_resched();
- }
-
- if (c->n_buffers[LIST_DIRTY] > threshold_buffers)
+ if (c->n_buffers[LIST_DIRTY] > c->n_buffers[LIST_CLEAN] * DM_BUFIO_WRITEBACK_RATIO)
__write_dirty_buffers_async(c, 1, write_list);
}
@@ -1814,6 +1796,74 @@ static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
dm_bufio_unlock(c);
}
+static void do_global_cleanup(struct work_struct *w)
+{
+ struct dm_bufio_client *locked_client = NULL;
+ struct dm_bufio_client *current_client;
+ struct dm_buffer *b;
+ unsigned spinlock_hold_count;
+ unsigned long threshold = dm_bufio_cache_size -
+ dm_bufio_cache_size / DM_BUFIO_LOW_WATERMARK_RATIO;
+ unsigned long loops = global_num * 2;
+
+ mutex_lock(&dm_bufio_clients_lock);
+
+ while (1) {
+ cond_resched();
+
+ spin_lock(&global_spinlock);
+ if (unlikely(dm_bufio_current_allocated <= threshold))
+ break;
+
+ spinlock_hold_count = 0;
+get_next:
+ if (!loops--)
+ break;
+ if (unlikely(list_empty(&global_queue)))
+ break;
+ b = list_entry(global_queue.prev, struct dm_buffer, global_list);
+
+ if (b->accessed) {
+ b->accessed = 0;
+ list_move(&b->global_list, &global_queue);
+ if (likely(++spinlock_hold_count < 16))
+ goto get_next;
+ spin_unlock(&global_spinlock);
+ continue;
+ }
+
+ current_client = b->c;
+ if (unlikely(current_client != locked_client)) {
+ if (locked_client)
+ dm_bufio_unlock(locked_client);
+
+ if (!dm_bufio_trylock(current_client)) {
+ spin_unlock(&global_spinlock);
+ dm_bufio_lock(current_client);
+ locked_client = current_client;
+ continue;
+ }
+
+ locked_client = current_client;
+ }
+
+ spin_unlock(&global_spinlock);
+
+ if (unlikely(!__try_evict_buffer(b, GFP_KERNEL))) {
+ spin_lock(&global_spinlock);
+ list_move(&b->global_list, &global_queue);
+ spin_unlock(&global_spinlock);
+ }
+ }
+
+ spin_unlock(&global_spinlock);
+
+ if (locked_client)
+ dm_bufio_unlock(locked_client);
+
+ mutex_unlock(&dm_bufio_clients_lock);
+}
+
static void cleanup_old_buffers(void)
{
unsigned long max_age_hz = get_max_age_hz();
@@ -1829,14 +1879,11 @@ static void cleanup_old_buffers(void)
mutex_unlock(&dm_bufio_clients_lock);
}
-static struct workqueue_struct *dm_bufio_wq;
-static struct delayed_work dm_bufio_work;
-
static void work_fn(struct work_struct *w)
{
cleanup_old_buffers();
- queue_delayed_work(dm_bufio_wq, &dm_bufio_work,
+ queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
DM_BUFIO_WORK_TIMER_SECS * HZ);
}
@@ -1881,8 +1928,9 @@ static int __init dm_bufio_init(void)
if (!dm_bufio_wq)
return -ENOMEM;
- INIT_DELAYED_WORK(&dm_bufio_work, work_fn);
- queue_delayed_work(dm_bufio_wq, &dm_bufio_work,
+ INIT_DELAYED_WORK(&dm_bufio_cleanup_old_work, work_fn);
+ INIT_WORK(&dm_bufio_replacement_work, do_global_cleanup);
+ queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
DM_BUFIO_WORK_TIMER_SECS * HZ);
return 0;
@@ -1896,7 +1944,8 @@ static void __exit dm_bufio_exit(void)
int bug = 0;
int i;
- cancel_delayed_work_sync(&dm_bufio_work);
+ cancel_delayed_work_sync(&dm_bufio_cleanup_old_work);
+ flush_workqueue(dm_bufio_wq);
destroy_workqueue(dm_bufio_wq);
for (i = 0; i < ARRAY_SIZE(dm_bufio_caches); i++)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 0aedd0e..45a1f92 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -115,6 +115,10 @@ struct iv_tcw_private {
enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
+enum cipher_flags {
+ CRYPT_IV_LARGE_SECTORS, /* Calculate IV from sector_size, not 512B sectors */
+};
+
/*
* The fields in here must be read only after initialization.
*/
@@ -150,11 +154,14 @@ struct crypt_config {
} iv_gen_private;
sector_t iv_offset;
unsigned int iv_size;
+ unsigned short int sector_size;
+ unsigned char sector_shift;
/* ESSIV: struct crypto_cipher *essiv_tfm */
void *iv_private;
struct crypto_skcipher **tfms;
unsigned tfms_count;
+ unsigned long cipher_flags;
/*
* Layout of each crypto request:
@@ -484,6 +491,11 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti,
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
+ if (cc->sector_size != (1 << SECTOR_SHIFT)) {
+ ti->error = "Unsupported sector size for LMK";
+ return -EINVAL;
+ }
+
lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(lmk->hash_tfm)) {
ti->error = "Error initializing LMK hash";
@@ -633,6 +645,11 @@ static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti,
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
+ if (cc->sector_size != (1 << SECTOR_SHIFT)) {
+ ti->error = "Unsupported sector size for TCW";
+ return -EINVAL;
+ }
+
if (cc->key_size <= (cc->iv_size + TCW_WHITENING_SIZE)) {
ti->error = "Wrong key size for TCW";
return -EINVAL;
@@ -846,21 +863,27 @@ static int crypt_convert_block(struct crypt_config *cc,
u8 *iv;
int r;
+ /* Reject unexpected unaligned bio. */
+ if (unlikely(bv_in.bv_len & (cc->sector_size - 1)))
+ return -EIO;
+
dmreq = dmreq_of_req(cc, req);
iv = iv_of_dmreq(cc, dmreq);
dmreq->iv_sector = ctx->cc_sector;
+ if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags))
+ dmreq->iv_sector >>= cc->sector_shift;
dmreq->ctx = ctx;
sg_init_table(&dmreq->sg_in, 1);
- sg_set_page(&dmreq->sg_in, bv_in.bv_page, 1 << SECTOR_SHIFT,
+ sg_set_page(&dmreq->sg_in, bv_in.bv_page, cc->sector_size,
bv_in.bv_offset);
sg_init_table(&dmreq->sg_out, 1);
- sg_set_page(&dmreq->sg_out, bv_out.bv_page, 1 << SECTOR_SHIFT,
+ sg_set_page(&dmreq->sg_out, bv_out.bv_page, cc->sector_size,
bv_out.bv_offset);
- bio_advance_iter(ctx->bio_in, &ctx->iter_in, 1 << SECTOR_SHIFT);
- bio_advance_iter(ctx->bio_out, &ctx->iter_out, 1 << SECTOR_SHIFT);
+ bio_advance_iter(ctx->bio_in, &ctx->iter_in, cc->sector_size);
+ bio_advance_iter(ctx->bio_out, &ctx->iter_out, cc->sector_size);
if (cc->iv_gen_ops) {
r = cc->iv_gen_ops->generator(cc, iv, dmreq);
@@ -869,7 +892,7 @@ static int crypt_convert_block(struct crypt_config *cc,
}
skcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out,
- 1 << SECTOR_SHIFT, iv);
+ cc->sector_size, iv);
if (bio_data_dir(ctx->bio_in) == WRITE)
r = crypto_skcipher_encrypt(req);
@@ -919,6 +942,7 @@ static void crypt_free_req(struct crypt_config *cc,
static int crypt_convert(struct crypt_config *cc,
struct convert_context *ctx)
{
+ unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
int r;
atomic_set(&ctx->cc_pending, 1);
@@ -926,7 +950,6 @@ static int crypt_convert(struct crypt_config *cc,
while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
crypt_alloc_req(cc, ctx);
-
atomic_inc(&ctx->cc_pending);
r = crypt_convert_block(cc, ctx, ctx->req);
@@ -946,14 +969,14 @@ static int crypt_convert(struct crypt_config *cc,
*/
case -EINPROGRESS:
ctx->req = NULL;
- ctx->cc_sector++;
+ ctx->cc_sector += sector_step;
continue;
/*
* The request was already processed (synchronously).
*/
case 0:
atomic_dec(&ctx->cc_pending);
- ctx->cc_sector++;
+ ctx->cc_sector += sector_step;
cond_resched();
continue;
@@ -1468,6 +1491,13 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode)
}
}
+ /*
+ * dm-crypt performance can vary greatly depending on which crypto
+ * algorithm implementation is used. Help people debug performance
+ * problems by logging the ->cra_driver_name.
+ */
+ DMINFO("%s using implementation \"%s\"", ciphermode,
+ crypto_skcipher_alg(any_tfm(cc))->base.cra_driver_name);
return 0;
}
@@ -1743,7 +1773,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
char dummy;
static struct dm_arg _args[] = {
- {0, 3, "Invalid number of feature args"},
+ {0, 5, "Invalid number of feature args"},
};
if (argc < 5) {
@@ -1759,6 +1789,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
return -ENOMEM;
}
cc->key_size = key_size;
+ cc->sector_size = (1 << SECTOR_SHIFT);
+ cc->sector_shift = 0;
ti->private = cc;
ret = crypt_ctr_cipher(ti, argv[0], argv[1]);
@@ -1810,7 +1842,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
mutex_init(&cc->bio_alloc_lock);
ret = -EINVAL;
- if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
+ if ((sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) ||
+ (tmpll & ((cc->sector_size >> SECTOR_SHIFT) - 1))) {
ti->error = "Invalid iv_offset sector";
goto bad;
}
@@ -1858,6 +1891,21 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
else if (!strcasecmp(opt_string, "submit_from_crypt_cpus"))
set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
+ else if (sscanf(opt_string, "sector_size:%hu%c",
+ &cc->sector_size, &dummy) == 1) {
+ if (cc->sector_size < (1 << SECTOR_SHIFT) ||
+ cc->sector_size > 4096 ||
+ (cc->sector_size & (cc->sector_size - 1))) {
+ ti->error = "Invalid feature value for sector_size";
+ goto bad;
+ }
+ if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) {
+ ti->error = "Device size is not multiple of sector_size feature";
+ goto bad;
+ }
+ cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT;
+ } else if (!strcasecmp(opt_string, "iv_large_sectors"))
+ set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags);
else {
ti->error = "Invalid feature arguments";
goto bad;
@@ -1866,16 +1914,24 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
}
ret = -ENOMEM;
- cc->io_queue = alloc_workqueue("kcryptd_io", WQ_MEM_RECLAIM, 1);
+ cc->io_queue = alloc_workqueue("kcryptd_io",
+ WQ_HIGHPRI |
+ WQ_MEM_RECLAIM,
+ 1);
if (!cc->io_queue) {
ti->error = "Couldn't create kcryptd io queue";
goto bad;
}
if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
- cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1);
+ cc->crypt_queue = alloc_workqueue("kcryptd",
+ WQ_HIGHPRI |
+ WQ_MEM_RECLAIM, 1);
else
- cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
+ cc->crypt_queue = alloc_workqueue("kcryptd",
+ WQ_HIGHPRI |
+ WQ_MEM_RECLAIM |
+ WQ_UNBOUND,
num_online_cpus());
if (!cc->crypt_queue) {
ti->error = "Couldn't create kcryptd queue";
@@ -1930,6 +1986,16 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
bio_data_dir(bio) == WRITE)
dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+ /*
+ * Ensure that bio is a multiple of internal sector encryption size
+ * and is aligned to this size as defined in IO hints.
+ */
+ if (unlikely((bio->bi_iter.bi_sector & ((cc->sector_size >> SECTOR_SHIFT) - 1)) != 0))
+ return -EIO;
+
+ if (unlikely(bio->bi_iter.bi_size & (cc->sector_size - 1)))
+ return -EIO;
+
io = dm_per_bio_data(bio, cc->per_bio_data_size);
crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
io->ctx.req = (struct skcipher_request *)(io + 1);
@@ -1970,6 +2036,8 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
num_feature_args += !!ti->num_discard_bios;
num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags);
num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
+ num_feature_args += cc->sector_size != (1 << SECTOR_SHIFT);
+ num_feature_args += test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags);
if (num_feature_args) {
DMEMIT(" %d", num_feature_args);
if (ti->num_discard_bios)
@@ -1978,6 +2046,10 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
DMEMIT(" same_cpu_crypt");
if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags))
DMEMIT(" submit_from_crypt_cpus");
+ if (cc->sector_size != (1 << SECTOR_SHIFT))
+ DMEMIT(" sector_size:%d", cc->sector_size);
+ if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags))
+ DMEMIT(" iv_large_sectors");
}
break;
@@ -2060,6 +2132,8 @@ static int crypt_iterate_devices(struct dm_target *ti,
static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
+ struct crypt_config *cc = ti->private;
+
/*
* Unfortunate constraint that is required to avoid the potential
* for exceeding underlying device's max_segments limits -- due to
@@ -2067,11 +2141,17 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
* bio that are not as physically contiguous as the original bio.
*/
limits->max_segment_size = PAGE_SIZE;
+
+ limits->logical_block_size =
+ max_t(unsigned short, limits->logical_block_size, cc->sector_size);
+ limits->physical_block_size =
+ max_t(unsigned, limits->physical_block_size, cc->sector_size);
+ limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size);
}
static struct target_type crypt_target = {
.name = "crypt",
- .version = {1, 14, 1},
+ .version = {1, 17, 0},
.module = THIS_MODULE,
.ctr = crypt_ctr,
.dtr = crypt_dtr,
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 836a280..f4fd4a4 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1922,6 +1922,45 @@ void dm_interface_exit(void)
dm_hash_exit();
}
+
+/**
+ * dm_ioctl_export - Permanently export a mapped device via the ioctl interface
+ * @md: Pointer to mapped_device
+ * @name: Buffer (size DM_NAME_LEN) for name
+ * @uuid: Buffer (size DM_UUID_LEN) for uuid or NULL if not desired
+ */
+int dm_ioctl_export(struct mapped_device *md, const char *name,
+ const char *uuid)
+{
+ int r = 0;
+ struct hash_cell *hc;
+
+ if (!md) {
+ r = -ENXIO;
+ goto out;
+ }
+
+ /* The name and uuid can only be set once. */
+ mutex_lock(&dm_hash_cells_mutex);
+ hc = dm_get_mdptr(md);
+ mutex_unlock(&dm_hash_cells_mutex);
+ if (hc) {
+ DMERR("%s: already exported", dm_device_name(md));
+ r = -ENXIO;
+ goto out;
+ }
+
+ r = dm_hash_insert(name, uuid, md);
+ if (r) {
+ DMERR("%s: could not bind to '%s'", dm_device_name(md), name);
+ goto out;
+ }
+
+ /* Let udev know we've changed. */
+ dm_kobject_uevent(md, KOBJ_CHANGE, dm_get_event_nr(md));
+out:
+ return r;
+}
/**
* dm_copy_name_and_uuid - Copy mapped device name & uuid into supplied buffers
* @md: Pointer to mapped_device
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 4788b0b..4ad62d6 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -25,7 +25,7 @@ struct linear_c {
/*
* Construct a linear mapping: <dev_path> <offset>
*/
-static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct linear_c *lc;
unsigned long long tmp;
@@ -66,14 +66,16 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
kfree(lc);
return ret;
}
+EXPORT_SYMBOL_GPL(dm_linear_ctr);
-static void linear_dtr(struct dm_target *ti)
+void dm_linear_dtr(struct dm_target *ti)
{
struct linear_c *lc = (struct linear_c *) ti->private;
dm_put_device(ti, lc->dev);
kfree(lc);
}
+EXPORT_SYMBOL_GPL(dm_linear_dtr);
static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
{
@@ -92,14 +94,15 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
linear_map_sector(ti, bio->bi_iter.bi_sector);
}
-static int linear_map(struct dm_target *ti, struct bio *bio)
+int dm_linear_map(struct dm_target *ti, struct bio *bio)
{
linear_map_bio(ti, bio);
return DM_MAPIO_REMAPPED;
}
+EXPORT_SYMBOL_GPL(dm_linear_map);
-static void linear_status(struct dm_target *ti, status_type_t type,
+void dm_linear_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct linear_c *lc = (struct linear_c *) ti->private;
@@ -115,8 +118,9 @@ static void linear_status(struct dm_target *ti, status_type_t type,
break;
}
}
+EXPORT_SYMBOL_GPL(dm_linear_status);
-static int linear_prepare_ioctl(struct dm_target *ti,
+int dm_linear_prepare_ioctl(struct dm_target *ti,
struct block_device **bdev, fmode_t *mode)
{
struct linear_c *lc = (struct linear_c *) ti->private;
@@ -132,16 +136,18 @@ static int linear_prepare_ioctl(struct dm_target *ti,
return 1;
return 0;
}
+EXPORT_SYMBOL_GPL(dm_linear_prepare_ioctl);
-static int linear_iterate_devices(struct dm_target *ti,
+int dm_linear_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct linear_c *lc = ti->private;
return fn(ti, lc->dev, lc->start, ti->len, data);
}
+EXPORT_SYMBOL_GPL(dm_linear_iterate_devices);
-static long linear_direct_access(struct dm_target *ti, sector_t sector,
+long dm_linear_direct_access(struct dm_target *ti, sector_t sector,
void **kaddr, pfn_t *pfn, long size)
{
struct linear_c *lc = ti->private;
@@ -158,18 +164,19 @@ static long linear_direct_access(struct dm_target *ti, sector_t sector,
return ret;
}
+EXPORT_SYMBOL_GPL(dm_linear_direct_access);
static struct target_type linear_target = {
.name = "linear",
.version = {1, 3, 0},
.module = THIS_MODULE,
- .ctr = linear_ctr,
- .dtr = linear_dtr,
- .map = linear_map,
- .status = linear_status,
- .prepare_ioctl = linear_prepare_ioctl,
- .iterate_devices = linear_iterate_devices,
- .direct_access = linear_direct_access,
+ .ctr = dm_linear_ctr,
+ .dtr = dm_linear_dtr,
+ .map = dm_linear_map,
+ .status = dm_linear_status,
+ .prepare_ioctl = dm_linear_prepare_ioctl,
+ .iterate_devices = dm_linear_iterate_devices,
+ .direct_access = dm_linear_direct_access,
};
int __init dm_linear_init(void)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5d120c3..e49a622 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -11,6 +11,7 @@
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
+#include <linux/mount.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/slab.h>
diff --git a/drivers/md/dm-verity-avb.c b/drivers/md/dm-verity-avb.c
new file mode 100644
index 0000000..89f95e4
--- /dev/null
+++ b/drivers/md/dm-verity-avb.c
@@ -0,0 +1,229 @@
+/*
+ * Copyright (C) 2017 Google.
+ *
+ * This file is released under the GPLv2.
+ *
+ * Based on drivers/md/dm-verity-chromeos.c
+ */
+
+#include <linux/device-mapper.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+
+#define DM_MSG_PREFIX "verity-avb"
+
+/* Set via module parameters. */
+static char avb_vbmeta_device[64];
+static char avb_invalidate_on_error[4];
+
+static void invalidate_vbmeta_endio(struct bio *bio)
+{
+ if (bio->bi_error)
+ DMERR("invalidate_vbmeta_endio: error %d", bio->bi_error);
+ complete(bio->bi_private);
+}
+
+static int invalidate_vbmeta_submit(struct bio *bio,
+ struct block_device *bdev,
+ int op, int access_last_sector,
+ struct page *page)
+{
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ bio->bi_private = &wait;
+ bio->bi_end_io = invalidate_vbmeta_endio;
+ bio->bi_bdev = bdev;
+ bio_set_op_attrs(bio, op, REQ_SYNC | REQ_NOIDLE);
+
+ bio->bi_iter.bi_sector = 0;
+ if (access_last_sector) {
+ sector_t last_sector;
+
+ last_sector = (i_size_read(bdev->bd_inode)>>SECTOR_SHIFT) - 1;
+ bio->bi_iter.bi_sector = last_sector;
+ }
+ if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
+ DMERR("invalidate_vbmeta_submit: bio_add_page error");
+ return -EIO;
+ }
+
+ submit_bio(bio);
+ /* Wait up to 2 seconds for completion or fail. */
+ if (!wait_for_completion_timeout(&wait, msecs_to_jiffies(2000)))
+ return -EIO;
+ return 0;
+}
+
+static int invalidate_vbmeta(dev_t vbmeta_devt)
+{
+ int ret = 0;
+ struct block_device *bdev;
+ struct bio *bio;
+ struct page *page;
+ fmode_t dev_mode;
+ /* Ensure we do synchronous unblocked I/O. We may also need
+ * sync_bdev() on completion, but it really shouldn't.
+ */
+ int access_last_sector = 0;
+
+ DMINFO("invalidate_vbmeta: acting on device %d:%d",
+ MAJOR(vbmeta_devt), MINOR(vbmeta_devt));
+
+ /* First we open the device for reading. */
+ dev_mode = FMODE_READ | FMODE_EXCL;
+ bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode,
+ invalidate_vbmeta);
+ if (IS_ERR(bdev)) {
+ DMERR("invalidate_kernel: could not open device for reading");
+ dev_mode = 0;
+ ret = -ENOENT;
+ goto failed_to_read;
+ }
+
+ bio = bio_alloc(GFP_NOIO, 1);
+ if (!bio) {
+ ret = -ENOMEM;
+ goto failed_bio_alloc;
+ }
+
+ page = alloc_page(GFP_NOIO);
+ if (!page) {
+ ret = -ENOMEM;
+ goto failed_to_alloc_page;
+ }
+
+ access_last_sector = 0;
+ ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_READ,
+ access_last_sector, page);
+ if (ret) {
+ DMERR("invalidate_vbmeta: error reading");
+ goto failed_to_submit_read;
+ }
+
+ /* We have a page. Let's make sure it looks right. */
+ if (memcmp("AVB0", page_address(page), 4) == 0) {
+ /* Stamp it. */
+ memcpy(page_address(page), "AVE0", 4);
+ DMINFO("invalidate_vbmeta: found vbmeta partition");
+ } else {
+ /* Could be this is on a AVB footer, check. Also, since the
+ * AVB footer is in the last 64 bytes, adjust for the fact that
+ * we're dealing with 512-byte sectors.
+ */
+ size_t offset = (1<<SECTOR_SHIFT) - 64;
+
+ access_last_sector = 1;
+ ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_READ,
+ access_last_sector, page);
+ if (ret) {
+ DMERR("invalidate_vbmeta: error reading");
+ goto failed_to_submit_read;
+ }
+ if (memcmp("AVBf", page_address(page) + offset, 4) != 0) {
+ DMERR("invalidate_vbmeta on non-vbmeta partition");
+ ret = -EINVAL;
+ goto invalid_header;
+ }
+ /* Stamp it. */
+ memcpy(page_address(page) + offset, "AVE0", 4);
+ DMINFO("invalidate_vbmeta: found vbmeta footer partition");
+ }
+
+ /* Now rewrite the changed page - the block dev was being
+ * changed on read. Let's reopen here.
+ */
+ blkdev_put(bdev, dev_mode);
+ dev_mode = FMODE_WRITE | FMODE_EXCL;
+ bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode,
+ invalidate_vbmeta);
+ if (IS_ERR(bdev)) {
+ DMERR("invalidate_vbmeta: could not open device for writing");
+ dev_mode = 0;
+ ret = -ENOENT;
+ goto failed_to_write;
+ }
+
+ /* We re-use the same bio to do the write after the read. Need to reset
+ * it to initialize bio->bi_remaining.
+ */
+ bio_reset(bio);
+
+ ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_WRITE,
+ access_last_sector, page);
+ if (ret) {
+ DMERR("invalidate_vbmeta: error writing");
+ goto failed_to_submit_write;
+ }
+
+ DMERR("invalidate_vbmeta: completed.");
+ ret = 0;
+failed_to_submit_write:
+failed_to_write:
+invalid_header:
+ __free_page(page);
+failed_to_submit_read:
+ /* Technically, we'll leak a page with the pending bio, but
+ * we're about to reboot anyway.
+ */
+failed_to_alloc_page:
+ bio_put(bio);
+failed_bio_alloc:
+ if (dev_mode)
+ blkdev_put(bdev, dev_mode);
+failed_to_read:
+ return ret;
+}
+
+void dm_verity_avb_error_handler(void)
+{
+ dev_t dev;
+
+ DMINFO("AVB error handler called for %s", avb_vbmeta_device);
+
+ if (strcmp(avb_invalidate_on_error, "yes") != 0) {
+ DMINFO("Not configured to invalidate");
+ return;
+ }
+
+ if (avb_vbmeta_device[0] == '\0') {
+ DMERR("avb_vbmeta_device parameter not set");
+ goto fail_no_dev;
+ }
+
+ dev = name_to_dev_t(avb_vbmeta_device);
+ if (!dev) {
+ DMERR("No matching partition for device: %s",
+ avb_vbmeta_device);
+ goto fail_no_dev;
+ }
+
+ invalidate_vbmeta(dev);
+
+fail_no_dev:
+ ;
+}
+
+static int __init dm_verity_avb_init(void)
+{
+ DMINFO("AVB error handler initialized with vbmeta device: %s",
+ avb_vbmeta_device);
+ return 0;
+}
+
+static void __exit dm_verity_avb_exit(void)
+{
+}
+
+module_init(dm_verity_avb_init);
+module_exit(dm_verity_avb_exit);
+
+MODULE_AUTHOR("David Zeuthen <zeuthen@google.com>");
+MODULE_DESCRIPTION("AVB-specific error handler for dm-verity");
+MODULE_LICENSE("GPL");
+
+/* Declare parameter with no module prefix */
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "androidboot.vbmeta."
+module_param_string(device, avb_vbmeta_device, sizeof(avb_vbmeta_device), 0);
+module_param_string(invalidate_on_error, avb_invalidate_on_error,
+ sizeof(avb_invalidate_on_error), 0);
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 1640298..330db48 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -11,6 +11,7 @@
#include "dm-verity-fec.h"
#include <linux/math64.h>
+#include <linux/sysfs.h>
#define DM_MSG_PREFIX "verity-fec"
@@ -175,9 +176,11 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
if (r < 0 && neras)
DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
v->data_dev->name, (unsigned long long)rsb, r);
- else if (r > 0)
+ else if (r > 0) {
DMWARN_LIMIT("%s: FEC %llu: corrected %d errors",
v->data_dev->name, (unsigned long long)rsb, r);
+ atomic_add_unless(&v->fec->corrected, 1, INT_MAX);
+ }
return r;
}
@@ -556,6 +559,7 @@ unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz,
void verity_fec_dtr(struct dm_verity *v)
{
struct dm_verity_fec *f = v->fec;
+ struct kobject *kobj = &f->kobj_holder.kobj;
if (!verity_fec_is_enabled(v))
goto out;
@@ -573,6 +577,12 @@ void verity_fec_dtr(struct dm_verity *v)
if (f->dev)
dm_put_device(v->ti, f->dev);
+
+ if (kobj->state_initialized) {
+ kobject_put(kobj);
+ wait_for_completion(dm_get_completion_from_kobject(kobj));
+ }
+
out:
kfree(f);
v->fec = NULL;
@@ -661,6 +671,28 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
return 0;
}
+static ssize_t corrected_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct dm_verity_fec *f = container_of(kobj, struct dm_verity_fec,
+ kobj_holder.kobj);
+
+ return sprintf(buf, "%d\n", atomic_read(&f->corrected));
+}
+
+static struct kobj_attribute attr_corrected = __ATTR_RO(corrected);
+
+static struct attribute *fec_attrs[] = {
+ &attr_corrected.attr,
+ NULL
+};
+
+static struct kobj_type fec_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_attrs = fec_attrs,
+ .release = dm_kobject_release
+};
+
/*
* Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr.
*/
@@ -684,8 +716,10 @@ int verity_fec_ctr_alloc(struct dm_verity *v)
*/
int verity_fec_ctr(struct dm_verity *v)
{
+ int r;
struct dm_verity_fec *f = v->fec;
struct dm_target *ti = v->ti;
+ struct mapped_device *md = dm_table_get_md(ti->table);
u64 hash_blocks;
if (!verity_fec_is_enabled(v)) {
@@ -693,6 +727,16 @@ int verity_fec_ctr(struct dm_verity *v)
return 0;
}
+ /* Create a kobject and sysfs attributes */
+ init_completion(&f->kobj_holder.completion);
+
+ r = kobject_init_and_add(&f->kobj_holder.kobj, &fec_ktype,
+ &disk_to_dev(dm_disk(md))->kobj, "%s", "fec");
+ if (r) {
+ ti->error = "Cannot create kobject";
+ return r;
+ }
+
/*
* FEC is computed over data blocks, possible metadata, and
* hash blocks. In other words, FEC covers total of fec_blocks
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index bb31ce8..4db0cae 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -12,6 +12,8 @@
#ifndef DM_VERITY_FEC_H
#define DM_VERITY_FEC_H
+#include "dm.h"
+#include "dm-core.h"
#include "dm-verity.h"
#include <linux/rslib.h>
@@ -51,6 +53,8 @@ struct dm_verity_fec {
mempool_t *extra_pool; /* mempool for extra buffers */
mempool_t *output_pool; /* mempool for output */
struct kmem_cache *cache; /* cache for buffers */
+ atomic_t corrected; /* corrected errors */
+ struct dm_kobject_holder kobj_holder; /* for sysfs attributes */
};
/* per-bio data */
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 727f9e5..7fb1d49 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/reboot.h>
+#include <linux/vmalloc.h>
#define DM_MSG_PREFIX "verity"
@@ -32,6 +33,7 @@
#define DM_VERITY_OPT_LOGGING "ignore_corruption"
#define DM_VERITY_OPT_RESTART "restart_on_corruption"
#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks"
+#define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once"
#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC)
@@ -233,8 +235,12 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
if (v->mode == DM_VERITY_MODE_LOGGING)
return 0;
- if (v->mode == DM_VERITY_MODE_RESTART)
+ if (v->mode == DM_VERITY_MODE_RESTART) {
+#ifdef CONFIG_DM_VERITY_AVB
+ dm_verity_avb_error_handler();
+#endif
kernel_restart("dm-verity device corrupted");
+ }
return 1;
}
@@ -395,6 +401,18 @@ static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
}
/*
+ * Moves the bio iter one data block forward.
+ */
+static inline void verity_bv_skip_block(struct dm_verity *v,
+ struct dm_verity_io *io,
+ struct bvec_iter *iter)
+{
+ struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
+
+ bio_advance_iter(bio, iter, 1 << v->data_dev_block_bits);
+}
+
+/*
* Verify one "dm_verity_io" structure.
*/
static int verity_verify_io(struct dm_verity_io *io)
@@ -406,9 +424,16 @@ static int verity_verify_io(struct dm_verity_io *io)
for (b = 0; b < io->n_blocks; b++) {
int r;
+ sector_t cur_block = io->block + b;
struct shash_desc *desc = verity_io_hash_desc(v, io);
- r = verity_hash_for_block(v, io, io->block + b,
+ if (v->validated_blocks &&
+ likely(test_bit(cur_block, v->validated_blocks))) {
+ verity_bv_skip_block(v, io, &io->iter);
+ continue;
+ }
+
+ r = verity_hash_for_block(v, io, cur_block,
verity_io_want_digest(v, io),
&is_zero);
if (unlikely(r < 0))
@@ -441,13 +466,16 @@ static int verity_verify_io(struct dm_verity_io *io)
return r;
if (likely(memcmp(verity_io_real_digest(v, io),
- verity_io_want_digest(v, io), v->digest_size) == 0))
+ verity_io_want_digest(v, io), v->digest_size) == 0)) {
+ if (v->validated_blocks)
+ set_bit(cur_block, v->validated_blocks);
continue;
+ }
else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
- io->block + b, NULL, &start) == 0)
+ cur_block, NULL, &start) == 0)
continue;
else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
- io->block + b))
+ cur_block))
return -EIO;
}
@@ -551,7 +579,7 @@ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
* Bio map function. It allocates dm_verity_io structure and bio vector and
* fills them. Then it issues prefetches and the I/O.
*/
-static int verity_map(struct dm_target *ti, struct bio *bio)
+int verity_map(struct dm_target *ti, struct bio *bio)
{
struct dm_verity *v = ti->private;
struct dm_verity_io *io;
@@ -592,11 +620,12 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_SUBMITTED;
}
+EXPORT_SYMBOL_GPL(verity_map);
/*
* Status: V (valid) or C (corruption found)
*/
-static void verity_status(struct dm_target *ti, status_type_t type,
+void verity_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct dm_verity *v = ti->private;
@@ -633,6 +662,8 @@ static void verity_status(struct dm_target *ti, status_type_t type,
args += DM_VERITY_OPTS_FEC;
if (v->zero_digest)
args++;
+ if (v->validated_blocks)
+ args++;
if (!args)
return;
DMEMIT(" %u", args);
@@ -651,12 +682,15 @@ static void verity_status(struct dm_target *ti, status_type_t type,
}
if (v->zero_digest)
DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
+ if (v->validated_blocks)
+ DMEMIT(" " DM_VERITY_OPT_AT_MOST_ONCE);
sz = verity_fec_status_table(v, sz, result, maxlen);
break;
}
}
+EXPORT_SYMBOL_GPL(verity_status);
-static int verity_prepare_ioctl(struct dm_target *ti,
+int verity_prepare_ioctl(struct dm_target *ti,
struct block_device **bdev, fmode_t *mode)
{
struct dm_verity *v = ti->private;
@@ -668,16 +702,18 @@ static int verity_prepare_ioctl(struct dm_target *ti,
return 1;
return 0;
}
+EXPORT_SYMBOL_GPL(verity_prepare_ioctl);
-static int verity_iterate_devices(struct dm_target *ti,
+int verity_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct dm_verity *v = ti->private;
return fn(ti, v->data_dev, v->data_start, ti->len, data);
}
+EXPORT_SYMBOL_GPL(verity_iterate_devices);
-static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
+void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct dm_verity *v = ti->private;
@@ -689,8 +725,9 @@ static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
blk_limits_io_min(limits, limits->logical_block_size);
}
+EXPORT_SYMBOL_GPL(verity_io_hints);
-static void verity_dtr(struct dm_target *ti)
+void verity_dtr(struct dm_target *ti)
{
struct dm_verity *v = ti->private;
@@ -700,6 +737,7 @@ static void verity_dtr(struct dm_target *ti)
if (v->bufio)
dm_bufio_client_destroy(v->bufio);
+ vfree(v->validated_blocks);
kfree(v->salt);
kfree(v->root_digest);
kfree(v->zero_digest);
@@ -719,6 +757,27 @@ static void verity_dtr(struct dm_target *ti)
kfree(v);
}
+EXPORT_SYMBOL_GPL(verity_dtr);
+
+static int verity_alloc_most_once(struct dm_verity *v)
+{
+ struct dm_target *ti = v->ti;
+
+ /* the bitset can only handle INT_MAX blocks */
+ if (v->data_blocks > INT_MAX) {
+ ti->error = "device too large to use check_at_most_once";
+ return -E2BIG;
+ }
+
+ v->validated_blocks = vzalloc(BITS_TO_LONGS(v->data_blocks) *
+ sizeof(unsigned long));
+ if (!v->validated_blocks) {
+ ti->error = "failed to allocate bitset for check_at_most_once";
+ return -ENOMEM;
+ }
+
+ return 0;
+}
static int verity_alloc_zero_digest(struct dm_verity *v)
{
@@ -789,6 +848,12 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
}
continue;
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_AT_MOST_ONCE)) {
+ r = verity_alloc_most_once(v);
+ if (r)
+ return r;
+ continue;
+
} else if (verity_is_fec_opt_arg(arg_name)) {
r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
if (r)
@@ -817,7 +882,7 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
* <digest>
* <salt> Hex string or "-" if no salt.
*/
-static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
+int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
struct dm_verity *v;
struct dm_arg_set as;
@@ -930,6 +995,15 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
v->tfm = NULL;
goto bad;
}
+
+ /*
+ * dm-verity performance can vary greatly depending on which hash
+ * algorithm implementation is used. Help people debug performance
+ * problems by logging the ->cra_driver_name.
+ */
+ DMINFO("%s using implementation \"%s\"", v->alg_name,
+ crypto_shash_alg(v->tfm)->base.cra_driver_name);
+
v->digest_size = crypto_shash_digestsize(v->tfm);
if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) {
ti->error = "Digest size too big";
@@ -981,6 +1055,14 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto bad;
}
+#ifdef CONFIG_DM_ANDROID_VERITY_AT_MOST_ONCE_DEFAULT_ENABLED
+ if (!v->validated_blocks) {
+ r = verity_alloc_most_once(v);
+ if (r)
+ goto bad;
+ }
+#endif
+
v->hash_per_block_bits =
__fls((1 << v->hash_dev_block_bits) / v->digest_size);
@@ -1053,10 +1135,11 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
return r;
}
+EXPORT_SYMBOL_GPL(verity_ctr);
static struct target_type verity_target = {
.name = "verity",
- .version = {1, 3, 0},
+ .version = {1, 4, 0},
.module = THIS_MODULE,
.ctr = verity_ctr,
.dtr = verity_dtr,
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index fb419f4..d216fc7 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -63,6 +63,7 @@ struct dm_verity {
sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
struct dm_verity_fec *fec; /* forward error correction */
+ unsigned long *validated_blocks; /* bitset blocks validated */
};
struct dm_verity_io {
@@ -126,4 +127,15 @@ extern int verity_hash(struct dm_verity *v, struct shash_desc *desc,
extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
sector_t block, u8 *digest, bool *is_zero);
+extern void verity_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen);
+extern int verity_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode);
+extern int verity_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data);
+extern void verity_io_hints(struct dm_target *ti, struct queue_limits *limits);
+extern void verity_dtr(struct dm_target *ti);
+extern int verity_ctr(struct dm_target *ti, unsigned argc, char **argv);
+extern int verity_map(struct dm_target *ti, struct bio *bio);
+extern void dm_verity_avb_error_handler(void);
#endif /* DM_VERITY_H */
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index f0aad08..ed25f30 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -80,8 +80,6 @@ void dm_set_md_type(struct mapped_device *md, unsigned type);
unsigned dm_get_md_type(struct mapped_device *md);
struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
-int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
-
/*
* To check the return value from dm_table_find_target().
*/
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0bfb77f..4e40a1a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5107,7 +5107,7 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data)
return NULL;
}
-static int add_named_array(const char *val, struct kernel_param *kp)
+static int add_named_array(const char *val, const struct kernel_param *kp)
{
/* val must be "md_*" where * is not all digits.
* We allocate an array with a large free minor number, and
@@ -9011,11 +9011,11 @@ static __exit void md_exit(void)
subsys_initcall(md_init);
module_exit(md_exit)
-static int get_ro(char *buffer, struct kernel_param *kp)
+static int get_ro(char *buffer, const struct kernel_param *kp)
{
return sprintf(buffer, "%d", start_readonly);
}
-static int set_ro(const char *val, struct kernel_param *kp)
+static int set_ro(const char *val, const struct kernel_param *kp)
{
return kstrtouint(val, 10, (unsigned int *)&start_readonly);
}
diff --git a/drivers/media/pci/tw686x/tw686x-core.c b/drivers/media/pci/tw686x/tw686x-core.c
index 71a0453..279d447 100644
--- a/drivers/media/pci/tw686x/tw686x-core.c
+++ b/drivers/media/pci/tw686x/tw686x-core.c
@@ -72,12 +72,12 @@ static const char *dma_mode_name(unsigned int mode)
}
}
-static int tw686x_dma_mode_get(char *buffer, struct kernel_param *kp)
+static int tw686x_dma_mode_get(char *buffer, const struct kernel_param *kp)
{
return sprintf(buffer, dma_mode_name(dma_mode));
}
-static int tw686x_dma_mode_set(const char *val, struct kernel_param *kp)
+static int tw686x_dma_mode_set(const char *val, const struct kernel_param *kp)
{
if (!strcasecmp(val, dma_mode_name(TW686X_DMA_MODE_MEMCPY)))
dma_mode = TW686X_DMA_MODE_MEMCPY;
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 9803135..94acf7c 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2206,7 +2206,7 @@ static int uvc_reset_resume(struct usb_interface *intf)
* Module parameters
*/
-static int uvc_clock_param_get(char *buffer, struct kernel_param *kp)
+static int uvc_clock_param_get(char *buffer, const struct kernel_param *kp)
{
if (uvc_clock_param == CLOCK_MONOTONIC)
return sprintf(buffer, "CLOCK_MONOTONIC");
@@ -2214,7 +2214,7 @@ static int uvc_clock_param_get(char *buffer, struct kernel_param *kp)
return sprintf(buffer, "CLOCK_REALTIME");
}
-static int uvc_clock_param_set(const char *val, struct kernel_param *kp)
+static int uvc_clock_param_set(const char *val, const struct kernel_param *kp)
{
if (strncasecmp(val, "clock_", strlen("clock_")) == 0)
val += strlen("clock_");
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 699e5f8..69eba2a 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2470,11 +2470,8 @@ struct v4l2_ioctl_info {
unsigned int ioctl;
u32 flags;
const char * const name;
- union {
- u32 offset;
- int (*func)(const struct v4l2_ioctl_ops *ops,
- struct file *file, void *fh, void *p);
- } u;
+ int (*func)(const struct v4l2_ioctl_ops *ops, struct file *file,
+ void *fh, void *p);
void (*debug)(const void *arg, bool write_only);
};
@@ -2482,25 +2479,21 @@ struct v4l2_ioctl_info {
#define INFO_FL_PRIO (1 << 0)
/* This control can be valid if the filehandle passes a control handler. */
#define INFO_FL_CTRL (1 << 1)
-/* This is a standard ioctl, no need for special code */
-#define INFO_FL_STD (1 << 2)
/* This is ioctl has its own function */
-#define INFO_FL_FUNC (1 << 3)
+#define INFO_FL_FUNC (1 << 2)
/* Queuing ioctl */
-#define INFO_FL_QUEUE (1 << 4)
+#define INFO_FL_QUEUE (1 << 3)
/* Zero struct from after the field to the end */
#define INFO_FL_CLEAR(v4l2_struct, field) \
((offsetof(struct v4l2_struct, field) + \
sizeof(((struct v4l2_struct *)0)->field)) << 16)
#define INFO_FL_CLEAR_MASK (_IOC_SIZEMASK << 16)
-#define IOCTL_INFO_STD(_ioctl, _vidioc, _debug, _flags) \
- [_IOC_NR(_ioctl)] = { \
- .ioctl = _ioctl, \
- .flags = _flags | INFO_FL_STD, \
- .name = #_ioctl, \
- .u.offset = offsetof(struct v4l2_ioctl_ops, _vidioc), \
- .debug = _debug, \
+#define DEFINE_IOCTL_STD_FNC(_vidioc) \
+ static int __v4l_ ## _vidioc ## _fnc( \
+ const struct v4l2_ioctl_ops *ops, \
+ struct file *file, void *fh, void *p) { \
+ return ops->_vidioc(file, fh, p); \
}
#define IOCTL_INFO_FNC(_ioctl, _func, _debug, _flags) \
@@ -2508,10 +2501,44 @@ struct v4l2_ioctl_info {
.ioctl = _ioctl, \
.flags = _flags | INFO_FL_FUNC, \
.name = #_ioctl, \
- .u.func = _func, \
+ .func = _func, \
.debug = _debug, \
}
+#define IOCTL_INFO_STD(_ioctl, _vidioc, _debug, _flags) \
+ IOCTL_INFO_FNC(_ioctl, __v4l_ ## _vidioc ## _fnc, _debug, _flags)
+
+DEFINE_IOCTL_STD_FNC(vidioc_g_fbuf)
+DEFINE_IOCTL_STD_FNC(vidioc_s_fbuf)
+DEFINE_IOCTL_STD_FNC(vidioc_expbuf)
+DEFINE_IOCTL_STD_FNC(vidioc_g_std)
+DEFINE_IOCTL_STD_FNC(vidioc_g_audio)
+DEFINE_IOCTL_STD_FNC(vidioc_s_audio)
+DEFINE_IOCTL_STD_FNC(vidioc_g_input)
+DEFINE_IOCTL_STD_FNC(vidioc_g_edid)
+DEFINE_IOCTL_STD_FNC(vidioc_s_edid)
+DEFINE_IOCTL_STD_FNC(vidioc_g_output)
+DEFINE_IOCTL_STD_FNC(vidioc_g_audout)
+DEFINE_IOCTL_STD_FNC(vidioc_s_audout)
+DEFINE_IOCTL_STD_FNC(vidioc_g_selection)
+DEFINE_IOCTL_STD_FNC(vidioc_s_selection)
+DEFINE_IOCTL_STD_FNC(vidioc_g_jpegcomp)
+DEFINE_IOCTL_STD_FNC(vidioc_s_jpegcomp)
+DEFINE_IOCTL_STD_FNC(vidioc_enumaudio)
+DEFINE_IOCTL_STD_FNC(vidioc_enumaudout)
+DEFINE_IOCTL_STD_FNC(vidioc_enum_framesizes)
+DEFINE_IOCTL_STD_FNC(vidioc_enum_frameintervals)
+DEFINE_IOCTL_STD_FNC(vidioc_g_enc_index)
+DEFINE_IOCTL_STD_FNC(vidioc_encoder_cmd)
+DEFINE_IOCTL_STD_FNC(vidioc_try_encoder_cmd)
+DEFINE_IOCTL_STD_FNC(vidioc_decoder_cmd)
+DEFINE_IOCTL_STD_FNC(vidioc_try_decoder_cmd)
+DEFINE_IOCTL_STD_FNC(vidioc_s_dv_timings)
+DEFINE_IOCTL_STD_FNC(vidioc_g_dv_timings)
+DEFINE_IOCTL_STD_FNC(vidioc_enum_dv_timings)
+DEFINE_IOCTL_STD_FNC(vidioc_query_dv_timings)
+DEFINE_IOCTL_STD_FNC(vidioc_dv_timings_cap)
+
static struct v4l2_ioctl_info v4l2_ioctls[] = {
IOCTL_INFO_FNC(VIDIOC_QUERYCAP, v4l_querycap, v4l_print_querycap, 0),
IOCTL_INFO_FNC(VIDIOC_ENUM_FMT, v4l_enum_fmt, v4l_print_fmtdesc, INFO_FL_CLEAR(v4l2_fmtdesc, type)),
@@ -2696,14 +2723,8 @@ static long __video_do_ioctl(struct file *file,
}
write_only = _IOC_DIR(cmd) == _IOC_WRITE;
- if (info->flags & INFO_FL_STD) {
- typedef int (*vidioc_op)(struct file *file, void *fh, void *p);
- const void *p = vfd->ioctl_ops;
- const vidioc_op *vidioc = p + info->u.offset;
-
- ret = (*vidioc)(file, fh, arg);
- } else if (info->flags & INFO_FL_FUNC) {
- ret = info->u.func(ops, file, fh, arg);
+ if (info->flags & INFO_FL_FUNC) {
+ ret = info->func(ops, file, fh, arg);
} else if (!ops->vidioc_default) {
ret = -ENOTTY;
} else {
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 89c7ed1..1cdab6d 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -99,7 +99,7 @@ module_param(mpt_channel_mapping, int, 0);
MODULE_PARM_DESC(mpt_channel_mapping, " Mapping id's to channels (default=0)");
static int mpt_debug_level;
-static int mpt_set_debug_level(const char *val, struct kernel_param *kp);
+static int mpt_set_debug_level(const char *val, const struct kernel_param *kp);
module_param_call(mpt_debug_level, mpt_set_debug_level, param_get_int,
&mpt_debug_level, 0600);
MODULE_PARM_DESC(mpt_debug_level,
@@ -242,7 +242,7 @@ pci_enable_io_access(struct pci_dev *pdev)
pci_write_config_word(pdev, PCI_COMMAND, command_reg);
}
-static int mpt_set_debug_level(const char *val, struct kernel_param *kp)
+static int mpt_set_debug_level(const char *val, const struct kernel_param *kp)
{
int ret = param_set_int(val, kp);
MPT_ADAPTER *ioc;
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 64971ba..9360e6e 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -766,6 +766,27 @@
An empty message will only clear the display at driver init time. Any other
printf()-formatted message is valid with newline and escape codes.
+config UID_SYS_STATS
+ bool "Per-UID statistics"
+ depends on PROFILING && TASK_XACCT && TASK_IO_ACCOUNTING
+ help
+ Per UID based cpu time statistics exported to /proc/uid_cputime
+ Per UID based io statistics exported to /proc/uid_io
+ Per UID based procstat control in /proc/uid_procstat
+
+config UID_SYS_STATS_DEBUG
+ bool "Per-TASK statistics"
+ depends on UID_SYS_STATS
+ default n
+ help
+ Per TASK based io statistics exported to /proc/uid_io
+
+config MEMORY_STATE_TIME
+ tristate "Memory freq/bandwidth time statistics"
+ depends on PROFILING
+ help
+ Memory time statistics exported to /sys/kernel/memory_state_time
+
source "drivers/misc/c2port/Kconfig"
source "drivers/misc/eeprom/Kconfig"
source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 2bf79ba..564406b 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -54,6 +54,9 @@
obj-$(CONFIG_CXL_BASE) += cxl/
obj-$(CONFIG_PANEL) += panel.o
+obj-$(CONFIG_UID_SYS_STATS) += uid_sys_stats.o
+obj-$(CONFIG_MEMORY_STATE_TIME) += memory_state_time.o
+
lkdtm-$(CONFIG_LKDTM) += lkdtm_core.o
lkdtm-$(CONFIG_LKDTM) += lkdtm_bugs.o
lkdtm-$(CONFIG_LKDTM) += lkdtm_heap.o
@@ -61,6 +64,7 @@
lkdtm-$(CONFIG_LKDTM) += lkdtm_rodata_objcopy.o
lkdtm-$(CONFIG_LKDTM) += lkdtm_usercopy.o
+CFLAGS_lkdtm_rodata.o += $(DISABLE_LTO)
KCOV_INSTRUMENT_lkdtm_rodata.o := n
OBJCOPYFLAGS :=
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index fc8cb85..9c5590e 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -1126,7 +1126,8 @@ static void kgdbts_put_char(u8 chr)
ts.run_test(0, chr);
}
-static int param_set_kgdbts_var(const char *kmessage, struct kernel_param *kp)
+static int param_set_kgdbts_var(const char *kmessage,
+ const struct kernel_param *kp)
{
size_t len = strlen(kmessage);
diff --git a/drivers/misc/lkdtm.h b/drivers/misc/lkdtm.h
index 6abc97b..296c711 100644
--- a/drivers/misc/lkdtm.h
+++ b/drivers/misc/lkdtm.h
@@ -21,6 +21,9 @@ void lkdtm_SPINLOCKUP(void);
void lkdtm_HUNG_TASK(void);
void lkdtm_ATOMIC_UNDERFLOW(void);
void lkdtm_ATOMIC_OVERFLOW(void);
+void lkdtm_CORRUPT_LIST_ADD(void);
+void lkdtm_CORRUPT_LIST_DEL(void);
+void lkdtm_CORRUPT_USER_DS(void);
/* lkdtm_heap.c */
void lkdtm_OVERWRITE_ALLOCATION(void);
diff --git a/drivers/misc/lkdtm_bugs.c b/drivers/misc/lkdtm_bugs.c
index 182ae18..da1cf47 100644
--- a/drivers/misc/lkdtm_bugs.c
+++ b/drivers/misc/lkdtm_bugs.c
@@ -5,7 +5,13 @@
* test source files.
*/
#include "lkdtm.h"
+#include <linux/list.h>
#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+struct lkdtm_list {
+ struct list_head node;
+};
/*
* Make sure our attempts to over run the kernel stack doesn't trigger
@@ -146,3 +152,75 @@ void lkdtm_ATOMIC_OVERFLOW(void)
pr_info("attempting bad atomic overflow\n");
atomic_inc(&over);
}
+
+void lkdtm_CORRUPT_LIST_ADD(void)
+{
+ /*
+ * Initially, an empty list via LIST_HEAD:
+ * test_head.next = &test_head
+ * test_head.prev = &test_head
+ */
+ LIST_HEAD(test_head);
+ struct lkdtm_list good, bad;
+ void *target[2] = { };
+ void *redirection = ⌖
+
+ pr_info("attempting good list addition\n");
+
+ /*
+ * Adding to the list performs these actions:
+ * test_head.next->prev = &good.node
+ * good.node.next = test_head.next
+ * good.node.prev = test_head
+ * test_head.next = good.node
+ */
+ list_add(&good.node, &test_head);
+
+ pr_info("attempting corrupted list addition\n");
+ /*
+ * In simulating this "write what where" primitive, the "what" is
+ * the address of &bad.node, and the "where" is the address held
+ * by "redirection".
+ */
+ test_head.next = redirection;
+ list_add(&bad.node, &test_head);
+
+ if (target[0] == NULL && target[1] == NULL)
+ pr_err("Overwrite did not happen, but no BUG?!\n");
+ else
+ pr_err("list_add() corruption not detected!\n");
+}
+
+void lkdtm_CORRUPT_LIST_DEL(void)
+{
+ LIST_HEAD(test_head);
+ struct lkdtm_list item;
+ void *target[2] = { };
+ void *redirection = ⌖
+
+ list_add(&item.node, &test_head);
+
+ pr_info("attempting good list removal\n");
+ list_del(&item.node);
+
+ pr_info("attempting corrupted list removal\n");
+ list_add(&item.node, &test_head);
+
+ /* As with the list_add() test above, this corrupts "next". */
+ item.node.next = redirection;
+ list_del(&item.node);
+
+ if (target[0] == NULL && target[1] == NULL)
+ pr_err("Overwrite did not happen, but no BUG?!\n");
+ else
+ pr_err("list_del() corruption not detected!\n");
+}
+
+void lkdtm_CORRUPT_USER_DS(void)
+{
+ pr_info("setting bad task size limit\n");
+ set_fs(KERNEL_DS);
+
+ /* Make sure we do not keep running with a KERNEL_DS! */
+ force_sig(SIGKILL, current);
+}
diff --git a/drivers/misc/lkdtm_core.c b/drivers/misc/lkdtm_core.c
index 035e51b..289c2d3 100644
--- a/drivers/misc/lkdtm_core.c
+++ b/drivers/misc/lkdtm_core.c
@@ -197,6 +197,9 @@ struct crashtype crashtypes[] = {
CRASHTYPE(EXCEPTION),
CRASHTYPE(LOOP),
CRASHTYPE(OVERFLOW),
+ CRASHTYPE(CORRUPT_LIST_ADD),
+ CRASHTYPE(CORRUPT_LIST_DEL),
+ CRASHTYPE(CORRUPT_USER_DS),
CRASHTYPE(CORRUPT_STACK),
CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE),
CRASHTYPE(OVERWRITE_ALLOCATION),
diff --git a/drivers/misc/memory_state_time.c b/drivers/misc/memory_state_time.c
new file mode 100644
index 0000000..ba94dcf
--- /dev/null
+++ b/drivers/misc/memory_state_time.c
@@ -0,0 +1,462 @@
+/* drivers/misc/memory_state_time.c
+ *
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/hashtable.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/memory-state-time.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/time.h>
+#include <linux/timekeeping.h>
+#include <linux/workqueue.h>
+
+#define KERNEL_ATTR_RO(_name) \
+static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+#define KERNEL_ATTR_RW(_name) \
+static struct kobj_attribute _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+#define FREQ_HASH_BITS 4
+DECLARE_HASHTABLE(freq_hash_table, FREQ_HASH_BITS);
+
+static DEFINE_MUTEX(mem_lock);
+
+#define TAG "memory_state_time"
+#define BW_NODE "/soc/memory-state-time"
+#define FREQ_TBL "freq-tbl"
+#define BW_TBL "bw-buckets"
+#define NUM_SOURCES "num-sources"
+
+#define LOWEST_FREQ 2
+
+static int curr_bw;
+static int curr_freq;
+static u32 *bw_buckets;
+static u32 *freq_buckets;
+static int num_freqs;
+static int num_buckets;
+static int registered_bw_sources;
+static u64 last_update;
+static bool init_success;
+static struct workqueue_struct *memory_wq;
+static u32 num_sources = 10;
+static int *bandwidths;
+
+struct freq_entry {
+ int freq;
+ u64 *buckets; /* Bandwidth buckets. */
+ struct hlist_node hash;
+};
+
+struct queue_container {
+ struct work_struct update_state;
+ int value;
+ u64 time_now;
+ int id;
+ struct mutex *lock;
+};
+
+static int find_bucket(int bw)
+{
+ int i;
+
+ if (bw_buckets != NULL) {
+ for (i = 0; i < num_buckets; i++) {
+ if (bw_buckets[i] > bw) {
+ pr_debug("Found bucket %d for bandwidth %d\n",
+ i, bw);
+ return i;
+ }
+ }
+ return num_buckets - 1;
+ }
+ return 0;
+}
+
+static u64 get_time_diff(u64 time_now)
+{
+ u64 ms;
+
+ ms = time_now - last_update;
+ last_update = time_now;
+ return ms;
+}
+
+static ssize_t show_stat_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ int i, j;
+ int len = 0;
+ struct freq_entry *freq_entry;
+
+ for (i = 0; i < num_freqs; i++) {
+ hash_for_each_possible(freq_hash_table, freq_entry, hash,
+ freq_buckets[i]) {
+ if (freq_entry->freq == freq_buckets[i]) {
+ len += scnprintf(buf + len, PAGE_SIZE - len,
+ "%d ", freq_buckets[i]);
+ if (len >= PAGE_SIZE)
+ break;
+ for (j = 0; j < num_buckets; j++) {
+ len += scnprintf(buf + len,
+ PAGE_SIZE - len,
+ "%llu ",
+ freq_entry->buckets[j]);
+ }
+ len += scnprintf(buf + len, PAGE_SIZE - len,
+ "\n");
+ }
+ }
+ }
+ pr_debug("Current Time: %llu\n", ktime_get_boot_ns());
+ return len;
+}
+KERNEL_ATTR_RO(show_stat);
+
+static void update_table(u64 time_now)
+{
+ struct freq_entry *freq_entry;
+
+ pr_debug("Last known bw %d freq %d\n", curr_bw, curr_freq);
+ hash_for_each_possible(freq_hash_table, freq_entry, hash, curr_freq) {
+ if (curr_freq == freq_entry->freq) {
+ freq_entry->buckets[find_bucket(curr_bw)]
+ += get_time_diff(time_now);
+ break;
+ }
+ }
+}
+
+static bool freq_exists(int freq)
+{
+ int i;
+
+ for (i = 0; i < num_freqs; i++) {
+ if (freq == freq_buckets[i])
+ return true;
+ }
+ return false;
+}
+
+static int calculate_total_bw(int bw, int index)
+{
+ int i;
+ int total_bw = 0;
+
+ pr_debug("memory_state_time New bw %d for id %d\n", bw, index);
+ bandwidths[index] = bw;
+ for (i = 0; i < registered_bw_sources; i++)
+ total_bw += bandwidths[i];
+ return total_bw;
+}
+
+static void freq_update_do_work(struct work_struct *work)
+{
+ struct queue_container *freq_state_update
+ = container_of(work, struct queue_container,
+ update_state);
+ if (freq_state_update) {
+ mutex_lock(&mem_lock);
+ update_table(freq_state_update->time_now);
+ curr_freq = freq_state_update->value;
+ mutex_unlock(&mem_lock);
+ kfree(freq_state_update);
+ }
+}
+
+static void bw_update_do_work(struct work_struct *work)
+{
+ struct queue_container *bw_state_update
+ = container_of(work, struct queue_container,
+ update_state);
+ if (bw_state_update) {
+ mutex_lock(&mem_lock);
+ update_table(bw_state_update->time_now);
+ curr_bw = calculate_total_bw(bw_state_update->value,
+ bw_state_update->id);
+ mutex_unlock(&mem_lock);
+ kfree(bw_state_update);
+ }
+}
+
+static void memory_state_freq_update(struct memory_state_update_block *ub,
+ int value)
+{
+ if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) {
+ if (freq_exists(value) && init_success) {
+ struct queue_container *freq_container
+ = kmalloc(sizeof(struct queue_container),
+ GFP_KERNEL);
+ if (!freq_container)
+ return;
+ INIT_WORK(&freq_container->update_state,
+ freq_update_do_work);
+ freq_container->time_now = ktime_get_boot_ns();
+ freq_container->value = value;
+ pr_debug("Scheduling freq update in work queue\n");
+ queue_work(memory_wq, &freq_container->update_state);
+ } else {
+ pr_debug("Freq does not exist.\n");
+ }
+ }
+}
+
+static void memory_state_bw_update(struct memory_state_update_block *ub,
+ int value)
+{
+ if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) {
+ if (init_success) {
+ struct queue_container *bw_container
+ = kmalloc(sizeof(struct queue_container),
+ GFP_KERNEL);
+ if (!bw_container)
+ return;
+ INIT_WORK(&bw_container->update_state,
+ bw_update_do_work);
+ bw_container->time_now = ktime_get_boot_ns();
+ bw_container->value = value;
+ bw_container->id = ub->id;
+ pr_debug("Scheduling bandwidth update in work queue\n");
+ queue_work(memory_wq, &bw_container->update_state);
+ }
+ }
+}
+
+struct memory_state_update_block *memory_state_register_frequency_source(void)
+{
+ struct memory_state_update_block *block;
+
+ if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) {
+ pr_debug("Allocating frequency source\n");
+ block = kmalloc(sizeof(struct memory_state_update_block),
+ GFP_KERNEL);
+ if (!block)
+ return NULL;
+ block->update_call = memory_state_freq_update;
+ return block;
+ }
+ pr_err("Config option disabled.\n");
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(memory_state_register_frequency_source);
+
+struct memory_state_update_block *memory_state_register_bandwidth_source(void)
+{
+ struct memory_state_update_block *block;
+
+ if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) {
+ pr_debug("Allocating bandwidth source %d\n",
+ registered_bw_sources);
+ block = kmalloc(sizeof(struct memory_state_update_block),
+ GFP_KERNEL);
+ if (!block)
+ return NULL;
+ block->update_call = memory_state_bw_update;
+ if (registered_bw_sources < num_sources) {
+ block->id = registered_bw_sources++;
+ } else {
+ pr_err("Unable to allocate source; max number reached\n");
+ kfree(block);
+ return NULL;
+ }
+ return block;
+ }
+ pr_err("Config option disabled.\n");
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(memory_state_register_bandwidth_source);
+
+/* Buckets are designated by their maximum.
+ * Returns the buckets decided by the capability of the device.
+ */
+static int get_bw_buckets(struct device *dev)
+{
+ int ret, lenb;
+ struct device_node *node = dev->of_node;
+
+ of_property_read_u32(node, NUM_SOURCES, &num_sources);
+ if (!of_find_property(node, BW_TBL, &lenb)) {
+ pr_err("Missing %s property\n", BW_TBL);
+ return -ENODATA;
+ }
+
+ bandwidths = devm_kzalloc(dev,
+ sizeof(*bandwidths) * num_sources, GFP_KERNEL);
+ if (!bandwidths)
+ return -ENOMEM;
+ lenb /= sizeof(*bw_buckets);
+ bw_buckets = devm_kzalloc(dev, lenb * sizeof(*bw_buckets),
+ GFP_KERNEL);
+ if (!bw_buckets) {
+ devm_kfree(dev, bandwidths);
+ return -ENOMEM;
+ }
+ ret = of_property_read_u32_array(node, BW_TBL, bw_buckets,
+ lenb);
+ if (ret < 0) {
+ devm_kfree(dev, bandwidths);
+ devm_kfree(dev, bw_buckets);
+ pr_err("Unable to read bandwidth table from device tree.\n");
+ return ret;
+ }
+
+ curr_bw = 0;
+ num_buckets = lenb;
+ return 0;
+}
+
+/* Adds struct freq_entry nodes to the hashtable for each compatible frequency.
+ * Returns the supported number of frequencies.
+ */
+static int freq_buckets_init(struct device *dev)
+{
+ struct freq_entry *freq_entry;
+ int i;
+ int ret, lenf;
+ struct device_node *node = dev->of_node;
+
+ if (!of_find_property(node, FREQ_TBL, &lenf)) {
+ pr_err("Missing %s property\n", FREQ_TBL);
+ return -ENODATA;
+ }
+
+ lenf /= sizeof(*freq_buckets);
+ freq_buckets = devm_kzalloc(dev, lenf * sizeof(*freq_buckets),
+ GFP_KERNEL);
+ if (!freq_buckets)
+ return -ENOMEM;
+ pr_debug("freqs found len %d\n", lenf);
+ ret = of_property_read_u32_array(node, FREQ_TBL, freq_buckets,
+ lenf);
+ if (ret < 0) {
+ devm_kfree(dev, freq_buckets);
+ pr_err("Unable to read frequency table from device tree.\n");
+ return ret;
+ }
+ pr_debug("ret freq %d\n", ret);
+
+ num_freqs = lenf;
+ curr_freq = freq_buckets[LOWEST_FREQ];
+
+ for (i = 0; i < num_freqs; i++) {
+ freq_entry = devm_kzalloc(dev, sizeof(struct freq_entry),
+ GFP_KERNEL);
+ if (!freq_entry)
+ return -ENOMEM;
+ freq_entry->buckets = devm_kzalloc(dev, sizeof(u64)*num_buckets,
+ GFP_KERNEL);
+ if (!freq_entry->buckets) {
+ devm_kfree(dev, freq_entry);
+ return -ENOMEM;
+ }
+ pr_debug("memory_state_time Adding freq to ht %d\n",
+ freq_buckets[i]);
+ freq_entry->freq = freq_buckets[i];
+ hash_add(freq_hash_table, &freq_entry->hash, freq_buckets[i]);
+ }
+ return 0;
+}
+
+struct kobject *memory_kobj;
+EXPORT_SYMBOL_GPL(memory_kobj);
+
+static struct attribute *memory_attrs[] = {
+ &show_stat_attr.attr,
+ NULL
+};
+
+static struct attribute_group memory_attr_group = {
+ .attrs = memory_attrs,
+};
+
+static int memory_state_time_probe(struct platform_device *pdev)
+{
+ int error;
+
+ error = get_bw_buckets(&pdev->dev);
+ if (error)
+ return error;
+ error = freq_buckets_init(&pdev->dev);
+ if (error)
+ return error;
+ last_update = ktime_get_boot_ns();
+ init_success = true;
+
+ pr_debug("memory_state_time initialized with num_freqs %d\n",
+ num_freqs);
+ return 0;
+}
+
+static const struct of_device_id match_table[] = {
+ { .compatible = "memory-state-time" },
+ {}
+};
+
+static struct platform_driver memory_state_time_driver = {
+ .probe = memory_state_time_probe,
+ .driver = {
+ .name = "memory-state-time",
+ .of_match_table = match_table,
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init memory_state_time_init(void)
+{
+ int error;
+
+ hash_init(freq_hash_table);
+ memory_wq = create_singlethread_workqueue("memory_wq");
+ if (!memory_wq) {
+ pr_err("Unable to create workqueue.\n");
+ return -EINVAL;
+ }
+ /*
+ * Create sys/kernel directory for memory_state_time.
+ */
+ memory_kobj = kobject_create_and_add(TAG, kernel_kobj);
+ if (!memory_kobj) {
+ pr_err("Unable to allocate memory_kobj for sysfs directory.\n");
+ error = -ENOMEM;
+ goto wq;
+ }
+ error = sysfs_create_group(memory_kobj, &memory_attr_group);
+ if (error) {
+ pr_err("Unable to create sysfs folder.\n");
+ goto kobj;
+ }
+
+ error = platform_driver_register(&memory_state_time_driver);
+ if (error) {
+ pr_err("Unable to register memory_state_time platform driver.\n");
+ goto group;
+ }
+ return 0;
+
+group: sysfs_remove_group(memory_kobj, &memory_attr_group);
+kobj: kobject_put(memory_kobj);
+wq: destroy_workqueue(memory_wq);
+ return error;
+}
+module_init(memory_state_time_init);
diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c
new file mode 100644
index 0000000..345f229
--- /dev/null
+++ b/drivers/misc/uid_sys_stats.c
@@ -0,0 +1,706 @@
+/* drivers/misc/uid_sys_stats.c
+ *
+ * Copyright (C) 2014 - 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/cpufreq_times.h>
+#include <linux/err.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/profile.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+
+#define UID_HASH_BITS 10
+DECLARE_HASHTABLE(hash_table, UID_HASH_BITS);
+
+static DEFINE_RT_MUTEX(uid_lock);
+static struct proc_dir_entry *cpu_parent;
+static struct proc_dir_entry *io_parent;
+static struct proc_dir_entry *proc_parent;
+
+struct io_stats {
+ u64 read_bytes;
+ u64 write_bytes;
+ u64 rchar;
+ u64 wchar;
+ u64 fsync;
+};
+
+#define UID_STATE_FOREGROUND 0
+#define UID_STATE_BACKGROUND 1
+#define UID_STATE_BUCKET_SIZE 2
+
+#define UID_STATE_TOTAL_CURR 2
+#define UID_STATE_TOTAL_LAST 3
+#define UID_STATE_DEAD_TASKS 4
+#define UID_STATE_SIZE 5
+
+#define MAX_TASK_COMM_LEN 256
+
+struct task_entry {
+ char comm[MAX_TASK_COMM_LEN];
+ pid_t pid;
+ struct io_stats io[UID_STATE_SIZE];
+ struct hlist_node hash;
+};
+
+struct uid_entry {
+ uid_t uid;
+ cputime_t utime;
+ cputime_t stime;
+ cputime_t active_utime;
+ cputime_t active_stime;
+ int state;
+ struct io_stats io[UID_STATE_SIZE];
+ struct hlist_node hash;
+#ifdef CONFIG_UID_SYS_STATS_DEBUG
+ DECLARE_HASHTABLE(task_entries, UID_HASH_BITS);
+#endif
+};
+
+static u64 compute_write_bytes(struct task_struct *task)
+{
+ if (task->ioac.write_bytes <= task->ioac.cancelled_write_bytes)
+ return 0;
+
+ return task->ioac.write_bytes - task->ioac.cancelled_write_bytes;
+}
+
+static void compute_io_bucket_stats(struct io_stats *io_bucket,
+ struct io_stats *io_curr,
+ struct io_stats *io_last,
+ struct io_stats *io_dead)
+{
+ /* tasks could switch to another uid group, but its io_last in the
+ * previous uid group could still be positive.
+ * therefore before each update, do an overflow check first
+ */
+ int64_t delta;
+
+ delta = io_curr->read_bytes + io_dead->read_bytes -
+ io_last->read_bytes;
+ io_bucket->read_bytes += delta > 0 ? delta : 0;
+ delta = io_curr->write_bytes + io_dead->write_bytes -
+ io_last->write_bytes;
+ io_bucket->write_bytes += delta > 0 ? delta : 0;
+ delta = io_curr->rchar + io_dead->rchar - io_last->rchar;
+ io_bucket->rchar += delta > 0 ? delta : 0;
+ delta = io_curr->wchar + io_dead->wchar - io_last->wchar;
+ io_bucket->wchar += delta > 0 ? delta : 0;
+ delta = io_curr->fsync + io_dead->fsync - io_last->fsync;
+ io_bucket->fsync += delta > 0 ? delta : 0;
+
+ io_last->read_bytes = io_curr->read_bytes;
+ io_last->write_bytes = io_curr->write_bytes;
+ io_last->rchar = io_curr->rchar;
+ io_last->wchar = io_curr->wchar;
+ io_last->fsync = io_curr->fsync;
+
+ memset(io_dead, 0, sizeof(struct io_stats));
+}
+
+#ifdef CONFIG_UID_SYS_STATS_DEBUG
+static void get_full_task_comm(struct task_entry *task_entry,
+ struct task_struct *task)
+{
+ int i = 0, offset = 0, len = 0;
+ /* save one byte for terminating null character */
+ int unused_len = MAX_TASK_COMM_LEN - TASK_COMM_LEN - 1;
+ char buf[unused_len];
+ struct mm_struct *mm = task->mm;
+
+ /* fill the first TASK_COMM_LEN bytes with thread name */
+ __get_task_comm(task_entry->comm, TASK_COMM_LEN, task);
+ i = strlen(task_entry->comm);
+ while (i < TASK_COMM_LEN)
+ task_entry->comm[i++] = ' ';
+
+ /* next the executable file name */
+ if (mm) {
+ down_read(&mm->mmap_sem);
+ if (mm->exe_file) {
+ char *pathname = d_path(&mm->exe_file->f_path, buf,
+ unused_len);
+
+ if (!IS_ERR(pathname)) {
+ len = strlcpy(task_entry->comm + i, pathname,
+ unused_len);
+ i += len;
+ task_entry->comm[i++] = ' ';
+ unused_len--;
+ }
+ }
+ up_read(&mm->mmap_sem);
+ }
+ unused_len -= len;
+
+ /* fill the rest with command line argument
+ * replace each null or new line character
+ * between args in argv with whitespace */
+ len = get_cmdline(task, buf, unused_len);
+ while (offset < len) {
+ if (buf[offset] != '\0' && buf[offset] != '\n')
+ task_entry->comm[i++] = buf[offset];
+ else
+ task_entry->comm[i++] = ' ';
+ offset++;
+ }
+
+ /* get rid of trailing whitespaces in case when arg is memset to
+ * zero before being reset in userspace
+ */
+ while (task_entry->comm[i-1] == ' ')
+ i--;
+ task_entry->comm[i] = '\0';
+}
+
+static struct task_entry *find_task_entry(struct uid_entry *uid_entry,
+ struct task_struct *task)
+{
+ struct task_entry *task_entry;
+
+ hash_for_each_possible(uid_entry->task_entries, task_entry, hash,
+ task->pid) {
+ if (task->pid == task_entry->pid) {
+ /* if thread name changed, update the entire command */
+ int len = strnchr(task_entry->comm, ' ', TASK_COMM_LEN)
+ - task_entry->comm;
+
+ if (strncmp(task_entry->comm, task->comm, len))
+ get_full_task_comm(task_entry, task);
+ return task_entry;
+ }
+ }
+ return NULL;
+}
+
+static struct task_entry *find_or_register_task(struct uid_entry *uid_entry,
+ struct task_struct *task)
+{
+ struct task_entry *task_entry;
+ pid_t pid = task->pid;
+
+ task_entry = find_task_entry(uid_entry, task);
+ if (task_entry)
+ return task_entry;
+
+ task_entry = kzalloc(sizeof(struct task_entry), GFP_ATOMIC);
+ if (!task_entry)
+ return NULL;
+
+ get_full_task_comm(task_entry, task);
+
+ task_entry->pid = pid;
+ hash_add(uid_entry->task_entries, &task_entry->hash, (unsigned int)pid);
+
+ return task_entry;
+}
+
+static void remove_uid_tasks(struct uid_entry *uid_entry)
+{
+ struct task_entry *task_entry;
+ unsigned long bkt_task;
+ struct hlist_node *tmp_task;
+
+ hash_for_each_safe(uid_entry->task_entries, bkt_task,
+ tmp_task, task_entry, hash) {
+ hash_del(&task_entry->hash);
+ kfree(task_entry);
+ }
+}
+
+static void set_io_uid_tasks_zero(struct uid_entry *uid_entry)
+{
+ struct task_entry *task_entry;
+ unsigned long bkt_task;
+
+ hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) {
+ memset(&task_entry->io[UID_STATE_TOTAL_CURR], 0,
+ sizeof(struct io_stats));
+ }
+}
+
+static void add_uid_tasks_io_stats(struct uid_entry *uid_entry,
+ struct task_struct *task, int slot)
+{
+ struct task_entry *task_entry = find_or_register_task(uid_entry, task);
+ struct io_stats *task_io_slot = &task_entry->io[slot];
+
+ task_io_slot->read_bytes += task->ioac.read_bytes;
+ task_io_slot->write_bytes += compute_write_bytes(task);
+ task_io_slot->rchar += task->ioac.rchar;
+ task_io_slot->wchar += task->ioac.wchar;
+ task_io_slot->fsync += task->ioac.syscfs;
+}
+
+static void compute_io_uid_tasks(struct uid_entry *uid_entry)
+{
+ struct task_entry *task_entry;
+ unsigned long bkt_task;
+
+ hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) {
+ compute_io_bucket_stats(&task_entry->io[uid_entry->state],
+ &task_entry->io[UID_STATE_TOTAL_CURR],
+ &task_entry->io[UID_STATE_TOTAL_LAST],
+ &task_entry->io[UID_STATE_DEAD_TASKS]);
+ }
+}
+
+static void show_io_uid_tasks(struct seq_file *m, struct uid_entry *uid_entry)
+{
+ struct task_entry *task_entry;
+ unsigned long bkt_task;
+
+ hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) {
+ /* Separated by comma because space exists in task comm */
+ seq_printf(m, "task,%s,%lu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu\n",
+ task_entry->comm,
+ (unsigned long)task_entry->pid,
+ task_entry->io[UID_STATE_FOREGROUND].rchar,
+ task_entry->io[UID_STATE_FOREGROUND].wchar,
+ task_entry->io[UID_STATE_FOREGROUND].read_bytes,
+ task_entry->io[UID_STATE_FOREGROUND].write_bytes,
+ task_entry->io[UID_STATE_BACKGROUND].rchar,
+ task_entry->io[UID_STATE_BACKGROUND].wchar,
+ task_entry->io[UID_STATE_BACKGROUND].read_bytes,
+ task_entry->io[UID_STATE_BACKGROUND].write_bytes,
+ task_entry->io[UID_STATE_FOREGROUND].fsync,
+ task_entry->io[UID_STATE_BACKGROUND].fsync);
+ }
+}
+#else
+static void remove_uid_tasks(struct uid_entry *uid_entry) {};
+static void set_io_uid_tasks_zero(struct uid_entry *uid_entry) {};
+static void add_uid_tasks_io_stats(struct uid_entry *uid_entry,
+ struct task_struct *task, int slot) {};
+static void compute_io_uid_tasks(struct uid_entry *uid_entry) {};
+static void show_io_uid_tasks(struct seq_file *m,
+ struct uid_entry *uid_entry) {}
+#endif
+
+static struct uid_entry *find_uid_entry(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+ hash_for_each_possible(hash_table, uid_entry, hash, uid) {
+ if (uid_entry->uid == uid)
+ return uid_entry;
+ }
+ return NULL;
+}
+
+static struct uid_entry *find_or_register_uid(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+
+ uid_entry = find_uid_entry(uid);
+ if (uid_entry)
+ return uid_entry;
+
+ uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC);
+ if (!uid_entry)
+ return NULL;
+
+ uid_entry->uid = uid;
+#ifdef CONFIG_UID_SYS_STATS_DEBUG
+ hash_init(uid_entry->task_entries);
+#endif
+ hash_add(hash_table, &uid_entry->hash, uid);
+
+ return uid_entry;
+}
+
+static int uid_cputime_show(struct seq_file *m, void *v)
+{
+ struct uid_entry *uid_entry = NULL;
+ struct task_struct *task, *temp;
+ struct user_namespace *user_ns = current_user_ns();
+ cputime_t utime;
+ cputime_t stime;
+ unsigned long bkt;
+ uid_t uid;
+
+ rt_mutex_lock(&uid_lock);
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ uid_entry->active_stime = 0;
+ uid_entry->active_utime = 0;
+ }
+
+ rcu_read_lock();
+ do_each_thread(temp, task) {
+ uid = from_kuid_munged(user_ns, task_uid(task));
+ if (!uid_entry || uid_entry->uid != uid)
+ uid_entry = find_or_register_uid(uid);
+ if (!uid_entry) {
+ rcu_read_unlock();
+ rt_mutex_unlock(&uid_lock);
+ pr_err("%s: failed to find the uid_entry for uid %d\n",
+ __func__, uid);
+ return -ENOMEM;
+ }
+ task_cputime_adjusted(task, &utime, &stime);
+ uid_entry->active_utime += utime;
+ uid_entry->active_stime += stime;
+ } while_each_thread(temp, task);
+ rcu_read_unlock();
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ cputime_t total_utime = uid_entry->utime +
+ uid_entry->active_utime;
+ cputime_t total_stime = uid_entry->stime +
+ uid_entry->active_stime;
+ seq_printf(m, "%d: %llu %llu\n", uid_entry->uid,
+ (unsigned long long)jiffies_to_msecs(
+ cputime_to_jiffies(total_utime)) * USEC_PER_MSEC,
+ (unsigned long long)jiffies_to_msecs(
+ cputime_to_jiffies(total_stime)) * USEC_PER_MSEC);
+ }
+
+ rt_mutex_unlock(&uid_lock);
+ return 0;
+}
+
+static int uid_cputime_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, uid_cputime_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_cputime_fops = {
+ .open = uid_cputime_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int uid_remove_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, NULL, NULL);
+}
+
+static ssize_t uid_remove_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos)
+{
+ struct uid_entry *uid_entry;
+ struct hlist_node *tmp;
+ char uids[128];
+ char *start_uid, *end_uid = NULL;
+ long int uid_start = 0, uid_end = 0;
+
+ if (count >= sizeof(uids))
+ count = sizeof(uids) - 1;
+
+ if (copy_from_user(uids, buffer, count))
+ return -EFAULT;
+
+ uids[count] = '\0';
+ end_uid = uids;
+ start_uid = strsep(&end_uid, "-");
+
+ if (!start_uid || !end_uid)
+ return -EINVAL;
+
+ if (kstrtol(start_uid, 10, &uid_start) != 0 ||
+ kstrtol(end_uid, 10, &uid_end) != 0) {
+ return -EINVAL;
+ }
+
+ /* Also remove uids from /proc/uid_time_in_state */
+ cpufreq_task_times_remove_uids(uid_start, uid_end);
+
+ rt_mutex_lock(&uid_lock);
+
+ for (; uid_start <= uid_end; uid_start++) {
+ hash_for_each_possible_safe(hash_table, uid_entry, tmp,
+ hash, (uid_t)uid_start) {
+ if (uid_start == uid_entry->uid) {
+ remove_uid_tasks(uid_entry);
+ hash_del(&uid_entry->hash);
+ kfree(uid_entry);
+ }
+ }
+ }
+
+ rt_mutex_unlock(&uid_lock);
+ return count;
+}
+
+static const struct file_operations uid_remove_fops = {
+ .open = uid_remove_open,
+ .release = single_release,
+ .write = uid_remove_write,
+};
+
+
+static void add_uid_io_stats(struct uid_entry *uid_entry,
+ struct task_struct *task, int slot)
+{
+ struct io_stats *io_slot = &uid_entry->io[slot];
+
+ io_slot->read_bytes += task->ioac.read_bytes;
+ io_slot->write_bytes += compute_write_bytes(task);
+ io_slot->rchar += task->ioac.rchar;
+ io_slot->wchar += task->ioac.wchar;
+ io_slot->fsync += task->ioac.syscfs;
+
+ add_uid_tasks_io_stats(uid_entry, task, slot);
+}
+
+static void update_io_stats_all_locked(void)
+{
+ struct uid_entry *uid_entry = NULL;
+ struct task_struct *task, *temp;
+ struct user_namespace *user_ns = current_user_ns();
+ unsigned long bkt;
+ uid_t uid;
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0,
+ sizeof(struct io_stats));
+ set_io_uid_tasks_zero(uid_entry);
+ }
+
+ rcu_read_lock();
+ do_each_thread(temp, task) {
+ uid = from_kuid_munged(user_ns, task_uid(task));
+ if (!uid_entry || uid_entry->uid != uid)
+ uid_entry = find_or_register_uid(uid);
+ if (!uid_entry)
+ continue;
+ add_uid_io_stats(uid_entry, task, UID_STATE_TOTAL_CURR);
+ } while_each_thread(temp, task);
+ rcu_read_unlock();
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ compute_io_bucket_stats(&uid_entry->io[uid_entry->state],
+ &uid_entry->io[UID_STATE_TOTAL_CURR],
+ &uid_entry->io[UID_STATE_TOTAL_LAST],
+ &uid_entry->io[UID_STATE_DEAD_TASKS]);
+ compute_io_uid_tasks(uid_entry);
+ }
+}
+
+static void update_io_stats_uid_locked(struct uid_entry *uid_entry)
+{
+ struct task_struct *task, *temp;
+ struct user_namespace *user_ns = current_user_ns();
+
+ memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0,
+ sizeof(struct io_stats));
+ set_io_uid_tasks_zero(uid_entry);
+
+ rcu_read_lock();
+ do_each_thread(temp, task) {
+ if (from_kuid_munged(user_ns, task_uid(task)) != uid_entry->uid)
+ continue;
+ add_uid_io_stats(uid_entry, task, UID_STATE_TOTAL_CURR);
+ } while_each_thread(temp, task);
+ rcu_read_unlock();
+
+ compute_io_bucket_stats(&uid_entry->io[uid_entry->state],
+ &uid_entry->io[UID_STATE_TOTAL_CURR],
+ &uid_entry->io[UID_STATE_TOTAL_LAST],
+ &uid_entry->io[UID_STATE_DEAD_TASKS]);
+ compute_io_uid_tasks(uid_entry);
+}
+
+
+static int uid_io_show(struct seq_file *m, void *v)
+{
+ struct uid_entry *uid_entry;
+ unsigned long bkt;
+
+ rt_mutex_lock(&uid_lock);
+
+ update_io_stats_all_locked();
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ seq_printf(m, "%d %llu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+ uid_entry->uid,
+ uid_entry->io[UID_STATE_FOREGROUND].rchar,
+ uid_entry->io[UID_STATE_FOREGROUND].wchar,
+ uid_entry->io[UID_STATE_FOREGROUND].read_bytes,
+ uid_entry->io[UID_STATE_FOREGROUND].write_bytes,
+ uid_entry->io[UID_STATE_BACKGROUND].rchar,
+ uid_entry->io[UID_STATE_BACKGROUND].wchar,
+ uid_entry->io[UID_STATE_BACKGROUND].read_bytes,
+ uid_entry->io[UID_STATE_BACKGROUND].write_bytes,
+ uid_entry->io[UID_STATE_FOREGROUND].fsync,
+ uid_entry->io[UID_STATE_BACKGROUND].fsync);
+
+ show_io_uid_tasks(m, uid_entry);
+ }
+
+ rt_mutex_unlock(&uid_lock);
+ return 0;
+}
+
+static int uid_io_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, uid_io_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_io_fops = {
+ .open = uid_io_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int uid_procstat_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, NULL, NULL);
+}
+
+static ssize_t uid_procstat_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos)
+{
+ struct uid_entry *uid_entry;
+ uid_t uid;
+ int argc, state;
+ char input[128];
+
+ if (count >= sizeof(input))
+ return -EINVAL;
+
+ if (copy_from_user(input, buffer, count))
+ return -EFAULT;
+
+ input[count] = '\0';
+
+ argc = sscanf(input, "%u %d", &uid, &state);
+ if (argc != 2)
+ return -EINVAL;
+
+ if (state != UID_STATE_BACKGROUND && state != UID_STATE_FOREGROUND)
+ return -EINVAL;
+
+ rt_mutex_lock(&uid_lock);
+
+ uid_entry = find_or_register_uid(uid);
+ if (!uid_entry) {
+ rt_mutex_unlock(&uid_lock);
+ return -EINVAL;
+ }
+
+ if (uid_entry->state == state) {
+ rt_mutex_unlock(&uid_lock);
+ return count;
+ }
+
+ update_io_stats_uid_locked(uid_entry);
+
+ uid_entry->state = state;
+
+ rt_mutex_unlock(&uid_lock);
+
+ return count;
+}
+
+static const struct file_operations uid_procstat_fops = {
+ .open = uid_procstat_open,
+ .release = single_release,
+ .write = uid_procstat_write,
+};
+
+static int process_notifier(struct notifier_block *self,
+ unsigned long cmd, void *v)
+{
+ struct task_struct *task = v;
+ struct uid_entry *uid_entry;
+ cputime_t utime, stime;
+ uid_t uid;
+
+ if (!task)
+ return NOTIFY_OK;
+
+ rt_mutex_lock(&uid_lock);
+ uid = from_kuid_munged(current_user_ns(), task_uid(task));
+ uid_entry = find_or_register_uid(uid);
+ if (!uid_entry) {
+ pr_err("%s: failed to find uid %d\n", __func__, uid);
+ goto exit;
+ }
+
+ task_cputime_adjusted(task, &utime, &stime);
+ uid_entry->utime += utime;
+ uid_entry->stime += stime;
+
+ add_uid_io_stats(uid_entry, task, UID_STATE_DEAD_TASKS);
+
+exit:
+ rt_mutex_unlock(&uid_lock);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block process_notifier_block = {
+ .notifier_call = process_notifier,
+};
+
+static int __init proc_uid_sys_stats_init(void)
+{
+ hash_init(hash_table);
+
+ cpu_parent = proc_mkdir("uid_cputime", NULL);
+ if (!cpu_parent) {
+ pr_err("%s: failed to create uid_cputime proc entry\n",
+ __func__);
+ goto err;
+ }
+
+ proc_create_data("remove_uid_range", 0222, cpu_parent,
+ &uid_remove_fops, NULL);
+ proc_create_data("show_uid_stat", 0444, cpu_parent,
+ &uid_cputime_fops, NULL);
+
+ io_parent = proc_mkdir("uid_io", NULL);
+ if (!io_parent) {
+ pr_err("%s: failed to create uid_io proc entry\n",
+ __func__);
+ goto err;
+ }
+
+ proc_create_data("stats", 0444, io_parent,
+ &uid_io_fops, NULL);
+
+ proc_parent = proc_mkdir("uid_procstat", NULL);
+ if (!proc_parent) {
+ pr_err("%s: failed to create uid_procstat proc entry\n",
+ __func__);
+ goto err;
+ }
+
+ proc_create_data("set", 0222, proc_parent,
+ &uid_procstat_fops, NULL);
+
+ profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block);
+
+ return 0;
+
+err:
+ remove_proc_subtree("uid_cputime", NULL);
+ remove_proc_subtree("uid_io", NULL);
+ remove_proc_subtree("uid_procstat", NULL);
+ return -ENOMEM;
+}
+
+early_initcall(proc_uid_sys_stats_init);
diff --git a/drivers/mmc/card/Kconfig b/drivers/mmc/card/Kconfig
index 5562308..6142ec1 100644
--- a/drivers/mmc/card/Kconfig
+++ b/drivers/mmc/card/Kconfig
@@ -68,3 +68,15 @@
This driver is only of interest to those developing or
testing a host driver. Most people should say N here.
+
+config MMC_SIMULATE_MAX_SPEED
+ bool "Turn on maximum speed control per block device"
+ depends on MMC_BLOCK
+ help
+ Say Y here to enable MMC device speed limiting. Used to test and
+ simulate the behavior of the system when confronted with a slow MMC.
+
+ Enables max_read_speed, max_write_speed and cache_size attributes to
+ control the write or read maximum KB/second speed behaviors.
+
+ If unsure, say N here.
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 709a872..817fcf8 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -287,6 +287,250 @@ static ssize_t force_ro_store(struct device *dev, struct device_attribute *attr,
return ret;
}
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+
+static int max_read_speed, max_write_speed, cache_size = 4;
+
+module_param(max_read_speed, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(max_read_speed, "maximum KB/s read speed 0=off");
+module_param(max_write_speed, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(max_write_speed, "maximum KB/s write speed 0=off");
+module_param(cache_size, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(cache_size, "MB high speed memory or SLC cache");
+
+/*
+ * helper macros and expectations:
+ * size - unsigned long number of bytes
+ * jiffies - unsigned long HZ timestamp difference
+ * speed - unsigned KB/s transfer rate
+ */
+#define size_and_speed_to_jiffies(size, speed) \
+ ((size) * HZ / (speed) / 1024UL)
+#define jiffies_and_speed_to_size(jiffies, speed) \
+ (((speed) * (jiffies) * 1024UL) / HZ)
+#define jiffies_and_size_to_speed(jiffies, size) \
+ ((size) * HZ / (jiffies) / 1024UL)
+
+/* Limits to report warning */
+/* jiffies_and_size_to_speed(10*HZ, queue_max_hw_sectors(q) * 512UL) ~ 25 */
+#define MIN_SPEED(q) 250 /* 10 times faster than a floppy disk */
+#define MAX_SPEED(q) jiffies_and_size_to_speed(1, queue_max_sectors(q) * 512UL)
+
+#define speed_valid(speed) ((speed) > 0)
+
+static const char off[] = "off\n";
+
+static int max_speed_show(int speed, char *buf)
+{
+ if (speed)
+ return scnprintf(buf, PAGE_SIZE, "%uKB/s\n", speed);
+ else
+ return scnprintf(buf, PAGE_SIZE, off);
+}
+
+static int max_speed_store(const char *buf, struct request_queue *q)
+{
+ unsigned int limit, set = 0;
+
+ if (!strncasecmp(off, buf, sizeof(off) - 2))
+ return set;
+ if (kstrtouint(buf, 0, &set) || (set > INT_MAX))
+ return -EINVAL;
+ if (set == 0)
+ return set;
+ limit = MAX_SPEED(q);
+ if (set > limit)
+ pr_warn("max speed %u ineffective above %u\n", set, limit);
+ limit = MIN_SPEED(q);
+ if (set < limit)
+ pr_warn("max speed %u painful below %u\n", set, limit);
+ return set;
+}
+
+static ssize_t max_write_speed_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int ret = max_speed_show(atomic_read(&md->queue.max_write_speed), buf);
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t max_write_speed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int set = max_speed_store(buf, md->queue.queue);
+
+ if (set < 0) {
+ mmc_blk_put(md);
+ return set;
+ }
+
+ atomic_set(&md->queue.max_write_speed, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(max_write_speed, S_IRUGO | S_IWUSR,
+ max_write_speed_show, max_write_speed_store);
+
+static ssize_t max_read_speed_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int ret = max_speed_show(atomic_read(&md->queue.max_read_speed), buf);
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t max_read_speed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int set = max_speed_store(buf, md->queue.queue);
+
+ if (set < 0) {
+ mmc_blk_put(md);
+ return set;
+ }
+
+ atomic_set(&md->queue.max_read_speed, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(max_read_speed, S_IRUGO | S_IWUSR,
+ max_read_speed_show, max_read_speed_store);
+
+static ssize_t cache_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ struct mmc_queue *mq = &md->queue;
+ int cache_size = atomic_read(&mq->cache_size);
+ int ret;
+
+ if (!cache_size)
+ ret = scnprintf(buf, PAGE_SIZE, off);
+ else {
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (!speed_valid(speed))
+ ret = scnprintf(buf, PAGE_SIZE, "%uMB\n", cache_size);
+ else { /* We accept race between cache_jiffies and cache_used */
+ unsigned long size = jiffies_and_speed_to_size(
+ jiffies - mq->cache_jiffies, speed);
+ long used = atomic_long_read(&mq->cache_used);
+
+ if (size >= used)
+ size = 0;
+ else
+ size = (used - size) * 100 / cache_size
+ / 1024UL / 1024UL;
+
+ ret = scnprintf(buf, PAGE_SIZE, "%uMB %lu%% used\n",
+ cache_size, size);
+ }
+ }
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t cache_size_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md;
+ unsigned int set = 0;
+
+ if (strncasecmp(off, buf, sizeof(off) - 2)
+ && (kstrtouint(buf, 0, &set) || (set > INT_MAX)))
+ return -EINVAL;
+
+ md = mmc_blk_get(dev_to_disk(dev));
+ atomic_set(&md->queue.cache_size, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(cache_size, S_IRUGO | S_IWUSR,
+ cache_size_show, cache_size_store);
+
+/* correct for write-back */
+static long mmc_blk_cache_used(struct mmc_queue *mq, unsigned long waitfor)
+{
+ long used = 0;
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (speed_valid(speed)) {
+ unsigned long size = jiffies_and_speed_to_size(
+ waitfor - mq->cache_jiffies, speed);
+ used = atomic_long_read(&mq->cache_used);
+
+ if (size >= used)
+ used = 0;
+ else
+ used -= size;
+ }
+
+ atomic_long_set(&mq->cache_used, used);
+ mq->cache_jiffies = waitfor;
+
+ return used;
+}
+
+static void mmc_blk_simulate_delay(
+ struct mmc_queue *mq,
+ struct request *req,
+ unsigned long waitfor)
+{
+ int max_speed;
+
+ if (!req)
+ return;
+
+ max_speed = (rq_data_dir(req) == READ)
+ ? atomic_read(&mq->max_read_speed)
+ : atomic_read(&mq->max_write_speed);
+ if (speed_valid(max_speed)) {
+ unsigned long bytes = blk_rq_bytes(req);
+
+ if (rq_data_dir(req) != READ) {
+ int cache_size = atomic_read(&mq->cache_size);
+
+ if (cache_size) {
+ unsigned long size = cache_size * 1024L * 1024L;
+ long used = mmc_blk_cache_used(mq, waitfor);
+
+ used += bytes;
+ atomic_long_set(&mq->cache_used, used);
+ bytes = 0;
+ if (used > size)
+ bytes = used - size;
+ }
+ }
+ waitfor += size_and_speed_to_jiffies(bytes, max_speed);
+ if (time_is_after_jiffies(waitfor)) {
+ long msecs = jiffies_to_msecs(waitfor - jiffies);
+
+ if (likely(msecs > 0))
+ msleep(msecs);
+ }
+ }
+}
+
+#else
+
+#define mmc_blk_simulate_delay(mq, req, waitfor)
+
+#endif
+
static int mmc_blk_open(struct block_device *bdev, fmode_t mode)
{
struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk);
@@ -1284,6 +1528,23 @@ static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
if (ret)
ret = -EIO;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ else if (atomic_read(&mq->cache_size)) {
+ long used = mmc_blk_cache_used(mq, jiffies);
+
+ if (used) {
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (speed_valid(speed)) {
+ unsigned long msecs = jiffies_to_msecs(
+ size_and_speed_to_jiffies(
+ used, speed));
+ if (msecs)
+ msleep(msecs);
+ }
+ }
+ }
+#endif
blk_end_request_all(req, ret);
return ret ? 0 : 1;
@@ -1965,6 +2226,9 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
struct mmc_async_req *areq;
const u8 packed_nr = 2;
u8 reqs = 0;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ unsigned long waitfor = jiffies;
+#endif
if (!rqc && !mq->mqrq_prev->req)
return 0;
@@ -2015,6 +2279,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
*/
mmc_blk_reset_success(md, type);
+ mmc_blk_simulate_delay(mq, rqc, waitfor);
+
if (mmc_packed_cmd(mq_rq->cmd_type)) {
ret = mmc_blk_end_packed_req(mq_rq);
break;
@@ -2437,6 +2703,14 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md)
card->ext_csd.boot_ro_lockable)
device_remove_file(disk_to_dev(md->disk),
&md->power_ro_lock);
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_max_write_speed);
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_max_read_speed);
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_cache_size);
+#endif
del_gendisk(md->disk);
}
@@ -2471,6 +2745,24 @@ static int mmc_add_disk(struct mmc_blk_data *md)
ret = device_create_file(disk_to_dev(md->disk), &md->force_ro);
if (ret)
goto force_ro_fail;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ atomic_set(&md->queue.max_write_speed, max_write_speed);
+ ret = device_create_file(disk_to_dev(md->disk),
+ &dev_attr_max_write_speed);
+ if (ret)
+ goto max_write_speed_fail;
+ atomic_set(&md->queue.max_read_speed, max_read_speed);
+ ret = device_create_file(disk_to_dev(md->disk),
+ &dev_attr_max_read_speed);
+ if (ret)
+ goto max_read_speed_fail;
+ atomic_set(&md->queue.cache_size, cache_size);
+ atomic_long_set(&md->queue.cache_used, 0);
+ md->queue.cache_jiffies = jiffies;
+ ret = device_create_file(disk_to_dev(md->disk), &dev_attr_cache_size);
+ if (ret)
+ goto cache_size_fail;
+#endif
if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) &&
card->ext_csd.boot_ro_lockable) {
@@ -2495,6 +2787,14 @@ static int mmc_add_disk(struct mmc_blk_data *md)
return ret;
power_ro_lock_fail:
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_cache_size);
+cache_size_fail:
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_max_read_speed);
+max_read_speed_fail:
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_max_write_speed);
+max_write_speed_fail:
+#endif
device_remove_file(disk_to_dev(md->disk), &md->force_ro);
force_ro_fail:
del_gendisk(md->disk);
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 8037f73..1810f76 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -19,6 +19,7 @@
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
+#include <linux/sched/rt.h>
#include "queue.h"
#include "block.h"
@@ -53,6 +54,11 @@ static int mmc_queue_thread(void *d)
{
struct mmc_queue *mq = d;
struct request_queue *q = mq->queue;
+ struct sched_param scheduler_params = {0};
+
+ scheduler_params.sched_priority = 1;
+
+ sched_setscheduler(current, SCHED_FIFO, &scheduler_params);
current->flags |= PF_MEMALLOC;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 342f1e3..fe58d31 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -62,6 +62,14 @@ struct mmc_queue {
struct mmc_queue_req mqrq[2];
struct mmc_queue_req *mqrq_cur;
struct mmc_queue_req *mqrq_prev;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ atomic_t max_write_speed;
+ atomic_t max_read_speed;
+ atomic_t cache_size;
+ /* i/o tracking */
+ atomic_long_t cache_used;
+ unsigned long cache_jiffies;
+#endif
};
extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index 250f223..daad32f 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -22,3 +22,18 @@
This driver can also be built as a module. If so, the module
will be called pwrseq_simple.
+
+config MMC_EMBEDDED_SDIO
+ boolean "MMC embedded SDIO device support (EXPERIMENTAL)"
+ help
+ If you say Y here, support will be added for embedded SDIO
+ devices which do not contain the necessary enumeration
+ support in hardware to be properly detected.
+
+config MMC_PARANOID_SD_INIT
+ bool "Enable paranoid SD card initialization (EXPERIMENTAL)"
+ help
+ If you say Y here, the MMC layer will be extra paranoid
+ about re-trying SD init requests. This can be a useful
+ work-around for buggy controllers and hardware. Enable
+ if you are experiencing issues with SD detection.
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index cff58297..e19c370 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -201,6 +201,20 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
pr_debug("%s: %d bytes transferred: %d\n",
mmc_hostname(host),
mrq->data->bytes_xfered, mrq->data->error);
+#ifdef CONFIG_BLOCK
+ if (mrq->lat_hist_enabled) {
+ ktime_t completion;
+ u_int64_t delta_us;
+
+ completion = ktime_get();
+ delta_us = ktime_us_delta(completion,
+ mrq->io_start);
+ blk_update_latency_hist(
+ (mrq->data->flags & MMC_DATA_READ) ?
+ &host->io_lat_read :
+ &host->io_lat_write, delta_us);
+ }
+#endif
}
if (mrq->stop) {
@@ -699,8 +713,16 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
}
}
- if (!err && areq)
+ if (!err && areq) {
+#ifdef CONFIG_BLOCK
+ if (host->latency_hist_enabled) {
+ areq->mrq->io_start = ktime_get();
+ areq->mrq->lat_hist_enabled = 1;
+ } else
+ areq->mrq->lat_hist_enabled = 0;
+#endif
start_err = __mmc_start_data_req(host, areq->mrq);
+ }
if (host->areq)
mmc_post_req(host, host->areq->mrq, 0);
@@ -2051,7 +2073,7 @@ void mmc_init_erase(struct mmc_card *card)
}
static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card,
- unsigned int arg, unsigned int qty)
+ unsigned int arg, unsigned int qty)
{
unsigned int erase_timeout;
@@ -3034,6 +3056,22 @@ void mmc_init_context_info(struct mmc_host *host)
init_waitqueue_head(&host->context_info.wait);
}
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+void mmc_set_embedded_sdio_data(struct mmc_host *host,
+ struct sdio_cis *cis,
+ struct sdio_cccr *cccr,
+ struct sdio_embedded_func *funcs,
+ int num_funcs)
+{
+ host->embedded_sdio_data.cis = cis;
+ host->embedded_sdio_data.cccr = cccr;
+ host->embedded_sdio_data.funcs = funcs;
+ host->embedded_sdio_data.num_funcs = num_funcs;
+}
+
+EXPORT_SYMBOL(mmc_set_embedded_sdio_data);
+#endif
+
static int __init mmc_init(void)
{
int ret;
@@ -3066,6 +3104,63 @@ static void __exit mmc_exit(void)
mmc_unregister_bus();
}
+#ifdef CONFIG_BLOCK
+static ssize_t
+latency_hist_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct mmc_host *host = cls_dev_to_mmc_host(dev);
+ size_t written_bytes;
+
+ written_bytes = blk_latency_hist_show("Read", &host->io_lat_read,
+ buf, PAGE_SIZE);
+ written_bytes += blk_latency_hist_show("Write", &host->io_lat_write,
+ buf + written_bytes, PAGE_SIZE - written_bytes);
+
+ return written_bytes;
+}
+
+/*
+ * Values permitted 0, 1, 2.
+ * 0 -> Disable IO latency histograms (default)
+ * 1 -> Enable IO latency histograms
+ * 2 -> Zero out IO latency histograms
+ */
+static ssize_t
+latency_hist_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_host *host = cls_dev_to_mmc_host(dev);
+ long value;
+
+ if (kstrtol(buf, 0, &value))
+ return -EINVAL;
+ if (value == BLK_IO_LAT_HIST_ZERO) {
+ memset(&host->io_lat_read, 0, sizeof(host->io_lat_read));
+ memset(&host->io_lat_write, 0, sizeof(host->io_lat_write));
+ } else if (value == BLK_IO_LAT_HIST_ENABLE ||
+ value == BLK_IO_LAT_HIST_DISABLE)
+ host->latency_hist_enabled = value;
+ return count;
+}
+
+static DEVICE_ATTR(latency_hist, S_IRUGO | S_IWUSR,
+ latency_hist_show, latency_hist_store);
+
+void
+mmc_latency_hist_sysfs_init(struct mmc_host *host)
+{
+ if (device_create_file(&host->class_dev, &dev_attr_latency_hist))
+ dev_err(&host->class_dev,
+ "Failed to create latency_hist sysfs entry\n");
+}
+
+void
+mmc_latency_hist_sysfs_exit(struct mmc_host *host)
+{
+ device_remove_file(&host->class_dev, &dev_attr_latency_hist);
+}
+#endif
+
subsys_initcall(mmc_init);
module_exit(mmc_exit);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 848b345..07f8891 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -31,8 +31,6 @@
#include "slot-gpio.h"
#include "pwrseq.h"
-#define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev)
-
static DEFINE_IDA(mmc_host_ida);
static DEFINE_SPINLOCK(mmc_host_lock);
@@ -428,8 +426,13 @@ int mmc_add_host(struct mmc_host *host)
mmc_add_host_debugfs(host);
#endif
+#ifdef CONFIG_BLOCK
+ mmc_latency_hist_sysfs_init(host);
+#endif
+
mmc_start_host(host);
- mmc_register_pm_notifier(host);
+ if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+ mmc_register_pm_notifier(host);
return 0;
}
@@ -446,13 +449,18 @@ EXPORT_SYMBOL(mmc_add_host);
*/
void mmc_remove_host(struct mmc_host *host)
{
- mmc_unregister_pm_notifier(host);
+ if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+ mmc_unregister_pm_notifier(host);
mmc_stop_host(host);
#ifdef CONFIG_DEBUG_FS
mmc_remove_host_debugfs(host);
#endif
+#ifdef CONFIG_BLOCK
+ mmc_latency_hist_sysfs_exit(host);
+#endif
+
device_del(&host->class_dev);
led_trigger_unregister_simple(host->led);
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index 992bf53..bf38533 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -12,6 +12,8 @@
#define _MMC_CORE_HOST_H
#include <linux/mmc/host.h>
+#define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev)
+
int mmc_register_host_class(void);
void mmc_unregister_host_class(void);
@@ -21,5 +23,8 @@ void mmc_retune_hold(struct mmc_host *host);
void mmc_retune_release(struct mmc_host *host);
int mmc_retune(struct mmc_host *host);
+void mmc_latency_hist_sysfs_init(struct mmc_host *host);
+void mmc_latency_hist_sysfs_exit(struct mmc_host *host);
+
#endif
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 97e5130..675c6f2 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -617,6 +617,12 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
card->ext_csd.ffu_capable =
(ext_csd[EXT_CSD_SUPPORTED_MODE] & 0x1) &&
!(ext_csd[EXT_CSD_FW_CONFIG] & 0x1);
+
+ card->ext_csd.pre_eol_info = ext_csd[EXT_CSD_PRE_EOL_INFO];
+ card->ext_csd.device_life_time_est_typ_a =
+ ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A];
+ card->ext_csd.device_life_time_est_typ_b =
+ ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B];
}
out:
return err;
@@ -746,6 +752,11 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
MMC_DEV_ATTR(prv, "0x%x\n", card->cid.prv);
+MMC_DEV_ATTR(rev, "0x%x\n", card->ext_csd.rev);
+MMC_DEV_ATTR(pre_eol_info, "%02x\n", card->ext_csd.pre_eol_info);
+MMC_DEV_ATTR(life_time, "0x%02x 0x%02x\n",
+ card->ext_csd.device_life_time_est_typ_a,
+ card->ext_csd.device_life_time_est_typ_b);
MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial);
MMC_DEV_ATTR(enhanced_area_offset, "%llu\n",
card->ext_csd.enhanced_area_offset);
@@ -799,6 +810,9 @@ static struct attribute *mmc_std_attrs[] = {
&dev_attr_name.attr,
&dev_attr_oemid.attr,
&dev_attr_prv.attr,
+ &dev_attr_rev.attr,
+ &dev_attr_pre_eol_info.attr,
+ &dev_attr_life_time.attr,
&dev_attr_serial.attr,
&dev_attr_enhanced_area_offset.attr,
&dev_attr_enhanced_area_size.attr,
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 7f654c7..ca41ba7 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -855,6 +855,9 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
bool reinit)
{
int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
if (!reinit) {
/*
@@ -881,7 +884,26 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
/*
* Fetch switch information from card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ for (retries = 1; retries <= 3; retries++) {
+ err = mmc_read_switch(card);
+ if (!err) {
+ if (retries > 1) {
+ printk(KERN_WARNING
+ "%s: recovered\n",
+ mmc_hostname(host));
+ }
+ break;
+ } else {
+ printk(KERN_WARNING
+ "%s: read switch failed (attempt %d)\n",
+ mmc_hostname(host), retries);
+ }
+ }
+#else
err = mmc_read_switch(card);
+#endif
+
if (err)
return err;
}
@@ -1079,7 +1101,10 @@ static int mmc_sd_alive(struct mmc_host *host)
*/
static void mmc_sd_detect(struct mmc_host *host)
{
- int err;
+ int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries = 5;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
@@ -1089,7 +1114,23 @@ static void mmc_sd_detect(struct mmc_host *host)
/*
* Just check if our card has been removed.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ while(retries) {
+ err = mmc_send_status(host->card, NULL);
+ if (err) {
+ retries--;
+ udelay(5);
+ continue;
+ }
+ break;
+ }
+ if (!retries) {
+ printk(KERN_ERR "%s(%s): Unable to re-detect card (%d)\n",
+ __func__, mmc_hostname(host), err);
+ }
+#else
err = _mmc_detect_card_removed(host);
+#endif
mmc_put_card(host->card);
@@ -1151,6 +1192,9 @@ static int mmc_sd_suspend(struct mmc_host *host)
static int _mmc_sd_resume(struct mmc_host *host)
{
int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
@@ -1161,7 +1205,23 @@ static int _mmc_sd_resume(struct mmc_host *host)
goto out;
mmc_power_up(host, host->card->ocr);
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, host->card->ocr, host->card);
+
+ if (err) {
+ printk(KERN_ERR "%s: Re-init card rc = %d (retries = %d)\n",
+ mmc_hostname(host), err, retries);
+ mdelay(5);
+ retries--;
+ continue;
+ }
+ break;
+ }
+#else
err = mmc_sd_init_card(host, host->card->ocr, host->card);
+#endif
mmc_card_clr_suspended(host->card);
out:
@@ -1236,6 +1296,9 @@ int mmc_attach_sd(struct mmc_host *host)
{
int err;
u32 ocr, rocr;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
WARN_ON(!host->claimed);
@@ -1278,9 +1341,27 @@ int mmc_attach_sd(struct mmc_host *host)
/*
* Detect and init the card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, rocr, NULL);
+ if (err) {
+ retries--;
+ continue;
+ }
+ break;
+ }
+
+ if (!retries) {
+ printk(KERN_ERR "%s: mmc_sd_init_card() failure (err = %d)\n",
+ mmc_hostname(host), err);
+ goto err;
+ }
+#else
err = mmc_sd_init_card(host, rocr, NULL);
if (err)
goto err;
+#endif
mmc_release_host(host);
err = mmc_add_card(host->card);
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index bd44ba8..b5ec3c8 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -10,6 +10,7 @@
*/
#include <linux/err.h>
+#include <linux/module.h>
#include <linux/pm_runtime.h>
#include <linux/mmc/host.h>
@@ -21,6 +22,7 @@
#include "core.h"
#include "bus.h"
+#include "host.h"
#include "sd.h"
#include "sdio_bus.h"
#include "mmc_ops.h"
@@ -28,6 +30,10 @@
#include "sdio_ops.h"
#include "sdio_cis.h"
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/sdio_ids.h>
+#endif
+
static int sdio_read_fbr(struct sdio_func *func)
{
int ret;
@@ -697,19 +703,35 @@ static int mmc_sdio_init_card(struct mmc_host *host, u32 ocr,
goto finish;
}
- /*
- * Read the common registers.
- */
- err = sdio_read_cccr(card, ocr);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cccr)
+ memcpy(&card->cccr, host->embedded_sdio_data.cccr, sizeof(struct sdio_cccr));
+ else {
+#endif
+ /*
+ * Read the common registers.
+ */
+ err = sdio_read_cccr(card, ocr);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
- /*
- * Read the common CIS tuples.
- */
- err = sdio_read_common_cis(card);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cis)
+ memcpy(&card->cis, host->embedded_sdio_data.cis, sizeof(struct sdio_cis));
+ else {
+#endif
+ /*
+ * Read the common CIS tuples.
+ */
+ err = sdio_read_common_cis(card);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
if (oldcard) {
int same = (card->cis.vendor == oldcard->cis.vendor &&
@@ -1118,14 +1140,36 @@ int mmc_attach_sdio(struct mmc_host *host)
funcs = (ocr & 0x70000000) >> 28;
card->sdio_funcs = 0;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs)
+ card->sdio_funcs = funcs = host->embedded_sdio_data.num_funcs;
+#endif
+
/*
* Initialize (but don't add) all present functions.
*/
for (i = 0; i < funcs; i++, card->sdio_funcs++) {
- err = sdio_init_func(host->card, i + 1);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs) {
+ struct sdio_func *tmp;
+ tmp = sdio_alloc_func(host->card);
+ if (IS_ERR(tmp))
+ goto remove;
+ tmp->num = (i + 1);
+ card->sdio_func[i] = tmp;
+ tmp->class = host->embedded_sdio_data.funcs[i].f_class;
+ tmp->max_blksize = host->embedded_sdio_data.funcs[i].f_maxblksize;
+ tmp->vendor = card->cis.vendor;
+ tmp->device = card->cis.device;
+ } else {
+#endif
+ err = sdio_init_func(host->card, i + 1);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
/*
* Enable Runtime PM for this func (if supported)
*/
@@ -1173,3 +1217,42 @@ int mmc_attach_sdio(struct mmc_host *host)
return err;
}
+int sdio_reset_comm(struct mmc_card *card)
+{
+ struct mmc_host *host = card->host;
+ u32 ocr;
+ u32 rocr;
+ int err;
+
+ printk("%s():\n", __func__);
+ mmc_claim_host(host);
+
+ mmc_retune_disable(host);
+
+ mmc_go_idle(host);
+
+ mmc_set_clock(host, host->f_min);
+
+ err = mmc_send_io_op_cond(host, 0, &ocr);
+ if (err)
+ goto err;
+
+ rocr = mmc_select_voltage(host, ocr);
+ if (!rocr) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = mmc_sdio_init_card(host, rocr, card, 0);
+ if (err)
+ goto err;
+
+ mmc_release_host(host);
+ return 0;
+err:
+ printk("%s: Error resetting SDIO communications (%d)\n",
+ mmc_hostname(host), err);
+ mmc_release_host(host);
+ return err;
+}
+EXPORT_SYMBOL(sdio_reset_comm);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index d56a3b6..528524a 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -28,6 +28,10 @@
#include "sdio_cis.h"
#include "sdio_bus.h"
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/host.h>
+#endif
+
#define to_sdio_driver(d) container_of(d, struct sdio_driver, drv)
/* show configuration fields */
@@ -263,7 +267,14 @@ static void sdio_release_func(struct device *dev)
{
struct sdio_func *func = dev_to_sdio_func(dev);
- sdio_free_func_cis(func);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ /*
+ * If this device is embedded then we never allocated
+ * cis tables for this func
+ */
+ if (!func->card->host->embedded_sdio_data.funcs)
+#endif
+ sdio_free_func_cis(func);
kfree(func->info);
kfree(func->tmpbuf);
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
index 406e5f0..3734cba 100644
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -390,6 +390,39 @@ u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret)
EXPORT_SYMBOL_GPL(sdio_readb);
/**
+ * sdio_readb_ext - read a single byte from a SDIO function
+ * @func: SDIO function to access
+ * @addr: address to read
+ * @err_ret: optional status value from transfer
+ * @in: value to add to argument
+ *
+ * Reads a single byte from the address space of a given SDIO
+ * function. If there is a problem reading the address, 0xff
+ * is returned and @err_ret will contain the error code.
+ */
+unsigned char sdio_readb_ext(struct sdio_func *func, unsigned int addr,
+ int *err_ret, unsigned in)
+{
+ int ret;
+ unsigned char val;
+
+ BUG_ON(!func);
+
+ if (err_ret)
+ *err_ret = 0;
+
+ ret = mmc_io_rw_direct(func->card, 0, func->num, addr, (u8)in, &val);
+ if (ret) {
+ if (err_ret)
+ *err_ret = ret;
+ return 0xFF;
+ }
+
+ return val;
+}
+EXPORT_SYMBOL_GPL(sdio_readb_ext);
+
+/**
* sdio_writeb - write a single byte to a SDIO function
* @func: SDIO function to access
* @b: byte to write
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 7c887f1..62fd690 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -431,7 +431,7 @@ static int block2mtd_setup2(const char *val)
}
-static int block2mtd_setup(const char *val, struct kernel_param *kp)
+static int block2mtd_setup(const char *val, const struct kernel_param *kp)
{
#ifdef MODULE
return block2mtd_setup2(val);
diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c
index 9734e69..d312c1b 100644
--- a/drivers/mtd/devices/phram.c
+++ b/drivers/mtd/devices/phram.c
@@ -269,7 +269,7 @@ static int phram_setup(const char *val)
return ret;
}
-static int phram_param_call(const char *val, struct kernel_param *kp)
+static int phram_param_call(const char *val, const struct kernel_param *kp)
{
#ifdef MODULE
return phram_setup(val);
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index b254090..50ee1ba 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -1,3 +1,10 @@
+config MTD_NAND_IDS
+ tristate "Include chip ids for known NAND devices."
+ depends on MTD
+ help
+ Useful for NAND drivers that do not use the NAND subsystem but
+ still like to take advantage of the known chip information.
+
config MTD_NAND_ECC
tristate
@@ -109,9 +116,6 @@
config MTD_NAND_OMAP_BCH_BUILD
def_tristate MTD_NAND_OMAP2 && MTD_NAND_OMAP_BCH
-config MTD_NAND_IDS
- tristate
-
config MTD_NAND_RICOH
tristate "Ricoh xD card reader"
default n
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 211ee13..6f06f8b5 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -1403,7 +1403,7 @@ static int __init bytes_str_to_int(const char *str)
* This function returns zero in case of success and a negative error code in
* case of error.
*/
-static int __init ubi_mtd_param_parse(const char *val, struct kernel_param *kp)
+static int __init ubi_mtd_param_parse(const char *val, const struct kernel_param *kp)
{
int i, len;
struct mtd_dev_param *p;
diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig
index 1373c6d..282aec4 100644
--- a/drivers/net/ppp/Kconfig
+++ b/drivers/net/ppp/Kconfig
@@ -149,6 +149,23 @@
tunnels. L2TP is replacing PPTP for VPN uses.
if TTY
+config PPPOLAC
+ tristate "PPP on L2TP Access Concentrator"
+ depends on PPP && INET
+ help
+ L2TP (RFC 2661) is a tunneling protocol widely used in virtual private
+ networks. This driver handles L2TP data packets between a UDP socket
+ and a PPP channel, but only permits one session per socket. Thus it is
+ fairly simple and suited for clients.
+
+config PPPOPNS
+ tristate "PPP on PPTP Network Server"
+ depends on PPP && INET
+ help
+ PPTP (RFC 2637) is a tunneling protocol widely used in virtual private
+ networks. This driver handles PPTP data packets between a RAW socket
+ and a PPP channel. It is fairly simple and easy to use.
+
config PPP_ASYNC
tristate "PPP support for async serial ports"
depends on PPP
diff --git a/drivers/net/ppp/Makefile b/drivers/net/ppp/Makefile
index a6b6297..d283d03c 100644
--- a/drivers/net/ppp/Makefile
+++ b/drivers/net/ppp/Makefile
@@ -11,3 +11,5 @@
obj-$(CONFIG_PPPOE) += pppox.o pppoe.o
obj-$(CONFIG_PPPOL2TP) += pppox.o
obj-$(CONFIG_PPTP) += pppox.o pptp.o
+obj-$(CONFIG_PPPOLAC) += pppox.o pppolac.o
+obj-$(CONFIG_PPPOPNS) += pppox.o pppopns.o
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index cef40de..a27ecd6 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -770,7 +770,7 @@ process_input_packet(struct asyncppp *ap)
{
struct sk_buff *skb;
unsigned char *p;
- unsigned int len, fcs, proto;
+ unsigned int len, fcs;
skb = ap->rpkt;
if (ap->state & (SC_TOSS | SC_ESCAPE))
@@ -799,14 +799,14 @@ process_input_packet(struct asyncppp *ap)
goto err;
p = skb_pull(skb, 2);
}
- proto = p[0];
- if (proto & 1) {
- /* protocol is compressed */
- skb_push(skb, 1)[0] = 0;
- } else {
+
+ /* If protocol field is not compressed, it can be LCP packet */
+ if (!(p[0] & 0x01)) {
+ unsigned int proto;
+
if (skb->len < 2)
goto err;
- proto = (proto << 8) + p[1];
+ proto = (p[0] << 8) + p[1];
if (proto == PPP_LCP)
async_lcp_peek(ap, p, skb->len, 1);
}
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 801bab5..d209d5f 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1980,6 +1980,46 @@ ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
ppp_recv_unlock(ppp);
}
+/**
+ * __ppp_decompress_proto - Decompress protocol field, slim version.
+ * @skb: Socket buffer where protocol field should be decompressed. It must have
+ * at least 1 byte of head room and 1 byte of linear data. First byte of
+ * data must be a protocol field byte.
+ *
+ * Decompress protocol field in PPP header if it's compressed, e.g. when
+ * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data
+ * length are done in this function.
+ */
+static void __ppp_decompress_proto(struct sk_buff *skb)
+{
+ if (skb->data[0] & 0x01)
+ *(u8 *)skb_push(skb, 1) = 0x00;
+}
+
+/**
+ * ppp_decompress_proto - Check skb data room and decompress protocol field.
+ * @skb: Socket buffer where protocol field should be decompressed. First byte
+ * of data must be a protocol field byte.
+ *
+ * Decompress protocol field in PPP header if it's compressed, e.g. when
+ * Protocol-Field-Compression (PFC) was negotiated. This function also makes
+ * sure that skb data room is sufficient for Protocol field, before and after
+ * decompression.
+ *
+ * Return: true - decompressed successfully, false - not enough room in skb.
+ */
+static bool ppp_decompress_proto(struct sk_buff *skb)
+{
+ /* At least one byte should be present (if protocol is compressed) */
+ if (!pskb_may_pull(skb, 1))
+ return false;
+
+ __ppp_decompress_proto(skb);
+
+ /* Protocol field should occupy 2 bytes when not compressed */
+ return pskb_may_pull(skb, 2);
+}
+
void
ppp_input(struct ppp_channel *chan, struct sk_buff *skb)
{
@@ -1992,7 +2032,7 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb)
}
read_lock_bh(&pch->upl);
- if (!pskb_may_pull(skb, 2)) {
+ if (!ppp_decompress_proto(skb)) {
kfree_skb(skb);
if (pch->ppp) {
++pch->ppp->dev->stats.rx_length_errors;
@@ -2089,6 +2129,9 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR)
goto err;
+ /* At this point the "Protocol" field MUST be decompressed, either in
+ * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame().
+ */
proto = PPP_PROTO(skb);
switch (proto) {
case PPP_VJC_COMP:
@@ -2260,6 +2303,9 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb)
skb_put(skb, len);
skb_pull(skb, 2); /* pull off the A/C bytes */
+ /* Don't call __ppp_decompress_proto() here, but instead rely on
+ * corresponding algo (mppe/bsd/deflate) to decompress it.
+ */
} else {
/* Uncompressed frame - pass to decompressor so it
can update its dictionary if necessary. */
@@ -2305,9 +2351,11 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
/*
* Do protocol ID decompression on the first fragment of each packet.
+ * We have to do that here, because ppp_receive_nonmp_frame() expects
+ * decompressed protocol field.
*/
- if ((PPP_MP_CB(skb)->BEbits & B) && (skb->data[0] & 1))
- *skb_push(skb, 1) = 0;
+ if (PPP_MP_CB(skb)->BEbits & B)
+ __ppp_decompress_proto(skb);
/*
* Expand sequence number to 32 bits, making it as close
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 925d3e2..48436c8 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -709,11 +709,10 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf,
p = skb_pull(skb, 2);
}
- /* decompress protocol field if compressed */
- if (p[0] & 1) {
- /* protocol is compressed */
- skb_push(skb, 1)[0] = 0;
- } else if (skb->len < 2)
+ /* PPP packet length should be >= 2 bytes when protocol field is not
+ * compressed.
+ */
+ if (!(p[0] & 0x01) && skb->len < 2)
goto err;
/* queue the frame to be processed */
diff --git a/drivers/net/ppp/pppolac.c b/drivers/net/ppp/pppolac.c
new file mode 100644
index 0000000..3a45cf8
--- /dev/null
+++ b/drivers/net/ppp/pppolac.c
@@ -0,0 +1,450 @@
+/* drivers/net/pppolac.c
+ *
+ * Driver for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles L2TP data packets between a UDP socket and a PPP channel.
+ * The socket must keep connected, and only one session per socket is permitted.
+ * Sequencing of outgoing packets is controlled by LNS. Incoming packets with
+ * sequences are reordered within a sliding window of one second. Currently
+ * reordering only happens when a packet is received. It is done for simplicity
+ * since no additional locks or threads are required. This driver only works on
+ * IPv4 due to the lack of UDP encapsulation support in IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/udp.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <net/tcp_states.h>
+#include <asm/uaccess.h>
+
+#define L2TP_CONTROL_BIT 0x80
+#define L2TP_LENGTH_BIT 0x40
+#define L2TP_SEQUENCE_BIT 0x08
+#define L2TP_OFFSET_BIT 0x02
+#define L2TP_VERSION 0x02
+#define L2TP_VERSION_MASK 0x0F
+
+#define PPP_ADDR 0xFF
+#define PPP_CTRL 0x03
+
+union unaligned {
+ __u32 u32;
+} __attribute__((packed));
+
+static inline union unaligned *unaligned(void *ptr)
+{
+ return (union unaligned *)ptr;
+}
+
+struct meta {
+ __u32 sequence;
+ __u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+ return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
+{
+ struct sock *sk = (struct sock *)sk_udp->sk_user_data;
+ struct pppolac_opt *opt = &pppox_sk(sk)->proto.lac;
+ struct meta *meta = skb_meta(skb);
+ __u32 now = jiffies;
+ __u8 bits;
+ __u8 *ptr;
+
+ /* Drop the packet if L2TP header is missing. */
+ if (skb->len < sizeof(struct udphdr) + 6)
+ goto drop;
+
+ /* Put it back if it is a control packet. */
+ if (skb->data[sizeof(struct udphdr)] & L2TP_CONTROL_BIT)
+ return opt->backlog_rcv(sk_udp, skb);
+
+ /* Skip UDP header. */
+ skb_pull(skb, sizeof(struct udphdr));
+
+ /* Check the version. */
+ if ((skb->data[1] & L2TP_VERSION_MASK) != L2TP_VERSION)
+ goto drop;
+ bits = skb->data[0];
+ ptr = &skb->data[2];
+
+ /* Check the length if it is present. */
+ if (bits & L2TP_LENGTH_BIT) {
+ if ((ptr[0] << 8 | ptr[1]) != skb->len)
+ goto drop;
+ ptr += 2;
+ }
+
+ /* Skip all fields including optional ones. */
+ if (!skb_pull(skb, 6 + (bits & L2TP_SEQUENCE_BIT ? 4 : 0) +
+ (bits & L2TP_LENGTH_BIT ? 2 : 0) +
+ (bits & L2TP_OFFSET_BIT ? 2 : 0)))
+ goto drop;
+
+ /* Skip the offset padding if it is present. */
+ if (bits & L2TP_OFFSET_BIT &&
+ !skb_pull(skb, skb->data[-2] << 8 | skb->data[-1]))
+ goto drop;
+
+ /* Check the tunnel and the session. */
+ if (unaligned(ptr)->u32 != opt->local)
+ goto drop;
+
+ /* Check the sequence if it is present. */
+ if (bits & L2TP_SEQUENCE_BIT) {
+ meta->sequence = ptr[4] << 8 | ptr[5];
+ if ((__s16)(meta->sequence - opt->recv_sequence) < 0)
+ goto drop;
+ }
+
+ /* Skip PPP address and control if they are present. */
+ if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+ skb->data[1] == PPP_CTRL)
+ skb_pull(skb, 2);
+
+ /* Fix PPP protocol if it is compressed. */
+ if (skb->len >= 1 && skb->data[0] & 1)
+ skb_push(skb, 1)[0] = 0;
+
+ /* Drop the packet if PPP protocol is missing. */
+ if (skb->len < 2)
+ goto drop;
+
+ /* Perform reordering if sequencing is enabled. */
+ atomic_set(&opt->sequencing, bits & L2TP_SEQUENCE_BIT);
+ if (bits & L2TP_SEQUENCE_BIT) {
+ struct sk_buff *skb1;
+
+ /* Insert the packet into receive queue in order. */
+ skb_set_owner_r(skb, sk);
+ skb_queue_walk(&sk->sk_receive_queue, skb1) {
+ struct meta *meta1 = skb_meta(skb1);
+ __s16 order = meta->sequence - meta1->sequence;
+ if (order == 0)
+ goto drop;
+ if (order < 0) {
+ meta->timestamp = meta1->timestamp;
+ skb_insert(skb1, skb, &sk->sk_receive_queue);
+ skb = NULL;
+ break;
+ }
+ }
+ if (skb) {
+ meta->timestamp = now;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ }
+
+ /* Remove packets from receive queue as long as
+ * 1. the receive buffer is full,
+ * 2. they are queued longer than one second, or
+ * 3. there are no missing packets before them. */
+ skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+ meta = skb_meta(skb);
+ if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+ now - meta->timestamp < HZ &&
+ meta->sequence != opt->recv_sequence)
+ break;
+ skb_unlink(skb, &sk->sk_receive_queue);
+ opt->recv_sequence = (__u16)(meta->sequence + 1);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ }
+ return NET_RX_SUCCESS;
+ }
+
+ /* Flush receive queue if sequencing is disabled. */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ return NET_RX_SUCCESS;
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static int pppolac_recv(struct sock *sk_udp, struct sk_buff *skb)
+{
+ sock_hold(sk_udp);
+ sk_receive_skb(sk_udp, skb, 0);
+ return 0;
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppolac_xmit_core(struct work_struct *delivery_work)
+{
+ mm_segment_t old_fs = get_fs();
+ struct sk_buff *skb;
+
+ set_fs(KERNEL_DS);
+ while ((skb = skb_dequeue(&delivery_queue))) {
+ struct sock *sk_udp = skb->sk;
+ struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+ struct msghdr msg = {
+ .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+ };
+
+ iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1,
+ skb->len);
+ sk_udp->sk_prot->sendmsg(sk_udp, &msg, skb->len);
+ kfree_skb(skb);
+ }
+ set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppolac_xmit_core);
+
+static int pppolac_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ struct sock *sk_udp = (struct sock *)chan->private;
+ struct pppolac_opt *opt = &pppox_sk(sk_udp->sk_user_data)->proto.lac;
+
+ /* Install PPP address and control. */
+ skb_push(skb, 2);
+ skb->data[0] = PPP_ADDR;
+ skb->data[1] = PPP_CTRL;
+
+ /* Install L2TP header. */
+ if (atomic_read(&opt->sequencing)) {
+ skb_push(skb, 10);
+ skb->data[0] = L2TP_SEQUENCE_BIT;
+ skb->data[6] = opt->xmit_sequence >> 8;
+ skb->data[7] = opt->xmit_sequence;
+ skb->data[8] = 0;
+ skb->data[9] = 0;
+ opt->xmit_sequence++;
+ } else {
+ skb_push(skb, 6);
+ skb->data[0] = 0;
+ }
+ skb->data[1] = L2TP_VERSION;
+ unaligned(&skb->data[2])->u32 = opt->remote;
+
+ /* Now send the packet via the delivery queue. */
+ skb_set_owner_w(skb, sk_udp);
+ skb_queue_tail(&delivery_queue, skb);
+ schedule_work(&delivery_work);
+ return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppolac_channel_ops = {
+ .start_xmit = pppolac_xmit,
+};
+
+static int pppolac_connect(struct socket *sock, struct sockaddr *useraddr,
+ int addrlen, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct sockaddr_pppolac *addr = (struct sockaddr_pppolac *)useraddr;
+ struct socket *sock_udp = NULL;
+ struct sock *sk_udp;
+ int error;
+
+ if (addrlen != sizeof(struct sockaddr_pppolac) ||
+ !addr->local.tunnel || !addr->local.session ||
+ !addr->remote.tunnel || !addr->remote.session) {
+ return -EINVAL;
+ }
+
+ lock_sock(sk);
+ error = -EALREADY;
+ if (sk->sk_state != PPPOX_NONE)
+ goto out;
+
+ sock_udp = sockfd_lookup(addr->udp_socket, &error);
+ if (!sock_udp)
+ goto out;
+ sk_udp = sock_udp->sk;
+ lock_sock(sk_udp);
+
+ /* Remove this check when IPv6 supports UDP encapsulation. */
+ error = -EAFNOSUPPORT;
+ if (sk_udp->sk_family != AF_INET)
+ goto out;
+ error = -EPROTONOSUPPORT;
+ if (sk_udp->sk_protocol != IPPROTO_UDP)
+ goto out;
+ error = -EDESTADDRREQ;
+ if (sk_udp->sk_state != TCP_ESTABLISHED)
+ goto out;
+ error = -EBUSY;
+ if (udp_sk(sk_udp)->encap_type || sk_udp->sk_user_data)
+ goto out;
+ if (!sk_udp->sk_bound_dev_if) {
+ struct dst_entry *dst = sk_dst_get(sk_udp);
+ error = -ENODEV;
+ if (!dst)
+ goto out;
+ sk_udp->sk_bound_dev_if = dst->dev->ifindex;
+ dst_release(dst);
+ }
+
+ po->chan.hdrlen = 12;
+ po->chan.private = sk_udp;
+ po->chan.ops = &pppolac_channel_ops;
+ po->chan.mtu = PPP_MRU - 80;
+ po->proto.lac.local = unaligned(&addr->local)->u32;
+ po->proto.lac.remote = unaligned(&addr->remote)->u32;
+ atomic_set(&po->proto.lac.sequencing, 1);
+ po->proto.lac.backlog_rcv = sk_udp->sk_backlog_rcv;
+
+ error = ppp_register_channel(&po->chan);
+ if (error)
+ goto out;
+
+ sk->sk_state = PPPOX_CONNECTED;
+ udp_sk(sk_udp)->encap_type = UDP_ENCAP_L2TPINUDP;
+ udp_sk(sk_udp)->encap_rcv = pppolac_recv;
+ sk_udp->sk_backlog_rcv = pppolac_recv_core;
+ sk_udp->sk_user_data = sk;
+out:
+ if (sock_udp) {
+ release_sock(sk_udp);
+ if (error)
+ sockfd_put(sock_udp);
+ }
+ release_sock(sk);
+ return error;
+}
+
+static int pppolac_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ release_sock(sk);
+ return -EBADF;
+ }
+
+ if (sk->sk_state != PPPOX_NONE) {
+ struct sock *sk_udp = (struct sock *)pppox_sk(sk)->chan.private;
+ lock_sock(sk_udp);
+ skb_queue_purge(&sk->sk_receive_queue);
+ pppox_unbind_sock(sk);
+ udp_sk(sk_udp)->encap_type = 0;
+ udp_sk(sk_udp)->encap_rcv = NULL;
+ sk_udp->sk_backlog_rcv = pppox_sk(sk)->proto.lac.backlog_rcv;
+ sk_udp->sk_user_data = NULL;
+ release_sock(sk_udp);
+ sockfd_put(sk_udp->sk_socket);
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppolac_proto = {
+ .name = "PPPOLAC",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppolac_proto_ops = {
+ .family = PF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppolac_release,
+ .bind = sock_no_bind,
+ .connect = pppolac_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = sock_no_poll,
+ .ioctl = pppox_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = sock_no_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = sock_no_mmap,
+};
+
+static int pppolac_create(struct net *net, struct socket *sock, int kern)
+{
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppolac_proto, kern);
+ if (!sk)
+ return -ENOMEM;
+
+ sock_init_data(sock, sk);
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppolac_proto_ops;
+ sk->sk_protocol = PX_PROTO_OLAC;
+ sk->sk_state = PPPOX_NONE;
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppolac_pppox_proto = {
+ .create = pppolac_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init pppolac_init(void)
+{
+ int error;
+
+ error = proto_register(&pppolac_proto, 0);
+ if (error)
+ return error;
+
+ error = register_pppox_proto(PX_PROTO_OLAC, &pppolac_pppox_proto);
+ if (error)
+ proto_unregister(&pppolac_proto);
+ else
+ skb_queue_head_init(&delivery_queue);
+ return error;
+}
+
+static void __exit pppolac_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OLAC);
+ proto_unregister(&pppolac_proto);
+}
+
+module_init(pppolac_init);
+module_exit(pppolac_exit);
+
+MODULE_DESCRIPTION("PPP on L2TP Access Concentrator (PPPoLAC)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/pppopns.c b/drivers/net/ppp/pppopns.c
new file mode 100644
index 0000000..cdb4fa1
--- /dev/null
+++ b/drivers/net/ppp/pppopns.c
@@ -0,0 +1,429 @@
+/* drivers/net/pppopns.c
+ *
+ * Driver for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles PPTP data packets between a RAW socket and a PPP channel.
+ * The socket is created in the kernel space and connected to the same address
+ * of the control socket. Outgoing packets are always sent with sequences but
+ * without acknowledgements. Incoming packets with sequences are reordered
+ * within a sliding window of one second. Currently reordering only happens when
+ * a packet is received. It is done for simplicity since no additional locks or
+ * threads are required. This driver should work on both IPv4 and IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/ppp_defs.h>
+#include <linux/if.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <asm/uaccess.h>
+
+#define GRE_HEADER_SIZE 8
+
+#define PPTP_GRE_BITS htons(0x2001)
+#define PPTP_GRE_BITS_MASK htons(0xEF7F)
+#define PPTP_GRE_SEQ_BIT htons(0x1000)
+#define PPTP_GRE_ACK_BIT htons(0x0080)
+#define PPTP_GRE_TYPE htons(0x880B)
+
+#define PPP_ADDR 0xFF
+#define PPP_CTRL 0x03
+
+struct header {
+ __u16 bits;
+ __u16 type;
+ __u16 length;
+ __u16 call;
+ __u32 sequence;
+} __attribute__((packed));
+
+struct meta {
+ __u32 sequence;
+ __u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+ return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
+{
+ struct sock *sk = (struct sock *)sk_raw->sk_user_data;
+ struct pppopns_opt *opt = &pppox_sk(sk)->proto.pns;
+ struct meta *meta = skb_meta(skb);
+ __u32 now = jiffies;
+ struct header *hdr;
+
+ /* Skip transport header */
+ skb_pull(skb, skb_transport_header(skb) - skb->data);
+
+ /* Drop the packet if GRE header is missing. */
+ if (skb->len < GRE_HEADER_SIZE)
+ goto drop;
+ hdr = (struct header *)skb->data;
+
+ /* Check the header. */
+ if (hdr->type != PPTP_GRE_TYPE || hdr->call != opt->local ||
+ (hdr->bits & PPTP_GRE_BITS_MASK) != PPTP_GRE_BITS)
+ goto drop;
+
+ /* Skip all fields including optional ones. */
+ if (!skb_pull(skb, GRE_HEADER_SIZE +
+ (hdr->bits & PPTP_GRE_SEQ_BIT ? 4 : 0) +
+ (hdr->bits & PPTP_GRE_ACK_BIT ? 4 : 0)))
+ goto drop;
+
+ /* Check the length. */
+ if (skb->len != ntohs(hdr->length))
+ goto drop;
+
+ /* Check the sequence if it is present. */
+ if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+ meta->sequence = ntohl(hdr->sequence);
+ if ((__s32)(meta->sequence - opt->recv_sequence) < 0)
+ goto drop;
+ }
+
+ /* Skip PPP address and control if they are present. */
+ if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+ skb->data[1] == PPP_CTRL)
+ skb_pull(skb, 2);
+
+ /* Fix PPP protocol if it is compressed. */
+ if (skb->len >= 1 && skb->data[0] & 1)
+ skb_push(skb, 1)[0] = 0;
+
+ /* Drop the packet if PPP protocol is missing. */
+ if (skb->len < 2)
+ goto drop;
+
+ /* Perform reordering if sequencing is enabled. */
+ if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+ struct sk_buff *skb1;
+
+ /* Insert the packet into receive queue in order. */
+ skb_set_owner_r(skb, sk);
+ skb_queue_walk(&sk->sk_receive_queue, skb1) {
+ struct meta *meta1 = skb_meta(skb1);
+ __s32 order = meta->sequence - meta1->sequence;
+ if (order == 0)
+ goto drop;
+ if (order < 0) {
+ meta->timestamp = meta1->timestamp;
+ skb_insert(skb1, skb, &sk->sk_receive_queue);
+ skb = NULL;
+ break;
+ }
+ }
+ if (skb) {
+ meta->timestamp = now;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ }
+
+ /* Remove packets from receive queue as long as
+ * 1. the receive buffer is full,
+ * 2. they are queued longer than one second, or
+ * 3. there are no missing packets before them. */
+ skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+ meta = skb_meta(skb);
+ if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+ now - meta->timestamp < HZ &&
+ meta->sequence != opt->recv_sequence)
+ break;
+ skb_unlink(skb, &sk->sk_receive_queue);
+ opt->recv_sequence = meta->sequence + 1;
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ }
+ return NET_RX_SUCCESS;
+ }
+
+ /* Flush receive queue if sequencing is disabled. */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ return NET_RX_SUCCESS;
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static void pppopns_recv(struct sock *sk_raw)
+{
+ struct sk_buff *skb;
+ while ((skb = skb_dequeue(&sk_raw->sk_receive_queue))) {
+ sock_hold(sk_raw);
+ sk_receive_skb(sk_raw, skb, 0);
+ }
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppopns_xmit_core(struct work_struct *delivery_work)
+{
+ mm_segment_t old_fs = get_fs();
+ struct sk_buff *skb;
+
+ set_fs(KERNEL_DS);
+ while ((skb = skb_dequeue(&delivery_queue))) {
+ struct sock *sk_raw = skb->sk;
+ struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+ struct msghdr msg = {
+ .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+ };
+
+ iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1,
+ skb->len);
+ sk_raw->sk_prot->sendmsg(sk_raw, &msg, skb->len);
+ kfree_skb(skb);
+ }
+ set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppopns_xmit_core);
+
+static int pppopns_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ struct sock *sk_raw = (struct sock *)chan->private;
+ struct pppopns_opt *opt = &pppox_sk(sk_raw->sk_user_data)->proto.pns;
+ struct header *hdr;
+ __u16 length;
+
+ /* Install PPP address and control. */
+ skb_push(skb, 2);
+ skb->data[0] = PPP_ADDR;
+ skb->data[1] = PPP_CTRL;
+ length = skb->len;
+
+ /* Install PPTP GRE header. */
+ hdr = (struct header *)skb_push(skb, 12);
+ hdr->bits = PPTP_GRE_BITS | PPTP_GRE_SEQ_BIT;
+ hdr->type = PPTP_GRE_TYPE;
+ hdr->length = htons(length);
+ hdr->call = opt->remote;
+ hdr->sequence = htonl(opt->xmit_sequence);
+ opt->xmit_sequence++;
+
+ /* Now send the packet via the delivery queue. */
+ skb_set_owner_w(skb, sk_raw);
+ skb_queue_tail(&delivery_queue, skb);
+ schedule_work(&delivery_work);
+ return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppopns_channel_ops = {
+ .start_xmit = pppopns_xmit,
+};
+
+static int pppopns_connect(struct socket *sock, struct sockaddr *useraddr,
+ int addrlen, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct sockaddr_pppopns *addr = (struct sockaddr_pppopns *)useraddr;
+ struct sockaddr_storage ss;
+ struct socket *sock_tcp = NULL;
+ struct socket *sock_raw = NULL;
+ struct sock *sk_tcp;
+ struct sock *sk_raw;
+ int error;
+
+ if (addrlen != sizeof(struct sockaddr_pppopns))
+ return -EINVAL;
+
+ lock_sock(sk);
+ error = -EALREADY;
+ if (sk->sk_state != PPPOX_NONE)
+ goto out;
+
+ sock_tcp = sockfd_lookup(addr->tcp_socket, &error);
+ if (!sock_tcp)
+ goto out;
+ sk_tcp = sock_tcp->sk;
+ error = -EPROTONOSUPPORT;
+ if (sk_tcp->sk_protocol != IPPROTO_TCP)
+ goto out;
+ addrlen = sizeof(struct sockaddr_storage);
+ error = kernel_getpeername(sock_tcp, (struct sockaddr *)&ss, &addrlen);
+ if (error)
+ goto out;
+ if (!sk_tcp->sk_bound_dev_if) {
+ struct dst_entry *dst = sk_dst_get(sk_tcp);
+ error = -ENODEV;
+ if (!dst)
+ goto out;
+ sk_tcp->sk_bound_dev_if = dst->dev->ifindex;
+ dst_release(dst);
+ }
+
+ error = sock_create(ss.ss_family, SOCK_RAW, IPPROTO_GRE, &sock_raw);
+ if (error)
+ goto out;
+ sk_raw = sock_raw->sk;
+ sk_raw->sk_bound_dev_if = sk_tcp->sk_bound_dev_if;
+ error = kernel_connect(sock_raw, (struct sockaddr *)&ss, addrlen, 0);
+ if (error)
+ goto out;
+
+ po->chan.hdrlen = 14;
+ po->chan.private = sk_raw;
+ po->chan.ops = &pppopns_channel_ops;
+ po->chan.mtu = PPP_MRU - 80;
+ po->proto.pns.local = addr->local;
+ po->proto.pns.remote = addr->remote;
+ po->proto.pns.data_ready = sk_raw->sk_data_ready;
+ po->proto.pns.backlog_rcv = sk_raw->sk_backlog_rcv;
+
+ error = ppp_register_channel(&po->chan);
+ if (error)
+ goto out;
+
+ sk->sk_state = PPPOX_CONNECTED;
+ lock_sock(sk_raw);
+ sk_raw->sk_data_ready = pppopns_recv;
+ sk_raw->sk_backlog_rcv = pppopns_recv_core;
+ sk_raw->sk_user_data = sk;
+ release_sock(sk_raw);
+out:
+ if (sock_tcp)
+ sockfd_put(sock_tcp);
+ if (error && sock_raw)
+ sock_release(sock_raw);
+ release_sock(sk);
+ return error;
+}
+
+static int pppopns_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ release_sock(sk);
+ return -EBADF;
+ }
+
+ if (sk->sk_state != PPPOX_NONE) {
+ struct sock *sk_raw = (struct sock *)pppox_sk(sk)->chan.private;
+ lock_sock(sk_raw);
+ skb_queue_purge(&sk->sk_receive_queue);
+ pppox_unbind_sock(sk);
+ sk_raw->sk_data_ready = pppox_sk(sk)->proto.pns.data_ready;
+ sk_raw->sk_backlog_rcv = pppox_sk(sk)->proto.pns.backlog_rcv;
+ sk_raw->sk_user_data = NULL;
+ release_sock(sk_raw);
+ sock_release(sk_raw->sk_socket);
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppopns_proto = {
+ .name = "PPPOPNS",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppopns_proto_ops = {
+ .family = PF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppopns_release,
+ .bind = sock_no_bind,
+ .connect = pppopns_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = sock_no_poll,
+ .ioctl = pppox_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = sock_no_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = sock_no_mmap,
+};
+
+static int pppopns_create(struct net *net, struct socket *sock, int kern)
+{
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppopns_proto, kern);
+ if (!sk)
+ return -ENOMEM;
+
+ sock_init_data(sock, sk);
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppopns_proto_ops;
+ sk->sk_protocol = PX_PROTO_OPNS;
+ sk->sk_state = PPPOX_NONE;
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppopns_pppox_proto = {
+ .create = pppopns_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init pppopns_init(void)
+{
+ int error;
+
+ error = proto_register(&pppopns_proto, 0);
+ if (error)
+ return error;
+
+ error = register_pppox_proto(PX_PROTO_OPNS, &pppopns_pppox_proto);
+ if (error)
+ proto_unregister(&pppopns_proto);
+ else
+ skb_queue_head_init(&delivery_queue);
+ return error;
+}
+
+static void __exit pppopns_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OPNS);
+ proto_unregister(&pppopns_proto);
+}
+
+module_init(pppopns_init);
+module_exit(pppopns_exit);
+
+MODULE_DESCRIPTION("PPP on PPTP Network Server (PPPoPNS)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index fa14a67..c3a9101 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -326,11 +326,6 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb)
skb_pull(skb, 2);
}
- if ((*skb->data) & 1) {
- /* protocol is compressed */
- skb_push(skb, 1)[0] = 0;
- }
-
skb->ip_summed = CHECKSUM_NONE;
skb_set_network_header(skb, skb->head-skb->data);
ppp_input(&po->chan, skb);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 44b16d9..682cb5b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2036,6 +2036,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
int le;
int ret;
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+ if (cmd != TUNGETIFF && !capable(CAP_NET_ADMIN)) {
+ return -EPERM;
+ }
+#endif
+
if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 8c8edaf..c7b29ab 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -100,4 +100,11 @@
If you choose to build a module, it'll be called rndis_wlan.
+config VIRT_WIFI
+ tristate "Wifi wrapper for ethernet drivers"
+ depends on CFG80211
+ ---help---
+ This option adds support for ethernet connections to appear as if they
+ are wifi connections through a special rtnetlink device.
+
endif # WLAN
diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile
index f00d429..1056115 100644
--- a/drivers/net/wireless/Makefile
+++ b/drivers/net/wireless/Makefile
@@ -25,3 +25,5 @@
obj-$(CONFIG_USB_NET_RNDIS_WLAN) += rndis_wlan.o
obj-$(CONFIG_MAC80211_HWSIM) += mac80211_hwsim.o
+
+obj-$(CONFIG_VIRT_WIFI) += virt_wifi.o
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 64f8f40..33987d7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2774,7 +2774,6 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg,
struct brcmf_bss_info_le *bi)
{
struct wiphy *wiphy = cfg_to_wiphy(cfg);
- struct ieee80211_channel *notify_channel;
struct cfg80211_bss *bss;
struct ieee80211_supported_band *band;
struct brcmu_chan ch;
@@ -2784,7 +2783,7 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg,
u16 notify_interval;
u8 *notify_ie;
size_t notify_ielen;
- s32 notify_signal;
+ struct cfg80211_inform_bss bss_data = {};
if (le32_to_cpu(bi->length) > WL_BSS_INFO_MAX) {
brcmf_err("Bss info is larger than buffer. Discarding\n");
@@ -2804,27 +2803,28 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg,
band = wiphy->bands[NL80211_BAND_5GHZ];
freq = ieee80211_channel_to_frequency(channel, band->band);
- notify_channel = ieee80211_get_channel(wiphy, freq);
+ bss_data.chan = ieee80211_get_channel(wiphy, freq);
+ bss_data.scan_width = NL80211_BSS_CHAN_WIDTH_20;
+ bss_data.boottime_ns = ktime_to_ns(ktime_get_boottime());
notify_capability = le16_to_cpu(bi->capability);
notify_interval = le16_to_cpu(bi->beacon_period);
notify_ie = (u8 *)bi + le16_to_cpu(bi->ie_offset);
notify_ielen = le32_to_cpu(bi->ie_length);
- notify_signal = (s16)le16_to_cpu(bi->RSSI) * 100;
+ bss_data.signal = (s16)le16_to_cpu(bi->RSSI) * 100;
brcmf_dbg(CONN, "bssid: %pM\n", bi->BSSID);
brcmf_dbg(CONN, "Channel: %d(%d)\n", channel, freq);
brcmf_dbg(CONN, "Capability: %X\n", notify_capability);
brcmf_dbg(CONN, "Beacon interval: %d\n", notify_interval);
- brcmf_dbg(CONN, "Signal: %d\n", notify_signal);
+ brcmf_dbg(CONN, "Signal: %d\n", bss_data.signal);
- bss = cfg80211_inform_bss(wiphy, notify_channel,
- CFG80211_BSS_FTYPE_UNKNOWN,
- (const u8 *)bi->BSSID,
- 0, notify_capability,
- notify_interval, notify_ie,
- notify_ielen, notify_signal,
- GFP_KERNEL);
+ bss = cfg80211_inform_bss_data(wiphy, &bss_data,
+ CFG80211_BSS_FTYPE_UNKNOWN,
+ (const u8 *)bi->BSSID,
+ 0, notify_capability,
+ notify_interval, notify_ie,
+ notify_ielen, GFP_KERNEL);
if (!bss)
return -ENOMEM;
diff --git a/drivers/net/wireless/ti/wlcore/init.c b/drivers/net/wireless/ti/wlcore/init.c
index d0b7734..b7974b4 100644
--- a/drivers/net/wireless/ti/wlcore/init.c
+++ b/drivers/net/wireless/ti/wlcore/init.c
@@ -549,6 +549,11 @@ static int wl12xx_init_ap_role(struct wl1271 *wl, struct wl12xx_vif *wlvif)
{
int ret;
+ /* Disable filtering */
+ ret = wl1271_acx_group_address_tbl(wl, wlvif, false, NULL, 0);
+ if (ret < 0)
+ return ret;
+
ret = wl1271_acx_ap_max_tx_retry(wl, wlvif);
if (ret < 0)
return ret;
diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c
new file mode 100644
index 0000000..d255147
--- /dev/null
+++ b/drivers/net/wireless/virt_wifi.c
@@ -0,0 +1,632 @@
+// SPDX-License-Identifier: GPL-2.0
+/* drivers/net/wireless/virt_wifi.c
+ *
+ * A fake implementation of cfg80211_ops that can be tacked on to an ethernet
+ * net_device to make it appear as a wireless connection.
+ *
+ * Copyright (C) 2018 Google, Inc.
+ *
+ * Author: schuffelen@google.com
+ */
+
+#include <net/cfg80211.h>
+#include <net/rtnetlink.h>
+#include <linux/etherdevice.h>
+#include <linux/module.h>
+
+#include <net/cfg80211.h>
+#include <net/rtnetlink.h>
+#include <linux/etherdevice.h>
+#include <linux/module.h>
+
+static struct wiphy *common_wiphy;
+
+struct virt_wifi_wiphy_priv {
+ struct delayed_work scan_result;
+ struct cfg80211_scan_request *scan_request;
+ bool being_deleted;
+};
+
+static struct ieee80211_channel channel_2ghz = {
+ .band = NL80211_BAND_2GHZ,
+ .center_freq = 2432,
+ .hw_value = 2432,
+ .max_power = 20,
+};
+
+static struct ieee80211_rate bitrates_2ghz[] = {
+ { .bitrate = 10 },
+ { .bitrate = 20 },
+ { .bitrate = 55 },
+ { .bitrate = 110 },
+ { .bitrate = 60 },
+ { .bitrate = 120 },
+ { .bitrate = 240 },
+};
+
+static struct ieee80211_supported_band band_2ghz = {
+ .channels = &channel_2ghz,
+ .bitrates = bitrates_2ghz,
+ .band = NL80211_BAND_2GHZ,
+ .n_channels = 1,
+ .n_bitrates = ARRAY_SIZE(bitrates_2ghz),
+ .ht_cap = {
+ .ht_supported = true,
+ .cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+ IEEE80211_HT_CAP_GRN_FLD |
+ IEEE80211_HT_CAP_SGI_20 |
+ IEEE80211_HT_CAP_SGI_40 |
+ IEEE80211_HT_CAP_DSSSCCK40,
+ .ampdu_factor = 0x3,
+ .ampdu_density = 0x6,
+ .mcs = {
+ .rx_mask = {0xff, 0xff},
+ .tx_params = IEEE80211_HT_MCS_TX_DEFINED,
+ },
+ },
+};
+
+static struct ieee80211_channel channel_5ghz = {
+ .band = NL80211_BAND_5GHZ,
+ .center_freq = 5240,
+ .hw_value = 5240,
+ .max_power = 20,
+};
+
+static struct ieee80211_rate bitrates_5ghz[] = {
+ { .bitrate = 60 },
+ { .bitrate = 120 },
+ { .bitrate = 240 },
+};
+
+#define RX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 14)
+
+#define TX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \
+ IEEE80211_VHT_MCS_SUPPORT_0_9 << 14)
+
+static struct ieee80211_supported_band band_5ghz = {
+ .channels = &channel_5ghz,
+ .bitrates = bitrates_5ghz,
+ .band = NL80211_BAND_5GHZ,
+ .n_channels = 1,
+ .n_bitrates = ARRAY_SIZE(bitrates_5ghz),
+ .ht_cap = {
+ .ht_supported = true,
+ .cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+ IEEE80211_HT_CAP_GRN_FLD |
+ IEEE80211_HT_CAP_SGI_20 |
+ IEEE80211_HT_CAP_SGI_40 |
+ IEEE80211_HT_CAP_DSSSCCK40,
+ .ampdu_factor = 0x3,
+ .ampdu_density = 0x6,
+ .mcs = {
+ .rx_mask = {0xff, 0xff},
+ .tx_params = IEEE80211_HT_MCS_TX_DEFINED,
+ },
+ },
+ .vht_cap = {
+ .vht_supported = true,
+ .cap = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
+ IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ |
+ IEEE80211_VHT_CAP_RXLDPC |
+ IEEE80211_VHT_CAP_SHORT_GI_80 |
+ IEEE80211_VHT_CAP_SHORT_GI_160 |
+ IEEE80211_VHT_CAP_TXSTBC |
+ IEEE80211_VHT_CAP_RXSTBC_1 |
+ IEEE80211_VHT_CAP_RXSTBC_2 |
+ IEEE80211_VHT_CAP_RXSTBC_3 |
+ IEEE80211_VHT_CAP_RXSTBC_4 |
+ IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK,
+ .vht_mcs = {
+ .rx_mcs_map = cpu_to_le16(RX_MCS_MAP),
+ .tx_mcs_map = cpu_to_le16(TX_MCS_MAP),
+ }
+ },
+};
+
+/* Assigned at module init. Guaranteed locally-administered and unicast. */
+static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {};
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_scan(struct wiphy *wiphy,
+ struct cfg80211_scan_request *request)
+{
+ struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy);
+
+ wiphy_debug(wiphy, "scan\n");
+
+ if (priv->scan_request || priv->being_deleted)
+ return -EBUSY;
+
+ priv->scan_request = request;
+ schedule_delayed_work(&priv->scan_result, HZ * 2);
+
+ return 0;
+}
+
+/* Acquires and releases the rdev BSS lock. */
+static void virt_wifi_scan_result(struct work_struct *work)
+{
+ struct {
+ u8 tag;
+ u8 len;
+ u8 ssid[8];
+ } __packed ssid = {
+ .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi",
+ };
+ struct cfg80211_bss *informed_bss;
+ struct virt_wifi_wiphy_priv *priv =
+ container_of(work, struct virt_wifi_wiphy_priv,
+ scan_result.work);
+ struct wiphy *wiphy = priv_to_wiphy(priv);
+ struct cfg80211_scan_info scan_info = { .aborted = false };
+
+ informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
+ CFG80211_BSS_FTYPE_PRESP,
+ fake_router_bssid,
+ ktime_get_boot_ns(),
+ WLAN_CAPABILITY_ESS, 0,
+ (void *)&ssid, sizeof(ssid),
+ DBM_TO_MBM(-50), GFP_KERNEL);
+ cfg80211_put_bss(wiphy, informed_bss);
+
+ /* Schedules work which acquires and releases the rtnl lock. */
+ cfg80211_scan_done(priv->scan_request, &scan_info);
+ priv->scan_request = NULL;
+}
+
+/* May acquire and release the rdev BSS lock. */
+static void virt_wifi_cancel_scan(struct wiphy *wiphy)
+{
+ struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy);
+
+ cancel_delayed_work_sync(&priv->scan_result);
+ /* Clean up dangling callbacks if necessary. */
+ if (priv->scan_request) {
+ struct cfg80211_scan_info scan_info = { .aborted = true };
+ /* Schedules work which acquires and releases the rtnl lock. */
+ cfg80211_scan_done(priv->scan_request, &scan_info);
+ priv->scan_request = NULL;
+ }
+}
+
+struct virt_wifi_netdev_priv {
+ struct delayed_work connect;
+ struct net_device *lowerdev;
+ struct net_device *upperdev;
+ u32 tx_packets;
+ u32 tx_failed;
+ u8 connect_requested_bss[ETH_ALEN];
+ bool is_up;
+ bool is_connected;
+ bool being_deleted;
+};
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev,
+ struct cfg80211_connect_params *sme)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+ bool could_schedule;
+
+ if (priv->being_deleted || !priv->is_up)
+ return -EBUSY;
+
+ could_schedule = schedule_delayed_work(&priv->connect, HZ * 2);
+ if (!could_schedule)
+ return -EBUSY;
+
+ if (sme->bssid)
+ ether_addr_copy(priv->connect_requested_bss, sme->bssid);
+ else
+ eth_zero_addr(priv->connect_requested_bss);
+
+ wiphy_debug(wiphy, "connect\n");
+
+ return 0;
+}
+
+/* Acquires and releases the rdev event lock. */
+static void virt_wifi_connect_complete(struct work_struct *work)
+{
+ struct virt_wifi_netdev_priv *priv =
+ container_of(work, struct virt_wifi_netdev_priv, connect.work);
+ u8 *requested_bss = priv->connect_requested_bss;
+ bool has_addr = !is_zero_ether_addr(requested_bss);
+ bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid);
+ u16 status = WLAN_STATUS_SUCCESS;
+
+ if (!priv->is_up || (has_addr && !right_addr))
+ status = WLAN_STATUS_UNSPECIFIED_FAILURE;
+ else
+ priv->is_connected = true;
+
+ /* Schedules an event that acquires the rtnl lock. */
+ cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0,
+ status, GFP_KERNEL);
+ netif_carrier_on(priv->upperdev);
+}
+
+/* May acquire and release the rdev event lock. */
+static void virt_wifi_cancel_connect(struct net_device *netdev)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+
+ /* If there is work pending, clean up dangling callbacks. */
+ if (cancel_delayed_work_sync(&priv->connect)) {
+ /* Schedules an event that acquires the rtnl lock. */
+ cfg80211_connect_result(priv->upperdev,
+ priv->connect_requested_bss, NULL, 0,
+ NULL, 0,
+ WLAN_STATUS_UNSPECIFIED_FAILURE,
+ GFP_KERNEL);
+ }
+}
+
+/* Called with the rtnl lock held. Acquires the rdev event lock. */
+static int virt_wifi_disconnect(struct wiphy *wiphy, struct net_device *netdev,
+ u16 reason_code)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+
+ if (priv->being_deleted)
+ return -EBUSY;
+
+ wiphy_debug(wiphy, "disconnect\n");
+ virt_wifi_cancel_connect(netdev);
+
+ cfg80211_disconnected(netdev, reason_code, NULL, 0, true, GFP_KERNEL);
+ priv->is_connected = false;
+ netif_carrier_off(netdev);
+
+ return 0;
+}
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_get_station(struct wiphy *wiphy, struct net_device *dev,
+ const u8 *mac, struct station_info *sinfo)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+ wiphy_debug(wiphy, "get_station\n");
+
+ if (!priv->is_connected || !ether_addr_equal(mac, fake_router_bssid))
+ return -ENOENT;
+
+ sinfo->filled = BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+ BIT_ULL(NL80211_STA_INFO_TX_FAILED) |
+ BIT_ULL(NL80211_STA_INFO_SIGNAL) |
+ BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+ sinfo->tx_packets = priv->tx_packets;
+ sinfo->tx_failed = priv->tx_failed;
+ /* For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_ */
+ sinfo->signal = -50;
+ sinfo->txrate = (struct rate_info) {
+ .legacy = 10, /* units are 100kbit/s */
+ };
+ return 0;
+}
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_dump_station(struct wiphy *wiphy, struct net_device *dev,
+ int idx, u8 *mac, struct station_info *sinfo)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+ wiphy_debug(wiphy, "dump_station\n");
+
+ if (idx != 0 || !priv->is_connected)
+ return -ENOENT;
+
+ ether_addr_copy(mac, fake_router_bssid);
+ return virt_wifi_get_station(wiphy, dev, fake_router_bssid, sinfo);
+}
+
+static const struct cfg80211_ops virt_wifi_cfg80211_ops = {
+ .scan = virt_wifi_scan,
+
+ .connect = virt_wifi_connect,
+ .disconnect = virt_wifi_disconnect,
+
+ .get_station = virt_wifi_get_station,
+ .dump_station = virt_wifi_dump_station,
+};
+
+/* Acquires and releases the rtnl lock. */
+static struct wiphy *virt_wifi_make_wiphy(void)
+{
+ struct wiphy *wiphy;
+ struct virt_wifi_wiphy_priv *priv;
+ int err;
+
+ wiphy = wiphy_new(&virt_wifi_cfg80211_ops, sizeof(*priv));
+
+ if (!wiphy)
+ return NULL;
+
+ wiphy->max_scan_ssids = 4;
+ wiphy->max_scan_ie_len = 1000;
+ wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
+
+ wiphy->bands[NL80211_BAND_2GHZ] = &band_2ghz;
+ wiphy->bands[NL80211_BAND_5GHZ] = &band_5ghz;
+ wiphy->bands[NL80211_BAND_60GHZ] = NULL;
+
+ wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+ priv = wiphy_priv(wiphy);
+ priv->being_deleted = false;
+ priv->scan_request = NULL;
+ INIT_DELAYED_WORK(&priv->scan_result, virt_wifi_scan_result);
+
+ err = wiphy_register(wiphy);
+ if (err < 0) {
+ wiphy_free(wiphy);
+ return NULL;
+ }
+
+ return wiphy;
+}
+
+/* Acquires and releases the rtnl lock. */
+static void virt_wifi_destroy_wiphy(struct wiphy *wiphy)
+{
+ struct virt_wifi_wiphy_priv *priv;
+
+ WARN(!wiphy, "%s called with null wiphy", __func__);
+ if (!wiphy)
+ return;
+
+ priv = wiphy_priv(wiphy);
+ priv->being_deleted = true;
+ virt_wifi_cancel_scan(wiphy);
+
+ if (wiphy->registered)
+ wiphy_unregister(wiphy);
+ wiphy_free(wiphy);
+}
+
+/* Enters and exits a RCU-bh critical section. */
+static netdev_tx_t virt_wifi_start_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+ priv->tx_packets++;
+ if (!priv->is_connected) {
+ priv->tx_failed++;
+ return NET_XMIT_DROP;
+ }
+
+ skb->dev = priv->lowerdev;
+ return dev_queue_xmit(skb);
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_net_device_open(struct net_device *dev)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+ priv->is_up = true;
+ return 0;
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_net_device_stop(struct net_device *dev)
+{
+ struct virt_wifi_netdev_priv *n_priv = netdev_priv(dev);
+ struct virt_wifi_wiphy_priv *w_priv;
+
+ n_priv->is_up = false;
+
+ if (!dev->ieee80211_ptr)
+ return 0;
+ w_priv = wiphy_priv(dev->ieee80211_ptr->wiphy);
+
+ virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy);
+ virt_wifi_cancel_connect(dev);
+ netif_carrier_off(dev);
+
+ return 0;
+}
+
+static const struct net_device_ops virt_wifi_ops = {
+ .ndo_start_xmit = virt_wifi_start_xmit,
+ .ndo_open = virt_wifi_net_device_open,
+ .ndo_stop = virt_wifi_net_device_stop,
+};
+
+/* Invoked as part of rtnl lock release. */
+static void virt_wifi_net_device_destructor(struct net_device *dev)
+{
+ /* Delayed past dellink to allow nl80211 to react to the device being
+ * deleted.
+ */
+ kfree(dev->ieee80211_ptr);
+ dev->ieee80211_ptr = NULL;
+ free_netdev(dev);
+}
+
+/* No lock interaction. */
+static void virt_wifi_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+ dev->netdev_ops = &virt_wifi_ops;
+ dev->destructor = virt_wifi_net_device_destructor;
+}
+
+/* Called in a RCU read critical section from netif_receive_skb */
+static rx_handler_result_t virt_wifi_rx_handler(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct virt_wifi_netdev_priv *priv =
+ rcu_dereference(skb->dev->rx_handler_data);
+
+ if (!priv->is_connected)
+ return RX_HANDLER_PASS;
+
+ /* GFP_ATOMIC because this is a packet interrupt handler. */
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb) {
+ dev_err(&priv->upperdev->dev, "can't skb_share_check\n");
+ return RX_HANDLER_CONSUMED;
+ }
+
+ *pskb = skb;
+ skb->dev = priv->upperdev;
+ skb->pkt_type = PACKET_HOST;
+ return RX_HANDLER_ANOTHER;
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+ int err;
+
+ if (!tb[IFLA_LINK])
+ return -EINVAL;
+
+ netif_carrier_off(dev);
+
+ priv->upperdev = dev;
+ priv->lowerdev = __dev_get_by_index(src_net,
+ nla_get_u32(tb[IFLA_LINK]));
+
+ if (!priv->lowerdev)
+ return -ENODEV;
+ if (!tb[IFLA_MTU])
+ dev->mtu = priv->lowerdev->mtu;
+ else if (dev->mtu > priv->lowerdev->mtu)
+ return -EINVAL;
+
+ err = netdev_rx_handler_register(priv->lowerdev, virt_wifi_rx_handler,
+ priv);
+ if (err) {
+ dev_err(&priv->lowerdev->dev,
+ "can't netdev_rx_handler_register: %d\n", err);
+ return err;
+ }
+
+ eth_hw_addr_inherit(dev, priv->lowerdev);
+ netif_stacked_transfer_operstate(priv->lowerdev, dev);
+
+ SET_NETDEV_DEV(dev, &priv->lowerdev->dev);
+ dev->ieee80211_ptr = kzalloc(sizeof(*dev->ieee80211_ptr), GFP_KERNEL);
+
+ if (!dev->ieee80211_ptr) {
+ err = -ENOMEM;
+ goto remove_handler;
+ }
+
+ dev->ieee80211_ptr->iftype = NL80211_IFTYPE_STATION;
+ dev->ieee80211_ptr->wiphy = common_wiphy;
+
+ err = register_netdevice(dev);
+ if (err) {
+ dev_err(&priv->lowerdev->dev, "can't register_netdevice: %d\n",
+ err);
+ goto free_wireless_dev;
+ }
+
+ err = netdev_upper_dev_link(priv->lowerdev, dev);
+ if (err) {
+ dev_err(&priv->lowerdev->dev, "can't netdev_upper_dev_link: %d\n",
+ err);
+ goto unregister_netdev;
+ }
+
+ priv->being_deleted = false;
+ priv->is_connected = false;
+ priv->is_up = false;
+ INIT_DELAYED_WORK(&priv->connect, virt_wifi_connect_complete);
+
+ return 0;
+unregister_netdev:
+ unregister_netdevice(dev);
+free_wireless_dev:
+ kfree(dev->ieee80211_ptr);
+ dev->ieee80211_ptr = NULL;
+remove_handler:
+ netdev_rx_handler_unregister(priv->lowerdev);
+
+ return err;
+}
+
+/* Called with rtnl lock held. */
+static void virt_wifi_dellink(struct net_device *dev,
+ struct list_head *head)
+{
+ struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+ if (dev->ieee80211_ptr)
+ virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy);
+
+ priv->being_deleted = true;
+ virt_wifi_cancel_connect(dev);
+ netif_carrier_off(dev);
+
+ netdev_rx_handler_unregister(priv->lowerdev);
+ netdev_upper_dev_unlink(priv->lowerdev, dev);
+
+ unregister_netdevice_queue(dev, head);
+
+ /* Deleting the wiphy is handled in the module destructor. */
+}
+
+static struct rtnl_link_ops virt_wifi_link_ops = {
+ .kind = "virt_wifi",
+ .setup = virt_wifi_setup,
+ .newlink = virt_wifi_newlink,
+ .dellink = virt_wifi_dellink,
+ .priv_size = sizeof(struct virt_wifi_netdev_priv),
+};
+
+/* Acquires and releases the rtnl lock. */
+static int __init virt_wifi_init_module(void)
+{
+ int err;
+
+ /* Guaranteed to be locallly-administered and not multicast. */
+ eth_random_addr(fake_router_bssid);
+
+ common_wiphy = virt_wifi_make_wiphy();
+ if (!common_wiphy)
+ return -ENOMEM;
+
+ err = rtnl_link_register(&virt_wifi_link_ops);
+ if (err)
+ virt_wifi_destroy_wiphy(common_wiphy);
+
+ return err;
+}
+
+/* Acquires and releases the rtnl lock. */
+static void __exit virt_wifi_cleanup_module(void)
+{
+ /* Will delete any devices that depend on the wiphy. */
+ rtnl_link_unregister(&virt_wifi_link_ops);
+ virt_wifi_destroy_wiphy(common_wiphy);
+}
+
+module_init(virt_wifi_init_module);
+module_exit(virt_wifi_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Cody Schuffelen <schuffelen@google.com>");
+MODULE_DESCRIPTION("Driver for a wireless wrapper of ethernet devices");
+MODULE_ALIAS_RTNL_LINK("virt_wifi");
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index f1addfd..4b8a0e6 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -177,6 +177,16 @@ static int fdp_nci_i2c_read(struct fdp_i2c_phy *phy, struct sk_buff **skb)
/* Packet that contains a length */
if (tmp[0] == 0 && tmp[1] == 0) {
phy->next_read_size = (tmp[2] << 8) + tmp[3] + 3;
+ /*
+ * Ensure next_read_size does not exceed sizeof(tmp)
+ * for reading that many bytes during next iteration
+ */
+ if (phy->next_read_size > FDP_NCI_I2C_MAX_PAYLOAD) {
+ dev_dbg(&client->dev, "%s: corrupted packet\n",
+ __func__);
+ phy->next_read_size = 5;
+ goto flush;
+ }
} else {
phy->next_read_size = FDP_NCI_I2C_MIN_PAYLOAD;
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index e023a67..6338492 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -219,7 +219,8 @@ static int st21nfca_tm_recv_atr_req(struct nfc_hci_dev *hdev,
atr_req = (struct st21nfca_atr_req *)skb->data;
- if (atr_req->length < sizeof(struct st21nfca_atr_req)) {
+ if (atr_req->length < sizeof(struct st21nfca_atr_req) ||
+ atr_req->length > skb->len) {
r = -EPROTO;
goto exit;
}
diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c
index eac608a..9add5fe 100644
--- a/drivers/nfc/st21nfca/se.c
+++ b/drivers/nfc/st21nfca/se.c
@@ -320,10 +320,17 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
* AID 81 5 to 16
* PARAMETERS 82 0 to 255
*/
- if (skb->len < NFC_MIN_AID_LENGTH + 2 &&
+ if (skb->len < NFC_MIN_AID_LENGTH + 2 ||
skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG)
return -EPROTO;
+ /*
+ * Buffer should have enough space for at least
+ * two tag fields + two length fields + aid_len (skb->data[1])
+ */
+ if (skb->len < skb->data[1] + 4)
+ return -EPROTO;
+
transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev,
skb->len - 2, GFP_KERNEL);
if (!transaction)
@@ -332,13 +339,16 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
transaction->aid_len = skb->data[1];
memcpy(transaction->aid, &skb->data[2],
transaction->aid_len);
-
- /* Check next byte is PARAMETERS tag (82) */
- if (skb->data[transaction->aid_len + 2] !=
- NFC_EVT_TRANSACTION_PARAMS_TAG)
- return -EPROTO;
-
transaction->params_len = skb->data[transaction->aid_len + 3];
+
+ /* Check next byte is PARAMETERS tag (82) and the length field */
+ if (skb->data[transaction->aid_len + 2] !=
+ NFC_EVT_TRANSACTION_PARAMS_TAG ||
+ skb->len < transaction->aid_len + transaction->params_len + 4) {
+ devm_kfree(dev, transaction);
+ return -EPROTO;
+ }
+
memcpy(transaction->params, skb->data +
transaction->aid_len + 4, transaction->params_len);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index e9360d5..e37a2a5 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1063,42 +1063,66 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
return 0;
}
+/*
+ * Convert configs to something easy to use in C code
+ */
+#if defined(CONFIG_CMDLINE_FORCE)
+static const int overwrite_incoming_cmdline = 1;
+static const int read_dt_cmdline;
+static const int concat_cmdline;
+#elif defined(CONFIG_CMDLINE_EXTEND)
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline = 1;
+#else /* CMDLINE_FROM_BOOTLOADER */
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline;
+#endif
+
+#ifdef CONFIG_CMDLINE
+static const char *config_cmdline = CONFIG_CMDLINE;
+#else
+static const char *config_cmdline = "";
+#endif
+
int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data)
{
- int l;
- const char *p;
+ int l = 0;
+ const char *p = NULL;
+ char *cmdline = data;
pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
- if (depth != 1 || !data ||
+ if (depth != 1 || !cmdline ||
(strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
return 0;
early_init_dt_check_for_initrd(node);
- /* Retrieve command line */
- p = of_get_flat_dt_prop(node, "bootargs", &l);
- if (p != NULL && l > 0)
- strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE));
+ /* Put CONFIG_CMDLINE in if forced or if data had nothing in it to start */
+ if (overwrite_incoming_cmdline || !cmdline[0])
+ strlcpy(cmdline, config_cmdline, COMMAND_LINE_SIZE);
- /*
- * CONFIG_CMDLINE is meant to be a default in case nothing else
- * managed to set the command line, unless CONFIG_CMDLINE_FORCE
- * is set in which case we override whatever was found earlier.
- */
-#ifdef CONFIG_CMDLINE
-#if defined(CONFIG_CMDLINE_EXTEND)
- strlcat(data, " ", COMMAND_LINE_SIZE);
- strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
- strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#else
- /* No arguments from boot loader, use kernel's cmdl*/
- if (!((char *)data)[0])
- strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif
-#endif /* CONFIG_CMDLINE */
+ /* Retrieve command line unless forcing */
+ if (read_dt_cmdline)
+ p = of_get_flat_dt_prop(node, "bootargs", &l);
+
+ if (p != NULL && l > 0) {
+ if (concat_cmdline) {
+ int cmdline_len;
+ int copy_len;
+ strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+ cmdline_len = strlen(cmdline);
+ copy_len = COMMAND_LINE_SIZE - cmdline_len - 1;
+ copy_len = min((int)l, copy_len);
+ strncpy(cmdline + cmdline_len, p, copy_len);
+ cmdline[cmdline_len + copy_len] = '\0';
+ } else {
+ strlcpy(cmdline, p, min((int)l, COMMAND_LINE_SIZE));
+ }
+ }
pr_debug("Command line is: %s\n", (char*)data);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 5eae5f3..51296c8 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -797,7 +797,8 @@ void pci_disable_link_state(struct pci_dev *pdev, int state)
}
EXPORT_SYMBOL(pci_disable_link_state);
-static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
+static int pcie_aspm_set_policy(const char *val,
+ const struct kernel_param *kp)
{
int i;
struct pcie_link_state *link;
@@ -824,7 +825,7 @@ static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
return 0;
}
-static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp)
+static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp)
{
int i, cnt = 0;
for (i = 0; i < ARRAY_SIZE(policy_str); i++)
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 9b899af..e30f576 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1018,7 +1018,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
const struct pmu_probe_info *probe_table)
{
const struct of_device_id *of_id;
- const int (*init_fn)(struct arm_pmu *);
+ int (*init_fn)(struct arm_pmu *);
struct device_node *node = pdev->dev.of_node;
struct arm_pmu *pmu;
int ret = -ENODEV;
diff --git a/drivers/platform/goldfish/Makefile b/drivers/platform/goldfish/Makefile
index d348712..277a820 100644
--- a/drivers/platform/goldfish/Makefile
+++ b/drivers/platform/goldfish/Makefile
@@ -2,4 +2,5 @@
# Makefile for Goldfish platform specific drivers
#
obj-$(CONFIG_GOLDFISH_BUS) += pdev_bus.o
-obj-$(CONFIG_GOLDFISH_PIPE) += goldfish_pipe.o
+obj-$(CONFIG_GOLDFISH_PIPE) += goldfish_pipe_all.o
+goldfish_pipe_all-objs := goldfish_pipe.o goldfish_pipe_v2.o
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 1aba2c7..91e0a56 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -15,52 +15,11 @@
*
*/
-/* This source file contains the implementation of a special device driver
- * that intends to provide a *very* fast communication channel between the
- * guest system and the QEMU emulator.
- *
- * Usage from the guest is simply the following (error handling simplified):
- *
- * int fd = open("/dev/qemu_pipe",O_RDWR);
- * .... write() or read() through the pipe.
- *
- * This driver doesn't deal with the exact protocol used during the session.
- * It is intended to be as simple as something like:
- *
- * // do this _just_ after opening the fd to connect to a specific
- * // emulator service.
- * const char* msg = "<pipename>";
- * if (write(fd, msg, strlen(msg)+1) < 0) {
- * ... could not connect to <pipename> service
- * close(fd);
- * }
- *
- * // after this, simply read() and write() to communicate with the
- * // service. Exact protocol details left as an exercise to the reader.
- *
- * This driver is very fast because it doesn't copy any data through
- * intermediate buffers, since the emulator is capable of translating
- * guest user addresses into host ones.
- *
- * Note that we must however ensure that each user page involved in the
- * exchange is properly mapped during a transfer.
+/* This source file contains the implementation of the legacy version of
+ * a goldfish pipe device driver. See goldfish_pipe_v2.c for the current
+ * version.
*/
-
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/spinlock.h>
-#include <linux/miscdevice.h>
-#include <linux/platform_device.h>
-#include <linux/poll.h>
-#include <linux/sched.h>
-#include <linux/bitops.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include <linux/goldfish.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/acpi.h>
+#include "goldfish_pipe.h"
/*
* IMPORTANT: The following constants must match the ones used and defined
@@ -110,29 +69,15 @@
#define PIPE_WAKE_READ (1 << 1) /* pipe can now be read from */
#define PIPE_WAKE_WRITE (1 << 2) /* pipe can now be written to */
-struct access_params {
- unsigned long channel;
- u32 size;
- unsigned long address;
- u32 cmd;
- u32 result;
- /* reserved for future extension */
- u32 flags;
-};
+#define MAX_PAGES_TO_GRAB 32
-/* The global driver data. Holds a reference to the i/o page used to
- * communicate with the emulator, and a wake queue for blocked tasks
- * waiting to be awoken.
- */
-struct goldfish_pipe_dev {
- spinlock_t lock;
- unsigned char __iomem *base;
- struct access_params *aps;
- int irq;
- u32 version;
-};
+#define DEBUG 0
-static struct goldfish_pipe_dev pipe_dev[1];
+#if DEBUG
+#define DPRINT(...) { printk(KERN_ERR __VA_ARGS__); }
+#else
+#define DPRINT(...)
+#endif
/* This data type models a given pipe instance */
struct goldfish_pipe {
@@ -142,6 +87,15 @@ struct goldfish_pipe {
wait_queue_head_t wake_queue;
};
+struct access_params {
+ unsigned long channel;
+ u32 size;
+ unsigned long address;
+ u32 cmd;
+ u32 result;
+ /* reserved for future extension */
+ u32 flags;
+};
/* Bit flags for the 'flags' field */
enum {
@@ -231,8 +185,10 @@ static int setup_access_params_addr(struct platform_device *pdev,
if (valid_batchbuffer_addr(dev, aps)) {
dev->aps = aps;
return 0;
- } else
+ } else {
+ devm_kfree(&pdev->dev, aps);
return -1;
+ }
}
/* A value that will not be set by qemu emulator */
@@ -269,6 +225,7 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
struct goldfish_pipe *pipe = filp->private_data;
struct goldfish_pipe_dev *dev = pipe->dev;
unsigned long address, address_end;
+ struct page* pages[MAX_PAGES_TO_GRAB] = {};
int count = 0, ret = -EINVAL;
/* If the emulator already closed the pipe, no need to go further */
@@ -293,45 +250,61 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
while (address < address_end) {
unsigned long page_end = (address & PAGE_MASK) + PAGE_SIZE;
- unsigned long next = page_end < address_end ? page_end
- : address_end;
- unsigned long avail = next - address;
- int status, wakeBit;
- struct page *page;
-
- /* Either vaddr or paddr depending on the device version */
- unsigned long xaddr;
+ unsigned long next, avail;
+ int status, wakeBit, page_i, num_contiguous_pages;
+ long first_page, last_page, requested_pages;
+ unsigned long xaddr, xaddr_prev, xaddr_i;
/*
- * We grab the pages on a page-by-page basis in case user
- * space gives us a potentially huge buffer but the read only
- * returns a small amount, then there's no need to pin that
- * much memory to the process.
+ * Attempt to grab multiple physically contiguous pages.
*/
- down_read(¤t->mm->mmap_sem);
- ret = get_user_pages(address, 1, is_write ? 0 : FOLL_WRITE,
- &page, NULL);
- up_read(¤t->mm->mmap_sem);
- if (ret < 0)
- break;
-
- if (dev->version) {
- /* Device version 1 or newer (qemu-android) expects the
- * physical address.
- */
- xaddr = page_to_phys(page) | (address & ~PAGE_MASK);
- } else {
- /* Device version 0 (classic emulator) expects the
- * virtual address.
- */
- xaddr = address;
+ first_page = address & PAGE_MASK;
+ last_page = (address_end - 1) & PAGE_MASK;
+ requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1;
+ if (requested_pages > MAX_PAGES_TO_GRAB) {
+ requested_pages = MAX_PAGES_TO_GRAB;
}
+ ret = get_user_pages_fast(first_page, requested_pages,
+ !is_write, pages);
+
+ DPRINT("%s: requested pages: %d %d %p\n", __FUNCTION__,
+ ret, requested_pages, first_page);
+ if (ret == 0) {
+ DPRINT("%s: error: (requested pages == 0) (wanted %d)\n",
+ __FUNCTION__, requested_pages);
+ mutex_unlock(&pipe->lock);
+ return ret;
+ }
+ if (ret < 0) {
+ DPRINT("%s: (requested pages < 0) %d \n",
+ __FUNCTION__, requested_pages);
+ mutex_unlock(&pipe->lock);
+ return ret;
+ }
+
+ xaddr = page_to_phys(pages[0]) | (address & ~PAGE_MASK);
+ xaddr_prev = xaddr;
+ num_contiguous_pages = ret == 0 ? 0 : 1;
+ for (page_i = 1; page_i < ret; page_i++) {
+ xaddr_i = page_to_phys(pages[page_i]) | (address & ~PAGE_MASK);
+ if (xaddr_i == xaddr_prev + PAGE_SIZE) {
+ page_end += PAGE_SIZE;
+ xaddr_prev = xaddr_i;
+ num_contiguous_pages++;
+ } else {
+ DPRINT("%s: discontinuous page boundary: %d pages instead\n",
+ __FUNCTION__, page_i);
+ break;
+ }
+ }
+ next = page_end < address_end ? page_end : address_end;
+ avail = next - address;
/* Now, try to transfer the bytes in the current page */
spin_lock_irqsave(&dev->lock, irq_flags);
if (access_with_param(dev,
- is_write ? CMD_WRITE_BUFFER : CMD_READ_BUFFER,
- xaddr, avail, pipe, &status)) {
+ is_write ? CMD_WRITE_BUFFER : CMD_READ_BUFFER,
+ xaddr, avail, pipe, &status)) {
gf_write_ptr(pipe, dev->base + PIPE_REG_CHANNEL,
dev->base + PIPE_REG_CHANNEL_HIGH);
writel(avail, dev->base + PIPE_REG_SIZE);
@@ -344,9 +317,13 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
}
spin_unlock_irqrestore(&dev->lock, irq_flags);
- if (status > 0 && !is_write)
- set_page_dirty(page);
- put_page(page);
+ for (page_i = 0; page_i < ret; page_i++) {
+ if (status > 0 && !is_write &&
+ page_i < num_contiguous_pages) {
+ set_page_dirty(pages[page_i]);
+ }
+ put_page(pages[page_i]);
+ }
if (status > 0) { /* Correct transfer */
count += status;
@@ -368,7 +345,7 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
*/
if (status != PIPE_ERROR_AGAIN)
pr_info_ratelimited("goldfish_pipe: backend returned error %d on %s\n",
- status, is_write ? "write" : "read");
+ status, is_write ? "write" : "read");
ret = 0;
break;
}
@@ -378,7 +355,7 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
* non-blocking mode, just return the error code.
*/
if (status != PIPE_ERROR_AGAIN ||
- (filp->f_flags & O_NONBLOCK) != 0) {
+ (filp->f_flags & O_NONBLOCK) != 0) {
ret = goldfish_pipe_error_convert(status);
break;
}
@@ -392,7 +369,7 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
/* Tell the emulator we're going to wait for a wake event */
goldfish_cmd(pipe,
- is_write ? CMD_WAKE_ON_WRITE : CMD_WAKE_ON_READ);
+ is_write ? CMD_WAKE_ON_WRITE : CMD_WAKE_ON_READ);
/* Unlock the pipe, then wait for the wake signal */
mutex_unlock(&pipe->lock);
@@ -538,6 +515,8 @@ static int goldfish_pipe_open(struct inode *inode, struct file *file)
pipe->dev = dev;
mutex_init(&pipe->lock);
+ DPRINT("%s: call. pipe_dev pipe_dev=0x%lx new_pipe_addr=0x%lx file=0x%lx\n", __FUNCTION__, pipe_dev, pipe, file);
+ // spin lock init, write head of list, i guess
init_waitqueue_head(&pipe->wake_queue);
/*
@@ -560,6 +539,7 @@ static int goldfish_pipe_release(struct inode *inode, struct file *filp)
{
struct goldfish_pipe *pipe = filp->private_data;
+ DPRINT("%s: call. pipe=0x%lx file=0x%lx\n", __FUNCTION__, pipe, filp);
/* The guest is closing the channel, so tell the emulator right now */
goldfish_cmd(pipe, CMD_CLOSE);
kfree(pipe);
@@ -576,98 +556,33 @@ static const struct file_operations goldfish_pipe_fops = {
.release = goldfish_pipe_release,
};
-static struct miscdevice goldfish_pipe_device = {
+static struct miscdevice goldfish_pipe_dev = {
.minor = MISC_DYNAMIC_MINOR,
.name = "goldfish_pipe",
.fops = &goldfish_pipe_fops,
};
-static int goldfish_pipe_probe(struct platform_device *pdev)
+int goldfish_pipe_device_init_v1(struct platform_device *pdev)
{
- int err;
- struct resource *r;
struct goldfish_pipe_dev *dev = pipe_dev;
-
- /* not thread safe, but this should not happen */
- WARN_ON(dev->base != NULL);
-
- spin_lock_init(&dev->lock);
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (r == NULL || resource_size(r) < PAGE_SIZE) {
- dev_err(&pdev->dev, "can't allocate i/o page\n");
- return -EINVAL;
- }
- dev->base = devm_ioremap(&pdev->dev, r->start, PAGE_SIZE);
- if (dev->base == NULL) {
- dev_err(&pdev->dev, "ioremap failed\n");
- return -EINVAL;
- }
-
- r = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (r == NULL) {
- err = -EINVAL;
- goto error;
- }
- dev->irq = r->start;
-
- err = devm_request_irq(&pdev->dev, dev->irq, goldfish_pipe_interrupt,
+ int err = devm_request_irq(&pdev->dev, dev->irq, goldfish_pipe_interrupt,
IRQF_SHARED, "goldfish_pipe", dev);
if (err) {
- dev_err(&pdev->dev, "unable to allocate IRQ\n");
- goto error;
+ dev_err(&pdev->dev, "unable to allocate IRQ for v1\n");
+ return err;
}
- err = misc_register(&goldfish_pipe_device);
+ err = misc_register(&goldfish_pipe_dev);
if (err) {
- dev_err(&pdev->dev, "unable to register device\n");
- goto error;
+ dev_err(&pdev->dev, "unable to register v1 device\n");
+ return err;
}
+
setup_access_params_addr(pdev, dev);
-
- /* Although the pipe device in the classic Android emulator does not
- * recognize the 'version' register, it won't treat this as an error
- * either and will simply return 0, which is fine.
- */
- dev->version = readl(dev->base + PIPE_REG_VERSION);
return 0;
-
-error:
- dev->base = NULL;
- return err;
}
-static int goldfish_pipe_remove(struct platform_device *pdev)
+void goldfish_pipe_device_deinit_v1(struct platform_device *pdev)
{
- struct goldfish_pipe_dev *dev = pipe_dev;
- misc_deregister(&goldfish_pipe_device);
- dev->base = NULL;
- return 0;
+ misc_deregister(&goldfish_pipe_dev);
}
-
-static const struct acpi_device_id goldfish_pipe_acpi_match[] = {
- { "GFSH0003", 0 },
- { },
-};
-MODULE_DEVICE_TABLE(acpi, goldfish_pipe_acpi_match);
-
-static const struct of_device_id goldfish_pipe_of_match[] = {
- { .compatible = "google,android-pipe", },
- {},
-};
-MODULE_DEVICE_TABLE(of, goldfish_pipe_of_match);
-
-static struct platform_driver goldfish_pipe = {
- .probe = goldfish_pipe_probe,
- .remove = goldfish_pipe_remove,
- .driver = {
- .name = "goldfish_pipe",
- .owner = THIS_MODULE,
- .of_match_table = goldfish_pipe_of_match,
- .acpi_match_table = ACPI_PTR(goldfish_pipe_acpi_match),
- }
-};
-
-module_platform_driver(goldfish_pipe);
-MODULE_AUTHOR("David Turner <digit@google.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/platform/goldfish/goldfish_pipe.h b/drivers/platform/goldfish/goldfish_pipe.h
new file mode 100644
index 0000000..6cd1b63
--- /dev/null
+++ b/drivers/platform/goldfish/goldfish_pipe.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef GOLDFISH_PIPE_H
+#define GOLDFISH_PIPE_H
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/miscdevice.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/goldfish.h>
+#include <linux/dma-mapping.h>
+#include <linux/mm.h>
+#include <linux/acpi.h>
+
+
+/* Initialize the legacy version of the pipe device driver */
+int goldfish_pipe_device_init_v1(struct platform_device *pdev);
+
+/* Deinitialize the legacy version of the pipe device driver */
+void goldfish_pipe_device_deinit_v1(struct platform_device *pdev);
+
+/* Forward declarations for the device struct */
+struct goldfish_pipe;
+struct goldfish_pipe_device_buffers;
+
+/* The global driver data. Holds a reference to the i/o page used to
+ * communicate with the emulator, and a wake queue for blocked tasks
+ * waiting to be awoken.
+ */
+struct goldfish_pipe_dev {
+ /*
+ * Global device spinlock. Protects the following members:
+ * - pipes, pipes_capacity
+ * - [*pipes, *pipes + pipes_capacity) - array data
+ * - first_signalled_pipe,
+ * goldfish_pipe::prev_signalled,
+ * goldfish_pipe::next_signalled,
+ * goldfish_pipe::signalled_flags - all singnalled-related fields,
+ * in all allocated pipes
+ * - open_command_params - PIPE_CMD_OPEN-related buffers
+ *
+ * It looks like a lot of different fields, but the trick is that the only
+ * operation that happens often is the signalled pipes array manipulation.
+ * That's why it's OK for now to keep the rest of the fields under the same
+ * lock. If we notice too much contention because of PIPE_CMD_OPEN,
+ * then we should add a separate lock there.
+ */
+ spinlock_t lock;
+
+ /*
+ * Array of the pipes of |pipes_capacity| elements,
+ * indexed by goldfish_pipe::id
+ */
+ struct goldfish_pipe **pipes;
+ u32 pipes_capacity;
+
+ /* Pointers to the buffers host uses for interaction with this driver */
+ struct goldfish_pipe_dev_buffers *buffers;
+
+ /* Head of a doubly linked list of signalled pipes */
+ struct goldfish_pipe *first_signalled_pipe;
+
+ /* Some device-specific data */
+ int irq;
+ int version;
+ unsigned char __iomem *base;
+
+ /* v1-specific access parameters */
+ struct access_params *aps;
+};
+
+extern struct goldfish_pipe_dev pipe_dev[1];
+
+#endif /* GOLDFISH_PIPE_H */
diff --git a/drivers/platform/goldfish/goldfish_pipe_v2.c b/drivers/platform/goldfish/goldfish_pipe_v2.c
new file mode 100644
index 0000000..ad373ed
--- /dev/null
+++ b/drivers/platform/goldfish/goldfish_pipe_v2.c
@@ -0,0 +1,889 @@
+/*
+ * Copyright (C) 2012 Intel, Inc.
+ * Copyright (C) 2013 Intel, Inc.
+ * Copyright (C) 2014 Linaro Limited
+ * Copyright (C) 2011-2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* This source file contains the implementation of a special device driver
+ * that intends to provide a *very* fast communication channel between the
+ * guest system and the QEMU emulator.
+ *
+ * Usage from the guest is simply the following (error handling simplified):
+ *
+ * int fd = open("/dev/qemu_pipe",O_RDWR);
+ * .... write() or read() through the pipe.
+ *
+ * This driver doesn't deal with the exact protocol used during the session.
+ * It is intended to be as simple as something like:
+ *
+ * // do this _just_ after opening the fd to connect to a specific
+ * // emulator service.
+ * const char* msg = "<pipename>";
+ * if (write(fd, msg, strlen(msg)+1) < 0) {
+ * ... could not connect to <pipename> service
+ * close(fd);
+ * }
+ *
+ * // after this, simply read() and write() to communicate with the
+ * // service. Exact protocol details left as an exercise to the reader.
+ *
+ * This driver is very fast because it doesn't copy any data through
+ * intermediate buffers, since the emulator is capable of translating
+ * guest user addresses into host ones.
+ *
+ * Note that we must however ensure that each user page involved in the
+ * exchange is properly mapped during a transfer.
+ */
+
+#include "goldfish_pipe.h"
+
+
+/*
+ * Update this when something changes in the driver's behavior so the host
+ * can benefit from knowing it
+ */
+enum {
+ PIPE_DRIVER_VERSION = 2,
+ PIPE_CURRENT_DEVICE_VERSION = 2
+};
+
+/*
+ * IMPORTANT: The following constants must match the ones used and defined
+ * in external/qemu/hw/goldfish_pipe.c in the Android source tree.
+ */
+
+/* List of bitflags returned in status of CMD_POLL command */
+enum PipePollFlags {
+ PIPE_POLL_IN = 1 << 0,
+ PIPE_POLL_OUT = 1 << 1,
+ PIPE_POLL_HUP = 1 << 2
+};
+
+/* Possible status values used to signal errors - see goldfish_pipe_error_convert */
+enum PipeErrors {
+ PIPE_ERROR_INVAL = -1,
+ PIPE_ERROR_AGAIN = -2,
+ PIPE_ERROR_NOMEM = -3,
+ PIPE_ERROR_IO = -4
+};
+
+/* Bit-flags used to signal events from the emulator */
+enum PipeWakeFlags {
+ PIPE_WAKE_CLOSED = 1 << 0, /* emulator closed pipe */
+ PIPE_WAKE_READ = 1 << 1, /* pipe can now be read from */
+ PIPE_WAKE_WRITE = 1 << 2 /* pipe can now be written to */
+};
+
+/* Bit flags for the 'flags' field */
+enum PipeFlagsBits {
+ BIT_CLOSED_ON_HOST = 0, /* pipe closed by host */
+ BIT_WAKE_ON_WRITE = 1, /* want to be woken on writes */
+ BIT_WAKE_ON_READ = 2, /* want to be woken on reads */
+};
+
+enum PipeRegs {
+ PIPE_REG_CMD = 0,
+
+ PIPE_REG_SIGNAL_BUFFER_HIGH = 4,
+ PIPE_REG_SIGNAL_BUFFER = 8,
+ PIPE_REG_SIGNAL_BUFFER_COUNT = 12,
+
+ PIPE_REG_OPEN_BUFFER_HIGH = 20,
+ PIPE_REG_OPEN_BUFFER = 24,
+
+ PIPE_REG_VERSION = 36,
+
+ PIPE_REG_GET_SIGNALLED = 48,
+};
+
+enum PipeCmdCode {
+ PIPE_CMD_OPEN = 1, /* to be used by the pipe device itself */
+ PIPE_CMD_CLOSE,
+ PIPE_CMD_POLL,
+ PIPE_CMD_WRITE,
+ PIPE_CMD_WAKE_ON_WRITE,
+ PIPE_CMD_READ,
+ PIPE_CMD_WAKE_ON_READ,
+
+ /*
+ * TODO(zyy): implement a deferred read/write execution to allow parallel
+ * processing of pipe operations on the host.
+ */
+ PIPE_CMD_WAKE_ON_DONE_IO,
+};
+
+enum {
+ MAX_BUFFERS_PER_COMMAND = 336,
+ MAX_SIGNALLED_PIPES = 64,
+ INITIAL_PIPES_CAPACITY = 64
+};
+
+struct goldfish_pipe_dev;
+struct goldfish_pipe;
+struct goldfish_pipe_command;
+
+/* A per-pipe command structure, shared with the host */
+struct goldfish_pipe_command {
+ s32 cmd; /* PipeCmdCode, guest -> host */
+ s32 id; /* pipe id, guest -> host */
+ s32 status; /* command execution status, host -> guest */
+ s32 reserved; /* to pad to 64-bit boundary */
+ union {
+ /* Parameters for PIPE_CMD_{READ,WRITE} */
+ struct {
+ u32 buffers_count; /* number of buffers, guest -> host */
+ s32 consumed_size; /* number of consumed bytes, host -> guest */
+ u64 ptrs[MAX_BUFFERS_PER_COMMAND]; /* buffer pointers, guest -> host */
+ u32 sizes[MAX_BUFFERS_PER_COMMAND]; /* buffer sizes, guest -> host */
+ } rw_params;
+ };
+};
+
+/* A single signalled pipe information */
+struct signalled_pipe_buffer {
+ u32 id;
+ u32 flags;
+};
+
+/* Parameters for the PIPE_CMD_OPEN command */
+struct open_command_param {
+ u64 command_buffer_ptr;
+ u32 rw_params_max_count;
+};
+
+/* Device-level set of buffers shared with the host */
+struct goldfish_pipe_dev_buffers {
+ struct open_command_param open_command_params;
+ struct signalled_pipe_buffer signalled_pipe_buffers[MAX_SIGNALLED_PIPES];
+};
+
+/* This data type models a given pipe instance */
+struct goldfish_pipe {
+ u32 id; /* pipe ID - index into goldfish_pipe_dev::pipes array */
+ unsigned long flags; /* The wake flags pipe is waiting for
+ * Note: not protected with any lock, uses atomic operations
+ * and barriers to make it thread-safe.
+ */
+ unsigned long signalled_flags; /* wake flags host have signalled,
+ * - protected by goldfish_pipe_dev::lock */
+
+ struct goldfish_pipe_command *command_buffer; /* A pointer to command buffer */
+
+ /* doubly linked list of signalled pipes, protected by goldfish_pipe_dev::lock */
+ struct goldfish_pipe *prev_signalled;
+ struct goldfish_pipe *next_signalled;
+
+ /*
+ * A pipe's own lock. Protects the following:
+ * - *command_buffer - makes sure a command can safely write its parameters
+ * to the host and read the results back.
+ */
+ struct mutex lock;
+
+ wait_queue_head_t wake_queue; /* A wake queue for sleeping until host signals an event */
+ struct goldfish_pipe_dev *dev; /* Pointer to the parent goldfish_pipe_dev instance */
+};
+
+struct goldfish_pipe_dev pipe_dev[1] = {};
+
+static int goldfish_cmd_locked(struct goldfish_pipe *pipe, enum PipeCmdCode cmd)
+{
+ pipe->command_buffer->cmd = cmd;
+ pipe->command_buffer->status = PIPE_ERROR_INVAL; /* failure by default */
+ writel(pipe->id, pipe->dev->base + PIPE_REG_CMD);
+ return pipe->command_buffer->status;
+}
+
+static int goldfish_cmd(struct goldfish_pipe *pipe, enum PipeCmdCode cmd)
+{
+ int status;
+ if (mutex_lock_interruptible(&pipe->lock))
+ return PIPE_ERROR_IO;
+ status = goldfish_cmd_locked(pipe, cmd);
+ mutex_unlock(&pipe->lock);
+ return status;
+}
+
+/*
+ * This function converts an error code returned by the emulator through
+ * the PIPE_REG_STATUS i/o register into a valid negative errno value.
+ */
+static int goldfish_pipe_error_convert(int status)
+{
+ switch (status) {
+ case PIPE_ERROR_AGAIN:
+ return -EAGAIN;
+ case PIPE_ERROR_NOMEM:
+ return -ENOMEM;
+ case PIPE_ERROR_IO:
+ return -EIO;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int pin_user_pages(unsigned long first_page, unsigned long last_page,
+ unsigned last_page_size, int is_write,
+ struct page *pages[MAX_BUFFERS_PER_COMMAND], unsigned *iter_last_page_size)
+{
+ int ret;
+ int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1;
+ if (requested_pages > MAX_BUFFERS_PER_COMMAND) {
+ requested_pages = MAX_BUFFERS_PER_COMMAND;
+ *iter_last_page_size = PAGE_SIZE;
+ } else {
+ *iter_last_page_size = last_page_size;
+ }
+
+ ret = get_user_pages_fast(
+ first_page, requested_pages, !is_write, pages);
+ if (ret <= 0)
+ return -EFAULT;
+ if (ret < requested_pages)
+ *iter_last_page_size = PAGE_SIZE;
+ return ret;
+
+}
+
+static void release_user_pages(struct page **pages, int pages_count,
+ int is_write, s32 consumed_size)
+{
+ int i;
+ for (i = 0; i < pages_count; i++) {
+ if (!is_write && consumed_size > 0) {
+ set_page_dirty(pages[i]);
+ }
+ put_page(pages[i]);
+ }
+}
+
+/* Populate the call parameters, merging adjacent pages together */
+static void populate_rw_params(
+ struct page **pages, int pages_count,
+ unsigned long address, unsigned long address_end,
+ unsigned long first_page, unsigned long last_page,
+ unsigned iter_last_page_size, int is_write,
+ struct goldfish_pipe_command *command)
+{
+ /*
+ * Process the first page separately - it's the only page that
+ * needs special handling for its start address.
+ */
+ unsigned long xaddr = page_to_phys(pages[0]);
+ unsigned long xaddr_prev = xaddr;
+ int buffer_idx = 0;
+ int i = 1;
+ int size_on_page = first_page == last_page
+ ? (int)(address_end - address)
+ : (PAGE_SIZE - (address & ~PAGE_MASK));
+ command->rw_params.ptrs[0] = (u64)(xaddr | (address & ~PAGE_MASK));
+ command->rw_params.sizes[0] = size_on_page;
+ for (; i < pages_count; ++i) {
+ xaddr = page_to_phys(pages[i]);
+ size_on_page = (i == pages_count - 1) ? iter_last_page_size : PAGE_SIZE;
+ if (xaddr == xaddr_prev + PAGE_SIZE) {
+ command->rw_params.sizes[buffer_idx] += size_on_page;
+ } else {
+ ++buffer_idx;
+ command->rw_params.ptrs[buffer_idx] = (u64)xaddr;
+ command->rw_params.sizes[buffer_idx] = size_on_page;
+ }
+ xaddr_prev = xaddr;
+ }
+ command->rw_params.buffers_count = buffer_idx + 1;
+}
+
+static int transfer_max_buffers(struct goldfish_pipe* pipe,
+ unsigned long address, unsigned long address_end, int is_write,
+ unsigned long last_page, unsigned int last_page_size,
+ s32* consumed_size, int* status)
+{
+ struct page *pages[MAX_BUFFERS_PER_COMMAND];
+ unsigned long first_page = address & PAGE_MASK;
+ unsigned int iter_last_page_size;
+ int pages_count = pin_user_pages(first_page, last_page,
+ last_page_size, is_write,
+ pages, &iter_last_page_size);
+ if (pages_count < 0)
+ return pages_count;
+
+ /* Serialize access to the pipe command buffers */
+ if (mutex_lock_interruptible(&pipe->lock))
+ return -ERESTARTSYS;
+
+ populate_rw_params(pages, pages_count, address, address_end,
+ first_page, last_page, iter_last_page_size, is_write,
+ pipe->command_buffer);
+
+ /* Transfer the data */
+ *status = goldfish_cmd_locked(pipe,
+ is_write ? PIPE_CMD_WRITE : PIPE_CMD_READ);
+
+ *consumed_size = pipe->command_buffer->rw_params.consumed_size;
+
+ mutex_unlock(&pipe->lock);
+
+ release_user_pages(pages, pages_count, is_write, *consumed_size);
+
+ return 0;
+}
+
+static int wait_for_host_signal(struct goldfish_pipe *pipe, int is_write)
+{
+ u32 wakeBit = is_write ? BIT_WAKE_ON_WRITE : BIT_WAKE_ON_READ;
+ set_bit(wakeBit, &pipe->flags);
+
+ /* Tell the emulator we're going to wait for a wake event */
+ (void)goldfish_cmd(pipe,
+ is_write ? PIPE_CMD_WAKE_ON_WRITE : PIPE_CMD_WAKE_ON_READ);
+
+ while (test_bit(wakeBit, &pipe->flags)) {
+ if (wait_event_interruptible(
+ pipe->wake_queue,
+ !test_bit(wakeBit, &pipe->flags)))
+ return -ERESTARTSYS;
+
+ if (test_bit(BIT_CLOSED_ON_HOST, &pipe->flags))
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static ssize_t goldfish_pipe_read_write(struct file *filp,
+ char __user *buffer, size_t bufflen, int is_write)
+{
+ struct goldfish_pipe *pipe = filp->private_data;
+ int count = 0, ret = -EINVAL;
+ unsigned long address, address_end, last_page;
+ unsigned int last_page_size;
+
+ /* If the emulator already closed the pipe, no need to go further */
+ if (unlikely(test_bit(BIT_CLOSED_ON_HOST, &pipe->flags)))
+ return -EIO;
+ /* Null reads or writes succeeds */
+ if (unlikely(bufflen == 0))
+ return 0;
+ /* Check the buffer range for access */
+ if (unlikely(!access_ok(is_write ? VERIFY_WRITE : VERIFY_READ,
+ buffer, bufflen)))
+ return -EFAULT;
+
+ address = (unsigned long)buffer;
+ address_end = address + bufflen;
+ last_page = (address_end - 1) & PAGE_MASK;
+ last_page_size = ((address_end - 1) & ~PAGE_MASK) + 1;
+
+ while (address < address_end) {
+ s32 consumed_size;
+ int status;
+ ret = transfer_max_buffers(pipe, address, address_end, is_write,
+ last_page, last_page_size, &consumed_size, &status);
+ if (ret < 0)
+ break;
+
+ if (consumed_size > 0) {
+ /* No matter what's the status, we've transfered something */
+ count += consumed_size;
+ address += consumed_size;
+ }
+ if (status > 0)
+ continue;
+ if (status == 0) {
+ /* EOF */
+ ret = 0;
+ break;
+ }
+ if (count > 0) {
+ /*
+ * An error occured, but we already transfered
+ * something on one of the previous iterations.
+ * Just return what we already copied and log this
+ * err.
+ */
+ if (status != PIPE_ERROR_AGAIN)
+ pr_info_ratelimited("goldfish_pipe: backend error %d on %s\n",
+ status, is_write ? "write" : "read");
+ break;
+ }
+
+ /*
+ * If the error is not PIPE_ERROR_AGAIN, or if we are in
+ * non-blocking mode, just return the error code.
+ */
+ if (status != PIPE_ERROR_AGAIN || (filp->f_flags & O_NONBLOCK) != 0) {
+ ret = goldfish_pipe_error_convert(status);
+ break;
+ }
+
+ status = wait_for_host_signal(pipe, is_write);
+ if (status < 0)
+ return status;
+ }
+
+ if (count > 0)
+ return count;
+ return ret;
+}
+
+static ssize_t goldfish_pipe_read(struct file *filp, char __user *buffer,
+ size_t bufflen, loff_t *ppos)
+{
+ return goldfish_pipe_read_write(filp, buffer, bufflen, /* is_write */ 0);
+}
+
+static ssize_t goldfish_pipe_write(struct file *filp,
+ const char __user *buffer, size_t bufflen,
+ loff_t *ppos)
+{
+ return goldfish_pipe_read_write(filp,
+ /* cast away the const */(char __user *)buffer, bufflen,
+ /* is_write */ 1);
+}
+
+static unsigned int goldfish_pipe_poll(struct file *filp, poll_table *wait)
+{
+ struct goldfish_pipe *pipe = filp->private_data;
+ unsigned int mask = 0;
+ int status;
+
+ poll_wait(filp, &pipe->wake_queue, wait);
+
+ status = goldfish_cmd(pipe, PIPE_CMD_POLL);
+ if (status < 0) {
+ return -ERESTARTSYS;
+ }
+
+ if (status & PIPE_POLL_IN)
+ mask |= POLLIN | POLLRDNORM;
+ if (status & PIPE_POLL_OUT)
+ mask |= POLLOUT | POLLWRNORM;
+ if (status & PIPE_POLL_HUP)
+ mask |= POLLHUP;
+ if (test_bit(BIT_CLOSED_ON_HOST, &pipe->flags))
+ mask |= POLLERR;
+
+ return mask;
+}
+
+static void signalled_pipes_add_locked(struct goldfish_pipe_dev *dev,
+ u32 id, u32 flags)
+{
+ struct goldfish_pipe *pipe;
+
+ BUG_ON(id >= dev->pipes_capacity);
+
+ pipe = dev->pipes[id];
+ if (!pipe)
+ return;
+ pipe->signalled_flags |= flags;
+
+ if (pipe->prev_signalled || pipe->next_signalled
+ || dev->first_signalled_pipe == pipe)
+ return; /* already in the list */
+ pipe->next_signalled = dev->first_signalled_pipe;
+ if (dev->first_signalled_pipe) {
+ dev->first_signalled_pipe->prev_signalled = pipe;
+ }
+ dev->first_signalled_pipe = pipe;
+}
+
+static void signalled_pipes_remove_locked(struct goldfish_pipe_dev *dev,
+ struct goldfish_pipe *pipe) {
+ if (pipe->prev_signalled)
+ pipe->prev_signalled->next_signalled = pipe->next_signalled;
+ if (pipe->next_signalled)
+ pipe->next_signalled->prev_signalled = pipe->prev_signalled;
+ if (pipe == dev->first_signalled_pipe)
+ dev->first_signalled_pipe = pipe->next_signalled;
+ pipe->prev_signalled = NULL;
+ pipe->next_signalled = NULL;
+}
+
+static struct goldfish_pipe *signalled_pipes_pop_front(struct goldfish_pipe_dev *dev,
+ int *wakes)
+{
+ struct goldfish_pipe *pipe;
+ unsigned long flags;
+ spin_lock_irqsave(&dev->lock, flags);
+
+ pipe = dev->first_signalled_pipe;
+ if (pipe) {
+ *wakes = pipe->signalled_flags;
+ pipe->signalled_flags = 0;
+ /*
+ * This is an optimized version of signalled_pipes_remove_locked() -
+ * we want to make it as fast as possible to wake the sleeping pipe
+ * operations faster
+ */
+ dev->first_signalled_pipe = pipe->next_signalled;
+ if (dev->first_signalled_pipe)
+ dev->first_signalled_pipe->prev_signalled = NULL;
+ pipe->next_signalled = NULL;
+ }
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return pipe;
+}
+
+static void goldfish_interrupt_task(unsigned long unused)
+{
+ struct goldfish_pipe_dev *dev = pipe_dev;
+ /* Iterate over the signalled pipes and wake them one by one */
+ struct goldfish_pipe *pipe;
+ int wakes;
+ while ((pipe = signalled_pipes_pop_front(dev, &wakes)) != NULL) {
+ if (wakes & PIPE_WAKE_CLOSED) {
+ pipe->flags = 1 << BIT_CLOSED_ON_HOST;
+ } else {
+ if (wakes & PIPE_WAKE_READ)
+ clear_bit(BIT_WAKE_ON_READ, &pipe->flags);
+ if (wakes & PIPE_WAKE_WRITE)
+ clear_bit(BIT_WAKE_ON_WRITE, &pipe->flags);
+ }
+ /*
+ * wake_up_interruptible() implies a write barrier, so don't explicitly
+ * add another one here.
+ */
+ wake_up_interruptible(&pipe->wake_queue);
+ }
+}
+DECLARE_TASKLET(goldfish_interrupt_tasklet, goldfish_interrupt_task, 0);
+
+/*
+ * The general idea of the interrupt handling:
+ *
+ * 1. device raises an interrupt if there's at least one signalled pipe
+ * 2. IRQ handler reads the signalled pipes and their count from the device
+ * 3. device writes them into a shared buffer and returns the count
+ * it only resets the IRQ if it has returned all signalled pipes,
+ * otherwise it leaves it raised, so IRQ handler will be called
+ * again for the next chunk
+ * 4. IRQ handler adds all returned pipes to the device's signalled pipes list
+ * 5. IRQ handler launches a tasklet to process the signalled pipes from the
+ * list in a separate context
+ */
+static irqreturn_t goldfish_pipe_interrupt(int irq, void *dev_id)
+{
+ u32 count;
+ u32 i;
+ unsigned long flags;
+ struct goldfish_pipe_dev *dev = dev_id;
+ if (dev != pipe_dev)
+ return IRQ_NONE;
+
+ /* Request the signalled pipes from the device */
+ spin_lock_irqsave(&dev->lock, flags);
+
+ count = readl(dev->base + PIPE_REG_GET_SIGNALLED);
+ if (count == 0) {
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return IRQ_NONE;
+ }
+ if (count > MAX_SIGNALLED_PIPES)
+ count = MAX_SIGNALLED_PIPES;
+
+ for (i = 0; i < count; ++i)
+ signalled_pipes_add_locked(dev,
+ dev->buffers->signalled_pipe_buffers[i].id,
+ dev->buffers->signalled_pipe_buffers[i].flags);
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ tasklet_schedule(&goldfish_interrupt_tasklet);
+ return IRQ_HANDLED;
+}
+
+static int get_free_pipe_id_locked(struct goldfish_pipe_dev *dev)
+{
+ int id;
+ for (id = 0; id < dev->pipes_capacity; ++id)
+ if (!dev->pipes[id])
+ return id;
+
+ {
+ /* Reallocate the array */
+ u32 new_capacity = 2 * dev->pipes_capacity;
+ struct goldfish_pipe **pipes =
+ kcalloc(new_capacity, sizeof(*pipes),
+ GFP_ATOMIC);
+ if (!pipes)
+ return -ENOMEM;
+ memcpy(pipes, dev->pipes, sizeof(*pipes) * dev->pipes_capacity);
+ kfree(dev->pipes);
+ dev->pipes = pipes;
+ id = dev->pipes_capacity;
+ dev->pipes_capacity = new_capacity;
+ }
+ return id;
+}
+
+/**
+ * goldfish_pipe_open - open a channel to the AVD
+ * @inode: inode of device
+ * @file: file struct of opener
+ *
+ * Create a new pipe link between the emulator and the use application.
+ * Each new request produces a new pipe.
+ *
+ * Note: we use the pipe ID as a mux. All goldfish emulations are 32bit
+ * right now so this is fine. A move to 64bit will need this addressing
+ */
+static int goldfish_pipe_open(struct inode *inode, struct file *file)
+{
+ struct goldfish_pipe_dev *dev = pipe_dev;
+ unsigned long flags;
+ int id;
+ int status;
+
+ /* Allocate new pipe kernel object */
+ struct goldfish_pipe *pipe = kzalloc(sizeof(*pipe), GFP_KERNEL);
+ if (pipe == NULL)
+ return -ENOMEM;
+
+ pipe->dev = dev;
+ mutex_init(&pipe->lock);
+ init_waitqueue_head(&pipe->wake_queue);
+
+ /*
+ * Command buffer needs to be allocated on its own page to make sure it is
+ * physically contiguous in host's address space.
+ */
+ pipe->command_buffer =
+ (struct goldfish_pipe_command*)__get_free_page(GFP_KERNEL);
+ if (!pipe->command_buffer) {
+ status = -ENOMEM;
+ goto err_pipe;
+ }
+
+ spin_lock_irqsave(&dev->lock, flags);
+
+ id = get_free_pipe_id_locked(dev);
+ if (id < 0) {
+ status = id;
+ goto err_id_locked;
+ }
+
+ dev->pipes[id] = pipe;
+ pipe->id = id;
+ pipe->command_buffer->id = id;
+
+ /* Now tell the emulator we're opening a new pipe. */
+ dev->buffers->open_command_params.rw_params_max_count =
+ MAX_BUFFERS_PER_COMMAND;
+ dev->buffers->open_command_params.command_buffer_ptr =
+ (u64)(unsigned long)__pa(pipe->command_buffer);
+ status = goldfish_cmd_locked(pipe, PIPE_CMD_OPEN);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ if (status < 0)
+ goto err_cmd;
+ /* All is done, save the pipe into the file's private data field */
+ file->private_data = pipe;
+ return 0;
+
+err_cmd:
+ spin_lock_irqsave(&dev->lock, flags);
+ dev->pipes[id] = NULL;
+err_id_locked:
+ spin_unlock_irqrestore(&dev->lock, flags);
+ free_page((unsigned long)pipe->command_buffer);
+err_pipe:
+ kfree(pipe);
+ return status;
+}
+
+static int goldfish_pipe_release(struct inode *inode, struct file *filp)
+{
+ unsigned long flags;
+ struct goldfish_pipe *pipe = filp->private_data;
+ struct goldfish_pipe_dev *dev = pipe->dev;
+
+ /* The guest is closing the channel, so tell the emulator right now */
+ (void)goldfish_cmd(pipe, PIPE_CMD_CLOSE);
+
+ spin_lock_irqsave(&dev->lock, flags);
+ dev->pipes[pipe->id] = NULL;
+ signalled_pipes_remove_locked(dev, pipe);
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ filp->private_data = NULL;
+ free_page((unsigned long)pipe->command_buffer);
+ kfree(pipe);
+ return 0;
+}
+
+static const struct file_operations goldfish_pipe_fops = {
+ .owner = THIS_MODULE,
+ .read = goldfish_pipe_read,
+ .write = goldfish_pipe_write,
+ .poll = goldfish_pipe_poll,
+ .open = goldfish_pipe_open,
+ .release = goldfish_pipe_release,
+};
+
+static struct miscdevice goldfish_pipe_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "goldfish_pipe",
+ .fops = &goldfish_pipe_fops,
+};
+
+static int goldfish_pipe_device_init_v2(struct platform_device *pdev)
+{
+ char *page;
+ struct goldfish_pipe_dev *dev = pipe_dev;
+ int err = devm_request_irq(&pdev->dev, dev->irq, goldfish_pipe_interrupt,
+ IRQF_SHARED, "goldfish_pipe", dev);
+ if (err) {
+ dev_err(&pdev->dev, "unable to allocate IRQ for v2\n");
+ return err;
+ }
+
+ err = misc_register(&goldfish_pipe_dev);
+ if (err) {
+ dev_err(&pdev->dev, "unable to register v2 device\n");
+ return err;
+ }
+
+ dev->first_signalled_pipe = NULL;
+ dev->pipes_capacity = INITIAL_PIPES_CAPACITY;
+ dev->pipes = kcalloc(dev->pipes_capacity, sizeof(*dev->pipes), GFP_KERNEL);
+ if (!dev->pipes)
+ return -ENOMEM;
+
+ /*
+ * We're going to pass two buffers, open_command_params and
+ * signalled_pipe_buffers, to the host. This means each of those buffers
+ * needs to be contained in a single physical page. The easiest choice is
+ * to just allocate a page and place the buffers in it.
+ */
+ BUG_ON(sizeof(*dev->buffers) > PAGE_SIZE);
+ page = (char*)__get_free_page(GFP_KERNEL);
+ if (!page) {
+ kfree(dev->pipes);
+ return -ENOMEM;
+ }
+ dev->buffers = (struct goldfish_pipe_dev_buffers*)page;
+
+ /* Send the buffer addresses to the host */
+ {
+ u64 paddr = __pa(&dev->buffers->signalled_pipe_buffers);
+ writel((u32)(unsigned long)(paddr >> 32), dev->base + PIPE_REG_SIGNAL_BUFFER_HIGH);
+ writel((u32)(unsigned long)paddr, dev->base + PIPE_REG_SIGNAL_BUFFER);
+ writel((u32)MAX_SIGNALLED_PIPES, dev->base + PIPE_REG_SIGNAL_BUFFER_COUNT);
+
+ paddr = __pa(&dev->buffers->open_command_params);
+ writel((u32)(unsigned long)(paddr >> 32), dev->base + PIPE_REG_OPEN_BUFFER_HIGH);
+ writel((u32)(unsigned long)paddr, dev->base + PIPE_REG_OPEN_BUFFER);
+ }
+ return 0;
+}
+
+static void goldfish_pipe_device_deinit_v2(struct platform_device *pdev) {
+ struct goldfish_pipe_dev *dev = pipe_dev;
+ misc_deregister(&goldfish_pipe_dev);
+ kfree(dev->pipes);
+ free_page((unsigned long)dev->buffers);
+}
+
+static int goldfish_pipe_probe(struct platform_device *pdev)
+{
+ int err;
+ struct resource *r;
+ struct goldfish_pipe_dev *dev = pipe_dev;
+
+ BUG_ON(sizeof(struct goldfish_pipe_command) > PAGE_SIZE);
+
+ /* not thread safe, but this should not happen */
+ WARN_ON(dev->base != NULL);
+
+ spin_lock_init(&dev->lock);
+
+ r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (r == NULL || resource_size(r) < PAGE_SIZE) {
+ dev_err(&pdev->dev, "can't allocate i/o page\n");
+ return -EINVAL;
+ }
+ dev->base = devm_ioremap(&pdev->dev, r->start, PAGE_SIZE);
+ if (dev->base == NULL) {
+ dev_err(&pdev->dev, "ioremap failed\n");
+ return -EINVAL;
+ }
+
+ r = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+ if (r == NULL) {
+ err = -EINVAL;
+ goto error;
+ }
+ dev->irq = r->start;
+
+ /*
+ * Exchange the versions with the host device
+ *
+ * Note: v1 driver used to not report its version, so we write it before
+ * reading device version back: this allows the host implementation to
+ * detect the old driver (if there was no version write before read).
+ */
+ writel((u32)PIPE_DRIVER_VERSION, dev->base + PIPE_REG_VERSION);
+ dev->version = readl(dev->base + PIPE_REG_VERSION);
+ if (dev->version < PIPE_CURRENT_DEVICE_VERSION) {
+ /* initialize the old device version */
+ err = goldfish_pipe_device_init_v1(pdev);
+ } else {
+ /* Host device supports the new interface */
+ err = goldfish_pipe_device_init_v2(pdev);
+ }
+ if (!err)
+ return 0;
+
+error:
+ dev->base = NULL;
+ return err;
+}
+
+static int goldfish_pipe_remove(struct platform_device *pdev)
+{
+ struct goldfish_pipe_dev *dev = pipe_dev;
+ if (dev->version < PIPE_CURRENT_DEVICE_VERSION)
+ goldfish_pipe_device_deinit_v1(pdev);
+ else
+ goldfish_pipe_device_deinit_v2(pdev);
+ dev->base = NULL;
+ return 0;
+}
+
+static const struct acpi_device_id goldfish_pipe_acpi_match[] = {
+ { "GFSH0003", 0 },
+ { },
+};
+MODULE_DEVICE_TABLE(acpi, goldfish_pipe_acpi_match);
+
+static const struct of_device_id goldfish_pipe_of_match[] = {
+ { .compatible = "google,android-pipe", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, goldfish_pipe_of_match);
+
+static struct platform_driver goldfish_pipe_driver = {
+ .probe = goldfish_pipe_probe,
+ .remove = goldfish_pipe_remove,
+ .driver = {
+ .name = "goldfish_pipe",
+ .of_match_table = goldfish_pipe_of_match,
+ .acpi_match_table = ACPI_PTR(goldfish_pipe_acpi_match),
+ }
+};
+
+module_platform_driver(goldfish_pipe_driver);
+MODULE_AUTHOR("David Turner <digit@google.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 55663b3..58dcee5 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -68,6 +68,7 @@
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/tick.h>
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 379f963..e52b9dd 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -9528,7 +9528,7 @@ static struct ibm_init_struct ibms_init[] __initdata = {
},
};
-static int __init set_ibm_param(const char *val, struct kernel_param *kp)
+static int __init set_ibm_param(const char *val, const struct kernel_param *kp)
{
unsigned int i;
struct ibm_struct *ibm;
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 85cb5b9..bc2f173 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -108,7 +108,10 @@ static ssize_t power_supply_show_property(struct device *dev,
else if (off >= POWER_SUPPLY_PROP_MODEL_NAME)
return sprintf(buf, "%s\n", value.strval);
- return sprintf(buf, "%d\n", value.intval);
+ if (off == POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT)
+ return sprintf(buf, "%lld\n", value.int64val);
+ else
+ return sprintf(buf, "%d\n", value.intval);
}
static ssize_t power_supply_store_property(struct device *dev,
@@ -199,6 +202,12 @@ static struct device_attribute power_supply_attrs[] = {
POWER_SUPPLY_ATTR(scope),
POWER_SUPPLY_ATTR(charge_term_current),
POWER_SUPPLY_ATTR(calibrate),
+ /* Local extensions */
+ POWER_SUPPLY_ATTR(usb_hc),
+ POWER_SUPPLY_ATTR(usb_otg),
+ POWER_SUPPLY_ATTR(charge_enabled),
+ /* Local extensions of type int64_t */
+ POWER_SUPPLY_ATTR(charge_counter_ext),
/* Properties of type `const char *' */
POWER_SUPPLY_ATTR(model_name),
POWER_SUPPLY_ATTR(manufacturer),
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index 4bcfb88..34aea38 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -45,6 +45,42 @@ struct palmas_rtc {
/* Total number of RTC registers needed to set time*/
#define PALMAS_NUM_TIME_REGS (PALMAS_YEARS_REG - PALMAS_SECONDS_REG + 1)
+/*
+ * Special bin2bcd mapping to deal with bcd storage of year.
+ *
+ * 0-69 -> 0xD0
+ * 70-99 (1970 - 1999) -> 0xD0 - 0xF9 (correctly rolls to 0x00)
+ * 100-199 (2000 - 2099) -> 0x00 - 0x99 (does not roll to 0xA0 :-( )
+ * 200-229 (2100 - 2129) -> 0xA0 - 0xC9 (really for completeness)
+ * 230- -> 0xC9
+ *
+ * Confirmed: the only transition that does not work correctly for this rtc
+ * clock is the transition from 2099 to 2100, it proceeds to 2000. We will
+ * accept this issue since the clock retains and transitions the year correctly
+ * in all other conditions.
+ */
+static unsigned char year_bin2bcd(int val)
+{
+ if (val < 70)
+ return 0xD0;
+ if (val < 100)
+ return bin2bcd(val - 20) | 0x80; /* KISS leverage of bin2bcd */
+ if (val >= 230)
+ return 0xC9;
+ if (val >= 200)
+ return bin2bcd(val - 180) | 0x80;
+ return bin2bcd(val - 100);
+}
+
+static int year_bcd2bin(unsigned char val)
+{
+ if (val >= 0xD0)
+ return bcd2bin(val & 0x7F) + 20;
+ if (val >= 0xA0)
+ return bcd2bin(val & 0x7F) + 180;
+ return bcd2bin(val) + 100;
+}
+
static int palmas_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
unsigned char rtc_data[PALMAS_NUM_TIME_REGS];
@@ -71,7 +107,7 @@ static int palmas_rtc_read_time(struct device *dev, struct rtc_time *tm)
tm->tm_hour = bcd2bin(rtc_data[2]);
tm->tm_mday = bcd2bin(rtc_data[3]);
tm->tm_mon = bcd2bin(rtc_data[4]) - 1;
- tm->tm_year = bcd2bin(rtc_data[5]) + 100;
+ tm->tm_year = year_bcd2bin(rtc_data[5]);
return ret;
}
@@ -87,7 +123,7 @@ static int palmas_rtc_set_time(struct device *dev, struct rtc_time *tm)
rtc_data[2] = bin2bcd(tm->tm_hour);
rtc_data[3] = bin2bcd(tm->tm_mday);
rtc_data[4] = bin2bcd(tm->tm_mon + 1);
- rtc_data[5] = bin2bcd(tm->tm_year - 100);
+ rtc_data[5] = year_bin2bcd(tm->tm_year);
/* Stop RTC while updating the RTC time registers */
ret = palmas_update_bits(palmas, PALMAS_RTC_BASE, PALMAS_RTC_CTRL_REG,
@@ -142,7 +178,7 @@ static int palmas_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
alm->time.tm_hour = bcd2bin(alarm_data[2]);
alm->time.tm_mday = bcd2bin(alarm_data[3]);
alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1;
- alm->time.tm_year = bcd2bin(alarm_data[5]) + 100;
+ alm->time.tm_year = year_bcd2bin(alarm_data[5]);
ret = palmas_read(palmas, PALMAS_RTC_BASE, PALMAS_RTC_INTERRUPTS_REG,
&int_val);
@@ -173,7 +209,7 @@ static int palmas_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
alarm_data[2] = bin2bcd(alm->time.tm_hour);
alarm_data[3] = bin2bcd(alm->time.tm_mday);
alarm_data[4] = bin2bcd(alm->time.tm_mon + 1);
- alarm_data[5] = bin2bcd(alm->time.tm_year - 100);
+ alarm_data[5] = year_bin2bcd(alm->time.tm_year);
ret = palmas_bulk_write(palmas, PALMAS_RTC_BASE,
PALMAS_ALARM_SECONDS_REG, alarm_data, PALMAS_NUM_TIME_REGS);
diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c
index 375c536..c5eb0c4 100644
--- a/drivers/scsi/fcoe/fcoe_transport.c
+++ b/drivers/scsi/fcoe/fcoe_transport.c
@@ -32,13 +32,13 @@ MODULE_AUTHOR("Open-FCoE.org");
MODULE_DESCRIPTION("FIP discovery protocol and FCoE transport for FCoE HBAs");
MODULE_LICENSE("GPL v2");
-static int fcoe_transport_create(const char *, struct kernel_param *);
-static int fcoe_transport_destroy(const char *, struct kernel_param *);
+static int fcoe_transport_create(const char *, const struct kernel_param *);
+static int fcoe_transport_destroy(const char *, const struct kernel_param *);
static int fcoe_transport_show(char *buffer, const struct kernel_param *kp);
static struct fcoe_transport *fcoe_transport_lookup(struct net_device *device);
static struct fcoe_transport *fcoe_netdev_map_lookup(struct net_device *device);
-static int fcoe_transport_enable(const char *, struct kernel_param *);
-static int fcoe_transport_disable(const char *, struct kernel_param *);
+static int fcoe_transport_enable(const char *, const struct kernel_param *);
+static int fcoe_transport_disable(const char *, const struct kernel_param *);
static int libfcoe_device_notification(struct notifier_block *notifier,
ulong event, void *ptr);
@@ -865,7 +865,8 @@ EXPORT_SYMBOL(fcoe_ctlr_destroy_store);
*
* Returns: 0 for success
*/
-static int fcoe_transport_create(const char *buffer, struct kernel_param *kp)
+static int fcoe_transport_create(const char *buffer,
+ const struct kernel_param *kp)
{
int rc = -ENODEV;
struct net_device *netdev = NULL;
@@ -930,7 +931,8 @@ static int fcoe_transport_create(const char *buffer, struct kernel_param *kp)
*
* Returns: 0 for success
*/
-static int fcoe_transport_destroy(const char *buffer, struct kernel_param *kp)
+static int fcoe_transport_destroy(const char *buffer,
+ const struct kernel_param *kp)
{
int rc = -ENODEV;
struct net_device *netdev = NULL;
@@ -974,7 +976,8 @@ static int fcoe_transport_destroy(const char *buffer, struct kernel_param *kp)
*
* Returns: 0 for success
*/
-static int fcoe_transport_disable(const char *buffer, struct kernel_param *kp)
+static int fcoe_transport_disable(const char *buffer,
+ const struct kernel_param *kp)
{
int rc = -ENODEV;
struct net_device *netdev = NULL;
@@ -1008,7 +1011,8 @@ static int fcoe_transport_disable(const char *buffer, struct kernel_param *kp)
*
* Returns: 0 for success
*/
-static int fcoe_transport_enable(const char *buffer, struct kernel_param *kp)
+static int fcoe_transport_enable(const char *buffer,
+ const struct kernel_param *kp)
{
int rc = -ENODEV;
struct net_device *netdev = NULL;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 16716b2..b583436 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -105,7 +105,7 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
*
*/
static int
-_scsih_set_fwfault_debug(const char *val, struct kernel_param *kp)
+_scsih_set_fwfault_debug(const char *val, const struct kernel_param *kp)
{
int ret = param_set_int(val, kp);
struct MPT3SAS_ADAPTER *ioc;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index aa2078d..f0a3bb4 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -281,7 +281,7 @@ struct _scsi_io_transfer {
* Note: The logging levels are defined in mpt3sas_debug.h.
*/
static int
-_scsih_set_debug_level(const char *val, struct kernel_param *kp)
+_scsih_set_debug_level(const char *val, const struct kernel_param *kp)
{
int ret = param_set_int(val, kp);
struct MPT3SAS_ADAPTER *ioc;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index a767d94..b8e9cd4 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -41,6 +41,7 @@
#include <linux/devfreq.h>
#include <linux/nls.h>
#include <linux/of.h>
+#include <linux/blkdev.h>
#include "ufshcd.h"
#include "ufs_quirks.h"
#include "unipro.h"
@@ -1501,6 +1502,17 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
clear_bit_unlock(tag, &hba->lrb_in_use);
goto out;
}
+
+ /* IO svc time latency histogram */
+ if (hba != NULL && cmd->request != NULL) {
+ if (hba->latency_hist_enabled &&
+ (cmd->request->cmd_type == REQ_TYPE_FS)) {
+ cmd->request->lat_hist_io_start = ktime_get();
+ cmd->request->lat_hist_enabled = 1;
+ } else
+ cmd->request->lat_hist_enabled = 0;
+ }
+
WARN_ON(hba->clk_gating.state != CLKS_ON);
lrbp = &hba->lrb[tag];
@@ -3710,6 +3722,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
struct scsi_cmnd *cmd;
int result;
int index;
+ struct request *req;
for_each_set_bit(index, &completed_reqs, hba->nutrs) {
lrbp = &hba->lrb[index];
@@ -3721,6 +3734,22 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
/* Mark completed command as NULL in LRB */
lrbp->cmd = NULL;
clear_bit_unlock(index, &hba->lrb_in_use);
+ req = cmd->request;
+ if (req) {
+ /* Update IO svc time latency histogram */
+ if (req->lat_hist_enabled) {
+ ktime_t completion;
+ u_int64_t delta_us;
+
+ completion = ktime_get();
+ delta_us = ktime_us_delta(completion,
+ req->lat_hist_io_start);
+ blk_update_latency_hist(
+ (rq_data_dir(req) == READ) ?
+ &hba->io_lat_read :
+ &hba->io_lat_write, delta_us);
+ }
+ }
/* Do not touch lrbp after scsi done */
cmd->scsi_done(cmd);
__ufshcd_release(hba);
@@ -6529,6 +6558,61 @@ int ufshcd_shutdown(struct ufs_hba *hba)
}
EXPORT_SYMBOL(ufshcd_shutdown);
+/*
+ * Values permitted 0, 1, 2.
+ * 0 -> Disable IO latency histograms (default)
+ * 1 -> Enable IO latency histograms
+ * 2 -> Zero out IO latency histograms
+ */
+static ssize_t
+latency_hist_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+ long value;
+
+ if (kstrtol(buf, 0, &value))
+ return -EINVAL;
+ if (value == BLK_IO_LAT_HIST_ZERO) {
+ memset(&hba->io_lat_read, 0, sizeof(hba->io_lat_read));
+ memset(&hba->io_lat_write, 0, sizeof(hba->io_lat_write));
+ } else if (value == BLK_IO_LAT_HIST_ENABLE ||
+ value == BLK_IO_LAT_HIST_DISABLE)
+ hba->latency_hist_enabled = value;
+ return count;
+}
+
+ssize_t
+latency_hist_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+ size_t written_bytes;
+
+ written_bytes = blk_latency_hist_show("Read", &hba->io_lat_read,
+ buf, PAGE_SIZE);
+ written_bytes += blk_latency_hist_show("Write", &hba->io_lat_write,
+ buf + written_bytes, PAGE_SIZE - written_bytes);
+
+ return written_bytes;
+}
+
+static DEVICE_ATTR(latency_hist, S_IRUGO | S_IWUSR,
+ latency_hist_show, latency_hist_store);
+
+static void
+ufshcd_init_latency_hist(struct ufs_hba *hba)
+{
+ if (device_create_file(hba->dev, &dev_attr_latency_hist))
+ dev_err(hba->dev, "Failed to create latency_hist sysfs entry\n");
+}
+
+static void
+ufshcd_exit_latency_hist(struct ufs_hba *hba)
+{
+ device_create_file(hba->dev, &dev_attr_latency_hist);
+}
+
/**
* ufshcd_remove - de-allocate SCSI host and host memory space
* data structure memory
@@ -6542,6 +6626,7 @@ void ufshcd_remove(struct ufs_hba *hba)
ufshcd_hba_stop(hba, true);
ufshcd_exit_clk_gating(hba);
+ ufshcd_exit_latency_hist(hba);
if (ufshcd_is_clkscaling_enabled(hba))
devfreq_remove_device(hba->devfreq);
ufshcd_hba_exit(hba);
@@ -6890,6 +6975,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
/* Hold auto suspend until async scan completes */
pm_runtime_get_sync(dev);
+ ufshcd_init_latency_hist(hba);
+
/*
* We are assuming that device wasn't put in sleep/power-down
* state exclusively during the boot stage before kernel.
@@ -6906,6 +6993,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
scsi_remove_host(hba->host);
exit_gating:
ufshcd_exit_clk_gating(hba);
+ ufshcd_exit_latency_hist(hba);
out_disable:
hba->is_irq_enabled = false;
ufshcd_hba_exit(hba);
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 6dbd2e1..096e667 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -575,6 +575,10 @@ struct ufs_hba {
bool is_urgent_bkops_lvl_checked;
struct ufs_desc_size desc_size;
+
+ int latency_hist_enabled;
+ struct io_latency_state io_lat_read;
+ struct io_latency_state io_lat_write;
};
/* Returns true if clocks can be gated. Otherwise false */
diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig
index 6c00d6f..8f548691 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -24,6 +24,24 @@
scripts (/init.rc), and it defines priority values with minimum free memory size
for each priority.
+config ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+ bool "Android Low Memory Killer: detect oom_adj values"
+ depends on ANDROID_LOW_MEMORY_KILLER
+ default y
+ ---help---
+ Detect oom_adj values written to
+ /sys/module/lowmemorykiller/parameters/adj and convert them
+ to oom_score_adj values.
+
+config ANDROID_VSOC
+ tristate "Android Virtual SoC support"
+ default n
+ depends on PCI_MSI
+ ---help---
+ This option adds support for the Virtual SoC driver needed to boot
+ a 'cuttlefish' Android image inside QEmu. The driver interacts with
+ a QEmu ivshmem device. If built as a module, it will be called vsoc.
+
source "drivers/staging/android/ion/Kconfig"
endif # if ANDROID
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index 7ed1be7..3482d43c 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -4,3 +4,4 @@
obj-$(CONFIG_ASHMEM) += ashmem.o
obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER) += lowmemorykiller.o
+obj-$(CONFIG_ANDROID_VSOC) += vsoc.o
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
index 64d8c87..edfb680 100644
--- a/drivers/staging/android/TODO
+++ b/drivers/staging/android/TODO
@@ -33,5 +33,14 @@
- clean up and ABI check for security issues
- move it to drivers/base/dma-buf
+vsoc.c, uapi/vsoc_shm.h
+ - The current driver uses the same wait queue for all of the futexes in a
+ region. This will cause false wakeups in regions with a large number of
+ waiting threads. We should eventually use multiple queues and select the
+ queue based on the region.
+ - Add debugfs support for examining the permissions of regions.
+ - Remove VSOC_WAIT_FOR_INCOMING_INTERRUPT ioctl. This functionality has been
+ superseded by the futex and is there for legacy reasons.
+
Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com>
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 99fd4f5..c58eae8 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -443,22 +443,14 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
}
get_file(asma->file);
- /*
- * XXX - Reworked to use shmem_zero_setup() instead of
- * shmem_set_file while we're in staging. -jstultz
- */
- if (vma->vm_flags & VM_SHARED) {
- ret = shmem_zero_setup(vma);
- if (ret) {
- fput(asma->file);
- goto out;
- }
+ if (vma->vm_flags & VM_SHARED)
+ shmem_set_file(vma, asma->file);
+ else {
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = asma->file;
}
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = asma->file;
-
out:
mutex_unlock(&ashmem_mutex);
return ret;
@@ -495,9 +487,9 @@ ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
loff_t start = range->pgstart * PAGE_SIZE;
loff_t end = (range->pgend + 1) * PAGE_SIZE;
- vfs_fallocate(range->asma->file,
- FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
- start, end - start);
+ range->asma->file->f_op->fallocate(range->asma->file,
+ FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ start, end - start);
range->purged = ASHMEM_WAS_PURGED;
lru_del(range);
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 806e9b3..3af862c 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -622,7 +622,7 @@ static int ion_debug_client_show(struct seq_file *s, void *unused)
mutex_lock(&debugfs_mutex);
if (!is_client_alive(client)) {
- seq_printf(s, "ion_client 0x%p dead, can't dump its buffers\n",
+ seq_printf(s, "ion_client 0x%pK dead, can't dump its buffers\n",
client);
mutex_unlock(&debugfs_mutex);
return 0;
@@ -775,7 +775,6 @@ void ion_client_destroy(struct ion_client *client)
struct ion_device *dev = client->dev;
struct rb_node *n;
- pr_debug("%s: %d\n", __func__, __LINE__);
mutex_lock(&debugfs_mutex);
while ((n = rb_first(&client->handles))) {
struct ion_handle *handle = rb_entry(n, struct ion_handle,
@@ -848,9 +847,6 @@ static void ion_buffer_sync_for_device(struct ion_buffer *buffer,
int pages = PAGE_ALIGN(buffer->size) / PAGE_SIZE;
int i;
- pr_debug("%s: syncing for device %s\n", __func__,
- dev ? dev_name(dev) : "null");
-
if (!ion_buffer_fault_user_mappings(buffer))
return;
@@ -904,7 +900,6 @@ static void ion_vm_open(struct vm_area_struct *vma)
mutex_lock(&buffer->lock);
list_add(&vma_list->list, &buffer->vmas);
mutex_unlock(&buffer->lock);
- pr_debug("%s: adding %p\n", __func__, vma);
}
static void ion_vm_close(struct vm_area_struct *vma)
@@ -912,14 +907,12 @@ static void ion_vm_close(struct vm_area_struct *vma)
struct ion_buffer *buffer = vma->vm_private_data;
struct ion_vma_list *vma_list, *tmp;
- pr_debug("%s\n", __func__);
mutex_lock(&buffer->lock);
list_for_each_entry_safe(vma_list, tmp, &buffer->vmas, list) {
if (vma_list->vma != vma)
continue;
list_del(&vma_list->list);
kfree(vma_list);
- pr_debug("%s: deleting %p\n", __func__, vma);
break;
}
mutex_unlock(&buffer->lock);
@@ -1231,7 +1224,6 @@ static int ion_release(struct inode *inode, struct file *file)
{
struct ion_client *client = file->private_data;
- pr_debug("%s: %d\n", __func__, __LINE__);
ion_client_destroy(client);
return 0;
}
@@ -1243,7 +1235,6 @@ static int ion_open(struct inode *inode, struct file *file)
struct ion_client *client;
char debug_name[64];
- pr_debug("%s: %d\n", __func__, __LINE__);
snprintf(debug_name, 64, "%u", task_pid_nr(current->group_leader));
client = ion_client_create(dev, debug_name);
if (IS_ERR(client))
diff --git a/drivers/staging/android/ion/ion_cma_heap.c b/drivers/staging/android/ion/ion_cma_heap.c
index 6c7de74..0ca90ba 100644
--- a/drivers/staging/android/ion/ion_cma_heap.c
+++ b/drivers/staging/android/ion/ion_cma_heap.c
@@ -49,8 +49,6 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer,
struct device *dev = cma_heap->dev;
struct ion_cma_buffer_info *info;
- dev_dbg(dev, "Request buffer allocation len %ld\n", len);
-
if (buffer->flags & ION_FLAG_CACHED)
return -EINVAL;
@@ -79,7 +77,6 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer,
/* keep this for memory release */
buffer->priv_virt = info;
buffer->sg_table = info->table;
- dev_dbg(dev, "Allocate buffer %p\n", buffer);
return 0;
free_table:
@@ -97,7 +94,6 @@ static void ion_cma_free(struct ion_buffer *buffer)
struct device *dev = cma_heap->dev;
struct ion_cma_buffer_info *info = buffer->priv_virt;
- dev_dbg(dev, "Release buffer %p\n", buffer);
/* release memory */
dma_free_coherent(dev, buffer->size, info->cpu_addr, info->handle);
/* release sg table */
diff --git a/drivers/staging/android/ion/ion_dummy_driver.c b/drivers/staging/android/ion/ion_dummy_driver.c
index b23f2c7..1991626 100644
--- a/drivers/staging/android/ion/ion_dummy_driver.c
+++ b/drivers/staging/android/ion/ion_dummy_driver.c
@@ -38,11 +38,6 @@ static struct ion_platform_heap dummy_heaps[] = {
.name = "system",
},
{
- .id = ION_HEAP_TYPE_SYSTEM_CONTIG,
- .type = ION_HEAP_TYPE_SYSTEM_CONTIG,
- .name = "system contig",
- },
- {
.id = ION_HEAP_TYPE_CARVEOUT,
.type = ION_HEAP_TYPE_CARVEOUT,
.name = "carveout",
@@ -76,34 +71,30 @@ static int __init ion_dummy_init(void)
return -ENOMEM;
- /* Allocate a dummy carveout heap */
- carveout_ptr = alloc_pages_exact(
- dummy_heaps[ION_HEAP_TYPE_CARVEOUT].size,
- GFP_KERNEL);
- if (carveout_ptr)
- dummy_heaps[ION_HEAP_TYPE_CARVEOUT].base =
- virt_to_phys(carveout_ptr);
- else
- pr_err("ion_dummy: Could not allocate carveout\n");
-
- /* Allocate a dummy chunk heap */
- chunk_ptr = alloc_pages_exact(
- dummy_heaps[ION_HEAP_TYPE_CHUNK].size,
- GFP_KERNEL);
- if (chunk_ptr)
- dummy_heaps[ION_HEAP_TYPE_CHUNK].base = virt_to_phys(chunk_ptr);
- else
- pr_err("ion_dummy: Could not allocate chunk\n");
-
for (i = 0; i < dummy_ion_pdata.nr; i++) {
struct ion_platform_heap *heap_data = &dummy_ion_pdata.heaps[i];
- if (heap_data->type == ION_HEAP_TYPE_CARVEOUT &&
- !heap_data->base)
- continue;
+ if (heap_data->type == ION_HEAP_TYPE_CARVEOUT) {
+ /* Allocate a dummy carveout heap */
+ carveout_ptr = alloc_pages_exact(heap_data->size,
+ GFP_KERNEL);
+ if (!carveout_ptr) {
+ pr_err("ion_dummy: Could not allocate carveout\n");
+ continue;
+ }
+ heap_data->base = virt_to_phys(carveout_ptr);
+ }
- if (heap_data->type == ION_HEAP_TYPE_CHUNK && !heap_data->base)
- continue;
+ if (heap_data->type == ION_HEAP_TYPE_CHUNK) {
+ /* Allocate a dummy chunk heap */
+ chunk_ptr = alloc_pages_exact(heap_data->size,
+ GFP_KERNEL);
+ if (!chunk_ptr) {
+ pr_err("ion_dummy: Could not allocate chunk\n");
+ continue;
+ }
+ heap_data->base = virt_to_phys(chunk_ptr);
+ }
heaps[i] = ion_heap_create(heap_data);
if (IS_ERR_OR_NULL(heaps[i])) {
@@ -114,20 +105,28 @@ static int __init ion_dummy_init(void)
}
return 0;
err:
- for (i = 0; i < dummy_ion_pdata.nr; ++i)
- ion_heap_destroy(heaps[i]);
+ for (i = 0; i < dummy_ion_pdata.nr; ++i) {
+ struct ion_platform_heap *heap_data = &dummy_ion_pdata.heaps[i];
+
+ if (!IS_ERR_OR_NULL(heaps[i]))
+ ion_heap_destroy(heaps[i]);
+
+ if (heap_data->type == ION_HEAP_TYPE_CARVEOUT) {
+ if (carveout_ptr) {
+ free_pages_exact(carveout_ptr,
+ heap_data->size);
+ }
+ carveout_ptr = NULL;
+ }
+ if (heap_data->type == ION_HEAP_TYPE_CHUNK) {
+ if (chunk_ptr) {
+ free_pages_exact(chunk_ptr, heap_data->size);
+ }
+ chunk_ptr = NULL;
+ }
+ }
kfree(heaps);
- if (carveout_ptr) {
- free_pages_exact(carveout_ptr,
- dummy_heaps[ION_HEAP_TYPE_CARVEOUT].size);
- carveout_ptr = NULL;
- }
- if (chunk_ptr) {
- free_pages_exact(chunk_ptr,
- dummy_heaps[ION_HEAP_TYPE_CHUNK].size);
- chunk_ptr = NULL;
- }
return err;
}
device_initcall(ion_dummy_init);
@@ -138,19 +137,26 @@ static void __exit ion_dummy_exit(void)
ion_device_destroy(idev);
- for (i = 0; i < dummy_ion_pdata.nr; i++)
- ion_heap_destroy(heaps[i]);
- kfree(heaps);
+ for (i = 0; i < dummy_ion_pdata.nr; ++i) {
+ struct ion_platform_heap *heap_data = &dummy_ion_pdata.heaps[i];
- if (carveout_ptr) {
- free_pages_exact(carveout_ptr,
- dummy_heaps[ION_HEAP_TYPE_CARVEOUT].size);
- carveout_ptr = NULL;
+ if (!IS_ERR_OR_NULL(heaps[i]))
+ ion_heap_destroy(heaps[i]);
+
+ if (heap_data->type == ION_HEAP_TYPE_CARVEOUT) {
+ if (carveout_ptr) {
+ free_pages_exact(carveout_ptr,
+ heap_data->size);
+ }
+ carveout_ptr = NULL;
+ }
+ if (heap_data->type == ION_HEAP_TYPE_CHUNK) {
+ if (chunk_ptr) {
+ free_pages_exact(chunk_ptr, heap_data->size);
+ }
+ chunk_ptr = NULL;
+ }
}
- if (chunk_ptr) {
- free_pages_exact(chunk_ptr,
- dummy_heaps[ION_HEAP_TYPE_CHUNK].size);
- chunk_ptr = NULL;
- }
+ kfree(heaps);
}
__exitcall(ion_dummy_exit);
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 4fc5de13..64c4837 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -321,8 +321,9 @@ struct ion_heap *ion_heap_create(struct ion_platform_heap *heap_data)
switch (heap_data->type) {
case ION_HEAP_TYPE_SYSTEM_CONTIG:
- heap = ion_system_contig_heap_create(heap_data);
- break;
+ pr_err("%s: Heap type is disabled: %d\n", __func__,
+ heap_data->type);
+ return ERR_PTR(-EINVAL);
case ION_HEAP_TYPE_SYSTEM:
heap = ion_system_heap_create(heap_data);
break;
@@ -361,7 +362,8 @@ void ion_heap_destroy(struct ion_heap *heap)
switch (heap->type) {
case ION_HEAP_TYPE_SYSTEM_CONTIG:
- ion_system_contig_heap_destroy(heap);
+ pr_err("%s: Heap type is disabled: %d\n", __func__,
+ heap->type);
break;
case ION_HEAP_TYPE_SYSTEM:
ion_system_heap_destroy(heap);
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index ec3b665..8894a5f 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -42,6 +42,13 @@
#include <linux/rcupdate.h>
#include <linux/profile.h>
#include <linux/notifier.h>
+#include <linux/circ_buf.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace/lowmemorykiller.h"
static u32 lowmem_debug_level = 1;
static short lowmem_adj[6] = {
@@ -69,6 +76,140 @@ static unsigned long lowmem_deathpending_timeout;
pr_info(x); \
} while (0)
+
+static DECLARE_WAIT_QUEUE_HEAD(event_wait);
+static DEFINE_SPINLOCK(lmk_event_lock);
+static struct circ_buf event_buffer;
+#define MAX_BUFFERED_EVENTS 8
+#define MAX_TASKNAME 128
+
+struct lmk_event {
+ char taskname[MAX_TASKNAME];
+ pid_t pid;
+ uid_t uid;
+ pid_t group_leader_pid;
+ unsigned long min_flt;
+ unsigned long maj_flt;
+ unsigned long rss_in_pages;
+ short oom_score_adj;
+ short min_score_adj;
+ unsigned long long start_time;
+ struct list_head list;
+};
+
+void handle_lmk_event(struct task_struct *selected, int selected_tasksize,
+ short min_score_adj)
+{
+ int head;
+ int tail;
+ struct lmk_event *events;
+ struct lmk_event *event;
+
+ spin_lock(&lmk_event_lock);
+
+ head = event_buffer.head;
+ tail = READ_ONCE(event_buffer.tail);
+
+ /* Do not continue to log if no space remains in the buffer. */
+ if (CIRC_SPACE(head, tail, MAX_BUFFERED_EVENTS) < 1) {
+ spin_unlock(&lmk_event_lock);
+ return;
+ }
+
+ events = (struct lmk_event *) event_buffer.buf;
+ event = &events[head];
+
+ strncpy(event->taskname, selected->comm, MAX_TASKNAME);
+
+ event->pid = selected->pid;
+ event->uid = from_kuid_munged(current_user_ns(), task_uid(selected));
+ if (selected->group_leader)
+ event->group_leader_pid = selected->group_leader->pid;
+ else
+ event->group_leader_pid = -1;
+ event->min_flt = selected->min_flt;
+ event->maj_flt = selected->maj_flt;
+ event->oom_score_adj = selected->signal->oom_score_adj;
+ event->start_time = nsec_to_clock_t(selected->real_start_time);
+ event->rss_in_pages = selected_tasksize;
+ event->min_score_adj = min_score_adj;
+
+ event_buffer.head = (head + 1) & (MAX_BUFFERED_EVENTS - 1);
+
+ spin_unlock(&lmk_event_lock);
+
+ wake_up_interruptible(&event_wait);
+}
+
+static int lmk_event_show(struct seq_file *s, void *unused)
+{
+ struct lmk_event *events = (struct lmk_event *) event_buffer.buf;
+ int head;
+ int tail;
+ struct lmk_event *event;
+
+ spin_lock(&lmk_event_lock);
+
+ head = event_buffer.head;
+ tail = event_buffer.tail;
+
+ if (head == tail) {
+ spin_unlock(&lmk_event_lock);
+ return -EAGAIN;
+ }
+
+ event = &events[tail];
+
+ seq_printf(s, "%lu %lu %lu %lu %lu %lu %hd %hd %llu\n%s\n",
+ (unsigned long) event->pid, (unsigned long) event->uid,
+ (unsigned long) event->group_leader_pid, event->min_flt,
+ event->maj_flt, event->rss_in_pages, event->oom_score_adj,
+ event->min_score_adj, event->start_time, event->taskname);
+
+ event_buffer.tail = (tail + 1) & (MAX_BUFFERED_EVENTS - 1);
+
+ spin_unlock(&lmk_event_lock);
+ return 0;
+}
+
+static unsigned int lmk_event_poll(struct file *file, poll_table *wait)
+{
+ int ret = 0;
+
+ poll_wait(file, &event_wait, wait);
+ spin_lock(&lmk_event_lock);
+ if (event_buffer.head != event_buffer.tail)
+ ret = POLLIN;
+ spin_unlock(&lmk_event_lock);
+ return ret;
+}
+
+static int lmk_event_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, lmk_event_show, inode->i_private);
+}
+
+static const struct file_operations event_file_ops = {
+ .open = lmk_event_open,
+ .poll = lmk_event_poll,
+ .read = seq_read
+};
+
+static void lmk_event_init(void)
+{
+ struct proc_dir_entry *entry;
+
+ event_buffer.head = 0;
+ event_buffer.tail = 0;
+ event_buffer.buf = kmalloc(
+ sizeof(struct lmk_event) * MAX_BUFFERED_EVENTS, GFP_KERNEL);
+ if (!event_buffer.buf)
+ return;
+ entry = proc_create("lowmemorykiller", 0, NULL, &event_file_ops);
+ if (!entry)
+ pr_err("error creating kernel lmk event file\n");
+}
+
static unsigned long lowmem_count(struct shrinker *s,
struct shrink_control *sc)
{
@@ -93,6 +234,7 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
int other_file = global_node_page_state(NR_FILE_PAGES) -
global_node_page_state(NR_SHMEM) -
+ global_node_page_state(NR_UNEVICTABLE) -
total_swapcache_pages();
if (lowmem_adj_size < array_size)
@@ -160,30 +302,40 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
p->comm, p->pid, oom_score_adj, tasksize);
}
if (selected) {
+ long cache_size = other_file * (long)(PAGE_SIZE / 1024);
+ long cache_limit = minfree * (long)(PAGE_SIZE / 1024);
+ long free = other_free * (long)(PAGE_SIZE / 1024);
+
task_lock(selected);
send_sig(SIGKILL, selected, 0);
if (selected->mm)
task_set_lmk_waiting(selected);
task_unlock(selected);
- lowmem_print(1, "Killing '%s' (%d), adj %hd,\n"
+ trace_lowmemory_kill(selected, cache_size, cache_limit, free);
+ lowmem_print(1, "Killing '%s' (%d) (tgid %d), adj %hd,\n"
" to free %ldkB on behalf of '%s' (%d) because\n"
" cache %ldkB is below limit %ldkB for oom_score_adj %hd\n"
" Free memory is %ldkB above reserved\n",
- selected->comm, selected->pid,
+ selected->comm, selected->pid, selected->tgid,
selected_oom_score_adj,
selected_tasksize * (long)(PAGE_SIZE / 1024),
current->comm, current->pid,
- other_file * (long)(PAGE_SIZE / 1024),
- minfree * (long)(PAGE_SIZE / 1024),
+ cache_size, cache_limit,
min_score_adj,
- other_free * (long)(PAGE_SIZE / 1024));
+ free);
lowmem_deathpending_timeout = jiffies + HZ;
rem += selected_tasksize;
+ get_task_struct(selected);
}
lowmem_print(4, "lowmem_scan %lu, %x, return %lu\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
+
+ if (selected) {
+ handle_lmk_event(selected, selected_tasksize, min_score_adj);
+ put_task_struct(selected);
+ }
return rem;
}
@@ -196,16 +348,101 @@ static struct shrinker lowmem_shrinker = {
static int __init lowmem_init(void)
{
register_shrinker(&lowmem_shrinker);
+ lmk_event_init();
return 0;
}
device_initcall(lowmem_init);
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+static short lowmem_oom_adj_to_oom_score_adj(short oom_adj)
+{
+ if (oom_adj == OOM_ADJUST_MAX)
+ return OOM_SCORE_ADJ_MAX;
+ else
+ return (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+}
+
+static void lowmem_autodetect_oom_adj_values(void)
+{
+ int i;
+ short oom_adj;
+ short oom_score_adj;
+ int array_size = ARRAY_SIZE(lowmem_adj);
+
+ if (lowmem_adj_size < array_size)
+ array_size = lowmem_adj_size;
+
+ if (array_size <= 0)
+ return;
+
+ oom_adj = lowmem_adj[array_size - 1];
+ if (oom_adj > OOM_ADJUST_MAX)
+ return;
+
+ oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+ if (oom_score_adj <= OOM_ADJUST_MAX)
+ return;
+
+ lowmem_print(1, "lowmem_shrink: convert oom_adj to oom_score_adj:\n");
+ for (i = 0; i < array_size; i++) {
+ oom_adj = lowmem_adj[i];
+ oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+ lowmem_adj[i] = oom_score_adj;
+ lowmem_print(1, "oom_adj %d => oom_score_adj %d\n",
+ oom_adj, oom_score_adj);
+ }
+}
+
+static int lowmem_adj_array_set(const char *val, const struct kernel_param *kp)
+{
+ int ret;
+
+ ret = param_array_ops.set(val, kp);
+
+ /* HACK: Autodetect oom_adj values in lowmem_adj array */
+ lowmem_autodetect_oom_adj_values();
+
+ return ret;
+}
+
+static int lowmem_adj_array_get(char *buffer, const struct kernel_param *kp)
+{
+ return param_array_ops.get(buffer, kp);
+}
+
+static void lowmem_adj_array_free(void *arg)
+{
+ param_array_ops.free(arg);
+}
+
+static struct kernel_param_ops lowmem_adj_array_ops = {
+ .set = lowmem_adj_array_set,
+ .get = lowmem_adj_array_get,
+ .free = lowmem_adj_array_free,
+};
+
+static const struct kparam_array __param_arr_adj = {
+ .max = ARRAY_SIZE(lowmem_adj),
+ .num = &lowmem_adj_size,
+ .ops = ¶m_ops_short,
+ .elemsize = sizeof(lowmem_adj[0]),
+ .elem = lowmem_adj,
+};
+#endif
+
/*
* not really modular, but the easiest way to keep compat with existing
* bootargs behaviour is to continue using module_param here.
*/
module_param_named(cost, lowmem_shrinker.seeks, int, 0644);
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+module_param_cb(adj, &lowmem_adj_array_ops,
+ .arr = &__param_arr_adj,
+ 0644);
+__MODULE_PARM_TYPE(adj, "array of short");
+#else
module_param_array_named(adj, lowmem_adj, short, &lowmem_adj_size, 0644);
+#endif
module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
0644);
module_param_named(debug_level, lowmem_debug_level, uint, 0644);
diff --git a/drivers/staging/android/trace/lowmemorykiller.h b/drivers/staging/android/trace/lowmemorykiller.h
new file mode 100644
index 0000000..f43d3fa
--- /dev/null
+++ b/drivers/staging/android/trace/lowmemorykiller.h
@@ -0,0 +1,41 @@
+#undef TRACE_SYSTEM
+#define TRACE_INCLUDE_PATH ../../drivers/staging/android/trace
+#define TRACE_SYSTEM lowmemorykiller
+
+#if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOWMEMORYKILLER_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(lowmemory_kill,
+ TP_PROTO(struct task_struct *killed_task, long cache_size, \
+ long cache_limit, long free),
+
+ TP_ARGS(killed_task, cache_size, cache_limit, free),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(long, pagecache_size)
+ __field(long, pagecache_limit)
+ __field(long, free)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, killed_task->comm, TASK_COMM_LEN);
+ __entry->pid = killed_task->pid;
+ __entry->pagecache_size = cache_size;
+ __entry->pagecache_limit = cache_limit;
+ __entry->free = free;
+ ),
+
+ TP_printk("%s (%d), page cache %ldkB (limit %ldkB), free %ldKb",
+ __entry->comm, __entry->pid, __entry->pagecache_size,
+ __entry->pagecache_limit, __entry->free)
+);
+
+
+#endif /* if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ) */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/drivers/staging/android/uapi/vsoc_shm.h b/drivers/staging/android/uapi/vsoc_shm.h
new file mode 100644
index 0000000..741b138
--- /dev/null
+++ b/drivers/staging/android/uapi/vsoc_shm.h
@@ -0,0 +1,303 @@
+/*
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_VSOC_SHM_H
+#define _UAPI_LINUX_VSOC_SHM_H
+
+#include <linux/types.h>
+
+/**
+ * A permission is a token that permits a receiver to read and/or write an area
+ * of memory within a Vsoc region.
+ *
+ * An fd_scoped permission grants both read and write access, and can be
+ * attached to a file description (see open(2)).
+ * Ownership of the area can then be shared by passing a file descriptor
+ * among processes.
+ *
+ * begin_offset and end_offset define the area of memory that is controlled by
+ * the permission. owner_offset points to a word, also in shared memory, that
+ * controls ownership of the area.
+ *
+ * ownership of the region expires when the associated file description is
+ * released.
+ *
+ * At most one permission can be attached to each file description.
+ *
+ * This is useful when implementing HALs like gralloc that scope and pass
+ * ownership of shared resources via file descriptors.
+ *
+ * The caller is responsibe for doing any fencing.
+ *
+ * The calling process will normally identify a currently free area of
+ * memory. It will construct a proposed fd_scoped_permission_arg structure:
+ *
+ * begin_offset and end_offset describe the area being claimed
+ *
+ * owner_offset points to the location in shared memory that indicates the
+ * owner of the area.
+ *
+ * owned_value is the value that will be stored in owner_offset iff the
+ * permission can be granted. It must be different than VSOC_REGION_FREE.
+ *
+ * Two fd_scoped_permission structures are compatible if they vary only by
+ * their owned_value fields.
+ *
+ * The driver ensures that, for any group of simultaneous callers proposing
+ * compatible fd_scoped_permissions, it will accept exactly one of the
+ * propopsals. The other callers will get a failure with errno of EAGAIN.
+ *
+ * A process receiving a file descriptor can identify the region being
+ * granted using the VSOC_GET_FD_SCOPED_PERMISSION ioctl.
+ */
+struct fd_scoped_permission {
+ __u32 begin_offset;
+ __u32 end_offset;
+ __u32 owner_offset;
+ __u32 owned_value;
+};
+
+/*
+ * This value represents a free area of memory. The driver expects to see this
+ * value at owner_offset when creating a permission otherwise it will not do it,
+ * and will write this value back once the permission is no longer needed.
+ */
+#define VSOC_REGION_FREE ((__u32)0)
+
+/**
+ * ioctl argument for VSOC_CREATE_FD_SCOPE_PERMISSION
+ */
+struct fd_scoped_permission_arg {
+ struct fd_scoped_permission perm;
+ __s32 managed_region_fd;
+};
+
+#define VSOC_NODE_FREE ((__u32)0)
+
+/*
+ * Describes a signal table in shared memory. Each non-zero entry in the
+ * table indicates that the receiver should signal the futex at the given
+ * offset. Offsets are relative to the region, not the shared memory window.
+ *
+ * interrupt_signalled_offset is used to reliably signal interrupts across the
+ * vmm boundary. There are two roles: transmitter and receiver. For example,
+ * in the host_to_guest_signal_table the host is the transmitter and the
+ * guest is the receiver. The protocol is as follows:
+ *
+ * 1. The transmitter should convert the offset of the futex to an offset
+ * in the signal table [0, (1 << num_nodes_lg2))
+ * The transmitter can choose any appropriate hashing algorithm, including
+ * hash = futex_offset & ((1 << num_nodes_lg2) - 1)
+ *
+ * 3. The transmitter should atomically compare and swap futex_offset with 0
+ * at hash. There are 3 possible outcomes
+ * a. The swap fails because the futex_offset is already in the table.
+ * The transmitter should stop.
+ * b. Some other offset is in the table. This is a hash collision. The
+ * transmitter should move to another table slot and try again. One
+ * possible algorithm:
+ * hash = (hash + 1) & ((1 << num_nodes_lg2) - 1)
+ * c. The swap worked. Continue below.
+ *
+ * 3. The transmitter atomically swaps 1 with the value at the
+ * interrupt_signalled_offset. There are two outcomes:
+ * a. The prior value was 1. In this case an interrupt has already been
+ * posted. The transmitter is done.
+ * b. The prior value was 0, indicating that the receiver may be sleeping.
+ * The transmitter will issue an interrupt.
+ *
+ * 4. On waking the receiver immediately exchanges a 0 with the
+ * interrupt_signalled_offset. If it receives a 0 then this a spurious
+ * interrupt. That may occasionally happen in the current protocol, but
+ * should be rare.
+ *
+ * 5. The receiver scans the signal table by atomicaly exchanging 0 at each
+ * location. If a non-zero offset is returned from the exchange the
+ * receiver wakes all sleepers at the given offset:
+ * futex((int*)(region_base + old_value), FUTEX_WAKE, MAX_INT);
+ *
+ * 6. The receiver thread then does a conditional wait, waking immediately
+ * if the value at interrupt_signalled_offset is non-zero. This catches cases
+ * here additional signals were posted while the table was being scanned.
+ * On the guest the wait is handled via the VSOC_WAIT_FOR_INCOMING_INTERRUPT
+ * ioctl.
+ */
+struct vsoc_signal_table_layout {
+ /* log_2(Number of signal table entries) */
+ __u32 num_nodes_lg2;
+ /*
+ * Offset to the first signal table entry relative to the start of the
+ * region
+ */
+ __u32 futex_uaddr_table_offset;
+ /*
+ * Offset to an atomic_t / atomic uint32_t. A non-zero value indicates
+ * that one or more offsets are currently posted in the table.
+ * semi-unique access to an entry in the table
+ */
+ __u32 interrupt_signalled_offset;
+};
+
+#define VSOC_REGION_WHOLE ((__s32)0)
+#define VSOC_DEVICE_NAME_SZ 16
+
+/**
+ * Each HAL would (usually) talk to a single device region
+ * Mulitple entities care about these regions:
+ * - The ivshmem_server will populate the regions in shared memory
+ * - The guest kernel will read the region, create minor device nodes, and
+ * allow interested parties to register for FUTEX_WAKE events in the region
+ * - HALs will access via the minor device nodes published by the guest kernel
+ * - Host side processes will access the region via the ivshmem_server:
+ * 1. Pass name to ivshmem_server at a UNIX socket
+ * 2. ivshmemserver will reply with 2 fds:
+ * - host->guest doorbell fd
+ * - guest->host doorbell fd
+ * - fd for the shared memory region
+ * - region offset
+ * 3. Start a futex receiver thread on the doorbell fd pointed at the
+ * signal_nodes
+ */
+struct vsoc_device_region {
+ __u16 current_version;
+ __u16 min_compatible_version;
+ __u32 region_begin_offset;
+ __u32 region_end_offset;
+ __u32 offset_of_region_data;
+ struct vsoc_signal_table_layout guest_to_host_signal_table;
+ struct vsoc_signal_table_layout host_to_guest_signal_table;
+ /* Name of the device. Must always be terminated with a '\0', so
+ * the longest supported device name is 15 characters.
+ */
+ char device_name[VSOC_DEVICE_NAME_SZ];
+ /* There are two ways that permissions to access regions are handled:
+ * - When subdivided_by is VSOC_REGION_WHOLE, any process that can
+ * open the device node for the region gains complete access to it.
+ * - When subdivided is set processes that open the region cannot
+ * access it. Access to a sub-region must be established by invoking
+ * the VSOC_CREATE_FD_SCOPE_PERMISSION ioctl on the region
+ * referenced in subdivided_by, providing a fileinstance
+ * (represented by a fd) opened on this region.
+ */
+ __u32 managed_by;
+};
+
+/*
+ * The vsoc layout descriptor.
+ * The first 4K should be reserved for the shm header and region descriptors.
+ * The regions should be page aligned.
+ */
+
+struct vsoc_shm_layout_descriptor {
+ __u16 major_version;
+ __u16 minor_version;
+
+ /* size of the shm. This may be redundant but nice to have */
+ __u32 size;
+
+ /* number of shared memory regions */
+ __u32 region_count;
+
+ /* The offset to the start of region descriptors */
+ __u32 vsoc_region_desc_offset;
+};
+
+/*
+ * This specifies the current version that should be stored in
+ * vsoc_shm_layout_descriptor.major_version and
+ * vsoc_shm_layout_descriptor.minor_version.
+ * It should be updated only if the vsoc_device_region and
+ * vsoc_shm_layout_descriptor structures have changed.
+ * Versioning within each region is transferred
+ * via the min_compatible_version and current_version fields in
+ * vsoc_device_region. The driver does not consult these fields: they are left
+ * for the HALs and host processes and will change independently of the layout
+ * version.
+ */
+#define CURRENT_VSOC_LAYOUT_MAJOR_VERSION 2
+#define CURRENT_VSOC_LAYOUT_MINOR_VERSION 0
+
+#define VSOC_CREATE_FD_SCOPED_PERMISSION \
+ _IOW(0xF5, 0, struct fd_scoped_permission)
+#define VSOC_GET_FD_SCOPED_PERMISSION _IOR(0xF5, 1, struct fd_scoped_permission)
+
+/*
+ * This is used to signal the host to scan the guest_to_host_signal_table
+ * for new futexes to wake. This sends an interrupt if one is not already
+ * in flight.
+ */
+#define VSOC_MAYBE_SEND_INTERRUPT_TO_HOST _IO(0xF5, 2)
+
+/*
+ * When this returns the guest will scan host_to_guest_signal_table to
+ * check for new futexes to wake.
+ */
+/* TODO(ghartman): Consider moving this to the bottom half */
+#define VSOC_WAIT_FOR_INCOMING_INTERRUPT _IO(0xF5, 3)
+
+/*
+ * Guest HALs will use this to retrieve the region description after
+ * opening their device node.
+ */
+#define VSOC_DESCRIBE_REGION _IOR(0xF5, 4, struct vsoc_device_region)
+
+/*
+ * Wake any threads that may be waiting for a host interrupt on this region.
+ * This is mostly used during shutdown.
+ */
+#define VSOC_SELF_INTERRUPT _IO(0xF5, 5)
+
+/*
+ * This is used to signal the host to scan the guest_to_host_signal_table
+ * for new futexes to wake. This sends an interrupt unconditionally.
+ */
+#define VSOC_SEND_INTERRUPT_TO_HOST _IO(0xF5, 6)
+
+enum wait_types {
+ VSOC_WAIT_UNDEFINED = 0,
+ VSOC_WAIT_IF_EQUAL = 1,
+ VSOC_WAIT_IF_EQUAL_TIMEOUT = 2
+};
+
+/*
+ * Wait for a condition to be true
+ *
+ * Note, this is sized and aligned so the 32 bit and 64 bit layouts are
+ * identical.
+ */
+struct vsoc_cond_wait {
+ /* Input: Offset of the 32 bit word to check */
+ __u32 offset;
+ /* Input: Value that will be compared with the offset */
+ __u32 value;
+ /* Monotonic time to wake at in seconds */
+ __u64 wake_time_sec;
+ /* Input: Monotonic time to wait in nanoseconds */
+ __u32 wake_time_nsec;
+ /* Input: Type of wait */
+ __u32 wait_type;
+ /* Output: Number of times the thread woke before returning. */
+ __u32 wakes;
+ /* Ensure that we're 8-byte aligned and 8 byte length for 32/64 bit
+ * compatibility.
+ */
+ __u32 reserved_1;
+};
+
+#define VSOC_COND_WAIT _IOWR(0xF5, 7, struct vsoc_cond_wait)
+
+/* Wake any local threads waiting at the offset given in arg */
+#define VSOC_COND_WAKE _IO(0xF5, 8)
+
+#endif /* _UAPI_LINUX_VSOC_SHM_H */
diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c
new file mode 100644
index 0000000..a9aa89c
--- /dev/null
+++ b/drivers/staging/android/vsoc.c
@@ -0,0 +1,1166 @@
+/*
+ * drivers/android/staging/vsoc.c
+ *
+ * Android Virtual System on a Chip (VSoC) driver
+ *
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * Author: ghartman@google.com
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ *
+ * Based on drivers/char/kvm_ivshmem.c - driver for KVM Inter-VM shared memory
+ * Copyright 2009 Cam Macdonell <cam@cs.ualberta.ca>
+ *
+ * Based on cirrusfb.c and 8139cp.c:
+ * Copyright 1999-2001 Jeff Garzik
+ * Copyright 2001-2004 Jeff Garzik
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/freezer.h>
+#include <linux/futex.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
+#include <linux/cdev.h>
+#include <linux/file.h>
+#include "uapi/vsoc_shm.h"
+
+#define VSOC_DEV_NAME "vsoc"
+
+/*
+ * Description of the ivshmem-doorbell PCI device used by QEmu. These
+ * constants follow docs/specs/ivshmem-spec.txt, which can be found in
+ * the QEmu repository. This was last reconciled with the version that
+ * came out with 2.8
+ */
+
+/*
+ * These constants are determined KVM Inter-VM shared memory device
+ * register offsets
+ */
+enum {
+ INTR_MASK = 0x00, /* Interrupt Mask */
+ INTR_STATUS = 0x04, /* Interrupt Status */
+ IV_POSITION = 0x08, /* VM ID */
+ DOORBELL = 0x0c, /* Doorbell */
+};
+
+static const int REGISTER_BAR; /* Equal to 0 */
+static const int MAX_REGISTER_BAR_LEN = 0x100;
+/*
+ * The MSI-x BAR is not used directly.
+ *
+ * static const int MSI_X_BAR = 1;
+ */
+static const int SHARED_MEMORY_BAR = 2;
+
+struct vsoc_region_data {
+ char name[VSOC_DEVICE_NAME_SZ + 1];
+ wait_queue_head_t interrupt_wait_queue;
+ /* TODO(b/73664181): Use multiple futex wait queues */
+ wait_queue_head_t futex_wait_queue;
+ /* Flag indicating that an interrupt has been signalled by the host. */
+ atomic_t *incoming_signalled;
+ /* Flag indicating the guest has signalled the host. */
+ atomic_t *outgoing_signalled;
+ bool irq_requested;
+ bool device_created;
+};
+
+struct vsoc_device {
+ /* Kernel virtual address of REGISTER_BAR. */
+ void __iomem *regs;
+ /* Physical address of SHARED_MEMORY_BAR. */
+ phys_addr_t shm_phys_start;
+ /* Kernel virtual address of SHARED_MEMORY_BAR. */
+ void __iomem *kernel_mapped_shm;
+ /* Size of the entire shared memory window in bytes. */
+ size_t shm_size;
+ /*
+ * Pointer to the virtual address of the shared memory layout structure.
+ * This is probably identical to kernel_mapped_shm, but saving this
+ * here saves a lot of annoying casts.
+ */
+ struct vsoc_shm_layout_descriptor *layout;
+ /*
+ * Points to a table of region descriptors in the kernel's virtual
+ * address space. Calculated from
+ * vsoc_shm_layout_descriptor.vsoc_region_desc_offset
+ */
+ struct vsoc_device_region *regions;
+ /* Head of a list of permissions that have been granted. */
+ struct list_head permissions;
+ struct pci_dev *dev;
+ /* Per-region (and therefore per-interrupt) information. */
+ struct vsoc_region_data *regions_data;
+ /*
+ * Table of msi-x entries. This has to be separated from struct
+ * vsoc_region_data because the kernel deals with them as an array.
+ */
+ struct msix_entry *msix_entries;
+ /* Mutex that protectes the permission list */
+ struct mutex mtx;
+ /* Major number assigned by the kernel */
+ int major;
+ /* Character device assigned by the kernel */
+ struct cdev cdev;
+ /* Device class assigned by the kernel */
+ struct class *class;
+ /*
+ * Flags that indicate what we've initialized. These are used to do an
+ * orderly cleanup of the device.
+ */
+ bool enabled_device;
+ bool requested_regions;
+ bool cdev_added;
+ bool class_added;
+ bool msix_enabled;
+};
+
+static struct vsoc_device vsoc_dev;
+
+/*
+ * TODO(ghartman): Add a /sys filesystem entry that summarizes the permissions.
+ */
+
+struct fd_scoped_permission_node {
+ struct fd_scoped_permission permission;
+ struct list_head list;
+};
+
+struct vsoc_private_data {
+ struct fd_scoped_permission_node *fd_scoped_permission_node;
+};
+
+static long vsoc_ioctl(struct file *, unsigned int, unsigned long);
+static int vsoc_mmap(struct file *, struct vm_area_struct *);
+static int vsoc_open(struct inode *, struct file *);
+static int vsoc_release(struct inode *, struct file *);
+static ssize_t vsoc_read(struct file *, char __user *, size_t, loff_t *);
+static ssize_t vsoc_write(struct file *, const char __user *, size_t, loff_t *);
+static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin);
+static int do_create_fd_scoped_permission(
+ struct vsoc_device_region *region_p,
+ struct fd_scoped_permission_node *np,
+ struct fd_scoped_permission_arg __user *arg);
+static void do_destroy_fd_scoped_permission(
+ struct vsoc_device_region *owner_region_p,
+ struct fd_scoped_permission *perm);
+static long do_vsoc_describe_region(struct file *,
+ struct vsoc_device_region __user *);
+static ssize_t vsoc_get_area(struct file *filp, __u32 *perm_off);
+
+/**
+ * Validate arguments on entry points to the driver.
+ */
+inline int vsoc_validate_inode(struct inode *inode)
+{
+ if (iminor(inode) >= vsoc_dev.layout->region_count) {
+ dev_err(&vsoc_dev.dev->dev,
+ "describe_region: invalid region %d\n", iminor(inode));
+ return -ENODEV;
+ }
+ return 0;
+}
+
+inline int vsoc_validate_filep(struct file *filp)
+{
+ int ret = vsoc_validate_inode(file_inode(filp));
+
+ if (ret)
+ return ret;
+ if (!filp->private_data) {
+ dev_err(&vsoc_dev.dev->dev,
+ "No private data on fd, region %d\n",
+ iminor(file_inode(filp)));
+ return -EBADFD;
+ }
+ return 0;
+}
+
+/* Converts from shared memory offset to virtual address */
+static inline void *shm_off_to_virtual_addr(__u32 offset)
+{
+ return (void __force *)vsoc_dev.kernel_mapped_shm + offset;
+}
+
+/* Converts from shared memory offset to physical address */
+static inline phys_addr_t shm_off_to_phys_addr(__u32 offset)
+{
+ return vsoc_dev.shm_phys_start + offset;
+}
+
+/**
+ * Convenience functions to obtain the region from the inode or file.
+ * Dangerous to call before validating the inode/file.
+ */
+static inline struct vsoc_device_region *vsoc_region_from_inode(
+ struct inode *inode)
+{
+ return &vsoc_dev.regions[iminor(inode)];
+}
+
+static inline struct vsoc_device_region *vsoc_region_from_filep(
+ struct file *inode)
+{
+ return vsoc_region_from_inode(file_inode(inode));
+}
+
+static inline uint32_t vsoc_device_region_size(struct vsoc_device_region *r)
+{
+ return r->region_end_offset - r->region_begin_offset;
+}
+
+static const struct file_operations vsoc_ops = {
+ .owner = THIS_MODULE,
+ .open = vsoc_open,
+ .mmap = vsoc_mmap,
+ .read = vsoc_read,
+ .unlocked_ioctl = vsoc_ioctl,
+ .compat_ioctl = vsoc_ioctl,
+ .write = vsoc_write,
+ .llseek = vsoc_lseek,
+ .release = vsoc_release,
+};
+
+static struct pci_device_id vsoc_id_table[] = {
+ {0x1af4, 0x1110, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
+ {0},
+};
+
+MODULE_DEVICE_TABLE(pci, vsoc_id_table);
+
+static void vsoc_remove_device(struct pci_dev *pdev);
+static int vsoc_probe_device(struct pci_dev *pdev,
+ const struct pci_device_id *ent);
+
+static struct pci_driver vsoc_pci_driver = {
+ .name = "vsoc",
+ .id_table = vsoc_id_table,
+ .probe = vsoc_probe_device,
+ .remove = vsoc_remove_device,
+};
+
+static int do_create_fd_scoped_permission(
+ struct vsoc_device_region *region_p,
+ struct fd_scoped_permission_node *np,
+ struct fd_scoped_permission_arg __user *arg)
+{
+ struct file *managed_filp;
+ s32 managed_fd;
+ atomic_t *owner_ptr = NULL;
+ struct vsoc_device_region *managed_region_p;
+
+ if (copy_from_user(&np->permission,
+ &arg->perm, sizeof(np->permission)) ||
+ copy_from_user(&managed_fd,
+ &arg->managed_region_fd, sizeof(managed_fd))) {
+ return -EFAULT;
+ }
+ managed_filp = fdget(managed_fd).file;
+ /* Check that it's a valid fd, */
+ if (!managed_filp || vsoc_validate_filep(managed_filp))
+ return -EPERM;
+ /* EEXIST if the given fd already has a permission. */
+ if (((struct vsoc_private_data *)managed_filp->private_data)->
+ fd_scoped_permission_node)
+ return -EEXIST;
+ managed_region_p = vsoc_region_from_filep(managed_filp);
+ /* Check that the provided region is managed by this one */
+ if (&vsoc_dev.regions[managed_region_p->managed_by] != region_p)
+ return -EPERM;
+ /* The area must be well formed and have non-zero size */
+ if (np->permission.begin_offset >= np->permission.end_offset)
+ return -EINVAL;
+ /* The area must fit in the memory window */
+ if (np->permission.end_offset >
+ vsoc_device_region_size(managed_region_p))
+ return -ERANGE;
+ /* The area must be in the region data section */
+ if (np->permission.begin_offset <
+ managed_region_p->offset_of_region_data)
+ return -ERANGE;
+ /* The area must be page aligned */
+ if (!PAGE_ALIGNED(np->permission.begin_offset) ||
+ !PAGE_ALIGNED(np->permission.end_offset))
+ return -EINVAL;
+ /* Owner offset must be naturally aligned in the window */
+ if (np->permission.owner_offset &
+ (sizeof(np->permission.owner_offset) - 1))
+ return -EINVAL;
+ /* The owner flag must reside in the owner memory */
+ if (np->permission.owner_offset + sizeof(np->permission.owner_offset) >
+ vsoc_device_region_size(region_p))
+ return -ERANGE;
+ /* The owner flag must reside in the data section */
+ if (np->permission.owner_offset < region_p->offset_of_region_data)
+ return -EINVAL;
+ /* The owner value must change to claim the memory */
+ if (np->permission.owned_value == VSOC_REGION_FREE)
+ return -EINVAL;
+ owner_ptr =
+ (atomic_t *)shm_off_to_virtual_addr(region_p->region_begin_offset +
+ np->permission.owner_offset);
+ /* We've already verified that this is in the shared memory window, so
+ * it should be safe to write to this address.
+ */
+ if (atomic_cmpxchg(owner_ptr,
+ VSOC_REGION_FREE,
+ np->permission.owned_value) != VSOC_REGION_FREE) {
+ return -EBUSY;
+ }
+ ((struct vsoc_private_data *)managed_filp->private_data)->
+ fd_scoped_permission_node = np;
+ /* The file offset needs to be adjusted if the calling
+ * process did any read/write operations on the fd
+ * before creating the permission.
+ */
+ if (managed_filp->f_pos) {
+ if (managed_filp->f_pos > np->permission.end_offset) {
+ /* If the offset is beyond the permission end, set it
+ * to the end.
+ */
+ managed_filp->f_pos = np->permission.end_offset;
+ } else {
+ /* If the offset is within the permission interval
+ * keep it there otherwise reset it to zero.
+ */
+ if (managed_filp->f_pos < np->permission.begin_offset) {
+ managed_filp->f_pos = 0;
+ } else {
+ managed_filp->f_pos -=
+ np->permission.begin_offset;
+ }
+ }
+ }
+ return 0;
+}
+
+static void do_destroy_fd_scoped_permission_node(
+ struct vsoc_device_region *owner_region_p,
+ struct fd_scoped_permission_node *node)
+{
+ if (node) {
+ do_destroy_fd_scoped_permission(owner_region_p,
+ &node->permission);
+ mutex_lock(&vsoc_dev.mtx);
+ list_del(&node->list);
+ mutex_unlock(&vsoc_dev.mtx);
+ kfree(node);
+ }
+}
+
+static void do_destroy_fd_scoped_permission(
+ struct vsoc_device_region *owner_region_p,
+ struct fd_scoped_permission *perm)
+{
+ atomic_t *owner_ptr = NULL;
+ int prev = 0;
+
+ if (!perm)
+ return;
+ owner_ptr = (atomic_t *)shm_off_to_virtual_addr(
+ owner_region_p->region_begin_offset + perm->owner_offset);
+ prev = atomic_xchg(owner_ptr, VSOC_REGION_FREE);
+ if (prev != perm->owned_value)
+ dev_err(&vsoc_dev.dev->dev,
+ "%x-%x: owner (%s) %x: expected to be %x was %x",
+ perm->begin_offset, perm->end_offset,
+ owner_region_p->device_name, perm->owner_offset,
+ perm->owned_value, prev);
+}
+
+static long do_vsoc_describe_region(struct file *filp,
+ struct vsoc_device_region __user *dest)
+{
+ struct vsoc_device_region *region_p;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ region_p = vsoc_region_from_filep(filp);
+ if (copy_to_user(dest, region_p, sizeof(*region_p)))
+ return -EFAULT;
+ return 0;
+}
+
+/**
+ * Implements the inner logic of cond_wait. Copies to and from userspace are
+ * done in the helper function below.
+ */
+static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg)
+{
+ DEFINE_WAIT(wait);
+ u32 region_number = iminor(file_inode(filp));
+ struct vsoc_region_data *data = vsoc_dev.regions_data + region_number;
+ struct hrtimer_sleeper timeout, *to = NULL;
+ int ret = 0;
+ struct vsoc_device_region *region_p = vsoc_region_from_filep(filp);
+ atomic_t *address = NULL;
+ struct timespec ts;
+
+ /* Ensure that the offset is aligned */
+ if (arg->offset & (sizeof(uint32_t) - 1))
+ return -EADDRNOTAVAIL;
+ /* Ensure that the offset is within shared memory */
+ if (((uint64_t)arg->offset) + region_p->region_begin_offset +
+ sizeof(uint32_t) > region_p->region_end_offset)
+ return -E2BIG;
+ address = shm_off_to_virtual_addr(region_p->region_begin_offset +
+ arg->offset);
+
+ /* Ensure that the type of wait is valid */
+ switch (arg->wait_type) {
+ case VSOC_WAIT_IF_EQUAL:
+ break;
+ case VSOC_WAIT_IF_EQUAL_TIMEOUT:
+ to = &timeout;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (to) {
+ /* Copy the user-supplied timesec into the kernel structure.
+ * We do things this way to flatten differences between 32 bit
+ * and 64 bit timespecs.
+ */
+ ts.tv_sec = arg->wake_time_sec;
+ ts.tv_nsec = arg->wake_time_nsec;
+
+ if (!timespec_valid(&ts))
+ return -EINVAL;
+ hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
+ hrtimer_set_expires_range_ns(&to->timer, timespec_to_ktime(ts),
+ current->timer_slack_ns);
+
+ hrtimer_init_sleeper(to, current);
+ }
+
+ while (1) {
+ prepare_to_wait(&data->futex_wait_queue, &wait,
+ TASK_INTERRUPTIBLE);
+ /*
+ * Check the sentinel value after prepare_to_wait. If the value
+ * changes after this check the writer will call signal,
+ * changing the task state from INTERRUPTIBLE to RUNNING. That
+ * will ensure that schedule() will eventually schedule this
+ * task.
+ */
+ if (atomic_read(address) != arg->value) {
+ ret = 0;
+ break;
+ }
+ if (to) {
+ hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+ if (likely(to->task))
+ freezable_schedule();
+ hrtimer_cancel(&to->timer);
+ if (!to->task) {
+ ret = -ETIMEDOUT;
+ break;
+ }
+ } else {
+ freezable_schedule();
+ }
+ /* Count the number of times that we woke up. This is useful
+ * for unit testing.
+ */
+ ++arg->wakes;
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+ }
+ finish_wait(&data->futex_wait_queue, &wait);
+ if (to)
+ destroy_hrtimer_on_stack(&to->timer);
+ return ret;
+}
+
+/**
+ * Handles the details of copying from/to userspace to ensure that the copies
+ * happen on all of the return paths of cond_wait.
+ */
+static int do_vsoc_cond_wait(struct file *filp,
+ struct vsoc_cond_wait __user *untrusted_in)
+{
+ struct vsoc_cond_wait arg;
+ int rval = 0;
+
+ if (copy_from_user(&arg, untrusted_in, sizeof(arg)))
+ return -EFAULT;
+ /* wakes is an out parameter. Initialize it to something sensible. */
+ arg.wakes = 0;
+ rval = handle_vsoc_cond_wait(filp, &arg);
+ if (copy_to_user(untrusted_in, &arg, sizeof(arg)))
+ return -EFAULT;
+ return rval;
+}
+
+static int do_vsoc_cond_wake(struct file *filp, uint32_t offset)
+{
+ struct vsoc_device_region *region_p = vsoc_region_from_filep(filp);
+ u32 region_number = iminor(file_inode(filp));
+ struct vsoc_region_data *data = vsoc_dev.regions_data + region_number;
+ /* Ensure that the offset is aligned */
+ if (offset & (sizeof(uint32_t) - 1))
+ return -EADDRNOTAVAIL;
+ /* Ensure that the offset is within shared memory */
+ if (((uint64_t)offset) + region_p->region_begin_offset +
+ sizeof(uint32_t) > region_p->region_end_offset)
+ return -E2BIG;
+ /*
+ * TODO(b/73664181): Use multiple futex wait queues.
+ * We need to wake every sleeper when the condition changes. Typically
+ * only a single thread will be waiting on the condition, but there
+ * are exceptions. The worst case is about 10 threads.
+ */
+ wake_up_interruptible_all(&data->futex_wait_queue);
+ return 0;
+}
+
+static long vsoc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ int rv = 0;
+ struct vsoc_device_region *region_p;
+ u32 reg_num;
+ struct vsoc_region_data *reg_data;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ region_p = vsoc_region_from_filep(filp);
+ reg_num = iminor(file_inode(filp));
+ reg_data = vsoc_dev.regions_data + reg_num;
+ switch (cmd) {
+ case VSOC_CREATE_FD_SCOPED_PERMISSION:
+ {
+ struct fd_scoped_permission_node *node = NULL;
+
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
+ /* We can't allocate memory for the permission */
+ if (!node)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&node->list);
+ rv = do_create_fd_scoped_permission(
+ region_p,
+ node,
+ (struct fd_scoped_permission_arg __user *)arg);
+ if (!rv) {
+ mutex_lock(&vsoc_dev.mtx);
+ list_add(&node->list, &vsoc_dev.permissions);
+ mutex_unlock(&vsoc_dev.mtx);
+ } else {
+ kfree(node);
+ return rv;
+ }
+ }
+ break;
+
+ case VSOC_GET_FD_SCOPED_PERMISSION:
+ {
+ struct fd_scoped_permission_node *node =
+ ((struct vsoc_private_data *)filp->private_data)->
+ fd_scoped_permission_node;
+ if (!node)
+ return -ENOENT;
+ if (copy_to_user
+ ((struct fd_scoped_permission __user *)arg,
+ &node->permission, sizeof(node->permission)))
+ return -EFAULT;
+ }
+ break;
+
+ case VSOC_MAYBE_SEND_INTERRUPT_TO_HOST:
+ if (!atomic_xchg(
+ reg_data->outgoing_signalled,
+ 1)) {
+ writel(reg_num, vsoc_dev.regs + DOORBELL);
+ return 0;
+ } else {
+ return -EBUSY;
+ }
+ break;
+
+ case VSOC_SEND_INTERRUPT_TO_HOST:
+ writel(reg_num, vsoc_dev.regs + DOORBELL);
+ return 0;
+
+ case VSOC_WAIT_FOR_INCOMING_INTERRUPT:
+ wait_event_interruptible(
+ reg_data->interrupt_wait_queue,
+ (atomic_read(reg_data->incoming_signalled) != 0));
+ break;
+
+ case VSOC_DESCRIBE_REGION:
+ return do_vsoc_describe_region(
+ filp,
+ (struct vsoc_device_region __user *)arg);
+
+ case VSOC_SELF_INTERRUPT:
+ atomic_set(reg_data->incoming_signalled, 1);
+ wake_up_interruptible(®_data->interrupt_wait_queue);
+ break;
+
+ case VSOC_COND_WAIT:
+ return do_vsoc_cond_wait(filp,
+ (struct vsoc_cond_wait __user *)arg);
+ case VSOC_COND_WAKE:
+ return do_vsoc_cond_wake(filp, arg);
+
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static ssize_t vsoc_read(struct file *filp, char __user *buffer, size_t len,
+ loff_t *poffset)
+{
+ __u32 area_off;
+ const void *area_p;
+ ssize_t area_len;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ area_len = vsoc_get_area(filp, &area_off);
+ area_p = shm_off_to_virtual_addr(area_off);
+ area_p += *poffset;
+ area_len -= *poffset;
+ if (area_len <= 0)
+ return 0;
+ if (area_len < len)
+ len = area_len;
+ if (copy_to_user(buffer, area_p, len))
+ return -EFAULT;
+ *poffset += len;
+ return len;
+}
+
+static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin)
+{
+ ssize_t area_len = 0;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ area_len = vsoc_get_area(filp, NULL);
+ switch (origin) {
+ case SEEK_SET:
+ break;
+
+ case SEEK_CUR:
+ if (offset > 0 && offset + filp->f_pos < 0)
+ return -EOVERFLOW;
+ offset += filp->f_pos;
+ break;
+
+ case SEEK_END:
+ if (offset > 0 && offset + area_len < 0)
+ return -EOVERFLOW;
+ offset += area_len;
+ break;
+
+ case SEEK_DATA:
+ if (offset >= area_len)
+ return -EINVAL;
+ if (offset < 0)
+ offset = 0;
+ break;
+
+ case SEEK_HOLE:
+ /* Next hole is always the end of the region, unless offset is
+ * beyond that
+ */
+ if (offset < area_len)
+ offset = area_len;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (offset < 0 || offset > area_len)
+ return -EINVAL;
+ filp->f_pos = offset;
+
+ return offset;
+}
+
+static ssize_t vsoc_write(struct file *filp, const char __user *buffer,
+ size_t len, loff_t *poffset)
+{
+ __u32 area_off;
+ void *area_p;
+ ssize_t area_len;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ area_len = vsoc_get_area(filp, &area_off);
+ area_p = shm_off_to_virtual_addr(area_off);
+ area_p += *poffset;
+ area_len -= *poffset;
+ if (area_len <= 0)
+ return 0;
+ if (area_len < len)
+ len = area_len;
+ if (copy_from_user(area_p, buffer, len))
+ return -EFAULT;
+ *poffset += len;
+ return len;
+}
+
+static irqreturn_t vsoc_interrupt(int irq, void *region_data_v)
+{
+ struct vsoc_region_data *region_data =
+ (struct vsoc_region_data *)region_data_v;
+ int reg_num = region_data - vsoc_dev.regions_data;
+
+ if (unlikely(!region_data))
+ return IRQ_NONE;
+
+ if (unlikely(reg_num < 0 ||
+ reg_num >= vsoc_dev.layout->region_count)) {
+ dev_err(&vsoc_dev.dev->dev,
+ "invalid irq @%p reg_num=0x%04x\n",
+ region_data, reg_num);
+ return IRQ_NONE;
+ }
+ if (unlikely(vsoc_dev.regions_data + reg_num != region_data)) {
+ dev_err(&vsoc_dev.dev->dev,
+ "irq not aligned @%p reg_num=0x%04x\n",
+ region_data, reg_num);
+ return IRQ_NONE;
+ }
+ wake_up_interruptible(®ion_data->interrupt_wait_queue);
+ return IRQ_HANDLED;
+}
+
+static int vsoc_probe_device(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
+{
+ int result;
+ int i;
+ resource_size_t reg_size;
+ dev_t devt;
+
+ vsoc_dev.dev = pdev;
+ result = pci_enable_device(pdev);
+ if (result) {
+ dev_err(&pdev->dev,
+ "pci_enable_device failed %s: error %d\n",
+ pci_name(pdev), result);
+ return result;
+ }
+ vsoc_dev.enabled_device = true;
+ result = pci_request_regions(pdev, "vsoc");
+ if (result < 0) {
+ dev_err(&pdev->dev, "pci_request_regions failed\n");
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+ vsoc_dev.requested_regions = true;
+ /* Set up the control registers in BAR 0 */
+ reg_size = pci_resource_len(pdev, REGISTER_BAR);
+ if (reg_size > MAX_REGISTER_BAR_LEN)
+ vsoc_dev.regs =
+ pci_iomap(pdev, REGISTER_BAR, MAX_REGISTER_BAR_LEN);
+ else
+ vsoc_dev.regs = pci_iomap(pdev, REGISTER_BAR, reg_size);
+
+ if (!vsoc_dev.regs) {
+ dev_err(&pdev->dev,
+ "cannot map registers of size %zu\n",
+ (size_t)reg_size);
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+
+ /* Map the shared memory in BAR 2 */
+ vsoc_dev.shm_phys_start = pci_resource_start(pdev, SHARED_MEMORY_BAR);
+ vsoc_dev.shm_size = pci_resource_len(pdev, SHARED_MEMORY_BAR);
+
+ dev_info(&pdev->dev, "shared memory @ DMA %pa size=0x%zx\n",
+ &vsoc_dev.shm_phys_start, vsoc_dev.shm_size);
+ vsoc_dev.kernel_mapped_shm = pci_iomap_wc(pdev, SHARED_MEMORY_BAR, 0);
+ if (!vsoc_dev.kernel_mapped_shm) {
+ dev_err(&vsoc_dev.dev->dev, "cannot iomap region\n");
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+
+ vsoc_dev.layout = (struct vsoc_shm_layout_descriptor __force *)
+ vsoc_dev.kernel_mapped_shm;
+ dev_info(&pdev->dev, "major_version: %d\n",
+ vsoc_dev.layout->major_version);
+ dev_info(&pdev->dev, "minor_version: %d\n",
+ vsoc_dev.layout->minor_version);
+ dev_info(&pdev->dev, "size: 0x%x\n", vsoc_dev.layout->size);
+ dev_info(&pdev->dev, "regions: %d\n", vsoc_dev.layout->region_count);
+ if (vsoc_dev.layout->major_version !=
+ CURRENT_VSOC_LAYOUT_MAJOR_VERSION) {
+ dev_err(&vsoc_dev.dev->dev,
+ "driver supports only major_version %d\n",
+ CURRENT_VSOC_LAYOUT_MAJOR_VERSION);
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+ result = alloc_chrdev_region(&devt, 0, vsoc_dev.layout->region_count,
+ VSOC_DEV_NAME);
+ if (result) {
+ dev_err(&vsoc_dev.dev->dev, "alloc_chrdev_region failed\n");
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+ vsoc_dev.major = MAJOR(devt);
+ cdev_init(&vsoc_dev.cdev, &vsoc_ops);
+ vsoc_dev.cdev.owner = THIS_MODULE;
+ result = cdev_add(&vsoc_dev.cdev, devt, vsoc_dev.layout->region_count);
+ if (result) {
+ dev_err(&vsoc_dev.dev->dev, "cdev_add error\n");
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+ vsoc_dev.cdev_added = true;
+ vsoc_dev.class = class_create(THIS_MODULE, VSOC_DEV_NAME);
+ if (IS_ERR(vsoc_dev.class)) {
+ dev_err(&vsoc_dev.dev->dev, "class_create failed\n");
+ vsoc_remove_device(pdev);
+ return PTR_ERR(vsoc_dev.class);
+ }
+ vsoc_dev.class_added = true;
+ vsoc_dev.regions = (struct vsoc_device_region __force *)
+ ((void *)vsoc_dev.layout +
+ vsoc_dev.layout->vsoc_region_desc_offset);
+ vsoc_dev.msix_entries = kcalloc(
+ vsoc_dev.layout->region_count,
+ sizeof(vsoc_dev.msix_entries[0]), GFP_KERNEL);
+ if (!vsoc_dev.msix_entries) {
+ dev_err(&vsoc_dev.dev->dev,
+ "unable to allocate msix_entries\n");
+ vsoc_remove_device(pdev);
+ return -ENOSPC;
+ }
+ vsoc_dev.regions_data = kcalloc(
+ vsoc_dev.layout->region_count,
+ sizeof(vsoc_dev.regions_data[0]), GFP_KERNEL);
+ if (!vsoc_dev.regions_data) {
+ dev_err(&vsoc_dev.dev->dev,
+ "unable to allocate regions' data\n");
+ vsoc_remove_device(pdev);
+ return -ENOSPC;
+ }
+ for (i = 0; i < vsoc_dev.layout->region_count; ++i)
+ vsoc_dev.msix_entries[i].entry = i;
+
+ result = pci_enable_msix_exact(vsoc_dev.dev, vsoc_dev.msix_entries,
+ vsoc_dev.layout->region_count);
+ if (result) {
+ dev_info(&pdev->dev, "pci_enable_msix failed: %d\n", result);
+ vsoc_remove_device(pdev);
+ return -ENOSPC;
+ }
+ /* Check that all regions are well formed */
+ for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
+ const struct vsoc_device_region *region = vsoc_dev.regions + i;
+
+ if (!PAGE_ALIGNED(region->region_begin_offset) ||
+ !PAGE_ALIGNED(region->region_end_offset)) {
+ dev_err(&vsoc_dev.dev->dev,
+ "region %d not aligned (%x:%x)", i,
+ region->region_begin_offset,
+ region->region_end_offset);
+ vsoc_remove_device(pdev);
+ return -EFAULT;
+ }
+ if (region->region_begin_offset >= region->region_end_offset ||
+ region->region_end_offset > vsoc_dev.shm_size) {
+ dev_err(&vsoc_dev.dev->dev,
+ "region %d offsets are wrong: %x %x %zx",
+ i, region->region_begin_offset,
+ region->region_end_offset, vsoc_dev.shm_size);
+ vsoc_remove_device(pdev);
+ return -EFAULT;
+ }
+ if (region->managed_by >= vsoc_dev.layout->region_count) {
+ dev_err(&vsoc_dev.dev->dev,
+ "region %d has invalid owner: %u",
+ i, region->managed_by);
+ vsoc_remove_device(pdev);
+ return -EFAULT;
+ }
+ }
+ vsoc_dev.msix_enabled = true;
+ for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
+ const struct vsoc_device_region *region = vsoc_dev.regions + i;
+ size_t name_sz = sizeof(vsoc_dev.regions_data[i].name) - 1;
+ const struct vsoc_signal_table_layout *h_to_g_signal_table =
+ ®ion->host_to_guest_signal_table;
+ const struct vsoc_signal_table_layout *g_to_h_signal_table =
+ ®ion->guest_to_host_signal_table;
+
+ vsoc_dev.regions_data[i].name[name_sz] = '\0';
+ memcpy(vsoc_dev.regions_data[i].name, region->device_name,
+ name_sz);
+ dev_info(&pdev->dev, "region %d name=%s\n",
+ i, vsoc_dev.regions_data[i].name);
+ init_waitqueue_head(
+ &vsoc_dev.regions_data[i].interrupt_wait_queue);
+ init_waitqueue_head(&vsoc_dev.regions_data[i].futex_wait_queue);
+ vsoc_dev.regions_data[i].incoming_signalled =
+ shm_off_to_virtual_addr(region->region_begin_offset) +
+ h_to_g_signal_table->interrupt_signalled_offset;
+ vsoc_dev.regions_data[i].outgoing_signalled =
+ shm_off_to_virtual_addr(region->region_begin_offset) +
+ g_to_h_signal_table->interrupt_signalled_offset;
+ result = request_irq(
+ vsoc_dev.msix_entries[i].vector,
+ vsoc_interrupt, 0,
+ vsoc_dev.regions_data[i].name,
+ vsoc_dev.regions_data + i);
+ if (result) {
+ dev_info(&pdev->dev,
+ "request_irq failed irq=%d vector=%d\n",
+ i, vsoc_dev.msix_entries[i].vector);
+ vsoc_remove_device(pdev);
+ return -ENOSPC;
+ }
+ vsoc_dev.regions_data[i].irq_requested = true;
+ if (!device_create(vsoc_dev.class, NULL,
+ MKDEV(vsoc_dev.major, i),
+ NULL, vsoc_dev.regions_data[i].name)) {
+ dev_err(&vsoc_dev.dev->dev, "device_create failed\n");
+ vsoc_remove_device(pdev);
+ return -EBUSY;
+ }
+ vsoc_dev.regions_data[i].device_created = true;
+ }
+ return 0;
+}
+
+/*
+ * This should undo all of the allocations in the probe function in reverse
+ * order.
+ *
+ * Notes:
+ *
+ * The device may have been partially initialized, so double check
+ * that the allocations happened.
+ *
+ * This function may be called multiple times, so mark resources as freed
+ * as they are deallocated.
+ */
+static void vsoc_remove_device(struct pci_dev *pdev)
+{
+ int i;
+ /*
+ * pdev is the first thing to be set on probe and the last thing
+ * to be cleared here. If it's NULL then there is no cleanup.
+ */
+ if (!pdev || !vsoc_dev.dev)
+ return;
+ dev_info(&pdev->dev, "remove_device\n");
+ if (vsoc_dev.regions_data) {
+ for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
+ if (vsoc_dev.regions_data[i].device_created) {
+ device_destroy(vsoc_dev.class,
+ MKDEV(vsoc_dev.major, i));
+ vsoc_dev.regions_data[i].device_created = false;
+ }
+ if (vsoc_dev.regions_data[i].irq_requested)
+ free_irq(vsoc_dev.msix_entries[i].vector, NULL);
+ vsoc_dev.regions_data[i].irq_requested = false;
+ }
+ kfree(vsoc_dev.regions_data);
+ vsoc_dev.regions_data = NULL;
+ }
+ if (vsoc_dev.msix_enabled) {
+ pci_disable_msix(pdev);
+ vsoc_dev.msix_enabled = false;
+ }
+ kfree(vsoc_dev.msix_entries);
+ vsoc_dev.msix_entries = NULL;
+ vsoc_dev.regions = NULL;
+ if (vsoc_dev.class_added) {
+ class_destroy(vsoc_dev.class);
+ vsoc_dev.class_added = false;
+ }
+ if (vsoc_dev.cdev_added) {
+ cdev_del(&vsoc_dev.cdev);
+ vsoc_dev.cdev_added = false;
+ }
+ if (vsoc_dev.major && vsoc_dev.layout) {
+ unregister_chrdev_region(MKDEV(vsoc_dev.major, 0),
+ vsoc_dev.layout->region_count);
+ vsoc_dev.major = 0;
+ }
+ vsoc_dev.layout = NULL;
+ if (vsoc_dev.kernel_mapped_shm) {
+ pci_iounmap(pdev, vsoc_dev.kernel_mapped_shm);
+ vsoc_dev.kernel_mapped_shm = NULL;
+ }
+ if (vsoc_dev.regs) {
+ pci_iounmap(pdev, vsoc_dev.regs);
+ vsoc_dev.regs = NULL;
+ }
+ if (vsoc_dev.requested_regions) {
+ pci_release_regions(pdev);
+ vsoc_dev.requested_regions = false;
+ }
+ if (vsoc_dev.enabled_device) {
+ pci_disable_device(pdev);
+ vsoc_dev.enabled_device = false;
+ }
+ /* Do this last: it indicates that the device is not initialized. */
+ vsoc_dev.dev = NULL;
+}
+
+static void __exit vsoc_cleanup_module(void)
+{
+ vsoc_remove_device(vsoc_dev.dev);
+ pci_unregister_driver(&vsoc_pci_driver);
+}
+
+static int __init vsoc_init_module(void)
+{
+ int err = -ENOMEM;
+
+ INIT_LIST_HEAD(&vsoc_dev.permissions);
+ mutex_init(&vsoc_dev.mtx);
+
+ err = pci_register_driver(&vsoc_pci_driver);
+ if (err < 0)
+ return err;
+ return 0;
+}
+
+static int vsoc_open(struct inode *inode, struct file *filp)
+{
+ /* Can't use vsoc_validate_filep because filp is still incomplete */
+ int ret = vsoc_validate_inode(inode);
+
+ if (ret)
+ return ret;
+ filp->private_data =
+ kzalloc(sizeof(struct vsoc_private_data), GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+ return 0;
+}
+
+static int vsoc_release(struct inode *inode, struct file *filp)
+{
+ struct vsoc_private_data *private_data = NULL;
+ struct fd_scoped_permission_node *node = NULL;
+ struct vsoc_device_region *owner_region_p = NULL;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ private_data = (struct vsoc_private_data *)filp->private_data;
+ if (!private_data)
+ return 0;
+
+ node = private_data->fd_scoped_permission_node;
+ if (node) {
+ owner_region_p = vsoc_region_from_inode(inode);
+ if (owner_region_p->managed_by != VSOC_REGION_WHOLE) {
+ owner_region_p =
+ &vsoc_dev.regions[owner_region_p->managed_by];
+ }
+ do_destroy_fd_scoped_permission_node(owner_region_p, node);
+ private_data->fd_scoped_permission_node = NULL;
+ }
+ kfree(private_data);
+ filp->private_data = NULL;
+
+ return 0;
+}
+
+/*
+ * Returns the device relative offset and length of the area specified by the
+ * fd scoped permission. If there is no fd scoped permission set, a default
+ * permission covering the entire region is assumed, unless the region is owned
+ * by another one, in which case the default is a permission with zero size.
+ */
+static ssize_t vsoc_get_area(struct file *filp, __u32 *area_offset)
+{
+ __u32 off = 0;
+ ssize_t length = 0;
+ struct vsoc_device_region *region_p;
+ struct fd_scoped_permission *perm;
+
+ region_p = vsoc_region_from_filep(filp);
+ off = region_p->region_begin_offset;
+ perm = &((struct vsoc_private_data *)filp->private_data)->
+ fd_scoped_permission_node->permission;
+ if (perm) {
+ off += perm->begin_offset;
+ length = perm->end_offset - perm->begin_offset;
+ } else if (region_p->managed_by == VSOC_REGION_WHOLE) {
+ /* No permission set and the regions is not owned by another,
+ * default to full region access.
+ */
+ length = vsoc_device_region_size(region_p);
+ } else {
+ /* return zero length, access is denied. */
+ length = 0;
+ }
+ if (area_offset)
+ *area_offset = off;
+ return length;
+}
+
+static int vsoc_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ unsigned long len = vma->vm_end - vma->vm_start;
+ __u32 area_off;
+ phys_addr_t mem_off;
+ ssize_t area_len;
+ int retval = vsoc_validate_filep(filp);
+
+ if (retval)
+ return retval;
+ area_len = vsoc_get_area(filp, &area_off);
+ /* Add the requested offset */
+ area_off += (vma->vm_pgoff << PAGE_SHIFT);
+ area_len -= (vma->vm_pgoff << PAGE_SHIFT);
+ if (area_len < len)
+ return -EINVAL;
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ mem_off = shm_off_to_phys_addr(area_off);
+ if (io_remap_pfn_range(vma, vma->vm_start, mem_off >> PAGE_SHIFT,
+ len, vma->vm_page_prot))
+ return -EAGAIN;
+ return 0;
+}
+
+module_init(vsoc_init_module);
+module_exit(vsoc_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Greg Hartman <ghartman@google.com>");
+MODULE_DESCRIPTION("VSoC interpretation of QEmu's ivshmem device");
+MODULE_VERSION("1.0");
diff --git a/drivers/staging/goldfish/Kconfig b/drivers/staging/goldfish/Kconfig
index 4e09460..d293bbc 100644
--- a/drivers/staging/goldfish/Kconfig
+++ b/drivers/staging/goldfish/Kconfig
@@ -4,6 +4,14 @@
---help---
Emulated audio channel for the Goldfish Android Virtual Device
+config GOLDFISH_SYNC
+ tristate "Goldfish AVD Sync Driver"
+ depends on GOLDFISH
+ depends on SW_SYNC
+ depends on SYNC_FILE
+ ---help---
+ Emulated sync fences for the Goldfish Android Virtual Device
+
config MTD_GOLDFISH_NAND
tristate "Goldfish NAND device"
depends on GOLDFISH
diff --git a/drivers/staging/goldfish/Makefile b/drivers/staging/goldfish/Makefile
index dec34ad..3313fce 100644
--- a/drivers/staging/goldfish/Makefile
+++ b/drivers/staging/goldfish/Makefile
@@ -4,3 +4,9 @@
obj-$(CONFIG_GOLDFISH_AUDIO) += goldfish_audio.o
obj-$(CONFIG_MTD_GOLDFISH_NAND) += goldfish_nand.o
+
+# and sync
+
+ccflags-y := -Idrivers/staging/android
+goldfish_sync-objs := goldfish_sync_timeline_fence.o goldfish_sync_timeline.o
+obj-$(CONFIG_GOLDFISH_SYNC) += goldfish_sync.o
diff --git a/drivers/staging/goldfish/goldfish_audio.c b/drivers/staging/goldfish/goldfish_audio.c
index bd55995..0bb0ee2 100644
--- a/drivers/staging/goldfish/goldfish_audio.c
+++ b/drivers/staging/goldfish/goldfish_audio.c
@@ -28,6 +28,7 @@
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <linux/goldfish.h>
+#include <linux/acpi.h>
MODULE_AUTHOR("Google, Inc.");
MODULE_DESCRIPTION("Android QEMU Audio Driver");
@@ -116,6 +117,7 @@ static ssize_t goldfish_audio_read(struct file *fp, char __user *buf,
size_t count, loff_t *pos)
{
struct goldfish_audio *data = fp->private_data;
+ unsigned long irq_flags;
int length;
int result = 0;
@@ -129,6 +131,10 @@ static ssize_t goldfish_audio_read(struct file *fp, char __user *buf,
wait_event_interruptible(data->wait, data->buffer_status &
AUDIO_INT_READ_BUFFER_FULL);
+ spin_lock_irqsave(&data->lock, irq_flags);
+ data->buffer_status &= ~AUDIO_INT_READ_BUFFER_FULL;
+ spin_unlock_irqrestore(&data->lock, irq_flags);
+
length = AUDIO_READ(data, AUDIO_READ_BUFFER_AVAILABLE);
/* copy data to user space */
@@ -351,12 +357,19 @@ static const struct of_device_id goldfish_audio_of_match[] = {
};
MODULE_DEVICE_TABLE(of, goldfish_audio_of_match);
+static const struct acpi_device_id goldfish_audio_acpi_match[] = {
+ { "GFSH0005", 0 },
+ { },
+};
+MODULE_DEVICE_TABLE(acpi, goldfish_audio_acpi_match);
+
static struct platform_driver goldfish_audio_driver = {
.probe = goldfish_audio_probe,
.remove = goldfish_audio_remove,
.driver = {
.name = "goldfish_audio",
.of_match_table = goldfish_audio_of_match,
+ .acpi_match_table = ACPI_PTR(goldfish_audio_acpi_match),
}
};
diff --git a/drivers/staging/goldfish/goldfish_sync_timeline.c b/drivers/staging/goldfish/goldfish_sync_timeline.c
new file mode 100644
index 0000000..5bef4c6
--- /dev/null
+++ b/drivers/staging/goldfish/goldfish_sync_timeline.c
@@ -0,0 +1,962 @@
+/*
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#include <linux/interrupt.h>
+#include <linux/kref.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/acpi.h>
+
+#include <linux/string.h>
+
+#include <linux/fs.h>
+#include <linux/syscalls.h>
+#include <linux/sync_file.h>
+#include <linux/fence.h>
+
+#include "goldfish_sync_timeline_fence.h"
+
+#define ERR(...) printk(KERN_ERR __VA_ARGS__);
+
+#define INFO(...) printk(KERN_INFO __VA_ARGS__);
+
+#define DPRINT(...) pr_debug(__VA_ARGS__);
+
+#define DTRACE() DPRINT("%s: enter", __func__)
+
+/* The Goldfish sync driver is designed to provide a interface
+ * between the underlying host's sync device and the kernel's
+ * fence sync framework..
+ * The purpose of the device/driver is to enable lightweight
+ * creation and signaling of timelines and fences
+ * in order to synchronize the guest with host-side graphics events.
+ *
+ * Each time the interrupt trips, the driver
+ * may perform a sync operation.
+ */
+
+/* The operations are: */
+
+/* Ready signal - used to mark when irq should lower */
+#define CMD_SYNC_READY 0
+
+/* Create a new timeline. writes timeline handle */
+#define CMD_CREATE_SYNC_TIMELINE 1
+
+/* Create a fence object. reads timeline handle and time argument.
+ * Writes fence fd to the SYNC_REG_HANDLE register. */
+#define CMD_CREATE_SYNC_FENCE 2
+
+/* Increments timeline. reads timeline handle and time argument */
+#define CMD_SYNC_TIMELINE_INC 3
+
+/* Destroys a timeline. reads timeline handle */
+#define CMD_DESTROY_SYNC_TIMELINE 4
+
+/* Starts a wait on the host with
+ * the given glsync object and sync thread handle. */
+#define CMD_TRIGGER_HOST_WAIT 5
+
+/* The register layout is: */
+
+#define SYNC_REG_BATCH_COMMAND 0x00 /* host->guest batch commands */
+#define SYNC_REG_BATCH_GUESTCOMMAND 0x04 /* guest->host batch commands */
+#define SYNC_REG_BATCH_COMMAND_ADDR 0x08 /* communicate physical address of host->guest batch commands */
+#define SYNC_REG_BATCH_COMMAND_ADDR_HIGH 0x0c /* 64-bit part */
+#define SYNC_REG_BATCH_GUESTCOMMAND_ADDR 0x10 /* communicate physical address of guest->host commands */
+#define SYNC_REG_BATCH_GUESTCOMMAND_ADDR_HIGH 0x14 /* 64-bit part */
+#define SYNC_REG_INIT 0x18 /* signals that the device has been probed */
+
+/* There is an ioctl associated with goldfish sync driver.
+ * Make it conflict with ioctls that are not likely to be used
+ * in the emulator.
+ *
+ * '@' 00-0F linux/radeonfb.h conflict!
+ * '@' 00-0F drivers/video/aty/aty128fb.c conflict!
+ */
+#define GOLDFISH_SYNC_IOC_MAGIC '@'
+
+#define GOLDFISH_SYNC_IOC_QUEUE_WORK _IOWR(GOLDFISH_SYNC_IOC_MAGIC, 0, struct goldfish_sync_ioctl_info)
+
+/* The above definitions (command codes, register layout, ioctl definitions)
+ * need to be in sync with the following files:
+ *
+ * Host-side (emulator):
+ * external/qemu/android/emulation/goldfish_sync.h
+ * external/qemu-android/hw/misc/goldfish_sync.c
+ *
+ * Guest-side (system image):
+ * device/generic/goldfish-opengl/system/egl/goldfish_sync.h
+ * device/generic/goldfish/ueventd.ranchu.rc
+ * platform/build/target/board/generic/sepolicy/file_contexts
+ */
+struct goldfish_sync_hostcmd {
+ /* sorted for alignment */
+ uint64_t handle;
+ uint64_t hostcmd_handle;
+ uint32_t cmd;
+ uint32_t time_arg;
+};
+
+struct goldfish_sync_guestcmd {
+ uint64_t host_command; /* uint64_t for alignment */
+ uint64_t glsync_handle;
+ uint64_t thread_handle;
+ uint64_t guest_timeline_handle;
+};
+
+#define GOLDFISH_SYNC_MAX_CMDS 32
+
+struct goldfish_sync_state {
+ char __iomem *reg_base;
+ int irq;
+
+ /* Spinlock protects |to_do| / |to_do_end|. */
+ spinlock_t lock;
+ /* |mutex_lock| protects all concurrent access
+ * to timelines for both kernel and user space. */
+ struct mutex mutex_lock;
+
+ /* Buffer holding commands issued from host. */
+ struct goldfish_sync_hostcmd to_do[GOLDFISH_SYNC_MAX_CMDS];
+ uint32_t to_do_end;
+
+ /* Addresses for the reading or writing
+ * of individual commands. The host can directly write
+ * to |batch_hostcmd| (and then this driver immediately
+ * copies contents to |to_do|). This driver either replies
+ * through |batch_hostcmd| or simply issues a
+ * guest->host command through |batch_guestcmd|.
+ */
+ struct goldfish_sync_hostcmd *batch_hostcmd;
+ struct goldfish_sync_guestcmd *batch_guestcmd;
+
+ /* Used to give this struct itself to a work queue
+ * function for executing actual sync commands. */
+ struct work_struct work_item;
+};
+
+static struct goldfish_sync_state global_sync_state[1];
+
+struct goldfish_sync_timeline_obj {
+ struct goldfish_sync_timeline *sync_tl;
+ uint32_t current_time;
+ /* We need to be careful about when we deallocate
+ * this |goldfish_sync_timeline_obj| struct.
+ * In order to ensure proper cleanup, we need to
+ * consider the triggered host-side wait that may
+ * still be in flight when the guest close()'s a
+ * goldfish_sync device's sync context fd (and
+ * destroys the |sync_tl| field above).
+ * The host-side wait may raise IRQ
+ * and tell the kernel to increment the timeline _after_
+ * the |sync_tl| has already been set to null.
+ *
+ * From observations on OpenGL apps and CTS tests, this
+ * happens at some very low probability upon context
+ * destruction or process close, but it does happen
+ * and it needs to be handled properly. Otherwise,
+ * if we clean up the surrounding |goldfish_sync_timeline_obj|
+ * too early, any |handle| field of any host->guest command
+ * might not even point to a null |sync_tl| field,
+ * but to garbage memory or even a reclaimed |sync_tl|.
+ * If we do not count such "pending waits" and kfree the object
+ * immediately upon |goldfish_sync_timeline_destroy|,
+ * we might get mysterous RCU stalls after running a long
+ * time because the garbage memory that is being read
+ * happens to be interpretable as a |spinlock_t| struct
+ * that is currently in the locked state.
+ *
+ * To track when to free the |goldfish_sync_timeline_obj|
+ * itself, we maintain a kref.
+ * The kref essentially counts the timeline itself plus
+ * the number of waits in flight. kref_init/kref_put
+ * are issued on
+ * |goldfish_sync_timeline_create|/|goldfish_sync_timeline_destroy|
+ * and kref_get/kref_put are issued on
+ * |goldfish_sync_fence_create|/|goldfish_sync_timeline_inc|.
+ *
+ * The timeline is destroyed after reference count
+ * reaches zero, which would happen after
+ * |goldfish_sync_timeline_destroy| and all pending
+ * |goldfish_sync_timeline_inc|'s are fulfilled.
+ *
+ * NOTE (1): We assume that |fence_create| and
+ * |timeline_inc| calls are 1:1, otherwise the kref scheme
+ * will not work. This is a valid assumption as long
+ * as the host-side virtual device implementation
+ * does not insert any timeline increments
+ * that we did not trigger from here.
+ *
+ * NOTE (2): The use of kref by itself requires no locks,
+ * but this does not mean everything works without locks.
+ * Related timeline operations do require a lock of some sort,
+ * or at least are not proven to work without it.
+ * In particualr, we assume that all the operations
+ * done on the |kref| field above are done in contexts where
+ * |global_sync_state->mutex_lock| is held. Do not
+ * remove that lock until everything is proven to work
+ * without it!!! */
+ struct kref kref;
+};
+
+/* We will call |delete_timeline_obj| when the last reference count
+ * of the kref is decremented. This deletes the sync
+ * timeline object along with the wrapper itself. */
+static void delete_timeline_obj(struct kref* kref) {
+ struct goldfish_sync_timeline_obj* obj =
+ container_of(kref, struct goldfish_sync_timeline_obj, kref);
+
+ goldfish_sync_timeline_put_internal(obj->sync_tl);
+ obj->sync_tl = NULL;
+ kfree(obj);
+}
+
+static uint64_t gensym_ctr;
+static void gensym(char *dst)
+{
+ sprintf(dst, "goldfish_sync:gensym:%llu", gensym_ctr);
+ gensym_ctr++;
+}
+
+/* |goldfish_sync_timeline_create| assumes that |global_sync_state->mutex_lock|
+ * is held. */
+static struct goldfish_sync_timeline_obj*
+goldfish_sync_timeline_create(void)
+{
+
+ char timeline_name[256];
+ struct goldfish_sync_timeline *res_sync_tl = NULL;
+ struct goldfish_sync_timeline_obj *res;
+
+ DTRACE();
+
+ gensym(timeline_name);
+
+ res_sync_tl = goldfish_sync_timeline_create_internal(timeline_name);
+ if (!res_sync_tl) {
+ ERR("Failed to create goldfish_sw_sync timeline.");
+ return NULL;
+ }
+
+ res = kzalloc(sizeof(struct goldfish_sync_timeline_obj), GFP_KERNEL);
+ res->sync_tl = res_sync_tl;
+ res->current_time = 0;
+ kref_init(&res->kref);
+
+ DPRINT("new timeline_obj=0x%p", res);
+ return res;
+}
+
+/* |goldfish_sync_fence_create| assumes that |global_sync_state->mutex_lock|
+ * is held. */
+static int
+goldfish_sync_fence_create(struct goldfish_sync_timeline_obj *obj,
+ uint32_t val)
+{
+
+ int fd;
+ char fence_name[256];
+ struct sync_pt *syncpt = NULL;
+ struct sync_file *sync_file_obj = NULL;
+ struct goldfish_sync_timeline *tl;
+
+ DTRACE();
+
+ if (!obj) return -1;
+
+ tl = obj->sync_tl;
+
+ syncpt = goldfish_sync_pt_create_internal(
+ tl, sizeof(struct sync_pt) + 4, val);
+ if (!syncpt) {
+ ERR("could not create sync point! "
+ "goldfish_sync_timeline=0x%p val=%d",
+ tl, val);
+ return -1;
+ }
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0) {
+ ERR("could not get unused fd for sync fence. "
+ "errno=%d", fd);
+ goto err_cleanup_pt;
+ }
+
+ gensym(fence_name);
+
+ sync_file_obj = sync_file_create(&syncpt->base);
+ if (!sync_file_obj) {
+ ERR("could not create sync fence! "
+ "goldfish_sync_timeline=0x%p val=%d sync_pt=0x%p",
+ tl, val, syncpt);
+ goto err_cleanup_fd_pt;
+ }
+
+ DPRINT("installing sync fence into fd %d sync_file_obj=0x%p",
+ fd, sync_file_obj);
+ fd_install(fd, sync_file_obj->file);
+ kref_get(&obj->kref);
+
+ return fd;
+
+err_cleanup_fd_pt:
+ put_unused_fd(fd);
+err_cleanup_pt:
+ fence_put(&syncpt->base);
+ return -1;
+}
+
+/* |goldfish_sync_timeline_inc| assumes that |global_sync_state->mutex_lock|
+ * is held. */
+static void
+goldfish_sync_timeline_inc(struct goldfish_sync_timeline_obj *obj, uint32_t inc)
+{
+ DTRACE();
+ /* Just give up if someone else nuked the timeline.
+ * Whoever it was won't care that it doesn't get signaled. */
+ if (!obj) return;
+
+ DPRINT("timeline_obj=0x%p", obj);
+ goldfish_sync_timeline_signal_internal(obj->sync_tl, inc);
+ DPRINT("incremented timeline. increment max_time");
+ obj->current_time += inc;
+
+ /* Here, we will end up deleting the timeline object if it
+ * turns out that this call was a pending increment after
+ * |goldfish_sync_timeline_destroy| was called. */
+ kref_put(&obj->kref, delete_timeline_obj);
+ DPRINT("done");
+}
+
+/* |goldfish_sync_timeline_destroy| assumes
+ * that |global_sync_state->mutex_lock| is held. */
+static void
+goldfish_sync_timeline_destroy(struct goldfish_sync_timeline_obj *obj)
+{
+ DTRACE();
+ /* See description of |goldfish_sync_timeline_obj| for why we
+ * should not immediately destroy |obj| */
+ kref_put(&obj->kref, delete_timeline_obj);
+}
+
+static inline void
+goldfish_sync_cmd_queue(struct goldfish_sync_state *sync_state,
+ uint32_t cmd,
+ uint64_t handle,
+ uint32_t time_arg,
+ uint64_t hostcmd_handle)
+{
+ struct goldfish_sync_hostcmd *to_add;
+
+ DTRACE();
+
+ BUG_ON(sync_state->to_do_end == GOLDFISH_SYNC_MAX_CMDS);
+
+ to_add = &sync_state->to_do[sync_state->to_do_end];
+
+ to_add->cmd = cmd;
+ to_add->handle = handle;
+ to_add->time_arg = time_arg;
+ to_add->hostcmd_handle = hostcmd_handle;
+
+ sync_state->to_do_end += 1;
+}
+
+static inline void
+goldfish_sync_hostcmd_reply(struct goldfish_sync_state *sync_state,
+ uint32_t cmd,
+ uint64_t handle,
+ uint32_t time_arg,
+ uint64_t hostcmd_handle)
+{
+ unsigned long irq_flags;
+ struct goldfish_sync_hostcmd *batch_hostcmd =
+ sync_state->batch_hostcmd;
+
+ DTRACE();
+
+ spin_lock_irqsave(&sync_state->lock, irq_flags);
+
+ batch_hostcmd->cmd = cmd;
+ batch_hostcmd->handle = handle;
+ batch_hostcmd->time_arg = time_arg;
+ batch_hostcmd->hostcmd_handle = hostcmd_handle;
+ writel(0, sync_state->reg_base + SYNC_REG_BATCH_COMMAND);
+
+ spin_unlock_irqrestore(&sync_state->lock, irq_flags);
+}
+
+static inline void
+goldfish_sync_send_guestcmd(struct goldfish_sync_state *sync_state,
+ uint32_t cmd,
+ uint64_t glsync_handle,
+ uint64_t thread_handle,
+ uint64_t timeline_handle)
+{
+ unsigned long irq_flags;
+ struct goldfish_sync_guestcmd *batch_guestcmd =
+ sync_state->batch_guestcmd;
+
+ DTRACE();
+
+ spin_lock_irqsave(&sync_state->lock, irq_flags);
+
+ batch_guestcmd->host_command = (uint64_t)cmd;
+ batch_guestcmd->glsync_handle = (uint64_t)glsync_handle;
+ batch_guestcmd->thread_handle = (uint64_t)thread_handle;
+ batch_guestcmd->guest_timeline_handle = (uint64_t)timeline_handle;
+ writel(0, sync_state->reg_base + SYNC_REG_BATCH_GUESTCOMMAND);
+
+ spin_unlock_irqrestore(&sync_state->lock, irq_flags);
+}
+
+/* |goldfish_sync_interrupt| handles IRQ raises from the virtual device.
+ * In the context of OpenGL, this interrupt will fire whenever we need
+ * to signal a fence fd in the guest, with the command
+ * |CMD_SYNC_TIMELINE_INC|.
+ * However, because this function will be called in an interrupt context,
+ * it is necessary to do the actual work of signaling off of interrupt context.
+ * The shared work queue is used for this purpose. At the end when
+ * all pending commands are intercepted by the interrupt handler,
+ * we call |schedule_work|, which will later run the actual
+ * desired sync command in |goldfish_sync_work_item_fn|.
+ */
+static irqreturn_t goldfish_sync_interrupt(int irq, void *dev_id)
+{
+
+ struct goldfish_sync_state *sync_state = dev_id;
+
+ uint32_t nextcmd;
+ uint32_t command_r;
+ uint64_t handle_rw;
+ uint32_t time_r;
+ uint64_t hostcmd_handle_rw;
+
+ int count = 0;
+
+ DTRACE();
+
+ sync_state = dev_id;
+
+ spin_lock(&sync_state->lock);
+
+ for (;;) {
+
+ readl(sync_state->reg_base + SYNC_REG_BATCH_COMMAND);
+ nextcmd = sync_state->batch_hostcmd->cmd;
+
+ if (nextcmd == 0)
+ break;
+
+ command_r = nextcmd;
+ handle_rw = sync_state->batch_hostcmd->handle;
+ time_r = sync_state->batch_hostcmd->time_arg;
+ hostcmd_handle_rw = sync_state->batch_hostcmd->hostcmd_handle;
+
+ goldfish_sync_cmd_queue(
+ sync_state,
+ command_r,
+ handle_rw,
+ time_r,
+ hostcmd_handle_rw);
+
+ count++;
+ }
+
+ spin_unlock(&sync_state->lock);
+
+ schedule_work(&sync_state->work_item);
+
+ return (count == 0) ? IRQ_NONE : IRQ_HANDLED;
+}
+
+/* |goldfish_sync_work_item_fn| does the actual work of servicing
+ * host->guest sync commands. This function is triggered whenever
+ * the IRQ for the goldfish sync device is raised. Once it starts
+ * running, it grabs the contents of the buffer containing the
+ * commands it needs to execute (there may be multiple, because
+ * our IRQ is active high and not edge triggered), and then
+ * runs all of them one after the other.
+ */
+static void goldfish_sync_work_item_fn(struct work_struct *input)
+{
+
+ struct goldfish_sync_state *sync_state;
+ int sync_fence_fd;
+
+ struct goldfish_sync_timeline_obj *timeline;
+ uint64_t timeline_ptr;
+
+ uint64_t hostcmd_handle;
+
+ uint32_t cmd;
+ uint64_t handle;
+ uint32_t time_arg;
+
+ struct goldfish_sync_hostcmd *todo;
+ uint32_t todo_end;
+
+ unsigned long irq_flags;
+
+ struct goldfish_sync_hostcmd to_run[GOLDFISH_SYNC_MAX_CMDS];
+ uint32_t i = 0;
+
+ sync_state = container_of(input, struct goldfish_sync_state, work_item);
+
+ mutex_lock(&sync_state->mutex_lock);
+
+ spin_lock_irqsave(&sync_state->lock, irq_flags); {
+
+ todo_end = sync_state->to_do_end;
+
+ DPRINT("num sync todos: %u", sync_state->to_do_end);
+
+ for (i = 0; i < todo_end; i++)
+ to_run[i] = sync_state->to_do[i];
+
+ /* We expect that commands will come in at a slow enough rate
+ * so that incoming items will not be more than
+ * GOLDFISH_SYNC_MAX_CMDS.
+ *
+ * This is because the way the sync device is used,
+ * it's only for managing buffer data transfers per frame,
+ * with a sequential dependency between putting things in
+ * to_do and taking them out. Once a set of commands is
+ * queued up in to_do, the user of the device waits for
+ * them to be processed before queuing additional commands,
+ * which limits the rate at which commands come in
+ * to the rate at which we take them out here.
+ *
+ * We also don't expect more than MAX_CMDS to be issued
+ * at once; there is a correspondence between
+ * which buffers need swapping to the (display / buffer queue)
+ * to particular commands, and we don't expect there to be
+ * enough display or buffer queues in operation at once
+ * to overrun GOLDFISH_SYNC_MAX_CMDS.
+ */
+ sync_state->to_do_end = 0;
+
+ } spin_unlock_irqrestore(&sync_state->lock, irq_flags);
+
+ for (i = 0; i < todo_end; i++) {
+ DPRINT("todo index: %u", i);
+
+ todo = &to_run[i];
+
+ cmd = todo->cmd;
+
+ handle = (uint64_t)todo->handle;
+ time_arg = todo->time_arg;
+ hostcmd_handle = (uint64_t)todo->hostcmd_handle;
+
+ DTRACE();
+
+ timeline = (struct goldfish_sync_timeline_obj *)(uintptr_t)handle;
+
+ switch (cmd) {
+ case CMD_SYNC_READY:
+ break;
+ case CMD_CREATE_SYNC_TIMELINE:
+ DPRINT("exec CMD_CREATE_SYNC_TIMELINE: "
+ "handle=0x%llx time_arg=%d",
+ handle, time_arg);
+ timeline = goldfish_sync_timeline_create();
+ timeline_ptr = (uintptr_t)timeline;
+ goldfish_sync_hostcmd_reply(sync_state, CMD_CREATE_SYNC_TIMELINE,
+ timeline_ptr,
+ 0,
+ hostcmd_handle);
+ DPRINT("sync timeline created: %p", timeline);
+ break;
+ case CMD_CREATE_SYNC_FENCE:
+ DPRINT("exec CMD_CREATE_SYNC_FENCE: "
+ "handle=0x%llx time_arg=%d",
+ handle, time_arg);
+ sync_fence_fd = goldfish_sync_fence_create(timeline, time_arg);
+ goldfish_sync_hostcmd_reply(sync_state, CMD_CREATE_SYNC_FENCE,
+ sync_fence_fd,
+ 0,
+ hostcmd_handle);
+ break;
+ case CMD_SYNC_TIMELINE_INC:
+ DPRINT("exec CMD_SYNC_TIMELINE_INC: "
+ "handle=0x%llx time_arg=%d",
+ handle, time_arg);
+ goldfish_sync_timeline_inc(timeline, time_arg);
+ break;
+ case CMD_DESTROY_SYNC_TIMELINE:
+ DPRINT("exec CMD_DESTROY_SYNC_TIMELINE: "
+ "handle=0x%llx time_arg=%d",
+ handle, time_arg);
+ goldfish_sync_timeline_destroy(timeline);
+ break;
+ }
+ DPRINT("Done executing sync command");
+ }
+ mutex_unlock(&sync_state->mutex_lock);
+}
+
+/* Guest-side interface: file operations */
+
+/* Goldfish sync context and ioctl info.
+ *
+ * When a sync context is created by open()-ing the goldfish sync device, we
+ * create a sync context (|goldfish_sync_context|).
+ *
+ * Currently, the only data required to track is the sync timeline itself
+ * along with the current time, which are all packed up in the
+ * |goldfish_sync_timeline_obj| field. We use a |goldfish_sync_context|
+ * as the filp->private_data.
+ *
+ * Next, when a sync context user requests that work be queued and a fence
+ * fd provided, we use the |goldfish_sync_ioctl_info| struct, which holds
+ * information about which host handles to touch for this particular
+ * queue-work operation. We need to know about the host-side sync thread
+ * and the particular host-side GLsync object. We also possibly write out
+ * a file descriptor.
+ */
+struct goldfish_sync_context {
+ struct goldfish_sync_timeline_obj *timeline;
+};
+
+struct goldfish_sync_ioctl_info {
+ uint64_t host_glsync_handle_in;
+ uint64_t host_syncthread_handle_in;
+ int fence_fd_out;
+};
+
+static int goldfish_sync_open(struct inode *inode, struct file *file)
+{
+
+ struct goldfish_sync_context *sync_context;
+
+ DTRACE();
+
+ mutex_lock(&global_sync_state->mutex_lock);
+
+ sync_context = kzalloc(sizeof(struct goldfish_sync_context), GFP_KERNEL);
+
+ if (sync_context == NULL) {
+ ERR("Creation of goldfish sync context failed!");
+ mutex_unlock(&global_sync_state->mutex_lock);
+ return -ENOMEM;
+ }
+
+ sync_context->timeline = NULL;
+
+ file->private_data = sync_context;
+
+ DPRINT("successfully create a sync context @0x%p", sync_context);
+
+ mutex_unlock(&global_sync_state->mutex_lock);
+
+ return 0;
+}
+
+static int goldfish_sync_release(struct inode *inode, struct file *file)
+{
+
+ struct goldfish_sync_context *sync_context;
+
+ DTRACE();
+
+ mutex_lock(&global_sync_state->mutex_lock);
+
+ sync_context = file->private_data;
+
+ if (sync_context->timeline)
+ goldfish_sync_timeline_destroy(sync_context->timeline);
+
+ sync_context->timeline = NULL;
+
+ kfree(sync_context);
+
+ mutex_unlock(&global_sync_state->mutex_lock);
+
+ return 0;
+}
+
+/* |goldfish_sync_ioctl| is the guest-facing interface of goldfish sync
+ * and is used in conjunction with eglCreateSyncKHR to queue up the
+ * actual work of waiting for the EGL sync command to complete,
+ * possibly returning a fence fd to the guest.
+ */
+static long goldfish_sync_ioctl(struct file *file,
+ unsigned int cmd,
+ unsigned long arg)
+{
+ struct goldfish_sync_context *sync_context_data;
+ struct goldfish_sync_timeline_obj *timeline;
+ int fd_out;
+ struct goldfish_sync_ioctl_info ioctl_data;
+
+ DTRACE();
+
+ sync_context_data = file->private_data;
+ fd_out = -1;
+
+ switch (cmd) {
+ case GOLDFISH_SYNC_IOC_QUEUE_WORK:
+
+ DPRINT("exec GOLDFISH_SYNC_IOC_QUEUE_WORK");
+
+ mutex_lock(&global_sync_state->mutex_lock);
+
+ if (copy_from_user(&ioctl_data,
+ (void __user *)arg,
+ sizeof(ioctl_data))) {
+ ERR("Failed to copy memory for ioctl_data from user.");
+ mutex_unlock(&global_sync_state->mutex_lock);
+ return -EFAULT;
+ }
+
+ if (ioctl_data.host_syncthread_handle_in == 0) {
+ DPRINT("Error: zero host syncthread handle!!!");
+ mutex_unlock(&global_sync_state->mutex_lock);
+ return -EFAULT;
+ }
+
+ if (!sync_context_data->timeline) {
+ DPRINT("no timeline yet, create one.");
+ sync_context_data->timeline = goldfish_sync_timeline_create();
+ DPRINT("timeline: 0x%p", &sync_context_data->timeline);
+ }
+
+ timeline = sync_context_data->timeline;
+ fd_out = goldfish_sync_fence_create(timeline,
+ timeline->current_time + 1);
+ DPRINT("Created fence with fd %d and current time %u (timeline: 0x%p)",
+ fd_out,
+ sync_context_data->timeline->current_time + 1,
+ sync_context_data->timeline);
+
+ ioctl_data.fence_fd_out = fd_out;
+
+ if (copy_to_user((void __user *)arg,
+ &ioctl_data,
+ sizeof(ioctl_data))) {
+ DPRINT("Error, could not copy to user!!!");
+
+ sys_close(fd_out);
+ /* We won't be doing an increment, kref_put immediately. */
+ kref_put(&timeline->kref, delete_timeline_obj);
+ mutex_unlock(&global_sync_state->mutex_lock);
+ return -EFAULT;
+ }
+
+ /* We are now about to trigger a host-side wait;
+ * accumulate on |pending_waits|. */
+ goldfish_sync_send_guestcmd(global_sync_state,
+ CMD_TRIGGER_HOST_WAIT,
+ ioctl_data.host_glsync_handle_in,
+ ioctl_data.host_syncthread_handle_in,
+ (uint64_t)(uintptr_t)(sync_context_data->timeline));
+
+ mutex_unlock(&global_sync_state->mutex_lock);
+ return 0;
+ default:
+ return -ENOTTY;
+ }
+}
+
+static const struct file_operations goldfish_sync_fops = {
+ .owner = THIS_MODULE,
+ .open = goldfish_sync_open,
+ .release = goldfish_sync_release,
+ .unlocked_ioctl = goldfish_sync_ioctl,
+ .compat_ioctl = goldfish_sync_ioctl,
+};
+
+static struct miscdevice goldfish_sync_device = {
+ .name = "goldfish_sync",
+ .fops = &goldfish_sync_fops,
+};
+
+
+static bool setup_verify_batch_cmd_addr(struct goldfish_sync_state *sync_state,
+ void *batch_addr,
+ uint32_t addr_offset,
+ uint32_t addr_offset_high)
+{
+ uint64_t batch_addr_phys;
+ uint32_t batch_addr_phys_test_lo;
+ uint32_t batch_addr_phys_test_hi;
+
+ if (!batch_addr) {
+ ERR("Could not use batch command address!");
+ return false;
+ }
+
+ batch_addr_phys = virt_to_phys(batch_addr);
+ writel((uint32_t)(batch_addr_phys),
+ sync_state->reg_base + addr_offset);
+ writel((uint32_t)(batch_addr_phys >> 32),
+ sync_state->reg_base + addr_offset_high);
+
+ batch_addr_phys_test_lo =
+ readl(sync_state->reg_base + addr_offset);
+ batch_addr_phys_test_hi =
+ readl(sync_state->reg_base + addr_offset_high);
+
+ if (virt_to_phys(batch_addr) !=
+ (((uint64_t)batch_addr_phys_test_hi << 32) |
+ batch_addr_phys_test_lo)) {
+ ERR("Invalid batch command address!");
+ return false;
+ }
+
+ return true;
+}
+
+int goldfish_sync_probe(struct platform_device *pdev)
+{
+ struct resource *ioresource;
+ struct goldfish_sync_state *sync_state = global_sync_state;
+ int status;
+
+ DTRACE();
+
+ sync_state->to_do_end = 0;
+
+ spin_lock_init(&sync_state->lock);
+ mutex_init(&sync_state->mutex_lock);
+
+ platform_set_drvdata(pdev, sync_state);
+
+ ioresource = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (ioresource == NULL) {
+ ERR("platform_get_resource failed");
+ return -ENODEV;
+ }
+
+ sync_state->reg_base =
+ devm_ioremap(&pdev->dev, ioresource->start, PAGE_SIZE);
+ if (sync_state->reg_base == NULL) {
+ ERR("Could not ioremap");
+ return -ENOMEM;
+ }
+
+ sync_state->irq = platform_get_irq(pdev, 0);
+ if (sync_state->irq < 0) {
+ ERR("Could not platform_get_irq");
+ return -ENODEV;
+ }
+
+ status = devm_request_irq(&pdev->dev,
+ sync_state->irq,
+ goldfish_sync_interrupt,
+ IRQF_SHARED,
+ pdev->name,
+ sync_state);
+ if (status) {
+ ERR("request_irq failed");
+ return -ENODEV;
+ }
+
+ INIT_WORK(&sync_state->work_item,
+ goldfish_sync_work_item_fn);
+
+ misc_register(&goldfish_sync_device);
+
+ /* Obtain addresses for batch send/recv of commands. */
+ {
+ struct goldfish_sync_hostcmd *batch_addr_hostcmd;
+ struct goldfish_sync_guestcmd *batch_addr_guestcmd;
+
+ batch_addr_hostcmd =
+ devm_kzalloc(&pdev->dev, sizeof(struct goldfish_sync_hostcmd),
+ GFP_KERNEL);
+ batch_addr_guestcmd =
+ devm_kzalloc(&pdev->dev, sizeof(struct goldfish_sync_guestcmd),
+ GFP_KERNEL);
+
+ if (!setup_verify_batch_cmd_addr(sync_state,
+ batch_addr_hostcmd,
+ SYNC_REG_BATCH_COMMAND_ADDR,
+ SYNC_REG_BATCH_COMMAND_ADDR_HIGH)) {
+ ERR("goldfish_sync: Could not setup batch command address");
+ return -ENODEV;
+ }
+
+ if (!setup_verify_batch_cmd_addr(sync_state,
+ batch_addr_guestcmd,
+ SYNC_REG_BATCH_GUESTCOMMAND_ADDR,
+ SYNC_REG_BATCH_GUESTCOMMAND_ADDR_HIGH)) {
+ ERR("goldfish_sync: Could not setup batch guest command address");
+ return -ENODEV;
+ }
+
+ sync_state->batch_hostcmd = batch_addr_hostcmd;
+ sync_state->batch_guestcmd = batch_addr_guestcmd;
+ }
+
+ INFO("goldfish_sync: Initialized goldfish sync device");
+
+ writel(0, sync_state->reg_base + SYNC_REG_INIT);
+
+ return 0;
+}
+
+static int goldfish_sync_remove(struct platform_device *pdev)
+{
+ struct goldfish_sync_state *sync_state = global_sync_state;
+
+ DTRACE();
+
+ misc_deregister(&goldfish_sync_device);
+ memset(sync_state, 0, sizeof(struct goldfish_sync_state));
+ return 0;
+}
+
+static const struct of_device_id goldfish_sync_of_match[] = {
+ { .compatible = "google,goldfish-sync", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, goldfish_sync_of_match);
+
+static const struct acpi_device_id goldfish_sync_acpi_match[] = {
+ { "GFSH0006", 0 },
+ { },
+};
+
+MODULE_DEVICE_TABLE(acpi, goldfish_sync_acpi_match);
+
+static struct platform_driver goldfish_sync = {
+ .probe = goldfish_sync_probe,
+ .remove = goldfish_sync_remove,
+ .driver = {
+ .name = "goldfish_sync",
+ .of_match_table = goldfish_sync_of_match,
+ .acpi_match_table = ACPI_PTR(goldfish_sync_acpi_match),
+ }
+};
+
+module_platform_driver(goldfish_sync);
+
+MODULE_AUTHOR("Google, Inc.");
+MODULE_DESCRIPTION("Android QEMU Sync Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
diff --git a/drivers/staging/goldfish/goldfish_sync_timeline_fence.c b/drivers/staging/goldfish/goldfish_sync_timeline_fence.c
new file mode 100644
index 0000000..e671618
--- /dev/null
+++ b/drivers/staging/goldfish/goldfish_sync_timeline_fence.c
@@ -0,0 +1,254 @@
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/syscalls.h>
+#include <linux/sync_file.h>
+#include <linux/fence.h>
+
+#include "goldfish_sync_timeline_fence.h"
+
+/*
+ * Timeline-based sync for Goldfish Sync
+ * Based on "Sync File validation framework"
+ * (drivers/dma-buf/sw_sync.c)
+ *
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/**
+ * struct goldfish_sync_timeline - sync object
+ * @kref: reference count on fence.
+ * @name: name of the goldfish_sync_timeline. Useful for debugging
+ * @child_list_head: list of children sync_pts for this goldfish_sync_timeline
+ * @child_list_lock: lock protecting @child_list_head and fence.status
+ * @active_list_head: list of active (unsignaled/errored) sync_pts
+ */
+struct goldfish_sync_timeline {
+ struct kref kref;
+ char name[32];
+
+ /* protected by child_list_lock */
+ u64 context;
+ int value;
+
+ struct list_head child_list_head;
+ spinlock_t child_list_lock;
+
+ struct list_head active_list_head;
+};
+
+static inline struct goldfish_sync_timeline *fence_parent(struct fence *fence)
+{
+ return container_of(fence->lock, struct goldfish_sync_timeline,
+ child_list_lock);
+}
+
+static const struct fence_ops goldfish_sync_timeline_fence_ops;
+
+static inline struct sync_pt *goldfish_sync_fence_to_sync_pt(struct fence *fence)
+{
+ if (fence->ops != &goldfish_sync_timeline_fence_ops)
+ return NULL;
+ return container_of(fence, struct sync_pt, base);
+}
+
+/**
+ * goldfish_sync_timeline_create_internal() - creates a sync object
+ * @name: sync_timeline name
+ *
+ * Creates a new sync_timeline. Returns the sync_timeline object or NULL in
+ * case of error.
+ */
+struct goldfish_sync_timeline
+*goldfish_sync_timeline_create_internal(const char *name)
+{
+ struct goldfish_sync_timeline *obj;
+
+ obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+ if (!obj)
+ return NULL;
+
+ kref_init(&obj->kref);
+ obj->context = fence_context_alloc(1);
+ strlcpy(obj->name, name, sizeof(obj->name));
+
+ INIT_LIST_HEAD(&obj->child_list_head);
+ INIT_LIST_HEAD(&obj->active_list_head);
+ spin_lock_init(&obj->child_list_lock);
+
+ return obj;
+}
+
+static void goldfish_sync_timeline_free_internal(struct kref *kref)
+{
+ struct goldfish_sync_timeline *obj =
+ container_of(kref, struct goldfish_sync_timeline, kref);
+
+ kfree(obj);
+}
+
+static void goldfish_sync_timeline_get_internal(
+ struct goldfish_sync_timeline *obj)
+{
+ kref_get(&obj->kref);
+}
+
+void goldfish_sync_timeline_put_internal(struct goldfish_sync_timeline *obj)
+{
+ kref_put(&obj->kref, goldfish_sync_timeline_free_internal);
+}
+
+/**
+ * goldfish_sync_timeline_signal() -
+ * signal a status change on a goldfish_sync_timeline
+ * @obj: sync_timeline to signal
+ * @inc: num to increment on timeline->value
+ *
+ * A sync implementation should call this any time one of it's fences
+ * has signaled or has an error condition.
+ */
+void goldfish_sync_timeline_signal_internal(struct goldfish_sync_timeline *obj,
+ unsigned int inc)
+{
+ unsigned long flags;
+ struct sync_pt *pt, *next;
+
+ spin_lock_irqsave(&obj->child_list_lock, flags);
+
+ obj->value += inc;
+
+ list_for_each_entry_safe(pt, next, &obj->active_list_head,
+ active_list) {
+ if (fence_is_signaled_locked(&pt->base))
+ list_del_init(&pt->active_list);
+ }
+
+ spin_unlock_irqrestore(&obj->child_list_lock, flags);
+}
+
+/**
+ * goldfish_sync_pt_create_internal() - creates a sync pt
+ * @parent: fence's parent sync_timeline
+ * @size: size to allocate for this pt
+ * @inc: value of the fence
+ *
+ * Creates a new sync_pt as a child of @parent. @size bytes will be
+ * allocated allowing for implementation specific data to be kept after
+ * the generic sync_timeline struct. Returns the sync_pt object or
+ * NULL in case of error.
+ */
+struct sync_pt *goldfish_sync_pt_create_internal(
+ struct goldfish_sync_timeline *obj, int size,
+ unsigned int value)
+{
+ unsigned long flags;
+ struct sync_pt *pt;
+
+ if (size < sizeof(*pt))
+ return NULL;
+
+ pt = kzalloc(size, GFP_KERNEL);
+ if (!pt)
+ return NULL;
+
+ spin_lock_irqsave(&obj->child_list_lock, flags);
+ goldfish_sync_timeline_get_internal(obj);
+ fence_init(&pt->base, &goldfish_sync_timeline_fence_ops, &obj->child_list_lock,
+ obj->context, value);
+ list_add_tail(&pt->child_list, &obj->child_list_head);
+ INIT_LIST_HEAD(&pt->active_list);
+ spin_unlock_irqrestore(&obj->child_list_lock, flags);
+ return pt;
+}
+
+static const char *goldfish_sync_timeline_fence_get_driver_name(
+ struct fence *fence)
+{
+ return "sw_sync";
+}
+
+static const char *goldfish_sync_timeline_fence_get_timeline_name(
+ struct fence *fence)
+{
+ struct goldfish_sync_timeline *parent = fence_parent(fence);
+
+ return parent->name;
+}
+
+static void goldfish_sync_timeline_fence_release(struct fence *fence)
+{
+ struct sync_pt *pt = goldfish_sync_fence_to_sync_pt(fence);
+ struct goldfish_sync_timeline *parent = fence_parent(fence);
+ unsigned long flags;
+
+ spin_lock_irqsave(fence->lock, flags);
+ list_del(&pt->child_list);
+ if (!list_empty(&pt->active_list))
+ list_del(&pt->active_list);
+ spin_unlock_irqrestore(fence->lock, flags);
+
+ goldfish_sync_timeline_put_internal(parent);
+ fence_free(fence);
+}
+
+static bool goldfish_sync_timeline_fence_signaled(struct fence *fence)
+{
+ struct goldfish_sync_timeline *parent = fence_parent(fence);
+
+ return (fence->seqno > parent->value) ? false : true;
+}
+
+static bool goldfish_sync_timeline_fence_enable_signaling(struct fence *fence)
+{
+ struct sync_pt *pt = goldfish_sync_fence_to_sync_pt(fence);
+ struct goldfish_sync_timeline *parent = fence_parent(fence);
+
+ if (goldfish_sync_timeline_fence_signaled(fence))
+ return false;
+
+ list_add_tail(&pt->active_list, &parent->active_list_head);
+ return true;
+}
+
+static void goldfish_sync_timeline_fence_disable_signaling(struct fence *fence)
+{
+ struct sync_pt *pt = container_of(fence, struct sync_pt, base);
+
+ list_del_init(&pt->active_list);
+}
+
+static void goldfish_sync_timeline_fence_value_str(struct fence *fence,
+ char *str, int size)
+{
+ snprintf(str, size, "%d", fence->seqno);
+}
+
+static void goldfish_sync_timeline_fence_timeline_value_str(
+ struct fence *fence,
+ char *str, int size)
+{
+ struct goldfish_sync_timeline *parent = fence_parent(fence);
+
+ snprintf(str, size, "%d", parent->value);
+}
+
+static const struct fence_ops goldfish_sync_timeline_fence_ops = {
+ .get_driver_name = goldfish_sync_timeline_fence_get_driver_name,
+ .get_timeline_name = goldfish_sync_timeline_fence_get_timeline_name,
+ .enable_signaling = goldfish_sync_timeline_fence_enable_signaling,
+ .disable_signaling = goldfish_sync_timeline_fence_disable_signaling,
+ .signaled = goldfish_sync_timeline_fence_signaled,
+ .wait = fence_default_wait,
+ .release = goldfish_sync_timeline_fence_release,
+ .fence_value_str = goldfish_sync_timeline_fence_value_str,
+ .timeline_value_str = goldfish_sync_timeline_fence_timeline_value_str,
+};
diff --git a/drivers/staging/goldfish/goldfish_sync_timeline_fence.h b/drivers/staging/goldfish/goldfish_sync_timeline_fence.h
new file mode 100644
index 0000000..fc25924
--- /dev/null
+++ b/drivers/staging/goldfish/goldfish_sync_timeline_fence.h
@@ -0,0 +1,58 @@
+#include <linux/sync_file.h>
+#include <linux/fence.h>
+
+/**
+ * struct sync_pt - sync_pt object
+ * @base: base fence object
+ * @child_list: sync timeline child's list
+ * @active_list: sync timeline active child's list
+ */
+struct sync_pt {
+ struct fence base;
+ struct list_head child_list;
+ struct list_head active_list;
+};
+
+/**
+ * goldfish_sync_timeline_create_internal() - creates a sync object
+ * @name: goldfish_sync_timeline name
+ *
+ * Creates a new goldfish_sync_timeline.
+ * Returns the goldfish_sync_timeline object or NULL in case of error.
+ */
+struct goldfish_sync_timeline
+*goldfish_sync_timeline_create_internal(const char *name);
+
+/**
+ * goldfish_sync_pt_create_internal() - creates a sync pt
+ * @parent: fence's parent goldfish_sync_timeline
+ * @size: size to allocate for this pt
+ * @inc: value of the fence
+ *
+ * Creates a new sync_pt as a child of @parent. @size bytes will be
+ * allocated allowing for implementation specific data to be kept after
+ * the generic sync_timeline struct. Returns the sync_pt object or
+ * NULL in case of error.
+ */
+struct sync_pt
+*goldfish_sync_pt_create_internal(struct goldfish_sync_timeline *obj,
+ int size, unsigned int value);
+
+/**
+ * goldfish_sync_timeline_signal_internal() -
+ * signal a status change on a sync_timeline
+ * @obj: goldfish_sync_timeline to signal
+ * @inc: num to increment on timeline->value
+ *
+ * A sync implementation should call this any time one of it's fences
+ * has signaled or has an error condition.
+ */
+void goldfish_sync_timeline_signal_internal(struct goldfish_sync_timeline *obj,
+ unsigned int inc);
+
+/**
+ * goldfish_sync_timeline_put_internal() - dec refcount of a sync_timeline
+ * and clean up memory if it was the last ref.
+ * @obj: goldfish_sync_timeline to decref
+ */
+void goldfish_sync_timeline_put_internal(struct goldfish_sync_timeline *obj);
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index f56ea64..6a146f4 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -1219,9 +1219,9 @@ struct readpage_param {
* in PAGE_SIZE (if PAGE_SIZE greater than LU_PAGE_SIZE), and the
* lu_dirpage for this integrated page will be adjusted.
**/
-static int mdc_read_page_remote(void *data, struct page *page0)
+static int mdc_read_page_remote(struct file *data, struct page *page0)
{
- struct readpage_param *rp = data;
+ struct readpage_param *rp = (struct readpage_param *)data;
struct page **page_pool;
struct page *page;
struct lu_dirpage *dp;
diff --git a/drivers/tee/Kconfig b/drivers/tee/Kconfig
new file mode 100644
index 0000000..a6df12d
--- /dev/null
+++ b/drivers/tee/Kconfig
@@ -0,0 +1,19 @@
+# Generic Trusted Execution Environment Configuration
+config TEE
+ tristate "Trusted Execution Environment support"
+ depends on HAVE_ARM_SMCCC || COMPILE_TEST
+ select DMA_SHARED_BUFFER
+ select GENERIC_ALLOCATOR
+ help
+ This implements a generic interface towards a Trusted Execution
+ Environment (TEE).
+
+if TEE
+
+menu "TEE drivers"
+
+source "drivers/tee/optee/Kconfig"
+
+endmenu
+
+endif
diff --git a/drivers/tee/Makefile b/drivers/tee/Makefile
new file mode 100644
index 0000000..7a4e4a1
--- /dev/null
+++ b/drivers/tee/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_TEE) += tee.o
+tee-objs += tee_core.o
+tee-objs += tee_shm.o
+tee-objs += tee_shm_pool.o
+obj-$(CONFIG_OPTEE) += optee/
diff --git a/drivers/tee/optee/Kconfig b/drivers/tee/optee/Kconfig
new file mode 100644
index 0000000..0126de8
--- /dev/null
+++ b/drivers/tee/optee/Kconfig
@@ -0,0 +1,7 @@
+# OP-TEE Trusted Execution Environment Configuration
+config OPTEE
+ tristate "OP-TEE"
+ depends on HAVE_ARM_SMCCC
+ help
+ This implements the OP-TEE Trusted Execution Environment (TEE)
+ driver.
diff --git a/drivers/tee/optee/Makefile b/drivers/tee/optee/Makefile
new file mode 100644
index 0000000..220cf42
--- /dev/null
+++ b/drivers/tee/optee/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_OPTEE) += optee.o
+optee-objs += core.o
+optee-objs += call.o
+optee-objs += rpc.o
+optee-objs += supp.o
+optee-objs += shm_pool.o
diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c
new file mode 100644
index 0000000..a5afbe6
--- /dev/null
+++ b/drivers/tee/optee/call.c
@@ -0,0 +1,662 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/arm-smccc.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+
+struct optee_call_waiter {
+ struct list_head list_node;
+ struct completion c;
+};
+
+static void optee_cq_wait_init(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ /*
+ * We're preparing to make a call to secure world. In case we can't
+ * allocate a thread in secure world we'll end up waiting in
+ * optee_cq_wait_for_completion().
+ *
+ * Normally if there's no contention in secure world the call will
+ * complete and we can cleanup directly with optee_cq_wait_final().
+ */
+ mutex_lock(&cq->mutex);
+
+ /*
+ * We add ourselves to the queue, but we don't wait. This
+ * guarantees that we don't lose a completion if secure world
+ * returns busy and another thread just exited and try to complete
+ * someone.
+ */
+ init_completion(&w->c);
+ list_add_tail(&w->list_node, &cq->waiters);
+
+ mutex_unlock(&cq->mutex);
+}
+
+static void optee_cq_wait_for_completion(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ wait_for_completion(&w->c);
+
+ mutex_lock(&cq->mutex);
+
+ /* Move to end of list to get out of the way for other waiters */
+ list_del(&w->list_node);
+ reinit_completion(&w->c);
+ list_add_tail(&w->list_node, &cq->waiters);
+
+ mutex_unlock(&cq->mutex);
+}
+
+static void optee_cq_complete_one(struct optee_call_queue *cq)
+{
+ struct optee_call_waiter *w;
+
+ list_for_each_entry(w, &cq->waiters, list_node) {
+ if (!completion_done(&w->c)) {
+ complete(&w->c);
+ break;
+ }
+ }
+}
+
+static void optee_cq_wait_final(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ /*
+ * We're done with the call to secure world. The thread in secure
+ * world that was used for this call is now available for some
+ * other task to use.
+ */
+ mutex_lock(&cq->mutex);
+
+ /* Get out of the list */
+ list_del(&w->list_node);
+
+ /* Wake up one eventual waiting task */
+ optee_cq_complete_one(cq);
+
+ /*
+ * If we're completed we've got a completion from another task that
+ * was just done with its call to secure world. Since yet another
+ * thread now is available in secure world wake up another eventual
+ * waiting task.
+ */
+ if (completion_done(&w->c))
+ optee_cq_complete_one(cq);
+
+ mutex_unlock(&cq->mutex);
+}
+
+/* Requires the filpstate mutex to be held */
+static struct optee_session *find_session(struct optee_context_data *ctxdata,
+ u32 session_id)
+{
+ struct optee_session *sess;
+
+ list_for_each_entry(sess, &ctxdata->sess_list, list_node)
+ if (sess->session_id == session_id)
+ return sess;
+
+ return NULL;
+}
+
+/**
+ * optee_do_call_with_arg() - Do an SMC to OP-TEE in secure world
+ * @ctx: calling context
+ * @parg: physical address of message to pass to secure world
+ *
+ * Does and SMC to OP-TEE in secure world and handles eventual resulting
+ * Remote Procedure Calls (RPC) from OP-TEE.
+ *
+ * Returns return code from secure world, 0 is OK
+ */
+u32 optee_do_call_with_arg(struct tee_context *ctx, phys_addr_t parg)
+{
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct optee_call_waiter w;
+ struct optee_rpc_param param = { };
+ struct optee_call_ctx call_ctx = { };
+ u32 ret;
+
+ param.a0 = OPTEE_SMC_CALL_WITH_ARG;
+ reg_pair_from_64(¶m.a1, ¶m.a2, parg);
+ /* Initialize waiter */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ struct arm_smccc_res res;
+
+ optee->invoke_fn(param.a0, param.a1, param.a2, param.a3,
+ param.a4, param.a5, param.a6, param.a7,
+ &res);
+
+ if (res.a0 == OPTEE_SMC_RETURN_ETHREAD_LIMIT) {
+ /*
+ * Out of threads in secure world, wait for a thread
+ * become available.
+ */
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ } else if (OPTEE_SMC_RETURN_IS_RPC(res.a0)) {
+ param.a0 = res.a0;
+ param.a1 = res.a1;
+ param.a2 = res.a2;
+ param.a3 = res.a3;
+ optee_handle_rpc(ctx, ¶m, &call_ctx);
+ } else {
+ ret = res.a0;
+ break;
+ }
+ }
+
+ optee_rpc_finalize_call(&call_ctx);
+ /*
+ * We're done with our thread in secure world, if there's any
+ * thread waiters wake up one.
+ */
+ optee_cq_wait_final(&optee->call_queue, &w);
+
+ return ret;
+}
+
+static struct tee_shm *get_msg_arg(struct tee_context *ctx, size_t num_params,
+ struct optee_msg_arg **msg_arg,
+ phys_addr_t *msg_parg)
+{
+ int rc;
+ struct tee_shm *shm;
+ struct optee_msg_arg *ma;
+
+ shm = tee_shm_alloc(ctx, OPTEE_MSG_GET_ARG_SIZE(num_params),
+ TEE_SHM_MAPPED);
+ if (IS_ERR(shm))
+ return shm;
+
+ ma = tee_shm_get_va(shm, 0);
+ if (IS_ERR(ma)) {
+ rc = PTR_ERR(ma);
+ goto out;
+ }
+
+ rc = tee_shm_get_pa(shm, 0, msg_parg);
+ if (rc)
+ goto out;
+
+ memset(ma, 0, OPTEE_MSG_GET_ARG_SIZE(num_params));
+ ma->num_params = num_params;
+ *msg_arg = ma;
+out:
+ if (rc) {
+ tee_shm_free(shm);
+ return ERR_PTR(rc);
+ }
+
+ return shm;
+}
+
+int optee_open_session(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ int rc;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess = NULL;
+
+ /* +2 for the meta parameters added below */
+ shm = get_msg_arg(ctx, arg->num_params + 2, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_OPEN_SESSION;
+ msg_arg->cancel_id = arg->cancel_id;
+
+ /*
+ * Initialize and add the meta parameters needed when opening a
+ * session.
+ */
+ msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT |
+ OPTEE_MSG_ATTR_META;
+ msg_arg->params[1].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT |
+ OPTEE_MSG_ATTR_META;
+ memcpy(&msg_arg->params[0].u.value, arg->uuid, sizeof(arg->uuid));
+ memcpy(&msg_arg->params[1].u.value, arg->uuid, sizeof(arg->clnt_uuid));
+ msg_arg->params[1].u.value.c = arg->clnt_login;
+
+ rc = optee_to_msg_param(msg_arg->params + 2, arg->num_params, param);
+ if (rc)
+ goto out;
+
+ sess = kzalloc(sizeof(*sess), GFP_KERNEL);
+ if (!sess) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ if (optee_do_call_with_arg(ctx, msg_parg)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ if (msg_arg->ret == TEEC_SUCCESS) {
+ /* A new session has been created, add it to the list. */
+ sess->session_id = msg_arg->session;
+ mutex_lock(&ctxdata->mutex);
+ list_add(&sess->list_node, &ctxdata->sess_list);
+ mutex_unlock(&ctxdata->mutex);
+ } else {
+ kfree(sess);
+ }
+
+ if (optee_from_msg_param(param, arg->num_params, msg_arg->params + 2)) {
+ arg->ret = TEEC_ERROR_COMMUNICATION;
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+ /* Close session again to avoid leakage */
+ optee_close_session(ctx, msg_arg->session);
+ } else {
+ arg->session = msg_arg->session;
+ arg->ret = msg_arg->ret;
+ arg->ret_origin = msg_arg->ret_origin;
+ }
+out:
+ tee_shm_free(shm);
+
+ return rc;
+}
+
+int optee_close_session(struct tee_context *ctx, u32 session)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+
+ /* Check that the session is valid and remove it from the list */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, session);
+ if (sess)
+ list_del(&sess->list_node);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+ kfree(sess);
+
+ shm = get_msg_arg(ctx, 0, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_CLOSE_SESSION;
+ msg_arg->session = session;
+ optee_do_call_with_arg(ctx, msg_parg);
+
+ tee_shm_free(shm);
+ return 0;
+}
+
+int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+ int rc;
+
+ /* Check that the session is valid */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, arg->session);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+
+ shm = get_msg_arg(ctx, arg->num_params, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+ msg_arg->cmd = OPTEE_MSG_CMD_INVOKE_COMMAND;
+ msg_arg->func = arg->func;
+ msg_arg->session = arg->session;
+ msg_arg->cancel_id = arg->cancel_id;
+
+ rc = optee_to_msg_param(msg_arg->params, arg->num_params, param);
+ if (rc)
+ goto out;
+
+ if (optee_do_call_with_arg(ctx, msg_parg)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ if (optee_from_msg_param(param, arg->num_params, msg_arg->params)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ arg->ret = msg_arg->ret;
+ arg->ret_origin = msg_arg->ret_origin;
+out:
+ tee_shm_free(shm);
+ return rc;
+}
+
+int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+
+ /* Check that the session is valid */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, session);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+
+ shm = get_msg_arg(ctx, 0, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_CANCEL;
+ msg_arg->session = session;
+ msg_arg->cancel_id = cancel_id;
+ optee_do_call_with_arg(ctx, msg_parg);
+
+ tee_shm_free(shm);
+ return 0;
+}
+
+/**
+ * optee_enable_shm_cache() - Enables caching of some shared memory allocation
+ * in OP-TEE
+ * @optee: main service struct
+ */
+void optee_enable_shm_cache(struct optee *optee)
+{
+ struct optee_call_waiter w;
+
+ /* We need to retry until secure world isn't busy. */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ struct arm_smccc_res res;
+
+ optee->invoke_fn(OPTEE_SMC_ENABLE_SHM_CACHE, 0, 0, 0, 0, 0, 0,
+ 0, &res);
+ if (res.a0 == OPTEE_SMC_RETURN_OK)
+ break;
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ }
+ optee_cq_wait_final(&optee->call_queue, &w);
+}
+
+/**
+ * optee_disable_shm_cache() - Disables caching of some shared memory allocation
+ * in OP-TEE
+ * @optee: main service struct
+ */
+void optee_disable_shm_cache(struct optee *optee)
+{
+ struct optee_call_waiter w;
+
+ /* We need to retry until secure world isn't busy. */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_disable_shm_cache_result result;
+ } res;
+
+ optee->invoke_fn(OPTEE_SMC_DISABLE_SHM_CACHE, 0, 0, 0, 0, 0, 0,
+ 0, &res.smccc);
+ if (res.result.status == OPTEE_SMC_RETURN_ENOTAVAIL)
+ break; /* All shm's freed */
+ if (res.result.status == OPTEE_SMC_RETURN_OK) {
+ struct tee_shm *shm;
+
+ shm = reg_pair_to_ptr(res.result.shm_upper32,
+ res.result.shm_lower32);
+ tee_shm_free(shm);
+ } else {
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ }
+ }
+ optee_cq_wait_final(&optee->call_queue, &w);
+}
+
+#define PAGELIST_ENTRIES_PER_PAGE \
+ ((OPTEE_MSG_NONCONTIG_PAGE_SIZE / sizeof(u64)) - 1)
+
+/**
+ * optee_fill_pages_list() - write list of user pages to given shared
+ * buffer.
+ *
+ * @dst: page-aligned buffer where list of pages will be stored
+ * @pages: array of pages that represents shared buffer
+ * @num_pages: number of entries in @pages
+ * @page_offset: offset of user buffer from page start
+ *
+ * @dst should be big enough to hold list of user page addresses and
+ * links to the next pages of buffer
+ */
+void optee_fill_pages_list(u64 *dst, struct page **pages, int num_pages,
+ size_t page_offset)
+{
+ int n = 0;
+ phys_addr_t optee_page;
+ /*
+ * Refer to OPTEE_MSG_ATTR_NONCONTIG description in optee_msg.h
+ * for details.
+ */
+ struct {
+ u64 pages_list[PAGELIST_ENTRIES_PER_PAGE];
+ u64 next_page_data;
+ } *pages_data;
+
+ /*
+ * Currently OP-TEE uses 4k page size and it does not looks
+ * like this will change in the future. On other hand, there are
+ * no know ARM architectures with page size < 4k.
+ * Thus the next built assert looks redundant. But the following
+ * code heavily relies on this assumption, so it is better be
+ * safe than sorry.
+ */
+ BUILD_BUG_ON(PAGE_SIZE < OPTEE_MSG_NONCONTIG_PAGE_SIZE);
+
+ pages_data = (void *)dst;
+ /*
+ * If linux page is bigger than 4k, and user buffer offset is
+ * larger than 4k/8k/12k/etc this will skip first 4k pages,
+ * because they bear no value data for OP-TEE.
+ */
+ optee_page = page_to_phys(*pages) +
+ round_down(page_offset, OPTEE_MSG_NONCONTIG_PAGE_SIZE);
+
+ while (true) {
+ pages_data->pages_list[n++] = optee_page;
+
+ if (n == PAGELIST_ENTRIES_PER_PAGE) {
+ pages_data->next_page_data =
+ virt_to_phys(pages_data + 1);
+ pages_data++;
+ n = 0;
+ }
+
+ optee_page += OPTEE_MSG_NONCONTIG_PAGE_SIZE;
+ if (!(optee_page & ~PAGE_MASK)) {
+ if (!--num_pages)
+ break;
+ pages++;
+ optee_page = page_to_phys(*pages);
+ }
+ }
+}
+
+/*
+ * The final entry in each pagelist page is a pointer to the next
+ * pagelist page.
+ */
+static size_t get_pages_list_size(size_t num_entries)
+{
+ int pages = DIV_ROUND_UP(num_entries, PAGELIST_ENTRIES_PER_PAGE);
+
+ return pages * OPTEE_MSG_NONCONTIG_PAGE_SIZE;
+}
+
+u64 *optee_allocate_pages_list(size_t num_entries)
+{
+ return alloc_pages_exact(get_pages_list_size(num_entries), GFP_KERNEL);
+}
+
+void optee_free_pages_list(void *list, size_t num_entries)
+{
+ free_pages_exact(list, get_pages_list_size(num_entries));
+}
+
+static bool is_normal_memory(pgprot_t p)
+{
+#if defined(CONFIG_ARM)
+ return (pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC;
+#elif defined(CONFIG_ARM64)
+ return (pgprot_val(p) & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL);
+#else
+#error "Unuspported architecture"
+#endif
+}
+
+static int __check_mem_type(struct vm_area_struct *vma, unsigned long end)
+{
+ while (vma && is_normal_memory(vma->vm_page_prot)) {
+ if (vma->vm_end >= end)
+ return 0;
+ vma = vma->vm_next;
+ }
+
+ return -EINVAL;
+}
+
+static int check_mem_type(unsigned long start, size_t num_pages)
+{
+ struct mm_struct *mm = current->mm;
+ int rc;
+
+ down_read(&mm->mmap_sem);
+ rc = __check_mem_type(find_vma(mm, start),
+ start + num_pages * PAGE_SIZE);
+ up_read(&mm->mmap_sem);
+
+ return rc;
+}
+
+int optee_shm_register(struct tee_context *ctx, struct tee_shm *shm,
+ struct page **pages, size_t num_pages,
+ unsigned long start)
+{
+ struct tee_shm *shm_arg = NULL;
+ struct optee_msg_arg *msg_arg;
+ u64 *pages_list;
+ phys_addr_t msg_parg;
+ int rc;
+
+ if (!num_pages)
+ return -EINVAL;
+
+ rc = check_mem_type(start, num_pages);
+ if (rc)
+ return rc;
+
+ pages_list = optee_allocate_pages_list(num_pages);
+ if (!pages_list)
+ return -ENOMEM;
+
+ shm_arg = get_msg_arg(ctx, 1, &msg_arg, &msg_parg);
+ if (IS_ERR(shm_arg)) {
+ rc = PTR_ERR(shm_arg);
+ goto out;
+ }
+
+ optee_fill_pages_list(pages_list, pages, num_pages,
+ tee_shm_get_page_offset(shm));
+
+ msg_arg->cmd = OPTEE_MSG_CMD_REGISTER_SHM;
+ msg_arg->params->attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT |
+ OPTEE_MSG_ATTR_NONCONTIG;
+ msg_arg->params->u.tmem.shm_ref = (unsigned long)shm;
+ msg_arg->params->u.tmem.size = tee_shm_get_size(shm);
+ /*
+ * In the least bits of msg_arg->params->u.tmem.buf_ptr we
+ * store buffer offset from 4k page, as described in OP-TEE ABI.
+ */
+ msg_arg->params->u.tmem.buf_ptr = virt_to_phys(pages_list) |
+ (tee_shm_get_page_offset(shm) & (OPTEE_MSG_NONCONTIG_PAGE_SIZE - 1));
+
+ if (optee_do_call_with_arg(ctx, msg_parg) ||
+ msg_arg->ret != TEEC_SUCCESS)
+ rc = -EINVAL;
+
+ tee_shm_free(shm_arg);
+out:
+ optee_free_pages_list(pages_list, num_pages);
+ return rc;
+}
+
+int optee_shm_unregister(struct tee_context *ctx, struct tee_shm *shm)
+{
+ struct tee_shm *shm_arg;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ int rc = 0;
+
+ shm_arg = get_msg_arg(ctx, 1, &msg_arg, &msg_parg);
+ if (IS_ERR(shm_arg))
+ return PTR_ERR(shm_arg);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_UNREGISTER_SHM;
+
+ msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_RMEM_INPUT;
+ msg_arg->params[0].u.rmem.shm_ref = (unsigned long)shm;
+
+ if (optee_do_call_with_arg(ctx, msg_parg) ||
+ msg_arg->ret != TEEC_SUCCESS)
+ rc = -EINVAL;
+ tee_shm_free(shm_arg);
+ return rc;
+}
+
+int optee_shm_register_supp(struct tee_context *ctx, struct tee_shm *shm,
+ struct page **pages, size_t num_pages,
+ unsigned long start)
+{
+ /*
+ * We don't want to register supplicant memory in OP-TEE.
+ * Instead information about it will be passed in RPC code.
+ */
+ return check_mem_type(start, num_pages);
+}
+
+int optee_shm_unregister_supp(struct tee_context *ctx, struct tee_shm *shm)
+{
+ return 0;
+}
diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
new file mode 100644
index 0000000..e9843c5
--- /dev/null
+++ b/drivers/tee/optee/core.c
@@ -0,0 +1,705 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+#include "shm_pool.h"
+
+#define DRIVER_NAME "optee"
+
+#define OPTEE_SHM_NUM_PRIV_PAGES 1
+
+/**
+ * optee_from_msg_param() - convert from OPTEE_MSG parameters to
+ * struct tee_param
+ * @params: subsystem internal parameter representation
+ * @num_params: number of elements in the parameter arrays
+ * @msg_params: OPTEE_MSG parameters
+ * Returns 0 on success or <0 on failure
+ */
+int optee_from_msg_param(struct tee_param *params, size_t num_params,
+ const struct optee_msg_param *msg_params)
+{
+ int rc;
+ size_t n;
+ struct tee_shm *shm;
+ phys_addr_t pa;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_param *p = params + n;
+ const struct optee_msg_param *mp = msg_params + n;
+ u32 attr = mp->attr & OPTEE_MSG_ATTR_TYPE_MASK;
+
+ switch (attr) {
+ case OPTEE_MSG_ATTR_TYPE_NONE:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+ memset(&p->u, 0, sizeof(p->u));
+ break;
+ case OPTEE_MSG_ATTR_TYPE_VALUE_INPUT:
+ case OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT:
+ case OPTEE_MSG_ATTR_TYPE_VALUE_INOUT:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT +
+ attr - OPTEE_MSG_ATTR_TYPE_VALUE_INPUT;
+ p->u.value.a = mp->u.value.a;
+ p->u.value.b = mp->u.value.b;
+ p->u.value.c = mp->u.value.c;
+ break;
+ case OPTEE_MSG_ATTR_TYPE_TMEM_INPUT:
+ case OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT:
+ case OPTEE_MSG_ATTR_TYPE_TMEM_INOUT:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT +
+ attr - OPTEE_MSG_ATTR_TYPE_TMEM_INPUT;
+ p->u.memref.size = mp->u.tmem.size;
+ shm = (struct tee_shm *)(unsigned long)
+ mp->u.tmem.shm_ref;
+ if (!shm) {
+ p->u.memref.shm_offs = 0;
+ p->u.memref.shm = NULL;
+ break;
+ }
+ rc = tee_shm_get_pa(shm, 0, &pa);
+ if (rc)
+ return rc;
+ p->u.memref.shm_offs = mp->u.tmem.buf_ptr - pa;
+ p->u.memref.shm = shm;
+
+ /* Check that the memref is covered by the shm object */
+ if (p->u.memref.size) {
+ size_t o = p->u.memref.shm_offs +
+ p->u.memref.size - 1;
+
+ rc = tee_shm_get_pa(shm, o, NULL);
+ if (rc)
+ return rc;
+ }
+ break;
+ case OPTEE_MSG_ATTR_TYPE_RMEM_INPUT:
+ case OPTEE_MSG_ATTR_TYPE_RMEM_OUTPUT:
+ case OPTEE_MSG_ATTR_TYPE_RMEM_INOUT:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT +
+ attr - OPTEE_MSG_ATTR_TYPE_RMEM_INPUT;
+ p->u.memref.size = mp->u.rmem.size;
+ shm = (struct tee_shm *)(unsigned long)
+ mp->u.rmem.shm_ref;
+
+ if (!shm) {
+ p->u.memref.shm_offs = 0;
+ p->u.memref.shm = NULL;
+ break;
+ }
+ p->u.memref.shm_offs = mp->u.rmem.offs;
+ p->u.memref.shm = shm;
+
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static int to_msg_param_tmp_mem(struct optee_msg_param *mp,
+ const struct tee_param *p)
+{
+ int rc;
+ phys_addr_t pa;
+
+ mp->attr = OPTEE_MSG_ATTR_TYPE_TMEM_INPUT + p->attr -
+ TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+
+ mp->u.tmem.shm_ref = (unsigned long)p->u.memref.shm;
+ mp->u.tmem.size = p->u.memref.size;
+
+ if (!p->u.memref.shm) {
+ mp->u.tmem.buf_ptr = 0;
+ return 0;
+ }
+
+ rc = tee_shm_get_pa(p->u.memref.shm, p->u.memref.shm_offs, &pa);
+ if (rc)
+ return rc;
+
+ mp->u.tmem.buf_ptr = pa;
+ mp->attr |= OPTEE_MSG_ATTR_CACHE_PREDEFINED <<
+ OPTEE_MSG_ATTR_CACHE_SHIFT;
+
+ return 0;
+}
+
+static int to_msg_param_reg_mem(struct optee_msg_param *mp,
+ const struct tee_param *p)
+{
+ mp->attr = OPTEE_MSG_ATTR_TYPE_RMEM_INPUT + p->attr -
+ TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+
+ mp->u.rmem.shm_ref = (unsigned long)p->u.memref.shm;
+ mp->u.rmem.size = p->u.memref.size;
+ mp->u.rmem.offs = p->u.memref.shm_offs;
+ return 0;
+}
+
+/**
+ * optee_to_msg_param() - convert from struct tee_params to OPTEE_MSG parameters
+ * @msg_params: OPTEE_MSG parameters
+ * @num_params: number of elements in the parameter arrays
+ * @params: subsystem itnernal parameter representation
+ * Returns 0 on success or <0 on failure
+ */
+int optee_to_msg_param(struct optee_msg_param *msg_params, size_t num_params,
+ const struct tee_param *params)
+{
+ int rc;
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ const struct tee_param *p = params + n;
+ struct optee_msg_param *mp = msg_params + n;
+
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_NONE:
+ mp->attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+ memset(&mp->u, 0, sizeof(mp->u));
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ mp->attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT + p->attr -
+ TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT;
+ mp->u.value.a = p->u.value.a;
+ mp->u.value.b = p->u.value.b;
+ mp->u.value.c = p->u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ if (tee_shm_is_registered(p->u.memref.shm))
+ rc = to_msg_param_reg_mem(mp, p);
+ else
+ rc = to_msg_param_tmp_mem(mp, p);
+ if (rc)
+ return rc;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static void optee_get_version(struct tee_device *teedev,
+ struct tee_ioctl_version_data *vers)
+{
+ struct tee_ioctl_version_data v = {
+ .impl_id = TEE_IMPL_ID_OPTEE,
+ .impl_caps = TEE_OPTEE_CAP_TZ,
+ .gen_caps = TEE_GEN_CAP_GP,
+ };
+ struct optee *optee = tee_get_drvdata(teedev);
+
+ if (optee->sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM)
+ v.gen_caps |= TEE_GEN_CAP_REG_MEM;
+ *vers = v;
+}
+
+static int optee_open(struct tee_context *ctx)
+{
+ struct optee_context_data *ctxdata;
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+
+ ctxdata = kzalloc(sizeof(*ctxdata), GFP_KERNEL);
+ if (!ctxdata)
+ return -ENOMEM;
+
+ if (teedev == optee->supp_teedev) {
+ bool busy = true;
+
+ mutex_lock(&optee->supp.mutex);
+ if (!optee->supp.ctx) {
+ busy = false;
+ optee->supp.ctx = ctx;
+ }
+ mutex_unlock(&optee->supp.mutex);
+ if (busy) {
+ kfree(ctxdata);
+ return -EBUSY;
+ }
+ }
+
+ mutex_init(&ctxdata->mutex);
+ INIT_LIST_HEAD(&ctxdata->sess_list);
+
+ ctx->data = ctxdata;
+ return 0;
+}
+
+static void optee_release(struct tee_context *ctx)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct tee_shm *shm;
+ struct optee_msg_arg *arg = NULL;
+ phys_addr_t parg;
+ struct optee_session *sess;
+ struct optee_session *sess_tmp;
+
+ if (!ctxdata)
+ return;
+
+ shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), TEE_SHM_MAPPED);
+ if (!IS_ERR(shm)) {
+ arg = tee_shm_get_va(shm, 0);
+ /*
+ * If va2pa fails for some reason, we can't call into
+ * secure world, only free the memory. Secure OS will leak
+ * sessions and finally refuse more sessions, but we will
+ * at least let normal world reclaim its memory.
+ */
+ if (!IS_ERR(arg))
+ if (tee_shm_va2pa(shm, arg, &parg))
+ arg = NULL; /* prevent usage of parg below */
+ }
+
+ list_for_each_entry_safe(sess, sess_tmp, &ctxdata->sess_list,
+ list_node) {
+ list_del(&sess->list_node);
+ if (!IS_ERR_OR_NULL(arg)) {
+ memset(arg, 0, sizeof(*arg));
+ arg->cmd = OPTEE_MSG_CMD_CLOSE_SESSION;
+ arg->session = sess->session_id;
+ optee_do_call_with_arg(ctx, parg);
+ }
+ kfree(sess);
+ }
+ kfree(ctxdata);
+
+ if (!IS_ERR(shm))
+ tee_shm_free(shm);
+
+ ctx->data = NULL;
+
+ if (teedev == optee->supp_teedev)
+ optee_supp_release(&optee->supp);
+}
+
+static const struct tee_driver_ops optee_ops = {
+ .get_version = optee_get_version,
+ .open = optee_open,
+ .release = optee_release,
+ .open_session = optee_open_session,
+ .close_session = optee_close_session,
+ .invoke_func = optee_invoke_func,
+ .cancel_req = optee_cancel_req,
+ .shm_register = optee_shm_register,
+ .shm_unregister = optee_shm_unregister,
+};
+
+static const struct tee_desc optee_desc = {
+ .name = DRIVER_NAME "-clnt",
+ .ops = &optee_ops,
+ .owner = THIS_MODULE,
+};
+
+static const struct tee_driver_ops optee_supp_ops = {
+ .get_version = optee_get_version,
+ .open = optee_open,
+ .release = optee_release,
+ .supp_recv = optee_supp_recv,
+ .supp_send = optee_supp_send,
+ .shm_register = optee_shm_register_supp,
+ .shm_unregister = optee_shm_unregister_supp,
+};
+
+static const struct tee_desc optee_supp_desc = {
+ .name = DRIVER_NAME "-supp",
+ .ops = &optee_supp_ops,
+ .owner = THIS_MODULE,
+ .flags = TEE_DESC_PRIVILEGED,
+};
+
+static bool optee_msg_api_uid_is_optee_api(optee_invoke_fn *invoke_fn)
+{
+ struct arm_smccc_res res;
+
+ invoke_fn(OPTEE_SMC_CALLS_UID, 0, 0, 0, 0, 0, 0, 0, &res);
+
+ if (res.a0 == OPTEE_MSG_UID_0 && res.a1 == OPTEE_MSG_UID_1 &&
+ res.a2 == OPTEE_MSG_UID_2 && res.a3 == OPTEE_MSG_UID_3)
+ return true;
+ return false;
+}
+
+static bool optee_msg_api_revision_is_compatible(optee_invoke_fn *invoke_fn)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_calls_revision_result result;
+ } res;
+
+ invoke_fn(OPTEE_SMC_CALLS_REVISION, 0, 0, 0, 0, 0, 0, 0, &res.smccc);
+
+ if (res.result.major == OPTEE_MSG_REVISION_MAJOR &&
+ (int)res.result.minor >= OPTEE_MSG_REVISION_MINOR)
+ return true;
+ return false;
+}
+
+static bool optee_msg_exchange_capabilities(optee_invoke_fn *invoke_fn,
+ u32 *sec_caps)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_exchange_capabilities_result result;
+ } res;
+ u32 a1 = 0;
+
+ /*
+ * TODO This isn't enough to tell if it's UP system (from kernel
+ * point of view) or not, is_smp() returns the the information
+ * needed, but can't be called directly from here.
+ */
+ if (!IS_ENABLED(CONFIG_SMP) || nr_cpu_ids == 1)
+ a1 |= OPTEE_SMC_NSEC_CAP_UNIPROCESSOR;
+
+ invoke_fn(OPTEE_SMC_EXCHANGE_CAPABILITIES, a1, 0, 0, 0, 0, 0, 0,
+ &res.smccc);
+
+ if (res.result.status != OPTEE_SMC_RETURN_OK)
+ return false;
+
+ *sec_caps = res.result.capabilities;
+ return true;
+}
+
+static struct tee_shm_pool *
+optee_config_shm_memremap(optee_invoke_fn *invoke_fn, void **memremaped_shm,
+ u32 sec_caps)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_get_shm_config_result result;
+ } res;
+ unsigned long vaddr;
+ phys_addr_t paddr;
+ size_t size;
+ phys_addr_t begin;
+ phys_addr_t end;
+ void *va;
+ struct tee_shm_pool_mgr *priv_mgr;
+ struct tee_shm_pool_mgr *dmabuf_mgr;
+ void *rc;
+
+ invoke_fn(OPTEE_SMC_GET_SHM_CONFIG, 0, 0, 0, 0, 0, 0, 0, &res.smccc);
+ if (res.result.status != OPTEE_SMC_RETURN_OK) {
+ pr_info("shm service not available\n");
+ return ERR_PTR(-ENOENT);
+ }
+
+ if (res.result.settings != OPTEE_SMC_SHM_CACHED) {
+ pr_err("only normal cached shared memory supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ begin = roundup(res.result.start, PAGE_SIZE);
+ end = rounddown(res.result.start + res.result.size, PAGE_SIZE);
+ paddr = begin;
+ size = end - begin;
+
+ if (size < 2 * OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE) {
+ pr_err("too small shared memory area\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ va = memremap(paddr, size, MEMREMAP_WB);
+ if (!va) {
+ pr_err("shared memory ioremap failed\n");
+ return ERR_PTR(-EINVAL);
+ }
+ vaddr = (unsigned long)va;
+
+ /*
+ * If OP-TEE can work with unregistered SHM, we will use own pool
+ * for private shm
+ */
+ if (sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM) {
+ rc = optee_shm_pool_alloc_pages();
+ if (IS_ERR(rc))
+ goto err_memunmap;
+ priv_mgr = rc;
+ } else {
+ const size_t sz = OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE;
+
+ rc = tee_shm_pool_mgr_alloc_res_mem(vaddr, paddr, sz,
+ 3 /* 8 bytes aligned */);
+ if (IS_ERR(rc))
+ goto err_memunmap;
+ priv_mgr = rc;
+
+ vaddr += sz;
+ paddr += sz;
+ size -= sz;
+ }
+
+ rc = tee_shm_pool_mgr_alloc_res_mem(vaddr, paddr, size, PAGE_SHIFT);
+ if (IS_ERR(rc))
+ goto err_free_priv_mgr;
+ dmabuf_mgr = rc;
+
+ rc = tee_shm_pool_alloc(priv_mgr, dmabuf_mgr);
+ if (IS_ERR(rc))
+ goto err_free_dmabuf_mgr;
+
+ *memremaped_shm = va;
+
+ return rc;
+
+err_free_dmabuf_mgr:
+ tee_shm_pool_mgr_destroy(dmabuf_mgr);
+err_free_priv_mgr:
+ tee_shm_pool_mgr_destroy(priv_mgr);
+err_memunmap:
+ memunmap(va);
+ return rc;
+}
+
+/* Simple wrapper functions to be able to use a function pointer */
+static void optee_smccc_smc(unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ unsigned long a4, unsigned long a5,
+ unsigned long a6, unsigned long a7,
+ struct arm_smccc_res *res)
+{
+ arm_smccc_smc(a0, a1, a2, a3, a4, a5, a6, a7, res);
+}
+
+static void optee_smccc_hvc(unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ unsigned long a4, unsigned long a5,
+ unsigned long a6, unsigned long a7,
+ struct arm_smccc_res *res)
+{
+ arm_smccc_hvc(a0, a1, a2, a3, a4, a5, a6, a7, res);
+}
+
+static optee_invoke_fn *get_invoke_func(struct device_node *np)
+{
+ const char *method;
+
+ pr_info("probing for conduit method from DT.\n");
+
+ if (of_property_read_string(np, "method", &method)) {
+ pr_warn("missing \"method\" property\n");
+ return ERR_PTR(-ENXIO);
+ }
+
+ if (!strcmp("hvc", method))
+ return optee_smccc_hvc;
+ else if (!strcmp("smc", method))
+ return optee_smccc_smc;
+
+ pr_warn("invalid \"method\" property: %s\n", method);
+ return ERR_PTR(-EINVAL);
+}
+
+static struct optee *optee_probe(struct device_node *np)
+{
+ optee_invoke_fn *invoke_fn;
+ struct tee_shm_pool *pool;
+ struct optee *optee = NULL;
+ void *memremaped_shm = NULL;
+ struct tee_device *teedev;
+ u32 sec_caps;
+ int rc;
+
+ invoke_fn = get_invoke_func(np);
+ if (IS_ERR(invoke_fn))
+ return (void *)invoke_fn;
+
+ if (!optee_msg_api_uid_is_optee_api(invoke_fn)) {
+ pr_warn("api uid mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!optee_msg_api_revision_is_compatible(invoke_fn)) {
+ pr_warn("api revision mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!optee_msg_exchange_capabilities(invoke_fn, &sec_caps)) {
+ pr_warn("capabilities mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ /*
+ * We have no other option for shared memory, if secure world
+ * doesn't have any reserved memory we can use we can't continue.
+ */
+ if (!(sec_caps & OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM))
+ return ERR_PTR(-EINVAL);
+
+ pool = optee_config_shm_memremap(invoke_fn, &memremaped_shm, sec_caps);
+ if (IS_ERR(pool))
+ return (void *)pool;
+
+ optee = kzalloc(sizeof(*optee), GFP_KERNEL);
+ if (!optee) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ optee->invoke_fn = invoke_fn;
+ optee->sec_caps = sec_caps;
+
+ teedev = tee_device_alloc(&optee_desc, NULL, pool, optee);
+ if (IS_ERR(teedev)) {
+ rc = PTR_ERR(teedev);
+ goto err;
+ }
+ optee->teedev = teedev;
+
+ teedev = tee_device_alloc(&optee_supp_desc, NULL, pool, optee);
+ if (IS_ERR(teedev)) {
+ rc = PTR_ERR(teedev);
+ goto err;
+ }
+ optee->supp_teedev = teedev;
+
+ rc = tee_device_register(optee->teedev);
+ if (rc)
+ goto err;
+
+ rc = tee_device_register(optee->supp_teedev);
+ if (rc)
+ goto err;
+
+ mutex_init(&optee->call_queue.mutex);
+ INIT_LIST_HEAD(&optee->call_queue.waiters);
+ optee_wait_queue_init(&optee->wait_queue);
+ optee_supp_init(&optee->supp);
+ optee->memremaped_shm = memremaped_shm;
+ optee->pool = pool;
+
+ optee_enable_shm_cache(optee);
+
+ pr_info("initialized driver\n");
+ return optee;
+err:
+ if (optee) {
+ /*
+ * tee_device_unregister() is safe to call even if the
+ * devices hasn't been registered with
+ * tee_device_register() yet.
+ */
+ tee_device_unregister(optee->supp_teedev);
+ tee_device_unregister(optee->teedev);
+ kfree(optee);
+ }
+ if (pool)
+ tee_shm_pool_free(pool);
+ if (memremaped_shm)
+ memunmap(memremaped_shm);
+ return ERR_PTR(rc);
+}
+
+static void optee_remove(struct optee *optee)
+{
+ /*
+ * Ask OP-TEE to free all cached shared memory objects to decrease
+ * reference counters and also avoid wild pointers in secure world
+ * into the old shared memory range.
+ */
+ optee_disable_shm_cache(optee);
+
+ /*
+ * The two devices has to be unregistered before we can free the
+ * other resources.
+ */
+ tee_device_unregister(optee->supp_teedev);
+ tee_device_unregister(optee->teedev);
+
+ tee_shm_pool_free(optee->pool);
+ if (optee->memremaped_shm)
+ memunmap(optee->memremaped_shm);
+ optee_wait_queue_exit(&optee->wait_queue);
+ optee_supp_uninit(&optee->supp);
+ mutex_destroy(&optee->call_queue.mutex);
+
+ kfree(optee);
+}
+
+static const struct of_device_id optee_match[] = {
+ { .compatible = "linaro,optee-tz" },
+ {},
+};
+
+static struct optee *optee_svc;
+
+static int __init optee_driver_init(void)
+{
+ struct device_node *fw_np;
+ struct device_node *np;
+ struct optee *optee;
+
+ /* Node is supposed to be below /firmware */
+ fw_np = of_find_node_by_name(NULL, "firmware");
+ if (!fw_np)
+ return -ENODEV;
+
+ np = of_find_matching_node(fw_np, optee_match);
+ if (!np)
+ return -ENODEV;
+
+ optee = optee_probe(np);
+ of_node_put(np);
+
+ if (IS_ERR(optee))
+ return PTR_ERR(optee);
+
+ optee_svc = optee;
+
+ return 0;
+}
+module_init(optee_driver_init);
+
+static void __exit optee_driver_exit(void)
+{
+ struct optee *optee = optee_svc;
+
+ optee_svc = NULL;
+ if (optee)
+ optee_remove(optee);
+}
+module_exit(optee_driver_exit);
+
+MODULE_AUTHOR("Linaro");
+MODULE_DESCRIPTION("OP-TEE driver");
+MODULE_SUPPORTED_DEVICE("");
+MODULE_VERSION("1.0");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/tee/optee/optee_msg.h b/drivers/tee/optee/optee_msg.h
new file mode 100644
index 0000000..3050490
--- /dev/null
+++ b/drivers/tee/optee/optee_msg.h
@@ -0,0 +1,444 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _OPTEE_MSG_H
+#define _OPTEE_MSG_H
+
+#include <linux/bitops.h>
+#include <linux/types.h>
+
+/*
+ * This file defines the OP-TEE message protocol used to communicate
+ * with an instance of OP-TEE running in secure world.
+ *
+ * This file is divided into three sections.
+ * 1. Formatting of messages.
+ * 2. Requests from normal world
+ * 3. Requests from secure world, Remote Procedure Call (RPC), handled by
+ * tee-supplicant.
+ */
+
+/*****************************************************************************
+ * Part 1 - formatting of messages
+ *****************************************************************************/
+
+#define OPTEE_MSG_ATTR_TYPE_NONE 0x0
+#define OPTEE_MSG_ATTR_TYPE_VALUE_INPUT 0x1
+#define OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT 0x2
+#define OPTEE_MSG_ATTR_TYPE_VALUE_INOUT 0x3
+#define OPTEE_MSG_ATTR_TYPE_RMEM_INPUT 0x5
+#define OPTEE_MSG_ATTR_TYPE_RMEM_OUTPUT 0x6
+#define OPTEE_MSG_ATTR_TYPE_RMEM_INOUT 0x7
+#define OPTEE_MSG_ATTR_TYPE_TMEM_INPUT 0x9
+#define OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT 0xa
+#define OPTEE_MSG_ATTR_TYPE_TMEM_INOUT 0xb
+
+#define OPTEE_MSG_ATTR_TYPE_MASK GENMASK(7, 0)
+
+/*
+ * Meta parameter to be absorbed by the Secure OS and not passed
+ * to the Trusted Application.
+ *
+ * Currently only used with OPTEE_MSG_CMD_OPEN_SESSION.
+ */
+#define OPTEE_MSG_ATTR_META BIT(8)
+
+/*
+ * Pointer to a list of pages used to register user-defined SHM buffer.
+ * Used with OPTEE_MSG_ATTR_TYPE_TMEM_*.
+ * buf_ptr should point to the beginning of the buffer. Buffer will contain
+ * list of page addresses. OP-TEE core can reconstruct contiguous buffer from
+ * that page addresses list. Page addresses are stored as 64 bit values.
+ * Last entry on a page should point to the next page of buffer.
+ * Every entry in buffer should point to a 4k page beginning (12 least
+ * significant bits must be equal to zero).
+ *
+ * 12 least significant bints of optee_msg_param.u.tmem.buf_ptr should hold page
+ * offset of the user buffer.
+ *
+ * So, entries should be placed like members of this structure:
+ *
+ * struct page_data {
+ * uint64_t pages_array[OPTEE_MSG_NONCONTIG_PAGE_SIZE/sizeof(uint64_t) - 1];
+ * uint64_t next_page_data;
+ * };
+ *
+ * Structure is designed to exactly fit into the page size
+ * OPTEE_MSG_NONCONTIG_PAGE_SIZE which is a standard 4KB page.
+ *
+ * The size of 4KB is chosen because this is the smallest page size for ARM
+ * architectures. If REE uses larger pages, it should divide them to 4KB ones.
+ */
+#define OPTEE_MSG_ATTR_NONCONTIG BIT(9)
+
+/*
+ * Memory attributes for caching passed with temp memrefs. The actual value
+ * used is defined outside the message protocol with the exception of
+ * OPTEE_MSG_ATTR_CACHE_PREDEFINED which means the attributes already
+ * defined for the memory range should be used. If optee_smc.h is used as
+ * bearer of this protocol OPTEE_SMC_SHM_* is used for values.
+ */
+#define OPTEE_MSG_ATTR_CACHE_SHIFT 16
+#define OPTEE_MSG_ATTR_CACHE_MASK GENMASK(2, 0)
+#define OPTEE_MSG_ATTR_CACHE_PREDEFINED 0
+
+/*
+ * Same values as TEE_LOGIN_* from TEE Internal API
+ */
+#define OPTEE_MSG_LOGIN_PUBLIC 0x00000000
+#define OPTEE_MSG_LOGIN_USER 0x00000001
+#define OPTEE_MSG_LOGIN_GROUP 0x00000002
+#define OPTEE_MSG_LOGIN_APPLICATION 0x00000004
+#define OPTEE_MSG_LOGIN_APPLICATION_USER 0x00000005
+#define OPTEE_MSG_LOGIN_APPLICATION_GROUP 0x00000006
+
+/*
+ * Page size used in non-contiguous buffer entries
+ */
+#define OPTEE_MSG_NONCONTIG_PAGE_SIZE 4096
+
+/**
+ * struct optee_msg_param_tmem - temporary memory reference parameter
+ * @buf_ptr: Address of the buffer
+ * @size: Size of the buffer
+ * @shm_ref: Temporary shared memory reference, pointer to a struct tee_shm
+ *
+ * Secure and normal world communicates pointers as physical address
+ * instead of the virtual address. This is because secure and normal world
+ * have completely independent memory mapping. Normal world can even have a
+ * hypervisor which need to translate the guest physical address (AKA IPA
+ * in ARM documentation) to a real physical address before passing the
+ * structure to secure world.
+ */
+struct optee_msg_param_tmem {
+ u64 buf_ptr;
+ u64 size;
+ u64 shm_ref;
+};
+
+/**
+ * struct optee_msg_param_rmem - registered memory reference parameter
+ * @offs: Offset into shared memory reference
+ * @size: Size of the buffer
+ * @shm_ref: Shared memory reference, pointer to a struct tee_shm
+ */
+struct optee_msg_param_rmem {
+ u64 offs;
+ u64 size;
+ u64 shm_ref;
+};
+
+/**
+ * struct optee_msg_param_value - opaque value parameter
+ *
+ * Value parameters are passed unchecked between normal and secure world.
+ */
+struct optee_msg_param_value {
+ u64 a;
+ u64 b;
+ u64 c;
+};
+
+/**
+ * struct optee_msg_param - parameter used together with struct optee_msg_arg
+ * @attr: attributes
+ * @tmem: parameter by temporary memory reference
+ * @rmem: parameter by registered memory reference
+ * @value: parameter by opaque value
+ *
+ * @attr & OPTEE_MSG_ATTR_TYPE_MASK indicates if tmem, rmem or value is used in
+ * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value,
+ * OPTEE_MSG_ATTR_TYPE_TMEM_* indicates @tmem and
+ * OPTEE_MSG_ATTR_TYPE_RMEM_* indicates @rmem,
+ * OPTEE_MSG_ATTR_TYPE_NONE indicates that none of the members are used.
+ */
+struct optee_msg_param {
+ u64 attr;
+ union {
+ struct optee_msg_param_tmem tmem;
+ struct optee_msg_param_rmem rmem;
+ struct optee_msg_param_value value;
+ } u;
+};
+
+/**
+ * struct optee_msg_arg - call argument
+ * @cmd: Command, one of OPTEE_MSG_CMD_* or OPTEE_MSG_RPC_CMD_*
+ * @func: Trusted Application function, specific to the Trusted Application,
+ * used if cmd == OPTEE_MSG_CMD_INVOKE_COMMAND
+ * @session: In parameter for all OPTEE_MSG_CMD_* except
+ * OPTEE_MSG_CMD_OPEN_SESSION where it's an output parameter instead
+ * @cancel_id: Cancellation id, a unique value to identify this request
+ * @ret: return value
+ * @ret_origin: origin of the return value
+ * @num_params: number of parameters supplied to the OS Command
+ * @params: the parameters supplied to the OS Command
+ *
+ * All normal calls to Trusted OS uses this struct. If cmd requires further
+ * information than what these field holds it can be passed as a parameter
+ * tagged as meta (setting the OPTEE_MSG_ATTR_META bit in corresponding
+ * attrs field). All parameters tagged as meta has to come first.
+ *
+ * Temp memref parameters can be fragmented if supported by the Trusted OS
+ * (when optee_smc.h is bearer of this protocol this is indicated with
+ * OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM). If a logical memref parameter is
+ * fragmented then has all but the last fragment the
+ * OPTEE_MSG_ATTR_FRAGMENT bit set in attrs. Even if a memref is fragmented
+ * it will still be presented as a single logical memref to the Trusted
+ * Application.
+ */
+struct optee_msg_arg {
+ u32 cmd;
+ u32 func;
+ u32 session;
+ u32 cancel_id;
+ u32 pad;
+ u32 ret;
+ u32 ret_origin;
+ u32 num_params;
+
+ /* num_params tells the actual number of element in params */
+ struct optee_msg_param params[0];
+};
+
+/**
+ * OPTEE_MSG_GET_ARG_SIZE - return size of struct optee_msg_arg
+ *
+ * @num_params: Number of parameters embedded in the struct optee_msg_arg
+ *
+ * Returns the size of the struct optee_msg_arg together with the number
+ * of embedded parameters.
+ */
+#define OPTEE_MSG_GET_ARG_SIZE(num_params) \
+ (sizeof(struct optee_msg_arg) + \
+ sizeof(struct optee_msg_param) * (num_params))
+
+/*****************************************************************************
+ * Part 2 - requests from normal world
+ *****************************************************************************/
+
+/*
+ * Return the following UID if using API specified in this file without
+ * further extensions:
+ * 384fb3e0-e7f8-11e3-af63-0002a5d5c51b.
+ * Represented in 4 32-bit words in OPTEE_MSG_UID_0, OPTEE_MSG_UID_1,
+ * OPTEE_MSG_UID_2, OPTEE_MSG_UID_3.
+ */
+#define OPTEE_MSG_UID_0 0x384fb3e0
+#define OPTEE_MSG_UID_1 0xe7f811e3
+#define OPTEE_MSG_UID_2 0xaf630002
+#define OPTEE_MSG_UID_3 0xa5d5c51b
+#define OPTEE_MSG_FUNCID_CALLS_UID 0xFF01
+
+/*
+ * Returns 2.0 if using API specified in this file without further
+ * extensions. Represented in 2 32-bit words in OPTEE_MSG_REVISION_MAJOR
+ * and OPTEE_MSG_REVISION_MINOR
+ */
+#define OPTEE_MSG_REVISION_MAJOR 2
+#define OPTEE_MSG_REVISION_MINOR 0
+#define OPTEE_MSG_FUNCID_CALLS_REVISION 0xFF03
+
+/*
+ * Get UUID of Trusted OS.
+ *
+ * Used by non-secure world to figure out which Trusted OS is installed.
+ * Note that returned UUID is the UUID of the Trusted OS, not of the API.
+ *
+ * Returns UUID in 4 32-bit words in the same way as
+ * OPTEE_MSG_FUNCID_CALLS_UID described above.
+ */
+#define OPTEE_MSG_OS_OPTEE_UUID_0 0x486178e0
+#define OPTEE_MSG_OS_OPTEE_UUID_1 0xe7f811e3
+#define OPTEE_MSG_OS_OPTEE_UUID_2 0xbc5e0002
+#define OPTEE_MSG_OS_OPTEE_UUID_3 0xa5d5c51b
+#define OPTEE_MSG_FUNCID_GET_OS_UUID 0x0000
+
+/*
+ * Get revision of Trusted OS.
+ *
+ * Used by non-secure world to figure out which version of the Trusted OS
+ * is installed. Note that the returned revision is the revision of the
+ * Trusted OS, not of the API.
+ *
+ * Returns revision in 2 32-bit words in the same way as
+ * OPTEE_MSG_CALLS_REVISION described above.
+ */
+#define OPTEE_MSG_FUNCID_GET_OS_REVISION 0x0001
+
+/*
+ * Do a secure call with struct optee_msg_arg as argument
+ * The OPTEE_MSG_CMD_* below defines what goes in struct optee_msg_arg::cmd
+ *
+ * OPTEE_MSG_CMD_OPEN_SESSION opens a session to a Trusted Application.
+ * The first two parameters are tagged as meta, holding two value
+ * parameters to pass the following information:
+ * param[0].u.value.a-b uuid of Trusted Application
+ * param[1].u.value.a-b uuid of Client
+ * param[1].u.value.c Login class of client OPTEE_MSG_LOGIN_*
+ *
+ * OPTEE_MSG_CMD_INVOKE_COMMAND invokes a command a previously opened
+ * session to a Trusted Application. struct optee_msg_arg::func is Trusted
+ * Application function, specific to the Trusted Application.
+ *
+ * OPTEE_MSG_CMD_CLOSE_SESSION closes a previously opened session to
+ * Trusted Application.
+ *
+ * OPTEE_MSG_CMD_CANCEL cancels a currently invoked command.
+ *
+ * OPTEE_MSG_CMD_REGISTER_SHM registers a shared memory reference. The
+ * information is passed as:
+ * [in] param[0].attr OPTEE_MSG_ATTR_TYPE_TMEM_INPUT
+ * [| OPTEE_MSG_ATTR_FRAGMENT]
+ * [in] param[0].u.tmem.buf_ptr physical address (of first fragment)
+ * [in] param[0].u.tmem.size size (of first fragment)
+ * [in] param[0].u.tmem.shm_ref holds shared memory reference
+ * ...
+ * The shared memory can optionally be fragmented, temp memrefs can follow
+ * each other with all but the last with the OPTEE_MSG_ATTR_FRAGMENT bit set.
+ *
+ * OPTEE_MSG_CMD_UNREGISTER_SHM unregisteres a previously registered shared
+ * memory reference. The information is passed as:
+ * [in] param[0].attr OPTEE_MSG_ATTR_TYPE_RMEM_INPUT
+ * [in] param[0].u.rmem.shm_ref holds shared memory reference
+ * [in] param[0].u.rmem.offs 0
+ * [in] param[0].u.rmem.size 0
+ */
+#define OPTEE_MSG_CMD_OPEN_SESSION 0
+#define OPTEE_MSG_CMD_INVOKE_COMMAND 1
+#define OPTEE_MSG_CMD_CLOSE_SESSION 2
+#define OPTEE_MSG_CMD_CANCEL 3
+#define OPTEE_MSG_CMD_REGISTER_SHM 4
+#define OPTEE_MSG_CMD_UNREGISTER_SHM 5
+#define OPTEE_MSG_FUNCID_CALL_WITH_ARG 0x0004
+
+/*****************************************************************************
+ * Part 3 - Requests from secure world, RPC
+ *****************************************************************************/
+
+/*
+ * All RPC is done with a struct optee_msg_arg as bearer of information,
+ * struct optee_msg_arg::arg holds values defined by OPTEE_MSG_RPC_CMD_* below
+ *
+ * RPC communication with tee-supplicant is reversed compared to normal
+ * client communication desribed above. The supplicant receives requests
+ * and sends responses.
+ */
+
+/*
+ * Load a TA into memory, defined in tee-supplicant
+ */
+#define OPTEE_MSG_RPC_CMD_LOAD_TA 0
+
+/*
+ * Reserved
+ */
+#define OPTEE_MSG_RPC_CMD_RPMB 1
+
+/*
+ * File system access, defined in tee-supplicant
+ */
+#define OPTEE_MSG_RPC_CMD_FS 2
+
+/*
+ * Get time
+ *
+ * Returns number of seconds and nano seconds since the Epoch,
+ * 1970-01-01 00:00:00 +0000 (UTC).
+ *
+ * [out] param[0].u.value.a Number of seconds
+ * [out] param[0].u.value.b Number of nano seconds.
+ */
+#define OPTEE_MSG_RPC_CMD_GET_TIME 3
+
+/*
+ * Wait queue primitive, helper for secure world to implement a wait queue.
+ *
+ * If secure world need to wait for a secure world mutex it issues a sleep
+ * request instead of spinning in secure world. Conversely is a wakeup
+ * request issued when a secure world mutex with a thread waiting thread is
+ * unlocked.
+ *
+ * Waiting on a key
+ * [in] param[0].u.value.a OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP
+ * [in] param[0].u.value.b wait key
+ *
+ * Waking up a key
+ * [in] param[0].u.value.a OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP
+ * [in] param[0].u.value.b wakeup key
+ */
+#define OPTEE_MSG_RPC_CMD_WAIT_QUEUE 4
+#define OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP 0
+#define OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP 1
+
+/*
+ * Suspend execution
+ *
+ * [in] param[0].value .a number of milliseconds to suspend
+ */
+#define OPTEE_MSG_RPC_CMD_SUSPEND 5
+
+/*
+ * Allocate a piece of shared memory
+ *
+ * Shared memory can optionally be fragmented, to support that additional
+ * spare param entries are allocated to make room for eventual fragments.
+ * The spare param entries has .attr = OPTEE_MSG_ATTR_TYPE_NONE when
+ * unused. All returned temp memrefs except the last should have the
+ * OPTEE_MSG_ATTR_FRAGMENT bit set in the attr field.
+ *
+ * [in] param[0].u.value.a type of memory one of
+ * OPTEE_MSG_RPC_SHM_TYPE_* below
+ * [in] param[0].u.value.b requested size
+ * [in] param[0].u.value.c required alignment
+ *
+ * [out] param[0].u.tmem.buf_ptr physical address (of first fragment)
+ * [out] param[0].u.tmem.size size (of first fragment)
+ * [out] param[0].u.tmem.shm_ref shared memory reference
+ * ...
+ * [out] param[n].u.tmem.buf_ptr physical address
+ * [out] param[n].u.tmem.size size
+ * [out] param[n].u.tmem.shm_ref shared memory reference (same value
+ * as in param[n-1].u.tmem.shm_ref)
+ */
+#define OPTEE_MSG_RPC_CMD_SHM_ALLOC 6
+/* Memory that can be shared with a non-secure user space application */
+#define OPTEE_MSG_RPC_SHM_TYPE_APPL 0
+/* Memory only shared with non-secure kernel */
+#define OPTEE_MSG_RPC_SHM_TYPE_KERNEL 1
+
+/*
+ * Free shared memory previously allocated with OPTEE_MSG_RPC_CMD_SHM_ALLOC
+ *
+ * [in] param[0].u.value.a type of memory one of
+ * OPTEE_MSG_RPC_SHM_TYPE_* above
+ * [in] param[0].u.value.b value of shared memory reference
+ * returned in param[0].u.tmem.shm_ref
+ * above
+ */
+#define OPTEE_MSG_RPC_CMD_SHM_FREE 7
+
+#endif /* _OPTEE_MSG_H */
diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h
new file mode 100644
index 0000000..35e7938
--- /dev/null
+++ b/drivers/tee/optee/optee_private.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef OPTEE_PRIVATE_H
+#define OPTEE_PRIVATE_H
+
+#include <linux/arm-smccc.h>
+#include <linux/semaphore.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include "optee_msg.h"
+
+#define OPTEE_MAX_ARG_SIZE 1024
+
+/* Some Global Platform error codes used in this driver */
+#define TEEC_SUCCESS 0x00000000
+#define TEEC_ERROR_BAD_PARAMETERS 0xFFFF0006
+#define TEEC_ERROR_COMMUNICATION 0xFFFF000E
+#define TEEC_ERROR_OUT_OF_MEMORY 0xFFFF000C
+
+#define TEEC_ORIGIN_COMMS 0x00000002
+
+typedef void (optee_invoke_fn)(unsigned long, unsigned long, unsigned long,
+ unsigned long, unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ struct arm_smccc_res *);
+
+struct optee_call_queue {
+ /* Serializes access to this struct */
+ struct mutex mutex;
+ struct list_head waiters;
+};
+
+struct optee_wait_queue {
+ /* Serializes access to this struct */
+ struct mutex mu;
+ struct list_head db;
+};
+
+/**
+ * struct optee_supp - supplicant synchronization struct
+ * @ctx the context of current connected supplicant.
+ * if !NULL the supplicant device is available for use,
+ * else busy
+ * @mutex: held while accessing content of this struct
+ * @req_id: current request id if supplicant is doing synchronous
+ * communication, else -1
+ * @reqs: queued request not yet retrieved by supplicant
+ * @idr: IDR holding all requests currently being processed
+ * by supplicant
+ * @reqs_c: completion used by supplicant when waiting for a
+ * request to be queued.
+ */
+struct optee_supp {
+ /* Serializes access to this struct */
+ struct mutex mutex;
+ struct tee_context *ctx;
+
+ int req_id;
+ struct list_head reqs;
+ struct idr idr;
+ struct completion reqs_c;
+};
+
+/**
+ * struct optee - main service struct
+ * @supp_teedev: supplicant device
+ * @teedev: client device
+ * @invoke_fn: function to issue smc or hvc
+ * @call_queue: queue of threads waiting to call @invoke_fn
+ * @wait_queue: queue of threads from secure world waiting for a
+ * secure world sync object
+ * @supp: supplicant synchronization struct for RPC to supplicant
+ * @pool: shared memory pool
+ * @memremaped_shm virtual address of memory in shared memory pool
+ * @sec_caps: secure world capabilities defined by
+ * OPTEE_SMC_SEC_CAP_* in optee_smc.h
+ */
+struct optee {
+ struct tee_device *supp_teedev;
+ struct tee_device *teedev;
+ optee_invoke_fn *invoke_fn;
+ struct optee_call_queue call_queue;
+ struct optee_wait_queue wait_queue;
+ struct optee_supp supp;
+ struct tee_shm_pool *pool;
+ void *memremaped_shm;
+ u32 sec_caps;
+};
+
+struct optee_session {
+ struct list_head list_node;
+ u32 session_id;
+};
+
+struct optee_context_data {
+ /* Serializes access to this struct */
+ struct mutex mutex;
+ struct list_head sess_list;
+};
+
+struct optee_rpc_param {
+ u32 a0;
+ u32 a1;
+ u32 a2;
+ u32 a3;
+ u32 a4;
+ u32 a5;
+ u32 a6;
+ u32 a7;
+};
+
+/* Holds context that is preserved during one STD call */
+struct optee_call_ctx {
+ /* information about pages list used in last allocation */
+ void *pages_list;
+ size_t num_entries;
+};
+
+void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param,
+ struct optee_call_ctx *call_ctx);
+void optee_rpc_finalize_call(struct optee_call_ctx *call_ctx);
+
+void optee_wait_queue_init(struct optee_wait_queue *wq);
+void optee_wait_queue_exit(struct optee_wait_queue *wq);
+
+u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
+ struct tee_param *param);
+
+int optee_supp_read(struct tee_context *ctx, void __user *buf, size_t len);
+int optee_supp_write(struct tee_context *ctx, void __user *buf, size_t len);
+void optee_supp_init(struct optee_supp *supp);
+void optee_supp_uninit(struct optee_supp *supp);
+void optee_supp_release(struct optee_supp *supp);
+
+int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param);
+int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param);
+
+u32 optee_do_call_with_arg(struct tee_context *ctx, phys_addr_t parg);
+int optee_open_session(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param);
+int optee_close_session(struct tee_context *ctx, u32 session);
+int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param);
+int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session);
+
+void optee_enable_shm_cache(struct optee *optee);
+void optee_disable_shm_cache(struct optee *optee);
+
+int optee_shm_register(struct tee_context *ctx, struct tee_shm *shm,
+ struct page **pages, size_t num_pages,
+ unsigned long start);
+int optee_shm_unregister(struct tee_context *ctx, struct tee_shm *shm);
+
+int optee_shm_register_supp(struct tee_context *ctx, struct tee_shm *shm,
+ struct page **pages, size_t num_pages,
+ unsigned long start);
+int optee_shm_unregister_supp(struct tee_context *ctx, struct tee_shm *shm);
+
+int optee_from_msg_param(struct tee_param *params, size_t num_params,
+ const struct optee_msg_param *msg_params);
+int optee_to_msg_param(struct optee_msg_param *msg_params, size_t num_params,
+ const struct tee_param *params);
+
+u64 *optee_allocate_pages_list(size_t num_entries);
+void optee_free_pages_list(void *array, size_t num_entries);
+void optee_fill_pages_list(u64 *dst, struct page **pages, int num_pages,
+ size_t page_offset);
+
+/*
+ * Small helpers
+ */
+
+static inline void *reg_pair_to_ptr(u32 reg0, u32 reg1)
+{
+ return (void *)(unsigned long)(((u64)reg0 << 32) | reg1);
+}
+
+static inline void reg_pair_from_64(u32 *reg0, u32 *reg1, u64 val)
+{
+ *reg0 = val >> 32;
+ *reg1 = val;
+}
+
+#endif /*OPTEE_PRIVATE_H*/
diff --git a/drivers/tee/optee/optee_smc.h b/drivers/tee/optee/optee_smc.h
new file mode 100644
index 0000000..7cd3272
--- /dev/null
+++ b/drivers/tee/optee/optee_smc.h
@@ -0,0 +1,457 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef OPTEE_SMC_H
+#define OPTEE_SMC_H
+
+#include <linux/arm-smccc.h>
+#include <linux/bitops.h>
+
+#define OPTEE_SMC_STD_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS, (func_num))
+#define OPTEE_SMC_FAST_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS, (func_num))
+
+/*
+ * Function specified by SMC Calling convention.
+ */
+#define OPTEE_SMC_FUNCID_CALLS_COUNT 0xFF00
+#define OPTEE_SMC_CALLS_COUNT \
+ ARM_SMCCC_CALL_VAL(OPTEE_SMC_FAST_CALL, SMCCC_SMC_32, \
+ SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_COUNT)
+
+/*
+ * Normal cached memory (write-back), shareable for SMP systems and not
+ * shareable for UP systems.
+ */
+#define OPTEE_SMC_SHM_CACHED 1
+
+/*
+ * a0..a7 is used as register names in the descriptions below, on arm32
+ * that translates to r0..r7 and on arm64 to w0..w7. In both cases it's
+ * 32-bit registers.
+ */
+
+/*
+ * Function specified by SMC Calling convention
+ *
+ * Return one of the following UIDs if using API specified in this file
+ * without further extentions:
+ * 65cb6b93-af0c-4617-8ed6-644a8d1140f8
+ * see also OPTEE_SMC_UID_* in optee_msg.h
+ */
+#define OPTEE_SMC_FUNCID_CALLS_UID OPTEE_MSG_FUNCID_CALLS_UID
+#define OPTEE_SMC_CALLS_UID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_UID)
+
+/*
+ * Function specified by SMC Calling convention
+ *
+ * Returns 2.0 if using API specified in this file without further extentions.
+ * see also OPTEE_MSG_REVISION_* in optee_msg.h
+ */
+#define OPTEE_SMC_FUNCID_CALLS_REVISION OPTEE_MSG_FUNCID_CALLS_REVISION
+#define OPTEE_SMC_CALLS_REVISION \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_REVISION)
+
+struct optee_smc_calls_revision_result {
+ unsigned long major;
+ unsigned long minor;
+ unsigned long reserved0;
+ unsigned long reserved1;
+};
+
+/*
+ * Get UUID of Trusted OS.
+ *
+ * Used by non-secure world to figure out which Trusted OS is installed.
+ * Note that returned UUID is the UUID of the Trusted OS, not of the API.
+ *
+ * Returns UUID in a0-4 in the same way as OPTEE_SMC_CALLS_UID
+ * described above.
+ */
+#define OPTEE_SMC_FUNCID_GET_OS_UUID OPTEE_MSG_FUNCID_GET_OS_UUID
+#define OPTEE_SMC_CALL_GET_OS_UUID \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_OS_UUID)
+
+/*
+ * Get revision of Trusted OS.
+ *
+ * Used by non-secure world to figure out which version of the Trusted OS
+ * is installed. Note that the returned revision is the revision of the
+ * Trusted OS, not of the API.
+ *
+ * Returns revision in a0-1 in the same way as OPTEE_SMC_CALLS_REVISION
+ * described above.
+ */
+#define OPTEE_SMC_FUNCID_GET_OS_REVISION OPTEE_MSG_FUNCID_GET_OS_REVISION
+#define OPTEE_SMC_CALL_GET_OS_REVISION \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_OS_REVISION)
+
+/*
+ * Call with struct optee_msg_arg as argument
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC*CALL_WITH_ARG
+ * a1 Upper 32bit of a 64bit physical pointer to a struct optee_msg_arg
+ * a2 Lower 32bit of a 64bit physical pointer to a struct optee_msg_arg
+ * a3 Cache settings, not used if physical pointer is in a predefined shared
+ * memory area else per OPTEE_SMC_SHM_*
+ * a4-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_*
+ * a1-3 Not used
+ * a4-7 Preserved
+ *
+ * OPTEE_SMC_RETURN_ETHREAD_LIMIT return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_ETHREAD_LIMIT
+ * a1-3 Preserved
+ * a4-7 Preserved
+ *
+ * RPC return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_IS_RPC(val)
+ * a1-2 RPC parameters
+ * a3-7 Resume information, must be preserved
+ *
+ * Possible return values:
+ * OPTEE_SMC_RETURN_UNKNOWN_FUNCTION Trusted OS does not recognize this
+ * function.
+ * OPTEE_SMC_RETURN_OK Call completed, result updated in
+ * the previously supplied struct
+ * optee_msg_arg.
+ * OPTEE_SMC_RETURN_ETHREAD_LIMIT Number of Trusted OS threads exceeded,
+ * try again later.
+ * OPTEE_SMC_RETURN_EBADADDR Bad physcial pointer to struct
+ * optee_msg_arg.
+ * OPTEE_SMC_RETURN_EBADCMD Bad/unknown cmd in struct optee_msg_arg
+ * OPTEE_SMC_RETURN_IS_RPC() Call suspended by RPC call to normal
+ * world.
+ */
+#define OPTEE_SMC_FUNCID_CALL_WITH_ARG OPTEE_MSG_FUNCID_CALL_WITH_ARG
+#define OPTEE_SMC_CALL_WITH_ARG \
+ OPTEE_SMC_STD_CALL_VAL(OPTEE_SMC_FUNCID_CALL_WITH_ARG)
+
+/*
+ * Get Shared Memory Config
+ *
+ * Returns the Secure/Non-secure shared memory config.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_GET_SHM_CONFIG
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Have config return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 Physical address of start of SHM
+ * a2 Size of of SHM
+ * a3 Cache settings of memory, as defined by the
+ * OPTEE_SMC_SHM_* values above
+ * a4-7 Preserved
+ *
+ * Not available register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL
+ * a1-3 Not used
+ * a4-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_GET_SHM_CONFIG 7
+#define OPTEE_SMC_GET_SHM_CONFIG \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_SHM_CONFIG)
+
+struct optee_smc_get_shm_config_result {
+ unsigned long status;
+ unsigned long start;
+ unsigned long size;
+ unsigned long settings;
+};
+
+/*
+ * Exchanges capabilities between normal world and secure world
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_EXCHANGE_CAPABILITIES
+ * a1 bitfield of normal world capabilities OPTEE_SMC_NSEC_CAP_*
+ * a2-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 bitfield of secure world capabilities OPTEE_SMC_SEC_CAP_*
+ * a2-7 Preserved
+ *
+ * Error return register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL, can't use the capabilities from normal world
+ * a1 bitfield of secure world capabilities OPTEE_SMC_SEC_CAP_*
+ * a2-7 Preserved
+ */
+/* Normal world works as a uniprocessor system */
+#define OPTEE_SMC_NSEC_CAP_UNIPROCESSOR BIT(0)
+/* Secure world has reserved shared memory for normal world to use */
+#define OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM BIT(0)
+/* Secure world can communicate via previously unregistered shared memory */
+#define OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM BIT(1)
+
+/*
+ * Secure world supports commands "register/unregister shared memory",
+ * secure world accepts command buffers located in any parts of non-secure RAM
+ */
+#define OPTEE_SMC_SEC_CAP_DYNAMIC_SHM BIT(2)
+
+#define OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES 9
+#define OPTEE_SMC_EXCHANGE_CAPABILITIES \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES)
+
+struct optee_smc_exchange_capabilities_result {
+ unsigned long status;
+ unsigned long capabilities;
+ unsigned long reserved0;
+ unsigned long reserved1;
+};
+
+/*
+ * Disable and empties cache of shared memory objects
+ *
+ * Secure world can cache frequently used shared memory objects, for
+ * example objects used as RPC arguments. When secure world is idle this
+ * function returns one shared memory reference to free. To disable the
+ * cache and free all cached objects this function has to be called until
+ * it returns OPTEE_SMC_RETURN_ENOTAVAIL.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_DISABLE_SHM_CACHE
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 Upper 32bit of a 64bit Shared memory cookie
+ * a2 Lower 32bit of a 64bit Shared memory cookie
+ * a3-7 Preserved
+ *
+ * Cache empty return register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL
+ * a1-7 Preserved
+ *
+ * Not idle return register usage:
+ * a0 OPTEE_SMC_RETURN_EBUSY
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_DISABLE_SHM_CACHE 10
+#define OPTEE_SMC_DISABLE_SHM_CACHE \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_DISABLE_SHM_CACHE)
+
+struct optee_smc_disable_shm_cache_result {
+ unsigned long status;
+ unsigned long shm_upper32;
+ unsigned long shm_lower32;
+ unsigned long reserved0;
+};
+
+/*
+ * Enable cache of shared memory objects
+ *
+ * Secure world can cache frequently used shared memory objects, for
+ * example objects used as RPC arguments. When secure world is idle this
+ * function returns OPTEE_SMC_RETURN_OK and the cache is enabled. If
+ * secure world isn't idle OPTEE_SMC_RETURN_EBUSY is returned.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_ENABLE_SHM_CACHE
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1-7 Preserved
+ *
+ * Not idle return register usage:
+ * a0 OPTEE_SMC_RETURN_EBUSY
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_ENABLE_SHM_CACHE 11
+#define OPTEE_SMC_ENABLE_SHM_CACHE \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_ENABLE_SHM_CACHE)
+
+/*
+ * Resume from RPC (for example after processing a foreign interrupt)
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC
+ * a1-3 Value of a1-3 when OPTEE_SMC_CALL_WITH_ARG returned
+ * OPTEE_SMC_RETURN_RPC in a0
+ *
+ * Return register usage is the same as for OPTEE_SMC_*CALL_WITH_ARG above.
+ *
+ * Possible return values
+ * OPTEE_SMC_RETURN_UNKNOWN_FUNCTION Trusted OS does not recognize this
+ * function.
+ * OPTEE_SMC_RETURN_OK Original call completed, result
+ * updated in the previously supplied.
+ * struct optee_msg_arg
+ * OPTEE_SMC_RETURN_RPC Call suspended by RPC call to normal
+ * world.
+ * OPTEE_SMC_RETURN_ERESUME Resume failed, the opaque resume
+ * information was corrupt.
+ */
+#define OPTEE_SMC_FUNCID_RETURN_FROM_RPC 3
+#define OPTEE_SMC_CALL_RETURN_FROM_RPC \
+ OPTEE_SMC_STD_CALL_VAL(OPTEE_SMC_FUNCID_RETURN_FROM_RPC)
+
+#define OPTEE_SMC_RETURN_RPC_PREFIX_MASK 0xFFFF0000
+#define OPTEE_SMC_RETURN_RPC_PREFIX 0xFFFF0000
+#define OPTEE_SMC_RETURN_RPC_FUNC_MASK 0x0000FFFF
+
+#define OPTEE_SMC_RETURN_GET_RPC_FUNC(ret) \
+ ((ret) & OPTEE_SMC_RETURN_RPC_FUNC_MASK)
+
+#define OPTEE_SMC_RPC_VAL(func) ((func) | OPTEE_SMC_RETURN_RPC_PREFIX)
+
+/*
+ * Allocate memory for RPC parameter passing. The memory is used to hold a
+ * struct optee_msg_arg.
+ *
+ * "Call" register usage:
+ * a0 This value, OPTEE_SMC_RETURN_RPC_ALLOC
+ * a1 Size in bytes of required argument memory
+ * a2 Not used
+ * a3 Resume information, must be preserved
+ * a4-5 Not used
+ * a6-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1 Upper 32bits of 64bit physical pointer to allocated
+ * memory, (a1 == 0 && a2 == 0) if size was 0 or if memory can't
+ * be allocated.
+ * a2 Lower 32bits of 64bit physical pointer to allocated
+ * memory, (a1 == 0 && a2 == 0) if size was 0 or if memory can't
+ * be allocated
+ * a3 Preserved
+ * a4 Upper 32bits of 64bit Shared memory cookie used when freeing
+ * the memory or doing an RPC
+ * a5 Lower 32bits of 64bit Shared memory cookie used when freeing
+ * the memory or doing an RPC
+ * a6-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_ALLOC 0
+#define OPTEE_SMC_RETURN_RPC_ALLOC \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_ALLOC)
+
+/*
+ * Free memory previously allocated by OPTEE_SMC_RETURN_RPC_ALLOC
+ *
+ * "Call" register usage:
+ * a0 This value, OPTEE_SMC_RETURN_RPC_FREE
+ * a1 Upper 32bits of 64bit shared memory cookie belonging to this
+ * argument memory
+ * a2 Lower 32bits of 64bit shared memory cookie belonging to this
+ * argument memory
+ * a3-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-2 Not used
+ * a3-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_FREE 2
+#define OPTEE_SMC_RETURN_RPC_FREE \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_FREE)
+
+/*
+ * Deliver foreign interrupt to normal world.
+ *
+ * "Call" register usage:
+ * a0 OPTEE_SMC_RETURN_RPC_FOREIGN_INTR
+ * a1-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_FOREIGN_INTR 4
+#define OPTEE_SMC_RETURN_RPC_FOREIGN_INTR \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_FOREIGN_INTR)
+
+/*
+ * Do an RPC request. The supplied struct optee_msg_arg tells which
+ * request to do and the parameters for the request. The following fields
+ * are used (the rest are unused):
+ * - cmd the Request ID
+ * - ret return value of the request, filled in by normal world
+ * - num_params number of parameters for the request
+ * - params the parameters
+ * - param_attrs attributes of the parameters
+ *
+ * "Call" register usage:
+ * a0 OPTEE_SMC_RETURN_RPC_CMD
+ * a1 Upper 32bit of a 64bit Shared memory cookie holding a
+ * struct optee_msg_arg, must be preserved, only the data should
+ * be updated
+ * a2 Lower 32bit of a 64bit Shared memory cookie holding a
+ * struct optee_msg_arg, must be preserved, only the data should
+ * be updated
+ * a3-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-2 Not used
+ * a3-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_CMD 5
+#define OPTEE_SMC_RETURN_RPC_CMD \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_CMD)
+
+/* Returned in a0 */
+#define OPTEE_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF
+
+/* Returned in a0 only from Trusted OS functions */
+#define OPTEE_SMC_RETURN_OK 0x0
+#define OPTEE_SMC_RETURN_ETHREAD_LIMIT 0x1
+#define OPTEE_SMC_RETURN_EBUSY 0x2
+#define OPTEE_SMC_RETURN_ERESUME 0x3
+#define OPTEE_SMC_RETURN_EBADADDR 0x4
+#define OPTEE_SMC_RETURN_EBADCMD 0x5
+#define OPTEE_SMC_RETURN_ENOMEM 0x6
+#define OPTEE_SMC_RETURN_ENOTAVAIL 0x7
+#define OPTEE_SMC_RETURN_IS_RPC(ret) __optee_smc_return_is_rpc((ret))
+
+static inline bool __optee_smc_return_is_rpc(u32 ret)
+{
+ return ret != OPTEE_SMC_RETURN_UNKNOWN_FUNCTION &&
+ (ret & OPTEE_SMC_RETURN_RPC_PREFIX_MASK) ==
+ OPTEE_SMC_RETURN_RPC_PREFIX;
+}
+
+#endif /* OPTEE_SMC_H */
diff --git a/drivers/tee/optee/rpc.c b/drivers/tee/optee/rpc.c
new file mode 100644
index 0000000..41aea12
--- /dev/null
+++ b/drivers/tee/optee/rpc.c
@@ -0,0 +1,452 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+
+struct wq_entry {
+ struct list_head link;
+ struct completion c;
+ u32 key;
+};
+
+void optee_wait_queue_init(struct optee_wait_queue *priv)
+{
+ mutex_init(&priv->mu);
+ INIT_LIST_HEAD(&priv->db);
+}
+
+void optee_wait_queue_exit(struct optee_wait_queue *priv)
+{
+ mutex_destroy(&priv->mu);
+}
+
+static void handle_rpc_func_cmd_get_time(struct optee_msg_arg *arg)
+{
+ struct timespec64 ts;
+
+ if (arg->num_params != 1)
+ goto bad;
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT)
+ goto bad;
+
+ getnstimeofday64(&ts);
+ arg->params[0].u.value.a = ts.tv_sec;
+ arg->params[0].u.value.b = ts.tv_nsec;
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static struct wq_entry *wq_entry_get(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w;
+
+ mutex_lock(&wq->mu);
+
+ list_for_each_entry(w, &wq->db, link)
+ if (w->key == key)
+ goto out;
+
+ w = kmalloc(sizeof(*w), GFP_KERNEL);
+ if (w) {
+ init_completion(&w->c);
+ w->key = key;
+ list_add_tail(&w->link, &wq->db);
+ }
+out:
+ mutex_unlock(&wq->mu);
+ return w;
+}
+
+static void wq_sleep(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w = wq_entry_get(wq, key);
+
+ if (w) {
+ wait_for_completion(&w->c);
+ mutex_lock(&wq->mu);
+ list_del(&w->link);
+ mutex_unlock(&wq->mu);
+ kfree(w);
+ }
+}
+
+static void wq_wakeup(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w = wq_entry_get(wq, key);
+
+ if (w)
+ complete(&w->c);
+}
+
+static void handle_rpc_func_cmd_wq(struct optee *optee,
+ struct optee_msg_arg *arg)
+{
+ if (arg->num_params != 1)
+ goto bad;
+
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_INPUT)
+ goto bad;
+
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP:
+ wq_sleep(&optee->wait_queue, arg->params[0].u.value.b);
+ break;
+ case OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP:
+ wq_wakeup(&optee->wait_queue, arg->params[0].u.value.b);
+ break;
+ default:
+ goto bad;
+ }
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static void handle_rpc_func_cmd_wait(struct optee_msg_arg *arg)
+{
+ u32 msec_to_wait;
+
+ if (arg->num_params != 1)
+ goto bad;
+
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_INPUT)
+ goto bad;
+
+ msec_to_wait = arg->params[0].u.value.a;
+
+ /* Go to interruptible sleep */
+ msleep_interruptible(msec_to_wait);
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static void handle_rpc_supp_cmd(struct tee_context *ctx,
+ struct optee_msg_arg *arg)
+{
+ struct tee_param *params;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ params = kmalloc_array(arg->num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ return;
+ }
+
+ if (optee_from_msg_param(params, arg->num_params, arg->params)) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ goto out;
+ }
+
+ arg->ret = optee_supp_thrd_req(ctx, arg->cmd, arg->num_params, params);
+
+ if (optee_to_msg_param(arg->params, arg->num_params, params))
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+out:
+ kfree(params);
+}
+
+static struct tee_shm *cmd_alloc_suppl(struct tee_context *ctx, size_t sz)
+{
+ u32 ret;
+ struct tee_param param;
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct tee_shm *shm;
+
+ param.attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT;
+ param.u.value.a = OPTEE_MSG_RPC_SHM_TYPE_APPL;
+ param.u.value.b = sz;
+ param.u.value.c = 0;
+
+ ret = optee_supp_thrd_req(ctx, OPTEE_MSG_RPC_CMD_SHM_ALLOC, 1, ¶m);
+ if (ret)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_lock(&optee->supp.mutex);
+ /* Increases count as secure world doesn't have a reference */
+ shm = tee_shm_get_from_id(optee->supp.ctx, param.u.value.c);
+ mutex_unlock(&optee->supp.mutex);
+ return shm;
+}
+
+static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx,
+ struct optee_msg_arg *arg,
+ struct optee_call_ctx *call_ctx)
+{
+ phys_addr_t pa;
+ struct tee_shm *shm;
+ size_t sz;
+ size_t n;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ if (!arg->num_params ||
+ arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ for (n = 1; n < arg->num_params; n++) {
+ if (arg->params[n].attr != OPTEE_MSG_ATTR_TYPE_NONE) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+ }
+
+ sz = arg->params[0].u.value.b;
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_SHM_TYPE_APPL:
+ shm = cmd_alloc_suppl(ctx, sz);
+ break;
+ case OPTEE_MSG_RPC_SHM_TYPE_KERNEL:
+ shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED);
+ break;
+ default:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ if (IS_ERR(shm)) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ return;
+ }
+
+ if (tee_shm_get_pa(shm, 0, &pa)) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ goto bad;
+ }
+
+ sz = tee_shm_get_size(shm);
+
+ if (tee_shm_is_registered(shm)) {
+ struct page **pages;
+ u64 *pages_list;
+ size_t page_num;
+
+ pages = tee_shm_get_pages(shm, &page_num);
+ if (!pages || !page_num) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ goto bad;
+ }
+
+ pages_list = optee_allocate_pages_list(page_num);
+ if (!pages_list) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ goto bad;
+ }
+
+ call_ctx->pages_list = pages_list;
+ call_ctx->num_entries = page_num;
+
+ arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT |
+ OPTEE_MSG_ATTR_NONCONTIG;
+ /*
+ * In the least bits of u.tmem.buf_ptr we store buffer offset
+ * from 4k page, as described in OP-TEE ABI.
+ */
+ arg->params[0].u.tmem.buf_ptr = virt_to_phys(pages_list) |
+ (tee_shm_get_page_offset(shm) &
+ (OPTEE_MSG_NONCONTIG_PAGE_SIZE - 1));
+ arg->params[0].u.tmem.size = tee_shm_get_size(shm);
+ arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
+
+ optee_fill_pages_list(pages_list, pages, page_num,
+ tee_shm_get_page_offset(shm));
+ } else {
+ arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT;
+ arg->params[0].u.tmem.buf_ptr = pa;
+ arg->params[0].u.tmem.size = sz;
+ arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
+ }
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ tee_shm_free(shm);
+}
+
+static void cmd_free_suppl(struct tee_context *ctx, struct tee_shm *shm)
+{
+ struct tee_param param;
+
+ param.attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT;
+ param.u.value.a = OPTEE_MSG_RPC_SHM_TYPE_APPL;
+ param.u.value.b = tee_shm_get_id(shm);
+ param.u.value.c = 0;
+
+ /*
+ * Match the tee_shm_get_from_id() in cmd_alloc_suppl() as secure
+ * world has released its reference.
+ *
+ * It's better to do this before sending the request to supplicant
+ * as we'd like to let the process doing the initial allocation to
+ * do release the last reference too in order to avoid stacking
+ * many pending fput() on the client process. This could otherwise
+ * happen if secure world does many allocate and free in a single
+ * invoke.
+ */
+ tee_shm_put(shm);
+
+ optee_supp_thrd_req(ctx, OPTEE_MSG_RPC_CMD_SHM_FREE, 1, ¶m);
+}
+
+static void handle_rpc_func_cmd_shm_free(struct tee_context *ctx,
+ struct optee_msg_arg *arg)
+{
+ struct tee_shm *shm;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ if (arg->num_params != 1 ||
+ arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ shm = (struct tee_shm *)(unsigned long)arg->params[0].u.value.b;
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_SHM_TYPE_APPL:
+ cmd_free_suppl(ctx, shm);
+ break;
+ case OPTEE_MSG_RPC_SHM_TYPE_KERNEL:
+ tee_shm_free(shm);
+ break;
+ default:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ }
+ arg->ret = TEEC_SUCCESS;
+}
+
+static void free_pages_list(struct optee_call_ctx *call_ctx)
+{
+ if (call_ctx->pages_list) {
+ optee_free_pages_list(call_ctx->pages_list,
+ call_ctx->num_entries);
+ call_ctx->pages_list = NULL;
+ call_ctx->num_entries = 0;
+ }
+}
+
+void optee_rpc_finalize_call(struct optee_call_ctx *call_ctx)
+{
+ free_pages_list(call_ctx);
+}
+
+static void handle_rpc_func_cmd(struct tee_context *ctx, struct optee *optee,
+ struct tee_shm *shm,
+ struct optee_call_ctx *call_ctx)
+{
+ struct optee_msg_arg *arg;
+
+ arg = tee_shm_get_va(shm, 0);
+ if (IS_ERR(arg)) {
+ pr_err("%s: tee_shm_get_va %p failed\n", __func__, shm);
+ return;
+ }
+
+ switch (arg->cmd) {
+ case OPTEE_MSG_RPC_CMD_GET_TIME:
+ handle_rpc_func_cmd_get_time(arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_WAIT_QUEUE:
+ handle_rpc_func_cmd_wq(optee, arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_SUSPEND:
+ handle_rpc_func_cmd_wait(arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_SHM_ALLOC:
+ free_pages_list(call_ctx);
+ handle_rpc_func_cmd_shm_alloc(ctx, arg, call_ctx);
+ break;
+ case OPTEE_MSG_RPC_CMD_SHM_FREE:
+ handle_rpc_func_cmd_shm_free(ctx, arg);
+ break;
+ default:
+ handle_rpc_supp_cmd(ctx, arg);
+ }
+}
+
+/**
+ * optee_handle_rpc() - handle RPC from secure world
+ * @ctx: context doing the RPC
+ * @param: value of registers for the RPC
+ * @call_ctx: call context. Preserved during one OP-TEE invocation
+ *
+ * Result of RPC is written back into @param.
+ */
+void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param,
+ struct optee_call_ctx *call_ctx)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct tee_shm *shm;
+ phys_addr_t pa;
+
+ switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) {
+ case OPTEE_SMC_RPC_FUNC_ALLOC:
+ shm = tee_shm_alloc(ctx, param->a1, TEE_SHM_MAPPED);
+ if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) {
+ reg_pair_from_64(¶m->a1, ¶m->a2, pa);
+ reg_pair_from_64(¶m->a4, ¶m->a5,
+ (unsigned long)shm);
+ } else {
+ param->a1 = 0;
+ param->a2 = 0;
+ param->a4 = 0;
+ param->a5 = 0;
+ }
+ break;
+ case OPTEE_SMC_RPC_FUNC_FREE:
+ shm = reg_pair_to_ptr(param->a1, param->a2);
+ tee_shm_free(shm);
+ break;
+ case OPTEE_SMC_RPC_FUNC_FOREIGN_INTR:
+ /*
+ * A foreign interrupt was raised while secure world was
+ * executing, since they are handled in Linux a dummy RPC is
+ * performed to let Linux take the interrupt through the normal
+ * vector.
+ */
+ break;
+ case OPTEE_SMC_RPC_FUNC_CMD:
+ shm = reg_pair_to_ptr(param->a1, param->a2);
+ handle_rpc_func_cmd(ctx, optee, shm, call_ctx);
+ break;
+ default:
+ pr_warn("Unknown RPC func 0x%x\n",
+ (u32)OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0));
+ break;
+ }
+
+ param->a0 = OPTEE_SMC_CALL_RETURN_FROM_RPC;
+}
diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c
new file mode 100644
index 0000000..4939781
--- /dev/null
+++ b/drivers/tee/optee/shm_pool.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ * Copyright (c) 2017, EPAM Systems
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+#include "shm_pool.h"
+
+static int pool_op_alloc(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm, size_t size)
+{
+ unsigned int order = get_order(size);
+ struct page *page;
+
+ page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+ if (!page)
+ return -ENOMEM;
+
+ shm->kaddr = page_address(page);
+ shm->paddr = page_to_phys(page);
+ shm->size = PAGE_SIZE << order;
+
+ return 0;
+}
+
+static void pool_op_free(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm)
+{
+ free_pages((unsigned long)shm->kaddr, get_order(shm->size));
+ shm->kaddr = NULL;
+}
+
+static void pool_op_destroy_poolmgr(struct tee_shm_pool_mgr *poolm)
+{
+ kfree(poolm);
+}
+
+static const struct tee_shm_pool_mgr_ops pool_ops = {
+ .alloc = pool_op_alloc,
+ .free = pool_op_free,
+ .destroy_poolmgr = pool_op_destroy_poolmgr,
+};
+
+/**
+ * optee_shm_pool_alloc_pages() - create page-based allocator pool
+ *
+ * This pool is used when OP-TEE supports dymanic SHM. In this case
+ * command buffers and such are allocated from kernel's own memory.
+ */
+struct tee_shm_pool_mgr *optee_shm_pool_alloc_pages(void)
+{
+ struct tee_shm_pool_mgr *mgr = kzalloc(sizeof(*mgr), GFP_KERNEL);
+
+ if (!mgr)
+ return ERR_PTR(-ENOMEM);
+
+ mgr->ops = &pool_ops;
+
+ return mgr;
+}
diff --git a/drivers/tee/optee/shm_pool.h b/drivers/tee/optee/shm_pool.h
new file mode 100644
index 0000000..4e753c3b
--- /dev/null
+++ b/drivers/tee/optee/shm_pool.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ * Copyright (c) 2016, EPAM Systems
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef SHM_POOL_H
+#define SHM_POOL_H
+
+#include <linux/tee_drv.h>
+
+struct tee_shm_pool_mgr *optee_shm_pool_alloc_pages(void);
+
+#endif
diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c
new file mode 100644
index 0000000..df35fc0
--- /dev/null
+++ b/drivers/tee/optee/supp.c
@@ -0,0 +1,382 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+
+struct optee_supp_req {
+ struct list_head link;
+
+ bool busy;
+ u32 func;
+ u32 ret;
+ size_t num_params;
+ struct tee_param *param;
+
+ struct completion c;
+};
+
+void optee_supp_init(struct optee_supp *supp)
+{
+ memset(supp, 0, sizeof(*supp));
+ mutex_init(&supp->mutex);
+ init_completion(&supp->reqs_c);
+ idr_init(&supp->idr);
+ INIT_LIST_HEAD(&supp->reqs);
+ supp->req_id = -1;
+}
+
+void optee_supp_uninit(struct optee_supp *supp)
+{
+ mutex_destroy(&supp->mutex);
+ idr_destroy(&supp->idr);
+}
+
+void optee_supp_release(struct optee_supp *supp)
+{
+ int id;
+ struct optee_supp_req *req;
+ struct optee_supp_req *req_tmp;
+
+ mutex_lock(&supp->mutex);
+
+ /* Abort all request retrieved by supplicant */
+ idr_for_each_entry(&supp->idr, req, id) {
+ req->busy = false;
+ idr_remove(&supp->idr, id);
+ req->ret = TEEC_ERROR_COMMUNICATION;
+ complete(&req->c);
+ }
+
+ /* Abort all queued requests */
+ list_for_each_entry_safe(req, req_tmp, &supp->reqs, link) {
+ list_del(&req->link);
+ req->ret = TEEC_ERROR_COMMUNICATION;
+ complete(&req->c);
+ }
+
+ supp->ctx = NULL;
+ supp->req_id = -1;
+
+ mutex_unlock(&supp->mutex);
+}
+
+/**
+ * optee_supp_thrd_req() - request service from supplicant
+ * @ctx: context doing the request
+ * @func: function requested
+ * @num_params: number of elements in @param array
+ * @param: parameters for function
+ *
+ * Returns result of operation to be passed to secure world
+ */
+u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
+ struct tee_param *param)
+
+{
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct optee_supp *supp = &optee->supp;
+ struct optee_supp_req *req = kzalloc(sizeof(*req), GFP_KERNEL);
+ bool interruptable;
+ u32 ret;
+
+ if (!req)
+ return TEEC_ERROR_OUT_OF_MEMORY;
+
+ init_completion(&req->c);
+ req->func = func;
+ req->num_params = num_params;
+ req->param = param;
+
+ /* Insert the request in the request list */
+ mutex_lock(&supp->mutex);
+ list_add_tail(&req->link, &supp->reqs);
+ mutex_unlock(&supp->mutex);
+
+ /* Tell an eventual waiter there's a new request */
+ complete(&supp->reqs_c);
+
+ /*
+ * Wait for supplicant to process and return result, once we've
+ * returned from wait_for_completion(&req->c) successfully we have
+ * exclusive access again.
+ */
+ while (wait_for_completion_interruptible(&req->c)) {
+ mutex_lock(&supp->mutex);
+ interruptable = !supp->ctx;
+ if (interruptable) {
+ /*
+ * There's no supplicant available and since the
+ * supp->mutex currently is held none can
+ * become available until the mutex released
+ * again.
+ *
+ * Interrupting an RPC to supplicant is only
+ * allowed as a way of slightly improving the user
+ * experience in case the supplicant hasn't been
+ * started yet. During normal operation the supplicant
+ * will serve all requests in a timely manner and
+ * interrupting then wouldn't make sense.
+ */
+ interruptable = !req->busy;
+ if (!req->busy)
+ list_del(&req->link);
+ }
+ mutex_unlock(&supp->mutex);
+
+ if (interruptable) {
+ req->ret = TEEC_ERROR_COMMUNICATION;
+ break;
+ }
+ }
+
+ ret = req->ret;
+ kfree(req);
+
+ return ret;
+}
+
+static struct optee_supp_req *supp_pop_entry(struct optee_supp *supp,
+ int num_params, int *id)
+{
+ struct optee_supp_req *req;
+
+ if (supp->req_id != -1) {
+ /*
+ * Supplicant should not mix synchronous and asnynchronous
+ * requests.
+ */
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (list_empty(&supp->reqs))
+ return NULL;
+
+ req = list_first_entry(&supp->reqs, struct optee_supp_req, link);
+
+ if (num_params < req->num_params) {
+ /* Not enough room for parameters */
+ return ERR_PTR(-EINVAL);
+ }
+
+ *id = idr_alloc(&supp->idr, req, 1, 0, GFP_KERNEL);
+ if (*id < 0)
+ return ERR_PTR(-ENOMEM);
+
+ list_del(&req->link);
+ req->busy = true;
+
+ return req;
+}
+
+static int supp_check_recv_params(size_t num_params, struct tee_param *params,
+ size_t *num_meta)
+{
+ size_t n;
+
+ if (!num_params)
+ return -EINVAL;
+
+ /*
+ * If there's memrefs we need to decrease those as they where
+ * increased earlier and we'll even refuse to accept any below.
+ */
+ for (n = 0; n < num_params; n++)
+ if (tee_param_is_memref(params + n) && params[n].u.memref.shm)
+ tee_shm_put(params[n].u.memref.shm);
+
+ /*
+ * We only expect parameters as TEE_IOCTL_PARAM_ATTR_TYPE_NONE with
+ * or without the TEE_IOCTL_PARAM_ATTR_META bit set.
+ */
+ for (n = 0; n < num_params; n++)
+ if (params[n].attr &&
+ params[n].attr != TEE_IOCTL_PARAM_ATTR_META)
+ return -EINVAL;
+
+ /* At most we'll need one meta parameter so no need to check for more */
+ if (params->attr == TEE_IOCTL_PARAM_ATTR_META)
+ *num_meta = 1;
+ else
+ *num_meta = 0;
+
+ return 0;
+}
+
+/**
+ * optee_supp_recv() - receive request for supplicant
+ * @ctx: context receiving the request
+ * @func: requested function in supplicant
+ * @num_params: number of elements allocated in @param, updated with number
+ * used elements
+ * @param: space for parameters for @func
+ *
+ * Returns 0 on success or <0 on failure
+ */
+int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct optee_supp *supp = &optee->supp;
+ struct optee_supp_req *req = NULL;
+ int id;
+ size_t num_meta;
+ int rc;
+
+ rc = supp_check_recv_params(*num_params, param, &num_meta);
+ if (rc)
+ return rc;
+
+ while (true) {
+ mutex_lock(&supp->mutex);
+ req = supp_pop_entry(supp, *num_params - num_meta, &id);
+ mutex_unlock(&supp->mutex);
+
+ if (req) {
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+ break;
+ }
+
+ /*
+ * If we didn't get a request we'll block in
+ * wait_for_completion() to avoid needless spinning.
+ *
+ * This is where supplicant will be hanging most of
+ * the time, let's make this interruptable so we
+ * can easily restart supplicant if needed.
+ */
+ if (wait_for_completion_interruptible(&supp->reqs_c))
+ return -ERESTARTSYS;
+ }
+
+ if (num_meta) {
+ /*
+ * tee-supplicant support meta parameters -> requsts can be
+ * processed asynchronously.
+ */
+ param->attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT |
+ TEE_IOCTL_PARAM_ATTR_META;
+ param->u.value.a = id;
+ param->u.value.b = 0;
+ param->u.value.c = 0;
+ } else {
+ mutex_lock(&supp->mutex);
+ supp->req_id = id;
+ mutex_unlock(&supp->mutex);
+ }
+
+ *func = req->func;
+ *num_params = req->num_params + num_meta;
+ memcpy(param + num_meta, req->param,
+ sizeof(struct tee_param) * req->num_params);
+
+ return 0;
+}
+
+static struct optee_supp_req *supp_pop_req(struct optee_supp *supp,
+ size_t num_params,
+ struct tee_param *param,
+ size_t *num_meta)
+{
+ struct optee_supp_req *req;
+ int id;
+ size_t nm;
+ const u32 attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT |
+ TEE_IOCTL_PARAM_ATTR_META;
+
+ if (!num_params)
+ return ERR_PTR(-EINVAL);
+
+ if (supp->req_id == -1) {
+ if (param->attr != attr)
+ return ERR_PTR(-EINVAL);
+ id = param->u.value.a;
+ nm = 1;
+ } else {
+ id = supp->req_id;
+ nm = 0;
+ }
+
+ req = idr_find(&supp->idr, id);
+ if (!req)
+ return ERR_PTR(-ENOENT);
+
+ if ((num_params - nm) != req->num_params)
+ return ERR_PTR(-EINVAL);
+
+ req->busy = false;
+ idr_remove(&supp->idr, id);
+ supp->req_id = -1;
+ *num_meta = nm;
+
+ return req;
+}
+
+/**
+ * optee_supp_send() - send result of request from supplicant
+ * @ctx: context sending result
+ * @ret: return value of request
+ * @num_params: number of parameters returned
+ * @param: returned parameters
+ *
+ * Returns 0 on success or <0 on failure.
+ */
+int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct optee_supp *supp = &optee->supp;
+ struct optee_supp_req *req;
+ size_t n;
+ size_t num_meta;
+
+ mutex_lock(&supp->mutex);
+ req = supp_pop_req(supp, num_params, param, &num_meta);
+ mutex_unlock(&supp->mutex);
+
+ if (IS_ERR(req)) {
+ /* Something is wrong, let supplicant restart. */
+ return PTR_ERR(req);
+ }
+
+ /* Update out and in/out parameters */
+ for (n = 0; n < req->num_params; n++) {
+ struct tee_param *p = req->param + n;
+
+ switch (p->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ p->u.value.a = param[n + num_meta].u.value.a;
+ p->u.value.b = param[n + num_meta].u.value.b;
+ p->u.value.c = param[n + num_meta].u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ p->u.memref.size = param[n + num_meta].u.memref.size;
+ break;
+ default:
+ break;
+ }
+ }
+ req->ret = ret;
+
+ /* Let the requesting thread continue */
+ complete(&req->c);
+
+ return 0;
+}
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
new file mode 100644
index 0000000..6c4b200
--- /dev/null
+++ b/drivers/tee/tee_core.c
@@ -0,0 +1,949 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/idr.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include <linux/uaccess.h>
+#include "tee_private.h"
+
+#define TEE_NUM_DEVICES 32
+
+#define TEE_IOCTL_PARAM_SIZE(x) (sizeof(struct tee_param) * (x))
+
+/*
+ * Unprivileged devices in the lower half range and privileged devices in
+ * the upper half range.
+ */
+static DECLARE_BITMAP(dev_mask, TEE_NUM_DEVICES);
+static DEFINE_SPINLOCK(driver_lock);
+
+static struct class *tee_class;
+static dev_t tee_devt;
+
+static int tee_open(struct inode *inode, struct file *filp)
+{
+ int rc;
+ struct tee_device *teedev;
+ struct tee_context *ctx;
+
+ teedev = container_of(inode->i_cdev, struct tee_device, cdev);
+ if (!tee_device_get(teedev))
+ return -EINVAL;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ kref_init(&ctx->refcount);
+ ctx->teedev = teedev;
+ INIT_LIST_HEAD(&ctx->list_shm);
+ filp->private_data = ctx;
+ rc = teedev->desc->ops->open(ctx);
+ if (rc)
+ goto err;
+
+ return 0;
+err:
+ kfree(ctx);
+ tee_device_put(teedev);
+ return rc;
+}
+
+void teedev_ctx_get(struct tee_context *ctx)
+{
+ if (ctx->releasing)
+ return;
+
+ kref_get(&ctx->refcount);
+}
+
+static void teedev_ctx_release(struct kref *ref)
+{
+ struct tee_context *ctx = container_of(ref, struct tee_context,
+ refcount);
+ ctx->releasing = true;
+ ctx->teedev->desc->ops->release(ctx);
+ kfree(ctx);
+}
+
+void teedev_ctx_put(struct tee_context *ctx)
+{
+ if (ctx->releasing)
+ return;
+
+ kref_put(&ctx->refcount, teedev_ctx_release);
+}
+
+static void teedev_close_context(struct tee_context *ctx)
+{
+ tee_device_put(ctx->teedev);
+ teedev_ctx_put(ctx);
+}
+
+static int tee_release(struct inode *inode, struct file *filp)
+{
+ teedev_close_context(filp->private_data);
+ return 0;
+}
+
+static int tee_ioctl_version(struct tee_context *ctx,
+ struct tee_ioctl_version_data __user *uvers)
+{
+ struct tee_ioctl_version_data vers;
+
+ ctx->teedev->desc->ops->get_version(ctx->teedev, &vers);
+
+ if (ctx->teedev->desc->flags & TEE_DESC_PRIVILEGED)
+ vers.gen_caps |= TEE_GEN_CAP_PRIVILEGED;
+
+ if (copy_to_user(uvers, &vers, sizeof(vers)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int tee_ioctl_shm_alloc(struct tee_context *ctx,
+ struct tee_ioctl_shm_alloc_data __user *udata)
+{
+ long ret;
+ struct tee_ioctl_shm_alloc_data data;
+ struct tee_shm *shm;
+
+ if (copy_from_user(&data, udata, sizeof(data)))
+ return -EFAULT;
+
+ /* Currently no input flags are supported */
+ if (data.flags)
+ return -EINVAL;
+
+ shm = tee_shm_alloc(ctx, data.size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ data.id = shm->id;
+ data.flags = shm->flags;
+ data.size = shm->size;
+
+ if (copy_to_user(udata, &data, sizeof(data)))
+ ret = -EFAULT;
+ else
+ ret = tee_shm_get_fd(shm);
+
+ /*
+ * When user space closes the file descriptor the shared memory
+ * should be freed or if tee_shm_get_fd() failed then it will
+ * be freed immediately.
+ */
+ tee_shm_put(shm);
+ return ret;
+}
+
+static int
+tee_ioctl_shm_register(struct tee_context *ctx,
+ struct tee_ioctl_shm_register_data __user *udata)
+{
+ long ret;
+ struct tee_ioctl_shm_register_data data;
+ struct tee_shm *shm;
+
+ if (copy_from_user(&data, udata, sizeof(data)))
+ return -EFAULT;
+
+ /* Currently no input flags are supported */
+ if (data.flags)
+ return -EINVAL;
+
+ shm = tee_shm_register(ctx, data.addr, data.length,
+ TEE_SHM_DMA_BUF | TEE_SHM_USER_MAPPED);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ data.id = shm->id;
+ data.flags = shm->flags;
+ data.length = shm->size;
+
+ if (copy_to_user(udata, &data, sizeof(data)))
+ ret = -EFAULT;
+ else
+ ret = tee_shm_get_fd(shm);
+ /*
+ * When user space closes the file descriptor the shared memory
+ * should be freed or if tee_shm_get_fd() failed then it will
+ * be freed immediately.
+ */
+ tee_shm_put(shm);
+ return ret;
+}
+
+static int params_from_user(struct tee_context *ctx, struct tee_param *params,
+ size_t num_params,
+ struct tee_ioctl_param __user *uparams)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_shm *shm;
+ struct tee_ioctl_param ip;
+
+ if (copy_from_user(&ip, uparams + n, sizeof(ip)))
+ return -EFAULT;
+
+ /* All unused attribute bits has to be zero */
+ if (ip.attr & ~TEE_IOCTL_PARAM_ATTR_MASK)
+ return -EINVAL;
+
+ params[n].attr = ip.attr;
+ switch (ip.attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_NONE:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ params[n].u.value.a = ip.a;
+ params[n].u.value.b = ip.b;
+ params[n].u.value.c = ip.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ /*
+ * If we fail to get a pointer to a shared memory
+ * object (and increase the ref count) from an
+ * identifier we return an error. All pointers that
+ * has been added in params have an increased ref
+ * count. It's the callers responibility to do
+ * tee_shm_put() on all resolved pointers.
+ */
+ shm = tee_shm_get_from_id(ctx, ip.c);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ params[n].u.memref.shm_offs = ip.a;
+ params[n].u.memref.size = ip.b;
+ params[n].u.memref.shm = shm;
+ break;
+ default:
+ /* Unknown attribute */
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static int params_to_user(struct tee_ioctl_param __user *uparams,
+ size_t num_params, struct tee_param *params)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_ioctl_param __user *up = uparams + n;
+ struct tee_param *p = params + n;
+
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ if (put_user(p->u.value.a, &up->a) ||
+ put_user(p->u.value.b, &up->b) ||
+ put_user(p->u.value.c, &up->c))
+ return -EFAULT;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ if (put_user((u64)p->u.memref.size, &up->b))
+ return -EFAULT;
+ default:
+ break;
+ }
+ }
+ return 0;
+}
+
+static int tee_ioctl_open_session(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ size_t n;
+ struct tee_ioctl_buf_data buf;
+ struct tee_ioctl_open_session_arg __user *uarg;
+ struct tee_ioctl_open_session_arg arg;
+ struct tee_ioctl_param __user *uparams = NULL;
+ struct tee_param *params = NULL;
+ bool have_session = false;
+
+ if (!ctx->teedev->desc->ops->open_session)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_ioctl_open_session_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+ return -EINVAL;
+
+ if (arg.num_params) {
+ params = kcalloc(arg.num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+ uparams = uarg->params;
+ rc = params_from_user(ctx, params, arg.num_params, uparams);
+ if (rc)
+ goto out;
+ }
+
+ rc = ctx->teedev->desc->ops->open_session(ctx, &arg, params);
+ if (rc)
+ goto out;
+ have_session = true;
+
+ if (put_user(arg.session, &uarg->session) ||
+ put_user(arg.ret, &uarg->ret) ||
+ put_user(arg.ret_origin, &uarg->ret_origin)) {
+ rc = -EFAULT;
+ goto out;
+ }
+ rc = params_to_user(uparams, arg.num_params, params);
+out:
+ /*
+ * If we've succeeded to open the session but failed to communicate
+ * it back to user space, close the session again to avoid leakage.
+ */
+ if (rc && have_session && ctx->teedev->desc->ops->close_session)
+ ctx->teedev->desc->ops->close_session(ctx, arg.session);
+
+ if (params) {
+ /* Decrease ref count for all valid shared memory pointers */
+ for (n = 0; n < arg.num_params; n++)
+ if (tee_param_is_memref(params + n) &&
+ params[n].u.memref.shm)
+ tee_shm_put(params[n].u.memref.shm);
+ kfree(params);
+ }
+
+ return rc;
+}
+
+static int tee_ioctl_invoke(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ size_t n;
+ struct tee_ioctl_buf_data buf;
+ struct tee_ioctl_invoke_arg __user *uarg;
+ struct tee_ioctl_invoke_arg arg;
+ struct tee_ioctl_param __user *uparams = NULL;
+ struct tee_param *params = NULL;
+
+ if (!ctx->teedev->desc->ops->invoke_func)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_ioctl_invoke_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+ return -EINVAL;
+
+ if (arg.num_params) {
+ params = kcalloc(arg.num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+ uparams = uarg->params;
+ rc = params_from_user(ctx, params, arg.num_params, uparams);
+ if (rc)
+ goto out;
+ }
+
+ rc = ctx->teedev->desc->ops->invoke_func(ctx, &arg, params);
+ if (rc)
+ goto out;
+
+ if (put_user(arg.ret, &uarg->ret) ||
+ put_user(arg.ret_origin, &uarg->ret_origin)) {
+ rc = -EFAULT;
+ goto out;
+ }
+ rc = params_to_user(uparams, arg.num_params, params);
+out:
+ if (params) {
+ /* Decrease ref count for all valid shared memory pointers */
+ for (n = 0; n < arg.num_params; n++)
+ if (tee_param_is_memref(params + n) &&
+ params[n].u.memref.shm)
+ tee_shm_put(params[n].u.memref.shm);
+ kfree(params);
+ }
+ return rc;
+}
+
+static int tee_ioctl_cancel(struct tee_context *ctx,
+ struct tee_ioctl_cancel_arg __user *uarg)
+{
+ struct tee_ioctl_cancel_arg arg;
+
+ if (!ctx->teedev->desc->ops->cancel_req)
+ return -EINVAL;
+
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ return ctx->teedev->desc->ops->cancel_req(ctx, arg.cancel_id,
+ arg.session);
+}
+
+static int
+tee_ioctl_close_session(struct tee_context *ctx,
+ struct tee_ioctl_close_session_arg __user *uarg)
+{
+ struct tee_ioctl_close_session_arg arg;
+
+ if (!ctx->teedev->desc->ops->close_session)
+ return -EINVAL;
+
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ return ctx->teedev->desc->ops->close_session(ctx, arg.session);
+}
+
+static int params_to_supp(struct tee_context *ctx,
+ struct tee_ioctl_param __user *uparams,
+ size_t num_params, struct tee_param *params)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_ioctl_param ip;
+ struct tee_param *p = params + n;
+
+ ip.attr = p->attr;
+ switch (p->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ ip.a = p->u.value.a;
+ ip.b = p->u.value.b;
+ ip.c = p->u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ ip.b = p->u.memref.size;
+ if (!p->u.memref.shm) {
+ ip.a = 0;
+ ip.c = (u64)-1; /* invalid shm id */
+ break;
+ }
+ ip.a = p->u.memref.shm_offs;
+ ip.c = p->u.memref.shm->id;
+ break;
+ default:
+ ip.a = 0;
+ ip.b = 0;
+ ip.c = 0;
+ break;
+ }
+
+ if (copy_to_user(uparams + n, &ip, sizeof(ip)))
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static int tee_ioctl_supp_recv(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ struct tee_ioctl_buf_data buf;
+ struct tee_iocl_supp_recv_arg __user *uarg;
+ struct tee_param *params;
+ u32 num_params;
+ u32 func;
+
+ if (!ctx->teedev->desc->ops->supp_recv)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_iocl_supp_recv_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (get_user(num_params, &uarg->num_params))
+ return -EFAULT;
+
+ if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) != buf.buf_len)
+ return -EINVAL;
+
+ params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+
+ rc = params_from_user(ctx, params, num_params, uarg->params);
+ if (rc)
+ goto out;
+
+ rc = ctx->teedev->desc->ops->supp_recv(ctx, &func, &num_params, params);
+ if (rc)
+ goto out;
+
+ if (put_user(func, &uarg->func) ||
+ put_user(num_params, &uarg->num_params)) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = params_to_supp(ctx, uarg->params, num_params, params);
+out:
+ kfree(params);
+ return rc;
+}
+
+static int params_from_supp(struct tee_param *params, size_t num_params,
+ struct tee_ioctl_param __user *uparams)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_param *p = params + n;
+ struct tee_ioctl_param ip;
+
+ if (copy_from_user(&ip, uparams + n, sizeof(ip)))
+ return -EFAULT;
+
+ /* All unused attribute bits has to be zero */
+ if (ip.attr & ~TEE_IOCTL_PARAM_ATTR_MASK)
+ return -EINVAL;
+
+ p->attr = ip.attr;
+ switch (ip.attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ /* Only out and in/out values can be updated */
+ p->u.value.a = ip.a;
+ p->u.value.b = ip.b;
+ p->u.value.c = ip.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ /*
+ * Only the size of the memref can be updated.
+ * Since we don't have access to the original
+ * parameters here, only store the supplied size.
+ * The driver will copy the updated size into the
+ * original parameters.
+ */
+ p->u.memref.shm = NULL;
+ p->u.memref.shm_offs = 0;
+ p->u.memref.size = ip.b;
+ break;
+ default:
+ memset(&p->u, 0, sizeof(p->u));
+ break;
+ }
+ }
+ return 0;
+}
+
+static int tee_ioctl_supp_send(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ long rc;
+ struct tee_ioctl_buf_data buf;
+ struct tee_iocl_supp_send_arg __user *uarg;
+ struct tee_param *params;
+ u32 num_params;
+ u32 ret;
+
+ /* Not valid for this driver */
+ if (!ctx->teedev->desc->ops->supp_send)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_iocl_supp_send_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (get_user(ret, &uarg->ret) ||
+ get_user(num_params, &uarg->num_params))
+ return -EFAULT;
+
+ if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) > buf.buf_len)
+ return -EINVAL;
+
+ params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+
+ rc = params_from_supp(params, num_params, uarg->params);
+ if (rc)
+ goto out;
+
+ rc = ctx->teedev->desc->ops->supp_send(ctx, ret, num_params, params);
+out:
+ kfree(params);
+ return rc;
+}
+
+static long tee_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct tee_context *ctx = filp->private_data;
+ void __user *uarg = (void __user *)arg;
+
+ switch (cmd) {
+ case TEE_IOC_VERSION:
+ return tee_ioctl_version(ctx, uarg);
+ case TEE_IOC_SHM_ALLOC:
+ return tee_ioctl_shm_alloc(ctx, uarg);
+ case TEE_IOC_SHM_REGISTER:
+ return tee_ioctl_shm_register(ctx, uarg);
+ case TEE_IOC_OPEN_SESSION:
+ return tee_ioctl_open_session(ctx, uarg);
+ case TEE_IOC_INVOKE:
+ return tee_ioctl_invoke(ctx, uarg);
+ case TEE_IOC_CANCEL:
+ return tee_ioctl_cancel(ctx, uarg);
+ case TEE_IOC_CLOSE_SESSION:
+ return tee_ioctl_close_session(ctx, uarg);
+ case TEE_IOC_SUPPL_RECV:
+ return tee_ioctl_supp_recv(ctx, uarg);
+ case TEE_IOC_SUPPL_SEND:
+ return tee_ioctl_supp_send(ctx, uarg);
+ default:
+ return -EINVAL;
+ }
+}
+
+static const struct file_operations tee_fops = {
+ .owner = THIS_MODULE,
+ .open = tee_open,
+ .release = tee_release,
+ .unlocked_ioctl = tee_ioctl,
+ .compat_ioctl = tee_ioctl,
+};
+
+static void tee_release_device(struct device *dev)
+{
+ struct tee_device *teedev = container_of(dev, struct tee_device, dev);
+
+ spin_lock(&driver_lock);
+ clear_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+ mutex_destroy(&teedev->mutex);
+ idr_destroy(&teedev->idr);
+ kfree(teedev);
+}
+
+/**
+ * tee_device_alloc() - Allocate a new struct tee_device instance
+ * @teedesc: Descriptor for this driver
+ * @dev: Parent device for this device
+ * @pool: Shared memory pool, NULL if not used
+ * @driver_data: Private driver data for this device
+ *
+ * Allocates a new struct tee_device instance. The device is
+ * removed by tee_device_unregister().
+ *
+ * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure
+ */
+struct tee_device *tee_device_alloc(const struct tee_desc *teedesc,
+ struct device *dev,
+ struct tee_shm_pool *pool,
+ void *driver_data)
+{
+ struct tee_device *teedev;
+ void *ret;
+ int rc;
+ int offs = 0;
+
+ if (!teedesc || !teedesc->name || !teedesc->ops ||
+ !teedesc->ops->get_version || !teedesc->ops->open ||
+ !teedesc->ops->release || !pool)
+ return ERR_PTR(-EINVAL);
+
+ teedev = kzalloc(sizeof(*teedev), GFP_KERNEL);
+ if (!teedev) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ if (teedesc->flags & TEE_DESC_PRIVILEGED)
+ offs = TEE_NUM_DEVICES / 2;
+
+ spin_lock(&driver_lock);
+ teedev->id = find_next_zero_bit(dev_mask, TEE_NUM_DEVICES, offs);
+ if (teedev->id < TEE_NUM_DEVICES)
+ set_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+
+ if (teedev->id >= TEE_NUM_DEVICES) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ snprintf(teedev->name, sizeof(teedev->name), "tee%s%d",
+ teedesc->flags & TEE_DESC_PRIVILEGED ? "priv" : "",
+ teedev->id - offs);
+
+ teedev->dev.class = tee_class;
+ teedev->dev.release = tee_release_device;
+ teedev->dev.parent = dev;
+
+ teedev->dev.devt = MKDEV(MAJOR(tee_devt), teedev->id);
+
+ rc = dev_set_name(&teedev->dev, "%s", teedev->name);
+ if (rc) {
+ ret = ERR_PTR(rc);
+ goto err_devt;
+ }
+
+ cdev_init(&teedev->cdev, &tee_fops);
+ teedev->cdev.owner = teedesc->owner;
+ teedev->cdev.kobj.parent = &teedev->dev.kobj;
+
+ dev_set_drvdata(&teedev->dev, driver_data);
+ device_initialize(&teedev->dev);
+
+ /* 1 as tee_device_unregister() does one final tee_device_put() */
+ teedev->num_users = 1;
+ init_completion(&teedev->c_no_users);
+ mutex_init(&teedev->mutex);
+ idr_init(&teedev->idr);
+
+ teedev->desc = teedesc;
+ teedev->pool = pool;
+
+ return teedev;
+err_devt:
+ unregister_chrdev_region(teedev->dev.devt, 1);
+err:
+ pr_err("could not register %s driver\n",
+ teedesc->flags & TEE_DESC_PRIVILEGED ? "privileged" : "client");
+ if (teedev && teedev->id < TEE_NUM_DEVICES) {
+ spin_lock(&driver_lock);
+ clear_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+ }
+ kfree(teedev);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tee_device_alloc);
+
+static ssize_t implementation_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct tee_device *teedev = container_of(dev, struct tee_device, dev);
+ struct tee_ioctl_version_data vers;
+
+ teedev->desc->ops->get_version(teedev, &vers);
+ return scnprintf(buf, PAGE_SIZE, "%d\n", vers.impl_id);
+}
+static DEVICE_ATTR_RO(implementation_id);
+
+static struct attribute *tee_dev_attrs[] = {
+ &dev_attr_implementation_id.attr,
+ NULL
+};
+
+static const struct attribute_group tee_dev_group = {
+ .attrs = tee_dev_attrs,
+};
+
+/**
+ * tee_device_register() - Registers a TEE device
+ * @teedev: Device to register
+ *
+ * tee_device_unregister() need to be called to remove the @teedev if
+ * this function fails.
+ *
+ * @returns < 0 on failure
+ */
+int tee_device_register(struct tee_device *teedev)
+{
+ int rc;
+
+ if (teedev->flags & TEE_DEVICE_FLAG_REGISTERED) {
+ dev_err(&teedev->dev, "attempt to register twice\n");
+ return -EINVAL;
+ }
+
+ rc = cdev_add(&teedev->cdev, teedev->dev.devt, 1);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "unable to cdev_add() %s, major %d, minor %d, err=%d\n",
+ teedev->name, MAJOR(teedev->dev.devt),
+ MINOR(teedev->dev.devt), rc);
+ return rc;
+ }
+
+ rc = device_add(&teedev->dev);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "unable to device_add() %s, major %d, minor %d, err=%d\n",
+ teedev->name, MAJOR(teedev->dev.devt),
+ MINOR(teedev->dev.devt), rc);
+ goto err_device_add;
+ }
+
+ rc = sysfs_create_group(&teedev->dev.kobj, &tee_dev_group);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "failed to create sysfs attributes, err=%d\n", rc);
+ goto err_sysfs_create_group;
+ }
+
+ teedev->flags |= TEE_DEVICE_FLAG_REGISTERED;
+ return 0;
+
+err_sysfs_create_group:
+ device_del(&teedev->dev);
+err_device_add:
+ cdev_del(&teedev->cdev);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tee_device_register);
+
+void tee_device_put(struct tee_device *teedev)
+{
+ mutex_lock(&teedev->mutex);
+ /* Shouldn't put in this state */
+ if (!WARN_ON(!teedev->desc)) {
+ teedev->num_users--;
+ if (!teedev->num_users) {
+ teedev->desc = NULL;
+ complete(&teedev->c_no_users);
+ }
+ }
+ mutex_unlock(&teedev->mutex);
+}
+
+bool tee_device_get(struct tee_device *teedev)
+{
+ mutex_lock(&teedev->mutex);
+ if (!teedev->desc) {
+ mutex_unlock(&teedev->mutex);
+ return false;
+ }
+ teedev->num_users++;
+ mutex_unlock(&teedev->mutex);
+ return true;
+}
+
+/**
+ * tee_device_unregister() - Removes a TEE device
+ * @teedev: Device to unregister
+ *
+ * This function should be called to remove the @teedev even if
+ * tee_device_register() hasn't been called yet. Does nothing if
+ * @teedev is NULL.
+ */
+void tee_device_unregister(struct tee_device *teedev)
+{
+ if (!teedev)
+ return;
+
+ if (teedev->flags & TEE_DEVICE_FLAG_REGISTERED) {
+ sysfs_remove_group(&teedev->dev.kobj, &tee_dev_group);
+ cdev_del(&teedev->cdev);
+ device_del(&teedev->dev);
+ }
+
+ tee_device_put(teedev);
+ wait_for_completion(&teedev->c_no_users);
+
+ /*
+ * No need to take a mutex any longer now since teedev->desc was
+ * set to NULL before teedev->c_no_users was completed.
+ */
+
+ teedev->pool = NULL;
+
+ put_device(&teedev->dev);
+}
+EXPORT_SYMBOL_GPL(tee_device_unregister);
+
+/**
+ * tee_get_drvdata() - Return driver_data pointer
+ * @teedev: Device containing the driver_data pointer
+ * @returns the driver_data pointer supplied to tee_register().
+ */
+void *tee_get_drvdata(struct tee_device *teedev)
+{
+ return dev_get_drvdata(&teedev->dev);
+}
+EXPORT_SYMBOL_GPL(tee_get_drvdata);
+
+static int __init tee_init(void)
+{
+ int rc;
+
+ tee_class = class_create(THIS_MODULE, "tee");
+ if (IS_ERR(tee_class)) {
+ pr_err("couldn't create class\n");
+ return PTR_ERR(tee_class);
+ }
+
+ rc = alloc_chrdev_region(&tee_devt, 0, TEE_NUM_DEVICES, "tee");
+ if (rc) {
+ pr_err("failed to allocate char dev region\n");
+ class_destroy(tee_class);
+ tee_class = NULL;
+ }
+
+ return rc;
+}
+
+static void __exit tee_exit(void)
+{
+ class_destroy(tee_class);
+ tee_class = NULL;
+ unregister_chrdev_region(tee_devt, TEE_NUM_DEVICES);
+}
+
+subsys_initcall(tee_init);
+module_exit(tee_exit);
+
+MODULE_AUTHOR("Linaro");
+MODULE_DESCRIPTION("TEE Driver");
+MODULE_VERSION("1.0");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/tee/tee_private.h b/drivers/tee/tee_private.h
new file mode 100644
index 0000000..85d99d6
--- /dev/null
+++ b/drivers/tee/tee_private.h
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef TEE_PRIVATE_H
+#define TEE_PRIVATE_H
+
+#include <linux/cdev.h>
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+/**
+ * struct tee_shm_pool - shared memory pool
+ * @private_mgr: pool manager for shared memory only between kernel
+ * and secure world
+ * @dma_buf_mgr: pool manager for shared memory exported to user space
+ */
+struct tee_shm_pool {
+ struct tee_shm_pool_mgr *private_mgr;
+ struct tee_shm_pool_mgr *dma_buf_mgr;
+};
+
+#define TEE_DEVICE_FLAG_REGISTERED 0x1
+#define TEE_MAX_DEV_NAME_LEN 32
+
+/**
+ * struct tee_device - TEE Device representation
+ * @name: name of device
+ * @desc: description of device
+ * @id: unique id of device
+ * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above
+ * @dev: embedded basic device structure
+ * @cdev: embedded cdev
+ * @num_users: number of active users of this device
+ * @c_no_user: completion used when unregistering the device
+ * @mutex: mutex protecting @num_users and @idr
+ * @idr: register of shared memory object allocated on this device
+ * @pool: shared memory pool
+ */
+struct tee_device {
+ char name[TEE_MAX_DEV_NAME_LEN];
+ const struct tee_desc *desc;
+ int id;
+ unsigned int flags;
+
+ struct device dev;
+ struct cdev cdev;
+
+ size_t num_users;
+ struct completion c_no_users;
+ struct mutex mutex; /* protects num_users and idr */
+
+ struct idr idr;
+ struct tee_shm_pool *pool;
+};
+
+int tee_shm_init(void);
+
+int tee_shm_get_fd(struct tee_shm *shm);
+
+bool tee_device_get(struct tee_device *teedev);
+void tee_device_put(struct tee_device *teedev);
+
+void teedev_ctx_get(struct tee_context *ctx);
+void teedev_ctx_put(struct tee_context *ctx);
+
+#endif /*TEE_PRIVATE_H*/
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
new file mode 100644
index 0000000..cdb52b1
--- /dev/null
+++ b/drivers/tee/tee_shm.c
@@ -0,0 +1,511 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/fdtable.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "tee_private.h"
+
+static void tee_shm_release(struct tee_shm *shm)
+{
+ struct tee_device *teedev = shm->teedev;
+
+ mutex_lock(&teedev->mutex);
+ idr_remove(&teedev->idr, shm->id);
+ if (shm->ctx)
+ list_del(&shm->link);
+ mutex_unlock(&teedev->mutex);
+
+ if (shm->flags & TEE_SHM_POOL) {
+ struct tee_shm_pool_mgr *poolm;
+
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ poolm = teedev->pool->dma_buf_mgr;
+ else
+ poolm = teedev->pool->private_mgr;
+
+ poolm->ops->free(poolm, shm);
+ } else if (shm->flags & TEE_SHM_REGISTER) {
+ size_t n;
+ int rc = teedev->desc->ops->shm_unregister(shm->ctx, shm);
+
+ if (rc)
+ dev_err(teedev->dev.parent,
+ "unregister shm %p failed: %d", shm, rc);
+
+ for (n = 0; n < shm->num_pages; n++)
+ put_page(shm->pages[n]);
+
+ kfree(shm->pages);
+ }
+
+ if (shm->ctx)
+ teedev_ctx_put(shm->ctx);
+
+ kfree(shm);
+
+ tee_device_put(teedev);
+}
+
+static struct sg_table *tee_shm_op_map_dma_buf(struct dma_buf_attachment
+ *attach, enum dma_data_direction dir)
+{
+ return NULL;
+}
+
+static void tee_shm_op_unmap_dma_buf(struct dma_buf_attachment *attach,
+ struct sg_table *table,
+ enum dma_data_direction dir)
+{
+}
+
+static void tee_shm_op_release(struct dma_buf *dmabuf)
+{
+ struct tee_shm *shm = dmabuf->priv;
+
+ tee_shm_release(shm);
+}
+
+static void *tee_shm_op_kmap_atomic(struct dma_buf *dmabuf, unsigned long pgnum)
+{
+ return NULL;
+}
+
+static void *tee_shm_op_kmap(struct dma_buf *dmabuf, unsigned long pgnum)
+{
+ return NULL;
+}
+
+static int tee_shm_op_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+ struct tee_shm *shm = dmabuf->priv;
+ size_t size = vma->vm_end - vma->vm_start;
+
+ /* Refuse sharing shared memory provided by application */
+ if (shm->flags & TEE_SHM_REGISTER)
+ return -EINVAL;
+
+ return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT,
+ size, vma->vm_page_prot);
+}
+
+static const struct dma_buf_ops tee_shm_dma_buf_ops = {
+ .map_dma_buf = tee_shm_op_map_dma_buf,
+ .unmap_dma_buf = tee_shm_op_unmap_dma_buf,
+ .release = tee_shm_op_release,
+ .kmap_atomic = tee_shm_op_kmap_atomic,
+ .kmap = tee_shm_op_kmap,
+ .mmap = tee_shm_op_mmap,
+};
+
+static struct tee_shm *__tee_shm_alloc(struct tee_context *ctx,
+ struct tee_device *teedev,
+ size_t size, u32 flags)
+{
+ struct tee_shm_pool_mgr *poolm = NULL;
+ struct tee_shm *shm;
+ void *ret;
+ int rc;
+
+ if (ctx && ctx->teedev != teedev) {
+ dev_err(teedev->dev.parent, "ctx and teedev mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!(flags & TEE_SHM_MAPPED)) {
+ dev_err(teedev->dev.parent,
+ "only mapped allocations supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF))) {
+ dev_err(teedev->dev.parent, "invalid shm flags 0x%x", flags);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!tee_device_get(teedev))
+ return ERR_PTR(-EINVAL);
+
+ if (!teedev->pool) {
+ /* teedev has been detached from driver */
+ ret = ERR_PTR(-EINVAL);
+ goto err_dev_put;
+ }
+
+ shm = kzalloc(sizeof(*shm), GFP_KERNEL);
+ if (!shm) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err_dev_put;
+ }
+
+ shm->flags = flags | TEE_SHM_POOL;
+ shm->teedev = teedev;
+ shm->ctx = ctx;
+ if (flags & TEE_SHM_DMA_BUF)
+ poolm = teedev->pool->dma_buf_mgr;
+ else
+ poolm = teedev->pool->private_mgr;
+
+ rc = poolm->ops->alloc(poolm, shm, size);
+ if (rc) {
+ ret = ERR_PTR(rc);
+ goto err_kfree;
+ }
+
+ mutex_lock(&teedev->mutex);
+ shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL);
+ mutex_unlock(&teedev->mutex);
+ if (shm->id < 0) {
+ ret = ERR_PTR(shm->id);
+ goto err_pool_free;
+ }
+
+ if (flags & TEE_SHM_DMA_BUF) {
+ DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+ exp_info.ops = &tee_shm_dma_buf_ops;
+ exp_info.size = shm->size;
+ exp_info.flags = O_RDWR;
+ exp_info.priv = shm;
+
+ shm->dmabuf = dma_buf_export(&exp_info);
+ if (IS_ERR(shm->dmabuf)) {
+ ret = ERR_CAST(shm->dmabuf);
+ goto err_rem;
+ }
+ }
+
+ if (ctx) {
+ teedev_ctx_get(ctx);
+ mutex_lock(&teedev->mutex);
+ list_add_tail(&shm->link, &ctx->list_shm);
+ mutex_unlock(&teedev->mutex);
+ }
+
+ return shm;
+err_rem:
+ mutex_lock(&teedev->mutex);
+ idr_remove(&teedev->idr, shm->id);
+ mutex_unlock(&teedev->mutex);
+err_pool_free:
+ poolm->ops->free(poolm, shm);
+err_kfree:
+ kfree(shm);
+err_dev_put:
+ tee_device_put(teedev);
+ return ret;
+}
+
+/**
+ * tee_shm_alloc() - Allocate shared memory
+ * @ctx: Context that allocates the shared memory
+ * @size: Requested size of shared memory
+ * @flags: Flags setting properties for the requested shared memory.
+ *
+ * Memory allocated as global shared memory is automatically freed when the
+ * TEE file pointer is closed. The @flags field uses the bits defined by
+ * TEE_SHM_* in <linux/tee_drv.h>. TEE_SHM_MAPPED must currently always be
+ * set. If TEE_SHM_DMA_BUF global shared memory will be allocated and
+ * associated with a dma-buf handle, else driver private memory.
+ */
+struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
+{
+ return __tee_shm_alloc(ctx, ctx->teedev, size, flags);
+}
+EXPORT_SYMBOL_GPL(tee_shm_alloc);
+
+struct tee_shm *tee_shm_priv_alloc(struct tee_device *teedev, size_t size)
+{
+ return __tee_shm_alloc(NULL, teedev, size, TEE_SHM_MAPPED);
+}
+EXPORT_SYMBOL_GPL(tee_shm_priv_alloc);
+
+struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
+ size_t length, u32 flags)
+{
+ struct tee_device *teedev = ctx->teedev;
+ const u32 req_flags = TEE_SHM_DMA_BUF | TEE_SHM_USER_MAPPED;
+ struct tee_shm *shm;
+ void *ret;
+ int rc;
+ int num_pages;
+ unsigned long start;
+
+ if (flags != req_flags)
+ return ERR_PTR(-ENOTSUPP);
+
+ if (!tee_device_get(teedev))
+ return ERR_PTR(-EINVAL);
+
+ if (!teedev->desc->ops->shm_register ||
+ !teedev->desc->ops->shm_unregister) {
+ tee_device_put(teedev);
+ return ERR_PTR(-ENOTSUPP);
+ }
+
+ teedev_ctx_get(ctx);
+
+ shm = kzalloc(sizeof(*shm), GFP_KERNEL);
+ if (!shm) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ shm->flags = flags | TEE_SHM_REGISTER;
+ shm->teedev = teedev;
+ shm->ctx = ctx;
+ shm->id = -1;
+ start = rounddown(addr, PAGE_SIZE);
+ shm->offset = addr - start;
+ shm->size = length;
+ num_pages = (roundup(addr + length, PAGE_SIZE) - start) / PAGE_SIZE;
+ shm->pages = kcalloc(num_pages, sizeof(*shm->pages), GFP_KERNEL);
+ if (!shm->pages) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ rc = get_user_pages_fast(start, num_pages, 1, shm->pages);
+ if (rc > 0)
+ shm->num_pages = rc;
+ if (rc != num_pages) {
+ if (rc >= 0)
+ rc = -ENOMEM;
+ ret = ERR_PTR(rc);
+ goto err;
+ }
+
+ mutex_lock(&teedev->mutex);
+ shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL);
+ mutex_unlock(&teedev->mutex);
+
+ if (shm->id < 0) {
+ ret = ERR_PTR(shm->id);
+ goto err;
+ }
+
+ rc = teedev->desc->ops->shm_register(ctx, shm, shm->pages,
+ shm->num_pages, start);
+ if (rc) {
+ ret = ERR_PTR(rc);
+ goto err;
+ }
+
+ if (flags & TEE_SHM_DMA_BUF) {
+ DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+ exp_info.ops = &tee_shm_dma_buf_ops;
+ exp_info.size = shm->size;
+ exp_info.flags = O_RDWR;
+ exp_info.priv = shm;
+
+ shm->dmabuf = dma_buf_export(&exp_info);
+ if (IS_ERR(shm->dmabuf)) {
+ ret = ERR_CAST(shm->dmabuf);
+ teedev->desc->ops->shm_unregister(ctx, shm);
+ goto err;
+ }
+ }
+
+ mutex_lock(&teedev->mutex);
+ list_add_tail(&shm->link, &ctx->list_shm);
+ mutex_unlock(&teedev->mutex);
+
+ return shm;
+err:
+ if (shm) {
+ size_t n;
+
+ if (shm->id >= 0) {
+ mutex_lock(&teedev->mutex);
+ idr_remove(&teedev->idr, shm->id);
+ mutex_unlock(&teedev->mutex);
+ }
+ if (shm->pages) {
+ for (n = 0; n < shm->num_pages; n++)
+ put_page(shm->pages[n]);
+ kfree(shm->pages);
+ }
+ }
+ kfree(shm);
+ teedev_ctx_put(ctx);
+ tee_device_put(teedev);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tee_shm_register);
+
+/**
+ * tee_shm_get_fd() - Increase reference count and return file descriptor
+ * @shm: Shared memory handle
+ * @returns user space file descriptor to shared memory
+ */
+int tee_shm_get_fd(struct tee_shm *shm)
+{
+ int fd;
+
+ if (!(shm->flags & TEE_SHM_DMA_BUF))
+ return -EINVAL;
+
+ get_dma_buf(shm->dmabuf);
+ fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
+ if (fd < 0)
+ dma_buf_put(shm->dmabuf);
+ return fd;
+}
+
+/**
+ * tee_shm_free() - Free shared memory
+ * @shm: Handle to shared memory to free
+ */
+void tee_shm_free(struct tee_shm *shm)
+{
+ /*
+ * dma_buf_put() decreases the dmabuf reference counter and will
+ * call tee_shm_release() when the last reference is gone.
+ *
+ * In the case of driver private memory we call tee_shm_release
+ * directly instead as it doesn't have a reference counter.
+ */
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ dma_buf_put(shm->dmabuf);
+ else
+ tee_shm_release(shm);
+}
+EXPORT_SYMBOL_GPL(tee_shm_free);
+
+/**
+ * tee_shm_va2pa() - Get physical address of a virtual address
+ * @shm: Shared memory handle
+ * @va: Virtual address to tranlsate
+ * @pa: Returned physical address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa)
+{
+ if (!(shm->flags & TEE_SHM_MAPPED))
+ return -EINVAL;
+ /* Check that we're in the range of the shm */
+ if ((char *)va < (char *)shm->kaddr)
+ return -EINVAL;
+ if ((char *)va >= ((char *)shm->kaddr + shm->size))
+ return -EINVAL;
+
+ return tee_shm_get_pa(
+ shm, (unsigned long)va - (unsigned long)shm->kaddr, pa);
+}
+EXPORT_SYMBOL_GPL(tee_shm_va2pa);
+
+/**
+ * tee_shm_pa2va() - Get virtual address of a physical address
+ * @shm: Shared memory handle
+ * @pa: Physical address to tranlsate
+ * @va: Returned virtual address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va)
+{
+ if (!(shm->flags & TEE_SHM_MAPPED))
+ return -EINVAL;
+ /* Check that we're in the range of the shm */
+ if (pa < shm->paddr)
+ return -EINVAL;
+ if (pa >= (shm->paddr + shm->size))
+ return -EINVAL;
+
+ if (va) {
+ void *v = tee_shm_get_va(shm, pa - shm->paddr);
+
+ if (IS_ERR(v))
+ return PTR_ERR(v);
+ *va = v;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tee_shm_pa2va);
+
+/**
+ * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @returns virtual address of the shared memory + offs if offs is within
+ * the bounds of this shared memory, else an ERR_PTR
+ */
+void *tee_shm_get_va(struct tee_shm *shm, size_t offs)
+{
+ if (!(shm->flags & TEE_SHM_MAPPED))
+ return ERR_PTR(-EINVAL);
+ if (offs >= shm->size)
+ return ERR_PTR(-EINVAL);
+ return (char *)shm->kaddr + offs;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_va);
+
+/**
+ * tee_shm_get_pa() - Get physical address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @pa: Physical address to return
+ * @returns 0 if offs is within the bounds of this shared memory, else an
+ * error code.
+ */
+int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa)
+{
+ if (offs >= shm->size)
+ return -EINVAL;
+ if (pa)
+ *pa = shm->paddr + offs;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_pa);
+
+/**
+ * tee_shm_get_from_id() - Find shared memory object and increase reference
+ * count
+ * @ctx: Context owning the shared memory
+ * @id: Id of shared memory object
+ * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure
+ */
+struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id)
+{
+ struct tee_device *teedev;
+ struct tee_shm *shm;
+
+ if (!ctx)
+ return ERR_PTR(-EINVAL);
+
+ teedev = ctx->teedev;
+ mutex_lock(&teedev->mutex);
+ shm = idr_find(&teedev->idr, id);
+ if (!shm || shm->ctx != ctx)
+ shm = ERR_PTR(-EINVAL);
+ else if (shm->flags & TEE_SHM_DMA_BUF)
+ get_dma_buf(shm->dmabuf);
+ mutex_unlock(&teedev->mutex);
+ return shm;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_from_id);
+
+/**
+ * tee_shm_put() - Decrease reference count on a shared memory handle
+ * @shm: Shared memory handle
+ */
+void tee_shm_put(struct tee_shm *shm)
+{
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ dma_buf_put(shm->dmabuf);
+}
+EXPORT_SYMBOL_GPL(tee_shm_put);
diff --git a/drivers/tee/tee_shm_pool.c b/drivers/tee/tee_shm_pool.c
new file mode 100644
index 0000000..e6d4b9e
--- /dev/null
+++ b/drivers/tee/tee_shm_pool.c
@@ -0,0 +1,195 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "tee_private.h"
+
+static int pool_op_gen_alloc(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm, size_t size)
+{
+ unsigned long va;
+ struct gen_pool *genpool = poolm->private_data;
+ size_t s = roundup(size, 1 << genpool->min_alloc_order);
+
+ va = gen_pool_alloc(genpool, s);
+ if (!va)
+ return -ENOMEM;
+
+ memset((void *)va, 0, s);
+ shm->kaddr = (void *)va;
+ shm->paddr = gen_pool_virt_to_phys(genpool, va);
+ shm->size = s;
+ return 0;
+}
+
+static void pool_op_gen_free(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm)
+{
+ gen_pool_free(poolm->private_data, (unsigned long)shm->kaddr,
+ shm->size);
+ shm->kaddr = NULL;
+}
+
+static void pool_op_gen_destroy_poolmgr(struct tee_shm_pool_mgr *poolm)
+{
+ gen_pool_destroy(poolm->private_data);
+ kfree(poolm);
+}
+
+static const struct tee_shm_pool_mgr_ops pool_ops_generic = {
+ .alloc = pool_op_gen_alloc,
+ .free = pool_op_gen_free,
+ .destroy_poolmgr = pool_op_gen_destroy_poolmgr,
+};
+
+/**
+ * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved
+ * memory range
+ * @priv_info: Information for driver private shared memory pool
+ * @dmabuf_info: Information for dma-buf shared memory pool
+ *
+ * Start and end of pools will must be page aligned.
+ *
+ * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied
+ * in @dmabuf, others will use the range provided by @priv.
+ *
+ * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool *
+tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info,
+ struct tee_shm_pool_mem_info *dmabuf_info)
+{
+ struct tee_shm_pool_mgr *priv_mgr;
+ struct tee_shm_pool_mgr *dmabuf_mgr;
+ void *rc;
+
+ /*
+ * Create the pool for driver private shared memory
+ */
+ rc = tee_shm_pool_mgr_alloc_res_mem(priv_info->vaddr, priv_info->paddr,
+ priv_info->size,
+ 3 /* 8 byte aligned */);
+ if (IS_ERR(rc))
+ return rc;
+ priv_mgr = rc;
+
+ /*
+ * Create the pool for dma_buf shared memory
+ */
+ rc = tee_shm_pool_mgr_alloc_res_mem(dmabuf_info->vaddr,
+ dmabuf_info->paddr,
+ dmabuf_info->size, PAGE_SHIFT);
+ if (IS_ERR(rc))
+ goto err_free_priv_mgr;
+ dmabuf_mgr = rc;
+
+ rc = tee_shm_pool_alloc(priv_mgr, dmabuf_mgr);
+ if (IS_ERR(rc))
+ goto err_free_dmabuf_mgr;
+
+ return rc;
+
+err_free_dmabuf_mgr:
+ tee_shm_pool_mgr_destroy(dmabuf_mgr);
+err_free_priv_mgr:
+ tee_shm_pool_mgr_destroy(priv_mgr);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_alloc_res_mem);
+
+struct tee_shm_pool_mgr *tee_shm_pool_mgr_alloc_res_mem(unsigned long vaddr,
+ phys_addr_t paddr,
+ size_t size,
+ int min_alloc_order)
+{
+ const size_t page_mask = PAGE_SIZE - 1;
+ struct tee_shm_pool_mgr *mgr;
+ int rc;
+
+ /* Start and end must be page aligned */
+ if (vaddr & page_mask || paddr & page_mask || size & page_mask)
+ return ERR_PTR(-EINVAL);
+
+ mgr = kzalloc(sizeof(*mgr), GFP_KERNEL);
+ if (!mgr)
+ return ERR_PTR(-ENOMEM);
+
+ mgr->private_data = gen_pool_create(min_alloc_order, -1);
+ if (!mgr->private_data) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ gen_pool_set_algo(mgr->private_data, gen_pool_best_fit, NULL);
+ rc = gen_pool_add_virt(mgr->private_data, vaddr, paddr, size, -1);
+ if (rc) {
+ gen_pool_destroy(mgr->private_data);
+ goto err;
+ }
+
+ mgr->ops = &pool_ops_generic;
+
+ return mgr;
+err:
+ kfree(mgr);
+
+ return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_mgr_alloc_res_mem);
+
+static bool check_mgr_ops(struct tee_shm_pool_mgr *mgr)
+{
+ return mgr && mgr->ops && mgr->ops->alloc && mgr->ops->free &&
+ mgr->ops->destroy_poolmgr;
+}
+
+struct tee_shm_pool *tee_shm_pool_alloc(struct tee_shm_pool_mgr *priv_mgr,
+ struct tee_shm_pool_mgr *dmabuf_mgr)
+{
+ struct tee_shm_pool *pool;
+
+ if (!check_mgr_ops(priv_mgr) || !check_mgr_ops(dmabuf_mgr))
+ return ERR_PTR(-EINVAL);
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return ERR_PTR(-ENOMEM);
+
+ pool->private_mgr = priv_mgr;
+ pool->dma_buf_mgr = dmabuf_mgr;
+
+ return pool;
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_alloc);
+
+/**
+ * tee_shm_pool_free() - Free a shared memory pool
+ * @pool: The shared memory pool to free
+ *
+ * There must be no remaining shared memory allocated from this pool when
+ * this function is called.
+ */
+void tee_shm_pool_free(struct tee_shm_pool *pool)
+{
+ if (pool->private_mgr)
+ tee_shm_pool_mgr_destroy(pool->private_mgr);
+ if (pool->dma_buf_mgr)
+ tee_shm_pool_mgr_destroy(pool->dma_buf_mgr);
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_free);
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index c5285ed..761d055 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -23,243 +23,450 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/io.h>
+#include <linux/of_device.h>
#include "thermal_core.h"
-#define TEMP0_TH (0x4)
-#define TEMP0_RST_TH (0x8)
-#define TEMP0_CFG (0xC)
-#define TEMP0_EN (0x10)
-#define TEMP0_INT_EN (0x14)
-#define TEMP0_INT_CLR (0x18)
-#define TEMP0_RST_MSK (0x1C)
-#define TEMP0_VALUE (0x28)
+#define HI6220_TEMP0_LAG (0x0)
+#define HI6220_TEMP0_TH (0x4)
+#define HI6220_TEMP0_RST_TH (0x8)
+#define HI6220_TEMP0_CFG (0xC)
+#define HI6220_TEMP0_CFG_SS_MSK (0xF000)
+#define HI6220_TEMP0_CFG_HDAK_MSK (0x30)
+#define HI6220_TEMP0_EN (0x10)
+#define HI6220_TEMP0_INT_EN (0x14)
+#define HI6220_TEMP0_INT_CLR (0x18)
+#define HI6220_TEMP0_RST_MSK (0x1C)
+#define HI6220_TEMP0_VALUE (0x28)
-#define HISI_TEMP_BASE (-60000)
-#define HISI_TEMP_RESET (100000)
-#define HISI_TEMP_STEP (784)
+#define HI3660_OFFSET(chan) ((chan) * 0x40)
+#define HI3660_TEMP(chan) (HI3660_OFFSET(chan) + 0x1C)
+#define HI3660_TH(chan) (HI3660_OFFSET(chan) + 0x20)
+#define HI3660_LAG(chan) (HI3660_OFFSET(chan) + 0x28)
+#define HI3660_INT_EN(chan) (HI3660_OFFSET(chan) + 0x2C)
+#define HI3660_INT_CLR(chan) (HI3660_OFFSET(chan) + 0x30)
-#define HISI_MAX_SENSORS 4
+#define HI6220_TEMP_BASE (-60000)
+#define HI6220_TEMP_RESET (100000)
+#define HI6220_TEMP_STEP (785)
+#define HI6220_TEMP_LAG (3500)
+
+#define HI3660_TEMP_BASE (-63780)
+#define HI3660_TEMP_STEP (205)
+#define HI3660_TEMP_LAG (4000)
+
+#define HI6220_DEFAULT_SENSOR 2
+#define HI3660_DEFAULT_SENSOR 1
struct hisi_thermal_sensor {
- struct hisi_thermal_data *thermal;
struct thermal_zone_device *tzd;
-
- long sensor_temp;
uint32_t id;
uint32_t thres_temp;
};
struct hisi_thermal_data {
- struct mutex thermal_lock; /* protects register data */
+ int (*get_temp)(struct hisi_thermal_data *data);
+ int (*enable_sensor)(struct hisi_thermal_data *data);
+ int (*disable_sensor)(struct hisi_thermal_data *data);
+ int (*irq_handler)(struct hisi_thermal_data *data);
struct platform_device *pdev;
struct clk *clk;
- struct hisi_thermal_sensor sensors[HISI_MAX_SENSORS];
-
- int irq, irq_bind_sensor;
- bool irq_enabled;
-
+ struct hisi_thermal_sensor sensor;
void __iomem *regs;
+ int irq;
};
/*
* The temperature computation on the tsensor is as follow:
* Unit: millidegree Celsius
- * Step: 255/200 (0.7843)
+ * Step: 200/255 (0.7843)
* Temperature base: -60°C
*
- * The register is programmed in temperature steps, every step is 784
+ * The register is programmed in temperature steps, every step is 785
* millidegree and begins at -60 000 m°C
*
* The temperature from the steps:
*
- * Temp = TempBase + (steps x 784)
+ * Temp = TempBase + (steps x 785)
*
* and the steps from the temperature:
*
- * steps = (Temp - TempBase) / 784
+ * steps = (Temp - TempBase) / 785
*
*/
-static inline int hisi_thermal_step_to_temp(int step)
+static inline int hi6220_thermal_step_to_temp(int step)
{
- return HISI_TEMP_BASE + (step * HISI_TEMP_STEP);
+ return HI6220_TEMP_BASE + (step * HI6220_TEMP_STEP);
}
-static inline long hisi_thermal_temp_to_step(long temp)
+static inline int hi6220_thermal_temp_to_step(int temp)
{
- return (temp - HISI_TEMP_BASE) / HISI_TEMP_STEP;
+ return DIV_ROUND_UP(temp - HI6220_TEMP_BASE, HI6220_TEMP_STEP);
}
-static inline long hisi_thermal_round_temp(int temp)
+/*
+ * for Hi3660,
+ * Step: 189/922 (0.205)
+ * Temperature base: -63.780°C
+ *
+ * The register is programmed in temperature steps, every step is 205
+ * millidegree and begins at -63 780 m°C
+ */
+static inline int hi3660_thermal_step_to_temp(int step)
{
- return hisi_thermal_step_to_temp(
- hisi_thermal_temp_to_step(temp));
+ return HI3660_TEMP_BASE + step * HI3660_TEMP_STEP;
}
-static long hisi_thermal_get_sensor_temp(struct hisi_thermal_data *data,
- struct hisi_thermal_sensor *sensor)
+static inline int hi3660_thermal_temp_to_step(int temp)
{
- long val;
-
- mutex_lock(&data->thermal_lock);
-
- /* disable interrupt */
- writel(0x0, data->regs + TEMP0_INT_EN);
- writel(0x1, data->regs + TEMP0_INT_CLR);
-
- /* disable module firstly */
- writel(0x0, data->regs + TEMP0_EN);
-
- /* select sensor id */
- writel((sensor->id << 12), data->regs + TEMP0_CFG);
-
- /* enable module */
- writel(0x1, data->regs + TEMP0_EN);
-
- usleep_range(3000, 5000);
-
- val = readl(data->regs + TEMP0_VALUE);
- val = hisi_thermal_step_to_temp(val);
-
- mutex_unlock(&data->thermal_lock);
-
- return val;
+ return DIV_ROUND_UP(temp - HI3660_TEMP_BASE, HI3660_TEMP_STEP);
}
-static void hisi_thermal_enable_bind_irq_sensor
- (struct hisi_thermal_data *data)
+/*
+ * The lag register contains 5 bits encoding the temperature in steps.
+ *
+ * Each time the temperature crosses the threshold boundary, an
+ * interrupt is raised. It could be when the temperature is going
+ * above the threshold or below. However, if the temperature is
+ * fluctuating around this value due to the load, we can receive
+ * several interrupts which may not desired.
+ *
+ * We can setup a temperature representing the delta between the
+ * threshold and the current temperature when the temperature is
+ * decreasing.
+ *
+ * For instance: the lag register is 5°C, the threshold is 65°C, when
+ * the temperature reaches 65°C an interrupt is raised and when the
+ * temperature decrease to 65°C - 5°C another interrupt is raised.
+ *
+ * A very short lag can lead to an interrupt storm, a long lag
+ * increase the latency to react to the temperature changes. In our
+ * case, that is not really a problem as we are polling the
+ * temperature.
+ *
+ * [0:4] : lag register
+ *
+ * The temperature is coded in steps, cf. HI6220_TEMP_STEP.
+ *
+ * Min : 0x00 : 0.0 °C
+ * Max : 0x1F : 24.3 °C
+ *
+ * The 'value' parameter is in milliCelsius.
+ */
+static inline void hi6220_thermal_set_lag(void __iomem *addr, int value)
{
- struct hisi_thermal_sensor *sensor;
-
- mutex_lock(&data->thermal_lock);
-
- sensor = &data->sensors[data->irq_bind_sensor];
-
- /* setting the hdak time */
- writel(0x0, data->regs + TEMP0_CFG);
-
- /* disable module firstly */
- writel(0x0, data->regs + TEMP0_RST_MSK);
- writel(0x0, data->regs + TEMP0_EN);
-
- /* select sensor id */
- writel((sensor->id << 12), data->regs + TEMP0_CFG);
-
- /* enable for interrupt */
- writel(hisi_thermal_temp_to_step(sensor->thres_temp) | 0x0FFFFFF00,
- data->regs + TEMP0_TH);
-
- writel(hisi_thermal_temp_to_step(HISI_TEMP_RESET),
- data->regs + TEMP0_RST_TH);
-
- /* enable module */
- writel(0x1, data->regs + TEMP0_RST_MSK);
- writel(0x1, data->regs + TEMP0_EN);
-
- writel(0x0, data->regs + TEMP0_INT_CLR);
- writel(0x1, data->regs + TEMP0_INT_EN);
-
- usleep_range(3000, 5000);
-
- mutex_unlock(&data->thermal_lock);
+ writel(DIV_ROUND_UP(value, HI6220_TEMP_STEP) & 0x1F,
+ addr + HI6220_TEMP0_LAG);
}
-static void hisi_thermal_disable_sensor(struct hisi_thermal_data *data)
+static inline void hi6220_thermal_alarm_clear(void __iomem *addr, int value)
{
- mutex_lock(&data->thermal_lock);
+ writel(value, addr + HI6220_TEMP0_INT_CLR);
+}
+static inline void hi6220_thermal_alarm_enable(void __iomem *addr, int value)
+{
+ writel(value, addr + HI6220_TEMP0_INT_EN);
+}
+
+static inline void hi6220_thermal_alarm_set(void __iomem *addr, int temp)
+{
+ writel(hi6220_thermal_temp_to_step(temp) | 0x0FFFFFF00,
+ addr + HI6220_TEMP0_TH);
+}
+
+static inline void hi6220_thermal_reset_set(void __iomem *addr, int temp)
+{
+ writel(hi6220_thermal_temp_to_step(temp), addr + HI6220_TEMP0_RST_TH);
+}
+
+static inline void hi6220_thermal_reset_enable(void __iomem *addr, int value)
+{
+ writel(value, addr + HI6220_TEMP0_RST_MSK);
+}
+
+static inline void hi6220_thermal_enable(void __iomem *addr, int value)
+{
+ writel(value, addr + HI6220_TEMP0_EN);
+}
+
+static inline int hi6220_thermal_get_temperature(void __iomem *addr)
+{
+ return hi6220_thermal_step_to_temp(readl(addr + HI6220_TEMP0_VALUE));
+}
+
+/*
+ * [0:6] lag register
+ *
+ * The temperature is coded in steps, cf. HI3660_TEMP_STEP.
+ *
+ * Min : 0x00 : 0.0 °C
+ * Max : 0x7F : 26.0 °C
+ *
+ */
+static inline void hi3660_thermal_set_lag(void __iomem *addr,
+ int id, int value)
+{
+ writel(DIV_ROUND_UP(value, HI3660_TEMP_STEP) & 0x7F,
+ addr + HI3660_LAG(id));
+}
+
+static inline void hi3660_thermal_alarm_clear(void __iomem *addr,
+ int id, int value)
+{
+ writel(value, addr + HI3660_INT_CLR(id));
+}
+
+static inline void hi3660_thermal_alarm_enable(void __iomem *addr,
+ int id, int value)
+{
+ writel(value, addr + HI3660_INT_EN(id));
+}
+
+static inline void hi3660_thermal_alarm_set(void __iomem *addr,
+ int id, int value)
+{
+ writel(value, addr + HI3660_TH(id));
+}
+
+static inline int hi3660_thermal_get_temperature(void __iomem *addr, int id)
+{
+ return hi3660_thermal_step_to_temp(readl(addr + HI3660_TEMP(id)));
+}
+
+/*
+ * Temperature configuration register - Sensor selection
+ *
+ * Bits [19:12]
+ *
+ * 0x0: local sensor (default)
+ * 0x1: remote sensor 1 (ACPU cluster 1)
+ * 0x2: remote sensor 2 (ACPU cluster 0)
+ * 0x3: remote sensor 3 (G3D)
+ */
+static inline void hi6220_thermal_sensor_select(void __iomem *addr, int sensor)
+{
+ writel((readl(addr + HI6220_TEMP0_CFG) & ~HI6220_TEMP0_CFG_SS_MSK) |
+ (sensor << 12), addr + HI6220_TEMP0_CFG);
+}
+
+/*
+ * Temperature configuration register - Hdak conversion polling interval
+ *
+ * Bits [5:4]
+ *
+ * 0x0 : 0.768 ms
+ * 0x1 : 6.144 ms
+ * 0x2 : 49.152 ms
+ * 0x3 : 393.216 ms
+ */
+static inline void hi6220_thermal_hdak_set(void __iomem *addr, int value)
+{
+ writel((readl(addr + HI6220_TEMP0_CFG) & ~HI6220_TEMP0_CFG_HDAK_MSK) |
+ (value << 4), addr + HI6220_TEMP0_CFG);
+}
+
+static int hi6220_thermal_irq_handler(struct hisi_thermal_data *data)
+{
+ hi6220_thermal_alarm_clear(data->regs, 1);
+ return 0;
+}
+
+static int hi3660_thermal_irq_handler(struct hisi_thermal_data *data)
+{
+ hi3660_thermal_alarm_clear(data->regs, data->sensor.id, 1);
+ return 0;
+}
+
+static int hi6220_thermal_get_temp(struct hisi_thermal_data *data)
+{
+ return hi6220_thermal_get_temperature(data->regs);
+}
+
+static int hi3660_thermal_get_temp(struct hisi_thermal_data *data)
+{
+ return hi3660_thermal_get_temperature(data->regs, data->sensor.id);
+}
+
+static int hi6220_thermal_disable_sensor(struct hisi_thermal_data *data)
+{
/* disable sensor module */
- writel(0x0, data->regs + TEMP0_INT_EN);
- writel(0x0, data->regs + TEMP0_RST_MSK);
- writel(0x0, data->regs + TEMP0_EN);
+ hi6220_thermal_enable(data->regs, 0);
+ hi6220_thermal_alarm_enable(data->regs, 0);
+ hi6220_thermal_reset_enable(data->regs, 0);
- mutex_unlock(&data->thermal_lock);
-}
-
-static int hisi_thermal_get_temp(void *_sensor, int *temp)
-{
- struct hisi_thermal_sensor *sensor = _sensor;
- struct hisi_thermal_data *data = sensor->thermal;
-
- int sensor_id = -1, i;
- long max_temp = 0;
-
- *temp = hisi_thermal_get_sensor_temp(data, sensor);
-
- sensor->sensor_temp = *temp;
-
- for (i = 0; i < HISI_MAX_SENSORS; i++) {
- if (!data->sensors[i].tzd)
- continue;
-
- if (data->sensors[i].sensor_temp >= max_temp) {
- max_temp = data->sensors[i].sensor_temp;
- sensor_id = i;
- }
- }
-
- /* If no sensor has been enabled, then skip to enable irq */
- if (sensor_id == -1)
- return 0;
-
- mutex_lock(&data->thermal_lock);
- data->irq_bind_sensor = sensor_id;
- mutex_unlock(&data->thermal_lock);
-
- dev_dbg(&data->pdev->dev, "id=%d, irq=%d, temp=%d, thres=%d\n",
- sensor->id, data->irq_enabled, *temp, sensor->thres_temp);
- /*
- * Bind irq to sensor for two cases:
- * Reenable alarm IRQ if temperature below threshold;
- * if irq has been enabled, always set it;
- */
- if (data->irq_enabled) {
- hisi_thermal_enable_bind_irq_sensor(data);
- return 0;
- }
-
- if (max_temp < sensor->thres_temp) {
- data->irq_enabled = true;
- hisi_thermal_enable_bind_irq_sensor(data);
- enable_irq(data->irq);
- }
+ clk_disable_unprepare(data->clk);
return 0;
}
-static struct thermal_zone_of_device_ops hisi_of_thermal_ops = {
+static int hi3660_thermal_disable_sensor(struct hisi_thermal_data *data)
+{
+ /* disable sensor module */
+ hi3660_thermal_alarm_enable(data->regs, data->sensor.id, 0);
+ return 0;
+}
+
+static int hi6220_thermal_enable_sensor(struct hisi_thermal_data *data)
+{
+ struct hisi_thermal_sensor *sensor = &data->sensor;
+ int ret;
+
+ /* enable clock for tsensor */
+ ret = clk_prepare_enable(data->clk);
+ if (ret)
+ return ret;
+
+ /* disable module firstly */
+ hi6220_thermal_reset_enable(data->regs, 0);
+ hi6220_thermal_enable(data->regs, 0);
+
+ /* select sensor id */
+ hi6220_thermal_sensor_select(data->regs, sensor->id);
+
+ /* setting the hdak time */
+ hi6220_thermal_hdak_set(data->regs, 0);
+
+ /* setting lag value between current temp and the threshold */
+ hi6220_thermal_set_lag(data->regs, HI6220_TEMP_LAG);
+
+ /* enable for interrupt */
+ hi6220_thermal_alarm_set(data->regs, sensor->thres_temp);
+
+ hi6220_thermal_reset_set(data->regs, HI6220_TEMP_RESET);
+
+ /* enable module */
+ hi6220_thermal_reset_enable(data->regs, 1);
+ hi6220_thermal_enable(data->regs, 1);
+
+ hi6220_thermal_alarm_clear(data->regs, 0);
+ hi6220_thermal_alarm_enable(data->regs, 1);
+
+ return 0;
+}
+
+static int hi3660_thermal_enable_sensor(struct hisi_thermal_data *data)
+{
+ unsigned int value;
+ struct hisi_thermal_sensor *sensor = &data->sensor;
+
+ /* disable interrupt */
+ hi3660_thermal_alarm_enable(data->regs, sensor->id, 0);
+
+ /* setting lag value between current temp and the threshold */
+ hi3660_thermal_set_lag(data->regs, sensor->id, HI3660_TEMP_LAG);
+
+ /* set interrupt threshold */
+ value = hi3660_thermal_temp_to_step(sensor->thres_temp);
+ hi3660_thermal_alarm_set(data->regs, sensor->id, value);
+
+ /* enable interrupt */
+ hi3660_thermal_alarm_clear(data->regs, sensor->id, 1);
+ hi3660_thermal_alarm_enable(data->regs, sensor->id, 1);
+
+ return 0;
+}
+
+static int hi6220_thermal_probe(struct hisi_thermal_data *data)
+{
+ struct platform_device *pdev = data->pdev;
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+ int ret;
+
+ data->get_temp = hi6220_thermal_get_temp;
+ data->enable_sensor = hi6220_thermal_enable_sensor;
+ data->disable_sensor = hi6220_thermal_disable_sensor;
+ data->irq_handler = hi6220_thermal_irq_handler;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ data->regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(data->regs)) {
+ dev_err(dev, "failed to get io address\n");
+ return PTR_ERR(data->regs);
+ }
+
+ data->clk = devm_clk_get(dev, "thermal_clk");
+ if (IS_ERR(data->clk)) {
+ ret = PTR_ERR(data->clk);
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "failed to get thermal clk: %d\n", ret);
+ return ret;
+ }
+
+ data->irq = platform_get_irq(pdev, 0);
+ if (data->irq < 0)
+ return data->irq;
+
+ data->sensor.id = HI6220_DEFAULT_SENSOR;
+
+ return 0;
+}
+
+static int hi3660_thermal_probe(struct hisi_thermal_data *data)
+{
+ struct platform_device *pdev = data->pdev;
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+
+ data->get_temp = hi3660_thermal_get_temp;
+ data->enable_sensor = hi3660_thermal_enable_sensor;
+ data->disable_sensor = hi3660_thermal_disable_sensor;
+ data->irq_handler = hi3660_thermal_irq_handler;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ data->regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(data->regs)) {
+ dev_err(dev, "failed to get io address\n");
+ return PTR_ERR(data->regs);
+ }
+
+ data->irq = platform_get_irq(pdev, 0);
+ if (data->irq < 0)
+ return data->irq;
+
+ data->sensor.id = HI3660_DEFAULT_SENSOR;
+
+ return 0;
+}
+
+static int hisi_thermal_get_temp(void *__data, int *temp)
+{
+ struct hisi_thermal_data *data = __data;
+ struct hisi_thermal_sensor *sensor = &data->sensor;
+
+ *temp = data->get_temp(data);
+
+ dev_dbg(&data->pdev->dev, "id=%d, temp=%d, thres=%d\n",
+ sensor->id, *temp, sensor->thres_temp);
+
+ return 0;
+}
+
+static const struct thermal_zone_of_device_ops hisi_of_thermal_ops = {
.get_temp = hisi_thermal_get_temp,
};
-static irqreturn_t hisi_thermal_alarm_irq(int irq, void *dev)
-{
- struct hisi_thermal_data *data = dev;
-
- disable_irq_nosync(irq);
- data->irq_enabled = false;
-
- return IRQ_WAKE_THREAD;
-}
-
static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
{
struct hisi_thermal_data *data = dev;
- struct hisi_thermal_sensor *sensor;
- int i;
+ struct hisi_thermal_sensor *sensor = &data->sensor;
+ int temp = 0;
- mutex_lock(&data->thermal_lock);
- sensor = &data->sensors[data->irq_bind_sensor];
+ data->irq_handler(data);
- dev_crit(&data->pdev->dev, "THERMAL ALARM: T > %d\n",
- sensor->thres_temp);
- mutex_unlock(&data->thermal_lock);
+ hisi_thermal_get_temp(data, &temp);
- for (i = 0; i < HISI_MAX_SENSORS; i++) {
- if (!data->sensors[i].tzd)
- continue;
+ if (temp >= sensor->thres_temp) {
+ dev_crit(&data->pdev->dev, "THERMAL ALARM: %d > %d\n",
+ temp, sensor->thres_temp);
- thermal_zone_device_update(data->sensors[i].tzd,
+ thermal_zone_device_update(data->sensor.tzd,
THERMAL_EVENT_UNSPECIFIED);
+
+ } else {
+ dev_crit(&data->pdev->dev, "THERMAL ALARM stopped: %d < %d\n",
+ temp, sensor->thres_temp);
}
return IRQ_HANDLED;
@@ -267,17 +474,14 @@ static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
static int hisi_thermal_register_sensor(struct platform_device *pdev,
struct hisi_thermal_data *data,
- struct hisi_thermal_sensor *sensor,
- int index)
+ struct hisi_thermal_sensor *sensor)
{
int ret, i;
const struct thermal_trip *trip;
- sensor->id = index;
- sensor->thermal = data;
-
sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
- sensor->id, sensor, &hisi_of_thermal_ops);
+ sensor->id, data,
+ &hisi_of_thermal_ops);
if (IS_ERR(sensor->tzd)) {
ret = PTR_ERR(sensor->tzd);
sensor->tzd = NULL;
@@ -290,7 +494,7 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev,
for (i = 0; i < of_thermal_get_ntrips(sensor->tzd); i++) {
if (trip[i].type == THERMAL_TRIP_PASSIVE) {
- sensor->thres_temp = hisi_thermal_round_temp(trip[i].temperature);
+ sensor->thres_temp = trip[i].temperature;
break;
}
}
@@ -299,7 +503,14 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev,
}
static const struct of_device_id of_hisi_thermal_match[] = {
- { .compatible = "hisilicon,tsensor" },
+ {
+ .compatible = "hisilicon,tsensor",
+ .data = hi6220_thermal_probe
+ },
+ {
+ .compatible = "hisilicon,hi3660-tsensor",
+ .data = hi3660_thermal_probe
+ },
{ /* end */ }
};
MODULE_DEVICE_TABLE(of, of_hisi_thermal_match);
@@ -316,69 +527,51 @@ static void hisi_thermal_toggle_sensor(struct hisi_thermal_sensor *sensor,
static int hisi_thermal_probe(struct platform_device *pdev)
{
struct hisi_thermal_data *data;
- struct resource *res;
- int i;
+ int (*platform_probe)(struct hisi_thermal_data *);
+ struct device *dev = &pdev->dev;
int ret;
- data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
- mutex_init(&data->thermal_lock);
data->pdev = pdev;
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- data->regs = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(data->regs)) {
- dev_err(&pdev->dev, "failed to get io address\n");
- return PTR_ERR(data->regs);
- }
-
- data->irq = platform_get_irq(pdev, 0);
- if (data->irq < 0)
- return data->irq;
-
platform_set_drvdata(pdev, data);
- data->clk = devm_clk_get(&pdev->dev, "thermal_clk");
- if (IS_ERR(data->clk)) {
- ret = PTR_ERR(data->clk);
- if (ret != -EPROBE_DEFER)
- dev_err(&pdev->dev,
- "failed to get thermal clk: %d\n", ret);
- return ret;
+ platform_probe = of_device_get_match_data(dev);
+ if (!platform_probe) {
+ dev_err(dev, "failed to get probe func\n");
+ return -EINVAL;
}
- /* enable clock for thermal */
- ret = clk_prepare_enable(data->clk);
+ ret = platform_probe(data);
+ if (ret)
+ return ret;
+
+ ret = hisi_thermal_register_sensor(pdev, data,
+ &data->sensor);
if (ret) {
- dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret);
+ dev_err(dev, "failed to register thermal sensor: %d\n", ret);
return ret;
}
- hisi_thermal_enable_bind_irq_sensor(data);
- data->irq_enabled = true;
-
- for (i = 0; i < HISI_MAX_SENSORS; ++i) {
- ret = hisi_thermal_register_sensor(pdev, data,
- &data->sensors[i], i);
- if (ret)
- dev_err(&pdev->dev,
- "failed to register thermal sensor: %d\n", ret);
- else
- hisi_thermal_toggle_sensor(&data->sensors[i], true);
- }
-
- ret = devm_request_threaded_irq(&pdev->dev, data->irq,
- hisi_thermal_alarm_irq,
- hisi_thermal_alarm_irq_thread,
- 0, "hisi_thermal", data);
- if (ret < 0) {
- dev_err(&pdev->dev, "failed to request alarm irq: %d\n", ret);
+ ret = data->enable_sensor(data);
+ if (ret) {
+ dev_err(dev, "Failed to setup the sensor: %d\n", ret);
return ret;
}
- enable_irq(data->irq);
+ if (data->irq) {
+ ret = devm_request_threaded_irq(dev, data->irq, NULL,
+ hisi_thermal_alarm_irq_thread,
+ IRQF_ONESHOT, "hisi_thermal", data);
+ if (ret < 0) {
+ dev_err(dev, "failed to request alarm irq: %d\n", ret);
+ return ret;
+ }
+ }
+
+ hisi_thermal_toggle_sensor(&data->sensor, true);
return 0;
}
@@ -386,19 +579,11 @@ static int hisi_thermal_probe(struct platform_device *pdev)
static int hisi_thermal_remove(struct platform_device *pdev)
{
struct hisi_thermal_data *data = platform_get_drvdata(pdev);
- int i;
+ struct hisi_thermal_sensor *sensor = &data->sensor;
- for (i = 0; i < HISI_MAX_SENSORS; i++) {
- struct hisi_thermal_sensor *sensor = &data->sensors[i];
+ hisi_thermal_toggle_sensor(sensor, false);
- if (!sensor->tzd)
- continue;
-
- hisi_thermal_toggle_sensor(sensor, false);
- }
-
- hisi_thermal_disable_sensor(data);
- clk_disable_unprepare(data->clk);
+ data->disable_sensor(data);
return 0;
}
@@ -408,10 +593,7 @@ static int hisi_thermal_suspend(struct device *dev)
{
struct hisi_thermal_data *data = dev_get_drvdata(dev);
- hisi_thermal_disable_sensor(data);
- data->irq_enabled = false;
-
- clk_disable_unprepare(data->clk);
+ data->disable_sensor(data);
return 0;
}
@@ -419,16 +601,8 @@ static int hisi_thermal_suspend(struct device *dev)
static int hisi_thermal_resume(struct device *dev)
{
struct hisi_thermal_data *data = dev_get_drvdata(dev);
- int ret;
- ret = clk_prepare_enable(data->clk);
- if (ret)
- return ret;
-
- data->irq_enabled = true;
- hisi_thermal_enable_bind_irq_sensor(data);
-
- return 0;
+ return data->enable_sensor(data);
}
#endif
diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c
index 0314e78..ec24e82 100644
--- a/drivers/tty/serial/kgdboc.c
+++ b/drivers/tty/serial/kgdboc.c
@@ -232,7 +232,8 @@ static void kgdboc_put_char(u8 chr)
kgdb_tty_line, chr);
}
-static int param_set_kgdboc_var(const char *kmessage, struct kernel_param *kp)
+static int param_set_kgdboc_var(const char *kmessage,
+ const struct kernel_param *kp)
{
size_t len = strlen(kmessage);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 74a1a97..cb137b3 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -131,6 +131,9 @@ static void __uart_start(struct tty_struct *tty)
struct uart_state *state = tty->driver_data;
struct uart_port *port = state->uart_port;
+ if (port && port->ops->wake_peer)
+ port->ops->wake_peer(port);
+
if (port && !uart_tx_stopped(port))
port->ops->start_tx(port);
}
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 59dc305..6bddf02 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -209,6 +209,18 @@
config USB_F_TCM
tristate
+config USB_F_MTP
+ tristate
+
+config USB_F_PTP
+ tristate
+
+config USB_F_AUDIO_SRC
+ tristate
+
+config USB_F_ACC
+ tristate
+
# this first set of drivers all depend on bulk-capable hardware.
config USB_CONFIGFS
@@ -364,6 +376,45 @@
implemented in kernel space (for instance Ethernet, serial or
mass storage) and other are implemented in user space.
+config USB_CONFIGFS_F_MTP
+ boolean "MTP gadget"
+ depends on USB_CONFIGFS
+ select USB_F_MTP
+ help
+ USB gadget MTP support
+
+config USB_CONFIGFS_F_PTP
+ boolean "PTP gadget"
+ depends on USB_CONFIGFS && USB_CONFIGFS_F_MTP
+ select USB_F_PTP
+ help
+ USB gadget PTP support
+
+config USB_CONFIGFS_F_ACC
+ boolean "Accessory gadget"
+ depends on USB_CONFIGFS
+ depends on HID=y
+ select USB_F_ACC
+ help
+ USB gadget Accessory support
+
+config USB_CONFIGFS_F_AUDIO_SRC
+ boolean "Audio Source gadget"
+ depends on USB_CONFIGFS && USB_CONFIGFS_F_ACC
+ depends on SND
+ select SND_PCM
+ select USB_F_AUDIO_SRC
+ help
+ USB gadget Audio Source support
+
+config USB_CONFIGFS_UEVENT
+ boolean "Uevent notification of Gadget state"
+ depends on USB_CONFIGFS
+ help
+ Enable uevent notifications to userspace when the gadget
+ state changes. The gadget can be in any of the following
+ three states: "CONNECTED/DISCONNECTED/CONFIGURED"
+
config USB_CONFIGFS_F_UAC1
bool "Audio Class 1.0"
depends on USB_CONFIGFS
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index c574bf9..8107136 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2057,6 +2057,12 @@ void composite_disconnect(struct usb_gadget *gadget)
struct usb_composite_dev *cdev = get_gadget_data(gadget);
unsigned long flags;
+ if (cdev == NULL) {
+ WARN(1, "%s: Calling disconnect on a Gadget that is \
+ not connected\n", __func__);
+ return;
+ }
+
/* REVISIT: should we have config and device level
* disconnect callbacks?
*/
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 0aa1b8f..5e98ee7 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -9,6 +9,31 @@
#include "u_f.h"
#include "u_os_desc.h"
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+#include <linux/platform_device.h>
+#include <linux/kdev_t.h>
+#include <linux/usb/ch9.h>
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+extern int acc_ctrlrequest(struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *ctrl);
+void acc_disconnect(void);
+#endif
+static struct class *android_class;
+static struct device *android_device;
+static int index;
+
+struct device *create_function_device(char *name)
+{
+ if (android_device && !IS_ERR(android_device))
+ return device_create(android_class, android_device,
+ MKDEV(0, index++), NULL, name);
+ else
+ return ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(create_function_device);
+#endif
+
int check_user_usb_string(const char *name,
struct usb_gadget_strings *stringtab_dev)
{
@@ -62,6 +87,12 @@ struct gadget_info {
char qw_sign[OS_STRING_QW_SIGN_LEN];
spinlock_t spinlock;
bool unbind;
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+ bool connected;
+ bool sw_connected;
+ struct work_struct work;
+ struct device *dev;
+#endif
};
static inline struct gadget_info *to_gadget_info(struct config_item *item)
@@ -277,7 +308,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
mutex_lock(&gi->lock);
- if (!strlen(name)) {
+ if (!strlen(name) || strcmp(name, "none") == 0) {
ret = unregister_gadget(gi);
if (ret)
goto err;
@@ -1382,6 +1413,60 @@ static int configfs_composite_bind(struct usb_gadget *gadget,
return ret;
}
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static void android_work(struct work_struct *data)
+{
+ struct gadget_info *gi = container_of(data, struct gadget_info, work);
+ struct usb_composite_dev *cdev = &gi->cdev;
+ char *disconnected[2] = { "USB_STATE=DISCONNECTED", NULL };
+ char *connected[2] = { "USB_STATE=CONNECTED", NULL };
+ char *configured[2] = { "USB_STATE=CONFIGURED", NULL };
+ /* 0-connected 1-configured 2-disconnected*/
+ bool status[3] = { false, false, false };
+ unsigned long flags;
+ bool uevent_sent = false;
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (cdev->config)
+ status[1] = true;
+
+ if (gi->connected != gi->sw_connected) {
+ if (gi->connected)
+ status[0] = true;
+ else
+ status[2] = true;
+ gi->sw_connected = gi->connected;
+ }
+ spin_unlock_irqrestore(&cdev->lock, flags);
+
+ if (status[0]) {
+ kobject_uevent_env(&android_device->kobj,
+ KOBJ_CHANGE, connected);
+ pr_info("%s: sent uevent %s\n", __func__, connected[0]);
+ uevent_sent = true;
+ }
+
+ if (status[1]) {
+ kobject_uevent_env(&android_device->kobj,
+ KOBJ_CHANGE, configured);
+ pr_info("%s: sent uevent %s\n", __func__, configured[0]);
+ uevent_sent = true;
+ }
+
+ if (status[2]) {
+ kobject_uevent_env(&android_device->kobj,
+ KOBJ_CHANGE, disconnected);
+ pr_info("%s: sent uevent %s\n", __func__, disconnected[0]);
+ uevent_sent = true;
+ }
+
+ if (!uevent_sent) {
+ pr_info("%s: did not send uevent (%d %d %p)\n", __func__,
+ gi->connected, gi->sw_connected, cdev->config);
+ }
+}
+#endif
+
static void configfs_composite_unbind(struct usb_gadget *gadget)
{
struct usb_composite_dev *cdev;
@@ -1498,14 +1583,91 @@ static void configfs_composite_resume(struct usb_gadget *gadget)
spin_unlock_irqrestore(&gi->spinlock, flags);
}
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static int android_setup(struct usb_gadget *gadget,
+ const struct usb_ctrlrequest *c)
+{
+ struct usb_composite_dev *cdev = get_gadget_data(gadget);
+ unsigned long flags;
+ struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev);
+ int value = -EOPNOTSUPP;
+ struct usb_function_instance *fi;
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (!gi->connected) {
+ gi->connected = 1;
+ schedule_work(&gi->work);
+ }
+ spin_unlock_irqrestore(&cdev->lock, flags);
+ list_for_each_entry(fi, &gi->available_func, cfs_list) {
+ if (fi != NULL && fi->f != NULL && fi->f->setup != NULL) {
+ value = fi->f->setup(fi->f, c);
+ if (value >= 0)
+ break;
+ }
+ }
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+ if (value < 0)
+ value = acc_ctrlrequest(cdev, c);
+#endif
+
+ if (value < 0)
+ value = composite_setup(gadget, c);
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (c->bRequest == USB_REQ_SET_CONFIGURATION &&
+ cdev->config) {
+ schedule_work(&gi->work);
+ }
+ spin_unlock_irqrestore(&cdev->lock, flags);
+
+ return value;
+}
+
+static void android_disconnect(struct usb_gadget *gadget)
+{
+ struct usb_composite_dev *cdev = get_gadget_data(gadget);
+ struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev);
+
+ /* FIXME: There's a race between usb_gadget_udc_stop() which is likely
+ * to set the gadget driver to NULL in the udc driver and this drivers
+ * gadget disconnect fn which likely checks for the gadget driver to
+ * be a null ptr. It happens that unbind (doing set_gadget_data(NULL))
+ * is called before the gadget driver is set to NULL and the udc driver
+ * calls disconnect fn which results in cdev being a null ptr.
+ */
+ if (cdev == NULL) {
+ WARN(1, "%s: gadget driver already disconnected\n", __func__);
+ return;
+ }
+
+ /* accessory HID support can be active while the
+ accessory function is not actually enabled,
+ so we need to inform it when we are disconnected.
+ */
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+ acc_disconnect();
+#endif
+ gi->connected = 0;
+ schedule_work(&gi->work);
+ composite_disconnect(gadget);
+}
+#endif
+
static const struct usb_gadget_driver configfs_driver_template = {
.bind = configfs_composite_bind,
.unbind = configfs_composite_unbind,
-
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+ .setup = android_setup,
+ .reset = android_disconnect,
+ .disconnect = android_disconnect,
+#else
.setup = configfs_composite_setup,
.reset = configfs_composite_disconnect,
.disconnect = configfs_composite_disconnect,
-
+#endif
.suspend = configfs_composite_suspend,
.resume = configfs_composite_resume,
@@ -1517,6 +1679,89 @@ static const struct usb_gadget_driver configfs_driver_template = {
.match_existing_only = 1,
};
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static ssize_t state_show(struct device *pdev, struct device_attribute *attr,
+ char *buf)
+{
+ struct gadget_info *dev = dev_get_drvdata(pdev);
+ struct usb_composite_dev *cdev;
+ char *state = "DISCONNECTED";
+ unsigned long flags;
+
+ if (!dev)
+ goto out;
+
+ cdev = &dev->cdev;
+
+ if (!cdev)
+ goto out;
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (cdev->config)
+ state = "CONFIGURED";
+ else if (dev->connected)
+ state = "CONNECTED";
+ spin_unlock_irqrestore(&cdev->lock, flags);
+out:
+ return sprintf(buf, "%s\n", state);
+}
+
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+
+static struct device_attribute *android_usb_attributes[] = {
+ &dev_attr_state,
+ NULL
+};
+
+static int android_device_create(struct gadget_info *gi)
+{
+ struct device_attribute **attrs;
+ struct device_attribute *attr;
+
+ INIT_WORK(&gi->work, android_work);
+ android_device = device_create(android_class, NULL,
+ MKDEV(0, 0), NULL, "android0");
+ if (IS_ERR(android_device))
+ return PTR_ERR(android_device);
+
+ dev_set_drvdata(android_device, gi);
+
+ attrs = android_usb_attributes;
+ while ((attr = *attrs++)) {
+ int err;
+
+ err = device_create_file(android_device, attr);
+ if (err) {
+ device_destroy(android_device->class,
+ android_device->devt);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static void android_device_destroy(void)
+{
+ struct device_attribute **attrs;
+ struct device_attribute *attr;
+
+ attrs = android_usb_attributes;
+ while ((attr = *attrs++))
+ device_remove_file(android_device, attr);
+ device_destroy(android_device->class, android_device->devt);
+}
+#else
+static inline int android_device_create(struct gadget_info *gi)
+{
+ return 0;
+}
+
+static inline void android_device_destroy(void)
+{
+}
+#endif
+
static struct config_group *gadgets_make(
struct config_group *group,
const char *name)
@@ -1569,7 +1814,11 @@ static struct config_group *gadgets_make(
if (!gi->composite.gadget_driver.function)
goto err;
+ if (android_device_create(gi) < 0)
+ goto err;
+
return &gi->group;
+
err:
kfree(gi);
return ERR_PTR(-ENOMEM);
@@ -1578,6 +1827,7 @@ static struct config_group *gadgets_make(
static void gadgets_drop(struct config_group *group, struct config_item *item)
{
config_item_put(item);
+ android_device_destroy();
}
static struct configfs_group_operations gadgets_ops = {
@@ -1617,6 +1867,13 @@ static int __init gadget_cfs_init(void)
config_group_init(&gadget_subsys.su_group);
ret = configfs_register_subsystem(&gadget_subsys);
+
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+ android_class = class_create(THIS_MODULE, "android_usb");
+ if (IS_ERR(android_class))
+ return PTR_ERR(android_class);
+#endif
+
return ret;
}
module_init(gadget_cfs_init);
@@ -1624,5 +1881,10 @@ module_init(gadget_cfs_init);
static void __exit gadget_cfs_exit(void)
{
configfs_unregister_subsystem(&gadget_subsys);
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+ if (!IS_ERR(android_class))
+ class_destroy(android_class);
+#endif
+
}
module_exit(gadget_cfs_exit);
diff --git a/drivers/usb/gadget/function/Makefile b/drivers/usb/gadget/function/Makefile
index cb8c225..78682d5 100644
--- a/drivers/usb/gadget/function/Makefile
+++ b/drivers/usb/gadget/function/Makefile
@@ -46,3 +46,11 @@
obj-$(CONFIG_USB_F_PRINTER) += usb_f_printer.o
usb_f_tcm-y := f_tcm.o
obj-$(CONFIG_USB_F_TCM) += usb_f_tcm.o
+usb_f_mtp-y := f_mtp.o
+obj-$(CONFIG_USB_F_MTP) += usb_f_mtp.o
+usb_f_ptp-y := f_ptp.o
+obj-$(CONFIG_USB_F_PTP) += usb_f_ptp.o
+usb_f_audio_source-y := f_audio_source.o
+obj-$(CONFIG_USB_F_AUDIO_SRC) += usb_f_audio_source.o
+usb_f_accessory-y := f_accessory.o
+obj-$(CONFIG_USB_F_ACC) += usb_f_accessory.o
diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c
new file mode 100644
index 0000000..718e01e
--- /dev/null
+++ b/drivers/usb/gadget/function/f_accessory.c
@@ -0,0 +1,1435 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/kref.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/hid.h>
+#include <linux/hiddev.h>
+#include <linux/usb.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_accessory.h>
+
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#define MAX_INST_NAME_LEN 40
+#define BULK_BUFFER_SIZE 16384
+#define ACC_STRING_SIZE 256
+
+#define PROTOCOL_VERSION 2
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX 0
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+
+struct acc_hid_dev {
+ struct list_head list;
+ struct hid_device *hid;
+ struct acc_dev *dev;
+ /* accessory defined ID */
+ int id;
+ /* HID report descriptor */
+ u8 *report_desc;
+ /* length of HID report descriptor */
+ int report_desc_len;
+ /* number of bytes of report_desc we have received so far */
+ int report_desc_offset;
+};
+
+struct acc_dev {
+ struct usb_function function;
+ struct usb_composite_dev *cdev;
+ spinlock_t lock;
+ struct acc_dev_ref *ref;
+
+ struct usb_ep *ep_in;
+ struct usb_ep *ep_out;
+
+ /* online indicates state of function_set_alt & function_unbind
+ * set to 1 when we connect
+ */
+ int online;
+
+ /* disconnected indicates state of open & release
+ * Set to 1 when we disconnect.
+ * Not cleared until our file is closed.
+ */
+ int disconnected;
+
+ /* strings sent by the host */
+ char manufacturer[ACC_STRING_SIZE];
+ char model[ACC_STRING_SIZE];
+ char description[ACC_STRING_SIZE];
+ char version[ACC_STRING_SIZE];
+ char uri[ACC_STRING_SIZE];
+ char serial[ACC_STRING_SIZE];
+
+ /* for acc_complete_set_string */
+ int string_index;
+
+ /* set to 1 if we have a pending start request */
+ int start_requested;
+
+ int audio_mode;
+
+ /* synchronize access to our device file */
+ atomic_t open_excl;
+
+ struct list_head tx_idle;
+
+ wait_queue_head_t read_wq;
+ wait_queue_head_t write_wq;
+ struct usb_request *rx_req[RX_REQ_MAX];
+ int rx_done;
+
+ /* delayed work for handling ACCESSORY_START */
+ struct delayed_work start_work;
+
+ /* worker for registering and unregistering hid devices */
+ struct work_struct hid_work;
+
+ /* list of active HID devices */
+ struct list_head hid_list;
+
+ /* list of new HID devices to register */
+ struct list_head new_hid_list;
+
+ /* list of dead HID devices to unregister */
+ struct list_head dead_hid_list;
+};
+
+static struct usb_interface_descriptor acc_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 2,
+ .bInterfaceClass = USB_CLASS_VENDOR_SPEC,
+ .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC,
+ .bInterfaceProtocol = 0,
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_descriptor_header *fs_acc_descs[] = {
+ (struct usb_descriptor_header *) &acc_interface_desc,
+ (struct usb_descriptor_header *) &acc_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &acc_fullspeed_out_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_acc_descs[] = {
+ (struct usb_descriptor_header *) &acc_interface_desc,
+ (struct usb_descriptor_header *) &acc_highspeed_in_desc,
+ (struct usb_descriptor_header *) &acc_highspeed_out_desc,
+ NULL,
+};
+
+static struct usb_string acc_string_defs[] = {
+ [INTERFACE_STRING_INDEX].s = "Android Accessory Interface",
+ { }, /* end of list */
+};
+
+static struct usb_gadget_strings acc_string_table = {
+ .language = 0x0409, /* en-US */
+ .strings = acc_string_defs,
+};
+
+static struct usb_gadget_strings *acc_strings[] = {
+ &acc_string_table,
+ NULL,
+};
+
+struct acc_dev_ref {
+ struct kref kref;
+ struct acc_dev *acc_dev;
+};
+
+static struct acc_dev_ref _acc_dev_ref = {
+ .kref = KREF_INIT(0),
+};
+
+struct acc_instance {
+ struct usb_function_instance func_inst;
+ const char *name;
+};
+
+static struct acc_dev *get_acc_dev(void)
+{
+ struct acc_dev_ref *ref = &_acc_dev_ref;
+
+ return kref_get_unless_zero(&ref->kref) ? ref->acc_dev : NULL;
+}
+
+static void __put_acc_dev(struct kref *kref)
+{
+ struct acc_dev_ref *ref = container_of(kref, struct acc_dev_ref, kref);
+ struct acc_dev *dev = ref->acc_dev;
+
+ /* Cancel any async work */
+ cancel_delayed_work_sync(&dev->start_work);
+ cancel_work_sync(&dev->hid_work);
+
+ ref->acc_dev = NULL;
+ kfree(dev);
+}
+
+static void put_acc_dev(struct acc_dev *dev)
+{
+ struct acc_dev_ref *ref = dev->ref;
+
+ WARN_ON(ref->acc_dev != dev);
+ kref_put(&ref->kref, __put_acc_dev);
+}
+
+static inline struct acc_dev *func_to_dev(struct usb_function *f)
+{
+ return container_of(f, struct acc_dev, function);
+}
+
+static struct usb_request *acc_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+
+ if (!req)
+ return NULL;
+
+ /* now allocate buffers for the requests */
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+
+ return req;
+}
+
+static void acc_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+/* add a request to the tail of a list */
+static void req_put(struct acc_dev *dev, struct list_head *head,
+ struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_add_tail(&req->list, head);
+ spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request *req_get(struct acc_dev *dev, struct list_head *head)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (list_empty(head)) {
+ req = 0;
+ } else {
+ req = list_first_entry(head, struct usb_request, list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return req;
+}
+
+static void acc_set_disconnected(struct acc_dev *dev)
+{
+ dev->disconnected = 1;
+}
+
+static void acc_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ if (!dev)
+ return;
+
+ if (req->status == -ESHUTDOWN) {
+ pr_debug("acc_complete_in set disconnected");
+ acc_set_disconnected(dev);
+ }
+
+ req_put(dev, &dev->tx_idle, req);
+
+ wake_up(&dev->write_wq);
+ put_acc_dev(dev);
+}
+
+static void acc_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ if (!dev)
+ return;
+
+ dev->rx_done = 1;
+ if (req->status == -ESHUTDOWN) {
+ pr_debug("acc_complete_out set disconnected");
+ acc_set_disconnected(dev);
+ }
+
+ wake_up(&dev->read_wq);
+ put_acc_dev(dev);
+}
+
+static void acc_complete_set_string(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = ep->driver_data;
+ char *string_dest = NULL;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_set_string, err %d\n", req->status);
+ return;
+ }
+
+ switch (dev->string_index) {
+ case ACCESSORY_STRING_MANUFACTURER:
+ string_dest = dev->manufacturer;
+ break;
+ case ACCESSORY_STRING_MODEL:
+ string_dest = dev->model;
+ break;
+ case ACCESSORY_STRING_DESCRIPTION:
+ string_dest = dev->description;
+ break;
+ case ACCESSORY_STRING_VERSION:
+ string_dest = dev->version;
+ break;
+ case ACCESSORY_STRING_URI:
+ string_dest = dev->uri;
+ break;
+ case ACCESSORY_STRING_SERIAL:
+ string_dest = dev->serial;
+ break;
+ }
+ if (string_dest) {
+ unsigned long flags;
+
+ if (length >= ACC_STRING_SIZE)
+ length = ACC_STRING_SIZE - 1;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ memcpy(string_dest, req->buf, length);
+ /* ensure zero termination */
+ string_dest[length] = 0;
+ spin_unlock_irqrestore(&dev->lock, flags);
+ } else {
+ pr_err("unknown accessory string index %d\n",
+ dev->string_index);
+ }
+}
+
+static void acc_complete_set_hid_report_desc(struct usb_ep *ep,
+ struct usb_request *req)
+{
+ struct acc_hid_dev *hid = req->context;
+ struct acc_dev *dev = hid->dev;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_set_hid_report_desc, err %d\n",
+ req->status);
+ return;
+ }
+
+ memcpy(hid->report_desc + hid->report_desc_offset, req->buf, length);
+ hid->report_desc_offset += length;
+ if (hid->report_desc_offset == hid->report_desc_len) {
+ /* After we have received the entire report descriptor
+ * we schedule work to initialize the HID device
+ */
+ schedule_work(&dev->hid_work);
+ }
+}
+
+static void acc_complete_send_hid_event(struct usb_ep *ep,
+ struct usb_request *req)
+{
+ struct acc_hid_dev *hid = req->context;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_send_hid_event, err %d\n", req->status);
+ return;
+ }
+
+ hid_report_raw_event(hid->hid, HID_INPUT_REPORT, req->buf, length, 1);
+}
+
+static int acc_hid_parse(struct hid_device *hid)
+{
+ struct acc_hid_dev *hdev = hid->driver_data;
+
+ hid_parse_report(hid, hdev->report_desc, hdev->report_desc_len);
+ return 0;
+}
+
+static int acc_hid_start(struct hid_device *hid)
+{
+ return 0;
+}
+
+static void acc_hid_stop(struct hid_device *hid)
+{
+}
+
+static int acc_hid_open(struct hid_device *hid)
+{
+ return 0;
+}
+
+static void acc_hid_close(struct hid_device *hid)
+{
+}
+
+static int acc_hid_raw_request(struct hid_device *hid, unsigned char reportnum,
+ __u8 *buf, size_t len, unsigned char rtype, int reqtype)
+{
+ return 0;
+}
+
+static struct hid_ll_driver acc_hid_ll_driver = {
+ .parse = acc_hid_parse,
+ .start = acc_hid_start,
+ .stop = acc_hid_stop,
+ .open = acc_hid_open,
+ .close = acc_hid_close,
+ .raw_request = acc_hid_raw_request,
+};
+
+static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev,
+ int id, int desc_len)
+{
+ struct acc_hid_dev *hdev;
+
+ hdev = kzalloc(sizeof(*hdev), GFP_ATOMIC);
+ if (!hdev)
+ return NULL;
+ hdev->report_desc = kzalloc(desc_len, GFP_ATOMIC);
+ if (!hdev->report_desc) {
+ kfree(hdev);
+ return NULL;
+ }
+ hdev->dev = dev;
+ hdev->id = id;
+ hdev->report_desc_len = desc_len;
+
+ return hdev;
+}
+
+static struct acc_hid_dev *acc_hid_get(struct list_head *list, int id)
+{
+ struct acc_hid_dev *hid;
+
+ list_for_each_entry(hid, list, list) {
+ if (hid->id == id)
+ return hid;
+ }
+ return NULL;
+}
+
+static int acc_register_hid(struct acc_dev *dev, int id, int desc_length)
+{
+ struct acc_hid_dev *hid;
+ unsigned long flags;
+
+ /* report descriptor length must be > 0 */
+ if (desc_length <= 0)
+ return -EINVAL;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ /* replace HID if one already exists with this ID */
+ hid = acc_hid_get(&dev->hid_list, id);
+ if (!hid)
+ hid = acc_hid_get(&dev->new_hid_list, id);
+ if (hid)
+ list_move(&hid->list, &dev->dead_hid_list);
+
+ hid = acc_hid_new(dev, id, desc_length);
+ if (!hid) {
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return -ENOMEM;
+ }
+
+ list_add(&hid->list, &dev->new_hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* schedule work to register the HID device */
+ schedule_work(&dev->hid_work);
+ return 0;
+}
+
+static int acc_unregister_hid(struct acc_dev *dev, int id)
+{
+ struct acc_hid_dev *hid;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->hid_list, id);
+ if (!hid)
+ hid = acc_hid_get(&dev->new_hid_list, id);
+ if (!hid) {
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return -EINVAL;
+ }
+
+ list_move(&hid->list, &dev->dead_hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ schedule_work(&dev->hid_work);
+ return 0;
+}
+
+static int create_bulk_endpoints(struct acc_dev *dev,
+ struct usb_endpoint_descriptor *in_desc,
+ struct usb_endpoint_descriptor *out_desc)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ struct usb_ep *ep;
+ int i;
+
+ DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+ ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_in = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_out got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_out = ep;
+
+ /* now allocate requests for our endpoints */
+ for (i = 0; i < TX_REQ_MAX; i++) {
+ req = acc_request_new(dev->ep_in, BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = acc_complete_in;
+ req_put(dev, &dev->tx_idle, req);
+ }
+ for (i = 0; i < RX_REQ_MAX; i++) {
+ req = acc_request_new(dev->ep_out, BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = acc_complete_out;
+ dev->rx_req[i] = req;
+ }
+
+ return 0;
+
+fail:
+ pr_err("acc_bind() could not allocate requests\n");
+ while ((req = req_get(dev, &dev->tx_idle)))
+ acc_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ acc_request_free(dev->rx_req[i], dev->ep_out);
+ return -1;
+}
+
+static ssize_t acc_read(struct file *fp, char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct acc_dev *dev = fp->private_data;
+ struct usb_request *req;
+ ssize_t r = count;
+ ssize_t data_length;
+ unsigned xfer;
+ int ret = 0;
+
+ pr_debug("acc_read(%zu)\n", count);
+
+ if (dev->disconnected) {
+ pr_debug("acc_read disconnected");
+ return -ENODEV;
+ }
+
+ if (count > BULK_BUFFER_SIZE)
+ count = BULK_BUFFER_SIZE;
+
+ /* we will block until we're online */
+ pr_debug("acc_read: waiting for online\n");
+ ret = wait_event_interruptible(dev->read_wq, dev->online);
+ if (ret < 0) {
+ r = ret;
+ goto done;
+ }
+
+ /*
+ * Calculate the data length by considering termination character.
+ * Then compansite the difference of rounding up to
+ * integer multiple of maxpacket size.
+ */
+ data_length = count;
+ data_length += dev->ep_out->maxpacket - 1;
+ data_length -= data_length % dev->ep_out->maxpacket;
+
+ if (dev->rx_done) {
+ // last req cancelled. try to get it.
+ req = dev->rx_req[0];
+ goto copy_data;
+ }
+
+requeue_req:
+ /* queue a request */
+ req = dev->rx_req[0];
+ req->length = data_length;
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ goto done;
+ } else {
+ pr_debug("rx %p queue\n", req);
+ }
+
+ /* wait for a request to complete */
+ ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+ if (ret < 0) {
+ r = ret;
+ ret = usb_ep_dequeue(dev->ep_out, req);
+ if (ret != 0) {
+ // cancel failed. There can be a data already received.
+ // it will be retrieved in the next read.
+ pr_debug("acc_read: cancelling failed %d", ret);
+ }
+ goto done;
+ }
+
+copy_data:
+ dev->rx_done = 0;
+ if (dev->online) {
+ /* If we got a 0-len packet, throw it back and try again. */
+ if (req->actual == 0)
+ goto requeue_req;
+
+ pr_debug("rx %p %u\n", req, req->actual);
+ xfer = (req->actual < count) ? req->actual : count;
+ r = xfer;
+ if (copy_to_user(buf, req->buf, xfer))
+ r = -EFAULT;
+ } else
+ r = -EIO;
+
+done:
+ pr_debug("acc_read returning %zd\n", r);
+ return r;
+}
+
+static ssize_t acc_write(struct file *fp, const char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct acc_dev *dev = fp->private_data;
+ struct usb_request *req = 0;
+ ssize_t r = count;
+ unsigned xfer;
+ int ret;
+
+ pr_debug("acc_write(%zu)\n", count);
+
+ if (!dev->online || dev->disconnected) {
+ pr_debug("acc_write disconnected or not online");
+ return -ENODEV;
+ }
+
+ while (count > 0) {
+ if (!dev->online) {
+ pr_debug("acc_write dev->error\n");
+ r = -EIO;
+ break;
+ }
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ ((req = req_get(dev, &dev->tx_idle)) || !dev->online));
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > BULK_BUFFER_SIZE) {
+ xfer = BULK_BUFFER_SIZE;
+ /* ZLP, They will be more TX requests so not yet. */
+ req->zero = 0;
+ } else {
+ xfer = count;
+ /* If the data length is a multple of the
+ * maxpacket size then send a zero length packet(ZLP).
+ */
+ req->zero = ((xfer % dev->ep_in->maxpacket) == 0);
+ }
+ if (copy_from_user(req->buf, buf, xfer)) {
+ r = -EFAULT;
+ break;
+ }
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ pr_debug("acc_write: xfer error %d\n", ret);
+ r = -EIO;
+ break;
+ }
+
+ buf += xfer;
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ req_put(dev, &dev->tx_idle, req);
+
+ pr_debug("acc_write returning %zd\n", r);
+ return r;
+}
+
+static long acc_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+ struct acc_dev *dev = fp->private_data;
+ char *src = NULL;
+ int ret;
+
+ switch (code) {
+ case ACCESSORY_GET_STRING_MANUFACTURER:
+ src = dev->manufacturer;
+ break;
+ case ACCESSORY_GET_STRING_MODEL:
+ src = dev->model;
+ break;
+ case ACCESSORY_GET_STRING_DESCRIPTION:
+ src = dev->description;
+ break;
+ case ACCESSORY_GET_STRING_VERSION:
+ src = dev->version;
+ break;
+ case ACCESSORY_GET_STRING_URI:
+ src = dev->uri;
+ break;
+ case ACCESSORY_GET_STRING_SERIAL:
+ src = dev->serial;
+ break;
+ case ACCESSORY_IS_START_REQUESTED:
+ return dev->start_requested;
+ case ACCESSORY_GET_AUDIO_MODE:
+ return dev->audio_mode;
+ }
+ if (!src)
+ return -EINVAL;
+
+ ret = strlen(src) + 1;
+ if (copy_to_user((void __user *)value, src, ret))
+ ret = -EFAULT;
+ return ret;
+}
+
+static int acc_open(struct inode *ip, struct file *fp)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ if (!dev)
+ return -ENODEV;
+
+ if (atomic_xchg(&dev->open_excl, 1)) {
+ put_acc_dev(dev);
+ return -EBUSY;
+ }
+
+ dev->disconnected = 0;
+ fp->private_data = dev;
+ return 0;
+}
+
+static int acc_release(struct inode *ip, struct file *fp)
+{
+ struct acc_dev *dev = fp->private_data;
+
+ if (!dev)
+ return -ENOENT;
+
+ /* indicate that we are disconnected
+ * still could be online so don't touch online flag
+ */
+ dev->disconnected = 1;
+
+ fp->private_data = NULL;
+ WARN_ON(!atomic_xchg(&dev->open_excl, 0));
+ put_acc_dev(dev);
+ return 0;
+}
+
+/* file operations for /dev/usb_accessory */
+static const struct file_operations acc_fops = {
+ .owner = THIS_MODULE,
+ .read = acc_read,
+ .write = acc_write,
+ .unlocked_ioctl = acc_ioctl,
+ .open = acc_open,
+ .release = acc_release,
+};
+
+static int acc_hid_probe(struct hid_device *hdev,
+ const struct hid_device_id *id)
+{
+ int ret;
+
+ ret = hid_parse(hdev);
+ if (ret)
+ return ret;
+ return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
+static struct miscdevice acc_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "usb_accessory",
+ .fops = &acc_fops,
+};
+
+static const struct hid_device_id acc_hid_table[] = {
+ { HID_USB_DEVICE(HID_ANY_ID, HID_ANY_ID) },
+ { }
+};
+
+static struct hid_driver acc_hid_driver = {
+ .name = "USB accessory",
+ .id_table = acc_hid_table,
+ .probe = acc_hid_probe,
+};
+
+static void acc_complete_setup_noop(struct usb_ep *ep, struct usb_request *req)
+{
+ /*
+ * Default no-op function when nothing needs to be done for the
+ * setup request
+ */
+}
+
+int acc_ctrlrequest(struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct acc_dev *dev = get_acc_dev();
+ int value = -EOPNOTSUPP;
+ struct acc_hid_dev *hid;
+ int offset;
+ u8 b_requestType = ctrl->bRequestType;
+ u8 b_request = ctrl->bRequest;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+ unsigned long flags;
+
+ /*
+ * If instance is not created which is the case in power off charging
+ * mode, dev will be NULL. Hence return error if it is the case.
+ */
+ if (!dev)
+ return -ENODEV;
+
+ if (b_requestType == (USB_DIR_OUT | USB_TYPE_VENDOR)) {
+ if (b_request == ACCESSORY_START) {
+ dev->start_requested = 1;
+ schedule_delayed_work(
+ &dev->start_work, msecs_to_jiffies(10));
+ value = 0;
+ cdev->req->complete = acc_complete_setup_noop;
+ } else if (b_request == ACCESSORY_SEND_STRING) {
+ dev->string_index = w_index;
+ cdev->gadget->ep0->driver_data = dev;
+ cdev->req->complete = acc_complete_set_string;
+ value = w_length;
+ } else if (b_request == ACCESSORY_SET_AUDIO_MODE &&
+ w_index == 0 && w_length == 0) {
+ dev->audio_mode = w_value;
+ cdev->req->complete = acc_complete_setup_noop;
+ value = 0;
+ } else if (b_request == ACCESSORY_REGISTER_HID) {
+ cdev->req->complete = acc_complete_setup_noop;
+ value = acc_register_hid(dev, w_value, w_index);
+ } else if (b_request == ACCESSORY_UNREGISTER_HID) {
+ cdev->req->complete = acc_complete_setup_noop;
+ value = acc_unregister_hid(dev, w_value);
+ } else if (b_request == ACCESSORY_SET_HID_REPORT_DESC) {
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->new_hid_list, w_value);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ if (!hid) {
+ value = -EINVAL;
+ goto err;
+ }
+ offset = w_index;
+ if (offset != hid->report_desc_offset
+ || offset + w_length > hid->report_desc_len) {
+ value = -EINVAL;
+ goto err;
+ }
+ cdev->req->context = hid;
+ cdev->req->complete = acc_complete_set_hid_report_desc;
+ value = w_length;
+ } else if (b_request == ACCESSORY_SEND_HID_EVENT) {
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->hid_list, w_value);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ if (!hid) {
+ value = -EINVAL;
+ goto err;
+ }
+ cdev->req->context = hid;
+ cdev->req->complete = acc_complete_send_hid_event;
+ value = w_length;
+ }
+ } else if (b_requestType == (USB_DIR_IN | USB_TYPE_VENDOR)) {
+ if (b_request == ACCESSORY_GET_PROTOCOL) {
+ *((u16 *)cdev->req->buf) = PROTOCOL_VERSION;
+ value = sizeof(u16);
+ cdev->req->complete = acc_complete_setup_noop;
+ /* clear any string left over from a previous session */
+ memset(dev->manufacturer, 0, sizeof(dev->manufacturer));
+ memset(dev->model, 0, sizeof(dev->model));
+ memset(dev->description, 0, sizeof(dev->description));
+ memset(dev->version, 0, sizeof(dev->version));
+ memset(dev->uri, 0, sizeof(dev->uri));
+ memset(dev->serial, 0, sizeof(dev->serial));
+ dev->start_requested = 0;
+ dev->audio_mode = 0;
+ }
+ }
+
+ if (value >= 0) {
+ cdev->req->zero = 0;
+ cdev->req->length = value;
+ value = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+ if (value < 0)
+ ERROR(cdev, "%s setup response queue error\n",
+ __func__);
+ }
+
+err:
+ if (value == -EOPNOTSUPP)
+ VDBG(cdev,
+ "unknown class-specific control req "
+ "%02x.%02x v%04x i%04x l%u\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+ put_acc_dev(dev);
+ return value;
+}
+EXPORT_SYMBOL_GPL(acc_ctrlrequest);
+
+static int
+__acc_function_bind(struct usb_configuration *c,
+ struct usb_function *f, bool configfs)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct acc_dev *dev = func_to_dev(f);
+ int id;
+ int ret;
+
+ DBG(cdev, "acc_function_bind dev: %p\n", dev);
+
+ if (configfs) {
+ if (acc_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+ ret = usb_string_id(c->cdev);
+ if (ret < 0)
+ return ret;
+ acc_string_defs[INTERFACE_STRING_INDEX].id = ret;
+ acc_interface_desc.iInterface = ret;
+ }
+ dev->cdev = c->cdev;
+ }
+ ret = hid_register_driver(&acc_hid_driver);
+ if (ret)
+ return ret;
+
+ dev->start_requested = 0;
+
+ /* allocate interface ID(s) */
+ id = usb_interface_id(c, f);
+ if (id < 0)
+ return id;
+ acc_interface_desc.bInterfaceNumber = id;
+
+ /* allocate endpoints */
+ ret = create_bulk_endpoints(dev, &acc_fullspeed_in_desc,
+ &acc_fullspeed_out_desc);
+ if (ret)
+ return ret;
+
+ /* support high speed hardware */
+ if (gadget_is_dualspeed(c->cdev->gadget)) {
+ acc_highspeed_in_desc.bEndpointAddress =
+ acc_fullspeed_in_desc.bEndpointAddress;
+ acc_highspeed_out_desc.bEndpointAddress =
+ acc_fullspeed_out_desc.bEndpointAddress;
+ }
+
+ DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+ gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+ f->name, dev->ep_in->name, dev->ep_out->name);
+ return 0;
+}
+
+static int
+acc_function_bind_configfs(struct usb_configuration *c,
+ struct usb_function *f) {
+ return __acc_function_bind(c, f, true);
+}
+
+static void
+kill_all_hid_devices(struct acc_dev *dev)
+{
+ struct acc_hid_dev *hid;
+ struct list_head *entry, *temp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_for_each_safe(entry, temp, &dev->hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ list_add(&hid->list, &dev->dead_hid_list);
+ }
+ list_for_each_safe(entry, temp, &dev->new_hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ list_add(&hid->list, &dev->dead_hid_list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ schedule_work(&dev->hid_work);
+}
+
+static void
+acc_hid_unbind(struct acc_dev *dev)
+{
+ hid_unregister_driver(&acc_hid_driver);
+ kill_all_hid_devices(dev);
+}
+
+static void
+acc_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_request *req;
+ int i;
+
+ dev->online = 0; /* clear online flag */
+ wake_up(&dev->read_wq); /* unblock reads on closure */
+ wake_up(&dev->write_wq); /* likewise for writes */
+
+ while ((req = req_get(dev, &dev->tx_idle)))
+ acc_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ acc_request_free(dev->rx_req[i], dev->ep_out);
+
+ acc_hid_unbind(dev);
+}
+
+static void acc_start_work(struct work_struct *data)
+{
+ char *envp[2] = { "ACCESSORY=START", NULL };
+
+ kobject_uevent_env(&acc_device.this_device->kobj, KOBJ_CHANGE, envp);
+}
+
+static int acc_hid_init(struct acc_hid_dev *hdev)
+{
+ struct hid_device *hid;
+ int ret;
+
+ hid = hid_allocate_device();
+ if (IS_ERR(hid))
+ return PTR_ERR(hid);
+
+ hid->ll_driver = &acc_hid_ll_driver;
+ hid->dev.parent = acc_device.this_device;
+
+ hid->bus = BUS_USB;
+ hid->vendor = HID_ANY_ID;
+ hid->product = HID_ANY_ID;
+ hid->driver_data = hdev;
+ ret = hid_add_device(hid);
+ if (ret) {
+ pr_err("can't add hid device: %d\n", ret);
+ hid_destroy_device(hid);
+ return ret;
+ }
+
+ hdev->hid = hid;
+ return 0;
+}
+
+static void acc_hid_delete(struct acc_hid_dev *hid)
+{
+ kfree(hid->report_desc);
+ kfree(hid);
+}
+
+static void acc_hid_work(struct work_struct *data)
+{
+ struct acc_dev *dev = get_acc_dev();
+ struct list_head *entry, *temp;
+ struct acc_hid_dev *hid;
+ struct list_head new_list, dead_list;
+ unsigned long flags;
+
+ if (!dev)
+ return;
+
+ INIT_LIST_HEAD(&new_list);
+
+ spin_lock_irqsave(&dev->lock, flags);
+
+ /* copy hids that are ready for initialization to new_list */
+ list_for_each_safe(entry, temp, &dev->new_hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ if (hid->report_desc_offset == hid->report_desc_len)
+ list_move(&hid->list, &new_list);
+ }
+
+ if (list_empty(&dev->dead_hid_list)) {
+ INIT_LIST_HEAD(&dead_list);
+ } else {
+ /* move all of dev->dead_hid_list to dead_list */
+ dead_list.prev = dev->dead_hid_list.prev;
+ dead_list.next = dev->dead_hid_list.next;
+ dead_list.next->prev = &dead_list;
+ dead_list.prev->next = &dead_list;
+ INIT_LIST_HEAD(&dev->dead_hid_list);
+ }
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* register new HID devices */
+ list_for_each_safe(entry, temp, &new_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ if (acc_hid_init(hid)) {
+ pr_err("can't add HID device %p\n", hid);
+ acc_hid_delete(hid);
+ } else {
+ spin_lock_irqsave(&dev->lock, flags);
+ list_move(&hid->list, &dev->hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ }
+ }
+
+ /* remove dead HID devices */
+ list_for_each_safe(entry, temp, &dead_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ if (hid->hid)
+ hid_destroy_device(hid->hid);
+ acc_hid_delete(hid);
+ }
+
+ put_acc_dev(dev);
+}
+
+static int acc_function_set_alt(struct usb_function *f,
+ unsigned intf, unsigned alt)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ DBG(cdev, "acc_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_out);
+ if (ret) {
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+
+ dev->online = 1;
+ dev->disconnected = 0; /* if online then not disconnected */
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+ return 0;
+}
+
+static void acc_function_disable(struct usb_function *f)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ DBG(cdev, "acc_function_disable\n");
+ acc_set_disconnected(dev); /* this now only sets disconnected */
+ dev->online = 0; /* so now need to clear online flag here too */
+ usb_ep_disable(dev->ep_in);
+ usb_ep_disable(dev->ep_out);
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+
+ VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int acc_setup(void)
+{
+ struct acc_dev_ref *ref = &_acc_dev_ref;
+ struct acc_dev *dev;
+ int ret;
+
+ if (kref_read(&ref->kref))
+ return -EBUSY;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ return -ENOMEM;
+
+ spin_lock_init(&dev->lock);
+ init_waitqueue_head(&dev->read_wq);
+ init_waitqueue_head(&dev->write_wq);
+ atomic_set(&dev->open_excl, 0);
+ INIT_LIST_HEAD(&dev->tx_idle);
+ INIT_LIST_HEAD(&dev->hid_list);
+ INIT_LIST_HEAD(&dev->new_hid_list);
+ INIT_LIST_HEAD(&dev->dead_hid_list);
+ INIT_DELAYED_WORK(&dev->start_work, acc_start_work);
+ INIT_WORK(&dev->hid_work, acc_hid_work);
+
+ dev->ref = ref;
+ if (cmpxchg_relaxed(&ref->acc_dev, NULL, dev)) {
+ ret = -EBUSY;
+ goto err_free_dev;
+ }
+
+ ret = misc_register(&acc_device);
+ if (ret)
+ goto err_zap_ptr;
+
+ kref_init(&ref->kref);
+ return 0;
+
+err_zap_ptr:
+ ref->acc_dev = NULL;
+err_free_dev:
+ kfree(dev);
+ pr_err("USB accessory gadget driver failed to initialize\n");
+ return ret;
+}
+
+void acc_disconnect(void)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ if (!dev)
+ return;
+
+ /* unregister all HID devices if USB is disconnected */
+ kill_all_hid_devices(dev);
+ put_acc_dev(dev);
+}
+EXPORT_SYMBOL_GPL(acc_disconnect);
+
+static void acc_cleanup(void)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ misc_deregister(&acc_device);
+ put_acc_dev(dev);
+ put_acc_dev(dev); /* Pairs with kref_init() in acc_setup() */
+}
+static struct acc_instance *to_acc_instance(struct config_item *item)
+{
+ return container_of(to_config_group(item), struct acc_instance,
+ func_inst.group);
+}
+
+static void acc_attr_release(struct config_item *item)
+{
+ struct acc_instance *fi_acc = to_acc_instance(item);
+
+ usb_put_function_instance(&fi_acc->func_inst);
+}
+
+static struct configfs_item_operations acc_item_ops = {
+ .release = acc_attr_release,
+};
+
+static struct config_item_type acc_func_type = {
+ .ct_item_ops = &acc_item_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+static struct acc_instance *to_fi_acc(struct usb_function_instance *fi)
+{
+ return container_of(fi, struct acc_instance, func_inst);
+}
+
+static int acc_set_inst_name(struct usb_function_instance *fi, const char *name)
+{
+ struct acc_instance *fi_acc;
+ char *ptr;
+ int name_len;
+
+ name_len = strlen(name) + 1;
+ if (name_len > MAX_INST_NAME_LEN)
+ return -ENAMETOOLONG;
+
+ ptr = kstrndup(name, name_len, GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
+
+ fi_acc = to_fi_acc(fi);
+ fi_acc->name = ptr;
+ return 0;
+}
+
+static void acc_free_inst(struct usb_function_instance *fi)
+{
+ struct acc_instance *fi_acc;
+
+ fi_acc = to_fi_acc(fi);
+ kfree(fi_acc->name);
+ acc_cleanup();
+}
+
+static struct usb_function_instance *acc_alloc_inst(void)
+{
+ struct acc_instance *fi_acc;
+ int err;
+
+ fi_acc = kzalloc(sizeof(*fi_acc), GFP_KERNEL);
+ if (!fi_acc)
+ return ERR_PTR(-ENOMEM);
+ fi_acc->func_inst.set_inst_name = acc_set_inst_name;
+ fi_acc->func_inst.free_func_inst = acc_free_inst;
+
+ err = acc_setup();
+ if (err) {
+ kfree(fi_acc);
+ return ERR_PTR(err);
+ }
+
+ config_group_init_type_name(&fi_acc->func_inst.group,
+ "", &acc_func_type);
+ return &fi_acc->func_inst;
+}
+
+static void acc_free(struct usb_function *f)
+{
+ struct acc_dev *dev = func_to_dev(f);
+
+ put_acc_dev(dev);
+}
+
+int acc_ctrlrequest_configfs(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl) {
+ if (f->config != NULL && f->config->cdev != NULL)
+ return acc_ctrlrequest(f->config->cdev, ctrl);
+ else
+ return -1;
+}
+
+static struct usb_function *acc_alloc(struct usb_function_instance *fi)
+{
+ struct acc_dev *dev = get_acc_dev();
+
+ dev->function.name = "accessory";
+ dev->function.strings = acc_strings,
+ dev->function.fs_descriptors = fs_acc_descs;
+ dev->function.hs_descriptors = hs_acc_descs;
+ dev->function.bind = acc_function_bind_configfs;
+ dev->function.unbind = acc_function_unbind;
+ dev->function.set_alt = acc_function_set_alt;
+ dev->function.disable = acc_function_disable;
+ dev->function.free_func = acc_free;
+ dev->function.setup = acc_ctrlrequest_configfs;
+
+ return &dev->function;
+}
+DECLARE_USB_FUNCTION_INIT(accessory, acc_alloc_inst, acc_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_audio_source.c b/drivers/usb/gadget/function/f_audio_source.c
new file mode 100644
index 0000000..8124af3
--- /dev/null
+++ b/drivers/usb/gadget/function/f_audio_source.c
@@ -0,0 +1,1071 @@
+/*
+ * Gadget Function Driver for USB audio source device
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/usb/audio.h>
+#include <linux/wait.h>
+#include <linux/pm_qos.h>
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+
+#include <linux/usb.h>
+#include <linux/usb_usual.h>
+#include <linux/usb/ch9.h>
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#define SAMPLE_RATE 44100
+#define FRAMES_PER_MSEC (SAMPLE_RATE / 1000)
+
+#define IN_EP_MAX_PACKET_SIZE 256
+
+/* Number of requests to allocate */
+#define IN_EP_REQ_COUNT 4
+
+#define AUDIO_AC_INTERFACE 0
+#define AUDIO_AS_INTERFACE 1
+#define AUDIO_NUM_INTERFACES 2
+#define MAX_INST_NAME_LEN 40
+
+/* B.3.1 Standard AC Interface Descriptor */
+static struct usb_interface_descriptor ac_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bNumEndpoints = 0,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+};
+
+DECLARE_UAC_AC_HEADER_DESCRIPTOR(2);
+
+#define UAC_DT_AC_HEADER_LENGTH UAC_DT_AC_HEADER_SIZE(AUDIO_NUM_INTERFACES)
+/* 1 input terminal, 1 output terminal and 1 feature unit */
+#define UAC_DT_TOTAL_LENGTH (UAC_DT_AC_HEADER_LENGTH \
+ + UAC_DT_INPUT_TERMINAL_SIZE + UAC_DT_OUTPUT_TERMINAL_SIZE \
+ + UAC_DT_FEATURE_UNIT_SIZE(0))
+/* B.3.2 Class-Specific AC Interface Descriptor */
+static struct uac1_ac_header_descriptor_2 ac_header_desc = {
+ .bLength = UAC_DT_AC_HEADER_LENGTH,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_HEADER,
+ .bcdADC = __constant_cpu_to_le16(0x0100),
+ .wTotalLength = __constant_cpu_to_le16(UAC_DT_TOTAL_LENGTH),
+ .bInCollection = AUDIO_NUM_INTERFACES,
+ .baInterfaceNr = {
+ [0] = AUDIO_AC_INTERFACE,
+ [1] = AUDIO_AS_INTERFACE,
+ }
+};
+
+#define INPUT_TERMINAL_ID 1
+static struct uac_input_terminal_descriptor input_terminal_desc = {
+ .bLength = UAC_DT_INPUT_TERMINAL_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_INPUT_TERMINAL,
+ .bTerminalID = INPUT_TERMINAL_ID,
+ .wTerminalType = UAC_INPUT_TERMINAL_MICROPHONE,
+ .bAssocTerminal = 0,
+ .wChannelConfig = 0x3,
+};
+
+DECLARE_UAC_FEATURE_UNIT_DESCRIPTOR(0);
+
+#define FEATURE_UNIT_ID 2
+static struct uac_feature_unit_descriptor_0 feature_unit_desc = {
+ .bLength = UAC_DT_FEATURE_UNIT_SIZE(0),
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_FEATURE_UNIT,
+ .bUnitID = FEATURE_UNIT_ID,
+ .bSourceID = INPUT_TERMINAL_ID,
+ .bControlSize = 2,
+};
+
+#define OUTPUT_TERMINAL_ID 3
+static struct uac1_output_terminal_descriptor output_terminal_desc = {
+ .bLength = UAC_DT_OUTPUT_TERMINAL_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_OUTPUT_TERMINAL,
+ .bTerminalID = OUTPUT_TERMINAL_ID,
+ .wTerminalType = UAC_TERMINAL_STREAMING,
+ .bAssocTerminal = FEATURE_UNIT_ID,
+ .bSourceID = FEATURE_UNIT_ID,
+};
+
+/* B.4.1 Standard AS Interface Descriptor */
+static struct usb_interface_descriptor as_interface_alt_0_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bAlternateSetting = 0,
+ .bNumEndpoints = 0,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+static struct usb_interface_descriptor as_interface_alt_1_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bAlternateSetting = 1,
+ .bNumEndpoints = 1,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+/* B.4.2 Class-Specific AS Interface Descriptor */
+static struct uac1_as_header_descriptor as_header_desc = {
+ .bLength = UAC_DT_AS_HEADER_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_AS_GENERAL,
+ .bTerminalLink = INPUT_TERMINAL_ID,
+ .bDelay = 1,
+ .wFormatTag = UAC_FORMAT_TYPE_I_PCM,
+};
+
+DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1);
+
+static struct uac_format_type_i_discrete_descriptor_1 as_type_i_desc = {
+ .bLength = UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1),
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_FORMAT_TYPE,
+ .bFormatType = UAC_FORMAT_TYPE_I,
+ .bSubframeSize = 2,
+ .bBitResolution = 16,
+ .bSamFreqType = 1,
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor hs_as_in_ep_desc = {
+ .bLength = USB_DT_ENDPOINT_AUDIO_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_SYNC_SYNC
+ | USB_ENDPOINT_XFER_ISOC,
+ .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+ .bInterval = 4, /* poll 1 per millisecond */
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor fs_as_in_ep_desc = {
+ .bLength = USB_DT_ENDPOINT_AUDIO_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_SYNC_SYNC
+ | USB_ENDPOINT_XFER_ISOC,
+ .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+ .bInterval = 1, /* poll 1 per millisecond */
+};
+
+/* Class-specific AS ISO OUT Endpoint Descriptor */
+static struct uac_iso_endpoint_descriptor as_iso_in_desc = {
+ .bLength = UAC_ISO_ENDPOINT_DESC_SIZE,
+ .bDescriptorType = USB_DT_CS_ENDPOINT,
+ .bDescriptorSubtype = UAC_EP_GENERAL,
+ .bmAttributes = 1,
+ .bLockDelayUnits = 1,
+ .wLockDelay = __constant_cpu_to_le16(1),
+};
+
+static struct usb_descriptor_header *hs_audio_desc[] = {
+ (struct usb_descriptor_header *)&ac_interface_desc,
+ (struct usb_descriptor_header *)&ac_header_desc,
+
+ (struct usb_descriptor_header *)&input_terminal_desc,
+ (struct usb_descriptor_header *)&output_terminal_desc,
+ (struct usb_descriptor_header *)&feature_unit_desc,
+
+ (struct usb_descriptor_header *)&as_interface_alt_0_desc,
+ (struct usb_descriptor_header *)&as_interface_alt_1_desc,
+ (struct usb_descriptor_header *)&as_header_desc,
+
+ (struct usb_descriptor_header *)&as_type_i_desc,
+
+ (struct usb_descriptor_header *)&hs_as_in_ep_desc,
+ (struct usb_descriptor_header *)&as_iso_in_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *fs_audio_desc[] = {
+ (struct usb_descriptor_header *)&ac_interface_desc,
+ (struct usb_descriptor_header *)&ac_header_desc,
+
+ (struct usb_descriptor_header *)&input_terminal_desc,
+ (struct usb_descriptor_header *)&output_terminal_desc,
+ (struct usb_descriptor_header *)&feature_unit_desc,
+
+ (struct usb_descriptor_header *)&as_interface_alt_0_desc,
+ (struct usb_descriptor_header *)&as_interface_alt_1_desc,
+ (struct usb_descriptor_header *)&as_header_desc,
+
+ (struct usb_descriptor_header *)&as_type_i_desc,
+
+ (struct usb_descriptor_header *)&fs_as_in_ep_desc,
+ (struct usb_descriptor_header *)&as_iso_in_desc,
+ NULL,
+};
+
+static struct snd_pcm_hardware audio_hw_info = {
+ .info = SNDRV_PCM_INFO_MMAP |
+ SNDRV_PCM_INFO_MMAP_VALID |
+ SNDRV_PCM_INFO_BATCH |
+ SNDRV_PCM_INFO_INTERLEAVED |
+ SNDRV_PCM_INFO_BLOCK_TRANSFER,
+
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
+ .channels_min = 2,
+ .channels_max = 2,
+ .rate_min = SAMPLE_RATE,
+ .rate_max = SAMPLE_RATE,
+
+ .buffer_bytes_max = 1024 * 1024,
+ .period_bytes_min = 64,
+ .period_bytes_max = 512 * 1024,
+ .periods_min = 2,
+ .periods_max = 1024,
+};
+
+/*-------------------------------------------------------------------------*/
+
+struct audio_source_config {
+ int card;
+ int device;
+};
+
+struct audio_dev {
+ struct usb_function func;
+ struct snd_card *card;
+ struct snd_pcm *pcm;
+ struct snd_pcm_substream *substream;
+
+ struct list_head idle_reqs;
+ struct usb_ep *in_ep;
+
+ spinlock_t lock;
+
+ /* beginning, end and current position in our buffer */
+ void *buffer_start;
+ void *buffer_end;
+ void *buffer_pos;
+
+ /* byte size of a "period" */
+ unsigned int period;
+ /* bytes sent since last call to snd_pcm_period_elapsed */
+ unsigned int period_offset;
+ /* time we started playing */
+ ktime_t start_time;
+ /* number of frames sent since start_time */
+ s64 frames_sent;
+ struct audio_source_config *config;
+ /* for creating and issuing QoS requests */
+ struct pm_qos_request pm_qos;
+};
+
+static inline struct audio_dev *func_to_audio(struct usb_function *f)
+{
+ return container_of(f, struct audio_dev, func);
+}
+
+/*-------------------------------------------------------------------------*/
+
+struct audio_source_instance {
+ struct usb_function_instance func_inst;
+ const char *name;
+ struct audio_source_config *config;
+ struct device *audio_device;
+};
+
+static void audio_source_attr_release(struct config_item *item);
+
+static struct configfs_item_operations audio_source_item_ops = {
+ .release = audio_source_attr_release,
+};
+
+static struct config_item_type audio_source_func_type = {
+ .ct_item_ops = &audio_source_item_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+static ssize_t audio_source_pcm_show(struct device *dev,
+ struct device_attribute *attr, char *buf);
+
+static DEVICE_ATTR(pcm, S_IRUGO, audio_source_pcm_show, NULL);
+
+static struct device_attribute *audio_source_function_attributes[] = {
+ &dev_attr_pcm,
+ NULL
+};
+
+/*--------------------------------------------------------------------------*/
+
+static struct usb_request *audio_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+
+ if (!req)
+ return NULL;
+
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+ req->length = buffer_size;
+ return req;
+}
+
+static void audio_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+static void audio_req_put(struct audio_dev *audio, struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ list_add_tail(&req->list, &audio->idle_reqs);
+ spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static struct usb_request *audio_req_get(struct audio_dev *audio)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ if (list_empty(&audio->idle_reqs)) {
+ req = 0;
+ } else {
+ req = list_first_entry(&audio->idle_reqs, struct usb_request,
+ list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&audio->lock, flags);
+ return req;
+}
+
+/* send the appropriate number of packets to match our bitrate */
+static void audio_send(struct audio_dev *audio)
+{
+ struct snd_pcm_runtime *runtime;
+ struct usb_request *req;
+ int length, length1, length2, ret;
+ s64 msecs;
+ s64 frames;
+ ktime_t now;
+
+ /* audio->substream will be null if we have been closed */
+ if (!audio->substream)
+ return;
+ /* audio->buffer_pos will be null if we have been stopped */
+ if (!audio->buffer_pos)
+ return;
+
+ runtime = audio->substream->runtime;
+
+ /* compute number of frames to send */
+ now = ktime_get();
+ msecs = div_s64((ktime_to_ns(now) - ktime_to_ns(audio->start_time)),
+ 1000000);
+ frames = div_s64((msecs * SAMPLE_RATE), 1000);
+
+ /* Readjust our frames_sent if we fall too far behind.
+ * If we get too far behind it is better to drop some frames than
+ * to keep sending data too fast in an attempt to catch up.
+ */
+ if (frames - audio->frames_sent > 10 * FRAMES_PER_MSEC)
+ audio->frames_sent = frames - FRAMES_PER_MSEC;
+
+ frames -= audio->frames_sent;
+
+ /* We need to send something to keep the pipeline going */
+ if (frames <= 0)
+ frames = FRAMES_PER_MSEC;
+
+ while (frames > 0) {
+ req = audio_req_get(audio);
+ if (!req)
+ break;
+
+ length = frames_to_bytes(runtime, frames);
+ if (length > IN_EP_MAX_PACKET_SIZE)
+ length = IN_EP_MAX_PACKET_SIZE;
+
+ if (audio->buffer_pos + length > audio->buffer_end)
+ length1 = audio->buffer_end - audio->buffer_pos;
+ else
+ length1 = length;
+ memcpy(req->buf, audio->buffer_pos, length1);
+ if (length1 < length) {
+ /* Wrap around and copy remaining length
+ * at beginning of buffer.
+ */
+ length2 = length - length1;
+ memcpy(req->buf + length1, audio->buffer_start,
+ length2);
+ audio->buffer_pos = audio->buffer_start + length2;
+ } else {
+ audio->buffer_pos += length1;
+ if (audio->buffer_pos >= audio->buffer_end)
+ audio->buffer_pos = audio->buffer_start;
+ }
+
+ req->length = length;
+ ret = usb_ep_queue(audio->in_ep, req, GFP_ATOMIC);
+ if (ret < 0) {
+ pr_err("usb_ep_queue failed ret: %d\n", ret);
+ audio_req_put(audio, req);
+ break;
+ }
+
+ frames -= bytes_to_frames(runtime, length);
+ audio->frames_sent += bytes_to_frames(runtime, length);
+ }
+}
+
+static void audio_control_complete(struct usb_ep *ep, struct usb_request *req)
+{
+ /* nothing to do here */
+}
+
+static void audio_data_complete(struct usb_ep *ep, struct usb_request *req)
+{
+ struct audio_dev *audio = req->context;
+
+ pr_debug("audio_data_complete req->status %d req->actual %d\n",
+ req->status, req->actual);
+
+ audio_req_put(audio, req);
+
+ if (!audio->buffer_start || req->status)
+ return;
+
+ audio->period_offset += req->actual;
+ if (audio->period_offset >= audio->period) {
+ snd_pcm_period_elapsed(audio->substream);
+ audio->period_offset = 0;
+ }
+ audio_send(audio);
+}
+
+static int audio_set_endpoint_req(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl)
+{
+ int value = -EOPNOTSUPP;
+ u16 ep = le16_to_cpu(ctrl->wIndex);
+ u16 len = le16_to_cpu(ctrl->wLength);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+
+ pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+ ctrl->bRequest, w_value, len, ep);
+
+ switch (ctrl->bRequest) {
+ case UAC_SET_CUR:
+ case UAC_SET_MIN:
+ case UAC_SET_MAX:
+ case UAC_SET_RES:
+ value = len;
+ break;
+ default:
+ break;
+ }
+
+ return value;
+}
+
+static int audio_get_endpoint_req(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int value = -EOPNOTSUPP;
+ u8 ep = ((le16_to_cpu(ctrl->wIndex) >> 8) & 0xFF);
+ u16 len = le16_to_cpu(ctrl->wLength);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u8 *buf = cdev->req->buf;
+
+ pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+ ctrl->bRequest, w_value, len, ep);
+
+ if (w_value == UAC_EP_CS_ATTR_SAMPLE_RATE << 8) {
+ switch (ctrl->bRequest) {
+ case UAC_GET_CUR:
+ case UAC_GET_MIN:
+ case UAC_GET_MAX:
+ case UAC_GET_RES:
+ /* return our sample rate */
+ buf[0] = (u8)SAMPLE_RATE;
+ buf[1] = (u8)(SAMPLE_RATE >> 8);
+ buf[2] = (u8)(SAMPLE_RATE >> 16);
+ value = 3;
+ break;
+ default:
+ break;
+ }
+ }
+
+ return value;
+}
+
+static int
+audio_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
+{
+ struct usb_composite_dev *cdev = f->config->cdev;
+ struct usb_request *req = cdev->req;
+ int value = -EOPNOTSUPP;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+
+ /* composite driver infrastructure handles everything; interface
+ * activation uses set_alt().
+ */
+ switch (ctrl->bRequestType) {
+ case USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+ value = audio_set_endpoint_req(f, ctrl);
+ break;
+
+ case USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+ value = audio_get_endpoint_req(f, ctrl);
+ break;
+ }
+
+ /* respond with data transfer or status phase? */
+ if (value >= 0) {
+ pr_debug("audio req%02x.%02x v%04x i%04x l%d\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+ req->zero = 0;
+ req->length = value;
+ req->complete = audio_control_complete;
+ value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC);
+ if (value < 0)
+ pr_err("audio response on err %d\n", value);
+ }
+
+ /* device either stalls (value < 0) or reports success */
+ return value;
+}
+
+static int audio_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
+{
+ struct audio_dev *audio = func_to_audio(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ pr_debug("audio_set_alt intf %d, alt %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, audio->in_ep);
+ if (ret)
+ return ret;
+
+ usb_ep_enable(audio->in_ep);
+ return 0;
+}
+
+static void audio_disable(struct usb_function *f)
+{
+ struct audio_dev *audio = func_to_audio(f);
+
+ pr_debug("audio_disable\n");
+ usb_ep_disable(audio->in_ep);
+}
+
+static void audio_free_func(struct usb_function *f)
+{
+ /* no-op */
+}
+
+/*-------------------------------------------------------------------------*/
+
+static void audio_build_desc(struct audio_dev *audio)
+{
+ u8 *sam_freq;
+ int rate;
+
+ /* Set channel numbers */
+ input_terminal_desc.bNrChannels = 2;
+ as_type_i_desc.bNrChannels = 2;
+
+ /* Set sample rates */
+ rate = SAMPLE_RATE;
+ sam_freq = as_type_i_desc.tSamFreq[0];
+ memcpy(sam_freq, &rate, 3);
+}
+
+
+static int snd_card_setup(struct usb_configuration *c,
+ struct audio_source_config *config);
+static struct audio_source_instance *to_fi_audio_source(
+ const struct usb_function_instance *fi);
+
+
+/* audio function driver setup/binding */
+static int
+audio_bind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct audio_dev *audio = func_to_audio(f);
+ int status;
+ struct usb_ep *ep;
+ struct usb_request *req;
+ int i;
+ int err;
+
+ if (IS_ENABLED(CONFIG_USB_CONFIGFS)) {
+ struct audio_source_instance *fi_audio =
+ to_fi_audio_source(f->fi);
+ struct audio_source_config *config =
+ fi_audio->config;
+
+ err = snd_card_setup(c, config);
+ if (err)
+ return err;
+ }
+
+ audio_build_desc(audio);
+
+ /* allocate instance-specific interface IDs, and patch descriptors */
+ status = usb_interface_id(c, f);
+ if (status < 0)
+ goto fail;
+ ac_interface_desc.bInterfaceNumber = status;
+
+ /* AUDIO_AC_INTERFACE */
+ ac_header_desc.baInterfaceNr[0] = status;
+
+ status = usb_interface_id(c, f);
+ if (status < 0)
+ goto fail;
+ as_interface_alt_0_desc.bInterfaceNumber = status;
+ as_interface_alt_1_desc.bInterfaceNumber = status;
+
+ /* AUDIO_AS_INTERFACE */
+ ac_header_desc.baInterfaceNr[1] = status;
+
+ status = -ENODEV;
+
+ /* allocate our endpoint */
+ ep = usb_ep_autoconfig(cdev->gadget, &fs_as_in_ep_desc);
+ if (!ep)
+ goto fail;
+ audio->in_ep = ep;
+ ep->driver_data = audio; /* claim */
+
+ if (gadget_is_dualspeed(c->cdev->gadget))
+ hs_as_in_ep_desc.bEndpointAddress =
+ fs_as_in_ep_desc.bEndpointAddress;
+
+ f->fs_descriptors = fs_audio_desc;
+ f->hs_descriptors = hs_audio_desc;
+
+ for (i = 0, status = 0; i < IN_EP_REQ_COUNT && status == 0; i++) {
+ req = audio_request_new(ep, IN_EP_MAX_PACKET_SIZE);
+ if (req) {
+ req->context = audio;
+ req->complete = audio_data_complete;
+ audio_req_put(audio, req);
+ } else
+ status = -ENOMEM;
+ }
+
+fail:
+ return status;
+}
+
+static void
+audio_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct audio_dev *audio = func_to_audio(f);
+ struct usb_request *req;
+
+ while ((req = audio_req_get(audio)))
+ audio_request_free(req, audio->in_ep);
+
+ snd_card_free_when_closed(audio->card);
+ audio->card = NULL;
+ audio->pcm = NULL;
+ audio->substream = NULL;
+ audio->in_ep = NULL;
+
+ if (IS_ENABLED(CONFIG_USB_CONFIGFS)) {
+ struct audio_source_instance *fi_audio =
+ to_fi_audio_source(f->fi);
+ struct audio_source_config *config =
+ fi_audio->config;
+
+ config->card = -1;
+ config->device = -1;
+ }
+}
+
+static void audio_pcm_playback_start(struct audio_dev *audio)
+{
+ audio->start_time = ktime_get();
+ audio->frames_sent = 0;
+ audio_send(audio);
+}
+
+static void audio_pcm_playback_stop(struct audio_dev *audio)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ audio->buffer_start = 0;
+ audio->buffer_end = 0;
+ audio->buffer_pos = 0;
+ spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static int audio_pcm_open(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = substream->private_data;
+
+ runtime->private_data = audio;
+ runtime->hw = audio_hw_info;
+ snd_pcm_limit_hw_rates(runtime);
+ runtime->hw.channels_max = 2;
+
+ audio->substream = substream;
+
+ /* Add the QoS request and set the latency to 0 */
+ pm_qos_add_request(&audio->pm_qos, PM_QOS_CPU_DMA_LATENCY, 0);
+
+ return 0;
+}
+
+static int audio_pcm_close(struct snd_pcm_substream *substream)
+{
+ struct audio_dev *audio = substream->private_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+
+ /* Remove the QoS request */
+ pm_qos_remove_request(&audio->pm_qos);
+
+ audio->substream = NULL;
+ spin_unlock_irqrestore(&audio->lock, flags);
+
+ return 0;
+}
+
+static int audio_pcm_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params)
+{
+ unsigned int channels = params_channels(params);
+ unsigned int rate = params_rate(params);
+
+ if (rate != SAMPLE_RATE)
+ return -EINVAL;
+ if (channels != 2)
+ return -EINVAL;
+
+ return snd_pcm_lib_alloc_vmalloc_buffer(substream,
+ params_buffer_bytes(params));
+}
+
+static int audio_pcm_hw_free(struct snd_pcm_substream *substream)
+{
+ return snd_pcm_lib_free_vmalloc_buffer(substream);
+}
+
+static int audio_pcm_prepare(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = runtime->private_data;
+
+ audio->period = snd_pcm_lib_period_bytes(substream);
+ audio->period_offset = 0;
+ audio->buffer_start = runtime->dma_area;
+ audio->buffer_end = audio->buffer_start
+ + snd_pcm_lib_buffer_bytes(substream);
+ audio->buffer_pos = audio->buffer_start;
+
+ return 0;
+}
+
+static snd_pcm_uframes_t audio_pcm_pointer(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = runtime->private_data;
+ ssize_t bytes = audio->buffer_pos - audio->buffer_start;
+
+ /* return offset of next frame to fill in our buffer */
+ return bytes_to_frames(runtime, bytes);
+}
+
+static int audio_pcm_playback_trigger(struct snd_pcm_substream *substream,
+ int cmd)
+{
+ struct audio_dev *audio = substream->runtime->private_data;
+ int ret = 0;
+
+ switch (cmd) {
+ case SNDRV_PCM_TRIGGER_START:
+ case SNDRV_PCM_TRIGGER_RESUME:
+ audio_pcm_playback_start(audio);
+ break;
+
+ case SNDRV_PCM_TRIGGER_STOP:
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ audio_pcm_playback_stop(audio);
+ break;
+
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static struct audio_dev _audio_dev = {
+ .func = {
+ .name = "audio_source",
+ .bind = audio_bind,
+ .unbind = audio_unbind,
+ .set_alt = audio_set_alt,
+ .setup = audio_setup,
+ .disable = audio_disable,
+ .free_func = audio_free_func,
+ },
+ .lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock),
+ .idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs),
+};
+
+static struct snd_pcm_ops audio_playback_ops = {
+ .open = audio_pcm_open,
+ .close = audio_pcm_close,
+ .ioctl = snd_pcm_lib_ioctl,
+ .hw_params = audio_pcm_hw_params,
+ .hw_free = audio_pcm_hw_free,
+ .prepare = audio_pcm_prepare,
+ .trigger = audio_pcm_playback_trigger,
+ .pointer = audio_pcm_pointer,
+};
+
+int audio_source_bind_config(struct usb_configuration *c,
+ struct audio_source_config *config)
+{
+ struct audio_dev *audio;
+ int err;
+
+ config->card = -1;
+ config->device = -1;
+
+ audio = &_audio_dev;
+
+ err = snd_card_setup(c, config);
+ if (err)
+ return err;
+
+ err = usb_add_function(c, &audio->func);
+ if (err)
+ goto add_fail;
+
+ return 0;
+
+add_fail:
+ snd_card_free(audio->card);
+ return err;
+}
+
+static int snd_card_setup(struct usb_configuration *c,
+ struct audio_source_config *config)
+{
+ struct audio_dev *audio;
+ struct snd_card *card;
+ struct snd_pcm *pcm;
+ int err;
+
+ audio = &_audio_dev;
+
+ err = snd_card_new(&c->cdev->gadget->dev,
+ SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
+ THIS_MODULE, 0, &card);
+ if (err)
+ return err;
+
+ err = snd_pcm_new(card, "USB audio source", 0, 1, 0, &pcm);
+ if (err)
+ goto pcm_fail;
+
+ pcm->private_data = audio;
+ pcm->info_flags = 0;
+ audio->pcm = pcm;
+
+ strlcpy(pcm->name, "USB gadget audio", sizeof(pcm->name));
+
+ snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &audio_playback_ops);
+ snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
+ NULL, 0, 64 * 1024);
+
+ strlcpy(card->driver, "audio_source", sizeof(card->driver));
+ strlcpy(card->shortname, card->driver, sizeof(card->shortname));
+ strlcpy(card->longname, "USB accessory audio source",
+ sizeof(card->longname));
+
+ err = snd_card_register(card);
+ if (err)
+ goto register_fail;
+
+ config->card = pcm->card->number;
+ config->device = pcm->device;
+ audio->card = card;
+ return 0;
+
+register_fail:
+pcm_fail:
+ snd_card_free(audio->card);
+ return err;
+}
+
+static struct audio_source_instance *to_audio_source_instance(
+ struct config_item *item)
+{
+ return container_of(to_config_group(item), struct audio_source_instance,
+ func_inst.group);
+}
+
+static struct audio_source_instance *to_fi_audio_source(
+ const struct usb_function_instance *fi)
+{
+ return container_of(fi, struct audio_source_instance, func_inst);
+}
+
+static void audio_source_attr_release(struct config_item *item)
+{
+ struct audio_source_instance *fi_audio = to_audio_source_instance(item);
+
+ usb_put_function_instance(&fi_audio->func_inst);
+}
+
+static int audio_source_set_inst_name(struct usb_function_instance *fi,
+ const char *name)
+{
+ struct audio_source_instance *fi_audio;
+ char *ptr;
+ int name_len;
+
+ name_len = strlen(name) + 1;
+ if (name_len > MAX_INST_NAME_LEN)
+ return -ENAMETOOLONG;
+
+ ptr = kstrndup(name, name_len, GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
+
+ fi_audio = to_fi_audio_source(fi);
+ fi_audio->name = ptr;
+
+ return 0;
+}
+
+static void audio_source_free_inst(struct usb_function_instance *fi)
+{
+ struct audio_source_instance *fi_audio;
+
+ fi_audio = to_fi_audio_source(fi);
+ device_destroy(fi_audio->audio_device->class,
+ fi_audio->audio_device->devt);
+ kfree(fi_audio->name);
+ kfree(fi_audio->config);
+}
+
+static ssize_t audio_source_pcm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct audio_source_instance *fi_audio = dev_get_drvdata(dev);
+ struct audio_source_config *config = fi_audio->config;
+
+ /* print PCM card and device numbers */
+ return sprintf(buf, "%d %d\n", config->card, config->device);
+}
+
+struct device *create_function_device(char *name);
+
+static struct usb_function_instance *audio_source_alloc_inst(void)
+{
+ struct audio_source_instance *fi_audio;
+ struct device_attribute **attrs;
+ struct device_attribute *attr;
+ struct device *dev;
+ void *err_ptr;
+ int err = 0;
+
+ fi_audio = kzalloc(sizeof(*fi_audio), GFP_KERNEL);
+ if (!fi_audio)
+ return ERR_PTR(-ENOMEM);
+
+ fi_audio->func_inst.set_inst_name = audio_source_set_inst_name;
+ fi_audio->func_inst.free_func_inst = audio_source_free_inst;
+
+ fi_audio->config = kzalloc(sizeof(struct audio_source_config),
+ GFP_KERNEL);
+ if (!fi_audio->config) {
+ err_ptr = ERR_PTR(-ENOMEM);
+ goto fail_audio;
+ }
+
+ config_group_init_type_name(&fi_audio->func_inst.group, "",
+ &audio_source_func_type);
+ dev = create_function_device("f_audio_source");
+
+ if (IS_ERR(dev)) {
+ err_ptr = dev;
+ goto fail_audio_config;
+ }
+
+ fi_audio->config->card = -1;
+ fi_audio->config->device = -1;
+ fi_audio->audio_device = dev;
+
+ attrs = audio_source_function_attributes;
+ if (attrs) {
+ while ((attr = *attrs++) && !err)
+ err = device_create_file(dev, attr);
+ if (err) {
+ err_ptr = ERR_PTR(-EINVAL);
+ goto fail_device;
+ }
+ }
+
+ dev_set_drvdata(dev, fi_audio);
+ _audio_dev.config = fi_audio->config;
+
+ return &fi_audio->func_inst;
+
+fail_device:
+ device_destroy(dev->class, dev->devt);
+fail_audio_config:
+ kfree(fi_audio->config);
+fail_audio:
+ kfree(fi_audio);
+ return err_ptr;
+
+}
+
+static struct usb_function *audio_source_alloc(struct usb_function_instance *fi)
+{
+ return &_audio_dev.func;
+}
+
+DECLARE_USB_FUNCTION_INIT(audio_source, audio_source_alloc_inst,
+ audio_source_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 58e8208..a4c2dc0 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -1174,6 +1174,65 @@ static void f_midi_free_inst(struct usb_function_instance *f)
kfree(opts);
}
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+extern struct device *create_function_device(char *name);
+static ssize_t alsa_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct usb_function_instance *fi_midi = dev_get_drvdata(dev);
+ struct f_midi *midi;
+
+ if (!fi_midi->f)
+ dev_warn(dev, "f_midi: function not set\n");
+
+ if (fi_midi && fi_midi->f) {
+ midi = func_to_midi(fi_midi->f);
+ if (midi->rmidi && midi->rmidi->card)
+ return sprintf(buf, "%d %d\n",
+ midi->rmidi->card->number, midi->rmidi->device);
+ }
+
+ /* print PCM card and device numbers */
+ return sprintf(buf, "%d %d\n", -1, -1);
+}
+
+static DEVICE_ATTR(alsa, S_IRUGO, alsa_show, NULL);
+
+static struct device_attribute *alsa_function_attributes[] = {
+ &dev_attr_alsa,
+ NULL
+};
+
+static int create_alsa_device(struct usb_function_instance *fi)
+{
+ struct device *dev;
+ struct device_attribute **attrs;
+ struct device_attribute *attr;
+ int err = 0;
+
+ dev = create_function_device("f_midi");
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
+
+ attrs = alsa_function_attributes;
+ if (attrs) {
+ while ((attr = *attrs++) && !err)
+ err = device_create_file(dev, attr);
+ if (err) {
+ device_destroy(dev->class, dev->devt);
+ return -EINVAL;
+ }
+ }
+ dev_set_drvdata(dev, fi);
+ return 0;
+}
+#else
+static int create_alsa_device(struct usb_function_instance *fi)
+{
+ return 0;
+}
+#endif
+
static struct usb_function_instance *f_midi_alloc_inst(void)
{
struct f_midi_opts *opts;
@@ -1191,6 +1250,11 @@ static struct usb_function_instance *f_midi_alloc_inst(void)
opts->in_ports = 1;
opts->out_ports = 1;
+ if (create_alsa_device(&opts->func_inst)) {
+ kfree(opts);
+ return ERR_PTR(-ENODEV);
+ }
+
config_group_init_type_name(&opts->func_inst.group, "",
&midi_func_type);
@@ -1208,6 +1272,7 @@ static void f_midi_free(struct usb_function *f)
mutex_lock(&opts->lock);
kfifo_free(&midi->in_req_fifo);
kfree(midi);
+ opts->func_inst.f = NULL;
--opts->refcnt;
mutex_unlock(&opts->lock);
}
@@ -1287,6 +1352,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi)
midi->func.disable = f_midi_disable;
midi->func.free_func = f_midi_free;
+ fi->f = &midi->func;
return &midi->func;
midi_free:
diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c
new file mode 100644
index 0000000..77fe8f5
--- /dev/null
+++ b/drivers/usb/gadget/function/f_mtp.c
@@ -0,0 +1,1564 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/usb.h>
+#include <linux/usb_usual.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_mtp.h>
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#include "configfs.h"
+
+#define MTP_BULK_BUFFER_SIZE 16384
+#define INTR_BUFFER_SIZE 28
+#define MAX_INST_NAME_LEN 40
+#define MTP_MAX_FILE_SIZE 0xFFFFFFFFL
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX 0
+
+/* values for mtp_dev.state */
+#define STATE_OFFLINE 0 /* initial state, disconnected */
+#define STATE_READY 1 /* ready for userspace calls */
+#define STATE_BUSY 2 /* processing userspace calls */
+#define STATE_CANCELED 3 /* transaction canceled by host */
+#define STATE_ERROR 4 /* error from completion routine */
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+#define INTR_REQ_MAX 5
+
+/* ID for Microsoft MTP OS String */
+#define MTP_OS_STRING_ID 0xEE
+
+/* MTP class reqeusts */
+#define MTP_REQ_CANCEL 0x64
+#define MTP_REQ_GET_EXT_EVENT_DATA 0x65
+#define MTP_REQ_RESET 0x66
+#define MTP_REQ_GET_DEVICE_STATUS 0x67
+
+/* constants for device status */
+#define MTP_RESPONSE_OK 0x2001
+#define MTP_RESPONSE_DEVICE_BUSY 0x2019
+#define DRIVER_NAME "mtp"
+
+static const char mtp_shortname[] = DRIVER_NAME "_usb";
+
+struct mtp_dev {
+ struct usb_function function;
+ struct usb_composite_dev *cdev;
+ spinlock_t lock;
+
+ struct usb_ep *ep_in;
+ struct usb_ep *ep_out;
+ struct usb_ep *ep_intr;
+
+ int state;
+
+ /* synchronize access to our device file */
+ atomic_t open_excl;
+ /* to enforce only one ioctl at a time */
+ atomic_t ioctl_excl;
+
+ struct list_head tx_idle;
+ struct list_head intr_idle;
+
+ wait_queue_head_t read_wq;
+ wait_queue_head_t write_wq;
+ wait_queue_head_t intr_wq;
+ struct usb_request *rx_req[RX_REQ_MAX];
+ int rx_done;
+
+ /* for processing MTP_SEND_FILE, MTP_RECEIVE_FILE and
+ * MTP_SEND_FILE_WITH_HEADER ioctls on a work queue
+ */
+ struct workqueue_struct *wq;
+ struct work_struct send_file_work;
+ struct work_struct receive_file_work;
+ struct file *xfer_file;
+ loff_t xfer_file_offset;
+ int64_t xfer_file_length;
+ unsigned xfer_send_header;
+ uint16_t xfer_command;
+ uint32_t xfer_transaction_id;
+ int xfer_result;
+};
+
+static struct usb_interface_descriptor mtp_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 3,
+ .bInterfaceClass = USB_CLASS_VENDOR_SPEC,
+ .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC,
+ .bInterfaceProtocol = 0,
+};
+
+static struct usb_interface_descriptor ptp_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 3,
+ .bInterfaceClass = USB_CLASS_STILL_IMAGE,
+ .bInterfaceSubClass = 1,
+ .bInterfaceProtocol = 1,
+};
+
+static struct usb_endpoint_descriptor mtp_ss_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(1024),
+};
+
+static struct usb_ss_ep_comp_descriptor mtp_ss_in_comp_desc = {
+ .bLength = sizeof(mtp_ss_in_comp_desc),
+ .bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+ /* .bMaxBurst = DYNAMIC, */
+};
+
+static struct usb_endpoint_descriptor mtp_ss_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(1024),
+};
+
+static struct usb_ss_ep_comp_descriptor mtp_ss_out_comp_desc = {
+ .bLength = sizeof(mtp_ss_out_comp_desc),
+ .bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+ /* .bMaxBurst = DYNAMIC, */
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_intr_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_INT,
+ .wMaxPacketSize = __constant_cpu_to_le16(INTR_BUFFER_SIZE),
+ .bInterval = 6,
+};
+
+static struct usb_ss_ep_comp_descriptor mtp_intr_ss_comp_desc = {
+ .bLength = sizeof(mtp_intr_ss_comp_desc),
+ .bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+ .wBytesPerInterval = cpu_to_le16(INTR_BUFFER_SIZE),
+};
+
+static struct usb_descriptor_header *fs_mtp_descs[] = {
+ (struct usb_descriptor_header *) &mtp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_mtp_descs[] = {
+ (struct usb_descriptor_header *) &mtp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *ss_mtp_descs[] = {
+ (struct usb_descriptor_header *) &mtp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_ss_in_desc,
+ (struct usb_descriptor_header *) &mtp_ss_in_comp_desc,
+ (struct usb_descriptor_header *) &mtp_ss_out_desc,
+ (struct usb_descriptor_header *) &mtp_ss_out_comp_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *fs_ptp_descs[] = {
+ (struct usb_descriptor_header *) &ptp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_ptp_descs[] = {
+ (struct usb_descriptor_header *) &ptp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *ss_ptp_descs[] = {
+ (struct usb_descriptor_header *) &ptp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_ss_in_desc,
+ (struct usb_descriptor_header *) &mtp_ss_in_comp_desc,
+ (struct usb_descriptor_header *) &mtp_ss_out_desc,
+ (struct usb_descriptor_header *) &mtp_ss_out_comp_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc,
+ NULL,
+};
+
+static struct usb_string mtp_string_defs[] = {
+ /* Naming interface "MTP" so libmtp will recognize us */
+ [INTERFACE_STRING_INDEX].s = "MTP",
+ { }, /* end of list */
+};
+
+static struct usb_gadget_strings mtp_string_table = {
+ .language = 0x0409, /* en-US */
+ .strings = mtp_string_defs,
+};
+
+static struct usb_gadget_strings *mtp_strings[] = {
+ &mtp_string_table,
+ NULL,
+};
+
+/* Microsoft MTP OS String */
+static u8 mtp_os_string[] = {
+ 18, /* sizeof(mtp_os_string) */
+ USB_DT_STRING,
+ /* Signature field: "MSFT100" */
+ 'M', 0, 'S', 0, 'F', 0, 'T', 0, '1', 0, '0', 0, '0', 0,
+ /* vendor code */
+ 1,
+ /* padding */
+ 0
+};
+
+/* Microsoft Extended Configuration Descriptor Header Section */
+struct mtp_ext_config_desc_header {
+ __le32 dwLength;
+ __u16 bcdVersion;
+ __le16 wIndex;
+ __u8 bCount;
+ __u8 reserved[7];
+};
+
+/* Microsoft Extended Configuration Descriptor Function Section */
+struct mtp_ext_config_desc_function {
+ __u8 bFirstInterfaceNumber;
+ __u8 bInterfaceCount;
+ __u8 compatibleID[8];
+ __u8 subCompatibleID[8];
+ __u8 reserved[6];
+};
+
+/* MTP Extended Configuration Descriptor */
+struct {
+ struct mtp_ext_config_desc_header header;
+ struct mtp_ext_config_desc_function function;
+} mtp_ext_config_desc = {
+ .header = {
+ .dwLength = __constant_cpu_to_le32(sizeof(mtp_ext_config_desc)),
+ .bcdVersion = __constant_cpu_to_le16(0x0100),
+ .wIndex = __constant_cpu_to_le16(4),
+ .bCount = 1,
+ },
+ .function = {
+ .bFirstInterfaceNumber = 0,
+ .bInterfaceCount = 1,
+ .compatibleID = { 'M', 'T', 'P' },
+ },
+};
+
+struct mtp_device_status {
+ __le16 wLength;
+ __le16 wCode;
+};
+
+struct mtp_data_header {
+ /* length of packet, including this header */
+ __le32 length;
+ /* container type (2 for data packet) */
+ __le16 type;
+ /* MTP command code */
+ __le16 command;
+ /* MTP transaction ID */
+ __le32 transaction_id;
+};
+
+struct mtp_instance {
+ struct usb_function_instance func_inst;
+ const char *name;
+ struct mtp_dev *dev;
+ char mtp_ext_compat_id[16];
+ struct usb_os_desc mtp_os_desc;
+};
+
+/* temporary variable used between mtp_open() and mtp_gadget_bind() */
+static struct mtp_dev *_mtp_dev;
+
+static inline struct mtp_dev *func_to_mtp(struct usb_function *f)
+{
+ return container_of(f, struct mtp_dev, function);
+}
+
+static struct usb_request *mtp_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+
+ if (!req)
+ return NULL;
+
+ /* now allocate buffers for the requests */
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+
+ return req;
+}
+
+static void mtp_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+static inline int mtp_lock(atomic_t *excl)
+{
+ if (atomic_inc_return(excl) == 1) {
+ return 0;
+ } else {
+ atomic_dec(excl);
+ return -1;
+ }
+}
+
+static inline void mtp_unlock(atomic_t *excl)
+{
+ atomic_dec(excl);
+}
+
+/* add a request to the tail of a list */
+static void mtp_req_put(struct mtp_dev *dev, struct list_head *head,
+ struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_add_tail(&req->list, head);
+ spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request
+*mtp_req_get(struct mtp_dev *dev, struct list_head *head)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (list_empty(head)) {
+ req = 0;
+ } else {
+ req = list_first_entry(head, struct usb_request, list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return req;
+}
+
+static void mtp_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ wake_up(&dev->write_wq);
+}
+
+static void mtp_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ dev->rx_done = 1;
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ wake_up(&dev->read_wq);
+}
+
+static void mtp_complete_intr(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ mtp_req_put(dev, &dev->intr_idle, req);
+
+ wake_up(&dev->intr_wq);
+}
+
+static int mtp_create_bulk_endpoints(struct mtp_dev *dev,
+ struct usb_endpoint_descriptor *in_desc,
+ struct usb_endpoint_descriptor *out_desc,
+ struct usb_endpoint_descriptor *intr_desc)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ struct usb_ep *ep;
+ int i;
+
+ DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+ ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_in = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for mtp ep_out got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_out = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, intr_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_intr failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for mtp ep_intr got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_intr = ep;
+
+ /* now allocate requests for our endpoints */
+ for (i = 0; i < TX_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_in, MTP_BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_in;
+ mtp_req_put(dev, &dev->tx_idle, req);
+ }
+ for (i = 0; i < RX_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_out, MTP_BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_out;
+ dev->rx_req[i] = req;
+ }
+ for (i = 0; i < INTR_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_intr, INTR_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_intr;
+ mtp_req_put(dev, &dev->intr_idle, req);
+ }
+
+ return 0;
+
+fail:
+ pr_err("mtp_bind() could not allocate requests\n");
+ return -1;
+}
+
+static ssize_t mtp_read(struct file *fp, char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ ssize_t r = count;
+ unsigned xfer;
+ int ret = 0;
+ size_t len = 0;
+
+ DBG(cdev, "mtp_read(%zu)\n", count);
+
+ /* we will block until we're online */
+ DBG(cdev, "mtp_read: waiting for online state\n");
+ ret = wait_event_interruptible(dev->read_wq,
+ dev->state != STATE_OFFLINE);
+ if (ret < 0) {
+ r = ret;
+ goto done;
+ }
+ spin_lock_irq(&dev->lock);
+ if (dev->ep_out->desc) {
+ len = usb_ep_align_maybe(cdev->gadget, dev->ep_out, count);
+ if (len > MTP_BULK_BUFFER_SIZE) {
+ spin_unlock_irq(&dev->lock);
+ return -EINVAL;
+ }
+ }
+
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ return -ECANCELED;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+requeue_req:
+ /* queue a request */
+ req = dev->rx_req[0];
+ req->length = len;
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ goto done;
+ } else {
+ DBG(cdev, "rx %p queue\n", req);
+ }
+
+ /* wait for a request to complete */
+ ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+ if (ret < 0) {
+ r = ret;
+ usb_ep_dequeue(dev->ep_out, req);
+ goto done;
+ }
+ if (dev->state == STATE_BUSY) {
+ /* If we got a 0-len packet, throw it back and try again. */
+ if (req->actual == 0)
+ goto requeue_req;
+
+ DBG(cdev, "rx %p %d\n", req, req->actual);
+ xfer = (req->actual < count) ? req->actual : count;
+ r = xfer;
+ if (copy_to_user(buf, req->buf, xfer))
+ r = -EFAULT;
+ } else
+ r = -EIO;
+
+done:
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ r = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+
+ DBG(cdev, "mtp_read returning %zd\n", r);
+ return r;
+}
+
+static ssize_t mtp_write(struct file *fp, const char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req = 0;
+ ssize_t r = count;
+ unsigned xfer;
+ int sendZLP = 0;
+ int ret;
+
+ DBG(cdev, "mtp_write(%zu)\n", count);
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ return -ECANCELED;
+ }
+ if (dev->state == STATE_OFFLINE) {
+ spin_unlock_irq(&dev->lock);
+ return -ENODEV;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+ /* we need to send a zero length packet to signal the end of transfer
+ * if the transfer size is aligned to a packet boundary.
+ */
+ if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+ sendZLP = 1;
+
+ while (count > 0 || sendZLP) {
+ /* so we exit after sending ZLP */
+ if (count == 0)
+ sendZLP = 0;
+
+ if (dev->state != STATE_BUSY) {
+ DBG(cdev, "mtp_write dev->error\n");
+ r = -EIO;
+ break;
+ }
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ ((req = mtp_req_get(dev, &dev->tx_idle))
+ || dev->state != STATE_BUSY));
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > MTP_BULK_BUFFER_SIZE)
+ xfer = MTP_BULK_BUFFER_SIZE;
+ else
+ xfer = count;
+ if (xfer && copy_from_user(req->buf, buf, xfer)) {
+ r = -EFAULT;
+ break;
+ }
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ DBG(cdev, "mtp_write: xfer error %d\n", ret);
+ r = -EIO;
+ break;
+ }
+
+ buf += xfer;
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ r = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+
+ DBG(cdev, "mtp_write returning %zd\n", r);
+ return r;
+}
+
+/* read from a local file and write to USB */
+static void send_file_work(struct work_struct *data)
+{
+ struct mtp_dev *dev = container_of(data, struct mtp_dev,
+ send_file_work);
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req = 0;
+ struct mtp_data_header *header;
+ struct file *filp;
+ loff_t offset;
+ int64_t count;
+ int xfer, ret, hdr_size;
+ int r = 0;
+ int sendZLP = 0;
+
+ /* read our parameters */
+ smp_rmb();
+ filp = dev->xfer_file;
+ offset = dev->xfer_file_offset;
+ count = dev->xfer_file_length;
+
+ if (count < 0) {
+ dev->xfer_result = -EINVAL;
+ return;
+ }
+
+ DBG(cdev, "send_file_work(%lld %lld)\n", offset, count);
+
+ if (dev->xfer_send_header) {
+ hdr_size = sizeof(struct mtp_data_header);
+ count += hdr_size;
+ } else {
+ hdr_size = 0;
+ }
+
+ /* we need to send a zero length packet to signal the end of transfer
+ * if the transfer size is aligned to a packet boundary.
+ */
+ if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+ sendZLP = 1;
+
+ while (count > 0 || sendZLP) {
+ /* so we exit after sending ZLP */
+ if (count == 0)
+ sendZLP = 0;
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ (req = mtp_req_get(dev, &dev->tx_idle))
+ || dev->state != STATE_BUSY);
+ if (dev->state == STATE_CANCELED) {
+ r = -ECANCELED;
+ break;
+ }
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > MTP_BULK_BUFFER_SIZE)
+ xfer = MTP_BULK_BUFFER_SIZE;
+ else
+ xfer = count;
+
+ if (hdr_size) {
+ /* prepend MTP data header */
+ header = (struct mtp_data_header *)req->buf;
+ /*
+ * set file size with header according to
+ * MTP Specification v1.0
+ */
+ header->length = (count > MTP_MAX_FILE_SIZE) ?
+ MTP_MAX_FILE_SIZE : __cpu_to_le32(count);
+ header->type = __cpu_to_le16(2); /* data packet */
+ header->command = __cpu_to_le16(dev->xfer_command);
+ header->transaction_id =
+ __cpu_to_le32(dev->xfer_transaction_id);
+ }
+
+ ret = vfs_read(filp, req->buf + hdr_size, xfer - hdr_size,
+ &offset);
+ if (ret < 0) {
+ r = ret;
+ break;
+ }
+ xfer = ret + hdr_size;
+ hdr_size = 0;
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ DBG(cdev, "send_file_work: xfer error %d\n", ret);
+ dev->state = STATE_ERROR;
+ r = -EIO;
+ break;
+ }
+
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ DBG(cdev, "send_file_work returning %d\n", r);
+ /* write the result */
+ dev->xfer_result = r;
+ smp_wmb();
+}
+
+/* read from USB and write to a local file */
+static void receive_file_work(struct work_struct *data)
+{
+ struct mtp_dev *dev = container_of(data, struct mtp_dev,
+ receive_file_work);
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *read_req = NULL, *write_req = NULL;
+ struct file *filp;
+ loff_t offset;
+ int64_t count, len;
+ int ret, cur_buf = 0;
+ int r = 0;
+
+ /* read our parameters */
+ smp_rmb();
+ filp = dev->xfer_file;
+ offset = dev->xfer_file_offset;
+ count = dev->xfer_file_length;
+
+ if (count < 0) {
+ dev->xfer_result = -EINVAL;
+ return;
+ }
+
+ DBG(cdev, "receive_file_work(%lld)\n", count);
+
+ while (count > 0 || write_req) {
+ if (count > 0) {
+ /* queue a request */
+ read_req = dev->rx_req[cur_buf];
+ cur_buf = (cur_buf + 1) % RX_REQ_MAX;
+
+ len = usb_ep_align_maybe(cdev->gadget, dev->ep_out, count);
+ if (len > MTP_BULK_BUFFER_SIZE)
+ len = MTP_BULK_BUFFER_SIZE;
+ read_req->length = len;
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, read_req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ dev->state = STATE_ERROR;
+ break;
+ }
+ }
+
+ if (write_req) {
+ DBG(cdev, "rx %p %d\n", write_req, write_req->actual);
+ ret = vfs_write(filp, write_req->buf, write_req->actual,
+ &offset);
+ DBG(cdev, "vfs_write %d\n", ret);
+ if (ret != write_req->actual) {
+ r = -EIO;
+ dev->state = STATE_ERROR;
+ break;
+ }
+ write_req = NULL;
+ }
+
+ if (read_req) {
+ /* wait for our last read to complete */
+ ret = wait_event_interruptible(dev->read_wq,
+ dev->rx_done || dev->state != STATE_BUSY);
+ if (dev->state == STATE_CANCELED) {
+ r = -ECANCELED;
+ if (!dev->rx_done)
+ usb_ep_dequeue(dev->ep_out, read_req);
+ break;
+ }
+ if (read_req->status) {
+ r = read_req->status;
+ break;
+ }
+ /* if xfer_file_length is 0xFFFFFFFF, then we read until
+ * we get a zero length packet
+ */
+ if (count != 0xFFFFFFFF)
+ count -= read_req->actual;
+ if (read_req->actual < read_req->length) {
+ /*
+ * short packet is used to signal EOF for
+ * sizes > 4 gig
+ */
+ DBG(cdev, "got short packet\n");
+ count = 0;
+ }
+
+ write_req = read_req;
+ read_req = NULL;
+ }
+ }
+
+ DBG(cdev, "receive_file_work returning %d\n", r);
+ /* write the result */
+ dev->xfer_result = r;
+ smp_wmb();
+}
+
+static int mtp_send_event(struct mtp_dev *dev, struct mtp_event *event)
+{
+ struct usb_request *req = NULL;
+ int ret;
+ int length = event->length;
+
+ DBG(dev->cdev, "mtp_send_event(%zu)\n", event->length);
+
+ if (length < 0 || length > INTR_BUFFER_SIZE)
+ return -EINVAL;
+ if (dev->state == STATE_OFFLINE)
+ return -ENODEV;
+
+ ret = wait_event_interruptible_timeout(dev->intr_wq,
+ (req = mtp_req_get(dev, &dev->intr_idle)),
+ msecs_to_jiffies(1000));
+ if (!req)
+ return -ETIME;
+
+ if (copy_from_user(req->buf, (void __user *)event->data, length)) {
+ mtp_req_put(dev, &dev->intr_idle, req);
+ return -EFAULT;
+ }
+ req->length = length;
+ ret = usb_ep_queue(dev->ep_intr, req, GFP_KERNEL);
+ if (ret)
+ mtp_req_put(dev, &dev->intr_idle, req);
+
+ return ret;
+}
+
+static long mtp_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct file *filp = NULL;
+ int ret = -EINVAL;
+
+ if (mtp_lock(&dev->ioctl_excl))
+ return -EBUSY;
+
+ switch (code) {
+ case MTP_SEND_FILE:
+ case MTP_RECEIVE_FILE:
+ case MTP_SEND_FILE_WITH_HEADER:
+ {
+ struct mtp_file_range mfr;
+ struct work_struct *work;
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ ret = -ECANCELED;
+ goto out;
+ }
+ if (dev->state == STATE_OFFLINE) {
+ spin_unlock_irq(&dev->lock);
+ ret = -ENODEV;
+ goto out;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+ if (copy_from_user(&mfr, (void __user *)value, sizeof(mfr))) {
+ ret = -EFAULT;
+ goto fail;
+ }
+ /* hold a reference to the file while we are working with it */
+ filp = fget(mfr.fd);
+ if (!filp) {
+ ret = -EBADF;
+ goto fail;
+ }
+
+ /* write the parameters */
+ dev->xfer_file = filp;
+ dev->xfer_file_offset = mfr.offset;
+ dev->xfer_file_length = mfr.length;
+ smp_wmb();
+
+ if (code == MTP_SEND_FILE_WITH_HEADER) {
+ work = &dev->send_file_work;
+ dev->xfer_send_header = 1;
+ dev->xfer_command = mfr.command;
+ dev->xfer_transaction_id = mfr.transaction_id;
+ } else if (code == MTP_SEND_FILE) {
+ work = &dev->send_file_work;
+ dev->xfer_send_header = 0;
+ } else {
+ work = &dev->receive_file_work;
+ }
+
+ /* We do the file transfer on a work queue so it will run
+ * in kernel context, which is necessary for vfs_read and
+ * vfs_write to use our buffers in the kernel address space.
+ */
+ queue_work(dev->wq, work);
+ /* wait for operation to complete */
+ flush_workqueue(dev->wq);
+ fput(filp);
+
+ /* read the result */
+ smp_rmb();
+ ret = dev->xfer_result;
+ break;
+ }
+ case MTP_SEND_EVENT:
+ {
+ struct mtp_event event;
+ /* return here so we don't change dev->state below,
+ * which would interfere with bulk transfer state.
+ */
+ if (copy_from_user(&event, (void __user *)value, sizeof(event)))
+ ret = -EFAULT;
+ else
+ ret = mtp_send_event(dev, &event);
+ goto out;
+ }
+ }
+
+fail:
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ ret = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+out:
+ mtp_unlock(&dev->ioctl_excl);
+ DBG(dev->cdev, "ioctl returning %d\n", ret);
+ return ret;
+}
+
+static int mtp_open(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "mtp_open\n");
+ if (mtp_lock(&_mtp_dev->open_excl))
+ return -EBUSY;
+
+ /* clear any error condition */
+ if (_mtp_dev->state != STATE_OFFLINE)
+ _mtp_dev->state = STATE_READY;
+
+ fp->private_data = _mtp_dev;
+ return 0;
+}
+
+static int mtp_release(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "mtp_release\n");
+
+ mtp_unlock(&_mtp_dev->open_excl);
+ return 0;
+}
+
+/* file operations for /dev/mtp_usb */
+static const struct file_operations mtp_fops = {
+ .owner = THIS_MODULE,
+ .read = mtp_read,
+ .write = mtp_write,
+ .unlocked_ioctl = mtp_ioctl,
+ .open = mtp_open,
+ .release = mtp_release,
+};
+
+static struct miscdevice mtp_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = mtp_shortname,
+ .fops = &mtp_fops,
+};
+
+static int mtp_ctrlrequest(struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct mtp_dev *dev = _mtp_dev;
+ int value = -EOPNOTSUPP;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+ unsigned long flags;
+
+ VDBG(cdev, "mtp_ctrlrequest "
+ "%02x.%02x v%04x i%04x l%u\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+
+ /* Handle MTP OS string */
+ if (ctrl->bRequestType ==
+ (USB_DIR_IN | USB_TYPE_STANDARD | USB_RECIP_DEVICE)
+ && ctrl->bRequest == USB_REQ_GET_DESCRIPTOR
+ && (w_value >> 8) == USB_DT_STRING
+ && (w_value & 0xFF) == MTP_OS_STRING_ID) {
+ value = (w_length < sizeof(mtp_os_string)
+ ? w_length : sizeof(mtp_os_string));
+ memcpy(cdev->req->buf, mtp_os_string, value);
+ } else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_VENDOR) {
+ /* Handle MTP OS descriptor */
+ DBG(cdev, "vendor request: %d index: %d value: %d length: %d\n",
+ ctrl->bRequest, w_index, w_value, w_length);
+
+ if (ctrl->bRequest == 1
+ && (ctrl->bRequestType & USB_DIR_IN)
+ && (w_index == 4 || w_index == 5)) {
+ value = (w_length < sizeof(mtp_ext_config_desc) ?
+ w_length : sizeof(mtp_ext_config_desc));
+ memcpy(cdev->req->buf, &mtp_ext_config_desc, value);
+ }
+ } else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+ DBG(cdev, "class request: %d index: %d value: %d length: %d\n",
+ ctrl->bRequest, w_index, w_value, w_length);
+
+ if (ctrl->bRequest == MTP_REQ_CANCEL && w_index == 0
+ && w_value == 0) {
+ DBG(cdev, "MTP_REQ_CANCEL\n");
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (dev->state == STATE_BUSY) {
+ dev->state = STATE_CANCELED;
+ wake_up(&dev->read_wq);
+ wake_up(&dev->write_wq);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* We need to queue a request to read the remaining
+ * bytes, but we don't actually need to look at
+ * the contents.
+ */
+ value = w_length;
+ } else if (ctrl->bRequest == MTP_REQ_GET_DEVICE_STATUS
+ && w_index == 0 && w_value == 0) {
+ struct mtp_device_status *status = cdev->req->buf;
+
+ status->wLength =
+ __constant_cpu_to_le16(sizeof(*status));
+
+ DBG(cdev, "MTP_REQ_GET_DEVICE_STATUS\n");
+ spin_lock_irqsave(&dev->lock, flags);
+ /* device status is "busy" until we report
+ * the cancelation to userspace
+ */
+ if (dev->state == STATE_CANCELED)
+ status->wCode =
+ __cpu_to_le16(MTP_RESPONSE_DEVICE_BUSY);
+ else
+ status->wCode =
+ __cpu_to_le16(MTP_RESPONSE_OK);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ value = sizeof(*status);
+ }
+ }
+
+ /* respond with data transfer or status phase? */
+ if (value >= 0) {
+ int rc;
+
+ cdev->req->zero = value < w_length;
+ cdev->req->length = value;
+ rc = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+ if (rc < 0)
+ ERROR(cdev, "%s: response queue error\n", __func__);
+ }
+ return value;
+}
+
+static int
+mtp_function_bind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct mtp_dev *dev = func_to_mtp(f);
+ int id;
+ int ret;
+ struct mtp_instance *fi_mtp;
+
+ dev->cdev = cdev;
+ DBG(cdev, "mtp_function_bind dev: %p\n", dev);
+
+ /* allocate interface ID(s) */
+ id = usb_interface_id(c, f);
+ if (id < 0)
+ return id;
+ mtp_interface_desc.bInterfaceNumber = id;
+
+ if (mtp_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+ ret = usb_string_id(c->cdev);
+ if (ret < 0)
+ return ret;
+ mtp_string_defs[INTERFACE_STRING_INDEX].id = ret;
+ mtp_interface_desc.iInterface = ret;
+ }
+
+ fi_mtp = container_of(f->fi, struct mtp_instance, func_inst);
+
+ if (cdev->use_os_string) {
+ f->os_desc_table = kzalloc(sizeof(*f->os_desc_table),
+ GFP_KERNEL);
+ if (!f->os_desc_table)
+ return -ENOMEM;
+ f->os_desc_n = 1;
+ f->os_desc_table[0].os_desc = &fi_mtp->mtp_os_desc;
+ }
+
+ /* allocate endpoints */
+ ret = mtp_create_bulk_endpoints(dev, &mtp_fullspeed_in_desc,
+ &mtp_fullspeed_out_desc, &mtp_intr_desc);
+ if (ret)
+ return ret;
+
+ /* support high speed hardware */
+ if (gadget_is_dualspeed(c->cdev->gadget)) {
+ mtp_highspeed_in_desc.bEndpointAddress =
+ mtp_fullspeed_in_desc.bEndpointAddress;
+ mtp_highspeed_out_desc.bEndpointAddress =
+ mtp_fullspeed_out_desc.bEndpointAddress;
+ }
+ /* support super speed hardware */
+ if (gadget_is_superspeed(c->cdev->gadget)) {
+ unsigned max_burst;
+
+ /* Calculate bMaxBurst, we know packet size is 1024 */
+ max_burst = min_t(unsigned, MTP_BULK_BUFFER_SIZE / 1024, 15);
+ mtp_ss_in_desc.bEndpointAddress =
+ mtp_fullspeed_in_desc.bEndpointAddress;
+ mtp_ss_in_comp_desc.bMaxBurst = max_burst;
+ mtp_ss_out_desc.bEndpointAddress =
+ mtp_fullspeed_out_desc.bEndpointAddress;
+ mtp_ss_out_comp_desc.bMaxBurst = max_burst;
+ }
+
+ DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+ gadget_is_superspeed(c->cdev->gadget) ? "super" :
+ (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full"),
+ f->name, dev->ep_in->name, dev->ep_out->name);
+ return 0;
+}
+
+static void
+mtp_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_request *req;
+ int i;
+
+ mtp_string_defs[INTERFACE_STRING_INDEX].id = 0;
+ while ((req = mtp_req_get(dev, &dev->tx_idle)))
+ mtp_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ mtp_request_free(dev->rx_req[i], dev->ep_out);
+ while ((req = mtp_req_get(dev, &dev->intr_idle)))
+ mtp_request_free(req, dev->ep_intr);
+ dev->state = STATE_OFFLINE;
+ kfree(f->os_desc_table);
+ f->os_desc_n = 0;
+}
+
+static int mtp_function_set_alt(struct usb_function *f,
+ unsigned intf, unsigned alt)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ DBG(cdev, "mtp_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_out);
+ if (ret) {
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_intr);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_intr);
+ if (ret) {
+ usb_ep_disable(dev->ep_out);
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+ dev->state = STATE_READY;
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+ return 0;
+}
+
+static void mtp_function_disable(struct usb_function *f)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ DBG(cdev, "mtp_function_disable\n");
+ dev->state = STATE_OFFLINE;
+ usb_ep_disable(dev->ep_in);
+ usb_ep_disable(dev->ep_out);
+ usb_ep_disable(dev->ep_intr);
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+
+ VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int __mtp_setup(struct mtp_instance *fi_mtp)
+{
+ struct mtp_dev *dev;
+ int ret;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
+ if (fi_mtp != NULL)
+ fi_mtp->dev = dev;
+
+ if (!dev)
+ return -ENOMEM;
+
+ spin_lock_init(&dev->lock);
+ init_waitqueue_head(&dev->read_wq);
+ init_waitqueue_head(&dev->write_wq);
+ init_waitqueue_head(&dev->intr_wq);
+ atomic_set(&dev->open_excl, 0);
+ atomic_set(&dev->ioctl_excl, 0);
+ INIT_LIST_HEAD(&dev->tx_idle);
+ INIT_LIST_HEAD(&dev->intr_idle);
+
+ dev->wq = create_singlethread_workqueue("f_mtp");
+ if (!dev->wq) {
+ ret = -ENOMEM;
+ goto err1;
+ }
+ INIT_WORK(&dev->send_file_work, send_file_work);
+ INIT_WORK(&dev->receive_file_work, receive_file_work);
+
+ _mtp_dev = dev;
+
+ ret = misc_register(&mtp_device);
+ if (ret)
+ goto err2;
+
+ return 0;
+
+err2:
+ destroy_workqueue(dev->wq);
+err1:
+ _mtp_dev = NULL;
+ kfree(dev);
+ printk(KERN_ERR "mtp gadget driver failed to initialize\n");
+ return ret;
+}
+
+static int mtp_setup_configfs(struct mtp_instance *fi_mtp)
+{
+ return __mtp_setup(fi_mtp);
+}
+
+
+static void mtp_cleanup(void)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (!dev)
+ return;
+
+ misc_deregister(&mtp_device);
+ destroy_workqueue(dev->wq);
+ _mtp_dev = NULL;
+ kfree(dev);
+}
+
+static struct mtp_instance *to_mtp_instance(struct config_item *item)
+{
+ return container_of(to_config_group(item), struct mtp_instance,
+ func_inst.group);
+}
+
+static void mtp_attr_release(struct config_item *item)
+{
+ struct mtp_instance *fi_mtp = to_mtp_instance(item);
+
+ usb_put_function_instance(&fi_mtp->func_inst);
+}
+
+static struct configfs_item_operations mtp_item_ops = {
+ .release = mtp_attr_release,
+};
+
+static struct config_item_type mtp_func_type = {
+ .ct_item_ops = &mtp_item_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+
+static struct mtp_instance *to_fi_mtp(struct usb_function_instance *fi)
+{
+ return container_of(fi, struct mtp_instance, func_inst);
+}
+
+static int mtp_set_inst_name(struct usb_function_instance *fi, const char *name)
+{
+ struct mtp_instance *fi_mtp;
+ char *ptr;
+ int name_len;
+
+ name_len = strlen(name) + 1;
+ if (name_len > MAX_INST_NAME_LEN)
+ return -ENAMETOOLONG;
+
+ ptr = kstrndup(name, name_len, GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
+
+ fi_mtp = to_fi_mtp(fi);
+ fi_mtp->name = ptr;
+
+ return 0;
+}
+
+static void mtp_free_inst(struct usb_function_instance *fi)
+{
+ struct mtp_instance *fi_mtp;
+
+ fi_mtp = to_fi_mtp(fi);
+ kfree(fi_mtp->name);
+ mtp_cleanup();
+ kfree(fi_mtp);
+}
+
+struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config)
+{
+ struct mtp_instance *fi_mtp;
+ int ret = 0;
+ struct usb_os_desc *descs[1];
+ char *names[1];
+
+ fi_mtp = kzalloc(sizeof(*fi_mtp), GFP_KERNEL);
+ if (!fi_mtp)
+ return ERR_PTR(-ENOMEM);
+ fi_mtp->func_inst.set_inst_name = mtp_set_inst_name;
+ fi_mtp->func_inst.free_func_inst = mtp_free_inst;
+
+ fi_mtp->mtp_os_desc.ext_compat_id = fi_mtp->mtp_ext_compat_id;
+ INIT_LIST_HEAD(&fi_mtp->mtp_os_desc.ext_prop);
+ descs[0] = &fi_mtp->mtp_os_desc;
+ names[0] = "MTP";
+
+ if (mtp_config) {
+ ret = mtp_setup_configfs(fi_mtp);
+ if (ret) {
+ kfree(fi_mtp);
+ pr_err("Error setting MTP\n");
+ return ERR_PTR(ret);
+ }
+ } else
+ fi_mtp->dev = _mtp_dev;
+
+ config_group_init_type_name(&fi_mtp->func_inst.group,
+ "", &mtp_func_type);
+ usb_os_desc_prepare_interf_dir(&fi_mtp->func_inst.group, 1,
+ descs, names, THIS_MODULE);
+
+ return &fi_mtp->func_inst;
+}
+EXPORT_SYMBOL_GPL(alloc_inst_mtp_ptp);
+
+static struct usb_function_instance *mtp_alloc_inst(void)
+{
+ return alloc_inst_mtp_ptp(true);
+}
+
+static int mtp_ctrlreq_configfs(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl)
+{
+ return mtp_ctrlrequest(f->config->cdev, ctrl);
+}
+
+static void mtp_free(struct usb_function *f)
+{
+ /*NO-OP: no function specific resource allocation in mtp_alloc*/
+}
+
+struct usb_function *function_alloc_mtp_ptp(struct usb_function_instance *fi,
+ bool mtp_config)
+{
+ struct mtp_instance *fi_mtp = to_fi_mtp(fi);
+ struct mtp_dev *dev;
+
+ /*
+ * PTP piggybacks on MTP function so make sure we have
+ * created MTP function before we associate this PTP
+ * function with a gadget configuration.
+ */
+ if (fi_mtp->dev == NULL) {
+ pr_err("Error: Create MTP function before linking"
+ " PTP function with a gadget configuration\n");
+ pr_err("\t1: Delete existing PTP function if any\n");
+ pr_err("\t2: Create MTP function\n");
+ pr_err("\t3: Create and symlink PTP function"
+ " with a gadget configuration\n");
+ return ERR_PTR(-EINVAL); /* Invalid Configuration */
+ }
+
+ dev = fi_mtp->dev;
+ dev->function.name = DRIVER_NAME;
+ dev->function.strings = mtp_strings;
+ if (mtp_config) {
+ dev->function.fs_descriptors = fs_mtp_descs;
+ dev->function.hs_descriptors = hs_mtp_descs;
+ dev->function.ss_descriptors = ss_mtp_descs;
+ } else {
+ dev->function.fs_descriptors = fs_ptp_descs;
+ dev->function.hs_descriptors = hs_ptp_descs;
+ dev->function.ss_descriptors = ss_ptp_descs;
+ }
+ dev->function.bind = mtp_function_bind;
+ dev->function.unbind = mtp_function_unbind;
+ dev->function.set_alt = mtp_function_set_alt;
+ dev->function.disable = mtp_function_disable;
+ dev->function.setup = mtp_ctrlreq_configfs;
+ dev->function.free_func = mtp_free;
+
+ return &dev->function;
+}
+EXPORT_SYMBOL_GPL(function_alloc_mtp_ptp);
+
+static struct usb_function *mtp_alloc(struct usb_function_instance *fi)
+{
+ return function_alloc_mtp_ptp(fi, true);
+}
+
+DECLARE_USB_FUNCTION_INIT(mtp, mtp_alloc_inst, mtp_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_mtp.h b/drivers/usb/gadget/function/f_mtp.h
new file mode 100644
index 0000000..7adb1ff
--- /dev/null
+++ b/drivers/usb/gadget/function/f_mtp.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Badhri Jagan Sridharan <badhri@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+extern struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config);
+extern struct usb_function *function_alloc_mtp_ptp(
+ struct usb_function_instance *fi, bool mtp_config);
diff --git a/drivers/usb/gadget/function/f_ptp.c b/drivers/usb/gadget/function/f_ptp.c
new file mode 100644
index 0000000..da3e4d5
--- /dev/null
+++ b/drivers/usb/gadget/function/f_ptp.c
@@ -0,0 +1,38 @@
+/*
+ * Gadget Function Driver for PTP
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Badhri Jagan Sridharan <badhri@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#include "f_mtp.h"
+
+static struct usb_function_instance *ptp_alloc_inst(void)
+{
+ return alloc_inst_mtp_ptp(false);
+}
+
+static struct usb_function *ptp_alloc(struct usb_function_instance *fi)
+{
+ return function_alloc_mtp_ptp(fi, false);
+}
+
+DECLARE_USB_FUNCTION_INIT(ptp, ptp_alloc_inst, ptp_alloc);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Badhri Jagan Sridharan");
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index de70e70..b33dc12 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -6,6 +6,14 @@
config USB_PHY
def_bool n
+config USB_OTG_WAKELOCK
+ bool "Hold a wakelock when USB connected"
+ depends on PM_WAKELOCKS
+ select USB_OTG_UTILS
+ help
+ Select this to automatically hold a wakelock when USB is
+ connected, preventing suspend.
+
#
# USB Transceiver Drivers
#
@@ -209,4 +217,13 @@
Provides read/write operations to the ULPI phy register set for
controllers with a viewport register (e.g. Chipidea/ARC controllers).
+config DUAL_ROLE_USB_INTF
+ bool "Generic DUAL ROLE sysfs interface"
+ depends on SYSFS && USB_PHY
+ help
+ A generic sysfs interface to track and change the state of
+ dual role usb phys. The usb phy drivers can register to
+ this interface to expose it capabilities to the userspace
+ and thereby allowing userspace to change the port mode.
+
endmenu
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index b433e5d..f65ac3e 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -3,6 +3,8 @@
#
obj-$(CONFIG_USB_PHY) += phy.o
obj-$(CONFIG_OF) += of.o
+obj-$(CONFIG_USB_OTG_WAKELOCK) += otg-wakelock.o
+obj-$(CONFIG_DUAL_ROLE_USB_INTF) += class-dual-role.o
# transceiver drivers, keep the list sorted
diff --git a/drivers/usb/phy/class-dual-role.c b/drivers/usb/phy/class-dual-role.c
new file mode 100644
index 0000000..51fcb54
--- /dev/null
+++ b/drivers/usb/phy/class-dual-role.c
@@ -0,0 +1,529 @@
+/*
+ * class-dual-role.c
+ *
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/usb/class-dual-role.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+
+#define DUAL_ROLE_NOTIFICATION_TIMEOUT 2000
+
+static ssize_t dual_role_store_property(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count);
+static ssize_t dual_role_show_property(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+
+#define DUAL_ROLE_ATTR(_name) \
+{ \
+ .attr = { .name = #_name }, \
+ .show = dual_role_show_property, \
+ .store = dual_role_store_property, \
+}
+
+static struct device_attribute dual_role_attrs[] = {
+ DUAL_ROLE_ATTR(supported_modes),
+ DUAL_ROLE_ATTR(mode),
+ DUAL_ROLE_ATTR(power_role),
+ DUAL_ROLE_ATTR(data_role),
+ DUAL_ROLE_ATTR(powers_vconn),
+};
+
+struct class *dual_role_class;
+EXPORT_SYMBOL_GPL(dual_role_class);
+
+static struct device_type dual_role_dev_type;
+
+static char *kstrdupcase(const char *str, gfp_t gfp, bool to_upper)
+{
+ char *ret, *ustr;
+
+ ustr = ret = kmalloc(strlen(str) + 1, gfp);
+
+ if (!ret)
+ return NULL;
+
+ while (*str)
+ *ustr++ = to_upper ? toupper(*str++) : tolower(*str++);
+
+ *ustr = 0;
+
+ return ret;
+}
+
+static void dual_role_changed_work(struct work_struct *work)
+{
+ struct dual_role_phy_instance *dual_role =
+ container_of(work, struct dual_role_phy_instance,
+ changed_work);
+
+ dev_dbg(&dual_role->dev, "%s\n", __func__);
+ kobject_uevent(&dual_role->dev.kobj, KOBJ_CHANGE);
+}
+
+void dual_role_instance_changed(struct dual_role_phy_instance *dual_role)
+{
+ dev_dbg(&dual_role->dev, "%s\n", __func__);
+ pm_wakeup_event(&dual_role->dev, DUAL_ROLE_NOTIFICATION_TIMEOUT);
+ schedule_work(&dual_role->changed_work);
+}
+EXPORT_SYMBOL_GPL(dual_role_instance_changed);
+
+int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val)
+{
+ return dual_role->desc->get_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_get_property);
+
+int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val)
+{
+ if (!dual_role->desc->set_property)
+ return -ENODEV;
+
+ return dual_role->desc->set_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_set_property);
+
+int dual_role_property_is_writeable(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop)
+{
+ if (!dual_role->desc->property_is_writeable)
+ return -ENODEV;
+
+ return dual_role->desc->property_is_writeable(dual_role, prop);
+}
+EXPORT_SYMBOL_GPL(dual_role_property_is_writeable);
+
+static void dual_role_dev_release(struct device *dev)
+{
+ struct dual_role_phy_instance *dual_role =
+ container_of(dev, struct dual_role_phy_instance, dev);
+ pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
+ kfree(dual_role);
+}
+
+static struct dual_role_phy_instance *__must_check
+__dual_role_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ struct device *dev;
+ struct dual_role_phy_instance *dual_role;
+ int rc;
+
+ dual_role = kzalloc(sizeof(*dual_role), GFP_KERNEL);
+ if (!dual_role)
+ return ERR_PTR(-ENOMEM);
+
+ dev = &dual_role->dev;
+
+ device_initialize(dev);
+
+ dev->class = dual_role_class;
+ dev->type = &dual_role_dev_type;
+ dev->parent = parent;
+ dev->release = dual_role_dev_release;
+ dev_set_drvdata(dev, dual_role);
+ dual_role->desc = desc;
+
+ rc = dev_set_name(dev, "%s", desc->name);
+ if (rc)
+ goto dev_set_name_failed;
+
+ INIT_WORK(&dual_role->changed_work, dual_role_changed_work);
+
+ rc = device_init_wakeup(dev, true);
+ if (rc)
+ goto wakeup_init_failed;
+
+ rc = device_add(dev);
+ if (rc)
+ goto device_add_failed;
+
+ dual_role_instance_changed(dual_role);
+
+ return dual_role;
+
+device_add_failed:
+ device_init_wakeup(dev, false);
+wakeup_init_failed:
+dev_set_name_failed:
+ put_device(dev);
+ kfree(dual_role);
+
+ return ERR_PTR(rc);
+}
+
+static void dual_role_instance_unregister(struct dual_role_phy_instance
+ *dual_role)
+{
+ cancel_work_sync(&dual_role->changed_work);
+ device_init_wakeup(&dual_role->dev, false);
+ device_unregister(&dual_role->dev);
+}
+
+static void devm_dual_role_release(struct device *dev, void *res)
+{
+ struct dual_role_phy_instance **dual_role = res;
+
+ dual_role_instance_unregister(*dual_role);
+}
+
+struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ struct dual_role_phy_instance **ptr, *dual_role;
+
+ ptr = devres_alloc(devm_dual_role_release, sizeof(*ptr), GFP_KERNEL);
+
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+ dual_role = __dual_role_register(parent, desc);
+ if (IS_ERR(dual_role)) {
+ devres_free(ptr);
+ } else {
+ *ptr = dual_role;
+ devres_add(parent, ptr);
+ }
+ return dual_role;
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_register);
+
+static int devm_dual_role_match(struct device *dev, void *res, void *data)
+{
+ struct dual_role_phy_instance **r = res;
+
+ if (WARN_ON(!r || !*r))
+ return 0;
+
+ return *r == data;
+}
+
+void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role)
+{
+ int rc;
+
+ rc = devres_release(dev, devm_dual_role_release,
+ devm_dual_role_match, dual_role);
+ WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_unregister);
+
+void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role)
+{
+ return dual_role->drv_data;
+}
+EXPORT_SYMBOL_GPL(dual_role_get_drvdata);
+
+/***************** Device attribute functions **************************/
+
+/* port type */
+static char *supported_modes_text[] = {
+ "ufp dfp", "dfp", "ufp"
+};
+
+/* current mode */
+static char *mode_text[] = {
+ "ufp", "dfp", "none"
+};
+
+/* Power role */
+static char *pr_text[] = {
+ "source", "sink", "none"
+};
+
+/* Data role */
+static char *dr_text[] = {
+ "host", "device", "none"
+};
+
+/* Vconn supply */
+static char *vconn_supply_text[] = {
+ "n", "y"
+};
+
+static ssize_t dual_role_show_property(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ ssize_t ret = 0;
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ const ptrdiff_t off = attr - dual_role_attrs;
+ unsigned int value;
+
+ if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+ value = dual_role->desc->supported_modes;
+ } else {
+ ret = dual_role_get_property(dual_role, off, &value);
+
+ if (ret < 0) {
+ if (ret == -ENODATA)
+ dev_dbg(dev,
+ "driver has no data for `%s' property\n",
+ attr->attr.name);
+ else if (ret != -ENODEV)
+ dev_err(dev,
+ "driver failed to report `%s' property: %zd\n",
+ attr->attr.name, ret);
+ return ret;
+ }
+ }
+
+ if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL !=
+ ARRAY_SIZE(supported_modes_text));
+ if (value < DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ supported_modes_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_MODE) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_MODE_TOTAL !=
+ ARRAY_SIZE(mode_text));
+ if (value < DUAL_ROLE_PROP_MODE_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ mode_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_PR) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_PR_TOTAL != ARRAY_SIZE(pr_text));
+ if (value < DUAL_ROLE_PROP_PR_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ pr_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_DR) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_DR_TOTAL != ARRAY_SIZE(dr_text));
+ if (value < DUAL_ROLE_PROP_DR_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ dr_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_VCONN_SUPPLY) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL !=
+ ARRAY_SIZE(vconn_supply_text));
+ if (value < DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ vconn_supply_text[value]);
+ else
+ return -EIO;
+ } else
+ return -EIO;
+}
+
+static ssize_t dual_role_store_property(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ ssize_t ret;
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ const ptrdiff_t off = attr - dual_role_attrs;
+ unsigned int value;
+ int total, i;
+ char *dup_buf, **text_array;
+ bool result = false;
+
+ dup_buf = kstrdupcase(buf, GFP_KERNEL, false);
+ switch (off) {
+ case DUAL_ROLE_PROP_MODE:
+ total = DUAL_ROLE_PROP_MODE_TOTAL;
+ text_array = mode_text;
+ break;
+ case DUAL_ROLE_PROP_PR:
+ total = DUAL_ROLE_PROP_PR_TOTAL;
+ text_array = pr_text;
+ break;
+ case DUAL_ROLE_PROP_DR:
+ total = DUAL_ROLE_PROP_DR_TOTAL;
+ text_array = dr_text;
+ break;
+ case DUAL_ROLE_PROP_VCONN_SUPPLY:
+ ret = strtobool(dup_buf, &result);
+ value = result;
+ if (!ret)
+ goto setprop;
+ default:
+ ret = -EINVAL;
+ goto error;
+ }
+
+ for (i = 0; i <= total; i++) {
+ if (i == total) {
+ ret = -ENOTSUPP;
+ goto error;
+ }
+ if (!strncmp(*(text_array + i), dup_buf,
+ strlen(*(text_array + i)))) {
+ value = i;
+ break;
+ }
+ }
+
+setprop:
+ ret = dual_role->desc->set_property(dual_role, off, &value);
+
+error:
+ kfree(dup_buf);
+
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static umode_t dual_role_attr_is_visible(struct kobject *kobj,
+ struct attribute *attr, int attrno)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+ int i;
+
+ if (attrno == DUAL_ROLE_PROP_SUPPORTED_MODES)
+ return mode;
+
+ for (i = 0; i < dual_role->desc->num_properties; i++) {
+ int property = dual_role->desc->properties[i];
+
+ if (property == attrno) {
+ if (dual_role->desc->property_is_writeable &&
+ dual_role_property_is_writeable(dual_role, property)
+ > 0)
+ mode |= S_IWUSR;
+
+ return mode;
+ }
+ }
+
+ return 0;
+}
+
+static struct attribute *__dual_role_attrs[ARRAY_SIZE(dual_role_attrs) + 1];
+
+static struct attribute_group dual_role_attr_group = {
+ .attrs = __dual_role_attrs,
+ .is_visible = dual_role_attr_is_visible,
+};
+
+static const struct attribute_group *dual_role_attr_groups[] = {
+ &dual_role_attr_group,
+ NULL,
+};
+
+void dual_role_init_attrs(struct device_type *dev_type)
+{
+ int i;
+
+ dev_type->groups = dual_role_attr_groups;
+
+ for (i = 0; i < ARRAY_SIZE(dual_role_attrs); i++)
+ __dual_role_attrs[i] = &dual_role_attrs[i].attr;
+}
+
+int dual_role_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ int ret = 0, j;
+ char *prop_buf;
+ char *attrname;
+
+ dev_dbg(dev, "uevent\n");
+
+ if (!dual_role || !dual_role->desc) {
+ dev_dbg(dev, "No dual_role phy yet\n");
+ return ret;
+ }
+
+ dev_dbg(dev, "DUAL_ROLE_NAME=%s\n", dual_role->desc->name);
+
+ ret = add_uevent_var(env, "DUAL_ROLE_NAME=%s", dual_role->desc->name);
+ if (ret)
+ return ret;
+
+ prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
+ if (!prop_buf)
+ return -ENOMEM;
+
+ for (j = 0; j < dual_role->desc->num_properties; j++) {
+ struct device_attribute *attr;
+ char *line;
+
+ attr = &dual_role_attrs[dual_role->desc->properties[j]];
+
+ ret = dual_role_show_property(dev, attr, prop_buf);
+ if (ret == -ENODEV || ret == -ENODATA) {
+ ret = 0;
+ continue;
+ }
+
+ if (ret < 0)
+ goto out;
+ line = strnchr(prop_buf, PAGE_SIZE, '\n');
+ if (line)
+ *line = 0;
+
+ attrname = kstrdupcase(attr->attr.name, GFP_KERNEL, true);
+ if (!attrname)
+ ret = -ENOMEM;
+
+ dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
+
+ ret = add_uevent_var(env, "DUAL_ROLE_%s=%s", attrname,
+ prop_buf);
+ kfree(attrname);
+ if (ret)
+ goto out;
+ }
+
+out:
+ free_page((unsigned long)prop_buf);
+
+ return ret;
+}
+
+/******************* Module Init ***********************************/
+
+static int __init dual_role_class_init(void)
+{
+ dual_role_class = class_create(THIS_MODULE, "dual_role_usb");
+
+ if (IS_ERR(dual_role_class))
+ return PTR_ERR(dual_role_class);
+
+ dual_role_class->dev_uevent = dual_role_uevent;
+ dual_role_init_attrs(&dual_role_dev_type);
+
+ return 0;
+}
+
+static void __exit dual_role_class_exit(void)
+{
+ class_destroy(dual_role_class);
+}
+
+subsys_initcall(dual_role_class_init);
+module_exit(dual_role_class_exit);
diff --git a/drivers/usb/phy/otg-wakelock.c b/drivers/usb/phy/otg-wakelock.c
new file mode 100644
index 0000000..ecd7410
--- /dev/null
+++ b/drivers/usb/phy/otg-wakelock.c
@@ -0,0 +1,170 @@
+/*
+ * otg-wakelock.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/spinlock.h>
+#include <linux/usb/otg.h>
+
+#define TEMPORARY_HOLD_TIME 2000
+
+static bool enabled = true;
+static struct usb_phy *otgwl_xceiv;
+static struct notifier_block otgwl_nb;
+
+/*
+ * otgwl_spinlock is held while the VBUS lock is grabbed or dropped and the
+ * held field is updated to match.
+ */
+
+static DEFINE_SPINLOCK(otgwl_spinlock);
+
+/*
+ * Only one lock, but since these 3 fields are associated with each other...
+ */
+
+struct otgwl_lock {
+ char name[40];
+ struct wakeup_source wakesrc;
+ bool held;
+};
+
+/*
+ * VBUS present lock. Also used as a timed lock on charger
+ * connect/disconnect and USB host disconnect, to allow the system
+ * to react to the change in power.
+ */
+
+static struct otgwl_lock vbus_lock;
+
+static void otgwl_hold(struct otgwl_lock *lock)
+{
+ if (!lock->held) {
+ __pm_stay_awake(&lock->wakesrc);
+ lock->held = true;
+ }
+}
+
+static void otgwl_temporary_hold(struct otgwl_lock *lock)
+{
+ __pm_wakeup_event(&lock->wakesrc, TEMPORARY_HOLD_TIME);
+ lock->held = false;
+}
+
+static void otgwl_drop(struct otgwl_lock *lock)
+{
+ if (lock->held) {
+ __pm_relax(&lock->wakesrc);
+ lock->held = false;
+ }
+}
+
+static void otgwl_handle_event(unsigned long event)
+{
+ unsigned long irqflags;
+
+ spin_lock_irqsave(&otgwl_spinlock, irqflags);
+
+ if (!enabled) {
+ otgwl_drop(&vbus_lock);
+ spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+ return;
+ }
+
+ switch (event) {
+ case USB_EVENT_VBUS:
+ case USB_EVENT_ENUMERATED:
+ otgwl_hold(&vbus_lock);
+ break;
+
+ case USB_EVENT_NONE:
+ case USB_EVENT_ID:
+ case USB_EVENT_CHARGER:
+ otgwl_temporary_hold(&vbus_lock);
+ break;
+
+ default:
+ break;
+ }
+
+ spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+}
+
+static int otgwl_otg_notifications(struct notifier_block *nb,
+ unsigned long event, void *unused)
+{
+ otgwl_handle_event(event);
+ return NOTIFY_OK;
+}
+
+static int set_enabled(const char *val, const struct kernel_param *kp)
+{
+ int rv = param_set_bool(val, kp);
+
+ if (rv)
+ return rv;
+
+ if (otgwl_xceiv)
+ otgwl_handle_event(otgwl_xceiv->last_event);
+
+ return 0;
+}
+
+static struct kernel_param_ops enabled_param_ops = {
+ .set = set_enabled,
+ .get = param_get_bool,
+};
+
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0644);
+MODULE_PARM_DESC(enabled, "enable wakelock when VBUS present");
+
+static int __init otg_wakelock_init(void)
+{
+ int ret;
+ struct usb_phy *phy;
+
+ phy = usb_get_phy(USB_PHY_TYPE_USB2);
+
+ if (IS_ERR(phy)) {
+ pr_err("%s: No USB transceiver found\n", __func__);
+ return PTR_ERR(phy);
+ }
+ otgwl_xceiv = phy;
+
+ snprintf(vbus_lock.name, sizeof(vbus_lock.name), "vbus-%s",
+ dev_name(otgwl_xceiv->dev));
+ wakeup_source_init(&vbus_lock.wakesrc, vbus_lock.name);
+
+ otgwl_nb.notifier_call = otgwl_otg_notifications;
+ ret = usb_register_notifier(otgwl_xceiv, &otgwl_nb);
+
+ if (ret) {
+ pr_err("%s: usb_register_notifier on transceiver %s"
+ " failed\n", __func__,
+ dev_name(otgwl_xceiv->dev));
+ otgwl_xceiv = NULL;
+ wakeup_source_trash(&vbus_lock.wakesrc);
+ return ret;
+ }
+
+ otgwl_handle_event(otgwl_xceiv->last_event);
+ return ret;
+}
+
+late_initcall(otg_wakelock_init);
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index da6e2ce..06cd48d 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -24,7 +24,6 @@
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU || ARM_SMMU_V3)
select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
select VFIO_SPAPR_EEH if (PPC_POWERNV || PPC_PSERIES)
- select ANON_INODES
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/vfio.txt for more details.
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index b90ef96..25d5bc3 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -41,12 +41,55 @@ static void dummycon_init(struct vc_data *vc, int init)
vc_resize(vc, DUMMY_COLUMNS, DUMMY_ROWS);
}
-static int dummycon_dummy(void)
+static void dummycon_deinit(struct vc_data *vc)
+{
+}
+
+static void dummycon_clear(struct vc_data *vc, int a, int b, int c, int d)
+{
+}
+
+static void dummycon_putc(struct vc_data *vc, int a, int b, int c)
+{
+}
+
+static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, int a, int b, int c)
+{
+}
+
+static void dummycon_cursor(struct vc_data *vc, int a)
+{
+}
+
+static int dummycon_scroll(struct vc_data *vc, int a, int b, int c, int d)
{
return 0;
}
-#define DUMMY (void *)dummycon_dummy
+static int dummycon_switch(struct vc_data *vc)
+{
+ return 0;
+}
+
+static int dummycon_blank(struct vc_data *vc, int a, int b)
+{
+ return 0;
+}
+
+static int dummycon_font_set(struct vc_data *vc, struct console_font *f, unsigned u)
+{
+ return 0;
+}
+
+static int dummycon_font_default(struct vc_data *vc, struct console_font *f, char *c)
+{
+ return 0;
+}
+
+static int dummycon_font_copy(struct vc_data *vc, int a)
+{
+ return 0;
+}
/*
* The console `switch' structure for the dummy console
@@ -58,16 +101,16 @@ const struct consw dummy_con = {
.owner = THIS_MODULE,
.con_startup = dummycon_startup,
.con_init = dummycon_init,
- .con_deinit = DUMMY,
- .con_clear = DUMMY,
- .con_putc = DUMMY,
- .con_putcs = DUMMY,
- .con_cursor = DUMMY,
- .con_scroll = DUMMY,
- .con_switch = DUMMY,
- .con_blank = DUMMY,
- .con_font_set = DUMMY,
- .con_font_default = DUMMY,
- .con_font_copy = DUMMY,
+ .con_deinit = dummycon_deinit,
+ .con_clear = dummycon_clear,
+ .con_putc = dummycon_putc,
+ .con_putcs = dummycon_putcs,
+ .con_cursor = dummycon_cursor,
+ .con_scroll = dummycon_scroll,
+ .con_switch = dummycon_switch,
+ .con_blank = dummycon_blank,
+ .con_font_set = dummycon_font_set,
+ .con_font_default = dummycon_font_default,
+ .con_font_copy = dummycon_font_copy,
};
EXPORT_SYMBOL_GPL(dummy_con);
diff --git a/drivers/video/fbdev/goldfishfb.c b/drivers/video/fbdev/goldfishfb.c
index 66d58e9..8c93ad1 100644
--- a/drivers/video/fbdev/goldfishfb.c
+++ b/drivers/video/fbdev/goldfishfb.c
@@ -26,6 +26,7 @@
#include <linux/interrupt.h>
#include <linux/ioport.h>
#include <linux/platform_device.h>
+#include <linux/acpi.h>
enum {
FB_GET_WIDTH = 0x00,
@@ -305,12 +306,25 @@ static int goldfish_fb_remove(struct platform_device *pdev)
return 0;
}
+static const struct of_device_id goldfish_fb_of_match[] = {
+ { .compatible = "google,goldfish-fb", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, goldfish_fb_of_match);
+
+static const struct acpi_device_id goldfish_fb_acpi_match[] = {
+ { "GFSH0004", 0 },
+ { },
+};
+MODULE_DEVICE_TABLE(acpi, goldfish_fb_acpi_match);
static struct platform_driver goldfish_fb_driver = {
.probe = goldfish_fb_probe,
.remove = goldfish_fb_remove,
.driver = {
- .name = "goldfish_fb"
+ .name = "goldfish_fb",
+ .of_match_table = goldfish_fb_of_match,
+ .acpi_match_table = ACPI_PTR(goldfish_fb_acpi_match),
}
};
diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c
index 2e30db1..fa13fa8 100644
--- a/drivers/w1/masters/ds2482.c
+++ b/drivers/w1/masters/ds2482.c
@@ -18,6 +18,8 @@
#include <linux/slab.h>
#include <linux/i2c.h>
#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/platform_data/ds2482.h>
#include <asm/delay.h>
#include "../w1.h"
@@ -97,7 +99,8 @@ static const u8 ds2482_chan_rd[8] =
static int ds2482_probe(struct i2c_client *client,
const struct i2c_device_id *id);
static int ds2482_remove(struct i2c_client *client);
-
+static int ds2482_suspend(struct device *dev);
+static int ds2482_resume(struct device *dev);
/**
* Driver data (common to all clients)
@@ -108,9 +111,15 @@ static const struct i2c_device_id ds2482_id[] = {
};
MODULE_DEVICE_TABLE(i2c, ds2482_id);
+static const struct dev_pm_ops ds2482_pm_ops = {
+ .suspend = ds2482_suspend,
+ .resume = ds2482_resume,
+};
+
static struct i2c_driver ds2482_driver = {
.driver = {
.name = "ds2482",
+ .pm = &ds2482_pm_ops,
},
.probe = ds2482_probe,
.remove = ds2482_remove,
@@ -132,6 +141,7 @@ struct ds2482_w1_chan {
struct ds2482_data {
struct i2c_client *client;
struct mutex access_lock;
+ int slpz_gpio;
/* 1-wire interface(s) */
int w1_count; /* 1 or 8 */
@@ -460,11 +470,31 @@ static u8 ds2482_w1_set_pullup(void *data, int delay)
return retval;
}
+static int ds2482_suspend(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct ds2482_data *data = i2c_get_clientdata(client);
+
+ if (data->slpz_gpio >= 0)
+ gpio_set_value(data->slpz_gpio, 0);
+ return 0;
+}
+
+static int ds2482_resume(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct ds2482_data *data = i2c_get_clientdata(client);
+
+ if (data->slpz_gpio >= 0)
+ gpio_set_value(data->slpz_gpio, 1);
+ return 0;
+}
static int ds2482_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
struct ds2482_data *data;
+ struct ds2482_platform_data *pdata;
int err = -ENODEV;
int temp1;
int idx;
@@ -531,6 +561,16 @@ static int ds2482_probe(struct i2c_client *client,
}
}
+ pdata = client->dev.platform_data;
+ data->slpz_gpio = pdata ? pdata->slpz_gpio : -1;
+
+ if (data->slpz_gpio >= 0) {
+ err = gpio_request_one(data->slpz_gpio, GPIOF_OUT_INIT_HIGH,
+ "ds2482.slpz");
+ if (err < 0)
+ goto exit_w1_remove;
+ }
+
return 0;
exit_w1_remove:
@@ -555,6 +595,11 @@ static int ds2482_remove(struct i2c_client *client)
w1_remove_master_device(&data->w1_ch[idx].w1_bm);
}
+ if (data->slpz_gpio >= 0) {
+ gpio_set_value(data->slpz_gpio, 0);
+ gpio_free(data->slpz_gpio);
+ }
+
/* Free the memory */
kfree(data);
return 0;
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index e45b1a0..d618c20 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -49,9 +49,9 @@
* @page: structure to page
*
*/
-static int v9fs_fid_readpage(void *data, struct page *page)
+static int v9fs_fid_readpage(struct file *data, struct page *page)
{
- struct p9_fid *fid = data;
+ struct p9_fid *fid = (struct p9_fid *)data;
struct inode *inode = page->mapping->host;
struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
struct iov_iter to;
@@ -293,7 +293,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
if (len == PAGE_SIZE)
goto out;
- retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
+ retval = v9fs_fid_readpage((struct file *)v9inode->writeback_fid, page);
put_page(page);
if (!retval)
goto start;
diff --git a/fs/Kconfig b/fs/Kconfig
index 4bd03a2..20a8d95 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -227,6 +227,7 @@
source "fs/adfs/Kconfig"
source "fs/affs/Kconfig"
source "fs/ecryptfs/Kconfig"
+source "fs/sdcardfs/Kconfig"
source "fs/hfs/Kconfig"
source "fs/hfsplus/Kconfig"
source "fs/befs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index ed2b632..bac780a 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -3,7 +3,7 @@
#
# 14 Sep 2000, Christoph Hellwig <hch@infradead.org>
# Rewritten to use lists instead of if-statements.
-#
+#
obj-y := open.o read_write.o file_table.o super.o \
char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
@@ -23,7 +23,7 @@
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
-obj-$(CONFIG_ANON_INODES) += anon_inodes.o
+obj-y += anon_inodes.o
obj-$(CONFIG_SIGNALFD) += signalfd.o
obj-$(CONFIG_TIMERFD) += timerfd.o
obj-$(CONFIG_EVENTFD) += eventfd.o
@@ -61,7 +61,7 @@
obj-$(CONFIG_PROFILING) += dcookies.o
obj-$(CONFIG_DLM) += dlm/
-
+
# Do not add any filesystems before this line
obj-$(CONFIG_FSCACHE) += fscache/
obj-$(CONFIG_REISERFS_FS) += reiserfs/
@@ -83,6 +83,7 @@
obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+
obj-$(CONFIG_HFS_FS) += hfs/
obj-$(CONFIG_ECRYPT_FS) += ecryptfs/
+obj-$(CONFIG_SDCARD_FS) += sdcardfs/
obj-$(CONFIG_VXFS_FS) += freevxfs/
obj-$(CONFIG_NFS_FS) += nfs/
obj-$(CONFIG_EXPORTFS) += exportfs/
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 7237297..37f97ba 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -123,11 +123,10 @@ static void afs_file_readpage_read_complete(struct page *page,
/*
* read page from file, directory or symlink, given a key to use
*/
-int afs_page_filler(void *data, struct page *page)
+static int __afs_page_filler(struct key *key, struct page *page)
{
struct inode *inode = page->mapping->host;
struct afs_vnode *vnode = AFS_FS_I(inode);
- struct key *key = data;
size_t len;
off_t offset;
int ret;
@@ -209,6 +208,13 @@ int afs_page_filler(void *data, struct page *page)
return ret;
}
+int afs_page_filler(struct file *data, struct page *page)
+{
+ struct key *key = (struct key *)data;
+
+ return __afs_page_filler(key, page);
+}
+
/*
* read page from file, directory or symlink, given a file to nominate the key
* to be used
@@ -221,14 +227,14 @@ static int afs_readpage(struct file *file, struct page *page)
if (file) {
key = file->private_data;
ASSERT(key != NULL);
- ret = afs_page_filler(key, page);
+ ret = __afs_page_filler(key, page);
} else {
struct inode *inode = page->mapping->host;
key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
} else {
- ret = afs_page_filler(key, page);
+ ret = __afs_page_filler(key, page);
key_put(key);
}
}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index dd98dcd..b4165cc 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -497,7 +497,7 @@ extern const struct file_operations afs_file_operations;
extern int afs_open(struct inode *, struct file *);
extern int afs_release(struct inode *, struct file *);
-extern int afs_page_filler(void *, struct page *);
+extern int afs_page_filler(struct file *, struct page *);
/*
* flock.c
diff --git a/fs/attr.c b/fs/attr.c
index c902b3d..c4093c5 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -200,7 +200,7 @@ EXPORT_SYMBOL(setattr_copy);
* the file open for write, as there can be no conflicting delegation in
* that case.
*/
-int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
+int notify_change2(struct vfsmount *mnt, struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
@@ -224,7 +224,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
return -EPERM;
if (!inode_owner_or_capable(inode)) {
- error = inode_permission(inode, MAY_WRITE);
+ error = inode_permission2(mnt, inode, MAY_WRITE);
if (error)
return error;
}
@@ -307,7 +307,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
if (error)
return error;
- if (inode->i_op->setattr)
+ if (mnt && inode->i_op->setattr2)
+ error = inode->i_op->setattr2(mnt, dentry, attr);
+ else if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
@@ -320,4 +322,10 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
return error;
}
+EXPORT_SYMBOL(notify_change2);
+
+int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
+{
+ return notify_change2(NULL, dentry, attr, delegated_inode);
+}
EXPORT_SYMBOL(notify_change);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 5c2f4f58..e7c8a13 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3830,8 +3830,8 @@ int btree_write_cache_pages(struct address_space *mapping,
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
while (!done && !nr_to_write_done && (index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+ (nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag))) {
unsigned i;
scanned = 1;
@@ -3841,11 +3841,6 @@ int btree_write_cache_pages(struct address_space *mapping,
if (!PagePrivate(page))
continue;
- if (!wbc->range_cyclic && page->index > end) {
- done = 1;
- break;
- }
-
spin_lock(&mapping->private_lock);
if (!PagePrivate(page)) {
spin_unlock(&mapping->private_lock);
@@ -3982,8 +3977,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+ (nr_pages = pagevec_lookup_range_tag(&pvec, mapping,
+ &index, end, tag))) {
unsigned i;
scanned = 1;
@@ -4008,12 +4003,6 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
continue;
}
- if (!wbc->range_cyclic && page->index > end) {
- done = 1;
- unlock_page(page);
- continue;
- }
-
if (wbc->sync_mode != WB_SYNC_NONE) {
if (PageWriteback(page))
flush_fn(data);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 36aa6d8..1672212 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -838,21 +838,15 @@ static int ceph_writepages_start(struct address_space *mapping,
struct page **pages = NULL, **data_pages;
mempool_t *pool = NULL; /* Becomes non-null if mempool used */
struct page *page;
- int want;
u64 offset = 0, len = 0;
max_pages = max_pages_ever;
get_more_pages:
first = -1;
- want = min(end - index,
- min((pgoff_t)PAGEVEC_SIZE,
- max_pages - (pgoff_t)locked_pages) - 1)
- + 1;
- pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- want);
- dout("pagevec_lookup_tag got %d\n", pvec_pages);
+ pvec_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
+ end, PAGECACHE_TAG_DIRTY);
+ dout("pagevec_lookup_range_tag got %d\n", pvec_pages);
if (!pvec_pages && !locked_pages)
break;
for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
@@ -870,12 +864,6 @@ static int ceph_writepages_start(struct address_space *mapping,
unlock_page(page);
break;
}
- if (!wbc->range_cyclic && page->index > end) {
- dout("end of range %p\n", page);
- done = 1;
- unlock_page(page);
- break;
- }
if (strip_unit_end && (page->index > strip_unit_end)) {
dout("end of strip unit %p\n", page);
unlock_page(page);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index af78de9..f7e957e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2505,7 +2505,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
}
down_read(&key->sem);
- upayload = user_key_payload(key);
+ upayload = user_key_payload_locked(key);
if (IS_ERR_OR_NULL(upayload)) {
rc = upayload ? PTR_ERR(upayload) : -EINVAL;
goto out_key_put;
diff --git a/fs/coredump.c b/fs/coredump.c
index 4407e27..00a900a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -744,7 +744,7 @@ void do_coredump(const siginfo_t *siginfo)
goto close_fail;
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
- if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
+ if (do_truncate2(cprm.file->f_path.mnt, cprm.file->f_path.dentry, 0, 0, cprm.file))
goto close_fail;
}
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index 92348fa..08b46e6 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -1,6 +1,5 @@
config FS_ENCRYPTION
tristate "FS Encryption (Per-file encryption)"
- depends on BLOCK
select CRYPTO
select CRYPTO_AES
select CRYPTO_CBC
@@ -8,9 +7,7 @@
select CRYPTO_XTS
select CRYPTO_CTS
select CRYPTO_CTR
- select CRYPTO_SHA256
select KEYS
- select ENCRYPTED_KEYS
help
Enable encryption of files and directories. This
feature is similar to ecryptfs, but it is more memory
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
index f17684c..cb49698 100644
--- a/fs/crypto/Makefile
+++ b/fs/crypto/Makefile
@@ -1,3 +1,4 @@
obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o
-fscrypto-y := crypto.o fname.o policy.o keyinfo.o
+fscrypto-y := crypto.o fname.o hooks.o keyinfo.o policy.o
+fscrypto-$(CONFIG_BLOCK) += bio.o
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
new file mode 100644
index 0000000..d7b4c48
--- /dev/null
+++ b/fs/crypto/bio.c
@@ -0,0 +1,154 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ * Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/namei.h>
+#include "fscrypt_private.h"
+
+static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
+{
+ struct bio_vec *bv;
+ int i;
+
+ bio_for_each_segment_all(bv, bio, i) {
+ struct page *page = bv->bv_page;
+ int ret = fscrypt_decrypt_page(page->mapping->host, page,
+ PAGE_SIZE, 0, page->index);
+
+ if (ret) {
+ WARN_ON_ONCE(1);
+ SetPageError(page);
+ } else if (done) {
+ SetPageUptodate(page);
+ }
+ if (done)
+ unlock_page(page);
+ }
+}
+
+void fscrypt_decrypt_bio(struct bio *bio)
+{
+ __fscrypt_decrypt_bio(bio, false);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio);
+
+static void completion_pages(struct work_struct *work)
+{
+ struct fscrypt_ctx *ctx =
+ container_of(work, struct fscrypt_ctx, r.work);
+ struct bio *bio = ctx->r.bio;
+
+ __fscrypt_decrypt_bio(bio, true);
+ fscrypt_release_ctx(ctx);
+ bio_put(bio);
+}
+
+void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+ INIT_WORK(&ctx->r.work, completion_pages);
+ ctx->r.bio = bio;
+ fscrypt_enqueue_decrypt_work(&ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+ struct fscrypt_ctx *ctx;
+ struct page *bounce_page;
+
+ /* The bounce data pages are unmapped. */
+ if ((*page)->mapping)
+ return;
+
+ /* The bounce data page is unmapped. */
+ bounce_page = *page;
+ ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+ /* restore control page */
+ *page = ctx->w.control_page;
+
+ if (restore)
+ fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+ sector_t pblk, unsigned int len)
+{
+ struct fscrypt_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ struct bio *bio;
+ int ret, err = 0;
+
+ BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
+ if (IS_ERR(ciphertext_page)) {
+ err = PTR_ERR(ciphertext_page);
+ goto errout;
+ }
+
+ while (len--) {
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
+ ZERO_PAGE(0), ciphertext_page,
+ PAGE_SIZE, 0, GFP_NOFS);
+ if (err)
+ goto errout;
+
+ bio = bio_alloc(GFP_NOWAIT, 1);
+ if (!bio) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ bio->bi_bdev = inode->i_sb->s_bdev;
+ bio->bi_iter.bi_sector =
+ pblk << (inode->i_sb->s_blocksize_bits - 9);
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ ret = bio_add_page(bio, ciphertext_page,
+ inode->i_sb->s_blocksize, 0);
+ if (ret != inode->i_sb->s_blocksize) {
+ /* should never happen! */
+ WARN_ON(1);
+ bio_put(bio);
+ err = -EIO;
+ goto errout;
+ }
+ err = submit_bio_wait(bio);
+ if (err == 0 && bio->bi_error)
+ err = -EIO;
+ bio_put(bio);
+ if (err)
+ goto errout;
+ lblk++;
+ pblk++;
+ }
+ err = 0;
+errout:
+ fscrypt_release_ctx(ctx);
+ return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 1a89625..4dc788e 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -24,10 +24,11 @@
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/ratelimit.h>
-#include <linux/bio.h>
#include <linux/dcache.h>
#include <linux/namei.h>
-#include <linux/fscrypto.h>
+#include <crypto/aes.h>
+#include <crypto/skcipher.h>
+#include "fscrypt_private.h"
static unsigned int num_prealloc_crypto_pages = 32;
static unsigned int num_prealloc_crypto_ctxs = 128;
@@ -50,6 +51,12 @@ static DEFINE_MUTEX(fscrypt_init_mutex);
static struct kmem_cache *fscrypt_ctx_cachep;
struct kmem_cache *fscrypt_info_cachep;
+void fscrypt_enqueue_decrypt_work(struct work_struct *work)
+{
+ queue_work(fscrypt_read_workqueue, work);
+}
+EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work);
+
/**
* fscrypt_release_ctx() - Releases an encryption context
* @ctx: The encryption context to release.
@@ -63,7 +70,7 @@ void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
{
unsigned long flags;
- if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+ if (ctx->flags & FS_CTX_HAS_BOUNCE_BUFFER_FL && ctx->w.bounce_page) {
mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
ctx->w.bounce_page = NULL;
}
@@ -88,7 +95,7 @@ EXPORT_SYMBOL(fscrypt_release_ctx);
* Return: An allocated and initialized encryption context on success; error
* value or NULL otherwise.
*/
-struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
+struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags)
{
struct fscrypt_ctx *ctx = NULL;
struct fscrypt_info *ci = inode->i_crypt_info;
@@ -121,134 +128,149 @@ struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
} else {
ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
}
- ctx->flags &= ~FS_WRITE_PATH_FL;
+ ctx->flags &= ~FS_CTX_HAS_BOUNCE_BUFFER_FL;
return ctx;
}
EXPORT_SYMBOL(fscrypt_get_ctx);
-/**
- * page_crypt_complete() - completion callback for page crypto
- * @req: The asynchronous cipher request context
- * @res: The result of the cipher operation
- */
-static void page_crypt_complete(struct crypto_async_request *req, int res)
+void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
+ const struct fscrypt_info *ci)
{
- struct fscrypt_completion_result *ecr = req->data;
+ memset(iv, 0, ci->ci_mode->ivsize);
+ iv->lblk_num = cpu_to_le64(lblk_num);
- if (res == -EINPROGRESS)
- return;
- ecr->res = res;
- complete(&ecr->completion);
+ if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY)
+ memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+
+ if (ci->ci_essiv_tfm != NULL)
+ crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw);
}
-typedef enum {
- FS_DECRYPT = 0,
- FS_ENCRYPT,
-} fscrypt_direction_t;
-
-static int do_page_crypto(struct inode *inode,
- fscrypt_direction_t rw, pgoff_t index,
- struct page *src_page, struct page *dest_page,
- gfp_t gfp_flags)
+int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
+ u64 lblk_num, struct page *src_page,
+ struct page *dest_page, unsigned int len,
+ unsigned int offs, gfp_t gfp_flags)
{
- struct {
- __le64 index;
- u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
- } xts_tweak;
+ union fscrypt_iv iv;
struct skcipher_request *req = NULL;
- DECLARE_FS_COMPLETION_RESULT(ecr);
+ DECLARE_CRYPTO_WAIT(wait);
struct scatterlist dst, src;
struct fscrypt_info *ci = inode->i_crypt_info;
struct crypto_skcipher *tfm = ci->ci_ctfm;
int res = 0;
+ BUG_ON(len == 0);
+
+ fscrypt_generate_iv(&iv, lblk_num, ci);
+
req = skcipher_request_alloc(tfm, gfp_flags);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_request_alloc() failed\n",
- __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(
req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- page_crypt_complete, &ecr);
-
- BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
- xts_tweak.index = cpu_to_le64(index);
- memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
+ crypto_req_done, &wait);
sg_init_table(&dst, 1);
- sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
+ sg_set_page(&dst, dest_page, len, offs);
sg_init_table(&src, 1);
- sg_set_page(&src, src_page, PAGE_SIZE, 0);
- skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak);
+ sg_set_page(&src, src_page, len, offs);
+ skcipher_request_set_crypt(req, &src, &dst, len, &iv);
if (rw == FS_DECRYPT)
- res = crypto_skcipher_decrypt(req);
+ res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
else
- res = crypto_skcipher_encrypt(req);
- if (res == -EINPROGRESS || res == -EBUSY) {
- BUG_ON(req->base.data != &ecr);
- wait_for_completion(&ecr.completion);
- res = ecr.res;
- }
+ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_skcipher_encrypt() returned %d\n",
- __func__, res);
+ fscrypt_err(inode->i_sb,
+ "%scryption failed for inode %lu, block %llu: %d",
+ (rw == FS_DECRYPT ? "de" : "en"),
+ inode->i_ino, lblk_num, res);
return res;
}
return 0;
}
-static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
+struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+ gfp_t gfp_flags)
{
ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
if (ctx->w.bounce_page == NULL)
return ERR_PTR(-ENOMEM);
- ctx->flags |= FS_WRITE_PATH_FL;
+ ctx->flags |= FS_CTX_HAS_BOUNCE_BUFFER_FL;
return ctx->w.bounce_page;
}
/**
* fscypt_encrypt_page() - Encrypts a page
- * @inode: The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- * @gfp_flags: The gfp flag for memory allocation
+ * @inode: The inode for which the encryption should take place
+ * @page: The page to encrypt. Must be locked for bounce-page
+ * encryption.
+ * @len: Length of data to encrypt in @page and encrypted
+ * data in returned page.
+ * @offs: Offset of data within @page and returned
+ * page holding encrypted data.
+ * @lblk_num: Logical block number. This must be unique for multiple
+ * calls with same inode, except when overwriting
+ * previously written data.
+ * @gfp_flags: The gfp flag for memory allocation
*
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
+ * Encrypts @page using the ctx encryption context. Performs encryption
+ * either in-place or into a newly allocated bounce page.
+ * Called on the page write path.
*
- * Called on the page write path. The caller must call
+ * Bounce page allocation is the default.
+ * In this case, the contents of @page are encrypted and stored in an
+ * allocated bounce page. @page has to be locked and the caller must call
* fscrypt_restore_control_page() on the returned ciphertext page to
* release the bounce buffer and the encryption context.
*
- * Return: An allocated page with the encrypted content on success. Else, an
+ * In-place encryption is used by setting the FS_CFLG_OWN_PAGES flag in
+ * fscrypt_operations. Here, the input-page is returned with its content
+ * encrypted.
+ *
+ * Return: A page with the encrypted content on success. Else, an
* error value or NULL.
*/
-struct page *fscrypt_encrypt_page(struct inode *inode,
- struct page *plaintext_page, gfp_t gfp_flags)
+struct page *fscrypt_encrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len,
+ unsigned int offs,
+ u64 lblk_num, gfp_t gfp_flags)
+
{
struct fscrypt_ctx *ctx;
- struct page *ciphertext_page = NULL;
+ struct page *ciphertext_page = page;
int err;
- BUG_ON(!PageLocked(plaintext_page));
+ BUG_ON(len % FS_CRYPTO_BLOCK_SIZE != 0);
+
+ if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
+ /* with inplace-encryption we just encrypt the page */
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page,
+ ciphertext_page, len, offs,
+ gfp_flags);
+ if (err)
+ return ERR_PTR(err);
+
+ return ciphertext_page;
+ }
+
+ BUG_ON(!PageLocked(page));
ctx = fscrypt_get_ctx(inode, gfp_flags);
if (IS_ERR(ctx))
return (struct page *)ctx;
/* The encryption operation will require a bounce page. */
- ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+ ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags);
if (IS_ERR(ciphertext_page))
goto errout;
- ctx->w.control_page = plaintext_page;
- err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
- plaintext_page, ciphertext_page,
- gfp_flags);
+ ctx->w.control_page = page;
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+ page, ciphertext_page, len, offs,
+ gfp_flags);
if (err) {
ciphertext_page = ERR_PTR(err);
goto errout;
@@ -265,8 +287,13 @@ struct page *fscrypt_encrypt_page(struct inode *inode,
EXPORT_SYMBOL(fscrypt_encrypt_page);
/**
- * f2crypt_decrypt_page() - Decrypts a page in-place
- * @page: The page to decrypt. Must be locked.
+ * fscrypt_decrypt_page() - Decrypts a page in-place
+ * @inode: The corresponding inode for the page to decrypt.
+ * @page: The page to decrypt. Must be locked in case
+ * it is a writeback page (FS_CFLG_OWN_PAGES unset).
+ * @len: Number of bytes in @page to be decrypted.
+ * @offs: Start of data in @page.
+ * @lblk_num: Logical block number.
*
* Decrypts page in-place using the ctx encryption context.
*
@@ -274,76 +301,17 @@ EXPORT_SYMBOL(fscrypt_encrypt_page);
*
* Return: Zero on success, non-zero otherwise.
*/
-int fscrypt_decrypt_page(struct page *page)
+int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
+ unsigned int len, unsigned int offs, u64 lblk_num)
{
- BUG_ON(!PageLocked(page));
+ if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
+ BUG_ON(!PageLocked(page));
- return do_page_crypto(page->mapping->host,
- FS_DECRYPT, page->index, page, page, GFP_NOFS);
+ return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page,
+ len, offs, GFP_NOFS);
}
EXPORT_SYMBOL(fscrypt_decrypt_page);
-int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
- sector_t pblk, unsigned int len)
-{
- struct fscrypt_ctx *ctx;
- struct page *ciphertext_page = NULL;
- struct bio *bio;
- int ret, err = 0;
-
- BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
-
- ctx = fscrypt_get_ctx(inode, GFP_NOFS);
- if (IS_ERR(ctx))
- return PTR_ERR(ctx);
-
- ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
- if (IS_ERR(ciphertext_page)) {
- err = PTR_ERR(ciphertext_page);
- goto errout;
- }
-
- while (len--) {
- err = do_page_crypto(inode, FS_ENCRYPT, lblk,
- ZERO_PAGE(0), ciphertext_page,
- GFP_NOFS);
- if (err)
- goto errout;
-
- bio = bio_alloc(GFP_NOWAIT, 1);
- if (!bio) {
- err = -ENOMEM;
- goto errout;
- }
- bio->bi_bdev = inode->i_sb->s_bdev;
- bio->bi_iter.bi_sector =
- pblk << (inode->i_sb->s_blocksize_bits - 9);
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- ret = bio_add_page(bio, ciphertext_page,
- inode->i_sb->s_blocksize, 0);
- if (ret != inode->i_sb->s_blocksize) {
- /* should never happen! */
- WARN_ON(1);
- bio_put(bio);
- err = -EIO;
- goto errout;
- }
- err = submit_bio_wait(bio);
- if ((err == 0) && bio->bi_error)
- err = -EIO;
- bio_put(bio);
- if (err)
- goto errout;
- lblk++;
- pblk++;
- }
- err = 0;
-errout:
- fscrypt_release_ctx(ctx);
- return err;
-}
-EXPORT_SYMBOL(fscrypt_zeroout_range);
-
/*
* Validate dentries for encrypted directories to make sure we aren't
* potentially caching stale data after a key has been added or
@@ -358,12 +326,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
return -ECHILD;
dir = dget_parent(dentry);
- if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) {
+ if (!IS_ENCRYPTED(d_inode(dir))) {
dput(dir);
return 0;
}
- /* this should eventually be an flag in d_flags */
spin_lock(&dentry->d_lock);
cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
spin_unlock(&dentry->d_lock);
@@ -390,64 +357,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
const struct dentry_operations fscrypt_d_ops = {
.d_revalidate = fscrypt_d_revalidate,
};
-EXPORT_SYMBOL(fscrypt_d_ops);
-
-/*
- * Call fscrypt_decrypt_page on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
- struct fscrypt_ctx *ctx =
- container_of(work, struct fscrypt_ctx, r.work);
- struct bio *bio = ctx->r.bio;
- struct bio_vec *bv;
- int i;
-
- bio_for_each_segment_all(bv, bio, i) {
- struct page *page = bv->bv_page;
- int ret = fscrypt_decrypt_page(page);
-
- if (ret) {
- WARN_ON_ONCE(1);
- SetPageError(page);
- } else {
- SetPageUptodate(page);
- }
- unlock_page(page);
- }
- fscrypt_release_ctx(ctx);
- bio_put(bio);
-}
-
-void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
-{
- INIT_WORK(&ctx->r.work, completion_pages);
- ctx->r.bio = bio;
- queue_work(fscrypt_read_workqueue, &ctx->r.work);
-}
-EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
-
-void fscrypt_pullback_bio_page(struct page **page, bool restore)
-{
- struct fscrypt_ctx *ctx;
- struct page *bounce_page;
-
- /* The bounce data pages are unmapped. */
- if ((*page)->mapping)
- return;
-
- /* The bounce data page is unmapped. */
- bounce_page = *page;
- ctx = (struct fscrypt_ctx *)page_private(bounce_page);
-
- /* restore control page */
- *page = ctx->w.control_page;
-
- if (restore)
- fscrypt_restore_control_page(bounce_page);
-}
-EXPORT_SYMBOL(fscrypt_pullback_bio_page);
void fscrypt_restore_control_page(struct page *page)
{
@@ -474,16 +383,21 @@ static void fscrypt_destroy(void)
/**
* fscrypt_initialize() - allocate major buffers for fs encryption.
+ * @cop_flags: fscrypt operations flags
*
* We only call this when we start accessing encrypted files, since it
* results in memory getting allocated that wouldn't otherwise be used.
*
* Return: Zero on success, non-zero otherwise.
*/
-int fscrypt_initialize(void)
+int fscrypt_initialize(unsigned int cop_flags)
{
int i, res = -ENOMEM;
+ /* No need to allocate a bounce page pool if this FS won't use it. */
+ if (cop_flags & FS_CFLG_OWN_PAGES)
+ return 0;
+
mutex_lock(&fscrypt_init_mutex);
if (fscrypt_bounce_page_pool)
goto already_initialized;
@@ -510,7 +424,27 @@ int fscrypt_initialize(void)
mutex_unlock(&fscrypt_init_mutex);
return res;
}
-EXPORT_SYMBOL(fscrypt_initialize);
+
+void fscrypt_msg(struct super_block *sb, const char *level,
+ const char *fmt, ...)
+{
+ static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+ struct va_format vaf;
+ va_list args;
+
+ if (!__ratelimit(&rs))
+ return;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (sb)
+ printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf);
+ else
+ printk("%sfscrypt: %pV\n", level, &vaf);
+ va_end(args);
+}
/**
* fscrypt_init() - Set up for fs encryption.
@@ -561,6 +495,8 @@ static void __exit fscrypt_exit(void)
destroy_workqueue(fscrypt_read_workqueue);
kmem_cache_destroy(fscrypt_ctx_cachep);
kmem_cache_destroy(fscrypt_info_cachep);
+
+ fscrypt_essiv_cleanup();
}
module_exit(fscrypt_exit);
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index e14bb7b..217d421 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -12,89 +12,71 @@
#include <linux/scatterlist.h>
#include <linux/ratelimit.h>
-#include <linux/fscrypto.h>
+#include <crypto/skcipher.h>
+#include "fscrypt_private.h"
-/**
- * fname_crypt_complete() - completion callback for filename crypto
- * @req: The asynchronous cipher request context
- * @res: The result of the cipher operation
- */
-static void fname_crypt_complete(struct crypto_async_request *req, int res)
+static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
{
- struct fscrypt_completion_result *ecr = req->data;
+ if (str->len == 1 && str->name[0] == '.')
+ return true;
- if (res == -EINPROGRESS)
- return;
- ecr->res = res;
- complete(&ecr->completion);
+ if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+ return true;
+
+ return false;
}
/**
* fname_encrypt() - encrypt a filename
*
- * The caller must have allocated sufficient memory for the @oname string.
+ * The output buffer must be at least as large as the input buffer.
+ * Any extra space is filled with NUL padding before encryption.
*
* Return: 0 on success, -errno on failure
*/
-static int fname_encrypt(struct inode *inode,
- const struct qstr *iname, struct fscrypt_str *oname)
+int fname_encrypt(struct inode *inode, const struct qstr *iname,
+ u8 *out, unsigned int olen)
{
struct skcipher_request *req = NULL;
- DECLARE_FS_COMPLETION_RESULT(ecr);
+ DECLARE_CRYPTO_WAIT(wait);
struct fscrypt_info *ci = inode->i_crypt_info;
struct crypto_skcipher *tfm = ci->ci_ctfm;
- int res = 0;
- char iv[FS_CRYPTO_BLOCK_SIZE];
+ union fscrypt_iv iv;
struct scatterlist sg;
- int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
- unsigned int lim;
- unsigned int cryptlen;
-
- lim = inode->i_sb->s_cop->max_namelen(inode);
- if (iname->len <= 0 || iname->len > lim)
- return -EIO;
+ int res;
/*
* Copy the filename to the output buffer for encrypting in-place and
* pad it with the needed number of NUL bytes.
*/
- cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE);
- cryptlen = round_up(cryptlen, padding);
- cryptlen = min(cryptlen, lim);
- memcpy(oname->name, iname->name, iname->len);
- memset(oname->name + iname->len, 0, cryptlen - iname->len);
+ if (WARN_ON(olen < iname->len))
+ return -ENOBUFS;
+ memcpy(out, iname->name, iname->len);
+ memset(out + iname->len, 0, olen - iname->len);
/* Initialize the IV */
- memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
+ fscrypt_generate_iv(&iv, 0, ci);
/* Set up the encryption request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: skcipher_request_alloc() failed\n", __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- fname_crypt_complete, &ecr);
- sg_init_one(&sg, oname->name, cryptlen);
- skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv);
+ crypto_req_done, &wait);
+ sg_init_one(&sg, out, olen);
+ skcipher_request_set_crypt(req, &sg, &sg, olen, &iv);
/* Do the encryption */
- res = crypto_skcipher_encrypt(req);
- if (res == -EINPROGRESS || res == -EBUSY) {
- /* Request is being completed asynchronously; wait for it */
- wait_for_completion(&ecr.completion);
- res = ecr.res;
- }
+ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
- printk_ratelimited(KERN_ERR
- "%s: Error (error code %d)\n", __func__, res);
+ fscrypt_err(inode->i_sb,
+ "Filename encryption failed for inode %lu: %d",
+ inode->i_ino, res);
return res;
}
- oname->len = cryptlen;
return 0;
}
@@ -110,45 +92,34 @@ static int fname_decrypt(struct inode *inode,
struct fscrypt_str *oname)
{
struct skcipher_request *req = NULL;
- DECLARE_FS_COMPLETION_RESULT(ecr);
+ DECLARE_CRYPTO_WAIT(wait);
struct scatterlist src_sg, dst_sg;
struct fscrypt_info *ci = inode->i_crypt_info;
struct crypto_skcipher *tfm = ci->ci_ctfm;
- int res = 0;
- char iv[FS_CRYPTO_BLOCK_SIZE];
- unsigned lim;
-
- lim = inode->i_sb->s_cop->max_namelen(inode);
- if (iname->len <= 0 || iname->len > lim)
- return -EIO;
+ union fscrypt_iv iv;
+ int res;
/* Allocate request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_request_alloc() failed\n", __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- fname_crypt_complete, &ecr);
+ crypto_req_done, &wait);
/* Initialize IV */
- memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
+ fscrypt_generate_iv(&iv, 0, ci);
/* Create decryption request */
sg_init_one(&src_sg, iname->name, iname->len);
sg_init_one(&dst_sg, oname->name, oname->len);
- skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
- res = crypto_skcipher_decrypt(req);
- if (res == -EINPROGRESS || res == -EBUSY) {
- wait_for_completion(&ecr.completion);
- res = ecr.res;
- }
+ skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv);
+ res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
- printk_ratelimited(KERN_ERR
- "%s: Error (error code %d)\n", __func__, res);
+ fscrypt_err(inode->i_sb,
+ "Filename decryption failed for inode %lu: %d",
+ inode->i_ino, res);
return res;
}
@@ -159,6 +130,8 @@ static int fname_decrypt(struct inode *inode,
static const char *lookup_table =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+#define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3)
+
/**
* digest_encode() -
*
@@ -209,47 +182,52 @@ static int digest_decode(const char *src, int len, char *dst)
return cp - dst;
}
-u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
+bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
+ u32 max_len, u32 *encrypted_len_ret)
{
- int padding = 32;
- struct fscrypt_info *ci = inode->i_crypt_info;
+ int padding = 4 << (inode->i_crypt_info->ci_flags &
+ FS_POLICY_FLAGS_PAD_MASK);
+ u32 encrypted_len;
- if (ci)
- padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
- ilen = max(ilen, (u32)FS_CRYPTO_BLOCK_SIZE);
- return round_up(ilen, padding);
+ if (orig_len > max_len)
+ return false;
+ encrypted_len = max(orig_len, (u32)FS_CRYPTO_BLOCK_SIZE);
+ encrypted_len = round_up(encrypted_len, padding);
+ *encrypted_len_ret = min(encrypted_len, max_len);
+ return true;
}
-EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
/**
- * fscrypt_fname_crypto_alloc_obuff() -
+ * fscrypt_fname_alloc_buffer - allocate a buffer for presented filenames
*
- * Allocates an output buffer that is sufficient for the crypto operation
- * specified by the context and the direction.
+ * Allocate a buffer that is large enough to hold any decrypted or encoded
+ * filename (null-terminated), for the given maximum encrypted filename length.
+ *
+ * Return: 0 on success, -errno on failure
*/
-int fscrypt_fname_alloc_buffer(struct inode *inode,
- u32 ilen, struct fscrypt_str *crypto_str)
+int fscrypt_fname_alloc_buffer(const struct inode *inode,
+ u32 max_encrypted_len,
+ struct fscrypt_str *crypto_str)
{
- unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
+ const u32 max_encoded_len =
+ max_t(u32, BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE),
+ 1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)));
+ u32 max_presented_len;
- crypto_str->len = olen;
- if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
- olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
- /*
- * Allocated buffer can hold one more character to null-terminate the
- * string
- */
- crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
- if (!(crypto_str->name))
+ max_presented_len = max(max_encoded_len, max_encrypted_len);
+
+ crypto_str->name = kmalloc(max_presented_len + 1, GFP_NOFS);
+ if (!crypto_str->name)
return -ENOMEM;
+ crypto_str->len = max_presented_len;
return 0;
}
EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
/**
- * fscrypt_fname_crypto_free_buffer() -
+ * fscrypt_fname_free_buffer - free the buffer for presented filenames
*
- * Frees the buffer allocated for crypto operation.
+ * Free the buffer allocated by fscrypt_fname_alloc_buffer().
*/
void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
{
@@ -266,6 +244,10 @@ EXPORT_SYMBOL(fscrypt_fname_free_buffer);
*
* The caller must have allocated sufficient memory for the @oname string.
*
+ * If the key is available, we'll decrypt the disk name; otherwise, we'll encode
+ * it for presentation. Short names are directly base64-encoded, while long
+ * names are encoded in fscrypt_digested_name format.
+ *
* Return: 0 on success, -errno on failure
*/
int fscrypt_fname_disk_to_usr(struct inode *inode,
@@ -274,7 +256,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
struct fscrypt_str *oname)
{
const struct qstr qname = FSTR_TO_QSTR(iname);
- char buf[24];
+ struct fscrypt_digested_name digested_name;
if (fscrypt_is_dot_dotdot(&qname)) {
oname->name[0] = '.';
@@ -289,77 +271,82 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
if (inode->i_crypt_info)
return fname_decrypt(inode, iname, oname);
- if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
+ if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) {
oname->len = digest_encode(iname->name, iname->len,
oname->name);
return 0;
}
if (hash) {
- memcpy(buf, &hash, 4);
- memcpy(buf + 4, &minor_hash, 4);
+ digested_name.hash = hash;
+ digested_name.minor_hash = minor_hash;
} else {
- memset(buf, 0, 8);
+ digested_name.hash = 0;
+ digested_name.minor_hash = 0;
}
- memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
+ memcpy(digested_name.digest,
+ FSCRYPT_FNAME_DIGEST(iname->name, iname->len),
+ FSCRYPT_FNAME_DIGEST_SIZE);
oname->name[0] = '_';
- oname->len = 1 + digest_encode(buf, 24, oname->name + 1);
+ oname->len = 1 + digest_encode((const char *)&digested_name,
+ sizeof(digested_name), oname->name + 1);
return 0;
}
EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
/**
- * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
- * space
+ * fscrypt_setup_filename() - prepare to search a possibly encrypted directory
+ * @dir: the directory that will be searched
+ * @iname: the user-provided filename being searched for
+ * @lookup: 1 if we're allowed to proceed without the key because it's
+ * ->lookup() or we're finding the dir_entry for deletion; 0 if we cannot
+ * proceed without the key because we're going to create the dir_entry.
+ * @fname: the filename information to be filled in
*
- * The caller must have allocated sufficient memory for the @oname string.
+ * Given a user-provided filename @iname, this function sets @fname->disk_name
+ * to the name that would be stored in the on-disk directory entry, if possible.
+ * If the directory is unencrypted this is simply @iname. Else, if we have the
+ * directory's encryption key, then @iname is the plaintext, so we encrypt it to
+ * get the disk_name.
+ *
+ * Else, for keyless @lookup operations, @iname is the presented ciphertext, so
+ * we decode it to get either the ciphertext disk_name (for short names) or the
+ * fscrypt_digested_name (for long names). Non-@lookup operations will be
+ * impossible in this case, so we fail them with ENOKEY.
+ *
+ * If successful, fscrypt_free_filename() must be called later to clean up.
*
* Return: 0 on success, -errno on failure
*/
-int fscrypt_fname_usr_to_disk(struct inode *inode,
- const struct qstr *iname,
- struct fscrypt_str *oname)
-{
- if (fscrypt_is_dot_dotdot(iname)) {
- oname->name[0] = '.';
- oname->name[iname->len - 1] = '.';
- oname->len = iname->len;
- return 0;
- }
- if (inode->i_crypt_info)
- return fname_encrypt(inode, iname, oname);
- /*
- * Without a proper key, a user is not allowed to modify the filenames
- * in a directory. Consequently, a user space name cannot be mapped to
- * a disk-space name
- */
- return -ENOKEY;
-}
-EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
-
int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
int lookup, struct fscrypt_name *fname)
{
- int ret = 0, bigname = 0;
+ int ret;
+ int digested;
memset(fname, 0, sizeof(struct fscrypt_name));
fname->usr_fname = iname;
- if (!dir->i_sb->s_cop->is_encrypted(dir) ||
- fscrypt_is_dot_dotdot(iname)) {
+ if (!IS_ENCRYPTED(dir) || fscrypt_is_dot_dotdot(iname)) {
fname->disk_name.name = (unsigned char *)iname->name;
fname->disk_name.len = iname->len;
return 0;
}
ret = fscrypt_get_encryption_info(dir);
- if (ret && ret != -EOPNOTSUPP)
+ if (ret)
return ret;
if (dir->i_crypt_info) {
- ret = fscrypt_fname_alloc_buffer(dir, iname->len,
- &fname->crypto_buf);
- if (ret)
- return ret;
- ret = fname_encrypt(dir, iname, &fname->crypto_buf);
+ if (!fscrypt_fname_encrypted_size(dir, iname->len,
+ dir->i_sb->s_cop->max_namelen,
+ &fname->crypto_buf.len))
+ return -ENAMETOOLONG;
+ fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,
+ GFP_NOFS);
+ if (!fname->crypto_buf.name)
+ return -ENOMEM;
+
+ ret = fname_encrypt(dir, iname, fname->crypto_buf.name,
+ fname->crypto_buf.len);
if (ret)
goto errout;
fname->disk_name.name = fname->crypto_buf.name;
@@ -373,25 +360,37 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
* We don't have the key and we are doing a lookup; decode the
* user-supplied name
*/
- if (iname->name[0] == '_')
- bigname = 1;
- if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
- return -ENOENT;
+ if (iname->name[0] == '_') {
+ if (iname->len !=
+ 1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)))
+ return -ENOENT;
+ digested = 1;
+ } else {
+ if (iname->len >
+ BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE))
+ return -ENOENT;
+ digested = 0;
+ }
- fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
+ fname->crypto_buf.name =
+ kmalloc(max_t(size_t, FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE,
+ sizeof(struct fscrypt_digested_name)),
+ GFP_KERNEL);
if (fname->crypto_buf.name == NULL)
return -ENOMEM;
- ret = digest_decode(iname->name + bigname, iname->len - bigname,
+ ret = digest_decode(iname->name + digested, iname->len - digested,
fname->crypto_buf.name);
if (ret < 0) {
ret = -ENOENT;
goto errout;
}
fname->crypto_buf.len = ret;
- if (bigname) {
- memcpy(&fname->hash, fname->crypto_buf.name, 4);
- memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
+ if (digested) {
+ const struct fscrypt_digested_name *n =
+ (const void *)fname->crypto_buf.name;
+ fname->hash = n->hash;
+ fname->minor_hash = n->minor_hash;
} else {
fname->disk_name.name = fname->crypto_buf.name;
fname->disk_name.len = fname->crypto_buf.len;
@@ -399,16 +398,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
return 0;
errout:
- fscrypt_fname_free_buffer(&fname->crypto_buf);
+ kfree(fname->crypto_buf.name);
return ret;
}
EXPORT_SYMBOL(fscrypt_setup_filename);
-
-void fscrypt_free_filename(struct fscrypt_name *fname)
-{
- kfree(fname->crypto_buf.name);
- fname->crypto_buf.name = NULL;
- fname->usr_fname = NULL;
- fname->disk_name.name = NULL;
-}
-EXPORT_SYMBOL(fscrypt_free_filename);
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
new file mode 100644
index 0000000..681963a
--- /dev/null
+++ b/fs/crypto/fscrypt_private.h
@@ -0,0 +1,174 @@
+/*
+ * fscrypt_private.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#ifndef _FSCRYPT_PRIVATE_H
+#define _FSCRYPT_PRIVATE_H
+
+#define __FS_HAS_ENCRYPTION 1
+#include <linux/fscrypt.h>
+#include <crypto/hash.h>
+
+/* Encryption parameters */
+#define FS_KEY_DERIVATION_NONCE_SIZE 16
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ * 1 byte: Protector format (1 = this version)
+ * 1 byte: File contents encryption mode
+ * 1 byte: File names encryption mode
+ * 1 byte: Flags
+ * 8 bytes: Master Key descriptor
+ * 16 bytes: Encryption Key derivation nonce
+ */
+struct fscrypt_context {
+ u8 format;
+ u8 contents_encryption_mode;
+ u8 filenames_encryption_mode;
+ u8 flags;
+ u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+} __packed;
+
+#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct fscrypt_symlink_data {
+ __le16 len;
+ char encrypted_path[1];
+} __packed;
+
+/*
+ * fscrypt_info - the "encryption key" for an inode
+ *
+ * When an encrypted file's key is made available, an instance of this struct is
+ * allocated and stored in ->i_crypt_info. Once created, it remains until the
+ * inode is evicted.
+ */
+struct fscrypt_info {
+
+ /* The actual crypto transform used for encryption and decryption */
+ struct crypto_skcipher *ci_ctfm;
+
+ /*
+ * Cipher for ESSIV IV generation. Only set for CBC contents
+ * encryption, otherwise is NULL.
+ */
+ struct crypto_cipher *ci_essiv_tfm;
+
+ /*
+ * Encryption mode used for this inode. It corresponds to either
+ * ci_data_mode or ci_filename_mode, depending on the inode type.
+ */
+ struct fscrypt_mode *ci_mode;
+
+ /*
+ * If non-NULL, then this inode uses a master key directly rather than a
+ * derived key, and ci_ctfm will equal ci_master_key->mk_ctfm.
+ * Otherwise, this inode uses a derived key.
+ */
+ struct fscrypt_master_key *ci_master_key;
+
+ /* fields from the fscrypt_context */
+ u8 ci_data_mode;
+ u8 ci_filename_mode;
+ u8 ci_flags;
+ u8 ci_master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+};
+
+typedef enum {
+ FS_DECRYPT = 0,
+ FS_ENCRYPT,
+} fscrypt_direction_t;
+
+#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
+#define FS_CTX_HAS_BOUNCE_BUFFER_FL 0x00000002
+
+static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
+ u32 filenames_mode)
+{
+ if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC &&
+ filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS)
+ return true;
+
+ if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS &&
+ filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS)
+ return true;
+
+ if (contents_mode == FS_ENCRYPTION_MODE_ADIANTUM &&
+ filenames_mode == FS_ENCRYPTION_MODE_ADIANTUM)
+ return true;
+
+ return false;
+}
+
+/* crypto.c */
+extern struct kmem_cache *fscrypt_info_cachep;
+extern int fscrypt_initialize(unsigned int cop_flags);
+extern int fscrypt_do_page_crypto(const struct inode *inode,
+ fscrypt_direction_t rw, u64 lblk_num,
+ struct page *src_page,
+ struct page *dest_page,
+ unsigned int len, unsigned int offs,
+ gfp_t gfp_flags);
+extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+ gfp_t gfp_flags);
+extern const struct dentry_operations fscrypt_d_ops;
+
+extern void __printf(3, 4) __cold
+fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+
+#define fscrypt_warn(sb, fmt, ...) \
+ fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define fscrypt_err(sb, fmt, ...) \
+ fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
+
+#define FSCRYPT_MAX_IV_SIZE 32
+
+union fscrypt_iv {
+ struct {
+ /* logical block number within the file */
+ __le64 lblk_num;
+
+ /* per-file nonce; only set in DIRECT_KEY mode */
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+ };
+ u8 raw[FSCRYPT_MAX_IV_SIZE];
+};
+
+void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
+ const struct fscrypt_info *ci);
+
+/* fname.c */
+extern int fname_encrypt(struct inode *inode, const struct qstr *iname,
+ u8 *out, unsigned int olen);
+extern bool fscrypt_fname_encrypted_size(const struct inode *inode,
+ u32 orig_len, u32 max_len,
+ u32 *encrypted_len_ret);
+
+/* keyinfo.c */
+
+struct fscrypt_mode {
+ const char *friendly_name;
+ const char *cipher_str;
+ int keysize;
+ int ivsize;
+ bool logged_impl_name;
+ bool needs_essiv;
+};
+
+extern void __exit fscrypt_essiv_cleanup(void);
+
+#endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
new file mode 100644
index 0000000..926e5df
--- /dev/null
+++ b/fs/crypto/hooks.c
@@ -0,0 +1,271 @@
+/*
+ * fs/crypto/hooks.c
+ *
+ * Encryption hooks for higher-level filesystem operations.
+ */
+
+#include <linux/ratelimit.h>
+#include "fscrypt_private.h"
+
+/**
+ * fscrypt_file_open - prepare to open a possibly-encrypted regular file
+ * @inode: the inode being opened
+ * @filp: the struct file being set up
+ *
+ * Currently, an encrypted regular file can only be opened if its encryption key
+ * is available; access to the raw encrypted contents is not supported.
+ * Therefore, we first set up the inode's encryption key (if not already done)
+ * and return an error if it's unavailable.
+ *
+ * We also verify that if the parent directory (from the path via which the file
+ * is being opened) is encrypted, then the inode being opened uses the same
+ * encryption policy. This is needed as part of the enforcement that all files
+ * in an encrypted directory tree use the same encryption policy, as a
+ * protection against certain types of offline attacks. Note that this check is
+ * needed even when opening an *unencrypted* file, since it's forbidden to have
+ * an unencrypted file in an encrypted directory.
+ *
+ * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
+ */
+int fscrypt_file_open(struct inode *inode, struct file *filp)
+{
+ int err;
+ struct dentry *dir;
+
+ err = fscrypt_require_key(inode);
+ if (err)
+ return err;
+
+ dir = dget_parent(file_dentry(filp));
+ if (IS_ENCRYPTED(d_inode(dir)) &&
+ !fscrypt_has_permitted_context(d_inode(dir), inode)) {
+ fscrypt_warn(inode->i_sb,
+ "inconsistent encryption contexts: %lu/%lu",
+ d_inode(dir)->i_ino, inode->i_ino);
+ err = -EPERM;
+ }
+ dput(dir);
+ return err;
+}
+EXPORT_SYMBOL_GPL(fscrypt_file_open);
+
+int __fscrypt_prepare_link(struct inode *inode, struct inode *dir)
+{
+ int err;
+
+ err = fscrypt_require_key(dir);
+ if (err)
+ return err;
+
+ if (!fscrypt_has_permitted_context(dir, inode))
+ return -EPERM;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_link);
+
+int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
+{
+ int err;
+
+ err = fscrypt_require_key(old_dir);
+ if (err)
+ return err;
+
+ err = fscrypt_require_key(new_dir);
+ if (err)
+ return err;
+
+ if (old_dir != new_dir) {
+ if (IS_ENCRYPTED(new_dir) &&
+ !fscrypt_has_permitted_context(new_dir,
+ d_inode(old_dentry)))
+ return -EPERM;
+
+ if ((flags & RENAME_EXCHANGE) &&
+ IS_ENCRYPTED(old_dir) &&
+ !fscrypt_has_permitted_context(old_dir,
+ d_inode(new_dentry)))
+ return -EPERM;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename);
+
+int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry)
+{
+ int err = fscrypt_get_encryption_info(dir);
+
+ if (err)
+ return err;
+
+ if (fscrypt_has_encryption_key(dir)) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+ spin_unlock(&dentry->d_lock);
+ }
+
+ d_set_d_op(dentry, &fscrypt_d_ops);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
+
+int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
+ unsigned int max_len,
+ struct fscrypt_str *disk_link)
+{
+ int err;
+
+ /*
+ * To calculate the size of the encrypted symlink target we need to know
+ * the amount of NUL padding, which is determined by the flags set in
+ * the encryption policy which will be inherited from the directory.
+ * The easiest way to get access to this is to just load the directory's
+ * fscrypt_info, since we'll need it to create the dir_entry anyway.
+ *
+ * Note: in test_dummy_encryption mode, @dir may be unencrypted.
+ */
+ err = fscrypt_get_encryption_info(dir);
+ if (err)
+ return err;
+ if (!fscrypt_has_encryption_key(dir))
+ return -ENOKEY;
+
+ /*
+ * Calculate the size of the encrypted symlink and verify it won't
+ * exceed max_len. Note that for historical reasons, encrypted symlink
+ * targets are prefixed with the ciphertext length, despite this
+ * actually being redundant with i_size. This decreases by 2 bytes the
+ * longest symlink target we can accept.
+ *
+ * We could recover 1 byte by not counting a null terminator, but
+ * counting it (even though it is meaningless for ciphertext) is simpler
+ * for now since filesystems will assume it is there and subtract it.
+ */
+ if (!fscrypt_fname_encrypted_size(dir, len,
+ max_len - sizeof(struct fscrypt_symlink_data),
+ &disk_link->len))
+ return -ENAMETOOLONG;
+ disk_link->len += sizeof(struct fscrypt_symlink_data);
+
+ disk_link->name = NULL;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_symlink);
+
+int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
+ unsigned int len, struct fscrypt_str *disk_link)
+{
+ int err;
+ struct qstr iname = QSTR_INIT(target, len);
+ struct fscrypt_symlink_data *sd;
+ unsigned int ciphertext_len;
+
+ err = fscrypt_require_key(inode);
+ if (err)
+ return err;
+
+ if (disk_link->name) {
+ /* filesystem-provided buffer */
+ sd = (struct fscrypt_symlink_data *)disk_link->name;
+ } else {
+ sd = kmalloc(disk_link->len, GFP_NOFS);
+ if (!sd)
+ return -ENOMEM;
+ }
+ ciphertext_len = disk_link->len - sizeof(*sd);
+ sd->len = cpu_to_le16(ciphertext_len);
+
+ err = fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len);
+ if (err) {
+ if (!disk_link->name)
+ kfree(sd);
+ return err;
+ }
+ /*
+ * Null-terminating the ciphertext doesn't make sense, but we still
+ * count the null terminator in the length, so we might as well
+ * initialize it just in case the filesystem writes it out.
+ */
+ sd->encrypted_path[ciphertext_len] = '\0';
+
+ if (!disk_link->name)
+ disk_link->name = (unsigned char *)sd;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
+
+/**
+ * fscrypt_get_symlink - get the target of an encrypted symlink
+ * @inode: the symlink inode
+ * @caddr: the on-disk contents of the symlink
+ * @max_size: size of @caddr buffer
+ * @done: if successful, will be set up to free the returned target
+ *
+ * If the symlink's encryption key is available, we decrypt its target.
+ * Otherwise, we encode its target for presentation.
+ *
+ * This may sleep, so the filesystem must have dropped out of RCU mode already.
+ *
+ * Return: the presentable symlink target or an ERR_PTR()
+ */
+const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
+ unsigned int max_size,
+ struct delayed_call *done)
+{
+ const struct fscrypt_symlink_data *sd;
+ struct fscrypt_str cstr, pstr;
+ int err;
+
+ /* This is for encrypted symlinks only */
+ if (WARN_ON(!IS_ENCRYPTED(inode)))
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * Try to set up the symlink's encryption key, but we can continue
+ * regardless of whether the key is available or not.
+ */
+ err = fscrypt_get_encryption_info(inode);
+ if (err)
+ return ERR_PTR(err);
+
+ /*
+ * For historical reasons, encrypted symlink targets are prefixed with
+ * the ciphertext length, even though this is redundant with i_size.
+ */
+
+ if (max_size < sizeof(*sd))
+ return ERR_PTR(-EUCLEAN);
+ sd = caddr;
+ cstr.name = (unsigned char *)sd->encrypted_path;
+ cstr.len = le16_to_cpu(sd->len);
+
+ if (cstr.len == 0)
+ return ERR_PTR(-EUCLEAN);
+
+ if (cstr.len + sizeof(*sd) - 1 > max_size)
+ return ERR_PTR(-EUCLEAN);
+
+ err = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
+ if (err)
+ return ERR_PTR(err);
+
+ err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
+ if (err)
+ goto err_kfree;
+
+ err = -EUCLEAN;
+ if (pstr.name[0] == '\0')
+ goto err_kfree;
+
+ pstr.name[pstr.len] = '\0';
+ set_delayed_call(done, kfree_link, pstr.name);
+ return pstr.name;
+
+err_kfree:
+ kfree(pstr.name);
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(fscrypt_get_symlink);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index a755fa1..98472a4 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -9,35 +9,35 @@
*/
#include <keys/user-type.h>
+#include <linux/hashtable.h>
#include <linux/scatterlist.h>
-#include <linux/fscrypto.h>
+#include <linux/ratelimit.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/sha.h>
+#include <crypto/skcipher.h>
+#include "fscrypt_private.h"
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
- struct fscrypt_completion_result *ecr = req->data;
+static struct crypto_shash *essiv_hash_tfm;
- if (rc == -EINPROGRESS)
- return;
+/* Table of keys referenced by FS_POLICY_FLAG_DIRECT_KEY policies */
+static DEFINE_HASHTABLE(fscrypt_master_keys, 6); /* 6 bits = 64 buckets */
+static DEFINE_SPINLOCK(fscrypt_master_keys_lock);
- ecr->res = rc;
- complete(&ecr->completion);
-}
-
-/**
- * derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivation.
- * @source_key: Source key to which to apply derivation.
- * @derived_key: Derived key.
+/*
+ * Key derivation function. This generates the derived key by encrypting the
+ * master key with AES-128-ECB using the inode's nonce as the AES key.
*
- * Return: Zero on success; non-zero otherwise.
+ * The master key must be at least as long as the derived key. If the master
+ * key is longer, then only the first 'derived_keysize' bytes are used.
*/
-static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
- u8 source_key[FS_AES_256_XTS_KEY_SIZE],
- u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+static int derive_key_aes(const u8 *master_key,
+ const struct fscrypt_context *ctx,
+ u8 *derived_key, unsigned int derived_keysize)
{
int res = 0;
struct skcipher_request *req = NULL;
- DECLARE_FS_COMPLETION_RESULT(ecr);
+ DECLARE_CRYPTO_WAIT(wait);
struct scatterlist src_sg, dst_sg;
struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
@@ -54,116 +54,436 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
}
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- derive_crypt_complete, &ecr);
- res = crypto_skcipher_setkey(tfm, deriving_key,
- FS_AES_128_ECB_KEY_SIZE);
+ crypto_req_done, &wait);
+ res = crypto_skcipher_setkey(tfm, ctx->nonce, sizeof(ctx->nonce));
if (res < 0)
goto out;
- sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
- sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
- skcipher_request_set_crypt(req, &src_sg, &dst_sg,
- FS_AES_256_XTS_KEY_SIZE, NULL);
- res = crypto_skcipher_encrypt(req);
- if (res == -EINPROGRESS || res == -EBUSY) {
- wait_for_completion(&ecr.completion);
- res = ecr.res;
- }
+ sg_init_one(&src_sg, master_key, derived_keysize);
+ sg_init_one(&dst_sg, derived_key, derived_keysize);
+ skcipher_request_set_crypt(req, &src_sg, &dst_sg, derived_keysize,
+ NULL);
+ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
out:
skcipher_request_free(req);
crypto_free_skcipher(tfm);
return res;
}
-static int validate_user_key(struct fscrypt_info *crypt_info,
- struct fscrypt_context *ctx, u8 *raw_key,
- u8 *prefix, int prefix_size)
+/*
+ * Search the current task's subscribed keyrings for a "logon" key with
+ * description prefix:descriptor, and if found acquire a read lock on it and
+ * return a pointer to its validated payload in *payload_ret.
+ */
+static struct key *
+find_and_lock_process_key(const char *prefix,
+ const u8 descriptor[FS_KEY_DESCRIPTOR_SIZE],
+ unsigned int min_keysize,
+ const struct fscrypt_key **payload_ret)
{
- u8 *full_key_descriptor;
- struct key *keyring_key;
- struct fscrypt_key *master_key;
+ char *description;
+ struct key *key;
const struct user_key_payload *ukp;
- int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
- int res;
+ const struct fscrypt_key *payload;
- full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
- if (!full_key_descriptor)
- return -ENOMEM;
+ description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
+ FS_KEY_DESCRIPTOR_SIZE, descriptor);
+ if (!description)
+ return ERR_PTR(-ENOMEM);
- memcpy(full_key_descriptor, prefix, prefix_size);
- sprintf(full_key_descriptor + prefix_size,
- "%*phN", FS_KEY_DESCRIPTOR_SIZE,
- ctx->master_key_descriptor);
- full_key_descriptor[full_key_len - 1] = '\0';
- keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
- kfree(full_key_descriptor);
- if (IS_ERR(keyring_key))
- return PTR_ERR(keyring_key);
- down_read(&keyring_key->sem);
+ key = request_key(&key_type_logon, description, NULL);
+ kfree(description);
+ if (IS_ERR(key))
+ return key;
- if (keyring_key->type != &key_type_logon) {
- printk_once(KERN_WARNING
- "%s: key type must be logon\n", __func__);
- res = -ENOKEY;
- goto out;
- }
- ukp = user_key_payload(keyring_key);
- if (!ukp) {
- /* key was revoked before we acquired its semaphore */
- res = -EKEYREVOKED;
- goto out;
- }
- if (ukp->datalen != sizeof(struct fscrypt_key)) {
- res = -EINVAL;
- goto out;
- }
- master_key = (struct fscrypt_key *)ukp->data;
- BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+ down_read(&key->sem);
+ ukp = user_key_payload_locked(key);
- if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
- printk_once(KERN_WARNING
- "%s: key size incorrect: %d\n",
- __func__, master_key->size);
- res = -ENOKEY;
- goto out;
+ if (!ukp) /* was the key revoked before we acquired its semaphore? */
+ goto invalid;
+
+ payload = (const struct fscrypt_key *)ukp->data;
+
+ if (ukp->datalen != sizeof(struct fscrypt_key) ||
+ payload->size < 1 || payload->size > FS_MAX_KEY_SIZE) {
+ fscrypt_warn(NULL,
+ "key with description '%s' has invalid payload",
+ key->description);
+ goto invalid;
}
- res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
-out:
- up_read(&keyring_key->sem);
- key_put(keyring_key);
- return res;
+
+ if (payload->size < min_keysize) {
+ fscrypt_warn(NULL,
+ "key with description '%s' is too short (got %u bytes, need %u+ bytes)",
+ key->description, payload->size, min_keysize);
+ goto invalid;
+ }
+
+ *payload_ret = payload;
+ return key;
+
+invalid:
+ up_read(&key->sem);
+ key_put(key);
+ return ERR_PTR(-ENOKEY);
}
-static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
- const char **cipher_str_ret, int *keysize_ret)
+static struct fscrypt_mode available_modes[] = {
+ [FS_ENCRYPTION_MODE_AES_256_XTS] = {
+ .friendly_name = "AES-256-XTS",
+ .cipher_str = "xts(aes)",
+ .keysize = 64,
+ .ivsize = 16,
+ },
+ [FS_ENCRYPTION_MODE_AES_256_CTS] = {
+ .friendly_name = "AES-256-CTS-CBC",
+ .cipher_str = "cts(cbc(aes))",
+ .keysize = 32,
+ .ivsize = 16,
+ },
+ [FS_ENCRYPTION_MODE_AES_128_CBC] = {
+ .friendly_name = "AES-128-CBC",
+ .cipher_str = "cbc(aes)",
+ .keysize = 16,
+ .ivsize = 16,
+ .needs_essiv = true,
+ },
+ [FS_ENCRYPTION_MODE_AES_128_CTS] = {
+ .friendly_name = "AES-128-CTS-CBC",
+ .cipher_str = "cts(cbc(aes))",
+ .keysize = 16,
+ .ivsize = 16,
+ },
+ [FS_ENCRYPTION_MODE_ADIANTUM] = {
+ .friendly_name = "Adiantum",
+ .cipher_str = "adiantum(xchacha12,aes)",
+ .keysize = 32,
+ .ivsize = 32,
+ },
+};
+
+static struct fscrypt_mode *
+select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode)
{
- if (S_ISREG(inode->i_mode)) {
- if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) {
- *cipher_str_ret = "xts(aes)";
- *keysize_ret = FS_AES_256_XTS_KEY_SIZE;
- return 0;
- }
- pr_warn_once("fscrypto: unsupported contents encryption mode "
- "%d for inode %lu\n",
- ci->ci_data_mode, inode->i_ino);
- return -ENOKEY;
+ if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
+ fscrypt_warn(inode->i_sb,
+ "inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)",
+ inode->i_ino, ci->ci_data_mode,
+ ci->ci_filename_mode);
+ return ERR_PTR(-EINVAL);
}
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
- if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) {
- *cipher_str_ret = "cts(cbc(aes))";
- *keysize_ret = FS_AES_256_CTS_KEY_SIZE;
- return 0;
+ if (S_ISREG(inode->i_mode))
+ return &available_modes[ci->ci_data_mode];
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ return &available_modes[ci->ci_filename_mode];
+
+ WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
+ inode->i_ino, (inode->i_mode & S_IFMT));
+ return ERR_PTR(-EINVAL);
+}
+
+/* Find the master key, then derive the inode's actual encryption key */
+static int find_and_derive_key(const struct inode *inode,
+ const struct fscrypt_context *ctx,
+ u8 *derived_key, const struct fscrypt_mode *mode)
+{
+ struct key *key;
+ const struct fscrypt_key *payload;
+ int err;
+
+ key = find_and_lock_process_key(FS_KEY_DESC_PREFIX,
+ ctx->master_key_descriptor,
+ mode->keysize, &payload);
+ if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) {
+ key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix,
+ ctx->master_key_descriptor,
+ mode->keysize, &payload);
+ }
+ if (IS_ERR(key))
+ return PTR_ERR(key);
+
+ if (ctx->flags & FS_POLICY_FLAG_DIRECT_KEY) {
+ if (mode->ivsize < offsetofend(union fscrypt_iv, nonce)) {
+ fscrypt_warn(inode->i_sb,
+ "direct key mode not allowed with %s",
+ mode->friendly_name);
+ err = -EINVAL;
+ } else if (ctx->contents_encryption_mode !=
+ ctx->filenames_encryption_mode) {
+ fscrypt_warn(inode->i_sb,
+ "direct key mode not allowed with different contents and filenames modes");
+ err = -EINVAL;
+ } else {
+ memcpy(derived_key, payload->raw, mode->keysize);
+ err = 0;
}
- pr_warn_once("fscrypto: unsupported filenames encryption mode "
- "%d for inode %lu\n",
- ci->ci_filename_mode, inode->i_ino);
- return -ENOKEY;
+ } else {
+ err = derive_key_aes(payload->raw, ctx, derived_key,
+ mode->keysize);
+ }
+ up_read(&key->sem);
+ key_put(key);
+ return err;
+}
+
+/* Allocate and key a symmetric cipher object for the given encryption mode */
+static struct crypto_skcipher *
+allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key,
+ const struct inode *inode)
+{
+ struct crypto_skcipher *tfm;
+ int err;
+
+ tfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0);
+ if (IS_ERR(tfm)) {
+ fscrypt_warn(inode->i_sb,
+ "error allocating '%s' transform for inode %lu: %ld",
+ mode->cipher_str, inode->i_ino, PTR_ERR(tfm));
+ return tfm;
+ }
+ if (unlikely(!mode->logged_impl_name)) {
+ /*
+ * fscrypt performance can vary greatly depending on which
+ * crypto algorithm implementation is used. Help people debug
+ * performance problems by logging the ->cra_driver_name the
+ * first time a mode is used. Note that multiple threads can
+ * race here, but it doesn't really matter.
+ */
+ mode->logged_impl_name = true;
+ pr_info("fscrypt: %s using implementation \"%s\"\n",
+ mode->friendly_name,
+ crypto_skcipher_alg(tfm)->base.cra_driver_name);
+ }
+ crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+ err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize);
+ if (err)
+ goto err_free_tfm;
+
+ return tfm;
+
+err_free_tfm:
+ crypto_free_skcipher(tfm);
+ return ERR_PTR(err);
+}
+
+/* Master key referenced by FS_POLICY_FLAG_DIRECT_KEY policy */
+struct fscrypt_master_key {
+ struct hlist_node mk_node;
+ atomic_t mk_refcount;
+ const struct fscrypt_mode *mk_mode;
+ struct crypto_skcipher *mk_ctfm;
+ u8 mk_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ u8 mk_raw[FS_MAX_KEY_SIZE];
+};
+
+static void free_master_key(struct fscrypt_master_key *mk)
+{
+ if (mk) {
+ crypto_free_skcipher(mk->mk_ctfm);
+ kzfree(mk);
+ }
+}
+
+static void put_master_key(struct fscrypt_master_key *mk)
+{
+ if (!atomic_dec_and_lock(&mk->mk_refcount, &fscrypt_master_keys_lock))
+ return;
+ hash_del(&mk->mk_node);
+ spin_unlock(&fscrypt_master_keys_lock);
+
+ free_master_key(mk);
+}
+
+/*
+ * Find/insert the given master key into the fscrypt_master_keys table. If
+ * found, it is returned with elevated refcount, and 'to_insert' is freed if
+ * non-NULL. If not found, 'to_insert' is inserted and returned if it's
+ * non-NULL; otherwise NULL is returned.
+ */
+static struct fscrypt_master_key *
+find_or_insert_master_key(struct fscrypt_master_key *to_insert,
+ const u8 *raw_key, const struct fscrypt_mode *mode,
+ const struct fscrypt_info *ci)
+{
+ unsigned long hash_key;
+ struct fscrypt_master_key *mk;
+
+ /*
+ * Careful: to avoid potentially leaking secret key bytes via timing
+ * information, we must key the hash table by descriptor rather than by
+ * raw key, and use crypto_memneq() when comparing raw keys.
+ */
+
+ BUILD_BUG_ON(sizeof(hash_key) > FS_KEY_DESCRIPTOR_SIZE);
+ memcpy(&hash_key, ci->ci_master_key_descriptor, sizeof(hash_key));
+
+ spin_lock(&fscrypt_master_keys_lock);
+ hash_for_each_possible(fscrypt_master_keys, mk, mk_node, hash_key) {
+ if (memcmp(ci->ci_master_key_descriptor, mk->mk_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE) != 0)
+ continue;
+ if (mode != mk->mk_mode)
+ continue;
+ if (crypto_memneq(raw_key, mk->mk_raw, mode->keysize))
+ continue;
+ /* using existing tfm with same (descriptor, mode, raw_key) */
+ atomic_inc(&mk->mk_refcount);
+ spin_unlock(&fscrypt_master_keys_lock);
+ free_master_key(to_insert);
+ return mk;
+ }
+ if (to_insert)
+ hash_add(fscrypt_master_keys, &to_insert->mk_node, hash_key);
+ spin_unlock(&fscrypt_master_keys_lock);
+ return to_insert;
+}
+
+/* Prepare to encrypt directly using the master key in the given mode */
+static struct fscrypt_master_key *
+fscrypt_get_master_key(const struct fscrypt_info *ci, struct fscrypt_mode *mode,
+ const u8 *raw_key, const struct inode *inode)
+{
+ struct fscrypt_master_key *mk;
+ int err;
+
+ /* Is there already a tfm for this key? */
+ mk = find_or_insert_master_key(NULL, raw_key, mode, ci);
+ if (mk)
+ return mk;
+
+ /* Nope, allocate one. */
+ mk = kzalloc(sizeof(*mk), GFP_NOFS);
+ if (!mk)
+ return ERR_PTR(-ENOMEM);
+ atomic_set(&mk->mk_refcount, 1);
+ mk->mk_mode = mode;
+ mk->mk_ctfm = allocate_skcipher_for_mode(mode, raw_key, inode);
+ if (IS_ERR(mk->mk_ctfm)) {
+ err = PTR_ERR(mk->mk_ctfm);
+ mk->mk_ctfm = NULL;
+ goto err_free_mk;
+ }
+ memcpy(mk->mk_descriptor, ci->ci_master_key_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE);
+ memcpy(mk->mk_raw, raw_key, mode->keysize);
+
+ return find_or_insert_master_key(mk, raw_key, mode, ci);
+
+err_free_mk:
+ free_master_key(mk);
+ return ERR_PTR(err);
+}
+
+static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
+{
+ struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm);
+
+ /* init hash transform on demand */
+ if (unlikely(!tfm)) {
+ struct crypto_shash *prev_tfm;
+
+ tfm = crypto_alloc_shash("sha256", 0, 0);
+ if (IS_ERR(tfm)) {
+ fscrypt_warn(NULL,
+ "error allocating SHA-256 transform: %ld",
+ PTR_ERR(tfm));
+ return PTR_ERR(tfm);
+ }
+ prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
+ if (prev_tfm) {
+ crypto_free_shash(tfm);
+ tfm = prev_tfm;
+ }
}
- pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n",
- (inode->i_mode & S_IFMT), inode->i_ino);
- return -ENOKEY;
+ {
+ SHASH_DESC_ON_STACK(desc, tfm);
+ desc->tfm = tfm;
+ desc->flags = 0;
+
+ return crypto_shash_digest(desc, key, keysize, salt);
+ }
+}
+
+static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key,
+ int keysize)
+{
+ int err;
+ struct crypto_cipher *essiv_tfm;
+ u8 salt[SHA256_DIGEST_SIZE];
+
+ essiv_tfm = crypto_alloc_cipher("aes", 0, 0);
+ if (IS_ERR(essiv_tfm))
+ return PTR_ERR(essiv_tfm);
+
+ ci->ci_essiv_tfm = essiv_tfm;
+
+ err = derive_essiv_salt(raw_key, keysize, salt);
+ if (err)
+ goto out;
+
+ /*
+ * Using SHA256 to derive the salt/key will result in AES-256 being
+ * used for IV generation. File contents encryption will still use the
+ * configured keysize (AES-128) nevertheless.
+ */
+ err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt));
+ if (err)
+ goto out;
+
+out:
+ memzero_explicit(salt, sizeof(salt));
+ return err;
+}
+
+void __exit fscrypt_essiv_cleanup(void)
+{
+ crypto_free_shash(essiv_hash_tfm);
+}
+
+/*
+ * Given the encryption mode and key (normally the derived key, but for
+ * FS_POLICY_FLAG_DIRECT_KEY mode it's the master key), set up the inode's
+ * symmetric cipher transform object(s).
+ */
+static int setup_crypto_transform(struct fscrypt_info *ci,
+ struct fscrypt_mode *mode,
+ const u8 *raw_key, const struct inode *inode)
+{
+ struct fscrypt_master_key *mk;
+ struct crypto_skcipher *ctfm;
+ int err;
+
+ if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) {
+ mk = fscrypt_get_master_key(ci, mode, raw_key, inode);
+ if (IS_ERR(mk))
+ return PTR_ERR(mk);
+ ctfm = mk->mk_ctfm;
+ } else {
+ mk = NULL;
+ ctfm = allocate_skcipher_for_mode(mode, raw_key, inode);
+ if (IS_ERR(ctfm))
+ return PTR_ERR(ctfm);
+ }
+ ci->ci_master_key = mk;
+ ci->ci_ctfm = ctfm;
+
+ if (mode->needs_essiv) {
+ /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */
+ WARN_ON(mode->ivsize != AES_BLOCK_SIZE);
+ WARN_ON(ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY);
+
+ err = init_essiv_generator(ci, raw_key, mode->keysize);
+ if (err) {
+ fscrypt_warn(inode->i_sb,
+ "error initializing ESSIV generator for inode %lu: %d",
+ inode->i_ino, err);
+ return err;
+ }
+ }
+ return 0;
}
static void put_crypt_info(struct fscrypt_info *ci)
@@ -171,7 +491,12 @@ static void put_crypt_info(struct fscrypt_info *ci)
if (!ci)
return;
- crypto_free_skcipher(ci->ci_ctfm);
+ if (ci->ci_master_key) {
+ put_master_key(ci->ci_master_key);
+ } else {
+ crypto_free_skcipher(ci->ci_ctfm);
+ crypto_free_cipher(ci->ci_essiv_tfm);
+ }
kmem_cache_free(fscrypt_info_cachep, ci);
}
@@ -179,30 +504,28 @@ int fscrypt_get_encryption_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
struct fscrypt_context ctx;
- struct crypto_skcipher *ctfm;
- const char *cipher_str;
- int keysize;
+ struct fscrypt_mode *mode;
u8 *raw_key = NULL;
int res;
if (inode->i_crypt_info)
return 0;
- res = fscrypt_initialize();
+ res = fscrypt_initialize(inode->i_sb->s_cop->flags);
if (res)
return res;
- if (!inode->i_sb->s_cop->get_context)
- return -EOPNOTSUPP;
-
res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
if (res < 0) {
- if (!fscrypt_dummy_context_enabled(inode))
+ if (!fscrypt_dummy_context_enabled(inode) ||
+ IS_ENCRYPTED(inode))
return res;
+ /* Fake up a context for an unencrypted directory */
+ memset(&ctx, 0, sizeof(ctx));
ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
- ctx.flags = 0;
+ memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
} else if (res != sizeof(ctx)) {
return -EINVAL;
}
@@ -213,65 +536,39 @@ int fscrypt_get_encryption_info(struct inode *inode)
if (ctx.flags & ~FS_POLICY_FLAGS_VALID)
return -EINVAL;
- crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS);
+ crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS);
if (!crypt_info)
return -ENOMEM;
crypt_info->ci_flags = ctx.flags;
crypt_info->ci_data_mode = ctx.contents_encryption_mode;
crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
- crypt_info->ci_ctfm = NULL;
- memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
- sizeof(crypt_info->ci_master_key));
+ memcpy(crypt_info->ci_master_key_descriptor, ctx.master_key_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE);
+ memcpy(crypt_info->ci_nonce, ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
- res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
- if (res)
+ mode = select_encryption_mode(crypt_info, inode);
+ if (IS_ERR(mode)) {
+ res = PTR_ERR(mode);
goto out;
+ }
+ WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE);
+ crypt_info->ci_mode = mode;
/*
- * This cannot be a stack buffer because it is passed to the scatterlist
- * crypto API as part of key derivation.
+ * This cannot be a stack buffer because it may be passed to the
+ * scatterlist crypto API as part of key derivation.
*/
res = -ENOMEM;
- raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+ raw_key = kmalloc(mode->keysize, GFP_NOFS);
if (!raw_key)
goto out;
- if (fscrypt_dummy_context_enabled(inode)) {
- memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
- goto got_key;
- }
-
- res = validate_user_key(crypt_info, &ctx, raw_key,
- FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
- if (res && inode->i_sb->s_cop->key_prefix) {
- u8 *prefix = NULL;
- int prefix_size, res2;
-
- prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
- res2 = validate_user_key(crypt_info, &ctx, raw_key,
- prefix, prefix_size);
- if (res2) {
- if (res2 == -ENOKEY)
- res = -ENOKEY;
- goto out;
- }
- } else if (res) {
+ res = find_and_derive_key(inode, &ctx, raw_key, mode);
+ if (res)
goto out;
- }
-got_key:
- ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
- if (!ctfm || IS_ERR(ctfm)) {
- res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
- printk(KERN_DEBUG
- "%s: error %d (inode %u) allocating crypto tfm\n",
- __func__, res, (unsigned) inode->i_ino);
- goto out;
- }
- crypt_info->ci_ctfm = ctfm;
- crypto_skcipher_clear_flags(ctfm, ~0);
- crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
- res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
+
+ res = setup_crypto_transform(crypt_info, mode, raw_key, inode);
if (res)
goto out;
@@ -286,19 +583,9 @@ int fscrypt_get_encryption_info(struct inode *inode)
}
EXPORT_SYMBOL(fscrypt_get_encryption_info);
-void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+void fscrypt_put_encryption_info(struct inode *inode)
{
- struct fscrypt_info *prev;
-
- if (ci == NULL)
- ci = ACCESS_ONCE(inode->i_crypt_info);
- if (ci == NULL)
- return;
-
- prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
- if (prev != ci)
- return;
-
- put_crypt_info(ci);
+ put_crypt_info(inode->i_crypt_info);
+ inode->i_crypt_info = NULL;
}
EXPORT_SYMBOL(fscrypt_put_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 2bf6e0a..caba7e8 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -10,76 +10,37 @@
#include <linux/random.h>
#include <linux/string.h>
-#include <linux/fscrypto.h>
#include <linux/mount.h>
-
-static int inode_has_encryption_context(struct inode *inode)
-{
- if (!inode->i_sb->s_cop->get_context)
- return 0;
- return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
-}
+#include "fscrypt_private.h"
/*
- * check whether the policy is consistent with the encryption context
- * for the inode
+ * check whether an encryption policy is consistent with an encryption context
*/
-static int is_encryption_context_consistent_with_policy(struct inode *inode,
+static bool is_encryption_context_consistent_with_policy(
+ const struct fscrypt_context *ctx,
const struct fscrypt_policy *policy)
{
- struct fscrypt_context ctx;
- int res;
-
- if (!inode->i_sb->s_cop->get_context)
- return 0;
-
- res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
- if (res != sizeof(ctx))
- return 0;
-
- return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
- FS_KEY_DESCRIPTOR_SIZE) == 0 &&
- (ctx.flags == policy->flags) &&
- (ctx.contents_encryption_mode ==
- policy->contents_encryption_mode) &&
- (ctx.filenames_encryption_mode ==
- policy->filenames_encryption_mode));
+ return memcmp(ctx->master_key_descriptor, policy->master_key_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (ctx->flags == policy->flags) &&
+ (ctx->contents_encryption_mode ==
+ policy->contents_encryption_mode) &&
+ (ctx->filenames_encryption_mode ==
+ policy->filenames_encryption_mode);
}
static int create_encryption_context_from_policy(struct inode *inode,
const struct fscrypt_policy *policy)
{
struct fscrypt_context ctx;
- int res;
-
- if (!inode->i_sb->s_cop->set_context)
- return -EOPNOTSUPP;
-
- if (inode->i_sb->s_cop->prepare_context) {
- res = inode->i_sb->s_cop->prepare_context(inode);
- if (res)
- return res;
- }
ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
FS_KEY_DESCRIPTOR_SIZE);
- if (!fscrypt_valid_contents_enc_mode(
- policy->contents_encryption_mode)) {
- printk(KERN_WARNING
- "%s: Invalid contents encryption mode %d\n", __func__,
- policy->contents_encryption_mode);
+ if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+ policy->filenames_encryption_mode))
return -EINVAL;
- }
-
- if (!fscrypt_valid_filenames_enc_mode(
- policy->filenames_encryption_mode)) {
- printk(KERN_WARNING
- "%s: Invalid filenames encryption mode %d\n", __func__,
- policy->filenames_encryption_mode);
- return -EINVAL;
- }
if (policy->flags & ~FS_POLICY_FLAGS_VALID)
return -EINVAL;
@@ -98,6 +59,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
int ret;
+ struct fscrypt_context ctx;
if (copy_from_user(&policy, arg, sizeof(policy)))
return -EFAULT;
@@ -114,23 +76,24 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
inode_lock(inode);
- if (!inode_has_encryption_context(inode)) {
+ ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (ret == -ENODATA) {
if (!S_ISDIR(inode->i_mode))
ret = -ENOTDIR;
else if (IS_DEADDIR(inode))
ret = -ENOENT;
- else if (!inode->i_sb->s_cop->empty_dir)
- ret = -EOPNOTSUPP;
else if (!inode->i_sb->s_cop->empty_dir(inode))
ret = -ENOTEMPTY;
else
ret = create_encryption_context_from_policy(inode,
&policy);
- } else if (!is_encryption_context_consistent_with_policy(inode,
- &policy)) {
- printk(KERN_WARNING
- "%s: Policy inconsistent with encryption context\n",
- __func__);
+ } else if (ret == sizeof(ctx) &&
+ is_encryption_context_consistent_with_policy(&ctx,
+ &policy)) {
+ /* The file already uses the same encryption policy. */
+ ret = 0;
+ } else if (ret >= 0 || ret == -ERANGE) {
+ /* The file already uses a different encryption policy. */
ret = -EEXIST;
}
@@ -148,13 +111,14 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
struct fscrypt_policy policy;
int res;
- if (!inode->i_sb->s_cop->get_context ||
- !inode->i_sb->s_cop->is_encrypted(inode))
+ if (!IS_ENCRYPTED(inode))
return -ENODATA;
res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (res < 0 && res != -ERANGE)
+ return res;
if (res != sizeof(ctx))
- return -ENODATA;
+ return -EINVAL;
if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
return -EINVAL;
@@ -203,11 +167,11 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
return 1;
/* No restrictions if the parent directory is unencrypted */
- if (!cops->is_encrypted(parent))
+ if (!IS_ENCRYPTED(parent))
return 1;
/* Encrypted directories must not contain unencrypted files */
- if (!cops->is_encrypted(child))
+ if (!IS_ENCRYPTED(child))
return 0;
/*
@@ -235,7 +199,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
child_ci = child->i_crypt_info;
if (parent_ci && child_ci) {
- return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+ return memcmp(parent_ci->ci_master_key_descriptor,
+ child_ci->ci_master_key_descriptor,
FS_KEY_DESCRIPTOR_SIZE) == 0 &&
(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
(parent_ci->ci_filename_mode ==
@@ -267,9 +232,9 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
* @parent: Parent inode from which the context is inherited.
* @child: Child inode that inherits the context from @parent.
* @fs_data: private data given by FS.
- * @preload: preload child i_crypt_info
+ * @preload: preload child i_crypt_info if true
*
- * Return: Zero on success, non-zero otherwise
+ * Return: 0 on success, -errno on failure
*/
int fscrypt_inherit_context(struct inode *parent, struct inode *child,
void *fs_data, bool preload)
@@ -278,9 +243,6 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
struct fscrypt_info *ci;
int res;
- if (!parent->i_sb->s_cop->set_context)
- return -EOPNOTSUPP;
-
res = fscrypt_get_encryption_info(parent);
if (res < 0)
return res;
@@ -290,19 +252,11 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
return -ENOKEY;
ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
- if (fscrypt_dummy_context_enabled(parent)) {
- ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
- ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
- ctx.flags = 0;
- memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
- res = 0;
- } else {
- ctx.contents_encryption_mode = ci->ci_data_mode;
- ctx.filenames_encryption_mode = ci->ci_filename_mode;
- ctx.flags = ci->ci_flags;
- memcpy(ctx.master_key_descriptor, ci->ci_master_key,
- FS_KEY_DESCRIPTOR_SIZE);
- }
+ ctx.contents_encryption_mode = ci->ci_data_mode;
+ ctx.filenames_encryption_mode = ci->ci_filename_mode;
+ ctx.flags = ci->ci_flags;
+ memcpy(ctx.master_key_descriptor, ci->ci_master_key_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE);
get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
res = parent->i_sb->s_cop->set_context(child, &ctx,
sizeof(ctx), fs_data);
diff --git a/fs/dcache.c b/fs/dcache.c
index 05bad55..426fe9b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3251,6 +3251,7 @@ char *d_absolute_path(const struct path *path,
return ERR_PTR(error);
return res;
}
+EXPORT_SYMBOL(d_absolute_path);
/*
* same as __d_path but appends "(deleted)" for unlinked files.
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index a896e46..d4d8ad1 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -125,7 +125,7 @@ ecryptfs_get_key_payload_data(struct key *key)
if (auth_tok)
return auth_tok;
- ukp = user_key_payload(key);
+ ukp = user_key_payload_locked(key);
if (!ukp)
return ERR_PTR(-EKEYREVOKED);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 865afb5..bb3f4be 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,6 +34,7 @@
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <linux/device.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/mman.h>
@@ -1671,7 +1672,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
}
spin_unlock_irqrestore(&ep->lock, flags);
- if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
+ if (!freezable_schedule_hrtimeout_range(to, slack,
+ HRTIMER_MODE_ABS))
timed_out = 1;
spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/exec.c b/fs/exec.c
index 319a1f5..4e17643 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1305,7 +1305,7 @@ EXPORT_SYMBOL(flush_old_exec);
void would_dump(struct linux_binprm *bprm, struct file *file)
{
struct inode *inode = file_inode(file);
- if (inode_permission(inode, MAY_READ) < 0) {
+ if (inode_permission2(file->f_path.mnt, inode, MAY_READ) < 0) {
struct user_namespace *old, *user_ns;
bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index d8072bc..7f5b735 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -377,9 +377,8 @@ static int read_exec(struct page_collect *pcol)
* and will start a new collection. Eventually caller must submit the last
* segment if present.
*/
-static int readpage_strip(void *data, struct page *page)
+static int __readpage_strip(struct page_collect *pcol, struct page *page)
{
- struct page_collect *pcol = data;
struct inode *inode = pcol->inode;
struct exofs_i_info *oi = exofs_i(inode);
loff_t i_size = i_size_read(inode);
@@ -470,6 +469,13 @@ static int readpage_strip(void *data, struct page *page)
return ret;
}
+static int readpage_strip(struct file *data, struct page *page)
+{
+ struct page_collect *pcol = (struct page_collect *)data;
+
+ return __readpage_strip(pcol, page);
+}
+
static int exofs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
@@ -499,7 +505,7 @@ static int _readpage(struct page *page, bool read_4_write)
_pcol_init(&pcol, 1, page->mapping->host);
pcol.read_4_write = read_4_write;
- ret = readpage_strip(&pcol, page);
+ ret = __readpage_strip(&pcol, page);
if (ret) {
EXOFS_ERR("_readpage => %d\n", ret);
return ret;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 54a7f3b..abd6371 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -32,13 +32,15 @@
#include <linux/percpu_counter.h>
#include <linux/ratelimit.h>
#include <crypto/hash.h>
-#include <linux/fscrypto.h>
#include <linux/falloc.h>
#include <linux/percpu-rwsem.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
+#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION)
+#include <linux/fscrypt.h>
+
/*
* The fourth extended filesystem constants/structures
*/
@@ -1342,11 +1344,6 @@ struct ext4_super_block {
/* Number of quota types we support */
#define EXT4_MAXQUOTAS 3
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-#define EXT4_KEY_DESC_PREFIX "ext4:"
-#define EXT4_KEY_DESC_PREFIX_SIZE 5
-#endif
-
/*
* fourth extended-fs super-block data in memory
*/
@@ -1519,12 +1516,6 @@ struct ext4_sb_info {
* or EXTENTS flag.
*/
struct percpu_rw_semaphore s_writepages_rwsem;
-
- /* Encryption support */
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- u8 key_prefix[EXT4_KEY_DESC_PREFIX_SIZE];
- u8 key_prefix_size;
-#endif
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2292,11 +2283,6 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
-static inline int ext4_sb_has_crypto(struct super_block *sb)
-{
- return ext4_has_feature_encrypt(sb);
-}
-
static inline bool ext4_encrypted_inode(struct inode *inode)
{
return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
@@ -2345,28 +2331,6 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
}
static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk fscrypt_notsupp_fname_usr_to_disk
#endif
/* dir.c */
@@ -2388,11 +2352,10 @@ extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
void *buf, int buf_size,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de);
-int ext4_insert_dentry(struct inode *dir,
- struct inode *inode,
- struct ext4_dir_entry_2 *de,
- int buf_size,
- struct ext4_filename *fname);
+void ext4_insert_dentry(struct inode *inode,
+ struct ext4_dir_entry_2 *de,
+ int buf_size,
+ struct ext4_filename *fname);
static inline void ext4_update_dx_flag(struct inode *inode)
{
if (!ext4_has_feature_dir_index(inode->i_sb) &&
@@ -2402,7 +2365,7 @@ static inline void ext4_update_dx_flag(struct inode *inode)
ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
}
}
-static unsigned char ext4_filetype_table[] = {
+static const unsigned char ext4_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
@@ -2469,7 +2432,8 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count);
-extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *,
+ unsigned long blkdev_flags);
/* inode.c */
int ext4_inode_is_fast_symlink(struct inode *inode);
@@ -3098,7 +3062,7 @@ extern int ext4_handle_dirty_dirent_node(handle_t *handle,
struct inode *inode,
struct buffer_head *bh);
#define S_SHIFT 12
-static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+static const unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = EXT4_FT_DIR,
[S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV,
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 2b699b1..2dda41e 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1077,6 +1077,17 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
if (err)
goto fail_drop;
+ /*
+ * Since the encryption xattr will always be unique, create it first so
+ * that it's less likely to end up in an external xattr block and
+ * prevent its deduplication.
+ */
+ if (encrypt) {
+ err = fscrypt_inherit_context(dir, inode, handle, true);
+ if (err)
+ goto fail_free_drop;
+ }
+
err = ext4_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
@@ -1098,13 +1109,6 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
ei->i_datasync_tid = handle->h_transaction->t_tid;
}
- if (encrypt) {
- /* give pointer to avoid set_context with journal ops. */
- err = fscrypt_inherit_context(dir, inode, &encrypt, true);
- if (err)
- goto fail_free_drop;
- }
-
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 5bf62bd..28c53b8 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -18,6 +18,7 @@
#include "ext4.h"
#include "xattr.h"
#include "truncate.h"
+#include <trace/events/android_fs.h>
#define EXT4_XATTR_SYSTEM_DATA "data"
#define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS))
@@ -502,6 +503,17 @@ int ext4_readpage_inline(struct inode *inode, struct page *page)
return -EAGAIN;
}
+ if (trace_android_fs_dataread_start_enabled()) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_dataread_start(inode, page_offset(page),
+ PAGE_SIZE, current->pid,
+ path, current->comm);
+ }
+
/*
* Current inline data can only exist in the 1st page,
* So for all the other pages, just set them uptodate.
@@ -513,6 +525,8 @@ int ext4_readpage_inline(struct inode *inode, struct page *page)
SetPageUptodate(page);
}
+ trace_android_fs_dataread_end(inode, page_offset(page), PAGE_SIZE);
+
up_read(&EXT4_I(inode)->xattr_sem);
unlock_page(page);
@@ -1028,7 +1042,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
- ext4_insert_dentry(dir, inode, de, inline_size, fname);
+ ext4_insert_dentry(inode, de, inline_size, fname);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ccce89d..0f671ef7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -44,6 +44,7 @@
#include "truncate.h"
#include <trace/events/ext4.h>
+#include <trace/events/android_fs.h>
#define MPAGE_DA_EXTENT_TAIL 0x01
@@ -1169,7 +1170,8 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
if (unlikely(err))
page_zero_new_buffers(page, from, to);
else if (decrypt)
- err = fscrypt_decrypt_page(page);
+ err = fscrypt_decrypt_page(page->mapping->host, page,
+ PAGE_SIZE, 0, page->index);
return err;
}
#endif
@@ -1186,6 +1188,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
pgoff_t index;
unsigned from, to;
+ if (trace_android_fs_datawrite_start_enabled()) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_datawrite_start(inode, pos, len,
+ current->pid, path,
+ current->comm);
+ }
trace_ext4_write_begin(inode, pos, len, flags);
/*
* Reserve one block more for addition to orphan list in case
@@ -1324,6 +1336,7 @@ static int ext4_write_end(struct file *file,
int i_size_changed = 0;
int inline_data = ext4_has_inline_data(inode);
+ trace_android_fs_datawrite_end(inode, pos, len);
trace_ext4_write_end(inode, pos, len, copied);
if (inline_data) {
ret = ext4_write_inline_data_end(inode, pos, len,
@@ -1429,6 +1442,7 @@ static int ext4_journalled_write_end(struct file *file,
int size_changed = 0;
int inline_data = ext4_has_inline_data(inode);
+ trace_android_fs_datawrite_end(inode, pos, len);
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
to = from + len;
@@ -2557,8 +2571,8 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
mpd->map.m_len = 0;
mpd->next_page = index;
while (index <= end) {
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag);
if (nr_pages == 0)
goto out;
@@ -2566,16 +2580,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
struct page *page = pvec.pages[i];
/*
- * At this point, the page may be truncated or
- * invalidated (changing page->mapping to NULL), or
- * even swizzled back from swapper_space to tmpfs file
- * mapping. However, page->index will not change
- * because we have a reference on the page.
- */
- if (page->index > end)
- goto out;
-
- /*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to
* keep going because someone may be concurrently
@@ -2926,6 +2930,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
len, flags, pagep, fsdata);
}
*fsdata = (void *)0;
+ if (trace_android_fs_datawrite_start_enabled()) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_datawrite_start(inode, pos, len,
+ current->pid,
+ path, current->comm);
+ }
trace_ext4_da_write_begin(inode, pos, len, flags);
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -3044,6 +3058,7 @@ static int ext4_da_write_end(struct file *file,
return ext4_write_end(file, mapping, pos,
len, copied, page, fsdata);
+ trace_android_fs_datawrite_end(inode, pos, len);
trace_ext4_da_write_end(inode, pos, len, copied);
start = pos & (PAGE_SIZE - 1);
end = start + copied - 1;
@@ -3612,6 +3627,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
ssize_t ret;
+ int rw = iov_iter_rw(iter);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -3628,12 +3644,42 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (ext4_has_inline_data(inode))
return 0;
+ if (trace_android_fs_dataread_start_enabled() &&
+ (rw == READ)) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_dataread_start(inode, offset, count,
+ current->pid, path,
+ current->comm);
+ }
+ if (trace_android_fs_datawrite_start_enabled() &&
+ (rw == WRITE)) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_datawrite_start(inode, offset, count,
+ current->pid, path,
+ current->comm);
+ }
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
if (iov_iter_rw(iter) == READ)
ret = ext4_direct_IO_read(iocb, iter);
else
ret = ext4_direct_IO_write(iocb, iter);
trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
+
+ if (trace_android_fs_dataread_start_enabled() &&
+ (rw == READ))
+ trace_android_fs_dataread_end(inode, offset, count);
+ if (trace_android_fs_datawrite_start_enabled() &&
+ (rw == WRITE))
+ trace_android_fs_datawrite_end(inode, offset, count);
+
return ret;
}
@@ -3784,7 +3830,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
BUG_ON(blocksize != PAGE_SIZE);
- WARN_ON_ONCE(fscrypt_decrypt_page(page));
+ WARN_ON_ONCE(fscrypt_decrypt_page(page->mapping->host,
+ page, PAGE_SIZE, 0, page->index));
}
}
if (ext4_should_journal_data(inode)) {
@@ -4411,8 +4458,11 @@ void ext4_set_inode_flags(struct inode *inode)
new_fl |= S_DIRSYNC;
if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
new_fl |= S_DAX;
+ if (flags & EXT4_ENCRYPT_FL)
+ new_fl |= S_ENCRYPTED;
inode_set_flags(inode, new_fl,
- S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
+ S_ENCRYPTED);
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 75fff70..f983e79 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -191,6 +191,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
return err;
}
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int uuid_is_zero(__u8 u[16])
{
int i;
@@ -200,6 +201,7 @@ static int uuid_is_zero(__u8 u[16])
return 0;
return 1;
}
+#endif
static int ext4_ioctl_setflags(struct inode *inode,
unsigned int flags)
@@ -737,11 +739,13 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return err;
}
+ case FIDTRIM:
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
+ int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -749,6 +753,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
+ if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secure_erase(q))
+ return -EOPNOTSUPP;
+
/*
* We haven't replayed the journal, so we cannot use our
* block-bitmap-guided storage zapping commands.
@@ -762,7 +769,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
- ret = ext4_trim_fs(sb, &range);
+ ret = ext4_trim_fs(sb, &range, flags);
if (ret < 0)
return ret;
@@ -781,11 +788,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
- if (!ext4_sb_has_crypto(sb))
+ if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
@@ -818,6 +826,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
}
case EXT4_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
@@ -827,7 +838,6 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
- ext4_get_inode_flags(ei);
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
if (ext4_has_feature_project(inode->i_sb)) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 1d543f8..d2b665f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2795,7 +2795,8 @@ int ext4_mb_release(struct super_block *sb)
}
static inline int ext4_issue_discard(struct super_block *sb,
- ext4_group_t block_group, ext4_grpblk_t cluster, int count)
+ ext4_group_t block_group, ext4_grpblk_t cluster, int count,
+ unsigned long flags)
{
ext4_fsblk_t discard_block;
@@ -2804,7 +2805,7 @@ static inline int ext4_issue_discard(struct super_block *sb,
count = EXT4_C2B(EXT4_SB(sb), count);
trace_ext4_discard_blocks(sb,
(unsigned long long) discard_block, count);
- return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+ return sb_issue_discard(sb, discard_block, count, GFP_NOFS, flags);
}
/*
@@ -2826,7 +2827,7 @@ static void ext4_free_data_callback(struct super_block *sb,
if (test_opt(sb, DISCARD)) {
err = ext4_issue_discard(sb, entry->efd_group,
entry->efd_start_cluster,
- entry->efd_count);
+ entry->efd_count, 0);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
" group:%d block:%d count:%d failed"
@@ -4887,7 +4888,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
* them with group lock_held
*/
if (test_opt(sb, DISCARD)) {
- err = ext4_issue_discard(sb, block_group, bit, count);
+ err = ext4_issue_discard(sb, block_group, bit, count,
+ 0);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
" group:%d block:%d count:%lu failed"
@@ -5085,13 +5087,15 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
* @count: number of blocks to TRIM
* @group: alloc. group we are working with
* @e4b: ext4 buddy for the group
+ * @blkdev_flags: flags for the block device
*
* Trim "count" blocks starting at "start" in the "group". To assure that no
* one will allocate those blocks, mark it as used in buddy bitmap. This must
* be called with under the group lock.
*/
static int ext4_trim_extent(struct super_block *sb, int start, int count,
- ext4_group_t group, struct ext4_buddy *e4b)
+ ext4_group_t group, struct ext4_buddy *e4b,
+ unsigned long blkdev_flags)
__releases(bitlock)
__acquires(bitlock)
{
@@ -5112,7 +5116,7 @@ __acquires(bitlock)
*/
mb_mark_used(e4b, &ex);
ext4_unlock_group(sb, group);
- ret = ext4_issue_discard(sb, group, start, count);
+ ret = ext4_issue_discard(sb, group, start, count, blkdev_flags);
ext4_lock_group(sb, group);
mb_free_blocks(NULL, e4b, start, ex.fe_len);
return ret;
@@ -5125,6 +5129,7 @@ __acquires(bitlock)
* @start: first group block to examine
* @max: last group block to examine
* @minblocks: minimum extent block count
+ * @blkdev_flags: flags for the block device
*
* ext4_trim_all_free walks through group's buddy bitmap searching for free
* extents. When the free block is found, ext4_trim_extent is called to TRIM
@@ -5139,7 +5144,7 @@ __acquires(bitlock)
static ext4_grpblk_t
ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t start, ext4_grpblk_t max,
- ext4_grpblk_t minblocks)
+ ext4_grpblk_t minblocks, unsigned long blkdev_flags)
{
void *bitmap;
ext4_grpblk_t next, count = 0, free_count = 0;
@@ -5172,7 +5177,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
if ((next - start) >= minblocks) {
ret = ext4_trim_extent(sb, start,
- next - start, group, &e4b);
+ next - start, group, &e4b,
+ blkdev_flags);
if (ret && ret != -EOPNOTSUPP)
break;
ret = 0;
@@ -5214,6 +5220,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
* ext4_trim_fs() -- trim ioctl handle function
* @sb: superblock for filesystem
* @range: fstrim_range structure
+ * @blkdev_flags: flags for the block device
*
* start: First Byte to trim
* len: number of Bytes to trim from start
@@ -5222,7 +5229,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
* start to start+len. For each such a group ext4_trim_all_free function
* is invoked to trim all free space.
*/
-int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range,
+ unsigned long blkdev_flags)
{
struct ext4_group_info *grp;
ext4_group_t group, first_group, last_group;
@@ -5278,7 +5286,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
if (grp->bb_free >= minlen) {
cnt = ext4_trim_all_free(sb, group, first_cluster,
- end, minlen);
+ end, minlen, blkdev_flags);
if (cnt < 0) {
ret = cnt;
break;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 6224b0e..7853b22 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1258,29 +1258,17 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
static inline bool ext4_match(const struct ext4_filename *fname,
const struct ext4_dir_entry_2 *de)
{
- const void *name = fname_name(fname);
- u32 len = fname_len(fname);
+ struct fscrypt_name f;
if (!de->inode)
return false;
+ f.usr_fname = fname->usr_fname;
+ f.disk_name = fname->disk_name;
#ifdef CONFIG_EXT4_FS_ENCRYPTION
- if (unlikely(!name)) {
- if (fname->usr_fname->name[0] == '_') {
- int ret;
- if (de->name_len <= 32)
- return 0;
- ret = memcmp(de->name + ((de->name_len - 17) & ~15),
- fname->crypto_buf.name + 8, 16);
- return (ret == 0) ? 1 : 0;
- }
- name = fname->crypto_buf.name;
- len = fname->crypto_buf.len;
- }
+ f.crypto_buf = fname->crypto_buf;
#endif
- if (de->name_len != len)
- return 0;
- return (memcmp(de->name, name, len) == 0) ? 1 : 0;
+ return fscrypt_match_name(&f, de->name, de->name_len);
}
/*
@@ -1573,24 +1561,14 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
struct inode *inode;
struct ext4_dir_entry_2 *de;
struct buffer_head *bh;
+ int err;
- if (ext4_encrypted_inode(dir)) {
- int res = fscrypt_get_encryption_info(dir);
+ err = fscrypt_prepare_lookup(dir, dentry, flags);
+ if (err)
+ return ERR_PTR(err);
- /*
- * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
- * created while the directory was encrypted and we
- * have access to the key.
- */
- if (fscrypt_has_encryption_key(dir))
- fscrypt_set_encrypted_dentry(dentry);
- fscrypt_set_d_op(dentry);
- if (res && res != -ENOKEY)
- return ERR_PTR(res);
- }
-
- if (dentry->d_name.len > EXT4_NAME_LEN)
- return ERR_PTR(-ENAMETOOLONG);
+ if (dentry->d_name.len > EXT4_NAME_LEN)
+ return ERR_PTR(-ENAMETOOLONG);
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
if (IS_ERR(bh))
@@ -1618,16 +1596,9 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
!fscrypt_has_permitted_context(dir, inode)) {
- int nokey = ext4_encrypted_inode(inode) &&
- !fscrypt_has_encryption_key(inode);
- if (nokey) {
- iput(inode);
- return ERR_PTR(-ENOKEY);
- }
ext4_warning(inode->i_sb,
"Inconsistent encryption contexts: %lu/%lu",
- (unsigned long) dir->i_ino,
- (unsigned long) inode->i_ino);
+ dir->i_ino, inode->i_ino);
iput(inode);
return ERR_PTR(-EPERM);
}
@@ -1868,11 +1839,10 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
return 0;
}
-int ext4_insert_dentry(struct inode *dir,
- struct inode *inode,
- struct ext4_dir_entry_2 *de,
- int buf_size,
- struct ext4_filename *fname)
+void ext4_insert_dentry(struct inode *inode,
+ struct ext4_dir_entry_2 *de,
+ int buf_size,
+ struct ext4_filename *fname)
{
int nlen, rlen;
@@ -1891,7 +1861,6 @@ int ext4_insert_dentry(struct inode *dir,
ext4_set_de_type(inode->i_sb, de, inode->i_mode);
de->name_len = fname_len(fname);
memcpy(de->name, fname_name(fname), fname_len(fname));
- return 0;
}
/*
@@ -1927,11 +1896,8 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
return err;
}
- /* By now the buffer is marked for journaling. Due to crypto operations,
- * the following function call may fail */
- err = ext4_insert_dentry(dir, inode, de, blocksize, fname);
- if (err < 0)
- return err;
+ /* By now the buffer is marked for journaling */
+ ext4_insert_dentry(inode, de, blocksize, fname);
/*
* XXX shouldn't update any times until successful
@@ -3100,36 +3066,16 @@ static int ext4_symlink(struct inode *dir,
struct inode *inode;
int err, len = strlen(symname);
int credits;
- bool encryption_required;
struct fscrypt_str disk_link;
- struct fscrypt_symlink_data *sd = NULL;
- disk_link.len = len + 1;
- disk_link.name = (char *) symname;
-
- encryption_required = (ext4_encrypted_inode(dir) ||
- DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb)));
- if (encryption_required) {
- err = fscrypt_get_encryption_info(dir);
- if (err)
- return err;
- if (!fscrypt_has_encryption_key(dir))
- return -ENOKEY;
- disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
- sizeof(struct fscrypt_symlink_data));
- sd = kzalloc(disk_link.len, GFP_KERNEL);
- if (!sd)
- return -ENOMEM;
- }
-
- if (disk_link.len > dir->i_sb->s_blocksize) {
- err = -ENAMETOOLONG;
- goto err_free_sd;
- }
+ err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
+ &disk_link);
+ if (err)
+ return err;
err = dquot_initialize(dir);
if (err)
- goto err_free_sd;
+ return err;
if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
/*
@@ -3158,27 +3104,18 @@ static int ext4_symlink(struct inode *dir,
if (IS_ERR(inode)) {
if (handle)
ext4_journal_stop(handle);
- err = PTR_ERR(inode);
- goto err_free_sd;
+ return PTR_ERR(inode);
}
- if (encryption_required) {
- struct qstr istr;
- struct fscrypt_str ostr =
- FSTR_INIT(sd->encrypted_path, disk_link.len);
-
- istr.name = (const unsigned char *) symname;
- istr.len = len;
- err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
+ if (IS_ENCRYPTED(inode)) {
+ err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link);
if (err)
goto err_drop_inode;
- sd->len = cpu_to_le16(ostr.len);
- disk_link.name = (char *) sd;
inode->i_op = &ext4_encrypted_symlink_inode_operations;
}
if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
- if (!encryption_required)
+ if (!IS_ENCRYPTED(inode))
inode->i_op = &ext4_symlink_inode_operations;
inode_nohighmem(inode);
ext4_set_aops(inode);
@@ -3220,7 +3157,7 @@ static int ext4_symlink(struct inode *dir,
} else {
/* clear the extent format for fast symlink */
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
- if (!encryption_required) {
+ if (!IS_ENCRYPTED(inode)) {
inode->i_op = &ext4_fast_symlink_inode_operations;
inode->i_link = (char *)&EXT4_I(inode)->i_data;
}
@@ -3235,16 +3172,17 @@ static int ext4_symlink(struct inode *dir,
if (handle)
ext4_journal_stop(handle);
- kfree(sd);
- return err;
+ goto out_free_encrypted_link;
+
err_drop_inode:
if (handle)
ext4_journal_stop(handle);
clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
-err_free_sd:
- kfree(sd);
+out_free_encrypted_link:
+ if (disk_link.name != (unsigned char *)symname)
+ kfree(disk_link.name);
return err;
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 94f60f9..d68032b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,7 +24,6 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/backing-dev.h>
-#include <linux/fscrypto.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -477,7 +476,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
if (io->io_bio)
gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
retry_encrypt:
- data_page = fscrypt_encrypt_page(inode, page, gfp_flags);
+ data_page = fscrypt_encrypt_page(inode, page, PAGE_SIZE, 0,
+ page->index, gfp_flags);
if (IS_ERR(data_page)) {
ret = PTR_ERR(data_page);
if (ret == -ENOMEM &&
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index a81b829..c39a12d 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -45,6 +45,7 @@
#include <linux/cleancache.h>
#include "ext4.h"
+#include <trace/events/android_fs.h>
static inline bool ext4_bio_encrypted(struct bio *bio)
{
@@ -55,6 +56,17 @@ static inline bool ext4_bio_encrypted(struct bio *bio)
#endif
}
+static void
+ext4_trace_read_completion(struct bio *bio)
+{
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
+
+ if (first_page != NULL)
+ trace_android_fs_dataread_end(first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size);
+}
+
/*
* I/O completion handler for multipage BIOs.
*
@@ -72,11 +84,14 @@ static void mpage_end_io(struct bio *bio)
struct bio_vec *bv;
int i;
+ if (trace_android_fs_dataread_start_enabled())
+ ext4_trace_read_completion(bio);
+
if (ext4_bio_encrypted(bio)) {
if (bio->bi_error) {
fscrypt_release_ctx(bio->bi_private);
} else {
- fscrypt_decrypt_bio_pages(bio->bi_private, bio);
+ fscrypt_enqueue_decrypt_bio(bio->bi_private, bio);
return;
}
}
@@ -95,6 +110,30 @@ static void mpage_end_io(struct bio *bio)
bio_put(bio);
}
+static void
+ext4_submit_bio_read(struct bio *bio)
+{
+ if (trace_android_fs_dataread_start_enabled()) {
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
+
+ if (first_page != NULL) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ first_page->mapping->host);
+ trace_android_fs_dataread_start(
+ first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size,
+ current->pid,
+ path,
+ current->comm);
+ }
+ }
+ submit_bio(bio);
+}
+
int ext4_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages)
@@ -235,7 +274,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
*/
if (bio && (last_block_in_bio != blocks[0] - 1)) {
submit_and_realloc:
- submit_bio(bio);
+ ext4_submit_bio_read(bio);
bio = NULL;
}
if (bio == NULL) {
@@ -268,14 +307,14 @@ int ext4_mpage_readpages(struct address_space *mapping,
if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
(relative_block == map.m_len)) ||
(first_hole != blocks_per_page)) {
- submit_bio(bio);
+ ext4_submit_bio_read(bio);
bio = NULL;
} else
last_block_in_bio = blocks[blocks_per_page - 1];
goto next_page;
confused:
if (bio) {
- submit_bio(bio);
+ ext4_submit_bio_read(bio);
bio = NULL;
}
if (!PageUptodate(page))
@@ -288,6 +327,6 @@ int ext4_mpage_readpages(struct address_space *mapping,
}
BUG_ON(pages && !list_empty(pages));
if (bio)
- submit_bio(bio);
+ ext4_submit_bio_read(bio);
return 0;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 84d28d3..4e515e9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1039,9 +1039,7 @@ void ext4_clear_inode(struct inode *inode)
jbd2_free_inode(EXT4_I(inode)->jinode);
EXT4_I(inode)->jinode = NULL;
}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- fscrypt_put_encryption_info(inode, NULL);
-#endif
+ fscrypt_put_encryption_info(inode);
}
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
@@ -1115,80 +1113,86 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
}
-static int ext4_key_prefix(struct inode *inode, u8 **key)
-{
- *key = EXT4_SB(inode->i_sb)->key_prefix;
- return EXT4_SB(inode->i_sb)->key_prefix_size;
-}
-
-static int ext4_prepare_context(struct inode *inode)
-{
- return ext4_convert_inline_data(inode);
-}
-
static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
- handle_t *handle;
- int res, res2;
+ handle_t *handle = fs_data;
+ int res, res2, retries = 0;
- /* fs_data is null when internally used. */
- if (fs_data) {
- res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
- EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
- len, 0);
+ res = ext4_convert_inline_data(inode);
+ if (res)
+ return res;
+
+ /*
+ * If a journal handle was specified, then the encryption context is
+ * being set on a new inode via inheritance and is part of a larger
+ * transaction to create the inode. Otherwise the encryption context is
+ * being set on an existing inode in its own transaction. Only in the
+ * latter case should the "retry on ENOSPC" logic be used.
+ */
+
+ if (handle) {
+ res = ext4_xattr_set_handle(handle, inode,
+ EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ ctx, len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
ext4_clear_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA);
+ /*
+ * Update inode->i_flags - S_ENCRYPTED will be enabled,
+ * S_DAX may be disabled
+ */
+ ext4_set_inode_flags(inode);
}
return res;
}
+ res = dquot_initialize(inode);
+ if (res)
+ return res;
+retry:
handle = ext4_journal_start(inode, EXT4_HT_MISC,
ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle))
return PTR_ERR(handle);
- res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
- EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
- len, 0);
+ res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ ctx, len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+ /*
+ * Update inode->i_flags - S_ENCRYPTED will be enabled,
+ * S_DAX may be disabled
+ */
+ ext4_set_inode_flags(inode);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
}
res2 = ext4_journal_stop(handle);
+
+ if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
if (!res)
res = res2;
return res;
}
-static int ext4_dummy_context(struct inode *inode)
+static bool ext4_dummy_context(struct inode *inode)
{
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
-static unsigned ext4_max_namelen(struct inode *inode)
-{
- return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
- EXT4_NAME_LEN;
-}
-
-static struct fscrypt_operations ext4_cryptops = {
+static const struct fscrypt_operations ext4_cryptops = {
+ .key_prefix = "ext4:",
.get_context = ext4_get_context,
- .key_prefix = ext4_key_prefix,
- .prepare_context = ext4_prepare_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
- .is_encrypted = ext4_encrypted_inode,
.empty_dir = ext4_empty_dir,
- .max_namelen = ext4_max_namelen,
-};
-#else
-static struct fscrypt_operations ext4_cryptops = {
- .is_encrypted = ext4_encrypted_inode,
+ .max_namelen = EXT4_NAME_LEN,
};
#endif
@@ -4027,7 +4031,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_op = &ext4_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
sb->s_cop = &ext4_cryptops;
+#endif
#ifdef CONFIG_QUOTA
sb->dq_op = &ext4_quota_operations;
if (ext4_has_feature_quota(sb))
@@ -4321,11 +4327,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
kfree(orig_data);
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
- EXT4_KEY_DESC_PREFIX_SIZE);
- sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
-#endif
return 0;
cantfind_ext4:
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 557b3b0..d4ce3af 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -27,59 +27,28 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
struct delayed_call *done)
{
struct page *cpage = NULL;
- char *caddr, *paddr = NULL;
- struct fscrypt_str cstr, pstr;
- struct fscrypt_symlink_data *sd;
- int res;
- u32 max_size = inode->i_sb->s_blocksize;
+ const void *caddr;
+ unsigned int max_size;
+ const char *paddr;
if (!dentry)
return ERR_PTR(-ECHILD);
- res = fscrypt_get_encryption_info(inode);
- if (res)
- return ERR_PTR(res);
-
if (ext4_inode_is_fast_symlink(inode)) {
- caddr = (char *) EXT4_I(inode)->i_data;
+ caddr = EXT4_I(inode)->i_data;
max_size = sizeof(EXT4_I(inode)->i_data);
} else {
cpage = read_mapping_page(inode->i_mapping, 0, NULL);
if (IS_ERR(cpage))
return ERR_CAST(cpage);
caddr = page_address(cpage);
+ max_size = inode->i_sb->s_blocksize;
}
- /* Symlink is encrypted */
- sd = (struct fscrypt_symlink_data *)caddr;
- cstr.name = sd->encrypted_path;
- cstr.len = le16_to_cpu(sd->len);
- if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
- /* Symlink data on the disk is corrupted */
- res = -EFSCORRUPTED;
- goto errout;
- }
-
- res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
- if (res)
- goto errout;
- paddr = pstr.name;
-
- res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
- if (res)
- goto errout;
-
- /* Null-terminate the name */
- paddr[pstr.len] = '\0';
+ paddr = fscrypt_get_symlink(inode, caddr, max_size, done);
if (cpage)
put_page(cpage);
- set_delayed_call(done, kfree_link, paddr);
return paddr;
-errout:
- if (cpage)
- put_page(cpage);
- kfree(paddr);
- return ERR_PTR(res);
}
const struct inode_operations ext4_encrypted_symlink_inode_operations = {
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index ca949ea..a0dc559 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -2,7 +2,7 @@
f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o
f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o
-f2fs-y += shrinker.o extent_cache.o
+f2fs-y += shrinker.o extent_cache.o sysfs.o
f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index a989408..b32efb5 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/acl.c
*
@@ -7,10 +8,6 @@
* Portions of this code from linux/fs/ext2/acl.c
*
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/f2fs_fs.h>
#include "f2fs.h"
@@ -53,6 +50,9 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1);
const char *end = value + size;
+ if (size < sizeof(struct f2fs_acl_header))
+ return ERR_PTR(-EINVAL);
+
if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION))
return ERR_PTR(-EINVAL);
@@ -160,7 +160,7 @@ static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
return (void *)f2fs_acl;
fail:
- kfree(f2fs_acl);
+ kvfree(f2fs_acl);
return ERR_PTR(-EINVAL);
}
@@ -190,7 +190,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
acl = NULL;
else
acl = ERR_PTR(retval);
- kfree(value);
+ kvfree(value);
return acl;
}
@@ -207,15 +207,16 @@ static int __f2fs_set_acl(struct inode *inode, int type,
void *value = NULL;
size_t size = 0;
int error;
+ umode_t mode = inode->i_mode;
switch (type) {
case ACL_TYPE_ACCESS:
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl && !ipage) {
- error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ error = posix_acl_update_mode(inode, &mode, &acl);
if (error)
return error;
- set_acl_inode(inode, inode->i_mode);
+ set_acl_inode(inode, mode);
}
break;
@@ -233,13 +234,13 @@ static int __f2fs_set_acl(struct inode *inode, int type,
value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
if (IS_ERR(value)) {
clear_inode_flag(inode, FI_ACL_MODE);
- return (int)PTR_ERR(value);
+ return PTR_ERR(value);
}
}
error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
- kfree(value);
+ kvfree(value);
if (!error)
set_cached_acl(inode, type, acl);
@@ -249,6 +250,9 @@ static int __f2fs_set_acl(struct inode *inode, int type,
int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
+
return __f2fs_set_acl(inode, type, acl, NULL);
}
@@ -386,18 +390,22 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
if (error)
return error;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (default_acl) {
error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
ipage);
posix_acl_release(default_acl);
+ } else {
+ inode->i_default_acl = NULL;
}
if (acl) {
if (!error)
error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
ipage);
posix_acl_release(acl);
+ } else {
+ inode->i_acl = NULL;
}
return error;
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index 2c68518..b96823c 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/acl.h
*
@@ -7,10 +8,6 @@
* Portions of this code from linux/fs/ext2/acl.h
*
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef __F2FS_ACL_H__
#define __F2FS_ACL_H__
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5e9f8ec..bf5b5db 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/checkpoint.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/bio.h>
@@ -24,20 +21,20 @@
#include <trace/events/f2fs.h>
static struct kmem_cache *ino_entry_slab;
-struct kmem_cache *inode_entry_slab;
+struct kmem_cache *f2fs_inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
+ f2fs_build_fault_attr(sbi, 0, 0);
set_ckpt_flags(sbi, CP_ERROR_FLAG);
- sbi->sb->s_flags |= MS_RDONLY;
if (!end_io)
- f2fs_flush_merged_bios(sbi);
+ f2fs_flush_merged_writes(sbi);
}
/*
* We guarantee no failure on the returned page.
*/
-struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
@@ -47,7 +44,7 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
cond_resched();
goto repeat;
}
- f2fs_wait_on_page_writeback(page, META, true);
+ f2fs_wait_on_page_writeback(page, META, true, true);
if (!PageUptodate(page))
SetPageUptodate(page);
return page;
@@ -65,12 +62,13 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
- .op_flags = READ_SYNC | REQ_META | REQ_PRIO,
+ .op_flags = REQ_META | REQ_PRIO,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
.is_meta = is_meta,
};
+ int err;
if (unlikely(!is_meta))
fio.op_flags &= ~REQ_META;
@@ -85,11 +83,10 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
fio.page = page;
- if (f2fs_submit_page_bio(&fio)) {
- memset(page_address(page), 0, PAGE_SIZE);
- f2fs_stop_checkpoint(sbi, false);
- f2fs_bug_on(sbi, 1);
- return page;
+ err = f2fs_submit_page_bio(&fio);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
}
lock_page(page);
@@ -98,24 +95,37 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
goto repeat;
}
- /*
- * if there is any IO error when accessing device, make our filesystem
- * readonly and make sure do not write checkpoint with non-uptodate
- * meta page.
- */
- if (unlikely(!PageUptodate(page)))
- f2fs_stop_checkpoint(sbi, false);
+ if (unlikely(!PageUptodate(page))) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
out:
return page;
}
-struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, true);
}
+struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ struct page *page;
+ int count = 0;
+
+retry:
+ page = __get_meta_page(sbi, index, true);
+ if (IS_ERR(page)) {
+ if (PTR_ERR(page) == -EIO &&
+ ++count <= DEFAULT_RETRY_IO_COUNT)
+ goto retry;
+ f2fs_stop_checkpoint(sbi, false);
+ }
+ return page;
+}
+
/* for POR only */
-struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
@@ -167,7 +177,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync)
{
struct page *page;
@@ -176,8 +186,9 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
- .op_flags = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : REQ_RAHEAD,
+ .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
+ .in_list = false,
.is_meta = (type != META_POR),
};
struct blk_plug plug;
@@ -226,17 +237,15 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
}
fio.page = page;
- fio.old_blkaddr = fio.new_blkaddr;
- f2fs_submit_page_mbio(&fio);
+ f2fs_submit_page_bio(&fio);
f2fs_put_page(page, 0);
}
out:
- f2fs_submit_merged_bio(sbi, META, READ);
blk_finish_plug(&plug);
return blkno - start;
}
-void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
+void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
bool readahead = false;
@@ -247,33 +256,34 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
f2fs_put_page(page, 0);
if (readahead)
- ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true);
+ f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
}
-static int f2fs_write_meta_page(struct page *page,
- struct writeback_control *wbc)
+static int __f2fs_write_meta_page(struct page *page,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto redirty_out;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
- if (unlikely(f2fs_cp_error(sbi)))
- goto redirty_out;
- write_meta_page(sbi, page);
+ f2fs_do_write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
unlock_page(page);
if (unlikely(f2fs_cp_error(sbi)))
- f2fs_submit_merged_bio(sbi, META, WRITE);
+ f2fs_submit_merged_write(sbi, META);
return 0;
@@ -282,23 +292,34 @@ static int f2fs_write_meta_page(struct page *page,
return AOP_WRITEPAGE_ACTIVATE;
}
+static int f2fs_write_meta_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __f2fs_write_meta_page(page, wbc, FS_META_IO);
+}
+
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto skip_write;
+
/* collect a number of dirty meta pages and write together */
- if (wbc->for_kupdate ||
- get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
+ if (wbc->sync_mode != WB_SYNC_ALL &&
+ get_pages(sbi, F2FS_DIRTY_META) <
+ nr_pages_to_skip(sbi, META))
+ goto skip_write;
+
+ /* if locked failed, cp will flush dirty pages instead */
+ if (!mutex_trylock(&sbi->cp_mutex))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, META);
-
- /* if mounting is failed, skip writing node pages */
- mutex_lock(&sbi->cp_mutex);
diff = nr_pages_to_write(sbi, META, wbc);
- written = sync_meta_pages(sbi, META, wbc->nr_to_write);
+ written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
return 0;
@@ -309,13 +330,14 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
return 0;
}
-long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
- long nr_to_write)
+long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+ long nr_to_write, enum iostat_type io_type)
{
struct address_space *mapping = META_MAPPING(sbi);
- pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
+ pgoff_t index = 0, prev = ULONG_MAX;
struct pagevec pvec;
long nwritten = 0;
+ int nr_pages;
struct writeback_control wbc = {
.for_reclaim = 0,
};
@@ -325,13 +347,9 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
blk_start_plug(&plug);
- while (index <= end) {
- int i, nr_pages;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
- if (unlikely(nr_pages == 0))
- break;
+ while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY))) {
+ int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@@ -355,13 +373,12 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
goto continue_unlock;
}
- f2fs_wait_on_page_writeback(page, META, true);
+ f2fs_wait_on_page_writeback(page, META, true, true);
- BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- if (mapping->a_ops->writepage(page, &wbc)) {
+ if (__f2fs_write_meta_page(page, &wbc, io_type)) {
unlock_page(page);
break;
}
@@ -375,7 +392,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
}
stop:
if (nwritten)
- f2fs_submit_merged_bio(sbi, type, WRITE);
+ f2fs_submit_merged_write(sbi, type);
blk_finish_plug(&plug);
@@ -389,9 +406,9 @@ static int f2fs_set_meta_page_dirty(struct page *page)
if (!PageUptodate(page))
SetPageUptodate(page);
if (!PageDirty(page)) {
- f2fs_set_page_dirty_nobuffers(page);
+ __set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
- SetPagePrivate(page);
+ f2fs_set_page_private(page, 0);
f2fs_trace_pid(page);
return 1;
}
@@ -409,24 +426,23 @@ const struct address_space_operations f2fs_meta_aops = {
#endif
};
-static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
+static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type)
{
struct inode_management *im = &sbi->im[type];
struct ino_entry *e, *tmp;
tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
-retry:
+
radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
e = tmp;
- if (radix_tree_insert(&im->ino_root, ino, e)) {
- spin_unlock(&im->ino_lock);
- radix_tree_preload_end();
- goto retry;
- }
+ if (unlikely(radix_tree_insert(&im->ino_root, ino, e)))
+ f2fs_bug_on(sbi, 1);
+
memset(e, 0, sizeof(struct ino_entry));
e->ino = ino;
@@ -434,6 +450,10 @@ static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
if (type != ORPHAN_INO)
im->ino_num++;
}
+
+ if (type == FLUSH_INO)
+ f2fs_set_bit(devidx, (char *)&e->dirty_device);
+
spin_unlock(&im->ino_lock);
radix_tree_preload_end();
@@ -459,20 +479,20 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
spin_unlock(&im->ino_lock);
}
-void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* add new dirty ino entry into list */
- __add_ino_entry(sbi, ino, type);
+ __add_ino_entry(sbi, ino, 0, type);
}
-void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* remove dirty ino entry from list */
__remove_ino_entry(sbi, ino, type);
}
/* mode should be APPEND_INO or UPDATE_INO */
-bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
+bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
@@ -483,12 +503,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
return e ? true : false;
}
-void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
+void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
- for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
+ for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
struct inode_management *im = &sbi->im[i];
spin_lock(&im->ino_lock);
@@ -502,19 +522,40 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
}
}
-int acquire_orphan_inode(struct f2fs_sb_info *sbi)
+void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type)
+{
+ __add_ino_entry(sbi, ino, devidx, type);
+}
+
+bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type)
+{
+ struct inode_management *im = &sbi->im[type];
+ struct ino_entry *e;
+ bool is_dirty = false;
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
+ if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
+ is_dirty = true;
+ spin_unlock(&im->ino_lock);
+ return is_dirty;
+}
+
+int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
spin_lock(&im->ino_lock);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
+ f2fs_show_injection_info(FAULT_ORPHAN);
return -ENOSPC;
}
-#endif
+
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
@@ -524,7 +565,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
return err;
}
-void release_orphan_inode(struct f2fs_sb_info *sbi)
+void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
@@ -534,14 +575,14 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
spin_unlock(&im->ino_lock);
}
-void add_orphan_inode(struct inode *inode)
+void f2fs_add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
- __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
- update_inode_page(inode);
+ __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
+ f2fs_update_inode_page(inode);
}
-void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
/* remove orphan entry from orphan list */
__remove_ino_entry(sbi, ino, ORPHAN_INO);
@@ -551,17 +592,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct node_info ni;
- int err = acquire_orphan_inode(sbi);
-
- if (err) {
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_msg(sbi->sb, KERN_WARNING,
- "%s: orphan failed (ino=%x), run fsck to fix.",
- __func__, ino);
- return err;
- }
-
- __add_ino_entry(sbi, ino, ORPHAN_INO);
+ int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode)) {
@@ -573,56 +604,103 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
return PTR_ERR(inode);
}
+ err = dquot_initialize(inode);
+ if (err) {
+ iput(inode);
+ goto err_out;
+ }
+
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
- get_node_info(sbi, ino, &ni);
+ err = f2fs_get_node_info(sbi, ino, &ni);
+ if (err)
+ goto err_out;
/* ENOMEM was fully retried in f2fs_evict_inode. */
if (ni.blk_addr != NULL_ADDR) {
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_msg(sbi->sb, KERN_WARNING,
- "%s: orphan failed (ino=%x), run fsck to fix.",
- __func__, ino);
- return -EIO;
+ err = -EIO;
+ goto err_out;
}
- __remove_ino_entry(sbi, ino, ORPHAN_INO);
return 0;
+
+err_out:
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: orphan failed (ino=%x), run fsck to fix.",
+ __func__, ino);
+ return err;
}
-int recover_orphan_inodes(struct f2fs_sb_info *sbi)
+int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
block_t start_blk, orphan_blocks, i, j;
- int err;
+ unsigned int s_flags = sbi->sb->s_flags;
+ int err = 0;
+#ifdef CONFIG_QUOTA
+ int quota_enabled;
+#endif
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
return 0;
+ if (s_flags & MS_RDONLY) {
+ f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
+ sbi->sb->s_flags &= ~MS_RDONLY;
+ }
+
+#ifdef CONFIG_QUOTA
+ /* Needed for iput() to work correctly and not trash data */
+ sbi->sb->s_flags |= MS_ACTIVE;
+
+ /*
+ * Turn on quotas which were not enabled for read-only mounts if
+ * filesystem has quota feature, so that they are updated correctly.
+ */
+ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
+#endif
+
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
- ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
+ f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
- struct page *page = get_meta_page(sbi, start_blk + i);
+ struct page *page;
struct f2fs_orphan_block *orphan_blk;
+ page = f2fs_get_meta_page(sbi, start_blk + i);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto out;
+ }
+
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
err = recover_orphan_inode(sbi, ino);
if (err) {
f2fs_put_page(page, 1);
- return err;
+ goto out;
}
}
f2fs_put_page(page, 1);
}
/* clear Orphan Flag */
clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
- return 0;
+out:
+ set_sbi_flag(sbi, SBI_IS_RECOVERED);
+
+#ifdef CONFIG_QUOTA
+ /* Turn quotas off */
+ if (quota_enabled)
+ f2fs_quota_off_umount(sbi->sb);
+#endif
+ sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+
+ return err;
}
static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -648,7 +726,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
- page = grab_meta_page(sbi, start_blk++);
+ page = f2fs_grab_meta_page(sbi, start_blk++);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
@@ -690,19 +768,21 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
size_t crc_offset = 0;
__u32 crc = 0;
- *cp_page = get_meta_page(sbi, cp_addr);
+ *cp_page = f2fs_get_meta_page(sbi, cp_addr);
+ if (IS_ERR(*cp_page))
+ return PTR_ERR(*cp_page);
+
*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
- if (crc_offset >= blk_size) {
+ if (crc_offset > (blk_size - sizeof(__le32))) {
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid crc_offset: %zu", crc_offset);
return -EINVAL;
}
- crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
- + crc_offset)));
+ crc = cur_cp_crc(*cp_block);
if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
@@ -753,7 +833,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
return NULL;
}
-int get_valid_checkpoint(struct f2fs_sb_info *sbi)
+int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *cp_block;
struct f2fs_super_block *fsb = sbi->raw_super;
@@ -765,7 +845,8 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
block_t cp_blk_no;
int i;
- sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
+ sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
+ GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
@@ -802,7 +883,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
sbi->cur_cp_pack = 2;
/* Sanity checking of checkpoint */
- if (sanity_check_ckpt(sbi))
+ if (f2fs_sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cp_blks <= 1)
@@ -816,7 +897,9 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
void *sit_bitmap_ptr;
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
- cur_page = get_meta_page(sbi, cp_blk_no + i);
+ cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
+ if (IS_ERR(cur_page))
+ goto free_fail_no_cp;
sit_bitmap_ptr = page_address(cur_page);
memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
f2fs_put_page(cur_page, 1);
@@ -830,7 +913,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
fail_no_cp:
- kfree(sbi->ckpt);
+ kvfree(sbi->ckpt);
return -EINVAL;
}
@@ -843,7 +926,9 @@ static void __add_dirty_inode(struct inode *inode, enum inode_type type)
return;
set_inode_flag(inode, flag);
- list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]);
+ if (!f2fs_is_volatile_file(inode))
+ list_add_tail(&F2FS_I(inode)->dirty_list,
+ &sbi->inode_list[type]);
stat_inc_dirty_inode(sbi, type);
}
@@ -859,7 +944,7 @@ static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
-void update_dirty_page(struct inode *inode, struct page *page)
+void f2fs_update_dirty_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
@@ -874,11 +959,11 @@ void update_dirty_page(struct inode *inode, struct page *page)
inode_inc_dirty_pages(inode);
spin_unlock(&sbi->inode_lock[type]);
- SetPagePrivate(page);
+ f2fs_set_page_private(page, 0);
f2fs_trace_pid(page);
}
-void remove_dirty_inode(struct inode *inode)
+void f2fs_remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
@@ -895,12 +980,13 @@ void remove_dirty_inode(struct inode *inode)
spin_unlock(&sbi->inode_lock[type]);
}
-int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
{
struct list_head *head;
struct inode *inode;
struct f2fs_inode_info *fi;
bool is_dir = (type == DIR_INODE);
+ unsigned long ino = 0;
trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
@@ -923,18 +1009,32 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
return 0;
}
- fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+ fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[type]);
if (inode) {
+ unsigned long cur_ino = inode->i_ino;
+
+ if (is_dir)
+ F2FS_I(inode)->cp_task = current;
+
filemap_fdatawrite(inode->i_mapping);
+
+ if (is_dir)
+ F2FS_I(inode)->cp_task = NULL;
+
iput(inode);
+ /* We need to give cpu to another writers. */
+ if (ino == cur_ino)
+ cond_resched();
+ else
+ ino = cur_ino;
} else {
/*
* We should submit bio, since it exists several
* wribacking dentry pages in the freeing inode.
*/
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ f2fs_submit_merged_write(sbi, DATA);
cond_resched();
}
goto retry;
@@ -956,18 +1056,50 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
spin_unlock(&sbi->inode_lock[DIRTY_META]);
return 0;
}
- fi = list_entry(head->next, struct f2fs_inode_info,
+ fi = list_first_entry(head, struct f2fs_inode_info,
gdirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[DIRTY_META]);
if (inode) {
- update_inode_page(inode);
+ sync_inode_metadata(inode, 0);
+
+ /* it's on eviction */
+ if (is_inode_flag_set(inode, FI_DIRTY_INODE))
+ f2fs_update_inode_page(inode);
iput(inode);
}
- };
+ }
return 0;
}
+static void __prepare_cp_block(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ nid_t last_nid = nm_i->next_scan_nid;
+
+ next_free_nid(sbi, &last_nid);
+ ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
+ ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
+ ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
+ ckpt->next_free_nid = cpu_to_le32(last_nid);
+}
+
+static bool __need_flush_quota(struct f2fs_sb_info *sbi)
+{
+ if (!is_journalled_quota(sbi))
+ return false;
+ if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
+ return false;
+ if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
+ return false;
+ if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH))
+ return true;
+ if (get_pages(sbi, F2FS_DIRTY_QDATA))
+ return true;
+ return false;
+}
+
/*
* Freeze all the FS-operations for checkpoint.
*/
@@ -979,45 +1111,91 @@ static int block_operations(struct f2fs_sb_info *sbi)
.for_reclaim = 0,
};
struct blk_plug plug;
- int err = 0;
+ int err = 0, cnt = 0;
blk_start_plug(&plug);
-retry_flush_dents:
+retry_flush_quotas:
+ if (__need_flush_quota(sbi)) {
+ int locked;
+
+ if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
+ set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
+ f2fs_lock_all(sbi);
+ goto retry_flush_dents;
+ }
+ clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
+
+ /* only failed during mount/umount/freeze/quotactl */
+ locked = down_read_trylock(&sbi->sb->s_umount);
+ f2fs_quota_sync(sbi->sb, -1);
+ if (locked)
+ up_read(&sbi->sb->s_umount);
+ }
+
f2fs_lock_all(sbi);
+ if (__need_flush_quota(sbi)) {
+ f2fs_unlock_all(sbi);
+ cond_resched();
+ goto retry_flush_quotas;
+ }
+
+retry_flush_dents:
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs_unlock_all(sbi);
- err = sync_dirty_inodes(sbi, DIR_INODE);
+ err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
if (err)
goto out;
- goto retry_flush_dents;
- }
-
- if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
- f2fs_unlock_all(sbi);
- err = f2fs_sync_inode_meta(sbi);
- if (err)
- goto out;
- goto retry_flush_dents;
+ cond_resched();
+ goto retry_flush_quotas;
}
/*
* POR: we should ensure that there are no dirty node pages
- * until finishing nat/sit flush.
+ * until finishing nat/sit flush. inode->i_blocks can be updated.
*/
+ down_write(&sbi->node_change);
+
+ if (__need_flush_quota(sbi)) {
+ up_write(&sbi->node_change);
+ f2fs_unlock_all(sbi);
+ goto retry_flush_quotas;
+ }
+
+ if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+ up_write(&sbi->node_change);
+ f2fs_unlock_all(sbi);
+ err = f2fs_sync_inode_meta(sbi);
+ if (err)
+ goto out;
+ cond_resched();
+ goto retry_flush_quotas;
+ }
+
retry_flush_nodes:
down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
- err = sync_node_pages(sbi, &wbc);
+ atomic_inc(&sbi->wb_sync_req[NODE]);
+ err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
+ atomic_dec(&sbi->wb_sync_req[NODE]);
if (err) {
+ up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
goto out;
}
+ cond_resched();
goto retry_flush_nodes;
}
+
+ /*
+ * sbi->node_change is used only for AIO write_begin path which produces
+ * dirty node blocks and some checkpoint values by block allocation.
+ */
+ __prepare_cp_block(sbi);
+ up_write(&sbi->node_change);
out:
blk_finish_plug(&plug);
return err;
@@ -1026,19 +1204,20 @@ static int block_operations(struct f2fs_sb_info *sbi)
static void unblock_operations(struct f2fs_sb_info *sbi)
{
up_write(&sbi->node_write);
-
- build_free_nids(sbi);
f2fs_unlock_all(sbi);
}
-static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (!atomic_read(&sbi->nr_wb_bios))
+ if (!get_pages(sbi, F2FS_WB_CP_DATA))
+ break;
+
+ if (unlikely(f2fs_cp_error(sbi)))
break;
io_schedule_timeout(5*HZ);
@@ -1050,15 +1229,26 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ unsigned long flags;
- spin_lock(&sbi->cp_lock);
+ spin_lock_irqsave(&sbi->cp_lock, flags);
- if (cpc->reason == CP_UMOUNT)
+ if ((cpc->reason & CP_UMOUNT) &&
+ le32_to_cpu(ckpt->cp_pack_total_block_count) >
+ sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+ disable_nat_bits(sbi, false);
+
+ if (cpc->reason & CP_TRIMMED)
+ __set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
+
+ if (cpc->reason & CP_UMOUNT)
__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
- if (cpc->reason == CP_FASTBOOT)
+ if (cpc->reason & CP_FASTBOOT)
__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
@@ -1071,18 +1261,75 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+ if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
+ __set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG);
+
+ if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK))
+ __set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
+
+ if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
+ __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
+ /*
+ * TODO: we count on fsck.f2fs to clear this flag until we figure out
+ * missing cases which clear it incorrectly.
+ */
+
+ if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
+ __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
+
/* set this flag to activate crc|cp_ver for recovery */
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+ __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
- spin_unlock(&sbi->cp_lock);
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
+}
+
+static void commit_checkpoint(struct f2fs_sb_info *sbi,
+ void *src, block_t blk_addr)
+{
+ struct writeback_control wbc = {
+ .for_reclaim = 0,
+ };
+
+ /*
+ * pagevec_lookup_tag and lock_page again will take
+ * some extra time. Therefore, f2fs_update_meta_pages and
+ * f2fs_sync_meta_pages are combined in this function.
+ */
+ struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
+ int err;
+
+ f2fs_wait_on_page_writeback(page, META, true, true);
+
+ memcpy(page_address(page), src, PAGE_SIZE);
+
+ set_page_dirty(page);
+ if (unlikely(!clear_page_dirty_for_io(page)))
+ f2fs_bug_on(sbi, 1);
+
+ /* writeout cp pack 2 page */
+ err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
+ if (unlikely(err && f2fs_cp_error(sbi))) {
+ f2fs_put_page(page, 1);
+ return;
+ }
+
+ f2fs_bug_on(sbi, err);
+ f2fs_put_page(page, 0);
+
+ /* submit checkpoint (with barrier if NOBARRIER is not set) */
+ f2fs_submit_merged_write(sbi, META_FLUSH);
}
static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
- unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
- nid_t last_nid = nm_i->next_scan_nid;
+ unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags;
block_t start_blk;
unsigned int data_sum_blocks, orphan_blocks;
__u32 crc32 = 0;
@@ -1091,22 +1338,18 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
struct super_block *sb = sbi->sb;
struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
u64 kbytes_written;
+ int err;
/* Flush all the NAT/SIT pages */
- while (get_pages(sbi, F2FS_DIRTY_META)) {
- sync_meta_pages(sbi, META, LONG_MAX);
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
- }
-
- next_free_nid(sbi, &last_nid);
+ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
+ f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
+ !f2fs_cp_error(sbi));
/*
* modify checkpoint
* version number is already updated
*/
- ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
- ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
+ ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
@@ -1125,18 +1368,14 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
- ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
- ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
- ckpt->next_free_nid = cpu_to_le32(last_nid);
-
/* 2 cp + n data seg summary + orphan inode blocks */
- data_sum_blocks = npages_for_summary_flush(sbi, false);
- spin_lock(&sbi->cp_lock);
+ data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
+ spin_lock_irqsave(&sbi->cp_lock, flags);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
else
__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
- spin_unlock(&sbi->cp_lock);
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
@@ -1165,16 +1404,25 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk = __start_cp_next_addr(sbi);
- /* need to wait for end_io results */
- wait_on_all_pages_writeback(sbi);
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
+ /* write nat bits */
+ if (enabled_nat_bits(sbi, cpc)) {
+ __u64 cp_ver = cur_cp_version(ckpt);
+ block_t blk;
+
+ cp_ver |= ((__u64)crc32 << 32);
+ *(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
+
+ blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+ for (i = 0; i < nm_i->nat_bits_blocks; i++)
+ f2fs_update_meta_page(sbi, nm_i->nat_bits +
+ (i << F2FS_BLKSIZE_BITS), blk + i);
+ }
/* write out checkpoint buffer at block 0 */
- update_meta_page(sbi, ckpt, start_blk++);
+ f2fs_update_meta_page(sbi, ckpt, start_blk++);
for (i = 1; i < 1 + cp_payload_blks; i++)
- update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
+ f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
start_blk++);
if (orphan_num) {
@@ -1182,7 +1430,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk += orphan_blocks;
}
- write_data_summaries(sbi, start_blk);
+ f2fs_write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
/* Record write statistics in the hot node summary */
@@ -1193,40 +1441,47 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
if (__remain_node_summaries(cpc->reason)) {
- write_node_summaries(sbi, start_blk);
+ f2fs_write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
- /* writeout checkpoint block */
- update_meta_page(sbi, ckpt, start_blk);
-
- /* wait for previous submitted node/meta pages writeback */
- wait_on_all_pages_writeback(sbi);
-
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
-
- filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
- filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
-
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
- /* Here, we only have one bio having CP pack */
- sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ /* Here, we have one bio having CP pack except cp pack 2 page */
+ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
+ f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
+ !f2fs_cp_error(sbi));
/* wait for previous submitted meta pages writeback */
- wait_on_all_pages_writeback(sbi);
+ f2fs_wait_on_all_pages_writeback(sbi);
- release_ino_entry(sbi, false);
+ /* flush all device cache */
+ err = f2fs_flush_device_cache(sbi);
+ if (err)
+ return err;
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
+ /* barrier and flush checkpoint cp pack 2 page if it can */
+ commit_checkpoint(sbi, ckpt, start_blk);
+ f2fs_wait_on_all_pages_writeback(sbi);
- clear_prefree_segments(sbi, cpc);
+ /*
+ * invalidate intermediate page cache borrowed from meta inode
+ * which are used for migration of encrypted inode's blocks.
+ */
+ if (f2fs_sb_has_encrypt(sbi))
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
+
+ f2fs_release_ino_entry(sbi, false);
+
+ f2fs_reset_fsync_node_info(sbi);
+
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
+ clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
+ sbi->unusable_block_count = 0;
__set_cp_next_pack(sbi);
/*
@@ -1239,23 +1494,29 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
- return 0;
+ return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
}
/*
* We guarantee that this checkpoint procedure will not fail.
*/
-int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
int err = 0;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ if (cpc->reason != CP_PAUSE)
+ return 0;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Start checkpoint disabled!");
+ }
mutex_lock(&sbi->cp_mutex);
if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
- (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC ||
- (cpc->reason == CP_DISCARD && !sbi->discard_blks)))
+ ((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
+ ((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
goto out;
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -1274,18 +1535,23 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
- f2fs_flush_merged_bios(sbi);
+ f2fs_flush_merged_writes(sbi);
/* this is the case of multiple fstrims without any changes */
- if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) {
- f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt);
- f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries);
- f2fs_bug_on(sbi, prefree_segments(sbi));
- flush_sit_entries(sbi, cpc);
- clear_prefree_segments(sbi, cpc);
- f2fs_wait_all_discard_bio(sbi);
- unblock_operations(sbi);
- goto out;
+ if (cpc->reason & CP_DISCARD) {
+ if (!f2fs_exist_trim_candidates(sbi, cpc)) {
+ unblock_operations(sbi);
+ goto out;
+ }
+
+ if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+ SIT_I(sbi)->dirty_sentries == 0 &&
+ prefree_segments(sbi) == 0) {
+ f2fs_flush_sit_entries(sbi, cpc);
+ f2fs_clear_prefree_segments(sbi, cpc);
+ unblock_operations(sbi);
+ goto out;
+ }
}
/*
@@ -1297,18 +1563,23 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
- flush_nat_entries(sbi);
- flush_sit_entries(sbi, cpc);
+ err = f2fs_flush_nat_entries(sbi, cpc);
+ if (err)
+ goto stop;
+
+ f2fs_flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
err = do_checkpoint(sbi, cpc);
-
- f2fs_wait_all_discard_bio(sbi);
-
+ if (err)
+ f2fs_release_discard_addrs(sbi);
+ else
+ f2fs_clear_prefree_segments(sbi, cpc);
+stop:
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
- if (cpc->reason == CP_RECOVERY)
+ if (cpc->reason & CP_RECOVERY)
f2fs_msg(sbi->sb, KERN_NOTICE,
"checkpoint: version = %llx", ckpt_ver);
@@ -1320,7 +1591,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
return err;
}
-void init_ino_entry_info(struct f2fs_sb_info *sbi)
+void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
{
int i;
@@ -1338,23 +1609,23 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi)
F2FS_ORPHANS_PER_BLOCK;
}
-int __init create_checkpoint_caches(void)
+int __init f2fs_create_checkpoint_caches(void)
{
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
- inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+ f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
sizeof(struct inode_entry));
- if (!inode_entry_slab) {
+ if (!f2fs_inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
}
return 0;
}
-void destroy_checkpoint_caches(void)
+void f2fs_destroy_checkpoint_caches(void)
{
kmem_cache_destroy(ino_entry_slab);
- kmem_cache_destroy(inode_entry_slab);
+ kmem_cache_destroy(f2fs_inode_entry_slab);
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b2cccd4..88f27eb 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -19,8 +16,6 @@
#include <linux/bio.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
-#include <linux/mm.h>
-#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include "f2fs.h"
@@ -28,39 +23,148 @@
#include "segment.h"
#include "trace.h"
#include <trace/events/f2fs.h>
+#include <trace/events/android_fs.h>
+
+#define NUM_PREALLOC_POST_READ_CTXS 128
+
+static struct kmem_cache *bio_post_read_ctx_cache;
+static mempool_t *bio_post_read_ctx_pool;
+
+static bool __is_cp_guaranteed(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct inode *inode;
+ struct f2fs_sb_info *sbi;
+
+ if (!mapping)
+ return false;
+
+ inode = mapping->host;
+ sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino == F2FS_META_INO(sbi) ||
+ inode->i_ino == F2FS_NODE_INO(sbi) ||
+ S_ISDIR(inode->i_mode) ||
+ (S_ISREG(inode->i_mode) &&
+ (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
+ is_cold_data(page))
+ return true;
+ return false;
+}
+
+static enum count_type __read_io_type(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+
+ if (mapping) {
+ struct inode *inode = mapping->host;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino == F2FS_META_INO(sbi))
+ return F2FS_RD_META;
+
+ if (inode->i_ino == F2FS_NODE_INO(sbi))
+ return F2FS_RD_NODE;
+ }
+ return F2FS_RD_DATA;
+}
+
+/* postprocessing steps for read bios */
+enum bio_post_read_step {
+ STEP_INITIAL = 0,
+ STEP_DECRYPT,
+};
+
+struct bio_post_read_ctx {
+ struct bio *bio;
+ struct work_struct work;
+ unsigned int cur_step;
+ unsigned int enabled_steps;
+};
+
+static void __read_end_io(struct bio *bio)
+{
+ struct page *page;
+ struct bio_vec *bv;
+ int i;
+
+ bio_for_each_segment_all(bv, bio, i) {
+ page = bv->bv_page;
+
+ /* PG_error was set if any post_read step failed */
+ if (bio->bi_error || PageError(page)) {
+ ClearPageUptodate(page);
+ /* will re-read again later */
+ ClearPageError(page);
+ } else {
+ SetPageUptodate(page);
+ }
+ dec_page_count(F2FS_P_SB(page), __read_io_type(page));
+ unlock_page(page);
+ }
+ if (bio->bi_private)
+ mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+ bio_put(bio);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
+
+static void decrypt_work(struct work_struct *work)
+{
+ struct bio_post_read_ctx *ctx =
+ container_of(work, struct bio_post_read_ctx, work);
+
+ fscrypt_decrypt_bio(ctx->bio);
+
+ bio_post_read_processing(ctx);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
+{
+ switch (++ctx->cur_step) {
+ case STEP_DECRYPT:
+ if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
+ INIT_WORK(&ctx->work, decrypt_work);
+ fscrypt_enqueue_decrypt_work(&ctx->work);
+ return;
+ }
+ ctx->cur_step++;
+ /* fall-through */
+ default:
+ __read_end_io(ctx->bio);
+ }
+}
+
+static bool f2fs_bio_post_read_required(struct bio *bio)
+{
+ return bio->bi_private && !bio->bi_error;
+}
static void f2fs_read_end_io(struct bio *bio)
{
- struct bio_vec *bvec;
- int i;
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO))
+ if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_READ_IO)) {
+ f2fs_show_injection_info(FAULT_READ_IO);
bio->bi_error = -EIO;
-#endif
-
- if (f2fs_bio_encrypted(bio)) {
- if (bio->bi_error) {
- fscrypt_release_ctx(bio->bi_private);
- } else {
- fscrypt_decrypt_bio_pages(bio->bi_private, bio);
- return;
- }
}
- bio_for_each_segment_all(bvec, bio, i) {
- struct page *page = bvec->bv_page;
+ if (f2fs_bio_post_read_required(bio)) {
+ struct bio_post_read_ctx *ctx = bio->bi_private;
- if (!bio->bi_error) {
- if (!PageUptodate(page))
- SetPageUptodate(page);
- } else {
- ClearPageUptodate(page);
- SetPageError(page);
- }
- unlock_page(page);
+ ctx->cur_step = STEP_INITIAL;
+ bio_post_read_processing(ctx);
+ return;
}
- bio_put(bio);
+
+ if (first_page != NULL &&
+ __read_io_type(first_page) == F2FS_RD_DATA) {
+ trace_android_fs_dataread_end(first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size);
+ }
+
+ __read_end_io(bio);
}
static void f2fs_write_end_io(struct bio *bio)
@@ -69,18 +173,44 @@ static void f2fs_write_end_io(struct bio *bio)
struct bio_vec *bvec;
int i;
+ if (time_to_inject(sbi, FAULT_WRITE_IO)) {
+ f2fs_show_injection_info(FAULT_WRITE_IO);
+ bio->bi_error = -EIO;
+ }
+
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
+ enum count_type type = WB_DATA_TYPE(page);
+
+ if (IS_DUMMY_WRITTEN_PAGE(page)) {
+ set_page_private(page, (unsigned long)NULL);
+ ClearPagePrivate(page);
+ unlock_page(page);
+ mempool_free(page, sbi->write_io_dummy);
+
+ if (unlikely(bio->bi_error))
+ f2fs_stop_checkpoint(sbi, true);
+ continue;
+ }
fscrypt_pullback_bio_page(&page, true);
if (unlikely(bio->bi_error)) {
mapping_set_error(page->mapping, -EIO);
- f2fs_stop_checkpoint(sbi, true);
+ if (type == F2FS_WB_CP_DATA)
+ f2fs_stop_checkpoint(sbi, true);
}
+
+ f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
+ page->index != nid_of_node(page));
+
+ dec_page_count(sbi, type);
+ if (f2fs_in_warm_node_list(sbi, page))
+ f2fs_del_fsync_node_entry(sbi, page);
+ clear_cold_data(page);
end_page_writeback(page);
}
- if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+ if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
@@ -88,19 +218,68 @@ static void f2fs_write_end_io(struct bio *bio)
}
/*
+ * Return true, if pre_bio's bdev is same as its target device.
+ */
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio)
+{
+ struct block_device *bdev = sbi->sb->s_bdev;
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ if (FDEV(i).start_blk <= blk_addr &&
+ FDEV(i).end_blk >= blk_addr) {
+ blk_addr -= FDEV(i).start_blk;
+ bdev = FDEV(i).bdev;
+ break;
+ }
+ }
+ if (bio) {
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+ }
+ return bdev;
+}
+
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++)
+ if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
+ return i;
+ return 0;
+}
+
+static bool __same_bdev(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio)
+{
+ return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev;
+}
+
+/*
* Low-level block read/write IO operations.
*/
static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
- int npages, bool is_read)
+ struct writeback_control *wbc,
+ int npages, bool is_read,
+ enum page_type type, enum temp_type temp)
{
struct bio *bio;
- bio = f2fs_bio_alloc(npages);
+ bio = f2fs_bio_alloc(sbi, npages, true);
- bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
- bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
- bio->bi_private = is_read ? NULL : sbi;
+ f2fs_target_device(sbi, blk_addr, bio);
+ if (is_read) {
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = NULL;
+ } else {
+ bio->bi_end_io = f2fs_write_end_io;
+ bio->bi_private = sbi;
+ bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, type, temp);
+ }
+ if (wbc)
+ wbc_init_bio(wbc, bio);
return bio;
}
@@ -109,14 +288,75 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
if (!is_read_io(bio_op(bio))) {
- atomic_inc(&sbi->nr_wb_bios);
- if (f2fs_sb_mounted_hmsmr(sbi->sb) &&
- current->plug && (type == DATA || type == NODE))
+ unsigned int start;
+
+ if (type != DATA && type != NODE)
+ goto submit_io;
+
+ if (test_opt(sbi, LFS) && current->plug)
blk_finish_plug(current->plug);
+
+ start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
+ start %= F2FS_IO_SIZE(sbi);
+
+ if (start == 0)
+ goto submit_io;
+
+ /* fill dummy pages */
+ for (; start < F2FS_IO_SIZE(sbi); start++) {
+ struct page *page =
+ mempool_alloc(sbi->write_io_dummy,
+ GFP_NOIO | __GFP_NOFAIL);
+ f2fs_bug_on(sbi, !page);
+
+ zero_user_segment(page, 0, PAGE_SIZE);
+ SetPagePrivate(page);
+ set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
+ lock_page(page);
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+ f2fs_bug_on(sbi, 1);
+ }
+ /*
+ * In the NODE case, we lose next block address chain. So, we
+ * need to do checkpoint in f2fs_sync_file.
+ */
+ if (type == NODE)
+ set_sbi_flag(sbi, SBI_NEED_CP);
}
+submit_io:
+ if (is_read_io(bio_op(bio)))
+ trace_f2fs_submit_read_bio(sbi->sb, type, bio);
+ else
+ trace_f2fs_submit_write_bio(sbi->sb, type, bio);
submit_bio(bio);
}
+static void __f2fs_submit_read_bio(struct f2fs_sb_info *sbi,
+ struct bio *bio, enum page_type type)
+{
+ if (trace_android_fs_dataread_start_enabled() && (type == DATA)) {
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
+
+ if (first_page != NULL &&
+ __read_io_type(first_page) == F2FS_RD_DATA) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ first_page->mapping->host);
+
+ trace_android_fs_dataread_start(
+ first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size,
+ current->pid,
+ path,
+ current->comm);
+ }
+ }
+ __submit_bio(sbi, bio, type);
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -124,13 +364,13 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
if (!io->bio)
return;
- if (is_read_io(fio->op))
- trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
- else
- trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
-
bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+ if (is_read_io(fio->op))
+ trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
+ else
+ trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
+
__submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
@@ -166,73 +406,73 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
return false;
}
-static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
- struct page *page, nid_t ino,
- enum page_type type)
+static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
- struct f2fs_bio_info *io = &sbi->write_io[btype];
- bool ret;
-
- down_read(&io->io_rwsem);
- ret = __has_merged_page(io, inode, page, ino);
- up_read(&io->io_rwsem);
- return ret;
-}
-
-static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
- struct inode *inode, struct page *page,
- nid_t ino, enum page_type type, int rw)
-{
- enum page_type btype = PAGE_TYPE_OF_BIO(type);
- struct f2fs_bio_info *io;
-
- io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype];
+ struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
down_write(&io->io_rwsem);
- if (!__has_merged_page(io, inode, page, ino))
- goto out;
-
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->fio.op = REQ_OP_WRITE;
- if (test_opt(sbi, NOBARRIER))
- io->fio.op_flags = WRITE_FLUSH | REQ_META | REQ_PRIO;
- else
- io->fio.op_flags = WRITE_FLUSH_FUA | REQ_META |
- REQ_PRIO;
+ io->fio.op_flags = REQ_META | REQ_PRIO | REQ_SYNC;
+ if (!test_opt(sbi, NOBARRIER))
+ io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
-out:
up_write(&io->io_rwsem);
}
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
- int rw)
-{
- __f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
-}
-
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
- nid_t ino, enum page_type type, int rw)
+ nid_t ino, enum page_type type, bool force)
{
- if (has_merged_page(sbi, inode, page, ino, type))
- __f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+ enum temp_type temp;
+ bool ret = true;
+
+ for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+ if (!force) {
+ enum page_type btype = PAGE_TYPE_OF_BIO(type);
+ struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
+
+ down_read(&io->io_rwsem);
+ ret = __has_merged_page(io, inode, page, ino);
+ up_read(&io->io_rwsem);
+ }
+ if (ret)
+ __f2fs_submit_merged_write(sbi, type, temp);
+
+ /* TODO: use HOT temp only for meta pages now. */
+ if (type >= META)
+ break;
+ }
}
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
- f2fs_submit_merged_bio(sbi, META, WRITE);
+ __submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
+}
+
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, struct page *page,
+ nid_t ino, enum page_type type)
+{
+ __submit_merged_write_cond(sbi, inode, page, ino, type, false);
+}
+
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
+{
+ f2fs_submit_merged_write(sbi, DATA);
+ f2fs_submit_merged_write(sbi, NODE);
+ f2fs_submit_merged_write(sbi, META);
}
/*
* Fill the locked page with data located in the block address.
- * Return unlocked page.
+ * A caller needs to unlock the page on failure.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
@@ -248,69 +488,168 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
- bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
+ bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc,
+ 1, is_read_io(fio->op), fio->type, fio->temp);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
+
+ if (fio->io_wbc && !is_read_io(fio->op))
+ wbc_account_io(fio->io_wbc, page, PAGE_SIZE);
+
bio_set_op_attrs(bio, fio->op, fio->op_flags);
- __submit_bio(fio->sbi, bio, fio->type);
+ inc_page_count(fio->sbi, is_read_io(fio->op) ?
+ __read_io_type(page): WB_DATA_TYPE(fio->page));
+
+ __f2fs_submit_read_bio(fio->sbi, bio, fio->type);
return 0;
}
-void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
- struct f2fs_bio_info *io;
- bool is_read = is_read_io(fio->op);
+ struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
- io = is_read ? &sbi->read_io : &sbi->write_io[btype];
+ f2fs_bug_on(sbi, is_read_io(fio->op));
+
+ down_write(&io->io_rwsem);
+next:
+ if (fio->in_list) {
+ spin_lock(&io->io_lock);
+ if (list_empty(&io->io_list)) {
+ spin_unlock(&io->io_lock);
+ goto out;
+ }
+ fio = list_first_entry(&io->io_list,
+ struct f2fs_io_info, list);
+ list_del(&fio->list);
+ spin_unlock(&io->io_lock);
+ }
if (__is_valid_data_blkaddr(fio->old_blkaddr))
verify_block_addr(fio, fio->old_blkaddr);
verify_block_addr(fio, fio->new_blkaddr);
- down_write(&io->io_rwsem);
+ bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+ /* set submitted = true as a return value */
+ fio->submitted = true;
+
+ inc_page_count(sbi, WB_DATA_TYPE(bio_page));
if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
- (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags)))
+ (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
+ !__same_bdev(sbi, fio->new_blkaddr, io->bio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- int bio_blocks = MAX_BIO_BLOCKS(sbi);
-
- io->bio = __bio_alloc(sbi, fio->new_blkaddr,
- bio_blocks, is_read);
+ if ((fio->type == DATA || fio->type == NODE) &&
+ fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
+ dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+ fio->retry = true;
+ goto skip;
+ }
+ io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc,
+ BIO_MAX_PAGES, false,
+ fio->type, fio->temp);
io->fio = *fio;
}
- bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
-
- if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
- PAGE_SIZE) {
+ if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
+ if (fio->io_wbc)
+ wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE);
+
io->last_block_in_bio = fio->new_blkaddr;
f2fs_trace_ios(fio, 0);
+ trace_f2fs_submit_page_write(fio->page, fio);
+skip:
+ if (fio->in_list)
+ goto next;
+out:
+ if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
+ f2fs_is_checkpoint_ready(sbi))
+ __submit_merged_bio(io);
up_write(&io->io_rwsem);
- trace_f2fs_submit_page_mbio(fio->page, fio);
+}
+
+static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages, unsigned op_flag)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct bio *bio;
+ struct bio_post_read_ctx *ctx;
+ unsigned int post_read_steps = 0;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+ return ERR_PTR(-EFAULT);
+
+ bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+ f2fs_target_device(sbi, blkaddr, bio);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
+
+ if (f2fs_encrypted_file(inode))
+ post_read_steps |= 1 << STEP_DECRYPT;
+ if (post_read_steps) {
+ ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+ if (!ctx) {
+ bio_put(bio);
+ return ERR_PTR(-ENOMEM);
+ }
+ ctx->bio = bio;
+ ctx->enabled_steps = post_read_steps;
+ bio->bi_private = ctx;
+ }
+
+ return bio;
+}
+
+/* This can handle encryption stuffs */
+static int f2fs_submit_page_read(struct inode *inode, struct page *page,
+ block_t blkaddr)
+{
+ struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0);
+
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ /* wait for GCed page writeback via META_MAPPING */
+ f2fs_wait_on_block_writeback(inode, blkaddr);
+
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ bio_put(bio);
+ return -EFAULT;
+ }
+ ClearPageError(page);
+ inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+ __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
+ return 0;
}
static void __set_data_blkaddr(struct dnode_of_data *dn)
{
struct f2fs_node *rn = F2FS_NODE(dn->node_page);
__le32 *addr_array;
+ int base = 0;
+
+ if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
+ base = get_extra_isize(dn->inode);
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
- addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+ addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
@@ -319,9 +658,9 @@ static void __set_data_blkaddr(struct dnode_of_data *dn)
* ->node_page
* update block addresses in the node page
*/
-void set_data_blkaddr(struct dnode_of_data *dn)
+void f2fs_set_data_blkaddr(struct dnode_of_data *dn)
{
- f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
__set_data_blkaddr(dn);
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
@@ -330,31 +669,32 @@ void set_data_blkaddr(struct dnode_of_data *dn)
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
dn->data_blkaddr = blkaddr;
- set_data_blkaddr(dn);
+ f2fs_set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
-int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
+int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ int err;
if (!count)
return 0;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
- return -ENOSPC;
+ if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+ return err;
trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
dn->ofs_in_node, count);
- f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
for (; count > 0; dn->ofs_in_node++) {
- block_t blkaddr =
- datablock_addr(dn->node_page, dn->ofs_in_node);
+ block_t blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
if (blkaddr == NULL_ADDR) {
dn->data_blkaddr = NEW_ADDR;
__set_data_blkaddr(dn);
@@ -368,12 +708,12 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
}
/* Should keep dn->ofs_in_node unchanged */
-int reserve_new_block(struct dnode_of_data *dn)
+int f2fs_reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
- ret = reserve_new_blocks(dn, 1);
+ ret = f2fs_reserve_new_blocks(dn, 1);
dn->ofs_in_node = ofs_in_node;
return ret;
}
@@ -383,12 +723,12 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
bool need_put = dn->inode_page ? false : true;
int err;
- err = get_dnode_of_data(dn, index, ALLOC_NODE);
+ err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
- err = reserve_new_block(dn);
+ err = f2fs_reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
@@ -396,7 +736,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
- struct extent_info ei;
+ struct extent_info ei = {0,0,0};
struct inode *inode = dn->inode;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
@@ -407,24 +747,14 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
return f2fs_reserve_block(dn, index);
}
-struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
- struct extent_info ei;
+ struct extent_info ei = {0,0,0};
int err;
- struct f2fs_io_info fio = {
- .sbi = F2FS_I_SB(inode),
- .type = DATA,
- .op = REQ_OP_READ,
- .op_flags = op_flags,
- .encrypted_page = NULL,
- };
-
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- return read_mapping_page(mapping, index, NULL);
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
@@ -436,7 +766,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_err;
f2fs_put_dnode(&dn);
@@ -455,7 +785,8 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
- * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
+ * see, f2fs_add_link -> f2fs_get_new_data_page ->
+ * f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
@@ -465,9 +796,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
return page;
}
- fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
- fio.page = page;
- err = f2fs_submit_page_bio(&fio);
+ err = f2fs_submit_page_read(inode, page, dn.data_blkaddr);
if (err)
goto put_err;
return page;
@@ -477,7 +806,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
return ERR_PTR(err);
}
-struct page *find_data_page(struct inode *inode, pgoff_t index)
+struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -487,7 +816,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
return page;
f2fs_put_page(page, 0);
- page = get_read_data_page(inode, index, READ_SYNC, false);
+ page = f2fs_get_read_data_page(inode, index, 0, false);
if (IS_ERR(page))
return page;
@@ -507,13 +836,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
-struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
- page = get_read_data_page(inode, index, READ_SYNC, for_write);
+ page = f2fs_get_read_data_page(inode, index, 0, for_write);
if (IS_ERR(page))
return page;
@@ -539,7 +868,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
-struct page *get_new_data_page(struct inode *inode,
+struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
@@ -578,7 +907,7 @@ struct page *get_new_data_page(struct inode *inode,
/* if ipage exists, blkaddr should be NEW_ADDR */
f2fs_bug_on(F2FS_I_SB(inode), ipage);
- page = get_lock_data_page(inode, index, true);
+ page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return page;
}
@@ -589,50 +918,67 @@ struct page *get_new_data_page(struct inode *inode,
return page;
}
-static int __allocate_data_block(struct dnode_of_data *dn)
+static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
- int seg = CURSEG_WARM_DATA;
- pgoff_t fofs;
+ block_t old_blkaddr;
blkcnt_t count = 1;
+ int err;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
- if (dn->data_blkaddr == NEW_ADDR)
+ err = f2fs_get_node_info(sbi, dn->nid, &ni);
+ if (err)
+ return err;
+
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
+ if (dn->data_blkaddr != NULL_ADDR)
goto alloc;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
- return -ENOSPC;
+ if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+ return err;
alloc:
- get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
+ old_blkaddr = dn->data_blkaddr;
+ f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
+ &sum, seg_type, NULL, false);
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ old_blkaddr, old_blkaddr);
+ f2fs_set_data_blkaddr(dn);
- if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
- seg = CURSEG_DIRECT_IO;
-
- allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
- &sum, seg);
- set_data_blkaddr(dn);
-
- /* update i_size */
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
- dn->ofs_in_node;
- if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
- f2fs_i_size_write(dn->inode,
- ((loff_t)(fofs + 1) << PAGE_SHIFT));
+ /*
+ * i_size will be updated by direct_IO. Otherwise, we'll get stale
+ * data from unwritten block via dio_read.
+ */
return 0;
}
-ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct f2fs_map_blocks map;
- ssize_t ret = 0;
+ int flag;
+ int err = 0;
+ bool direct_io = iocb->ki_flags & IOCB_DIRECT;
+
+ /* convert inline data for Direct I/O*/
+ if (direct_io) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+
+ if (direct_io && allow_outplace_dio(inode, iocb, from))
+ return 0;
+
+ if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+ return 0;
map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
@@ -642,21 +988,50 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
map.m_len = 0;
map.m_next_pgofs = NULL;
+ map.m_next_extent = NULL;
+ map.m_seg_type = NO_CHECK_TYPE;
+ map.m_may_create = true;
- if (iocb->ki_flags & IOCB_DIRECT) {
- ret = f2fs_convert_inline_inode(inode);
- if (ret)
- return ret;
- return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+ if (direct_io) {
+ map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
+ flag = f2fs_force_buffered_io(inode, iocb, from) ?
+ F2FS_GET_BLOCK_PRE_AIO :
+ F2FS_GET_BLOCK_PRE_DIO;
+ goto map_blocks;
}
- if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
- ret = f2fs_convert_inline_inode(inode);
- if (ret)
- return ret;
+ if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
}
- if (!f2fs_has_inline_data(inode))
- return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
- return ret;
+ if (f2fs_has_inline_data(inode))
+ return err;
+
+ flag = F2FS_GET_BLOCK_PRE_AIO;
+
+map_blocks:
+ err = f2fs_map_blocks(inode, &map, 1, flag);
+ if (map.m_len > 0 && err == -ENOSPC) {
+ if (!direct_io)
+ set_inode_flag(inode, FI_NO_PREALLOC);
+ err = 0;
+ }
+ return err;
+}
+
+void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+{
+ if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+ if (lock)
+ down_read(&sbi->node_change);
+ else
+ up_read(&sbi->node_change);
+ } else {
+ if (lock)
+ f2fs_lock_op(sbi);
+ else
+ f2fs_unlock_op(sbi);
+ }
}
/*
@@ -674,14 +1049,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- int mode = create ? ALLOC_NODE : LOOKUP_NODE;
+ int mode = map->m_may_create ? ALLOC_NODE : LOOKUP_NODE;
pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
unsigned int ofs_in_node, last_ofs_in_node;
blkcnt_t prealloc;
- struct extent_info ei;
- bool allocated = false;
+ struct extent_info ei = {0,0,0};
block_t blkaddr;
+ unsigned int start_pgofs;
if (!maxblocks)
return 0;
@@ -694,19 +1069,30 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
end = pgofs + maxblocks;
if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+ if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
+ map->m_may_create)
+ goto next_dnode;
+
map->m_pblk = ei.blk + pgofs - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
map->m_flags = F2FS_MAP_MAPPED;
+ if (map->m_next_extent)
+ *map->m_next_extent = pgofs + map->m_len;
+
+ /* for hardware encryption, but to avoid potential issue in future */
+ if (flag == F2FS_GET_BLOCK_DIO)
+ f2fs_wait_on_block_writeback_range(inode,
+ map->m_pblk, map->m_len);
goto out;
}
next_dnode:
- if (create)
- f2fs_lock_op(sbi);
+ if (map->m_may_create)
+ __do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, mode);
+ err = f2fs_get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
@@ -714,17 +1100,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
err = 0;
if (map->m_next_pgofs)
*map->m_next_pgofs =
- get_next_page_offset(&dn, pgofs);
+ f2fs_get_next_page_offset(&dn, pgofs);
+ if (map->m_next_extent)
+ *map->m_next_extent =
+ f2fs_get_next_page_offset(&dn, pgofs);
}
goto unlock_out;
}
+ start_pgofs = pgofs;
prealloc = 0;
last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
@@ -732,7 +1122,17 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
goto sync_out;
}
- if (!is_valid_data_blkaddr(sbi, blkaddr)) {
+ if (is_valid_data_blkaddr(sbi, blkaddr)) {
+ /* use out-place-update for driect IO under LFS mode */
+ if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
+ map->m_may_create) {
+ err = __allocate_data_block(&dn, map->m_seg_type);
+ if (!err) {
+ blkaddr = dn.data_blkaddr;
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ }
+ }
+ } else {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -744,29 +1144,36 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
last_ofs_in_node = dn.ofs_in_node;
}
} else {
- err = __allocate_data_block(&dn);
- if (!err) {
+ WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO &&
+ flag != F2FS_GET_BLOCK_DIO);
+ err = __allocate_data_block(&dn,
+ map->m_seg_type);
+ if (!err)
set_inode_flag(inode, FI_APPEND_WRITE);
- allocated = true;
- }
}
if (err)
goto sync_out;
- map->m_flags = F2FS_MAP_NEW;
+ map->m_flags |= F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
} else {
if (flag == F2FS_GET_BLOCK_BMAP) {
map->m_pblk = 0;
goto sync_out;
}
+ if (flag == F2FS_GET_BLOCK_PRECACHE)
+ goto sync_out;
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
- }
- if (flag != F2FS_GET_BLOCK_FIEMAP ||
- blkaddr != NEW_ADDR)
goto sync_out;
+ }
+ if (flag != F2FS_GET_BLOCK_FIEMAP) {
+ /* for defragment case */
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs = pgofs + 1;
+ goto sync_out;
+ }
}
}
@@ -800,10 +1207,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
(pgofs == end || dn.ofs_in_node == end_offset)) {
dn.ofs_in_node = ofs_in_node;
- err = reserve_new_blocks(&dn, prealloc);
+ err = f2fs_reserve_new_blocks(&dn, prealloc);
if (err)
goto sync_out;
- allocated = dn.node_changed;
map->m_len += dn.ofs_in_node - ofs_in_node;
if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
@@ -818,45 +1224,100 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
else if (dn.ofs_in_node < end_offset)
goto next_block;
+ if (flag == F2FS_GET_BLOCK_PRECACHE) {
+ if (map->m_flags & F2FS_MAP_MAPPED) {
+ unsigned int ofs = start_pgofs - map->m_lblk;
+
+ f2fs_update_extent_cache_range(&dn,
+ start_pgofs, map->m_pblk + ofs,
+ map->m_len - ofs);
+ }
+ }
+
f2fs_put_dnode(&dn);
- if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ if (map->m_may_create) {
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
}
- allocated = false;
goto next_dnode;
sync_out:
+
+ /* for hardware encryption, but to avoid potential issue in future */
+ if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
+ f2fs_wait_on_block_writeback_range(inode,
+ map->m_pblk, map->m_len);
+
+ if (flag == F2FS_GET_BLOCK_PRECACHE) {
+ if (map->m_flags & F2FS_MAP_MAPPED) {
+ unsigned int ofs = start_pgofs - map->m_lblk;
+
+ f2fs_update_extent_cache_range(&dn,
+ start_pgofs, map->m_pblk + ofs,
+ map->m_len - ofs);
+ }
+ if (map->m_next_extent)
+ *map->m_next_extent = pgofs + 1;
+ }
f2fs_put_dnode(&dn);
unlock_out:
- if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ if (map->m_may_create) {
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, err);
return err;
}
-static int __get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create, int flag,
- pgoff_t *next_pgofs)
+bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
{
struct f2fs_map_blocks map;
- int ret;
+ block_t last_lblk;
+ int err;
+
+ if (pos + len > i_size_read(inode))
+ return false;
+
+ map.m_lblk = F2FS_BYTES_TO_BLK(pos);
+ map.m_next_pgofs = NULL;
+ map.m_next_extent = NULL;
+ map.m_seg_type = NO_CHECK_TYPE;
+ map.m_may_create = false;
+ last_lblk = F2FS_BLK_ALIGN(pos + len);
+
+ while (map.m_lblk < last_lblk) {
+ map.m_len = last_lblk - map.m_lblk;
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
+ if (err || map.m_len == 0)
+ return false;
+ map.m_lblk += map.m_len;
+ }
+ return true;
+}
+
+static int __get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create, int flag,
+ pgoff_t *next_pgofs, int seg_type, bool may_write)
+{
+ struct f2fs_map_blocks map;
+ int err;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
map.m_next_pgofs = next_pgofs;
+ map.m_next_extent = NULL;
+ map.m_seg_type = seg_type;
+ map.m_may_create = may_write;
- ret = f2fs_map_blocks(inode, &map, create, flag);
- if (!ret) {
+ err = f2fs_map_blocks(inode, &map, create, flag);
+ if (!err) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
bh->b_size = (u64)map.m_len << inode->i_blkbits;
}
- return ret;
+ return err;
}
static int get_data_block(struct inode *inode, sector_t iblock,
@@ -864,14 +1325,26 @@ static int get_data_block(struct inode *inode, sector_t iblock,
pgoff_t *next_pgofs)
{
return __get_data_block(inode, iblock, bh_result, create,
- flag, next_pgofs);
+ flag, next_pgofs,
+ NO_CHECK_TYPE, create);
+}
+
+static int get_data_block_dio_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return __get_data_block(inode, iblock, bh_result, create,
+ F2FS_GET_BLOCK_DIO, NULL,
+ f2fs_rw_hint_to_seg_type(inode->i_write_hint),
+ true);
}
static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_DIO, NULL);
+ F2FS_GET_BLOCK_DIO, NULL,
+ f2fs_rw_hint_to_seg_type(inode->i_write_hint),
+ false);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -882,7 +1355,8 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock,
return -EFBIG;
return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_BMAP, NULL);
+ F2FS_GET_BLOCK_BMAP, NULL,
+ NO_CHECK_TYPE, create);
}
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -895,36 +1369,109 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
return (blk << inode->i_blkbits);
}
+static int f2fs_xattr_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct page *page;
+ struct node_info ni;
+ __u64 phys = 0, len;
+ __u32 flags;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ int err = 0;
+
+ if (f2fs_has_inline_xattr(inode)) {
+ int offset;
+
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
+ inode->i_ino, false);
+ if (!page)
+ return -ENOMEM;
+
+ err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return err;
+ }
+
+ phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+ offset = offsetof(struct f2fs_inode, i_addr) +
+ sizeof(__le32) * (DEF_ADDRS_PER_INODE -
+ get_inline_xattr_addrs(inode));
+
+ phys += offset;
+ len = inline_xattr_size(inode);
+
+ f2fs_put_page(page, 1);
+
+ flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
+
+ if (!xnid)
+ flags |= FIEMAP_EXTENT_LAST;
+
+ err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+ if (err || err == 1)
+ return err;
+ }
+
+ if (xnid) {
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
+ if (!page)
+ return -ENOMEM;
+
+ err = f2fs_get_node_info(sbi, xnid, &ni);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return err;
+ }
+
+ phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+ len = inode->i_sb->s_blocksize;
+
+ f2fs_put_page(page, 1);
+
+ flags = FIEMAP_EXTENT_LAST;
+ }
+
+ if (phys)
+ err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+
+ return (err < 0 ? err : 0);
+}
+
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
pgoff_t next_pgofs;
- loff_t isize;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
- ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+ if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+ ret = f2fs_precache_extents(inode);
+ if (ret)
+ return ret;
+ }
+
+ ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
if (ret)
return ret;
+ inode_lock(inode);
+
+ if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+ ret = f2fs_xattr_fiemap(inode, fieinfo);
+ goto out;
+ }
+
if (f2fs_has_inline_data(inode)) {
ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
if (ret != -EAGAIN)
- return ret;
+ goto out;
}
- inode_lock(inode);
-
- isize = i_size_read(inode);
- if (start >= isize)
- goto out;
-
- if (start + len > isize)
- len = isize - start;
-
if (logical_to_blk(inode, len) == 0)
len = blk_to_logical(inode, 1);
@@ -943,13 +1490,11 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
/* HOLE */
if (!buffer_mapped(&map_bh)) {
start_blk = next_pgofs;
- /* Go through holes util pass the EOF */
- if (blk_to_logical(inode, start_blk) < isize)
+
+ if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
+ F2FS_I_SB(inode)->max_file_blocks))
goto prep_next;
- /* Found a hole beyond isize means no more extents.
- * Note that the premise is that filesystems don't
- * punch holes beyond isize and keep size unchanged.
- */
+
flags |= FIEMAP_EXTENT_LAST;
}
@@ -987,50 +1532,20 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return ret;
}
-static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
- unsigned nr_pages)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct fscrypt_ctx *ctx = NULL;
- struct block_device *bdev = sbi->sb->s_bdev;
- struct bio *bio;
-
- if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
- return ERR_PTR(-EFAULT);
-
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- ctx = fscrypt_get_ctx(inode, GFP_NOFS);
- if (IS_ERR(ctx))
- return ERR_CAST(ctx);
-
- /* wait the page to be moved by cleaning */
- f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
- }
-
- bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- fscrypt_release_ctx(ctx);
- return ERR_PTR(-ENOMEM);
- }
- bio->bi_bdev = bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
- bio->bi_end_io = f2fs_read_end_io;
- bio->bi_private = ctx;
-
- return bio;
-}
-
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
+ *
+ * Note that the aops->readpages() function is ONLY used for read-ahead. If
+ * this function ever deviates from doing just read-ahead, it should either
+ * use ->readpage() or do the necessary surgery to decouple ->readpages()
+ * from read-ahead.
*/
static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
- unsigned nr_pages)
+ unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
- unsigned page_idx;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
@@ -1046,12 +1561,15 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
map.m_len = 0;
map.m_flags = 0;
map.m_next_pgofs = NULL;
+ map.m_next_extent = NULL;
+ map.m_seg_type = NO_CHECK_TYPE;
+ map.m_may_create = false;
- for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
-
- prefetchw(&page->flags);
+ for (; nr_pages; nr_pages--) {
if (pages) {
- page = list_entry(pages->prev, struct page, lru);
+ page = list_last_entry(pages, struct page, lru);
+
+ prefetchw(&page->flags);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
page->index,
@@ -1066,6 +1584,9 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
if (last_block > last_block_in_file)
last_block = last_block_in_file;
+ /* just zeroing out page which is beyond EOF */
+ if (block_in_file >= last_block)
+ goto zero_out;
/*
* Map blocks using the previous result first.
*/
@@ -1078,16 +1599,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
* Then do more f2fs_map_blocks() calls until we are
* done with this page.
*/
- map.m_flags = 0;
+ map.m_lblk = block_in_file;
+ map.m_len = last_block - block_in_file;
- if (block_in_file < last_block) {
- map.m_lblk = block_in_file;
- map.m_len = last_block - block_in_file;
-
- if (f2fs_map_blocks(inode, &map, 0,
- F2FS_GET_BLOCK_READ))
- goto set_error_page;
- }
+ if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT))
+ goto set_error_page;
got_it:
if ((map.m_flags & F2FS_MAP_MAPPED)) {
block_nr = map.m_pblk + block_in_file - map.m_lblk;
@@ -1102,6 +1618,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
DATA_GENERIC))
goto set_error_page;
} else {
+zero_out:
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
@@ -1113,23 +1630,32 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
- if (bio && (last_block_in_bio != block_nr - 1)) {
+ if (bio && (last_block_in_bio != block_nr - 1 ||
+ !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
submit_and_realloc:
- __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
- bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
+ is_readahead ? REQ_RAHEAD : 0);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
}
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
}
+ /*
+ * If the page is under writeback, we need to wait for
+ * its completion to see the correct decrypted data.
+ */
+ f2fs_wait_on_block_writeback(inode, block_nr);
+
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
+ inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+ ClearPageError(page);
last_block_in_bio = block_nr;
goto next_page;
set_error_page:
@@ -1139,7 +1665,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
goto next_page;
confused:
if (bio) {
- __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
unlock_page(page);
@@ -1149,7 +1675,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
}
BUG_ON(pages && !list_empty(pages));
if (bio)
- __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
return 0;
}
@@ -1164,7 +1690,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
- ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
+ ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1, false);
return ret;
}
@@ -1172,8 +1698,8 @@ static int f2fs_read_data_pages(struct file *file,
struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- struct inode *inode = file->f_mapping->host;
- struct page *page = list_entry(pages->prev, struct page, lru);
+ struct inode *inode = mapping->host;
+ struct page *page = list_last_entry(pages, struct page, lru);
trace_f2fs_readpages(inode, page, nr_pages);
@@ -1181,20 +1707,160 @@ static int f2fs_read_data_pages(struct file *file,
if (f2fs_has_inline_data(inode))
return 0;
- return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
+ return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
}
-int do_write_data_page(struct f2fs_io_info *fio)
+static int encrypt_one_page(struct f2fs_io_info *fio)
+{
+ struct inode *inode = fio->page->mapping->host;
+ struct page *mpage;
+ gfp_t gfp_flags = GFP_NOFS;
+
+ if (!f2fs_encrypted_file(inode))
+ return 0;
+
+ /* wait for GCed page writeback via META_MAPPING */
+ f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
+
+retry_encrypt:
+ fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
+ PAGE_SIZE, 0, fio->page->index, gfp_flags);
+ if (IS_ERR(fio->encrypted_page)) {
+ /* flush pending IOs and wait for a while in the ENOMEM case */
+ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
+ f2fs_flush_merged_writes(fio->sbi);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ gfp_flags |= __GFP_NOFAIL;
+ goto retry_encrypt;
+ }
+ return PTR_ERR(fio->encrypted_page);
+ }
+
+ mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr);
+ if (mpage) {
+ if (PageUptodate(mpage))
+ memcpy(page_address(mpage),
+ page_address(fio->encrypted_page), PAGE_SIZE);
+ f2fs_put_page(mpage, 1);
+ }
+ return 0;
+}
+
+static inline bool check_inplace_update_policy(struct inode *inode,
+ struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned int policy = SM_I(sbi)->ipu_policy;
+
+ if (policy & (0x1 << F2FS_IPU_FORCE))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_UTIL) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
+ return true;
+
+ /*
+ * IPU for rewrite async pages
+ */
+ if (policy & (0x1 << F2FS_IPU_ASYNC) &&
+ fio && fio->op == REQ_OP_WRITE &&
+ !(fio->op_flags & REQ_SYNC) &&
+ !f2fs_encrypted_inode(inode))
+ return true;
+
+ /* this is only set during fdatasync */
+ if (policy & (0x1 << F2FS_IPU_FSYNC) &&
+ is_inode_flag_set(inode, FI_NEED_IPU))
+ return true;
+
+ if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
+ return true;
+
+ return false;
+}
+
+bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+ if (f2fs_is_pinned_file(inode))
+ return true;
+
+ /* if this is cold file, we should overwrite to avoid fragmentation */
+ if (file_is_cold(inode))
+ return true;
+
+ return check_inplace_update_policy(inode, fio);
+}
+
+bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (test_opt(sbi, LFS))
+ return true;
+ if (S_ISDIR(inode->i_mode))
+ return true;
+ if (IS_NOQUOTA(inode))
+ return true;
+ if (f2fs_is_atomic_file(inode))
+ return true;
+ if (fio) {
+ if (is_cold_data(fio->page))
+ return true;
+ if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+ return true;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
+ return true;
+ }
+ return false;
+}
+
+static inline bool need_inplace_update(struct f2fs_io_info *fio)
+{
+ struct inode *inode = fio->page->mapping->host;
+
+ if (f2fs_should_update_outplace(inode, fio))
+ return false;
+
+ return f2fs_should_update_inplace(inode, fio);
+}
+
+int f2fs_do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
+ struct extent_info ei = {0,0,0};
+ struct node_info ni;
+ bool ipu_force = false;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+ if (need_inplace_update(fio) &&
+ f2fs_lookup_extent_cache(inode, page->index, &ei)) {
+ fio->old_blkaddr = ei.blk + page->index - ei.fofs;
+
+ if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
+ DATA_GENERIC))
+ return -EFAULT;
+
+ ipu_force = true;
+ fio->need_lock = LOCK_DONE;
+ goto got_it;
+ }
+
+ /* Deadlock due to between page->lock and f2fs_lock_op */
+ if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
+ return -EAGAIN;
+
+ err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
- return err;
+ goto out;
fio->old_blkaddr = dn.data_blkaddr;
@@ -1204,32 +1870,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
clear_cold_data(page);
goto out_writepage;
}
-
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- gfp_t gfp_flags = GFP_NOFS;
-
- /* wait for GCed encrypted page writeback */
- f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
- fio->old_blkaddr);
-retry_encrypt:
- fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
- gfp_flags);
- if (IS_ERR(fio->encrypted_page)) {
- err = PTR_ERR(fio->encrypted_page);
- if (err == -ENOMEM) {
- /* flush pending ios and wait for a while */
- f2fs_flush_merged_bios(F2FS_I_SB(inode));
- congestion_wait(BLK_RW_ASYNC, HZ/50);
- gfp_flags |= __GFP_NOFAIL;
- err = 0;
- goto retry_encrypt;
- }
- goto out_writepage;
- }
- }
-
- set_page_writeback(page);
-
+got_it:
if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC)) {
@@ -1240,27 +1881,68 @@ int do_write_data_page(struct f2fs_io_info *fio)
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) &&
- !is_cold_data(page) &&
- !IS_ATOMIC_WRITTEN_PAGE(page) &&
- need_inplace_update(inode))) {
- rewrite_data_page(fio);
+ if (ipu_force || (is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) &&
+ need_inplace_update(fio))) {
+ err = encrypt_one_page(fio);
+ if (err)
+ goto out_writepage;
+
+ set_page_writeback(page);
+ ClearPageError(page);
+ f2fs_put_dnode(&dn);
+ if (fio->need_lock == LOCK_REQ)
+ f2fs_unlock_op(fio->sbi);
+ err = f2fs_inplace_write_data(fio);
+ if (err) {
+ if (f2fs_encrypted_file(inode))
+ fscrypt_pullback_bio_page(&fio->encrypted_page,
+ true);
+ if (PageWriteback(page))
+ end_page_writeback(page);
+ }
+ trace_f2fs_do_write_data_page(fio->page, IPU);
set_inode_flag(inode, FI_UPDATE_WRITE);
- trace_f2fs_do_write_data_page(page, IPU);
- } else {
- write_data_page(&dn, fio);
- trace_f2fs_do_write_data_page(page, OPU);
- set_inode_flag(inode, FI_APPEND_WRITE);
- if (page->index == 0)
- set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+ return err;
}
+
+ if (fio->need_lock == LOCK_RETRY) {
+ if (!f2fs_trylock_op(fio->sbi)) {
+ err = -EAGAIN;
+ goto out_writepage;
+ }
+ fio->need_lock = LOCK_REQ;
+ }
+
+ err = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
+ if (err)
+ goto out_writepage;
+
+ fio->version = ni.version;
+
+ err = encrypt_one_page(fio);
+ if (err)
+ goto out_writepage;
+
+ set_page_writeback(page);
+ ClearPageError(page);
+
+ /* LFS mode write path */
+ f2fs_outplace_write_data(&dn, fio);
+ trace_f2fs_do_write_data_page(page, OPU);
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ if (page->index == 0)
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
out_writepage:
f2fs_put_dnode(&dn);
+out:
+ if (fio->need_lock == LOCK_REQ)
+ f2fs_unlock_op(fio->sbi);
return err;
}
-static int f2fs_write_data_page(struct page *page,
- struct writeback_control *wbc)
+static int __write_data_page(struct page *page, bool *submitted,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -1273,15 +1955,36 @@ static int f2fs_write_data_page(struct page *page,
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
+ .ino = inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
- .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
+ .op_flags = wbc_to_write_flags(wbc),
+ .old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
+ .submitted = false,
+ .need_lock = LOCK_RETRY,
+ .io_type = io_type,
+ .io_wbc = wbc,
};
trace_f2fs_writepage(page, DATA);
+ /* we should bypass data pages to proceed the kworkder jobs */
+ if (unlikely(f2fs_cp_error(sbi))) {
+ mapping_set_error(page->mapping, -EIO);
+ /*
+ * don't drop any dirty dentry pages for keeping lastest
+ * directory structure.
+ */
+ if (S_ISDIR(inode->i_mode))
+ goto redirty_out;
+ goto out;
+ }
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto redirty_out;
+
if (page->index < end_index)
goto write;
@@ -1295,25 +1998,18 @@ static int f2fs_write_data_page(struct page *page,
zero_user_segment(page, offset, PAGE_SIZE);
write:
- if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
- goto redirty_out;
if (f2fs_is_drop_cache(inode))
goto out;
/* we should not write 0'th page having journal header */
if (f2fs_is_volatile_file(inode) && (!page->index ||
(!wbc->for_reclaim &&
- available_free_memory(sbi, BASE_CHECK))))
+ f2fs_available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
- /* we should bypass data pages to proceed the kworkder jobs */
- if (unlikely(f2fs_cp_error(sbi))) {
- mapping_set_error(page->mapping, -EIO);
- goto out;
- }
-
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
- err = do_write_data_page(&fio);
+ fio.need_lock = LOCK_DONE;
+ err = f2fs_do_write_data_page(&fio);
goto done;
}
@@ -1321,21 +2017,37 @@ static int f2fs_write_data_page(struct page *page,
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0, 0))
goto redirty_out;
+ else
+ set_inode_flag(inode, FI_HOT_DATA);
err = -EAGAIN;
- f2fs_lock_op(sbi);
- if (f2fs_has_inline_data(inode))
+ if (f2fs_has_inline_data(inode)) {
err = f2fs_write_inline_data(inode, page);
- if (err == -EAGAIN)
- err = do_write_data_page(&fio);
- if (F2FS_I(inode)->last_disk_size < psize)
- F2FS_I(inode)->last_disk_size = psize;
- f2fs_unlock_op(sbi);
+ if (!err)
+ goto out;
+ }
+
+ if (err == -EAGAIN) {
+ err = f2fs_do_write_data_page(&fio);
+ if (err == -EAGAIN) {
+ fio.need_lock = LOCK_REQ;
+ err = f2fs_do_write_data_page(&fio);
+ }
+ }
+
+ if (err) {
+ file_set_keep_isize(inode);
+ } else {
+ down_write(&F2FS_I(inode)->i_sem);
+ if (F2FS_I(inode)->last_disk_size < psize)
+ F2FS_I(inode)->last_disk_size = psize;
+ up_write(&F2FS_I(inode)->i_sem);
+ }
+
done:
if (err && err != -ENOENT)
goto redirty_out;
- clear_cold_data(page);
out:
inode_dec_dirty_pages(inode);
if (err) {
@@ -1344,35 +2056,59 @@ static int f2fs_write_data_page(struct page *page,
}
if (wbc->for_reclaim) {
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
- remove_dirty_inode(inode);
+ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ f2fs_remove_dirty_inode(inode);
+ submitted = NULL;
}
unlock_page(page);
- f2fs_balance_fs(sbi, need_balance_fs);
+ if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode))
+ f2fs_balance_fs(sbi, need_balance_fs);
- if (unlikely(f2fs_cp_error(sbi)))
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_submit_merged_write(sbi, DATA);
+ submitted = NULL;
+ }
+
+ if (submitted)
+ *submitted = fio.submitted;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
+ /*
+ * pageout() in MM traslates EAGAIN, so calls handle_write_error()
+ * -> mapping_set_error() -> set_bit(AS_EIO, ...).
+ * file_write_and_wait_range() will see EIO error, which is critical
+ * to return value of fsync() followed by atomic_write failure to user.
+ */
+ if (!err || wbc->for_reclaim)
+ return AOP_WRITEPAGE_ACTIVATE;
unlock_page(page);
return err;
}
+static int f2fs_write_data_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __write_data_page(page, NULL, wbc, FS_DATA_IO);
+}
+
/*
* This function was copied from write_cche_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
@@ -1385,6 +2121,12 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
pagevec_init(&pvec, 0);
+ if (get_dirty_pages(mapping->host) <=
+ SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
+ set_inode_flag(mapping->host, FI_HOT_DATA);
+ else
+ clear_inode_flag(mapping->host, FI_HOT_DATA);
+
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
@@ -1411,21 +2153,24 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
while (!done && (index <= end)) {
int i;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1);
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ bool submitted = false;
- if (page->index > end) {
+ /* give a priority to WB_SYNC threads */
+ if (atomic_read(&sbi->wb_sync_req[DATA]) &&
+ wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
done_index = page->index;
-
+retry_write:
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -1442,26 +2187,43 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page,
- DATA, true);
+ DATA, true, true);
else
goto continue_unlock;
}
- BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- ret = mapping->a_ops->writepage(page, wbc);
+ ret = __write_data_page(page, &submitted, wbc, io_type);
if (unlikely(ret)) {
+ /*
+ * keep nr_to_write, since vfs uses this to
+ * get # of written pages.
+ */
+ if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ unlock_page(page);
+ ret = 0;
+ continue;
+ } else if (ret == -EAGAIN) {
+ ret = 0;
+ if (wbc->sync_mode == WB_SYNC_ALL) {
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC,
+ HZ/50);
+ goto retry_write;
+ }
+ continue;
+ }
done_index = page->index + 1;
done = 1;
break;
- } else {
+ } else if (submitted) {
nwritten++;
}
if (--wbc->nr_to_write <= 0 &&
- wbc->sync_mode == WB_SYNC_NONE) {
+ wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
@@ -1480,19 +2242,35 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
mapping->writeback_index = done_index;
if (nwritten)
- f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
- NULL, 0, DATA, WRITE);
+ f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+ NULL, 0, DATA);
return ret;
}
-static int f2fs_write_data_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+static inline bool __should_serialize_io(struct inode *inode,
+ struct writeback_control *wbc)
+{
+ if (!S_ISREG(inode->i_mode))
+ return false;
+ if (IS_NOQUOTA(inode))
+ return false;
+ if (wbc->sync_mode != WB_SYNC_ALL)
+ return true;
+ if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
+ return true;
+ return false;
+}
+
+static int __f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct blk_plug plug;
int ret;
+ bool locked = false;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
@@ -1502,30 +2280,48 @@ static int f2fs_write_data_pages(struct address_space *mapping,
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
- if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
+ /* during POR, we don't need to trigger writepage at all. */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto skip_write;
+
+ if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) &&
+ wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
- available_free_memory(sbi, DIRTY_DENTS))
+ f2fs_available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
/* skip writing during file defragment */
if (is_inode_flag_set(inode, FI_DO_DEFRAG))
goto skip_write;
- /* during POR, we don't need to trigger writepage at all. */
- if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
- goto skip_write;
-
trace_f2fs_writepages(mapping->host, wbc, DATA);
+ /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_inc(&sbi->wb_sync_req[DATA]);
+ else if (atomic_read(&sbi->wb_sync_req[DATA]))
+ goto skip_write;
+
+ if (__should_serialize_io(inode, wbc)) {
+ mutex_lock(&sbi->writepages);
+ locked = true;
+ }
+
blk_start_plug(&plug);
- ret = f2fs_write_cache_pages(mapping, wbc);
+ ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
+
+ if (locked)
+ mutex_unlock(&sbi->writepages);
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_dec(&sbi->wb_sync_req[DATA]);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
*/
- remove_dirty_inode(inode);
+ f2fs_remove_dirty_inode(inode);
return ret;
skip_write:
@@ -1534,14 +2330,31 @@ static int f2fs_write_data_pages(struct address_space *mapping,
return 0;
}
+static int f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = mapping->host;
+
+ return __f2fs_write_data_pages(mapping, wbc,
+ F2FS_I(inode)->cp_task == current ?
+ FS_CP_DATA_IO : FS_DATA_IO);
+}
+
static void f2fs_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
loff_t i_size = i_size_read(inode);
if (to > i_size) {
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
truncate_pagecache(inode, i_size);
- truncate_blocks(inode, i_size, true);
+ if (!IS_NOQUOTA(inode))
+ f2fs_truncate_blocks(inode, i_size, true);
+
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
@@ -1554,24 +2367,32 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
struct dnode_of_data dn;
struct page *ipage;
bool locked = false;
- struct extent_info ei;
+ struct extent_info ei = {0,0,0};
int err = 0;
+ int flag;
/*
* we already allocated all the blocks, so we don't need to get
* the block addresses when there is no need to fill the page.
*/
- if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE)
+ if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
+ !is_inode_flag_set(inode, FI_NO_PREALLOC))
return 0;
+ /* f2fs_lock_op avoids race between write CP and convert_inline_page */
+ if (f2fs_has_inline_data(inode) && pos + len > MAX_INLINE_DATA(inode))
+ flag = F2FS_GET_BLOCK_DEFAULT;
+ else
+ flag = F2FS_GET_BLOCK_PRE_AIO;
+
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_MASK) >= i_size_read(inode)) {
- f2fs_lock_op(sbi);
+ __do_map_lock(sbi, flag, true);
locked = true;
}
restart:
/* check inline_data */
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
@@ -1580,8 +2401,8 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
- if (pos + len <= MAX_INLINE_DATA) {
- read_inline_data(page, ipage);
+ if (pos + len <= MAX_INLINE_DATA(inode)) {
+ f2fs_do_read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
set_inline_node(ipage);
@@ -1599,10 +2420,12 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
dn.data_blkaddr = ei.blk + index - ei.fofs;
} else {
/* hole case */
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
- f2fs_lock_op(sbi);
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+ true);
+ WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
locked = true;
goto restart;
}
@@ -1616,7 +2439,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
- f2fs_unlock_op(sbi);
+ __do_map_lock(sbi, flag, false);
return err;
}
@@ -1628,12 +2451,34 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
- bool need_balance = false;
+ bool need_balance = false, drop_atomic = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
+ if (trace_android_fs_datawrite_start_enabled()) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_datawrite_start(inode, pos, len,
+ current->pid, path,
+ current->comm);
+ }
trace_f2fs_write_begin(inode, pos, len, flags);
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ goto fail;
+
+ if ((f2fs_is_atomic_file(inode) &&
+ !f2fs_available_free_memory(sbi, INMEM_PAGES)) ||
+ is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
+ err = -ENOMEM;
+ drop_atomic = true;
+ goto fail;
+ }
+
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
@@ -1649,7 +2494,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
* Do not use grab_cache_page_write_begin() to avoid deadlock due to
* wait_for_stable_page. Will wait that below with our IO control.
*/
- page = pagecache_get_page(mapping, index,
+ page = f2fs_pagecache_get_page(mapping, index,
FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
if (!page) {
err = -ENOMEM;
@@ -1663,7 +2508,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
if (err)
goto fail;
- if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) {
+ if (need_balance && !IS_NOQUOTA(inode) &&
+ has_not_enough_free_secs(sbi, 0, 0)) {
unlock_page(page);
f2fs_balance_fs(sbi, true);
lock_page(page);
@@ -1674,34 +2520,23 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
}
}
- f2fs_wait_on_page_writeback(page, DATA, false);
-
- /* wait for GCed encrypted page writeback */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ f2fs_wait_on_page_writeback(page, DATA, false, true);
if (len == PAGE_SIZE || PageUptodate(page))
return 0;
+ if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+ zero_user_segment(page, len, PAGE_SIZE);
+ return 0;
+ }
+
if (blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
} else {
- struct bio *bio;
-
- bio = f2fs_grab_bio(inode, blkaddr, 1);
- if (IS_ERR(bio)) {
- err = PTR_ERR(bio);
+ err = f2fs_submit_page_read(inode, page, blkaddr);
+ if (err)
goto fail;
- }
- bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC);
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
- bio_put(bio);
- err = -EFAULT;
- goto fail;
- }
-
- __submit_bio(sbi, bio, DATA);
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -1718,6 +2553,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
+ if (drop_atomic)
+ f2fs_drop_inmem_pages_all(sbi, false);
return err;
}
@@ -1728,6 +2565,7 @@ static int f2fs_write_end(struct file *file,
{
struct inode *inode = page->mapping->host;
+ trace_android_fs_datawrite_end(inode, pos, len);
trace_f2fs_write_end(inode, pos, len, copied);
/*
@@ -1736,7 +2574,7 @@ static int f2fs_write_end(struct file *file,
* let generic_perform_write() try to copy data again through copied=0.
*/
if (!PageUptodate(page)) {
- if (unlikely(copied != PAGE_SIZE))
+ if (unlikely(copied != len))
copied = 0;
else
SetPageUptodate(page);
@@ -1745,7 +2583,6 @@ static int f2fs_write_end(struct file *file,
goto unlock_out;
set_page_dirty(page);
- clear_cold_data(page);
if (pos + copied > i_size_read(inode))
f2fs_i_size_write(inode, pos + copied);
@@ -1758,47 +2595,164 @@ static int f2fs_write_end(struct file *file,
static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
loff_t offset)
{
- unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
+ unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
+ unsigned blkbits = i_blkbits;
+ unsigned blocksize_mask = (1 << blkbits) - 1;
+ unsigned long align = offset | iov_iter_alignment(iter);
+ struct block_device *bdev = inode->i_sb->s_bdev;
- if (offset & blocksize_mask)
- return -EINVAL;
-
- if (iov_iter_alignment(iter) & blocksize_mask)
- return -EINVAL;
-
+ if (align & blocksize_mask) {
+ if (bdev)
+ blkbits = blksize_bits(bdev_logical_block_size(bdev));
+ blocksize_mask = (1 << blkbits) - 1;
+ if (align & blocksize_mask)
+ return -EINVAL;
+ return 1;
+ }
return 0;
}
+static void f2fs_dio_end_io(struct bio *bio)
+{
+ struct f2fs_private_dio *dio = bio->bi_private;
+
+ dec_page_count(F2FS_I_SB(dio->inode),
+ dio->write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
+
+ bio->bi_private = dio->orig_private;
+ bio->bi_end_io = dio->orig_end_io;
+
+ kvfree(dio);
+
+ bio_endio(bio);
+}
+
+static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode,
+ loff_t file_offset)
+{
+ struct f2fs_private_dio *dio;
+ bool write = (bio_op(bio) == REQ_OP_WRITE);
+
+ dio = f2fs_kzalloc(F2FS_I_SB(inode),
+ sizeof(struct f2fs_private_dio), GFP_NOFS);
+ if (!dio)
+ goto out;
+
+ dio->inode = inode;
+ dio->orig_end_io = bio->bi_end_io;
+ dio->orig_private = bio->bi_private;
+ dio->write = write;
+
+ bio->bi_end_io = f2fs_dio_end_io;
+ bio->bi_private = dio;
+
+ inc_page_count(F2FS_I_SB(inode),
+ write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
+
+ submit_bio(bio);
+ return;
+out:
+ bio->bi_error = -EIO;
+ bio_endio(bio);
+}
+
static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
int rw = iov_iter_rw(iter);
int err;
+ enum rw_hint hint = iocb->ki_hint;
+ int whint_mode = F2FS_OPTION(sbi).whint_mode;
+ bool do_opu;
err = check_direct_IO(inode, iter, offset);
if (err)
- return err;
+ return err < 0 ? err : 0;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ if (f2fs_force_buffered_io(inode, iocb, iter))
return 0;
- if (test_opt(F2FS_I_SB(inode), LFS))
- return 0;
+
+ do_opu = allow_outplace_dio(inode, iocb, iter);
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
- down_read(&F2FS_I(inode)->dio_rwsem[rw]);
- err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
- up_read(&F2FS_I(inode)->dio_rwsem[rw]);
+ if (trace_android_fs_dataread_start_enabled() &&
+ (rw == READ)) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_dataread_start(inode, offset,
+ count, current->pid, path,
+ current->comm);
+ }
+ if (trace_android_fs_datawrite_start_enabled() &&
+ (rw == WRITE)) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_datawrite_start(inode, offset, count,
+ current->pid, path,
+ current->comm);
+ }
+ if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
+ iocb->ki_hint = WRITE_LIFE_NOT_SET;
+
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!down_read_trylock(&fi->i_gc_rwsem[rw])) {
+ iocb->ki_hint = hint;
+ err = -EAGAIN;
+ goto out;
+ }
+ if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) {
+ up_read(&fi->i_gc_rwsem[rw]);
+ iocb->ki_hint = hint;
+ err = -EAGAIN;
+ goto out;
+ }
+ } else {
+ down_read(&fi->i_gc_rwsem[rw]);
+ if (do_opu)
+ down_read(&fi->i_gc_rwsem[READ]);
+ }
+
+ err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+ iter, rw == WRITE ? get_data_block_dio_write :
+ get_data_block_dio, NULL, f2fs_dio_submit_bio,
+ DIO_LOCKING | DIO_SKIP_HOLES);
+
+ if (do_opu)
+ up_read(&fi->i_gc_rwsem[READ]);
+
+ up_read(&fi->i_gc_rwsem[rw]);
if (rw == WRITE) {
- if (err > 0)
- set_inode_flag(inode, FI_UPDATE_WRITE);
- else if (err < 0)
+ if (whint_mode == WHINT_MODE_OFF)
+ iocb->ki_hint = hint;
+ if (err > 0) {
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
+ err);
+ if (!do_opu)
+ set_inode_flag(inode, FI_UPDATE_WRITE);
+ } else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
+ }
}
+out:
+ if (trace_android_fs_dataread_start_enabled() &&
+ (rw == READ))
+ trace_android_fs_dataread_end(inode, offset, count);
+ if (trace_android_fs_datawrite_start_enabled() &&
+ (rw == WRITE))
+ trace_android_fs_datawrite_end(inode, offset, count);
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
@@ -1816,22 +2770,22 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
return;
if (PageDirty(page)) {
- if (inode->i_ino == F2FS_META_INO(sbi))
+ if (inode->i_ino == F2FS_META_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_META);
- else if (inode->i_ino == F2FS_NODE_INO(sbi))
+ } else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_NODES);
- else
+ } else {
inode_dec_dirty_pages(inode);
+ f2fs_remove_dirty_inode(inode);
+ }
}
clear_cold_data(page);
- /* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
- return;
+ return f2fs_drop_inmem_page(inode, page);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ f2fs_clear_page_private(page);
}
int f2fs_release_page(struct page *page, gfp_t wait)
@@ -1845,40 +2799,10 @@ int f2fs_release_page(struct page *page, gfp_t wait)
return 0;
clear_cold_data(page);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ f2fs_clear_page_private(page);
return 1;
}
-/*
- * This was copied from __set_page_dirty_buffers which gives higher performance
- * in very high speed storages. (e.g., pmem)
- */
-void f2fs_set_page_dirty_nobuffers(struct page *page)
-{
- struct address_space *mapping = page->mapping;
- unsigned long flags;
-
- if (unlikely(!mapping))
- return;
-
- spin_lock(&mapping->private_lock);
- lock_page_memcg(page);
- SetPageDirty(page);
- spin_unlock(&mapping->private_lock);
-
- spin_lock_irqsave(&mapping->tree_lock, flags);
- WARN_ON_ONCE(!PageUptodate(page));
- account_page_dirtied(page, mapping);
- radix_tree_tag_set(&mapping->page_tree,
- page_index(page), PAGECACHE_TAG_DIRTY);
- spin_unlock_irqrestore(&mapping->tree_lock, flags);
- unlock_page_memcg(page);
-
- __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- return;
-}
-
static int f2fs_set_data_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
@@ -1889,9 +2813,9 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (!PageUptodate(page))
SetPageUptodate(page);
- if (f2fs_is_atomic_file(inode)) {
+ if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
- register_inmem_page(inode, page);
+ f2fs_register_inmem_page(inode, page);
return 1;
}
/*
@@ -1902,8 +2826,8 @@ static int f2fs_set_data_page_dirty(struct page *page)
}
if (!PageDirty(page)) {
- f2fs_set_page_dirty_nobuffers(page);
- update_dirty_page(inode, page);
+ __set_page_dirty_nobuffers(page);
+ f2fs_update_dirty_page(inode, page);
return 1;
}
return 0;
@@ -1936,15 +2860,15 @@ int f2fs_migrate_page(struct address_space *mapping,
BUG_ON(PageWriteback(page));
/* migrating an atomic written page is safe with the inmem_lock hold */
- if (atomic_written && !mutex_trylock(&fi->inmem_lock))
- return -EAGAIN;
+ if (atomic_written) {
+ if (mode != MIGRATE_SYNC)
+ return -EBUSY;
+ if (!mutex_trylock(&fi->inmem_lock))
+ return -EAGAIN;
+ }
- /*
- * A reference is expected if PagePrivate set when move mapping,
- * however F2FS breaks this for maintaining dirty page counts when
- * truncating pages. So here adjusting the 'extra_count' make it work.
- */
- extra_count = (atomic_written ? 1 : 0) - page_has_private(page);
+ /* one extra reference was held for atomic_write page */
+ extra_count = atomic_written ? 1 : 0;
rc = migrate_page_move_mapping(mapping, newpage,
page, NULL, mode, extra_count);
if (rc != MIGRATEPAGE_SUCCESS) {
@@ -1965,9 +2889,10 @@ int f2fs_migrate_page(struct address_space *mapping,
get_page(newpage);
}
- if (PagePrivate(page))
- SetPagePrivate(newpage);
- set_page_private(newpage, page_private(page));
+ if (PagePrivate(page)) {
+ f2fs_set_page_private(newpage, page_private(page));
+ f2fs_clear_page_private(page);
+ }
migrate_page_copy(newpage, page);
@@ -1991,3 +2916,38 @@ const struct address_space_operations f2fs_dblock_aops = {
.migratepage = f2fs_migrate_page,
#endif
};
+
+void f2fs_clear_radix_tree_dirty_tag(struct page *page)
+{
+ struct address_space *mapping = page_mapping(page);
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ radix_tree_tag_clear(&mapping->page_tree, page_index(page),
+ PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+}
+
+int __init f2fs_init_post_read_processing(void)
+{
+ bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0);
+ if (!bio_post_read_ctx_cache)
+ goto fail;
+ bio_post_read_ctx_pool =
+ mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
+ bio_post_read_ctx_cache);
+ if (!bio_post_read_ctx_pool)
+ goto fail_free_cache;
+ return 0;
+
+fail_free_cache:
+ kmem_cache_destroy(bio_post_read_ctx_cache);
+fail:
+ return -ENOMEM;
+}
+
+void __exit f2fs_destroy_post_read_processing(void)
+{
+ mempool_destroy(bio_post_read_ctx_pool);
+ kmem_cache_destroy(bio_post_read_ctx_cache);
+}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 687998e..d00ba9b 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* f2fs debugging statistics
*
@@ -5,10 +6,6 @@
* http://www.samsung.com/
* Copyright (c) 2012 Linux Foundation
* Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
@@ -45,12 +42,41 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+ si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+ si->nquota_files = sbi->nquota_files;
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
- si->wb_bios = atomic_read(&sbi->nr_wb_bios);
+ si->aw_cnt = atomic_read(&sbi->aw_cnt);
+ si->vw_cnt = atomic_read(&sbi->vw_cnt);
+ si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
+ si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
+ si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ);
+ si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE);
+ si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
+ si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+ si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA);
+ si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE);
+ si->nr_rd_meta = get_pages(sbi, F2FS_RD_META);
+ if (SM_I(sbi) && SM_I(sbi)->fcc_info) {
+ si->nr_flushed =
+ atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
+ si->nr_flushing =
+ atomic_read(&SM_I(sbi)->fcc_info->queued_flush);
+ si->flush_list_empty =
+ llist_empty(&SM_I(sbi)->fcc_info->issue_list);
+ }
+ if (SM_I(sbi) && SM_I(sbi)->dcc_info) {
+ si->nr_discarded =
+ atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
+ si->nr_discarding =
+ atomic_read(&SM_I(sbi)->dcc_info->queued_discard);
+ si->nr_discard_cmd =
+ atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+ si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks;
+ }
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
@@ -61,6 +87,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->inline_xattr = atomic_read(&sbi->inline_xattr);
si->inline_inode = atomic_read(&sbi->inline_inode);
si->inline_dir = atomic_read(&sbi->inline_dir);
+ si->append = sbi->im[APPEND_INO].ino_num;
+ si->update = sbi->im[UPDATE_INO].ino_num;
si->orphans = sbi->im[ORPHAN_INO].ino_num;
si->utilization = utilization(sbi);
@@ -68,14 +96,22 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->free_secs = free_sections(sbi);
si->prefree_count = prefree_segments(sbi);
si->dirty_count = dirty_segments(sbi);
- si->node_pages = NODE_MAPPING(sbi)->nrpages;
- si->meta_pages = META_MAPPING(sbi)->nrpages;
+ if (sbi->node_inode)
+ si->node_pages = NODE_MAPPING(sbi)->nrpages;
+ if (sbi->meta_inode)
+ si->meta_pages = META_MAPPING(sbi)->nrpages;
si->nats = NM_I(sbi)->nat_cnt;
si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
si->sits = MAIN_SEGS(sbi);
si->dirty_sits = SIT_I(sbi)->dirty_sentries;
- si->fnids = NM_I(sbi)->fcnt;
+ si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
+ si->avail_nids = NM_I(sbi)->available_nids;
+ si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
si->bg_gc = sbi->bg_gc;
+ si->io_skip_bggc = sbi->io_skip_bggc;
+ si->other_skip_bggc = sbi->other_skip_bggc;
+ si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC];
+ si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC];
si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
/ 2;
@@ -87,10 +123,13 @@ static void update_general_status(struct f2fs_sb_info *sbi)
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
si->curseg[i] = curseg->segno;
- si->cursec[i] = curseg->segno / sbi->segs_per_sec;
- si->curzone[i] = si->cursec[i] / sbi->secs_per_zone;
+ si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
+ si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
}
+ for (i = META_CP; i < META_MAX; i++)
+ si->meta_count[i] = atomic_read(&sbi->meta_count[i]);
+
for (i = 0; i < 2; i++) {
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
@@ -112,10 +151,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
bimodal = 0;
total_vblocks = 0;
- blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
+ blks_per_sec = BLKS_PER_SEC(sbi);
hblks_per_sec = blks_per_sec / 2;
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
- vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+ vblocks = get_valid_blocks(sbi, segno, true);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -138,16 +177,18 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
static void update_mem_info(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
- unsigned npages;
int i;
if (si->base_mem)
goto get_cache;
- si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
+ /* build stat */
+ si->base_mem = sizeof(struct f2fs_stat_info);
+
+ /* build superblock */
+ si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
si->base_mem += 2 * sizeof(struct f2fs_inode_info);
si->base_mem += sizeof(*sbi->ckpt);
- si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
/* build sm */
si->base_mem += sizeof(struct f2fs_sm_info);
@@ -157,10 +198,9 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
- if (f2fs_discard_en(sbi))
- si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+ si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
si->base_mem += SIT_VBLOCK_MAP_SIZE;
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi))
si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -181,6 +221,11 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build nm */
si->base_mem += sizeof(struct f2fs_nm_info);
si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+ si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+ si->base_mem += NM_I(sbi)->nat_blocks *
+ f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
+ si->base_mem += NM_I(sbi)->nat_blocks / 8;
+ si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
get_cache:
si->cache_mem = 0;
@@ -190,16 +235,23 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->cache_mem += sizeof(struct f2fs_gc_kthread);
/* build merge flush thread */
- if (SM_I(sbi)->cmd_control_info)
+ if (SM_I(sbi)->fcc_info)
si->cache_mem += sizeof(struct flush_cmd_control);
+ if (SM_I(sbi)->dcc_info) {
+ si->cache_mem += sizeof(struct discard_cmd_control);
+ si->cache_mem += sizeof(struct discard_cmd) *
+ atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+ }
/* free nids */
- si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+ si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
+ NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
+ sizeof(struct free_nid);
si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
sizeof(struct nat_entry_set);
si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
- for (i = 0; i <= ORPHAN_INO; i++)
+ for (i = 0; i < MAX_INO_ENTRY; i++)
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
si->cache_mem += atomic_read(&sbi->total_ext_tree) *
sizeof(struct extent_tree);
@@ -207,10 +259,14 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
sizeof(struct extent_node);
si->page_mem = 0;
- npages = NODE_MAPPING(sbi)->nrpages;
- si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
- npages = META_MAPPING(sbi)->nrpages;
- si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+ if (sbi->node_inode) {
+ unsigned npages = NODE_MAPPING(sbi)->nrpages;
+ si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+ }
+ if (sbi->meta_inode) {
+ unsigned npages = META_MAPPING(sbi)->nrpages;
+ si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+ }
}
static int stat_show(struct seq_file *s, void *v)
@@ -223,9 +279,11 @@ static int stat_show(struct seq_file *s, void *v)
list_for_each_entry(si, &f2fs_stat_list, stat_list) {
update_general_status(si->sbi);
- seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+ seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
si->sbi->sb->s_bdev, i++,
- f2fs_readonly(si->sbi->sb) ? "RO": "RW");
+ f2fs_readonly(si->sbi->sb) ? "RO": "RW",
+ is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ?
+ "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good"));
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -250,8 +308,8 @@ static int stat_show(struct seq_file *s, void *v)
si->inline_inode);
seq_printf(s, " - Inline_dentry Inode: %u\n",
si->inline_dir);
- seq_printf(s, " - Orphan Inode: %u\n",
- si->orphans);
+ seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n",
+ si->orphans, si->append, si->update);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
@@ -287,6 +345,13 @@ static int stat_show(struct seq_file *s, void *v)
si->prefree_count, si->free_segs, si->free_secs);
seq_printf(s, "CP calls: %d (BG: %d)\n",
si->cp_count, si->bg_cp_count);
+ seq_printf(s, " - cp blocks : %u\n", si->meta_count[META_CP]);
+ seq_printf(s, " - sit blocks : %u\n",
+ si->meta_count[META_SIT]);
+ seq_printf(s, " - nat blocks : %u\n",
+ si->meta_count[META_NAT]);
+ seq_printf(s, " - ssa blocks : %u\n",
+ si->meta_count[META_SSA]);
seq_printf(s, "GC calls: %d (BG: %d)\n",
si->call_count, si->bg_gc);
seq_printf(s, " - data segments : %d (%d)\n",
@@ -299,6 +364,12 @@ static int stat_show(struct seq_file *s, void *v)
si->bg_data_blks);
seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks,
si->bg_node_blks);
+ seq_printf(s, "Skipped : atomic write %llu (%llu)\n",
+ si->skipped_atomic_files[BG_GC] +
+ si->skipped_atomic_files[FG_GC],
+ si->skipped_atomic_files[BG_GC]);
+ seq_printf(s, "BG skip : IO: %u, Other: %u\n",
+ si->io_skip_bggc, si->other_skip_bggc);
seq_puts(s, "\nExtent Cache:\n");
seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
si->hit_largest, si->hit_cached,
@@ -310,22 +381,37 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
si->ext_tree, si->zombie_tree, si->ext_node);
seq_puts(s, "\nBalancing F2FS Async:\n");
- seq_printf(s, " - inmem: %4d, wb_bios: %4d\n",
- si->inmem_pages, si->wb_bios);
+ seq_printf(s, " - DIO (R: %4d, W: %4d)\n",
+ si->nr_dio_read, si->nr_dio_write);
+ seq_printf(s, " - IO_R (Data: %4d, Node: %4d, Meta: %4d\n",
+ si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta);
+ seq_printf(s, " - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), "
+ "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
+ si->nr_wb_cp_data, si->nr_wb_data,
+ si->nr_flushing, si->nr_flushed,
+ si->flush_list_empty,
+ si->nr_discarding, si->nr_discarded,
+ si->nr_discard_cmd, si->undiscard_blks);
+ seq_printf(s, " - inmem: %4d, atomic IO: %4d (Max. %4d), "
+ "volatile IO: %4d (Max. %4d)\n",
+ si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
+ si->vw_cnt, si->max_vw_cnt);
seq_printf(s, " - nodes: %4d in %4d\n",
si->ndirty_node, si->node_pages);
seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",
si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
seq_printf(s, " - datas: %4d in files:%4d\n",
si->ndirty_data, si->ndirty_files);
+ seq_printf(s, " - quota datas: %4d in quota files:%4d\n",
+ si->ndirty_qdata, si->nquota_files);
seq_printf(s, " - meta: %4d in %4d\n",
si->ndirty_meta, si->meta_pages);
seq_printf(s, " - imeta: %4d\n",
si->ndirty_imeta);
seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
si->dirty_nats, si->nats, si->dirty_sits, si->sits);
- seq_printf(s, " - free_nids: %9d\n",
- si->fnids);
+ seq_printf(s, " - free_nids: %9d/%9d\n - alloc_nids: %9d\n",
+ si->free_nids, si->avail_nids, si->alloc_nids);
seq_puts(s, "\nDistribution of User Blocks:");
seq_puts(s, " [ valid | invalid | free ]\n");
seq_puts(s, " [");
@@ -384,8 +470,9 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_stat_info *si;
+ int i;
- si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
+ si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL);
if (!si)
return -ENOMEM;
@@ -409,6 +496,13 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
atomic_set(&sbi->inline_inode, 0);
atomic_set(&sbi->inline_dir, 0);
atomic_set(&sbi->inplace_count, 0);
+ for (i = META_CP; i < META_MAX; i++)
+ atomic_set(&sbi->meta_count[i], 0);
+
+ atomic_set(&sbi->aw_cnt, 0);
+ atomic_set(&sbi->vw_cnt, 0);
+ atomic_set(&sbi->max_aw_cnt, 0);
+ atomic_set(&sbi->max_vw_cnt, 0);
mutex_lock(&f2fs_stat_mutex);
list_add_tail(&si->stat_list, &f2fs_stat_list);
@@ -425,33 +519,19 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
list_del(&si->stat_list);
mutex_unlock(&f2fs_stat_mutex);
- kfree(si);
+ kvfree(si);
}
-int __init f2fs_create_root_stats(void)
+void __init f2fs_create_root_stats(void)
{
- struct dentry *file;
-
f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
- if (!f2fs_debugfs_root)
- return -ENOMEM;
- file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
- NULL, &stat_fops);
- if (!file) {
- debugfs_remove(f2fs_debugfs_root);
- f2fs_debugfs_root = NULL;
- return -ENOMEM;
- }
-
- return 0;
+ debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL,
+ &stat_fops);
}
void f2fs_destroy_root_stats(void)
{
- if (!f2fs_debugfs_root)
- return;
-
debugfs_remove_recursive(f2fs_debugfs_root);
f2fs_debugfs_root = NULL;
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 9a11b48..9ef8b10 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1,19 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/dir.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
+#include <linux/sched.h>
#include "f2fs.h"
#include "node.h"
#include "acl.h"
#include "xattr.h"
+#include <trace/events/f2fs.h>
static unsigned long dir_blocks(struct inode *inode)
{
@@ -58,12 +57,12 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK,
};
-void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
+static void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
{
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
-unsigned char get_de_type(struct f2fs_dir_entry *de)
+unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
{
if (de->file_type < F2FS_FT_MAX)
return f2fs_filetype_table[de->file_type];
@@ -92,27 +91,23 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
- dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
+ dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- de = find_target_dentry(fname, namehash, max_slots, &d);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
+ de = f2fs_find_target_dentry(fname, namehash, max_slots, &d);
if (de)
*res_page = dentry_page;
- else
- kunmap(dentry_page);
return de;
}
-struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
+struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
f2fs_hash_t namehash, int *max_slots,
struct f2fs_dentry_ptr *d)
{
struct f2fs_dir_entry *de;
unsigned long bit_pos = 0;
int max_len = 0;
- struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
- struct fscrypt_str *name = &fname->disk_name;
if (max_slots)
*max_slots = 0;
@@ -130,29 +125,11 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
continue;
}
- if (de->hash_code != namehash)
- goto not_match;
-
- de_name.name = d->filename[bit_pos];
- de_name.len = le16_to_cpu(de->name_len);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
- if (unlikely(!name->name)) {
- if (fname->usr_fname->name[0] == '_') {
- if (de_name.len > 32 &&
- !memcmp(de_name.name + ((de_name.len - 17) & ~15),
- fname->crypto_buf.name + 8, 16))
- goto found;
- goto not_match;
- }
- name->name = fname->crypto_buf.name;
- name->len = fname->crypto_buf.len;
- }
-#endif
- if (de_name.len == name->len &&
- !memcmp(de_name.name, name->name, name->len))
+ if (de->hash_code == namehash &&
+ fscrypt_match_name(fname, d->filename[bit_pos],
+ le16_to_cpu(de->name_len)))
goto found;
-not_match:
+
if (max_slots && max_len > *max_slots)
*max_slots = max_len;
max_len = 0;
@@ -191,7 +168,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
for (; bidx < end_block; bidx++) {
/* no need to allocate new dentry pages to all the indices */
- dentry_page = find_data_page(dir, bidx);
+ dentry_page = f2fs_find_data_page(dir, bidx);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT) {
room = true;
@@ -230,7 +207,7 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
if (f2fs_has_inline_dentry(dir)) {
*res_page = NULL;
- de = find_in_inline_dir(dir, fname, res_page);
+ de = f2fs_find_in_inline_dir(dir, fname, res_page);
goto out;
}
@@ -305,7 +282,6 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
de = f2fs_find_entry(dir, qstr, page);
if (de) {
res = le32_to_cpu(de->ino);
- f2fs_dentry_kunmap(dir, *page);
f2fs_put_page(*page, 0);
}
@@ -317,14 +293,13 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
{
enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
lock_page(page);
- f2fs_wait_on_page_writeback(page, type, true);
+ f2fs_wait_on_page_writeback(page, type, true, true);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode->i_mode);
- f2fs_dentry_kunmap(dir, page);
set_page_dirty(page);
dir->i_mtime = dir->i_ctime = current_time(dir);
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
f2fs_put_page(page, 1);
}
@@ -332,7 +307,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_inode *ri;
- f2fs_wait_on_page_writeback(ipage, NODE, true);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
@@ -341,25 +316,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
set_page_dirty(ipage);
}
-int update_dent_inode(struct inode *inode, struct inode *to,
- const struct qstr *name)
-{
- struct page *page;
-
- if (file_enc_name(to))
- return 0;
-
- page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
- if (IS_ERR(page))
- return PTR_ERR(page);
-
- init_dent_inode(name, page);
- f2fs_put_page(page, 1);
-
- return 0;
-}
-
-void do_make_empty_dir(struct inode *inode, struct inode *parent,
+void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d)
{
struct qstr dot = QSTR_INIT(".", 1);
@@ -380,33 +337,32 @@ static int make_empty_dir(struct inode *inode,
struct f2fs_dentry_ptr d;
if (f2fs_has_inline_dentry(inode))
- return make_empty_inline_dir(inode, parent, page);
+ return f2fs_make_empty_inline_dir(inode, parent, page);
- dentry_page = get_new_data_page(inode, page, 0, true);
+ dentry_page = f2fs_get_new_data_page(inode, page, 0, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
- dentry_blk = kmap_atomic(dentry_page);
+ dentry_blk = page_address(dentry_page);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- do_make_empty_dir(inode, parent, &d);
-
- kunmap_atomic(dentry_blk);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
+ f2fs_do_make_empty_dir(inode, parent, &d);
set_page_dirty(dentry_page);
f2fs_put_page(dentry_page, 1);
return 0;
}
-struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
const struct qstr *new_name, const struct qstr *orig_name,
struct page *dpage)
{
struct page *page;
+ int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir));
int err;
if (is_inode_flag_set(inode, FI_NEW_INODE)) {
- page = new_inode_page(inode);
+ page = f2fs_new_inode_page(inode);
if (IS_ERR(page))
return page;
@@ -429,46 +385,49 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
if (err)
goto put_error;
- if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
+ if ((f2fs_encrypted_inode(dir) || dummy_encrypt) &&
+ f2fs_may_encrypt(inode)) {
err = fscrypt_inherit_context(dir, inode, page, false);
if (err)
goto put_error;
}
} else {
- page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
+ page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
-
- set_cold_node(inode, page);
}
- if (new_name)
+ if (new_name) {
init_dent_inode(new_name, page);
+ if (f2fs_encrypted_inode(dir))
+ file_set_enc_name(inode);
+ }
/*
* This file should be checkpointed during fsync.
* We lost i_pino from now on.
*/
if (is_inode_flag_set(inode, FI_INC_LINK)) {
- file_lost_pino(inode);
+ if (!S_ISDIR(inode->i_mode))
+ file_lost_pino(inode);
/*
* If link the tmpfile to alias through linkat path,
* we should remove this inode from orphan list.
*/
if (inode->i_nlink == 0)
- remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
+ f2fs_remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
f2fs_i_links_write(inode, true);
}
return page;
put_error:
clear_nlink(inode);
- update_inode(inode, page);
+ f2fs_update_inode(inode, page);
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
-void update_parent_metadata(struct inode *dir, struct inode *inode,
+void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
@@ -477,7 +436,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode,
clear_inode_flag(inode, FI_NEW_INODE);
}
dir->i_mtime = dir->i_ctime = current_time(dir);
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
if (F2FS_I(dir)->i_current_depth != current_depth)
f2fs_i_depth_write(dir, current_depth);
@@ -486,7 +445,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode,
clear_inode_flag(inode, FI_INC_LINK);
}
-int room_for_filename(const void *bitmap, int slots, int max_slots)
+int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots)
{
int bit_start = 0;
int zero_start, zero_end;
@@ -555,10 +514,11 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
}
start:
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH))
+ if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
+ f2fs_show_injection_info(FAULT_DIR_DEPTH);
return -ENOSPC;
-#endif
+ }
+
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
@@ -573,17 +533,16 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
(le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
- dentry_page = get_new_data_page(dir, NULL, block, true);
+ dentry_page = f2fs_get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
- dentry_blk = kmap(dentry_page);
- bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
+ dentry_blk = page_address(dentry_page);
+ bit_pos = f2fs_room_for_filename(&dentry_blk->dentry_bitmap,
slots, NR_DENTRY_IN_BLOCK);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
- kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
@@ -591,21 +550,19 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
++level;
goto start;
add_dentry:
- f2fs_wait_on_page_writeback(dentry_page, DATA, true);
+ f2fs_wait_on_page_writeback(dentry_page, DATA, true, true);
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, new_name,
+ page = f2fs_init_inode_metadata(inode, dir, new_name,
orig_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
- if (f2fs_encrypted_inode(dir))
- file_set_enc_name(inode);
}
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
@@ -615,18 +572,17 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
f2fs_put_page(page, 1);
}
- update_parent_metadata(dir, inode, current_depth);
+ f2fs_update_parent_metadata(dir, inode, current_depth);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
- kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
return err;
}
-int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
struct inode *inode, nid_t ino, umode_t mode)
{
struct qstr new_name;
@@ -650,7 +606,7 @@ int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
struct fscrypt_name fname;
@@ -674,13 +630,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
F2FS_I(dir)->task = NULL;
}
if (de) {
- f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
err = -EEXIST;
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
- err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+ err = f2fs_add_dentry(dir, &fname, inode, ino, mode);
}
fscrypt_free_filename(&fname);
return err;
@@ -692,7 +647,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
int err = 0;
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, NULL, NULL, NULL);
+ page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -700,9 +655,9 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
f2fs_put_page(page, 1);
clear_inode_flag(inode, FI_NEW_INODE);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
fail:
up_write(&F2FS_I(inode)->i_sem);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return err;
}
@@ -724,9 +679,9 @@ void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
up_write(&F2FS_I(inode)->i_sem);
if (inode->i_nlink == 0)
- add_orphan_inode(inode);
+ f2fs_add_orphan_inode(inode);
else
- release_orphan_inode(sbi);
+ f2fs_release_orphan_inode(sbi);
}
/*
@@ -743,37 +698,41 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+ if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT)
+ f2fs_add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO);
+
if (f2fs_has_inline_dentry(dir))
return f2fs_delete_inline_entry(dentry, page, dir, inode);
lock_page(page);
- f2fs_wait_on_page_writeback(page, DATA, true);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
for (i = 0; i < slots; i++)
- clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+ __clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
/* Let's check and deallocate this dentry page */
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
0);
- kunmap(page); /* kunmap - pair of f2fs_find_entry */
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = current_time(dir);
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
if (inode)
f2fs_drop_nlink(dir, inode);
if (bit_pos == NR_DENTRY_IN_BLOCK &&
- !truncate_hole(dir, page->index, page->index + 1)) {
+ !f2fs_truncate_hole(dir, page->index, page->index + 1)) {
+ f2fs_clear_radix_tree_dirty_tag(page);
clear_page_dirty_for_io(page);
- ClearPagePrivate(page);
+ f2fs_clear_page_private(page);
ClearPageUptodate(page);
clear_cold_data(page);
inode_dec_dirty_pages(dir);
+ f2fs_remove_dirty_inode(dir);
}
f2fs_put_page(page, 1);
}
@@ -790,7 +749,7 @@ bool f2fs_empty_dir(struct inode *dir)
return f2fs_empty_inline_dir(dir);
for (bidx = 0; bidx < nblock; bidx++) {
- dentry_page = get_lock_data_page(dir, bidx, false);
+ dentry_page = f2fs_get_lock_data_page(dir, bidx, false);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT)
continue;
@@ -798,7 +757,7 @@ bool f2fs_empty_dir(struct inode *dir)
return false;
}
- dentry_blk = kmap_atomic(dentry_page);
+ dentry_blk = page_address(dentry_page);
if (bidx == 0)
bit_pos = 2;
else
@@ -806,7 +765,6 @@ bool f2fs_empty_dir(struct inode *dir)
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
bit_pos);
- kunmap_atomic(dentry_blk);
f2fs_put_page(dentry_page, 1);
@@ -816,16 +774,23 @@ bool f2fs_empty_dir(struct inode *dir)
return true;
}
-bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr)
{
unsigned char d_type = DT_UNKNOWN;
unsigned int bit_pos;
struct f2fs_dir_entry *de = NULL;
struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode);
+ struct blk_plug plug;
+ bool readdir_ra = sbi->readdir_ra == 1;
+ int err = 0;
bit_pos = ((unsigned long)ctx->pos % d->max);
+ if (readdir_ra)
+ blk_start_plug(&plug);
+
while (bit_pos < d->max) {
bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
if (bit_pos >= d->max)
@@ -835,10 +800,14 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
if (de->name_len == 0) {
bit_pos++;
ctx->pos = start_pos + bit_pos;
+ printk_ratelimited(
+ "%s, invalid namelen(0), ino:%u, run fsck to fix.",
+ KERN_WARNING, le32_to_cpu(de->ino));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
continue;
}
- d_type = get_de_type(de);
+ d_type = f2fs_get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -847,34 +816,42 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
if (unlikely(bit_pos > d->max ||
le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) {
- f2fs_msg(F2FS_I_SB(d->inode)->sb, KERN_WARNING,
+ f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted namelen=%d, run fsck to fix.",
__func__, le16_to_cpu(de->name_len));
- set_sbi_flag(F2FS_I_SB(d->inode)->sb->s_fs_info, SBI_NEED_FSCK);
- return -EINVAL;
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EINVAL;
+ goto out;
}
if (f2fs_encrypted_inode(d->inode)) {
int save_len = fstr->len;
- int err;
err = fscrypt_fname_disk_to_usr(d->inode,
(u32)de->hash_code, 0,
&de_name, fstr);
if (err)
- return true;
+ goto out;
de_name = *fstr;
fstr->len = save_len;
}
if (!dir_emit(ctx, de_name.name, de_name.len,
- le32_to_cpu(de->ino), d_type))
- return true;
+ le32_to_cpu(de->ino), d_type)) {
+ err = 1;
+ goto out;
+ }
+
+ if (readdir_ra)
+ f2fs_ra_node_page(sbi, le32_to_cpu(de->ino));
ctx->pos = start_pos + bit_pos;
}
- return false;
+out:
+ if (readdir_ra)
+ blk_finish_plug(&plug);
+ return err;
}
static int f2fs_readdir(struct file *file, struct dir_context *ctx)
@@ -884,6 +861,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
struct f2fs_dentry_block *dentry_blk = NULL;
struct page *dentry_page = NULL;
struct file_ra_state *ra = &file->f_ra;
+ loff_t start_pos = ctx->pos;
unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
struct f2fs_dentry_ptr d;
struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
@@ -892,51 +870,61 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
if (f2fs_encrypted_inode(inode)) {
err = fscrypt_get_encryption_info(inode);
if (err && err != -ENOKEY)
- return err;
+ goto out;
err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
if (err < 0)
- return err;
+ goto out;
}
if (f2fs_has_inline_dentry(inode)) {
err = f2fs_read_inline_dir(file, ctx, &fstr);
- goto out;
+ goto out_free;
}
- /* readahead for multi pages of dir */
- if (npages - n > 1 && !ra_has_index(ra, n))
- page_cache_sync_readahead(inode->i_mapping, ra, file, n,
+ for (; n < npages; n++, ctx->pos = n * NR_DENTRY_IN_BLOCK) {
+
+ /* allow readdir() to be interrupted */
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto out_free;
+ }
+ cond_resched();
+
+ /* readahead for multi pages of dir */
+ if (npages - n > 1 && !ra_has_index(ra, n))
+ page_cache_sync_readahead(inode->i_mapping, ra, file, n,
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
- for (; n < npages; n++) {
- dentry_page = get_lock_data_page(inode, n, false);
+ dentry_page = f2fs_find_data_page(inode, n);
if (IS_ERR(dentry_page)) {
err = PTR_ERR(dentry_page);
- if (err == -ENOENT)
+ if (err == -ENOENT) {
+ err = 0;
continue;
- else
- goto out;
+ } else {
+ goto out_free;
+ }
}
- dentry_blk = kmap(dentry_page);
+ dentry_blk = page_address(dentry_page);
- make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
+ make_dentry_ptr_block(inode, &d, dentry_blk);
- if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
- kunmap(dentry_page);
- f2fs_put_page(dentry_page, 1);
+ err = f2fs_fill_dentries(ctx, &d,
+ n * NR_DENTRY_IN_BLOCK, &fstr);
+ if (err) {
+ f2fs_put_page(dentry_page, 0);
break;
}
- ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
- kunmap(dentry_page);
- f2fs_put_page(dentry_page, 1);
+ f2fs_put_page(dentry_page, 0);
}
- err = 0;
-out:
+out_free:
fscrypt_fname_free_buffer(&fstr);
- return err;
+out:
+ trace_f2fs_readdir(inode, start_pos, ctx->pos, err);
+ return err < 0 ? err : 0;
}
static int f2fs_dir_open(struct inode *inode, struct file *filp)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index d7b8c8b..904ad7b 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* f2fs extent cache support
*
@@ -5,10 +6,6 @@
* Copyright (c) 2015 Samsung Electronics
* Authors: Jaegeuk Kim <jaegeuk@kernel.org>
* Chao Yu <chao2.yu@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
@@ -18,6 +15,179 @@
#include "node.h"
#include <trace/events/f2fs.h>
+static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
+ unsigned int ofs)
+{
+ if (cached_re) {
+ if (cached_re->ofs <= ofs &&
+ cached_re->ofs + cached_re->len > ofs) {
+ return cached_re;
+ }
+ }
+ return NULL;
+}
+
+static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root,
+ unsigned int ofs)
+{
+ struct rb_node *node = root->rb_node;
+ struct rb_entry *re;
+
+ while (node) {
+ re = rb_entry(node, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ node = node->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ node = node->rb_right;
+ else
+ return re;
+ }
+ return NULL;
+}
+
+struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs)
+{
+ struct rb_entry *re;
+
+ re = __lookup_rb_tree_fast(cached_re, ofs);
+ if (!re)
+ return __lookup_rb_tree_slow(root, ofs);
+
+ return re;
+}
+
+struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+ struct rb_root *root, struct rb_node **parent,
+ unsigned int ofs)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_entry *re;
+
+ while (*p) {
+ *parent = *p;
+ re = rb_entry(*parent, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ p = &(*p)->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ p = &(*p)->rb_right;
+ else
+ f2fs_bug_on(sbi, 1);
+ }
+
+ return p;
+}
+
+/*
+ * lookup rb entry in position of @ofs in rb-tree,
+ * if hit, return the entry, otherwise, return NULL
+ * @prev_ex: extent before ofs
+ * @next_ex: extent after ofs
+ * @insert_p: insert point for new extent at ofs
+ * in order to simpfy the insertion after.
+ * tree must stay unchanged between lookup and insertion.
+ */
+struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root,
+ struct rb_entry *cached_re,
+ unsigned int ofs,
+ struct rb_entry **prev_entry,
+ struct rb_entry **next_entry,
+ struct rb_node ***insert_p,
+ struct rb_node **insert_parent,
+ bool force)
+{
+ struct rb_node **pnode = &root->rb_node;
+ struct rb_node *parent = NULL, *tmp_node;
+ struct rb_entry *re = cached_re;
+
+ *insert_p = NULL;
+ *insert_parent = NULL;
+ *prev_entry = NULL;
+ *next_entry = NULL;
+
+ if (RB_EMPTY_ROOT(root))
+ return NULL;
+
+ if (re) {
+ if (re->ofs <= ofs && re->ofs + re->len > ofs)
+ goto lookup_neighbors;
+ }
+
+ while (*pnode) {
+ parent = *pnode;
+ re = rb_entry(*pnode, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ pnode = &(*pnode)->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ pnode = &(*pnode)->rb_right;
+ else
+ goto lookup_neighbors;
+ }
+
+ *insert_p = pnode;
+ *insert_parent = parent;
+
+ re = rb_entry(parent, struct rb_entry, rb_node);
+ tmp_node = parent;
+ if (parent && ofs > re->ofs)
+ tmp_node = rb_next(parent);
+ *next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+
+ tmp_node = parent;
+ if (parent && ofs < re->ofs)
+ tmp_node = rb_prev(parent);
+ *prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ return NULL;
+
+lookup_neighbors:
+ if (ofs == re->ofs || force) {
+ /* lookup prev node for merging backward later */
+ tmp_node = rb_prev(&re->rb_node);
+ *prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ }
+ if (ofs == re->ofs + re->len - 1 || force) {
+ /* lookup next node for merging frontward later */
+ tmp_node = rb_next(&re->rb_node);
+ *next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ }
+ return re;
+}
+
+bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+ struct rb_root *root)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+ struct rb_node *cur = rb_first(root), *next;
+ struct rb_entry *cur_re, *next_re;
+
+ if (!cur)
+ return true;
+
+ while (cur) {
+ next = rb_next(cur);
+ if (!next)
+ return true;
+
+ cur_re = rb_entry(cur, struct rb_entry, rb_node);
+ next_re = rb_entry(next, struct rb_entry, rb_node);
+
+ if (cur_re->ofs + cur_re->len > next_re->ofs) {
+ f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, "
+ "cur(%u, %u) next(%u, %u)",
+ cur_re->ofs, cur_re->len,
+ next_re->ofs, next_re->len);
+ return false;
+ }
+
+ cur = next;
+ }
+#endif
+ return true;
+}
+
static struct kmem_cache *extent_tree_slab;
static struct kmem_cache *extent_node_slab;
@@ -77,7 +247,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
struct extent_tree *et;
nid_t ino = inode->i_ino;
- down_write(&sbi->extent_tree_lock);
+ mutex_lock(&sbi->extent_tree_lock);
et = radix_tree_lookup(&sbi->extent_tree_root, ino);
if (!et) {
et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
@@ -94,7 +264,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
atomic_dec(&sbi->total_zombie_tree);
list_del_init(&et->list);
}
- up_write(&sbi->extent_tree_lock);
+ mutex_unlock(&sbi->extent_tree_lock);
/* never died until evict_inode */
F2FS_I(inode)->extent_tree = et;
@@ -102,36 +272,6 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
return et;
}
-static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi,
- struct extent_tree *et, unsigned int fofs)
-{
- struct rb_node *node = et->root.rb_node;
- struct extent_node *en = et->cached_en;
-
- if (en) {
- struct extent_info *cei = &en->ei;
-
- if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) {
- stat_inc_cached_node_hit(sbi);
- return en;
- }
- }
-
- while (node) {
- en = rb_entry(node, struct extent_node, rb_node);
-
- if (fofs < en->ei.fofs) {
- node = node->rb_left;
- } else if (fofs >= en->ei.fofs + en->ei.len) {
- node = node->rb_right;
- } else {
- stat_inc_rbtree_node_hit(sbi);
- return en;
- }
- }
- return NULL;
-}
-
static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei)
{
@@ -165,14 +305,13 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
return count - atomic_read(&et->node_cnt);
}
-static void __drop_largest_extent(struct inode *inode,
+static void __drop_largest_extent(struct extent_tree *et,
pgoff_t fofs, unsigned int len)
{
- struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
-
- if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
- largest->len = 0;
- f2fs_mark_inode_dirty_sync(inode);
+ if (fofs < et->largest.fofs + et->largest.len &&
+ fofs + len > et->largest.fofs) {
+ et->largest.len = 0;
+ et->largest_updated = true;
}
}
@@ -247,17 +386,24 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
goto out;
}
- en = __lookup_extent_tree(sbi, et, pgofs);
- if (en) {
- *ei = en->ei;
- spin_lock(&sbi->extent_lock);
- if (!list_empty(&en->list)) {
- list_move_tail(&en->list, &sbi->extent_list);
- et->cached_en = en;
- }
- spin_unlock(&sbi->extent_lock);
- ret = true;
+ en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root,
+ (struct rb_entry *)et->cached_en, pgofs);
+ if (!en)
+ goto out;
+
+ if (en == et->cached_en)
+ stat_inc_cached_node_hit(sbi);
+ else
+ stat_inc_rbtree_node_hit(sbi);
+
+ *ei = en->ei;
+ spin_lock(&sbi->extent_lock);
+ if (!list_empty(&en->list)) {
+ list_move_tail(&en->list, &sbi->extent_list);
+ et->cached_en = en;
}
+ spin_unlock(&sbi->extent_lock);
+ ret = true;
out:
stat_inc_total_hit(sbi);
read_unlock(&et->lock);
@@ -266,93 +412,11 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
return ret;
}
-
-/*
- * lookup extent at @fofs, if hit, return the extent
- * if not, return NULL and
- * @prev_ex: extent before fofs
- * @next_ex: extent after fofs
- * @insert_p: insert point for new extent at fofs
- * in order to simpfy the insertion after.
- * tree must stay unchanged between lookup and insertion.
- */
-static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
- unsigned int fofs,
- struct extent_node **prev_ex,
- struct extent_node **next_ex,
- struct rb_node ***insert_p,
- struct rb_node **insert_parent)
-{
- struct rb_node **pnode = &et->root.rb_node;
- struct rb_node *parent = NULL, *tmp_node;
- struct extent_node *en = et->cached_en;
-
- *insert_p = NULL;
- *insert_parent = NULL;
- *prev_ex = NULL;
- *next_ex = NULL;
-
- if (RB_EMPTY_ROOT(&et->root))
- return NULL;
-
- if (en) {
- struct extent_info *cei = &en->ei;
-
- if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
- goto lookup_neighbors;
- }
-
- while (*pnode) {
- parent = *pnode;
- en = rb_entry(*pnode, struct extent_node, rb_node);
-
- if (fofs < en->ei.fofs)
- pnode = &(*pnode)->rb_left;
- else if (fofs >= en->ei.fofs + en->ei.len)
- pnode = &(*pnode)->rb_right;
- else
- goto lookup_neighbors;
- }
-
- *insert_p = pnode;
- *insert_parent = parent;
-
- en = rb_entry(parent, struct extent_node, rb_node);
- tmp_node = parent;
- if (parent && fofs > en->ei.fofs)
- tmp_node = rb_next(parent);
- *next_ex = tmp_node ?
- rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
-
- tmp_node = parent;
- if (parent && fofs < en->ei.fofs)
- tmp_node = rb_prev(parent);
- *prev_ex = tmp_node ?
- rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
- return NULL;
-
-lookup_neighbors:
- if (fofs == en->ei.fofs) {
- /* lookup prev node for merging backward later */
- tmp_node = rb_prev(&en->rb_node);
- *prev_ex = tmp_node ?
- rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
- }
- if (fofs == en->ei.fofs + en->ei.len - 1) {
- /* lookup next node for merging frontward later */
- tmp_node = rb_next(&en->rb_node);
- *next_ex = tmp_node ?
- rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
- }
- return en;
-}
-
-static struct extent_node *__try_merge_extent_node(struct inode *inode,
+static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
struct extent_node *prev_ex,
struct extent_node *next_ex)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_node *en = NULL;
if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
@@ -374,7 +438,7 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode,
if (!en)
return NULL;
- __try_update_largest_extent(inode, et, en);
+ __try_update_largest_extent(et, en);
spin_lock(&sbi->extent_lock);
if (!list_empty(&en->list)) {
@@ -385,13 +449,12 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode,
return en;
}
-static struct extent_node *__insert_extent_tree(struct inode *inode,
+static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
struct rb_node **insert_p,
struct rb_node *insert_parent)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct rb_node **p = &et->root.rb_node;
+ struct rb_node **p;
struct rb_node *parent = NULL;
struct extent_node *en = NULL;
@@ -401,23 +464,13 @@ static struct extent_node *__insert_extent_tree(struct inode *inode,
goto do_insert;
}
- while (*p) {
- parent = *p;
- en = rb_entry(parent, struct extent_node, rb_node);
-
- if (ei->fofs < en->ei.fofs)
- p = &(*p)->rb_left;
- else if (ei->fofs >= en->ei.fofs + en->ei.len)
- p = &(*p)->rb_right;
- else
- f2fs_bug_on(sbi, 1);
- }
+ p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
do_insert:
en = __attach_extent_node(sbi, et, ei, parent, p);
if (!en)
return NULL;
- __try_update_largest_extent(inode, et, en);
+ __try_update_largest_extent(et, en);
/* update in global extent list */
spin_lock(&sbi->extent_lock);
@@ -427,7 +480,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode,
return en;
}
-static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+static void f2fs_update_extent_tree_range(struct inode *inode,
pgoff_t fofs, block_t blkaddr, unsigned int len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -438,9 +491,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
struct rb_node **insert_p = NULL, *insert_parent = NULL;
unsigned int end = fofs + len;
unsigned int pos = (unsigned int)fofs;
+ bool updated = false;
if (!et)
- return false;
+ return;
trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
@@ -448,7 +502,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
write_unlock(&et->lock);
- return false;
+ return;
}
prev = et->largest;
@@ -458,11 +512,14 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
* drop largest extent before lookup, in case it's already
* been shrunk from extent tree
*/
- __drop_largest_extent(inode, fofs, len);
+ __drop_largest_extent(et, fofs, len);
/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
- en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
- &insert_p, &insert_parent);
+ en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
+ (struct rb_entry *)et->cached_en, fofs,
+ (struct rb_entry **)&prev_en,
+ (struct rb_entry **)&next_en,
+ &insert_p, &insert_parent, false);
if (!en)
en = next_en;
@@ -488,7 +545,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
set_extent_info(&ei, end,
end - dei.fofs + dei.blk,
org_end - end);
- en1 = __insert_extent_tree(inode, et, &ei,
+ en1 = __insert_extent_tree(sbi, et, &ei,
NULL, NULL);
next_en = en1;
} else {
@@ -503,13 +560,12 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (!next_en) {
struct rb_node *node = rb_next(&en->rb_node);
- next_en = node ?
- rb_entry(node, struct extent_node, rb_node)
- : NULL;
+ next_en = rb_entry_safe(node, struct extent_node,
+ rb_node);
}
if (parts)
- __try_update_largest_extent(inode, et, en);
+ __try_update_largest_extent(et, en);
else
__release_extent_node(sbi, et, en);
@@ -529,15 +585,16 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (blkaddr) {
set_extent_info(&ei, fofs, blkaddr, len);
- if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en))
- __insert_extent_tree(inode, et, &ei,
+ if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+ __insert_extent_tree(sbi, et, &ei,
insert_p, insert_parent);
/* give up extent_cache, if split and small updates happen */
if (dei.len >= 1 &&
prev.len < F2FS_MIN_EXTENT_LEN &&
et->largest.len < F2FS_MIN_EXTENT_LEN) {
- __drop_largest_extent(inode, 0, UINT_MAX);
+ et->largest.len = 0;
+ et->largest_updated = true;
set_inode_flag(inode, FI_NO_EXTENT);
}
}
@@ -545,9 +602,15 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (is_inode_flag_set(inode, FI_NO_EXTENT))
__free_extent_tree(sbi, et);
+ if (et->largest_updated) {
+ et->largest_updated = false;
+ updated = true;
+ }
+
write_unlock(&et->lock);
- return !__is_extent_same(&prev, &et->largest);
+ if (updated)
+ f2fs_mark_inode_dirty_sync(inode, true);
}
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -563,7 +626,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
if (!atomic_read(&sbi->total_zombie_tree))
goto free_node;
- if (!down_write_trylock(&sbi->extent_tree_lock))
+ if (!mutex_trylock(&sbi->extent_tree_lock))
goto out;
/* 1. remove unreferenced extent tree */
@@ -585,11 +648,11 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
goto unlock_out;
cond_resched();
}
- up_write(&sbi->extent_tree_lock);
+ mutex_unlock(&sbi->extent_tree_lock);
free_node:
/* 2. remove LRU extent entries */
- if (!down_write_trylock(&sbi->extent_tree_lock))
+ if (!mutex_trylock(&sbi->extent_tree_lock))
goto out;
remained = nr_shrink - (node_cnt + tree_cnt);
@@ -619,7 +682,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
spin_unlock(&sbi->extent_lock);
unlock_out:
- up_write(&sbi->extent_tree_lock);
+ mutex_unlock(&sbi->extent_tree_lock);
out:
trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
@@ -646,6 +709,7 @@ void f2fs_drop_extent_tree(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
+ bool updated = false;
if (!f2fs_may_extent_tree(inode))
return;
@@ -654,8 +718,13 @@ void f2fs_drop_extent_tree(struct inode *inode)
write_lock(&et->lock);
__free_extent_tree(sbi, et);
- __drop_largest_extent(inode, 0, UINT_MAX);
+ if (et->largest.len) {
+ et->largest.len = 0;
+ updated = true;
+ }
write_unlock(&et->lock);
+ if (updated)
+ f2fs_mark_inode_dirty_sync(inode, true);
}
void f2fs_destroy_extent_tree(struct inode *inode)
@@ -669,10 +738,10 @@ void f2fs_destroy_extent_tree(struct inode *inode)
if (inode->i_nlink && !is_bad_inode(inode) &&
atomic_read(&et->node_cnt)) {
- down_write(&sbi->extent_tree_lock);
+ mutex_lock(&sbi->extent_tree_lock);
list_add_tail(&et->list, &sbi->zombie_list);
atomic_inc(&sbi->total_zombie_tree);
- up_write(&sbi->extent_tree_lock);
+ mutex_unlock(&sbi->extent_tree_lock);
return;
}
@@ -680,12 +749,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
node_cnt = f2fs_destroy_extent_node(inode);
/* delete extent tree entry in radix tree */
- down_write(&sbi->extent_tree_lock);
+ mutex_lock(&sbi->extent_tree_lock);
f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
kmem_cache_free(extent_tree_slab, et);
atomic_dec(&sbi->total_ext_tree);
- up_write(&sbi->extent_tree_lock);
+ mutex_unlock(&sbi->extent_tree_lock);
F2FS_I(inode)->extent_tree = NULL;
@@ -714,7 +783,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
else
blkaddr = dn->data_blkaddr;
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+ fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
}
@@ -729,10 +798,10 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
}
-void init_extent_cache_info(struct f2fs_sb_info *sbi)
+void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
{
INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
- init_rwsem(&sbi->extent_tree_lock);
+ mutex_init(&sbi->extent_tree_lock);
INIT_LIST_HEAD(&sbi->extent_list);
spin_lock_init(&sbi->extent_lock);
atomic_set(&sbi->total_ext_tree, 0);
@@ -741,7 +810,7 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi)
atomic_set(&sbi->total_ext_node, 0);
}
-int __init create_extent_cache(void)
+int __init f2fs_create_extent_cache(void)
{
extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
sizeof(struct extent_tree));
@@ -756,7 +825,7 @@ int __init create_extent_cache(void)
return 0;
}
-void destroy_extent_cache(void)
+void f2fs_destroy_extent_cache(void)
{
kmem_cache_destroy(extent_node_slab);
kmem_cache_destroy(extent_tree_slab);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7016a59..d9de7bd 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1,16 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/f2fs.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef _LINUX_F2FS_H
#define _LINUX_F2FS_H
+#include <linux/uio.h>
#include <linux/types.h>
#include <linux/page-flags.h>
#include <linux/buffer_head.h>
@@ -19,11 +17,17 @@
#include <linux/magic.h>
#include <linux/kobject.h>
#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/cred.h>
#include <linux/vmalloc.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
-#include <linux/fscrypto.h>
+#include <linux/quotaops.h>
#include <crypto/hash.h>
+#include <linux/overflow.h>
+
+#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_F2FS_FS_ENCRYPTION)
+#include <linux/fscrypt.h>
#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
@@ -37,28 +41,36 @@
} while (0)
#endif
-#ifdef CONFIG_F2FS_FAULT_INJECTION
enum {
FAULT_KMALLOC,
+ FAULT_KVMALLOC,
FAULT_PAGE_ALLOC,
+ FAULT_PAGE_GET,
+ FAULT_ALLOC_BIO,
FAULT_ALLOC_NID,
FAULT_ORPHAN,
FAULT_BLOCK,
FAULT_DIR_DEPTH,
FAULT_EVICT_INODE,
- FAULT_IO,
+ FAULT_TRUNCATE,
+ FAULT_READ_IO,
FAULT_CHECKPOINT,
+ FAULT_DISCARD,
+ FAULT_WRITE_IO,
FAULT_MAX,
};
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+#define F2FS_ALL_FAULT_TYPE ((1 << FAULT_MAX) - 1)
+
struct f2fs_fault_info {
atomic_t inject_ops;
unsigned int inject_rate;
unsigned int inject_type;
};
-extern char *fault_name[FAULT_MAX];
-#define IS_FAULT_SET(fi, type) (fi->inject_type & (1 << (type)))
+extern const char *f2fs_fault_name[FAULT_MAX];
+#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
#endif
/*
@@ -83,10 +95,18 @@ extern char *fault_name[FAULT_MAX];
#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
#define F2FS_MOUNT_ADAPTIVE 0x00020000
#define F2FS_MOUNT_LFS 0x00040000
+#define F2FS_MOUNT_USRQUOTA 0x00080000
+#define F2FS_MOUNT_GRPQUOTA 0x00100000
+#define F2FS_MOUNT_PRJQUOTA 0x00200000
+#define F2FS_MOUNT_QUOTA 0x00400000
+#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000
+#define F2FS_MOUNT_RESERVE_ROOT 0x01000000
+#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000
-#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
-#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
-#define test_opt(sbi, option) (sbi->mount_opt.opt & F2FS_MOUNT_##option)
+#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
+#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
+#define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option)
+#define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option)
#define ver_after(a, b) (typecheck(unsigned long long, a) && \
typecheck(unsigned long long, b) && \
@@ -99,18 +119,54 @@ typedef u32 block_t; /*
typedef u32 nid_t;
struct f2fs_mount_info {
- unsigned int opt;
+ unsigned int opt;
+ int write_io_size_bits; /* Write IO size bits */
+ block_t root_reserved_blocks; /* root reserved blocks */
+ kuid_t s_resuid; /* reserved blocks for uid */
+ kgid_t s_resgid; /* reserved blocks for gid */
+ int active_logs; /* # of active logs */
+ int inline_xattr_size; /* inline xattr size */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct f2fs_fault_info fault_info; /* For fault injection */
+#endif
+#ifdef CONFIG_QUOTA
+ /* Names of quota files with journalled quota */
+ char *s_qf_names[MAXQUOTAS];
+ int s_jquota_fmt; /* Format of quota to use */
+#endif
+ /* For which write hints are passed down to block layer */
+ int whint_mode;
+ int alloc_mode; /* segment allocation policy */
+ int fsync_mode; /* fsync policy */
+ bool test_dummy_encryption; /* test dummy encryption */
};
-#define F2FS_FEATURE_ENCRYPT 0x0001
-#define F2FS_FEATURE_HMSMR 0x0002
+#define F2FS_FEATURE_ENCRYPT 0x0001
+#define F2FS_FEATURE_BLKZONED 0x0002
+#define F2FS_FEATURE_ATOMIC_WRITE 0x0004
+#define F2FS_FEATURE_EXTRA_ATTR 0x0008
+#define F2FS_FEATURE_PRJQUOTA 0x0010
+#define F2FS_FEATURE_INODE_CHKSUM 0x0020
+#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x0040
+#define F2FS_FEATURE_QUOTA_INO 0x0080
+#define F2FS_FEATURE_INODE_CRTIME 0x0100
+#define F2FS_FEATURE_LOST_FOUND 0x0200
+#define F2FS_FEATURE_VERITY 0x0400 /* reserved */
+#define F2FS_FEATURE_SB_CHKSUM 0x0800
-#define F2FS_HAS_FEATURE(sb, mask) \
- ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
-#define F2FS_SET_FEATURE(sb, mask) \
- F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)
-#define F2FS_CLEAR_FEATURE(sb, mask) \
- F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
+#define __F2FS_HAS_FEATURE(raw_super, mask) \
+ ((raw_super->feature & cpu_to_le32(mask)) != 0)
+#define F2FS_HAS_FEATURE(sbi, mask) __F2FS_HAS_FEATURE(sbi->raw_super, mask)
+#define F2FS_SET_FEATURE(sbi, mask) \
+ (sbi->raw_super->feature |= cpu_to_le32(mask))
+#define F2FS_CLEAR_FEATURE(sbi, mask) \
+ (sbi->raw_super->feature &= ~cpu_to_le32(mask))
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define F2FS_DEF_RESUID 0
+#define F2FS_DEF_RESGID 0
/*
* For checkpoint manager
@@ -120,28 +176,31 @@ enum {
SIT_BITMAP
};
-enum {
- CP_UMOUNT,
- CP_FASTBOOT,
- CP_SYNC,
- CP_RECOVERY,
- CP_DISCARD,
-};
+#define CP_UMOUNT 0x00000001
+#define CP_FASTBOOT 0x00000002
+#define CP_SYNC 0x00000004
+#define CP_RECOVERY 0x00000008
+#define CP_DISCARD 0x00000010
+#define CP_TRIMMED 0x00000020
+#define CP_PAUSE 0x00000040
-#define DEF_BATCHED_TRIM_SECTIONS 2
-#define BATCHED_TRIM_SEGMENTS(sbi) \
- (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
-#define BATCHED_TRIM_BLOCKS(sbi) \
- (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi)
+#define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */
+#define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */
+#define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */
+#define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */
+#define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */
#define DEF_CP_INTERVAL 60 /* 60 secs */
#define DEF_IDLE_INTERVAL 5 /* 5 secs */
+#define DEF_DISABLE_INTERVAL 5 /* 5 secs */
+#define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */
+#define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */
struct cp_control {
int reason;
__u64 trim_start;
__u64 trim_end;
__u64 trim_minlen;
- __u64 trimmed;
};
/*
@@ -152,6 +211,7 @@ enum {
META_NAT,
META_SIT,
META_SSA,
+ META_MAX,
META_POR,
DATA_GENERIC,
META_GENERIC,
@@ -162,12 +222,15 @@ enum {
ORPHAN_INO, /* for orphan ino list */
APPEND_INO, /* for append ino list */
UPDATE_INO, /* for update ino list */
+ TRANS_DIR_INO, /* for trasactions dir ino list */
+ FLUSH_INO, /* for multiple device flushing */
MAX_INO_ENTRY, /* max. list */
};
struct ino_entry {
- struct list_head list; /* list head */
- nid_t ino; /* inode number */
+ struct list_head list; /* list head */
+ nid_t ino; /* inode number */
+ unsigned int dirty_device; /* dirty device bitmap */
};
/* for the list of inodes to be GCed */
@@ -176,18 +239,103 @@ struct inode_entry {
struct inode *inode; /* vfs inode pointer */
};
-/* for the list of blockaddresses to be discarded */
-struct discard_entry {
+struct fsync_node_entry {
struct list_head list; /* list head */
- block_t blkaddr; /* block address to be discarded */
- int len; /* # of consecutive blocks of the discard */
+ struct page *page; /* warm node page pointer */
+ unsigned int seq_id; /* sequence id */
};
-struct bio_entry {
- struct list_head list;
- struct bio *bio;
- struct completion event;
- int error;
+/* for the bitmap indicate blocks to be discarded */
+struct discard_entry {
+ struct list_head list; /* list head */
+ block_t start_blkaddr; /* start blockaddr of current segment */
+ unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */
+};
+
+/* default discard granularity of inner discard thread, unit: block count */
+#define DEFAULT_DISCARD_GRANULARITY 16
+
+/* max discard pend list number */
+#define MAX_PLIST_NUM 512
+#define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \
+ (MAX_PLIST_NUM - 1) : ((blk_num) - 1))
+
+enum {
+ D_PREP, /* initial */
+ D_PARTIAL, /* partially submitted */
+ D_SUBMIT, /* all submitted */
+ D_DONE, /* finished */
+};
+
+struct discard_info {
+ block_t lstart; /* logical start address */
+ block_t len; /* length */
+ block_t start; /* actual start address in dev */
+};
+
+struct discard_cmd {
+ struct rb_node rb_node; /* rb node located in rb-tree */
+ union {
+ struct {
+ block_t lstart; /* logical start address */
+ block_t len; /* length */
+ block_t start; /* actual start address in dev */
+ };
+ struct discard_info di; /* discard info */
+
+ };
+ struct list_head list; /* command list */
+ struct completion wait; /* compleation */
+ struct block_device *bdev; /* bdev */
+ unsigned short ref; /* reference count */
+ unsigned char state; /* state */
+ unsigned char queued; /* queued discard */
+ int error; /* bio error */
+ spinlock_t lock; /* for state/bio_ref updating */
+ unsigned short bio_ref; /* bio reference count */
+};
+
+enum {
+ DPOLICY_BG,
+ DPOLICY_FORCE,
+ DPOLICY_FSTRIM,
+ DPOLICY_UMOUNT,
+ MAX_DPOLICY,
+};
+
+struct discard_policy {
+ int type; /* type of discard */
+ unsigned int min_interval; /* used for candidates exist */
+ unsigned int mid_interval; /* used for device busy */
+ unsigned int max_interval; /* used for candidates not exist */
+ unsigned int max_requests; /* # of discards issued per round */
+ unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */
+ bool io_aware; /* issue discard in idle time */
+ bool sync; /* submit discard with REQ_SYNC flag */
+ bool ordered; /* issue discard by lba order */
+ unsigned int granularity; /* discard granularity */
+ int timeout; /* discard timeout for put_super */
+};
+
+struct discard_cmd_control {
+ struct task_struct *f2fs_issue_discard; /* discard thread */
+ struct list_head entry_list; /* 4KB discard entry list */
+ struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
+ struct list_head wait_list; /* store on-flushing entries */
+ struct list_head fstrim_list; /* in-flight discard from fstrim */
+ wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */
+ unsigned int discard_wake; /* to wake up discard thread */
+ struct mutex cmd_lock;
+ unsigned int nr_discards; /* # of discards in the list */
+ unsigned int max_discards; /* max. discards to be issued */
+ unsigned int discard_granularity; /* discard granularity */
+ unsigned int undiscard_blks; /* # of undiscard blocks */
+ unsigned int next_pos; /* next discard position */
+ atomic_t issued_discard; /* # of issued discard */
+ atomic_t queued_discard; /* # of queued discard */
+ atomic_t discard_cmd_cnt; /* # of cached cmd count */
+ struct rb_root root; /* root of discard rb-tree */
+ bool rbtree_check; /* config for consistence check */
};
/* for the list of fsync inodes, used only during recovery */
@@ -198,13 +346,13 @@ struct fsync_inode_entry {
block_t last_dentry; /* block address locating the last dentry */
};
-#define nats_in_cursum(jnl) (le16_to_cpu(jnl->n_nats))
-#define sits_in_cursum(jnl) (le16_to_cpu(jnl->n_sits))
+#define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats))
+#define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits))
-#define nat_in_journal(jnl, i) (jnl->nat_j.entries[i].ne)
-#define nid_in_journal(jnl, i) (jnl->nat_j.entries[i].nid)
-#define sit_in_journal(jnl, i) (jnl->sit_j.entries[i].se)
-#define segno_in_journal(jnl, i) (jnl->sit_j.entries[i].segno)
+#define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne)
+#define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid)
+#define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se)
+#define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno)
#define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
#define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
@@ -212,6 +360,7 @@ struct fsync_inode_entry {
static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
{
int before = nats_in_cursum(journal);
+
journal->n_nats = cpu_to_le16(before + i);
return before;
}
@@ -219,6 +368,7 @@ static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
{
int before = sits_in_cursum(journal);
+
journal->n_sits = cpu_to_le16(before + i);
return before;
}
@@ -244,11 +394,20 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
-#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6)
+#define F2FS_IOC_GARBAGE_COLLECT _IOW(F2FS_IOCTL_MAGIC, 6, __u32)
#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
-#define F2FS_IOC_DEFRAGMENT _IO(F2FS_IOCTL_MAGIC, 8)
+#define F2FS_IOC_DEFRAGMENT _IOWR(F2FS_IOCTL_MAGIC, 8, \
+ struct f2fs_defragment)
#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
struct f2fs_move_range)
+#define F2FS_IOC_FLUSH_DEVICE _IOW(F2FS_IOCTL_MAGIC, 10, \
+ struct f2fs_flush_device)
+#define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \
+ struct f2fs_gc_range)
+#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32)
+#define F2FS_IOC_SET_PIN_FILE _IOW(F2FS_IOCTL_MAGIC, 13, __u32)
+#define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32)
+#define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15)
#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
@@ -263,6 +422,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */
#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
+#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -273,6 +433,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
#endif
+struct f2fs_gc_range {
+ u32 sync;
+ u64 start;
+ u64 len;
+};
+
struct f2fs_defragment {
u64 start;
u64 len;
@@ -285,36 +451,69 @@ struct f2fs_move_range {
u64 len; /* size to move */
};
+struct f2fs_flush_device {
+ u32 dev_num; /* device number to flush */
+ u32 segments; /* # of segments to flush */
+};
+
+/* for inline stuff */
+#define DEF_INLINE_RESERVED_SIZE 1
+static inline int get_extra_isize(struct inode *inode);
+static inline int get_inline_xattr_addrs(struct inode *inode);
+#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \
+ (CUR_ADDRS_PER_INODE(inode) - \
+ get_inline_xattr_addrs(inode) - \
+ DEF_INLINE_RESERVED_SIZE))
+
+/* for inline dir */
+#define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ BITS_PER_BYTE + 1))
+#define INLINE_DENTRY_BITMAP_SIZE(inode) ((NR_INLINE_DENTRY(inode) + \
+ BITS_PER_BYTE - 1) / BITS_PER_BYTE)
+#define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ NR_INLINE_DENTRY(inode) + \
+ INLINE_DENTRY_BITMAP_SIZE(inode)))
+
/*
* For INODE and NODE manager
*/
/* for directory operations */
struct f2fs_dentry_ptr {
struct inode *inode;
- const void *bitmap;
+ void *bitmap;
struct f2fs_dir_entry *dentry;
__u8 (*filename)[F2FS_SLOT_LEN];
int max;
+ int nr_bitmap;
};
-static inline void make_dentry_ptr(struct inode *inode,
- struct f2fs_dentry_ptr *d, void *src, int type)
+static inline void make_dentry_ptr_block(struct inode *inode,
+ struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
{
d->inode = inode;
+ d->max = NR_DENTRY_IN_BLOCK;
+ d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
+ d->bitmap = t->dentry_bitmap;
+ d->dentry = t->dentry;
+ d->filename = t->filename;
+}
- if (type == 1) {
- struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src;
- d->max = NR_DENTRY_IN_BLOCK;
- d->bitmap = &t->dentry_bitmap;
- d->dentry = t->dentry;
- d->filename = t->filename;
- } else {
- struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src;
- d->max = NR_INLINE_DENTRY;
- d->bitmap = &t->dentry_bitmap;
- d->dentry = t->dentry;
- d->filename = t->filename;
- }
+static inline void make_dentry_ptr_inline(struct inode *inode,
+ struct f2fs_dentry_ptr *d, void *t)
+{
+ int entry_cnt = NR_INLINE_DENTRY(inode);
+ int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
+ int reserved_size = INLINE_RESERVED_SIZE(inode);
+
+ d->inode = inode;
+ d->max = entry_cnt;
+ d->nr_bitmap = bitmap_size;
+ d->bitmap = t;
+ d->dentry = t + bitmap_size + reserved_size;
+ d->filename = t + bitmap_size + reserved_size +
+ SIZE_OF_DIR_ENTRY * entry_cnt;
}
/*
@@ -333,29 +532,37 @@ enum {
*/
};
+#define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */
+
+/* maximum retry quota flush count */
+#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8
+
#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */
#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
-/* vector size for gang look-up from extent cache that consists of radix tree */
-#define EXT_TREE_VEC_SIZE 64
-
/* for in-memory extent cache entry */
#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */
/* number of extent info in extent cache we try to shrink */
#define EXTENT_CACHE_SHRINK_NUMBER 128
+struct rb_entry {
+ struct rb_node rb_node; /* rb node located in rb-tree */
+ unsigned int ofs; /* start offset of the entry */
+ unsigned int len; /* length of the entry */
+};
+
struct extent_info {
unsigned int fofs; /* start offset in a file */
- u32 blk; /* start block address of the extent */
unsigned int len; /* length of the extent */
+ u32 blk; /* start block address of the extent */
};
struct extent_node {
struct rb_node rb_node; /* rb node located in rb-tree */
- struct list_head list; /* node in global extent list of sbi */
struct extent_info ei; /* extent info */
+ struct list_head list; /* node in global extent list of sbi */
struct extent_tree *et; /* extent tree pointer */
};
@@ -367,6 +574,7 @@ struct extent_tree {
struct list_head list; /* to be used by sbi->zombie_list */
rwlock_t lock; /* protect extent info rb-tree */
atomic_t node_cnt; /* # of extent node in rb-tree*/
+ bool largest_updated; /* largest extent updated */
};
/*
@@ -386,15 +594,21 @@ struct f2fs_map_blocks {
unsigned int m_len;
unsigned int m_flags;
pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */
+ pgoff_t *m_next_extent; /* point to next possible extent */
+ int m_seg_type;
+ bool m_may_create; /* indicate it is from write path */
};
/* for flag in get_data_block */
-#define F2FS_GET_BLOCK_READ 0
-#define F2FS_GET_BLOCK_DIO 1
-#define F2FS_GET_BLOCK_FIEMAP 2
-#define F2FS_GET_BLOCK_BMAP 3
-#define F2FS_GET_BLOCK_PRE_DIO 4
-#define F2FS_GET_BLOCK_PRE_AIO 5
+enum {
+ F2FS_GET_BLOCK_DEFAULT,
+ F2FS_GET_BLOCK_FIEMAP,
+ F2FS_GET_BLOCK_BMAP,
+ F2FS_GET_BLOCK_DIO,
+ F2FS_GET_BLOCK_PRE_DIO,
+ F2FS_GET_BLOCK_PRE_AIO,
+ F2FS_GET_BLOCK_PRECACHE,
+};
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -403,6 +617,11 @@ struct f2fs_map_blocks {
#define FADVISE_LOST_PINO_BIT 0x02
#define FADVISE_ENCRYPT_BIT 0x04
#define FADVISE_ENC_NAME_BIT 0x08
+#define FADVISE_KEEP_SIZE_BIT 0x10
+#define FADVISE_HOT_BIT 0x20
+#define FADVISE_VERITY_BIT 0x40 /* reserved */
+
+#define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT)
#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
@@ -415,15 +634,28 @@ struct f2fs_map_blocks {
#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT)
#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+#define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT)
+#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
+#define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT)
+#define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT)
+#define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT)
#define DEF_DIR_LEVEL 0
+enum {
+ GC_FAILURE_PIN,
+ GC_FAILURE_ATOMIC,
+ MAX_GC_FAILURE
+};
+
struct f2fs_inode_info {
struct inode vfs_inode; /* serve a vfs inode */
unsigned long i_flags; /* keep an inode flags for ioctl */
unsigned char i_advise; /* use to give file attribute hints */
unsigned char i_dir_level; /* use for dentry level for large dir */
- unsigned int i_current_depth; /* use only in directory structure */
+ unsigned int i_current_depth; /* only for directory depth */
+ /* for gc failure statistic */
+ unsigned int i_gc_failures[MAX_GC_FAILURE];
unsigned int i_pino; /* parent inode number */
umode_t i_acl_mode; /* keep file acl mode temporarily */
@@ -434,16 +666,34 @@ struct f2fs_inode_info {
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
struct task_struct *task; /* lookup and create consistency */
+ struct task_struct *cp_task; /* separate cp/wb IO stats*/
nid_t i_xattr_nid; /* node id that contains xattrs */
- unsigned long long xattr_ver; /* cp version of xattr modification */
loff_t last_disk_size; /* lastly written file size */
+#ifdef CONFIG_QUOTA
+ struct dquot *i_dquot[MAXQUOTAS];
+
+ /* quota space reservation, managed internally by quota code */
+ qsize_t i_reserved_quota;
+#endif
struct list_head dirty_list; /* dirty list for dirs and files */
struct list_head gdirty_list; /* linked in global dirty list */
+ struct list_head inmem_ilist; /* list for inmem inodes */
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
+ struct task_struct *inmem_task; /* store inmemory task */
struct mutex inmem_lock; /* lock for inmemory pages */
struct extent_tree *extent_tree; /* cached extent_tree entry */
- struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
+
+ /* avoid racing between foreground op and gc */
+ struct rw_semaphore i_gc_rwsem[2];
+ struct rw_semaphore i_mmap_sem;
+ struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
+
+ int i_extra_isize; /* size of extra space located in i_addr */
+ kprojid_t i_projid; /* id for project quota */
+ int i_inline_xattr_size; /* inline xattr size */
+ struct timespec i_crtime; /* inode creation time */
+ struct timespec i_disk_time[4]; /* inode disk times */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -470,11 +720,23 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
ei->len = len;
}
-static inline bool __is_extent_same(struct extent_info *ei1,
- struct extent_info *ei2)
+static inline bool __is_discard_mergeable(struct discard_info *back,
+ struct discard_info *front, unsigned int max_len)
{
- return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk &&
- ei1->len == ei2->len);
+ return (back->lstart + back->len == front->lstart) &&
+ (back->len + front->len <= max_len);
+}
+
+static inline bool __is_discard_back_mergeable(struct discard_info *cur,
+ struct discard_info *back, unsigned int max_len)
+{
+ return __is_discard_mergeable(back, cur, max_len);
+}
+
+static inline bool __is_discard_front_mergeable(struct discard_info *cur,
+ struct discard_info *front, unsigned int max_len)
+{
+ return __is_discard_mergeable(cur, front, max_len);
}
static inline bool __is_extent_mergeable(struct extent_info *back,
@@ -496,20 +758,29 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
return __is_extent_mergeable(cur, front);
}
-extern void f2fs_mark_inode_dirty_sync(struct inode *);
-static inline void __try_update_largest_extent(struct inode *inode,
- struct extent_tree *et, struct extent_node *en)
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
+static inline void __try_update_largest_extent(struct extent_tree *et,
+ struct extent_node *en)
{
if (en->ei.len > et->largest.len) {
et->largest = en->ei;
- f2fs_mark_inode_dirty_sync(inode);
+ et->largest_updated = true;
}
}
+/*
+ * For free nid management
+ */
+enum nid_state {
+ FREE_NID, /* newly added to free nid list */
+ PREALLOC_NID, /* it is preallocated */
+ MAX_NID_STATE,
+};
+
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
- nid_t available_nids; /* maximum available node ids */
+ nid_t available_nids; /* # of available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
unsigned int ram_thresh; /* control the memory footprint */
unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */
@@ -520,18 +791,31 @@ struct f2fs_nm_info {
struct radix_tree_root nat_set_root;/* root of the nat set cache */
struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
+ spinlock_t nat_list_lock; /* protect clean nat entry list */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
+ unsigned int nat_blocks; /* # of nat blocks */
/* free node ids management */
struct radix_tree_root free_nid_root;/* root of the free_nid cache */
- struct list_head free_nid_list; /* a list for free nids */
- spinlock_t free_nid_list_lock; /* protect free nid list */
- unsigned int fcnt; /* the number of free node id */
+ struct list_head free_nid_list; /* list for free nids excluding preallocated nids */
+ unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */
+ spinlock_t nid_list_lock; /* protect nid lists ops */
struct mutex build_lock; /* lock for build free nids */
+ unsigned char **free_nid_bitmap;
+ unsigned char *nat_block_bitmap;
+ unsigned short *free_nid_count; /* free nid count of NAT block */
/* for checkpoint */
char *nat_bitmap; /* NAT bitmap pointer */
+
+ unsigned int nat_bits_blocks; /* # of nat bits blocks */
+ unsigned char *nat_bits; /* NAT bits blocks */
+ unsigned char *full_nat_bits; /* full NAT pages */
+ unsigned char *empty_nat_bits; /* empty NAT pages */
+#ifdef CONFIG_F2FS_CHECK_FS
+ char *nat_bitmap_mir; /* NAT bitmap mirror */
+#endif
int bitmap_size; /* bitmap size */
};
@@ -588,19 +872,20 @@ enum {
CURSEG_WARM_NODE, /* direct node blocks of normal files */
CURSEG_COLD_NODE, /* indirect node blocks */
NO_CHECK_TYPE,
- CURSEG_DIRECT_IO, /* to use for the direct IO path */
};
struct flush_cmd {
struct completion wait;
struct llist_node llnode;
+ nid_t ino;
int ret;
};
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
- atomic_t submit_flush; /* # of issued flushes */
+ atomic_t issued_flush; /* # of issued flushes */
+ atomic_t queued_flush; /* # of queued flushes */
struct llist_head issue_list; /* list for command issue */
struct llist_node *dispatch_list; /* list for command dispatch */
};
@@ -611,6 +896,8 @@ struct f2fs_sm_info {
struct dirty_seglist_info *dirty_info; /* dirty segment information */
struct curseg_info *curseg_array; /* active segment information */
+ struct rw_semaphore curseg_lock; /* for preventing curseg change */
+
block_t seg0_blkaddr; /* block address of 0'th segment */
block_t main_blkaddr; /* start block address of main area */
block_t ssa_blkaddr; /* start block address of SSA area */
@@ -623,12 +910,6 @@ struct f2fs_sm_info {
/* a threshold to reclaim prefree segments */
unsigned int rec_prefree_segments;
- /* for small discard management */
- struct list_head discard_list; /* 4KB discard list */
- struct list_head wait_list; /* linked with issued discard bio */
- int nr_discards; /* # of discards in the list */
- int max_discards; /* max. discards to be issued */
-
/* for batched trimming */
unsigned int trim_sections; /* # of sections to trim */
@@ -637,10 +918,15 @@ struct f2fs_sm_info {
unsigned int ipu_policy; /* in-place-update policy */
unsigned int min_ipu_util; /* in-place-update threshold */
unsigned int min_fsync_blocks; /* threshold for fsync */
+ unsigned int min_seq_blocks; /* threshold for sequential blocks */
+ unsigned int min_hot_blocks; /* threshold for hot block allocation */
+ unsigned int min_ssr_sections; /* threshold to trigger SSR allocation */
/* for flush command control */
- struct flush_cmd_control *cmd_control_info;
+ struct flush_cmd_control *fcc_info;
+ /* for discard command control */
+ struct discard_cmd_control *dcc_info;
};
/*
@@ -652,13 +938,22 @@ struct f2fs_sm_info {
* f2fs monitors the number of several block types such as on-writeback,
* dirty dentry blocks, dirty node blocks, and dirty meta blocks.
*/
+#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
enum count_type {
F2FS_DIRTY_DENTS,
F2FS_DIRTY_DATA,
+ F2FS_DIRTY_QDATA,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
F2FS_INMEM_PAGES,
F2FS_DIRTY_IMETA,
+ F2FS_WB_CP_DATA,
+ F2FS_WB_DATA,
+ F2FS_RD_DATA,
+ F2FS_RD_NODE,
+ F2FS_RD_META,
+ F2FS_DIO_WRITE,
+ F2FS_DIO_READ,
NR_COUNT_TYPE,
};
@@ -682,36 +977,107 @@ enum page_type {
META_FLUSH,
INMEM, /* the below types are used by tracepoints only. */
INMEM_DROP,
+ INMEM_INVALIDATE,
INMEM_REVOKE,
IPU,
OPU,
};
+enum temp_type {
+ HOT = 0, /* must be zero for meta bio */
+ WARM,
+ COLD,
+ NR_TEMP_TYPE,
+};
+
+enum need_lock_type {
+ LOCK_REQ = 0,
+ LOCK_DONE,
+ LOCK_RETRY,
+};
+
+enum cp_reason_type {
+ CP_NO_NEEDED,
+ CP_NON_REGULAR,
+ CP_HARDLINK,
+ CP_SB_NEED_CP,
+ CP_WRONG_PINO,
+ CP_NO_SPC_ROLL,
+ CP_NODE_NEED_CP,
+ CP_FASTBOOT_MODE,
+ CP_SPEC_LOG_NUM,
+ CP_RECOVER_DIR,
+};
+
+enum iostat_type {
+ APP_DIRECT_IO, /* app direct IOs */
+ APP_BUFFERED_IO, /* app buffered IOs */
+ APP_WRITE_IO, /* app write IOs */
+ APP_MAPPED_IO, /* app mapped IOs */
+ FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */
+ FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */
+ FS_META_IO, /* meta IOs from kworker/reclaimer */
+ FS_GC_DATA_IO, /* data IOs from forground gc */
+ FS_GC_NODE_IO, /* node IOs from forground gc */
+ FS_CP_DATA_IO, /* data IOs from checkpoint */
+ FS_CP_NODE_IO, /* node IOs from checkpoint */
+ FS_CP_META_IO, /* meta IOs from checkpoint */
+ FS_DISCARD, /* discard */
+ NR_IO_TYPE,
+};
+
struct f2fs_io_info {
struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
+ nid_t ino; /* inode number */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
+ enum temp_type temp; /* contains HOT/WARM/COLD */
int op; /* contains REQ_OP_ */
- int op_flags; /* rq_flag_bits */
+ int op_flags; /* req_flag_bits */
block_t new_blkaddr; /* new block address to be written */
block_t old_blkaddr; /* old block address before Cow */
struct page *page; /* page to be written */
struct page *encrypted_page; /* encrypted page */
+ struct list_head list; /* serialize IOs */
+ bool submitted; /* indicate IO submission */
+ int need_lock; /* indicate we need to lock cp_rwsem */
+ bool in_list; /* indicate fio is in io_list */
bool is_meta; /* indicate borrow meta inode mapping or not */
+ bool retry; /* need to reallocate block address */
+ enum iostat_type io_type; /* io type */
+ struct writeback_control *io_wbc; /* writeback control */
+ unsigned char version; /* version of the node */
};
-#define is_read_io(rw) (rw == READ)
+#define is_read_io(rw) ((rw) == READ)
struct f2fs_bio_info {
struct f2fs_sb_info *sbi; /* f2fs superblock */
struct bio *bio; /* bios to merge */
sector_t last_block_in_bio; /* last block number */
struct f2fs_io_info fio; /* store buffered io info. */
struct rw_semaphore io_rwsem; /* blocking op for bio */
+ spinlock_t io_lock; /* serialize DATA/NODE IOs */
+ struct list_head io_list; /* track fios */
+};
+
+#define FDEV(i) (sbi->devs[i])
+#define RDEV(i) (raw_super->devs[i])
+struct f2fs_dev_info {
+ struct block_device *bdev;
+ char path[MAX_PATH_LEN];
+ unsigned int total_segments;
+ block_t start_blk;
+ block_t end_blk;
+#ifdef CONFIG_BLK_DEV_ZONED
+ unsigned int nr_blkz; /* Total number of zones */
+ u8 *blkz_type; /* Array of zones type */
+#endif
};
enum inode_type {
DIR_INODE, /* for dirty dir inode */
FILE_INODE, /* for dirty regular/symlink inode */
DIRTY_META, /* for all dirtied inode metadata */
+ ATOMIC_FILE, /* for all atomic files */
NR_INODE_TYPE,
};
@@ -731,29 +1097,70 @@ enum {
SBI_POR_DOING, /* recovery is doing or not */
SBI_NEED_SB_WRITE, /* need to recover superblock */
SBI_NEED_CP, /* need to checkpoint */
+ SBI_IS_SHUTDOWN, /* shutdown by ioctl */
+ SBI_IS_RECOVERED, /* recovered orphan/data */
+ SBI_CP_DISABLED, /* CP was disabled last mount */
+ SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */
+ SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */
+ SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */
+ SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */
};
enum {
CP_TIME,
REQ_TIME,
+ DISCARD_TIME,
+ GC_TIME,
+ DISABLE_TIME,
+ UMOUNT_DISCARD_TIMEOUT,
MAX_TIME,
};
+enum {
+ GC_NORMAL,
+ GC_IDLE_CB,
+ GC_IDLE_GREEDY,
+ GC_URGENT,
+};
+
+enum {
+ WHINT_MODE_OFF, /* not pass down write hints */
+ WHINT_MODE_USER, /* try to pass down hints given by users */
+ WHINT_MODE_FS, /* pass down hints with F2FS policy */
+};
+
+enum {
+ ALLOC_MODE_DEFAULT, /* stay default */
+ ALLOC_MODE_REUSE, /* reuse segments as much as possible */
+};
+
+enum fsync_mode {
+ FSYNC_MODE_POSIX, /* fsync follows posix semantics */
+ FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */
+ FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */
+};
+
#ifdef CONFIG_F2FS_FS_ENCRYPTION
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
+#define DUMMY_ENCRYPTION_ENABLED(sbi) \
+ (unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
+#else
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
+
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
struct f2fs_super_block *raw_super; /* raw super block pointer */
+ struct rw_semaphore sb_lock; /* lock for raw super block */
int valid_super_block; /* valid super block no */
unsigned long s_flag; /* flags for sbi */
+ struct mutex writepages; /* mutex for writepages() */
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
- u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
- u8 key_prefix_size;
+#ifdef CONFIG_BLK_DEV_ZONED
+ unsigned int blocks_per_blkz; /* F2FS blocks per zone */
+ unsigned int log_blocks_per_blkz; /* log2 F2FS blocks per zone */
#endif
+
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
struct inode *node_inode; /* cache node blocks */
@@ -762,9 +1169,10 @@ struct f2fs_sb_info {
struct f2fs_sm_info *sm_info; /* segment manager */
/* for bio operations */
- struct f2fs_bio_info read_io; /* for read bios */
- struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */
- struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */
+ struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
+ /* keep migration IO order for LFS mode */
+ struct rw_semaphore io_order_lock;
+ mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
@@ -774,12 +1182,18 @@ struct f2fs_sb_info {
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
+ struct rw_semaphore node_change; /* locking node change */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
long interval_time[MAX_TIME]; /* to store thresholds */
struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
+ spinlock_t fsync_node_lock; /* for node entry lock */
+ struct list_head fsync_node_list; /* node list head */
+ unsigned int fsync_seg_id; /* sequence id */
+ unsigned int fsync_node_num; /* number of node entries */
+
/* for orphan inode, use 0'th array */
unsigned int max_orphans; /* max orphan inodes */
@@ -789,7 +1203,7 @@ struct f2fs_sb_info {
/* for extent tree cache */
struct radix_tree_root extent_tree_root;/* cache extent cache entries */
- struct rw_semaphore extent_tree_lock; /* locking extent radix tree */
+ struct mutex extent_tree_lock; /* locking extent radix tree */
struct list_head extent_list; /* lru list for shrinker */
spinlock_t extent_lock; /* locking extent lru list */
atomic_t total_ext_tree; /* extent tree count */
@@ -812,21 +1226,29 @@ struct f2fs_sb_info {
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
loff_t max_file_blocks; /* max block index of file */
- int active_logs; /* # of active logs */
int dir_level; /* directory level */
+ int readdir_ra; /* readahead inode in readdir */
block_t user_block_count; /* # of user blocks */
block_t total_valid_block_count; /* # of valid blocks */
block_t discard_blks; /* discard command candidats */
block_t last_valid_block_count; /* for recovery */
- u32 s_next_generation; /* for NFS support */
- atomic_t nr_wb_bios; /* # of writeback bios */
+ block_t reserved_blocks; /* configurable reserved blocks */
+ block_t current_reserved_blocks; /* current reserved blocks */
+
+ /* Additional tracking for no checkpoint mode */
+ block_t unusable_block_count; /* # of blocks saved by last cp */
+
+ unsigned int nquota_files; /* # of quota sysfile */
/* # of pages, see count_type */
atomic_t nr_pages[NR_COUNT_TYPE];
/* # of allocated blocks */
struct percpu_counter alloc_valid_block_count;
+ /* writeback control */
+ atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */
+
/* valid inode count */
struct percpu_counter total_valid_inode_count;
@@ -836,12 +1258,19 @@ struct f2fs_sb_info {
struct mutex gc_mutex; /* mutex for GC */
struct f2fs_gc_kthread *gc_thread; /* GC thread */
unsigned int cur_victim_sec; /* current victim section num */
+ unsigned int gc_mode; /* current GC state */
+ unsigned int next_victim_seg[2]; /* next segment in victim section */
+ /* for skip statistic */
+ unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
+ unsigned long long skipped_gc_rwsem; /* FG_GC only */
- /* threshold for converting bg victims for fg */
- u64 fggc_threshold;
+ /* threshold for gc trials on pinned files */
+ u64 gc_pin_file_threshold;
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
+ /* migration granularity of garbage collection, unit: segment */
+ unsigned int migration_granularity;
/*
* for stat information.
@@ -849,6 +1278,7 @@ struct f2fs_sb_info {
*/
#ifdef CONFIG_F2FS_STAT_FS
struct f2fs_stat_info *stat_info; /* FS status information */
+ atomic_t meta_count[META_MAX]; /* # of meta blocks */
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
atomic_t inplace_count; /* # of inplace update */
@@ -859,18 +1289,32 @@ struct f2fs_sb_info {
atomic_t inline_xattr; /* # of inline_xattr inodes */
atomic_t inline_inode; /* # of inline_data inodes */
atomic_t inline_dir; /* # of inline_dentry inodes */
+ atomic_t aw_cnt; /* # of atomic writes */
+ atomic_t vw_cnt; /* # of volatile writes */
+ atomic_t max_aw_cnt; /* max # of atomic writes */
+ atomic_t max_vw_cnt; /* max # of volatile writes */
int bg_gc; /* background gc calls */
+ unsigned int io_skip_bggc; /* skip background gc for in-flight IO */
+ unsigned int other_skip_bggc; /* skip background gc for other reasons */
unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */
#endif
- unsigned int last_victim[2]; /* last victim segment # */
spinlock_t stat_lock; /* lock for stat operations */
+ /* For app/fs IO statistics */
+ spinlock_t iostat_lock;
+ unsigned long long write_iostat[NR_IO_TYPE];
+ bool iostat_enable;
+
/* For sysfs suppport */
struct kobject s_kobj;
struct completion s_kobj_unregister;
/* For shrinker support */
struct list_head s_list;
+ int s_ndevs; /* number of devices */
+ struct f2fs_dev_info *devs; /* for device list */
+ unsigned int dirty_device; /* for checkpoint data flush */
+ spinlock_t dev_lock; /* protect dirty_device */
struct mutex umount_mutex;
unsigned int shrinker_run_no;
@@ -881,16 +1325,25 @@ struct f2fs_sb_info {
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
- /* For fault injection */
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- struct f2fs_fault_info fault_info;
-#endif
+ /* Precomputed FS UUID checksum for seeding other checksums */
+ __u32 s_chksum_seed;
+};
+
+struct f2fs_private_dio {
+ struct inode *inode;
+ void *orig_private;
+ bio_end_io_t *orig_end_io;
+ bool write;
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
+#define f2fs_show_injection_info(type) \
+ printk_ratelimited("%sF2FS-fs : inject %s in %s of %pF\n", \
+ KERN_INFO, f2fs_fault_name[type], \
+ __func__, __builtin_return_address(0))
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
- struct f2fs_fault_info *ffi = &sbi->fault_info;
+ struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
if (!ffi->inject_rate)
return false;
@@ -901,69 +1354,87 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
atomic_inc(&ffi->inject_ops);
if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
atomic_set(&ffi->inject_ops, 0);
- printk("%sF2FS-fs : inject %s in %pF\n",
- KERN_INFO,
- fault_name[type],
- __builtin_return_address(0));
return true;
}
return false;
}
+#else
+#define f2fs_show_injection_info(type) do { } while (0)
+static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
+{
+ return false;
+}
#endif
/* For write statistics. Suppose sector size is 512 bytes,
* and the return value is in kbytes. s is of struct f2fs_sb_info.
*/
#define BD_PART_WRITTEN(s) \
-(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) - \
- s->sectors_written_start) >> 1)
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) - \
+ (s)->sectors_written_start) >> 1)
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
- sbi->last_time[type] = jiffies;
+ unsigned long now = jiffies;
+
+ sbi->last_time[type] = now;
+
+ /* DISCARD_TIME and GC_TIME are based on REQ_TIME */
+ if (type == REQ_TIME) {
+ sbi->last_time[DISCARD_TIME] = now;
+ sbi->last_time[GC_TIME] = now;
+ }
}
static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
- struct timespec ts = {sbi->interval_time[type], 0};
- unsigned long interval = timespec_to_jiffies(&ts);
+ unsigned long interval = sbi->interval_time[type] * HZ;
return time_after(jiffies, sbi->last_time[type] + interval);
}
-static inline bool is_idle(struct f2fs_sb_info *sbi)
+static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi,
+ int type)
{
- struct block_device *bdev = sbi->sb->s_bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- struct request_list *rl = &q->root_rl;
+ unsigned long interval = sbi->interval_time[type] * HZ;
+ unsigned int wait_ms = 0;
+ long delta;
- if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC])
- return 0;
+ delta = (sbi->last_time[type] + interval) - jiffies;
+ if (delta > 0)
+ wait_ms = jiffies_to_msecs(delta);
- return f2fs_time_over(sbi, REQ_TIME);
+ return wait_ms;
}
/*
* Inline functions
*/
+static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
+ const void *address, unsigned int length)
+{
+ struct {
+ struct shash_desc shash;
+ char ctx[4];
+ } desc;
+ int err;
+
+ BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
+
+ desc.shash.tfm = sbi->s_chksum_driver;
+ desc.shash.flags = 0;
+ *(u32 *)desc.ctx = crc;
+
+ err = crypto_shash_update(&desc.shash, address, length);
+ BUG_ON(err);
+
+ return *(u32 *)desc.ctx;
+}
+
static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
unsigned int length)
{
- SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
- u32 *ctx = (u32 *)shash_desc_ctx(shash);
- u32 retval;
- int err;
-
- shash->tfm = sbi->s_chksum_driver;
- shash->flags = 0;
- *ctx = F2FS_SUPER_MAGIC;
-
- err = crypto_shash_update(shash, address, length);
- BUG_ON(err);
-
- retval = *ctx;
- barrier_data(ctx);
- return retval;
+ return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length);
}
static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
@@ -972,6 +1443,12 @@ static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
}
+static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc,
+ const void *address, unsigned int length)
+{
+ return __f2fs_crc32(sbi, crc, address, length);
+}
+
static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -1072,6 +1549,19 @@ static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
return le64_to_cpu(cp->checkpoint_ver);
}
+static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type)
+{
+ if (type < F2FS_MAX_QUOTAS)
+ return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]);
+ return 0;
+}
+
+static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
+{
+ size_t crc_offset = le32_to_cpu(cp->checksum_offset);
+ return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
+}
+
static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
@@ -1095,9 +1585,11 @@ static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
- spin_lock(&sbi->cp_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&sbi->cp_lock, flags);
__set_ckpt_flags(F2FS_CKPT(sbi), f);
- spin_unlock(&sbi->cp_lock);
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
@@ -1111,16 +1603,38 @@ static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f
static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
- spin_lock(&sbi->cp_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&sbi->cp_lock, flags);
__clear_ckpt_flags(F2FS_CKPT(sbi), f);
- spin_unlock(&sbi->cp_lock);
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
-static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi)
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
- struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
+ unsigned long flags;
- return blk_queue_discard(q);
+ /*
+ * In order to re-enable nat_bits we need to call fsck.f2fs by
+ * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
+ * so let's rely on regular fsck or unclean shutdown.
+ */
+
+ if (lock)
+ spin_lock_irqsave(&sbi->cp_lock, flags);
+ __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+ kvfree(NM_I(sbi)->nat_bits);
+ NM_I(sbi)->nat_bits = NULL;
+ if (lock)
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
+}
+
+static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
+{
+ bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
+
+ return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
}
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
@@ -1128,6 +1642,11 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
down_read(&sbi->cp_rwsem);
}
+static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
+{
+ return down_read_trylock(&sbi->cp_rwsem);
+}
+
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
up_read(&sbi->cp_rwsem);
@@ -1156,7 +1675,7 @@ static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
static inline bool __remain_node_summaries(int reason)
{
- return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+ return (reason & (CP_UMOUNT | CP_FASTBOOT));
}
static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
@@ -1166,28 +1685,13 @@ static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
}
/*
- * Check whether the given nid is within node id range.
- */
-static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
-{
- if (unlikely(nid < F2FS_ROOT_INO(sbi)))
- return -EINVAL;
- if (unlikely(nid >= NM_I(sbi)->max_nid))
- return -EINVAL;
- return 0;
-}
-
-#define F2FS_DEFAULT_ALLOCATED_BLOCKS 1
-
-/*
* Check whether the inode has blocks or not
*/
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
- if (F2FS_I(inode)->i_xattr_nid)
- return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1;
- else
- return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS;
+ block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;
+
+ return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
}
static inline bool f2fs_has_xattr_block(unsigned int ofs)
@@ -1195,16 +1699,43 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
return ofs == XATTR_NODE_OFFSET;
}
-static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
-static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
+ struct inode *inode, bool cap)
+{
+ if (!inode)
+ return true;
+ if (!test_opt(sbi, RESERVE_ROOT))
+ return false;
+ if (IS_NOQUOTA(inode))
+ return true;
+ if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
+ return true;
+ if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
+ in_group_p(F2FS_OPTION(sbi).s_resgid))
+ return true;
+ if (cap && capable(CAP_SYS_RESOURCE))
+ return true;
+ return false;
+}
+
+static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
+static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
struct inode *inode, blkcnt_t *count)
{
- blkcnt_t diff;
+ blkcnt_t diff = 0, release = 0;
+ block_t avail_user_block_count;
+ int ret;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_BLOCK))
- return false;
-#endif
+ ret = dquot_reserve_block(inode, *count);
+ if (ret)
+ return ret;
+
+ if (time_to_inject(sbi, FAULT_BLOCK)) {
+ f2fs_show_injection_info(FAULT_BLOCK);
+ release = *count;
+ goto enospc;
+ }
+
/*
* let's increase this in prior to actual block count change in order
* for f2fs_sync_file to avoid data races when deciding checkpoint.
@@ -1213,42 +1744,68 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
spin_lock(&sbi->stat_lock);
sbi->total_valid_block_count += (block_t)(*count);
- if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
- diff = sbi->total_valid_block_count - sbi->user_block_count;
+ avail_user_block_count = sbi->user_block_count -
+ sbi->current_reserved_blocks;
+
+ if (!__allow_reserved_blocks(sbi, inode, true))
+ avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ avail_user_block_count -= sbi->unusable_block_count;
+ if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
+ diff = sbi->total_valid_block_count - avail_user_block_count;
+ if (diff > *count)
+ diff = *count;
*count -= diff;
- sbi->total_valid_block_count = sbi->user_block_count;
+ release = diff;
+ sbi->total_valid_block_count -= diff;
if (!*count) {
spin_unlock(&sbi->stat_lock);
- percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
- return false;
+ goto enospc;
}
}
spin_unlock(&sbi->stat_lock);
- f2fs_i_blocks_write(inode, *count, true);
- return true;
+ if (unlikely(release)) {
+ percpu_counter_sub(&sbi->alloc_valid_block_count, release);
+ dquot_release_reservation_block(inode, release);
+ }
+ f2fs_i_blocks_write(inode, *count, true, true);
+ return 0;
+
+enospc:
+ percpu_counter_sub(&sbi->alloc_valid_block_count, release);
+ dquot_release_reservation_block(inode, release);
+ return -ENOSPC;
}
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
struct inode *inode,
- blkcnt_t count)
+ block_t count)
{
+ blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
+
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
- f2fs_bug_on(sbi, inode->i_blocks < count);
+ f2fs_bug_on(sbi, inode->i_blocks < sectors);
sbi->total_valid_block_count -= (block_t)count;
+ if (sbi->reserved_blocks &&
+ sbi->current_reserved_blocks < sbi->reserved_blocks)
+ sbi->current_reserved_blocks = min(sbi->reserved_blocks,
+ sbi->current_reserved_blocks + count);
spin_unlock(&sbi->stat_lock);
- f2fs_i_blocks_write(inode, count, false);
+ f2fs_i_blocks_write(inode, count, false, true);
}
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
atomic_inc(&sbi->nr_pages[count_type]);
- if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES)
- return;
-
- set_sbi_flag(sbi, SBI_IS_DIRTY);
+ if (count_type == F2FS_DIRTY_DENTS ||
+ count_type == F2FS_DIRTY_NODES ||
+ count_type == F2FS_DIRTY_META ||
+ count_type == F2FS_DIRTY_QDATA ||
+ count_type == F2FS_DIRTY_IMETA)
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
}
static inline void inode_inc_dirty_pages(struct inode *inode)
@@ -1256,6 +1813,8 @@ static inline void inode_inc_dirty_pages(struct inode *inode)
atomic_inc(&F2FS_I(inode)->dirty_pages);
inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
+ if (IS_NOQUOTA(inode))
+ inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1272,6 +1831,8 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
atomic_dec(&F2FS_I(inode)->dirty_pages);
dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
+ if (IS_NOQUOTA(inode))
+ dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
}
static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
@@ -1326,6 +1887,12 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
int offset;
+ if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
+ offset = (flag == SIT_BITMAP) ?
+ le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
+ return &ckpt->sit_nat_version_bitmap + offset;
+ }
+
if (__cp_payload(sbi) > 0) {
if (flag == NAT_BITMAP)
return &ckpt->sit_nat_version_bitmap;
@@ -1366,51 +1933,96 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}
-static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
- struct inode *inode)
+static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
+ struct inode *inode, bool is_inode)
{
block_t valid_block_count;
unsigned int valid_node_count;
+ int err;
+
+ if (is_inode) {
+ if (inode) {
+ err = dquot_alloc_inode(inode);
+ if (err)
+ return err;
+ }
+ } else {
+ err = dquot_reserve_block(inode, 1);
+ if (err)
+ return err;
+ }
+
+ if (time_to_inject(sbi, FAULT_BLOCK)) {
+ f2fs_show_injection_info(FAULT_BLOCK);
+ goto enospc;
+ }
spin_lock(&sbi->stat_lock);
- valid_block_count = sbi->total_valid_block_count + 1;
+ valid_block_count = sbi->total_valid_block_count +
+ sbi->current_reserved_blocks + 1;
+
+ if (!__allow_reserved_blocks(sbi, inode, false))
+ valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ valid_block_count += sbi->unusable_block_count;
+
if (unlikely(valid_block_count > sbi->user_block_count)) {
spin_unlock(&sbi->stat_lock);
- return false;
+ goto enospc;
}
valid_node_count = sbi->total_valid_node_count + 1;
if (unlikely(valid_node_count > sbi->total_node_count)) {
spin_unlock(&sbi->stat_lock);
- return false;
+ goto enospc;
}
- if (inode)
- f2fs_i_blocks_write(inode, 1, true);
-
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
+ if (inode) {
+ if (is_inode)
+ f2fs_mark_inode_dirty_sync(inode, true);
+ else
+ f2fs_i_blocks_write(inode, 1, true, true);
+ }
+
percpu_counter_inc(&sbi->alloc_valid_block_count);
- return true;
+ return 0;
+
+enospc:
+ if (is_inode) {
+ if (inode)
+ dquot_free_inode(inode);
+ } else {
+ dquot_release_reservation_block(inode, 1);
+ }
+ return -ENOSPC;
}
static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
- struct inode *inode)
+ struct inode *inode, bool is_inode)
{
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, !sbi->total_valid_block_count);
f2fs_bug_on(sbi, !sbi->total_valid_node_count);
- f2fs_bug_on(sbi, !inode->i_blocks);
+ f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
- f2fs_i_blocks_write(inode, 1, false);
sbi->total_valid_node_count--;
sbi->total_valid_block_count--;
+ if (sbi->reserved_blocks &&
+ sbi->current_reserved_blocks < sbi->reserved_blocks)
+ sbi->current_reserved_blocks++;
spin_unlock(&sbi->stat_lock);
+
+ if (is_inode)
+ dquot_free_inode(inode);
+ else
+ f2fs_i_blocks_write(inode, 1, false, true);
}
static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1436,19 +2048,40 @@ static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
pgoff_t index, bool for_write)
{
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- struct page *page = find_lock_page(mapping, index);
- if (page)
- return page;
+ struct page *page;
- if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
- return NULL;
-#endif
+ if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
+ if (!for_write)
+ page = find_get_page_flags(mapping, index,
+ FGP_LOCK | FGP_ACCESSED);
+ else
+ page = find_lock_page(mapping, index);
+ if (page)
+ return page;
+
+ if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
+ f2fs_show_injection_info(FAULT_PAGE_ALLOC);
+ return NULL;
+ }
+ }
+
if (!for_write)
return grab_cache_page(mapping, index);
return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
}
+static inline struct page *f2fs_pagecache_get_page(
+ struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp_mask)
+{
+ if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
+ f2fs_show_injection_info(FAULT_PAGE_GET);
+ return NULL;
+ }
+
+ return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
+}
+
static inline void f2fs_copy_page(struct page *src, struct page *dst)
{
char *src_kaddr = kmap(src);
@@ -1498,15 +2131,44 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
return entry;
}
-static inline struct bio *f2fs_bio_alloc(int npages)
+static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
+ int npages, bool no_fail)
{
struct bio *bio;
- /* No failure on bio allocation */
- bio = bio_alloc(GFP_NOIO, npages);
- if (!bio)
- bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
- return bio;
+ if (no_fail) {
+ /* No failure on bio allocation */
+ bio = bio_alloc(GFP_NOIO, npages);
+ if (!bio)
+ bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
+ return bio;
+ }
+ if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
+ f2fs_show_injection_info(FAULT_ALLOC_BIO);
+ return NULL;
+ }
+
+ return bio_alloc(GFP_KERNEL, npages);
+}
+
+static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
+{
+ if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
+ get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
+ get_pages(sbi, F2FS_WB_CP_DATA) ||
+ get_pages(sbi, F2FS_DIO_READ) ||
+ get_pages(sbi, F2FS_DIO_WRITE))
+ return false;
+
+ if (SM_I(sbi) && SM_I(sbi)->dcc_info &&
+ atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
+ return false;
+
+ if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
+ atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
+ return false;
+
+ return f2fs_time_over(sbi, type);
}
static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
@@ -1521,22 +2183,42 @@ static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
static inline bool IS_INODE(struct page *page)
{
struct f2fs_node *p = F2FS_NODE(page);
+
return RAW_IS_INODE(p);
}
+static inline int offset_in_addr(struct f2fs_inode *i)
+{
+ return (i->i_inline & F2FS_EXTRA_ATTR) ?
+ (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0;
+}
+
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}
-static inline block_t datablock_addr(struct page *node_page,
- unsigned int offset)
+static inline int f2fs_has_extra_attr(struct inode *inode);
+static inline block_t datablock_addr(struct inode *inode,
+ struct page *node_page, unsigned int offset)
{
struct f2fs_node *raw_node;
__le32 *addr_array;
+ int base = 0;
+ bool is_inode = IS_INODE(node_page);
+
raw_node = F2FS_NODE(node_page);
+
+ /* from GC path only */
+ if (is_inode) {
+ if (!inode)
+ base = offset_in_addr(&raw_node->i);
+ else if (f2fs_has_extra_attr(inode))
+ base = get_extra_isize(inode);
+ }
+
addr_array = blkaddr_in_node(raw_node);
- return le32_to_cpu(addr_array[offset]);
+ return le32_to_cpu(addr_array[base + offset]);
}
static inline int f2fs_test_bit(unsigned int nr, char *addr)
@@ -1599,6 +2281,72 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
*addr ^= mask;
}
+/*
+ * Inode flags
+ */
+#define F2FS_SECRM_FL 0x00000001 /* Secure deletion */
+#define F2FS_UNRM_FL 0x00000002 /* Undelete */
+#define F2FS_COMPR_FL 0x00000004 /* Compress file */
+#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */
+#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
+#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */
+#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */
+#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define F2FS_DIRTY_FL 0x00000100
+#define F2FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
+#define F2FS_NOCOMPR_FL 0x00000400 /* Don't compress */
+#define F2FS_ENCRYPT_FL 0x00000800 /* encrypted file */
+/* End compression flags --- maybe not all used */
+#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */
+#define F2FS_IMAGIC_FL 0x00002000 /* AFS directory */
+#define F2FS_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */
+#define F2FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
+#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
+#define F2FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
+#define F2FS_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
+#define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */
+#define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
+#define F2FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
+#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
+#define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
+
+#define F2FS_FL_USER_VISIBLE 0x30CBDFFF /* User visible flags */
+#define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */
+
+/* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */
+#define F2FS_FL_XFLAG_VISIBLE (F2FS_SYNC_FL | \
+ F2FS_IMMUTABLE_FL | \
+ F2FS_APPEND_FL | \
+ F2FS_NODUMP_FL | \
+ F2FS_NOATIME_FL | \
+ F2FS_PROJINHERIT_FL)
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define F2FS_FL_INHERITED (F2FS_SECRM_FL | F2FS_UNRM_FL | F2FS_COMPR_FL |\
+ F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL |\
+ F2FS_NOCOMPR_FL | F2FS_JOURNAL_DATA_FL |\
+ F2FS_NOTAIL_FL | F2FS_DIRSYNC_FL |\
+ F2FS_PROJINHERIT_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL)
+
+static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+{
+ if (S_ISDIR(mode))
+ return flags;
+ else if (S_ISREG(mode))
+ return flags & F2FS_REG_FLMASK;
+ else
+ return flags & F2FS_OTHER_FLMASK;
+}
+
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
@@ -1617,6 +2365,7 @@ enum {
FI_UPDATE_WRITE, /* inode has in-place-update data */
FI_NEED_IPU, /* used for ipu per file */
FI_ATOMIC_FILE, /* indicate atomic file */
+ FI_ATOMIC_COMMIT, /* indicate the state of atomical committing */
FI_VOLATILE_FILE, /* indicate volatile file */
FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */
FI_DROP_CACHE, /* drop dirty page cache */
@@ -1624,6 +2373,12 @@ enum {
FI_INLINE_DOTS, /* indicate inline dot dentries */
FI_DO_DEFRAG, /* indicate defragment is running */
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
+ FI_NO_PREALLOC, /* indicate skipped preallocated blocks */
+ FI_HOT_DATA, /* indicate file is hot */
+ FI_EXTRA_ATTR, /* indicate file has extra attribute */
+ FI_PROJ_INHERIT, /* indicate file inherits projectid */
+ FI_PIN_FILE, /* indicate file should not be gced */
+ FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
};
static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -1633,11 +2388,14 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
case FI_INLINE_XATTR:
case FI_INLINE_DATA:
case FI_INLINE_DENTRY:
+ case FI_NEW_INODE:
if (set)
return;
+ /* fall through */
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
- f2fs_mark_inode_dirty_sync(inode);
+ case FI_PIN_FILE:
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}
@@ -1664,7 +2422,7 @@ static inline void set_acl_inode(struct inode *inode, umode_t mode)
{
F2FS_I(inode)->i_acl_mode = mode;
set_inode_flag(inode, FI_ACL_MODE);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
}
static inline void f2fs_i_links_write(struct inode *inode, bool inc)
@@ -1673,18 +2431,26 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
inc_nlink(inode);
else
drop_nlink(inode);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void f2fs_i_blocks_write(struct inode *inode,
- blkcnt_t diff, bool add)
+ block_t diff, bool add, bool claim)
{
bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
- inode->i_blocks = add ? inode->i_blocks + diff :
- inode->i_blocks - diff;
- f2fs_mark_inode_dirty_sync(inode);
+ /* add = 1, claim = 1 should be dquot_reserve_block in pair */
+ if (add) {
+ if (claim)
+ dquot_claim_block(inode, diff);
+ else
+ dquot_alloc_block_nofail(inode, diff);
+ } else {
+ dquot_free_block(inode, diff);
+ }
+
+ f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
@@ -1698,34 +2464,34 @@ static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
return;
i_size_write(inode, i_size);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
-static inline bool f2fs_skip_inode_update(struct inode *inode)
-{
- if (!is_inode_flag_set(inode, FI_AUTO_RECOVER))
- return false;
- return F2FS_I(inode)->last_disk_size == i_size_read(inode);
-}
-
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
{
F2FS_I(inode)->i_current_depth = depth;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void f2fs_i_gc_failures_write(struct inode *inode,
+ unsigned int count)
+{
+ F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
+ f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
{
F2FS_I(inode)->i_xattr_nid = xnid;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
F2FS_I(inode)->i_pino = pino;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
@@ -1742,6 +2508,10 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
set_bit(FI_DATA_EXIST, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DOTS)
set_bit(FI_INLINE_DOTS, &fi->flags);
+ if (ri->i_inline & F2FS_EXTRA_ATTR)
+ set_bit(FI_EXTRA_ATTR, &fi->flags);
+ if (ri->i_inline & F2FS_PIN_FILE)
+ set_bit(FI_PIN_FILE, &fi->flags);
}
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
@@ -1758,6 +2528,15 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
ri->i_inline |= F2FS_DATA_EXIST;
if (is_inode_flag_set(inode, FI_INLINE_DOTS))
ri->i_inline |= F2FS_INLINE_DOTS;
+ if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
+ ri->i_inline |= F2FS_EXTRA_ATTR;
+ if (is_inode_flag_set(inode, FI_PIN_FILE))
+ ri->i_inline |= F2FS_PIN_FILE;
+}
+
+static inline int f2fs_has_extra_attr(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_EXTRA_ATTR);
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
@@ -1767,24 +2546,20 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
static inline unsigned int addrs_per_inode(struct inode *inode)
{
- if (f2fs_has_inline_xattr(inode))
- return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
- return DEF_ADDRS_PER_INODE;
+ return CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode);
}
-static inline void *inline_xattr_addr(struct page *page)
+static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
+
return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
- F2FS_INLINE_XATTR_ADDRS]);
+ get_inline_xattr_addrs(inode)]);
}
static inline int inline_xattr_size(struct inode *inode)
{
- if (f2fs_has_inline_xattr(inode))
- return F2FS_INLINE_XATTR_ADDRS << 2;
- else
- return 0;
+ return get_inline_xattr_addrs(inode) * sizeof(__le32);
}
static inline int f2fs_has_inline_data(struct inode *inode)
@@ -1792,12 +2567,6 @@ static inline int f2fs_has_inline_data(struct inode *inode)
return is_inode_flag_set(inode, FI_INLINE_DATA);
}
-static inline void f2fs_clear_inline_inode(struct inode *inode)
-{
- clear_inode_flag(inode, FI_INLINE_DATA);
- clear_inode_flag(inode, FI_DATA_EXIST);
-}
-
static inline int f2fs_exist_data(struct inode *inode)
{
return is_inode_flag_set(inode, FI_DATA_EXIST);
@@ -1808,11 +2577,21 @@ static inline int f2fs_has_inline_dots(struct inode *inode)
return is_inode_flag_set(inode, FI_INLINE_DOTS);
}
+static inline bool f2fs_is_pinned_file(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_PIN_FILE);
+}
+
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_ATOMIC_FILE);
}
+static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
+}
+
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_VOLATILE_FILE);
@@ -1828,10 +2607,12 @@ static inline bool f2fs_is_drop_cache(struct inode *inode)
return is_inode_flag_set(inode, FI_DROP_CACHE);
}
-static inline void *inline_data_addr(struct page *page)
+static inline void *inline_data_addr(struct inode *inode, struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
- return (void *)&(ri->i_addr[1]);
+ int extra_size = get_extra_isize(inode);
+
+ return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
}
static inline int f2fs_has_inline_dentry(struct inode *inode)
@@ -1839,12 +2620,6 @@ static inline int f2fs_has_inline_dentry(struct inode *inode)
return is_inode_flag_set(inode, FI_INLINE_DENTRY);
}
-static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
-{
- if (!f2fs_has_inline_dentry(dir))
- kunmap(page);
-}
-
static inline int is_file(struct inode *inode, int type)
{
return F2FS_I(inode)->i_advise & type;
@@ -1853,16 +2628,50 @@ static inline int is_file(struct inode *inode, int type)
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
-static inline int f2fs_readonly(struct super_block *sb)
+static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
+{
+ bool ret;
+
+ if (dsync) {
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ ret = list_empty(&F2FS_I(inode)->gdirty_list);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return ret;
+ }
+ if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
+ file_keep_isize(inode) ||
+ i_size_read(inode) & ~PAGE_MASK)
+ return false;
+
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
+ return false;
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
+ return false;
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
+ return false;
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time + 3,
+ &F2FS_I(inode)->i_crtime))
+ return false;
+
+ down_read(&F2FS_I(inode)->i_sem);
+ ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
+ up_read(&F2FS_I(inode)->i_sem);
+
+ return ret;
+}
+
+static inline bool f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
}
@@ -1901,17 +2710,7 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
return S_ISREG(inode->i_mode);
}
-static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
- size_t size, gfp_t flags)
-{
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_KMALLOC))
- return NULL;
-#endif
- return kmalloc(size, flags);
-}
-
-static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
+static inline void *kvmalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -1921,7 +2720,24 @@ static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
return ret;
}
-static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
+static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
+ size_t size, gfp_t flags)
+{
+ void *ret;
+
+ if (time_to_inject(sbi, FAULT_KMALLOC)) {
+ f2fs_show_injection_info(FAULT_KMALLOC);
+ return NULL;
+ }
+
+ ret = kmalloc(size, flags);
+ if (ret)
+ return ret;
+
+ return kvmalloc(size, flags);
+}
+
+static inline void *kvzalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -1931,18 +2747,92 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
return ret;
}
-#define get_inode_mode(i) \
+static inline int wbc_to_write_flags(struct writeback_control *wbc)
+{
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ return REQ_SYNC;
+ else if (wbc->for_kupdate || wbc->for_background)
+ return 0;
+
+ return 0;
+}
+
+static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
+ size_t size, gfp_t flags)
+{
+ return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO);
+}
+
+static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
+ size_t size, gfp_t flags)
+{
+ if (time_to_inject(sbi, FAULT_KVMALLOC)) {
+ f2fs_show_injection_info(FAULT_KVMALLOC);
+ return NULL;
+ }
+
+ return kvmalloc(size, flags);
+}
+
+static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi,
+ size_t size, gfp_t flags)
+{
+ return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO);
+}
+
+static inline int get_extra_isize(struct inode *inode)
+{
+ return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
+}
+
+static inline int get_inline_xattr_addrs(struct inode *inode)
+{
+ return F2FS_I(inode)->i_inline_xattr_size;
+}
+
+#define f2fs_get_inode_mode(i) \
((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
-/* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, inode) \
- ((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) : \
- (pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) / \
- ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
+#define F2FS_TOTAL_EXTRA_ATTR_SIZE \
+ (offsetof(struct f2fs_inode, i_extra_end) - \
+ offsetof(struct f2fs_inode, i_extra_isize)) \
-#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \
- (!is_read_io(fio->op) || fio->is_meta))
+#define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr))
+#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \
+ ((offsetof(typeof(*(f2fs_inode)), field) + \
+ sizeof((f2fs_inode)->field)) \
+ <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \
+
+static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ spin_lock(&sbi->iostat_lock);
+ for (i = 0; i < NR_IO_TYPE; i++)
+ sbi->write_iostat[i] = 0;
+ spin_unlock(&sbi->iostat_lock);
+}
+
+static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
+ enum iostat_type type, unsigned long long io_bytes)
+{
+ if (!sbi->iostat_enable)
+ return;
+ spin_lock(&sbi->iostat_lock);
+ sbi->write_iostat[type] += io_bytes;
+
+ if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
+ sbi->write_iostat[APP_BUFFERED_IO] =
+ sbi->write_iostat[APP_WRITE_IO] -
+ sbi->write_iostat[APP_DIRECT_IO];
+ spin_unlock(&sbi->iostat_lock);
+}
+
+#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1)
+
+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \
+ (!is_read_io((fio)->op) || (fio)->is_meta))
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
@@ -1974,92 +2864,127 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
return true;
}
+static inline void f2fs_set_page_private(struct page *page,
+ unsigned long data)
+{
+ if (PagePrivate(page))
+ return;
+
+ get_page(page);
+ SetPagePrivate(page);
+ set_page_private(page, data);
+}
+
+static inline void f2fs_clear_page_private(struct page *page)
+{
+ if (!PagePrivate(page))
+ return;
+
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ f2fs_put_page(page, 0);
+}
+
/*
* file.c
*/
-int f2fs_sync_file(struct file *, loff_t, loff_t, int);
-void truncate_data_blocks(struct dnode_of_data *);
-int truncate_blocks(struct inode *, u64, bool);
-int f2fs_truncate(struct inode *);
-int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
-int f2fs_setattr(struct dentry *, struct iattr *);
-int truncate_hole(struct inode *, pgoff_t, pgoff_t);
-int truncate_data_blocks_range(struct dnode_of_data *, int);
-long f2fs_ioctl(struct file *, unsigned int, unsigned long);
-long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
+void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
+int f2fs_truncate(struct inode *inode);
+int f2fs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat);
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
+int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+int f2fs_precache_extents(struct inode *inode);
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int f2fs_pin_file_control(struct inode *inode, bool inc);
/*
* inode.c
*/
-void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget(struct super_block *, unsigned long);
-struct inode *f2fs_iget_retry(struct super_block *, unsigned long);
-int try_to_free_nats(struct f2fs_sb_info *, int);
-int update_inode(struct inode *, struct page *);
-int update_inode_page(struct inode *);
-int f2fs_write_inode(struct inode *, struct writeback_control *);
-void f2fs_evict_inode(struct inode *);
-void handle_failed_inode(struct inode *);
+void f2fs_set_inode_flags(struct inode *inode);
+bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
+struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
+int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
+void f2fs_update_inode(struct inode *inode, struct page *node_page);
+void f2fs_update_inode_page(struct inode *inode);
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
+void f2fs_evict_inode(struct inode *inode);
+void f2fs_handle_failed_inode(struct inode *inode);
/*
* namei.c
*/
+int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
+ bool hot, bool set);
struct dentry *f2fs_get_parent(struct dentry *child);
/*
* dir.c
*/
-void set_de_type(struct f2fs_dir_entry *, umode_t);
-unsigned char get_de_type(struct f2fs_dir_entry *);
-struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
- f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
-bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
- unsigned int, struct fscrypt_str *);
-void do_make_empty_dir(struct inode *, struct inode *,
- struct f2fs_dentry_ptr *);
-struct page *init_inode_metadata(struct inode *, struct inode *,
- const struct qstr *, const struct qstr *, struct page *);
-void update_parent_metadata(struct inode *, struct inode *, unsigned int);
-int room_for_filename(const void *, int, int);
-void f2fs_drop_nlink(struct inode *, struct inode *);
-struct f2fs_dir_entry *__f2fs_find_entry(struct inode *, struct fscrypt_name *,
- struct page **);
-struct f2fs_dir_entry *f2fs_find_entry(struct inode *, const struct qstr *,
- struct page **);
-struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, const struct qstr *, struct page **);
-void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
- struct page *, struct inode *);
-int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
-void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
- const struct qstr *, f2fs_hash_t , unsigned int);
-int f2fs_add_regular_entry(struct inode *, const struct qstr *,
- const struct qstr *, struct inode *, nid_t, umode_t);
-int __f2fs_do_add_link(struct inode *, struct fscrypt_name*, struct inode *,
- nid_t, umode_t);
-int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
- umode_t);
-void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
- struct inode *);
-int f2fs_do_tmpfile(struct inode *, struct inode *);
-bool f2fs_empty_dir(struct inode *);
+unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
+struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
+ f2fs_hash_t namehash, int *max_slots,
+ struct f2fs_dentry_ptr *d);
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+ unsigned int start_pos, struct fscrypt_str *fstr);
+void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
+ struct f2fs_dentry_ptr *d);
+struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
+ const struct qstr *new_name,
+ const struct qstr *orig_name, struct page *dpage);
+void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
+ unsigned int current_depth);
+int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page);
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
+ const struct qstr *child, struct page **res_page);
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
+ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
+ struct page **page);
+void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
+ struct page *page, struct inode *inode);
+void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
+ const struct qstr *name, f2fs_hash_t name_hash,
+ unsigned int bit_pos);
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode);
+int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
+ struct inode *inode, nid_t ino, umode_t mode);
+int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
+ struct inode *dir, struct inode *inode);
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
+bool f2fs_empty_dir(struct inode *dir);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
- return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name,
+ return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
inode, inode->i_ino, inode->i_mode);
}
/*
* super.c
*/
-int f2fs_inode_dirtied(struct inode *);
-void f2fs_inode_synced(struct inode *);
-int f2fs_commit_super(struct f2fs_sb_info *, bool);
-int f2fs_sync_fs(struct super_block *, int);
+int f2fs_inode_dirtied(struct inode *inode, bool sync);
+void f2fs_inode_synced(struct inode *inode);
+int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
+int f2fs_quota_sync(struct super_block *sb, int type);
+void f2fs_quota_off_umount(struct super_block *sb);
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
+int f2fs_sync_fs(struct super_block *sb, int sync);
extern __printf(3, 4)
-void f2fs_msg(struct super_block *, const char *, const char *, ...);
-int sanity_check_ckpt(struct f2fs_sb_info *sbi);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
@@ -2073,161 +2998,221 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
struct dnode_of_data;
struct node_info;
-bool available_free_memory(struct f2fs_sb_info *, int);
-int need_dentry_mark(struct f2fs_sb_info *, nid_t);
-bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
-void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
-pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
-int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
-int truncate_inode_blocks(struct inode *, pgoff_t);
-int truncate_xattr_node(struct inode *, struct page *);
-int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t);
-int remove_inode_page(struct inode *);
-struct page *new_inode_page(struct inode *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
-void ra_node_page(struct f2fs_sb_info *, nid_t);
-struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_node_page_ra(struct page *, int);
-void move_node_page(struct page *, int);
-int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
- struct writeback_control *, bool);
-int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
-void build_free_nids(struct f2fs_sb_info *);
-bool alloc_nid(struct f2fs_sb_info *, nid_t *);
-void alloc_nid_done(struct f2fs_sb_info *, nid_t);
-void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
-int try_to_free_nids(struct f2fs_sb_info *, int);
-void recover_inline_xattr(struct inode *, struct page *);
-void recover_xattr_data(struct inode *, struct page *, block_t);
-int recover_inode_page(struct f2fs_sb_info *, struct page *);
-int restore_node_summary(struct f2fs_sb_info *, unsigned int,
- struct f2fs_summary_block *);
-void flush_nat_entries(struct f2fs_sb_info *);
-int build_node_manager(struct f2fs_sb_info *);
-void destroy_node_manager(struct f2fs_sb_info *);
-int __init create_node_manager_caches(void);
-void destroy_node_manager_caches(void);
+int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
+bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
+void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
+int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
+int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
+ struct node_info *ni);
+pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
+int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
+int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
+int f2fs_truncate_xattr_node(struct inode *inode);
+int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
+ unsigned int seq_id);
+int f2fs_remove_inode_page(struct inode *inode);
+struct page *f2fs_new_inode_page(struct inode *inode);
+struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
+void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
+struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct page *f2fs_get_node_page_ra(struct page *parent, int start);
+int f2fs_move_node_page(struct page *node_page, int gc_type);
+int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic,
+ unsigned int *seq_id);
+int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
+ struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type);
+int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
+bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
+void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
+void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
+int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
+void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
+int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
+int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
+int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
+ unsigned int segno, struct f2fs_summary_block *sum);
+int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
+void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
+int __init f2fs_create_node_manager_caches(void);
+void f2fs_destroy_node_manager_caches(void);
/*
* segment.c
*/
-void register_inmem_page(struct inode *, struct page *);
-void drop_inmem_pages(struct inode *);
-int commit_inmem_pages(struct inode *);
-void f2fs_balance_fs(struct f2fs_sb_info *, bool);
-void f2fs_balance_fs_bg(struct f2fs_sb_info *);
-int f2fs_issue_flush(struct f2fs_sb_info *);
-int create_flush_cmd_control(struct f2fs_sb_info *);
-void destroy_flush_cmd_control(struct f2fs_sb_info *);
-void invalidate_blocks(struct f2fs_sb_info *, block_t);
-bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
-void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *);
-void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
-void release_discard_addrs(struct f2fs_sb_info *);
-int npages_for_summary_flush(struct f2fs_sb_info *, bool);
-void allocate_new_segments(struct f2fs_sb_info *);
-int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
-struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
-void update_meta_page(struct f2fs_sb_info *, void *, block_t);
-void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(unsigned int, struct f2fs_io_info *);
-void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
-void rewrite_data_page(struct f2fs_io_info *);
-void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
- block_t, block_t, bool, bool);
-void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
- block_t, block_t, unsigned char, bool, bool);
-void allocate_data_block(struct f2fs_sb_info *, struct page *,
- block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
-void write_data_summaries(struct f2fs_sb_info *, block_t);
-void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
-int build_segment_manager(struct f2fs_sb_info *);
-void destroy_segment_manager(struct f2fs_sb_info *);
-int __init create_segment_manager_caches(void);
-void destroy_segment_manager_caches(void);
+bool f2fs_need_SSR(struct f2fs_sb_info *sbi);
+void f2fs_register_inmem_page(struct inode *inode, struct page *page);
+void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure);
+void f2fs_drop_inmem_pages(struct inode *inode);
+void f2fs_drop_inmem_page(struct inode *inode, struct page *page);
+int f2fs_commit_inmem_pages(struct inode *inode);
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
+int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
+int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
+int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
+void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
+void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
+bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
+void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc);
+void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
+int f2fs_disable_cp_again(struct f2fs_sb_info *sbi);
+void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
+int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
+bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc);
+struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
+void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
+ block_t blk_addr);
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+ enum iostat_type io_type);
+void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
+void f2fs_outplace_write_data(struct dnode_of_data *dn,
+ struct f2fs_io_info *fio);
+int f2fs_inplace_write_data(struct f2fs_io_info *fio);
+void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ block_t old_blkaddr, block_t new_blkaddr,
+ bool recover_curseg, bool recover_newaddr);
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+ block_t old_addr, block_t new_addr,
+ unsigned char version, bool recover_curseg,
+ bool recover_newaddr);
+void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+ block_t old_blkaddr, block_t *new_blkaddr,
+ struct f2fs_summary *sum, int type,
+ struct f2fs_io_info *fio, bool add_list);
+void f2fs_wait_on_page_writeback(struct page *page,
+ enum page_type type, bool ordered, bool locked);
+void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
+void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
+ block_t len);
+void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+ unsigned int val, int alloc);
+void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
+void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
+int __init f2fs_create_segment_manager_caches(void);
+void f2fs_destroy_segment_manager_caches(void);
+int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp);
/*
* checkpoint.c
*/
-void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
-struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
-int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
-void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
-long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *, bool);
-bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
-int f2fs_sync_inode_meta(struct f2fs_sb_info *);
-int acquire_orphan_inode(struct f2fs_sb_info *);
-void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct inode *);
-void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
-int recover_orphan_inodes(struct f2fs_sb_info *);
-int get_valid_checkpoint(struct f2fs_sb_info *);
-void update_dirty_page(struct inode *, struct page *);
-void remove_dirty_inode(struct inode *);
-int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
-int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
-void init_ino_entry_info(struct f2fs_sb_info *);
-int __init create_checkpoint_caches(void);
-void destroy_checkpoint_caches(void);
+int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+ int type, bool sync);
+void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+ long nr_to_write, enum iostat_type io_type);
+void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all);
+bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type);
+bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
+int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi);
+void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi);
+void f2fs_add_orphan_inode(struct inode *inode);
+void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
+int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
+int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
+void f2fs_update_dirty_page(struct inode *inode, struct page *page);
+void f2fs_remove_dirty_inode(struct inode *inode);
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
+int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
+int __init f2fs_create_checkpoint_caches(void);
+void f2fs_destroy_checkpoint_caches(void);
/*
* data.c
*/
-void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
- struct page *, nid_t, enum page_type, int);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *);
-int f2fs_submit_page_bio(struct f2fs_io_info *);
-void f2fs_submit_page_mbio(struct f2fs_io_info *);
-void set_data_blkaddr(struct dnode_of_data *);
-void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
-int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
-int reserve_new_block(struct dnode_of_data *);
-int f2fs_get_block(struct dnode_of_data *, pgoff_t);
-ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
-int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
-struct page *find_data_page(struct inode *, pgoff_t);
-struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
-struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
-int do_write_data_page(struct f2fs_io_info *);
-int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
-int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
-void f2fs_set_page_dirty_nobuffers(struct page *);
-void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
-int f2fs_release_page(struct page *, gfp_t);
+int f2fs_init_post_read_processing(void);
+void f2fs_destroy_post_read_processing(void);
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, struct page *page,
+ nid_t ino, enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
+int f2fs_submit_page_bio(struct f2fs_io_info *fio);
+void f2fs_submit_page_write(struct f2fs_io_info *fio);
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio);
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
+int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
+int f2fs_reserve_new_block(struct dnode_of_data *dn);
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
+int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
+struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
+ int op_flags, bool for_write);
+struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
+struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
+ bool for_write);
+struct page *f2fs_get_new_data_page(struct inode *inode,
+ struct page *ipage, pgoff_t index, bool new_i_size);
+int f2fs_do_write_data_page(struct f2fs_io_info *fio);
+void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+ int create, int flag);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
+bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
+bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length);
+int f2fs_release_page(struct page *page, gfp_t wait);
#ifdef CONFIG_MIGRATION
-int f2fs_migrate_page(struct address_space *, struct page *, struct page *,
- enum migrate_mode);
+int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
+ struct page *page, enum migrate_mode mode);
#endif
+bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
+void f2fs_clear_radix_tree_dirty_tag(struct page *page);
/*
* gc.c
*/
-int start_gc_thread(struct f2fs_sb_info *);
-void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct inode *);
-int f2fs_gc(struct f2fs_sb_info *, bool);
-void build_gc_manager(struct f2fs_sb_info *);
+int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
+void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
+block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
+ unsigned int segno);
+void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *, bool);
-bool space_for_roll_forward(struct f2fs_sb_info *);
+int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
+bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
/*
* debug.c
@@ -2241,13 +3226,23 @@ struct f2fs_stat_info {
unsigned long long hit_largest, hit_cached, hit_rbtree;
unsigned long long hit_total, total_ext;
int ext_tree, zombie_tree, ext_node;
- int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
+ int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
+ int ndirty_data, ndirty_qdata;
int inmem_pages;
- unsigned int ndirty_dirs, ndirty_files, ndirty_all;
- int nats, dirty_nats, sits, dirty_sits, fnids;
+ unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
+ int nats, dirty_nats, sits, dirty_sits;
+ int free_nids, avail_nids, alloc_nids;
int total_count, utilization;
- int bg_gc, wb_bios;
- int inline_xattr, inline_inode, inline_dir, orphans;
+ int bg_gc, nr_wb_cp_data, nr_wb_data;
+ int nr_rd_data, nr_rd_node, nr_rd_meta;
+ int nr_dio_read, nr_dio_write;
+ unsigned int io_skip_bggc, other_skip_bggc;
+ int nr_flushing, nr_flushed, flush_list_empty;
+ int nr_discarding, nr_discarded;
+ int nr_discard_cmd;
+ unsigned int undiscard_blks;
+ int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+ int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
@@ -2258,10 +3253,12 @@ struct f2fs_stat_info {
int bg_node_segs, bg_data_segs;
int tot_blks, data_blks, node_blks;
int bg_data_blks, bg_node_blks;
+ unsigned long long skipped_atomic_files[2];
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
+ unsigned int meta_count[META_MAX];
unsigned int segment_count[2];
unsigned int block_count[2];
unsigned int inplace_count;
@@ -2277,6 +3274,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++)
#define stat_inc_call_count(si) ((si)->call_count++)
#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
+#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++)
+#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++)
#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--)
#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
@@ -2313,17 +3312,50 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
if (f2fs_has_inline_dentry(inode)) \
(atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \
} while (0)
+#define stat_inc_meta_count(sbi, blkaddr) \
+ do { \
+ if (blkaddr < SIT_I(sbi)->sit_base_addr) \
+ atomic_inc(&(sbi)->meta_count[META_CP]); \
+ else if (blkaddr < NM_I(sbi)->nat_blkaddr) \
+ atomic_inc(&(sbi)->meta_count[META_SIT]); \
+ else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \
+ atomic_inc(&(sbi)->meta_count[META_NAT]); \
+ else if (blkaddr < SM_I(sbi)->main_blkaddr) \
+ atomic_inc(&(sbi)->meta_count[META_SSA]); \
+ } while (0)
#define stat_inc_seg_type(sbi, curseg) \
((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg) \
((sbi)->block_count[(curseg)->alloc_type]++)
#define stat_inc_inplace_blocks(sbi) \
(atomic_inc(&(sbi)->inplace_count))
+#define stat_inc_atomic_write(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_dec_atomic_write(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_update_max_atomic_write(inode) \
+ do { \
+ int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt); \
+ int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \
+ if (cur > max) \
+ atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
+ } while (0)
+#define stat_inc_volatile_write(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_dec_volatile_write(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_update_max_volatile_write(inode) \
+ do { \
+ int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt); \
+ int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt); \
+ if (cur > max) \
+ atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur); \
+ } while (0)
#define stat_inc_seg_count(sbi, type, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
- (si)->tot_segs++; \
- if (type == SUM_TYPE_DATA) { \
+ si->tot_segs++; \
+ if ((type) == SUM_TYPE_DATA) { \
si->data_segs++; \
si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0; \
} else { \
@@ -2333,14 +3365,14 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
} while (0)
#define stat_inc_tot_blk_count(si, blks) \
- (si->tot_blks += (blks))
+ ((si)->tot_blks += (blks))
#define stat_inc_data_blk_count(sbi, blks, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->data_blks += (blks); \
- si->bg_data_blks += (gc_type == BG_GC) ? (blks) : 0; \
+ si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0; \
} while (0)
#define stat_inc_node_blk_count(sbi, blks, gc_type) \
@@ -2348,41 +3380,50 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->node_blks += (blks); \
- si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0; \
+ si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0; \
} while (0)
-int f2fs_build_stats(struct f2fs_sb_info *);
-void f2fs_destroy_stats(struct f2fs_sb_info *);
-int __init f2fs_create_root_stats(void);
+int f2fs_build_stats(struct f2fs_sb_info *sbi);
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
+void __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
#else
-#define stat_inc_cp_count(si)
-#define stat_inc_bg_cp_count(si)
-#define stat_inc_call_count(si)
-#define stat_inc_bggc_count(si)
-#define stat_inc_dirty_inode(sbi, type)
-#define stat_dec_dirty_inode(sbi, type)
-#define stat_inc_total_hit(sb)
-#define stat_inc_rbtree_node_hit(sb)
-#define stat_inc_largest_node_hit(sbi)
-#define stat_inc_cached_node_hit(sbi)
-#define stat_inc_inline_xattr(inode)
-#define stat_dec_inline_xattr(inode)
-#define stat_inc_inline_inode(inode)
-#define stat_dec_inline_inode(inode)
-#define stat_inc_inline_dir(inode)
-#define stat_dec_inline_dir(inode)
-#define stat_inc_seg_type(sbi, curseg)
-#define stat_inc_block_count(sbi, curseg)
-#define stat_inc_inplace_blocks(sbi)
-#define stat_inc_seg_count(sbi, type, gc_type)
-#define stat_inc_tot_blk_count(si, blks)
-#define stat_inc_data_blk_count(sbi, blks, gc_type)
-#define stat_inc_node_blk_count(sbi, blks, gc_type)
+#define stat_inc_cp_count(si) do { } while (0)
+#define stat_inc_bg_cp_count(si) do { } while (0)
+#define stat_inc_call_count(si) do { } while (0)
+#define stat_inc_bggc_count(si) do { } while (0)
+#define stat_io_skip_bggc_count(sbi) do { } while (0)
+#define stat_other_skip_bggc_count(sbi) do { } while (0)
+#define stat_inc_dirty_inode(sbi, type) do { } while (0)
+#define stat_dec_dirty_inode(sbi, type) do { } while (0)
+#define stat_inc_total_hit(sb) do { } while (0)
+#define stat_inc_rbtree_node_hit(sb) do { } while (0)
+#define stat_inc_largest_node_hit(sbi) do { } while (0)
+#define stat_inc_cached_node_hit(sbi) do { } while (0)
+#define stat_inc_inline_xattr(inode) do { } while (0)
+#define stat_dec_inline_xattr(inode) do { } while (0)
+#define stat_inc_inline_inode(inode) do { } while (0)
+#define stat_dec_inline_inode(inode) do { } while (0)
+#define stat_inc_inline_dir(inode) do { } while (0)
+#define stat_dec_inline_dir(inode) do { } while (0)
+#define stat_inc_atomic_write(inode) do { } while (0)
+#define stat_dec_atomic_write(inode) do { } while (0)
+#define stat_update_max_atomic_write(inode) do { } while (0)
+#define stat_inc_volatile_write(inode) do { } while (0)
+#define stat_dec_volatile_write(inode) do { } while (0)
+#define stat_update_max_volatile_write(inode) do { } while (0)
+#define stat_inc_meta_count(sbi, blkaddr) do { } while (0)
+#define stat_inc_seg_type(sbi, curseg) do { } while (0)
+#define stat_inc_block_count(sbi, curseg) do { } while (0)
+#define stat_inc_inplace_blocks(sbi) do { } while (0)
+#define stat_inc_seg_count(sbi, type, gc_type) do { } while (0)
+#define stat_inc_tot_blk_count(si, blks) do { } while (0)
+#define stat_inc_data_blk_count(sbi, blks, gc_type) do { } while (0)
+#define stat_inc_node_blk_count(sbi, blks, gc_type) do { } while (0)
static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline int __init f2fs_create_root_stats(void) { return 0; }
+static inline void __init f2fs_create_root_stats(void) { }
static inline void f2fs_destroy_root_stats(void) { }
#endif
@@ -2396,56 +3437,84 @@ extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
-extern struct kmem_cache *inode_entry_slab;
+extern struct kmem_cache *f2fs_inode_entry_slab;
/*
* inline.c
*/
-bool f2fs_may_inline_data(struct inode *);
-bool f2fs_may_inline_dentry(struct inode *);
-void read_inline_data(struct page *, struct page *);
-bool truncate_inline_inode(struct page *, u64);
-int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
-int f2fs_convert_inline_inode(struct inode *);
-int f2fs_write_inline_data(struct inode *, struct page *);
-bool recover_inline_data(struct inode *, struct page *);
-struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
- struct fscrypt_name *, struct page **);
-int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
-int f2fs_add_inline_entry(struct inode *, const struct qstr *,
- const struct qstr *, struct inode *, nid_t, umode_t);
-void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
- struct inode *, struct inode *);
-bool f2fs_empty_inline_dir(struct inode *);
-int f2fs_read_inline_dir(struct file *, struct dir_context *,
- struct fscrypt_str *);
-int f2fs_inline_data_fiemap(struct inode *,
- struct fiemap_extent_info *, __u64, __u64);
+bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_may_inline_dentry(struct inode *inode);
+void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
+void f2fs_truncate_inline_inode(struct inode *inode,
+ struct page *ipage, u64 from);
+int f2fs_read_inline_data(struct inode *inode, struct page *page);
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
+int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_write_inline_data(struct inode *inode, struct page *page);
+bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
+struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page);
+int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
+ struct page *ipage);
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
+ struct page *page, struct inode *dir,
+ struct inode *inode);
+bool f2fs_empty_inline_dir(struct inode *dir);
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+ struct fscrypt_str *fstr);
+int f2fs_inline_data_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len);
/*
* shrinker.c
*/
-unsigned long f2fs_shrink_count(struct shrinker *, struct shrink_control *);
-unsigned long f2fs_shrink_scan(struct shrinker *, struct shrink_control *);
-void f2fs_join_shrinker(struct f2fs_sb_info *);
-void f2fs_leave_shrinker(struct f2fs_sb_info *);
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
/*
* extent_cache.c
*/
-unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
-bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
-void f2fs_drop_extent_tree(struct inode *);
-unsigned int f2fs_destroy_extent_node(struct inode *);
-void f2fs_destroy_extent_tree(struct inode *);
-bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
-void f2fs_update_extent_cache(struct dnode_of_data *);
+struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs);
+struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+ struct rb_root *root, struct rb_node **parent,
+ unsigned int ofs);
+struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs,
+ struct rb_entry **prev_entry, struct rb_entry **next_entry,
+ struct rb_node ***insert_p, struct rb_node **insert_parent,
+ bool force);
+bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+ struct rb_root *root);
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_drop_extent_tree(struct inode *inode);
+unsigned int f2fs_destroy_extent_node(struct inode *inode);
+void f2fs_destroy_extent_tree(struct inode *inode);
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei);
+void f2fs_update_extent_cache(struct dnode_of_data *dn);
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
- pgoff_t, block_t, unsigned int);
-void init_extent_cache_info(struct f2fs_sb_info *);
-int __init create_extent_cache(void);
-void destroy_extent_cache(void);
+ pgoff_t fofs, block_t blkaddr, unsigned int len);
+void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
+int __init f2fs_create_extent_cache(void);
+void f2fs_destroy_extent_cache(void);
+
+/*
+ * sysfs.c
+ */
+int __init f2fs_init_sysfs(void);
+void f2fs_exit_sysfs(void);
+int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
+void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi);
/*
* crypto support
@@ -2455,26 +3524,73 @@ static inline bool f2fs_encrypted_inode(struct inode *inode)
return file_is_encrypt(inode);
}
+static inline bool f2fs_encrypted_file(struct inode *inode)
+{
+ return f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode);
+}
+
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_ENCRYPTION
file_set_encrypt(inode);
+ f2fs_set_inode_flags(inode);
#endif
}
-static inline bool f2fs_bio_encrypted(struct bio *bio)
+/*
+ * Returns true if the reads of the inode's data need to undergo some
+ * postprocessing step, like decryption or authenticity verification.
+ */
+static inline bool f2fs_post_read_required(struct inode *inode)
{
- return bio->bi_private != NULL;
+ return f2fs_encrypted_file(inode);
}
-static inline int f2fs_sb_has_crypto(struct super_block *sb)
-{
- return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
+#define F2FS_FEATURE_FUNCS(name, flagname) \
+static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
+{ \
+ return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
}
-static inline int f2fs_sb_mounted_hmsmr(struct super_block *sb)
+F2FS_FEATURE_FUNCS(encrypt, ENCRYPT);
+F2FS_FEATURE_FUNCS(blkzoned, BLKZONED);
+F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR);
+F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA);
+F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM);
+F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR);
+F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO);
+F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME);
+F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
+F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline int get_blkz_type(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkaddr)
{
- return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_HMSMR);
+ unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++)
+ if (FDEV(i).bdev == bdev)
+ return FDEV(i).blkz_type[zno];
+ return -EINVAL;
+}
+#endif
+
+static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
+{
+ return f2fs_sb_has_blkzoned(sbi);
+}
+
+static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
+{
+ return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev));
+}
+
+static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi)
+{
+ return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) ||
+ f2fs_hw_should_discard(sbi);
}
static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
@@ -2499,32 +3615,74 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
#else
- return 0;
+ return false;
#endif
}
-#ifndef CONFIG_F2FS_FS_ENCRYPTION
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk fscrypt_notsupp_fname_usr_to_disk
+static inline int block_unaligned_IO(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
+{
+ unsigned int i_blkbits = READ_ONCE(inode->i_blkbits);
+ unsigned int blocksize_mask = (1 << i_blkbits) - 1;
+ loff_t offset = iocb->ki_pos;
+ unsigned long align = offset | iov_iter_alignment(iter);
+
+ return align & blocksize_mask;
+}
+
+static inline int allow_outplace_dio(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int rw = iov_iter_rw(iter);
+
+ return (test_opt(sbi, LFS) && (rw == WRITE) &&
+ !block_unaligned_IO(inode, iocb, iter));
+}
+
+static inline bool f2fs_force_buffered_io(struct inode *inode,
+ struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int rw = iov_iter_rw(iter);
+
+ if (f2fs_post_read_required(inode))
+ return true;
+ if (sbi->s_ndevs)
+ return true;
+ /*
+ * for blkzoned device, fallback direct IO to buffered IO, so
+ * all IOs can be serialized by log-structured write.
+ */
+ if (f2fs_sb_has_blkzoned(sbi))
+ return true;
+ if (test_opt(sbi, LFS) && (rw == WRITE) &&
+ block_unaligned_IO(inode, iocb, iter))
+ return true;
+ if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED))
+ return true;
+
+ return false;
+}
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
+ unsigned int type);
+#else
+#define f2fs_build_fault_attr(sbi, rate, type) do { } while (0)
#endif
+
+static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
+{
+#ifdef CONFIG_QUOTA
+ if (f2fs_sb_has_quota_ino(sbi))
+ return true;
+ if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] ||
+ F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] ||
+ F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
+ return true;
+#endif
+ return false;
+}
+
#endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0bedcd7..8d611b1 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/file.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -20,6 +17,7 @@
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
+#include <linux/uio.h>
#include <linux/uuid.h>
#include <linux/file.h>
@@ -32,52 +30,76 @@
#include "trace.h"
#include <trace/events/f2fs.h>
+static int f2fs_filemap_fault(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ int err;
+
+ down_read(&F2FS_I(inode)->i_mmap_sem);
+ err = filemap_fault(vma, vmf);
+ up_read(&F2FS_I(inode)->i_mmap_sem);
+
+ return err;
+}
+
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dnode_of_data dn;
+ struct dnode_of_data dn = { .node_changed = false };
int err;
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto err;
+ }
+
sb_start_pagefault(inode->i_sb);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
- /* block allocation */
- f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_reserve_block(&dn, page->index);
- if (err) {
- f2fs_unlock_op(sbi);
- goto out;
- }
- f2fs_put_dnode(&dn);
- f2fs_unlock_op(sbi);
-
- f2fs_balance_fs(sbi, dn.node_changed);
-
file_update_time(vma->vm_file);
+ down_read(&F2FS_I(inode)->i_mmap_sem);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
- goto out;
+ goto out_sem;
}
+ /* block allocation */
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = f2fs_get_block(&dn, page->index);
+ f2fs_put_dnode(&dn);
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ if (err) {
+ unlock_page(page);
+ goto out_sem;
+ }
+
+ /* fill the page */
+ f2fs_wait_on_page_writeback(page, DATA, false, true);
+
+ /* wait for GCed page writeback via META_MAPPING */
+ f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
- goto mapped;
+ goto out_sem;
/* page is wholly or partially inside EOF */
if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
- unsigned offset;
+ loff_t offset;
+
offset = i_size_read(inode) & ~PAGE_MASK;
zero_user_segment(page, offset, PAGE_SIZE);
}
@@ -85,25 +107,22 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
if (!PageUptodate(page))
SetPageUptodate(page);
- trace_f2fs_vm_page_mkwrite(page, DATA);
-mapped:
- /* fill the page */
- f2fs_wait_on_page_writeback(page, DATA, false);
-
- /* wait for GCed encrypted page writeback */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
-
- /* if gced page is attached, don't write to cold segment */
- clear_cold_data(page);
-out:
- sb_end_pagefault(inode->i_sb);
+ f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
f2fs_update_time(sbi, REQ_TIME);
+
+ trace_f2fs_vm_page_mkwrite(page, DATA);
+out_sem:
+ up_read(&F2FS_I(inode)->i_mmap_sem);
+
+ f2fs_balance_fs(sbi, dn.node_changed);
+
+ sb_end_pagefault(inode->i_sb);
+err:
return block_page_mkwrite_return(err);
}
static const struct vm_operations_struct f2fs_file_vm_ops = {
- .fault = filemap_fault,
+ .fault = f2fs_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = f2fs_vm_page_mkwrite,
};
@@ -118,39 +137,39 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
if (!dentry)
return 0;
- if (update_dent_inode(inode, inode, &dentry->d_name)) {
- dput(dentry);
- return 0;
- }
-
*pino = parent_ino(dentry);
dput(dentry);
return 1;
}
-static inline bool need_do_checkpoint(struct inode *inode)
+static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- bool need_cp = false;
+ enum cp_reason_type cp_reason = CP_NO_NEEDED;
- if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
- need_cp = true;
+ if (!S_ISREG(inode->i_mode))
+ cp_reason = CP_NON_REGULAR;
+ else if (inode->i_nlink != 1)
+ cp_reason = CP_HARDLINK;
else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
- need_cp = true;
+ cp_reason = CP_SB_NEED_CP;
else if (file_wrong_pino(inode))
- need_cp = true;
- else if (!space_for_roll_forward(sbi))
- need_cp = true;
- else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
- need_cp = true;
- else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
- need_cp = true;
+ cp_reason = CP_WRONG_PINO;
+ else if (!f2fs_space_for_roll_forward(sbi))
+ cp_reason = CP_NO_SPC_ROLL;
+ else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
+ cp_reason = CP_NODE_NEED_CP;
else if (test_opt(sbi, FASTBOOT))
- need_cp = true;
- else if (sbi->active_logs == 2)
- need_cp = true;
+ cp_reason = CP_FASTBOOT_MODE;
+ else if (F2FS_OPTION(sbi).active_logs == 2)
+ cp_reason = CP_SPEC_LOG_NUM;
+ else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT &&
+ f2fs_need_dentry_mark(sbi, inode->i_ino) &&
+ f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
+ TRANS_DIR_INO))
+ cp_reason = CP_RECOVER_DIR;
- return need_cp;
+ return cp_reason;
}
static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
@@ -158,7 +177,7 @@ static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
bool ret = false;
/* But we need to avoid that there are some inode updates */
- if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
+ if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino))
ret = true;
f2fs_put_page(i, 0);
return ret;
@@ -170,7 +189,6 @@ static void try_to_fix_pino(struct inode *inode)
nid_t pino;
down_write(&fi->i_sem);
- fi->xattr_ver = 0;
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
get_parent_ino(inode, &pino)) {
f2fs_i_pino_write(inode, pino);
@@ -186,14 +204,16 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
- bool need_cp = false;
+ enum cp_reason_type cp_reason = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
+ unsigned int seq_id = 0;
- if (unlikely(f2fs_readonly(inode->i_sb)))
+ if (unlikely(f2fs_readonly(inode->i_sb) ||
+ is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return 0;
trace_f2fs_sync_file_enter(inode);
@@ -208,12 +228,12 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
clear_inode_flag(inode, FI_NEED_IPU);
if (ret) {
- trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+ trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
- if (!datasync && !f2fs_skip_inode_update(inode)) {
+ if (!f2fs_skip_inode_update(inode, datasync)) {
f2fs_write_inode(inode, NULL);
goto go_write;
}
@@ -222,14 +242,14 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
- !exist_written_data(sbi, ino, APPEND_INO)) {
+ !f2fs_exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
- exist_written_data(sbi, ino, UPDATE_INO))
+ f2fs_exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
@@ -239,10 +259,10 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
* sudden-power-off.
*/
down_read(&F2FS_I(inode)->i_sem);
- need_cp = need_do_checkpoint(inode);
+ cp_reason = need_do_checkpoint(inode);
up_read(&F2FS_I(inode)->i_sem);
- if (need_cp) {
+ if (cp_reason) {
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
@@ -256,7 +276,9 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
goto out;
}
sync_nodes:
- ret = fsync_node_pages(sbi, inode, &wbc, atomic);
+ atomic_inc(&sbi->wb_sync_req[NODE]);
+ ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic, &seq_id);
+ atomic_dec(&sbi->wb_sync_req[NODE]);
if (ret)
goto out;
@@ -266,50 +288,67 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
goto out;
}
- if (need_inode_block_update(sbi, ino)) {
- f2fs_mark_inode_dirty_sync(inode);
+ if (f2fs_need_inode_block_update(sbi, ino)) {
+ f2fs_mark_inode_dirty_sync(inode, true);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
- ret = wait_on_node_pages_writeback(sbi, ino);
- if (ret)
- goto out;
+ /*
+ * If it's atomic_write, it's just fine to keep write ordering. So
+ * here we don't need to wait for node write completion, since we use
+ * node chain which serializes node blocks. If one of node writes are
+ * reordered, we can see simply broken chain, resulting in stopping
+ * roll-forward recovery. It means we'll recover all or none node blocks
+ * given fsync mark.
+ */
+ if (!atomic) {
+ ret = f2fs_wait_on_node_pages_writeback(sbi, seq_id);
+ if (ret)
+ goto out;
+ }
/* once recovery info is written, don't need to tack this */
- remove_ino_entry(sbi, ino, APPEND_INO);
+ f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
- remove_ino_entry(sbi, ino, UPDATE_INO);
- clear_inode_flag(inode, FI_UPDATE_WRITE);
- ret = f2fs_issue_flush(sbi);
+ if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
+ ret = f2fs_issue_flush(sbi, inode->i_ino);
+ if (!ret) {
+ f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
+ f2fs_remove_ino_entry(sbi, ino, FLUSH_INO);
+ }
f2fs_update_time(sbi, REQ_TIME);
out:
- trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+ trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
f2fs_trace_ios(NULL, 1);
return ret;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file)))))
+ return -EIO;
return f2fs_do_sync_file(file, start, end, datasync, false);
}
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
- struct pagevec pvec;
+ struct page *page;
int nr_pages;
if (whence != SEEK_DATA)
return 0;
/* find first dirty page index */
- pagevec_init(&pvec, 0);
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
- PAGECACHE_TAG_DIRTY, 1);
- pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
- pagevec_release(&pvec);
+ nr_pages = find_get_pages_tag(mapping, &pgofs, PAGECACHE_TAG_DIRTY,
+ 1, &page);
+ if (!nr_pages)
+ return ULONG_MAX;
+ pgofs = page->index;
+ put_page(page);
return pgofs;
}
@@ -359,13 +398,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
- pgofs = get_next_page_offset(&dn, pgofs);
+ pgofs = f2fs_get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
@@ -379,7 +418,9 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
@@ -435,13 +476,8 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
struct inode *inode = file_inode(file);
int err;
- if (f2fs_encrypted_inode(inode)) {
- err = fscrypt_get_encryption_info(inode);
- if (err)
- return 0;
- if (!f2fs_encrypted_inode(inode))
- return -ENOKEY;
- }
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
/* we don't need to use inline_data strictly */
err = f2fs_convert_inline_inode(inode);
@@ -455,49 +491,44 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
- int ret = generic_file_open(inode, filp);
- struct dentry *dir;
+ int err = fscrypt_file_open(inode, filp);
- if (!ret && f2fs_encrypted_inode(inode)) {
- ret = fscrypt_get_encryption_info(inode);
- if (ret)
- return -EACCES;
- if (!fscrypt_has_encryption_key(inode))
- return -ENOKEY;
- }
- dir = dget_parent(file_dentry(filp));
- if (f2fs_encrypted_inode(d_inode(dir)) &&
- !fscrypt_has_permitted_context(d_inode(dir), inode)) {
- dput(dir);
- return -EPERM;
- }
- dput(dir);
- return ret;
+ if (err)
+ return err;
+
+ filp->f_mode |= FMODE_NOWAIT;
+
+ return dquot_file_open(inode, filp);
}
-int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
+ int base = 0;
+
+ if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
+ base = get_extra_isize(dn->inode);
raw_node = F2FS_NODE(dn->node_page);
- addr = blkaddr_in_node(raw_node) + ofs;
+ addr = blkaddr_in_node(raw_node) + base + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
+
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
- set_data_blkaddr(dn);
+ f2fs_set_data_blkaddr(dn);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
continue;
- invalidate_blocks(sbi, blkaddr);
+ f2fs_invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
nr_free++;
@@ -509,7 +540,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
* once we invalidate valid blkaddr in range [ofs, ofs + count],
* we will invalidate all blkaddr in the whole range.
*/
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
+ fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page),
dn->inode) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
@@ -519,18 +550,17 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
- return nr_free;
}
-void truncate_data_blocks(struct dnode_of_data *dn)
+void f2fs_truncate_data_blocks(struct dnode_of_data *dn)
{
- truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
+ f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}
static int truncate_partial_data_page(struct inode *inode, u64 from,
bool cache_only)
{
- unsigned offset = from & (PAGE_SIZE - 1);
+ loff_t offset = from & (PAGE_SIZE - 1);
pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -546,23 +576,24 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
}
- page = get_lock_data_page(inode, index, true);
+ page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
- return 0;
+ return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
truncate_out:
- f2fs_wait_on_page_writeback(page, DATA, true);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, offset, PAGE_SIZE - offset);
- if (!cache_only || !f2fs_encrypted_inode(inode) ||
- !S_ISREG(inode->i_mode))
+
+ /* An encrypted inode should have a key and truncate the last page. */
+ f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode));
+ if (!cache_only)
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
-int truncate_blocks(struct inode *inode, u64 from, bool lock)
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- unsigned int blocksize = inode->i_sb->s_blocksize;
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
@@ -571,7 +602,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
trace_f2fs_truncate_blocks_enter(inode, from);
- free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
+ free_from = (pgoff_t)F2FS_BLK_ALIGN(from);
if (free_from >= sbi->max_file_blocks)
goto free_partial;
@@ -579,22 +610,21 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
if (lock)
f2fs_lock_op(sbi);
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
if (f2fs_has_inline_data(inode)) {
- if (truncate_inline_inode(ipage, from))
- set_page_dirty(ipage);
+ f2fs_truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
- err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
+ err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
@@ -607,13 +637,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
- truncate_data_blocks_range(&dn, count);
+ f2fs_truncate_data_blocks_range(&dn, count);
free_from += count;
}
f2fs_put_dnode(&dn);
free_next:
- err = truncate_inode_blocks(inode, free_from);
+ err = f2fs_truncate_inode_blocks(inode, free_from);
out:
if (lock)
f2fs_unlock_op(sbi);
@@ -630,12 +660,20 @@ int f2fs_truncate(struct inode *inode)
{
int err;
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
+
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return 0;
trace_f2fs_truncate(inode);
+ if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
+ f2fs_show_injection_info(FAULT_TRUNCATE);
+ return -EIO;
+ }
+
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
@@ -643,21 +681,57 @@ int f2fs_truncate(struct inode *inode)
return err;
}
- err = truncate_blocks(inode, i_size_read(inode), true);
+ err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
if (err)
return err;
inode->i_mtime = inode->i_ctime = current_time(inode);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
return 0;
}
int f2fs_getattr(struct vfsmount *mnt,
- struct dentry *dentry, struct kstat *stat)
+ struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = d_inode(dentry);
+#if 0
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_inode *ri;
+ unsigned int flags;
+
+ if (f2fs_has_extra_attr(inode) &&
+ f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = fi->i_crtime.tv_sec;
+ stat->btime.tv_nsec = fi->i_crtime.tv_nsec;
+ }
+
+ flags = fi->i_flags & F2FS_FL_USER_VISIBLE;
+ if (flags & F2FS_APPEND_FL)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (flags & F2FS_COMPR_FL)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (f2fs_encrypted_inode(inode))
+ stat->attributes |= STATX_ATTR_ENCRYPTED;
+ if (flags & F2FS_IMMUTABLE_FL)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (flags & F2FS_NODUMP_FL)
+ stat->attributes |= STATX_ATTR_NODUMP;
+
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_ENCRYPTED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
+#endif
generic_fillattr(inode, stat);
- stat->blocks <<= 3;
+
+ /* we need to show initial sectors used for inline_data/dentries */
+ if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) ||
+ f2fs_has_inline_dentry(inode))
+ stat->blocks += (stat->size + 511) >> 9;
+
return 0;
}
@@ -696,28 +770,67 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
struct inode *inode = d_inode(dentry);
int err;
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
+
err = setattr_prepare(dentry, attr);
if (err)
return err;
+ err = fscrypt_prepare_setattr(dentry, attr);
+ if (err)
+ return err;
+
+ if (is_quota_modification(inode, attr)) {
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+ }
+ if ((attr->ia_valid & ATTR_UID &&
+ !uid_eq(attr->ia_uid, inode->i_uid)) ||
+ (attr->ia_valid & ATTR_GID &&
+ !gid_eq(attr->ia_gid, inode->i_gid))) {
+ f2fs_lock_op(F2FS_I_SB(inode));
+ err = dquot_transfer(inode, attr);
+ if (err) {
+ set_sbi_flag(F2FS_I_SB(inode),
+ SBI_QUOTA_NEED_REPAIR);
+ f2fs_unlock_op(F2FS_I_SB(inode));
+ return err;
+ }
+ /*
+ * update uid/gid under lock_op(), so that dquot and inode can
+ * be updated atomically.
+ */
+ if (attr->ia_valid & ATTR_UID)
+ inode->i_uid = attr->ia_uid;
+ if (attr->ia_valid & ATTR_GID)
+ inode->i_gid = attr->ia_gid;
+ f2fs_mark_inode_dirty_sync(inode, true);
+ f2fs_unlock_op(F2FS_I_SB(inode));
+ }
+
if (attr->ia_valid & ATTR_SIZE) {
- if (f2fs_encrypted_inode(inode) &&
- fscrypt_get_encryption_info(inode))
- return -EACCES;
+ bool to_smaller = (attr->ia_size <= i_size_read(inode));
- if (attr->ia_size <= i_size_read(inode)) {
- truncate_setsize(inode, attr->ia_size);
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ truncate_setsize(inode, attr->ia_size);
+
+ if (to_smaller)
err = f2fs_truncate(inode);
- if (err)
- return err;
- f2fs_balance_fs(F2FS_I_SB(inode), true);
- } else {
- /*
- * do not trim all blocks after i_size if target size is
- * larger than i_size.
- */
- truncate_setsize(inode, attr->ia_size);
+ /*
+ * do not trim all blocks after i_size if target size is
+ * larger than i_size.
+ */
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ if (err)
+ return err;
+
+ if (!to_smaller) {
/* should convert inline inode here */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
@@ -726,19 +839,28 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
}
inode->i_mtime = inode->i_ctime = current_time(inode);
}
+
+ down_write(&F2FS_I(inode)->i_sem);
+ F2FS_I(inode)->last_disk_size = i_size_read(inode);
+ up_write(&F2FS_I(inode)->i_sem);
}
__setattr_copy(inode, attr);
if (attr->ia_valid & ATTR_MODE) {
- err = posix_acl_chmod(inode, get_inode_mode(inode));
+ err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode));
if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
inode->i_mode = F2FS_I(inode)->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
}
}
- f2fs_mark_inode_dirty_sync(inode);
+ /* file size may changed here */
+ f2fs_mark_inode_dirty_sync(inode, true);
+
+ /* inode change will produce dirty node pages flushed by checkpoint */
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
return err;
}
@@ -765,20 +887,20 @@ static int fill_zero(struct inode *inode, pgoff_t index,
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
- page = get_new_data_page(inode, NULL, index, false);
+ page = f2fs_get_new_data_page(inode, NULL, index, false);
f2fs_unlock_op(sbi);
if (IS_ERR(page))
return PTR_ERR(page);
- f2fs_wait_on_page_writeback(page, DATA, true);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, start, len);
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
-int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
+int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
int err;
@@ -787,10 +909,11 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
- pg_start++;
+ pg_start = f2fs_get_next_page_offset(&dn,
+ pg_start);
continue;
}
return err;
@@ -801,7 +924,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
- truncate_data_blocks_range(&dn, count);
+ f2fs_truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
pg_start += count;
@@ -852,12 +975,19 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
blk_start = (loff_t)pg_start << PAGE_SHIFT;
blk_end = (loff_t)pg_end << PAGE_SHIFT;
+
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
f2fs_lock_op(sbi);
- ret = truncate_hole(inode, pg_start, pg_end);
+ ret = f2fs_truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
+
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
@@ -873,7 +1003,7 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
+ ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
@@ -888,8 +1018,9 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
dn.ofs_in_node, len);
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
- *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (!is_checkpointed_data(sbi, *blkaddr)) {
+ *blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
+ if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) {
if (test_opt(sbi, LFS)) {
f2fs_put_dnode(&dn);
@@ -922,10 +1053,10 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
continue;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
+ ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
if (ret) {
dec_valid_block_count(sbi, inode, 1);
- invalidate_blocks(sbi, *blkaddr);
+ f2fs_invalidate_blocks(sbi, *blkaddr);
} else {
f2fs_update_data_blkaddr(&dn, *blkaddr);
}
@@ -955,24 +1086,29 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
pgoff_t ilen;
set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
+ ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
if (ret)
return ret;
- get_node_info(sbi, dn.nid, &ni);
+ ret = f2fs_get_node_info(sbi, dn.nid, &ni);
+ if (ret) {
+ f2fs_put_dnode(&dn);
+ return ret;
+ }
+
ilen = min((pgoff_t)
ADDRS_PER_PAGE(dn.node_page, dst_inode) -
dn.ofs_in_node, len - i);
do {
- dn.data_blkaddr = datablock_addr(dn.node_page,
- dn.ofs_in_node);
- truncate_data_blocks_range(&dn, 1);
+ dn.data_blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
+ f2fs_truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
f2fs_i_blocks_write(src_inode,
- 1, false);
+ 1, false, false);
f2fs_i_blocks_write(dst_inode,
- 1, true);
+ 1, true, false);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
blkaddr[i], ni.version, true, false);
@@ -989,10 +1125,11 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
} else {
struct page *psrc, *pdst;
- psrc = get_lock_data_page(src_inode, src + i, true);
+ psrc = f2fs_get_lock_data_page(src_inode,
+ src + i, true);
if (IS_ERR(psrc))
return PTR_ERR(psrc);
- pdst = get_new_data_page(dst_inode, NULL, dst + i,
+ pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i,
true);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
@@ -1003,7 +1140,8 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
- ret = truncate_hole(src_inode, src + i, src + i + 1);
+ ret = f2fs_truncate_hole(src_inode,
+ src + i, src + i + 1);
if (ret)
return ret;
i++;
@@ -1024,11 +1162,15 @@ static int __exchange_data_block(struct inode *src_inode,
while (len) {
olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
- src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+ src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
+ array_size(olen, sizeof(block_t)),
+ GFP_KERNEL);
if (!src_blkaddr)
return -ENOMEM;
- do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+ do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
+ array_size(olen, sizeof(int)),
+ GFP_KERNEL);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
@@ -1054,31 +1196,39 @@ static int __exchange_data_block(struct inode *src_inode,
return 0;
roll_back:
- __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
+ __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen);
kvfree(src_blkaddr);
kvfree(do_replace);
return ret;
}
-static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
+static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ pgoff_t start = offset >> PAGE_SHIFT;
+ pgoff_t end = (offset + len) >> PAGE_SHIFT;
int ret;
f2fs_balance_fs(sbi, true);
+
+ /* avoid gc operation during block exchange */
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
f2fs_lock_op(sbi);
-
f2fs_drop_extent_tree(inode);
-
+ truncate_pagecache(inode, offset);
ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
f2fs_unlock_op(sbi);
+
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
- pgoff_t pg_start, pg_end;
loff_t new_size;
int ret;
@@ -1093,31 +1243,27 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- pg_start = offset >> PAGE_SHIFT;
- pg_end = (offset + len) >> PAGE_SHIFT;
-
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
return ret;
- truncate_pagecache(inode, offset);
-
- ret = f2fs_do_collapse(inode, pg_start, pg_end);
+ ret = f2fs_do_collapse(inode, offset, len);
if (ret)
return ret;
/* write out all moved pages, if possible */
+ down_write(&F2FS_I(inode)->i_mmap_sem);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
truncate_pagecache(inode, new_size);
- ret = truncate_blocks(inode, new_size, true);
+ ret = f2fs_truncate_blocks(inode, new_size, true);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
f2fs_i_size_write(inode, new_size);
-
return ret;
}
@@ -1131,21 +1277,22 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
int ret;
for (; index < end; index++, dn->ofs_in_node++) {
- if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ if (datablock_addr(dn->inode, dn->node_page,
+ dn->ofs_in_node) == NULL_ADDR)
count++;
}
dn->ofs_in_node = ofs_in_node;
- ret = reserve_new_blocks(dn, count);
+ ret = f2fs_reserve_new_blocks(dn, count);
if (ret)
return ret;
dn->ofs_in_node = ofs_in_node;
for (index = start; index < end; index++, dn->ofs_in_node++) {
- dn->data_blkaddr =
- datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
/*
- * reserve_new_blocks will not guarantee entire block
+ * f2fs_reserve_new_blocks will not guarantee entire block
* allocation.
*/
if (dn->data_blkaddr == NULL_ADDR) {
@@ -1153,9 +1300,9 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
break;
}
if (dn->data_blkaddr != NEW_ADDR) {
- invalidate_blocks(sbi, dn->data_blkaddr);
+ f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
dn->data_blkaddr = NEW_ADDR;
- set_data_blkaddr(dn);
+ f2fs_set_data_blkaddr(dn);
}
}
@@ -1186,8 +1333,6 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
- truncate_pagecache_range(inode, offset, offset + len - 1);
-
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
@@ -1200,8 +1345,6 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
- if (offset + len > new_size)
- new_size = offset + len;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
@@ -1219,12 +1362,21 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
unsigned int end_offset;
pgoff_t end;
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ truncate_pagecache_range(inode,
+ (loff_t)index << PAGE_SHIFT,
+ ((loff_t)pg_end << PAGE_SHIFT) - 1);
+
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
+ ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
goto out;
}
@@ -1233,7 +1385,13 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
ret = f2fs_do_zero_range(&dn, index, end);
f2fs_put_dnode(&dn);
+
f2fs_unlock_op(sbi);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+
+ f2fs_balance_fs(sbi, dn.node_changed);
+
if (ret)
goto out;
@@ -1252,9 +1410,12 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
}
out:
- if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
- f2fs_i_size_write(inode, new_size);
-
+ if (new_size > i_size_read(inode)) {
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ file_set_keep_isize(inode);
+ else
+ f2fs_i_size_write(inode, new_size);
+ }
return ret;
}
@@ -1266,8 +1427,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
int ret = 0;
new_size = i_size_read(inode) + len;
- if (new_size > inode->i_sb->s_maxbytes)
- return -EFBIG;
+ ret = inode_newsize_ok(inode, new_size);
+ if (ret)
+ return ret;
if (offset >= i_size_read(inode))
return -EINVAL;
@@ -1282,7 +1444,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
- ret = truncate_blocks(inode, i_size_read(inode), true);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+ ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
if (ret)
return ret;
@@ -1291,13 +1455,16 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- truncate_pagecache(inode, offset);
-
pg_start = offset >> PAGE_SHIFT;
pg_end = (offset + len) >> PAGE_SHIFT;
delta = pg_end - pg_start;
idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ /* avoid gc operation during block exchange */
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+ truncate_pagecache(inode, offset);
+
while (!ret && idx > pg_start) {
nr = idx - pg_start;
if (nr > delta)
@@ -1311,10 +1478,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
idx + delta, nr, false);
f2fs_unlock_op(sbi);
}
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
/* write out all moved pages, if possible */
+ down_write(&F2FS_I(inode)->i_mmap_sem);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
f2fs_i_size_write(inode, new_size);
@@ -1325,19 +1496,21 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL,
+ .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE,
+ .m_may_create = true };
pgoff_t pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_end;
- int ret;
+ int err;
- ret = inode_newsize_ok(inode, (len + offset));
- if (ret)
- return ret;
+ err = inode_newsize_ok(inode, (len + offset));
+ if (err)
+ return err;
- ret = f2fs_convert_inline_inode(inode);
- if (ret)
- return ret;
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
f2fs_balance_fs(sbi, true);
@@ -1349,26 +1522,30 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
if (off_end)
map.m_len++;
- ret = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
- if (ret) {
+ err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ if (err) {
pgoff_t last_off;
if (!map.m_len)
- return ret;
+ return err;
last_off = map.m_lblk + map.m_len - 1;
/* update new size to the failed position */
- new_size = (last_off == pg_end) ? offset + len:
+ new_size = (last_off == pg_end) ? offset + len :
(loff_t)(last_off + 1) << PAGE_SHIFT;
} else {
new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
}
- if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
- f2fs_i_size_write(inode, new_size);
+ if (new_size > i_size_read(inode)) {
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ file_set_keep_isize(inode);
+ else
+ f2fs_i_size_write(inode, new_size);
+ }
- return ret;
+ return err;
}
static long f2fs_fallocate(struct file *file, int mode,
@@ -1377,6 +1554,9 @@ static long f2fs_fallocate(struct file *file, int mode,
struct inode *inode = file_inode(file);
long ret = 0;
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
+
/* f2fs only support ->fallocate for regular file */
if (!S_ISREG(inode->i_mode))
return -EINVAL;
@@ -1409,7 +1589,7 @@ static long f2fs_fallocate(struct file *file, int mode,
if (!ret) {
inode->i_mtime = inode->i_ctime = current_time(inode);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
}
@@ -1432,34 +1612,48 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- drop_inmem_pages(inode);
+ f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
- clear_inode_flag(inode, FI_VOLATILE_FILE);
set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(inode, FI_DROP_CACHE);
+ clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
}
return 0;
}
-#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
-#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
-
-static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+static int f2fs_file_flush(struct file *file, fl_owner_t id)
{
- if (S_ISDIR(mode))
- return flags;
- else if (S_ISREG(mode))
- return flags & F2FS_REG_FLMASK;
- else
- return flags & F2FS_OTHER_FLMASK;
+ struct inode *inode = file_inode(file);
+
+ /*
+ * If the process doing a transaction is crashed, we should do
+ * roll-back. Otherwise, other reader/write can see corrupted database
+ * until all the writers close its file. Since this should be done
+ * before dropping file lock, it needs to do in ->flush.
+ */
+ if (f2fs_is_atomic_file(inode) &&
+ F2FS_I(inode)->inmem_task == current)
+ f2fs_drop_inmem_pages(inode);
+ return 0;
}
static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int flags = fi->i_flags;
+
+ if (f2fs_encrypted_inode(inode))
+ flags |= F2FS_ENCRYPT_FL;
+ if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
+ flags |= F2FS_INLINE_DATA_FL;
+ if (is_inode_flag_set(inode, FI_PIN_FILE))
+ flags |= F2FS_NOCOW_FL;
+
+ flags &= F2FS_FL_USER_VISIBLE;
+
return put_user(flags, (int __user *)arg);
}
@@ -1481,28 +1675,34 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
if (ret)
return ret;
- flags = f2fs_mask_flags(inode->i_mode, flags);
-
inode_lock(inode);
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode)) {
+ ret = -EPERM;
+ goto unlock_out;
+ }
+
+ flags = f2fs_mask_flags(inode->i_mode, flags);
+
oldflags = fi->i_flags;
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+ if ((flags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
- inode_unlock(inode);
ret = -EPERM;
- goto out;
+ goto unlock_out;
}
}
- flags = flags & FS_FL_USER_MODIFIABLE;
- flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
+ flags = flags & (F2FS_FL_USER_MODIFIABLE);
+ flags |= oldflags & ~(F2FS_FL_USER_MODIFIABLE);
fi->i_flags = flags;
- inode_unlock(inode);
inode->i_ctime = current_time(inode);
f2fs_set_inode_flags(inode);
-out:
+ f2fs_mark_inode_dirty_sync(inode, false);
+unlock_out:
+ inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
@@ -1522,35 +1722,50 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
- down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
-
- if (f2fs_is_atomic_file(inode))
+ if (f2fs_is_atomic_file(inode)) {
+ if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST))
+ ret = -EINVAL;
goto out;
+ }
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
- set_inode_flag(inode, FI_ATOMIC_FILE);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- if (!get_dirty_pages(inode))
- goto out;
-
- f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
+ /*
+ * Should wait end_io to count F2FS_WB_CP_DATA correctly by
+ * f2fs_is_atomic_file.
+ */
+ if (get_dirty_pages(inode))
+ f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
"Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
- if (ret)
- clear_inode_flag(inode, FI_ATOMIC_FILE);
+ if (ret) {
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ goto out;
+ }
+
+ set_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ F2FS_I(inode)->inmem_task = current;
+ stat_inc_atomic_write(inode);
+ stat_update_max_atomic_write(inode);
out:
- up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
@@ -1568,22 +1783,34 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
if (ret)
return ret;
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
inode_lock(inode);
- if (f2fs_is_volatile_file(inode))
+ if (f2fs_is_volatile_file(inode)) {
+ ret = -EINVAL;
goto err_out;
-
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(inode, FI_ATOMIC_FILE);
- ret = commit_inmem_pages(inode);
- if (ret) {
- set_inode_flag(inode, FI_ATOMIC_FILE);
- goto err_out;
- }
}
- ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ if (f2fs_is_atomic_file(inode)) {
+ ret = f2fs_commit_inmem_pages(inode);
+ if (ret)
+ goto err_out;
+
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ if (!ret) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
+ stat_dec_atomic_write(inode);
+ }
+ } else {
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
+ }
err_out:
+ if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
+ clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
+ ret = -EINVAL;
+ }
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
@@ -1597,6 +1824,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
@@ -1610,6 +1840,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (ret)
goto out;
+ stat_inc_volatile_write(inode);
+ stat_update_max_volatile_write(inode);
+
set_inode_flag(inode, FI_VOLATILE_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
out:
@@ -1662,12 +1895,15 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
inode_lock(inode);
if (f2fs_is_atomic_file(inode))
- drop_inmem_pages(inode);
+ f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
}
+ clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
+
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -1698,31 +1934,58 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
switch (in) {
case F2FS_GOING_DOWN_FULLSYNC:
sb = freeze_bdev(sb->s_bdev);
- if (sb && !IS_ERR(sb)) {
+ if (IS_ERR(sb)) {
+ ret = PTR_ERR(sb);
+ goto out;
+ }
+ if (sb) {
f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
thaw_bdev(sb->s_bdev, sb);
}
break;
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
- f2fs_sync_fs(sb, 1);
+ ret = f2fs_sync_fs(sb, 1);
+ if (ret)
+ goto out;
f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NOSYNC:
f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_METAFLUSH:
- sync_meta_pages(sbi, META, LONG_MAX);
+ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
+ case F2FS_GOING_DOWN_NEED_FSCK:
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ /* do checkpoint only */
+ ret = f2fs_sync_fs(sb, 1);
+ goto out;
default:
ret = -EINVAL;
goto out;
}
+
+ f2fs_stop_gc_thread(sbi);
+ f2fs_stop_discard_thread(sbi);
+
+ f2fs_drop_discard_cmd(sbi);
+ clear_opt(sbi, DISCARD);
+
f2fs_update_time(sbi, REQ_TIME);
out:
if (in != F2FS_GOING_DOWN_FULLSYNC)
mnt_drop_write_file(filp);
+
+ trace_f2fs_shutdown(sbi, in, ret);
+
return ret;
}
@@ -1737,7 +2000,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!blk_queue_discard(q))
+ if (!f2fs_hw_support_discard(F2FS_SB(sb)))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
@@ -1776,6 +2039,9 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode)))
+ return -EOPNOTSUPP;
+
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
@@ -1783,6 +2049,8 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
{
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
+ return -EOPNOTSUPP;
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
}
@@ -1792,16 +2060,18 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
- if (!f2fs_sb_has_crypto(inode->i_sb))
+ if (!f2fs_sb_has_encrypt(sbi))
return -EOPNOTSUPP;
- if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
- goto got_it;
-
err = mnt_want_write_file(filp);
if (err)
return err;
+ down_write(&sbi->sb_lock);
+
+ if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
+ goto got_it;
+
/* update superblock with uuid */
generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
@@ -1809,15 +2079,16 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
if (err) {
/* undo new data */
memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
- mnt_drop_write_file(filp);
- return err;
+ goto out_err;
}
- mnt_drop_write_file(filp);
got_it:
if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt,
16))
- return -EFAULT;
- return 0;
+ err = -EFAULT;
+out_err:
+ up_write(&sbi->sb_lock);
+ mnt_drop_write_file(filp);
+ return err;
}
static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
@@ -1849,7 +2120,53 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
mutex_lock(&sbi->gc_mutex);
}
- ret = f2fs_gc(sbi, sync);
+ ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_gc_range range;
+ u64 end;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ end = range.start + range.len;
+ if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) {
+ return -EINVAL;
+ }
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+do_more:
+ if (!range.sync) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ } else {
+ mutex_lock(&sbi->gc_mutex);
+ }
+
+ ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+ range.start += BLKS_PER_SEC(sbi);
+ if (range.start <= end)
+ goto do_more;
out:
mnt_drop_write_file(filp);
return ret;
@@ -1867,6 +2184,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Skipping Checkpoint. Checkpoints currently disabled.");
+ return -EINVAL;
+ }
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
@@ -1882,18 +2205,19 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct f2fs_defragment *range)
{
struct inode *inode = file_inode(filp);
- struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
- struct extent_info ei;
- pgoff_t pg_start, pg_end;
+ struct f2fs_map_blocks map = { .m_next_extent = NULL,
+ .m_seg_type = NO_CHECK_TYPE ,
+ .m_may_create = false };
+ struct extent_info ei = {0, 0, 0};
+ pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
- unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg;
block_t blk_end = 0;
bool fragmented = false;
int err;
/* if in-place-update policy is enabled, don't waste time here */
- if (need_inplace_update(inode))
+ if (f2fs_should_update_inplace(inode, NULL))
return -EINVAL;
pg_start = range->start >> PAGE_SHIFT;
@@ -1919,6 +2243,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
}
map.m_lblk = pg_start;
+ map.m_next_pgofs = &next_pgofs;
/*
* lookup mapping info in dnode page cache, skip defragmenting if all
@@ -1927,19 +2252,21 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
- map.m_lblk++;
+ map.m_lblk = next_pgofs;
continue;
}
- if (blk_end && blk_end != map.m_pblk) {
+ if (blk_end && blk_end != map.m_pblk)
fragmented = true;
- break;
- }
+
+ /* record total count of block that we're going to move */
+ total += map.m_len;
+
blk_end = map.m_pblk + map.m_len;
map.m_lblk += map.m_len;
@@ -1948,10 +2275,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
if (!fragmented)
goto out;
- map.m_lblk = pg_start;
- map.m_len = pg_end - pg_start;
-
- sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec;
+ sec_num = (total + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi);
/*
* make sure there are enough free section for LFS allocation, this can
@@ -1963,18 +2287,22 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
goto out;
}
+ map.m_lblk = pg_start;
+ map.m_len = pg_end - pg_start;
+ total = 0;
+
while (map.m_lblk < pg_end) {
pgoff_t idx;
int cnt = 0;
do_map:
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto clear_out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
- map.m_lblk++;
+ map.m_lblk = next_pgofs;
continue;
}
@@ -1984,7 +2312,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
struct page *page;
- page = get_lock_data_page(inode, idx, true);
+ page = f2fs_get_lock_data_page(inode, idx, true);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto clear_out;
@@ -2028,42 +2356,40 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!S_ISREG(inode->i_mode))
+ if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
+ return -EINVAL;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ /* verify alignment of offset & size */
+ if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ if (unlikely((range.start + range.len) >> PAGE_SHIFT >
+ sbi->max_file_blocks))
return -EINVAL;
err = mnt_want_write_file(filp);
if (err)
return err;
- if (f2fs_readonly(sbi->sb)) {
- err = -EROFS;
- goto out;
- }
-
- if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
- sizeof(range))) {
- err = -EFAULT;
- goto out;
- }
-
- /* verify alignment of offset & size */
- if (range.start & (F2FS_BLKSIZE - 1) ||
- range.len & (F2FS_BLKSIZE - 1)) {
- err = -EINVAL;
- goto out;
- }
-
err = f2fs_defragment_range(sbi, filp, &range);
+ mnt_drop_write_file(filp);
+
f2fs_update_time(sbi, REQ_TIME);
if (err < 0)
- goto out;
+ return err;
if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
sizeof(range)))
- err = -EFAULT;
-out:
- mnt_drop_write_file(filp);
- return err;
+ return -EFAULT;
+
+ return 0;
}
static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
@@ -2098,10 +2424,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
inode_lock(src);
if (src != dst) {
- if (!inode_trylock(dst)) {
- ret = -EBUSY;
+ ret = -EBUSY;
+ if (!inode_trylock(dst))
goto out;
- }
}
ret = -EINVAL;
@@ -2146,6 +2471,14 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
goto out_unlock;
f2fs_balance_fs(sbi, true);
+
+ down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
+ if (src != dst) {
+ ret = -EBUSY;
+ if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE]))
+ goto out_src;
+ }
+
f2fs_lock_op(sbi);
ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
pos_out >> F2FS_BLKSIZE_BITS,
@@ -2158,6 +2491,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
f2fs_i_size_write(dst, dst_osize);
}
f2fs_unlock_op(sbi);
+
+ if (src != dst)
+ up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]);
+out_src:
+ up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
out_unlock:
if (src != dst)
inode_unlock(dst);
@@ -2197,6 +2535,8 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
range.pos_out, range.len);
mnt_drop_write_file(filp);
+ if (err)
+ goto err_out;
if (copy_to_user((struct f2fs_move_range __user *)arg,
&range, sizeof(range)))
@@ -2206,8 +2546,209 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
return err;
}
+static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct sit_info *sm = SIT_I(sbi);
+ unsigned int start_segno = 0, end_segno = 0;
+ unsigned int dev_start_segno = 0, dev_end_segno = 0;
+ struct f2fs_flush_device range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return -EINVAL;
+
+ if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num ||
+ __is_large_section(sbi)) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Can't flush %u in %d for segs_per_sec %u != 1\n",
+ range.dev_num, sbi->s_ndevs,
+ sbi->segs_per_sec);
+ return -EINVAL;
+ }
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (range.dev_num != 0)
+ dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk);
+ dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk);
+
+ start_segno = sm->last_victim[FLUSH_DEVICE];
+ if (start_segno < dev_start_segno || start_segno >= dev_end_segno)
+ start_segno = dev_start_segno;
+ end_segno = min(start_segno + range.segments, dev_end_segno);
+
+ while (start_segno < end_segno) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ sm->last_victim[GC_CB] = end_segno + 1;
+ sm->last_victim[GC_GREEDY] = end_segno + 1;
+ sm->last_victim[ALLOC_NEXT] = end_segno + 1;
+ ret = f2fs_gc(sbi, true, true, start_segno);
+ if (ret == -EAGAIN)
+ ret = 0;
+ else if (ret < 0)
+ break;
+ start_segno++;
+ }
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_get_features(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature);
+
+ /* Must validate to set it with SQLite behavior in Android. */
+ sb_feature |= F2FS_FEATURE_ATOMIC_WRITE;
+
+ return put_user(sb_feature, (u32 __user *)arg);
+}
+
+int f2fs_pin_file_control(struct inode *inode, bool inc)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ /* Use i_gc_failures for normal file as a risk signal. */
+ if (inc)
+ f2fs_i_gc_failures_write(inode,
+ fi->i_gc_failures[GC_FAILURE_PIN] + 1);
+
+ if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: Enable GC = ino %lx after %x GC trials\n",
+ __func__, inode->i_ino,
+ fi->i_gc_failures[GC_FAILURE_PIN]);
+ clear_inode_flag(inode, FI_PIN_FILE);
+ return -EAGAIN;
+ }
+ return 0;
+}
+
+static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ __u32 pin;
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(pin, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ if (f2fs_should_update_outplace(inode, NULL)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!pin) {
+ clear_inode_flag(inode, FI_PIN_FILE);
+ f2fs_i_gc_failures_write(inode, 0);
+ goto done;
+ }
+
+ if (f2fs_pin_file_control(inode, false)) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto out;
+
+ set_inode_flag(inode, FI_PIN_FILE);
+ ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
+done:
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ __u32 pin = 0;
+
+ if (is_inode_flag_set(inode, FI_PIN_FILE))
+ pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
+ return put_user(pin, (u32 __user *)arg);
+}
+
+int f2fs_precache_extents(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_map_blocks map;
+ pgoff_t m_next_extent;
+ loff_t end;
+ int err;
+
+ if (is_inode_flag_set(inode, FI_NO_EXTENT))
+ return -EOPNOTSUPP;
+
+ map.m_lblk = 0;
+ map.m_next_pgofs = NULL;
+ map.m_next_extent = &m_next_extent;
+ map.m_seg_type = NO_CHECK_TYPE;
+ map.m_may_create = false;
+ end = F2FS_I_SB(inode)->max_file_blocks;
+
+ while (map.m_lblk < end) {
+ map.m_len = end - map.m_lblk;
+
+ down_write(&fi->i_gc_rwsem[WRITE]);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE);
+ up_write(&fi->i_gc_rwsem[WRITE]);
+ if (err)
+ return err;
+
+ map.m_lblk = m_next_extent;
+ }
+
+ return err;
+}
+
+static int f2fs_ioc_precache_extents(struct file *filp, unsigned long arg)
+{
+ return f2fs_precache_extents(file_inode(filp));
+}
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
+ return -EIO;
+
switch (cmd) {
case F2FS_IOC_GETFLAGS:
return f2fs_ioc_getflags(filp, arg);
@@ -2237,12 +2778,24 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT:
return f2fs_ioc_gc(filp, arg);
+ case F2FS_IOC_GARBAGE_COLLECT_RANGE:
+ return f2fs_ioc_gc_range(filp, arg);
case F2FS_IOC_WRITE_CHECKPOINT:
return f2fs_ioc_write_checkpoint(filp, arg);
case F2FS_IOC_DEFRAGMENT:
return f2fs_ioc_defragment(filp, arg);
case F2FS_IOC_MOVE_RANGE:
return f2fs_ioc_move_range(filp, arg);
+ case F2FS_IOC_FLUSH_DEVICE:
+ return f2fs_ioc_flush_device(filp, arg);
+ case F2FS_IOC_GET_FEATURES:
+ return f2fs_ioc_get_features(filp, arg);
+ case F2FS_IOC_GET_PIN_FILE:
+ return f2fs_ioc_get_pin_file(filp, arg);
+ case F2FS_IOC_SET_PIN_FILE:
+ return f2fs_ioc_set_pin_file(filp, arg);
+ case F2FS_IOC_PRECACHE_EXTENTS:
+ return f2fs_ioc_precache_extents(filp, arg);
default:
return -ENOTTY;
}
@@ -2252,23 +2805,62 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
- struct blk_plug plug;
ssize_t ret;
- if (f2fs_encrypted_inode(inode) &&
- !fscrypt_has_encryption_key(inode) &&
- fscrypt_get_encryption_info(inode))
- return -EACCES;
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
- inode_lock(inode);
+ if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+ return -EINVAL;
+
+ if (!inode_trylock(inode)) {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ inode_lock(inode);
+ }
+
ret = generic_write_checks(iocb, from);
if (ret > 0) {
- ret = f2fs_preallocate_blocks(iocb, from);
- if (!ret) {
- blk_start_plug(&plug);
- ret = __generic_file_write_iter(iocb, from);
- blk_finish_plug(&plug);
+ bool preallocated = false;
+ size_t target_size = 0;
+ int err;
+
+ if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+ set_inode_flag(inode, FI_NO_PREALLOC);
+
+ if ((iocb->ki_flags & IOCB_NOWAIT) &&
+ (iocb->ki_flags & IOCB_DIRECT)) {
+ if (!f2fs_overwrite_io(inode, iocb->ki_pos,
+ iov_iter_count(from)) ||
+ f2fs_has_inline_data(inode) ||
+ f2fs_force_buffered_io(inode,
+ iocb, from)) {
+ clear_inode_flag(inode,
+ FI_NO_PREALLOC);
+ inode_unlock(inode);
+ return -EAGAIN;
+ }
+
+ } else {
+ preallocated = true;
+ target_size = iocb->ki_pos + iov_iter_count(from);
+
+ err = f2fs_preallocate_blocks(iocb, from);
+ if (err) {
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+ inode_unlock(inode);
+ return err;
+ }
}
+ ret = __generic_file_write_iter(iocb, from);
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+
+ /* if we couldn't write data, we should deallocate blocks. */
+ if (preallocated && i_size_read(inode) < target_size)
+ f2fs_truncate(inode);
+
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
}
inode_unlock(inode);
@@ -2300,10 +2892,15 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_GET_ENCRYPTION_PWSALT:
case F2FS_IOC_GET_ENCRYPTION_POLICY:
case F2FS_IOC_GARBAGE_COLLECT:
+ case F2FS_IOC_GARBAGE_COLLECT_RANGE:
case F2FS_IOC_WRITE_CHECKPOINT:
case F2FS_IOC_DEFRAGMENT:
- break;
case F2FS_IOC_MOVE_RANGE:
+ case F2FS_IOC_FLUSH_DEVICE:
+ case F2FS_IOC_GET_FEATURES:
+ case F2FS_IOC_GET_PIN_FILE:
+ case F2FS_IOC_SET_PIN_FILE:
+ case F2FS_IOC_PRECACHE_EXTENTS:
break;
default:
return -ENOIOCTLCMD;
@@ -2319,6 +2916,7 @@ const struct file_operations f2fs_file_operations = {
.open = f2fs_file_open,
.release = f2fs_release_file,
.mmap = f2fs_file_mmap,
+ .flush = f2fs_file_flush,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b1d6200..d421720 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/gc.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/module.h>
@@ -28,29 +25,43 @@ static int gc_thread_func(void *data)
struct f2fs_sb_info *sbi = data;
struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
- long wait_ms;
+ unsigned int wait_ms;
wait_ms = gc_th->min_sleep_time;
+ set_freezable();
do {
- if (try_to_freeze())
+ wait_event_interruptible_timeout(*wq,
+ kthread_should_stop() || freezing(current) ||
+ gc_th->gc_wake,
+ msecs_to_jiffies(wait_ms));
+
+ /* give it a try one time */
+ if (gc_th->gc_wake)
+ gc_th->gc_wake = 0;
+
+ if (try_to_freeze()) {
+ stat_other_skip_bggc_count(sbi);
continue;
- else
- wait_event_interruptible_timeout(*wq,
- kthread_should_stop(),
- msecs_to_jiffies(wait_ms));
+ }
if (kthread_should_stop())
break;
if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
increase_sleep_time(gc_th, &wait_ms);
+ stat_other_skip_bggc_count(sbi);
continue;
}
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_CHECKPOINT))
+ if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+ f2fs_show_injection_info(FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
-#endif
+ }
+
+ if (!sb_start_write_trylock(sbi->sb)) {
+ stat_other_skip_bggc_count(sbi);
+ continue;
+ }
/*
* [GC triggering condition]
@@ -65,24 +76,33 @@ static int gc_thread_func(void *data)
* invalidated soon after by user update or deletion.
* So, I'd like to wait some time to collect dirty segments.
*/
- if (!mutex_trylock(&sbi->gc_mutex))
- continue;
+ if (sbi->gc_mode == GC_URGENT) {
+ wait_ms = gc_th->urgent_sleep_time;
+ mutex_lock(&sbi->gc_mutex);
+ goto do_gc;
+ }
- if (!is_idle(sbi)) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ stat_other_skip_bggc_count(sbi);
+ goto next;
+ }
+
+ if (!is_idle(sbi, GC_TIME)) {
increase_sleep_time(gc_th, &wait_ms);
mutex_unlock(&sbi->gc_mutex);
- continue;
+ stat_io_skip_bggc_count(sbi);
+ goto next;
}
if (has_enough_invalid_blocks(sbi))
decrease_sleep_time(gc_th, &wait_ms);
else
increase_sleep_time(gc_th, &wait_ms);
-
+do_gc:
stat_inc_bggc_count(sbi);
/* if return value is not zero, no victim was selected */
- if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC)))
+ if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO))
wait_ms = gc_th->no_gc_sleep_time;
trace_f2fs_background_gc(sbi->sb, wait_ms,
@@ -90,12 +110,14 @@ static int gc_thread_func(void *data)
/* balancing f2fs's metadata periodically */
f2fs_balance_fs_bg(sbi);
+next:
+ sb_end_write(sbi->sb);
} while (!kthread_should_stop());
return 0;
}
-int start_gc_thread(struct f2fs_sb_info *sbi)
+int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th;
dev_t dev = sbi->sb->s_bdev->bd_dev;
@@ -107,11 +129,12 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
goto out;
}
+ gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
- gc_th->gc_idle = 0;
+ gc_th->gc_wake= 0;
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
@@ -119,32 +142,35 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(gc_th->f2fs_gc_task)) {
err = PTR_ERR(gc_th->f2fs_gc_task);
- kfree(gc_th);
+ kvfree(gc_th);
sbi->gc_thread = NULL;
}
out:
return err;
}
-void stop_gc_thread(struct f2fs_sb_info *sbi)
+void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
if (!gc_th)
return;
kthread_stop(gc_th->f2fs_gc_task);
- kfree(gc_th);
+ kvfree(gc_th);
sbi->gc_thread = NULL;
}
-static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type)
+static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
{
int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
- if (gc_th && gc_th->gc_idle) {
- if (gc_th->gc_idle == 1)
- gc_mode = GC_CB;
- else if (gc_th->gc_idle == 2)
- gc_mode = GC_GREEDY;
+ switch (sbi->gc_mode) {
+ case GC_IDLE_CB:
+ gc_mode = GC_CB;
+ break;
+ case GC_IDLE_GREEDY:
+ case GC_URGENT:
+ gc_mode = GC_GREEDY;
+ break;
}
return gc_mode;
}
@@ -160,17 +186,24 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
p->max_search = dirty_i->nr_dirty[type];
p->ofs_unit = 1;
} else {
- p->gc_mode = select_gc_type(sbi->gc_thread, gc_type);
+ p->gc_mode = select_gc_type(sbi, gc_type);
p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
p->max_search = dirty_i->nr_dirty[DIRTY];
p->ofs_unit = sbi->segs_per_sec;
}
/* we need to check every dirty segments in the FG_GC case */
- if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
+ if (gc_type != FG_GC &&
+ (sbi->gc_mode != GC_URGENT) &&
+ p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
- p->offset = sbi->last_victim[p->gc_mode];
+ /* let's select beginning hot/small space first in no_heap mode*/
+ if (test_opt(sbi, NOHEAP) &&
+ (type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+ p->offset = 0;
+ else
+ p->offset = SIT_I(sbi)->last_victim[p->gc_mode];
}
static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
@@ -180,7 +213,7 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
if (p->alloc_mode == SSR)
return sbi->blocks_per_seg;
if (p->gc_mode == GC_GREEDY)
- return sbi->blocks_per_seg * p->ofs_unit;
+ return 2 * sbi->blocks_per_seg * p->ofs_unit;
else if (p->gc_mode == GC_CB)
return UINT_MAX;
else /* No other gc_mode */
@@ -200,12 +233,8 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
if (sec_usage_check(sbi, secno))
continue;
-
- if (no_fggc_candidate(sbi, secno))
- continue;
-
clear_bit(secno, dirty_i->victim_secmap);
- return secno * sbi->segs_per_sec;
+ return GET_SEG_FROM_SEC(sbi, secno);
}
return NULL_SEGNO;
}
@@ -213,8 +242,8 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int secno = GET_SECNO(sbi, segno);
- unsigned int start = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
unsigned long long mtime = 0;
unsigned int vblocks;
unsigned char age = 0;
@@ -223,7 +252,7 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
for (i = 0; i < sbi->segs_per_sec; i++)
mtime += get_seg_entry(sbi, start + i)->mtime;
- vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+ vblocks = get_valid_blocks(sbi, segno, true);
mtime = div_u64(mtime, sbi->segs_per_sec);
vblocks = div_u64(vblocks, sbi->segs_per_sec);
@@ -250,7 +279,7 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
/* alloc_mode == LFS */
if (p->gc_mode == GC_GREEDY)
- return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+ return get_valid_blocks(sbi, segno, true);
else
return get_cb_cost(sbi, segno);
}
@@ -279,6 +308,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned int *result, int gc_type, int type, char alloc_mode)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ struct sit_info *sm = SIT_I(sbi);
struct victim_sel_policy p;
unsigned int secno, last_victim;
unsigned int last_segment = MAIN_SEGS(sbi);
@@ -292,10 +322,33 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
p.min_segno = NULL_SEGNO;
p.min_cost = get_max_cost(sbi, &p);
+ if (*result != NULL_SEGNO) {
+ if (get_valid_blocks(sbi, *result, false) &&
+ !sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ p.min_segno = *result;
+ goto out;
+ }
+
if (p.max_search == 0)
goto out;
- last_victim = sbi->last_victim[p.gc_mode];
+ if (__is_large_section(sbi) && p.alloc_mode == LFS) {
+ if (sbi->next_victim_seg[BG_GC] != NULL_SEGNO) {
+ p.min_segno = sbi->next_victim_seg[BG_GC];
+ *result = p.min_segno;
+ sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
+ goto got_result;
+ }
+ if (gc_type == FG_GC &&
+ sbi->next_victim_seg[FG_GC] != NULL_SEGNO) {
+ p.min_segno = sbi->next_victim_seg[FG_GC];
+ *result = p.min_segno;
+ sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
+ goto got_result;
+ }
+ }
+
+ last_victim = sm->last_victim[p.gc_mode];
if (p.alloc_mode == LFS && gc_type == FG_GC) {
p.min_segno = check_bg_victims(sbi);
if (p.min_segno != NULL_SEGNO)
@@ -308,9 +361,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
if (segno >= last_segment) {
- if (sbi->last_victim[p.gc_mode]) {
- last_segment = sbi->last_victim[p.gc_mode];
- sbi->last_victim[p.gc_mode] = 0;
+ if (sm->last_victim[p.gc_mode]) {
+ last_segment =
+ sm->last_victim[p.gc_mode];
+ sm->last_victim[p.gc_mode] = 0;
p.offset = 0;
continue;
}
@@ -327,14 +381,15 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
nsearched++;
}
- secno = GET_SECNO(sbi, segno);
+ secno = GET_SEC_FROM_SEG(sbi, segno);
if (sec_usage_check(sbi, secno))
goto next;
- if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
+ /* Don't touch checkpointed data */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ get_ckpt_valid_blocks(sbi, segno)))
goto next;
- if (gc_type == FG_GC && p.alloc_mode == LFS &&
- no_fggc_candidate(sbi, secno))
+ if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
goto next;
cost = get_gc_cost(sbi, segno, &p);
@@ -345,29 +400,32 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
}
next:
if (nsearched >= p.max_search) {
- if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
- sbi->last_victim[p.gc_mode] = last_victim + 1;
+ if (!sm->last_victim[p.gc_mode] && segno <= last_victim)
+ sm->last_victim[p.gc_mode] = last_victim + 1;
else
- sbi->last_victim[p.gc_mode] = segno + 1;
+ sm->last_victim[p.gc_mode] = segno + 1;
+ sm->last_victim[p.gc_mode] %= MAIN_SEGS(sbi);
break;
}
}
if (p.min_segno != NULL_SEGNO) {
got_it:
+ *result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
+got_result:
if (p.alloc_mode == LFS) {
- secno = GET_SECNO(sbi, p.min_segno);
+ secno = GET_SEC_FROM_SEG(sbi, p.min_segno);
if (gc_type == FG_GC)
sbi->cur_victim_sec = secno;
else
set_bit(secno, dirty_i->victim_secmap);
}
- *result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
+ }
+out:
+ if (p.min_segno != NULL_SEGNO)
trace_f2fs_get_victim(sbi->sb, type, gc_type, &p,
sbi->cur_victim_sec,
prefree_segments(sbi), free_segments(sbi));
- }
-out:
mutex_unlock(&dirty_i->seglist_lock);
return (p.min_segno == NULL_SEGNO) ? 0 : 1;
@@ -395,7 +453,7 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
iput(inode);
return;
}
- new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
+ new_ie = f2fs_kmem_cache_alloc(f2fs_inode_entry_slab, GFP_NOFS);
new_ie->inode = inode;
f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
@@ -409,7 +467,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list)
radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
iput(ie->inode);
list_del(&ie->list);
- kmem_cache_free(inode_entry_slab, ie);
+ kmem_cache_free(f2fs_inode_entry_slab, ie);
}
}
@@ -420,10 +478,10 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
struct seg_entry *sentry;
int ret;
- mutex_lock(&sit_i->sentry_lock);
+ down_read(&sit_i->sentry_lock);
sentry = get_seg_entry(sbi, segno);
ret = f2fs_test_bit(offset, sentry->cur_valid_map);
- mutex_unlock(&sit_i->sentry_lock);
+ up_read(&sit_i->sentry_lock);
return ret;
}
@@ -432,65 +490,81 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
* On validity, copy that node with cold status, otherwise (invalid node)
* ignore that.
*/
-static void gc_node_segment(struct f2fs_sb_info *sbi,
+static int gc_node_segment(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum, unsigned int segno, int gc_type)
{
struct f2fs_summary *entry;
block_t start_addr;
int off;
int phase = 0;
+ bool fggc = (gc_type == FG_GC);
+ int submitted = 0;
start_addr = START_BLOCK(sbi, segno);
next_step:
entry = sum;
+ if (fggc && phase == 2)
+ atomic_inc(&sbi->wb_sync_req[NODE]);
+
for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
nid_t nid = le32_to_cpu(entry->nid);
struct page *node_page;
struct node_info ni;
+ int err;
/* stop BG_GC if there is not enough free sections. */
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
- return;
+ return submitted;
if (check_valid_map(sbi, segno, off) == 0)
continue;
if (phase == 0) {
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+ f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
META_NAT, true);
continue;
}
if (phase == 1) {
- ra_node_page(sbi, nid);
+ f2fs_ra_node_page(sbi, nid);
continue;
}
/* phase == 2 */
- node_page = get_node_page(sbi, nid);
+ node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
continue;
- /* block may become invalid during get_node_page */
+ /* block may become invalid during f2fs_get_node_page */
if (check_valid_map(sbi, segno, off) == 0) {
f2fs_put_page(node_page, 1);
continue;
}
- get_node_info(sbi, nid, &ni);
+ if (f2fs_get_node_info(sbi, nid, &ni)) {
+ f2fs_put_page(node_page, 1);
+ continue;
+ }
+
if (ni.blk_addr != start_addr + off) {
f2fs_put_page(node_page, 1);
continue;
}
- move_node_page(node_page, gc_type);
+ err = f2fs_move_node_page(node_page, gc_type);
+ if (!err && gc_type == FG_GC)
+ submitted++;
stat_inc_node_blk_count(sbi, 1, gc_type);
}
if (++phase < 3)
goto next_step;
+
+ if (fggc)
+ atomic_dec(&sbi->wb_sync_req[NODE]);
+ return submitted;
}
/*
@@ -500,7 +574,7 @@ static void gc_node_segment(struct f2fs_sb_info *sbi,
* as indirect or double indirect node blocks, are given, it must be a caller's
* bug.
*/
-block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
+block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
{
unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
unsigned int bidx;
@@ -531,11 +605,14 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
nid = le32_to_cpu(sum->nid);
ofs_in_node = le16_to_cpu(sum->ofs_in_node);
- node_page = get_node_page(sbi, nid);
+ node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return false;
- get_node_info(sbi, nid, dni);
+ if (f2fs_get_node_info(sbi, nid, dni)) {
+ f2fs_put_page(node_page, 1);
+ return false;
+ }
if (sum->version != dni->version) {
f2fs_msg(sbi->sb, KERN_WARNING,
@@ -545,7 +622,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
}
*nofs = ofs_of_node(node_page);
- source_blkaddr = datablock_addr(node_page, ofs_in_node);
+ source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node);
f2fs_put_page(node_page, 1);
if (source_blkaddr != blkaddr)
@@ -553,34 +630,137 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
return true;
}
-static void move_encrypted_block(struct inode *inode, block_t bidx)
+static int ra_data_block(struct inode *inode, pgoff_t index)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
+ struct dnode_of_data dn;
+ struct page *page;
+ struct extent_info ei = {0, 0, 0};
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .ino = inode->i_ino,
+ .type = DATA,
+ .temp = COLD,
+ .op = REQ_OP_READ,
+ .op_flags = 0,
+ .encrypted_page = NULL,
+ .in_list = false,
+ .retry = false,
+ };
+ int err;
+
+ page = f2fs_grab_cache_page(mapping, index, true);
+ if (!page)
+ return -ENOMEM;
+
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn.data_blkaddr = ei.blk + index - ei.fofs;
+ goto got_it;
+ }
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (err)
+ goto put_page;
+ f2fs_put_dnode(&dn);
+
+ if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
+ DATA_GENERIC))) {
+ err = -EFAULT;
+ goto put_page;
+ }
+got_it:
+ /* read page */
+ fio.page = page;
+ fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
+
+ /*
+ * don't cache encrypted data into meta inode until previous dirty
+ * data were writebacked to avoid racing between GC and flush.
+ */
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+
+ f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+
+ fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(sbi),
+ dn.data_blkaddr,
+ FGP_LOCK | FGP_CREAT, GFP_NOFS);
+ if (!fio.encrypted_page) {
+ err = -ENOMEM;
+ goto put_page;
+ }
+
+ err = f2fs_submit_page_bio(&fio);
+ if (err)
+ goto put_encrypted_page;
+ f2fs_put_page(fio.encrypted_page, 0);
+ f2fs_put_page(page, 1);
+ return 0;
+put_encrypted_page:
+ f2fs_put_page(fio.encrypted_page, 1);
+put_page:
+ f2fs_put_page(page, 1);
+ return err;
+}
+
+/*
+ * Move data block via META_MAPPING while keeping locked data page.
+ * This can be used to move blocks, aka LBAs, directly on disk.
+ */
+static int move_data_block(struct inode *inode, block_t bidx,
+ int gc_type, unsigned int segno, int off)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
+ .ino = inode->i_ino,
.type = DATA,
+ .temp = COLD,
.op = REQ_OP_READ,
- .op_flags = READ_SYNC,
+ .op_flags = 0,
.encrypted_page = NULL,
+ .in_list = false,
+ .retry = false,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
struct node_info ni;
- struct page *page;
+ struct page *page, *mpage;
block_t newaddr;
- int err;
+ int err = 0;
+ bool lfs_mode = test_opt(fio.sbi, LFS);
/* do not read out */
page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
if (!page)
- return;
+ return -ENOMEM;
+
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off)) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ if (f2fs_is_atomic_file(inode)) {
+ F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
+ F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
+ err = -EAGAIN;
+ goto out;
+ }
+
+ if (f2fs_is_pinned_file(inode)) {
+ f2fs_pin_file_control(inode, true);
+ err = -EAGAIN;
+ goto out;
+ }
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
if (err)
goto out;
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
ClearPageUptodate(page);
+ err = -ENOENT;
goto put_out;
}
@@ -588,25 +768,50 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
* don't cache encrypted data into meta inode until previous dirty
* data were writebacked to avoid racing between GC and flush.
*/
- f2fs_wait_on_page_writeback(page, DATA, true);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
- get_node_info(fio.sbi, dn.nid, &ni);
+ f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+
+ err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+ if (err)
+ goto put_out;
+
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* read page */
fio.page = page;
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
- allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
- &sum, CURSEG_COLD_DATA);
+ if (lfs_mode)
+ down_write(&fio.sbi->io_order_lock);
- fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
- FGP_LOCK | FGP_CREAT, GFP_NOFS);
+ f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
+ &sum, CURSEG_COLD_DATA, NULL, false);
+
+ fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
+ newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
if (!fio.encrypted_page) {
err = -ENOMEM;
goto recover_block;
}
+ mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
+ fio.old_blkaddr, FGP_LOCK, GFP_NOFS);
+ if (mpage) {
+ bool updated = false;
+
+ if (PageUptodate(mpage)) {
+ memcpy(page_address(fio.encrypted_page),
+ page_address(mpage), PAGE_SIZE);
+ updated = true;
+ }
+ f2fs_put_page(mpage, 1);
+ invalidate_mapping_pages(META_MAPPING(fio.sbi),
+ fio.old_blkaddr, fio.old_blkaddr);
+ if (updated)
+ goto write_page;
+ }
+
err = f2fs_submit_page_bio(&fio);
if (err)
goto put_page_out;
@@ -623,20 +828,30 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
goto put_page_out;
}
+write_page:
+ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true);
set_page_dirty(fio.encrypted_page);
- f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
set_page_writeback(fio.encrypted_page);
+ ClearPageError(page);
/* allocate block address */
- f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
+ f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
fio.op = REQ_OP_WRITE;
- fio.op_flags = WRITE_SYNC;
+ fio.op_flags = REQ_SYNC;
fio.new_blkaddr = newaddr;
- f2fs_submit_page_mbio(&fio);
+ f2fs_submit_page_write(&fio);
+ if (fio.retry) {
+ err = -EAGAIN;
+ if (PageWriteback(fio.encrypted_page))
+ end_page_writeback(fio.encrypted_page);
+ goto put_page_out;
+ }
+
+ f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);
f2fs_update_data_blkaddr(&dn, newaddr);
set_inode_flag(inode, FI_APPEND_WRITE);
@@ -645,49 +860,81 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
+ if (lfs_mode)
+ up_write(&fio.sbi->io_order_lock);
if (err)
- __f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
+ f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
true, true);
put_out:
f2fs_put_dnode(&dn);
out:
f2fs_put_page(page, 1);
+ return err;
}
-static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
+static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
+ unsigned int segno, int off)
{
struct page *page;
+ int err = 0;
- page = get_lock_data_page(inode, bidx, true);
+ page = f2fs_get_lock_data_page(inode, bidx, true);
if (IS_ERR(page))
- return;
+ return PTR_ERR(page);
+
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off)) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ if (f2fs_is_atomic_file(inode)) {
+ F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
+ F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
+ err = -EAGAIN;
+ goto out;
+ }
+ if (f2fs_is_pinned_file(inode)) {
+ if (gc_type == FG_GC)
+ f2fs_pin_file_control(inode, true);
+ err = -EAGAIN;
+ goto out;
+ }
if (gc_type == BG_GC) {
- if (PageWriteback(page))
+ if (PageWriteback(page)) {
+ err = -EAGAIN;
goto out;
+ }
set_page_dirty(page);
set_cold_data(page);
} else {
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
+ .ino = inode->i_ino,
.type = DATA,
+ .temp = COLD,
.op = REQ_OP_WRITE,
- .op_flags = WRITE_SYNC,
+ .op_flags = REQ_SYNC,
+ .old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
+ .need_lock = LOCK_REQ,
+ .io_type = FS_GC_DATA_IO,
};
bool is_dirty = PageDirty(page);
- int err;
retry:
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+
set_page_dirty(page);
- f2fs_wait_on_page_writeback(page, DATA, true);
- if (clear_page_dirty_for_io(page))
+ if (clear_page_dirty_for_io(page)) {
inode_dec_dirty_pages(inode);
+ f2fs_remove_dirty_inode(inode);
+ }
set_cold_data(page);
- err = do_write_data_page(&fio);
+ err = f2fs_do_write_data_page(&fio);
if (err) {
clear_cold_data(page);
if (err == -ENOMEM) {
@@ -697,11 +944,10 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
if (is_dirty)
set_page_dirty(page);
}
-
- clear_cold_data(page);
}
out:
f2fs_put_page(page, 1);
+ return err;
}
/*
@@ -711,7 +957,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
* If the parent node is not valid or the data block address is different,
* the victim data block is ignored.
*/
-static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
{
struct super_block *sb = sbi->sb;
@@ -719,6 +965,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t start_addr;
int off;
int phase = 0;
+ int submitted = 0;
start_addr = START_BLOCK(sbi, segno);
@@ -735,19 +982,19 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
/* stop BG_GC if there is not enough free sections. */
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
- return;
+ return submitted;
if (check_valid_map(sbi, segno, off) == 0)
continue;
if (phase == 0) {
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+ f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
META_NAT, true);
continue;
}
if (phase == 1) {
- ra_node_page(sbi, nid);
+ f2fs_ra_node_page(sbi, nid);
continue;
}
@@ -756,7 +1003,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
continue;
if (phase == 2) {
- ra_node_page(sbi, dni.ino);
+ f2fs_ra_node_page(sbi, dni.ino);
continue;
}
@@ -767,17 +1014,31 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (IS_ERR(inode) || is_bad_inode(inode))
continue;
- /* if encrypted inode, let's go phase 3 */
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
+ if (!down_write_trylock(
+ &F2FS_I(inode)->i_gc_rwsem[WRITE])) {
+ iput(inode);
+ sbi->skipped_gc_rwsem++;
+ continue;
+ }
+
+ start_bidx = f2fs_start_bidx_of_node(nofs, inode) +
+ ofs_in_node;
+
+ if (f2fs_post_read_required(inode)) {
+ int err = ra_data_block(inode, start_bidx);
+
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ if (err) {
+ iput(inode);
+ continue;
+ }
add_gc_inode(gc_list, inode);
continue;
}
- start_bidx = start_bidx_of_node(nofs, inode);
- data_page = get_read_data_page(inode,
- start_bidx + ofs_in_node, REQ_RAHEAD,
- true);
+ data_page = f2fs_get_read_data_page(inode,
+ start_bidx, REQ_RAHEAD, true);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (IS_ERR(data_page)) {
iput(inode);
continue;
@@ -793,28 +1054,39 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (inode) {
struct f2fs_inode_info *fi = F2FS_I(inode);
bool locked = false;
+ int err;
if (S_ISREG(inode->i_mode)) {
- if (!down_write_trylock(&fi->dio_rwsem[READ]))
+ if (!down_write_trylock(&fi->i_gc_rwsem[READ]))
continue;
if (!down_write_trylock(
- &fi->dio_rwsem[WRITE])) {
- up_write(&fi->dio_rwsem[READ]);
+ &fi->i_gc_rwsem[WRITE])) {
+ sbi->skipped_gc_rwsem++;
+ up_write(&fi->i_gc_rwsem[READ]);
continue;
}
locked = true;
+
+ /* wait for all inflight aio data */
+ inode_dio_wait(inode);
}
- start_bidx = start_bidx_of_node(nofs, inode)
+ start_bidx = f2fs_start_bidx_of_node(nofs, inode)
+ ofs_in_node;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- move_encrypted_block(inode, start_bidx);
+ if (f2fs_post_read_required(inode))
+ err = move_data_block(inode, start_bidx,
+ gc_type, segno, off);
else
- move_data_page(inode, start_bidx, gc_type);
+ err = move_data_page(inode, start_bidx, gc_type,
+ segno, off);
+
+ if (!err && (gc_type == FG_GC ||
+ f2fs_post_read_required(inode)))
+ submitted++;
if (locked) {
- up_write(&fi->dio_rwsem[WRITE]);
- up_write(&fi->dio_rwsem[READ]);
+ up_write(&fi->i_gc_rwsem[WRITE]);
+ up_write(&fi->i_gc_rwsem[READ]);
}
stat_inc_data_blk_count(sbi, 1, gc_type);
@@ -823,6 +1095,8 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (++phase < 5)
goto next_step;
+
+ return submitted;
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -831,10 +1105,10 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
struct sit_info *sit_i = SIT_I(sbi);
int ret;
- mutex_lock(&sit_i->sentry_lock);
+ down_write(&sit_i->sentry_lock);
ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type,
NO_CHECK_TYPE, LFS);
- mutex_unlock(&sit_i->sentry_lock);
+ up_write(&sit_i->sentry_lock);
return ret;
}
@@ -847,18 +1121,34 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
struct blk_plug plug;
unsigned int segno = start_segno;
unsigned int end_segno = start_segno + sbi->segs_per_sec;
- int sec_freed = 0;
+ int seg_freed = 0, migrated = 0;
unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
SUM_TYPE_DATA : SUM_TYPE_NODE;
+ int submitted = 0;
+
+ if (__is_large_section(sbi))
+ end_segno = rounddown(end_segno, sbi->segs_per_sec);
/* readahead multi ssa blocks those have contiguous address */
- if (sbi->segs_per_sec > 1)
- ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
- sbi->segs_per_sec, META_SSA, true);
+ if (__is_large_section(sbi))
+ f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
+ end_segno - segno, META_SSA, true);
/* reference all summary page */
while (segno < end_segno) {
- sum_page = get_sum_page(sbi, segno++);
+ sum_page = f2fs_get_sum_page(sbi, segno++);
+ if (IS_ERR(sum_page)) {
+ int err = PTR_ERR(sum_page);
+
+ end_segno = segno - 1;
+ for (segno = start_segno; segno < end_segno; segno++) {
+ sum_page = find_get_page(META_MAPPING(sbi),
+ GET_SUM_BLOCK(sbi, segno));
+ f2fs_put_page(sum_page, 0);
+ f2fs_put_page(sum_page, 0);
+ }
+ return err;
+ }
unlock_page(sum_page);
}
@@ -871,10 +1161,13 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
GET_SUM_BLOCK(sbi, segno));
f2fs_put_page(sum_page, 0);
- if (get_valid_blocks(sbi, segno, 1) == 0 ||
- !PageUptodate(sum_page) ||
- unlikely(f2fs_cp_error(sbi)))
- goto next;
+ if (get_valid_blocks(sbi, segno, false) == 0)
+ goto freed;
+ if (__is_large_section(sbi) &&
+ migrated >= sbi->migration_granularity)
+ goto skip;
+ if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi)))
+ goto skip;
sum = page_address(sum_page);
if (type != GET_SUM_TYPE((&sum->footer))) {
@@ -882,105 +1175,161 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
"type [%d, %d] in SSA and SIT",
segno, type, GET_SUM_TYPE((&sum->footer)));
set_sbi_flag(sbi, SBI_NEED_FSCK);
- goto next;
+ goto skip;
}
/*
* this is to avoid deadlock:
* - lock_page(sum_page) - f2fs_replace_block
- * - check_valid_map() - mutex_lock(sentry_lock)
- * - mutex_lock(sentry_lock) - change_curseg()
+ * - check_valid_map() - down_write(sentry_lock)
+ * - down_read(sentry_lock) - change_curseg()
* - lock_page(sum_page)
*/
-
if (type == SUM_TYPE_NODE)
- gc_node_segment(sbi, sum->entries, segno, gc_type);
- else
- gc_data_segment(sbi, sum->entries, gc_list, segno,
+ submitted += gc_node_segment(sbi, sum->entries, segno,
gc_type);
+ else
+ submitted += gc_data_segment(sbi, sum->entries, gc_list,
+ segno, gc_type);
stat_inc_seg_count(sbi, type, gc_type);
-next:
+
+freed:
+ if (gc_type == FG_GC &&
+ get_valid_blocks(sbi, segno, false) == 0)
+ seg_freed++;
+ migrated++;
+
+ if (__is_large_section(sbi) && segno + 1 < end_segno)
+ sbi->next_victim_seg[gc_type] = segno + 1;
+skip:
f2fs_put_page(sum_page, 0);
}
- if (gc_type == FG_GC)
- f2fs_submit_merged_bio(sbi,
- (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+ if (submitted)
+ f2fs_submit_merged_write(sbi,
+ (type == SUM_TYPE_NODE) ? NODE : DATA);
blk_finish_plug(&plug);
- if (gc_type == FG_GC &&
- get_valid_blocks(sbi, start_segno, sbi->segs_per_sec) == 0)
- sec_freed = 1;
-
stat_inc_call_count(sbi->stat_info);
- return sec_freed;
+ return seg_freed;
}
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
+ bool background, unsigned int segno)
{
- unsigned int segno;
int gc_type = sync ? FG_GC : BG_GC;
- int sec_freed = 0;
- int ret = -EINVAL;
+ int sec_freed = 0, seg_freed = 0, total_freed = 0;
+ int ret = 0;
struct cp_control cpc;
+ unsigned int init_segno = segno;
struct gc_inode_list gc_list = {
.ilist = LIST_HEAD_INIT(gc_list.ilist),
.iroot = RADIX_TREE_INIT(GFP_NOFS),
};
+ unsigned long long last_skipped = sbi->skipped_atomic_files[FG_GC];
+ unsigned long long first_skipped;
+ unsigned int skipped_round = 0, round = 0;
+
+ trace_f2fs_gc_begin(sbi->sb, sync, background,
+ get_pages(sbi, F2FS_DIRTY_NODES),
+ get_pages(sbi, F2FS_DIRTY_DENTS),
+ get_pages(sbi, F2FS_DIRTY_IMETA),
+ free_sections(sbi),
+ free_segments(sbi),
+ reserved_segments(sbi),
+ prefree_segments(sbi));
cpc.reason = __get_cp_reason(sbi);
+ sbi->skipped_gc_rwsem = 0;
+ first_skipped = last_skipped;
gc_more:
- segno = NULL_SEGNO;
-
- if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
+ if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) {
+ ret = -EINVAL;
goto stop;
+ }
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto stop;
}
- if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) {
- gc_type = FG_GC;
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) {
/*
- * If there is no victim and no prefree segment but still not
- * enough free sections, we should flush dent/node blocks and do
- * garbage collections.
+ * For example, if there are many prefree_segments below given
+ * threshold, we can make them free by checkpoint. Then, we
+ * secure free segments which doesn't need fggc any more.
*/
- if (__get_victim(sbi, &segno, gc_type) ||
- prefree_segments(sbi)) {
- ret = write_checkpoint(sbi, &cpc);
- if (ret)
- goto stop;
- segno = NULL_SEGNO;
- } else if (has_not_enough_free_secs(sbi, 0, 0)) {
- ret = write_checkpoint(sbi, &cpc);
+ if (prefree_segments(sbi) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+ ret = f2fs_write_checkpoint(sbi, &cpc);
if (ret)
goto stop;
}
+ if (has_not_enough_free_secs(sbi, 0, 0))
+ gc_type = FG_GC;
}
- if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
+ /* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+ if (gc_type == BG_GC && !background) {
+ ret = -EINVAL;
goto stop;
- ret = 0;
+ }
+ if (!__get_victim(sbi, &segno, gc_type)) {
+ ret = -ENODATA;
+ goto stop;
+ }
- if (do_garbage_collect(sbi, segno, &gc_list, gc_type) &&
- gc_type == FG_GC)
+ seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
+ if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
sec_freed++;
+ total_freed += seg_freed;
+
+ if (gc_type == FG_GC) {
+ if (sbi->skipped_atomic_files[FG_GC] > last_skipped ||
+ sbi->skipped_gc_rwsem)
+ skipped_round++;
+ last_skipped = sbi->skipped_atomic_files[FG_GC];
+ round++;
+ }
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
- if (!sync) {
- if (has_not_enough_free_secs(sbi, sec_freed, 0))
- goto gc_more;
+ if (sync)
+ goto stop;
- if (gc_type == FG_GC)
- ret = write_checkpoint(sbi, &cpc);
+ if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
+ if (skipped_round <= MAX_SKIP_GC_COUNT ||
+ skipped_round * 2 < round) {
+ segno = NULL_SEGNO;
+ goto gc_more;
+ }
+
+ if (first_skipped < last_skipped &&
+ (last_skipped - first_skipped) >
+ sbi->skipped_gc_rwsem) {
+ f2fs_drop_inmem_pages_all(sbi, true);
+ segno = NULL_SEGNO;
+ goto gc_more;
+ }
+ if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED))
+ ret = f2fs_write_checkpoint(sbi, &cpc);
}
stop:
+ SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
+ SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno;
+
+ trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed,
+ get_pages(sbi, F2FS_DIRTY_NODES),
+ get_pages(sbi, F2FS_DIRTY_DENTS),
+ get_pages(sbi, F2FS_DIRTY_IMETA),
+ free_sections(sbi),
+ free_segments(sbi),
+ reserved_segments(sbi),
+ prefree_segments(sbi));
+
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&gc_list);
@@ -990,18 +1339,14 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
return ret;
}
-void build_gc_manager(struct f2fs_sb_info *sbi)
+void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
{
- u64 main_count, resv_count, ovp_count, blocks_per_sec;
-
DIRTY_I(sbi)->v_ops = &default_v_ops;
- /* threshold of # of valid blocks in a section for victims of FG_GC */
- main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
- resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
- ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
- blocks_per_sec = sbi->blocks_per_seg * sbi->segs_per_sec;
+ sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES;
- sbi->fggc_threshold = div_u64((main_count - ovp_count) * blocks_per_sec,
- (main_count - resv_count));
+ /* give warm/cold data area from slower device */
+ if (sbi->s_ndevs && !__is_large_section(sbi))
+ SIT_I(sbi)->last_victim[ALLOC_NEXT] =
+ GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index a993967..bbac9d3 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -1,24 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/gc.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#define GC_THREAD_MIN_WB_PAGES 1 /*
* a threshold to determine
* whether IO subsystem is idle
* or not
*/
+#define DEF_GC_THREAD_URGENT_SLEEP_TIME 500 /* 500 ms */
#define DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */
#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000
#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */
#define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */
#define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */
+#define DEF_GC_FAILED_PINNED_FILES 2048
+
/* Search max. number of dirty segments to select a victim segment */
#define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
@@ -27,12 +27,13 @@ struct f2fs_gc_kthread {
wait_queue_head_t gc_wait_queue_head;
/* for gc sleep time */
+ unsigned int urgent_sleep_time;
unsigned int min_sleep_time;
unsigned int max_sleep_time;
unsigned int no_gc_sleep_time;
/* for changing gc mode */
- unsigned int gc_idle;
+ unsigned int gc_wake;
};
struct gc_inode_list {
@@ -65,25 +66,32 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
}
static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
- long *wait)
+ unsigned int *wait)
{
+ unsigned int min_time = gc_th->min_sleep_time;
+ unsigned int max_time = gc_th->max_sleep_time;
+
if (*wait == gc_th->no_gc_sleep_time)
return;
- *wait += gc_th->min_sleep_time;
- if (*wait > gc_th->max_sleep_time)
- *wait = gc_th->max_sleep_time;
+ if ((long long)*wait + (long long)min_time > (long long)max_time)
+ *wait = max_time;
+ else
+ *wait += min_time;
}
static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
- long *wait)
+ unsigned int *wait)
{
+ unsigned int min_time = gc_th->min_sleep_time;
+
if (*wait == gc_th->no_gc_sleep_time)
*wait = gc_th->max_sleep_time;
- *wait -= gc_th->min_sleep_time;
- if (*wait <= gc_th->min_sleep_time)
- *wait = gc_th->min_sleep_time;
+ if ((long long)*wait - (long long)min_time < (long long)min_time)
+ *wait = min_time;
+ else
+ *wait -= min_time;
}
static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index eb2e031..cc82f14 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/hash.c
*
@@ -7,10 +8,6 @@
* Portions of this code from linux/fs/ext3/hash.c
*
* Copyright (C) 2002 by Theodore Ts'o
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/fs.h>
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 482888e..8422a13 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -1,11 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/inline.c
* Copyright (c) 2013, Intel Corporation
* Authors: Huajun Li <huajun.li@intel.com>
* Haicheng Li <haicheng.li@intel.com>
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
@@ -13,6 +11,7 @@
#include "f2fs.h"
#include "node.h"
+#include <trace/events/android_fs.h>
bool f2fs_may_inline_data(struct inode *inode)
{
@@ -22,10 +21,10 @@ bool f2fs_may_inline_data(struct inode *inode)
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
- if (i_size_read(inode) > MAX_INLINE_DATA)
+ if (i_size_read(inode) > MAX_INLINE_DATA(inode))
return false;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ if (f2fs_post_read_required(inode))
return false;
return true;
@@ -42,8 +41,9 @@ bool f2fs_may_inline_dentry(struct inode *inode)
return true;
}
-void read_inline_data(struct page *page, struct page *ipage)
+void f2fs_do_read_inline_data(struct page *page, struct page *ipage)
{
+ struct inode *inode = page->mapping->host;
void *src_addr, *dst_addr;
if (PageUptodate(page))
@@ -51,56 +51,76 @@ void read_inline_data(struct page *page, struct page *ipage)
f2fs_bug_on(F2FS_P_SB(page), page->index);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+ zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE);
/* Copy the whole inline data block */
- src_addr = inline_data_addr(ipage);
+ src_addr = inline_data_addr(inode, ipage);
dst_addr = kmap_atomic(page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
flush_dcache_page(page);
kunmap_atomic(dst_addr);
if (!PageUptodate(page))
SetPageUptodate(page);
}
-bool truncate_inline_inode(struct page *ipage, u64 from)
+void f2fs_truncate_inline_inode(struct inode *inode,
+ struct page *ipage, u64 from)
{
void *addr;
- if (from >= MAX_INLINE_DATA)
- return false;
+ if (from >= MAX_INLINE_DATA(inode))
+ return;
- addr = inline_data_addr(ipage);
+ addr = inline_data_addr(inode, ipage);
- f2fs_wait_on_page_writeback(ipage, NODE, true);
- memset(addr + from, 0, MAX_INLINE_DATA - from);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+ memset(addr + from, 0, MAX_INLINE_DATA(inode) - from);
set_page_dirty(ipage);
- return true;
+
+ if (from == 0)
+ clear_inode_flag(inode, FI_DATA_EXIST);
}
int f2fs_read_inline_data(struct inode *inode, struct page *page)
{
struct page *ipage;
- ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ if (trace_android_fs_dataread_start_enabled()) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ inode);
+ trace_android_fs_dataread_start(inode, page_offset(page),
+ PAGE_SIZE, current->pid,
+ path, current->comm);
+ }
+
+ ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
+ trace_android_fs_dataread_end(inode, page_offset(page),
+ PAGE_SIZE);
unlock_page(page);
return PTR_ERR(ipage);
}
if (!f2fs_has_inline_data(inode)) {
f2fs_put_page(ipage, 1);
+ trace_android_fs_dataread_end(inode, page_offset(page),
+ PAGE_SIZE);
return -EAGAIN;
}
if (page->index)
zero_user_segment(page, 0, PAGE_SIZE);
else
- read_inline_data(page, ipage);
+ f2fs_do_read_inline_data(page, ipage);
if (!PageUptodate(page))
SetPageUptodate(page);
f2fs_put_page(ipage, 1);
+ trace_android_fs_dataread_end(inode, page_offset(page),
+ PAGE_SIZE);
unlock_page(page);
return 0;
}
@@ -109,12 +129,15 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
+ .ino = dn->inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
- .op_flags = WRITE_SYNC | REQ_PRIO,
+ .op_flags = REQ_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
+ .io_type = FS_DATA_IO,
};
+ struct node_info ni;
int dirty, err;
if (!f2fs_exist_data(dn->inode))
@@ -124,6 +147,14 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
if (err)
return err;
+ err = f2fs_get_node_info(fio.sbi, dn->nid, &ni);
+ if (err) {
+ f2fs_put_dnode(dn);
+ return err;
+ }
+
+ fio.version = ni.version;
+
if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
f2fs_put_dnode(dn);
set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
@@ -136,7 +167,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
- read_inline_data(page, dn->inode_page);
+ f2fs_do_read_inline_data(page, dn->inode_page);
set_page_dirty(page);
/* clear dirty state */
@@ -144,21 +175,25 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
/* write data page to try to make data consistent */
set_page_writeback(page);
+ ClearPageError(page);
fio.old_blkaddr = dn->data_blkaddr;
- write_data_page(dn, &fio);
- f2fs_wait_on_page_writeback(page, DATA, true);
- if (dirty)
+ set_inode_flag(dn->inode, FI_HOT_DATA);
+ f2fs_outplace_write_data(dn, &fio);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+ if (dirty) {
inode_dec_dirty_pages(dn->inode);
+ f2fs_remove_dirty_inode(dn->inode);
+ }
/* this converted inline_data should be recovered. */
set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
- truncate_inline_inode(dn->inode_page, 0);
+ f2fs_truncate_inline_inode(dn->inode, dn->inode_page, 0);
clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
- f2fs_clear_inline_inode(dn->inode);
+ clear_inode_flag(dn->inode, FI_INLINE_DATA);
f2fs_put_dnode(dn);
return 0;
}
@@ -179,7 +214,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
f2fs_lock_op(sbi);
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
@@ -208,7 +243,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
@@ -219,13 +254,15 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
f2fs_bug_on(F2FS_I_SB(inode), page->index);
- f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
+ f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true);
src_addr = kmap_atomic(page);
- dst_addr = inline_data_addr(dn.inode_page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ dst_addr = inline_data_addr(inode, dn.inode_page);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
+ f2fs_clear_radix_tree_dirty_tag(page);
+
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
@@ -234,7 +271,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
return 0;
}
-bool recover_inline_data(struct inode *inode, struct page *npage)
+bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
@@ -255,14 +292,14 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
if (f2fs_has_inline_data(inode) &&
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
- f2fs_wait_on_page_writeback(ipage, NODE, true);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
- src_addr = inline_data_addr(npage);
- dst_addr = inline_data_addr(ipage);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ src_addr = inline_data_addr(inode, npage);
+ dst_addr = inline_data_addr(inode, ipage);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
set_inode_flag(inode, FI_INLINE_DATA);
set_inode_flag(inode, FI_DATA_EXIST);
@@ -273,32 +310,31 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
}
if (f2fs_has_inline_data(inode)) {
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
- if (!truncate_inline_inode(ipage, 0))
- return false;
- f2fs_clear_inline_inode(inode);
+ f2fs_truncate_inline_inode(inode, ipage, 0);
+ clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
- if (truncate_blocks(inode, 0, false))
+ if (f2fs_truncate_blocks(inode, 0, false))
return false;
goto process_inline;
}
return false;
}
-struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
- struct f2fs_inline_dentry *inline_dentry;
struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
struct page *ipage;
+ void *inline_dentry;
f2fs_hash_t namehash;
- ipage = get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
*res_page = ipage;
return NULL;
@@ -306,10 +342,10 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
namehash = f2fs_dentry_hash(&name, fname);
- inline_dentry = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(dir, ipage);
- make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
- de = find_target_dentry(fname, namehash, NULL, &d);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+ de = f2fs_find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
*res_page = ipage;
@@ -319,22 +355,22 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
return de;
}
-int make_empty_inline_dir(struct inode *inode, struct inode *parent,
+int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
- struct f2fs_inline_dentry *dentry_blk;
struct f2fs_dentry_ptr d;
+ void *inline_dentry;
- dentry_blk = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(inode, ipage);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
- do_make_empty_dir(inode, parent, &d);
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
+ f2fs_do_make_empty_dir(inode, parent, &d);
set_page_dirty(ipage);
/* update i_size to MAX_INLINE_DATA */
- if (i_size_read(inode) < MAX_INLINE_DATA)
- f2fs_i_size_write(inode, MAX_INLINE_DATA);
+ if (i_size_read(inode) < MAX_INLINE_DATA(inode))
+ f2fs_i_size_write(inode, MAX_INLINE_DATA(inode));
return 0;
}
@@ -343,11 +379,12 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* release ipage in this function.
*/
static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dentry_ptr src, dst;
int err;
page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
@@ -372,34 +409,31 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
goto out;
}
- f2fs_wait_on_page_writeback(page, DATA, true);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
- dentry_blk = kmap_atomic(page);
+ dentry_blk = page_address(page);
+
+ make_dentry_ptr_inline(dir, &src, inline_dentry);
+ make_dentry_ptr_block(dir, &dst, dentry_blk);
/* copy data from inline dentry block to new dentry block */
- memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
- INLINE_DENTRY_BITMAP_SIZE);
- memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
- SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
+ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap);
+ memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap);
/*
* we do not need to zero out remainder part of dentry and filename
* field, since we have used bitmap for marking the usage status of
* them, besides, we can also ignore copying/zeroing reserved space
* of dentry block, because them haven't been used so far.
*/
- memcpy(dentry_blk->dentry, inline_dentry->dentry,
- sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
- memcpy(dentry_blk->filename, inline_dentry->filename,
- NR_INLINE_DENTRY * F2FS_SLOT_LEN);
+ memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max);
+ memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN);
- kunmap_atomic(dentry_blk);
if (!PageUptodate(page))
SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
- truncate_inline_inode(ipage, 0);
+ f2fs_truncate_inline_inode(dir, ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
@@ -412,14 +446,13 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
return err;
}
-static int f2fs_add_inline_entries(struct inode *dir,
- struct f2fs_inline_dentry *inline_dentry)
+static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
{
struct f2fs_dentry_ptr d;
unsigned long bit_pos = 0;
int err = 0;
- make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
while (bit_pos < d.max) {
struct f2fs_dir_entry *de;
@@ -440,10 +473,10 @@ static int f2fs_add_inline_entries(struct inode *dir,
}
new_name.name = d.filename[bit_pos];
- new_name.len = de->name_len;
+ new_name.len = le16_to_cpu(de->name_len);
ino = le32_to_cpu(de->ino);
- fake_mode = get_de_type(de) << S_SHIFT;
+ fake_mode = f2fs_get_de_type(de) << S_SHIFT;
err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
ino, fake_mode);
@@ -455,26 +488,26 @@ static int f2fs_add_inline_entries(struct inode *dir,
return 0;
punch_dentry_pages:
truncate_inode_pages(&dir->i_data, 0);
- truncate_blocks(dir, 0, false);
- remove_dirty_inode(dir);
+ f2fs_truncate_blocks(dir, 0, false);
+ f2fs_remove_dirty_inode(dir);
return err;
}
static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
- struct f2fs_inline_dentry *backup_dentry;
+ void *backup_dentry;
int err;
backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
- sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO);
+ MAX_INLINE_DATA(dir), GFP_F2FS_ZERO);
if (!backup_dentry) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
}
- memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
- truncate_inline_inode(ipage, 0);
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir));
+ f2fs_truncate_inline_inode(dir, ipage, 0);
unlock_page(ipage);
@@ -486,22 +519,23 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
- kfree(backup_dentry);
+ kvfree(backup_dentry);
return 0;
recover:
lock_page(ipage);
- memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir));
f2fs_i_depth_write(dir, 0);
- f2fs_i_size_write(dir, MAX_INLINE_DATA);
+ f2fs_i_size_write(dir, MAX_INLINE_DATA(dir));
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
- kfree(backup_dentry);
+ kvfree(backup_dentry);
return err;
}
static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
if (!F2FS_I(dir)->i_dir_level)
return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
@@ -517,21 +551,22 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
struct page *ipage;
unsigned int bit_pos;
f2fs_hash_t name_hash;
- struct f2fs_inline_dentry *dentry_blk = NULL;
+ void *inline_dentry = NULL;
struct f2fs_dentry_ptr d;
int slots = GET_DENTRY_SLOTS(new_name->len);
struct page *page = NULL;
int err = 0;
- ipage = get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
- dentry_blk = inline_data_addr(ipage);
- bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
- slots, NR_INLINE_DENTRY);
- if (bit_pos >= NR_INLINE_DENTRY) {
- err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
+ inline_dentry = inline_data_addr(dir, ipage);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
+ if (bit_pos >= d.max) {
+ err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
if (err)
return err;
err = -EAGAIN;
@@ -540,20 +575,17 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, new_name,
+ page = f2fs_init_inode_metadata(inode, dir, new_name,
orig_name, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
- if (f2fs_encrypted_inode(dir))
- file_set_enc_name(inode);
}
- f2fs_wait_on_page_writeback(ipage, NODE, true);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
name_hash = f2fs_dentry_hash(new_name, NULL);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
set_page_dirty(ipage);
@@ -564,7 +596,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
f2fs_put_page(page, 1);
}
- update_parent_metadata(dir, inode, 0);
+ f2fs_update_parent_metadata(dir, inode, 0);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
@@ -576,25 +608,27 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode)
{
- struct f2fs_inline_dentry *inline_dentry;
+ struct f2fs_dentry_ptr d;
+ void *inline_dentry;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
unsigned int bit_pos;
int i;
lock_page(page);
- f2fs_wait_on_page_writeback(page, NODE, true);
+ f2fs_wait_on_page_writeback(page, NODE, true, true);
- inline_dentry = inline_data_addr(page);
- bit_pos = dentry - inline_dentry->dentry;
+ inline_dentry = inline_data_addr(dir, page);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = dentry - d.dentry;
for (i = 0; i < slots; i++)
- __clear_bit_le(bit_pos + i,
- &inline_dentry->dentry_bitmap);
+ __clear_bit_le(bit_pos + i, d.bitmap);
set_page_dirty(page);
f2fs_put_page(page, 1);
dir->i_ctime = dir->i_mtime = current_time(dir);
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
if (inode)
f2fs_drop_nlink(dir, inode);
@@ -605,20 +639,21 @@ bool f2fs_empty_inline_dir(struct inode *dir)
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos = 2;
- struct f2fs_inline_dentry *dentry_blk;
+ void *inline_dentry;
+ struct f2fs_dentry_ptr d;
- ipage = get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
- dentry_blk = inline_data_addr(ipage);
- bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
- NR_INLINE_DENTRY,
- bit_pos);
+ inline_dentry = inline_data_addr(dir, ipage);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos);
f2fs_put_page(ipage, 1);
- if (bit_pos < NR_INLINE_DENTRY)
+ if (bit_pos < d.max)
return false;
return true;
@@ -628,26 +663,36 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr)
{
struct inode *inode = file_inode(file);
- struct f2fs_inline_dentry *inline_dentry = NULL;
struct page *ipage = NULL;
struct f2fs_dentry_ptr d;
+ void *inline_dentry = NULL;
+ int err;
- if (ctx->pos == NR_INLINE_DENTRY)
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
+
+ if (ctx->pos == d.max)
return 0;
- ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
- inline_dentry = inline_data_addr(ipage);
+ /*
+ * f2fs_readdir was protected by inode.i_rwsem, it is safe to access
+ * ipage without page's lock held.
+ */
+ unlock_page(ipage);
- make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
+ inline_dentry = inline_data_addr(inode, ipage);
- if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
- ctx->pos = NR_INLINE_DENTRY;
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
- f2fs_put_page(ipage, 1);
- return 0;
+ err = f2fs_fill_dentries(ctx, &d, 0, fstr);
+ if (!err)
+ ctx->pos = d.max;
+
+ f2fs_put_page(ipage, 0);
+ return err < 0 ? err : 0;
}
int f2fs_inline_data_fiemap(struct inode *inode,
@@ -660,7 +705,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
struct page *ipage;
int err = 0;
- ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -669,16 +714,20 @@ int f2fs_inline_data_fiemap(struct inode *inode,
goto out;
}
- ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
+ ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode));
if (start >= ilen)
goto out;
if (start + len < ilen)
ilen = start + len;
ilen -= start;
- get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+ err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+ if (err)
+ goto out;
+
byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
- byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
+ byteaddr += (char *)inline_data_addr(inode, ipage) -
+ (char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
out:
f2fs_put_page(ipage, 1);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index c56d04e..3cb80e6 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/inode.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -16,13 +13,19 @@
#include "f2fs.h"
#include "node.h"
+#include "segment.h"
+#include "xattr.h"
#include <trace/events/f2fs.h>
-void f2fs_mark_inode_dirty_sync(struct inode *inode)
+void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
{
- if (f2fs_inode_dirtied(inode))
+ if (is_inode_flag_set(inode, FI_NEW_INODE))
return;
+
+ if (f2fs_inode_dirtied(inode, sync))
+ return;
+
mark_inode_dirty_sync(inode);
}
@@ -31,38 +34,42 @@ void f2fs_set_inode_flags(struct inode *inode)
unsigned int flags = F2FS_I(inode)->i_flags;
unsigned int new_fl = 0;
- if (flags & FS_SYNC_FL)
+ if (flags & F2FS_SYNC_FL)
new_fl |= S_SYNC;
- if (flags & FS_APPEND_FL)
+ if (flags & F2FS_APPEND_FL)
new_fl |= S_APPEND;
- if (flags & FS_IMMUTABLE_FL)
+ if (flags & F2FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
- if (flags & FS_NOATIME_FL)
+ if (flags & F2FS_NOATIME_FL)
new_fl |= S_NOATIME;
- if (flags & FS_DIRSYNC_FL)
+ if (flags & F2FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
+ if (f2fs_encrypted_inode(inode))
+ new_fl |= S_ENCRYPTED;
inode_set_flags(inode, new_fl,
- S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
- f2fs_mark_inode_dirty_sync(inode);
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|
+ S_ENCRYPTED);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
+ int extra_size = get_extra_isize(inode);
+
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
- if (ri->i_addr[0])
- inode->i_rdev =
- old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+ if (ri->i_addr[extra_size])
+ inode->i_rdev = old_decode_dev(
+ le32_to_cpu(ri->i_addr[extra_size]));
else
- inode->i_rdev =
- new_decode_dev(le32_to_cpu(ri->i_addr[1]));
+ inode->i_rdev = new_decode_dev(
+ le32_to_cpu(ri->i_addr[extra_size + 1]));
}
}
static int __written_first_block(struct f2fs_sb_info *sbi,
struct f2fs_inode *ri)
{
- block_t addr = le32_to_cpu(ri->i_addr[0]);
+ block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);
if (!__is_valid_data_blkaddr(addr))
return 1;
@@ -73,29 +80,31 @@ static int __written_first_block(struct f2fs_sb_info *sbi,
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
+ int extra_size = get_extra_isize(inode);
+
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
- ri->i_addr[0] =
+ ri->i_addr[extra_size] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
- ri->i_addr[1] = 0;
+ ri->i_addr[extra_size + 1] = 0;
} else {
- ri->i_addr[0] = 0;
- ri->i_addr[1] =
+ ri->i_addr[extra_size] = 0;
+ ri->i_addr[extra_size + 1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
- ri->i_addr[2] = 0;
+ ri->i_addr[extra_size + 2] = 0;
}
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
- void *inline_data = inline_data_addr(ipage);
+ void *inline_data = inline_data_addr(inode, ipage);
__le32 *start = inline_data;
- __le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
+ __le32 *end = start + MAX_INLINE_DATA(inode) / sizeof(__le32);
while (start < end) {
if (*start++) {
- f2fs_wait_on_page_writeback(ipage, NODE, true);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
set_inode_flag(inode, FI_DATA_EXIST);
set_raw_inline(inode, F2FS_INODE(ipage));
@@ -106,9 +115,88 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
return;
}
+static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri = &F2FS_NODE(page)->i;
+
+ if (!f2fs_sb_has_inode_chksum(sbi))
+ return false;
+
+ if (!IS_INODE(page) || !(ri->i_inline & F2FS_EXTRA_ATTR))
+ return false;
+
+ if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
+ i_inode_checksum))
+ return false;
+
+ return true;
+}
+
+static __u32 f2fs_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_node *node = F2FS_NODE(page);
+ struct f2fs_inode *ri = &node->i;
+ __le32 ino = node->footer.ino;
+ __le32 gen = ri->i_generation;
+ __u32 chksum, chksum_seed;
+ __u32 dummy_cs = 0;
+ unsigned int offset = offsetof(struct f2fs_inode, i_inode_checksum);
+ unsigned int cs_size = sizeof(dummy_cs);
+
+ chksum = f2fs_chksum(sbi, sbi->s_chksum_seed, (__u8 *)&ino,
+ sizeof(ino));
+ chksum_seed = f2fs_chksum(sbi, chksum, (__u8 *)&gen, sizeof(gen));
+
+ chksum = f2fs_chksum(sbi, chksum_seed, (__u8 *)ri, offset);
+ chksum = f2fs_chksum(sbi, chksum, (__u8 *)&dummy_cs, cs_size);
+ offset += cs_size;
+ chksum = f2fs_chksum(sbi, chksum, (__u8 *)ri + offset,
+ F2FS_BLKSIZE - offset);
+ return chksum;
+}
+
+bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri;
+ __u32 provided, calculated;
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)))
+ return true;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (!f2fs_enable_inode_chksum(sbi, page))
+#else
+ if (!f2fs_enable_inode_chksum(sbi, page) ||
+ PageDirty(page) || PageWriteback(page))
+#endif
+ return true;
+
+ ri = &F2FS_NODE(page)->i;
+ provided = le32_to_cpu(ri->i_inode_checksum);
+ calculated = f2fs_inode_chksum(sbi, page);
+
+ if (provided != calculated)
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "checksum invalid, ino = %x, %x vs. %x",
+ ino_of_node(page), provided, calculated);
+
+ return provided == calculated;
+}
+
+void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri = &F2FS_NODE(page)->i;
+
+ if (!f2fs_enable_inode_chksum(sbi, page))
+ return;
+
+ ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
+}
+
static bool sanity_check_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned long long iblocks;
iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
@@ -131,6 +219,50 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
+ if (f2fs_sb_has_flexible_inline_xattr(sbi)
+ && !f2fs_has_extra_attr(inode)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: corrupted inode ino=%lx, run fsck to fix.",
+ __func__, inode->i_ino);
+ return false;
+ }
+
+ if (f2fs_has_extra_attr(inode) &&
+ !f2fs_sb_has_extra_attr(sbi)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx) is with extra_attr, "
+ "but extra_attr feature is off",
+ __func__, inode->i_ino);
+ return false;
+ }
+
+ if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE ||
+ fi->i_extra_isize % sizeof(__le32)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, "
+ "max: %zu",
+ __func__, inode->i_ino, fi->i_extra_isize,
+ F2FS_TOTAL_EXTRA_ATTR_SIZE);
+ return false;
+ }
+
+ if (f2fs_has_extra_attr(inode) &&
+ f2fs_sb_has_flexible_inline_xattr(sbi) &&
+ f2fs_has_inline_xattr(inode) &&
+ (!fi->i_inline_xattr_size ||
+ fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx) has corrupted "
+ "i_inline_xattr_size: %d, max: %zu",
+ __func__, inode->i_ino, fi->i_inline_xattr_size,
+ MAX_INLINE_XATTR_SIZE);
+ return false;
+ }
+
if (F2FS_I(inode)->extent_tree) {
struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
@@ -147,6 +279,26 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
}
+
+ if (f2fs_has_inline_data(inode) &&
+ (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx, mode=%u) should not have "
+ "inline_data, run fsck to fix",
+ __func__, inode->i_ino, inode->i_mode);
+ return false;
+ }
+
+ if (f2fs_has_inline_dentry(inode) && !S_ISDIR(inode->i_mode)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx, mode=%u) should not have "
+ "inline_dentry, run fsck to fix",
+ __func__, inode->i_ino, inode->i_mode);
+ return false;
+ }
+
return true;
}
@@ -156,17 +308,14 @@ static int do_read_inode(struct inode *inode)
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
+ projid_t i_projid;
int err;
/* Check if ino is within scope */
- if (check_nid_range(sbi, inode->i_ino)) {
- f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
- (unsigned long) inode->i_ino);
- WARN_ON(1);
+ if (f2fs_check_nid_range(sbi, inode->i_ino))
return -EINVAL;
- }
- node_page = get_node_page(sbi, inode->i_ino);
+ node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@@ -177,7 +326,7 @@ static int do_read_inode(struct inode *inode)
i_gid_write(inode, le32_to_cpu(ri->i_gid));
set_nlink(inode, le32_to_cpu(ri->i_links));
inode->i_size = le64_to_cpu(ri->i_size);
- inode->i_blocks = le64_to_cpu(ri->i_blocks);
+ inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1);
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
@@ -186,8 +335,11 @@ static int do_read_inode(struct inode *inode)
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
-
- fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
+ if (S_ISDIR(inode->i_mode))
+ fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
+ else if (S_ISREG(inode->i_mode))
+ fi->i_gc_failures[GC_FAILURE_PIN] =
+ le16_to_cpu(ri->i_gc_failures);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
@@ -200,6 +352,25 @@ static int do_read_inode(struct inode *inode)
get_inline_info(inode, ri);
+ fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
+ le16_to_cpu(ri->i_extra_isize) : 0;
+
+ if (f2fs_sb_has_flexible_inline_xattr(sbi)) {
+ fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
+ } else if (f2fs_has_inline_xattr(inode) ||
+ f2fs_has_inline_dentry(inode)) {
+ fi->i_inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+ } else {
+
+ /*
+ * Previous inline data or directory always reserved 200 bytes
+ * in inode layout, even if inline_xattr is disabled. In order
+ * to keep inline_dentry's structure for backward compatibility,
+ * we get the space back only from inline_data.
+ */
+ fi->i_inline_xattr_size = 0;
+ }
+
if (!sanity_check_inode(inode, node_page)) {
f2fs_put_page(node_page, 1);
return -EINVAL;
@@ -209,20 +380,48 @@ static int do_read_inode(struct inode *inode)
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
+ /* try to recover cold bit for non-dir inode */
+ if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) {
+ set_cold_node(node_page, false);
+ set_page_dirty(node_page);
+ }
+
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
- err = __written_first_block(sbi, ri);
- if (err < 0) {
- f2fs_put_page(node_page, 1);
- return err;
+ if (S_ISREG(inode->i_mode)) {
+ err = __written_first_block(sbi, ri);
+ if (err < 0) {
+ f2fs_put_page(node_page, 1);
+ return err;
+ }
+ if (!err)
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
}
- if (!err)
- set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
- if (!need_inode_block_update(sbi, inode->i_ino))
+ if (!f2fs_need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
+ if (fi->i_flags & F2FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi) &&
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid))
+ i_projid = (projid_t)le32_to_cpu(ri->i_projid);
+ else
+ i_projid = F2FS_DEF_PROJID;
+ fi->i_projid = make_kprojid(&init_user_ns, i_projid);
+
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_inode_crtime(sbi) &&
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
+ fi->i_crtime.tv_sec = le64_to_cpu(ri->i_crtime);
+ fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
+ }
+
+ F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
+ F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
+ F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
+ F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -255,10 +454,10 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
- mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+ mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
- mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+ mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
@@ -267,7 +466,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
- mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
+ inode_nohighmem(inode);
} else if (S_ISLNK(inode->i_mode)) {
if (f2fs_encrypted_inode(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
@@ -283,6 +482,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
ret = -EIO;
goto bad_inode;
}
+ f2fs_set_inode_flags(inode);
unlock_new_inode(inode);
trace_f2fs_iget(inode);
return inode;
@@ -308,14 +508,16 @@ struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
return inode;
}
-int update_inode(struct inode *inode, struct page *node_page)
+void f2fs_update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
+
+ f2fs_wait_on_page_writeback(node_page, NODE, true, true);
+ set_page_dirty(node_page);
f2fs_inode_synced(inode);
- f2fs_wait_on_page_writeback(node_page, NODE, true);
-
ri = F2FS_INODE(node_page);
ri->i_mode = cpu_to_le16(inode->i_mode);
@@ -324,13 +526,15 @@ int update_inode(struct inode *inode, struct page *node_page)
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
- ri->i_blocks = cpu_to_le64(inode->i_blocks);
+ ri->i_blocks = cpu_to_le64(SECTOR_TO_BLOCK(inode->i_blocks) + 1);
- if (F2FS_I(inode)->extent_tree)
- set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
- &ri->i_ext);
- else
+ if (et) {
+ read_lock(&et->lock);
+ set_raw_extent(&et->largest, &ri->i_ext);
+ read_unlock(&et->lock);
+ } else {
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
+ }
set_raw_inline(inode, ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
@@ -339,30 +543,67 @@ int update_inode(struct inode *inode, struct page *node_page)
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
- ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
+ if (S_ISDIR(inode->i_mode))
+ ri->i_current_depth =
+ cpu_to_le32(F2FS_I(inode)->i_current_depth);
+ else if (S_ISREG(inode->i_mode))
+ ri->i_gc_failures =
+ cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
ri->i_dir_level = F2FS_I(inode)->i_dir_level;
+ if (f2fs_has_extra_attr(inode)) {
+ ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
+
+ if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)))
+ ri->i_inline_xattr_size =
+ cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
+
+ if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
+ F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+ i_projid)) {
+ projid_t i_projid;
+
+ i_projid = from_kprojid(&init_user_ns,
+ F2FS_I(inode)->i_projid);
+ ri->i_projid = cpu_to_le32(i_projid);
+ }
+
+ if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
+ F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+ i_crtime)) {
+ ri->i_crtime =
+ cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
+ ri->i_crtime_nsec =
+ cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
+ }
+ }
+
__set_inode_rdev(inode, ri);
- set_cold_node(inode, node_page);
/* deleted inode */
if (inode->i_nlink == 0)
clear_inline_node(node_page);
- return set_page_dirty(node_page);
+ F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
+ F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
+ F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
+ F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page);
+#endif
}
-int update_inode_page(struct inode *inode)
+void f2fs_update_inode_page(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
- int ret = 0;
retry:
- node_page = get_node_page(sbi, inode->i_ino);
+ node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
int err = PTR_ERR(node_page);
if (err == -ENOMEM) {
@@ -371,12 +612,10 @@ int update_inode_page(struct inode *inode)
} else if (err != -ENOENT) {
f2fs_stop_checkpoint(sbi, false);
}
- f2fs_inode_synced(inode);
- return 0;
+ return;
}
- ret = update_inode(inode, node_page);
+ f2fs_update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
- return ret;
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -390,11 +629,15 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
+ if (f2fs_is_checkpoint_ready(sbi))
+ return -ENOSPC;
+
/*
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
- if (update_inode_page(inode))
+ f2fs_update_inode_page(inode);
+ if (wbc && wbc->nr_to_write)
f2fs_balance_fs(sbi, true);
return 0;
}
@@ -410,7 +653,7 @@ void f2fs_evict_inode(struct inode *inode)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- drop_inmem_pages(inode);
+ f2fs_drop_inmem_pages(inode);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
@@ -420,17 +663,22 @@ void f2fs_evict_inode(struct inode *inode)
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
- remove_dirty_inode(inode);
+ f2fs_remove_dirty_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_EVICT_INODE))
- goto no_delete;
-#endif
+ err = dquot_initialize(inode);
+ if (err) {
+ err = 0;
+ set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+ }
+
+ f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
+ f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+ f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
@@ -439,10 +687,17 @@ void f2fs_evict_inode(struct inode *inode)
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
+ if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+ f2fs_show_injection_info(FAULT_EVICT_INODE);
+ err = -EIO;
+ }
+
if (!err) {
f2fs_lock_op(sbi);
- err = remove_inode_page(inode);
+ err = f2fs_remove_inode_page(inode);
f2fs_unlock_op(sbi);
+ if (err == -ENOENT)
+ err = 0;
}
/* give more chances, if ENOMEM case */
@@ -451,37 +706,70 @@ void f2fs_evict_inode(struct inode *inode)
goto retry;
}
- if (err)
- update_inode_page(inode);
+ if (err) {
+ f2fs_update_inode_page(inode);
+ set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+ }
sb_end_intwrite(inode->i_sb);
no_delete:
+ dquot_drop(inode);
+
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
- invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
+ if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
+ else
+ f2fs_inode_synced(inode);
+
+ /* ino == 0, if f2fs_new_inode() was failed t*/
+ if (inode->i_ino)
+ invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
+ inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
- if (is_inode_flag_set(inode, FI_APPEND_WRITE))
- add_ino_entry(sbi, inode->i_ino, APPEND_INO);
- if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
- add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
- if (is_inode_flag_set(inode, FI_FREE_NID)) {
- alloc_nid_failed(sbi, inode->i_ino);
- clear_inode_flag(inode, FI_FREE_NID);
+ if (inode->i_nlink) {
+ if (is_inode_flag_set(inode, FI_APPEND_WRITE))
+ f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO);
+ if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
+ f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
}
- f2fs_bug_on(sbi, err &&
- !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
+ if (is_inode_flag_set(inode, FI_FREE_NID)) {
+ f2fs_alloc_nid_failed(sbi, inode->i_ino);
+ clear_inode_flag(inode, FI_FREE_NID);
+ } else {
+ /*
+ * If xattr nid is corrupted, we can reach out error condition,
+ * err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
+ * In that case, f2fs_check_nid_range() is enough to give a clue.
+ */
+ }
out_clear:
- fscrypt_put_encryption_info(inode, NULL);
+ fscrypt_put_encryption_info(inode);
clear_inode(inode);
}
/* caller should call f2fs_lock_op() */
-void handle_failed_inode(struct inode *inode)
+void f2fs_handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct node_info ni;
+ int err;
+
+ /*
+ * clear nlink of inode in order to release resource of inode
+ * immediately.
+ */
+ clear_nlink(inode);
+
+ /*
+ * we must call this to avoid inode being remained as dirty, resulting
+ * in a panic when flushing dirty inodes in gdirty_list.
+ */
+ f2fs_update_inode_page(inode);
+ f2fs_inode_synced(inode);
/* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
@@ -491,22 +779,29 @@ void handle_failed_inode(struct inode *inode)
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
- get_node_info(sbi, inode->i_ino, &ni);
+ err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+ if (err) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "May loss orphan inode, run fsck to fix.");
+ goto out;
+ }
if (ni.blk_addr != NULL_ADDR) {
- int err = acquire_orphan_inode(sbi);
+ err = f2fs_acquire_orphan_inode(sbi);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"Too many orphan inodes, run fsck to fix.");
} else {
- add_orphan_inode(inode);
+ f2fs_add_orphan_inode(inode);
}
- alloc_nid_done(sbi, inode->i_ino);
+ f2fs_alloc_nid_done(sbi, inode->i_ino);
} else {
set_inode_flag(inode, FI_FREE_NID);
}
+out:
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index ce09573..331ff8b 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -1,23 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/namei.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/ctype.h>
+#include <linux/random.h>
#include <linux/dcache.h>
#include <linux/namei.h>
+#include <linux/quotaops.h>
#include "f2fs.h"
#include "node.h"
+#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include <trace/events/f2fs.h>
@@ -28,6 +28,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
nid_t ino;
struct inode *inode;
bool nid_free = false;
+ int xattr_size = 0;
int err;
inode = new_inode(dir->i_sb);
@@ -35,46 +36,91 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
return ERR_PTR(-ENOMEM);
f2fs_lock_op(sbi);
- if (!alloc_nid(sbi, &ino)) {
+ if (!f2fs_alloc_nid(sbi, &ino)) {
f2fs_unlock_op(sbi);
err = -ENOSPC;
goto fail;
}
f2fs_unlock_op(sbi);
+ nid_free = true;
+
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
- inode->i_generation = sbi->s_next_generation++;
+ inode->i_mtime = inode->i_atime = inode->i_ctime =
+ F2FS_I(inode)->i_crtime = current_time(inode);
+ inode->i_generation = prandom_u32();
+
+ if (S_ISDIR(inode->i_mode))
+ F2FS_I(inode)->i_current_depth = 1;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
- nid_free = true;
goto fail;
}
- /* If the directory encrypted, then we should encrypt the inode. */
- if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
- f2fs_set_encrypted_inode(inode);
+ if (f2fs_sb_has_project_quota(sbi) &&
+ (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL))
+ F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
+ else
+ F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
+ F2FS_DEF_PROJID);
+
+ err = dquot_initialize(inode);
+ if (err)
+ goto fail_drop;
set_inode_flag(inode, FI_NEW_INODE);
+ /* If the directory encrypted, then we should encrypt the inode. */
+ if ((f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) &&
+ f2fs_may_encrypt(inode))
+ f2fs_set_encrypted_inode(inode);
+
+ if (f2fs_sb_has_extra_attr(sbi)) {
+ set_inode_flag(inode, FI_EXTRA_ATTR);
+ F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
+ }
+
if (test_opt(sbi, INLINE_XATTR))
set_inode_flag(inode, FI_INLINE_XATTR);
+
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
set_inode_flag(inode, FI_INLINE_DATA);
if (f2fs_may_inline_dentry(inode))
set_inode_flag(inode, FI_INLINE_DENTRY);
+ if (f2fs_sb_has_flexible_inline_xattr(sbi)) {
+ f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+ if (f2fs_has_inline_xattr(inode))
+ xattr_size = F2FS_OPTION(sbi).inline_xattr_size;
+ /* Otherwise, will be 0 */
+ } else if (f2fs_has_inline_xattr(inode) ||
+ f2fs_has_inline_dentry(inode)) {
+ xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+ }
+ F2FS_I(inode)->i_inline_xattr_size = xattr_size;
+
f2fs_init_extent_tree(inode, NULL);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
+ F2FS_I(inode)->i_flags =
+ f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
+
+ if (S_ISDIR(inode->i_mode))
+ F2FS_I(inode)->i_flags |= F2FS_INDEX_FL;
+
+ if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
+ f2fs_set_inode_flags(inode);
+
trace_f2fs_new_inode(inode, 0);
return inode;
@@ -85,9 +131,19 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
set_inode_flag(inode, FI_FREE_NID);
iput(inode);
return ERR_PTR(err);
+fail_drop:
+ trace_f2fs_new_inode(inode, err);
+ dquot_drop(inode);
+ inode->i_flags |= S_NOQUOTA;
+ if (nid_free)
+ set_inode_flag(inode, FI_FREE_NID);
+ clear_nlink(inode);
+ unlock_new_inode(inode);
+ iput(inode);
+ return ERR_PTR(err);
}
-static int is_multimedia_file(const unsigned char *s, const char *sub)
+static int is_extension_exist(const unsigned char *s, const char *sub)
{
size_t slen = strlen(s);
size_t sublen = strlen(sub);
@@ -113,19 +169,97 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
/*
* Set multimedia files as cold files for hot/cold data separation
*/
-static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode,
+static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode,
const unsigned char *name)
{
- int i;
- __u8 (*extlist)[8] = sbi->raw_super->extension_list;
+ __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
+ int i, cold_count, hot_count;
- int count = le32_to_cpu(sbi->raw_super->extension_count);
- for (i = 0; i < count; i++) {
- if (is_multimedia_file(name, extlist[i])) {
- file_set_cold(inode);
+ down_read(&sbi->sb_lock);
+
+ cold_count = le32_to_cpu(sbi->raw_super->extension_count);
+ hot_count = sbi->raw_super->hot_ext_count;
+
+ for (i = 0; i < cold_count + hot_count; i++) {
+ if (is_extension_exist(name, extlist[i]))
break;
- }
}
+
+ up_read(&sbi->sb_lock);
+
+ if (i == cold_count + hot_count)
+ return;
+
+ if (i < cold_count)
+ file_set_cold(inode);
+ else
+ file_set_hot(inode);
+}
+
+int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
+ bool hot, bool set)
+{
+ __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
+ int cold_count = le32_to_cpu(sbi->raw_super->extension_count);
+ int hot_count = sbi->raw_super->hot_ext_count;
+ int total_count = cold_count + hot_count;
+ int start, count;
+ int i;
+
+ if (set) {
+ if (total_count == F2FS_MAX_EXTENSION)
+ return -EINVAL;
+ } else {
+ if (!hot && !cold_count)
+ return -EINVAL;
+ if (hot && !hot_count)
+ return -EINVAL;
+ }
+
+ if (hot) {
+ start = cold_count;
+ count = total_count;
+ } else {
+ start = 0;
+ count = cold_count;
+ }
+
+ for (i = start; i < count; i++) {
+ if (strcmp(name, extlist[i]))
+ continue;
+
+ if (set)
+ return -EINVAL;
+
+ memcpy(extlist[i], extlist[i + 1],
+ F2FS_EXTENSION_LEN * (total_count - i - 1));
+ memset(extlist[total_count - 1], 0, F2FS_EXTENSION_LEN);
+ if (hot)
+ sbi->raw_super->hot_ext_count = hot_count - 1;
+ else
+ sbi->raw_super->extension_count =
+ cpu_to_le32(cold_count - 1);
+ return 0;
+ }
+
+ if (!set)
+ return -EINVAL;
+
+ if (hot) {
+ memcpy(extlist[count], name, strlen(name));
+ sbi->raw_super->hot_ext_count = hot_count + 1;
+ } else {
+ char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];
+
+ memcpy(buf, &extlist[cold_count],
+ F2FS_EXTENSION_LEN * hot_count);
+ memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN);
+ memcpy(extlist[cold_count], name, strlen(name));
+ memcpy(&extlist[cold_count + 1], buf,
+ F2FS_EXTENSION_LEN * hot_count);
+ sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1);
+ }
+ return 0;
}
static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
@@ -136,35 +270,45 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
nid_t ino = 0;
int err;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
+
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
- set_cold_files(sbi, inode, dentry->d_name.name);
+ set_file_temperature(sbi, inode, dentry->d_name.name);
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
ino = inode->i_ino;
- f2fs_balance_fs(sbi, true);
-
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out;
f2fs_unlock_op(sbi);
- alloc_nid_done(sbi, ino);
+ f2fs_alloc_nid_done(sbi, ino);
d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
- handle_failed_inode(inode);
+ f2fs_handle_failed_inode(inode);
return err;
}
@@ -175,10 +319,25 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
- if (f2fs_encrypted_inode(dir) &&
- !fscrypt_has_permitted_context(dir, inode))
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
+
+ err = fscrypt_prepare_link(old_dentry, dir, dentry);
+ if (err)
+ return err;
+
+ if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
+ (!projid_eq(F2FS_I(dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)))
return -EXDEV;
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
f2fs_balance_fs(sbi, true);
inode->i_ctime = current_time(inode);
@@ -232,32 +391,33 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
return 0;
}
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
de = f2fs_find_entry(dir, &dot, &page);
if (de) {
- f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
} else {
- err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
+ err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
if (err)
goto out;
}
de = f2fs_find_entry(dir, &dotdot, &page);
- if (de) {
- f2fs_dentry_kunmap(dir, page);
+ if (de)
f2fs_put_page(page, 0);
- } else if (IS_ERR(page)) {
+ else if (IS_ERR(page))
err = PTR_ERR(page);
- } else {
- err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
- }
+ else
+ err = f2fs_do_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
out:
if (!err)
clear_inode_flag(dir, FI_INLINE_DOTS);
@@ -272,66 +432,70 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
struct page *page;
- nid_t ino;
+ struct dentry *new;
+ nid_t ino = -1;
int err = 0;
unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
- if (f2fs_encrypted_inode(dir)) {
- int res = fscrypt_get_encryption_info(dir);
+ trace_f2fs_lookup_start(dir, dentry, flags);
- /*
- * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
- * created while the directory was encrypted and we
- * don't have access to the key.
- */
- if (fscrypt_has_encryption_key(dir))
- fscrypt_set_encrypted_dentry(dentry);
- fscrypt_set_d_op(dentry);
- if (res && res != -ENOKEY)
- return ERR_PTR(res);
+ err = fscrypt_prepare_lookup(dir, dentry, flags);
+ if (err)
+ goto out;
+
+ if (dentry->d_name.len > F2FS_NAME_LEN) {
+ err = -ENAMETOOLONG;
+ goto out;
}
- if (dentry->d_name.len > F2FS_NAME_LEN)
- return ERR_PTR(-ENAMETOOLONG);
-
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de) {
- if (IS_ERR(page))
- return (struct dentry *)page;
- return d_splice_alias(inode, dentry);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto out;
+ }
+ goto out_splice;
}
ino = le32_to_cpu(de->ino);
- f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
inode = f2fs_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto out;
+ }
if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
err = __recover_dot_dentries(dir, root_ino);
if (err)
- goto err_out;
+ goto out_iput;
}
if (f2fs_has_inline_dots(inode)) {
err = __recover_dot_dentries(inode, dir->i_ino);
if (err)
- goto err_out;
+ goto out_iput;
}
- if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
- (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
- !fscrypt_has_permitted_context(dir, inode)) {
- bool nokey = f2fs_encrypted_inode(inode) &&
- !fscrypt_has_encryption_key(inode);
- err = nokey ? -ENOKEY : -EPERM;
- goto err_out;
+ if (f2fs_encrypted_inode(dir) &&
+ (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+ !fscrypt_has_permitted_context(dir, inode)) {
+ f2fs_msg(inode->i_sb, KERN_WARNING,
+ "Inconsistent encryption contexts: %lu/%lu",
+ dir->i_ino, inode->i_ino);
+ err = -EPERM;
+ goto out_iput;
}
- return d_splice_alias(inode, dentry);
-
-err_out:
+out_splice:
+ new = d_splice_alias(inode, dentry);
+ if (IS_ERR(new))
+ err = PTR_ERR(new);
+ trace_f2fs_lookup_end(dir, dentry, ino, err);
+ return new;
+out_iput:
iput(inode);
+out:
+ trace_f2fs_lookup_end(dir, dentry, ino, err);
return ERR_PTR(err);
}
@@ -345,6 +509,16 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
trace_f2fs_unlink_enter(dir, dentry);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de) {
if (IS_ERR(page))
@@ -355,10 +529,9 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
- err = acquire_orphan_inode(sbi);
+ err = f2fs_acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
- f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
goto fail;
}
@@ -392,73 +565,45 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
size_t len = strlen(symname);
- struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
- struct fscrypt_symlink_data *sd = NULL;
+ struct fscrypt_str disk_link;
int err;
- if (f2fs_encrypted_inode(dir)) {
- err = fscrypt_get_encryption_info(dir);
- if (err)
- return err;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
- if (!fscrypt_has_encryption_key(dir))
- return -ENOKEY;
+ err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
+ &disk_link);
+ if (err)
+ return err;
- disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
- sizeof(struct fscrypt_symlink_data));
- }
-
- if (disk_link.len > dir->i_sb->s_blocksize)
- return -ENAMETOOLONG;
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
if (IS_ERR(inode))
return PTR_ERR(inode);
- if (f2fs_encrypted_inode(inode))
+ if (IS_ENCRYPTED(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
else
inode->i_op = &f2fs_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &f2fs_dblock_aops;
- f2fs_balance_fs(sbi, true);
-
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
- goto out;
+ goto out_f2fs_handle_failed_inode;
f2fs_unlock_op(sbi);
- alloc_nid_done(sbi, inode->i_ino);
+ f2fs_alloc_nid_done(sbi, inode->i_ino);
- if (f2fs_encrypted_inode(inode)) {
- struct qstr istr = QSTR_INIT(symname, len);
- struct fscrypt_str ostr;
-
- sd = kzalloc(disk_link.len, GFP_NOFS);
- if (!sd) {
- err = -ENOMEM;
- goto err_out;
- }
-
- err = fscrypt_get_encryption_info(inode);
- if (err)
- goto err_out;
-
- if (!fscrypt_has_encryption_key(inode)) {
- err = -ENOKEY;
- goto err_out;
- }
-
- ostr.name = sd->encrypted_path;
- ostr.len = disk_link.len;
- err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
- if (err)
- goto err_out;
-
- sd->len = cpu_to_le16(ostr.len);
- disk_link.name = (char *)sd;
- }
+ err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link);
+ if (err)
+ goto err_out;
err = page_symlink(inode, disk_link.name, disk_link.len);
@@ -484,10 +629,14 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
f2fs_unlink(dir, dentry);
}
- kfree(sd);
- return err;
-out:
- handle_failed_inode(inode);
+ f2fs_balance_fs(sbi, true);
+ goto out_free_encrypted_link;
+
+out_f2fs_handle_failed_inode:
+ f2fs_handle_failed_inode(inode);
+out_free_encrypted_link:
+ if (disk_link.name != (unsigned char *)symname)
+ kvfree(disk_link.name);
return err;
}
@@ -497,6 +646,13 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct inode *inode;
int err;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, S_IFDIR | mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -504,9 +660,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
- mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
-
- f2fs_balance_fs(sbi, true);
+ inode_nohighmem(inode);
set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
@@ -515,17 +669,19 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out_fail;
f2fs_unlock_op(sbi);
- alloc_nid_done(sbi, inode->i_ino);
+ f2fs_alloc_nid_done(sbi, inode->i_ino);
d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out_fail:
clear_inode_flag(inode, FI_INC_LINK);
- handle_failed_inode(inode);
+ f2fs_handle_failed_inode(inode);
return err;
}
@@ -544,6 +700,16 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
struct inode *inode;
int err = 0;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
+
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -551,23 +717,23 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &f2fs_special_inode_operations;
- f2fs_balance_fs(sbi, true);
-
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out;
f2fs_unlock_op(sbi);
- alloc_nid_done(sbi, inode->i_ino);
+ f2fs_alloc_nid_done(sbi, inode->i_ino);
d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
- handle_failed_inode(inode);
+ f2fs_handle_failed_inode(inode);
return err;
}
@@ -578,6 +744,10 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
struct inode *inode;
int err;
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -591,10 +761,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
inode->i_mapping->a_ops = &f2fs_dblock_aops;
}
- f2fs_balance_fs(sbi, true);
-
f2fs_lock_op(sbi);
- err = acquire_orphan_inode(sbi);
+ err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto out;
@@ -606,8 +774,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
* add this non-linked tmpfile to orphan list, in this way we could
* remove all unused data of tmpfile after abnormal power-off.
*/
- add_orphan_inode(inode);
- alloc_nid_done(sbi, inode->i_ino);
+ f2fs_add_orphan_inode(inode);
+ f2fs_alloc_nid_done(sbi, inode->i_ino);
if (whiteout) {
f2fs_i_links_write(inode, false);
@@ -618,18 +786,25 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
/* link_count was changed by d_tmpfile as well. */
f2fs_unlock_op(sbi);
unlock_new_inode(inode);
+
+ f2fs_balance_fs(sbi, true);
return 0;
release_out:
- release_orphan_inode(sbi);
+ f2fs_release_orphan_inode(sbi);
out:
- handle_failed_inode(inode);
+ f2fs_handle_failed_inode(inode);
return err;
}
static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
- if (f2fs_encrypted_inode(dir)) {
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ if (f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) {
int err = fscrypt_get_encryption_info(dir);
if (err)
return err;
@@ -640,6 +815,9 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout)
{
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(dir))))
+ return -EIO;
+
return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout);
}
@@ -657,20 +835,34 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
bool is_old_inline = f2fs_has_inline_dentry(old_dir);
- int err = -ENOENT;
+ int err;
- if ((f2fs_encrypted_inode(old_dir) &&
- !fscrypt_has_encryption_key(old_dir)) ||
- (f2fs_encrypted_inode(new_dir) &&
- !fscrypt_has_encryption_key(new_dir)))
- return -ENOKEY;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
- if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
- !fscrypt_has_permitted_context(new_dir, old_inode)) {
- err = -EXDEV;
+ if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ (!projid_eq(F2FS_I(new_dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)))
+ return -EXDEV;
+
+ err = dquot_initialize(old_dir);
+ if (err)
goto out;
+
+ err = dquot_initialize(new_dir);
+ if (err)
+ goto out;
+
+ if (new_inode) {
+ err = dquot_initialize(new_inode);
+ if (err)
+ goto out;
}
+ err = -ENOENT;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
@@ -712,17 +904,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_lock_op(sbi);
- err = acquire_orphan_inode(sbi);
+ err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto put_out_dir;
- err = update_dent_inode(old_inode, new_inode,
- &new_dentry->d_name);
- if (err) {
- release_orphan_inode(sbi);
- goto put_out_dir;
- }
-
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
new_inode->i_ctime = current_time(new_inode);
@@ -733,9 +918,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
up_write(&F2FS_I(new_inode)->i_sem);
if (!new_inode->i_nlink)
- add_orphan_inode(new_inode);
+ f2fs_add_orphan_inode(new_inode);
else
- release_orphan_inode(sbi);
+ f2fs_release_orphan_inode(sbi);
} else {
f2fs_balance_fs(sbi, true);
@@ -774,13 +959,14 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
down_write(&F2FS_I(old_inode)->i_sem);
- file_lost_pino(old_inode);
- if (new_inode && file_enc_name(new_inode))
- file_set_enc_name(old_inode);
+ if (!old_dir_entry || whiteout)
+ file_lost_pino(old_inode);
+ else
+ F2FS_I(old_inode)->i_pino = new_dir->i_ino;
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = current_time(old_inode);
- f2fs_mark_inode_dirty_sync(old_inode);
+ f2fs_mark_inode_dirty_sync(old_inode, false);
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
@@ -795,38 +981,39 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
if (old_dir_entry) {
- if (old_dir != new_dir && !whiteout) {
+ if (old_dir != new_dir && !whiteout)
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
- } else {
- f2fs_dentry_kunmap(old_inode, old_dir_page);
+ else
f2fs_put_page(old_dir_page, 0);
- }
f2fs_i_links_write(old_dir, false);
}
+ if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
+ f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
+ if (S_ISDIR(old_inode->i_mode))
+ f2fs_add_ino_entry(sbi, old_inode->i_ino,
+ TRANS_DIR_INO);
+ }
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_update_time(sbi, REQ_TIME);
return 0;
put_out_dir:
f2fs_unlock_op(sbi);
- if (new_page) {
- f2fs_dentry_kunmap(new_dir, new_page);
+ if (new_page)
f2fs_put_page(new_page, 0);
- }
out_whiteout:
if (whiteout)
iput(whiteout);
out_dir:
- if (old_dir_entry) {
- f2fs_dentry_kunmap(old_inode, old_dir_page);
+ if (old_dir_entry)
f2fs_put_page(old_dir_page, 0);
- }
out_old:
- f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@@ -843,20 +1030,31 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL;
struct f2fs_dir_entry *old_entry, *new_entry;
int old_nlink = 0, new_nlink = 0;
- int err = -ENOENT;
+ int err;
- if ((f2fs_encrypted_inode(old_dir) &&
- !fscrypt_has_encryption_key(old_dir)) ||
- (f2fs_encrypted_inode(new_dir) &&
- !fscrypt_has_encryption_key(new_dir)))
- return -ENOKEY;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;
- if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
- (old_dir != new_dir) &&
- (!fscrypt_has_permitted_context(new_dir, old_inode) ||
- !fscrypt_has_permitted_context(old_dir, new_inode)))
+ if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ !projid_eq(F2FS_I(new_dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)) ||
+ (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ !projid_eq(F2FS_I(old_dir)->i_projid,
+ F2FS_I(new_dentry->d_inode)->i_projid)))
return -EXDEV;
+ err = dquot_initialize(old_dir);
+ if (err)
+ goto out;
+
+ err = dquot_initialize(new_dir);
+ if (err)
+ goto out;
+
+ err = -ENOENT;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
@@ -904,8 +1102,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
old_nlink = old_dir_entry ? -1 : 1;
new_nlink = -old_nlink;
err = -EMLINK;
- if ((old_nlink > 0 && old_inode->i_nlink >= F2FS_LINK_MAX) ||
- (new_nlink > 0 && new_inode->i_nlink >= F2FS_LINK_MAX))
+ if ((old_nlink > 0 && old_dir->i_nlink >= F2FS_LINK_MAX) ||
+ (new_nlink > 0 && new_dir->i_nlink >= F2FS_LINK_MAX))
goto out_new_dir;
}
@@ -913,18 +1111,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_lock_op(sbi);
- err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
- if (err)
- goto out_unlock;
- if (file_enc_name(new_inode))
- file_set_enc_name(old_inode);
-
- err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name);
- if (err)
- goto out_undo;
- if (file_enc_name(old_inode))
- file_set_enc_name(new_inode);
-
/* update ".." directory entry info of old dentry */
if (old_dir_entry)
f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
@@ -946,7 +1132,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_i_links_write(old_dir, old_nlink > 0);
up_write(&F2FS_I(old_dir)->i_sem);
}
- f2fs_mark_inode_dirty_sync(old_dir);
+ f2fs_mark_inode_dirty_sync(old_dir, false);
/* update directory entry info of new dir inode */
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -961,36 +1147,31 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_i_links_write(new_dir, new_nlink > 0);
up_write(&F2FS_I(new_dir)->i_sem);
}
- f2fs_mark_inode_dirty_sync(new_dir);
+ f2fs_mark_inode_dirty_sync(new_dir, false);
+
+ if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
+ f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO);
+ f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
+ }
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_update_time(sbi, REQ_TIME);
return 0;
-out_undo:
- /*
- * Still we may fail to recover name info of f2fs_inode here
- * Drop it, once its name is set as encrypted
- */
- update_dent_inode(old_inode, old_inode, &old_dentry->d_name);
-out_unlock:
- f2fs_unlock_op(sbi);
out_new_dir:
if (new_dir_entry) {
- f2fs_dentry_kunmap(new_inode, new_dir_page);
f2fs_put_page(new_dir_page, 0);
}
out_old_dir:
if (old_dir_entry) {
- f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_new:
- f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
out_old:
- f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@@ -1000,9 +1181,16 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
+ int err;
+
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
+ err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry,
+ flags);
+ if (err)
+ return err;
+
if (flags & RENAME_EXCHANGE) {
return f2fs_cross_rename(old_dir, old_dentry,
new_dir, new_dentry);
@@ -1018,68 +1206,20 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- struct page *cpage = NULL;
- char *caddr, *paddr = NULL;
- struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
- struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
- struct fscrypt_symlink_data *sd;
- u32 max_size = inode->i_sb->s_blocksize;
- int res;
+ struct page *page;
+ const char *target;
if (!dentry)
return ERR_PTR(-ECHILD);
- res = fscrypt_get_encryption_info(inode);
- if (res)
- return ERR_PTR(res);
+ page = read_mapping_page(inode->i_mapping, 0, NULL);
+ if (IS_ERR(page))
+ return ERR_CAST(page);
- cpage = read_mapping_page(inode->i_mapping, 0, NULL);
- if (IS_ERR(cpage))
- return ERR_CAST(cpage);
- caddr = page_address(cpage);
-
- /* Symlink is encrypted */
- sd = (struct fscrypt_symlink_data *)caddr;
- cstr.name = sd->encrypted_path;
- cstr.len = le16_to_cpu(sd->len);
-
- /* this is broken symlink case */
- if (unlikely(cstr.len == 0)) {
- res = -ENOENT;
- goto errout;
- }
-
- if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
- /* Symlink data on the disk is corrupted */
- res = -EIO;
- goto errout;
- }
- res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
- if (res)
- goto errout;
-
- res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
- if (res)
- goto errout;
-
- /* this is broken symlink case */
- if (unlikely(pstr.name[0] == 0)) {
- res = -ENOENT;
- goto errout;
- }
-
- paddr = pstr.name;
-
- /* Null-terminate the name */
- paddr[pstr.len] = '\0';
-
- put_page(cpage);
- set_delayed_call(done, kfree_link, paddr);
- return paddr;
-errout:
- fscrypt_fname_free_buffer(&pstr);
- put_page(cpage);
- return ERR_PTR(res);
+ target = fscrypt_get_symlink(inode, page_address(page),
+ inode->i_sb->s_blocksize, done);
+ put_page(page);
+ return target;
}
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index d87c48e..93e9d42 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/node.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -19,16 +16,33 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "xattr.h"
#include "trace.h"
#include <trace/events/f2fs.h>
-#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
+#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
static struct kmem_cache *nat_entry_set_slab;
+static struct kmem_cache *fsync_node_entry_slab;
-bool available_free_memory(struct f2fs_sb_info *sbi, int type)
+/*
+ * Check whether the given nid is within node id range.
+ */
+int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
+{
+ if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: out-of-range nid=%x, run fsck to fix.",
+ __func__, nid);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct sysinfo val;
@@ -45,8 +59,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
* give 25%, 25%, 50%, 50%, 50% memory for each components respectively
*/
if (type == FREE_NIDS) {
- mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
- PAGE_SHIFT;
+ mem_size = (nm_i->nid_cnt[FREE_NID] *
+ sizeof(struct free_nid)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
@@ -62,9 +76,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
} else if (type == INO_ENTRIES) {
int i;
- for (i = 0; i <= UPDATE_INO; i++)
- mem_size += (sbi->im[i].ino_num *
- sizeof(struct ino_entry)) >> PAGE_SHIFT;
+ for (i = 0; i < MAX_INO_ENTRY; i++)
+ mem_size += sbi->im[i].ino_num *
+ sizeof(struct ino_entry);
+ mem_size >>= PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else if (type == EXTENT_CACHE) {
mem_size = (atomic_read(&sbi->total_ext_tree) *
@@ -72,6 +87,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
atomic_read(&sbi->total_ext_node) *
sizeof(struct extent_node)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else if (type == INMEM_PAGES) {
+ /* it allows 20% / total_ram for inmemory pages */
+ mem_size = get_pages(sbi, F2FS_INMEM_PAGES);
+ res = mem_size < (val.totalram / 5);
} else {
if (!sbi->sb->s_bdi->wb.dirty_exceeded)
return true;
@@ -81,44 +100,35 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
static void clear_node_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- unsigned int long flags;
-
if (PageDirty(page)) {
- spin_lock_irqsave(&mapping->tree_lock, flags);
- radix_tree_tag_clear(&mapping->page_tree,
- page_index(page),
- PAGECACHE_TAG_DIRTY);
- spin_unlock_irqrestore(&mapping->tree_lock, flags);
-
+ f2fs_clear_radix_tree_dirty_tag(page);
clear_page_dirty_for_io(page);
- dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
+ dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
}
ClearPageUptodate(page);
}
static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
- pgoff_t index = current_nat_addr(sbi, nid);
- return get_meta_page(sbi, index);
+ return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid));
}
static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
struct page *src_page;
struct page *dst_page;
- pgoff_t src_off;
pgoff_t dst_off;
void *src_addr;
void *dst_addr;
struct f2fs_nm_info *nm_i = NM_I(sbi);
- src_off = current_nat_addr(sbi, nid);
- dst_off = next_nat_addr(sbi, src_off);
+ dst_off = next_nat_addr(sbi, current_nat_addr(sbi, nid));
/* get current nat block page with lock */
- src_page = get_meta_page(sbi, src_off);
- dst_page = grab_meta_page(sbi, dst_off);
+ src_page = get_current_nat_page(sbi, nid);
+ if (IS_ERR(src_page))
+ return src_page;
+ dst_page = f2fs_grab_meta_page(sbi, dst_off);
f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
@@ -132,9 +142,61 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
return dst_page;
}
+static struct nat_entry *__alloc_nat_entry(nid_t nid, bool no_fail)
+{
+ struct nat_entry *new;
+
+ if (no_fail)
+ new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO);
+ else
+ new = kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO);
+ if (new) {
+ nat_set_nid(new, nid);
+ nat_reset_flag(new);
+ }
+ return new;
+}
+
+static void __free_nat_entry(struct nat_entry *e)
+{
+ kmem_cache_free(nat_entry_slab, e);
+}
+
+/* must be locked by nat_tree_lock */
+static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne, struct f2fs_nat_entry *raw_ne, bool no_fail)
+{
+ if (no_fail)
+ f2fs_radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne);
+ else if (radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne))
+ return NULL;
+
+ if (raw_ne)
+ node_info_from_raw_nat(&ne->ni, raw_ne);
+
+ spin_lock(&nm_i->nat_list_lock);
+ list_add_tail(&ne->list, &nm_i->nat_entries);
+ spin_unlock(&nm_i->nat_list_lock);
+
+ nm_i->nat_cnt++;
+ return ne;
+}
+
static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
{
- return radix_tree_lookup(&nm_i->nat_root, n);
+ struct nat_entry *ne;
+
+ ne = radix_tree_lookup(&nm_i->nat_root, n);
+
+ /* for recent accessed nat entry, move it to tail of lru list */
+ if (ne && !get_nat_flag(ne, IS_DIRTY)) {
+ spin_lock(&nm_i->nat_list_lock);
+ if (!list_empty(&ne->list))
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ spin_unlock(&nm_i->nat_list_lock);
+ }
+
+ return ne;
}
static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
@@ -145,21 +207,17 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
{
- list_del(&e->list);
radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
nm_i->nat_cnt--;
- kmem_cache_free(nat_entry_slab, e);
+ __free_nat_entry(e);
}
-static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
- struct nat_entry *ne)
+static struct nat_entry_set *__grab_nat_entry_set(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
{
nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
struct nat_entry_set *head;
- if (get_nat_flag(ne, IS_DIRTY))
- return;
-
head = radix_tree_lookup(&nm_i->nat_set_root, set);
if (!head) {
head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS);
@@ -170,25 +228,53 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
head->entry_cnt = 0;
f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
}
- list_move_tail(&ne->list, &head->entry_list);
+ return head;
+}
+
+static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
+{
+ struct nat_entry_set *head;
+ bool new_ne = nat_get_blkaddr(ne) == NEW_ADDR;
+
+ if (!new_ne)
+ head = __grab_nat_entry_set(nm_i, ne);
+
+ /*
+ * update entry_cnt in below condition:
+ * 1. update NEW_ADDR to valid block address;
+ * 2. update old block address to new one;
+ */
+ if (!new_ne && (get_nat_flag(ne, IS_PREALLOC) ||
+ !get_nat_flag(ne, IS_DIRTY)))
+ head->entry_cnt++;
+
+ set_nat_flag(ne, IS_PREALLOC, new_ne);
+
+ if (get_nat_flag(ne, IS_DIRTY))
+ goto refresh_list;
+
nm_i->dirty_nat_cnt++;
- head->entry_cnt++;
set_nat_flag(ne, IS_DIRTY, true);
+refresh_list:
+ spin_lock(&nm_i->nat_list_lock);
+ if (new_ne)
+ list_del_init(&ne->list);
+ else
+ list_move_tail(&ne->list, &head->entry_list);
+ spin_unlock(&nm_i->nat_list_lock);
}
static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
- struct nat_entry *ne)
+ struct nat_entry_set *set, struct nat_entry *ne)
{
- nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
- struct nat_entry_set *head;
+ spin_lock(&nm_i->nat_list_lock);
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ spin_unlock(&nm_i->nat_list_lock);
- head = radix_tree_lookup(&nm_i->nat_set_root, set);
- if (head) {
- list_move_tail(&ne->list, &nm_i->nat_entries);
- set_nat_flag(ne, IS_DIRTY, false);
- head->entry_cnt--;
- nm_i->dirty_nat_cnt--;
- }
+ set_nat_flag(ne, IS_DIRTY, false);
+ set->entry_cnt--;
+ nm_i->dirty_nat_cnt--;
}
static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -198,7 +284,73 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
start, nr);
}
-int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page)
+{
+ return NODE_MAPPING(sbi) == page->mapping &&
+ IS_DNODE(page) && is_cold_node(page);
+}
+
+void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi)
+{
+ spin_lock_init(&sbi->fsync_node_lock);
+ INIT_LIST_HEAD(&sbi->fsync_node_list);
+ sbi->fsync_seg_id = 0;
+ sbi->fsync_node_num = 0;
+}
+
+static unsigned int f2fs_add_fsync_node_entry(struct f2fs_sb_info *sbi,
+ struct page *page)
+{
+ struct fsync_node_entry *fn;
+ unsigned long flags;
+ unsigned int seq_id;
+
+ fn = f2fs_kmem_cache_alloc(fsync_node_entry_slab, GFP_NOFS);
+
+ get_page(page);
+ fn->page = page;
+ INIT_LIST_HEAD(&fn->list);
+
+ spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+ list_add_tail(&fn->list, &sbi->fsync_node_list);
+ fn->seq_id = sbi->fsync_seg_id++;
+ seq_id = fn->seq_id;
+ sbi->fsync_node_num++;
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+
+ return seq_id;
+}
+
+void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct fsync_node_entry *fn;
+ unsigned long flags;
+
+ spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+ list_for_each_entry(fn, &sbi->fsync_node_list, list) {
+ if (fn->page == page) {
+ list_del(&fn->list);
+ sbi->fsync_node_num--;
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+ kmem_cache_free(fsync_node_entry_slab, fn);
+ put_page(page);
+ return;
+ }
+ }
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+ f2fs_bug_on(sbi, 1);
+}
+
+void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+ sbi->fsync_seg_id = 0;
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+}
+
+int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@@ -215,7 +367,7 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
return need;
}
-bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
+bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@@ -229,7 +381,7 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
return is_cp;
}
-bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
+bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@@ -245,35 +397,29 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
return need_update;
}
-static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
-{
- struct nat_entry *new;
-
- new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
- f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
- memset(new, 0, sizeof(struct nat_entry));
- nat_set_nid(new, nid);
- nat_reset_flag(new);
- list_add_tail(&new->list, &nm_i->nat_entries);
- nm_i->nat_cnt++;
- return new;
-}
-
+/* must be locked by nat_tree_lock */
static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
struct f2fs_nat_entry *ne)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct nat_entry *e;
+ struct nat_entry *new, *e;
+ new = __alloc_nat_entry(nid, false);
+ if (!new)
+ return;
+
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
- if (!e) {
- e = grab_nat_entry(nm_i, nid);
- node_info_from_raw_nat(&e->ni, ne);
- } else {
- f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
- nat_get_blkaddr(e) != ne->block_addr ||
+ if (!e)
+ e = __init_nat_entry(nm_i, new, ne, false);
+ else
+ f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
+ nat_get_blkaddr(e) !=
+ le32_to_cpu(ne->block_addr) ||
nat_get_version(e) != ne->version);
- }
+ up_write(&nm_i->nat_tree_lock);
+ if (e != new)
+ __free_nat_entry(new);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -281,11 +427,12 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
+ struct nat_entry *new = __alloc_nat_entry(ni->nid, true);
down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
- e = grab_nat_entry(nm_i, ni->nid);
+ e = __init_nat_entry(nm_i, new, NULL, true);
copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
} else if (new_blkaddr == NEW_ADDR) {
@@ -297,6 +444,9 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
}
+ /* let's free early to reduce memory consumption */
+ if (e != new)
+ __free_nat_entry(new);
/* sanity check */
f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr);
@@ -311,10 +461,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
unsigned char version = nat_get_version(e);
nat_set_version(e, inc_node_version(version));
-
- /* in order to reuse the nid */
- if (nm_i->next_scan_nid > ni->nid)
- nm_i->next_scan_nid = ni->nid;
}
/* change address */
@@ -334,7 +480,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
up_write(&nm_i->nat_tree_lock);
}
-int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
+int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
@@ -342,13 +488,25 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
if (!down_write_trylock(&nm_i->nat_tree_lock))
return 0;
- while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
+ spin_lock(&nm_i->nat_list_lock);
+ while (nr_shrink) {
struct nat_entry *ne;
+
+ if (list_empty(&nm_i->nat_entries))
+ break;
+
ne = list_first_entry(&nm_i->nat_entries,
struct nat_entry, list);
+ list_del(&ne->list);
+ spin_unlock(&nm_i->nat_list_lock);
+
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
+
+ spin_lock(&nm_i->nat_list_lock);
}
+ spin_unlock(&nm_i->nat_list_lock);
+
up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
@@ -356,7 +514,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
/*
* This function always returns success
*/
-void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
+int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
+ struct node_info *ni)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -366,6 +525,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
struct page *page = NULL;
struct f2fs_nat_entry ne;
struct nat_entry *e;
+ pgoff_t index;
int i;
ni->nid = nid;
@@ -378,40 +538,46 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
up_read(&nm_i->nat_tree_lock);
- return;
+ return 0;
}
memset(&ne, 0, sizeof(struct f2fs_nat_entry));
/* Check current segment summary */
down_read(&curseg->journal_rwsem);
- i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
+ i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
if (i >= 0) {
ne = nat_in_journal(journal, i);
node_info_from_raw_nat(ni, &ne);
}
up_read(&curseg->journal_rwsem);
- if (i >= 0)
+ if (i >= 0) {
+ up_read(&nm_i->nat_tree_lock);
goto cache;
+ }
/* Fill node_info from nat page */
- page = get_current_nat_page(sbi, start_nid);
+ index = current_nat_addr(sbi, nid);
+ up_read(&nm_i->nat_tree_lock);
+
+ page = f2fs_get_meta_page(sbi, index);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
nat_blk = (struct f2fs_nat_block *)page_address(page);
ne = nat_blk->entries[nid - start_nid];
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
- up_read(&nm_i->nat_tree_lock);
/* cache nat entry */
- down_write(&nm_i->nat_tree_lock);
cache_nat_entry(sbi, nid, &ne);
- up_write(&nm_i->nat_tree_lock);
+ return 0;
}
/*
* readahead MAX_RA_NODE number of node pages.
*/
-static void ra_node_pages(struct page *parent, int start, int n)
+static void f2fs_ra_node_pages(struct page *parent, int start, int n)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
struct blk_plug plug;
@@ -425,13 +591,13 @@ static void ra_node_pages(struct page *parent, int start, int n)
end = min(end, NIDS_PER_BLOCK);
for (i = start; i < end; i++) {
nid = get_nid(parent, i, false);
- ra_node_page(sbi, nid);
+ f2fs_ra_node_page(sbi, nid);
}
blk_finish_plug(&plug);
}
-pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
{
const long direct_index = ADDRS_PER_INODE(dn->inode);
const long direct_blks = ADDRS_PER_BLOCK;
@@ -534,7 +700,7 @@ static int get_node_path(struct inode *inode, long block,
level = 3;
goto got;
} else {
- BUG();
+ return -E2BIG;
}
got:
return level;
@@ -546,7 +712,7 @@ static int get_node_path(struct inode *inode, long block,
* f2fs_unlock_op() only if ro is not set RDONLY_NODE.
* In the case of RDONLY_NODE, we don't need to care about mutex.
*/
-int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
+int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
@@ -558,12 +724,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
int err = 0;
level = get_node_path(dn->inode, index, offset, noffset);
+ if (level < 0)
+ return level;
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
if (!npage[0]) {
- npage[0] = get_node_page(sbi, nids[0]);
+ npage[0] = f2fs_get_node_page(sbi, nids[0]);
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
@@ -587,24 +755,24 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
if (!nids[i] && mode == ALLOC_NODE) {
/* alloc new node */
- if (!alloc_nid(sbi, &(nids[i]))) {
+ if (!f2fs_alloc_nid(sbi, &(nids[i]))) {
err = -ENOSPC;
goto release_pages;
}
dn->nid = nids[i];
- npage[i] = new_node_page(dn, noffset[i], NULL);
+ npage[i] = f2fs_new_node_page(dn, noffset[i]);
if (IS_ERR(npage[i])) {
- alloc_nid_failed(sbi, nids[i]);
+ f2fs_alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
goto release_pages;
}
set_nid(parent, offset[i - 1], nids[i], i == 1);
- alloc_nid_done(sbi, nids[i]);
+ f2fs_alloc_nid_done(sbi, nids[i]);
done = true;
} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
- npage[i] = get_node_page_ra(parent, offset[i - 1]);
+ npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
goto release_pages;
@@ -619,7 +787,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
}
if (!done) {
- npage[i] = get_node_page(sbi, nids[i]);
+ npage[i] = f2fs_get_node_page(sbi, nids[i]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
f2fs_put_page(npage[0], 0);
@@ -634,7 +802,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
dn->nid = nids[level];
dn->ofs_in_node = offset[level];
dn->node_page = npage[level];
- dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
return 0;
release_pages:
@@ -652,30 +821,28 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
return err;
}
-static void truncate_node(struct dnode_of_data *dn)
+static int truncate_node(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info ni;
+ int err;
pgoff_t index;
- get_node_info(sbi, dn->nid, &ni);
- if (dn->inode->i_blocks == 0) {
- f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR);
- goto invalidate;
- }
- f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
+ err = f2fs_get_node_info(sbi, dn->nid, &ni);
+ if (err)
+ return err;
/* Deallocate node address */
- invalidate_blocks(sbi, ni.blk_addr);
- dec_valid_node_count(sbi, dn->inode);
+ f2fs_invalidate_blocks(sbi, ni.blk_addr);
+ dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
set_node_addr(sbi, &ni, NULL_ADDR, false);
if (dn->nid == dn->inode->i_ino) {
- remove_orphan_inode(sbi, dn->nid);
+ f2fs_remove_orphan_inode(sbi, dn->nid);
dec_valid_inode_count(sbi);
f2fs_inode_synced(dn->inode);
}
-invalidate:
+
clear_node_page_dirty(dn->node_page);
set_sbi_flag(sbi, SBI_IS_DIRTY);
@@ -687,17 +854,20 @@ static void truncate_node(struct dnode_of_data *dn)
dn->node_page = NULL;
trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
+
+ return 0;
}
static int truncate_dnode(struct dnode_of_data *dn)
{
struct page *page;
+ int err;
if (dn->nid == 0)
return 1;
/* get direct node */
- page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
+ page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
return 1;
else if (IS_ERR(page))
@@ -706,8 +876,11 @@ static int truncate_dnode(struct dnode_of_data *dn)
/* Make dnode_of_data for parameter */
dn->node_page = page;
dn->ofs_in_node = 0;
- truncate_data_blocks(dn);
- truncate_node(dn);
+ f2fs_truncate_data_blocks(dn);
+ err = truncate_node(dn);
+ if (err)
+ return err;
+
return 1;
}
@@ -727,13 +900,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
- page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
+ page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page)) {
trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
return PTR_ERR(page);
}
- ra_node_pages(page, ofs, NIDS_PER_BLOCK);
+ f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK);
rn = F2FS_NODE(page);
if (depth < 3) {
@@ -772,7 +945,9 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
if (!ofs) {
/* remove current indirect node */
dn->node_page = page;
- truncate_node(dn);
+ ret = truncate_node(dn);
+ if (ret)
+ goto out_err;
freed++;
} else {
f2fs_put_page(page, 1);
@@ -803,7 +978,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
/* get indirect nodes in the path */
for (i = 0; i < idx + 1; i++) {
/* reference count'll be increased */
- pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]);
+ pages[i] = f2fs_get_node_page(F2FS_I_SB(dn->inode), nid[i]);
if (IS_ERR(pages[i])) {
err = PTR_ERR(pages[i]);
idx = i - 1;
@@ -812,7 +987,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
}
- ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
+ f2fs_ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
/* free direct nodes linked to a partial indirect node */
for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
@@ -830,7 +1005,9 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
if (offset[idx + 1] == 0) {
dn->node_page = pages[idx];
dn->nid = nid[idx];
- truncate_node(dn);
+ err = truncate_node(dn);
+ if (err)
+ goto fail;
} else {
f2fs_put_page(pages[idx], 1);
}
@@ -849,7 +1026,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
/*
* All the block addresses of data and nodes should be nullified.
*/
-int truncate_inode_blocks(struct inode *inode, pgoff_t from)
+int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0, cont = 1;
@@ -862,8 +1039,10 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
+ if (level < 0)
+ return level;
- page = get_node_page(sbi, inode->i_ino);
+ page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
return PTR_ERR(page);
@@ -927,7 +1106,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
lock_page(page);
BUG_ON(page->mapping != NODE_MAPPING(sbi));
- f2fs_wait_on_page_writeback(page, NODE, true);
+ f2fs_wait_on_page_writeback(page, NODE, true, true);
ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
set_page_dirty(page);
unlock_page(page);
@@ -942,30 +1121,31 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
return err > 0 ? 0 : err;
}
-int truncate_xattr_node(struct inode *inode, struct page *page)
+/* caller must lock inode page */
+int f2fs_truncate_xattr_node(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t nid = F2FS_I(inode)->i_xattr_nid;
struct dnode_of_data dn;
struct page *npage;
+ int err;
if (!nid)
return 0;
- npage = get_node_page(sbi, nid);
+ npage = f2fs_get_node_page(sbi, nid);
if (IS_ERR(npage))
return PTR_ERR(npage);
+ set_new_dnode(&dn, inode, NULL, npage, nid);
+ err = truncate_node(&dn);
+ if (err) {
+ f2fs_put_page(npage, 1);
+ return err;
+ }
+
f2fs_i_xnid_write(inode, 0);
- /* need to do checkpoint during fsync */
- F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
-
- set_new_dnode(&dn, inode, page, npage, nid);
-
- if (page)
- dn.inode_page_locked = true;
- truncate_node(&dn);
return 0;
}
@@ -973,17 +1153,17 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
-int remove_inode_page(struct inode *inode)
+int f2fs_remove_inode_page(struct inode *inode)
{
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
- err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
- err = truncate_xattr_node(inode, dn.inode_page);
+ err = f2fs_truncate_xattr_node(inode);
if (err) {
f2fs_put_dnode(&dn);
return err;
@@ -992,18 +1172,26 @@ int remove_inode_page(struct inode *inode)
/* remove potential inline_data blocks */
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode))
- truncate_data_blocks_range(&dn, 1);
+ f2fs_truncate_data_blocks_range(&dn, 1);
/* 0 is possible, after f2fs_new_inode() has failed */
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
+ f2fs_put_dnode(&dn);
+ return -EIO;
+ }
f2fs_bug_on(F2FS_I_SB(inode),
- inode->i_blocks != 0 && inode->i_blocks != 1);
+ inode->i_blocks != 0 && inode->i_blocks != 8);
/* will put inode & node pages */
- truncate_node(&dn);
+ err = truncate_node(&dn);
+ if (err) {
+ f2fs_put_dnode(&dn);
+ return err;
+ }
return 0;
}
-struct page *new_inode_page(struct inode *inode)
+struct page *f2fs_new_inode_page(struct inode *inode)
{
struct dnode_of_data dn;
@@ -1011,14 +1199,13 @@ struct page *new_inode_page(struct inode *inode)
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
/* caller should f2fs_put_page(page, 1); */
- return new_node_page(&dn, 0, NULL);
+ return f2fs_new_node_page(&dn, 0);
}
-struct page *new_node_page(struct dnode_of_data *dn,
- unsigned int ofs, struct page *ipage)
+struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- struct node_info old_ni, new_ni;
+ struct node_info new_ni;
struct page *page;
int err;
@@ -1029,22 +1216,27 @@ struct page *new_node_page(struct dnode_of_data *dn,
if (!page)
return ERR_PTR(-ENOMEM);
- if (unlikely(!inc_valid_node_count(sbi, dn->inode))) {
- err = -ENOSPC;
+ if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs))))
+ goto fail;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ err = f2fs_get_node_info(sbi, dn->nid, &new_ni);
+ if (err) {
+ dec_valid_node_count(sbi, dn->inode, !ofs);
goto fail;
}
-
- get_node_info(sbi, dn->nid, &old_ni);
-
- /* Reinitialize old_ni with new node page */
- f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
- new_ni = old_ni;
+ f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+#endif
+ new_ni.nid = dn->nid;
new_ni.ino = dn->inode->i_ino;
+ new_ni.blk_addr = NULL_ADDR;
+ new_ni.flag = 0;
+ new_ni.version = 0;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
- f2fs_wait_on_page_writeback(page, NODE, true);
+ f2fs_wait_on_page_writeback(page, NODE, true, true);
fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
- set_cold_node(dn->inode, page);
+ set_cold_node(page, S_ISDIR(dn->inode->i_mode));
if (!PageUptodate(page))
SetPageUptodate(page);
if (set_page_dirty(page))
@@ -1080,13 +1272,21 @@ static int read_node_page(struct page *page, int op_flags)
.page = page,
.encrypted_page = NULL,
};
+ int err;
- if (PageUptodate(page))
+ if (PageUptodate(page)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_bug_on(sbi, !f2fs_inode_chksum_verify(sbi, page));
+#endif
return LOCKED_PAGE;
+ }
- get_node_info(sbi, page->index, &ni);
+ err = f2fs_get_node_info(sbi, page->index, &ni);
+ if (err)
+ return err;
- if (unlikely(ni.blk_addr == NULL_ADDR)) {
+ if (unlikely(ni.blk_addr == NULL_ADDR) ||
+ is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) {
ClearPageUptodate(page);
return -ENOENT;
}
@@ -1098,14 +1298,15 @@ static int read_node_page(struct page *page, int op_flags)
/*
* Readahead a node page
*/
-void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
+void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
{
struct page *apage;
int err;
if (!nid)
return;
- f2fs_bug_on(sbi, check_nid_range(sbi, nid));
+ if (f2fs_check_nid_range(sbi, nid))
+ return;
rcu_read_lock();
apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
@@ -1129,22 +1330,24 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
if (!nid)
return ERR_PTR(-ENOENT);
- f2fs_bug_on(sbi, check_nid_range(sbi, nid));
+ if (f2fs_check_nid_range(sbi, nid))
+ return ERR_PTR(-EINVAL);
repeat:
page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
- err = read_node_page(page, READ_SYNC);
+ err = read_node_page(page, 0);
if (err < 0) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
} else if (err == LOCKED_PAGE) {
+ err = 0;
goto page_hit;
}
if (parent)
- ra_node_pages(parent, start + 1, MAX_RA_NODE);
+ f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE);
lock_page(page);
@@ -1153,25 +1356,37 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
goto repeat;
}
- if (unlikely(!PageUptodate(page)))
+ if (unlikely(!PageUptodate(page))) {
+ err = -EIO;
goto out_err;
+ }
+
+ if (!f2fs_inode_chksum_verify(sbi, page)) {
+ err = -EBADMSG;
+ goto out_err;
+ }
page_hit:
if(unlikely(nid != nid_of_node(page))) {
- f2fs_bug_on(sbi, 1);
- ClearPageUptodate(page);
+ f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, "
+ "nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+ nid, nid_of_node(page), ino_of_node(page),
+ ofs_of_node(page), cpver_of_node(page),
+ next_blkaddr_of_node(page));
+ err = -EINVAL;
out_err:
+ ClearPageUptodate(page);
f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
+ return ERR_PTR(err);
}
return page;
}
-struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
+struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
{
return __get_node_page(sbi, nid, NULL, 0);
}
-struct page *get_node_page_ra(struct page *parent, int start)
+struct page *f2fs_get_node_page_ra(struct page *parent, int start)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
nid_t nid = get_nid(parent, start, false);
@@ -1190,7 +1405,8 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
if (!inode)
return;
- page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
+ page = f2fs_pagecache_get_page(inode->i_mapping, 0,
+ FGP_LOCK|FGP_NOWAIT, 0);
if (!page)
goto iput_out;
@@ -1205,6 +1421,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
ret = f2fs_write_inline_data(inode, page);
inode_dec_dirty_pages(inode);
+ f2fs_remove_dirty_inode(inode);
if (ret)
set_page_dirty(page);
page_out:
@@ -1213,54 +1430,19 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
iput(inode);
}
-void move_node_page(struct page *node_page, int gc_type)
-{
- if (gc_type == FG_GC) {
- struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = 1,
- .for_reclaim = 0,
- };
-
- set_page_dirty(node_page);
- f2fs_wait_on_page_writeback(node_page, NODE, true);
-
- f2fs_bug_on(sbi, PageWriteback(node_page));
- if (!clear_page_dirty_for_io(node_page))
- goto out_page;
-
- if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
- unlock_page(node_page);
- goto release_page;
- } else {
- /* set page dirty and write it */
- if (!PageWriteback(node_page))
- set_page_dirty(node_page);
- }
-out_page:
- unlock_page(node_page);
-release_page:
- f2fs_put_page(node_page, 0);
-}
-
static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
{
- pgoff_t index, end;
+ pgoff_t index;
struct pagevec pvec;
struct page *last_page = NULL;
+ int nr_pages;
pagevec_init(&pvec, 0);
index = 0;
- end = ULONG_MAX;
- while (index <= end) {
- int i, nr_pages;
- nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
- if (nr_pages == 0)
- break;
+ while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY))) {
+ int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@@ -1304,15 +1486,165 @@ static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
return last_page;
}
-int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
- struct writeback_control *wbc, bool atomic)
+static int __write_node_page(struct page *page, bool atomic, bool *submitted,
+ struct writeback_control *wbc, bool do_balance,
+ enum iostat_type io_type, unsigned int *seq_id)
{
- pgoff_t index, end;
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ nid_t nid;
+ struct node_info ni;
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .ino = ino_of_node(page),
+ .type = NODE,
+ .op = REQ_OP_WRITE,
+ .op_flags = wbc_to_write_flags(wbc),
+ .page = page,
+ .encrypted_page = NULL,
+ .submitted = false,
+ .io_type = io_type,
+ .io_wbc = wbc,
+ };
+ unsigned int seq;
+
+ trace_f2fs_writepage(page, NODE);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto redirty_out;
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto redirty_out;
+
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ IS_DNODE(page) && is_cold_node(page))
+ goto redirty_out;
+
+ /* get old block addr of this node page */
+ nid = nid_of_node(page);
+ f2fs_bug_on(sbi, page->index != nid);
+
+ if (f2fs_get_node_info(sbi, nid, &ni))
+ goto redirty_out;
+
+ if (wbc->for_reclaim) {
+ if (!down_read_trylock(&sbi->node_write))
+ goto redirty_out;
+ } else {
+ down_read(&sbi->node_write);
+ }
+
+ /* This page is already truncated */
+ if (unlikely(ni.blk_addr == NULL_ADDR)) {
+ ClearPageUptodate(page);
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ up_read(&sbi->node_write);
+ unlock_page(page);
+ return 0;
+ }
+
+ if (__is_valid_data_blkaddr(ni.blk_addr) &&
+ !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
+ up_read(&sbi->node_write);
+ goto redirty_out;
+ }
+
+ if (atomic && !test_opt(sbi, NOBARRIER))
+ fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
+
+ set_page_writeback(page);
+ ClearPageError(page);
+
+ if (f2fs_in_warm_node_list(sbi, page)) {
+ seq = f2fs_add_fsync_node_entry(sbi, page);
+ if (seq_id)
+ *seq_id = seq;
+ }
+
+ fio.old_blkaddr = ni.blk_addr;
+ f2fs_do_write_node_page(nid, &fio);
+ set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ up_read(&sbi->node_write);
+
+ if (wbc->for_reclaim) {
+ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, NODE);
+ submitted = NULL;
+ }
+
+ unlock_page(page);
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_submit_merged_write(sbi, NODE);
+ submitted = NULL;
+ }
+ if (submitted)
+ *submitted = fio.submitted;
+
+ if (do_balance)
+ f2fs_balance_fs(sbi, false);
+ return 0;
+
+redirty_out:
+ redirty_page_for_writepage(wbc, page);
+ return AOP_WRITEPAGE_ACTIVATE;
+}
+
+int f2fs_move_node_page(struct page *node_page, int gc_type)
+{
+ int err = 0;
+
+ if (gc_type == FG_GC) {
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 1,
+ .for_reclaim = 0,
+ };
+
+ f2fs_wait_on_page_writeback(node_page, NODE, true, true);
+
+ set_page_dirty(node_page);
+
+ if (!clear_page_dirty_for_io(node_page)) {
+ err = -EAGAIN;
+ goto out_page;
+ }
+
+ if (__write_node_page(node_page, false, NULL,
+ &wbc, false, FS_GC_NODE_IO, NULL)) {
+ err = -EAGAIN;
+ unlock_page(node_page);
+ }
+ goto release_page;
+ } else {
+ /* set page dirty and write it */
+ if (!PageWriteback(node_page))
+ set_page_dirty(node_page);
+ }
+out_page:
+ unlock_page(node_page);
+release_page:
+ f2fs_put_page(node_page, 0);
+ return err;
+}
+
+static int f2fs_write_node_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __write_node_page(page, false, NULL, wbc, false,
+ FS_NODE_IO, NULL);
+}
+
+int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic,
+ unsigned int *seq_id)
+{
+ pgoff_t index;
struct pagevec pvec;
int ret = 0;
struct page *last_page = NULL;
bool marked = false;
nid_t ino = inode->i_ino;
+ int nr_pages;
int nwritten = 0;
if (atomic) {
@@ -1323,23 +1655,20 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
retry:
pagevec_init(&pvec, 0);
index = 0;
- end = ULONG_MAX;
- while (index <= end) {
- int i, nr_pages;
- nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
- if (nr_pages == 0)
- break;
+ while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY))) {
+ int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ bool submitted = false;
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_put_page(last_page, 0);
pagevec_release(&pvec);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
if (!IS_DNODE(page) || !is_cold_node(page))
@@ -1362,17 +1691,19 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
goto continue_unlock;
}
- f2fs_wait_on_page_writeback(page, NODE, true);
- BUG_ON(PageWriteback(page));
+ f2fs_wait_on_page_writeback(page, NODE, true, true);
+
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
if (!atomic || page == last_page) {
set_fsync_mark(page, 1);
if (IS_INODE(page)) {
if (is_inode_flag_set(inode,
FI_DIRTY_INODE))
- update_inode(inode, page);
+ f2fs_update_inode(inode, page);
set_dentry_mark(page,
- need_dentry_mark(sbi, ino));
+ f2fs_need_dentry_mark(sbi, ino));
}
/* may be written by other thread */
if (!PageDirty(page))
@@ -1382,12 +1713,15 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+ ret = __write_node_page(page, atomic &&
+ page == last_page,
+ &submitted, wbc, true,
+ FS_NODE_IO, seq_id);
if (ret) {
unlock_page(page);
f2fs_put_page(last_page, 0);
break;
- } else {
+ } else if (submitted) {
nwritten++;
}
@@ -1408,45 +1742,46 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
"Retry to write fsync mark: ino=%u, idx=%lx",
ino, last_page->index);
lock_page(last_page);
+ f2fs_wait_on_page_writeback(last_page, NODE, true, true);
set_page_dirty(last_page);
unlock_page(last_page);
goto retry;
}
-
+out:
if (nwritten)
- f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
+ f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE);
return ret ? -EIO: 0;
}
-int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
+ struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type)
{
- pgoff_t index, end;
+ pgoff_t index;
struct pagevec pvec;
int step = 0;
int nwritten = 0;
int ret = 0;
+ int nr_pages, done = 0;
pagevec_init(&pvec, 0);
next_step:
index = 0;
- end = ULONG_MAX;
- while (index <= end) {
- int i, nr_pages;
- nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
- if (nr_pages == 0)
- break;
+ while (!done && (nr_pages = pagevec_lookup_tag(&pvec,
+ NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) {
+ int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ bool submitted = false;
- if (unlikely(f2fs_cp_error(sbi))) {
- pagevec_release(&pvec);
- ret = -EIO;
- goto out;
+ /* give a priority to WB_SYNC threads */
+ if (atomic_read(&sbi->wb_sync_req[NODE]) &&
+ wbc->sync_mode == WB_SYNC_NONE) {
+ done = 1;
+ break;
}
/*
@@ -1488,18 +1823,19 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
goto lock_node;
}
- f2fs_wait_on_page_writeback(page, NODE, true);
+ f2fs_wait_on_page_writeback(page, NODE, true, true);
- BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
set_fsync_mark(page, 0);
set_dentry_mark(page, 0);
- if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
+ ret = __write_node_page(page, false, &submitted,
+ wbc, do_balance, io_type, NULL);
+ if (ret)
unlock_page(page);
- else
+ else if (submitted)
nwritten++;
if (--wbc->nr_to_write == 0)
@@ -1515,126 +1851,63 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
}
if (step < 2) {
+ if (wbc->sync_mode == WB_SYNC_NONE && step == 1)
+ goto out;
step++;
goto next_step;
}
out:
if (nwritten)
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ f2fs_submit_merged_write(sbi, NODE);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
return ret;
}
-int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
+int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
+ unsigned int seq_id)
{
- pgoff_t index = 0, end = ULONG_MAX;
- struct pagevec pvec;
+ struct fsync_node_entry *fn;
+ struct page *page;
+ struct list_head *head = &sbi->fsync_node_list;
+ unsigned long flags;
+ unsigned int cur_seq_id = 0;
int ret2, ret = 0;
- pagevec_init(&pvec, 0);
-
- while (index <= end) {
- int i, nr_pages;
- nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
- PAGECACHE_TAG_WRITEBACK,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
- if (nr_pages == 0)
+ while (seq_id && cur_seq_id < seq_id) {
+ spin_lock_irqsave(&sbi->fsync_node_lock, flags);
+ if (list_empty(head)) {
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
break;
-
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
-
- /* until radix tree lookup accepts end_index */
- if (unlikely(page->index > end))
- continue;
-
- if (ino && ino_of_node(page) == ino) {
- f2fs_wait_on_page_writeback(page, NODE, true);
- if (TestClearPageError(page))
- ret = -EIO;
- }
}
- pagevec_release(&pvec);
- cond_resched();
+ fn = list_first_entry(head, struct fsync_node_entry, list);
+ if (fn->seq_id > seq_id) {
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+ break;
+ }
+ cur_seq_id = fn->seq_id;
+ page = fn->page;
+ get_page(page);
+ spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
+
+ f2fs_wait_on_page_writeback(page, NODE, true, false);
+ if (TestClearPageError(page))
+ ret = -EIO;
+
+ put_page(page);
+
+ if (ret)
+ break;
}
ret2 = filemap_check_errors(NODE_MAPPING(sbi));
if (!ret)
ret = ret2;
+
return ret;
}
-static int f2fs_write_node_page(struct page *page,
- struct writeback_control *wbc)
-{
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- nid_t nid;
- struct node_info ni;
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .type = NODE,
- .op = REQ_OP_WRITE,
- .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
- .page = page,
- .encrypted_page = NULL,
- };
-
- trace_f2fs_writepage(page, NODE);
-
- if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
- goto redirty_out;
- if (unlikely(f2fs_cp_error(sbi)))
- goto redirty_out;
-
- /* get old block addr of this node page */
- nid = nid_of_node(page);
- f2fs_bug_on(sbi, page->index != nid);
-
- if (wbc->for_reclaim) {
- if (!down_read_trylock(&sbi->node_write))
- goto redirty_out;
- } else {
- down_read(&sbi->node_write);
- }
-
- get_node_info(sbi, nid, &ni);
-
- /* This page is already truncated */
- if (unlikely(ni.blk_addr == NULL_ADDR)) {
- ClearPageUptodate(page);
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- up_read(&sbi->node_write);
- unlock_page(page);
- return 0;
- }
-
- if (__is_valid_data_blkaddr(ni.blk_addr) &&
- !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
- up_read(&sbi->node_write);
- goto redirty_out;
- }
-
- set_page_writeback(page);
- fio.old_blkaddr = ni.blk_addr;
- write_node_page(nid, &fio);
- set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- up_read(&sbi->node_write);
-
- if (wbc->for_reclaim)
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
-
- unlock_page(page);
-
- if (unlikely(f2fs_cp_error(sbi)))
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
-
- return 0;
-
-redirty_out:
- redirty_page_for_writepage(wbc, page);
- return AOP_WRITEPAGE_ACTIVATE;
-}
-
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -1642,21 +1915,33 @@ static int f2fs_write_node_pages(struct address_space *mapping,
struct blk_plug plug;
long diff;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto skip_write;
+
/* balancing f2fs's metadata in background */
f2fs_balance_fs_bg(sbi);
/* collect a number of dirty node pages and write together */
- if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
+ if (wbc->sync_mode != WB_SYNC_ALL &&
+ get_pages(sbi, F2FS_DIRTY_NODES) <
+ nr_pages_to_skip(sbi, NODE))
+ goto skip_write;
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_inc(&sbi->wb_sync_req[NODE]);
+ else if (atomic_read(&sbi->wb_sync_req[NODE]))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, NODE);
diff = nr_pages_to_write(sbi, NODE, wbc);
- wbc->sync_mode = WB_SYNC_NONE;
blk_start_plug(&plug);
- sync_node_pages(sbi, wbc);
+ f2fs_sync_node_pages(sbi, wbc, true, FS_NODE_IO);
blk_finish_plug(&plug);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_dec(&sbi->wb_sync_req[NODE]);
return 0;
skip_write:
@@ -1671,10 +1956,14 @@ static int f2fs_set_node_page_dirty(struct page *page)
if (!PageUptodate(page))
SetPageUptodate(page);
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (IS_INODE(page))
+ f2fs_inode_chksum_set(F2FS_P_SB(page), page);
+#endif
if (!PageDirty(page)) {
- f2fs_set_page_dirty_nobuffers(page);
+ __set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
- SetPagePrivate(page);
+ f2fs_set_page_private(page, 0);
f2fs_trace_pid(page);
return 1;
}
@@ -1701,57 +1990,123 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
return radix_tree_lookup(&nm_i->free_nid_root, n);
}
-static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
- struct free_nid *i)
+static int __insert_free_nid(struct f2fs_sb_info *sbi,
+ struct free_nid *i, enum nid_state state)
{
- list_del(&i->list);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i);
+ if (err)
+ return err;
+
+ f2fs_bug_on(sbi, state != i->state);
+ nm_i->nid_cnt[state]++;
+ if (state == FREE_NID)
+ list_add_tail(&i->list, &nm_i->free_nid_list);
+ return 0;
+}
+
+static void __remove_free_nid(struct f2fs_sb_info *sbi,
+ struct free_nid *i, enum nid_state state)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ f2fs_bug_on(sbi, state != i->state);
+ nm_i->nid_cnt[state]--;
+ if (state == FREE_NID)
+ list_del(&i->list);
radix_tree_delete(&nm_i->free_nid_root, i->nid);
}
-static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i,
+ enum nid_state org_state, enum nid_state dst_state)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ f2fs_bug_on(sbi, org_state != i->state);
+ i->state = dst_state;
+ nm_i->nid_cnt[org_state]--;
+ nm_i->nid_cnt[dst_state]++;
+
+ switch (dst_state) {
+ case PREALLOC_NID:
+ list_del(&i->list);
+ break;
+ case FREE_NID:
+ list_add_tail(&i->list, &nm_i->free_nid_list);
+ break;
+ default:
+ BUG_ON(1);
+ }
+}
+
+static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
+ bool set, bool build)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
+ unsigned int nid_ofs = nid - START_NID(nid);
+
+ if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+ return;
+
+ if (set) {
+ if (test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]))
+ return;
+ __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+ nm_i->free_nid_count[nat_ofs]++;
+ } else {
+ if (!test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]))
+ return;
+ __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+ if (!build)
+ nm_i->free_nid_count[nat_ofs]--;
+ }
+}
+
+/* return if the nid is recognized as free */
+static bool add_free_nid(struct f2fs_sb_info *sbi,
+ nid_t nid, bool build, bool update)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *e;
struct nat_entry *ne;
int err = -EINVAL;
-
- if (!available_free_memory(sbi, FREE_NIDS))
- return -1;
+ bool ret = false;
/* 0 nid should not be used */
if (unlikely(nid == 0))
- return 0;
+ return false;
i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
i->nid = nid;
- i->state = NID_NEW;
+ i->state = FREE_NID;
- if (radix_tree_preload(GFP_NOFS))
- goto err;
+ radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
if (build) {
/*
* Thread A Thread B
* - f2fs_create
* - f2fs_new_inode
- * - alloc_nid
- * - __insert_nid_to_list(ALLOC_NID_LIST)
+ * - f2fs_alloc_nid
+ * - __insert_nid_to_list(PREALLOC_NID)
* - f2fs_balance_fs_bg
- * - build_free_nids
- * - __build_free_nids
+ * - f2fs_build_free_nids
+ * - __f2fs_build_free_nids
* - scan_nat_page
* - add_free_nid
* - __lookup_nat_cache
* - f2fs_add_link
- * - init_inode_metadata
- * - new_inode_page
- * - new_node_page
+ * - f2fs_init_inode_metadata
+ * - f2fs_new_inode_page
+ * - f2fs_new_node_page
* - set_node_addr
- * - alloc_nid_done
- * - __remove_nid_from_list(ALLOC_NID_LIST)
- * - __insert_nid_to_list(FREE_NID_LIST)
+ * - f2fs_alloc_nid_done
+ * - __remove_nid_from_list(PREALLOC_NID)
+ * - __insert_nid_to_list(FREE_NID)
*/
ne = __lookup_nat_cache(nm_i, nid);
if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
@@ -1759,88 +2114,184 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
goto err_out;
e = __lookup_free_nid_list(nm_i, nid);
- if (e)
+ if (e) {
+ if (e->state == FREE_NID)
+ ret = true;
goto err_out;
+ }
}
- if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i))
- goto err_out;
- err = 0;
- list_add_tail(&i->list, &nm_i->free_nid_list);
- nm_i->fcnt++;
+ ret = true;
+ err = __insert_free_nid(sbi, i, FREE_NID);
err_out:
- spin_unlock(&nm_i->free_nid_list_lock);
+ if (update) {
+ update_free_nid_bitmap(sbi, nid, ret, build);
+ if (!build)
+ nm_i->available_nids++;
+ }
+ spin_unlock(&nm_i->nid_list_lock);
radix_tree_preload_end();
-err:
+
if (err)
kmem_cache_free(free_nid_slab, i);
- return !err;
+ return ret;
}
-static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
+static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
bool need_free = false;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- if (i && i->state == NID_NEW) {
- __del_from_free_nid_list(nm_i, i);
- nm_i->fcnt--;
+ if (i && i->state == FREE_NID) {
+ __remove_free_nid(sbi, i, FREE_NID);
need_free = true;
}
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
if (need_free)
kmem_cache_free(free_nid_slab, i);
}
-static void scan_nat_page(struct f2fs_sb_info *sbi,
+static int scan_nat_page(struct f2fs_sb_info *sbi,
struct page *nat_page, nid_t start_nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct f2fs_nat_block *nat_blk = page_address(nat_page);
block_t blk_addr;
+ unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
int i;
+ __set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
+
i = start_nid % NAT_ENTRY_PER_BLOCK;
for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {
-
if (unlikely(start_nid >= nm_i->max_nid))
break;
blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
- f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
+
+ if (blk_addr == NEW_ADDR)
+ return -EINVAL;
+
if (blk_addr == NULL_ADDR) {
- if (add_free_nid(sbi, start_nid, true) < 0)
- break;
+ add_free_nid(sbi, start_nid, true, true);
+ } else {
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ update_free_nid_bitmap(sbi, start_nid, false, true);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
}
}
+
+ return 0;
}
-void build_free_nids(struct f2fs_sb_info *sbi)
+static void scan_curseg_cache(struct f2fs_sb_info *sbi)
{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
struct f2fs_journal *journal = curseg->journal;
- int i = 0;
+ int i;
+
+ down_read(&curseg->journal_rwsem);
+ for (i = 0; i < nats_in_cursum(journal); i++) {
+ block_t addr;
+ nid_t nid;
+
+ addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+ nid = le32_to_cpu(nid_in_journal(journal, i));
+ if (addr == NULL_ADDR)
+ add_free_nid(sbi, nid, true, false);
+ else
+ remove_free_nid(sbi, nid);
+ }
+ up_read(&curseg->journal_rwsem);
+}
+
+static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int i, idx;
+ nid_t nid;
+
+ down_read(&nm_i->nat_tree_lock);
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ if (!test_bit_le(i, nm_i->nat_block_bitmap))
+ continue;
+ if (!nm_i->free_nid_count[i])
+ continue;
+ for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
+ idx = find_next_bit_le(nm_i->free_nid_bitmap[i],
+ NAT_ENTRY_PER_BLOCK, idx);
+ if (idx >= NAT_ENTRY_PER_BLOCK)
+ break;
+
+ nid = i * NAT_ENTRY_PER_BLOCK + idx;
+ add_free_nid(sbi, nid, true, false);
+
+ if (nm_i->nid_cnt[FREE_NID] >= MAX_FREE_NIDS)
+ goto out;
+ }
+ }
+out:
+ scan_curseg_cache(sbi);
+
+ up_read(&nm_i->nat_tree_lock);
+}
+
+static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
+ bool sync, bool mount)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ int i = 0, ret;
nid_t nid = nm_i->next_scan_nid;
+ if (unlikely(nid >= nm_i->max_nid))
+ nid = 0;
+
/* Enough entries */
- if (nm_i->fcnt >= NAT_ENTRY_PER_BLOCK)
- return;
+ if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
+ return 0;
+
+ if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS))
+ return 0;
+
+ if (!mount) {
+ /* try to find free nids in free_nid_bitmap */
+ scan_free_nid_bits(sbi);
+
+ if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
+ return 0;
+ }
/* readahead nat pages to be scanned */
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
+ f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
down_read(&nm_i->nat_tree_lock);
while (1) {
- struct page *page = get_current_nat_page(sbi, nid);
+ if (!test_bit_le(NAT_BLOCK_OFFSET(nid),
+ nm_i->nat_block_bitmap)) {
+ struct page *page = get_current_nat_page(sbi, nid);
- scan_nat_page(sbi, page, nid);
- f2fs_put_page(page, 1);
+ if (IS_ERR(page)) {
+ ret = PTR_ERR(page);
+ } else {
+ ret = scan_nat_page(sbi, page, nid);
+ f2fs_put_page(page, 1);
+ }
+
+ if (ret) {
+ up_read(&nm_i->nat_tree_lock);
+ f2fs_bug_on(sbi, !mount);
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "NAT is corrupt, run fsck to fix it");
+ return ret;
+ }
+ }
nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
if (unlikely(nid >= nm_i->max_nid))
@@ -1854,22 +2305,25 @@ void build_free_nids(struct f2fs_sb_info *sbi)
nm_i->next_scan_nid = nid;
/* find free nids from current sum_pages */
- down_read(&curseg->journal_rwsem);
- for (i = 0; i < nats_in_cursum(journal); i++) {
- block_t addr;
+ scan_curseg_cache(sbi);
- addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
- nid = le32_to_cpu(nid_in_journal(journal, i));
- if (addr == NULL_ADDR)
- add_free_nid(sbi, nid, true);
- else
- remove_free_nid(nm_i, nid);
- }
- up_read(&curseg->journal_rwsem);
up_read(&nm_i->nat_tree_lock);
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
+ f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
+
+ return 0;
+}
+
+int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+{
+ int ret;
+
+ mutex_lock(&NM_I(sbi)->build_lock);
+ ret = __f2fs_build_free_nids(sbi, sync, mount);
+ mutex_unlock(&NM_I(sbi)->build_lock);
+
+ return ret;
}
/*
@@ -1877,64 +2331,67 @@ void build_free_nids(struct f2fs_sb_info *sbi)
* from second parameter of this function.
* The returned nid could be used ino as well as nid when inode is created.
*/
-bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
retry:
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_ALLOC_NID))
+ if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
+ f2fs_show_injection_info(FAULT_ALLOC_NID);
return false;
-#endif
- if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
+ }
+
+ spin_lock(&nm_i->nid_list_lock);
+
+ if (unlikely(nm_i->available_nids == 0)) {
+ spin_unlock(&nm_i->nid_list_lock);
return false;
+ }
- spin_lock(&nm_i->free_nid_list_lock);
-
- /* We should not use stale free nids created by build_free_nids */
- if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
+ /* We should not use stale free nids created by f2fs_build_free_nids */
+ if (nm_i->nid_cnt[FREE_NID] && !on_f2fs_build_free_nids(nm_i)) {
f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
- list_for_each_entry(i, &nm_i->free_nid_list, list)
- if (i->state == NID_NEW)
- break;
-
- f2fs_bug_on(sbi, i->state != NID_NEW);
+ i = list_first_entry(&nm_i->free_nid_list,
+ struct free_nid, list);
*nid = i->nid;
- i->state = NID_ALLOC;
- nm_i->fcnt--;
- spin_unlock(&nm_i->free_nid_list_lock);
+
+ __move_free_nid(sbi, i, FREE_NID, PREALLOC_NID);
+ nm_i->available_nids--;
+
+ update_free_nid_bitmap(sbi, *nid, false, false);
+
+ spin_unlock(&nm_i->nid_list_lock);
return true;
}
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
/* Let's scan nat pages and its caches to get free nids */
- mutex_lock(&nm_i->build_lock);
- build_free_nids(sbi);
- mutex_unlock(&nm_i->build_lock);
- goto retry;
+ if (!f2fs_build_free_nids(sbi, true, false))
+ goto retry;
+ return false;
}
/*
- * alloc_nid() should be called prior to this function.
+ * f2fs_alloc_nid() should be called prior to this function.
*/
-void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
+void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
- __del_from_free_nid_list(nm_i, i);
- spin_unlock(&nm_i->free_nid_list_lock);
+ f2fs_bug_on(sbi, !i);
+ __remove_free_nid(sbi, i, PREALLOC_NID);
+ spin_unlock(&nm_i->nid_list_lock);
kmem_cache_free(free_nid_slab, i);
}
/*
- * alloc_nid() should be called prior to this function.
+ * f2fs_alloc_nid() should be called prior to this function.
*/
-void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
+void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
@@ -1943,120 +2400,141 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
if (!nid)
return;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
- if (!available_free_memory(sbi, FREE_NIDS)) {
- __del_from_free_nid_list(nm_i, i);
+ f2fs_bug_on(sbi, !i);
+
+ if (!f2fs_available_free_memory(sbi, FREE_NIDS)) {
+ __remove_free_nid(sbi, i, PREALLOC_NID);
need_free = true;
} else {
- i->state = NID_NEW;
- nm_i->fcnt++;
+ __move_free_nid(sbi, i, PREALLOC_NID, FREE_NID);
}
- spin_unlock(&nm_i->free_nid_list_lock);
+
+ nm_i->available_nids++;
+
+ update_free_nid_bitmap(sbi, nid, true, false);
+
+ spin_unlock(&nm_i->nid_list_lock);
if (need_free)
kmem_cache_free(free_nid_slab, i);
}
-int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
+int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next;
int nr = nr_shrink;
- if (nm_i->fcnt <= MAX_FREE_NIDS)
+ if (nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
return 0;
if (!mutex_trylock(&nm_i->build_lock))
return 0;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
- if (nr_shrink <= 0 || nm_i->fcnt <= MAX_FREE_NIDS)
+ if (nr_shrink <= 0 ||
+ nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
break;
- if (i->state == NID_ALLOC)
- continue;
- __del_from_free_nid_list(nm_i, i);
+
+ __remove_free_nid(sbi, i, FREE_NID);
kmem_cache_free(free_nid_slab, i);
- nm_i->fcnt--;
nr_shrink--;
}
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
mutex_unlock(&nm_i->build_lock);
return nr - nr_shrink;
}
-void recover_inline_xattr(struct inode *inode, struct page *page)
+void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
size_t inline_size;
struct page *ipage;
struct f2fs_inode *ri;
- ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
ri = F2FS_INODE(page);
- if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
+ if (ri->i_inline & F2FS_INLINE_XATTR) {
+ set_inode_flag(inode, FI_INLINE_XATTR);
+ } else {
clear_inode_flag(inode, FI_INLINE_XATTR);
goto update_inode;
}
- dst_addr = inline_xattr_addr(ipage);
- src_addr = inline_xattr_addr(page);
+ dst_addr = inline_xattr_addr(inode, ipage);
+ src_addr = inline_xattr_addr(inode, page);
inline_size = inline_xattr_size(inode);
- f2fs_wait_on_page_writeback(ipage, NODE, true);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
memcpy(dst_addr, src_addr, inline_size);
update_inode:
- update_inode(inode, ipage);
+ f2fs_update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
}
-void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
+int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
- nid_t new_xnid = nid_of_node(page);
+ nid_t new_xnid;
+ struct dnode_of_data dn;
struct node_info ni;
+ struct page *xpage;
+ int err;
- /* 1: invalidate the previous xattr nid */
if (!prev_xnid)
goto recover_xnid;
- /* Deallocate node address */
- get_node_info(sbi, prev_xnid, &ni);
- f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
- invalidate_blocks(sbi, ni.blk_addr);
- dec_valid_node_count(sbi, inode);
+ /* 1: invalidate the previous xattr nid */
+ err = f2fs_get_node_info(sbi, prev_xnid, &ni);
+ if (err)
+ return err;
+
+ f2fs_invalidate_blocks(sbi, ni.blk_addr);
+ dec_valid_node_count(sbi, inode, false);
set_node_addr(sbi, &ni, NULL_ADDR, false);
recover_xnid:
- /* 2: allocate new xattr nid */
- if (unlikely(!inc_valid_node_count(sbi, inode)))
- f2fs_bug_on(sbi, 1);
+ /* 2: update xattr nid in inode */
+ if (!f2fs_alloc_nid(sbi, &new_xnid))
+ return -ENOSPC;
- remove_free_nid(NM_I(sbi), new_xnid);
- get_node_info(sbi, new_xnid, &ni);
- ni.ino = inode->i_ino;
- set_node_addr(sbi, &ni, NEW_ADDR, false);
- f2fs_i_xnid_write(inode, new_xnid);
+ set_new_dnode(&dn, inode, NULL, NULL, new_xnid);
+ xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
+ if (IS_ERR(xpage)) {
+ f2fs_alloc_nid_failed(sbi, new_xnid);
+ return PTR_ERR(xpage);
+ }
- /* 3: update xattr blkaddr */
- refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
- set_node_addr(sbi, &ni, blkaddr, false);
+ f2fs_alloc_nid_done(sbi, new_xnid);
+ f2fs_update_inode_page(inode);
+
+ /* 3: update and set xattr node page dirty */
+ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE);
+
+ set_page_dirty(xpage);
+ f2fs_put_page(xpage, 1);
+
+ return 0;
}
-int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
+int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *src, *dst;
nid_t ino = ino_of_node(page);
struct node_info old_ni, new_ni;
struct page *ipage;
+ int err;
- get_node_info(sbi, ino, &old_ni);
+ err = f2fs_get_node_info(sbi, ino, &old_ni);
+ if (err)
+ return err;
if (unlikely(old_ni.blk_addr != NULL_ADDR))
return -EINVAL;
@@ -2068,11 +2546,12 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
}
/* Should not use this inode from free nid list */
- remove_free_nid(NM_I(sbi), ino);
+ remove_free_nid(sbi, ino);
if (!PageUptodate(ipage))
SetPageUptodate(ipage);
fill_node_footer(ipage, ino, ino, 0, true);
+ set_cold_node(ipage, false);
src = F2FS_INODE(page);
dst = F2FS_INODE(ipage);
@@ -2082,12 +2561,32 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
dst->i_blocks = cpu_to_le64(1);
dst->i_links = cpu_to_le32(1);
dst->i_xattr_nid = 0;
- dst->i_inline = src->i_inline & F2FS_INLINE_XATTR;
+ dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR);
+ if (dst->i_inline & F2FS_EXTRA_ATTR) {
+ dst->i_extra_isize = src->i_extra_isize;
+
+ if (f2fs_sb_has_flexible_inline_xattr(sbi) &&
+ F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+ i_inline_xattr_size))
+ dst->i_inline_xattr_size = src->i_inline_xattr_size;
+
+ if (f2fs_sb_has_project_quota(sbi) &&
+ F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+ i_projid))
+ dst->i_projid = src->i_projid;
+
+ if (f2fs_sb_has_inode_crtime(sbi) &&
+ F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+ i_crtime_nsec)) {
+ dst->i_crtime = src->i_crtime;
+ dst->i_crtime_nsec = src->i_crtime_nsec;
+ }
+ }
new_ni = old_ni;
new_ni.ino = ino;
- if (unlikely(!inc_valid_node_count(sbi, NULL)))
+ if (unlikely(inc_valid_node_count(sbi, NULL, true)))
WARN_ON(1);
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
inc_valid_inode_count(sbi);
@@ -2096,13 +2595,12 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
return 0;
}
-int restore_node_summary(struct f2fs_sb_info *sbi,
+int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum)
{
struct f2fs_node *rn;
struct f2fs_summary *sum_entry;
block_t addr;
- int bio_blocks = MAX_BIO_BLOCKS(sbi);
int i, idx, last_offset, nrpages;
/* scan the node segment */
@@ -2111,13 +2609,16 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
sum_entry = &sum->entries[0];
for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
- nrpages = min(last_offset - i, bio_blocks);
+ nrpages = min(last_offset - i, BIO_MAX_PAGES);
/* readahead node pages */
- ra_meta_pages(sbi, addr, nrpages, META_POR, true);
+ f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true);
for (idx = addr; idx < addr + nrpages; idx++) {
- struct page *page = get_tmp_page(sbi, idx);
+ struct page *page = f2fs_get_tmp_page(sbi, idx);
+
+ if (IS_ERR(page))
+ return PTR_ERR(page);
rn = F2FS_NODE(page);
sum_entry->nid = rn->footer.nid;
@@ -2150,9 +2651,22 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
ne = __lookup_nat_cache(nm_i, nid);
if (!ne) {
- ne = grab_nat_entry(nm_i, nid);
- node_info_from_raw_nat(&ne->ni, &raw_ne);
+ ne = __alloc_nat_entry(nid, true);
+ __init_nat_entry(nm_i, ne, &raw_ne, true);
}
+
+ /*
+ * if a free nat in journal has not been used after last
+ * checkpoint, we should remove it from available nids,
+ * since later we will add it again.
+ */
+ if (!get_nat_flag(ne, IS_DIRTY) &&
+ le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) {
+ spin_lock(&nm_i->nid_list_lock);
+ nm_i->available_nids--;
+ spin_unlock(&nm_i->nid_list_lock);
+ }
+
__set_nat_cache_dirty(nm_i, ne);
}
update_nats_in_cursum(journal, -i);
@@ -2177,8 +2691,41 @@ static void __adjust_nat_entry_set(struct nat_entry_set *nes,
list_add_tail(&nes->set_list, head);
}
-static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
- struct nat_entry_set *set)
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+ struct page *page)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK;
+ struct f2fs_nat_block *nat_blk = page_address(page);
+ int valid = 0;
+ int i = 0;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return;
+
+ if (nat_index == 0) {
+ valid = 1;
+ i = 1;
+ }
+ for (; i < NAT_ENTRY_PER_BLOCK; i++) {
+ if (nat_blk->entries[i].block_addr != NULL_ADDR)
+ valid++;
+ }
+ if (valid == 0) {
+ __set_bit_le(nat_index, nm_i->empty_nat_bits);
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
+ return;
+ }
+
+ __clear_bit_le(nat_index, nm_i->empty_nat_bits);
+ if (valid == NAT_ENTRY_PER_BLOCK)
+ __set_bit_le(nat_index, nm_i->full_nat_bits);
+ else
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
+}
+
+static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
+ struct nat_entry_set *set, struct cp_control *cpc)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
struct f2fs_journal *journal = curseg->journal;
@@ -2193,13 +2740,17 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
* #1, flush nat entries to journal in current hot data summary block.
* #2, flush nat entries to nat page.
*/
- if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
+ if (enabled_nat_bits(sbi, cpc) ||
+ !__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
to_journal = false;
if (to_journal) {
down_write(&curseg->journal_rwsem);
} else {
page = get_next_nat_page(sbi, start_nid);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
nat_blk = page_address(page);
f2fs_bug_on(sbi, !nat_blk);
}
@@ -2210,11 +2761,10 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
nid_t nid = nat_get_nid(ne);
int offset;
- if (nat_get_blkaddr(ne) == NEW_ADDR)
- continue;
+ f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR);
if (to_journal) {
- offset = lookup_journal_in_cursum(journal,
+ offset = f2fs_lookup_journal_in_cursum(journal,
NAT_JOURNAL, nid, 1);
f2fs_bug_on(sbi, offset < 0);
raw_ne = &nat_in_journal(journal, offset);
@@ -2224,26 +2774,35 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
}
raw_nat_from_node_info(raw_ne, &ne->ni);
nat_reset_flag(ne);
- __clear_nat_cache_dirty(NM_I(sbi), ne);
- if (nat_get_blkaddr(ne) == NULL_ADDR)
- add_free_nid(sbi, nid, false);
+ __clear_nat_cache_dirty(NM_I(sbi), set, ne);
+ if (nat_get_blkaddr(ne) == NULL_ADDR) {
+ add_free_nid(sbi, nid, false, true);
+ } else {
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ update_free_nid_bitmap(sbi, nid, false, false);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ }
}
- if (to_journal)
+ if (to_journal) {
up_write(&curseg->journal_rwsem);
- else
+ } else {
+ __update_nat_bits(sbi, start_nid, page);
f2fs_put_page(page, 1);
+ }
- f2fs_bug_on(sbi, set->entry_cnt);
-
- radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
- kmem_cache_free(nat_entry_set_slab, set);
+ /* Allow dirty nats by node block allocation in write_begin */
+ if (!set->entry_cnt) {
+ radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
+ kmem_cache_free(nat_entry_set_slab, set);
+ }
+ return 0;
}
/*
* This function is called during the checkpointing process.
*/
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -2253,9 +2812,17 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
unsigned int found;
nid_t set_idx = 0;
LIST_HEAD(sets);
+ int err = 0;
+
+ /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */
+ if (enabled_nat_bits(sbi, cpc)) {
+ down_write(&nm_i->nat_tree_lock);
+ remove_nats_in_journal(sbi);
+ up_write(&nm_i->nat_tree_lock);
+ }
if (!nm_i->dirty_nat_cnt)
- return;
+ return 0;
down_write(&nm_i->nat_tree_lock);
@@ -2264,7 +2831,8 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
* entries, remove all entries from journal and merge them
* into nat entry set.
*/
- if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+ if (enabled_nat_bits(sbi, cpc) ||
+ !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
while ((found = __gang_lookup_nat_set(nm_i,
@@ -2277,12 +2845,95 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
}
/* flush dirty nats in nat entry set */
- list_for_each_entry_safe(set, tmp, &sets, set_list)
- __flush_nat_entry_set(sbi, set);
+ list_for_each_entry_safe(set, tmp, &sets, set_list) {
+ err = __flush_nat_entry_set(sbi, set, cpc);
+ if (err)
+ break;
+ }
up_write(&nm_i->nat_tree_lock);
+ /* Allow dirty nats by node block allocation in write_begin */
- f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
+ return err;
+}
+
+static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE;
+ unsigned int i;
+ __u64 cp_ver = cur_cp_version(ckpt);
+ block_t nat_bits_addr;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return 0;
+
+ nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
+ nm_i->nat_bits = f2fs_kzalloc(sbi,
+ nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
+ if (!nm_i->nat_bits)
+ return -ENOMEM;
+
+ nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
+ nm_i->nat_bits_blocks;
+ for (i = 0; i < nm_i->nat_bits_blocks; i++) {
+ struct page *page;
+
+ page = f2fs_get_meta_page(sbi, nat_bits_addr++);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
+ memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+ page_address(page), F2FS_BLKSIZE);
+ f2fs_put_page(page, 1);
+ }
+
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+ if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
+ disable_nat_bits(sbi, true);
+ return 0;
+ }
+
+ nm_i->full_nat_bits = nm_i->nat_bits + 8;
+ nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
+
+ f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint");
+ return 0;
+}
+
+static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int i = 0;
+ nid_t nid, last_nid;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return;
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+
+ nid = i * NAT_ENTRY_PER_BLOCK;
+ last_nid = nid + NAT_ENTRY_PER_BLOCK;
+
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ for (; nid < last_nid; nid++)
+ update_free_nid_bitmap(sbi, nid, true, true);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ }
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+ }
}
static int init_node_manager(struct f2fs_sb_info *sbi)
@@ -2290,19 +2941,21 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
unsigned char *version_bitmap;
- unsigned int nat_segs, nat_blocks;
+ unsigned int nat_segs;
+ int err;
nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr);
/* segment_count_nat includes pair segment so divide to 2. */
nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
- nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
-
- nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+ nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
+ nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks;
/* not used nids: 0, node, meta, (and root counted as valid node) */
- nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM;
- nm_i->fcnt = 0;
+ nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
+ sbi->nquota_files - F2FS_RESERVED_NODE_NUM;
+ nm_i->nid_cnt[FREE_NID] = 0;
+ nm_i->nid_cnt[PREALLOC_NID] = 0;
nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
@@ -2313,9 +2966,10 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
INIT_LIST_HEAD(&nm_i->nat_entries);
+ spin_lock_init(&nm_i->nat_list_lock);
mutex_init(&nm_i->build_lock);
- spin_lock_init(&nm_i->free_nid_list_lock);
+ spin_lock_init(&nm_i->nid_list_lock);
init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
@@ -2328,14 +2982,60 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
GFP_KERNEL);
if (!nm_i->nat_bitmap)
return -ENOMEM;
+
+ err = __get_nat_bitmaps(sbi);
+ if (err)
+ return err;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size,
+ GFP_KERNEL);
+ if (!nm_i->nat_bitmap_mir)
+ return -ENOMEM;
+#endif
+
return 0;
}
-int build_node_manager(struct f2fs_sb_info *sbi)
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ int i;
+
+ nm_i->free_nid_bitmap =
+ f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *),
+ nm_i->nat_blocks),
+ GFP_KERNEL);
+ if (!nm_i->free_nid_bitmap)
+ return -ENOMEM;
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi,
+ f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK), GFP_KERNEL);
+ if (!nm_i->free_nid_bitmap[i])
+ return -ENOMEM;
+ }
+
+ nm_i->nat_block_bitmap = f2fs_kvzalloc(sbi, nm_i->nat_blocks / 8,
+ GFP_KERNEL);
+ if (!nm_i->nat_block_bitmap)
+ return -ENOMEM;
+
+ nm_i->free_nid_count =
+ f2fs_kvzalloc(sbi, array_size(sizeof(unsigned short),
+ nm_i->nat_blocks),
+ GFP_KERNEL);
+ if (!nm_i->free_nid_count)
+ return -ENOMEM;
+ return 0;
+}
+
+int f2fs_build_node_manager(struct f2fs_sb_info *sbi)
{
int err;
- sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL);
+ sbi->nm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_nm_info),
+ GFP_KERNEL);
if (!sbi->nm_info)
return -ENOMEM;
@@ -2343,11 +3043,17 @@ int build_node_manager(struct f2fs_sb_info *sbi)
if (err)
return err;
- build_free_nids(sbi);
- return 0;
+ err = init_free_nid_cache(sbi);
+ if (err)
+ return err;
+
+ /* load free nid status from nat_bits table */
+ load_free_nid_bitmap(sbi);
+
+ return f2fs_build_free_nids(sbi, true, true);
}
-void destroy_node_manager(struct f2fs_sb_info *sbi)
+void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next_i;
@@ -2360,17 +3066,17 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
return;
/* destroy free nid list */
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
- f2fs_bug_on(sbi, i->state == NID_ALLOC);
- __del_from_free_nid_list(nm_i, i);
- nm_i->fcnt--;
- spin_unlock(&nm_i->free_nid_list_lock);
+ __remove_free_nid(sbi, i, FREE_NID);
+ spin_unlock(&nm_i->nid_list_lock);
kmem_cache_free(free_nid_slab, i);
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
}
- f2fs_bug_on(sbi, nm_i->fcnt);
- spin_unlock(&nm_i->free_nid_list_lock);
+ f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID]);
+ f2fs_bug_on(sbi, nm_i->nid_cnt[PREALLOC_NID]);
+ f2fs_bug_on(sbi, !list_empty(&nm_i->free_nid_list));
+ spin_unlock(&nm_i->nid_list_lock);
/* destroy nat cache */
down_write(&nm_i->nat_tree_lock);
@@ -2379,8 +3085,13 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
unsigned idx;
nid = nat_get_nid(natvec[found - 1]) + 1;
- for (idx = 0; idx < found; idx++)
+ for (idx = 0; idx < found; idx++) {
+ spin_lock(&nm_i->nat_list_lock);
+ list_del(&natvec[idx]->list);
+ spin_unlock(&nm_i->nat_list_lock);
+
__del_from_nat_cache(nm_i, natvec[idx]);
+ }
}
f2fs_bug_on(sbi, nm_i->nat_cnt);
@@ -2400,12 +3111,26 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
}
up_write(&nm_i->nat_tree_lock);
- kfree(nm_i->nat_bitmap);
+ kvfree(nm_i->nat_block_bitmap);
+ if (nm_i->free_nid_bitmap) {
+ int i;
+
+ for (i = 0; i < nm_i->nat_blocks; i++)
+ kvfree(nm_i->free_nid_bitmap[i]);
+ kvfree(nm_i->free_nid_bitmap);
+ }
+ kvfree(nm_i->free_nid_count);
+
+ kvfree(nm_i->nat_bitmap);
+ kvfree(nm_i->nat_bits);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kvfree(nm_i->nat_bitmap_mir);
+#endif
sbi->nm_info = NULL;
- kfree(nm_i);
+ kvfree(nm_i);
}
-int __init create_node_manager_caches(void)
+int __init f2fs_create_node_manager_caches(void)
{
nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
sizeof(struct nat_entry));
@@ -2421,8 +3146,15 @@ int __init create_node_manager_caches(void)
sizeof(struct nat_entry_set));
if (!nat_entry_set_slab)
goto destroy_free_nid;
+
+ fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry",
+ sizeof(struct fsync_node_entry));
+ if (!fsync_node_entry_slab)
+ goto destroy_nat_entry_set;
return 0;
+destroy_nat_entry_set:
+ kmem_cache_destroy(nat_entry_set_slab);
destroy_free_nid:
kmem_cache_destroy(free_nid_slab);
destroy_nat_entry:
@@ -2431,8 +3163,9 @@ int __init create_node_manager_caches(void)
return -ENOMEM;
}
-void destroy_node_manager_caches(void)
+void f2fs_destroy_node_manager_caches(void)
{
+ kmem_cache_destroy(fsync_node_entry_slab);
kmem_cache_destroy(nat_entry_set_slab);
kmem_cache_destroy(free_nid_slab);
kmem_cache_destroy(nat_entry_slab);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 868bec6..e05af5d 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -1,18 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/node.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
/* start node id of a node block dedicated to the given node id */
-#define START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
+#define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
/* node block offset on the NAT area dedicated to the given start node id */
-#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
+#define NAT_BLOCK_OFFSET(start_nid) ((start_nid) / NAT_ENTRY_PER_BLOCK)
/* # of pages to perform synchronous readahead before building free nids */
#define FREE_NID_PAGES 8
@@ -44,6 +41,7 @@ enum {
HAS_FSYNCED_INODE, /* is the inode fsynced before? */
HAS_LAST_FSYNC, /* has the latest node fsync mark? */
IS_DIRTY, /* this nat entry is dirty? */
+ IS_PREALLOC, /* nat entry is preallocated */
};
/*
@@ -62,16 +60,16 @@ struct nat_entry {
struct node_info ni; /* in-memory node information */
};
-#define nat_get_nid(nat) (nat->ni.nid)
-#define nat_set_nid(nat, n) (nat->ni.nid = n)
-#define nat_get_blkaddr(nat) (nat->ni.blk_addr)
-#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b)
-#define nat_get_ino(nat) (nat->ni.ino)
-#define nat_set_ino(nat, i) (nat->ni.ino = i)
-#define nat_get_version(nat) (nat->ni.version)
-#define nat_set_version(nat, v) (nat->ni.version = v)
+#define nat_get_nid(nat) ((nat)->ni.nid)
+#define nat_set_nid(nat, n) ((nat)->ni.nid = (n))
+#define nat_get_blkaddr(nat) ((nat)->ni.blk_addr)
+#define nat_set_blkaddr(nat, b) ((nat)->ni.blk_addr = (b))
+#define nat_get_ino(nat) ((nat)->ni.ino)
+#define nat_set_ino(nat, i) ((nat)->ni.ino = (i))
+#define nat_get_version(nat) ((nat)->ni.version)
+#define nat_set_version(nat, v) ((nat)->ni.version = (v))
-#define inc_node_version(version) (++version)
+#define inc_node_version(version) (++(version))
static inline void copy_node_info(struct node_info *dst,
struct node_info *src)
@@ -134,12 +132,18 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
}
+static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
+{
+ return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8;
+}
+
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
DIRTY_DENTS, /* indicates dirty dentry pages */
INO_ENTRIES, /* indicates inode entries */
EXTENT_CACHE, /* indicates extent cache */
+ INMEM_PAGES, /* indicates inmemory pages */
BASE_CHECK, /* check kernel status */
};
@@ -150,18 +154,10 @@ struct nat_entry_set {
unsigned int entry_cnt; /* the # of nat entries in set */
};
-/*
- * For free nid mangement
- */
-enum nid_state {
- NID_NEW, /* newly added to free nid list */
- NID_ALLOC /* it is allocated */
-};
-
struct free_nid {
struct list_head list; /* for free node id list */
nid_t nid; /* node id */
- int state; /* in use or not: NID_NEW or NID_ALLOC */
+ int state; /* in use or not: FREE_NID or PREALLOC_NID */
};
static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
@@ -169,14 +165,14 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
- spin_lock(&nm_i->free_nid_list_lock);
- if (nm_i->fcnt <= 0) {
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
+ if (nm_i->nid_cnt[FREE_NID] <= 0) {
+ spin_unlock(&nm_i->nid_list_lock);
return;
}
- fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
+ fnid = list_first_entry(&nm_i->free_nid_list, struct free_nid, list);
*nid = fnid->nid;
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
}
/*
@@ -185,6 +181,12 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+ nm_i->bitmap_size))
+ f2fs_bug_on(sbi, 1);
+#endif
memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
}
@@ -193,13 +195,16 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
struct f2fs_nm_info *nm_i = NM_I(sbi);
pgoff_t block_off;
pgoff_t block_addr;
- int seg_off;
+ /*
+ * block_off = segment_off * 512 + off_in_segment
+ * OLD = (segment_off * 512) * 2 + off_in_segment
+ * NEW = 2 * (segment_off * 512 + off_in_segment) - off_in_segment
+ */
block_off = NAT_BLOCK_OFFSET(start);
- seg_off = block_off >> sbi->log_blocks_per_seg;
block_addr = (pgoff_t)(nm_i->nat_blkaddr +
- (seg_off << sbi->log_blocks_per_seg << 1) +
+ (block_off << 1) -
(block_off & (sbi->blocks_per_seg - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
@@ -214,11 +219,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
struct f2fs_nm_info *nm_i = NM_I(sbi);
block_addr -= nm_i->nat_blkaddr;
- if ((block_addr >> sbi->log_blocks_per_seg) % 2)
- block_addr -= sbi->blocks_per_seg;
- else
- block_addr += sbi->blocks_per_seg;
-
+ block_addr ^= 1 << sbi->log_blocks_per_seg;
return block_addr + nm_i->nat_blkaddr;
}
@@ -227,6 +228,9 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
}
static inline nid_t ino_of_node(struct page *node_page)
@@ -290,14 +294,11 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
- size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
- __u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
+ __u64 cp_ver = cur_cp_version(ckpt);
- if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
- __u64 crc = le32_to_cpu(*((__le32 *)
- ((unsigned char *)ckpt + crc_offset)));
- cp_ver |= (crc << 32);
- }
+ if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+
rn->footer.cp_ver = cpu_to_le64(cp_ver);
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
@@ -305,15 +306,16 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
static inline bool is_recoverable_dnode(struct page *page)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
- size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
__u64 cp_ver = cur_cp_version(ckpt);
- if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
- __u64 crc = le32_to_cpu(*((__le32 *)
- ((unsigned char *)ckpt + crc_offset)));
- cp_ver |= (crc << 32);
- }
- return cpu_to_le64(cp_ver) == cpver_of_node(page);
+ /* Don't care crc part, if fsck.f2fs sets it. */
+ if (__is_set_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG))
+ return (cp_ver << 32) == (cpver_of_node(page) << 32);
+
+ if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+
+ return cp_ver == cpver_of_node(page);
}
/*
@@ -342,7 +344,7 @@ static inline bool IS_DNODE(struct page *node_page)
unsigned int ofs = ofs_of_node(node_page);
if (f2fs_has_xattr_block(ofs))
- return false;
+ return true;
if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
ofs == 5 + 2 * NIDS_PER_BLOCK)
@@ -359,7 +361,7 @@ static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
- f2fs_wait_on_page_writeback(p, NODE, true);
+ f2fs_wait_on_page_writeback(p, NODE, true, true);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
@@ -423,12 +425,12 @@ static inline void clear_inline_node(struct page *page)
ClearPageChecked(page);
}
-static inline void set_cold_node(struct inode *inode, struct page *page)
+static inline void set_cold_node(struct page *page, bool is_dir)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
- if (S_ISDIR(inode->i_mode))
+ if (is_dir)
flag &= ~(0x1 << COLD_BIT_SHIFT);
else
flag |= (0x1 << COLD_BIT_SHIFT);
@@ -444,6 +446,10 @@ static inline void set_mark(struct page *page, int mark, int type)
else
flag &= ~(0x1 << type);
rn->footer.flag = cpu_to_le32(flag);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_inode_chksum_set(F2FS_P_SB(page), page);
+#endif
}
#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT)
#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index e87b7d7..258c31b 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/recovery.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -47,7 +44,7 @@
static struct kmem_cache *fsync_entry_slab;
-bool space_for_roll_forward(struct f2fs_sb_info *sbi)
+bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
@@ -69,24 +66,42 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
}
static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
- struct list_head *head, nid_t ino)
+ struct list_head *head, nid_t ino, bool quota_inode)
{
struct inode *inode;
struct fsync_inode_entry *entry;
+ int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
+ err = dquot_initialize(inode);
+ if (err)
+ goto err_out;
+
+ if (quota_inode) {
+ err = dquot_alloc_inode(inode);
+ if (err)
+ goto err_out;
+ }
+
entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
entry->inode = inode;
list_add_tail(&entry->list, head);
return entry;
+err_out:
+ iput(inode);
+ return ERR_PTR(err);
}
-static void del_fsync_inode(struct fsync_inode_entry *entry)
+static void del_fsync_inode(struct fsync_inode_entry *entry, int drop)
{
+ if (drop) {
+ /* inode should not be recovered, drop it */
+ f2fs_inode_synced(entry->inode);
+ }
iput(entry->inode);
list_del(&entry->list);
kmem_cache_free(fsync_entry_slab, entry);
@@ -107,7 +122,8 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
entry = get_fsync_inode(dir_list, pino);
if (!entry) {
- entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino);
+ entry = add_fsync_inode(F2FS_I_SB(inode), dir_list,
+ pino, false);
if (IS_ERR(entry)) {
dir = ERR_CAST(entry);
err = PTR_ERR(entry);
@@ -129,7 +145,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
retry:
de = __f2fs_find_entry(dir, &fname, &page);
if (de && inode->i_ino == le32_to_cpu(de->ino))
- goto out_unmap_put;
+ goto out_put;
if (de) {
einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
@@ -138,12 +154,19 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
err = PTR_ERR(einode);
if (err == -ENOENT)
err = -EEXIST;
- goto out_unmap_put;
+ goto out_put;
}
- err = acquire_orphan_inode(F2FS_I_SB(inode));
+
+ err = dquot_initialize(einode);
if (err) {
iput(einode);
- goto out_unmap_put;
+ goto out_put;
+ }
+
+ err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode));
+ if (err) {
+ iput(einode);
+ goto out_put;
}
f2fs_delete_entry(de, page, dir, einode);
iput(einode);
@@ -151,15 +174,14 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
- err = __f2fs_do_add_link(dir, &fname, inode,
+ err = f2fs_add_dentry(dir, &fname, inode,
inode->i_ino, inode->i_mode);
}
if (err == -ENOMEM)
goto retry;
goto out;
-out_unmap_put:
- f2fs_dentry_kunmap(dir, page);
+out_put:
f2fs_put_page(page, 0);
out:
if (file_enc_name(inode))
@@ -173,36 +195,110 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
return err;
}
-static void recover_inode(struct inode *inode, struct page *page)
+static int recover_quota_data(struct inode *inode, struct page *page)
+{
+ struct f2fs_inode *raw = F2FS_INODE(page);
+ struct iattr attr;
+ uid_t i_uid = le32_to_cpu(raw->i_uid);
+ gid_t i_gid = le32_to_cpu(raw->i_gid);
+ int err;
+
+ memset(&attr, 0, sizeof(attr));
+
+ attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid);
+ attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid);
+
+ if (!uid_eq(attr.ia_uid, inode->i_uid))
+ attr.ia_valid |= ATTR_UID;
+ if (!gid_eq(attr.ia_gid, inode->i_gid))
+ attr.ia_valid |= ATTR_GID;
+
+ if (!attr.ia_valid)
+ return 0;
+
+ err = dquot_transfer(inode, &attr);
+ if (err)
+ set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR);
+ return err;
+}
+
+static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
+{
+ if (ri->i_inline & F2FS_PIN_FILE)
+ set_inode_flag(inode, FI_PIN_FILE);
+ else
+ clear_inode_flag(inode, FI_PIN_FILE);
+ if (ri->i_inline & F2FS_DATA_EXIST)
+ set_inode_flag(inode, FI_DATA_EXIST);
+ else
+ clear_inode_flag(inode, FI_DATA_EXIST);
+}
+
+static int recover_inode(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
char *name;
+ int err;
inode->i_mode = le16_to_cpu(raw->i_mode);
+
+ err = recover_quota_data(inode, page);
+ if (err)
+ return err;
+
i_uid_write(inode, le32_to_cpu(raw->i_uid));
i_gid_write(inode, le32_to_cpu(raw->i_gid));
+
+ if (raw->i_inline & F2FS_EXTRA_ATTR) {
+ if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
+ F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize),
+ i_projid)) {
+ projid_t i_projid;
+
+ i_projid = (projid_t)le32_to_cpu(raw->i_projid);
+ F2FS_I(inode)->i_projid =
+ make_kprojid(&init_user_ns, i_projid);
+ }
+ }
+
f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
- inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+ inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
- inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ F2FS_I(inode)->i_advise = raw->i_advise;
+ F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
+ f2fs_set_inode_flags(inode);
+ F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] =
+ le16_to_cpu(raw->i_gc_failures);
+
+ recover_inline_flags(inode, raw);
+
+ f2fs_mark_inode_dirty_sync(inode, true);
+
if (file_enc_name(inode))
name = "<encrypted>";
else
name = F2FS_INODE(page)->i_name;
- f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
- ino_of_node(page), name);
+ f2fs_msg(inode->i_sb, KERN_NOTICE,
+ "recover_inode: ino = %x, name = %s, inline = %x",
+ ino_of_node(page), name, raw->i_inline);
+ return 0;
}
-static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
+static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
+ bool check_only)
{
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
+ unsigned int loop_cnt = 0;
+ unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg -
+ valid_user_blocks(sbi);
int err = 0;
/* get node pages in the current segment */
@@ -215,7 +311,11 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
- page = get_tmp_page(sbi, blkaddr);
+ page = f2fs_get_tmp_page(sbi, blkaddr);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ break;
+ }
if (!is_recoverable_dnode(page))
break;
@@ -225,17 +325,22 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry) {
- if (IS_INODE(page) && is_dent_dnode(page)) {
- err = recover_inode_page(sbi, page);
+ bool quota_inode = false;
+
+ if (!check_only &&
+ IS_INODE(page) && is_dent_dnode(page)) {
+ err = f2fs_recover_inode_page(sbi, page);
if (err)
break;
+ quota_inode = true;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry = add_fsync_inode(sbi, head, ino_of_node(page));
+ entry = add_fsync_inode(sbi, head, ino_of_node(page),
+ quota_inode);
if (IS_ERR(entry)) {
err = PTR_ERR(entry);
if (err == -ENOENT) {
@@ -250,22 +355,33 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
if (IS_INODE(page) && is_dent_dnode(page))
entry->last_dentry = blkaddr;
next:
+ /* sanity check in order to detect looped node chain */
+ if (++loop_cnt >= free_blocks ||
+ blkaddr == next_blkaddr_of_node(page)) {
+ f2fs_msg(sbi->sb, KERN_NOTICE,
+ "%s: detect looped node chain, "
+ "blkaddr:%u, next:%u",
+ __func__, blkaddr, next_blkaddr_of_node(page));
+ err = -EINVAL;
+ break;
+ }
+
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
- ra_meta_pages_cond(sbi, blkaddr);
+ f2fs_ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
}
-static void destroy_fsync_dnodes(struct list_head *head)
+static void destroy_fsync_dnodes(struct list_head *head, int drop)
{
struct fsync_inode_entry *entry, *tmp;
list_for_each_entry_safe(entry, tmp, head, list)
- del_fsync_inode(entry);
+ del_fsync_inode(entry, drop);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -297,7 +413,9 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
}
}
- sum_page = get_sum_page(sbi, segno);
+ sum_page = f2fs_get_sum_page(sbi, segno);
+ if (IS_ERR(sum_page))
+ return PTR_ERR(sum_page);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
sum = sum_node->entries[blkoff];
f2fs_put_page(sum_page, 1);
@@ -317,7 +435,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
}
/* Get the node page */
- node_page = get_node_page(sbi, nid);
+ node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@@ -326,15 +444,24 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
+ int ret;
+
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
+
+ ret = dquot_initialize(inode);
+ if (ret) {
+ iput(inode);
+ return ret;
+ }
} else {
inode = dn->inode;
}
- bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
+ bidx = f2fs_start_bidx_of_node(offset, inode) +
+ le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
@@ -344,11 +471,11 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
- if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
+ if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
- truncate_data_blocks_range(&tdn, 1);
+ f2fs_truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
@@ -359,15 +486,16 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
return 0;
truncate_out:
- if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr)
- truncate_data_blocks_range(&tdn, 1);
+ if (datablock_addr(tdn.inode, tdn.node_page,
+ tdn.ofs_in_node) == blkaddr)
+ f2fs_truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
- struct page *page, block_t blkaddr)
+ struct page *page)
{
struct dnode_of_data dn;
struct node_info ni;
@@ -376,27 +504,25 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
/* step 1: recover xattr */
if (IS_INODE(page)) {
- recover_inline_xattr(inode, page);
+ f2fs_recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
- /*
- * Deprecated; xattr blocks should be found from cold log.
- * But, we should remain this for backward compatibility.
- */
- recover_xattr_data(inode, page, blkaddr);
+ err = f2fs_recover_xattr_data(inode, page);
+ if (!err)
+ recovered++;
goto out;
}
/* step 2: recover inline data */
- if (recover_inline_data(inode, page))
+ if (f2fs_recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
- start = start_bidx_of_node(ofs_of_node(page), inode);
+ start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
- err = get_dnode_of_data(&dn, start, ALLOC_NODE);
+ err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
@@ -405,9 +531,12 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
goto out;
}
- f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
+ f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
- get_node_info(sbi, dn.nid, &ni);
+ err = f2fs_get_node_info(sbi, dn.nid, &ni);
+ if (err)
+ goto err;
+
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
@@ -422,8 +551,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
- src = datablock_addr(dn.node_page, dn.ofs_in_node);
- dest = datablock_addr(page, dn.ofs_in_node);
+ src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
+ dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
/* skip recovering if dest is the same as src */
if (src == dest)
@@ -431,20 +560,22 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
- truncate_data_blocks_range(&dn, 1);
+ f2fs_truncate_data_blocks_range(&dn, 1);
continue;
}
- if ((start + 1) << PAGE_SHIFT > i_size_read(inode))
- f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+ if (!file_keep_isize(inode) &&
+ (i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
+ f2fs_i_size_write(inode,
+ (loff_t)(start + 1) << PAGE_SHIFT);
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
- truncate_data_blocks_range(&dn, 1);
- reserve_new_block(&dn);
+ f2fs_truncate_data_blocks_range(&dn, 1);
+ f2fs_reserve_new_block(&dn);
continue;
}
@@ -452,11 +583,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
- err = reserve_new_block(&dn);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- while (err)
- err = reserve_new_block(&dn);
-#endif
+ err = f2fs_reserve_new_block(&dn);
+ while (err &&
+ IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION))
+ err = f2fs_reserve_new_block(&dn);
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
@@ -488,13 +618,15 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
f2fs_put_dnode(&dn);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
- "recover_data: ino = %lx, recovered = %d blocks, err = %d",
- inode->i_ino, recovered, err);
+ "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
+ inode->i_ino,
+ file_keep_isize(inode) ? "keep" : "recover",
+ recovered, err);
return err;
}
static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
- struct list_head *dir_list)
+ struct list_head *tmp_inode_list, struct list_head *dir_list)
{
struct curseg_info *curseg;
struct page *page = NULL;
@@ -511,9 +643,13 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
- ra_meta_pages_cond(sbi, blkaddr);
+ f2fs_ra_meta_pages_cond(sbi, blkaddr);
- page = get_tmp_page(sbi, blkaddr);
+ page = f2fs_get_tmp_page(sbi, blkaddr);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ break;
+ }
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
@@ -528,8 +664,11 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
- if (IS_INODE(page))
- recover_inode(entry->inode, page);
+ if (IS_INODE(page)) {
+ err = recover_inode(entry->inode, page);
+ if (err)
+ break;
+ }
if (entry->last_dentry == blkaddr) {
err = recover_dentry(entry->inode, page, dir_list);
if (err) {
@@ -537,65 +676,86 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
break;
}
}
- err = do_recover_data(sbi, entry->inode, page, blkaddr);
+ err = do_recover_data(sbi, entry->inode, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
if (entry->blkaddr == blkaddr)
- del_fsync_inode(entry);
+ list_move_tail(&entry->list, tmp_inode_list);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
}
if (!err)
- allocate_new_segments(sbi);
+ f2fs_allocate_new_segments(sbi);
return err;
}
-int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
+int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
- struct list_head inode_list;
+ struct list_head inode_list, tmp_inode_list;
struct list_head dir_list;
- block_t blkaddr;
int err;
int ret = 0;
+ unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
+#ifdef CONFIG_QUOTA
+ int quota_enabled;
+#endif
+
+ if (s_flags & MS_RDONLY) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "recover fsync data on readonly fs");
+ sbi->sb->s_flags &= ~MS_RDONLY;
+ }
+
+#ifdef CONFIG_QUOTA
+ /* Needed for iput() to work correctly and not trash data */
+ sbi->sb->s_flags |= MS_ACTIVE;
+ /* Turn on quotas so that they are updated correctly */
+ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
+#endif
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
sizeof(struct fsync_inode_entry));
- if (!fsync_entry_slab)
- return -ENOMEM;
+ if (!fsync_entry_slab) {
+ err = -ENOMEM;
+ goto out;
+ }
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&tmp_inode_list);
INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
- blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
-
/* step #1: find fsynced inode numbers */
- err = find_fsync_dnodes(sbi, &inode_list);
+ err = find_fsync_dnodes(sbi, &inode_list, check_only);
if (err || list_empty(&inode_list))
- goto out;
+ goto skip;
if (check_only) {
ret = 1;
- goto out;
+ goto skip;
}
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list, &dir_list);
+ err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
-out:
- destroy_fsync_dnodes(&inode_list);
+ else {
+ /* restore s_flags to let iput() trash data */
+ sbi->sb->s_flags = s_flags;
+ }
+skip:
+ destroy_fsync_dnodes(&inode_list, err);
+ destroy_fsync_dnodes(&tmp_inode_list, err);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
@@ -604,21 +764,33 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
+ } else {
+ clear_sbi_flag(sbi, SBI_POR_DOING);
}
-
- clear_sbi_flag(sbi, SBI_POR_DOING);
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
- destroy_fsync_dnodes(&dir_list);
+ destroy_fsync_dnodes(&dir_list, err);
- if (!err && need_writecp) {
- struct cp_control cpc = {
- .reason = CP_RECOVERY,
- };
- err = write_checkpoint(sbi, &cpc);
+ if (need_writecp) {
+ set_sbi_flag(sbi, SBI_IS_RECOVERED);
+
+ if (!err) {
+ struct cp_control cpc = {
+ .reason = CP_RECOVERY,
+ };
+ err = f2fs_write_checkpoint(sbi, &cpc);
+ }
}
kmem_cache_destroy(fsync_entry_slab);
+out:
+#ifdef CONFIG_QUOTA
+ /* Turn quotas off */
+ if (quota_enabled)
+ f2fs_quota_off_umount(sbi->sb);
+#endif
+ sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+
return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index c4c84af..0f090f3 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/segment.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -16,17 +13,20 @@
#include <linux/kthread.h>
#include <linux/swap.h>
#include <linux/timer.h>
+#include <linux/freezer.h>
+#include <linux/sched.h>
#include "f2fs.h"
#include "segment.h"
#include "node.h"
+#include "gc.h"
#include "trace.h"
#include <trace/events/f2fs.h>
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *bio_entry_slab;
+static struct kmem_cache *discard_cmd_slab;
static struct kmem_cache *sit_entry_set_slab;
static struct kmem_cache *inmem_entry_slab;
@@ -166,15 +166,32 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
return result - size + __reverse_ffz(tmp);
}
-void register_inmem_page(struct inode *inode, struct page *page)
+bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
{
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
+ if (test_opt(sbi, LFS))
+ return false;
+ if (sbi->gc_mode == GC_URGENT)
+ return true;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return true;
+
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
+ SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
+}
+
+void f2fs_register_inmem_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct inmem_pages *new;
f2fs_trace_pid(page);
- set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
- SetPagePrivate(page);
+ f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
@@ -186,6 +203,10 @@ void register_inmem_page(struct inode *inode, struct page *page)
mutex_lock(&fi->inmem_lock);
get_page(page);
list_add_tail(&new->list, &fi->inmem_pages);
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ if (list_empty(&fi->inmem_ilist))
+ list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
mutex_unlock(&fi->inmem_lock);
@@ -193,7 +214,8 @@ void register_inmem_page(struct inode *inode, struct page *page)
}
static int __revoke_inmem_pages(struct inode *inode,
- struct list_head *head, bool drop, bool recover)
+ struct list_head *head, bool drop, bool recover,
+ bool trylock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct inmem_pages *cur, *tmp;
@@ -205,23 +227,49 @@ static int __revoke_inmem_pages(struct inode *inode,
if (drop)
trace_f2fs_commit_inmem_page(page, INMEM_DROP);
- lock_page(page);
+ if (trylock) {
+ /*
+ * to avoid deadlock in between page lock and
+ * inmem_lock.
+ */
+ if (!trylock_page(page))
+ continue;
+ } else {
+ lock_page(page);
+ }
- f2fs_wait_on_page_writeback(page, DATA, true);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
if (recover) {
struct dnode_of_data dn;
struct node_info ni;
trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
-
+retry:
set_new_dnode(&dn, inode, NULL, NULL, 0);
- if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+ err = f2fs_get_dnode_of_data(&dn, page->index,
+ LOOKUP_NODE);
+ if (err) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto retry;
+ }
err = -EAGAIN;
goto next;
}
- get_node_info(sbi, dn.nid, &ni);
- f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+
+ err = f2fs_get_node_info(sbi, dn.nid, &ni);
+ if (err) {
+ f2fs_put_dnode(&dn);
+ return err;
+ }
+
+ if (cur->old_addr == NEW_ADDR) {
+ f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
+ f2fs_update_data_blkaddr(&dn, NEW_ADDR);
+ } else
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
cur->old_addr, ni.version, true, true);
f2fs_put_dnode(&dn);
}
@@ -231,8 +279,7 @@ static int __revoke_inmem_pages(struct inode *inode,
ClearPageUptodate(page);
clear_cold_data(page);
}
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ f2fs_clear_page_private(page);
f2fs_put_page(page, 1);
list_del(&cur->list);
@@ -242,33 +289,110 @@ static int __revoke_inmem_pages(struct inode *inode,
return err;
}
-void drop_inmem_pages(struct inode *inode)
+void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
+ struct inode *inode;
+ struct f2fs_inode_info *fi;
+next:
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ if (list_empty(head)) {
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ return;
+ }
+ fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
+ inode = igrab(&fi->vfs_inode);
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- clear_inode_flag(inode, FI_ATOMIC_FILE);
-
- mutex_lock(&fi->inmem_lock);
- __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
- mutex_unlock(&fi->inmem_lock);
+ if (inode) {
+ if (gc_failure) {
+ if (fi->i_gc_failures[GC_FAILURE_ATOMIC])
+ goto drop;
+ goto skip;
+ }
+drop:
+ set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
+ f2fs_drop_inmem_pages(inode);
+ iput(inode);
+ }
+skip:
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto next;
}
-static int __commit_inmem_pages(struct inode *inode,
- struct list_head *revoke_list)
+void f2fs_drop_inmem_pages(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ while (!list_empty(&fi->inmem_pages)) {
+ mutex_lock(&fi->inmem_lock);
+ __revoke_inmem_pages(inode, &fi->inmem_pages,
+ true, false, true);
+
+ if (list_empty(&fi->inmem_pages)) {
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ if (!list_empty(&fi->inmem_ilist))
+ list_del_init(&fi->inmem_ilist);
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ }
+ mutex_unlock(&fi->inmem_lock);
+ }
+
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
+ stat_dec_atomic_write(inode);
+}
+
+void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct list_head *head = &fi->inmem_pages;
+ struct inmem_pages *cur = NULL;
+
+ f2fs_bug_on(sbi, !IS_ATOMIC_WRITTEN_PAGE(page));
+
+ mutex_lock(&fi->inmem_lock);
+ list_for_each_entry(cur, head, list) {
+ if (cur->page == page)
+ break;
+ }
+
+ f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
+ list_del(&cur->list);
+ mutex_unlock(&fi->inmem_lock);
+
+ dec_page_count(sbi, F2FS_INMEM_PAGES);
+ kmem_cache_free(inmem_entry_slab, cur);
+
+ ClearPageUptodate(page);
+ f2fs_clear_page_private(page);
+ f2fs_put_page(page, 0);
+
+ trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
+}
+
+static int __f2fs_commit_inmem_pages(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct inmem_pages *cur, *tmp;
struct f2fs_io_info fio = {
.sbi = sbi,
+ .ino = inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
- .op_flags = WRITE_SYNC | REQ_PRIO,
- .encrypted_page = NULL,
+ .op_flags = REQ_SYNC | REQ_PRIO,
+ .io_type = FS_DATA_IO,
};
+ struct list_head revoke_list;
bool submit_bio = false;
int err = 0;
+ INIT_LIST_HEAD(&revoke_list);
+
list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
struct page *page = cur->page;
@@ -276,52 +400,40 @@ static int __commit_inmem_pages(struct inode *inode,
if (page->mapping == inode->i_mapping) {
trace_f2fs_commit_inmem_page(page, INMEM);
- set_page_dirty(page);
- f2fs_wait_on_page_writeback(page, DATA, true);
- if (clear_page_dirty_for_io(page))
- inode_dec_dirty_pages(inode);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+ set_page_dirty(page);
+ if (clear_page_dirty_for_io(page)) {
+ inode_dec_dirty_pages(inode);
+ f2fs_remove_dirty_inode(inode);
+ }
+retry:
fio.page = page;
- err = do_write_data_page(&fio);
+ fio.old_blkaddr = NULL_ADDR;
+ fio.encrypted_page = NULL;
+ fio.need_lock = LOCK_DONE;
+ err = f2fs_do_write_data_page(&fio);
if (err) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto retry;
+ }
unlock_page(page);
break;
}
-
/* record old blkaddr for revoking */
cur->old_addr = fio.old_blkaddr;
-
- clear_cold_data(page);
submit_bio = true;
}
unlock_page(page);
- list_move_tail(&cur->list, revoke_list);
+ list_move_tail(&cur->list, &revoke_list);
}
if (submit_bio)
- f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+ f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);
- if (!err)
- __revoke_inmem_pages(inode, revoke_list, false, false);
-
- return err;
-}
-
-int commit_inmem_pages(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- struct list_head revoke_list;
- int err;
-
- INIT_LIST_HEAD(&revoke_list);
- f2fs_balance_fs(sbi, true);
- f2fs_lock_op(sbi);
-
- mutex_lock(&fi->inmem_lock);
- err = __commit_inmem_pages(inode, &revoke_list);
if (err) {
- int ret;
/*
* try to revoke all committed pages, but still we could fail
* due to no memory or other reason, if that happened, EAGAIN
@@ -330,16 +442,47 @@ int commit_inmem_pages(struct inode *inode)
* recovery or rewrite & commit last transaction. For other
* error number, revoking was done by filesystem itself.
*/
- ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
- if (ret)
- err = ret;
+ err = __revoke_inmem_pages(inode, &revoke_list,
+ false, true, false);
/* drop all uncommitted pages */
- __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+ __revoke_inmem_pages(inode, &fi->inmem_pages,
+ true, false, false);
+ } else {
+ __revoke_inmem_pages(inode, &revoke_list,
+ false, false, false);
}
+
+ return err;
+}
+
+int f2fs_commit_inmem_pages(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ int err;
+
+ f2fs_balance_fs(sbi, true);
+
+ down_write(&fi->i_gc_rwsem[WRITE]);
+
+ f2fs_lock_op(sbi);
+ set_inode_flag(inode, FI_ATOMIC_COMMIT);
+
+ mutex_lock(&fi->inmem_lock);
+ err = __f2fs_commit_inmem_pages(inode);
+
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ if (!list_empty(&fi->inmem_ilist))
+ list_del_init(&fi->inmem_ilist);
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
mutex_unlock(&fi->inmem_lock);
+ clear_inode_flag(inode, FI_ATOMIC_COMMIT);
+
f2fs_unlock_op(sbi);
+ up_write(&fi->i_gc_rwsem[WRITE]);
+
return err;
}
@@ -349,25 +492,25 @@ int commit_inmem_pages(struct inode *inode)
*/
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_CHECKPOINT))
+ if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+ f2fs_show_injection_info(FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
-#endif
-
- if (!need)
- return;
+ }
/* balance_fs_bg is able to be pending */
- if (excess_cached_nats(sbi))
+ if (need && excess_cached_nats(sbi))
f2fs_balance_fs_bg(sbi);
+ if (f2fs_is_checkpoint_ready(sbi))
+ return;
+
/*
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
*/
if (has_not_enough_free_secs(sbi, 0, 0)) {
mutex_lock(&sbi->gc_mutex);
- f2fs_gc(sbi, false);
+ f2fs_gc(sbi, false, false, NULL_SEGNO);
}
}
@@ -377,29 +520,34 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
return;
/* try to shrink extent cache when there is no enough memory */
- if (!available_free_memory(sbi, EXTENT_CACHE))
+ if (!f2fs_available_free_memory(sbi, EXTENT_CACHE))
f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
/* check the # of cached NAT entries */
- if (!available_free_memory(sbi, NAT_ENTRIES))
- try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
+ if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
+ f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
- if (!available_free_memory(sbi, FREE_NIDS))
- try_to_free_nids(sbi, MAX_FREE_NIDS);
+ if (!f2fs_available_free_memory(sbi, FREE_NIDS))
+ f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS);
else
- build_free_nids(sbi);
+ f2fs_build_free_nids(sbi, false, false);
+
+ if (!is_idle(sbi, REQ_TIME) &&
+ (!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi)))
+ return;
/* checkpoint is the only way to shrink partial cached entries */
- if (!available_free_memory(sbi, NAT_ENTRIES) ||
- !available_free_memory(sbi, INO_ENTRIES) ||
+ if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
+ !f2fs_available_free_memory(sbi, INO_ENTRIES) ||
excess_prefree_segs(sbi) ||
excess_dirty_nats(sbi) ||
- (is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+ excess_dirty_nodes(sbi) ||
+ f2fs_time_over(sbi, CP_TIME)) {
if (test_opt(sbi, DATA_FLUSH)) {
struct blk_plug plug;
blk_start_plug(&plug);
- sync_dirty_inodes(sbi, FILE_INODE);
+ f2fs_sync_dirty_inodes(sbi, FILE_INODE);
blk_finish_plug(&plug);
}
f2fs_sync_fs(sbi->sb, true);
@@ -407,117 +555,221 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
}
}
+static int __submit_flush_wait(struct f2fs_sb_info *sbi,
+ struct block_device *bdev)
+{
+ struct bio *bio;
+ int ret;
+
+ bio = f2fs_bio_alloc(sbi, 0, false);
+ if (!bio)
+ return -ENOMEM;
+
+ bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
+ bio->bi_bdev = bdev;
+ ret = submit_bio_wait(bio);
+ bio_put(bio);
+
+ trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
+ test_opt(sbi, FLUSH_MERGE), ret);
+ return ret;
+}
+
+static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ int ret = 0;
+ int i;
+
+ if (!sbi->s_ndevs)
+ return __submit_flush_wait(sbi, sbi->sb->s_bdev);
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO))
+ continue;
+ ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
static int issue_flush_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
wait_queue_head_t *q = &fcc->flush_wait_queue;
repeat:
if (kthread_should_stop())
return 0;
+ sb_start_intwrite(sbi->sb);
+
if (!llist_empty(&fcc->issue_list)) {
- struct bio *bio;
struct flush_cmd *cmd, *next;
int ret;
- bio = f2fs_bio_alloc(0);
-
fcc->dispatch_list = llist_del_all(&fcc->issue_list);
fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
- bio->bi_bdev = sbi->sb->s_bdev;
- bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
- ret = submit_bio_wait(bio);
+ cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode);
+
+ ret = submit_flush_wait(sbi, cmd->ino);
+ atomic_inc(&fcc->issued_flush);
llist_for_each_entry_safe(cmd, next,
fcc->dispatch_list, llnode) {
cmd->ret = ret;
complete(&cmd->wait);
}
- bio_put(bio);
fcc->dispatch_list = NULL;
}
+ sb_end_intwrite(sbi->sb);
+
wait_event_interruptible(*q,
kthread_should_stop() || !llist_empty(&fcc->issue_list));
goto repeat;
}
-int f2fs_issue_flush(struct f2fs_sb_info *sbi)
+int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
{
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
struct flush_cmd cmd;
-
- trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER),
- test_opt(sbi, FLUSH_MERGE));
+ int ret;
if (test_opt(sbi, NOBARRIER))
return 0;
- if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
- struct bio *bio = f2fs_bio_alloc(0);
- int ret;
-
- atomic_inc(&fcc->submit_flush);
- bio->bi_bdev = sbi->sb->s_bdev;
- bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
- ret = submit_bio_wait(bio);
- atomic_dec(&fcc->submit_flush);
- bio_put(bio);
+ if (!test_opt(sbi, FLUSH_MERGE)) {
+ atomic_inc(&fcc->queued_flush);
+ ret = submit_flush_wait(sbi, ino);
+ atomic_dec(&fcc->queued_flush);
+ atomic_inc(&fcc->issued_flush);
return ret;
}
+ if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) {
+ ret = submit_flush_wait(sbi, ino);
+ atomic_dec(&fcc->queued_flush);
+
+ atomic_inc(&fcc->issued_flush);
+ return ret;
+ }
+
+ cmd.ino = ino;
init_completion(&cmd.wait);
- atomic_inc(&fcc->submit_flush);
llist_add(&cmd.llnode, &fcc->issue_list);
- if (!fcc->dispatch_list)
+ /* update issue_list before we wake up issue_flush thread */
+ smp_mb();
+
+ if (waitqueue_active(&fcc->flush_wait_queue))
wake_up(&fcc->flush_wait_queue);
- wait_for_completion(&cmd.wait);
- atomic_dec(&fcc->submit_flush);
+ if (fcc->f2fs_issue_flush) {
+ wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->queued_flush);
+ } else {
+ struct llist_node *list;
+
+ list = llist_del_all(&fcc->issue_list);
+ if (!list) {
+ wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->queued_flush);
+ } else {
+ struct flush_cmd *tmp, *next;
+
+ ret = submit_flush_wait(sbi, ino);
+
+ llist_for_each_entry_safe(tmp, next, list, llnode) {
+ if (tmp == &cmd) {
+ cmd.ret = ret;
+ atomic_dec(&fcc->queued_flush);
+ continue;
+ }
+ tmp->ret = ret;
+ complete(&tmp->wait);
+ }
+ }
+ }
return cmd.ret;
}
-int create_flush_cmd_control(struct f2fs_sb_info *sbi)
+int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
struct flush_cmd_control *fcc;
int err = 0;
- fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
+ if (SM_I(sbi)->fcc_info) {
+ fcc = SM_I(sbi)->fcc_info;
+ if (fcc->f2fs_issue_flush)
+ return err;
+ goto init_thread;
+ }
+
+ fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
- atomic_set(&fcc->submit_flush, 0);
+ atomic_set(&fcc->issued_flush, 0);
+ atomic_set(&fcc->queued_flush, 0);
init_waitqueue_head(&fcc->flush_wait_queue);
init_llist_head(&fcc->issue_list);
- SM_I(sbi)->cmd_control_info = fcc;
+ SM_I(sbi)->fcc_info = fcc;
if (!test_opt(sbi, FLUSH_MERGE))
return err;
+init_thread:
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->cmd_control_info = NULL;
+ kvfree(fcc);
+ SM_I(sbi)->fcc_info = NULL;
return err;
}
return err;
}
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
{
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
- if (fcc && fcc->f2fs_issue_flush)
- kthread_stop(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->cmd_control_info = NULL;
+ if (fcc && fcc->f2fs_issue_flush) {
+ struct task_struct *flush_thread = fcc->f2fs_issue_flush;
+
+ fcc->f2fs_issue_flush = NULL;
+ kthread_stop(flush_thread);
+ }
+ if (free) {
+ kvfree(fcc);
+ SM_I(sbi)->fcc_info = NULL;
+ }
+}
+
+int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
+{
+ int ret = 0, i;
+
+ if (!sbi->s_ndevs)
+ return 0;
+
+ for (i = 1; i < sbi->s_ndevs; i++) {
+ if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
+ continue;
+ ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+ if (ret)
+ break;
+
+ spin_lock(&sbi->dev_lock);
+ f2fs_clear_bit(i, (char *)&sbi->dirty_device);
+ spin_unlock(&sbi->dev_lock);
+ }
+
+ return ret;
}
static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -560,8 +812,8 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]--;
- if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
- clear_bit(GET_SECNO(sbi, segno),
+ if (get_valid_blocks(sbi, segno, true) == 0)
+ clear_bit(GET_SEC_FROM_SEG(sbi, segno),
dirty_i->victim_secmap);
}
}
@@ -574,16 +826,18 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned short valid_blocks;
+ unsigned short valid_blocks, ckpt_valid_blocks;
if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
return;
mutex_lock(&dirty_i->seglist_lock);
- valid_blocks = get_valid_blocks(sbi, segno, 0);
+ valid_blocks = get_valid_blocks(sbi, segno, false);
+ ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);
- if (valid_blocks == 0) {
+ if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
+ ckpt_valid_blocks == sbi->blocks_per_seg)) {
__locate_dirty_segment(sbi, segno, PRE);
__remove_dirty_segment(sbi, segno, DIRTY);
} else if (valid_blocks < sbi->blocks_per_seg) {
@@ -596,120 +850,976 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
mutex_unlock(&dirty_i->seglist_lock);
}
-static struct bio_entry *__add_bio_entry(struct f2fs_sb_info *sbi,
- struct bio *bio)
+/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */
+void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi)
{
- struct list_head *wait_list = &(SM_I(sbi)->wait_list);
- struct bio_entry *be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned int segno;
- INIT_LIST_HEAD(&be->list);
- be->bio = bio;
- init_completion(&be->event);
- list_add_tail(&be->list, wait_list);
-
- return be;
+ mutex_lock(&dirty_i->seglist_lock);
+ for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
+ if (get_valid_blocks(sbi, segno, false))
+ continue;
+ if (IS_CURSEG(sbi, segno))
+ continue;
+ __locate_dirty_segment(sbi, segno, PRE);
+ __remove_dirty_segment(sbi, segno, DIRTY);
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
}
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *sbi)
+int f2fs_disable_cp_again(struct f2fs_sb_info *sbi)
{
- struct list_head *wait_list = &(SM_I(sbi)->wait_list);
- struct bio_entry *be, *tmp;
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg;
+ block_t holes[2] = {0, 0}; /* DATA and NODE */
+ struct seg_entry *se;
+ unsigned int segno;
- list_for_each_entry_safe(be, tmp, wait_list, list) {
- struct bio *bio = be->bio;
- int err;
+ mutex_lock(&dirty_i->seglist_lock);
+ for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
+ se = get_seg_entry(sbi, segno);
+ if (IS_NODESEG(se->type))
+ holes[NODE] += sbi->blocks_per_seg - se->valid_blocks;
+ else
+ holes[DATA] += sbi->blocks_per_seg - se->valid_blocks;
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
- wait_for_completion_io(&be->event);
- err = be->error;
- if (err == -EOPNOTSUPP)
- err = 0;
+ if (holes[DATA] > ovp || holes[NODE] > ovp)
+ return -EAGAIN;
+ if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&
+ dirty_segments(sbi) > overprovision_segments(sbi))
+ return -EAGAIN;
+ return 0;
+}
- if (err)
- f2fs_msg(sbi->sb, KERN_INFO,
- "Issue discard failed, ret: %d", err);
+/* This is only used by SBI_CP_DISABLED */
+static unsigned int get_free_segment(struct f2fs_sb_info *sbi)
+{
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned int segno = 0;
- bio_put(bio);
- list_del(&be->list);
- kmem_cache_free(bio_entry_slab, be);
+ mutex_lock(&dirty_i->seglist_lock);
+ for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
+ if (get_valid_blocks(sbi, segno, false))
+ continue;
+ if (get_ckpt_valid_blocks(sbi, segno))
+ continue;
+ mutex_unlock(&dirty_i->seglist_lock);
+ return segno;
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
+ return NULL_SEGNO;
+}
+
+static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc;
+
+ f2fs_bug_on(sbi, !len);
+
+ pend_list = &dcc->pend_list[plist_idx(len)];
+
+ dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS);
+ INIT_LIST_HEAD(&dc->list);
+ dc->bdev = bdev;
+ dc->lstart = lstart;
+ dc->start = start;
+ dc->len = len;
+ dc->ref = 0;
+ dc->state = D_PREP;
+ dc->queued = 0;
+ dc->error = 0;
+ init_completion(&dc->wait);
+ list_add_tail(&dc->list, pend_list);
+ spin_lock_init(&dc->lock);
+ dc->bio_ref = 0;
+ atomic_inc(&dcc->discard_cmd_cnt);
+ dcc->undiscard_blks += len;
+
+ return dc;
+}
+
+static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len,
+ struct rb_node *parent, struct rb_node **p)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *dc;
+
+ dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
+
+ rb_link_node(&dc->rb_node, parent, p);
+ rb_insert_color(&dc->rb_node, &dcc->root);
+
+ return dc;
+}
+
+static void __detach_discard_cmd(struct discard_cmd_control *dcc,
+ struct discard_cmd *dc)
+{
+ if (dc->state == D_DONE)
+ atomic_sub(dc->queued, &dcc->queued_discard);
+
+ list_del(&dc->list);
+ rb_erase(&dc->rb_node, &dcc->root);
+ dcc->undiscard_blks -= dc->len;
+
+ kmem_cache_free(discard_cmd_slab, dc);
+
+ atomic_dec(&dcc->discard_cmd_cnt);
+}
+
+static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ unsigned long flags;
+
+ trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
+
+ spin_lock_irqsave(&dc->lock, flags);
+ if (dc->bio_ref) {
+ spin_unlock_irqrestore(&dc->lock, flags);
+ return;
+ }
+ spin_unlock_irqrestore(&dc->lock, flags);
+
+ f2fs_bug_on(sbi, dc->ref);
+
+ if (dc->error == -EOPNOTSUPP)
+ dc->error = 0;
+
+ if (dc->error)
+ printk_ratelimited(
+ "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d",
+ KERN_INFO, dc->lstart, dc->start, dc->len, dc->error);
+ __detach_discard_cmd(dcc, dc);
+}
+
+static void f2fs_submit_discard_endio(struct bio *bio)
+{
+ struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
+ unsigned long flags;
+
+ dc->error = bio->bi_error;
+
+ spin_lock_irqsave(&dc->lock, flags);
+ dc->bio_ref--;
+ if (!dc->bio_ref && dc->state == D_SUBMIT) {
+ dc->state = D_DONE;
+ complete_all(&dc->wait);
+ }
+ spin_unlock_irqrestore(&dc->lock, flags);
+ bio_put(bio);
+}
+
+static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
+ block_t start, block_t end)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+ struct seg_entry *sentry;
+ unsigned int segno;
+ block_t blk = start;
+ unsigned long offset, size, max_blocks = sbi->blocks_per_seg;
+ unsigned long *map;
+
+ while (blk < end) {
+ segno = GET_SEGNO(sbi, blk);
+ sentry = get_seg_entry(sbi, segno);
+ offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
+
+ if (end < START_BLOCK(sbi, segno + 1))
+ size = GET_BLKOFF_FROM_SEG0(sbi, end);
+ else
+ size = max_blocks;
+ map = (unsigned long *)(sentry->cur_valid_map);
+ offset = __find_rev_next_bit(map, size, offset);
+ f2fs_bug_on(sbi, offset != size);
+ blk = START_BLOCK(sbi, segno + 1);
+ }
+#endif
+}
+
+static void __init_discard_policy(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy,
+ int discard_type, unsigned int granularity)
+{
+ /* common policy */
+ dpolicy->type = discard_type;
+ dpolicy->sync = true;
+ dpolicy->ordered = false;
+ dpolicy->granularity = granularity;
+
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+ dpolicy->timeout = 0;
+
+ if (discard_type == DPOLICY_BG) {
+ dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+ dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
+ dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+ dpolicy->io_aware = true;
+ dpolicy->sync = false;
+ dpolicy->ordered = true;
+ if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
+ dpolicy->granularity = 1;
+ dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+ }
+ } else if (discard_type == DPOLICY_FORCE) {
+ dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+ dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
+ dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+ dpolicy->io_aware = false;
+ } else if (discard_type == DPOLICY_FSTRIM) {
+ dpolicy->io_aware = false;
+ } else if (discard_type == DPOLICY_UMOUNT) {
+ dpolicy->max_requests = UINT_MAX;
+ dpolicy->io_aware = false;
+ /* we need to issue all to keep CP_TRIMMED_FLAG */
+ dpolicy->granularity = 1;
}
}
-static void f2fs_submit_bio_wait_endio(struct bio *bio)
-{
- struct bio_entry *be = (struct bio_entry *)bio->bi_private;
-
- be->error = bio->bi_error;
- complete(&be->event);
-}
-
+static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len);
/* this function is copied from blkdev_issue_discard from block/blk-lib.c */
-int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi, sector_t sector,
- sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy,
+ struct discard_cmd *dc,
+ unsigned int *issued)
{
- struct block_device *bdev = sbi->sb->s_bdev;
- struct bio *bio = NULL;
- int err;
+ struct block_device *bdev = dc->bdev;
+ struct request_queue *q = bdev_get_queue(bdev);
+ unsigned int max_discard_blocks =
+ SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
+ &(dcc->fstrim_list) : &(dcc->wait_list);
+ int flag = dpolicy->sync ? REQ_SYNC : 0;
+ block_t lstart, start, len, total_len;
+ int err = 0;
- err = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
- &bio);
- if (!err && bio) {
- struct bio_entry *be = __add_bio_entry(sbi, bio);
+ if (dc->state != D_PREP)
+ return 0;
- bio->bi_private = be;
- bio->bi_end_io = f2fs_submit_bio_wait_endio;
- bio->bi_opf |= REQ_SYNC;
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+ return 0;
+
+ trace_f2fs_issue_discard(bdev, dc->start, dc->len);
+
+ lstart = dc->lstart;
+ start = dc->start;
+ len = dc->len;
+ total_len = len;
+
+ dc->len = 0;
+
+ while (total_len && *issued < dpolicy->max_requests && !err) {
+ struct bio *bio = NULL;
+ unsigned long flags;
+ bool last = true;
+
+ if (len > max_discard_blocks) {
+ len = max_discard_blocks;
+ last = false;
+ }
+
+ (*issued)++;
+ if (*issued == dpolicy->max_requests)
+ last = true;
+
+ dc->len += len;
+
+ if (time_to_inject(sbi, FAULT_DISCARD)) {
+ f2fs_show_injection_info(FAULT_DISCARD);
+ err = -EIO;
+ goto submit;
+ }
+ err = __blkdev_issue_discard(bdev,
+ SECTOR_FROM_BLOCK(start),
+ SECTOR_FROM_BLOCK(len),
+ GFP_NOFS, 0, &bio);
+submit:
+ if (err) {
+ spin_lock_irqsave(&dc->lock, flags);
+ if (dc->state == D_PARTIAL)
+ dc->state = D_SUBMIT;
+ spin_unlock_irqrestore(&dc->lock, flags);
+
+ break;
+ }
+
+ f2fs_bug_on(sbi, !bio);
+
+ /*
+ * should keep before submission to avoid D_DONE
+ * right away
+ */
+ spin_lock_irqsave(&dc->lock, flags);
+ if (last)
+ dc->state = D_SUBMIT;
+ else
+ dc->state = D_PARTIAL;
+ dc->bio_ref++;
+ spin_unlock_irqrestore(&dc->lock, flags);
+
+ atomic_inc(&dcc->queued_discard);
+ dc->queued++;
+ list_move_tail(&dc->list, wait_list);
+
+ /* sanity check on discard range */
+ __check_sit_bitmap(sbi, lstart, lstart + len);
+
+ bio->bi_private = dc;
+ bio->bi_end_io = f2fs_submit_discard_endio;
+ bio->bi_opf |= flag;
submit_bio(bio);
+
+ atomic_inc(&dcc->issued_discard);
+
+ f2fs_update_iostat(sbi, FS_DISCARD, 1);
+
+ lstart += len;
+ start += len;
+ total_len -= len;
+ len = total_len;
}
+ if (!err && len)
+ __update_discard_tree_range(sbi, bdev, lstart, start, len);
return err;
}
+static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len,
+ struct rb_node **insert_p,
+ struct rb_node *insert_parent)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct rb_node **p;
+ struct rb_node *parent = NULL;
+ struct discard_cmd *dc = NULL;
+
+ if (insert_p && insert_parent) {
+ parent = insert_parent;
+ p = insert_p;
+ goto do_insert;
+ }
+
+ p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
+do_insert:
+ dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p);
+ if (!dc)
+ return NULL;
+
+ return dc;
+}
+
+static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
+ struct discard_cmd *dc)
+{
+ list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->len)]);
+}
+
+static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc, block_t blkaddr)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_info di = dc->di;
+ bool modified = false;
+
+ if (dc->state == D_DONE || dc->len == 1) {
+ __remove_discard_cmd(sbi, dc);
+ return;
+ }
+
+ dcc->undiscard_blks -= di.len;
+
+ if (blkaddr > di.lstart) {
+ dc->len = blkaddr - dc->lstart;
+ dcc->undiscard_blks += dc->len;
+ __relocate_discard_cmd(dcc, dc);
+ modified = true;
+ }
+
+ if (blkaddr < di.lstart + di.len - 1) {
+ if (modified) {
+ __insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
+ di.start + blkaddr + 1 - di.lstart,
+ di.lstart + di.len - 1 - blkaddr,
+ NULL, NULL);
+ } else {
+ dc->lstart++;
+ dc->len--;
+ dc->start++;
+ dcc->undiscard_blks += dc->len;
+ __relocate_discard_cmd(dcc, dc);
+ }
+ }
+}
+
+static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+ struct discard_cmd *dc;
+ struct discard_info di = {0};
+ struct rb_node **insert_p = NULL, *insert_parent = NULL;
+ struct request_queue *q = bdev_get_queue(bdev);
+ unsigned int max_discard_blocks =
+ SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
+ block_t end = lstart + len;
+
+ dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
+ NULL, lstart,
+ (struct rb_entry **)&prev_dc,
+ (struct rb_entry **)&next_dc,
+ &insert_p, &insert_parent, true);
+ if (dc)
+ prev_dc = dc;
+
+ if (!prev_dc) {
+ di.lstart = lstart;
+ di.len = next_dc ? next_dc->lstart - lstart : len;
+ di.len = min(di.len, len);
+ di.start = start;
+ }
+
+ while (1) {
+ struct rb_node *node;
+ bool merged = false;
+ struct discard_cmd *tdc = NULL;
+
+ if (prev_dc) {
+ di.lstart = prev_dc->lstart + prev_dc->len;
+ if (di.lstart < lstart)
+ di.lstart = lstart;
+ if (di.lstart >= end)
+ break;
+
+ if (!next_dc || next_dc->lstart > end)
+ di.len = end - di.lstart;
+ else
+ di.len = next_dc->lstart - di.lstart;
+ di.start = start + di.lstart - lstart;
+ }
+
+ if (!di.len)
+ goto next;
+
+ if (prev_dc && prev_dc->state == D_PREP &&
+ prev_dc->bdev == bdev &&
+ __is_discard_back_mergeable(&di, &prev_dc->di,
+ max_discard_blocks)) {
+ prev_dc->di.len += di.len;
+ dcc->undiscard_blks += di.len;
+ __relocate_discard_cmd(dcc, prev_dc);
+ di = prev_dc->di;
+ tdc = prev_dc;
+ merged = true;
+ }
+
+ if (next_dc && next_dc->state == D_PREP &&
+ next_dc->bdev == bdev &&
+ __is_discard_front_mergeable(&di, &next_dc->di,
+ max_discard_blocks)) {
+ next_dc->di.lstart = di.lstart;
+ next_dc->di.len += di.len;
+ next_dc->di.start = di.start;
+ dcc->undiscard_blks += di.len;
+ __relocate_discard_cmd(dcc, next_dc);
+ if (tdc)
+ __remove_discard_cmd(sbi, tdc);
+ merged = true;
+ }
+
+ if (!merged) {
+ __insert_discard_tree(sbi, bdev, di.lstart, di.start,
+ di.len, NULL, NULL);
+ }
+ next:
+ prev_dc = next_dc;
+ if (!prev_dc)
+ break;
+
+ node = rb_next(&prev_dc->rb_node);
+ next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+ }
+}
+
+static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+ block_t lblkstart = blkstart;
+
+ trace_f2fs_queue_discard(bdev, blkstart, blklen);
+
+ if (sbi->s_ndevs) {
+ int devi = f2fs_target_device_index(sbi, blkstart);
+
+ blkstart -= FDEV(devi).start_blk;
+ }
+ mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
+ __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
+ mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
+ return 0;
+}
+
+static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+ struct rb_node **insert_p = NULL, *insert_parent = NULL;
+ struct discard_cmd *dc;
+ struct blk_plug plug;
+ unsigned int pos = dcc->next_pos;
+ unsigned int issued = 0;
+ bool io_interrupted = false;
+
+ mutex_lock(&dcc->cmd_lock);
+ dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
+ NULL, pos,
+ (struct rb_entry **)&prev_dc,
+ (struct rb_entry **)&next_dc,
+ &insert_p, &insert_parent, true);
+ if (!dc)
+ dc = next_dc;
+
+ blk_start_plug(&plug);
+
+ while (dc) {
+ struct rb_node *node;
+ int err = 0;
+
+ if (dc->state != D_PREP)
+ goto next;
+
+ if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) {
+ io_interrupted = true;
+ break;
+ }
+
+ dcc->next_pos = dc->lstart + dc->len;
+ err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+ if (issued >= dpolicy->max_requests)
+ break;
+next:
+ node = rb_next(&dc->rb_node);
+ if (err)
+ __remove_discard_cmd(sbi, dc);
+ dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+ }
+
+ blk_finish_plug(&plug);
+
+ if (!dc)
+ dcc->next_pos = 0;
+
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (!issued && io_interrupted)
+ issued = -1;
+
+ return issued;
+}
+
+static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc, *tmp;
+ struct blk_plug plug;
+ int i, issued = 0;
+ bool io_interrupted = false;
+
+ if (dpolicy->timeout != 0)
+ f2fs_update_time(sbi, dpolicy->timeout);
+
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ if (dpolicy->timeout != 0 &&
+ f2fs_time_over(sbi, dpolicy->timeout))
+ break;
+
+ if (i + 1 < dpolicy->granularity)
+ break;
+
+ if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered)
+ return __issue_discard_cmd_orderly(sbi, dpolicy);
+
+ pend_list = &dcc->pend_list[i];
+
+ mutex_lock(&dcc->cmd_lock);
+ if (list_empty(pend_list))
+ goto next;
+ if (unlikely(dcc->rbtree_check))
+ f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+ &dcc->root));
+ blk_start_plug(&plug);
+ list_for_each_entry_safe(dc, tmp, pend_list, list) {
+ f2fs_bug_on(sbi, dc->state != D_PREP);
+
+ if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
+ !is_idle(sbi, DISCARD_TIME)) {
+ io_interrupted = true;
+ break;
+ }
+
+ __submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+ if (issued >= dpolicy->max_requests)
+ break;
+ }
+ blk_finish_plug(&plug);
+next:
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (issued >= dpolicy->max_requests || io_interrupted)
+ break;
+ }
+
+ if (!issued && io_interrupted)
+ issued = -1;
+
+ return issued;
+}
+
+static bool __drop_discard_cmd(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc, *tmp;
+ int i;
+ bool dropped = false;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ pend_list = &dcc->pend_list[i];
+ list_for_each_entry_safe(dc, tmp, pend_list, list) {
+ f2fs_bug_on(sbi, dc->state != D_PREP);
+ __remove_discard_cmd(sbi, dc);
+ dropped = true;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ return dropped;
+}
+
+void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi)
+{
+ __drop_discard_cmd(sbi);
+}
+
+static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ unsigned int len = 0;
+
+ wait_for_completion_io(&dc->wait);
+ mutex_lock(&dcc->cmd_lock);
+ f2fs_bug_on(sbi, dc->state != D_DONE);
+ dc->ref--;
+ if (!dc->ref) {
+ if (!dc->error)
+ len = dc->len;
+ __remove_discard_cmd(sbi, dc);
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ return len;
+}
+
+static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy,
+ block_t start, block_t end)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
+ &(dcc->fstrim_list) : &(dcc->wait_list);
+ struct discard_cmd *dc, *tmp;
+ bool need_wait;
+ unsigned int trimmed = 0;
+
+next:
+ need_wait = false;
+
+ mutex_lock(&dcc->cmd_lock);
+ list_for_each_entry_safe(dc, tmp, wait_list, list) {
+ if (dc->lstart + dc->len <= start || end <= dc->lstart)
+ continue;
+ if (dc->len < dpolicy->granularity)
+ continue;
+ if (dc->state == D_DONE && !dc->ref) {
+ wait_for_completion_io(&dc->wait);
+ if (!dc->error)
+ trimmed += dc->len;
+ __remove_discard_cmd(sbi, dc);
+ } else {
+ dc->ref++;
+ need_wait = true;
+ break;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (need_wait) {
+ trimmed += __wait_one_discard_bio(sbi, dc);
+ goto next;
+ }
+
+ return trimmed;
+}
+
+static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy)
+{
+ struct discard_policy dp;
+ unsigned int discard_blks;
+
+ if (dpolicy)
+ return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
+
+ /* wait all */
+ __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1);
+ discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+ __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
+ discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+
+ return discard_blks;
+}
+
+/* This should be covered by global mutex, &sit_i->sentry_lock */
+static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *dc;
+ bool need_wait = false;
+
+ mutex_lock(&dcc->cmd_lock);
+ dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root,
+ NULL, blkaddr);
+ if (dc) {
+ if (dc->state == D_PREP) {
+ __punch_discard_cmd(sbi, dc, blkaddr);
+ } else {
+ dc->ref++;
+ need_wait = true;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (need_wait)
+ __wait_one_discard_bio(sbi, dc);
+}
+
+void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+ if (dcc && dcc->f2fs_issue_discard) {
+ struct task_struct *discard_thread = dcc->f2fs_issue_discard;
+
+ dcc->f2fs_issue_discard = NULL;
+ kthread_stop(discard_thread);
+ }
+}
+
+/* This comes from f2fs_put_super */
+bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_policy dpolicy;
+ bool dropped;
+
+ __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
+ dcc->discard_granularity);
+ dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT;
+ __issue_discard_cmd(sbi, &dpolicy);
+ dropped = __drop_discard_cmd(sbi);
+
+ /* just to make sure there is no pending discard commands */
+ __wait_all_discard_cmd(sbi, NULL);
+
+ f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt));
+ return dropped;
+}
+
+static int issue_discard_thread(void *data)
+{
+ struct f2fs_sb_info *sbi = data;
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ wait_queue_head_t *q = &dcc->discard_wait_queue;
+ struct discard_policy dpolicy;
+ unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
+ int issued;
+
+ set_freezable();
+
+ do {
+ __init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
+ dcc->discard_granularity);
+
+ wait_event_interruptible_timeout(*q,
+ kthread_should_stop() || freezing(current) ||
+ dcc->discard_wake,
+ msecs_to_jiffies(wait_ms));
+
+ if (dcc->discard_wake)
+ dcc->discard_wake = 0;
+
+ /* clean up pending candidates before going to sleep */
+ if (atomic_read(&dcc->queued_discard))
+ __wait_all_discard_cmd(sbi, NULL);
+
+ if (try_to_freeze())
+ continue;
+ if (f2fs_readonly(sbi->sb))
+ continue;
+ if (kthread_should_stop())
+ return 0;
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
+ wait_ms = dpolicy.max_interval;
+ continue;
+ }
+
+ if (sbi->gc_mode == GC_URGENT)
+ __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
+
+ sb_start_intwrite(sbi->sb);
+
+ issued = __issue_discard_cmd(sbi, &dpolicy);
+ if (issued > 0) {
+ __wait_all_discard_cmd(sbi, &dpolicy);
+ wait_ms = dpolicy.min_interval;
+ } else if (issued == -1){
+ wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME);
+ if (!wait_ms)
+ wait_ms = dpolicy.mid_interval;
+ } else {
+ wait_ms = dpolicy.max_interval;
+ }
+
+ sb_end_intwrite(sbi->sb);
+
+ } while (!kthread_should_stop());
+ return 0;
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+ sector_t sector, nr_sects;
+ block_t lblkstart = blkstart;
+ int devi = 0;
+
+ if (sbi->s_ndevs) {
+ devi = f2fs_target_device_index(sbi, blkstart);
+ blkstart -= FDEV(devi).start_blk;
+ }
+
+ /*
+ * We need to know the type of the zone: for conventional zones,
+ * use regular discard if the drive supports it. For sequential
+ * zones, reset the zone write pointer.
+ */
+ switch (get_blkz_type(sbi, bdev, blkstart)) {
+
+ case BLK_ZONE_TYPE_CONVENTIONAL:
+ if (!blk_queue_discard(bdev_get_queue(bdev)))
+ return 0;
+ return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
+ case BLK_ZONE_TYPE_SEQWRITE_REQ:
+ case BLK_ZONE_TYPE_SEQWRITE_PREF:
+ sector = SECTOR_FROM_BLOCK(blkstart);
+ nr_sects = SECTOR_FROM_BLOCK(blklen);
+
+ if (sector & (bdev_zone_sectors(bdev) - 1) ||
+ nr_sects != bdev_zone_sectors(bdev)) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "(%d) %s: Unaligned discard attempted (block %x + %x)",
+ devi, sbi->s_ndevs ? FDEV(devi).path: "",
+ blkstart, blklen);
+ return -EIO;
+ }
+ trace_f2fs_issue_reset_zone(bdev, blkstart);
+ return blkdev_reset_zones(bdev, sector,
+ nr_sects, GFP_NOFS);
+ default:
+ /* Unknown zone type: broken device ? */
+ return -EIO;
+ }
+}
+#endif
+
+static int __issue_discard_async(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (f2fs_sb_has_blkzoned(sbi) &&
+ bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+ return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
+#endif
+ return __queue_discard_cmd(sbi, bdev, blkstart, blklen);
+}
+
static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
block_t blkstart, block_t blklen)
{
- sector_t start = SECTOR_FROM_BLOCK(blkstart);
- sector_t len = SECTOR_FROM_BLOCK(blklen);
+ sector_t start = blkstart, len = 0;
+ struct block_device *bdev;
struct seg_entry *se;
unsigned int offset;
block_t i;
+ int err = 0;
- for (i = blkstart; i < blkstart + blklen; i++) {
+ bdev = f2fs_target_device(sbi, blkstart, NULL);
+
+ for (i = blkstart; i < blkstart + blklen; i++, len++) {
+ if (i != start) {
+ struct block_device *bdev2 =
+ f2fs_target_device(sbi, i, NULL);
+
+ if (bdev2 != bdev) {
+ err = __issue_discard_async(sbi, bdev,
+ start, len);
+ if (err)
+ return err;
+ bdev = bdev2;
+ start = i;
+ len = 0;
+ }
+ }
+
se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
offset = GET_BLKOFF_FROM_SEG0(sbi, i);
if (!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
}
- trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
- return __f2fs_issue_discard_async(sbi, start, len, GFP_NOFS, 0);
+
+ if (len)
+ err = __issue_discard_async(sbi, bdev, start, len);
+ return err;
}
-static void __add_discard_entry(struct f2fs_sb_info *sbi,
- struct cp_control *cpc, struct seg_entry *se,
- unsigned int start, unsigned int end)
-{
- struct list_head *head = &SM_I(sbi)->discard_list;
- struct discard_entry *new, *last;
-
- if (!list_empty(head)) {
- last = list_last_entry(head, struct discard_entry, list);
- if (START_BLOCK(sbi, cpc->trim_start) + start ==
- last->blkaddr + last->len) {
- last->len += end - start;
- goto done;
- }
- }
-
- new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
- INIT_LIST_HEAD(&new->list);
- new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
- new->len = end - start;
- list_add_tail(&new->list, head);
-done:
- SM_I(sbi)->nr_discards += end - start;
-}
-
-static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
+ bool check_only)
{
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
int max_blocks = sbi->blocks_per_seg;
@@ -719,16 +1829,19 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
unsigned long *discard_map = (unsigned long *)se->discard_map;
unsigned long *dmap = SIT_I(sbi)->tmp_map;
unsigned int start = 0, end = -1;
- bool force = (cpc->reason == CP_DISCARD);
+ bool force = (cpc->reason & CP_DISCARD);
+ struct discard_entry *de = NULL;
+ struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
int i;
- if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
- return;
+ if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi))
+ return false;
if (!force) {
- if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
- SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
- return;
+ if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
+ SM_I(sbi)->dcc_info->nr_discards >=
+ SM_I(sbi)->dcc_info->max_discards)
+ return false;
}
/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
@@ -736,7 +1849,8 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
- while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+ while (force || SM_I(sbi)->dcc_info->nr_discards <=
+ SM_I(sbi)->dcc_info->max_discards) {
start = __find_rev_next_bit(dmap, max_blocks, end + 1);
if (start >= max_blocks)
break;
@@ -746,24 +1860,42 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
&& (end - start) < cpc->trim_minlen)
continue;
- __add_discard_entry(sbi, cpc, se, start, end);
+ if (check_only)
+ return true;
+
+ if (!de) {
+ de = f2fs_kmem_cache_alloc(discard_entry_slab,
+ GFP_F2FS_ZERO);
+ de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start);
+ list_add_tail(&de->list, head);
+ }
+
+ for (i = start; i < end; i++)
+ __set_bit_le(i, (void *)de->discard_map);
+
+ SM_I(sbi)->dcc_info->nr_discards += end - start;
}
+ return false;
}
-void release_discard_addrs(struct f2fs_sb_info *sbi)
+static void release_discard_addr(struct discard_entry *entry)
{
- struct list_head *head = &(SM_I(sbi)->discard_list);
+ list_del(&entry->list);
+ kmem_cache_free(discard_entry_slab, entry);
+}
+
+void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi)
+{
+ struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
/* drop caches */
- list_for_each_entry_safe(entry, this, head, list) {
- list_del(&entry->list);
- kmem_cache_free(discard_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, this, head, list)
+ release_discard_addr(entry);
}
/*
- * Should call clear_prefree_segments after checkpoint is done.
+ * Should call f2fs_clear_prefree_segments after checkpoint is done.
*/
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
@@ -776,47 +1908,59 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
mutex_unlock(&dirty_i->seglist_lock);
}
-void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
{
- struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *head = &dcc->entry_list;
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- struct blk_plug plug;
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
unsigned int start = 0, end = -1;
unsigned int secno, start_segno;
- bool force = (cpc->reason == CP_DISCARD);
-
- blk_start_plug(&plug);
+ bool force = (cpc->reason & CP_DISCARD);
+ bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi);
mutex_lock(&dirty_i->seglist_lock);
while (1) {
int i;
+
+ if (need_align && end != -1)
+ end--;
start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
if (start >= MAIN_SEGS(sbi))
break;
end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
start + 1);
- for (i = start; i < end; i++)
- clear_bit(i, prefree_map);
+ if (need_align) {
+ start = rounddown(start, sbi->segs_per_sec);
+ end = roundup(end, sbi->segs_per_sec);
+ }
- dirty_i->nr_dirty[PRE] -= end - start;
+ for (i = start; i < end; i++) {
+ if (test_and_clear_bit(i, prefree_map))
+ dirty_i->nr_dirty[PRE]--;
+ }
- if (force || !test_opt(sbi, DISCARD))
+ if (!f2fs_realtime_discard_enable(sbi))
continue;
- if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+ if (force && start >= cpc->trim_start &&
+ (end - 1) <= cpc->trim_end)
+ continue;
+
+ if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) {
f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
(end - start) << sbi->log_blocks_per_seg);
continue;
}
next:
- secno = GET_SECNO(sbi, start);
- start_segno = secno * sbi->segs_per_sec;
+ secno = GET_SEC_FROM_SEG(sbi, start);
+ start_segno = GET_SEG_FROM_SEC(sbi, secno);
if (!IS_CURSEC(sbi, secno) &&
- !get_valid_blocks(sbi, start, sbi->segs_per_sec))
+ !get_valid_blocks(sbi, start, true))
f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
sbi->segs_per_sec << sbi->log_blocks_per_seg);
@@ -830,17 +1974,98 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* send small discards */
list_for_each_entry_safe(entry, this, head, list) {
- if (force && entry->len < cpc->trim_minlen)
- goto skip;
- f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
- cpc->trimmed += entry->len;
+ unsigned int cur_pos = 0, next_pos, len, total_len = 0;
+ bool is_valid = test_bit_le(0, entry->discard_map);
+
+find_next:
+ if (is_valid) {
+ next_pos = find_next_zero_bit_le(entry->discard_map,
+ sbi->blocks_per_seg, cur_pos);
+ len = next_pos - cur_pos;
+
+ if (f2fs_sb_has_blkzoned(sbi) ||
+ (force && len < cpc->trim_minlen))
+ goto skip;
+
+ f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
+ len);
+ total_len += len;
+ } else {
+ next_pos = find_next_bit_le(entry->discard_map,
+ sbi->blocks_per_seg, cur_pos);
+ }
skip:
- list_del(&entry->list);
- SM_I(sbi)->nr_discards -= entry->len;
- kmem_cache_free(discard_entry_slab, entry);
+ cur_pos = next_pos;
+ is_valid = !is_valid;
+
+ if (cur_pos < sbi->blocks_per_seg)
+ goto find_next;
+
+ release_discard_addr(entry);
+ dcc->nr_discards -= total_len;
}
- blk_finish_plug(&plug);
+ wake_up_discard_thread(sbi, false);
+}
+
+static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+ dev_t dev = sbi->sb->s_bdev->bd_dev;
+ struct discard_cmd_control *dcc;
+ int err = 0, i;
+
+ if (SM_I(sbi)->dcc_info) {
+ dcc = SM_I(sbi)->dcc_info;
+ goto init_thread;
+ }
+
+ dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL);
+ if (!dcc)
+ return -ENOMEM;
+
+ dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
+ INIT_LIST_HEAD(&dcc->entry_list);
+ for (i = 0; i < MAX_PLIST_NUM; i++)
+ INIT_LIST_HEAD(&dcc->pend_list[i]);
+ INIT_LIST_HEAD(&dcc->wait_list);
+ INIT_LIST_HEAD(&dcc->fstrim_list);
+ mutex_init(&dcc->cmd_lock);
+ atomic_set(&dcc->issued_discard, 0);
+ atomic_set(&dcc->queued_discard, 0);
+ atomic_set(&dcc->discard_cmd_cnt, 0);
+ dcc->nr_discards = 0;
+ dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
+ dcc->undiscard_blks = 0;
+ dcc->next_pos = 0;
+ dcc->root = RB_ROOT;
+ dcc->rbtree_check = false;
+
+ init_waitqueue_head(&dcc->discard_wait_queue);
+ SM_I(sbi)->dcc_info = dcc;
+init_thread:
+ dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
+ "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
+ if (IS_ERR(dcc->f2fs_issue_discard)) {
+ err = PTR_ERR(dcc->f2fs_issue_discard);
+ kvfree(dcc);
+ SM_I(sbi)->dcc_info = NULL;
+ return err;
+ }
+
+ return err;
+}
+
+static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+ if (!dcc)
+ return;
+
+ f2fs_stop_discard_thread(sbi);
+
+ kvfree(dcc);
+ SM_I(sbi)->dcc_info = NULL;
}
static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
@@ -869,6 +2094,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
struct seg_entry *se;
unsigned int segno, offset;
long int new_vblocks;
+ bool exist;
+#ifdef CONFIG_F2FS_CHECK_FS
+ bool mir_exist;
+#endif
segno = GET_SEGNO(sbi, blkaddr);
@@ -880,21 +2109,70 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
- se->mtime = get_mtime(sbi);
- SIT_I(sbi)->max_mtime = se->mtime;
+ se->mtime = get_mtime(sbi, false);
+ if (se->mtime > SIT_I(sbi)->max_mtime)
+ SIT_I(sbi)->max_mtime = se->mtime;
/* Update valid block bitmap */
if (del > 0) {
- if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
+ exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+ mir_exist = f2fs_test_and_set_bit(offset,
+ se->cur_valid_map_mir);
+ if (unlikely(exist != mir_exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
+ "when setting bitmap, blk:%u, old bit:%d",
+ blkaddr, exist);
f2fs_bug_on(sbi, 1);
- if (f2fs_discard_en(sbi) &&
- !f2fs_test_and_set_bit(offset, se->discard_map))
+ }
+#endif
+ if (unlikely(exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Bitmap was wrongly set, blk:%u", blkaddr);
+ f2fs_bug_on(sbi, 1);
+ se->valid_blocks--;
+ del = 0;
+ }
+
+ if (!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
+
+ /* don't overwrite by SSR to keep node chain */
+ if (IS_NODESEG(se->type) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+ if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+ se->ckpt_valid_blocks++;
+ }
} else {
- if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
+ exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+ mir_exist = f2fs_test_and_clear_bit(offset,
+ se->cur_valid_map_mir);
+ if (unlikely(exist != mir_exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
+ "when clearing bitmap, blk:%u, old bit:%d",
+ blkaddr, exist);
f2fs_bug_on(sbi, 1);
- if (f2fs_discard_en(sbi) &&
- f2fs_test_and_clear_bit(offset, se->discard_map))
+ }
+#endif
+ if (unlikely(!exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Bitmap was wrongly cleared, blk:%u", blkaddr);
+ f2fs_bug_on(sbi, 1);
+ se->valid_blocks++;
+ del = 0;
+ } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ /*
+ * If checkpoints are off, we must not reuse data that
+ * was used in the previous checkpoint. If it was used
+ * before, we must track that to know how much space we
+ * really have.
+ */
+ if (f2fs_test_bit(offset, se->ckpt_valid_map))
+ sbi->unusable_block_count++;
+ }
+
+ if (f2fs_test_and_clear_bit(offset, se->discard_map))
sbi->discard_blks++;
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
@@ -905,21 +2183,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
/* update total number of valid blocks to be written in ckpt area */
SIT_I(sbi)->written_valid_blocks += del;
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi))
get_sec_entry(sbi, segno)->valid_blocks += del;
}
-void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new)
-{
- update_sit_entry(sbi, new, 1);
- if (GET_SEGNO(sbi, old) != NULL_SEGNO)
- update_sit_entry(sbi, old, -1);
-
- locate_dirty_segment(sbi, GET_SEGNO(sbi, old));
- locate_dirty_segment(sbi, GET_SEGNO(sbi, new));
-}
-
-void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
{
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
@@ -928,18 +2196,20 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
if (addr == NEW_ADDR)
return;
+ invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
+
/* add it into sit main buffer */
- mutex_lock(&sit_i->sentry_lock);
+ down_write(&sit_i->sentry_lock);
update_sit_entry(sbi, addr, -1);
/* add it into dirty seglist */
locate_dirty_segment(sbi, segno);
- mutex_unlock(&sit_i->sentry_lock);
+ up_write(&sit_i->sentry_lock);
}
-bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
+bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned int segno, offset;
@@ -949,7 +2219,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
if (!is_valid_data_blkaddr(sbi, blkaddr))
return true;
- mutex_lock(&sit_i->sentry_lock);
+ down_read(&sit_i->sentry_lock);
segno = GET_SEGNO(sbi, blkaddr);
se = get_seg_entry(sbi, segno);
@@ -958,7 +2228,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
if (f2fs_test_bit(offset, se->ckpt_valid_map))
is_cp = true;
- mutex_unlock(&sit_i->sentry_lock);
+ up_read(&sit_i->sentry_lock);
return is_cp;
}
@@ -978,7 +2248,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
/*
* Calculate the number of current summary pages for writing
*/
-int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
+int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
@@ -1008,20 +2278,17 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
/*
* Caller should put this summary page
*/
-struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
+struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
- return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
+ return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
}
-void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
+void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
+ void *src, block_t blk_addr)
{
- struct page *page = grab_meta_page(sbi, blk_addr);
- void *dst = page_address(page);
+ struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
- if (src)
- memcpy(dst, src, PAGE_SIZE);
- else
- memset(dst, 0, PAGE_SIZE);
+ memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
@@ -1029,18 +2296,19 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
static void write_sum_page(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
- update_meta_page(sbi, (void *)sum_blk, blk_addr);
+ f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr);
}
static void write_current_sum_page(struct f2fs_sb_info *sbi,
int type, block_t blk_addr)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
- struct page *page = grab_meta_page(sbi, blk_addr);
+ struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
struct f2fs_summary_block *src = curseg->sum_blk;
struct f2fs_summary_block *dst;
dst = (struct f2fs_summary_block *)page_address(page);
+ memset(dst, 0, PAGE_SIZE);
mutex_lock(&curseg->curseg_mutex);
@@ -1078,8 +2346,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
- unsigned int hint = *newseg / sbi->segs_per_sec;
- unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
+ unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
+ unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
unsigned int left_start = hint;
bool init = true;
int go_left = 0;
@@ -1089,8 +2357,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
segno = find_next_zero_bit(free_i->free_segmap,
- (hint + 1) * sbi->segs_per_sec, *newseg + 1);
- if (segno < (hint + 1) * sbi->segs_per_sec)
+ GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
+ if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
goto got_it;
}
find_other_zone:
@@ -1120,9 +2388,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
}
secno = left_start;
skip_left:
- hint = secno;
- segno = secno * sbi->segs_per_sec;
- zoneno = secno / sbi->secs_per_zone;
+ segno = GET_SEG_FROM_SEC(sbi, secno);
+ zoneno = GET_ZONE_FROM_SEC(sbi, secno);
/* give up on finding another zone */
if (!init)
@@ -1166,7 +2433,7 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
struct summary_footer *sum_footer;
curseg->segno = curseg->next_segno;
- curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno);
+ curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
curseg->next_blkoff = 0;
curseg->next_segno = NULL_SEGNO;
@@ -1179,6 +2446,29 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
__set_sit_entry_type(sbi, type, curseg->segno, modified);
}
+static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
+{
+ /* if segs_per_sec is large than 1, we need to keep original policy. */
+ if (__is_large_section(sbi))
+ return CURSEG_I(sbi, type)->segno;
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;
+
+ if (test_opt(sbi, NOHEAP) &&
+ (type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+ return 0;
+
+ if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
+ return SIT_I(sbi)->last_victim[ALLOC_NEXT];
+
+ /* find segments from 0 to reuse freed segments */
+ if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
+ return 0;
+
+ return CURSEG_I(sbi, type)->segno;
+}
+
/*
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
@@ -1197,6 +2487,7 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
if (test_opt(sbi, NOHEAP))
dir = ALLOC_RIGHT;
+ segno = __get_next_segno(sbi, type);
get_new_segment(sbi, &segno, new_sec, dir);
curseg->next_segno = segno;
reset_curseg(sbi, type, 1);
@@ -1239,7 +2530,7 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
* This function always allocates a used segment(from dirty seglist) by SSR
* manner, so it should recover the existing segment information of valid blocks
*/
-static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
+static void change_curseg(struct f2fs_sb_info *sbi, int type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1260,28 +2551,63 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
curseg->alloc_type = SSR;
__next_free_blkoff(sbi, curseg, 0);
- if (reuse) {
- sum_page = get_sum_page(sbi, new_segno);
- sum_node = (struct f2fs_summary_block *)page_address(sum_page);
- memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
- f2fs_put_page(sum_page, 1);
- }
+ sum_page = f2fs_get_sum_page(sbi, new_segno);
+ f2fs_bug_on(sbi, IS_ERR(sum_page));
+ sum_node = (struct f2fs_summary_block *)page_address(sum_page);
+ memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
+ f2fs_put_page(sum_page, 1);
}
static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+ unsigned segno = NULL_SEGNO;
+ int i, cnt;
+ bool reversed = false;
- if (IS_NODESEG(type))
- return v_ops->get_victim(sbi,
- &(curseg)->next_segno, BG_GC, type, SSR);
+ /* f2fs_need_SSR() already forces to do this */
+ if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+ curseg->next_segno = segno;
+ return 1;
+ }
- /* For data segments, let's do SSR more intensively */
- for (; type >= CURSEG_HOT_DATA; type--)
- if (v_ops->get_victim(sbi, &(curseg)->next_segno,
- BG_GC, type, SSR))
+ /* For node segments, let's do SSR more intensively */
+ if (IS_NODESEG(type)) {
+ if (type >= CURSEG_WARM_NODE) {
+ reversed = true;
+ i = CURSEG_COLD_NODE;
+ } else {
+ i = CURSEG_HOT_NODE;
+ }
+ cnt = NR_CURSEG_NODE_TYPE;
+ } else {
+ if (type >= CURSEG_WARM_DATA) {
+ reversed = true;
+ i = CURSEG_COLD_DATA;
+ } else {
+ i = CURSEG_HOT_DATA;
+ }
+ cnt = NR_CURSEG_DATA_TYPE;
+ }
+
+ for (; cnt-- > 0; reversed ? i-- : i++) {
+ if (i == type)
+ continue;
+ if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+ curseg->next_segno = segno;
return 1;
+ }
+ }
+
+ /* find valid_blocks=0 in dirty list */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ segno = get_free_segment(sbi);
+ if (segno != NULL_SEGNO) {
+ curseg->next_segno = segno;
+ return 1;
+ }
+ }
return 0;
}
@@ -1296,95 +2622,201 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
if (force)
new_curseg(sbi, type, true);
- else if (type == CURSEG_WARM_NODE)
+ else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
+ type == CURSEG_WARM_NODE)
new_curseg(sbi, type, false);
- else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
+ else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) &&
+ likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
new_curseg(sbi, type, false);
- else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
- change_curseg(sbi, type, true);
+ else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
+ change_curseg(sbi, type);
else
new_curseg(sbi, type, false);
stat_inc_seg_type(sbi, curseg);
}
-static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
{
- struct curseg_info *curseg = CURSEG_I(sbi, type);
+ struct curseg_info *curseg;
unsigned int old_segno;
-
- old_segno = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
- locate_dirty_segment(sbi, old_segno);
-}
-
-void allocate_new_segments(struct f2fs_sb_info *sbi)
-{
int i;
- if (test_opt(sbi, LFS))
- return;
+ down_write(&SIT_I(sbi)->sentry_lock);
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
- __allocate_new_segments(sbi, i);
+ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+ curseg = CURSEG_I(sbi, i);
+ old_segno = curseg->segno;
+ SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+ locate_dirty_segment(sbi, old_segno);
+ }
+
+ up_write(&SIT_I(sbi)->sentry_lock);
}
static const struct segment_allocation default_salloc_ops = {
.allocate_segment = allocate_segment_by_default,
};
+bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
+{
+ __u64 trim_start = cpc->trim_start;
+ bool has_candidate = false;
+
+ down_write(&SIT_I(sbi)->sentry_lock);
+ for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
+ if (add_discard_addrs(sbi, cpc, true)) {
+ has_candidate = true;
+ break;
+ }
+ }
+ up_write(&SIT_I(sbi)->sentry_lock);
+
+ cpc->trim_start = trim_start;
+ return has_candidate;
+}
+
+static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy,
+ unsigned int start, unsigned int end)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+ struct rb_node **insert_p = NULL, *insert_parent = NULL;
+ struct discard_cmd *dc;
+ struct blk_plug plug;
+ int issued;
+ unsigned int trimmed = 0;
+
+next:
+ issued = 0;
+
+ mutex_lock(&dcc->cmd_lock);
+ if (unlikely(dcc->rbtree_check))
+ f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+ &dcc->root));
+
+ dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
+ NULL, start,
+ (struct rb_entry **)&prev_dc,
+ (struct rb_entry **)&next_dc,
+ &insert_p, &insert_parent, true);
+ if (!dc)
+ dc = next_dc;
+
+ blk_start_plug(&plug);
+
+ while (dc && dc->lstart <= end) {
+ struct rb_node *node;
+ int err = 0;
+
+ if (dc->len < dpolicy->granularity)
+ goto skip;
+
+ if (dc->state != D_PREP) {
+ list_move_tail(&dc->list, &dcc->fstrim_list);
+ goto skip;
+ }
+
+ err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+ if (issued >= dpolicy->max_requests) {
+ start = dc->lstart + dc->len;
+
+ if (err)
+ __remove_discard_cmd(sbi, dc);
+
+ blk_finish_plug(&plug);
+ mutex_unlock(&dcc->cmd_lock);
+ trimmed += __wait_all_discard_cmd(sbi, NULL);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto next;
+ }
+skip:
+ node = rb_next(&dc->rb_node);
+ if (err)
+ __remove_discard_cmd(sbi, dc);
+ dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+
+ if (fatal_signal_pending(current))
+ break;
+ }
+
+ blk_finish_plug(&plug);
+ mutex_unlock(&dcc->cmd_lock);
+
+ return trimmed;
+}
+
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
{
__u64 start = F2FS_BYTES_TO_BLK(range->start);
__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
unsigned int start_segno, end_segno;
+ block_t start_block, end_block;
struct cp_control cpc;
+ struct discard_policy dpolicy;
+ unsigned long long trimmed = 0;
int err = 0;
+ bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi);
if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
return -EINVAL;
- cpc.trimmed = 0;
- if (end <= MAIN_BLKADDR(sbi))
+ if (end < MAIN_BLKADDR(sbi))
goto out;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
f2fs_msg(sbi->sb, KERN_WARNING,
"Found FS corruption, run fsck to fix.");
- goto out;
+ return -EIO;
}
/* start/end segment number in main_area */
start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
GET_SEGNO(sbi, end);
+ if (need_align) {
+ start_segno = rounddown(start_segno, sbi->segs_per_sec);
+ end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1;
+ }
+
cpc.reason = CP_DISCARD;
cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
+ cpc.trim_start = start_segno;
+ cpc.trim_end = end_segno;
- /* do checkpoint to issue discard commands safely */
- for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
- cpc.trim_start = start_segno;
+ if (sbi->discard_blks == 0)
+ goto out;
- if (sbi->discard_blks == 0)
- break;
- else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
- cpc.trim_end = end_segno;
- else
- cpc.trim_end = min_t(unsigned int,
- rounddown(start_segno +
- BATCHED_TRIM_SEGMENTS(sbi),
- sbi->segs_per_sec) - 1, end_segno);
+ mutex_lock(&sbi->gc_mutex);
+ err = f2fs_write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+ if (err)
+ goto out;
- mutex_lock(&sbi->gc_mutex);
- err = write_checkpoint(sbi, &cpc);
- mutex_unlock(&sbi->gc_mutex);
- if (err)
- break;
+ /*
+ * We filed discard candidates, but actually we don't need to wait for
+ * all of them, since they'll be issued in idle time along with runtime
+ * discard option. User configuration looks like using runtime discard
+ * or periodic fstrim instead of it.
+ */
+ if (f2fs_realtime_discard_enable(sbi))
+ goto out;
- schedule();
- }
+ start_block = START_BLOCK(sbi, start_segno);
+ end_block = START_BLOCK(sbi, end_segno + 1);
+
+ __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
+ trimmed = __issue_discard_cmd_range(sbi, &dpolicy,
+ start_block, end_block);
+
+ trimmed += __wait_discard_cmd_range(sbi, &dpolicy,
+ start_block, end_block);
out:
- range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
+ if (!err)
+ range->len = F2FS_BLK_TO_BYTES(trimmed);
return err;
}
@@ -1396,87 +2828,204 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
return false;
}
-static int __get_segment_type_2(struct page *page, enum page_type p_type)
+int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
{
- if (p_type == DATA)
+ switch (hint) {
+ case WRITE_LIFE_SHORT:
+ return CURSEG_HOT_DATA;
+ case WRITE_LIFE_EXTREME:
+ return CURSEG_COLD_DATA;
+ default:
+ return CURSEG_WARM_DATA;
+ }
+}
+
+/* This returns write hints for each segment type. This hints will be
+ * passed down to block layer. There are mapping tables which depend on
+ * the mount option 'whint_mode'.
+ *
+ * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
+ *
+ * 2) whint_mode=user-based. F2FS tries to pass down hints given by users.
+ *
+ * User F2FS Block
+ * ---- ---- -----
+ * META WRITE_LIFE_NOT_SET
+ * HOT_NODE "
+ * WARM_NODE "
+ * COLD_NODE "
+ * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+ * extension list " "
+ *
+ * -- buffered io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " "
+ * WRITE_LIFE_MEDIUM " "
+ * WRITE_LIFE_LONG " "
+ *
+ * -- direct io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " WRITE_LIFE_NONE
+ * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+ * WRITE_LIFE_LONG " WRITE_LIFE_LONG
+ *
+ * 3) whint_mode=fs-based. F2FS passes down hints with its policy.
+ *
+ * User F2FS Block
+ * ---- ---- -----
+ * META WRITE_LIFE_MEDIUM;
+ * HOT_NODE WRITE_LIFE_NOT_SET
+ * WARM_NODE "
+ * COLD_NODE WRITE_LIFE_NONE
+ * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+ * extension list " "
+ *
+ * -- buffered io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
+ * WRITE_LIFE_NONE " "
+ * WRITE_LIFE_MEDIUM " "
+ * WRITE_LIFE_LONG " "
+ *
+ * -- direct io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " WRITE_LIFE_NONE
+ * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+ * WRITE_LIFE_LONG " WRITE_LIFE_LONG
+ */
+
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp)
+{
+ if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
+ if (type == DATA) {
+ if (temp == WARM)
+ return WRITE_LIFE_NOT_SET;
+ else if (temp == HOT)
+ return WRITE_LIFE_SHORT;
+ else if (temp == COLD)
+ return WRITE_LIFE_EXTREME;
+ } else {
+ return WRITE_LIFE_NOT_SET;
+ }
+ } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) {
+ if (type == DATA) {
+ if (temp == WARM)
+ return WRITE_LIFE_LONG;
+ else if (temp == HOT)
+ return WRITE_LIFE_SHORT;
+ else if (temp == COLD)
+ return WRITE_LIFE_EXTREME;
+ } else if (type == NODE) {
+ if (temp == WARM || temp == HOT)
+ return WRITE_LIFE_NOT_SET;
+ else if (temp == COLD)
+ return WRITE_LIFE_NONE;
+ } else if (type == META) {
+ return WRITE_LIFE_MEDIUM;
+ }
+ }
+ return WRITE_LIFE_NOT_SET;
+}
+
+static int __get_segment_type_2(struct f2fs_io_info *fio)
+{
+ if (fio->type == DATA)
return CURSEG_HOT_DATA;
else
return CURSEG_HOT_NODE;
}
-static int __get_segment_type_4(struct page *page, enum page_type p_type)
+static int __get_segment_type_4(struct f2fs_io_info *fio)
{
- if (p_type == DATA) {
- struct inode *inode = page->mapping->host;
+ if (fio->type == DATA) {
+ struct inode *inode = fio->page->mapping->host;
if (S_ISDIR(inode->i_mode))
return CURSEG_HOT_DATA;
else
return CURSEG_COLD_DATA;
} else {
- if (IS_DNODE(page) && is_cold_node(page))
+ if (IS_DNODE(fio->page) && is_cold_node(fio->page))
return CURSEG_WARM_NODE;
else
return CURSEG_COLD_NODE;
}
}
-static int __get_segment_type_6(struct page *page, enum page_type p_type)
+static int __get_segment_type_6(struct f2fs_io_info *fio)
{
- if (p_type == DATA) {
- struct inode *inode = page->mapping->host;
+ if (fio->type == DATA) {
+ struct inode *inode = fio->page->mapping->host;
- if (S_ISDIR(inode->i_mode))
- return CURSEG_HOT_DATA;
- else if (is_cold_data(page) || file_is_cold(inode))
+ if (is_cold_data(fio->page) || file_is_cold(inode))
return CURSEG_COLD_DATA;
- else
- return CURSEG_WARM_DATA;
+ if (file_is_hot(inode) ||
+ is_inode_flag_set(inode, FI_HOT_DATA) ||
+ f2fs_is_atomic_file(inode) ||
+ f2fs_is_volatile_file(inode))
+ return CURSEG_HOT_DATA;
+ /* f2fs_rw_hint_to_seg_type(inode->i_write_hint); */
+ return CURSEG_WARM_DATA;
} else {
- if (IS_DNODE(page))
- return is_cold_node(page) ? CURSEG_WARM_NODE :
+ if (IS_DNODE(fio->page))
+ return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
CURSEG_HOT_NODE;
- else
- return CURSEG_COLD_NODE;
+ return CURSEG_COLD_NODE;
}
}
-static int __get_segment_type(struct page *page, enum page_type p_type)
+static int __get_segment_type(struct f2fs_io_info *fio)
{
- switch (F2FS_P_SB(page)->active_logs) {
+ int type = 0;
+
+ switch (F2FS_OPTION(fio->sbi).active_logs) {
case 2:
- return __get_segment_type_2(page, p_type);
+ type = __get_segment_type_2(fio);
+ break;
case 4:
- return __get_segment_type_4(page, p_type);
+ type = __get_segment_type_4(fio);
+ break;
+ case 6:
+ type = __get_segment_type_6(fio);
+ break;
+ default:
+ f2fs_bug_on(fio->sbi, true);
}
- /* NR_CURSEG_TYPE(6) logs by default */
- f2fs_bug_on(F2FS_P_SB(page),
- F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE);
- return __get_segment_type_6(page, p_type);
+
+ if (IS_HOT(type))
+ fio->temp = HOT;
+ else if (IS_WARM(type))
+ fio->temp = WARM;
+ else
+ fio->temp = COLD;
+ return type;
}
-void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
- struct f2fs_summary *sum, int type)
+ struct f2fs_summary *sum, int type,
+ struct f2fs_io_info *fio, bool add_list)
{
struct sit_info *sit_i = SIT_I(sbi);
- struct curseg_info *curseg;
- bool direct_io = (type == CURSEG_DIRECT_IO);
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
- type = direct_io ? CURSEG_WARM_DATA : type;
-
- curseg = CURSEG_I(sbi, type);
+ down_read(&SM_I(sbi)->curseg_lock);
mutex_lock(&curseg->curseg_mutex);
- mutex_lock(&sit_i->sentry_lock);
-
- /* direct_io'ed data is aligned to the segment for better performance */
- if (direct_io && curseg->next_blkoff &&
- !has_not_enough_free_secs(sbi, 0, 0))
- __allocate_new_segments(sbi, type);
+ down_write(&sit_i->sentry_lock);
*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+ f2fs_wait_discard_bio(sbi, *new_blkaddr);
+
/*
* __add_sum_entry should be resided under the curseg_mutex
* because, this function updates a summary entry in the
@@ -1488,88 +3037,185 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
stat_inc_block_count(sbi, curseg);
- if (!__has_curseg_space(sbi, type))
- sit_i->s_ops->allocate_segment(sbi, type, false);
/*
* SIT information should be updated before segment allocation,
* since SSR needs latest valid block information.
*/
- refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
+ update_sit_entry(sbi, *new_blkaddr, 1);
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ update_sit_entry(sbi, old_blkaddr, -1);
- mutex_unlock(&sit_i->sentry_lock);
+ if (!__has_curseg_space(sbi, type))
+ sit_i->s_ops->allocate_segment(sbi, type, false);
- if (page && IS_NODESEG(type))
+ /*
+ * segment dirty status should be updated after segment allocation,
+ * so we just need to update status only one time after previous
+ * segment being closed.
+ */
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
+
+ up_write(&sit_i->sentry_lock);
+
+ if (page && IS_NODESEG(type)) {
fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
+ f2fs_inode_chksum_set(sbi, page);
+ }
+
+ if (add_list) {
+ struct f2fs_bio_info *io;
+
+ INIT_LIST_HEAD(&fio->list);
+ fio->in_list = true;
+ fio->retry = false;
+ io = sbi->write_io[fio->type] + fio->temp;
+ spin_lock(&io->io_lock);
+ list_add_tail(&fio->list, &io->io_list);
+ spin_unlock(&io->io_lock);
+ }
+
mutex_unlock(&curseg->curseg_mutex);
+
+ up_read(&SM_I(sbi)->curseg_lock);
+}
+
+static void update_device_state(struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = fio->sbi;
+ unsigned int devidx;
+
+ if (!sbi->s_ndevs)
+ return;
+
+ devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
+
+ /* update device state for fsync */
+ f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+
+ /* update device state for checkpoint */
+ if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
+ spin_lock(&sbi->dev_lock);
+ f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
+ spin_unlock(&sbi->dev_lock);
+ }
}
static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
- int type = __get_segment_type(fio->page, fio->type);
+ int type = __get_segment_type(fio);
+ bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA);
- if (fio->type == NODE || fio->type == DATA)
- mutex_lock(&fio->sbi->wio_mutex[fio->type]);
-
- allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type);
+ if (keep_order)
+ down_read(&fio->sbi->io_order_lock);
+reallocate:
+ f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+ &fio->new_blkaddr, sum, type, fio, true);
+ if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
+ invalidate_mapping_pages(META_MAPPING(fio->sbi),
+ fio->old_blkaddr, fio->old_blkaddr);
/* writeout dirty page into bdev */
- f2fs_submit_page_mbio(fio);
+ f2fs_submit_page_write(fio);
+ if (fio->retry) {
+ fio->old_blkaddr = fio->new_blkaddr;
+ goto reallocate;
+ }
- if (fio->type == NODE || fio->type == DATA)
- mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
+ update_device_state(fio);
+
+ if (keep_order)
+ up_read(&fio->sbi->io_order_lock);
}
-void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+ enum iostat_type io_type)
{
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
+ .temp = HOT,
.op = REQ_OP_WRITE,
- .op_flags = WRITE_SYNC | REQ_META | REQ_PRIO,
+ .op_flags = REQ_SYNC | REQ_META | REQ_PRIO,
.old_blkaddr = page->index,
.new_blkaddr = page->index,
.page = page,
.encrypted_page = NULL,
+ .in_list = false,
};
if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
fio.op_flags &= ~REQ_META;
set_page_writeback(page);
- f2fs_submit_page_mbio(&fio);
+ ClearPageError(page);
+ f2fs_submit_page_write(&fio);
+
+ stat_inc_meta_count(sbi, page->index);
+ f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
}
-void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
+void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
{
struct f2fs_summary sum;
set_summary(&sum, nid, 0, 0);
do_write_page(&sum, fio);
+
+ f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
}
-void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
+void f2fs_outplace_write_data(struct dnode_of_data *dn,
+ struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct f2fs_summary sum;
- struct node_info ni;
f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
- get_node_info(sbi, dn->nid, &ni);
- set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
+ set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version);
do_write_page(&sum, fio);
f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
+
+ f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
}
-void rewrite_data_page(struct f2fs_io_info *fio)
+int f2fs_inplace_write_data(struct f2fs_io_info *fio)
{
+ int err;
+ struct f2fs_sb_info *sbi = fio->sbi;
+
fio->new_blkaddr = fio->old_blkaddr;
+ /* i/o temperature is needed for passing down write hints */
+ __get_segment_type(fio);
+
+ f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi,
+ GET_SEGNO(sbi, fio->new_blkaddr))->type));
+
stat_inc_inplace_blocks(fio->sbi);
- f2fs_submit_page_mbio(fio);
+
+ err = f2fs_submit_page_bio(fio);
+ if (!err) {
+ update_device_state(fio);
+ f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+ }
+
+ return err;
}
-void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
+ unsigned int segno)
+{
+ int i;
+
+ for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
+ if (CURSEG_I(sbi, i)->segno == segno)
+ break;
+ }
+ return i;
+}
+
+void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
bool recover_curseg, bool recover_newaddr)
{
@@ -1584,6 +3230,8 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
se = get_seg_entry(sbi, segno);
type = se->type;
+ down_write(&SM_I(sbi)->curseg_lock);
+
if (!recover_curseg) {
/* for recovery flow */
if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
@@ -1593,14 +3241,20 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
type = CURSEG_WARM_DATA;
}
} else {
- if (!IS_CURSEG(sbi, segno))
+ if (IS_CURSEG(sbi, segno)) {
+ /* se->type is volatile as SSR allocation */
+ type = __f2fs_get_curseg(sbi, segno);
+ f2fs_bug_on(sbi, type == NO_CHECK_TYPE);
+ } else {
type = CURSEG_WARM_DATA;
+ }
}
+ f2fs_bug_on(sbi, !IS_DATASEG(type));
curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
- mutex_lock(&sit_i->sentry_lock);
+ down_write(&sit_i->sentry_lock);
old_cursegno = curseg->segno;
old_blkoff = curseg->next_blkoff;
@@ -1608,7 +3262,7 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
/* change the current segment */
if (segno != curseg->segno) {
curseg->next_segno = segno;
- change_curseg(sbi, type, true);
+ change_curseg(sbi, type);
}
curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
@@ -1616,8 +3270,11 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (!recover_curseg || recover_newaddr)
update_sit_entry(sbi, new_blkaddr, 1);
- if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ old_blkaddr, old_blkaddr);
update_sit_entry(sbi, old_blkaddr, -1);
+ }
locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
@@ -1627,13 +3284,14 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (recover_curseg) {
if (old_cursegno != curseg->segno) {
curseg->next_segno = old_cursegno;
- change_curseg(sbi, type, true);
+ change_curseg(sbi, type);
}
curseg->next_blkoff = old_blkoff;
}
- mutex_unlock(&sit_i->sentry_lock);
+ up_write(&sit_i->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
+ up_write(&SM_I(sbi)->curseg_lock);
}
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
@@ -1645,41 +3303,55 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
set_summary(&sum, dn->nid, dn->ofs_in_node, version);
- __f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+ f2fs_do_replace_block(sbi, &sum, old_addr, new_addr,
recover_curseg, recover_newaddr);
f2fs_update_data_blkaddr(dn, new_addr);
}
void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type, bool ordered)
+ enum page_type type, bool ordered, bool locked)
{
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
- if (ordered)
+ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+ if (ordered) {
wait_on_page_writeback(page);
- else
+ f2fs_bug_on(sbi, locked && PageWriteback(page));
+ } else {
wait_for_stable_page(page);
+ }
}
}
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *cpage;
+ if (!f2fs_post_read_required(inode))
+ return;
+
if (!is_valid_data_blkaddr(sbi, blkaddr))
return;
cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
if (cpage) {
- f2fs_wait_on_page_writeback(cpage, DATA, true);
+ f2fs_wait_on_page_writeback(cpage, DATA, true, true);
f2fs_put_page(cpage, 1);
}
}
+void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
+ block_t len)
+{
+ block_t i;
+
+ for (i = 0; i < len; i++)
+ f2fs_wait_on_block_writeback(inode, blkaddr + i);
+}
+
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -1691,7 +3363,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
start = start_sum_block(sbi);
- page = get_meta_page(sbi, start++);
+ page = f2fs_get_meta_page(sbi, start++);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
/* Step 1: restore nat cache */
@@ -1731,7 +3405,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
f2fs_put_page(page, 1);
page = NULL;
- page = get_meta_page(sbi, start++);
+ page = f2fs_get_meta_page(sbi, start++);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
offset = 0;
}
@@ -1749,6 +3425,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
unsigned short blk_off;
unsigned int segno = 0;
block_t blk_addr = 0;
+ int err = 0;
/* get segment number and block addr */
if (IS_DATASEG(type)) {
@@ -1771,7 +3448,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
blk_addr = GET_SUM_BLOCK(sbi, segno);
}
- new = get_meta_page(sbi, blk_addr);
+ new = f2fs_get_meta_page(sbi, blk_addr);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
sum = (struct f2fs_summary_block *)page_address(new);
if (IS_NODESEG(type)) {
@@ -1783,13 +3462,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
ns->ofs_in_node = 0;
}
} else {
- int err;
-
- err = restore_node_summary(sbi, segno, sum);
- if (err) {
- f2fs_put_page(new, 1);
- return err;
- }
+ err = f2fs_restore_node_summary(sbi, segno, sum);
+ if (err)
+ goto out;
}
}
@@ -1809,8 +3484,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
curseg->alloc_type = ckpt->alloc_type[type];
curseg->next_blkoff = blk_off;
mutex_unlock(&curseg->curseg_mutex);
+out:
f2fs_put_page(new, 1);
- return 0;
+ return err;
}
static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
@@ -1821,20 +3497,21 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
int err;
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
- int npages = npages_for_summary_flush(sbi, true);
+ int npages = f2fs_npages_for_summary_flush(sbi, true);
if (npages >= 2)
- ra_meta_pages(sbi, start_sum_block(sbi), npages,
+ f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages,
META_CP, true);
/* restore for compacted data summary */
- if (read_compacted_summaries(sbi))
- return -EINVAL;
+ err = read_compacted_summaries(sbi);
+ if (err)
+ return err;
type = CURSEG_HOT_NODE;
}
if (__exist_node_summaries(sbi))
- ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+ f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
NR_CURSEG_TYPE - type, META_CP, true);
for (; type <= CURSEG_COLD_NODE; type++) {
@@ -1860,8 +3537,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
int written_size = 0;
int i, j;
- page = grab_meta_page(sbi, blkaddr++);
+ page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
+ memset(kaddr, 0, PAGE_SIZE);
/* Step 1: write nat cache */
seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -1884,8 +3562,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
for (j = 0; j < blkoff; j++) {
if (!page) {
- page = grab_meta_page(sbi, blkaddr++);
+ page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
+ memset(kaddr, 0, PAGE_SIZE);
written_size = 0;
}
summary = (struct f2fs_summary *)(kaddr + written_size);
@@ -1920,7 +3599,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
write_current_sum_page(sbi, i, blkaddr + (i - type));
}
-void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
write_compacted_summaries(sbi, start_blk);
@@ -1928,12 +3607,12 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
}
-void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}
-int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc)
{
int i;
@@ -1958,35 +3637,26 @@ int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
- return get_meta_page(sbi, current_sit_addr(sbi, segno));
+ return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
}
static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
unsigned int start)
{
struct sit_info *sit_i = SIT_I(sbi);
- struct page *src_page, *dst_page;
+ struct page *page;
pgoff_t src_off, dst_off;
- void *src_addr, *dst_addr;
src_off = current_sit_addr(sbi, start);
dst_off = next_sit_addr(sbi, src_off);
- /* get current sit block page without lock */
- src_page = get_meta_page(sbi, src_off);
- dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(sbi, PageDirty(src_page));
+ page = f2fs_grab_meta_page(sbi, dst_off);
+ seg_info_to_sit_page(sbi, page, start);
- src_addr = page_address(src_page);
- dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_SIZE);
-
- set_page_dirty(dst_page);
- f2fs_put_page(src_page, 1);
-
+ set_page_dirty(page);
set_to_next_sit(sit_i, start);
- return dst_page;
+ return page;
}
static struct sit_entry_set *grab_sit_entry_set(void)
@@ -2076,7 +3746,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
* CP calls this function, which flushes SIT entries including sit_journal,
* and moves prefree segs to free segs.
*/
-void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
@@ -2087,7 +3757,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
bool to_journal = true;
struct seg_entry *se;
- mutex_lock(&sit_i->sentry_lock);
+ down_write(&sit_i->sentry_lock);
if (!sit_i->dirty_sentries)
goto out;
@@ -2135,25 +3805,34 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
int offset, sit_offset;
se = get_seg_entry(sbi, segno);
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(se->cur_valid_map, se->cur_valid_map_mir,
+ SIT_VBLOCK_MAP_SIZE))
+ f2fs_bug_on(sbi, 1);
+#endif
/* add discard candidates */
- if (cpc->reason != CP_DISCARD) {
+ if (!(cpc->reason & CP_DISCARD)) {
cpc->trim_start = segno;
- add_discard_addrs(sbi, cpc);
+ add_discard_addrs(sbi, cpc, false);
}
if (to_journal) {
- offset = lookup_journal_in_cursum(journal,
+ offset = f2fs_lookup_journal_in_cursum(journal,
SIT_JOURNAL, segno, 1);
f2fs_bug_on(sbi, offset < 0);
segno_in_journal(journal, offset) =
cpu_to_le32(segno);
seg_info_to_raw_sit(se,
&sit_in_journal(journal, offset));
+ check_block_count(sbi, segno,
+ &sit_in_journal(journal, offset));
} else {
sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
seg_info_to_raw_sit(se,
&raw_sit->entries[sit_offset]);
+ check_block_count(sbi, segno,
+ &raw_sit->entries[sit_offset]);
}
__clear_bit(segno, bitmap);
@@ -2173,11 +3852,15 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_bug_on(sbi, !list_empty(head));
f2fs_bug_on(sbi, sit_i->dirty_sentries);
out:
- if (cpc->reason == CP_DISCARD) {
+ if (cpc->reason & CP_DISCARD) {
+ __u64 trim_start = cpc->trim_start;
+
for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
- add_discard_addrs(sbi, cpc);
+ add_discard_addrs(sbi, cpc, false);
+
+ cpc->trim_start = trim_start;
}
- mutex_unlock(&sit_i->sentry_lock);
+ up_write(&sit_i->sentry_lock);
set_prefree_as_free_segments(sbi);
}
@@ -2185,53 +3868,63 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
static int build_sit_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct sit_info *sit_i;
unsigned int sit_segs, start;
- char *src_bitmap, *dst_bitmap;
+ char *src_bitmap;
unsigned int bitmap_size;
/* allocate memory for SIT information */
- sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL);
+ sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL);
if (!sit_i)
return -ENOMEM;
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
- sizeof(struct seg_entry), GFP_KERNEL);
+ sit_i->sentries =
+ f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry),
+ MAIN_SEGS(sbi)),
+ GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+ sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, bitmap_size,
+ GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
for (start = 0; start < MAIN_SEGS(sbi); start++) {
sit_i->sentries[start].cur_valid_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
sit_i->sentries[start].ckpt_valid_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->sentries[start].cur_valid_map ||
!sit_i->sentries[start].ckpt_valid_map)
return -ENOMEM;
- if (f2fs_discard_en(sbi)) {
- sit_i->sentries[start].discard_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
- if (!sit_i->sentries[start].discard_map)
- return -ENOMEM;
- }
+#ifdef CONFIG_F2FS_CHECK_FS
+ sit_i->sentries[start].cur_valid_map_mir
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->sentries[start].cur_valid_map_mir)
+ return -ENOMEM;
+#endif
+
+ sit_i->sentries[start].discard_map
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE,
+ GFP_KERNEL);
+ if (!sit_i->sentries[start].discard_map)
+ return -ENOMEM;
}
- sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->tmp_map)
return -ENOMEM;
- if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
- sizeof(struct sec_entry), GFP_KERNEL);
+ if (__is_large_section(sbi)) {
+ sit_i->sec_entries =
+ f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry),
+ MAIN_SECS(sbi)),
+ GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
}
@@ -2243,23 +3936,28 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
- dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
- if (!dst_bitmap)
+ sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+ if (!sit_i->sit_bitmap)
return -ENOMEM;
+#ifdef CONFIG_F2FS_CHECK_FS
+ sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+ if (!sit_i->sit_bitmap_mir)
+ return -ENOMEM;
+#endif
+
/* init SIT information */
sit_i->s_ops = &default_salloc_ops;
sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
- sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
- sit_i->sit_bitmap = dst_bitmap;
+ sit_i->written_valid_blocks = 0;
sit_i->bitmap_size = bitmap_size;
sit_i->dirty_sentries = 0;
sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
- sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec;
- mutex_init(&sit_i->sentry_lock);
+ sit_i->mounted_time = ktime_get_real_seconds();
+ init_rwsem(&sit_i->sentry_lock);
return 0;
}
@@ -2269,19 +3967,19 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
unsigned int bitmap_size, sec_bitmap_size;
/* allocate memory for free segmap information */
- free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL);
+ free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL);
if (!free_i)
return -ENOMEM;
SM_I(sbi)->free_info = free_i;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
+ free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL);
+ free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -2302,7 +4000,8 @@ static int build_curseg(struct f2fs_sb_info *sbi)
struct curseg_info *array;
int i;
- array = kcalloc(NR_CURSEG_TYPE, sizeof(*array), GFP_KERNEL);
+ array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)),
+ GFP_KERNEL);
if (!array)
return -ENOMEM;
@@ -2310,12 +4009,12 @@ static int build_curseg(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_CURSEG_TYPE; i++) {
mutex_init(&array[i].curseg_mutex);
- array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL);
if (!array[i].sum_blk)
return -ENOMEM;
init_rwsem(&array[i].journal_rwsem);
- array[i].journal = kzalloc(sizeof(struct f2fs_journal),
- GFP_KERNEL);
+ array[i].journal = f2fs_kzalloc(sbi,
+ sizeof(struct f2fs_journal), GFP_KERNEL);
if (!array[i].journal)
return -ENOMEM;
array[i].segno = NULL_SEGNO;
@@ -2334,11 +4033,12 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
int sit_blk_cnt = SIT_BLK_CNT(sbi);
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
- int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
int err = 0;
+ block_t total_node_blocks = 0;
do {
- readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
+ readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+ META_SIT, true);
start = start_blk * sit_i->sents_per_block;
end = (start_blk + readed) * sit_i->sents_per_block;
@@ -2349,6 +4049,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
se = &sit_i->sentries[start];
page = get_current_sit_page(sbi, start);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
sit_blk = (struct f2fs_sit_block *)page_address(page);
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
@@ -2357,16 +4059,23 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
if (err)
return err;
seg_info_from_raw_sit(se, &sit);
+ if (IS_NODESEG(se->type))
+ total_node_blocks += se->valid_blocks;
/* build discard map only one time */
- if (f2fs_discard_en(sbi)) {
- memcpy(se->discard_map, se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks += sbi->blocks_per_seg -
- se->valid_blocks;
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff,
+ SIT_VBLOCK_MAP_SIZE);
+ } else {
+ memcpy(se->discard_map,
+ se->cur_valid_map,
+ SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks +=
+ sbi->blocks_per_seg -
+ se->valid_blocks;
}
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi))
get_sec_entry(sbi, start)->valid_blocks +=
se->valid_blocks;
}
@@ -2391,24 +4100,42 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
sit = sit_in_journal(journal, i);
old_valid_blocks = se->valid_blocks;
+ if (IS_NODESEG(se->type))
+ total_node_blocks -= old_valid_blocks;
err = check_block_count(sbi, start, &sit);
if (err)
break;
seg_info_from_raw_sit(se, &sit);
+ if (IS_NODESEG(se->type))
+ total_node_blocks += se->valid_blocks;
- if (f2fs_discard_en(sbi)) {
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE);
+ } else {
memcpy(se->discard_map, se->cur_valid_map,
SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks += old_valid_blocks -
- se->valid_blocks;
+ sbi->discard_blks += old_valid_blocks;
+ sbi->discard_blks -= se->valid_blocks;
}
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi)) {
get_sec_entry(sbi, start)->valid_blocks +=
- se->valid_blocks - old_valid_blocks;
+ se->valid_blocks;
+ get_sec_entry(sbi, start)->valid_blocks -=
+ old_valid_blocks;
+ }
}
up_read(&curseg->journal_rwsem);
+
+ if (!err && total_node_blocks != valid_node_count(sbi)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "SIT is corrupted node# %u vs %u",
+ total_node_blocks, valid_node_count(sbi));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EINVAL;
+ }
+
return err;
}
@@ -2421,6 +4148,9 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
struct seg_entry *sentry = get_seg_entry(sbi, start);
if (!sentry->valid_blocks)
__set_free(sbi, start);
+ else
+ SIT_I(sbi)->written_valid_blocks +=
+ sentry->valid_blocks;
}
/* set use the current segments */
@@ -2443,7 +4173,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
if (segno >= MAIN_SEGS(sbi))
break;
offset = segno + 1;
- valid_blocks = get_valid_blocks(sbi, segno, 0);
+ valid_blocks = get_valid_blocks(sbi, segno, false);
if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
continue;
if (valid_blocks > sbi->blocks_per_seg) {
@@ -2461,7 +4191,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi)
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
return 0;
@@ -2473,7 +4203,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
unsigned int bitmap_size, i;
/* allocate memory for dirty segments list information */
- dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL);
+ dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info),
+ GFP_KERNEL);
if (!dirty_i)
return -ENOMEM;
@@ -2483,7 +4214,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
for (i = 0; i < NR_DIRTY_TYPE; i++) {
- dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size,
+ GFP_KERNEL);
if (!dirty_i->dirty_segmap[i])
return -ENOMEM;
}
@@ -2535,9 +4267,9 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
struct sit_info *sit_i = SIT_I(sbi);
unsigned int segno;
- mutex_lock(&sit_i->sentry_lock);
+ down_write(&sit_i->sentry_lock);
- sit_i->min_mtime = LLONG_MAX;
+ sit_i->min_mtime = ULLONG_MAX;
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
unsigned int i;
@@ -2551,18 +4283,18 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
if (sit_i->min_mtime > mtime)
sit_i->min_mtime = mtime;
}
- sit_i->max_mtime = get_mtime(sbi);
- mutex_unlock(&sit_i->sentry_lock);
+ sit_i->max_mtime = get_mtime(sbi, false);
+ up_write(&sit_i->sentry_lock);
}
-int build_segment_manager(struct f2fs_sb_info *sbi)
+int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_sm_info *sm_info;
int err;
- sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL);
+ sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL);
if (!sm_info)
return -ENOMEM;
@@ -2584,22 +4316,24 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
-
- INIT_LIST_HEAD(&sm_info->discard_list);
- INIT_LIST_HEAD(&sm_info->wait_list);
- sm_info->nr_discards = 0;
- sm_info->max_discards = 0;
-
- sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+ sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
+ sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
+ sm_info->min_ssr_sections = reserved_sections(sbi);
INIT_LIST_HEAD(&sm_info->sit_entry_set);
+ init_rwsem(&sm_info->curseg_lock);
+
if (!f2fs_readonly(sbi->sb)) {
- err = create_flush_cmd_control(sbi);
+ err = f2fs_create_flush_cmd_control(sbi);
if (err)
return err;
}
+ err = create_discard_cmd_control(sbi);
+ if (err)
+ return err;
+
err = build_sit_info(sbi);
if (err)
return err;
@@ -2659,7 +4393,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
destroy_victim_secmap(sbi);
SM_I(sbi)->dirty_info = NULL;
- kfree(dirty_i);
+ kvfree(dirty_i);
}
static void destroy_curseg(struct f2fs_sb_info *sbi)
@@ -2671,10 +4405,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
return;
SM_I(sbi)->curseg_array = NULL;
for (i = 0; i < NR_CURSEG_TYPE; i++) {
- kfree(array[i].sum_blk);
- kfree(array[i].journal);
+ kvfree(array[i].sum_blk);
+ kvfree(array[i].journal);
}
- kfree(array);
+ kvfree(array);
}
static void destroy_free_segmap(struct f2fs_sb_info *sbi)
@@ -2685,7 +4419,7 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi)
SM_I(sbi)->free_info = NULL;
kvfree(free_i->free_segmap);
kvfree(free_i->free_secmap);
- kfree(free_i);
+ kvfree(free_i);
}
static void destroy_sit_info(struct f2fs_sb_info *sbi)
@@ -2698,53 +4432,60 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
if (sit_i->sentries) {
for (start = 0; start < MAIN_SEGS(sbi); start++) {
- kfree(sit_i->sentries[start].cur_valid_map);
- kfree(sit_i->sentries[start].ckpt_valid_map);
- kfree(sit_i->sentries[start].discard_map);
+ kvfree(sit_i->sentries[start].cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kvfree(sit_i->sentries[start].cur_valid_map_mir);
+#endif
+ kvfree(sit_i->sentries[start].ckpt_valid_map);
+ kvfree(sit_i->sentries[start].discard_map);
}
}
- kfree(sit_i->tmp_map);
+ kvfree(sit_i->tmp_map);
kvfree(sit_i->sentries);
kvfree(sit_i->sec_entries);
kvfree(sit_i->dirty_sentries_bitmap);
SM_I(sbi)->sit_info = NULL;
- kfree(sit_i->sit_bitmap);
- kfree(sit_i);
+ kvfree(sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kvfree(sit_i->sit_bitmap_mir);
+#endif
+ kvfree(sit_i);
}
-void destroy_segment_manager(struct f2fs_sb_info *sbi)
+void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_sm_info *sm_info = SM_I(sbi);
if (!sm_info)
return;
- destroy_flush_cmd_control(sbi);
+ f2fs_destroy_flush_cmd_control(sbi, true);
+ destroy_discard_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
destroy_free_segmap(sbi);
destroy_sit_info(sbi);
sbi->sm_info = NULL;
- kfree(sm_info);
+ kvfree(sm_info);
}
-int __init create_segment_manager_caches(void)
+int __init f2fs_create_segment_manager_caches(void)
{
discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
sizeof(struct discard_entry));
if (!discard_entry_slab)
goto fail;
- bio_entry_slab = f2fs_kmem_cache_create("bio_entry",
- sizeof(struct bio_entry));
- if (!bio_entry_slab)
+ discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd",
+ sizeof(struct discard_cmd));
+ if (!discard_cmd_slab)
goto destroy_discard_entry;
sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
sizeof(struct sit_entry_set));
if (!sit_entry_set_slab)
- goto destroy_bio_entry;
+ goto destroy_discard_cmd;
inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
sizeof(struct inmem_pages));
@@ -2754,18 +4495,18 @@ int __init create_segment_manager_caches(void)
destroy_sit_entry_set:
kmem_cache_destroy(sit_entry_set_slab);
-destroy_bio_entry:
- kmem_cache_destroy(bio_entry_slab);
+destroy_discard_cmd:
+ kmem_cache_destroy(discard_cmd_slab);
destroy_discard_entry:
kmem_cache_destroy(discard_entry_slab);
fail:
return -ENOMEM;
}
-void destroy_segment_manager_caches(void)
+void f2fs_destroy_segment_manager_caches(void)
{
kmem_cache_destroy(sit_entry_set_slab);
- kmem_cache_destroy(bio_entry_slab);
+ kmem_cache_destroy(discard_cmd_slab);
kmem_cache_destroy(discard_entry_slab);
kmem_cache_destroy(inmem_entry_slab);
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index faca7fd..6f48e07 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/segment.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -21,33 +18,37 @@
#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
/* L: Logical segment # in volume, R: Relative segment # in main area */
-#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno)
-#define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno)
+#define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno)
+#define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno)
-#define IS_DATASEG(t) (t <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t) (t >= CURSEG_HOT_NODE)
+#define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA)
+#define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE)
+
+#define IS_HOT(t) ((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
+#define IS_WARM(t) ((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
+#define IS_COLD(t) ((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
#define IS_CURSEG(sbi, seg) \
- ((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+ (((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
#define IS_CURSEC(sbi, secno) \
- ((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
- sbi->segs_per_sec)) \
+ (((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
+ (sbi)->segs_per_sec)) \
#define MAIN_BLKADDR(sbi) \
(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
@@ -57,48 +58,54 @@
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
-#define MAIN_SECS(sbi) (sbi->total_sections)
+#define MAIN_SECS(sbi) ((sbi)->total_sections)
#define TOTAL_SEGS(sbi) \
(SM_I(sbi) ? SM_I(sbi)->segment_count : \
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
-#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
-#define SEGMENT_SIZE(sbi) (1ULL << (sbi->log_blocksize + \
- sbi->log_blocks_per_seg))
+#define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \
+ (sbi)->log_blocks_per_seg))
#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
- (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+ (GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
#define NEXT_FREE_BLKADDR(sbi, curseg) \
- (START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
+ (START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
+ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
+ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
((!is_valid_data_blkaddr(sbi, blk_addr)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
-#define GET_SECNO(sbi, segno) \
- ((segno) / sbi->segs_per_sec)
-#define GET_ZONENO_FROM_SEGNO(sbi, segno) \
- ((segno / sbi->segs_per_sec) / sbi->secs_per_zone)
+#define BLKS_PER_SEC(sbi) \
+ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
+#define GET_SEC_FROM_SEG(sbi, segno) \
+ ((segno) / (sbi)->segs_per_sec)
+#define GET_SEG_FROM_SEC(sbi, secno) \
+ ((secno) * (sbi)->segs_per_sec)
+#define GET_ZONE_FROM_SEC(sbi, secno) \
+ ((secno) / (sbi)->secs_per_zone)
+#define GET_ZONE_FROM_SEG(sbi, segno) \
+ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
#define GET_SUM_BLOCK(sbi, segno) \
- ((sbi->sm_info->ssa_blkaddr) + segno)
+ ((sbi)->sm_info->ssa_blkaddr + (segno))
#define GET_SUM_TYPE(footer) ((footer)->entry_type)
-#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)
+#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
#define SIT_ENTRY_OFFSET(sit_i, segno) \
- (segno % sit_i->sents_per_block)
+ ((segno) % (sit_i)->sents_per_block)
#define SIT_BLOCK_OFFSET(segno) \
- (segno / SIT_ENTRY_PER_BLOCK)
+ ((segno) / SIT_ENTRY_PER_BLOCK)
#define START_SEGNO(segno) \
(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi) \
@@ -109,9 +116,7 @@
#define SECTOR_FROM_BLOCK(blk_addr) \
(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
#define SECTOR_TO_BLOCK(sectors) \
- (sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
-#define MAX_BIO_BLOCKS(sbi) \
- ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
+ ((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
/*
* indicate a block allocation direction: RIGHT and LEFT.
@@ -140,7 +145,10 @@ enum {
*/
enum {
GC_CB = 0,
- GC_GREEDY
+ GC_GREEDY,
+ ALLOC_NEXT,
+ FLUSH_DEVICE,
+ MAX_GC_POLICY,
};
/*
@@ -172,6 +180,9 @@ struct seg_entry {
unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */
unsigned int padding:6; /* padding */
unsigned char *cur_valid_map; /* validity bitmap of blocks */
+#ifdef CONFIG_F2FS_CHECK_FS
+ unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
+#endif
/*
* # of valid blocks and the validity bitmap stored in the the last
* checkpoint pack. This information is used by the SSR mode.
@@ -194,9 +205,14 @@ struct segment_allocation {
* the page is atomically written, and it is in inmem_pages list.
*/
#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
#define IS_ATOMIC_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+
+#define MAX_SKIP_GC_COUNT 16
struct inmem_pages {
struct list_head list;
@@ -211,13 +227,16 @@ struct sit_info {
block_t sit_blocks; /* # of blocks used by SIT area */
block_t written_valid_blocks; /* # of valid blocks in main area */
char *sit_bitmap; /* SIT bitmap pointer */
+#ifdef CONFIG_F2FS_CHECK_FS
+ char *sit_bitmap_mir; /* SIT bitmap mirror */
+#endif
unsigned int bitmap_size; /* SIT bitmap size */
unsigned long *tmp_map; /* bitmap for temporal use */
unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */
unsigned int dirty_sentries; /* # of dirty sentries */
unsigned int sents_per_block; /* # of SIT entries per block */
- struct mutex sentry_lock; /* to protect SIT cache */
+ struct rw_semaphore sentry_lock; /* to protect SIT cache */
struct seg_entry *sentries; /* SIT segment-level cache */
struct sec_entry *sec_entries; /* SIT section-level cache */
@@ -226,6 +245,8 @@ struct sit_info {
unsigned long long mounted_time; /* mount time */
unsigned long long min_mtime; /* min. modification time */
unsigned long long max_mtime; /* max. modification time */
+
+ unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
};
struct free_segmap_info {
@@ -302,22 +323,28 @@ static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
+ return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)];
}
static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
- unsigned int segno, int section)
+ unsigned int segno, bool use_section)
{
/*
* In order to get # of valid blocks in a section instantly from many
* segments, f2fs manages two counting structures separately.
*/
- if (section > 1)
+ if (use_section && __is_large_section(sbi))
return get_sec_entry(sbi, segno)->valid_blocks;
else
return get_seg_entry(sbi, segno)->valid_blocks;
}
+static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
+ unsigned int segno)
+{
+ return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+}
+
static inline void seg_info_from_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
@@ -325,20 +352,49 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se,
se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#ifdef CONFIG_F2FS_CHECK_FS
+ memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#endif
se->type = GET_SIT_TYPE(rs);
se->mtime = le64_to_cpu(rs->mtime);
}
-static inline void seg_info_to_raw_sit(struct seg_entry *se,
+static inline void __seg_info_to_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
se->valid_blocks;
rs->vblocks = cpu_to_le16(raw_vblocks);
memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+ rs->mtime = cpu_to_le64(se->mtime);
+}
+
+static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
+ struct page *page, unsigned int start)
+{
+ struct f2fs_sit_block *raw_sit;
+ struct seg_entry *se;
+ struct f2fs_sit_entry *rs;
+ unsigned int end = min(start + SIT_ENTRY_PER_BLOCK,
+ (unsigned long)MAIN_SEGS(sbi));
+ int i;
+
+ raw_sit = (struct f2fs_sit_block *)page_address(page);
+ memset(raw_sit, 0, PAGE_SIZE);
+ for (i = 0; i < end - start; i++) {
+ rs = &raw_sit->entries[i];
+ se = get_seg_entry(sbi, start + i);
+ __seg_info_to_raw_sit(se, rs);
+ }
+}
+
+static inline void seg_info_to_raw_sit(struct seg_entry *se,
+ struct f2fs_sit_entry *rs)
+{
+ __seg_info_to_raw_sit(se, rs);
+
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
se->ckpt_valid_blocks = se->valid_blocks;
- rs->mtime = cpu_to_le64(se->mtime);
}
static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
@@ -354,8 +410,8 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
- unsigned int start_segno = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
spin_lock(&free_i->segmap_lock);
@@ -375,7 +431,8 @@ static inline void __set_inuse(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
set_bit(segno, free_i->free_segmap);
free_i->free_segments--;
if (!test_and_set_bit(secno, free_i->free_secmap))
@@ -386,8 +443,8 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
- unsigned int start_segno = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
spin_lock(&free_i->segmap_lock);
@@ -411,7 +468,8 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
spin_lock(&free_i->segmap_lock);
if (!test_and_set_bit(segno, free_i->free_segmap)) {
free_i->free_segments--;
@@ -425,6 +483,12 @@ static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
void *dst_addr)
{
struct sit_info *sit_i = SIT_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
+ sit_i->bitmap_size))
+ f2fs_bug_on(sbi, 1);
+#endif
memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
}
@@ -468,26 +532,36 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi)
return SM_I(sbi)->ovp_segments;
}
-static inline int overprovision_sections(struct f2fs_sb_info *sbi)
-{
- return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
-}
-
static inline int reserved_sections(struct f2fs_sb_info *sbi)
{
- return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
+ return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
}
-static inline bool need_SSR(struct f2fs_sb_info *sbi)
+static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
{
- int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
- int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
+ get_pages(sbi, F2FS_DIRTY_DENTS);
+ unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+ unsigned int segno, left_blocks;
+ int i;
- if (test_opt(sbi, LFS))
+ /* check current node segment */
+ for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
+ segno = CURSEG_I(sbi, i)->segno;
+ left_blocks = sbi->blocks_per_seg -
+ get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+
+ if (node_blocks > left_blocks)
+ return false;
+ }
+
+ /* check current data segment */
+ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
+ left_blocks = sbi->blocks_per_seg -
+ get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+ if (dent_blocks > left_blocks)
return false;
-
- return free_sections(sbi) <= (node_secs + 2 * dent_secs +
- reserved_sections(sbi) + 1);
+ return true;
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
@@ -495,14 +569,26 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
-
- node_secs += get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+ int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
+ if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
+ has_curseg_enough_space(sbi))
+ return false;
return (free_sections(sbi) + freed) <=
- (node_secs + 2 * dent_secs + reserved_sections(sbi) + needed);
+ (node_secs + 2 * dent_secs + imeta_secs +
+ reserved_sections(sbi) + needed);
+}
+
+static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
+{
+ if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;
+ if (likely(!has_not_enough_free_secs(sbi, 0, 0)))
+ return 0;
+ return -ENOSPC;
}
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -532,6 +618,9 @@ static inline int utilization(struct f2fs_sb_info *sbi)
*/
#define DEF_MIN_IPU_UTIL 70
#define DEF_MIN_FSYNC_BLOCKS 8
+#define DEF_MIN_HOT_BLOCKS 16
+
+#define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */
enum {
F2FS_IPU_FORCE,
@@ -539,39 +628,9 @@ enum {
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
F2FS_IPU_FSYNC,
+ F2FS_IPU_ASYNC,
};
-static inline bool need_inplace_update(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- unsigned int policy = SM_I(sbi)->ipu_policy;
-
- /* IPU can be done only for the user data */
- if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
- return false;
-
- if (test_opt(sbi, LFS))
- return false;
-
- if (policy & (0x1 << F2FS_IPU_FORCE))
- return true;
- if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
- return true;
- if (policy & (0x1 << F2FS_IPU_UTIL) &&
- utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
- if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
- utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
-
- /* this is only set during fdatasync */
- if (policy & (0x1 << F2FS_IPU_FSYNC) &&
- is_inode_flag_set(inode, FI_NEED_IPU))
- return true;
-
- return false;
-}
-
static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
int type)
{
@@ -661,6 +720,12 @@ static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
check_seg_range(sbi, start);
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
+ f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
+ f2fs_bug_on(sbi, 1);
+#endif
+
/* calculate sit block address */
if (f2fs_test_bit(offset, sit_i->sit_bitmap))
blk_addr += sit_i->sit_blocks;
@@ -686,13 +751,28 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
unsigned int block_off = SIT_BLOCK_OFFSET(start);
f2fs_change_bit(block_off, sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
+#endif
}
-static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
+static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi,
+ bool base_time)
{
struct sit_info *sit_i = SIT_I(sbi);
- return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
- sit_i->mounted_time;
+ time64_t diff, now = ktime_get_real_seconds();
+
+ if (now >= sit_i->mounted_time)
+ return sit_i->elapsed_time + now - sit_i->mounted_time;
+
+ /* system time is set to the past */
+ if (!base_time) {
+ diff = sit_i->mounted_time - now;
+ if (sit_i->elapsed_time >= diff)
+ return sit_i->elapsed_time - diff;
+ return 0;
+ }
+ return sit_i->elapsed_time;
}
static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
@@ -716,15 +796,6 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
- (base + 1) + type;
}
-static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
- unsigned int secno)
-{
- if (get_valid_blocks(sbi, secno, sbi->segs_per_sec) >=
- sbi->fggc_threshold)
- return true;
- return false;
-}
-
static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
{
if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
@@ -732,19 +803,12 @@ static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
return false;
}
-static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
-{
- struct block_device *bdev = sbi->sb->s_bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- return SECTOR_TO_BLOCK(queue_max_sectors(q));
-}
-
/*
* It is very important to gather dirty pages and write at once, so that we can
* submit a big bio without interfering other data writes.
* By default, 512 pages for directory data,
- * 512 pages (2MB) * 3 for three types of nodes, and
- * max_bio_blocks for meta are set.
+ * 512 pages (2MB) * 8 for nodes, and
+ * 256 pages * 8 for meta are set.
*/
static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
{
@@ -756,7 +820,7 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
else if (type == NODE)
return 8 * sbi->blocks_per_seg;
else if (type == META)
- return 8 * MAX_BIO_BLOCKS(sbi);
+ return 8 * BIO_MAX_PAGES;
else
return 0;
}
@@ -773,12 +837,36 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
return 0;
nr_to_write = wbc->nr_to_write;
-
+ desired = BIO_MAX_PAGES;
if (type == NODE)
- desired = 2 * max_hw_blocks(sbi);
- else
- desired = MAX_BIO_BLOCKS(sbi);
+ desired <<= 1;
wbc->nr_to_write = desired;
return desired - nr_to_write;
}
+
+static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ bool wakeup = false;
+ int i;
+
+ if (force)
+ goto wake_up;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ if (i + 1 < dcc->discard_granularity)
+ break;
+ if (!list_empty(&dcc->pend_list[i])) {
+ wakeup = true;
+ break;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+ if (!wakeup || !is_idle(sbi, DISCARD_TIME))
+ return;
+wake_up:
+ dcc->discard_wake = 1;
+ wake_up_interruptible_all(&dcc->discard_wait_queue);
+}
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index a40bfa7..a467aca 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* f2fs shrinker support
* the basic infra was copied from fs/ubifs/shrinker.c
*
* Copyright (c) 2015 Motorola Mobility
* Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -21,14 +18,16 @@ static unsigned int shrinker_run_no;
static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
{
- return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+ long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+
+ return count > 0 ? count : 0;
}
static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
{
- if (NM_I(sbi)->fcnt > MAX_FREE_NIDS)
- return NM_I(sbi)->fcnt - MAX_FREE_NIDS;
- return 0;
+ long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS;
+
+ return count > 0 ? count : 0;
}
static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
@@ -107,11 +106,11 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink,
/* shrink clean nat cache entries */
if (freed < nr)
- freed += try_to_free_nats(sbi, nr - freed);
+ freed += f2fs_try_to_free_nats(sbi, nr - freed);
/* shrink free nids cache entries */
if (freed < nr)
- freed += try_to_free_nids(sbi, nr - freed);
+ freed += f2fs_try_to_free_nids(sbi, nr - freed);
spin_lock(&f2fs_list_lock);
p = p->next;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e0ac676..dbf5043 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/super.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/init.h>
@@ -22,8 +19,10 @@
#include <linux/random.h>
#include <linux/exportfs.h>
#include <linux/blkdev.h>
+#include <linux/quotaops.h>
#include <linux/f2fs_fs.h>
#include <linux/sysfs.h>
+#include <linux/quota.h>
#include "f2fs.h"
#include "node.h"
@@ -35,36 +34,43 @@
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>
-static struct proc_dir_entry *f2fs_proc_root;
static struct kmem_cache *f2fs_inode_cachep;
-static struct kset *f2fs_kset;
#ifdef CONFIG_F2FS_FAULT_INJECTION
-char *fault_name[FAULT_MAX] = {
+const char *f2fs_fault_name[FAULT_MAX] = {
[FAULT_KMALLOC] = "kmalloc",
+ [FAULT_KVMALLOC] = "kvmalloc",
[FAULT_PAGE_ALLOC] = "page alloc",
+ [FAULT_PAGE_GET] = "page get",
+ [FAULT_ALLOC_BIO] = "alloc bio",
[FAULT_ALLOC_NID] = "alloc nid",
[FAULT_ORPHAN] = "orphan",
[FAULT_BLOCK] = "no more block",
[FAULT_DIR_DEPTH] = "too big dir depth",
[FAULT_EVICT_INODE] = "evict_inode fail",
- [FAULT_IO] = "IO error",
+ [FAULT_TRUNCATE] = "truncate fail",
+ [FAULT_READ_IO] = "read IO error",
[FAULT_CHECKPOINT] = "checkpoint error",
+ [FAULT_DISCARD] = "discard error",
+ [FAULT_WRITE_IO] = "write IO error",
};
-static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
- unsigned int rate)
+void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
+ unsigned int type)
{
- struct f2fs_fault_info *ffi = &sbi->fault_info;
+ struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
if (rate) {
atomic_set(&ffi->inject_ops, 0);
ffi->inject_rate = rate;
- ffi->inject_type = (1 << FAULT_MAX) - 1;
- } else {
- memset(ffi, 0, sizeof(struct f2fs_fault_info));
}
+
+ if (type)
+ ffi->inject_type = type;
+
+ if (!rate && !type)
+ memset(ffi, 0, sizeof(struct f2fs_fault_info));
}
#endif
@@ -82,6 +88,7 @@ enum {
Opt_discard,
Opt_nodiscard,
Opt_noheap,
+ Opt_heap,
Opt_user_xattr,
Opt_nouser_xattr,
Opt_acl,
@@ -89,6 +96,8 @@ enum {
Opt_active_logs,
Opt_disable_ext_identify,
Opt_inline_xattr,
+ Opt_noinline_xattr,
+ Opt_inline_xattr_size,
Opt_inline_data,
Opt_inline_dentry,
Opt_noinline_dentry,
@@ -100,10 +109,34 @@ enum {
Opt_noextent_cache,
Opt_noinline_data,
Opt_data_flush,
+ Opt_reserve_root,
+ Opt_resgid,
+ Opt_resuid,
Opt_mode,
+ Opt_io_size_bits,
Opt_fault_injection,
+ Opt_fault_type,
Opt_lazytime,
Opt_nolazytime,
+ Opt_quota,
+ Opt_noquota,
+ Opt_usrquota,
+ Opt_grpquota,
+ Opt_prjquota,
+ Opt_usrjquota,
+ Opt_grpjquota,
+ Opt_prjjquota,
+ Opt_offusrjquota,
+ Opt_offgrpjquota,
+ Opt_offprjjquota,
+ Opt_jqfmt_vfsold,
+ Opt_jqfmt_vfsv0,
+ Opt_jqfmt_vfsv1,
+ Opt_whint,
+ Opt_alloc,
+ Opt_fsync,
+ Opt_test_dummy_encryption,
+ Opt_checkpoint,
Opt_err,
};
@@ -114,6 +147,7 @@ static match_table_t f2fs_tokens = {
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_noheap, "no_heap"},
+ {Opt_heap, "heap"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
@@ -121,6 +155,8 @@ static match_table_t f2fs_tokens = {
{Opt_active_logs, "active_logs=%u"},
{Opt_disable_ext_identify, "disable_ext_identify"},
{Opt_inline_xattr, "inline_xattr"},
+ {Opt_noinline_xattr, "noinline_xattr"},
+ {Opt_inline_xattr_size, "inline_xattr_size=%u"},
{Opt_inline_data, "inline_data"},
{Opt_inline_dentry, "inline_dentry"},
{Opt_noinline_dentry, "noinline_dentry"},
@@ -132,211 +168,37 @@ static match_table_t f2fs_tokens = {
{Opt_noextent_cache, "noextent_cache"},
{Opt_noinline_data, "noinline_data"},
{Opt_data_flush, "data_flush"},
+ {Opt_reserve_root, "reserve_root=%u"},
+ {Opt_resgid, "resgid=%u"},
+ {Opt_resuid, "resuid=%u"},
{Opt_mode, "mode=%s"},
+ {Opt_io_size_bits, "io_bits=%u"},
{Opt_fault_injection, "fault_injection=%u"},
+ {Opt_fault_type, "fault_type=%u"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
+ {Opt_quota, "quota"},
+ {Opt_noquota, "noquota"},
+ {Opt_usrquota, "usrquota"},
+ {Opt_grpquota, "grpquota"},
+ {Opt_prjquota, "prjquota"},
+ {Opt_usrjquota, "usrjquota=%s"},
+ {Opt_grpjquota, "grpjquota=%s"},
+ {Opt_prjjquota, "prjjquota=%s"},
+ {Opt_offusrjquota, "usrjquota="},
+ {Opt_offgrpjquota, "grpjquota="},
+ {Opt_offprjjquota, "prjjquota="},
+ {Opt_jqfmt_vfsold, "jqfmt=vfsold"},
+ {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+ {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
+ {Opt_whint, "whint_mode=%s"},
+ {Opt_alloc, "alloc_mode=%s"},
+ {Opt_fsync, "fsync_mode=%s"},
+ {Opt_test_dummy_encryption, "test_dummy_encryption"},
+ {Opt_checkpoint, "checkpoint=%s"},
{Opt_err, NULL},
};
-/* Sysfs support for f2fs */
-enum {
- GC_THREAD, /* struct f2fs_gc_thread */
- SM_INFO, /* struct f2fs_sm_info */
- NM_INFO, /* struct f2fs_nm_info */
- F2FS_SBI, /* struct f2fs_sb_info */
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- FAULT_INFO_RATE, /* struct f2fs_fault_info */
- FAULT_INFO_TYPE, /* struct f2fs_fault_info */
-#endif
-};
-
-struct f2fs_attr {
- struct attribute attr;
- ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
- ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
- const char *, size_t);
- int struct_type;
- int offset;
-};
-
-static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
-{
- if (struct_type == GC_THREAD)
- return (unsigned char *)sbi->gc_thread;
- else if (struct_type == SM_INFO)
- return (unsigned char *)SM_I(sbi);
- else if (struct_type == NM_INFO)
- return (unsigned char *)NM_I(sbi);
- else if (struct_type == F2FS_SBI)
- return (unsigned char *)sbi;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- else if (struct_type == FAULT_INFO_RATE ||
- struct_type == FAULT_INFO_TYPE)
- return (unsigned char *)&sbi->fault_info;
-#endif
- return NULL;
-}
-
-static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
- struct f2fs_sb_info *sbi, char *buf)
-{
- struct super_block *sb = sbi->sb;
-
- if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
-
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long)(sbi->kbytes_written +
- BD_PART_WRITTEN(sbi)));
-}
-
-static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
- struct f2fs_sb_info *sbi, char *buf)
-{
- unsigned char *ptr = NULL;
- unsigned int *ui;
-
- ptr = __struct_ptr(sbi, a->struct_type);
- if (!ptr)
- return -EINVAL;
-
- ui = (unsigned int *)(ptr + a->offset);
-
- return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
-}
-
-static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
- struct f2fs_sb_info *sbi,
- const char *buf, size_t count)
-{
- unsigned char *ptr;
- unsigned long t;
- unsigned int *ui;
- ssize_t ret;
-
- ptr = __struct_ptr(sbi, a->struct_type);
- if (!ptr)
- return -EINVAL;
-
- ui = (unsigned int *)(ptr + a->offset);
-
- ret = kstrtoul(skip_spaces(buf), 0, &t);
- if (ret < 0)
- return ret;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
- return -EINVAL;
-#endif
- *ui = t;
- return count;
-}
-
-static ssize_t f2fs_attr_show(struct kobject *kobj,
- struct attribute *attr, char *buf)
-{
- struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
- s_kobj);
- struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
- return a->show ? a->show(a, sbi, buf) : 0;
-}
-
-static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
- const char *buf, size_t len)
-{
- struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
- s_kobj);
- struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
- return a->store ? a->store(a, sbi, buf, len) : 0;
-}
-
-static void f2fs_sb_release(struct kobject *kobj)
-{
- struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
- s_kobj);
- complete(&sbi->s_kobj_unregister);
-}
-
-#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
-static struct f2fs_attr f2fs_attr_##_name = { \
- .attr = {.name = __stringify(_name), .mode = _mode }, \
- .show = _show, \
- .store = _store, \
- .struct_type = _struct_type, \
- .offset = _offset \
-}
-
-#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \
- F2FS_ATTR_OFFSET(struct_type, name, 0644, \
- f2fs_sbi_show, f2fs_sbi_store, \
- offsetof(struct struct_name, elname))
-
-#define F2FS_GENERAL_RO_ATTR(name) \
-static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
-
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
-F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
-#endif
-F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
-
-#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
-static struct attribute *f2fs_attrs[] = {
- ATTR_LIST(gc_min_sleep_time),
- ATTR_LIST(gc_max_sleep_time),
- ATTR_LIST(gc_no_gc_sleep_time),
- ATTR_LIST(gc_idle),
- ATTR_LIST(reclaim_segments),
- ATTR_LIST(max_small_discards),
- ATTR_LIST(batched_trim_sections),
- ATTR_LIST(ipu_policy),
- ATTR_LIST(min_ipu_util),
- ATTR_LIST(min_fsync_blocks),
- ATTR_LIST(max_victim_search),
- ATTR_LIST(dir_level),
- ATTR_LIST(ram_thresh),
- ATTR_LIST(ra_nid_pages),
- ATTR_LIST(dirty_nats_ratio),
- ATTR_LIST(cp_interval),
- ATTR_LIST(idle_interval),
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- ATTR_LIST(inject_rate),
- ATTR_LIST(inject_type),
-#endif
- ATTR_LIST(lifetime_write_kbytes),
- NULL,
-};
-
-static const struct sysfs_ops f2fs_attr_ops = {
- .show = f2fs_attr_show,
- .store = f2fs_attr_store,
-};
-
-static struct kobj_type f2fs_ktype = {
- .default_attrs = f2fs_attrs,
- .sysfs_ops = &f2fs_attr_ops,
- .release = f2fs_sb_release,
-};
-
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
struct va_format vaf;
@@ -349,6 +211,31 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
va_end(args);
}
+static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
+{
+ block_t limit = (sbi->user_block_count << 1) / 1000;
+
+ /* limit is 0.2% */
+ if (test_opt(sbi, RESERVE_ROOT) &&
+ F2FS_OPTION(sbi).root_reserved_blocks > limit) {
+ F2FS_OPTION(sbi).root_reserved_blocks = limit;
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Reduce reserved blocks for root = %u",
+ F2FS_OPTION(sbi).root_reserved_blocks);
+ }
+ if (!test_opt(sbi, RESERVE_ROOT) &&
+ (!uid_eq(F2FS_OPTION(sbi).s_resuid,
+ make_kuid(&init_user_ns, F2FS_DEF_RESUID)) ||
+ !gid_eq(F2FS_OPTION(sbi).s_resgid,
+ make_kgid(&init_user_ns, F2FS_DEF_RESGID))))
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root",
+ from_kuid_munged(&init_user_ns,
+ F2FS_OPTION(sbi).s_resuid),
+ from_kgid_munged(&init_user_ns,
+ F2FS_OPTION(sbi).s_resgid));
+}
+
static void init_once(void *foo)
{
struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -356,13 +243,131 @@ static void init_once(void *foo)
inode_init_once(&fi->vfs_inode);
}
+#ifdef CONFIG_QUOTA
+static const char * const quotatypes[] = INITQFNAMES;
+#define QTYPE2NAME(t) (quotatypes[t])
+static int f2fs_set_qf_name(struct super_block *sb, int qtype,
+ substring_t *args)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ char *qname;
+ int ret = -EINVAL;
+
+ if (sb_any_quota_loaded(sb) && !F2FS_OPTION(sbi).s_qf_names[qtype]) {
+ f2fs_msg(sb, KERN_ERR,
+ "Cannot change journaled "
+ "quota options when quota turned on");
+ return -EINVAL;
+ }
+ if (f2fs_sb_has_quota_ino(sbi)) {
+ f2fs_msg(sb, KERN_INFO,
+ "QUOTA feature is enabled, so ignore qf_name");
+ return 0;
+ }
+
+ qname = match_strdup(args);
+ if (!qname) {
+ f2fs_msg(sb, KERN_ERR,
+ "Not enough memory for storing quotafile name");
+ return -ENOMEM;
+ }
+ if (F2FS_OPTION(sbi).s_qf_names[qtype]) {
+ if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0)
+ ret = 0;
+ else
+ f2fs_msg(sb, KERN_ERR,
+ "%s quota file already specified",
+ QTYPE2NAME(qtype));
+ goto errout;
+ }
+ if (strchr(qname, '/')) {
+ f2fs_msg(sb, KERN_ERR,
+ "quotafile must be on filesystem root");
+ goto errout;
+ }
+ F2FS_OPTION(sbi).s_qf_names[qtype] = qname;
+ set_opt(sbi, QUOTA);
+ return 0;
+errout:
+ kvfree(qname);
+ return ret;
+}
+
+static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) {
+ f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+ " when quota turned on");
+ return -EINVAL;
+ }
+ kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
+ F2FS_OPTION(sbi).s_qf_names[qtype] = NULL;
+ return 0;
+}
+
+static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
+{
+ /*
+ * We do the test below only for project quotas. 'usrquota' and
+ * 'grpquota' mount options are allowed even without quota feature
+ * to support legacy quotas in quota files.
+ */
+ if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. "
+ "Cannot enable project quota enforcement.");
+ return -1;
+ }
+ if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] ||
+ F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] ||
+ F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) {
+ if (test_opt(sbi, USRQUOTA) &&
+ F2FS_OPTION(sbi).s_qf_names[USRQUOTA])
+ clear_opt(sbi, USRQUOTA);
+
+ if (test_opt(sbi, GRPQUOTA) &&
+ F2FS_OPTION(sbi).s_qf_names[GRPQUOTA])
+ clear_opt(sbi, GRPQUOTA);
+
+ if (test_opt(sbi, PRJQUOTA) &&
+ F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
+ clear_opt(sbi, PRJQUOTA);
+
+ if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) ||
+ test_opt(sbi, PRJQUOTA)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "old and new quota "
+ "format mixing");
+ return -1;
+ }
+
+ if (!F2FS_OPTION(sbi).s_jquota_fmt) {
+ f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format "
+ "not specified");
+ return -1;
+ }
+ }
+
+ if (f2fs_sb_has_quota_ino(sbi) && F2FS_OPTION(sbi).s_jquota_fmt) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "QUOTA feature is enabled, so ignore jquota_fmt");
+ F2FS_OPTION(sbi).s_jquota_fmt = 0;
+ }
+ return 0;
+}
+#endif
+
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
- struct request_queue *q;
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
+ kuid_t uid;
+ kgid_t gid;
+#ifdef CONFIG_QUOTA
+ int ret;
+#endif
if (!options)
return 0;
@@ -394,10 +399,10 @@ static int parse_options(struct super_block *sb, char *options)
set_opt(sbi, BG_GC);
set_opt(sbi, FORCE_FG_GC);
} else {
- kfree(name);
+ kvfree(name);
return -EINVAL;
}
- kfree(name);
+ kvfree(name);
break;
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
@@ -409,20 +414,22 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
break;
case Opt_discard:
- q = bdev_get_queue(sb->s_bdev);
- if (blk_queue_discard(q)) {
- set_opt(sbi, DISCARD);
- } else {
- f2fs_msg(sb, KERN_WARNING,
- "mounting with \"discard\" option, but "
- "the device does not support discard");
- }
+ set_opt(sbi, DISCARD);
break;
case Opt_nodiscard:
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "discard is required for zoned block devices");
+ return -EINVAL;
+ }
clear_opt(sbi, DISCARD);
+ break;
case Opt_noheap:
set_opt(sbi, NOHEAP);
break;
+ case Opt_heap:
+ clear_opt(sbi, NOHEAP);
+ break;
#ifdef CONFIG_F2FS_FS_XATTR
case Opt_user_xattr:
set_opt(sbi, XATTR_USER);
@@ -433,6 +440,15 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_inline_xattr:
set_opt(sbi, INLINE_XATTR);
break;
+ case Opt_noinline_xattr:
+ clear_opt(sbi, INLINE_XATTR);
+ break;
+ case Opt_inline_xattr_size:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ set_opt(sbi, INLINE_XATTR_SIZE);
+ F2FS_OPTION(sbi).inline_xattr_size = arg;
+ break;
#else
case Opt_user_xattr:
f2fs_msg(sb, KERN_INFO,
@@ -446,6 +462,10 @@ static int parse_options(struct super_block *sb, char *options)
f2fs_msg(sb, KERN_INFO,
"inline_xattr options not supported");
break;
+ case Opt_noinline_xattr:
+ f2fs_msg(sb, KERN_INFO,
+ "noinline_xattr options not supported");
+ break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
case Opt_acl:
@@ -467,7 +487,7 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
return -EINVAL;
- sbi->active_logs = arg;
+ F2FS_OPTION(sbi).active_logs = arg;
break;
case Opt_disable_ext_identify:
set_opt(sbi, DISABLE_EXT_IDENTIFY);
@@ -505,6 +525,40 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_data_flush:
set_opt(sbi, DATA_FLUSH);
break;
+ case Opt_reserve_root:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (test_opt(sbi, RESERVE_ROOT)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Preserve previous reserve_root=%u",
+ F2FS_OPTION(sbi).root_reserved_blocks);
+ } else {
+ F2FS_OPTION(sbi).root_reserved_blocks = arg;
+ set_opt(sbi, RESERVE_ROOT);
+ }
+ break;
+ case Opt_resuid:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ uid = make_kuid(current_user_ns(), arg);
+ if (!uid_valid(uid)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Invalid uid value %d", arg);
+ return -EINVAL;
+ }
+ F2FS_OPTION(sbi).s_resuid = uid;
+ break;
+ case Opt_resgid:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ gid = make_kgid(current_user_ns(), arg);
+ if (!gid_valid(gid)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Invalid gid value %d", arg);
+ return -EINVAL;
+ }
+ F2FS_OPTION(sbi).s_resgid = gid;
+ break;
case Opt_mode:
name = match_strdup(&args[0]);
@@ -512,32 +566,228 @@ static int parse_options(struct super_block *sb, char *options)
return -ENOMEM;
if (strlen(name) == 8 &&
!strncmp(name, "adaptive", 8)) {
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "adaptive mode is not allowed with "
+ "zoned block device feature");
+ kvfree(name);
+ return -EINVAL;
+ }
set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
} else if (strlen(name) == 3 &&
!strncmp(name, "lfs", 3)) {
set_opt_mode(sbi, F2FS_MOUNT_LFS);
} else {
- kfree(name);
+ kvfree(name);
return -EINVAL;
}
- kfree(name);
+ kvfree(name);
break;
+ case Opt_io_size_bits:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "Not support %d, larger than %d",
+ 1 << arg, BIO_MAX_PAGES);
+ return -EINVAL;
+ }
+ F2FS_OPTION(sbi).write_io_size_bits = arg;
+ break;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
case Opt_fault_injection:
if (args->from && match_int(args, &arg))
return -EINVAL;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- f2fs_build_fault_attr(sbi, arg);
-#else
- f2fs_msg(sb, KERN_INFO,
- "FAULT_INJECTION was not selected");
-#endif
+ f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE);
+ set_opt(sbi, FAULT_INJECTION);
break;
+
+ case Opt_fault_type:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ f2fs_build_fault_attr(sbi, 0, arg);
+ set_opt(sbi, FAULT_INJECTION);
+ break;
+#else
+ case Opt_fault_injection:
+ f2fs_msg(sb, KERN_INFO,
+ "fault_injection options not supported");
+ break;
+
+ case Opt_fault_type:
+ f2fs_msg(sb, KERN_INFO,
+ "fault_type options not supported");
+ break;
+#endif
case Opt_lazytime:
sb->s_flags |= MS_LAZYTIME;
break;
case Opt_nolazytime:
sb->s_flags &= ~MS_LAZYTIME;
break;
+#ifdef CONFIG_QUOTA
+ case Opt_quota:
+ case Opt_usrquota:
+ set_opt(sbi, USRQUOTA);
+ break;
+ case Opt_grpquota:
+ set_opt(sbi, GRPQUOTA);
+ break;
+ case Opt_prjquota:
+ set_opt(sbi, PRJQUOTA);
+ break;
+ case Opt_usrjquota:
+ ret = f2fs_set_qf_name(sb, USRQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_grpjquota:
+ ret = f2fs_set_qf_name(sb, GRPQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_prjjquota:
+ ret = f2fs_set_qf_name(sb, PRJQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offusrjquota:
+ ret = f2fs_clear_qf_name(sb, USRQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offgrpjquota:
+ ret = f2fs_clear_qf_name(sb, GRPQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offprjjquota:
+ ret = f2fs_clear_qf_name(sb, PRJQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_jqfmt_vfsold:
+ F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_OLD;
+ break;
+ case Opt_jqfmt_vfsv0:
+ F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V0;
+ break;
+ case Opt_jqfmt_vfsv1:
+ F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V1;
+ break;
+ case Opt_noquota:
+ clear_opt(sbi, QUOTA);
+ clear_opt(sbi, USRQUOTA);
+ clear_opt(sbi, GRPQUOTA);
+ clear_opt(sbi, PRJQUOTA);
+ break;
+#else
+ case Opt_quota:
+ case Opt_usrquota:
+ case Opt_grpquota:
+ case Opt_prjquota:
+ case Opt_usrjquota:
+ case Opt_grpjquota:
+ case Opt_prjjquota:
+ case Opt_offusrjquota:
+ case Opt_offgrpjquota:
+ case Opt_offprjjquota:
+ case Opt_jqfmt_vfsold:
+ case Opt_jqfmt_vfsv0:
+ case Opt_jqfmt_vfsv1:
+ case Opt_noquota:
+ f2fs_msg(sb, KERN_INFO,
+ "quota operations not supported");
+ break;
+#endif
+ case Opt_whint:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+ if (strlen(name) == 10 &&
+ !strncmp(name, "user-based", 10)) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER;
+ } else if (strlen(name) == 3 &&
+ !strncmp(name, "off", 3)) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
+ } else if (strlen(name) == 8 &&
+ !strncmp(name, "fs-based", 8)) {
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
+ } else {
+ kvfree(name);
+ return -EINVAL;
+ }
+ kvfree(name);
+ break;
+ case Opt_alloc:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+
+ if (strlen(name) == 7 &&
+ !strncmp(name, "default", 7)) {
+ F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
+ } else if (strlen(name) == 5 &&
+ !strncmp(name, "reuse", 5)) {
+ F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
+ } else {
+ kvfree(name);
+ return -EINVAL;
+ }
+ kvfree(name);
+ break;
+ case Opt_fsync:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+ if (strlen(name) == 5 &&
+ !strncmp(name, "posix", 5)) {
+ F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
+ } else if (strlen(name) == 6 &&
+ !strncmp(name, "strict", 6)) {
+ F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT;
+ } else if (strlen(name) == 9 &&
+ !strncmp(name, "nobarrier", 9)) {
+ F2FS_OPTION(sbi).fsync_mode =
+ FSYNC_MODE_NOBARRIER;
+ } else {
+ kvfree(name);
+ return -EINVAL;
+ }
+ kvfree(name);
+ break;
+ case Opt_test_dummy_encryption:
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (!f2fs_sb_has_encrypt(sbi)) {
+ f2fs_msg(sb, KERN_ERR, "Encrypt feature is off");
+ return -EINVAL;
+ }
+
+ F2FS_OPTION(sbi).test_dummy_encryption = true;
+ f2fs_msg(sb, KERN_INFO,
+ "Test dummy encryption mode enabled");
+#else
+ f2fs_msg(sb, KERN_INFO,
+ "Test dummy encryption mount option ignored");
+#endif
+ break;
+ case Opt_checkpoint:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+
+ if (strlen(name) == 6 &&
+ !strncmp(name, "enable", 6)) {
+ clear_opt(sbi, DISABLE_CHECKPOINT);
+ } else if (strlen(name) == 7 &&
+ !strncmp(name, "disable", 7)) {
+ set_opt(sbi, DISABLE_CHECKPOINT);
+ } else {
+ kvfree(name);
+ return -EINVAL;
+ }
+ kvfree(name);
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -545,6 +795,71 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
}
}
+#ifdef CONFIG_QUOTA
+ if (f2fs_check_quota_options(sbi))
+ return -EINVAL;
+#else
+ if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sbi->sb)) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Filesystem with quota feature cannot be mounted RDWR "
+ "without CONFIG_QUOTA");
+ return -EINVAL;
+ }
+ if (f2fs_sb_has_project_quota(sbi) && !f2fs_readonly(sbi->sb)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Filesystem with project quota feature cannot be "
+ "mounted RDWR without CONFIG_QUOTA");
+ return -EINVAL;
+ }
+#endif
+
+ if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Should set mode=lfs with %uKB-sized IO",
+ F2FS_IO_SIZE_KB(sbi));
+ return -EINVAL;
+ }
+
+ if (test_opt(sbi, INLINE_XATTR_SIZE)) {
+ int min_size, max_size;
+
+ if (!f2fs_sb_has_extra_attr(sbi) ||
+ !f2fs_sb_has_flexible_inline_xattr(sbi)) {
+ f2fs_msg(sb, KERN_ERR,
+ "extra_attr or flexible_inline_xattr "
+ "feature is off");
+ return -EINVAL;
+ }
+ if (!test_opt(sbi, INLINE_XATTR)) {
+ f2fs_msg(sb, KERN_ERR,
+ "inline_xattr_size option should be "
+ "set with inline_xattr option");
+ return -EINVAL;
+ }
+
+ min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32);
+ max_size = MAX_INLINE_XATTR_SIZE;
+
+ if (F2FS_OPTION(sbi).inline_xattr_size < min_size ||
+ F2FS_OPTION(sbi).inline_xattr_size > max_size) {
+ f2fs_msg(sb, KERN_ERR,
+ "inline xattr size is out of range: %d ~ %d",
+ min_size, max_size);
+ return -EINVAL;
+ }
+ }
+
+ if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) {
+ f2fs_msg(sb, KERN_ERR,
+ "LFS not compatible with checkpoint=disable\n");
+ return -EINVAL;
+ }
+
+ /* Not pass down write hints if the number of active logs is lesser
+ * than NR_CURSEG_TYPE.
+ */
+ if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE)
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
return 0;
}
@@ -559,25 +874,27 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
init_once((void *) fi);
/* Initialize f2fs-specific inode info */
- fi->vfs_inode.i_version = 1;
atomic_set(&fi->dirty_pages, 0);
- fi->i_current_depth = 1;
- fi->i_advise = 0;
init_rwsem(&fi->i_sem);
INIT_LIST_HEAD(&fi->dirty_list);
INIT_LIST_HEAD(&fi->gdirty_list);
+ INIT_LIST_HEAD(&fi->inmem_ilist);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
- init_rwsem(&fi->dio_rwsem[READ]);
- init_rwsem(&fi->dio_rwsem[WRITE]);
+ init_rwsem(&fi->i_gc_rwsem[READ]);
+ init_rwsem(&fi->i_gc_rwsem[WRITE]);
+ init_rwsem(&fi->i_mmap_sem);
+ init_rwsem(&fi->i_xattr_sem);
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
+
return &fi->vfs_inode;
}
static int f2fs_drop_inode(struct inode *inode)
{
+ int ret;
/*
* This is to avoid a deadlock condition like below.
* writeback_single_inode(inode)
@@ -593,7 +910,7 @@ static int f2fs_drop_inode(struct inode *inode)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- drop_inmem_pages(inode);
+ f2fs_drop_inmem_pages(inode);
/* should remain fi->extent_tree for writepage */
f2fs_destroy_extent_node(inode);
@@ -601,39 +918,45 @@ static int f2fs_drop_inode(struct inode *inode)
sb_start_intwrite(inode->i_sb);
f2fs_i_size_write(inode, 0);
+ f2fs_submit_merged_write_cond(F2FS_I_SB(inode),
+ inode, NULL, 0, DATA);
+ truncate_inode_pages_final(inode->i_mapping);
+
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode);
sb_end_intwrite(inode->i_sb);
- fscrypt_put_encryption_info(inode, NULL);
spin_lock(&inode->i_lock);
atomic_dec(&inode->i_count);
}
+ trace_f2fs_drop_inode(inode, 0);
return 0;
}
-
- return generic_drop_inode(inode);
+ ret = generic_drop_inode(inode);
+ trace_f2fs_drop_inode(inode, ret);
+ return ret;
}
-int f2fs_inode_dirtied(struct inode *inode)
+int f2fs_inode_dirtied(struct inode *inode, bool sync)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret = 0;
spin_lock(&sbi->inode_lock[DIRTY_META]);
if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
- spin_unlock(&sbi->inode_lock[DIRTY_META]);
- return 1;
+ ret = 1;
+ } else {
+ set_inode_flag(inode, FI_DIRTY_INODE);
+ stat_inc_dirty_inode(sbi, DIRTY_META);
}
-
- set_inode_flag(inode, FI_DIRTY_INODE);
- list_add_tail(&F2FS_I(inode)->gdirty_list,
+ if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) {
+ list_add_tail(&F2FS_I(inode)->gdirty_list,
&sbi->inode_list[DIRTY_META]);
- inc_page_count(sbi, F2FS_DIRTY_IMETA);
- stat_inc_dirty_inode(sbi, DIRTY_META);
+ inc_page_count(sbi, F2FS_DIRTY_IMETA);
+ }
spin_unlock(&sbi->inode_lock[DIRTY_META]);
-
- return 0;
+ return ret;
}
void f2fs_inode_synced(struct inode *inode)
@@ -645,10 +968,12 @@ void f2fs_inode_synced(struct inode *inode)
spin_unlock(&sbi->inode_lock[DIRTY_META]);
return;
}
- list_del_init(&F2FS_I(inode)->gdirty_list);
+ if (!list_empty(&F2FS_I(inode)->gdirty_list)) {
+ list_del_init(&F2FS_I(inode)->gdirty_list);
+ dec_page_count(sbi, F2FS_DIRTY_IMETA);
+ }
clear_inode_flag(inode, FI_DIRTY_INODE);
clear_inode_flag(inode, FI_AUTO_RECOVER);
- dec_page_count(sbi, F2FS_DIRTY_IMETA);
stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
spin_unlock(&sbi->inode_lock[DIRTY_META]);
}
@@ -672,7 +997,7 @@ static void f2fs_dirty_inode(struct inode *inode, int flags)
if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
clear_inode_flag(inode, FI_AUTO_RECOVER);
- f2fs_inode_dirtied(inode);
+ f2fs_inode_dirtied(inode, false);
}
static void f2fs_i_callback(struct rcu_head *head)
@@ -692,18 +1017,26 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi)
percpu_counter_destroy(&sbi->total_valid_inode_count);
}
+static void destroy_device_list(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ blkdev_put(FDEV(i).bdev, FMODE_EXCL);
+#ifdef CONFIG_BLK_DEV_ZONED
+ kvfree(FDEV(i).blkz_type);
+#endif
+ }
+ kvfree(sbi->devs);
+}
+
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ int i;
+ bool dropped;
- if (sbi->s_proc) {
- remove_proc_entry("segment_info", sbi->s_proc);
- remove_proc_entry("segment_bits", sbi->s_proc);
- remove_proc_entry(sb->s_id, f2fs_proc_root);
- }
- kobject_del(&sbi->s_kobj);
-
- stop_gc_thread(sbi);
+ f2fs_quota_off_umount(sb);
/* prevent remaining shrinker jobs */
mutex_lock(&sbi->umount_mutex);
@@ -713,48 +1046,76 @@ static void f2fs_put_super(struct super_block *sb)
* But, the previous checkpoint was not done by umount, it needs to do
* clean checkpoint again.
*/
- if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
- !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+ if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+ !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) {
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
- write_checkpoint(sbi, &cpc);
+ f2fs_write_checkpoint(sbi, &cpc);
}
- /* write_checkpoint can update stat informaion */
- f2fs_destroy_stats(sbi);
+ /* be sure to wait for any on-going discard commands */
+ dropped = f2fs_issue_discard_timeout(sbi);
+
+ if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) &&
+ !sbi->discard_blks && !dropped) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT | CP_TRIMMED,
+ };
+ f2fs_write_checkpoint(sbi, &cpc);
+ }
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
- release_ino_entry(sbi, true);
- release_discard_addrs(sbi);
+ f2fs_release_ino_entry(sbi, true);
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
/* our cp_error case, we can wait for any writeback page */
- f2fs_flush_merged_bios(sbi);
+ f2fs_flush_merged_writes(sbi);
+
+ f2fs_wait_on_all_pages_writeback(sbi);
+
+ f2fs_bug_on(sbi, sbi->fsync_node_num);
iput(sbi->node_inode);
+ sbi->node_inode = NULL;
+
iput(sbi->meta_inode);
+ sbi->meta_inode = NULL;
+
+ /*
+ * iput() can update stat information, if f2fs_write_checkpoint()
+ * above failed with error.
+ */
+ f2fs_destroy_stats(sbi);
/* destroy f2fs internal modules */
- destroy_node_manager(sbi);
- destroy_segment_manager(sbi);
+ f2fs_destroy_node_manager(sbi);
+ f2fs_destroy_segment_manager(sbi);
- kfree(sbi->ckpt);
- kobject_put(&sbi->s_kobj);
- wait_for_completion(&sbi->s_kobj_unregister);
+ kvfree(sbi->ckpt);
+
+ f2fs_unregister_sysfs(sbi);
sb->s_fs_info = NULL;
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kfree(sbi->raw_super);
+ kvfree(sbi->raw_super);
+ destroy_device_list(sbi);
+ mempool_destroy(sbi->write_io_dummy);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+#endif
destroy_percpu_info(sbi);
- kfree(sbi);
+ for (i = 0; i < NR_PAGE_TYPE; i++)
+ kvfree(sbi->write_io[i]);
+ kvfree(sbi);
}
int f2fs_sync_fs(struct super_block *sb, int sync)
@@ -762,15 +1123,23 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
struct f2fs_sb_info *sbi = F2FS_SB(sb);
int err = 0;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return 0;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;
+
trace_f2fs_sync_fs(sb, sync);
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ return -EAGAIN;
+
if (sync) {
struct cp_control cpc;
cpc.reason = __get_cp_reason(sbi);
mutex_lock(&sbi->gc_mutex);
- err = write_checkpoint(sbi, &cpc);
+ err = f2fs_write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
}
f2fs_trace_ios(NULL, 1);
@@ -780,13 +1149,17 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
static int f2fs_freeze(struct super_block *sb)
{
- int err;
-
if (f2fs_readonly(sb))
return 0;
- err = f2fs_sync_fs(sb, 1);
- return err;
+ /* IO error happened before */
+ if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+ return -EIO;
+
+ /* must be clean, since sync_filesystem() was already called */
+ if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+ return -EINVAL;
+ return 0;
}
static int f2fs_unfreeze(struct super_block *sb)
@@ -794,34 +1167,138 @@ static int f2fs_unfreeze(struct super_block *sb)
return 0;
}
+#ifdef CONFIG_QUOTA
+static int f2fs_statfs_project(struct super_block *sb,
+ kprojid_t projid, struct kstatfs *buf)
+{
+ struct kqid qid;
+ struct dquot *dquot;
+ u64 limit;
+ u64 curblock;
+
+ qid = make_kqid_projid(projid);
+ dquot = dqget(sb, qid);
+ if (IS_ERR(dquot))
+ return PTR_ERR(dquot);
+ spin_lock(&dq_data_lock);
+
+ limit = (dquot->dq_dqb.dqb_bsoftlimit ?
+ dquot->dq_dqb.dqb_bsoftlimit :
+ dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+ if (limit && buf->f_blocks > limit) {
+ curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+ buf->f_blocks = limit;
+ buf->f_bfree = buf->f_bavail =
+ (buf->f_blocks > curblock) ?
+ (buf->f_blocks - curblock) : 0;
+ }
+
+ limit = dquot->dq_dqb.dqb_isoftlimit ?
+ dquot->dq_dqb.dqb_isoftlimit :
+ dquot->dq_dqb.dqb_ihardlimit;
+ if (limit && buf->f_files > limit) {
+ buf->f_files = limit;
+ buf->f_ffree =
+ (buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
+ (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+ }
+
+ spin_unlock(&dq_data_lock);
+ dqput(dquot);
+ return 0;
+}
+#endif
+
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
- block_t total_count, user_block_count, start_count, ovp_count;
+ block_t total_count, user_block_count, start_count;
+ u64 avail_node_count;
total_count = le64_to_cpu(sbi->raw_super->block_count);
user_block_count = sbi->user_block_count;
start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
- ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
buf->f_type = F2FS_SUPER_MAGIC;
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
- buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
- buf->f_bavail = user_block_count - valid_user_blocks(sbi);
+ buf->f_bfree = user_block_count - valid_user_blocks(sbi) -
+ sbi->current_reserved_blocks;
+ if (unlikely(buf->f_bfree <= sbi->unusable_block_count))
+ buf->f_bfree = 0;
+ else
+ buf->f_bfree -= sbi->unusable_block_count;
- buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
- buf->f_ffree = buf->f_files - valid_inode_count(sbi);
+ if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks)
+ buf->f_bavail = buf->f_bfree -
+ F2FS_OPTION(sbi).root_reserved_blocks;
+ else
+ buf->f_bavail = 0;
+
+ avail_node_count = sbi->total_node_count - sbi->nquota_files -
+ F2FS_RESERVED_NODE_NUM;
+
+ if (avail_node_count > user_block_count) {
+ buf->f_files = user_block_count;
+ buf->f_ffree = buf->f_bavail;
+ } else {
+ buf->f_files = avail_node_count;
+ buf->f_ffree = min(avail_node_count - valid_node_count(sbi),
+ buf->f_bavail);
+ }
buf->f_namelen = F2FS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
+#ifdef CONFIG_QUOTA
+ if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
+ sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
+ f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf);
+ }
+#endif
return 0;
}
+static inline void f2fs_show_quota_options(struct seq_file *seq,
+ struct super_block *sb)
+{
+#ifdef CONFIG_QUOTA
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ if (F2FS_OPTION(sbi).s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (F2FS_OPTION(sbi).s_jquota_fmt) {
+ case QFMT_VFS_OLD:
+ fmtname = "vfsold";
+ break;
+ case QFMT_VFS_V0:
+ fmtname = "vfsv0";
+ break;
+ case QFMT_VFS_V1:
+ fmtname = "vfsv1";
+ break;
+ }
+ seq_printf(seq, ",jqfmt=%s", fmtname);
+ }
+
+ if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA])
+ seq_show_option(seq, "usrjquota",
+ F2FS_OPTION(sbi).s_qf_names[USRQUOTA]);
+
+ if (F2FS_OPTION(sbi).s_qf_names[GRPQUOTA])
+ seq_show_option(seq, "grpjquota",
+ F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]);
+
+ if (F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
+ seq_show_option(seq, "prjjquota",
+ F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]);
+#endif
+}
+
static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
@@ -839,7 +1316,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
if (test_opt(sbi, DISCARD))
seq_puts(seq, ",discard");
if (test_opt(sbi, NOHEAP))
- seq_puts(seq, ",no_heap_alloc");
+ seq_puts(seq, ",no_heap");
+ else
+ seq_puts(seq, ",heap");
#ifdef CONFIG_F2FS_FS_XATTR
if (test_opt(sbi, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -847,6 +1326,11 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",nouser_xattr");
if (test_opt(sbi, INLINE_XATTR))
seq_puts(seq, ",inline_xattr");
+ else
+ seq_puts(seq, ",noinline_xattr");
+ if (test_opt(sbi, INLINE_XATTR_SIZE))
+ seq_printf(seq, ",inline_xattr_size=%u",
+ F2FS_OPTION(sbi).inline_xattr_size);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
@@ -882,95 +1366,88 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, "adaptive");
else if (test_opt(sbi, LFS))
seq_puts(seq, "lfs");
- seq_printf(seq, ",active_logs=%u", sbi->active_logs);
-
- return 0;
-}
-
-static int segment_info_seq_show(struct seq_file *seq, void *offset)
-{
- struct super_block *sb = seq->private;
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
- unsigned int total_segs =
- le32_to_cpu(sbi->raw_super->segment_count_main);
- int i;
-
- seq_puts(seq, "format: segment_type|valid_blocks\n"
- "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
- for (i = 0; i < total_segs; i++) {
- struct seg_entry *se = get_seg_entry(sbi, i);
-
- if ((i % 10) == 0)
- seq_printf(seq, "%-10d", i);
- seq_printf(seq, "%d|%-3u", se->type,
- get_valid_blocks(sbi, i, 1));
- if ((i % 10) == 9 || i == (total_segs - 1))
- seq_putc(seq, '\n');
- else
- seq_putc(seq, ' ');
+ seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs);
+ if (test_opt(sbi, RESERVE_ROOT))
+ seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u",
+ F2FS_OPTION(sbi).root_reserved_blocks,
+ from_kuid_munged(&init_user_ns,
+ F2FS_OPTION(sbi).s_resuid),
+ from_kgid_munged(&init_user_ns,
+ F2FS_OPTION(sbi).s_resgid));
+ if (F2FS_IO_SIZE_BITS(sbi))
+ seq_printf(seq, ",io_bits=%u",
+ F2FS_OPTION(sbi).write_io_size_bits);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (test_opt(sbi, FAULT_INJECTION)) {
+ seq_printf(seq, ",fault_injection=%u",
+ F2FS_OPTION(sbi).fault_info.inject_rate);
+ seq_printf(seq, ",fault_type=%u",
+ F2FS_OPTION(sbi).fault_info.inject_type);
}
+#endif
+#ifdef CONFIG_QUOTA
+ if (test_opt(sbi, QUOTA))
+ seq_puts(seq, ",quota");
+ if (test_opt(sbi, USRQUOTA))
+ seq_puts(seq, ",usrquota");
+ if (test_opt(sbi, GRPQUOTA))
+ seq_puts(seq, ",grpquota");
+ if (test_opt(sbi, PRJQUOTA))
+ seq_puts(seq, ",prjquota");
+#endif
+ f2fs_show_quota_options(seq, sbi->sb);
+ if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER)
+ seq_printf(seq, ",whint_mode=%s", "user-based");
+ else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS)
+ seq_printf(seq, ",whint_mode=%s", "fs-based");
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (F2FS_OPTION(sbi).test_dummy_encryption)
+ seq_puts(seq, ",test_dummy_encryption");
+#endif
+ if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT)
+ seq_printf(seq, ",alloc_mode=%s", "default");
+ else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
+ seq_printf(seq, ",alloc_mode=%s", "reuse");
+
+ if (test_opt(sbi, DISABLE_CHECKPOINT))
+ seq_puts(seq, ",checkpoint=disable");
+
+ if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX)
+ seq_printf(seq, ",fsync_mode=%s", "posix");
+ else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
+ seq_printf(seq, ",fsync_mode=%s", "strict");
+ else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
+ seq_printf(seq, ",fsync_mode=%s", "nobarrier");
return 0;
}
-static int segment_bits_seq_show(struct seq_file *seq, void *offset)
-{
- struct super_block *sb = seq->private;
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
- unsigned int total_segs =
- le32_to_cpu(sbi->raw_super->segment_count_main);
- int i, j;
-
- seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
- "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
- for (i = 0; i < total_segs; i++) {
- struct seg_entry *se = get_seg_entry(sbi, i);
-
- seq_printf(seq, "%-10d", i);
- seq_printf(seq, "%d|%-3u|", se->type,
- get_valid_blocks(sbi, i, 1));
- for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
- seq_printf(seq, " %.2x", se->cur_valid_map[j]);
- seq_putc(seq, '\n');
- }
- return 0;
-}
-
-#define F2FS_PROC_FILE_DEF(_name) \
-static int _name##_open_fs(struct inode *inode, struct file *file) \
-{ \
- return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
-} \
- \
-static const struct file_operations f2fs_seq_##_name##_fops = { \
- .open = _name##_open_fs, \
- .read = seq_read, \
- .llseek = seq_lseek, \
- .release = single_release, \
-};
-
-F2FS_PROC_FILE_DEF(segment_info);
-F2FS_PROC_FILE_DEF(segment_bits);
-
static void default_options(struct f2fs_sb_info *sbi)
{
/* init some FS parameters */
- sbi->active_logs = NR_CURSEG_TYPE;
+ F2FS_OPTION(sbi).active_logs = NR_CURSEG_TYPE;
+ F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
+ F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
+ F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
+ F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
+ F2FS_OPTION(sbi).test_dummy_encryption = false;
+ F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
+ F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
set_opt(sbi, BG_GC);
+ set_opt(sbi, INLINE_XATTR);
set_opt(sbi, INLINE_DATA);
set_opt(sbi, INLINE_DENTRY);
set_opt(sbi, EXTENT_CACHE);
+ set_opt(sbi, NOHEAP);
sbi->sb->s_flags |= MS_LAZYTIME;
+ clear_opt(sbi, DISABLE_CHECKPOINT);
set_opt(sbi, FLUSH_MERGE);
- if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+ set_opt(sbi, DISCARD);
+ if (f2fs_sb_has_blkzoned(sbi))
set_opt_mode(sbi, F2FS_MOUNT_LFS);
- set_opt(sbi, DISCARD);
- } else {
+ else
set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
- }
#ifdef CONFIG_F2FS_FS_XATTR
set_opt(sbi, XATTR_USER);
@@ -979,21 +1456,88 @@ static void default_options(struct f2fs_sb_info *sbi)
set_opt(sbi, POSIX_ACL);
#endif
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- f2fs_build_fault_attr(sbi, 0);
+ f2fs_build_fault_attr(sbi, 0, 0);
+}
+
+#ifdef CONFIG_QUOTA
+static int f2fs_enable_quotas(struct super_block *sb);
#endif
+
+static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
+{
+ unsigned int s_flags = sbi->sb->s_flags;
+ struct cp_control cpc;
+ int err = 0;
+ int ret;
+
+ if (s_flags & MS_RDONLY) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "checkpoint=disable on readonly fs");
+ return -EINVAL;
+ }
+ sbi->sb->s_flags |= MS_ACTIVE;
+
+ f2fs_update_time(sbi, DISABLE_TIME);
+
+ while (!f2fs_time_over(sbi, DISABLE_TIME)) {
+ mutex_lock(&sbi->gc_mutex);
+ err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+ if (err == -ENODATA) {
+ err = 0;
+ break;
+ }
+ if (err && err != -EAGAIN)
+ break;
+ }
+
+ ret = sync_filesystem(sbi->sb);
+ if (ret || err) {
+ err = ret ? ret: err;
+ goto restore_flag;
+ }
+
+ if (f2fs_disable_cp_again(sbi)) {
+ err = -EAGAIN;
+ goto restore_flag;
+ }
+
+ mutex_lock(&sbi->gc_mutex);
+ cpc.reason = CP_PAUSE;
+ set_sbi_flag(sbi, SBI_CP_DISABLED);
+ f2fs_write_checkpoint(sbi, &cpc);
+
+ sbi->unusable_block_count = 0;
+ mutex_unlock(&sbi->gc_mutex);
+restore_flag:
+ sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+ return err;
+}
+
+static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
+{
+ mutex_lock(&sbi->gc_mutex);
+ f2fs_dirty_to_prefree(sbi);
+
+ clear_sbi_flag(sbi, SBI_CP_DISABLED);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ mutex_unlock(&sbi->gc_mutex);
+
+ f2fs_sync_fs(sbi->sb, 1);
}
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct f2fs_mount_info org_mount_opt;
- int err, active_logs;
+ unsigned long old_sb_flags;
+ int err;
bool need_restart_gc = false;
bool need_stop_gc = false;
bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- struct f2fs_fault_info ffi = sbi->fault_info;
+ bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
+ bool checkpoint_changed;
+#ifdef CONFIG_QUOTA
+ int i, j;
#endif
/*
@@ -1001,7 +1545,25 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
* need to restore them.
*/
org_mount_opt = sbi->mount_opt;
- active_logs = sbi->active_logs;
+ old_sb_flags = sb->s_flags;
+
+#ifdef CONFIG_QUOTA
+ org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (F2FS_OPTION(sbi).s_qf_names[i]) {
+ org_mount_opt.s_qf_names[i] =
+ kstrdup(F2FS_OPTION(sbi).s_qf_names[i],
+ GFP_KERNEL);
+ if (!org_mount_opt.s_qf_names[i]) {
+ for (j = 0; j < i; j++)
+ kvfree(org_mount_opt.s_qf_names[j]);
+ return -ENOMEM;
+ }
+ } else {
+ org_mount_opt.s_qf_names[i] = NULL;
+ }
+ }
+#endif
/* recover superblocks we couldn't write due to previous RO mount */
if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
@@ -1012,13 +1574,14 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
}
- sbi->mount_opt.opt = 0;
default_options(sbi);
/* parse mount options */
err = parse_options(sb, data);
if (err)
goto restore_opts;
+ checkpoint_changed =
+ disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT);
/*
* Previous and new state of filesystem is RO,
@@ -1027,6 +1590,23 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
+#ifdef CONFIG_QUOTA
+ if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) {
+ err = dquot_suspend(sb, -1);
+ if (err < 0)
+ goto restore_opts;
+ } else if (f2fs_readonly(sb) && !(*flags & MS_RDONLY)) {
+ /* dquot_resume needs RW */
+ sb->s_flags &= ~MS_RDONLY;
+ if (sb_any_quota_suspended(sb)) {
+ dquot_resume(sb, -1);
+ } else if (f2fs_sb_has_quota_ino(sbi)) {
+ err = f2fs_enable_quotas(sb);
+ if (err)
+ goto restore_opts;
+ }
+ }
+#endif
/* disallow enable/disable extent_cache dynamically */
if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
err = -EINVAL;
@@ -1035,6 +1615,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ if ((*flags & MS_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "disabling checkpoint not compatible with read-only");
+ goto restore_opts;
+ }
+
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
@@ -1042,17 +1629,18 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
- stop_gc_thread(sbi);
+ f2fs_stop_gc_thread(sbi);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
- err = start_gc_thread(sbi);
+ err = f2fs_start_gc_thread(sbi);
if (err)
goto restore_opts;
need_stop_gc = true;
}
- if (*flags & MS_RDONLY) {
+ if (*flags & MS_RDONLY ||
+ F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) {
writeback_inodes_sb(sb, WB_REASON_SYNC);
sync_inodes_sb(sb);
@@ -1062,47 +1650,532 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
clear_sbi_flag(sbi, SBI_IS_CLOSE);
}
+ if (checkpoint_changed) {
+ if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = f2fs_disable_checkpoint(sbi);
+ if (err)
+ goto restore_gc;
+ } else {
+ f2fs_enable_checkpoint(sbi);
+ }
+ }
+
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
- destroy_flush_cmd_control(sbi);
- } else if (!SM_I(sbi)->cmd_control_info) {
- err = create_flush_cmd_control(sbi);
+ clear_opt(sbi, FLUSH_MERGE);
+ f2fs_destroy_flush_cmd_control(sbi, false);
+ } else {
+ err = f2fs_create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
}
skip:
+#ifdef CONFIG_QUOTA
+ /* Release old quota file names */
+ for (i = 0; i < MAXQUOTAS; i++)
+ kvfree(org_mount_opt.s_qf_names[i]);
+#endif
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+ limit_reserve_root(sbi);
+ *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
return 0;
restore_gc:
if (need_restart_gc) {
- if (start_gc_thread(sbi))
+ if (f2fs_start_gc_thread(sbi))
f2fs_msg(sbi->sb, KERN_WARNING,
"background gc thread has stopped");
} else if (need_stop_gc) {
- stop_gc_thread(sbi);
+ f2fs_stop_gc_thread(sbi);
}
restore_opts:
- sbi->mount_opt = org_mount_opt;
- sbi->active_logs = active_logs;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
- sbi->fault_info = ffi;
+#ifdef CONFIG_QUOTA
+ F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i];
+ }
#endif
+ sbi->mount_opt = org_mount_opt;
+ sb->s_flags = old_sb_flags;
return err;
}
-static struct super_operations f2fs_sops = {
+#ifdef CONFIG_QUOTA
+/* Read data from quotafile */
+static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
+ size_t len, loff_t off)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ struct address_space *mapping = inode->i_mapping;
+ block_t blkidx = F2FS_BYTES_TO_BLK(off);
+ int offset = off & (sb->s_blocksize - 1);
+ int tocopy;
+ size_t toread;
+ loff_t i_size = i_size_read(inode);
+ struct page *page;
+ char *kaddr;
+
+ if (off > i_size)
+ return 0;
+
+ if (off + len > i_size)
+ len = i_size - off;
+ toread = len;
+ while (toread > 0) {
+ tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread);
+repeat:
+ page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS);
+ if (IS_ERR(page)) {
+ if (PTR_ERR(page) == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto repeat;
+ }
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ return PTR_ERR(page);
+ }
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+ if (unlikely(!PageUptodate(page))) {
+ f2fs_put_page(page, 1);
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ return -EIO;
+ }
+
+ kaddr = kmap_atomic(page);
+ memcpy(data, kaddr + offset, tocopy);
+ kunmap_atomic(kaddr);
+ f2fs_put_page(page, 1);
+
+ offset = 0;
+ toread -= tocopy;
+ data += tocopy;
+ blkidx++;
+ }
+ return len;
+}
+
+/* Write to quotafile */
+static ssize_t f2fs_quota_write(struct super_block *sb, int type,
+ const char *data, size_t len, loff_t off)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ struct address_space *mapping = inode->i_mapping;
+ const struct address_space_operations *a_ops = mapping->a_ops;
+ int offset = off & (sb->s_blocksize - 1);
+ size_t towrite = len;
+ struct page *page;
+ char *kaddr;
+ int err = 0;
+ int tocopy;
+
+ while (towrite > 0) {
+ tocopy = min_t(unsigned long, sb->s_blocksize - offset,
+ towrite);
+retry:
+ err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
+ &page, NULL);
+ if (unlikely(err)) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ break;
+ }
+
+ kaddr = kmap_atomic(page);
+ memcpy(kaddr + offset, data, tocopy);
+ kunmap_atomic(kaddr);
+ flush_dcache_page(page);
+
+ a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
+ page, NULL);
+ offset = 0;
+ towrite -= tocopy;
+ off += tocopy;
+ data += tocopy;
+ cond_resched();
+ }
+
+ if (len == towrite)
+ return err;
+ inode->i_mtime = inode->i_ctime = current_time(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+ return len - towrite;
+}
+
+static struct dquot **f2fs_get_dquots(struct inode *inode)
+{
+ return F2FS_I(inode)->i_dquot;
+}
+
+static qsize_t *f2fs_get_reserved_space(struct inode *inode)
+{
+ return &F2FS_I(inode)->i_reserved_quota;
+}
+
+static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type)
+{
+ if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "quota sysfile may be corrupted, skip loading it");
+ return 0;
+ }
+
+ return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type],
+ F2FS_OPTION(sbi).s_jquota_fmt, type);
+}
+
+int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly)
+{
+ int enabled = 0;
+ int i, err;
+
+ if (f2fs_sb_has_quota_ino(sbi) && rdonly) {
+ err = f2fs_enable_quotas(sbi->sb);
+ if (err) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Cannot turn on quota_ino: %d", err);
+ return 0;
+ }
+ return 1;
+ }
+
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (F2FS_OPTION(sbi).s_qf_names[i]) {
+ err = f2fs_quota_on_mount(sbi, i);
+ if (!err) {
+ enabled = 1;
+ continue;
+ }
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Cannot turn on quotas: %d on %d", err, i);
+ }
+ }
+ return enabled;
+}
+
+static int f2fs_quota_enable(struct super_block *sb, int type, int format_id,
+ unsigned int flags)
+{
+ struct inode *qf_inode;
+ unsigned long qf_inum;
+ int err;
+
+ BUG_ON(!f2fs_sb_has_quota_ino(F2FS_SB(sb)));
+
+ qf_inum = f2fs_qf_ino(sb, type);
+ if (!qf_inum)
+ return -EPERM;
+
+ qf_inode = f2fs_iget(sb, qf_inum);
+ if (IS_ERR(qf_inode)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Bad quota inode %u:%lu", type, qf_inum);
+ return PTR_ERR(qf_inode);
+ }
+
+ /* Don't account quota for quota files to avoid recursion */
+ qf_inode->i_flags |= S_NOQUOTA;
+ err = dquot_enable(qf_inode, type, format_id, flags);
+ iput(qf_inode);
+ return err;
+}
+
+static int f2fs_enable_quotas(struct super_block *sb)
+{
+ int type, err = 0;
+ unsigned long qf_inum;
+ bool quota_mopt[MAXQUOTAS] = {
+ test_opt(F2FS_SB(sb), USRQUOTA),
+ test_opt(F2FS_SB(sb), GRPQUOTA),
+ test_opt(F2FS_SB(sb), PRJQUOTA),
+ };
+
+ if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) {
+ f2fs_msg(sb, KERN_ERR,
+ "quota file may be corrupted, skip loading it");
+ return 0;
+ }
+
+ sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+
+ for (type = 0; type < MAXQUOTAS; type++) {
+ qf_inum = f2fs_qf_ino(sb, type);
+ if (qf_inum) {
+ err = f2fs_quota_enable(sb, type, QFMT_VFS_V1,
+ DQUOT_USAGE_ENABLED |
+ (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
+ if (err) {
+ f2fs_msg(sb, KERN_ERR,
+ "Failed to enable quota tracking "
+ "(type=%d, err=%d). Please run "
+ "fsck to fix.", type, err);
+ for (type--; type >= 0; type--)
+ dquot_quota_off(sb, type);
+ set_sbi_flag(F2FS_SB(sb),
+ SBI_QUOTA_NEED_REPAIR);
+ return err;
+ }
+ }
+ }
+ return 0;
+}
+
+int f2fs_quota_sync(struct super_block *sb, int type)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct quota_info *dqopt = sb_dqopt(sb);
+ int cnt;
+ int ret;
+
+ ret = dquot_writeback_dquots(sb, type);
+ if (ret)
+ goto out;
+
+ /*
+ * Now when everything is written we can discard the pagecache so
+ * that userspace sees the changes.
+ */
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+ struct address_space *mapping;
+
+ if (type != -1 && cnt != type)
+ continue;
+ if (!sb_has_quota_active(sb, cnt))
+ continue;
+
+ mapping = dqopt->files[cnt]->i_mapping;
+
+ ret = filemap_fdatawrite(mapping);
+ if (ret)
+ goto out;
+
+ /* if we are using journalled quota */
+ if (is_journalled_quota(sbi))
+ continue;
+
+ ret = filemap_fdatawait(mapping);
+ if (ret)
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+
+ inode_lock(dqopt->files[cnt]);
+ truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+ inode_unlock(dqopt->files[cnt]);
+ }
+out:
+ if (ret)
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ return ret;
+}
+
+static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
+ struct path *path)
+{
+ struct inode *inode;
+ int err;
+
+ err = f2fs_quota_sync(sb, type);
+ if (err)
+ return err;
+
+ err = dquot_quota_on(sb, type, format_id, path);
+ if (err)
+ return err;
+
+ inode = d_inode(path->dentry);
+
+ inode_lock(inode);
+ F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL;
+ f2fs_set_inode_flags(inode);
+ inode_unlock(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+
+ return 0;
+}
+
+static int f2fs_quota_off(struct super_block *sb, int type)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ int err;
+
+ if (!inode || !igrab(inode))
+ return dquot_quota_off(sb, type);
+
+ err = f2fs_quota_sync(sb, type);
+ if (err)
+ goto out_put;
+
+ err = dquot_quota_off(sb, type);
+ if (err || f2fs_sb_has_quota_ino(F2FS_SB(sb)))
+ goto out_put;
+
+ inode_lock(inode);
+ F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL);
+ f2fs_set_inode_flags(inode);
+ inode_unlock(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+out_put:
+ iput(inode);
+ return err;
+}
+
+void f2fs_quota_off_umount(struct super_block *sb)
+{
+ int type;
+ int err;
+
+ for (type = 0; type < MAXQUOTAS; type++) {
+ err = f2fs_quota_off(sb, type);
+ if (err) {
+ int ret = dquot_quota_off(sb, type);
+
+ f2fs_msg(sb, KERN_ERR,
+ "Fail to turn off disk quota "
+ "(type: %d, err: %d, ret:%d), Please "
+ "run fsck to fix it.", type, err, ret);
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ }
+ }
+ /*
+ * In case of checkpoint=disable, we must flush quota blocks.
+ * This can cause NULL exception for node_inode in end_io, since
+ * put_super already dropped it.
+ */
+ sync_filesystem(sb);
+}
+
+static void f2fs_truncate_quota_inode_pages(struct super_block *sb)
+{
+ struct quota_info *dqopt = sb_dqopt(sb);
+ int type;
+
+ for (type = 0; type < MAXQUOTAS; type++) {
+ if (!dqopt->files[type])
+ continue;
+ f2fs_inode_synced(dqopt->files[type]);
+ }
+}
+
+static int f2fs_dquot_commit(struct dquot *dquot)
+{
+ int ret;
+
+ ret = dquot_commit(dquot);
+ if (ret < 0)
+ set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR);
+ return ret;
+}
+
+static int f2fs_dquot_acquire(struct dquot *dquot)
+{
+ int ret;
+
+ ret = dquot_acquire(dquot);
+ if (ret < 0)
+ set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR);
+
+ return ret;
+}
+
+static int f2fs_dquot_release(struct dquot *dquot)
+{
+ int ret;
+
+ ret = dquot_release(dquot);
+ if (ret < 0)
+ set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR);
+ return ret;
+}
+
+static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot)
+{
+ struct super_block *sb = dquot->dq_sb;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ int ret;
+
+ ret = dquot_mark_dquot_dirty(dquot);
+
+ /* if we are using journalled quota */
+ if (is_journalled_quota(sbi))
+ set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
+
+ return ret;
+}
+
+static int f2fs_dquot_commit_info(struct super_block *sb, int type)
+{
+ int ret;
+
+ ret = dquot_commit_info(sb, type);
+ if (ret < 0)
+ set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ return ret;
+}
+
+static int f2fs_get_projid(struct inode *inode, kprojid_t *projid)
+{
+ *projid = F2FS_I(inode)->i_projid;
+ return 0;
+}
+
+static const struct dquot_operations f2fs_quota_operations = {
+ .get_reserved_space = f2fs_get_reserved_space,
+ .write_dquot = f2fs_dquot_commit,
+ .acquire_dquot = f2fs_dquot_acquire,
+ .release_dquot = f2fs_dquot_release,
+ .mark_dirty = f2fs_dquot_mark_dquot_dirty,
+ .write_info = f2fs_dquot_commit_info,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
+ .get_projid = f2fs_get_projid,
+ .get_next_id = dquot_get_next_id,
+};
+
+static const struct quotactl_ops f2fs_quotactl_ops = {
+ .quota_on = f2fs_quota_on,
+ .quota_off = f2fs_quota_off,
+ .quota_sync = f2fs_quota_sync,
+ .get_state = dquot_get_state,
+ .set_info = dquot_set_dqinfo,
+ .get_dqblk = dquot_get_dqblk,
+ .set_dqblk = dquot_set_dqblk,
+ .get_nextdqblk = dquot_get_next_dqblk,
+};
+#else
+int f2fs_quota_sync(struct super_block *sb, int type)
+{
+ return 0;
+}
+
+void f2fs_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
+static const struct super_operations f2fs_sops = {
.alloc_inode = f2fs_alloc_inode,
.drop_inode = f2fs_drop_inode,
.destroy_inode = f2fs_destroy_inode,
.write_inode = f2fs_write_inode,
.dirty_inode = f2fs_dirty_inode,
.show_options = f2fs_show_options,
+#ifdef CONFIG_QUOTA
+ .quota_read = f2fs_quota_read,
+ .quota_write = f2fs_quota_write,
+ .get_dquots = f2fs_get_dquots,
+#endif
.evict_inode = f2fs_evict_inode,
.put_super = f2fs_put_super,
.sync_fs = f2fs_sync_fs,
@@ -1120,37 +2193,38 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
ctx, len, NULL);
}
-static int f2fs_key_prefix(struct inode *inode, u8 **key)
-{
- *key = F2FS_I_SB(inode)->key_prefix;
- return F2FS_I_SB(inode)->key_prefix_size;
-}
-
static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ /*
+ * Encrypting the root directory is not allowed because fsck
+ * expects lost+found directory to exist and remain unencrypted
+ * if LOST_FOUND feature is enabled.
+ *
+ */
+ if (f2fs_sb_has_lost_found(sbi) &&
+ inode->i_ino == F2FS_ROOT_INO(sbi))
+ return -EPERM;
+
return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
ctx, len, fs_data, XATTR_CREATE);
}
-static unsigned f2fs_max_namelen(struct inode *inode)
+static bool f2fs_dummy_context(struct inode *inode)
{
- return S_ISLNK(inode->i_mode) ?
- inode->i_sb->s_blocksize : F2FS_NAME_LEN;
+ return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
}
-static struct fscrypt_operations f2fs_cryptops = {
+static const struct fscrypt_operations f2fs_cryptops = {
+ .key_prefix = "f2fs:",
.get_context = f2fs_get_context,
- .key_prefix = f2fs_key_prefix,
.set_context = f2fs_set_context,
- .is_encrypted = f2fs_encrypted_inode,
+ .dummy_context = f2fs_dummy_context,
.empty_dir = f2fs_empty_dir,
- .max_namelen = f2fs_max_namelen,
-};
-#else
-static struct fscrypt_operations f2fs_cryptops = {
- .is_encrypted = f2fs_encrypted_inode,
+ .max_namelen = F2FS_NAME_LEN,
};
#endif
@@ -1160,7 +2234,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
- if (check_nid_range(sbi, ino))
+ if (f2fs_check_nid_range(sbi, ino))
return ERR_PTR(-ESTALE);
/*
@@ -1201,9 +2275,16 @@ static const struct export_operations f2fs_export_ops = {
static loff_t max_file_blocks(void)
{
- loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
+ loff_t result = 0;
loff_t leaf_count = ADDRS_PER_BLOCK;
+ /*
+ * note: previously, result is equal to (DEF_ADDRS_PER_INODE -
+ * DEFAULT_INLINE_XATTR_ADDRS), but now f2fs try to reserve more
+ * space in inode.i_addr, it will be more safe to reassign
+ * result as zero.
+ */
+
/* two direct node blocks */
result += (leaf_count * 2);
@@ -1224,12 +2305,11 @@ static int __f2fs_commit_super(struct buffer_head *bh,
lock_buffer(bh);
if (super)
memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
- set_buffer_uptodate(bh);
set_buffer_dirty(bh);
unlock_buffer(bh);
/* it's rare case, we can do fua all the time */
- return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+ return __sync_dirty_buffer(bh, REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
}
static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
@@ -1343,6 +2423,26 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
(bh->b_data + F2FS_SUPER_OFFSET);
struct super_block *sb = sbi->sb;
unsigned int blocksize;
+ size_t crc_offset = 0;
+ __u32 crc = 0;
+
+ /* Check checksum_offset and crc in superblock */
+ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) {
+ crc_offset = le32_to_cpu(raw_super->checksum_offset);
+ if (crc_offset !=
+ offsetof(struct f2fs_super_block, crc)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid SB checksum offset: %zu",
+ crc_offset);
+ return 1;
+ }
+ crc = le32_to_cpu(raw_super->crc);
+ if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid SB checksum value: %u", crc);
+ return 1;
+ }
+ }
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
f2fs_msg(sb, KERN_INFO,
@@ -1440,10 +2540,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
secs_per_zone, total_sections);
return 1;
}
- if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
+ if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION ||
+ raw_super->hot_ext_count > F2FS_MAX_EXTENSION ||
+ (le32_to_cpu(raw_super->extension_count) +
+ raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) {
f2fs_msg(sb, KERN_INFO,
- "Corrupted extension count (%u > %u)",
+ "Corrupted extension count (%u + %u > %u)",
le32_to_cpu(raw_super->extension_count),
+ raw_super->hot_ext_count,
F2FS_MAX_EXTENSION);
return 1;
}
@@ -1476,7 +2580,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
return 0;
}
-int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -1619,27 +2723,36 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
sbi->cur_victim_sec = NULL_SECNO;
+ sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
+ sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
+ sbi->migration_granularity = sbi->segs_per_sec;
sbi->dir_level = DEF_DIR_LEVEL;
sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
+ sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL;
+ sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL;
+ sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL;
+ sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] =
+ DEF_UMOUNT_DISCARD_TIMEOUT;
clear_sbi_flag(sbi, SBI_NEED_FSCK);
for (i = 0; i < NR_COUNT_TYPE; i++)
atomic_set(&sbi->nr_pages[i], 0);
+ for (i = 0; i < META; i++)
+ atomic_set(&sbi->wb_sync_req[i], 0);
+
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
- mutex_init(&sbi->wio_mutex[NODE]);
- mutex_init(&sbi->wio_mutex[DATA]);
+ init_rwsem(&sbi->io_order_lock);
spin_lock_init(&sbi->cp_lock);
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
- memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
- F2FS_KEY_DESC_PREFIX_SIZE);
- sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
-#endif
+ sbi->dirty_device = 0;
+ spin_lock_init(&sbi->dev_lock);
+
+ init_rwsem(&sbi->sb_lock);
}
static int init_percpu_info(struct f2fs_sb_info *sbi)
@@ -1658,6 +2771,74 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
return err;
}
+#ifdef CONFIG_BLK_DEV_ZONED
+static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
+{
+ struct block_device *bdev = FDEV(devi).bdev;
+ sector_t nr_sectors = bdev->bd_part->nr_sects;
+ sector_t sector = 0;
+ struct blk_zone *zones;
+ unsigned int i, nr_zones;
+ unsigned int n = 0;
+ int err = -EIO;
+
+ if (!f2fs_sb_has_blkzoned(sbi))
+ return 0;
+
+ if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
+ SECTOR_TO_BLOCK(bdev_zone_sectors(bdev)))
+ return -EINVAL;
+ sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_sectors(bdev));
+ if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
+ __ilog2_u32(sbi->blocks_per_blkz))
+ return -EINVAL;
+ sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
+ FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
+ sbi->log_blocks_per_blkz;
+ if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
+ FDEV(devi).nr_blkz++;
+
+ FDEV(devi).blkz_type = f2fs_kmalloc(sbi, FDEV(devi).nr_blkz,
+ GFP_KERNEL);
+ if (!FDEV(devi).blkz_type)
+ return -ENOMEM;
+
+#define F2FS_REPORT_NR_ZONES 4096
+
+ zones = f2fs_kzalloc(sbi,
+ array_size(F2FS_REPORT_NR_ZONES,
+ sizeof(struct blk_zone)),
+ GFP_KERNEL);
+ if (!zones)
+ return -ENOMEM;
+
+ /* Get block zones type */
+ while (zones && sector < nr_sectors) {
+
+ nr_zones = F2FS_REPORT_NR_ZONES;
+ err = blkdev_report_zones(bdev, sector,
+ zones, &nr_zones,
+ GFP_KERNEL);
+ if (err)
+ break;
+ if (!nr_zones) {
+ err = -EIO;
+ break;
+ }
+
+ for (i = 0; i < nr_zones; i++) {
+ FDEV(devi).blkz_type[n] = zones[i].type;
+ sector += zones[i].len;
+ n++;
+ }
+ }
+
+ kvfree(zones);
+
+ return err;
+}
+#endif
+
/*
* Read f2fs raw super block.
* Because we have two copies of super block, so read both of them
@@ -1712,7 +2893,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
/* No valid superblock */
if (!*raw_super)
- kfree(super);
+ kvfree(super);
else
err = 0;
@@ -1722,6 +2903,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
{
struct buffer_head *bh;
+ __u32 crc = 0;
int err;
if ((recover && f2fs_readonly(sbi->sb)) ||
@@ -1730,8 +2912,15 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
return -EROFS;
}
+ /* we should update superblock crc here */
+ if (!recover && f2fs_sb_has_sb_chksum(sbi)) {
+ crc = f2fs_crc32(sbi, F2FS_RAW_SUPER(sbi),
+ offsetof(struct f2fs_super_block, crc));
+ F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc);
+ }
+
/* write back-up superblock first */
- bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
+ bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1);
if (!bh)
return -EIO;
err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
@@ -1742,7 +2931,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
return err;
/* write current valid superblock */
- bh = sb_getblk(sbi->sb, sbi->valid_super_block);
+ bh = sb_bread(sbi->sb, sbi->valid_super_block);
if (!bh)
return -EIO;
err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
@@ -1750,16 +2939,131 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
return err;
}
+static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+ unsigned int max_devices = MAX_DEVICES;
+ int i;
+
+ /* Initialize single device information */
+ if (!RDEV(0).path[0]) {
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (!bdev_is_zoned(sbi->sb->s_bdev))
+ return 0;
+ max_devices = 1;
+#else
+ return 0;
+#endif
+ }
+
+ /*
+ * Initialize multiple devices information, or single
+ * zoned block device information.
+ */
+ sbi->devs = f2fs_kzalloc(sbi,
+ array_size(max_devices,
+ sizeof(struct f2fs_dev_info)),
+ GFP_KERNEL);
+ if (!sbi->devs)
+ return -ENOMEM;
+
+ for (i = 0; i < max_devices; i++) {
+
+ if (i > 0 && !RDEV(i).path[0])
+ break;
+
+ if (max_devices == 1) {
+ /* Single zoned block device mount */
+ FDEV(0).bdev =
+ blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev,
+ sbi->sb->s_mode, sbi->sb->s_type);
+ } else {
+ /* Multi-device mount */
+ memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+ FDEV(i).total_segments =
+ le32_to_cpu(RDEV(i).total_segments);
+ if (i == 0) {
+ FDEV(i).start_blk = 0;
+ FDEV(i).end_blk = FDEV(i).start_blk +
+ (FDEV(i).total_segments <<
+ sbi->log_blocks_per_seg) - 1 +
+ le32_to_cpu(raw_super->segment0_blkaddr);
+ } else {
+ FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+ FDEV(i).end_blk = FDEV(i).start_blk +
+ (FDEV(i).total_segments <<
+ sbi->log_blocks_per_seg) - 1;
+ }
+ FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+ sbi->sb->s_mode, sbi->sb->s_type);
+ }
+ if (IS_ERR(FDEV(i).bdev))
+ return PTR_ERR(FDEV(i).bdev);
+
+ /* to release errored devices */
+ sbi->s_ndevs = i + 1;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
+ !f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Zoned block device feature not enabled\n");
+ return -EINVAL;
+ }
+ if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+ if (init_blkz_info(sbi, i)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Failed to initialize F2FS blkzone information");
+ return -EINVAL;
+ }
+ if (max_devices == 1)
+ break;
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+ i, FDEV(i).path,
+ FDEV(i).total_segments,
+ FDEV(i).start_blk, FDEV(i).end_blk,
+ bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
+ "Host-aware" : "Host-managed");
+ continue;
+ }
+#endif
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Mount Device [%2d]: %20s, %8u, %8x - %8x",
+ i, FDEV(i).path,
+ FDEV(i).total_segments,
+ FDEV(i).start_blk, FDEV(i).end_blk);
+ }
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi));
+ return 0;
+}
+
+static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_sm_info *sm_i = SM_I(sbi);
+
+ /* adjust parameters according to the volume size */
+ if (sm_i->main_segments <= SMALL_VOLUME_SEGMENTS) {
+ F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
+ sm_i->dcc_info->discard_granularity = 1;
+ sm_i->ipu_policy = 1 << F2FS_IPU_FORCE;
+ }
+
+ sbi->readdir_ra = 1;
+}
+
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
struct inode *root;
int err;
- bool retry = true, need_fsck = false;
+ bool skip_recovery = false, need_fsck = false;
char *options = NULL;
int recovery, i, valid_super_block;
struct curseg_info *seg_i;
+ int retry_cnt = 1;
try_onemore:
err = -EINVAL;
@@ -1797,6 +3101,24 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_fs_info = sbi;
sbi->raw_super = raw_super;
+ /* precompute checksum seed for metadata */
+ if (f2fs_sb_has_inode_chksum(sbi))
+ sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid,
+ sizeof(raw_super->uuid));
+
+ /*
+ * The BLKZONED feature indicates that the drive was formatted with
+ * zone alignment optimization. This is optional for host-aware
+ * devices, but mandatory for host-managed zoned block devices.
+ */
+#ifndef CONFIG_BLK_DEV_ZONED
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Zoned block device support is not enabled\n");
+ err = -EOPNOTSUPP;
+ goto free_sb_buf;
+ }
+#endif
default_options(sbi);
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
@@ -1813,35 +3135,73 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_maxbytes = sbi->max_file_blocks <<
le32_to_cpu(raw_super->log_blocksize);
sb->s_max_links = F2FS_LINK_MAX;
- get_random_bytes(&sbi->s_next_generation, sizeof(u32));
+
+#ifdef CONFIG_QUOTA
+ sb->dq_op = &f2fs_quota_operations;
+ if (f2fs_sb_has_quota_ino(sbi))
+ sb->s_qcop = &dquot_quotactl_sysfile_ops;
+ else
+ sb->s_qcop = &f2fs_quotactl_ops;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
+
+ if (f2fs_sb_has_quota_ino(sbi)) {
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (f2fs_qf_ino(sbi->sb, i))
+ sbi->nquota_files++;
+ }
+ }
+#endif
sb->s_op = &f2fs_sops;
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
sb->s_cop = &f2fs_cryptops;
+#endif
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
- memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+ memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+ sb->s_iflags |= SB_I_CGROUPWB;
/* init f2fs-specific super block info */
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
+ mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
+ init_rwsem(&sbi->node_change);
/* disallow all the data/node/meta page writes */
set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
- init_rwsem(&sbi->read_io.io_rwsem);
- sbi->read_io.sbi = sbi;
- sbi->read_io.bio = NULL;
+ /* init iostat info */
+ spin_lock_init(&sbi->iostat_lock);
+ sbi->iostat_enable = false;
+
for (i = 0; i < NR_PAGE_TYPE; i++) {
- init_rwsem(&sbi->write_io[i].io_rwsem);
- sbi->write_io[i].sbi = sbi;
- sbi->write_io[i].bio = NULL;
+ int n = (i == META) ? 1: NR_TEMP_TYPE;
+ int j;
+
+ sbi->write_io[i] =
+ f2fs_kmalloc(sbi,
+ array_size(n,
+ sizeof(struct f2fs_bio_info)),
+ GFP_KERNEL);
+ if (!sbi->write_io[i]) {
+ err = -ENOMEM;
+ goto free_bio_info;
+ }
+
+ for (j = HOT; j < n; j++) {
+ init_rwsem(&sbi->write_io[i][j].io_rwsem);
+ sbi->write_io[i][j].sbi = sbi;
+ sbi->write_io[i][j].bio = NULL;
+ spin_lock_init(&sbi->write_io[i][j].io_lock);
+ INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
+ }
}
init_rwsem(&sbi->cp_rwsem);
@@ -1850,22 +3210,45 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
err = init_percpu_info(sbi);
if (err)
- goto free_options;
+ goto free_bio_info;
+
+ if (F2FS_IO_SIZE(sbi) > 1) {
+ sbi->write_io_dummy =
+ mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
+ if (!sbi->write_io_dummy) {
+ err = -ENOMEM;
+ goto free_percpu;
+ }
+ }
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
- goto free_options;
+ goto free_io_dummy;
}
- err = get_valid_checkpoint(sbi);
+ err = f2fs_get_valid_checkpoint(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
}
+ if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG))
+ set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+ if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_DISABLED_QUICK_FLAG)) {
+ set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
+ sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL;
+ }
+
+ /* Initialize device list */
+ err = f2fs_scan_devices(sbi);
+ if (err) {
+ f2fs_msg(sb, KERN_ERR, "Failed to find devices");
+ goto free_devices;
+ }
+
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
percpu_counter_set(&sbi->total_valid_inode_count,
@@ -1874,24 +3257,29 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
+ sbi->reserved_blocks = 0;
+ sbi->current_reserved_blocks = 0;
+ limit_reserve_root(sbi);
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
spin_lock_init(&sbi->inode_lock[i]);
}
- init_extent_cache_info(sbi);
+ f2fs_init_extent_cache_info(sbi);
- init_ino_entry_info(sbi);
+ f2fs_init_ino_entry_info(sbi);
+
+ f2fs_init_fsync_node_info(sbi);
/* setup f2fs internal modules */
- err = build_segment_manager(sbi);
+ err = f2fs_build_segment_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS segment manager");
goto free_sm;
}
- err = build_node_manager(sbi);
+ err = f2fs_build_node_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS node manager");
@@ -1909,23 +3297,20 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sbi->kbytes_written =
le64_to_cpu(seg_i->journal->info.kbytes_written);
- build_gc_manager(sbi);
+ f2fs_build_gc_manager(sbi);
+
+ err = f2fs_build_stats(sbi);
+ if (err)
+ goto free_nm;
/* get an inode for node space */
sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
if (IS_ERR(sbi->node_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
err = PTR_ERR(sbi->node_inode);
- goto free_nm;
+ goto free_stats;
}
- f2fs_join_shrinker(sbi);
-
- /* if there are nt orphan nodes free them */
- err = recover_orphan_inodes(sbi);
- if (err)
- goto free_node_inode;
-
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
@@ -1933,7 +3318,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
err = PTR_ERR(root);
goto free_node_inode;
}
- if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
+ if (!S_ISDIR(root->i_mode) || !root->i_blocks ||
+ !root->i_size || !root->i_nlink) {
iput(root);
err = -EINVAL;
goto free_node_inode;
@@ -1942,29 +3328,29 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_root = d_make_root(root); /* allocate root dentry */
if (!sb->s_root) {
err = -ENOMEM;
- goto free_root_inode;
+ goto free_node_inode;
}
- err = f2fs_build_stats(sbi);
+ err = f2fs_register_sysfs(sbi);
if (err)
goto free_root_inode;
- if (f2fs_proc_root)
- sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
-
- if (sbi->s_proc) {
- proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
- &f2fs_seq_segment_info_fops, sb);
- proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
- &f2fs_seq_segment_bits_fops, sb);
+#ifdef CONFIG_QUOTA
+ /* Enable quota usage during mount */
+ if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) {
+ err = f2fs_enable_quotas(sb);
+ if (err)
+ f2fs_msg(sb, KERN_ERR,
+ "Cannot turn on quotas: error %d", err);
}
-
- sbi->s_kobj.kset = f2fs_kset;
- init_completion(&sbi->s_kobj_unregister);
- err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
- "%s", sb->s_id);
+#endif
+ /* if there are nt orphan nodes free them */
+ err = f2fs_recover_orphan_inodes(sbi);
if (err)
- goto free_proc;
+ goto free_meta;
+
+ if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)))
+ goto reset_checkpoint;
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
@@ -1975,47 +3361,57 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (bdev_read_only(sb->s_bdev) &&
!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
err = -EROFS;
- goto free_kobj;
+ goto free_meta;
}
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
- if (!retry)
- goto skip_recovery;
+ if (skip_recovery)
+ goto reset_checkpoint;
- err = recover_fsync_data(sbi, false);
+ err = f2fs_recover_fsync_data(sbi, false);
if (err < 0) {
+ if (err != -ENOMEM)
+ skip_recovery = true;
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%d", err);
- goto free_kobj;
+ goto free_meta;
}
} else {
- err = recover_fsync_data(sbi, true);
+ err = f2fs_recover_fsync_data(sbi, true);
if (!f2fs_readonly(sb) && err > 0) {
err = -EINVAL;
f2fs_msg(sb, KERN_ERR,
"Need to recover fsync data");
- goto free_kobj;
+ goto free_meta;
}
}
-skip_recovery:
- /* recover_fsync_data() cleared this already */
+reset_checkpoint:
+ /* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
+ if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = f2fs_disable_checkpoint(sbi);
+ if (err)
+ goto sync_free_meta;
+ } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) {
+ f2fs_enable_checkpoint(sbi);
+ }
+
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
- err = start_gc_thread(sbi);
+ err = f2fs_start_gc_thread(sbi);
if (err)
- goto free_kobj;
+ goto sync_free_meta;
}
- kfree(options);
+ kvfree(options);
/* recover broken superblock */
if (recovery) {
@@ -2025,53 +3421,82 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sbi->valid_super_block ? 1 : 2, err);
}
+ f2fs_join_shrinker(sbi);
+
+ f2fs_tuning_parameters(sbi);
+
+ f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx",
+ cur_cp_version(F2FS_CKPT(sbi)));
f2fs_update_time(sbi, CP_TIME);
f2fs_update_time(sbi, REQ_TIME);
+ clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
return 0;
-free_kobj:
- f2fs_sync_inode_meta(sbi);
- kobject_del(&sbi->s_kobj);
- kobject_put(&sbi->s_kobj);
- wait_for_completion(&sbi->s_kobj_unregister);
-free_proc:
- if (sbi->s_proc) {
- remove_proc_entry("segment_info", sbi->s_proc);
- remove_proc_entry("segment_bits", sbi->s_proc);
- remove_proc_entry(sb->s_id, f2fs_proc_root);
- }
- f2fs_destroy_stats(sbi);
+sync_free_meta:
+ /* safe to flush all the data */
+ sync_filesystem(sbi->sb);
+ retry_cnt = 0;
+
+free_meta:
+#ifdef CONFIG_QUOTA
+ f2fs_truncate_quota_inode_pages(sb);
+ if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb))
+ f2fs_quota_off_umount(sbi->sb);
+#endif
+ /*
+ * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes()
+ * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+ * followed by f2fs_write_checkpoint() through f2fs_write_node_pages(), which
+ * falls into an infinite loop in f2fs_sync_meta_pages().
+ */
+ truncate_inode_pages_final(META_MAPPING(sbi));
+ /* evict some inodes being cached by GC */
+ evict_inodes(sb);
+ f2fs_unregister_sysfs(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
+ f2fs_release_ino_entry(sbi, true);
truncate_inode_pages_final(NODE_MAPPING(sbi));
- mutex_lock(&sbi->umount_mutex);
- release_ino_entry(sbi, true);
- f2fs_leave_shrinker(sbi);
iput(sbi->node_inode);
- mutex_unlock(&sbi->umount_mutex);
+ sbi->node_inode = NULL;
+free_stats:
+ f2fs_destroy_stats(sbi);
free_nm:
- destroy_node_manager(sbi);
+ f2fs_destroy_node_manager(sbi);
free_sm:
- destroy_segment_manager(sbi);
- kfree(sbi->ckpt);
+ f2fs_destroy_segment_manager(sbi);
+free_devices:
+ destroy_device_list(sbi);
+ kvfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
-free_options:
+ sbi->meta_inode = NULL;
+free_io_dummy:
+ mempool_destroy(sbi->write_io_dummy);
+free_percpu:
destroy_percpu_info(sbi);
- kfree(options);
+free_bio_info:
+ for (i = 0; i < NR_PAGE_TYPE; i++)
+ kvfree(sbi->write_io[i]);
+free_options:
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+#endif
+ kvfree(options);
free_sb_buf:
- kfree(raw_super);
+ kvfree(raw_super);
free_sbi:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kfree(sbi);
+ kvfree(sbi);
/* give only one another chance */
- if (retry) {
- retry = false;
+ if (retry_cnt > 0 && skip_recovery) {
+ retry_cnt--;
shrink_dcache_sb(sb);
goto try_onemore;
}
@@ -2086,8 +3511,24 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
static void kill_f2fs_super(struct super_block *sb)
{
- if (sb->s_root)
- set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+ if (sb->s_root) {
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ set_sbi_flag(sbi, SBI_IS_CLOSE);
+ f2fs_stop_gc_thread(sbi);
+ f2fs_stop_discard_thread(sbi);
+
+ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+ !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT,
+ };
+ f2fs_write_checkpoint(sbi, &cpc);
+ }
+
+ if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb))
+ sb->s_flags &= ~MS_RDONLY;
+ }
kill_block_super(sb);
}
@@ -2135,50 +3576,48 @@ static int __init init_f2fs_fs(void)
err = init_inodecache();
if (err)
goto fail;
- err = create_node_manager_caches();
+ err = f2fs_create_node_manager_caches();
if (err)
goto free_inodecache;
- err = create_segment_manager_caches();
+ err = f2fs_create_segment_manager_caches();
if (err)
goto free_node_manager_caches;
- err = create_checkpoint_caches();
+ err = f2fs_create_checkpoint_caches();
if (err)
goto free_segment_manager_caches;
- err = create_extent_cache();
+ err = f2fs_create_extent_cache();
if (err)
goto free_checkpoint_caches;
- f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
- if (!f2fs_kset) {
- err = -ENOMEM;
+ err = f2fs_init_sysfs();
+ if (err)
goto free_extent_cache;
- }
err = register_shrinker(&f2fs_shrinker_info);
if (err)
- goto free_kset;
-
+ goto free_sysfs;
err = register_filesystem(&f2fs_fs_type);
if (err)
goto free_shrinker;
- err = f2fs_create_root_stats();
+ f2fs_create_root_stats();
+ err = f2fs_init_post_read_processing();
if (err)
- goto free_filesystem;
- f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ goto free_root_stats;
return 0;
-free_filesystem:
+free_root_stats:
+ f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
free_shrinker:
unregister_shrinker(&f2fs_shrinker_info);
-free_kset:
- kset_unregister(f2fs_kset);
+free_sysfs:
+ f2fs_exit_sysfs();
free_extent_cache:
- destroy_extent_cache();
+ f2fs_destroy_extent_cache();
free_checkpoint_caches:
- destroy_checkpoint_caches();
+ f2fs_destroy_checkpoint_caches();
free_segment_manager_caches:
- destroy_segment_manager_caches();
+ f2fs_destroy_segment_manager_caches();
free_node_manager_caches:
- destroy_node_manager_caches();
+ f2fs_destroy_node_manager_caches();
free_inodecache:
destroy_inodecache();
fail:
@@ -2187,15 +3626,15 @@ static int __init init_f2fs_fs(void)
static void __exit exit_f2fs_fs(void)
{
- remove_proc_entry("fs/f2fs", NULL);
+ f2fs_destroy_post_read_processing();
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
unregister_shrinker(&f2fs_shrinker_info);
- kset_unregister(f2fs_kset);
- destroy_extent_cache();
- destroy_checkpoint_caches();
- destroy_segment_manager_caches();
- destroy_node_manager_caches();
+ f2fs_exit_sysfs();
+ f2fs_destroy_extent_cache();
+ f2fs_destroy_checkpoint_caches();
+ f2fs_destroy_segment_manager_caches();
+ f2fs_destroy_node_manager_caches();
destroy_inodecache();
f2fs_destroy_trace_ios();
}
@@ -2206,3 +3645,4 @@ module_exit(exit_f2fs_fs)
MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");
+
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
new file mode 100644
index 0000000..d7b4766
--- /dev/null
+++ b/fs/f2fs/sysfs.c
@@ -0,0 +1,753 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs sysfs interface
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com/
+ * Copyright (c) 2017 Chao Yu <chao@kernel.org>
+ */
+#include <linux/compiler.h>
+#include <linux/proc_fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/seq_file.h>
+
+#include "f2fs.h"
+#include "segment.h"
+#include "gc.h"
+
+static struct proc_dir_entry *f2fs_proc_root;
+
+/* Sysfs support for f2fs */
+enum {
+ GC_THREAD, /* struct f2fs_gc_thread */
+ SM_INFO, /* struct f2fs_sm_info */
+ DCC_INFO, /* struct discard_cmd_control */
+ NM_INFO, /* struct f2fs_nm_info */
+ F2FS_SBI, /* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ FAULT_INFO_RATE, /* struct f2fs_fault_info */
+ FAULT_INFO_TYPE, /* struct f2fs_fault_info */
+#endif
+ RESERVED_BLOCKS, /* struct f2fs_sb_info */
+};
+
+struct f2fs_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
+ ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
+ const char *, size_t);
+ int struct_type;
+ int offset;
+ int id;
+};
+
+static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
+{
+ if (struct_type == GC_THREAD)
+ return (unsigned char *)sbi->gc_thread;
+ else if (struct_type == SM_INFO)
+ return (unsigned char *)SM_I(sbi);
+ else if (struct_type == DCC_INFO)
+ return (unsigned char *)SM_I(sbi)->dcc_info;
+ else if (struct_type == NM_INFO)
+ return (unsigned char *)NM_I(sbi);
+ else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS)
+ return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ else if (struct_type == FAULT_INFO_RATE ||
+ struct_type == FAULT_INFO_TYPE)
+ return (unsigned char *)&F2FS_OPTION(sbi).fault_info;
+#endif
+ return NULL;
+}
+
+static ssize_t dirty_segments_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)(dirty_segments(sbi)));
+}
+
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct super_block *sb = sbi->sb;
+
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
+
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)(sbi->kbytes_written +
+ BD_PART_WRITTEN(sbi)));
+}
+
+static ssize_t features_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct super_block *sb = sbi->sb;
+ int len = 0;
+
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
+
+ if (f2fs_sb_has_encrypt(sbi))
+ len += snprintf(buf, PAGE_SIZE - len, "%s",
+ "encryption");
+ if (f2fs_sb_has_blkzoned(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "blkzoned");
+ if (f2fs_sb_has_extra_attr(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "extra_attr");
+ if (f2fs_sb_has_project_quota(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "projquota");
+ if (f2fs_sb_has_inode_chksum(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "inode_checksum");
+ if (f2fs_sb_has_flexible_inline_xattr(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "flexible_inline_xattr");
+ if (f2fs_sb_has_quota_ino(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "quota_ino");
+ if (f2fs_sb_has_inode_crtime(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "inode_crtime");
+ if (f2fs_sb_has_lost_found(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "lost_found");
+ if (f2fs_sb_has_sb_chksum(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "sb_checksum");
+ len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+ return len;
+}
+
+static ssize_t current_reserved_blocks_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%u\n", sbi->current_reserved_blocks);
+}
+
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ unsigned char *ptr = NULL;
+ unsigned int *ui;
+
+ ptr = __struct_ptr(sbi, a->struct_type);
+ if (!ptr)
+ return -EINVAL;
+
+ if (!strcmp(a->attr.name, "extension_list")) {
+ __u8 (*extlist)[F2FS_EXTENSION_LEN] =
+ sbi->raw_super->extension_list;
+ int cold_count = le32_to_cpu(sbi->raw_super->extension_count);
+ int hot_count = sbi->raw_super->hot_ext_count;
+ int len = 0, i;
+
+ len += snprintf(buf + len, PAGE_SIZE - len,
+ "cold file extension:\n");
+ for (i = 0; i < cold_count; i++)
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
+ extlist[i]);
+
+ len += snprintf(buf + len, PAGE_SIZE - len,
+ "hot file extension:\n");
+ for (i = cold_count; i < cold_count + hot_count; i++)
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
+ extlist[i]);
+ return len;
+ }
+
+ ui = (unsigned int *)(ptr + a->offset);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t __sbi_store(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi,
+ const char *buf, size_t count)
+{
+ unsigned char *ptr;
+ unsigned long t;
+ unsigned int *ui;
+ ssize_t ret;
+
+ ptr = __struct_ptr(sbi, a->struct_type);
+ if (!ptr)
+ return -EINVAL;
+
+ if (!strcmp(a->attr.name, "extension_list")) {
+ const char *name = strim((char *)buf);
+ bool set = true, hot;
+
+ if (!strncmp(name, "[h]", 3))
+ hot = true;
+ else if (!strncmp(name, "[c]", 3))
+ hot = false;
+ else
+ return -EINVAL;
+
+ name += 3;
+
+ if (*name == '!') {
+ name++;
+ set = false;
+ }
+
+ if (strlen(name) >= F2FS_EXTENSION_LEN)
+ return -EINVAL;
+
+ down_write(&sbi->sb_lock);
+
+ ret = f2fs_update_extension_list(sbi, name, hot, set);
+ if (ret)
+ goto out;
+
+ ret = f2fs_commit_super(sbi, false);
+ if (ret)
+ f2fs_update_extension_list(sbi, name, hot, !set);
+out:
+ up_write(&sbi->sb_lock);
+ return ret ? ret : count;
+ }
+
+ ui = (unsigned int *)(ptr + a->offset);
+
+ ret = kstrtoul(skip_spaces(buf), 0, &t);
+ if (ret < 0)
+ return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+ return -EINVAL;
+ if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX)
+ return -EINVAL;
+#endif
+ if (a->struct_type == RESERVED_BLOCKS) {
+ spin_lock(&sbi->stat_lock);
+ if (t > (unsigned long)(sbi->user_block_count -
+ F2FS_OPTION(sbi).root_reserved_blocks)) {
+ spin_unlock(&sbi->stat_lock);
+ return -EINVAL;
+ }
+ *ui = t;
+ sbi->current_reserved_blocks = min(sbi->reserved_blocks,
+ sbi->user_block_count - valid_user_blocks(sbi));
+ spin_unlock(&sbi->stat_lock);
+ return count;
+ }
+
+ if (!strcmp(a->attr.name, "discard_granularity")) {
+ if (t == 0 || t > MAX_PLIST_NUM)
+ return -EINVAL;
+ if (t == *ui)
+ return count;
+ *ui = t;
+ return count;
+ }
+
+ if (!strcmp(a->attr.name, "migration_granularity")) {
+ if (t == 0 || t > sbi->segs_per_sec)
+ return -EINVAL;
+ }
+
+ if (!strcmp(a->attr.name, "trim_sections"))
+ return -EINVAL;
+
+ if (!strcmp(a->attr.name, "gc_urgent")) {
+ if (t >= 1) {
+ sbi->gc_mode = GC_URGENT;
+ if (sbi->gc_thread) {
+ sbi->gc_thread->gc_wake = 1;
+ wake_up_interruptible_all(
+ &sbi->gc_thread->gc_wait_queue_head);
+ wake_up_discard_thread(sbi, true);
+ }
+ } else {
+ sbi->gc_mode = GC_NORMAL;
+ }
+ return count;
+ }
+ if (!strcmp(a->attr.name, "gc_idle")) {
+ if (t == GC_IDLE_CB)
+ sbi->gc_mode = GC_IDLE_CB;
+ else if (t == GC_IDLE_GREEDY)
+ sbi->gc_mode = GC_IDLE_GREEDY;
+ else
+ sbi->gc_mode = GC_NORMAL;
+ return count;
+ }
+
+
+ if (!strcmp(a->attr.name, "iostat_enable")) {
+ sbi->iostat_enable = !!t;
+ if (!sbi->iostat_enable)
+ f2fs_reset_iostat(sbi);
+ return count;
+ }
+
+ *ui = (unsigned int)t;
+
+ return count;
+}
+
+static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi,
+ const char *buf, size_t count)
+{
+ ssize_t ret;
+ bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") ||
+ a->struct_type == GC_THREAD);
+
+ if (gc_entry) {
+ if (!down_read_trylock(&sbi->sb->s_umount))
+ return -EAGAIN;
+ }
+ ret = __sbi_store(a, sbi, buf, count);
+ if (gc_entry)
+ up_read(&sbi->sb->s_umount);
+
+ return ret;
+}
+
+static ssize_t f2fs_attr_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+ return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+ return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void f2fs_sb_release(struct kobject *kobj)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ complete(&sbi->s_kobj_unregister);
+}
+
+enum feat_id {
+ FEAT_CRYPTO = 0,
+ FEAT_BLKZONED,
+ FEAT_ATOMIC_WRITE,
+ FEAT_EXTRA_ATTR,
+ FEAT_PROJECT_QUOTA,
+ FEAT_INODE_CHECKSUM,
+ FEAT_FLEXIBLE_INLINE_XATTR,
+ FEAT_QUOTA_INO,
+ FEAT_INODE_CRTIME,
+ FEAT_LOST_FOUND,
+ FEAT_SB_CHECKSUM,
+};
+
+static ssize_t f2fs_feature_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ switch (a->id) {
+ case FEAT_CRYPTO:
+ case FEAT_BLKZONED:
+ case FEAT_ATOMIC_WRITE:
+ case FEAT_EXTRA_ATTR:
+ case FEAT_PROJECT_QUOTA:
+ case FEAT_INODE_CHECKSUM:
+ case FEAT_FLEXIBLE_INLINE_XATTR:
+ case FEAT_QUOTA_INO:
+ case FEAT_INODE_CRTIME:
+ case FEAT_LOST_FOUND:
+ case FEAT_SB_CHECKSUM:
+ return snprintf(buf, PAGE_SIZE, "supported\n");
+ }
+ return 0;
+}
+
+#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
+static struct f2fs_attr f2fs_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = _mode }, \
+ .show = _show, \
+ .store = _store, \
+ .struct_type = _struct_type, \
+ .offset = _offset \
+}
+
+#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \
+ F2FS_ATTR_OFFSET(struct_type, name, 0644, \
+ f2fs_sbi_show, f2fs_sbi_store, \
+ offsetof(struct struct_name, elname))
+
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
+#define F2FS_FEATURE_RO_ATTR(_name, _id) \
+static struct f2fs_attr f2fs_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0444 }, \
+ .show = f2fs_feature_show, \
+ .id = _id, \
+}
+
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time,
+ urgent_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity);
+F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_seq_blocks, min_seq_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, migration_granularity, migration_granularity);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval,
+ interval_time[DISCARD_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info,
+ umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
+F2FS_GENERAL_RO_ATTR(dirty_segments);
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
+F2FS_GENERAL_RO_ATTR(features);
+F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED);
+#endif
+F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE);
+F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR);
+F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA);
+F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM);
+F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR);
+F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO);
+F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME);
+F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND);
+F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
+
+#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
+static struct attribute *f2fs_attrs[] = {
+ ATTR_LIST(gc_urgent_sleep_time),
+ ATTR_LIST(gc_min_sleep_time),
+ ATTR_LIST(gc_max_sleep_time),
+ ATTR_LIST(gc_no_gc_sleep_time),
+ ATTR_LIST(gc_idle),
+ ATTR_LIST(gc_urgent),
+ ATTR_LIST(reclaim_segments),
+ ATTR_LIST(max_small_discards),
+ ATTR_LIST(discard_granularity),
+ ATTR_LIST(batched_trim_sections),
+ ATTR_LIST(ipu_policy),
+ ATTR_LIST(min_ipu_util),
+ ATTR_LIST(min_fsync_blocks),
+ ATTR_LIST(min_seq_blocks),
+ ATTR_LIST(min_hot_blocks),
+ ATTR_LIST(min_ssr_sections),
+ ATTR_LIST(max_victim_search),
+ ATTR_LIST(migration_granularity),
+ ATTR_LIST(dir_level),
+ ATTR_LIST(ram_thresh),
+ ATTR_LIST(ra_nid_pages),
+ ATTR_LIST(dirty_nats_ratio),
+ ATTR_LIST(cp_interval),
+ ATTR_LIST(idle_interval),
+ ATTR_LIST(discard_idle_interval),
+ ATTR_LIST(gc_idle_interval),
+ ATTR_LIST(umount_discard_timeout),
+ ATTR_LIST(iostat_enable),
+ ATTR_LIST(readdir_ra),
+ ATTR_LIST(gc_pin_file_thresh),
+ ATTR_LIST(extension_list),
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ ATTR_LIST(inject_rate),
+ ATTR_LIST(inject_type),
+#endif
+ ATTR_LIST(dirty_segments),
+ ATTR_LIST(lifetime_write_kbytes),
+ ATTR_LIST(features),
+ ATTR_LIST(reserved_blocks),
+ ATTR_LIST(current_reserved_blocks),
+ NULL,
+};
+
+static struct attribute *f2fs_feat_attrs[] = {
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ ATTR_LIST(encryption),
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+ ATTR_LIST(block_zoned),
+#endif
+ ATTR_LIST(atomic_write),
+ ATTR_LIST(extra_attr),
+ ATTR_LIST(project_quota),
+ ATTR_LIST(inode_checksum),
+ ATTR_LIST(flexible_inline_xattr),
+ ATTR_LIST(quota_ino),
+ ATTR_LIST(inode_crtime),
+ ATTR_LIST(lost_found),
+ ATTR_LIST(sb_checksum),
+ NULL,
+};
+
+static const struct sysfs_ops f2fs_attr_ops = {
+ .show = f2fs_attr_show,
+ .store = f2fs_attr_store,
+};
+
+static struct kobj_type f2fs_sb_ktype = {
+ .default_attrs = f2fs_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+ .release = f2fs_sb_release,
+};
+
+static struct kobj_type f2fs_ktype = {
+ .sysfs_ops = &f2fs_attr_ops,
+};
+
+static struct kset f2fs_kset = {
+ .kobj = {.ktype = &f2fs_ktype},
+};
+
+static struct kobj_type f2fs_feat_ktype = {
+ .default_attrs = f2fs_feat_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+};
+
+static struct kobject f2fs_feat = {
+ .kset = &f2fs_kset,
+};
+
+static int __maybe_unused segment_info_seq_show(struct seq_file *seq,
+ void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs =
+ le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i;
+
+ seq_puts(seq, "format: segment_type|valid_blocks\n"
+ "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+ for (i = 0; i < total_segs; i++) {
+ struct seg_entry *se = get_seg_entry(sbi, i);
+
+ if ((i % 10) == 0)
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d|%-3u", se->type,
+ get_valid_blocks(sbi, i, false));
+ if ((i % 10) == 9 || i == (total_segs - 1))
+ seq_putc(seq, '\n');
+ else
+ seq_putc(seq, ' ');
+ }
+
+ return 0;
+}
+
+static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
+ void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs =
+ le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i, j;
+
+ seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+ "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+ for (i = 0; i < total_segs; i++) {
+ struct seg_entry *se = get_seg_entry(sbi, i);
+
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d|%-3u|", se->type,
+ get_valid_blocks(sbi, i, false));
+ for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+ seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+ seq_putc(seq, '\n');
+ }
+ return 0;
+}
+
+static int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
+ void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ time64_t now = ktime_get_real_seconds();
+
+ if (!sbi->iostat_enable)
+ return 0;
+
+ seq_printf(seq, "time: %-16llu\n", now);
+
+ /* print app IOs */
+ seq_printf(seq, "app buffered: %-16llu\n",
+ sbi->write_iostat[APP_BUFFERED_IO]);
+ seq_printf(seq, "app direct: %-16llu\n",
+ sbi->write_iostat[APP_DIRECT_IO]);
+ seq_printf(seq, "app mapped: %-16llu\n",
+ sbi->write_iostat[APP_MAPPED_IO]);
+
+ /* print fs IOs */
+ seq_printf(seq, "fs data: %-16llu\n",
+ sbi->write_iostat[FS_DATA_IO]);
+ seq_printf(seq, "fs node: %-16llu\n",
+ sbi->write_iostat[FS_NODE_IO]);
+ seq_printf(seq, "fs meta: %-16llu\n",
+ sbi->write_iostat[FS_META_IO]);
+ seq_printf(seq, "fs gc data: %-16llu\n",
+ sbi->write_iostat[FS_GC_DATA_IO]);
+ seq_printf(seq, "fs gc node: %-16llu\n",
+ sbi->write_iostat[FS_GC_NODE_IO]);
+ seq_printf(seq, "fs cp data: %-16llu\n",
+ sbi->write_iostat[FS_CP_DATA_IO]);
+ seq_printf(seq, "fs cp node: %-16llu\n",
+ sbi->write_iostat[FS_CP_NODE_IO]);
+ seq_printf(seq, "fs cp meta: %-16llu\n",
+ sbi->write_iostat[FS_CP_META_IO]);
+ seq_printf(seq, "fs discard: %-16llu\n",
+ sbi->write_iostat[FS_DISCARD]);
+
+ return 0;
+}
+
+static int __maybe_unused victim_bits_seq_show(struct seq_file *seq,
+ void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ int i;
+
+ seq_puts(seq, "format: victim_secmap bitmaps\n");
+
+ for (i = 0; i < MAIN_SECS(sbi); i++) {
+ if ((i % 10) == 0)
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d", test_bit(i, dirty_i->victim_secmap) ? 1 : 0);
+ if ((i % 10) == 9 || i == (MAIN_SECS(sbi) - 1))
+ seq_putc(seq, '\n');
+ else
+ seq_putc(seq, ' ');
+ }
+ return 0;
+}
+
+#define F2FS_PROC_FILE_DEF(_name) \
+static int _name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+ return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
+} \
+ \
+static const struct file_operations f2fs_seq_##_name##_fops = { \
+ .open = _name##_open_fs, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
+};
+
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+F2FS_PROC_FILE_DEF(iostat_info);
+F2FS_PROC_FILE_DEF(victim_bits);
+
+int __init f2fs_init_sysfs(void)
+{
+ int ret;
+
+ kobject_set_name(&f2fs_kset.kobj, "f2fs");
+ f2fs_kset.kobj.parent = fs_kobj;
+ ret = kset_register(&f2fs_kset);
+ if (ret)
+ return ret;
+
+ ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
+ NULL, "features");
+ if (ret)
+ kset_unregister(&f2fs_kset);
+ else
+ f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ return ret;
+}
+
+void f2fs_exit_sysfs(void)
+{
+ kobject_put(&f2fs_feat);
+ kset_unregister(&f2fs_kset);
+ remove_proc_entry("fs/f2fs", NULL);
+ f2fs_proc_root = NULL;
+}
+
+int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
+{
+ struct super_block *sb = sbi->sb;
+ int err;
+
+ sbi->s_kobj.kset = &f2fs_kset;
+ init_completion(&sbi->s_kobj_unregister);
+ err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
+ "%s", sb->s_id);
+ if (err)
+ return err;
+
+ if (f2fs_proc_root)
+ sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
+
+ if (sbi->s_proc) {
+ proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_info_fops, sb);
+ proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_bits_fops, sb);
+ proc_create_data("iostat_info", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_iostat_info_fops, sb);
+ proc_create_data("victim_bits", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_victim_bits_fops, sb);
+ }
+ return 0;
+}
+
+void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
+{
+ if (sbi->s_proc) {
+ remove_proc_entry("iostat_info", sbi->s_proc);
+ remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
+ remove_proc_entry("victim_bits", sbi->s_proc);
+ remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
+ }
+ kobject_del(&sbi->s_kobj);
+}
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 501c283..d0ab533 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* f2fs IO tracer
*
* Copyright (c) 2014 Motorola Mobility
* Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
@@ -59,7 +56,7 @@ void f2fs_trace_pid(struct page *page)
pid_t pid = task_pid_nr(current);
void *p;
- page->private = pid;
+ set_page_private(page, (unsigned long)pid);
retry:
if (radix_tree_preload(GFP_NOFS))
@@ -144,7 +141,7 @@ static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
results[ret] = iter.index;
- if (++ret == PIDVEC_SIZE)
+ if (++ret == max_items)
break;
}
return ret;
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
index 67db24a..e8075fc 100644
--- a/fs/f2fs/trace.h
+++ b/fs/f2fs/trace.h
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* f2fs IO tracer
*
* Copyright (c) 2014 Motorola Mobility
* Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef __F2FS_TRACE_H__
#define __F2FS_TRACE_H__
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 3e1c028..848a785 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/xattr.c
*
@@ -13,10 +14,6 @@
* suggestion of Luka Renko <luka.renko@hermes.si>.
* xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
* Red Hat Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/rwsem.h>
#include <linux/f2fs_fs.h>
@@ -37,9 +34,6 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
@@ -62,9 +56,6 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
@@ -100,13 +91,23 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
const char *name, const void *value,
size_t size, int flags)
{
+ unsigned char old_advise = F2FS_I(inode)->i_advise;
+ unsigned char new_advise;
+
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
- F2FS_I(inode)->i_advise |= *(char *)value;
- f2fs_mark_inode_dirty_sync(inode);
+ new_advise = *(char *)value;
+ if (new_advise & ~FADVISE_MODIFIABLE_BITS)
+ return -EINVAL;
+
+ new_advise = new_advise & FADVISE_MODIFIABLE_BITS;
+ new_advise |= old_advise & ~FADVISE_MODIFIABLE_BITS;
+
+ F2FS_I(inode)->i_advise = new_advise;
+ f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
@@ -217,55 +218,166 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
return entry;
}
-static int read_all_xattrs(struct inode *inode, struct page *ipage,
- void **base_addr)
+static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
+ void *base_addr, void **last_addr, int index,
+ size_t len, const char *name)
+{
+ struct f2fs_xattr_entry *entry;
+ unsigned int inline_size = inline_xattr_size(inode);
+ void *max_addr = base_addr + inline_size;
+
+ list_for_each_xattr(entry, base_addr) {
+ if ((void *)entry + sizeof(__u32) > max_addr ||
+ (void *)XATTR_NEXT_ENTRY(entry) > max_addr) {
+ *last_addr = entry;
+ return NULL;
+ }
+ if (entry->e_name_index != index)
+ continue;
+ if (entry->e_name_len != len)
+ continue;
+ if (!memcmp(entry->e_name, name, len))
+ break;
+ }
+
+ /* inline xattr header or entry across max inline xattr size */
+ if (IS_XATTR_LAST_ENTRY(entry) &&
+ (void *)entry + sizeof(__u32) > max_addr) {
+ *last_addr = entry;
+ return NULL;
+ }
+ return entry;
+}
+
+static int read_inline_xattr(struct inode *inode, struct page *ipage,
+ void *txattr_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_xattr_header *header;
- size_t size = PAGE_SIZE, inline_size = 0;
- void *txattr_addr;
- int err;
+ unsigned int inline_size = inline_xattr_size(inode);
+ struct page *page = NULL;
+ void *inline_addr;
- inline_size = inline_xattr_size(inode);
+ if (ipage) {
+ inline_addr = inline_xattr_addr(inode, ipage);
+ } else {
+ page = f2fs_get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
- txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO);
+ inline_addr = inline_xattr_addr(inode, page);
+ }
+ memcpy(txattr_addr, inline_addr, inline_size);
+ f2fs_put_page(page, 1);
+
+ return 0;
+}
+
+static int read_xattr_block(struct inode *inode, void *txattr_addr)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ unsigned int inline_size = inline_xattr_size(inode);
+ struct page *xpage;
+ void *xattr_addr;
+
+ /* The inode already has an extended attribute block. */
+ xpage = f2fs_get_node_page(sbi, xnid);
+ if (IS_ERR(xpage))
+ return PTR_ERR(xpage);
+
+ xattr_addr = page_address(xpage);
+ memcpy(txattr_addr + inline_size, xattr_addr, VALID_XATTR_BLOCK_SIZE);
+ f2fs_put_page(xpage, 1);
+
+ return 0;
+}
+
+static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
+ unsigned int index, unsigned int len,
+ const char *name, struct f2fs_xattr_entry **xe,
+ void **base_addr, int *base_size)
+{
+ void *cur_addr, *txattr_addr, *last_addr = NULL;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
+ unsigned int inline_size = inline_xattr_size(inode);
+ int err = 0;
+
+ if (!size && !inline_size)
+ return -ENODATA;
+
+ *base_size = inline_size + size + XATTR_PADDING_SIZE;
+ txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS);
if (!txattr_addr)
return -ENOMEM;
/* read from inline xattr */
if (inline_size) {
- struct page *page = NULL;
- void *inline_addr;
+ err = read_inline_xattr(inode, ipage, txattr_addr);
+ if (err)
+ goto out;
- if (ipage) {
- inline_addr = inline_xattr_addr(ipage);
- } else {
- page = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(page)) {
- err = PTR_ERR(page);
- goto fail;
- }
- inline_addr = inline_xattr_addr(page);
+ *xe = __find_inline_xattr(inode, txattr_addr, &last_addr,
+ index, len, name);
+ if (*xe) {
+ *base_size = inline_size;
+ goto check;
}
- memcpy(txattr_addr, inline_addr, inline_size);
- f2fs_put_page(page, 1);
}
/* read from xattr node block */
- if (F2FS_I(inode)->i_xattr_nid) {
- struct page *xpage;
- void *xattr_addr;
+ if (xnid) {
+ err = read_xattr_block(inode, txattr_addr);
+ if (err)
+ goto out;
+ }
- /* The inode already has an extended attribute block. */
- xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
- if (IS_ERR(xpage)) {
- err = PTR_ERR(xpage);
+ if (last_addr)
+ cur_addr = XATTR_HDR(last_addr) - 1;
+ else
+ cur_addr = txattr_addr;
+
+ *xe = __find_xattr(cur_addr, index, len, name);
+check:
+ if (IS_XATTR_LAST_ENTRY(*xe)) {
+ err = -ENODATA;
+ goto out;
+ }
+
+ *base_addr = txattr_addr;
+ return 0;
+out:
+ kvfree(txattr_addr);
+ return err;
+}
+
+static int read_all_xattrs(struct inode *inode, struct page *ipage,
+ void **base_addr)
+{
+ struct f2fs_xattr_header *header;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ unsigned int size = VALID_XATTR_BLOCK_SIZE;
+ unsigned int inline_size = inline_xattr_size(inode);
+ void *txattr_addr;
+ int err;
+
+ txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode),
+ inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS);
+ if (!txattr_addr)
+ return -ENOMEM;
+
+ /* read from inline xattr */
+ if (inline_size) {
+ err = read_inline_xattr(inode, ipage, txattr_addr);
+ if (err)
goto fail;
- }
+ }
- xattr_addr = page_address(xpage);
- memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
- f2fs_put_page(xpage, 1);
+ /* read from xattr node block */
+ if (xnid) {
+ err = read_xattr_block(inode, txattr_addr);
+ if (err)
+ goto fail;
}
header = XATTR_HDR(txattr_addr);
@@ -278,7 +390,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage,
*base_addr = txattr_addr;
return 0;
fail:
- kzfree(txattr_addr);
+ kvfree(txattr_addr);
return err;
}
@@ -286,85 +398,92 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
void *txattr_addr, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- size_t inline_size = 0;
+ size_t inline_size = inline_xattr_size(inode);
+ struct page *in_page = NULL;
void *xattr_addr;
+ void *inline_addr = NULL;
struct page *xpage;
nid_t new_nid = 0;
- int err;
-
- inline_size = inline_xattr_size(inode);
+ int err = 0;
if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
- if (!alloc_nid(sbi, &new_nid))
+ if (!f2fs_alloc_nid(sbi, &new_nid))
return -ENOSPC;
/* write to inline xattr */
if (inline_size) {
- struct page *page = NULL;
- void *inline_addr;
-
if (ipage) {
- inline_addr = inline_xattr_addr(ipage);
- f2fs_wait_on_page_writeback(ipage, NODE, true);
- set_page_dirty(ipage);
+ inline_addr = inline_xattr_addr(inode, ipage);
} else {
- page = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(page)) {
- alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(page);
+ in_page = f2fs_get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(in_page)) {
+ f2fs_alloc_nid_failed(sbi, new_nid);
+ return PTR_ERR(in_page);
}
- inline_addr = inline_xattr_addr(page);
- f2fs_wait_on_page_writeback(page, NODE, true);
+ inline_addr = inline_xattr_addr(inode, in_page);
}
- memcpy(inline_addr, txattr_addr, inline_size);
- f2fs_put_page(page, 1);
+ f2fs_wait_on_page_writeback(ipage ? ipage : in_page,
+ NODE, true, true);
/* no need to use xattr node block */
if (hsize <= inline_size) {
- err = truncate_xattr_node(inode, ipage);
- alloc_nid_failed(sbi, new_nid);
- return err;
+ err = f2fs_truncate_xattr_node(inode);
+ f2fs_alloc_nid_failed(sbi, new_nid);
+ if (err) {
+ f2fs_put_page(in_page, 1);
+ return err;
+ }
+ memcpy(inline_addr, txattr_addr, inline_size);
+ set_page_dirty(ipage ? ipage : in_page);
+ goto in_page_out;
}
}
/* write to xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
- xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+ xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
- alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(xpage);
+ err = PTR_ERR(xpage);
+ f2fs_alloc_nid_failed(sbi, new_nid);
+ goto in_page_out;
}
f2fs_bug_on(sbi, new_nid);
- f2fs_wait_on_page_writeback(xpage, NODE, true);
+ f2fs_wait_on_page_writeback(xpage, NODE, true, true);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
- xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
+ xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
- alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(xpage);
+ err = PTR_ERR(xpage);
+ f2fs_alloc_nid_failed(sbi, new_nid);
+ goto in_page_out;
}
- alloc_nid_done(sbi, new_nid);
+ f2fs_alloc_nid_done(sbi, new_nid);
}
-
xattr_addr = page_address(xpage);
- memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
- sizeof(struct node_footer));
- set_page_dirty(xpage);
- f2fs_put_page(xpage, 1);
- /* need to checkpoint during fsync */
- F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
- return 0;
+ if (inline_size)
+ memcpy(inline_addr, txattr_addr, inline_size);
+ memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
+
+ if (inline_size)
+ set_page_dirty(ipage ? ipage : in_page);
+ set_page_dirty(xpage);
+
+ f2fs_put_page(xpage, 1);
+in_page_out:
+ f2fs_put_page(in_page, 1);
+ return err;
}
int f2fs_getxattr(struct inode *inode, int index, const char *name,
void *buffer, size_t buffer_size, struct page *ipage)
{
- struct f2fs_xattr_entry *entry;
- void *base_addr;
+ struct f2fs_xattr_entry *entry = NULL;
int error = 0;
- size_t size, len;
+ unsigned int size, len;
+ void *base_addr = NULL;
+ int base_size;
if (name == NULL)
return -EINVAL;
@@ -373,31 +492,32 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
if (len > F2FS_NAME_LEN)
return -ERANGE;
- error = read_all_xattrs(inode, ipage, &base_addr);
+ down_read(&F2FS_I(inode)->i_xattr_sem);
+ error = lookup_all_xattrs(inode, ipage, index, len, name,
+ &entry, &base_addr, &base_size);
+ up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
- entry = __find_xattr(base_addr, index, len, name);
- if (IS_XATTR_LAST_ENTRY(entry)) {
- error = -ENODATA;
- goto cleanup;
- }
-
size = le16_to_cpu(entry->e_value_size);
if (buffer && size > buffer_size) {
error = -ERANGE;
- goto cleanup;
+ goto out;
}
if (buffer) {
char *pval = entry->e_name + entry->e_name_len;
+
+ if (base_size - (pval - (char *)base_addr) < size) {
+ error = -ERANGE;
+ goto out;
+ }
memcpy(buffer, pval, size);
}
error = size;
-
-cleanup:
- kzfree(base_addr);
+out:
+ kvfree(base_addr);
return error;
}
@@ -409,7 +529,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
int error = 0;
size_t rest = buffer_size;
+ down_read(&F2FS_I(inode)->i_xattr_sem);
error = read_all_xattrs(inode, NULL, &base_addr);
+ up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
@@ -423,7 +545,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
if (!handler || (handler->list && !handler->list(dentry)))
continue;
- prefix = handler->prefix ?: handler->name;
+ prefix = xattr_prefix(handler);
prefix_len = strlen(prefix);
size = prefix_len + entry->e_name_len + 1;
if (buffer) {
@@ -441,10 +563,19 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
}
error = buffer_size - rest;
cleanup:
- kzfree(base_addr);
+ kvfree(base_addr);
return error;
}
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+ const void *value, size_t size)
+{
+ void *pval = entry->e_name + entry->e_name_len;
+
+ return (le16_to_cpu(entry->e_value_size) == size) &&
+ !memcmp(pval, value, size);
+}
+
static int __f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *ipage, int flags)
@@ -479,12 +610,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
- if ((flags & XATTR_REPLACE) && !found) {
+ if (found) {
+ if ((flags & XATTR_CREATE)) {
+ error = -EEXIST;
+ goto exit;
+ }
+
+ if (value && f2fs_xattr_value_same(here, value, size))
+ goto exit;
+ } else if ((flags & XATTR_REPLACE)) {
error = -ENODATA;
goto exit;
- } else if ((flags & XATTR_CREATE) && found) {
- error = -EEXIST;
- goto exit;
}
last = here;
@@ -554,11 +690,11 @@ static int __f2fs_setxattr(struct inode *inode, int index,
if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
f2fs_set_encrypted_inode(inode);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (!error && S_ISDIR(inode->i_mode))
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
exit:
- kzfree(base_addr);
+ kvfree(base_addr);
return error;
}
@@ -569,7 +705,11 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
- /* this case is only from init_inode_metadata */
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
+ /* this case is only from f2fs_init_inode_metadata */
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
size, ipage, flags);
@@ -578,7 +718,9 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
f2fs_lock_op(sbi);
/* protect xattr_ver */
down_write(&F2FS_I(inode)->i_sem);
+ down_write(&F2FS_I(inode)->i_xattr_sem);
err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
+ up_write(&F2FS_I(inode)->i_xattr_sem);
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index f990de2..9172ee0 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/xattr.h
*
@@ -9,10 +10,6 @@
* On-disk format of extended attributes for the ext2 filesystem.
*
* (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef __F2FS_XATTR_H__
#define __F2FS_XATTR_H__
@@ -58,10 +55,10 @@ struct f2fs_xattr_entry {
#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1))
#define XATTR_ROUND (3)
-#define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND)
+#define XATTR_ALIGN(size) (((size) + XATTR_ROUND) & ~XATTR_ROUND)
#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \
- entry->e_name_len + le16_to_cpu(entry->e_value_size)))
+ (entry)->e_name_len + le16_to_cpu((entry)->e_value_size)))
#define XATTR_NEXT_ENTRY(entry) ((struct f2fs_xattr_entry *)((char *)(entry) +\
ENTRY_SIZE(entry)))
@@ -72,14 +69,21 @@ struct f2fs_xattr_entry {
for (entry = XATTR_FIRST_ENTRY(addr);\
!IS_XATTR_LAST_ENTRY(entry);\
entry = XATTR_NEXT_ENTRY(entry))
-
-#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \
- sizeof(struct node_footer) - sizeof(__u32))
+#define VALID_XATTR_BLOCK_SIZE (PAGE_SIZE - sizeof(struct node_footer))
+#define XATTR_PADDING_SIZE (sizeof(__u32))
+#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \
+ VALID_XATTR_BLOCK_SIZE)
#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \
sizeof(struct f2fs_xattr_header) - \
sizeof(struct f2fs_xattr_entry))
+#define MAX_INLINE_XATTR_SIZE \
+ (DEF_ADDRS_PER_INODE - \
+ F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \
+ DEF_INLINE_RESERVED_SIZE - \
+ MIN_INLINE_DENTRY_SIZE / sizeof(__le32))
+
/*
* On-disk structure of f2fs_xattr
* We use inline xattrs space + 1 block for xattr.
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f978ae2..bc3e9fa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2168,7 +2168,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
(dirtytime && (inode->i_state & I_DIRTY_INODE)))
return;
- if (unlikely(block_dump))
+ if (unlikely(block_dump > 1))
block_dump___mark_inode_dirty(inode);
spin_lock(&inode->i_lock);
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 7dca743..940c683 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -44,6 +44,7 @@ void set_fs_pwd(struct fs_struct *fs, const struct path *path)
if (old_pwd.dentry)
path_put(&old_pwd);
}
+EXPORT_SYMBOL(set_fs_pwd);
static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
{
@@ -89,6 +90,7 @@ void free_fs_struct(struct fs_struct *fs)
path_put(&fs->pwd);
kmem_cache_free(fs_cachep, fs);
}
+EXPORT_SYMBOL(free_fs_struct);
void exit_fs(struct task_struct *tsk)
{
@@ -127,6 +129,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
}
return fs;
}
+EXPORT_SYMBOL_GPL(copy_fs_struct);
int unshare_fs_struct(void)
{
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 37e0c31d..5eb2e24 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -329,7 +329,7 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
config = 0;
rcu_read_lock();
- confkey = user_key_payload(key);
+ confkey = user_key_payload_rcu(key);
if (!confkey) {
/* key was revoked */
rcu_read_unlock();
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 33c90e2..a5b0480 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -13,12 +13,14 @@
#include <linux/poll.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
+#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/pipe_fs_i.h>
#include <linux/swap.h>
#include <linux/splice.h>
+#include <linux/freezer.h>
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
@@ -475,7 +477,9 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
* Either request is already in userspace, or it was forced.
* Wait it out.
*/
- wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags));
+ while (!test_bit(FR_FINISHED, &req->flags))
+ wait_event_freezable(req->waitq,
+ test_bit(FR_FINISHED, &req->flags));
}
static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
@@ -1917,6 +1921,12 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
cs->move_pages = 0;
err = copy_out_args(cs, &req->out, nbytes);
+ if (req->in.h.opcode == FUSE_CANONICAL_PATH) {
+ char *path = (char *)req->out.args[0].value;
+
+ path[req->out.args[0].size - 1] = 0;
+ req->out.h.error = kern_path(path, 0, req->canonical_path);
+ }
fuse_copy_finish(cs);
spin_lock(&fpq->lock);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 9af23f4..531ecc7 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -263,6 +263,50 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
goto out;
}
+/*
+ * Get the canonical path. Since we must translate to a path, this must be done
+ * in the context of the userspace daemon, however, the userspace daemon cannot
+ * look up paths on its own. Instead, we handle the lookup as a special case
+ * inside of the write request.
+ */
+static void fuse_dentry_canonical_path(const struct path *path, struct path *canonical_path) {
+ struct inode *inode = path->dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_req *req;
+ int err;
+ char *path_name;
+
+ req = fuse_get_req(fc, 1);
+ err = PTR_ERR(req);
+ if (IS_ERR(req))
+ goto default_path;
+
+ path_name = (char*)__get_free_page(GFP_KERNEL);
+ if (!path_name) {
+ fuse_put_request(fc, req);
+ goto default_path;
+ }
+
+ req->in.h.opcode = FUSE_CANONICAL_PATH;
+ req->in.h.nodeid = get_node_id(inode);
+ req->in.numargs = 0;
+ req->out.numargs = 1;
+ req->out.args[0].size = PATH_MAX;
+ req->out.args[0].value = path_name;
+ req->canonical_path = canonical_path;
+ req->out.argvar = 1;
+ fuse_request_send(fc, req);
+ err = req->out.h.error;
+ fuse_put_request(fc, req);
+ free_page((unsigned long)path_name);
+ if (!err)
+ return;
+default_path:
+ canonical_path->dentry = path->dentry;
+ canonical_path->mnt = path->mnt;
+ path_get(canonical_path);
+}
+
static int invalid_nodeid(u64 nodeid)
{
return !nodeid || nodeid == FUSE_ROOT_ID;
@@ -285,11 +329,13 @@ const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
.d_init = fuse_dentry_init,
.d_release = fuse_dentry_release,
+ .d_canonical_path = fuse_dentry_canonical_path,
};
const struct dentry_operations fuse_root_dentry_operations = {
.d_init = fuse_dentry_init,
.d_release = fuse_dentry_release,
+ .d_canonical_path = fuse_dentry_canonical_path,
};
int fuse_valid_type(int m)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index cea2317..7e44fd3 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -846,9 +846,9 @@ struct fuse_fill_data {
unsigned nr_pages;
};
-static int fuse_readpages_fill(void *_data, struct page *page)
+static int fuse_readpages_fill(struct file *_data, struct page *page)
{
- struct fuse_fill_data *data = _data;
+ struct fuse_fill_data *data = (struct fuse_fill_data *)_data;
struct fuse_req *req = data->req;
struct inode *inode = data->inode;
struct fuse_conn *fc = get_fuse_conn(inode);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index f84dd6d..89c33c3 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -256,7 +256,7 @@ struct fuse_io_priv {
#define FUSE_IO_PRIV_SYNC(f) \
{ \
- .refcnt = { ATOMIC_INIT(1) }, \
+ .refcnt = KREF_INIT(1), \
.async = 0, \
.file = f, \
}
@@ -368,6 +368,9 @@ struct fuse_req {
/** Inode used in the request or NULL */
struct inode *inode;
+ /** Path used for completing d_canonical_path */
+ struct path *canonical_path;
+
/** AIO control block */
struct fuse_io_priv *io;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 7a9b106..c32fe64 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -30,7 +30,7 @@ static struct kmem_cache *fuse_inode_cachep;
struct list_head fuse_conn_list;
DEFINE_MUTEX(fuse_mutex);
-static int set_global_limit(const char *val, struct kernel_param *kp);
+static int set_global_limit(const char *val, const struct kernel_param *kp);
unsigned max_user_bgreq;
module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
@@ -830,7 +830,7 @@ static void sanitize_global_limit(unsigned *limit)
*limit = (1 << 16) - 1;
}
-static int set_global_limit(const char *val, struct kernel_param *kp)
+static int set_global_limit(const char *val, const struct kernel_param *kp)
{
int rv;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 5a6f52e..0283ee0 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -268,22 +268,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
for(i = 0; i < nr_pages; i++) {
struct page *page = pvec->pages[i];
- /*
- * At this point, the page may be truncated or
- * invalidated (changing page->mapping to NULL), or
- * even swizzled back from swapper_space to tmpfs file
- * mapping. However, page->index will not change
- * because we have a reference on the page.
- */
- if (page->index > end) {
- /*
- * can't be range_cyclic (1st pass) because
- * end == -1 in that case.
- */
- ret = 1;
- break;
- }
-
*done_index = page->index;
lock_page(page);
@@ -401,8 +385,8 @@ static int gfs2_write_cache_jdata(struct address_space *mapping,
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag);
if (nr_pages == 0)
break;
@@ -511,7 +495,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
*
*/
-static int __gfs2_readpage(void *file, struct page *page)
+static int __gfs2_readpage(struct file *file, struct page *page)
{
struct gfs2_inode *ip = GFS2_I(page->mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
diff --git a/fs/inode.c b/fs/inode.c
index 0d993ce..2fe03a5 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1782,7 +1782,7 @@ int dentry_needs_remove_privs(struct dentry *dentry)
return mask;
}
-static int __remove_privs(struct dentry *dentry, int kill)
+static int __remove_privs(struct vfsmount *mnt, struct dentry *dentry, int kill)
{
struct iattr newattrs;
@@ -1791,7 +1791,7 @@ static int __remove_privs(struct dentry *dentry, int kill)
* Note we call this on write, so notify_change will not
* encounter any conflicting delegations:
*/
- return notify_change(dentry, &newattrs, NULL);
+ return notify_change2(mnt, dentry, &newattrs, NULL);
}
/*
@@ -1818,7 +1818,7 @@ int file_remove_privs(struct file *file)
if (kill < 0)
return kill;
if (kill)
- error = __remove_privs(dentry, kill);
+ error = __remove_privs(file->f_path.mnt, dentry, kill);
if (!error)
inode_has_no_xattr(inode);
diff --git a/fs/internal.h b/fs/internal.h
index 8b7143b..3e58863 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -88,9 +88,11 @@ extern struct file *get_empty_filp(void);
* super.c
*/
extern int do_remount_sb(struct super_block *, int, void *, int);
+extern int do_remount_sb2(struct vfsmount *, struct super_block *, int,
+ void *, int);
extern bool trylock_super(struct super_block *sb);
extern struct dentry *mount_fs(struct file_system_type *,
- int, const char *, void *);
+ int, const char *, struct vfsmount *, void *);
extern struct super_block *user_get_super(dev_t);
/*
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index cf4c636..0b9d23b 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -468,7 +468,7 @@ static void kernfs_drain(struct kernfs_node *kn)
rwsem_release(&kn->dep_map, 1, _RET_IP_);
}
- kernfs_unmap_bin_file(kn);
+ kernfs_drain_open_files(kn);
mutex_lock(&kernfs_mutex);
}
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index d6512cd..27358c8 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -708,7 +708,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
if (error)
goto err_free;
- ((struct seq_file *)file->private_data)->private = of;
+ of->seq_file = file->private_data;
+ of->seq_file->private = of;
/* seq_file clears PWRITE unconditionally, restore it if WRITE */
if (file->f_mode & FMODE_WRITE)
@@ -717,13 +718,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
/* make sure we have open node struct */
error = kernfs_get_open_node(kn, of);
if (error)
- goto err_close;
+ goto err_seq_release;
+
+ if (ops->open) {
+ /* nobody has access to @of yet, skip @of->mutex */
+ error = ops->open(of);
+ if (error)
+ goto err_put_node;
+ }
/* open succeeded, put active references */
kernfs_put_active(kn);
return 0;
-err_close:
+err_put_node:
+ kernfs_put_open_node(kn, of);
+err_seq_release:
seq_release(inode, file);
err_free:
kfree(of->prealloc_buf);
@@ -733,11 +743,41 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
return error;
}
+/* used from release/drain to ensure that ->release() is called exactly once */
+static void kernfs_release_file(struct kernfs_node *kn,
+ struct kernfs_open_file *of)
+{
+ /*
+ * @of is guaranteed to have no other file operations in flight and
+ * we just want to synchronize release and drain paths.
+ * @kernfs_open_file_mutex is enough. @of->mutex can't be used
+ * here because drain path may be called from places which can
+ * cause circular dependency.
+ */
+ lockdep_assert_held(&kernfs_open_file_mutex);
+
+ if (!of->released) {
+ /*
+ * A file is never detached without being released and we
+ * need to be able to release files which are deactivated
+ * and being drained. Don't use kernfs_ops().
+ */
+ kn->attr.ops->release(of);
+ of->released = true;
+ }
+}
+
static int kernfs_fop_release(struct inode *inode, struct file *filp)
{
struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
struct kernfs_open_file *of = kernfs_of(filp);
+ if (kn->flags & KERNFS_HAS_RELEASE) {
+ mutex_lock(&kernfs_open_file_mutex);
+ kernfs_release_file(kn, of);
+ mutex_unlock(&kernfs_open_file_mutex);
+ }
+
kernfs_put_open_node(kn, of);
seq_release(inode, filp);
kfree(of->prealloc_buf);
@@ -746,12 +786,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp)
return 0;
}
-void kernfs_unmap_bin_file(struct kernfs_node *kn)
+void kernfs_drain_open_files(struct kernfs_node *kn)
{
struct kernfs_open_node *on;
struct kernfs_open_file *of;
- if (!(kn->flags & KERNFS_HAS_MMAP))
+ if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
return;
spin_lock_irq(&kernfs_open_node_lock);
@@ -763,10 +803,17 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn)
return;
mutex_lock(&kernfs_open_file_mutex);
+
list_for_each_entry(of, &on->files, list) {
struct inode *inode = file_inode(of->file);
- unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+ if (kn->flags & KERNFS_HAS_MMAP)
+ unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+ if (kn->flags & KERNFS_HAS_RELEASE)
+ kernfs_release_file(kn, of);
}
+
mutex_unlock(&kernfs_open_file_mutex);
kernfs_put_open_node(kn, NULL);
@@ -786,26 +833,35 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn)
* to see if it supports poll (Neither 'poll' nor 'select' return
* an appropriate error code). When in doubt, set a suitable timeout value.
*/
+unsigned int kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
+{
+ struct kernfs_node *kn = of->file->f_path.dentry->d_fsdata;
+ struct kernfs_open_node *on = kn->attr.open;
+
+ poll_wait(of->file, &on->poll, wait);
+
+ if (of->event != atomic_read(&on->event))
+ return DEFAULT_POLLMASK|POLLERR|POLLPRI;
+
+ return DEFAULT_POLLMASK;
+}
+
static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
{
struct kernfs_open_file *of = kernfs_of(filp);
struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
- struct kernfs_open_node *on = kn->attr.open;
+ unsigned int ret;
if (!kernfs_get_active(kn))
- goto trigger;
+ return DEFAULT_POLLMASK|POLLERR|POLLPRI;
- poll_wait(filp, &on->poll, wait);
+ if (kn->attr.ops->poll)
+ ret = kn->attr.ops->poll(of, wait);
+ else
+ ret = kernfs_generic_poll(of, wait);
kernfs_put_active(kn);
-
- if (of->event != atomic_read(&on->event))
- goto trigger;
-
- return DEFAULT_POLLMASK;
-
- trigger:
- return DEFAULT_POLLMASK|POLLERR|POLLPRI;
+ return ret;
}
static void kernfs_notify_workfn(struct work_struct *work)
@@ -965,6 +1021,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
kn->flags |= KERNFS_HAS_SEQ_SHOW;
if (ops->mmap)
kn->flags |= KERNFS_HAS_MMAP;
+ if (ops->release)
+ kn->flags |= KERNFS_HAS_RELEASE;
rc = kernfs_add_one(kn);
if (rc) {
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index bfd551b..3100987 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -104,7 +104,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
*/
extern const struct file_operations kernfs_file_fops;
-void kernfs_unmap_bin_file(struct kernfs_node *kn);
+void kernfs_drain_open_files(struct kernfs_node *kn);
/*
* symlink.c
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index c19123d..d484c63 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -600,7 +600,7 @@ static struct ctl_table nlm_sysctl_root[] = {
*/
#define param_set_min_max(name, type, which_strtol, min, max) \
-static int param_set_##name(const char *val, struct kernel_param *kp) \
+static int param_set_##name(const char *val, const struct kernel_param *kp) \
{ \
char *endp; \
__typeof__(type) num = which_strtol(val, &endp, 0); \
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index a8329cc..fdf844f 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -34,9 +34,9 @@ static int sync_request(struct page *page, struct block_device *bdev, int op)
return submit_bio_wait(&bio);
}
-static int bdev_readpage(void *_sb, struct page *page)
+static int bdev_readpage(struct file *_sb, struct page *page)
{
- struct super_block *sb = _sb;
+ struct super_block *sb = (struct super_block *)_sb;
struct block_device *bdev = logfs_super(sb)->s_bdev;
int err;
diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c
index b76a62b..9ec8e8f 100644
--- a/fs/logfs/dev_mtd.c
+++ b/fs/logfs/dev_mtd.c
@@ -122,9 +122,9 @@ static void logfs_mtd_sync(struct super_block *sb)
mtd_sync(mtd);
}
-static int logfs_mtd_readpage(void *_sb, struct page *page)
+static int logfs_mtd_readpage(struct file *_sb, struct page *page)
{
- struct super_block *sb = _sb;
+ struct super_block *sb = (struct super_block *)_sb;
int err;
err = logfs_mtd_read(sb, page->index << PAGE_SHIFT, PAGE_SIZE,
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index c87ea52..8ddacc1 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -174,7 +174,7 @@ static struct page *logfs_get_dd_page(struct inode *dir, struct dentry *dentry)
if (!logfs_exist_block(dir, index))
continue;
page = read_cache_page(dir->i_mapping, index,
- (filler_t *)logfs_readpage, NULL);
+ logfs_readpage, NULL);
if (IS_ERR(page))
return page;
dd = kmap_atomic(page);
@@ -306,7 +306,7 @@ static int logfs_readdir(struct file *file, struct dir_context *ctx)
continue;
}
page = read_cache_page(dir->i_mapping, pos,
- (filler_t *)logfs_readpage, NULL);
+ logfs_readpage, NULL);
if (IS_ERR(page))
return PTR_ERR(page);
dd = kmap(page);
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 27d040e..1a7c0b0 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -151,7 +151,7 @@ struct logfs_device_ops {
struct page *(*find_first_sb)(struct super_block *sb, u64 *ofs);
struct page *(*find_last_sb)(struct super_block *sb, u64 *ofs);
int (*write_sb)(struct super_block *sb, struct page *page);
- int (*readpage)(void *_sb, struct page *page);
+ int (*readpage)(struct file *_sb, struct page *page);
void (*writeseg)(struct super_block *sb, u64 ofs, size_t len);
int (*erase)(struct super_block *sb, loff_t ofs, size_t len,
int ensure_write);
diff --git a/fs/mpage.c b/fs/mpage.c
index e2ea442..d4e17c8 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -31,6 +31,14 @@
#include <linux/cleancache.h>
#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/android_fs.h>
+
+EXPORT_TRACEPOINT_SYMBOL(android_fs_datawrite_start);
+EXPORT_TRACEPOINT_SYMBOL(android_fs_datawrite_end);
+EXPORT_TRACEPOINT_SYMBOL(android_fs_dataread_start);
+EXPORT_TRACEPOINT_SYMBOL(android_fs_dataread_end);
+
/*
* I/O completion handler for multipage BIOs.
*
@@ -48,6 +56,16 @@ static void mpage_end_io(struct bio *bio)
struct bio_vec *bv;
int i;
+ if (trace_android_fs_dataread_end_enabled() &&
+ (bio_data_dir(bio) == READ)) {
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
+
+ if (first_page != NULL)
+ trace_android_fs_dataread_end(first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size);
+ }
+
bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
page_endio(page, op_is_write(bio_op(bio)), bio->bi_error);
@@ -58,6 +76,24 @@ static void mpage_end_io(struct bio *bio)
static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio)
{
+ if (trace_android_fs_dataread_start_enabled() && (op == REQ_OP_READ)) {
+ struct page *first_page = bio->bi_io_vec[0].bv_page;
+
+ if (first_page != NULL) {
+ char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+ path = android_fstrace_get_pathname(pathbuf,
+ MAX_TRACE_PATHBUF_LEN,
+ first_page->mapping->host);
+ trace_android_fs_dataread_start(
+ first_page->mapping->host,
+ page_offset(first_page),
+ bio->bi_iter.bi_size,
+ current->pid,
+ path,
+ current->comm);
+ }
+ }
bio->bi_end_io = mpage_end_io;
bio_set_op_attrs(bio, op, op_flags);
guard_bio_eod(op, bio);
diff --git a/fs/namei.c b/fs/namei.c
index 0953281..d2ab786 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -376,9 +376,11 @@ EXPORT_SYMBOL(generic_permission);
* flag in inode->i_opflags, that says "this has not special
* permission function, use the fast case".
*/
-static inline int do_inode_permission(struct inode *inode, int mask)
+static inline int do_inode_permission(struct vfsmount *mnt, struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
+ if (likely(mnt && inode->i_op->permission2))
+ return inode->i_op->permission2(mnt, inode, mask);
if (likely(inode->i_op->permission))
return inode->i_op->permission(inode, mask);
@@ -402,7 +404,7 @@ static inline int do_inode_permission(struct inode *inode, int mask)
* This does not check for a read-only file system. You probably want
* inode_permission().
*/
-int __inode_permission(struct inode *inode, int mask)
+int __inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
{
int retval;
@@ -422,7 +424,7 @@ int __inode_permission(struct inode *inode, int mask)
return -EACCES;
}
- retval = do_inode_permission(inode, mask);
+ retval = do_inode_permission(mnt, inode, mask);
if (retval)
return retval;
@@ -430,7 +432,14 @@ int __inode_permission(struct inode *inode, int mask)
if (retval)
return retval;
- return security_inode_permission(inode, mask);
+ retval = security_inode_permission(inode, mask);
+ return retval;
+}
+EXPORT_SYMBOL(__inode_permission2);
+
+int __inode_permission(struct inode *inode, int mask)
+{
+ return __inode_permission2(NULL, inode, mask);
}
EXPORT_SYMBOL(__inode_permission);
@@ -466,14 +475,20 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*/
-int inode_permission(struct inode *inode, int mask)
+int inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
- return __inode_permission(inode, mask);
+ return __inode_permission2(mnt, inode, mask);
+}
+EXPORT_SYMBOL(inode_permission2);
+
+int inode_permission(struct inode *inode, int mask)
+{
+ return inode_permission2(NULL, inode, mask);
}
EXPORT_SYMBOL(inode_permission);
@@ -1707,13 +1722,13 @@ static struct dentry *lookup_slow(const struct qstr *name,
static inline int may_lookup(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
- int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
+ int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
if (unlazy_walk(nd, NULL, 0))
return -ECHILD;
}
- return inode_permission(nd->inode, MAY_EXEC);
+ return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC);
}
static inline int handle_dots(struct nameidata *nd, int type)
@@ -2187,11 +2202,12 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->depth = 0;
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
+ struct vfsmount *mnt = nd->root.mnt;
struct inode *inode = root->d_inode;
if (*s) {
if (!d_can_lookup(root))
return ERR_PTR(-ENOTDIR);
- retval = inode_permission(inode, MAY_EXEC);
+ retval = inode_permission2(mnt, inode, MAY_EXEC);
if (retval)
return ERR_PTR(retval);
}
@@ -2456,6 +2472,7 @@ EXPORT_SYMBOL(vfs_path_lookup);
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
+ * @mnt: mount we are looking up on
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
@@ -2464,7 +2481,7 @@ EXPORT_SYMBOL(vfs_path_lookup);
*
* The caller must hold base->i_mutex.
*/
-struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
+struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len)
{
struct qstr this;
unsigned int c;
@@ -2498,12 +2515,18 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
return ERR_PTR(err);
}
- err = inode_permission(base->d_inode, MAY_EXEC);
+ err = inode_permission2(mnt, base->d_inode, MAY_EXEC);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, 0);
}
+EXPORT_SYMBOL(lookup_one_len2);
+
+struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
+{
+ return lookup_one_len2(name, NULL, base, len);
+}
EXPORT_SYMBOL(lookup_one_len);
/**
@@ -2806,7 +2829,7 @@ EXPORT_SYMBOL(__check_sticky);
* 11. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
-static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
+static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir)
{
struct inode *inode = d_backing_inode(victim);
int error;
@@ -2818,7 +2841,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
BUG_ON(victim->d_parent->d_inode != dir);
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
@@ -2850,7 +2873,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
* 4. We should have write and exec permissions on dir
* 5. We can't do it if dir is immutable (done in permission())
*/
-static inline int may_create(struct inode *dir, struct dentry *child)
+static inline int may_create(struct vfsmount *mnt, struct inode *dir, struct dentry *child)
{
struct user_namespace *s_user_ns;
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
@@ -2862,7 +2885,7 @@ static inline int may_create(struct inode *dir, struct dentry *child)
if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
!kgid_has_mapping(s_user_ns, current_fsgid()))
return -EOVERFLOW;
- return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
}
/*
@@ -2909,10 +2932,10 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
}
EXPORT_SYMBOL(unlock_rename);
-int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool want_excl)
+int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool want_excl)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
@@ -2928,6 +2951,13 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
fsnotify_create(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_create2);
+
+int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+ bool want_excl)
+{
+ return vfs_create2(NULL, dir, dentry, mode, want_excl);
+}
EXPORT_SYMBOL(vfs_create);
bool may_open_dev(const struct path *path)
@@ -2939,6 +2969,7 @@ bool may_open_dev(const struct path *path)
static int may_open(struct path *path, int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
+ struct vfsmount *mnt = path->mnt;
struct inode *inode = dentry->d_inode;
int error;
@@ -2963,7 +2994,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
break;
}
- error = inode_permission(inode, MAY_OPEN | acc_mode);
+ error = inode_permission2(mnt, inode, MAY_OPEN | acc_mode);
if (error)
return error;
@@ -2998,7 +3029,7 @@ static int handle_truncate(struct file *filp)
if (!error)
error = security_path_truncate(path);
if (!error) {
- error = do_truncate(path->dentry, 0,
+ error = do_truncate2(path->mnt, path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
filp);
}
@@ -3025,7 +3056,7 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
!kgid_has_mapping(s_user_ns, current_fsgid()))
return -EOVERFLOW;
- error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(dir->mnt, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
@@ -3464,7 +3495,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
goto out;
dir = path.dentry->d_inode;
/* we want directory to be writable */
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ error = inode_permission2(nd->path.mnt, dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out2;
if (!dir->i_op->tmpfile) {
@@ -3717,9 +3748,9 @@ inline struct dentry *user_path_create(int dfd, const char __user *pathname,
}
EXPORT_SYMBOL(user_path_create);
-int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+int vfs_mknod2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
@@ -3743,6 +3774,12 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
fsnotify_create(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_mknod2);
+
+int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+{
+ return vfs_mknod2(NULL, dir, dentry, mode, dev);
+}
EXPORT_SYMBOL(vfs_mknod);
static int may_mknod(umode_t mode)
@@ -3785,12 +3822,12 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
goto out;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create(path.dentry->d_inode,dentry,mode,true);
+ error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true);
if (!error)
ima_post_path_mknod(dentry);
break;
case S_IFCHR: case S_IFBLK:
- error = vfs_mknod(path.dentry->d_inode,dentry,mode,
+ error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode,
new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
@@ -3811,9 +3848,9 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
return sys_mknodat(AT_FDCWD, filename, mode, dev);
}
-int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int vfs_mkdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
unsigned max_links = dir->i_sb->s_max_links;
if (error)
@@ -3835,6 +3872,12 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
fsnotify_mkdir(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_mkdir2);
+
+int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ return vfs_mkdir2(NULL, dir, dentry, mode);
+}
EXPORT_SYMBOL(vfs_mkdir);
SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
@@ -3853,7 +3896,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
mode &= ~current_umask();
error = security_path_mkdir(&path, dentry, mode);
if (!error)
- error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+ error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode);
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
@@ -3867,9 +3910,9 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
return sys_mkdirat(AT_FDCWD, pathname, mode);
}
-int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+int vfs_rmdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry)
{
- int error = may_delete(dir, dentry, 1);
+ int error = may_delete(mnt, dir, dentry, 1);
if (error)
return error;
@@ -3904,6 +3947,12 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
d_delete(dentry);
return error;
}
+EXPORT_SYMBOL(vfs_rmdir2);
+
+int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ return vfs_rmdir2(NULL, dir, dentry);
+}
EXPORT_SYMBOL(vfs_rmdir);
static long do_rmdir(int dfd, const char __user *pathname)
@@ -3949,7 +3998,7 @@ static long do_rmdir(int dfd, const char __user *pathname)
error = security_path_rmdir(&path, dentry);
if (error)
goto exit3;
- error = vfs_rmdir(path.dentry->d_inode, dentry);
+ error = vfs_rmdir2(path.mnt, path.dentry->d_inode, dentry);
exit3:
dput(dentry);
exit2:
@@ -3988,10 +4037,10 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*/
-int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+int vfs_unlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
{
struct inode *target = dentry->d_inode;
- int error = may_delete(dir, dentry, 0);
+ int error = may_delete(mnt, dir, dentry, 0);
if (error)
return error;
@@ -4026,6 +4075,12 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
return error;
}
+EXPORT_SYMBOL(vfs_unlink2);
+
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+{
+ return vfs_unlink2(NULL, dir, dentry, delegated_inode);
+}
EXPORT_SYMBOL(vfs_unlink);
/*
@@ -4073,7 +4128,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
error = security_path_unlink(&path, dentry);
if (error)
goto exit2;
- error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
+ error = vfs_unlink2(path.mnt, path.dentry->d_inode, dentry, &delegated_inode);
exit2:
dput(dentry);
}
@@ -4123,9 +4178,9 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname)
return do_unlinkat(AT_FDCWD, pathname);
}
-int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+int vfs_symlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, const char *oldname)
{
- int error = may_create(dir, dentry);
+ int error = may_create(mnt, dir, dentry);
if (error)
return error;
@@ -4142,6 +4197,12 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
fsnotify_create(dir, dentry);
return error;
}
+EXPORT_SYMBOL(vfs_symlink2);
+
+int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+{
+ return vfs_symlink2(NULL, dir, dentry, oldname);
+}
EXPORT_SYMBOL(vfs_symlink);
SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
@@ -4164,7 +4225,7 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
error = security_path_symlink(&path, dentry, from->name);
if (!error)
- error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
+ error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name);
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
@@ -4199,7 +4260,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*/
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+int vfs_link2(struct vfsmount *mnt, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
{
struct inode *inode = old_dentry->d_inode;
unsigned max_links = dir->i_sb->s_max_links;
@@ -4208,7 +4269,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
if (!inode)
return -ENOENT;
- error = may_create(dir, new_dentry);
+ error = may_create(mnt, dir, new_dentry);
if (error)
return error;
@@ -4258,6 +4319,12 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
fsnotify_link(dir, inode, new_dentry);
return error;
}
+EXPORT_SYMBOL(vfs_link2);
+
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+{
+ return vfs_link2(NULL, old_dentry, dir, new_dentry, delegated_inode);
+}
EXPORT_SYMBOL(vfs_link);
/*
@@ -4313,7 +4380,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
- error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
+ error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
out_dput:
done_path_create(&new_path, new_dentry);
if (delegated_inode) {
@@ -4388,7 +4455,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
* ->i_mutex on parents, which works but leads to some truly excessive
* locking].
*/
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int vfs_rename2(struct vfsmount *mnt,
+ struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
struct inode **delegated_inode, unsigned int flags)
{
@@ -4407,19 +4475,19 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (d_real_inode(old_dentry) == d_real_inode(new_dentry))
return 0;
- error = may_delete(old_dir, old_dentry, is_dir);
+ error = may_delete(mnt, old_dir, old_dentry, is_dir);
if (error)
return error;
if (!target) {
- error = may_create(new_dir, new_dentry);
+ error = may_create(mnt, new_dir, new_dentry);
} else {
new_is_dir = d_is_dir(new_dentry);
if (!(flags & RENAME_EXCHANGE))
- error = may_delete(new_dir, new_dentry, is_dir);
+ error = may_delete(mnt, new_dir, new_dentry, is_dir);
else
- error = may_delete(new_dir, new_dentry, new_is_dir);
+ error = may_delete(mnt, new_dir, new_dentry, new_is_dir);
}
if (error)
return error;
@@ -4433,12 +4501,12 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
*/
if (new_dir != old_dir) {
if (is_dir) {
- error = inode_permission(source, MAY_WRITE);
+ error = inode_permission2(mnt, source, MAY_WRITE);
if (error)
return error;
}
if ((flags & RENAME_EXCHANGE) && new_is_dir) {
- error = inode_permission(target, MAY_WRITE);
+ error = inode_permission2(mnt, target, MAY_WRITE);
if (error)
return error;
}
@@ -4515,6 +4583,14 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
return error;
}
+EXPORT_SYMBOL(vfs_rename2);
+
+int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ struct inode **delegated_inode, unsigned int flags)
+{
+ return vfs_rename2(NULL, old_dir, old_dentry, new_dir, new_dentry, delegated_inode, flags);
+}
EXPORT_SYMBOL(vfs_rename);
SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
@@ -4628,7 +4704,7 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
&new_path, new_dentry, flags);
if (error)
goto exit5;
- error = vfs_rename(old_path.dentry->d_inode, old_dentry,
+ error = vfs_rename2(old_path.mnt, old_path.dentry->d_inode, old_dentry,
new_path.dentry->d_inode, new_dentry,
&delegated_inode, flags);
exit5:
@@ -4673,7 +4749,7 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
int vfs_whiteout(struct inode *dir, struct dentry *dentry)
{
- int error = may_create(dir, dentry);
+ int error = may_create(NULL, dir, dentry);
if (error)
return error;
diff --git a/fs/namespace.c b/fs/namespace.c
index 3b20c7f..d7a3289 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -227,6 +227,7 @@ static struct mount *alloc_vfsmnt(const char *name)
mnt->mnt_count = 1;
mnt->mnt_writers = 0;
#endif
+ mnt->mnt.data = NULL;
INIT_HLIST_NODE(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child);
@@ -581,6 +582,7 @@ int sb_prepare_remount_readonly(struct super_block *sb)
static void free_vfsmnt(struct mount *mnt)
{
+ kfree(mnt->mnt.data);
kfree_const(mnt->mnt_devname);
#ifdef CONFIG_SMP
free_percpu(mnt->mnt_pcp);
@@ -984,10 +986,18 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
if (!mnt)
return ERR_PTR(-ENOMEM);
+ if (type->alloc_mnt_data) {
+ mnt->mnt.data = type->alloc_mnt_data();
+ if (!mnt->mnt.data) {
+ mnt_free_id(mnt);
+ free_vfsmnt(mnt);
+ return ERR_PTR(-ENOMEM);
+ }
+ }
if (flags & MS_KERNMOUNT)
mnt->mnt.mnt_flags = MNT_INTERNAL;
- root = mount_fs(type, flags, name, data);
+ root = mount_fs(type, flags, name, &mnt->mnt, data);
if (IS_ERR(root)) {
mnt_free_id(mnt);
free_vfsmnt(mnt);
@@ -1031,6 +1041,14 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
if (!mnt)
return ERR_PTR(-ENOMEM);
+ if (sb->s_op->clone_mnt_data) {
+ mnt->mnt.data = sb->s_op->clone_mnt_data(old->mnt.data);
+ if (!mnt->mnt.data) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+ }
+
if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE))
mnt->mnt_group_id = 0; /* not a peer of original */
else
@@ -2342,8 +2360,14 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
err = change_mount_flags(path->mnt, flags);
else if (!capable(CAP_SYS_ADMIN))
err = -EPERM;
- else
- err = do_remount_sb(sb, flags, data, 0);
+ else {
+ err = do_remount_sb2(path->mnt, sb, flags, data, 0);
+ namespace_lock();
+ lock_mount_hash();
+ propagate_remount(mnt);
+ unlock_mount_hash();
+ namespace_unlock();
+ }
if (!err) {
lock_mount_hash();
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 3d4602d..b5f02f1 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -316,7 +316,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
if (ret < 0)
goto out_up;
- payload = user_key_payload(rkey);
+ payload = user_key_payload_rcu(rkey);
if (IS_ERR_OR_NULL(payload)) {
ret = PTR_ERR(payload);
goto out_up;
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index defc923..67b8000 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -346,7 +346,7 @@ struct nfs_readdesc {
};
static int
-readpage_async_filler(void *data, struct page *page)
+readpage_async_filler(struct file *data, struct page *page)
{
struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
struct nfs_page *new;
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 2e315f9..ac1ec8f 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -2158,8 +2158,8 @@ static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree,
pagevec_init(&pvec, 0);
- while (pagevec_lookup_tag(&pvec, btcache, &index, PAGECACHE_TAG_DIRTY,
- PAGEVEC_SIZE)) {
+ while (pagevec_lookup_tag(&pvec, btcache, &index,
+ PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index f11a3ad..454ee52 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -257,8 +257,7 @@ int nilfs_copy_dirty_pages(struct address_space *dmap,
pagevec_init(&pvec, 0);
repeat:
- if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY,
- PAGEVEC_SIZE))
+ if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY))
return 0;
for (i = 0; i < pagevec_count(&pvec); i++) {
@@ -377,8 +376,8 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
pagevec_init(&pvec, 0);
- while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
- PAGEVEC_SIZE)) {
+ while (pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a92af0e..3dff3d5 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -709,18 +709,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
pagevec_init(&pvec, 0);
repeat:
if (unlikely(index > last) ||
- !pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
- min_t(pgoff_t, last - index,
- PAGEVEC_SIZE - 1) + 1))
+ !pagevec_lookup_range_tag(&pvec, mapping, &index, last,
+ PAGECACHE_TAG_DIRTY))
return ndirties;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct buffer_head *bh, *head;
struct page *page = pvec.pages[i];
- if (unlikely(page->index > last))
- break;
-
lock_page(page);
if (!page_has_buffers(page))
create_empty_buffers(page, i_blocksize(inode), 0);
@@ -757,8 +753,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
pagevec_init(&pvec, 0);
- while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
- PAGEVEC_SIZE)) {
+ while (pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
index e5f911b..390827f 100644
--- a/fs/notify/fanotify/Kconfig
+++ b/fs/notify/fanotify/Kconfig
@@ -1,7 +1,6 @@
config FANOTIFY
bool "Filesystem wide access notification"
select FSNOTIFY
- select ANON_INODES
default n
---help---
Say Y here to enable fanotify support. fanotify is a file access
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 258e8f6..cef9885 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -498,7 +498,7 @@ static int fanotify_find_path(int dfd, const char __user *filename,
}
/* you can only watch an inode if you have read permissions on it */
- ret = inode_permission(path->dentry->d_inode, MAY_READ);
+ ret = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ);
if (ret)
path_put(path);
out:
diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
index b981fc0..0161c74 100644
--- a/fs/notify/inotify/Kconfig
+++ b/fs/notify/inotify/Kconfig
@@ -1,6 +1,5 @@
config INOTIFY_USER
bool "Inotify support for userspace"
- select ANON_INODES
select FSNOTIFY
default y
---help---
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 69d1ea3..4da5c6a 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -337,7 +337,7 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
if (error)
return error;
/* you can only watch an inode if you have read permissions on it */
- error = inode_permission(path->dentry->d_inode, MAY_READ);
+ error = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ);
if (error)
path_put(path);
return error;
@@ -702,6 +702,8 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
struct fsnotify_group *group;
struct inode *inode;
struct path path;
+ struct path alteredpath;
+ struct path *canonical_path = &path;
struct fd f;
int ret;
unsigned flags = 0;
@@ -741,13 +743,22 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
if (ret)
goto fput_and_out;
+ /* support stacked filesystems */
+ if(path.dentry && path.dentry->d_op) {
+ if (path.dentry->d_op->d_canonical_path) {
+ path.dentry->d_op->d_canonical_path(&path, &alteredpath);
+ canonical_path = &alteredpath;
+ path_put(&path);
+ }
+ }
+
/* inode held in place by reference to path; group by fget on fd */
- inode = path.dentry->d_inode;
+ inode = canonical_path->dentry->d_inode;
group = f.file->private_data;
/* create/update an inode mark */
ret = inotify_update_watch(group, inode, mask);
- path_put(&path);
+ path_put(canonical_path);
fput_and_out:
fdput(f);
return ret;
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 1079fae..47e08e4 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -88,13 +88,13 @@ struct workqueue_struct *user_dlm_worker;
*/
#define DLMFS_CAPABILITIES "bast stackglue"
static int param_set_dlmfs_capabilities(const char *val,
- struct kernel_param *kp)
+ const struct kernel_param *kp)
{
printk(KERN_ERR "%s: readonly parameter\n", kp->name);
return -EINVAL;
}
static int param_get_dlmfs_capabilities(char *buffer,
- struct kernel_param *kp)
+ const struct kernel_param *kp)
{
return strlcpy(buffer, DLMFS_CAPABILITIES,
strlen(DLMFS_CAPABILITIES) + 1);
diff --git a/fs/open.c b/fs/open.c
index e17cc79..f2b82c4 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -34,8 +34,8 @@
#include "internal.h"
-int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
- struct file *filp)
+int do_truncate2(struct vfsmount *mnt, struct dentry *dentry, loff_t length,
+ unsigned int time_attrs, struct file *filp)
{
int ret;
struct iattr newattrs;
@@ -60,18 +60,25 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
inode_lock(dentry->d_inode);
/* Note any delegations or leases have already been broken: */
- ret = notify_change(dentry, &newattrs, NULL);
+ ret = notify_change2(mnt, dentry, &newattrs, NULL);
inode_unlock(dentry->d_inode);
return ret;
}
+int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
+ struct file *filp)
+{
+ return do_truncate2(NULL, dentry, length, time_attrs, filp);
+}
long vfs_truncate(const struct path *path, loff_t length)
{
struct inode *inode;
+ struct vfsmount *mnt;
struct dentry *upperdentry;
long error;
inode = path->dentry->d_inode;
+ mnt = path->mnt;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
if (S_ISDIR(inode->i_mode))
@@ -83,7 +90,7 @@ long vfs_truncate(const struct path *path, loff_t length)
if (error)
goto out;
- error = inode_permission(inode, MAY_WRITE);
+ error = inode_permission2(mnt, inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
@@ -117,7 +124,7 @@ long vfs_truncate(const struct path *path, loff_t length)
if (!error)
error = security_path_truncate(path);
if (!error)
- error = do_truncate(path->dentry, length, 0, NULL);
+ error = do_truncate2(mnt, path->dentry, length, 0, NULL);
put_write_and_out:
put_write_access(upperdentry->d_inode);
@@ -166,6 +173,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
+ struct vfsmount *mnt;
struct fd f;
int error;
@@ -182,6 +190,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
small = 0;
dentry = f.file->f_path.dentry;
+ mnt = f.file->f_path.mnt;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
@@ -201,7 +210,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
- error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
+ error = do_truncate2(mnt, dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
@@ -357,6 +366,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
struct cred *override_cred;
struct path path;
struct inode *inode;
+ struct vfsmount *mnt;
int res;
unsigned int lookup_flags = LOOKUP_FOLLOW;
@@ -406,6 +416,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
goto out;
inode = d_backing_inode(path.dentry);
+ mnt = path.mnt;
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
@@ -417,7 +428,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
goto out_path_release;
}
- res = inode_permission(inode, mode | MAY_ACCESS);
+ res = inode_permission2(mnt, inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
@@ -461,7 +472,7 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
@@ -481,6 +492,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
struct fd f = fdget_raw(fd);
struct inode *inode;
+ struct vfsmount *mnt;
int error = -EBADF;
error = -EBADF;
@@ -488,12 +500,13 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
goto out;
inode = file_inode(f.file);
+ mnt = f.file->f_path.mnt;
error = -ENOTDIR;
if (!S_ISDIR(inode->i_mode))
goto out_putf;
- error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
+ error = inode_permission2(mnt, inode, MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &f.file->f_path);
out_putf:
@@ -512,7 +525,7 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
+ error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
@@ -552,7 +565,7 @@ static int chmod_common(const struct path *path, umode_t mode)
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode);
out_unlock:
inode_unlock(inode);
if (delegated_inode) {
@@ -632,7 +645,7 @@ static int chown_common(const struct path *path, uid_t user, gid_t group)
inode_lock(inode);
error = security_path_chown(path, uid, gid);
if (!error)
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 299dbf5..b9661f1 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -421,7 +421,7 @@ int ovl_copy_up(struct dentry *dentry)
dput(parent);
dput(next);
}
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return err;
}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 8546384..7c52993 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -148,7 +148,7 @@ static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
type = ovl_path_real(dentry, &realpath);
old_cred = ovl_override_creds(dentry->d_sb);
err = vfs_getattr(&realpath, stat);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
if (err)
return err;
@@ -482,7 +482,7 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
struct dentry *hardlink)
{
int err;
- const struct cred *old_cred;
+ const struct cred *old_cred, *hold_cred = NULL;
struct cred *override_cred;
err = ovl_copy_up(dentry->d_parent);
@@ -497,14 +497,15 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
override_cred->fsgid = inode->i_gid;
if (!hardlink) {
err = security_dentry_create_files_as(dentry,
- stat->mode, &dentry->d_name, old_cred,
+ stat->mode, &dentry->d_name,
+ old_cred ? old_cred : current_cred(),
override_cred);
if (err) {
put_cred(override_cred);
goto out_revert_creds;
}
}
- put_cred(override_creds(override_cred));
+ hold_cred = override_creds(override_cred);
put_cred(override_cred);
if (!ovl_dentry_is_opaque(dentry))
@@ -515,7 +516,9 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
link, hardlink);
}
out_revert_creds:
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred ?: hold_cred);
+ if (old_cred && hold_cred)
+ put_cred(hold_cred);
if (!err) {
struct inode *realinode = d_inode(ovl_dentry_upper(dentry));
@@ -757,7 +760,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
err = ovl_remove_upper(dentry, is_dir);
else
err = ovl_remove_and_whiteout(dentry, is_dir);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
if (!err) {
if (is_dir)
clear_nlink(dentry->d_inode);
@@ -998,7 +1001,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
out_unlock:
unlock_rename(new_upperdir, old_upperdir);
out_revert_creds:
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
out_drop_write:
ovl_drop_write(old);
out:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 804b346..5b5153b 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -34,7 +34,7 @@ static int ovl_copy_up_truncate(struct dentry *dentry)
stat.size = 0;
err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
}
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
out_dput_parent:
dput(parent);
@@ -91,7 +91,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
inode_lock(upperdentry->d_inode);
old_cred = ovl_override_creds(dentry->d_sb);
err = notify_change(upperdentry, attr, NULL);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
@@ -115,7 +115,7 @@ static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry,
ovl_path_real(dentry, &realpath);
old_cred = ovl_override_creds(dentry->d_sb);
err = vfs_getattr(&realpath, stat);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return err;
}
@@ -147,7 +147,7 @@ int ovl_permission(struct inode *inode, int mask)
mask |= MAY_READ;
}
err = inode_permission(realinode, mask);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return err;
}
@@ -164,7 +164,7 @@ static const char *ovl_get_link(struct dentry *dentry,
old_cred = ovl_override_creds(dentry->d_sb);
p = vfs_get_link(ovl_dentry_real(dentry), done);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return p;
}
@@ -206,7 +206,7 @@ int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
WARN_ON(flags != XATTR_REPLACE);
err = vfs_removexattr(realpath.dentry, name);
}
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
out_drop_write:
ovl_drop_write(dentry);
@@ -223,7 +223,7 @@ int ovl_xattr_get(struct dentry *dentry, const char *name,
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_getxattr(realdentry, name, value, size);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return res;
}
@@ -248,7 +248,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_listxattr(realdentry, list, size);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
if (res <= 0 || size == 0)
return res;
@@ -283,7 +283,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
old_cred = ovl_override_creds(inode->i_sb);
acl = get_acl(realinode, type);
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return acl;
}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index e218e74..83f22da 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -164,6 +164,7 @@ bool ovl_dentry_is_opaque(struct dentry *dentry);
void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque);
bool ovl_is_whiteout(struct dentry *dentry);
const struct cred *ovl_override_creds(struct super_block *sb);
+void ovl_revert_creds(const struct cred *oldcred);
void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
void ovl_inode_update(struct inode *inode, struct inode *upperinode);
struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index a1be6ba..4fcbfd0 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -223,7 +223,7 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
}
inode_unlock(dir->d_inode);
}
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return err;
}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index e7c8ac4..ae1b424 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -31,6 +31,7 @@ struct ovl_config {
char *upperdir;
char *workdir;
bool default_permissions;
+ bool override_creds;
};
/* private information held for overlayfs's superblock */
@@ -266,9 +267,17 @@ const struct cred *ovl_override_creds(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
+ if (!ofs->config.override_creds)
+ return NULL;
return override_creds(ofs->creator_cred);
}
+void ovl_revert_creds(const struct cred *old_cred)
+{
+ if (old_cred)
+ revert_creds(old_cred);
+}
+
static bool ovl_is_opaquedir(struct dentry *dentry)
{
int res;
@@ -584,7 +593,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
ovl_copyattr(realdentry->d_inode, inode);
}
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
oe->opaque = upperopaque;
oe->__upperdentry = upperdentry;
memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
@@ -603,7 +612,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
out_put_upper:
dput(upperdentry);
out:
- revert_creds(old_cred);
+ ovl_revert_creds(old_cred);
return ERR_PTR(err);
}
@@ -656,6 +665,11 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
return err;
}
+static bool __read_mostly ovl_override_creds_def = true;
+module_param_named(override_creds, ovl_override_creds_def, bool, 0644);
+MODULE_PARM_DESC(ovl_override_creds_def,
+ "Use mounter's credentials for accesses");
+
/**
* ovl_show_options
*
@@ -674,6 +688,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
}
if (ufs->config.default_permissions)
seq_puts(m, ",default_permissions");
+ if (ufs->config.override_creds != ovl_override_creds_def)
+ seq_show_option(m, "override_creds",
+ ufs->config.override_creds ? "on" : "off");
return 0;
}
@@ -700,6 +717,8 @@ enum {
OPT_UPPERDIR,
OPT_WORKDIR,
OPT_DEFAULT_PERMISSIONS,
+ OPT_OVERRIDE_CREDS_ON,
+ OPT_OVERRIDE_CREDS_OFF,
OPT_ERR,
};
@@ -708,6 +727,8 @@ static const match_table_t ovl_tokens = {
{OPT_UPPERDIR, "upperdir=%s"},
{OPT_WORKDIR, "workdir=%s"},
{OPT_DEFAULT_PERMISSIONS, "default_permissions"},
+ {OPT_OVERRIDE_CREDS_ON, "override_creds=on"},
+ {OPT_OVERRIDE_CREDS_OFF, "override_creds=off"},
{OPT_ERR, NULL}
};
@@ -738,6 +759,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
{
char *p;
+ config->override_creds = ovl_override_creds_def;
while ((p = ovl_next_opt(&opt)) != NULL) {
int token;
substring_t args[MAX_OPT_ARGS];
@@ -772,6 +794,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
config->default_permissions = true;
break;
+ case OPT_OVERRIDE_CREDS_ON:
+ config->override_creds = true;
+ break;
+
+ case OPT_OVERRIDE_CREDS_OFF:
+ config->override_creds = false;
+ break;
+
default:
pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
return -EINVAL;
@@ -1353,7 +1383,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
ovl_copyattr(realinode, d_inode(root_dentry));
sb->s_root = root_dentry;
-
return 0;
out_free_oe:
diff --git a/fs/pnode.c b/fs/pnode.c
index 64e9a40..b812317 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -608,3 +608,19 @@ int propagate_umount(struct list_head *list)
return 0;
}
+
+void propagate_remount(struct mount *mnt)
+{
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *p = mnt, *m;
+ struct super_block *sb = mnt->mnt.mnt_sb;
+
+ if (!sb->s_op->copy_mnt_data)
+ return;
+ for (p = propagation_next(parent, parent); p;
+ p = propagation_next(p, parent)) {
+ m = __lookup_mnt(&p->mnt, mnt->mnt_mountpoint);
+ if (m)
+ sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data);
+ }
+}
diff --git a/fs/pnode.h b/fs/pnode.h
index dc87e65..a9a6576 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -44,6 +44,7 @@ int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
int propagate_umount(struct list_head *);
int propagate_mount_busy(struct mount *, int);
void propagate_mount_unlock(struct mount *);
+void propagate_remount(struct mount *);
void mnt_release_group_id(struct mount *);
int get_dominating_id(struct mount *mnt, const struct path *root);
unsigned int mnt_get_count(struct mount *mnt);
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 1ade120..08dce22 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -81,3 +81,10 @@
Say Y if you are running any user-space software which takes benefit from
this interface. For example, rkt is such a piece of software.
+
+config PROC_UID
+ bool "Include /proc/uid/ files"
+ default y
+ depends on PROC_FS && RT_MUTEXES
+ help
+ Provides aggregated per-uid information under /proc/uid.
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 12c6922..dea53ba 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -25,6 +25,7 @@
proc-y += namespaces.o
proc-y += self.o
proc-y += thread_self.o
+proc-$(CONFIG_PROC_UID) += uid.o
proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o
proc-$(CONFIG_NET) += proc_net.o
proc-$(CONFIG_PROC_KCORE) += kcore.o
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b9e4183..19bd9ca 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -87,6 +87,7 @@
#include <linux/slab.h>
#include <linux/flex_array.h>
#include <linux/posix-timers.h>
+#include <linux/cpufreq_times.h>
#ifdef CONFIG_HARDWALL
#include <asm/hardwall.h>
#endif
@@ -2925,6 +2926,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
REG("smaps", S_IRUGO, proc_pid_smaps_operations),
+ REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
REG("pagemap", S_IRUSR, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
@@ -2977,6 +2979,9 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("timers", S_IRUGO, proc_timers_operations),
#endif
REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
+#ifdef CONFIG_CPU_FREQ_TIMES
+ ONE("time_in_state", 0444, proc_time_in_state_show),
+#endif
};
static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -2991,6 +2996,15 @@ static const struct file_operations proc_tgid_base_operations = {
.llseek = generic_file_llseek,
};
+struct pid *tgid_pidfd_to_pid(const struct file *file)
+{
+ if (!d_is_dir(file->f_path.dentry) ||
+ (file->f_op != &proc_tgid_base_operations))
+ return ERR_PTR(-EBADF);
+
+ return proc_pid(file_inode(file));
+}
+
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
@@ -3316,6 +3330,7 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
REG("smaps", S_IRUGO, proc_tid_smaps_operations),
+ REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
REG("pagemap", S_IRUSR, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
@@ -3361,6 +3376,9 @@ static const struct pid_entry tid_base_stuff[] = {
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
#endif
+#ifdef CONFIG_CPU_FREQ_TIMES
+ ONE("time_in_state", 0444, proc_time_in_state_show),
+#endif
};
static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a289349..e1b530c 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -457,17 +457,12 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
return inode;
}
-int proc_fill_super(struct super_block *s, void *data, int silent)
+int proc_fill_super(struct super_block *s)
{
- struct pid_namespace *ns = get_pid_ns(s->s_fs_info);
struct inode *root_inode;
int ret;
- if (!proc_parse_options(data, ns))
- return -EINVAL;
-
- /* User space would break if executables or devices appear on proc */
- s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
+ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NODEV;
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c0bdece..fbe699e 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -213,7 +213,7 @@ extern const struct inode_operations proc_pid_link_inode_operations;
extern void proc_init_inodecache(void);
extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
-extern int proc_fill_super(struct super_block *, void *data, int flags);
+extern int proc_fill_super(struct super_block *);
extern void proc_entry_rundown(struct proc_dir_entry *);
/*
@@ -259,6 +259,15 @@ static inline void proc_sys_evict_inode(struct inode *inode,
#endif
/*
+ * uid.c
+ */
+#ifdef CONFIG_PROC_UID
+extern int proc_uid_init(void);
+#else
+static inline void proc_uid_init(void) { }
+#endif
+
+/*
* proc_tty.c
*/
#ifdef CONFIG_TTY
@@ -271,7 +280,6 @@ static inline void proc_tty_init(void) {}
* root.c
*/
extern struct proc_dir_entry proc_root;
-extern int proc_parse_options(char *options, struct pid_namespace *pid);
extern void proc_self_init(void);
extern int proc_remount(struct super_block *, int *, char *);
@@ -279,10 +287,12 @@ extern int proc_remount(struct super_block *, int *, char *);
/*
* task_[no]mmu.c
*/
+struct mem_size_stats;
struct proc_maps_private {
struct inode *inode;
struct task_struct *task;
struct mm_struct *mm;
+ struct mem_size_stats *rollup;
#ifdef CONFIG_MMU
struct vm_area_struct *tail_vma;
#endif
@@ -298,6 +308,7 @@ extern const struct file_operations proc_tid_maps_operations;
extern const struct file_operations proc_pid_numa_maps_operations;
extern const struct file_operations proc_tid_numa_maps_operations;
extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_pid_smaps_rollup_operations;
extern const struct file_operations proc_tid_smaps_operations;
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index aec66e6..e4b986e 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -3,13 +3,11 @@
#include <linux/pid_namespace.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/seq_file.h>
#include <linux/seqlock.h>
#include <linux/time.h>
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
static int loadavg_proc_show(struct seq_file *m, void *v)
{
unsigned long avnrun[3];
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 8d3e484..1d68fcd 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -23,6 +23,21 @@
#include "internal.h"
+static int proc_test_super(struct super_block *sb, void *data)
+{
+ return sb->s_fs_info == data;
+}
+
+static int proc_set_super(struct super_block *sb, void *data)
+{
+ int err = set_anon_super(sb, NULL);
+ if (!err) {
+ struct pid_namespace *ns = (struct pid_namespace *)data;
+ sb->s_fs_info = get_pid_ns(ns);
+ }
+ return err;
+}
+
enum {
Opt_gid, Opt_hidepid, Opt_err,
};
@@ -33,7 +48,7 @@ static const match_table_t tokens = {
{Opt_err, NULL},
};
-int proc_parse_options(char *options, struct pid_namespace *pid)
+static int proc_parse_options(char *options, struct pid_namespace *pid)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -85,16 +100,45 @@ int proc_remount(struct super_block *sb, int *flags, char *data)
static struct dentry *proc_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
+ int err;
+ struct super_block *sb;
struct pid_namespace *ns;
+ char *options;
if (flags & MS_KERNMOUNT) {
- ns = data;
- data = NULL;
+ ns = (struct pid_namespace *)data;
+ options = NULL;
} else {
ns = task_active_pid_ns(current);
+ options = data;
+
+ /* Does the mounter have privilege over the pid namespace? */
+ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
}
- return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
+ sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
+ if (IS_ERR(sb))
+ return ERR_CAST(sb);
+
+ if (!proc_parse_options(options, ns)) {
+ deactivate_locked_super(sb);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!sb->s_root) {
+ err = proc_fill_super(sb);
+ if (err) {
+ deactivate_locked_super(sb);
+ return ERR_PTR(err);
+ }
+
+ sb->s_flags |= MS_ACTIVE;
+ /* User space would break if executables appear on proc */
+ sb->s_iflags |= SB_I_NOEXEC;
+ }
+
+ return dget(sb->s_root);
}
static void proc_kill_sb(struct super_block *sb)
@@ -131,7 +175,7 @@ void __init proc_root_init(void)
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
-
+ proc_uid_init();
#ifdef CONFIG_SYSVIPC
proc_mkdir("sysvipc", NULL);
#endif
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4b207b1..7fe7e0f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -127,6 +127,56 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
}
#endif
+static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
+{
+ const char __user *name = vma_get_anon_name(vma);
+ struct mm_struct *mm = vma->vm_mm;
+
+ unsigned long page_start_vaddr;
+ unsigned long page_offset;
+ unsigned long num_pages;
+ unsigned long max_len = NAME_MAX;
+ int i;
+
+ page_start_vaddr = (unsigned long)name & PAGE_MASK;
+ page_offset = (unsigned long)name - page_start_vaddr;
+ num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE);
+
+ seq_puts(m, "[anon:");
+
+ for (i = 0; i < num_pages; i++) {
+ int len;
+ int write_len;
+ const char *kaddr;
+ long pages_pinned;
+ struct page *page;
+
+ pages_pinned = get_user_pages_remote(current, mm,
+ page_start_vaddr, 1, 0, &page, NULL);
+ if (pages_pinned < 1) {
+ seq_puts(m, "<fault>]");
+ return;
+ }
+
+ kaddr = (const char *)kmap(page);
+ len = min(max_len, PAGE_SIZE - page_offset);
+ write_len = strnlen(kaddr + page_offset, len);
+ seq_write(m, kaddr + page_offset, write_len);
+ kunmap(page);
+ put_page(page);
+
+ /* if strnlen hit a null terminator then we're done */
+ if (write_len != len)
+ break;
+
+ max_len -= len;
+ page_offset = 0;
+ page_start_vaddr += PAGE_SIZE;
+ }
+
+ seq_putc(m, ']');
+}
+
static void vma_stop(struct proc_maps_private *priv)
{
struct mm_struct *mm = priv->mm;
@@ -251,6 +301,7 @@ static int proc_map_release(struct inode *inode, struct file *file)
if (priv->mm)
mmdrop(priv->mm);
+ kfree(priv->rollup);
return seq_release_private(inode, file);
}
@@ -277,6 +328,23 @@ static int is_stack(struct proc_maps_private *priv,
vma->vm_end >= vma->vm_mm->start_stack;
}
+static void show_vma_header_prefix(struct seq_file *m,
+ unsigned long start, unsigned long end,
+ vm_flags_t flags, unsigned long long pgoff,
+ dev_t dev, unsigned long ino)
+{
+ seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+ seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+ start,
+ end,
+ flags & VM_READ ? 'r' : '-',
+ flags & VM_WRITE ? 'w' : '-',
+ flags & VM_EXEC ? 'x' : '-',
+ flags & VM_MAYSHARE ? 's' : 'p',
+ pgoff,
+ MAJOR(dev), MINOR(dev), ino);
+}
+
static void
show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
@@ -300,17 +368,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
/* We don't show the stack guard page in /proc/maps */
start = vma->vm_start;
end = vma->vm_end;
-
- seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
- seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
- start,
- end,
- flags & VM_READ ? 'r' : '-',
- flags & VM_WRITE ? 'w' : '-',
- flags & VM_EXEC ? 'x' : '-',
- flags & VM_MAYSHARE ? 's' : 'p',
- pgoff,
- MAJOR(dev), MINOR(dev), ino);
+ show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino);
/*
* Print the dentry name for named mappings, and a
@@ -341,8 +399,15 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
goto done;
}
- if (is_stack(priv, vma))
+ if (is_stack(priv, vma)) {
name = "[stack]";
+ goto done;
+ }
+
+ if (vma_get_anon_name(vma)) {
+ seq_pad(m, ' ');
+ seq_print_vma_name(m, vma);
+ }
}
done:
@@ -429,6 +494,7 @@ const struct file_operations proc_tid_maps_operations = {
#ifdef CONFIG_PROC_PAGE_MONITOR
struct mem_size_stats {
+ bool first;
unsigned long resident;
unsigned long shared_clean;
unsigned long shared_dirty;
@@ -441,13 +507,15 @@ struct mem_size_stats {
unsigned long swap;
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
+ unsigned long first_vma_start;
u64 pss;
+ u64 pss_locked;
u64 swap_pss;
bool check_shmem_swap;
};
static void smaps_account(struct mem_size_stats *mss, struct page *page,
- bool compound, bool young, bool dirty)
+ bool compound, bool young, bool dirty, bool locked)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
@@ -471,24 +539,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
else
mss->private_clean += size;
mss->pss += (u64)size << PSS_SHIFT;
+ if (locked)
+ mss->pss_locked += (u64)size << PSS_SHIFT;
return;
}
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
+ unsigned long pss = (PAGE_SIZE << PSS_SHIFT);
if (mapcount >= 2) {
if (dirty || PageDirty(page))
mss->shared_dirty += PAGE_SIZE;
else
mss->shared_clean += PAGE_SIZE;
- mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+ mss->pss += pss / mapcount;
+ if (locked)
+ mss->pss_locked += pss / mapcount;
} else {
if (dirty || PageDirty(page))
mss->private_dirty += PAGE_SIZE;
else
mss->private_clean += PAGE_SIZE;
- mss->pss += PAGE_SIZE << PSS_SHIFT;
+ mss->pss += pss;
+ if (locked)
+ mss->pss_locked += pss;
}
}
}
@@ -511,6 +586,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
+ bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
if (pte_present(*pte)) {
@@ -551,7 +627,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
if (!page)
return;
- smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
+ smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -560,6 +636,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
+ bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page;
/* FOLL_DUMP will return -EFAULT on huge zero page */
@@ -574,7 +651,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
/* pass */;
else
VM_BUG_ON_PAGE(1, page);
- smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
+ smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked);
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -714,20 +791,40 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
static int show_smap(struct seq_file *m, void *v, int is_pid)
{
+ struct proc_maps_private *priv = m->private;
struct vm_area_struct *vma = v;
- struct mem_size_stats mss;
+ struct mem_size_stats mss_stack;
+ struct mem_size_stats *mss;
struct mm_walk smaps_walk = {
.pmd_entry = smaps_pte_range,
#ifdef CONFIG_HUGETLB_PAGE
.hugetlb_entry = smaps_hugetlb_range,
#endif
.mm = vma->vm_mm,
- .private = &mss,
};
+ int ret = 0;
+ bool rollup_mode;
+ bool last_vma;
- memset(&mss, 0, sizeof mss);
+ if (priv->rollup) {
+ rollup_mode = true;
+ mss = priv->rollup;
+ if (mss->first) {
+ mss->first_vma_start = vma->vm_start;
+ mss->first = false;
+ }
+ last_vma = !m_next_vma(priv, vma);
+ } else {
+ rollup_mode = false;
+ memset(&mss_stack, 0, sizeof(mss_stack));
+ mss = &mss_stack;
+ }
+
+ smaps_walk.private = mss;
#ifdef CONFIG_SHMEM
+ /* In case of smaps_rollup, reset the value from previous vma */
+ mss->check_shmem_swap = false;
if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
/*
* For shared or readonly shmem mappings we know that all
@@ -743,62 +840,83 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
!(vma->vm_flags & VM_WRITE)) {
- mss.swap = shmem_swapped;
+ mss->swap += shmem_swapped;
} else {
- mss.check_shmem_swap = true;
+ mss->check_shmem_swap = true;
smaps_walk.pte_hole = smaps_pte_hole;
}
}
#endif
-
/* mmap_sem is held in m_start */
walk_page_vma(vma, &smaps_walk);
- show_map_vma(m, vma, is_pid);
+ if (!rollup_mode) {
+ show_map_vma(m, vma, is_pid);
+ } else if (last_vma) {
+ show_vma_header_prefix(
+ m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0);
+ seq_pad(m, ' ');
+ seq_puts(m, "[rollup]\n");
+ } else {
+ ret = SEQ_SKIP;
+ }
- seq_printf(m,
- "Size: %8lu kB\n"
- "Rss: %8lu kB\n"
- "Pss: %8lu kB\n"
- "Shared_Clean: %8lu kB\n"
- "Shared_Dirty: %8lu kB\n"
- "Private_Clean: %8lu kB\n"
- "Private_Dirty: %8lu kB\n"
- "Referenced: %8lu kB\n"
- "Anonymous: %8lu kB\n"
- "AnonHugePages: %8lu kB\n"
- "ShmemPmdMapped: %8lu kB\n"
- "Shared_Hugetlb: %8lu kB\n"
- "Private_Hugetlb: %7lu kB\n"
- "Swap: %8lu kB\n"
- "SwapPss: %8lu kB\n"
- "KernelPageSize: %8lu kB\n"
- "MMUPageSize: %8lu kB\n"
- "Locked: %8lu kB\n",
- (vma->vm_end - vma->vm_start) >> 10,
- mss.resident >> 10,
- (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
- mss.shared_clean >> 10,
- mss.shared_dirty >> 10,
- mss.private_clean >> 10,
- mss.private_dirty >> 10,
- mss.referenced >> 10,
- mss.anonymous >> 10,
- mss.anonymous_thp >> 10,
- mss.shmem_thp >> 10,
- mss.shared_hugetlb >> 10,
- mss.private_hugetlb >> 10,
- mss.swap >> 10,
- (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
- vma_kernel_pagesize(vma) >> 10,
- vma_mmu_pagesize(vma) >> 10,
- (vma->vm_flags & VM_LOCKED) ?
- (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
+ if (!rollup_mode && vma_get_anon_name(vma)) {
+ seq_puts(m, "Name: ");
+ seq_print_vma_name(m, vma);
+ seq_putc(m, '\n');
+ }
- arch_show_smap(m, vma);
- show_smap_vma_flags(m, vma);
+ if (!rollup_mode)
+ seq_printf(m,
+ "Size: %8lu kB\n"
+ "KernelPageSize: %8lu kB\n"
+ "MMUPageSize: %8lu kB\n",
+ (vma->vm_end - vma->vm_start) >> 10,
+ vma_kernel_pagesize(vma) >> 10,
+ vma_mmu_pagesize(vma) >> 10);
+
+ if (!rollup_mode || last_vma)
+ seq_printf(m,
+ "Rss: %8lu kB\n"
+ "Pss: %8lu kB\n"
+ "Shared_Clean: %8lu kB\n"
+ "Shared_Dirty: %8lu kB\n"
+ "Private_Clean: %8lu kB\n"
+ "Private_Dirty: %8lu kB\n"
+ "Referenced: %8lu kB\n"
+ "Anonymous: %8lu kB\n"
+ "AnonHugePages: %8lu kB\n"
+ "ShmemPmdMapped: %8lu kB\n"
+ "Shared_Hugetlb: %8lu kB\n"
+ "Private_Hugetlb: %7lu kB\n"
+ "Swap: %8lu kB\n"
+ "SwapPss: %8lu kB\n"
+ "Locked: %8lu kB\n",
+ mss->resident >> 10,
+ (unsigned long)(mss->pss >> (10 + PSS_SHIFT)),
+ mss->shared_clean >> 10,
+ mss->shared_dirty >> 10,
+ mss->private_clean >> 10,
+ mss->private_dirty >> 10,
+ mss->referenced >> 10,
+ mss->anonymous >> 10,
+ mss->anonymous_thp >> 10,
+ mss->shmem_thp >> 10,
+ mss->shared_hugetlb >> 10,
+ mss->private_hugetlb >> 10,
+ mss->swap >> 10,
+ (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)),
+ (unsigned long)(mss->pss_locked >> (10 + PSS_SHIFT)));
+
+
+ if (!rollup_mode) {
+ arch_show_smap(m, vma);
+ show_smap_vma_flags(m, vma);
+ }
+
m_cache_vma(m, vma);
- return 0;
+ return ret;
}
static int show_pid_smap(struct seq_file *m, void *v)
@@ -830,6 +948,25 @@ static int pid_smaps_open(struct inode *inode, struct file *file)
return do_maps_open(inode, file, &proc_pid_smaps_op);
}
+static int pid_smaps_rollup_open(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ struct proc_maps_private *priv;
+ int ret = do_maps_open(inode, file, &proc_pid_smaps_op);
+
+ if (ret < 0)
+ return ret;
+ seq = file->private_data;
+ priv = seq->private;
+ priv->rollup = kzalloc(sizeof(*priv->rollup), GFP_KERNEL);
+ if (!priv->rollup) {
+ proc_map_release(inode, file);
+ return -ENOMEM;
+ }
+ priv->rollup->first = true;
+ return 0;
+}
+
static int tid_smaps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_tid_smaps_op);
@@ -842,6 +979,13 @@ const struct file_operations proc_pid_smaps_operations = {
.release = proc_map_release,
};
+const struct file_operations proc_pid_smaps_rollup_operations = {
+ .open = pid_smaps_rollup_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = proc_map_release,
+};
+
const struct file_operations proc_tid_smaps_operations = {
.open = tid_smaps_open,
.read = seq_read,
diff --git a/fs/proc/uid.c b/fs/proc/uid.c
new file mode 100644
index 0000000..b2bb085
--- /dev/null
+++ b/fs/proc/uid.c
@@ -0,0 +1,295 @@
+/*
+ * /proc/uid support
+ */
+
+#include <linux/cpufreq_times.h>
+#include <linux/fs.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+static struct proc_dir_entry *proc_uid;
+
+#define UID_HASH_BITS 10
+
+static DECLARE_HASHTABLE(proc_uid_hash_table, UID_HASH_BITS);
+
+/*
+ * use rt_mutex here to avoid priority inversion between high-priority readers
+ * of these files and tasks calling proc_register_uid().
+ */
+static DEFINE_RT_MUTEX(proc_uid_lock); /* proc_uid_hash_table */
+
+struct uid_hash_entry {
+ uid_t uid;
+ struct hlist_node hash;
+};
+
+/* Caller must hold proc_uid_lock */
+static bool uid_hash_entry_exists_locked(uid_t uid)
+{
+ struct uid_hash_entry *entry;
+
+ hash_for_each_possible(proc_uid_hash_table, entry, hash, uid) {
+ if (entry->uid == uid)
+ return true;
+ }
+ return false;
+}
+
+void proc_register_uid(kuid_t kuid)
+{
+ struct uid_hash_entry *entry;
+ bool exists;
+ uid_t uid = from_kuid_munged(current_user_ns(), kuid);
+
+ rt_mutex_lock(&proc_uid_lock);
+ exists = uid_hash_entry_exists_locked(uid);
+ rt_mutex_unlock(&proc_uid_lock);
+ if (exists)
+ return;
+
+ entry = kzalloc(sizeof(struct uid_hash_entry), GFP_KERNEL);
+ if (!entry)
+ return;
+ entry->uid = uid;
+
+ rt_mutex_lock(&proc_uid_lock);
+ if (uid_hash_entry_exists_locked(uid))
+ kfree(entry);
+ else
+ hash_add(proc_uid_hash_table, &entry->hash, uid);
+ rt_mutex_unlock(&proc_uid_lock);
+}
+
+struct uid_entry {
+ const char *name;
+ int len;
+ umode_t mode;
+ const struct inode_operations *iop;
+ const struct file_operations *fop;
+};
+
+#define NOD(NAME, MODE, IOP, FOP) { \
+ .name = (NAME), \
+ .len = sizeof(NAME) - 1, \
+ .mode = MODE, \
+ .iop = IOP, \
+ .fop = FOP, \
+}
+
+#ifdef CONFIG_CPU_FREQ_TIMES
+static const struct file_operations proc_uid_time_in_state_operations = {
+ .open = single_uid_time_in_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
+static const struct uid_entry uid_base_stuff[] = {
+#ifdef CONFIG_CPU_FREQ_TIMES
+ NOD("time_in_state", 0444, NULL, &proc_uid_time_in_state_operations),
+#endif
+};
+
+static const struct inode_operations proc_uid_def_inode_operations = {
+ .setattr = proc_setattr,
+};
+
+static struct inode *proc_uid_make_inode(struct super_block *sb, kuid_t kuid)
+{
+ struct inode *inode;
+
+ inode = new_inode(sb);
+ if (!inode)
+ return NULL;
+
+ inode->i_ino = get_next_ino();
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode->i_op = &proc_uid_def_inode_operations;
+ inode->i_uid = kuid;
+
+ return inode;
+}
+
+static int proc_uident_instantiate(struct inode *dir, struct dentry *dentry,
+ struct task_struct *unused, const void *ptr)
+{
+ const struct uid_entry *u = ptr;
+ struct inode *inode;
+
+ inode = proc_uid_make_inode(dir->i_sb, dir->i_uid);
+ if (!inode)
+ return -ENOENT;
+
+ inode->i_mode = u->mode;
+ if (S_ISDIR(inode->i_mode))
+ set_nlink(inode, 2);
+ if (u->iop)
+ inode->i_op = u->iop;
+ if (u->fop)
+ inode->i_fop = u->fop;
+ d_add(dentry, inode);
+ return 0;
+}
+
+static struct dentry *proc_uid_base_lookup(struct inode *dir,
+ struct dentry *dentry,
+ unsigned int flags)
+{
+ const struct uid_entry *u, *last;
+ unsigned int nents = ARRAY_SIZE(uid_base_stuff);
+
+ if (nents == 0)
+ return ERR_PTR(-ENOENT);
+
+ last = &uid_base_stuff[nents - 1];
+ for (u = uid_base_stuff; u <= last; u++) {
+ if (u->len != dentry->d_name.len)
+ continue;
+ if (!memcmp(dentry->d_name.name, u->name, u->len))
+ break;
+ }
+ if (u > last)
+ return ERR_PTR(-ENOENT);
+
+ return ERR_PTR(proc_uident_instantiate(dir, dentry, NULL, u));
+}
+
+static int proc_uid_base_readdir(struct file *file, struct dir_context *ctx)
+{
+ unsigned int nents = ARRAY_SIZE(uid_base_stuff);
+ const struct uid_entry *u;
+
+ if (!dir_emit_dots(file, ctx))
+ return 0;
+
+ if (ctx->pos >= nents + 2)
+ return 0;
+
+ for (u = uid_base_stuff + (ctx->pos - 2);
+ u < uid_base_stuff + nents; u++) {
+ if (!proc_fill_cache(file, ctx, u->name, u->len,
+ proc_uident_instantiate, NULL, u))
+ break;
+ ctx->pos++;
+ }
+
+ return 0;
+}
+
+static const struct inode_operations proc_uid_base_inode_operations = {
+ .lookup = proc_uid_base_lookup,
+ .setattr = proc_setattr,
+};
+
+static const struct file_operations proc_uid_base_operations = {
+ .read = generic_read_dir,
+ .iterate = proc_uid_base_readdir,
+ .llseek = default_llseek,
+};
+
+static int proc_uid_instantiate(struct inode *dir, struct dentry *dentry,
+ struct task_struct *unused, const void *ptr)
+{
+ unsigned int i, len;
+ nlink_t nlinks;
+ kuid_t *kuid = (kuid_t *)ptr;
+ struct inode *inode = proc_uid_make_inode(dir->i_sb, *kuid);
+
+ if (!inode)
+ return -ENOENT;
+
+ inode->i_mode = S_IFDIR | 0555;
+ inode->i_op = &proc_uid_base_inode_operations;
+ inode->i_fop = &proc_uid_base_operations;
+ inode->i_flags |= S_IMMUTABLE;
+
+ nlinks = 2;
+ len = ARRAY_SIZE(uid_base_stuff);
+ for (i = 0; i < len; ++i) {
+ if (S_ISDIR(uid_base_stuff[i].mode))
+ ++nlinks;
+ }
+ set_nlink(inode, nlinks);
+
+ d_add(dentry, inode);
+
+ return 0;
+}
+
+static int proc_uid_readdir(struct file *file, struct dir_context *ctx)
+{
+ int last_shown, i;
+ unsigned long bkt;
+ struct uid_hash_entry *entry;
+
+ if (!dir_emit_dots(file, ctx))
+ return 0;
+
+ i = 0;
+ last_shown = ctx->pos - 2;
+ rt_mutex_lock(&proc_uid_lock);
+ hash_for_each(proc_uid_hash_table, bkt, entry, hash) {
+ int len;
+ char buf[PROC_NUMBUF];
+
+ if (i < last_shown)
+ continue;
+ len = snprintf(buf, sizeof(buf), "%u", entry->uid);
+ if (!proc_fill_cache(file, ctx, buf, len,
+ proc_uid_instantiate, NULL, &entry->uid))
+ break;
+ i++;
+ ctx->pos++;
+ }
+ rt_mutex_unlock(&proc_uid_lock);
+ return 0;
+}
+
+static struct dentry *proc_uid_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ int result = -ENOENT;
+
+ uid_t uid = name_to_int(&dentry->d_name);
+ bool uid_exists;
+
+ rt_mutex_lock(&proc_uid_lock);
+ uid_exists = uid_hash_entry_exists_locked(uid);
+ rt_mutex_unlock(&proc_uid_lock);
+ if (uid_exists) {
+ kuid_t kuid = make_kuid(current_user_ns(), uid);
+
+ result = proc_uid_instantiate(dir, dentry, NULL, &kuid);
+ }
+ return ERR_PTR(result);
+}
+
+static const struct file_operations proc_uid_operations = {
+ .read = generic_read_dir,
+ .iterate = proc_uid_readdir,
+ .llseek = default_llseek,
+};
+
+static const struct inode_operations proc_uid_inode_operations = {
+ .lookup = proc_uid_lookup,
+ .setattr = proc_setattr,
+};
+
+int __init proc_uid_init(void)
+{
+ proc_uid = proc_mkdir("uid", NULL);
+ if (!proc_uid)
+ return -ENOMEM;
+ proc_uid->proc_iops = &proc_uid_inode_operations;
+ proc_uid->proc_fops = &proc_uid_operations;
+
+ return 0;
+}
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 3f1190d..6863773 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -118,7 +118,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
if (err)
goto out;
show_mnt_opts(m, mnt);
- if (sb->s_op->show_options)
+ if (sb->s_op->show_options2)
+ err = sb->s_op->show_options2(mnt, m, mnt_path.dentry);
+ else if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt_path.dentry);
seq_puts(m, " 0 0\n");
out:
@@ -180,7 +182,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
err = show_sb_opts(m, sb);
if (err)
goto out;
- if (sb->s_op->show_options)
+ if (sb->s_op->show_options2) {
+ err = sb->s_op->show_options2(mnt, m, mnt->mnt_root);
+ } else if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt->mnt_root);
seq_putc(m, '\n');
out:
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index a73959e..9d5dd62 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -561,6 +561,12 @@ static int ramoops_parse_dt(struct platform_device *pdev,
return 0;
}
+void notrace ramoops_console_write_buf(const char *buf, size_t size)
+{
+ struct ramoops_context *cxt = &oops_cxt;
+ persistent_ram_write(cxt->cprz, buf, size);
+}
+
static int ramoops_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
diff --git a/fs/read_write.c b/fs/read_write.c
index 9e1fd4c..9012312 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -23,9 +23,6 @@
#include <asm/uaccess.h>
#include <asm/unistd.h>
-typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
-
const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
@@ -678,7 +675,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
EXPORT_SYMBOL(iov_shorten);
static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
- loff_t *ppos, iter_fn_t fn, int flags)
+ loff_t *ppos, int type, int flags)
{
struct kiocb kiocb;
ssize_t ret;
@@ -695,7 +692,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
kiocb.ki_pos = *ppos;
- ret = fn(&kiocb, iter);
+ if (type == READ)
+ ret = filp->f_op->read_iter(&kiocb, iter);
+ else
+ ret = filp->f_op->write_iter(&kiocb, iter);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
@@ -703,7 +703,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
/* Do it by hand, with file-ops */
static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
- loff_t *ppos, io_fn_t fn, int flags)
+ loff_t *ppos, int type, int flags)
{
ssize_t ret = 0;
@@ -714,7 +714,13 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
struct iovec iovec = iov_iter_iovec(iter);
ssize_t nr;
- nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
+ if (type == READ) {
+ nr = filp->f_op->read(filp, iovec.iov_base,
+ iovec.iov_len, ppos);
+ } else {
+ nr = filp->f_op->write(filp, iovec.iov_base,
+ iovec.iov_len, ppos);
+ }
if (nr < 0) {
if (!ret)
@@ -847,8 +853,6 @@ static ssize_t do_readv_writev(int type, struct file *file,
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
- io_fn_t fn;
- iter_fn_t iter_fn;
ret = import_iovec(type, uvector, nr_segs,
ARRAY_SIZE(iovstack), &iov, &iter);
@@ -862,19 +866,14 @@ static ssize_t do_readv_writev(int type, struct file *file,
if (ret < 0)
goto out;
- if (type == READ) {
- fn = file->f_op->read;
- iter_fn = file->f_op->read_iter;
- } else {
- fn = (io_fn_t)file->f_op->write;
- iter_fn = file->f_op->write_iter;
+ if (type != READ)
file_start_write(file);
- }
- if (iter_fn)
- ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
+ if ((type == READ && file->f_op->read_iter) ||
+ (type == WRITE && file->f_op->write_iter))
+ ret = do_iter_readv_writev(file, &iter, pos, type, flags);
else
- ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
+ ret = do_loop_readv_writev(file, &iter, pos, type, flags);
if (type != READ)
file_end_write(file);
@@ -1072,8 +1071,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
- io_fn_t fn;
- iter_fn_t iter_fn;
ret = compat_import_iovec(type, uvector, nr_segs,
UIO_FASTIOV, &iov, &iter);
@@ -1087,19 +1084,14 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
if (ret < 0)
goto out;
- if (type == READ) {
- fn = file->f_op->read;
- iter_fn = file->f_op->read_iter;
- } else {
- fn = (io_fn_t)file->f_op->write;
- iter_fn = file->f_op->write_iter;
+ if (type != READ)
file_start_write(file);
- }
- if (iter_fn)
- ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
+ if ((type == READ && file->f_op->read_iter) ||
+ (type == WRITE && file->f_op->write_iter))
+ ret = do_iter_readv_writev(file, &iter, pos, type, flags);
else
- ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
+ ret = do_loop_readv_writev(file, &iter, pos, type, flags);
if (type != READ)
file_end_write(file);
diff --git a/fs/sdcardfs/Kconfig b/fs/sdcardfs/Kconfig
new file mode 100644
index 0000000..a1c1033
--- /dev/null
+++ b/fs/sdcardfs/Kconfig
@@ -0,0 +1,13 @@
+config SDCARD_FS
+ tristate "sdcard file system"
+ depends on CONFIGFS_FS
+ default n
+ help
+ Sdcardfs is based on Wrapfs file system.
+
+config SDCARD_FS_FADV_NOACTIVE
+ bool "sdcardfs fadvise noactive support"
+ depends on FADV_NOACTIVE
+ default y
+ help
+ Sdcardfs supports fadvise noactive mode.
diff --git a/fs/sdcardfs/Makefile b/fs/sdcardfs/Makefile
new file mode 100644
index 0000000..b84fbb2
--- /dev/null
+++ b/fs/sdcardfs/Makefile
@@ -0,0 +1,7 @@
+SDCARDFS_VERSION="0.1"
+
+EXTRA_CFLAGS += -DSDCARDFS_VERSION=\"$(SDCARDFS_VERSION)\"
+
+obj-$(CONFIG_SDCARD_FS) += sdcardfs.o
+
+sdcardfs-y := dentry.o file.o inode.o main.o super.o lookup.o mmap.o packagelist.o derived_perm.o
diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c
new file mode 100644
index 0000000..cb573f1
--- /dev/null
+++ b/fs/sdcardfs/dentry.c
@@ -0,0 +1,196 @@
+/*
+ * fs/sdcardfs/dentry.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include "linux/ctype.h"
+
+/*
+ * returns: -ERRNO if error (returned to user)
+ * 0: tell VFS to invalidate dentry
+ * 1: dentry is valid
+ */
+static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ int err = 1;
+ struct path parent_lower_path, lower_path;
+ struct dentry *parent_dentry = NULL;
+ struct dentry *parent_lower_dentry = NULL;
+ struct dentry *lower_cur_parent_dentry = NULL;
+ struct dentry *lower_dentry = NULL;
+ struct inode *inode;
+ struct sdcardfs_inode_data *data;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ spin_lock(&dentry->d_lock);
+ if (IS_ROOT(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ return 1;
+ }
+ spin_unlock(&dentry->d_lock);
+
+ /* check uninitialized obb_dentry and
+ * whether the base obbpath has been changed or not
+ */
+ if (is_obbpath_invalid(dentry)) {
+ return 0;
+ }
+
+ parent_dentry = dget_parent(dentry);
+ sdcardfs_get_lower_path(parent_dentry, &parent_lower_path);
+ sdcardfs_get_real_lower(dentry, &lower_path);
+ parent_lower_dentry = parent_lower_path.dentry;
+ lower_dentry = lower_path.dentry;
+ lower_cur_parent_dentry = dget_parent(lower_dentry);
+
+ if ((lower_dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+ err = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
+ if (err == 0) {
+ goto out;
+ }
+ }
+
+ spin_lock(&lower_dentry->d_lock);
+ if (d_unhashed(lower_dentry)) {
+ spin_unlock(&lower_dentry->d_lock);
+ err = 0;
+ goto out;
+ }
+ spin_unlock(&lower_dentry->d_lock);
+
+ if (parent_lower_dentry != lower_cur_parent_dentry) {
+ err = 0;
+ goto out;
+ }
+
+ if (dentry < lower_dentry) {
+ spin_lock(&dentry->d_lock);
+ spin_lock_nested(&lower_dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ } else {
+ spin_lock(&lower_dentry->d_lock);
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ }
+
+ if (!qstr_case_eq(&dentry->d_name, &lower_dentry->d_name)) {
+ err = 0;
+ }
+
+ if (dentry < lower_dentry) {
+ spin_unlock(&lower_dentry->d_lock);
+ spin_unlock(&dentry->d_lock);
+ } else {
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&lower_dentry->d_lock);
+ }
+ if (!err)
+ goto out;
+
+ /* If our top's inode is gone, we may be out of date */
+ inode = igrab(d_inode(dentry));
+ if (inode) {
+ data = top_data_get(SDCARDFS_I(inode));
+ if (!data || data->abandoned) {
+ err = 0;
+ }
+ if (data)
+ data_put(data);
+ iput(inode);
+ }
+
+out:
+ dput(parent_dentry);
+ dput(lower_cur_parent_dentry);
+ sdcardfs_put_lower_path(parent_dentry, &parent_lower_path);
+ sdcardfs_put_real_lower(dentry, &lower_path);
+ return err;
+}
+
+/* 1 = delete, 0 = cache */
+static int sdcardfs_d_delete(const struct dentry *d)
+{
+ return SDCARDFS_SB(d->d_sb)->options.nocache ? 1 : 0;
+}
+
+static void sdcardfs_d_release(struct dentry *dentry)
+{
+ if (!dentry || !dentry->d_fsdata)
+ return;
+ /* release and reset the lower paths */
+ if (has_graft_path(dentry))
+ sdcardfs_put_reset_orig_path(dentry);
+ sdcardfs_put_reset_lower_path(dentry);
+ free_dentry_private_data(dentry);
+}
+
+static int sdcardfs_hash_ci(const struct dentry *dentry,
+ struct qstr *qstr)
+{
+ /*
+ * This function is copy of vfat_hashi.
+ * FIXME Should we support national language?
+ * Refer to vfat_hashi()
+ * struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
+ */
+ const unsigned char *name;
+ unsigned int len;
+ unsigned long hash;
+
+ name = qstr->name;
+ len = qstr->len;
+
+ hash = init_name_hash(dentry);
+ while (len--)
+ hash = partial_name_hash(tolower(*name++), hash);
+ qstr->hash = end_name_hash(hash);
+
+ return 0;
+}
+
+/*
+ * Case insensitive compare of two vfat names.
+ */
+static int sdcardfs_cmp_ci(const struct dentry *dentry,
+ unsigned int len, const char *str, const struct qstr *name)
+{
+ /* FIXME Should we support national language? */
+
+ if (name->len == len) {
+ if (str_n_case_eq(name->name, str, len))
+ return 0;
+ }
+ return 1;
+}
+
+static void sdcardfs_canonical_path(const struct path *path,
+ struct path *actual_path)
+{
+ sdcardfs_get_real_lower(path->dentry, actual_path);
+}
+
+const struct dentry_operations sdcardfs_ci_dops = {
+ .d_revalidate = sdcardfs_d_revalidate,
+ .d_delete = sdcardfs_d_delete,
+ .d_release = sdcardfs_d_release,
+ .d_hash = sdcardfs_hash_ci,
+ .d_compare = sdcardfs_cmp_ci,
+ .d_canonical_path = sdcardfs_canonical_path,
+};
+
diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c
new file mode 100644
index 0000000..78a669c
--- /dev/null
+++ b/fs/sdcardfs/derived_perm.c
@@ -0,0 +1,477 @@
+/*
+ * fs/sdcardfs/derived_perm.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+/* copy derived state from parent inode */
+static void inherit_derived_state(struct inode *parent, struct inode *child)
+{
+ struct sdcardfs_inode_info *pi = SDCARDFS_I(parent);
+ struct sdcardfs_inode_info *ci = SDCARDFS_I(child);
+
+ ci->data->perm = PERM_INHERIT;
+ ci->data->userid = pi->data->userid;
+ ci->data->d_uid = pi->data->d_uid;
+ ci->data->under_android = pi->data->under_android;
+ ci->data->under_cache = pi->data->under_cache;
+ ci->data->under_obb = pi->data->under_obb;
+}
+
+/* helper function for derived state */
+void setup_derived_state(struct inode *inode, perm_t perm, userid_t userid,
+ uid_t uid)
+{
+ struct sdcardfs_inode_info *info = SDCARDFS_I(inode);
+
+ info->data->perm = perm;
+ info->data->userid = userid;
+ info->data->d_uid = uid;
+ info->data->under_android = false;
+ info->data->under_cache = false;
+ info->data->under_obb = false;
+}
+
+/* While renaming, there is a point where we want the path from dentry,
+ * but the name from newdentry
+ */
+void get_derived_permission_new(struct dentry *parent, struct dentry *dentry,
+ const struct qstr *name)
+{
+ struct sdcardfs_inode_info *info = SDCARDFS_I(d_inode(dentry));
+ struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent));
+ struct sdcardfs_inode_data *parent_data = parent_info->data;
+ appid_t appid;
+ unsigned long user_num;
+ int err;
+ struct qstr q_Android = QSTR_LITERAL("Android");
+ struct qstr q_data = QSTR_LITERAL("data");
+ struct qstr q_sandbox = QSTR_LITERAL("sandbox");
+ struct qstr q_obb = QSTR_LITERAL("obb");
+ struct qstr q_media = QSTR_LITERAL("media");
+ struct qstr q_cache = QSTR_LITERAL("cache");
+
+ /* By default, each inode inherits from its parent.
+ * the properties are maintained on its private fields
+ * because the inode attributes will be modified with that of
+ * its lower inode.
+ * These values are used by our custom permission call instead
+ * of using the inode permissions.
+ */
+
+ inherit_derived_state(d_inode(parent), d_inode(dentry));
+
+ /* Files don't get special labels */
+ if (!S_ISDIR(d_inode(dentry)->i_mode)) {
+ set_top(info, parent_info);
+ return;
+ }
+ /* Derive custom permissions based on parent and current node */
+ switch (parent_data->perm) {
+ case PERM_INHERIT:
+ case PERM_ANDROID_PACKAGE_CACHE:
+ set_top(info, parent_info);
+ break;
+ case PERM_PRE_ROOT:
+ /* Legacy internal layout places users at top level */
+ info->data->perm = PERM_ROOT;
+ err = kstrtoul(name->name, 10, &user_num);
+ if (err)
+ info->data->userid = 0;
+ else
+ info->data->userid = user_num;
+ break;
+ case PERM_ROOT:
+ /* Assume masked off by default. */
+ if (qstr_case_eq(name, &q_Android)) {
+ /* App-specific directories inside; let anyone traverse */
+ info->data->perm = PERM_ANDROID;
+ info->data->under_android = true;
+ } else {
+ set_top(info, parent_info);
+ }
+ break;
+ case PERM_ANDROID:
+ if (qstr_case_eq(name, &q_data)) {
+ /* App-specific directories inside; let anyone traverse */
+ info->data->perm = PERM_ANDROID_DATA;
+ } else if (qstr_case_eq(name, &q_sandbox)) {
+ /* App-specific directories inside; let anyone traverse */
+ info->data->perm = PERM_ANDROID_DATA;
+ } else if (qstr_case_eq(name, &q_obb)) {
+ /* App-specific directories inside; let anyone traverse */
+ info->data->perm = PERM_ANDROID_OBB;
+ info->data->under_obb = true;
+ /* Single OBB directory is always shared */
+ } else if (qstr_case_eq(name, &q_media)) {
+ /* App-specific directories inside; let anyone traverse */
+ info->data->perm = PERM_ANDROID_MEDIA;
+ } else {
+ set_top(info, parent_info);
+ }
+ break;
+ case PERM_ANDROID_OBB:
+ case PERM_ANDROID_DATA:
+ case PERM_ANDROID_MEDIA:
+ info->data->perm = PERM_ANDROID_PACKAGE;
+ appid = get_appid(name->name);
+ if (appid != 0 && !is_excluded(name->name, parent_data->userid))
+ info->data->d_uid =
+ multiuser_get_uid(parent_data->userid, appid);
+ break;
+ case PERM_ANDROID_PACKAGE:
+ if (qstr_case_eq(name, &q_cache)) {
+ info->data->perm = PERM_ANDROID_PACKAGE_CACHE;
+ info->data->under_cache = true;
+ }
+ set_top(info, parent_info);
+ break;
+ }
+}
+
+void get_derived_permission(struct dentry *parent, struct dentry *dentry)
+{
+ get_derived_permission_new(parent, dentry, &dentry->d_name);
+}
+
+static appid_t get_type(const char *name)
+{
+ const char *ext = strrchr(name, '.');
+ appid_t id;
+
+ if (ext && ext[0]) {
+ ext = &ext[1];
+ id = get_ext_gid(ext);
+ return id?:AID_MEDIA_RW;
+ }
+ return AID_MEDIA_RW;
+}
+
+void fixup_lower_ownership(struct dentry *dentry, const char *name)
+{
+ struct path path;
+ struct inode *inode;
+ struct inode *delegated_inode = NULL;
+ int error;
+ struct sdcardfs_inode_info *info;
+ struct sdcardfs_inode_data *info_d;
+ struct sdcardfs_inode_data *info_top;
+ perm_t perm;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ uid_t uid = sbi->options.fs_low_uid;
+ gid_t gid = sbi->options.fs_low_gid;
+ struct iattr newattrs;
+
+ if (!sbi->options.gid_derivation)
+ return;
+
+ info = SDCARDFS_I(d_inode(dentry));
+ info_d = info->data;
+ perm = info_d->perm;
+ if (info_d->under_obb) {
+ perm = PERM_ANDROID_OBB;
+ } else if (info_d->under_cache) {
+ perm = PERM_ANDROID_PACKAGE_CACHE;
+ } else if (perm == PERM_INHERIT) {
+ info_top = top_data_get(info);
+ perm = info_top->perm;
+ data_put(info_top);
+ }
+
+ switch (perm) {
+ case PERM_ROOT:
+ case PERM_ANDROID:
+ case PERM_ANDROID_DATA:
+ case PERM_ANDROID_MEDIA:
+ case PERM_ANDROID_PACKAGE:
+ case PERM_ANDROID_PACKAGE_CACHE:
+ uid = multiuser_get_uid(info_d->userid, uid);
+ break;
+ case PERM_ANDROID_OBB:
+ uid = AID_MEDIA_OBB;
+ break;
+ case PERM_PRE_ROOT:
+ default:
+ break;
+ }
+ switch (perm) {
+ case PERM_ROOT:
+ case PERM_ANDROID:
+ case PERM_ANDROID_DATA:
+ case PERM_ANDROID_MEDIA:
+ if (S_ISDIR(d_inode(dentry)->i_mode))
+ gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW);
+ else
+ gid = multiuser_get_uid(info_d->userid, get_type(name));
+ break;
+ case PERM_ANDROID_OBB:
+ gid = AID_MEDIA_OBB;
+ break;
+ case PERM_ANDROID_PACKAGE:
+ if (uid_is_app(info_d->d_uid))
+ gid = multiuser_get_ext_gid(info_d->d_uid);
+ else
+ gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW);
+ break;
+ case PERM_ANDROID_PACKAGE_CACHE:
+ if (uid_is_app(info_d->d_uid))
+ gid = multiuser_get_ext_cache_gid(info_d->d_uid);
+ else
+ gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW);
+ break;
+ case PERM_PRE_ROOT:
+ default:
+ break;
+ }
+
+ sdcardfs_get_lower_path(dentry, &path);
+ inode = d_inode(path.dentry);
+ if (d_inode(path.dentry)->i_gid.val != gid || d_inode(path.dentry)->i_uid.val != uid) {
+retry_deleg:
+ newattrs.ia_valid = ATTR_GID | ATTR_UID | ATTR_FORCE;
+ newattrs.ia_uid = make_kuid(current_user_ns(), uid);
+ newattrs.ia_gid = make_kgid(current_user_ns(), gid);
+ if (!S_ISDIR(inode->i_mode))
+ newattrs.ia_valid |=
+ ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+ inode_lock(inode);
+ error = security_path_chown(&path, newattrs.ia_uid, newattrs.ia_gid);
+ if (!error)
+ error = notify_change2(path.mnt, path.dentry, &newattrs, &delegated_inode);
+ inode_unlock(inode);
+ if (delegated_inode) {
+ error = break_deleg_wait(&delegated_inode);
+ if (!error)
+ goto retry_deleg;
+ }
+ if (error)
+ pr_debug("sdcardfs: Failed to touch up lower fs gid/uid for %s\n", name);
+ }
+ sdcardfs_put_lower_path(dentry, &path);
+}
+
+static int descendant_may_need_fixup(struct sdcardfs_inode_data *data,
+ struct limit_search *limit)
+{
+ if (data->perm == PERM_ROOT)
+ return (limit->flags & BY_USERID) ?
+ data->userid == limit->userid : 1;
+ if (data->perm == PERM_PRE_ROOT || data->perm == PERM_ANDROID)
+ return 1;
+ return 0;
+}
+
+static int needs_fixup(perm_t perm)
+{
+ if (perm == PERM_ANDROID_DATA || perm == PERM_ANDROID_OBB
+ || perm == PERM_ANDROID_MEDIA)
+ return 1;
+ return 0;
+}
+
+static void __fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit, int depth)
+{
+ struct dentry *child;
+ struct sdcardfs_inode_info *info;
+
+ /*
+ * All paths will terminate their recursion on hitting PERM_ANDROID_OBB,
+ * PERM_ANDROID_MEDIA, or PERM_ANDROID_DATA. This happens at a depth of
+ * at most 3.
+ */
+ WARN(depth > 3, "%s: Max expected depth exceeded!\n", __func__);
+ spin_lock_nested(&dentry->d_lock, depth);
+ if (!d_inode(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ return;
+ }
+ info = SDCARDFS_I(d_inode(dentry));
+
+ if (needs_fixup(info->data->perm)) {
+ list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+ spin_lock_nested(&child->d_lock, depth + 1);
+ if (!(limit->flags & BY_NAME) || qstr_case_eq(&child->d_name, &limit->name)) {
+ if (d_inode(child)) {
+ get_derived_permission(dentry, child);
+ fixup_tmp_permissions(d_inode(child));
+ spin_unlock(&child->d_lock);
+ break;
+ }
+ }
+ spin_unlock(&child->d_lock);
+ }
+ } else if (descendant_may_need_fixup(info->data, limit)) {
+ list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+ __fixup_perms_recursive(child, limit, depth + 1);
+ }
+ }
+ spin_unlock(&dentry->d_lock);
+}
+
+void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit)
+{
+ __fixup_perms_recursive(dentry, limit, 0);
+}
+
+/* main function for updating derived permission */
+inline void update_derived_permission_lock(struct dentry *dentry)
+{
+ struct dentry *parent;
+
+ if (!dentry || !d_inode(dentry)) {
+ pr_err("sdcardfs: %s: invalid dentry\n", __func__);
+ return;
+ }
+ /* FIXME:
+ * 1. need to check whether the dentry is updated or not
+ * 2. remove the root dentry update
+ */
+ if (!IS_ROOT(dentry)) {
+ parent = dget_parent(dentry);
+ if (parent) {
+ get_derived_permission(parent, dentry);
+ dput(parent);
+ }
+ }
+ fixup_tmp_permissions(d_inode(dentry));
+}
+
+int need_graft_path(struct dentry *dentry)
+{
+ int ret = 0;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent));
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ struct qstr obb = QSTR_LITERAL("obb");
+
+ if (!sbi->options.unshared_obb &&
+ parent_info->data->perm == PERM_ANDROID &&
+ qstr_case_eq(&dentry->d_name, &obb)) {
+
+ /* /Android/obb is the base obbpath of DERIVED_UNIFIED */
+ if (!(sbi->options.multiuser == false
+ && parent_info->data->userid == 0)) {
+ ret = 1;
+ }
+ }
+ dput(parent);
+ return ret;
+}
+
+int is_obbpath_invalid(struct dentry *dent)
+{
+ int ret = 0;
+ struct sdcardfs_dentry_info *di = SDCARDFS_D(dent);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb);
+ char *path_buf, *obbpath_s;
+ int need_put = 0;
+ struct path lower_path;
+
+ /* check the base obbpath has been changed.
+ * this routine can check an uninitialized obb dentry as well.
+ * regarding the uninitialized obb, refer to the sdcardfs_mkdir()
+ */
+ spin_lock(&di->lock);
+ if (di->orig_path.dentry) {
+ if (!di->lower_path.dentry) {
+ ret = 1;
+ } else {
+ path_get(&di->lower_path);
+
+ path_buf = kmalloc(PATH_MAX, GFP_ATOMIC);
+ if (!path_buf) {
+ ret = 1;
+ pr_err("sdcardfs: fail to allocate path_buf in %s.\n", __func__);
+ } else {
+ obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX);
+ if (d_unhashed(di->lower_path.dentry) ||
+ !str_case_eq(sbi->obbpath_s, obbpath_s)) {
+ ret = 1;
+ }
+ kfree(path_buf);
+ }
+
+ pathcpy(&lower_path, &di->lower_path);
+ need_put = 1;
+ }
+ }
+ spin_unlock(&di->lock);
+ if (need_put)
+ path_put(&lower_path);
+ return ret;
+}
+
+int is_base_obbpath(struct dentry *dentry)
+{
+ int ret = 0;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent));
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ struct qstr q_obb = QSTR_LITERAL("obb");
+
+ spin_lock(&SDCARDFS_D(dentry)->lock);
+ if (sbi->options.multiuser) {
+ if (parent_info->data->perm == PERM_PRE_ROOT &&
+ qstr_case_eq(&dentry->d_name, &q_obb)) {
+ ret = 1;
+ }
+ } else if (parent_info->data->perm == PERM_ANDROID &&
+ qstr_case_eq(&dentry->d_name, &q_obb)) {
+ ret = 1;
+ }
+ spin_unlock(&SDCARDFS_D(dentry)->lock);
+ return ret;
+}
+
+/* The lower_path will be stored to the dentry's orig_path
+ * and the base obbpath will be copyed to the lower_path variable.
+ * if an error returned, there's no change in the lower_path
+ * returns: -ERRNO if error (0: no error)
+ */
+int setup_obb_dentry(struct dentry *dentry, struct path *lower_path)
+{
+ int err = 0;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ struct path obbpath;
+
+ /* A local obb dentry must have its own orig_path to support rmdir
+ * and mkdir of itself. Usually, we expect that the sbi->obbpath
+ * is avaiable on this stage.
+ */
+ sdcardfs_set_orig_path(dentry, lower_path);
+
+ err = kern_path(sbi->obbpath_s,
+ LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath);
+
+ if (!err) {
+ /* the obbpath base has been found */
+ pathcpy(lower_path, &obbpath);
+ } else {
+ /* if the sbi->obbpath is not available, we can optionally
+ * setup the lower_path with its orig_path.
+ * but, the current implementation just returns an error
+ * because the sdcard daemon also regards this case as
+ * a lookup fail.
+ */
+ pr_info("sdcardfs: the sbi->obbpath is not available\n");
+ }
+ return err;
+}
+
+
diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c
new file mode 100644
index 0000000..271c4c4
--- /dev/null
+++ b/fs/sdcardfs/file.c
@@ -0,0 +1,467 @@
+/*
+ * fs/sdcardfs/file.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+#include <linux/backing-dev.h>
+#endif
+
+static ssize_t sdcardfs_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err;
+ struct file *lower_file;
+ struct dentry *dentry = file->f_path.dentry;
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+ struct backing_dev_info *bdi;
+#endif
+
+ lower_file = sdcardfs_lower_file(file);
+
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+ if (file->f_mode & FMODE_NOACTIVE) {
+ if (!(lower_file->f_mode & FMODE_NOACTIVE)) {
+ bdi = lower_file->f_mapping->backing_dev_info;
+ lower_file->f_ra.ra_pages = bdi->ra_pages * 2;
+ spin_lock(&lower_file->f_lock);
+ lower_file->f_mode |= FMODE_NOACTIVE;
+ spin_unlock(&lower_file->f_lock);
+ }
+ }
+#endif
+
+ err = vfs_read(lower_file, buf, count, ppos);
+ /* update our inode atime upon a successful lower read */
+ if (err >= 0)
+ fsstack_copy_attr_atime(d_inode(dentry),
+ file_inode(lower_file));
+
+ return err;
+}
+
+static ssize_t sdcardfs_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err;
+ struct file *lower_file;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *inode = d_inode(dentry);
+
+ /* check disk space */
+ if (!check_min_free_space(dentry, count, 0)) {
+ pr_err("No minimum free space.\n");
+ return -ENOSPC;
+ }
+
+ lower_file = sdcardfs_lower_file(file);
+ err = vfs_write(lower_file, buf, count, ppos);
+ /* update our inode times+sizes upon a successful lower write */
+ if (err >= 0) {
+ if (sizeof(loff_t) > sizeof(long))
+ inode_lock(inode);
+ fsstack_copy_inode_size(inode, file_inode(lower_file));
+ fsstack_copy_attr_times(inode, file_inode(lower_file));
+ if (sizeof(loff_t) > sizeof(long))
+ inode_unlock(inode);
+ }
+
+ return err;
+}
+
+static int sdcardfs_readdir(struct file *file, struct dir_context *ctx)
+{
+ int err;
+ struct file *lower_file = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+
+ lower_file = sdcardfs_lower_file(file);
+
+ lower_file->f_pos = file->f_pos;
+ err = iterate_dir(lower_file, ctx);
+ file->f_pos = lower_file->f_pos;
+ if (err >= 0) /* copy the atime */
+ fsstack_copy_attr_atime(d_inode(dentry),
+ file_inode(lower_file));
+ return err;
+}
+
+static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ long err = -ENOTTY;
+ struct file *lower_file;
+ const struct cred *saved_cred = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ lower_file = sdcardfs_lower_file(file);
+
+ /* XXX: use vfs_ioctl if/when VFS exports it */
+ if (!lower_file || !lower_file->f_op)
+ goto out;
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(sbi, SDCARDFS_I(file_inode(file))->data);
+ if (!saved_cred) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ if (lower_file->f_op->unlocked_ioctl)
+ err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
+
+ /* some ioctls can change inode attributes (EXT2_IOC_SETFLAGS) */
+ if (!err)
+ sdcardfs_copy_and_fix_attrs(file_inode(file),
+ file_inode(lower_file));
+ revert_fsids(saved_cred);
+out:
+ return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long sdcardfs_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ long err = -ENOTTY;
+ struct file *lower_file;
+ const struct cred *saved_cred = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ lower_file = sdcardfs_lower_file(file);
+
+ /* XXX: use vfs_ioctl if/when VFS exports it */
+ if (!lower_file || !lower_file->f_op)
+ goto out;
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(sbi, SDCARDFS_I(file_inode(file))->data);
+ if (!saved_cred) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ if (lower_file->f_op->compat_ioctl)
+ err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
+
+ revert_fsids(saved_cred);
+out:
+ return err;
+}
+#endif
+
+static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int err = 0;
+ bool willwrite;
+ struct file *lower_file;
+ const struct vm_operations_struct *saved_vm_ops = NULL;
+
+ /* this might be deferred to mmap's writepage */
+ willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags);
+
+ /*
+ * File systems which do not implement ->writepage may use
+ * generic_file_readonly_mmap as their ->mmap op. If you call
+ * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL.
+ * But we cannot call the lower ->mmap op, so we can't tell that
+ * writeable mappings won't work. Therefore, our only choice is to
+ * check if the lower file system supports the ->writepage, and if
+ * not, return EINVAL (the same error that
+ * generic_file_readonly_mmap returns in that case).
+ */
+ lower_file = sdcardfs_lower_file(file);
+ if (willwrite && !lower_file->f_mapping->a_ops->writepage) {
+ err = -EINVAL;
+ pr_err("sdcardfs: lower file system does not support writeable mmap\n");
+ goto out;
+ }
+
+ /*
+ * find and save lower vm_ops.
+ *
+ * XXX: the VFS should have a cleaner way of finding the lower vm_ops
+ */
+ if (!SDCARDFS_F(file)->lower_vm_ops) {
+ err = lower_file->f_op->mmap(lower_file, vma);
+ if (err) {
+ pr_err("sdcardfs: lower mmap failed %d\n", err);
+ goto out;
+ }
+ saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */
+ }
+
+ /*
+ * Next 3 lines are all I need from generic_file_mmap. I definitely
+ * don't want its test for ->readpage which returns -ENOEXEC.
+ */
+ file_accessed(file);
+ vma->vm_ops = &sdcardfs_vm_ops;
+
+ file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */
+ if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */
+ SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops;
+ vma->vm_private_data = file;
+ get_file(lower_file);
+ vma->vm_file = lower_file;
+
+out:
+ return err;
+}
+
+static int sdcardfs_open(struct inode *inode, struct file *file)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct path lower_path;
+ struct dentry *dentry = file->f_path.dentry;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ const struct cred *saved_cred = NULL;
+
+ /* don't open unhashed/deleted files */
+ if (d_unhashed(dentry)) {
+ err = -ENOENT;
+ goto out_err;
+ }
+
+ if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) {
+ err = -EACCES;
+ goto out_err;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(sbi, SDCARDFS_I(inode)->data);
+ if (!saved_cred) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ file->private_data =
+ kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL);
+ if (!SDCARDFS_F(file)) {
+ err = -ENOMEM;
+ goto out_revert_cred;
+ }
+
+ /* open lower object and link sdcardfs's file struct to lower's */
+ sdcardfs_get_lower_path(file->f_path.dentry, &lower_path);
+ lower_file = dentry_open(&lower_path, file->f_flags, current_cred());
+ path_put(&lower_path);
+ if (IS_ERR(lower_file)) {
+ err = PTR_ERR(lower_file);
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file) {
+ sdcardfs_set_lower_file(file, NULL);
+ fput(lower_file); /* fput calls dput for lower_dentry */
+ }
+ } else {
+ sdcardfs_set_lower_file(file, lower_file);
+ }
+
+ if (err)
+ kfree(SDCARDFS_F(file));
+ else
+ sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode));
+
+out_revert_cred:
+ revert_fsids(saved_cred);
+out_err:
+ dput(parent);
+ return err;
+}
+
+static int sdcardfs_flush(struct file *file, fl_owner_t id)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file && lower_file->f_op && lower_file->f_op->flush) {
+ filemap_write_and_wait(file->f_mapping);
+ err = lower_file->f_op->flush(lower_file, id);
+ }
+
+ return err;
+}
+
+/* release all lower object references & free the file info structure */
+static int sdcardfs_file_release(struct inode *inode, struct file *file)
+{
+ struct file *lower_file;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file) {
+ sdcardfs_set_lower_file(file, NULL);
+ fput(lower_file);
+ }
+
+ kfree(SDCARDFS_F(file));
+ return 0;
+}
+
+static int sdcardfs_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ int err;
+ struct file *lower_file;
+ struct path lower_path;
+ struct dentry *dentry = file->f_path.dentry;
+
+ err = __generic_file_fsync(file, start, end, datasync);
+ if (err)
+ goto out;
+
+ lower_file = sdcardfs_lower_file(file);
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_fsync_range(lower_file, start, end, datasync);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out:
+ return err;
+}
+
+static int sdcardfs_fasync(int fd, struct file *file, int flag)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file->f_op && lower_file->f_op->fasync)
+ err = lower_file->f_op->fasync(fd, lower_file, flag);
+
+ return err;
+}
+
+/*
+ * Sdcardfs cannot use generic_file_llseek as ->llseek, because it would
+ * only set the offset of the upper file. So we have to implement our
+ * own method to set both the upper and lower file offsets
+ * consistently.
+ */
+static loff_t sdcardfs_file_llseek(struct file *file, loff_t offset, int whence)
+{
+ int err;
+ struct file *lower_file;
+
+ err = generic_file_llseek(file, offset, whence);
+ if (err < 0)
+ goto out;
+
+ lower_file = sdcardfs_lower_file(file);
+ err = generic_file_llseek(lower_file, offset, whence);
+
+out:
+ return err;
+}
+
+/*
+ * Sdcardfs read_iter, redirect modified iocb to lower read_iter
+ */
+ssize_t sdcardfs_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ int err;
+ struct file *file = iocb->ki_filp, *lower_file;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (!lower_file->f_op->read_iter) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ get_file(lower_file); /* prevent lower_file from being released */
+ iocb->ki_filp = lower_file;
+ err = lower_file->f_op->read_iter(iocb, iter);
+ iocb->ki_filp = file;
+ fput(lower_file);
+ /* update upper inode atime as needed */
+ if (err >= 0 || err == -EIOCBQUEUED)
+ fsstack_copy_attr_atime(file->f_path.dentry->d_inode,
+ file_inode(lower_file));
+out:
+ return err;
+}
+
+/*
+ * Sdcardfs write_iter, redirect modified iocb to lower write_iter
+ */
+ssize_t sdcardfs_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ int err;
+ struct file *file = iocb->ki_filp, *lower_file;
+ struct inode *inode = file->f_path.dentry->d_inode;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (!lower_file->f_op->write_iter) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ get_file(lower_file); /* prevent lower_file from being released */
+ iocb->ki_filp = lower_file;
+ err = lower_file->f_op->write_iter(iocb, iter);
+ iocb->ki_filp = file;
+ fput(lower_file);
+ /* update upper inode times/sizes as needed */
+ if (err >= 0 || err == -EIOCBQUEUED) {
+ if (sizeof(loff_t) > sizeof(long))
+ inode_lock(inode);
+ fsstack_copy_inode_size(inode, file_inode(lower_file));
+ fsstack_copy_attr_times(inode, file_inode(lower_file));
+ if (sizeof(loff_t) > sizeof(long))
+ inode_unlock(inode);
+ }
+out:
+ return err;
+}
+
+const struct file_operations sdcardfs_main_fops = {
+ .llseek = generic_file_llseek,
+ .read = sdcardfs_read,
+ .write = sdcardfs_write,
+ .unlocked_ioctl = sdcardfs_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = sdcardfs_compat_ioctl,
+#endif
+ .mmap = sdcardfs_mmap,
+ .open = sdcardfs_open,
+ .flush = sdcardfs_flush,
+ .release = sdcardfs_file_release,
+ .fsync = sdcardfs_fsync,
+ .fasync = sdcardfs_fasync,
+ .read_iter = sdcardfs_read_iter,
+ .write_iter = sdcardfs_write_iter,
+};
+
+/* trimmed directory options */
+const struct file_operations sdcardfs_dir_fops = {
+ .llseek = sdcardfs_file_llseek,
+ .read = generic_read_dir,
+ .iterate = sdcardfs_readdir,
+ .unlocked_ioctl = sdcardfs_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = sdcardfs_compat_ioctl,
+#endif
+ .open = sdcardfs_open,
+ .release = sdcardfs_file_release,
+ .flush = sdcardfs_flush,
+ .fsync = sdcardfs_fsync,
+ .fasync = sdcardfs_fasync,
+};
diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c
new file mode 100644
index 0000000..63d0736
--- /dev/null
+++ b/fs/sdcardfs/inode.c
@@ -0,0 +1,818 @@
+/*
+ * fs/sdcardfs/inode.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include <linux/fs_struct.h>
+#include <linux/ratelimit.h>
+
+const struct cred *override_fsids(struct sdcardfs_sb_info *sbi,
+ struct sdcardfs_inode_data *data)
+{
+ struct cred *cred;
+ const struct cred *old_cred;
+ uid_t uid;
+
+ cred = prepare_creds();
+ if (!cred)
+ return NULL;
+
+ if (sbi->options.gid_derivation) {
+ if (data->under_obb)
+ uid = AID_MEDIA_OBB;
+ else
+ uid = multiuser_get_uid(data->userid, sbi->options.fs_low_uid);
+ } else {
+ uid = sbi->options.fs_low_uid;
+ }
+ cred->fsuid = make_kuid(&init_user_ns, uid);
+ cred->fsgid = make_kgid(&init_user_ns, sbi->options.fs_low_gid);
+
+ old_cred = override_creds(cred);
+
+ return old_cred;
+}
+
+void revert_fsids(const struct cred *old_cred)
+{
+ const struct cred *cur_cred;
+
+ cur_cred = current->cred;
+ revert_creds(old_cred);
+ put_cred(cur_cred);
+}
+
+static int sdcardfs_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool want_excl)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct vfsmount *lower_dentry_mnt;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+ struct fs_struct *saved_fs;
+ struct fs_struct *copied_fs;
+
+ if (!check_caller_access_to_name(dir, &dentry->d_name)) {
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb),
+ SDCARDFS_I(dir)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_dentry_mnt = lower_path.mnt;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ /* set last 16bytes of mode field to 0664 */
+ mode = (mode & S_IFMT) | 00664;
+
+ /* temporarily change umask for lower fs write */
+ saved_fs = current->fs;
+ copied_fs = copy_fs_struct(current->fs);
+ if (!copied_fs) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+ copied_fs->umask = 0;
+ task_lock(current);
+ current->fs = copied_fs;
+ task_unlock(current);
+
+ err = vfs_create2(lower_dentry_mnt, d_inode(lower_parent_dentry), lower_dentry, mode, want_excl);
+ if (err)
+ goto out;
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path,
+ SDCARDFS_I(dir)->data->userid);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry));
+ fixup_lower_ownership(dentry, dentry->d_name.name);
+
+out:
+ task_lock(current);
+ current->fs = saved_fs;
+ task_unlock(current);
+ free_fs_struct(copied_fs);
+out_unlock:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ revert_fsids(saved_cred);
+out_eacces:
+ return err;
+}
+
+static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct vfsmount *lower_mnt;
+ struct inode *lower_dir_inode = sdcardfs_lower_inode(dir);
+ struct dentry *lower_dir_dentry;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+
+ if (!check_caller_access_to_name(dir, &dentry->d_name)) {
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb),
+ SDCARDFS_I(dir)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_mnt = lower_path.mnt;
+ dget(lower_dentry);
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ err = vfs_unlink2(lower_mnt, lower_dir_inode, lower_dentry, NULL);
+
+ /*
+ * Note: unlinking on top of NFS can cause silly-renamed files.
+ * Trying to delete such files results in EBUSY from NFS
+ * below. Silly-renamed files will get deleted by NFS later on, so
+ * we just need to detect them here and treat such EBUSY errors as
+ * if the upper file was successfully deleted.
+ */
+ if (err == -EBUSY && lower_dentry->d_flags & DCACHE_NFSFS_RENAMED)
+ err = 0;
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, lower_dir_inode);
+ fsstack_copy_inode_size(dir, lower_dir_inode);
+ set_nlink(d_inode(dentry),
+ sdcardfs_lower_inode(d_inode(dentry))->i_nlink);
+ d_inode(dentry)->i_ctime = dir->i_ctime;
+ d_drop(dentry); /* this is needed, else LTP fails (VFS won't do it) */
+out:
+ unlock_dir(lower_dir_dentry);
+ dput(lower_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ revert_fsids(saved_cred);
+out_eacces:
+ return err;
+}
+
+static int touch(char *abs_path, mode_t mode)
+{
+ struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode);
+
+ if (IS_ERR(filp)) {
+ if (PTR_ERR(filp) == -EEXIST) {
+ return 0;
+ } else {
+ pr_err("sdcardfs: failed to open(%s): %ld\n",
+ abs_path, PTR_ERR(filp));
+ return PTR_ERR(filp);
+ }
+ }
+ filp_close(filp, current->files);
+ return 0;
+}
+
+static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ int err;
+ int make_nomedia_in_obb = 0;
+ struct dentry *lower_dentry;
+ struct vfsmount *lower_mnt;
+ struct dentry *lower_parent_dentry = NULL;
+ struct dentry *parent_dentry = NULL;
+ struct path lower_path;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ const struct cred *saved_cred = NULL;
+ struct sdcardfs_inode_data *pd = SDCARDFS_I(dir)->data;
+ int touch_err = 0;
+ struct fs_struct *saved_fs;
+ struct fs_struct *copied_fs;
+ struct qstr q_obb = QSTR_LITERAL("obb");
+ struct qstr q_data = QSTR_LITERAL("data");
+
+ if (!check_caller_access_to_name(dir, &dentry->d_name)) {
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb),
+ SDCARDFS_I(dir)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ /* check disk space */
+ parent_dentry = dget_parent(dentry);
+ if (!check_min_free_space(parent_dentry, 0, 1)) {
+ pr_err("sdcardfs: No minimum free space.\n");
+ err = -ENOSPC;
+ dput(parent_dentry);
+ goto out_revert;
+ }
+ dput(parent_dentry);
+
+ /* the lower_dentry is negative here */
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_mnt = lower_path.mnt;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ /* set last 16bytes of mode field to 0775 */
+ mode = (mode & S_IFMT) | 00775;
+
+ /* temporarily change umask for lower fs write */
+ saved_fs = current->fs;
+ copied_fs = copy_fs_struct(current->fs);
+ if (!copied_fs) {
+ err = -ENOMEM;
+ unlock_dir(lower_parent_dentry);
+ goto out_unlock;
+ }
+ copied_fs->umask = 0;
+ task_lock(current);
+ current->fs = copied_fs;
+ task_unlock(current);
+
+ err = vfs_mkdir2(lower_mnt, d_inode(lower_parent_dentry), lower_dentry, mode);
+
+ if (err) {
+ unlock_dir(lower_parent_dentry);
+ goto out;
+ }
+
+ /* if it is a local obb dentry, setup it with the base obbpath */
+ if (need_graft_path(dentry)) {
+
+ err = setup_obb_dentry(dentry, &lower_path);
+ if (err) {
+ /* if the sbi->obbpath is not available, the lower_path won't be
+ * changed by setup_obb_dentry() but the lower path is saved to
+ * its orig_path. this dentry will be revalidated later.
+ * but now, the lower_path should be NULL
+ */
+ sdcardfs_put_reset_lower_path(dentry);
+
+ /* the newly created lower path which saved to its orig_path or
+ * the lower_path is the base obbpath.
+ * therefore, an additional path_get is required
+ */
+ path_get(&lower_path);
+ } else
+ make_nomedia_in_obb = 1;
+ }
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pd->userid);
+ if (err) {
+ unlock_dir(lower_parent_dentry);
+ goto out;
+ }
+
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry));
+ /* update number of links on parent directory */
+ set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink);
+ fixup_lower_ownership(dentry, dentry->d_name.name);
+ unlock_dir(lower_parent_dentry);
+ if ((!sbi->options.multiuser) && (qstr_case_eq(&dentry->d_name, &q_obb))
+ && (pd->perm == PERM_ANDROID) && (pd->userid == 0))
+ make_nomedia_in_obb = 1;
+
+ /* When creating /Android/data and /Android/obb, mark them as .nomedia */
+ if (make_nomedia_in_obb ||
+ ((pd->perm == PERM_ANDROID)
+ && (qstr_case_eq(&dentry->d_name, &q_data)))) {
+ revert_fsids(saved_cred);
+ saved_cred = override_fsids(sbi,
+ SDCARDFS_I(d_inode(dentry))->data);
+ if (!saved_cred) {
+ pr_err("sdcardfs: failed to set up .nomedia in %s: %d\n",
+ lower_path.dentry->d_name.name,
+ -ENOMEM);
+ goto out;
+ }
+ set_fs_pwd(current->fs, &lower_path);
+ touch_err = touch(".nomedia", 0664);
+ if (touch_err) {
+ pr_err("sdcardfs: failed to create .nomedia in %s: %d\n",
+ lower_path.dentry->d_name.name,
+ touch_err);
+ goto out;
+ }
+ }
+out:
+ task_lock(current);
+ current->fs = saved_fs;
+ task_unlock(current);
+
+ free_fs_struct(copied_fs);
+out_unlock:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out_revert:
+ revert_fsids(saved_cred);
+out_eacces:
+ return err;
+}
+
+static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ struct dentry *lower_dentry;
+ struct dentry *lower_dir_dentry;
+ struct vfsmount *lower_mnt;
+ int err;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+
+ if (!check_caller_access_to_name(dir, &dentry->d_name)) {
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb),
+ SDCARDFS_I(dir)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry
+ * the dentry on the original path should be deleted.
+ */
+ sdcardfs_get_real_lower(dentry, &lower_path);
+
+ lower_dentry = lower_path.dentry;
+ lower_mnt = lower_path.mnt;
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ err = vfs_rmdir2(lower_mnt, d_inode(lower_dir_dentry), lower_dentry);
+ if (err)
+ goto out;
+
+ d_drop(dentry); /* drop our dentry on success (why not VFS's job?) */
+ if (d_inode(dentry))
+ clear_nlink(d_inode(dentry));
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
+
+out:
+ unlock_dir(lower_dir_dentry);
+ sdcardfs_put_real_lower(dentry, &lower_path);
+ revert_fsids(saved_cred);
+out_eacces:
+ return err;
+}
+
+/*
+ * The locking rules in sdcardfs_rename are complex. We could use a simpler
+ * superblock-level name-space lock for renames and copy-ups.
+ */
+static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
+{
+ int err = 0;
+ struct dentry *lower_old_dentry = NULL;
+ struct dentry *lower_new_dentry = NULL;
+ struct dentry *lower_old_dir_dentry = NULL;
+ struct dentry *lower_new_dir_dentry = NULL;
+ struct vfsmount *lower_mnt = NULL;
+ struct dentry *trap = NULL;
+ struct path lower_old_path, lower_new_path;
+ const struct cred *saved_cred = NULL;
+
+ if (flags)
+ return -EINVAL;
+
+ if (!check_caller_access_to_name(old_dir, &old_dentry->d_name) ||
+ !check_caller_access_to_name(new_dir, &new_dentry->d_name)) {
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(old_dir->i_sb),
+ SDCARDFS_I(new_dir)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ sdcardfs_get_real_lower(old_dentry, &lower_old_path);
+ sdcardfs_get_lower_path(new_dentry, &lower_new_path);
+ lower_old_dentry = lower_old_path.dentry;
+ lower_new_dentry = lower_new_path.dentry;
+ lower_mnt = lower_old_path.mnt;
+ lower_old_dir_dentry = dget_parent(lower_old_dentry);
+ lower_new_dir_dentry = dget_parent(lower_new_dentry);
+
+ trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+ /* source should not be ancestor of target */
+ if (trap == lower_old_dentry) {
+ err = -EINVAL;
+ goto out;
+ }
+ /* target should not be ancestor of source */
+ if (trap == lower_new_dentry) {
+ err = -ENOTEMPTY;
+ goto out;
+ }
+
+ err = vfs_rename2(lower_mnt,
+ d_inode(lower_old_dir_dentry), lower_old_dentry,
+ d_inode(lower_new_dir_dentry), lower_new_dentry,
+ NULL, 0);
+ if (err)
+ goto out;
+
+ /* Copy attrs from lower dir, but i_uid/i_gid */
+ sdcardfs_copy_and_fix_attrs(new_dir, d_inode(lower_new_dir_dentry));
+ fsstack_copy_inode_size(new_dir, d_inode(lower_new_dir_dentry));
+
+ if (new_dir != old_dir) {
+ sdcardfs_copy_and_fix_attrs(old_dir, d_inode(lower_old_dir_dentry));
+ fsstack_copy_inode_size(old_dir, d_inode(lower_old_dir_dentry));
+ }
+ get_derived_permission_new(new_dentry->d_parent, old_dentry, &new_dentry->d_name);
+ fixup_tmp_permissions(d_inode(old_dentry));
+ fixup_lower_ownership(old_dentry, new_dentry->d_name.name);
+ d_invalidate(old_dentry); /* Can't fixup ownership recursively :( */
+out:
+ unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+ dput(lower_old_dir_dentry);
+ dput(lower_new_dir_dentry);
+ sdcardfs_put_real_lower(old_dentry, &lower_old_path);
+ sdcardfs_put_lower_path(new_dentry, &lower_new_path);
+ revert_fsids(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct path lower_path;
+ /* XXX readlink does not requires overriding credential */
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ if (!d_inode(lower_dentry)->i_op ||
+ !d_inode(lower_dentry)->i_op->readlink) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = d_inode(lower_dentry)->i_op->readlink(lower_dentry,
+ buf, bufsiz);
+ if (err < 0)
+ goto out;
+ fsstack_copy_attr_atime(d_inode(dentry), d_inode(lower_dentry));
+
+out:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ return err;
+}
+#endif
+
+#if 0
+static const char *sdcardfs_follow_link(struct dentry *dentry, void **cookie)
+{
+ char *buf;
+ int len = PAGE_SIZE, err;
+ mm_segment_t old_fs;
+
+ /* This is freed by the put_link method assuming a successful call. */
+ buf = kmalloc(len, GFP_KERNEL);
+ if (!buf) {
+ buf = ERR_PTR(-ENOMEM);
+ return buf;
+ }
+
+ /* read the symlink, and then we will follow it */
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = sdcardfs_readlink(dentry, buf, len);
+ set_fs(old_fs);
+ if (err < 0) {
+ kfree(buf);
+ buf = ERR_PTR(err);
+ } else {
+ buf[err] = '\0';
+ }
+ return *cookie = buf;
+}
+#endif
+
+static int sdcardfs_permission_wrn(struct inode *inode, int mask)
+{
+ WARN_RATELIMIT(1, "sdcardfs does not support permission. Use permission2.\n");
+ return -EINVAL;
+}
+
+void copy_attrs(struct inode *dest, const struct inode *src)
+{
+ dest->i_mode = src->i_mode;
+ dest->i_uid = src->i_uid;
+ dest->i_gid = src->i_gid;
+ dest->i_rdev = src->i_rdev;
+ dest->i_atime = src->i_atime;
+ dest->i_mtime = src->i_mtime;
+ dest->i_ctime = src->i_ctime;
+ dest->i_blkbits = src->i_blkbits;
+ dest->i_flags = src->i_flags;
+#ifdef CONFIG_FS_POSIX_ACL
+ dest->i_acl = src->i_acl;
+#endif
+#ifdef CONFIG_SECURITY
+ dest->i_security = src->i_security;
+#endif
+}
+
+static int sdcardfs_permission(struct vfsmount *mnt, struct inode *inode, int mask)
+{
+ int err;
+ struct inode tmp;
+ struct sdcardfs_inode_data *top = top_data_get(SDCARDFS_I(inode));
+
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+ if (!top)
+ return -EINVAL;
+
+ /*
+ * Permission check on sdcardfs inode.
+ * Calling process should have AID_SDCARD_RW permission
+ * Since generic_permission only needs i_mode, i_uid,
+ * i_gid, and i_sb, we can create a fake inode to pass
+ * this information down in.
+ *
+ * The underlying code may attempt to take locks in some
+ * cases for features we're not using, but if that changes,
+ * locks must be dealt with to avoid undefined behavior.
+ */
+ copy_attrs(&tmp, inode);
+ tmp.i_uid = make_kuid(&init_user_ns, top->d_uid);
+ tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, inode->i_sb, top));
+ tmp.i_mode = (inode->i_mode & S_IFMT)
+ | get_mode(mnt, SDCARDFS_I(inode), top);
+ data_put(top);
+ tmp.i_sb = inode->i_sb;
+ if (IS_POSIXACL(inode))
+ pr_warn("%s: This may be undefined behavior...\n", __func__);
+ err = generic_permission(&tmp, mask);
+ return err;
+}
+
+static int sdcardfs_setattr_wrn(struct dentry *dentry, struct iattr *ia)
+{
+ WARN_RATELIMIT(1, "sdcardfs does not support setattr. User setattr2.\n");
+ return -EINVAL;
+}
+
+static int sdcardfs_setattr(struct vfsmount *mnt, struct dentry *dentry, struct iattr *ia)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct vfsmount *lower_mnt;
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct path lower_path;
+ struct iattr lower_ia;
+ struct dentry *parent;
+ struct inode tmp;
+ struct dentry tmp_d;
+ struct sdcardfs_inode_data *top;
+
+ const struct cred *saved_cred = NULL;
+
+ inode = d_inode(dentry);
+ top = top_data_get(SDCARDFS_I(inode));
+
+ if (!top)
+ return -EINVAL;
+
+ /*
+ * Permission check on sdcardfs inode.
+ * Calling process should have AID_SDCARD_RW permission
+ * Since generic_permission only needs i_mode, i_uid,
+ * i_gid, and i_sb, we can create a fake inode to pass
+ * this information down in.
+ *
+ * The underlying code may attempt to take locks in some
+ * cases for features we're not using, but if that changes,
+ * locks must be dealt with to avoid undefined behavior.
+ *
+ */
+ copy_attrs(&tmp, inode);
+ tmp.i_uid = make_kuid(&init_user_ns, top->d_uid);
+ tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, dentry->d_sb, top));
+ tmp.i_mode = (inode->i_mode & S_IFMT)
+ | get_mode(mnt, SDCARDFS_I(inode), top);
+ tmp.i_size = i_size_read(inode);
+ data_put(top);
+ tmp.i_sb = inode->i_sb;
+ tmp_d.d_inode = &tmp;
+
+ /*
+ * Check if user has permission to change dentry. We don't check if
+ * this user can change the lower inode: that should happen when
+ * calling notify_change on the lower inode.
+ */
+ /* prepare our own lower struct iattr (with the lower file) */
+ memcpy(&lower_ia, ia, sizeof(lower_ia));
+ /* Allow touch updating timestamps. A previous permission check ensures
+ * we have write access. Changes to mode, owner, and group are ignored
+ */
+ ia->ia_valid |= ATTR_FORCE;
+ err = setattr_prepare(&tmp_d, ia);
+
+ if (!err) {
+ /* check the Android group ID */
+ parent = dget_parent(dentry);
+ if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name))
+ err = -EACCES;
+ dput(parent);
+ }
+
+ if (err)
+ goto out_err;
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dentry->d_sb),
+ SDCARDFS_I(inode)->data);
+ if (!saved_cred)
+ return -ENOMEM;
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_mnt = lower_path.mnt;
+ lower_inode = sdcardfs_lower_inode(inode);
+
+ if (ia->ia_valid & ATTR_FILE)
+ lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file);
+
+ lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE);
+
+ /*
+ * If shrinking, first truncate upper level to cancel writing dirty
+ * pages beyond the new eof; and also if its' maxbytes is more
+ * limiting (fail with -EFBIG before making any change to the lower
+ * level). There is no need to vmtruncate the upper level
+ * afterwards in the other cases: we fsstack_copy_inode_size from
+ * the lower level.
+ */
+ if (ia->ia_valid & ATTR_SIZE) {
+ err = inode_newsize_ok(&tmp, ia->ia_size);
+ if (err) {
+ goto out;
+ }
+ truncate_setsize(inode, ia->ia_size);
+ }
+
+ /*
+ * mode change is for clearing setuid/setgid bits. Allow lower fs
+ * to interpret this in its own way.
+ */
+ if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
+ lower_ia.ia_valid &= ~ATTR_MODE;
+
+ /* notify the (possibly copied-up) lower inode */
+ /*
+ * Note: we use d_inode(lower_dentry), because lower_inode may be
+ * unlinked (no inode->i_sb and i_ino==0. This happens if someone
+ * tries to open(), unlink(), then ftruncate() a file.
+ */
+ inode_lock(d_inode(lower_dentry));
+ err = notify_change2(lower_mnt, lower_dentry, &lower_ia, /* note: lower_ia */
+ NULL);
+ inode_unlock(d_inode(lower_dentry));
+ if (err)
+ goto out;
+
+ /* get attributes from the lower inode and update derived permissions */
+ sdcardfs_copy_and_fix_attrs(inode, lower_inode);
+
+ /*
+ * Not running fsstack_copy_inode_size(inode, lower_inode), because
+ * VFS should update our inode size, and notify_change on
+ * lower_inode should update its size.
+ */
+
+out:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ revert_fsids(saved_cred);
+out_err:
+ return err;
+}
+
+static int sdcardfs_fillattr(struct vfsmount *mnt, struct inode *inode,
+ struct kstat *lower_stat, struct kstat *stat)
+{
+ struct sdcardfs_inode_info *info = SDCARDFS_I(inode);
+ struct sdcardfs_inode_data *top = top_data_get(info);
+ struct super_block *sb = inode->i_sb;
+
+ if (!top)
+ return -EINVAL;
+
+ stat->dev = inode->i_sb->s_dev;
+ stat->ino = inode->i_ino;
+ stat->mode = (inode->i_mode & S_IFMT) | get_mode(mnt, info, top);
+ stat->nlink = inode->i_nlink;
+ stat->uid = make_kuid(&init_user_ns, top->d_uid);
+ stat->gid = make_kgid(&init_user_ns, get_gid(mnt, sb, top));
+ stat->rdev = inode->i_rdev;
+ stat->size = lower_stat->size;
+ stat->atime = lower_stat->atime;
+ stat->mtime = lower_stat->mtime;
+ stat->ctime = lower_stat->ctime;
+ stat->blksize = lower_stat->blksize;
+ stat->blocks = lower_stat->blocks;
+ data_put(top);
+ return 0;
+}
+
+static int sdcardfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct kstat lower_stat;
+ struct path lower_path;
+ struct dentry *parent;
+ int err;
+
+ parent = dget_parent(dentry);
+ if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) {
+ dput(parent);
+ return -EACCES;
+ }
+ dput(parent);
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_getattr(&lower_path, &lower_stat);
+ if (err)
+ goto out;
+ sdcardfs_copy_and_fix_attrs(d_inode(dentry),
+ d_inode(lower_path.dentry));
+ err = sdcardfs_fillattr(mnt, d_inode(dentry), &lower_stat, stat);
+out:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ return err;
+}
+
+const struct inode_operations sdcardfs_symlink_iops = {
+ .permission2 = sdcardfs_permission,
+ .setattr2 = sdcardfs_setattr,
+ /* XXX Following operations are implemented,
+ * but FUSE(sdcard) or FAT does not support them
+ * These methods are *NOT* perfectly tested.
+ .readlink = sdcardfs_readlink,
+ .follow_link = sdcardfs_follow_link,
+ .put_link = kfree_put_link,
+ */
+};
+
+const struct inode_operations sdcardfs_dir_iops = {
+ .create = sdcardfs_create,
+ .lookup = sdcardfs_lookup,
+ .permission = sdcardfs_permission_wrn,
+ .permission2 = sdcardfs_permission,
+ .unlink = sdcardfs_unlink,
+ .mkdir = sdcardfs_mkdir,
+ .rmdir = sdcardfs_rmdir,
+ .rename = sdcardfs_rename,
+ .setattr = sdcardfs_setattr_wrn,
+ .setattr2 = sdcardfs_setattr,
+ .getattr = sdcardfs_getattr,
+};
+
+const struct inode_operations sdcardfs_main_iops = {
+ .permission = sdcardfs_permission_wrn,
+ .permission2 = sdcardfs_permission,
+ .setattr = sdcardfs_setattr_wrn,
+ .setattr2 = sdcardfs_setattr,
+ .getattr = sdcardfs_getattr,
+};
diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c
new file mode 100644
index 0000000..beec63b
--- /dev/null
+++ b/fs/sdcardfs/lookup.c
@@ -0,0 +1,469 @@
+/*
+ * fs/sdcardfs/lookup.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include "linux/delay.h"
+
+/* The dentry cache is just so we have properly sized dentries */
+static struct kmem_cache *sdcardfs_dentry_cachep;
+
+int sdcardfs_init_dentry_cache(void)
+{
+ sdcardfs_dentry_cachep =
+ kmem_cache_create("sdcardfs_dentry",
+ sizeof(struct sdcardfs_dentry_info),
+ 0, SLAB_RECLAIM_ACCOUNT, NULL);
+
+ return sdcardfs_dentry_cachep ? 0 : -ENOMEM;
+}
+
+void sdcardfs_destroy_dentry_cache(void)
+{
+ kmem_cache_destroy(sdcardfs_dentry_cachep);
+}
+
+void free_dentry_private_data(struct dentry *dentry)
+{
+ kmem_cache_free(sdcardfs_dentry_cachep, dentry->d_fsdata);
+ dentry->d_fsdata = NULL;
+}
+
+/* allocate new dentry private data */
+int new_dentry_private_data(struct dentry *dentry)
+{
+ struct sdcardfs_dentry_info *info = SDCARDFS_D(dentry);
+
+ /* use zalloc to init dentry_info.lower_path */
+ info = kmem_cache_zalloc(sdcardfs_dentry_cachep, GFP_ATOMIC);
+ if (!info)
+ return -ENOMEM;
+
+ spin_lock_init(&info->lock);
+ dentry->d_fsdata = info;
+
+ return 0;
+}
+
+struct inode_data {
+ struct inode *lower_inode;
+ userid_t id;
+};
+
+static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void *candidate_lower_inode*/)
+{
+ struct inode *current_lower_inode = sdcardfs_lower_inode(inode);
+ userid_t current_userid = SDCARDFS_I(inode)->data->userid;
+
+ if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode &&
+ current_userid == ((struct inode_data *)candidate_data)->id)
+ return 1; /* found a match */
+ else
+ return 0; /* no match */
+}
+
+static int sdcardfs_inode_set(struct inode *inode, void *lower_inode)
+{
+ /* we do actual inode initialization in sdcardfs_iget */
+ return 0;
+}
+
+struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, userid_t id)
+{
+ struct sdcardfs_inode_info *info;
+ struct inode_data data;
+ struct inode *inode; /* the new inode to return */
+
+ if (!igrab(lower_inode))
+ return ERR_PTR(-ESTALE);
+
+ data.id = id;
+ data.lower_inode = lower_inode;
+ inode = iget5_locked(sb, /* our superblock */
+ /*
+ * hashval: we use inode number, but we can
+ * also use "(unsigned long)lower_inode"
+ * instead.
+ */
+ lower_inode->i_ino, /* hashval */
+ sdcardfs_inode_test, /* inode comparison function */
+ sdcardfs_inode_set, /* inode init function */
+ &data); /* data passed to test+set fxns */
+ if (!inode) {
+ iput(lower_inode);
+ return ERR_PTR(-ENOMEM);
+ }
+ /* if found a cached inode, then just return it (after iput) */
+ if (!(inode->i_state & I_NEW)) {
+ iput(lower_inode);
+ return inode;
+ }
+
+ /* initialize new inode */
+ info = SDCARDFS_I(inode);
+
+ inode->i_ino = lower_inode->i_ino;
+ sdcardfs_set_lower_inode(inode, lower_inode);
+
+ inode->i_version++;
+
+ /* use different set of inode ops for symlinks & directories */
+ if (S_ISDIR(lower_inode->i_mode))
+ inode->i_op = &sdcardfs_dir_iops;
+ else if (S_ISLNK(lower_inode->i_mode))
+ inode->i_op = &sdcardfs_symlink_iops;
+ else
+ inode->i_op = &sdcardfs_main_iops;
+
+ /* use different set of file ops for directories */
+ if (S_ISDIR(lower_inode->i_mode))
+ inode->i_fop = &sdcardfs_dir_fops;
+ else
+ inode->i_fop = &sdcardfs_main_fops;
+
+ inode->i_mapping->a_ops = &sdcardfs_aops;
+
+ inode->i_atime.tv_sec = 0;
+ inode->i_atime.tv_nsec = 0;
+ inode->i_mtime.tv_sec = 0;
+ inode->i_mtime.tv_nsec = 0;
+ inode->i_ctime.tv_sec = 0;
+ inode->i_ctime.tv_nsec = 0;
+
+ /* properly initialize special inodes */
+ if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) ||
+ S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode))
+ init_special_inode(inode, lower_inode->i_mode,
+ lower_inode->i_rdev);
+
+ /* all well, copy inode attributes */
+ sdcardfs_copy_and_fix_attrs(inode, lower_inode);
+ fsstack_copy_inode_size(inode, lower_inode);
+
+ unlock_new_inode(inode);
+ return inode;
+}
+
+/*
+ * Helper interpose routine, called directly by ->lookup to handle
+ * spliced dentries.
+ */
+static struct dentry *__sdcardfs_interpose(struct dentry *dentry,
+ struct super_block *sb,
+ struct path *lower_path,
+ userid_t id)
+{
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct super_block *lower_sb;
+ struct dentry *ret_dentry;
+
+ lower_inode = d_inode(lower_path->dentry);
+ lower_sb = sdcardfs_lower_super(sb);
+
+ /* check that the lower file system didn't cross a mount point */
+ if (lower_inode->i_sb != lower_sb) {
+ ret_dentry = ERR_PTR(-EXDEV);
+ goto out;
+ }
+
+ /*
+ * We allocate our new inode below by calling sdcardfs_iget,
+ * which will initialize some of the new inode's fields
+ */
+
+ /* inherit lower inode number for sdcardfs's inode */
+ inode = sdcardfs_iget(sb, lower_inode, id);
+ if (IS_ERR(inode)) {
+ ret_dentry = ERR_CAST(inode);
+ goto out;
+ }
+
+ ret_dentry = d_splice_alias(inode, dentry);
+ dentry = ret_dentry ?: dentry;
+ if (!IS_ERR(dentry))
+ update_derived_permission_lock(dentry);
+out:
+ return ret_dentry;
+}
+
+/*
+ * Connect an sdcardfs inode dentry/inode with several lower ones. This is
+ * the classic stackable file system "vnode interposition" action.
+ *
+ * @dentry: sdcardfs's dentry which interposes on lower one
+ * @sb: sdcardfs's super_block
+ * @lower_path: the lower path (caller does path_get/put)
+ */
+int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb,
+ struct path *lower_path, userid_t id)
+{
+ struct dentry *ret_dentry;
+
+ ret_dentry = __sdcardfs_interpose(dentry, sb, lower_path, id);
+ return PTR_ERR(ret_dentry);
+}
+
+struct sdcardfs_name_data {
+ struct dir_context ctx;
+ const struct qstr *to_find;
+ char *name;
+ bool found;
+};
+
+static int sdcardfs_name_match(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct sdcardfs_name_data *buf = container_of(ctx, struct sdcardfs_name_data, ctx);
+ struct qstr candidate = QSTR_INIT(name, namelen);
+
+ if (qstr_case_eq(buf->to_find, &candidate)) {
+ memcpy(buf->name, name, namelen);
+ buf->name[namelen] = 0;
+ buf->found = true;
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Main driver function for sdcardfs's lookup.
+ *
+ * Returns: NULL (ok), ERR_PTR if an error occurred.
+ * Fills in lower_parent_path with <dentry,mnt> on success.
+ */
+static struct dentry *__sdcardfs_lookup(struct dentry *dentry,
+ unsigned int flags, struct path *lower_parent_path, userid_t id)
+{
+ int err = 0;
+ struct vfsmount *lower_dir_mnt;
+ struct dentry *lower_dir_dentry = NULL;
+ struct dentry *lower_dentry;
+ const struct qstr *name;
+ struct path lower_path;
+ struct qstr dname;
+ struct dentry *ret_dentry = NULL;
+ struct sdcardfs_sb_info *sbi;
+
+ sbi = SDCARDFS_SB(dentry->d_sb);
+ /* must initialize dentry operations */
+ d_set_d_op(dentry, &sdcardfs_ci_dops);
+
+ if (IS_ROOT(dentry))
+ goto out;
+
+ name = &dentry->d_name;
+
+ /* now start the actual lookup procedure */
+ lower_dir_dentry = lower_parent_path->dentry;
+ lower_dir_mnt = lower_parent_path->mnt;
+
+ /* Use vfs_path_lookup to check if the dentry exists or not */
+ err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name->name, 0,
+ &lower_path);
+ /* check for other cases */
+ if (err == -ENOENT) {
+ struct file *file;
+ const struct cred *cred = current_cred();
+
+ struct sdcardfs_name_data buffer = {
+ .ctx.actor = sdcardfs_name_match,
+ .to_find = name,
+ .name = __getname(),
+ .found = false,
+ };
+
+ if (!buffer.name) {
+ err = -ENOMEM;
+ goto out;
+ }
+ file = dentry_open(lower_parent_path, O_RDONLY, cred);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ goto put_name;
+ }
+ err = iterate_dir(file, &buffer.ctx);
+ fput(file);
+ if (err)
+ goto put_name;
+
+ if (buffer.found)
+ err = vfs_path_lookup(lower_dir_dentry,
+ lower_dir_mnt,
+ buffer.name, 0,
+ &lower_path);
+ else
+ err = -ENOENT;
+put_name:
+ __putname(buffer.name);
+ }
+
+ /* no error: handle positive dentries */
+ if (!err) {
+ /* check if the dentry is an obb dentry
+ * if true, the lower_inode must be replaced with
+ * the inode of the graft path
+ */
+
+ if (need_graft_path(dentry)) {
+
+ /* setup_obb_dentry()
+ * The lower_path will be stored to the dentry's orig_path
+ * and the base obbpath will be copyed to the lower_path variable.
+ * if an error returned, there's no change in the lower_path
+ * returns: -ERRNO if error (0: no error)
+ */
+ err = setup_obb_dentry(dentry, &lower_path);
+
+ if (err) {
+ /* if the sbi->obbpath is not available, we can optionally
+ * setup the lower_path with its orig_path.
+ * but, the current implementation just returns an error
+ * because the sdcard daemon also regards this case as
+ * a lookup fail.
+ */
+ pr_info("sdcardfs: base obbpath is not available\n");
+ sdcardfs_put_reset_orig_path(dentry);
+ goto out;
+ }
+ }
+
+ sdcardfs_set_lower_path(dentry, &lower_path);
+ ret_dentry =
+ __sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id);
+ if (IS_ERR(ret_dentry)) {
+ err = PTR_ERR(ret_dentry);
+ /* path_put underlying path on error */
+ sdcardfs_put_reset_lower_path(dentry);
+ }
+ goto out;
+ }
+
+ /*
+ * We don't consider ENOENT an error, and we want to return a
+ * negative dentry.
+ */
+ if (err && err != -ENOENT)
+ goto out;
+
+ /* instatiate a new negative dentry */
+ dname.name = name->name;
+ dname.len = name->len;
+
+ /* See if the low-level filesystem might want
+ * to use its own hash
+ */
+ lower_dentry = d_hash_and_lookup(lower_dir_dentry, &dname);
+ if (IS_ERR(lower_dentry))
+ return lower_dentry;
+ if (!lower_dentry) {
+ /* We called vfs_path_lookup earlier, and did not get a negative
+ * dentry then. Don't confuse the lower filesystem by forcing
+ * one on it now...
+ */
+ err = -ENOENT;
+ goto out;
+ }
+
+ lower_path.dentry = lower_dentry;
+ lower_path.mnt = mntget(lower_dir_mnt);
+ sdcardfs_set_lower_path(dentry, &lower_path);
+
+ /*
+ * If the intent is to create a file, then don't return an error, so
+ * the VFS will continue the process of making this negative dentry
+ * into a positive one.
+ */
+ if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET))
+ err = 0;
+
+out:
+ if (err)
+ return ERR_PTR(err);
+ return ret_dentry;
+}
+
+/*
+ * On success:
+ * fills dentry object appropriate values and returns NULL.
+ * On fail (== error)
+ * returns error ptr
+ *
+ * @dir : Parent inode.
+ * @dentry : Target dentry to lookup. we should set each of fields.
+ * (dentry->d_name is initialized already)
+ * @nd : nameidata of parent inode
+ */
+struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct dentry *ret = NULL, *parent;
+ struct path lower_parent_path;
+ int err = 0;
+ const struct cred *saved_cred = NULL;
+
+ parent = dget_parent(dentry);
+
+ if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) {
+ ret = ERR_PTR(-EACCES);
+ goto out_err;
+ }
+
+ /* save current_cred and override it */
+ saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb),
+ SDCARDFS_I(dir)->data);
+ if (!saved_cred) {
+ ret = ERR_PTR(-ENOMEM);
+ goto out_err;
+ }
+
+ sdcardfs_get_lower_path(parent, &lower_parent_path);
+
+ /* allocate dentry private data. We free it in ->d_release */
+ err = new_dentry_private_data(dentry);
+ if (err) {
+ ret = ERR_PTR(err);
+ goto out;
+ }
+
+ ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path,
+ SDCARDFS_I(dir)->data->userid);
+ if (IS_ERR(ret))
+ goto out;
+ if (ret)
+ dentry = ret;
+ if (d_inode(dentry)) {
+ fsstack_copy_attr_times(d_inode(dentry),
+ sdcardfs_lower_inode(d_inode(dentry)));
+ /* get derived permission */
+ get_derived_permission(parent, dentry);
+ fixup_tmp_permissions(d_inode(dentry));
+ fixup_lower_ownership(dentry, dentry->d_name.name);
+ }
+ /* update parent directory's atime */
+ fsstack_copy_attr_atime(d_inode(parent),
+ sdcardfs_lower_inode(d_inode(parent)));
+
+out:
+ sdcardfs_put_lower_path(parent, &lower_parent_path);
+ revert_fsids(saved_cred);
+out_err:
+ dput(parent);
+ return ret;
+}
diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c
new file mode 100644
index 0000000..d890c57
--- /dev/null
+++ b/fs/sdcardfs/main.c
@@ -0,0 +1,511 @@
+/*
+ * fs/sdcardfs/main.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/parser.h>
+
+enum {
+ Opt_fsuid,
+ Opt_fsgid,
+ Opt_gid,
+ Opt_debug,
+ Opt_mask,
+ Opt_multiuser,
+ Opt_userid,
+ Opt_reserved_mb,
+ Opt_gid_derivation,
+ Opt_default_normal,
+ Opt_nocache,
+ Opt_unshared_obb,
+ Opt_err,
+};
+
+static const match_table_t sdcardfs_tokens = {
+ {Opt_fsuid, "fsuid=%u"},
+ {Opt_fsgid, "fsgid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_debug, "debug"},
+ {Opt_mask, "mask=%u"},
+ {Opt_userid, "userid=%d"},
+ {Opt_multiuser, "multiuser"},
+ {Opt_gid_derivation, "derive_gid"},
+ {Opt_default_normal, "default_normal"},
+ {Opt_unshared_obb, "unshared_obb"},
+ {Opt_reserved_mb, "reserved_mb=%u"},
+ {Opt_nocache, "nocache"},
+ {Opt_err, NULL}
+};
+
+static int parse_options(struct super_block *sb, char *options, int silent,
+ int *debug, struct sdcardfs_vfsmount_options *vfsopts,
+ struct sdcardfs_mount_options *opts)
+{
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+
+ /* by default, we use AID_MEDIA_RW as uid, gid */
+ opts->fs_low_uid = AID_MEDIA_RW;
+ opts->fs_low_gid = AID_MEDIA_RW;
+ vfsopts->mask = 0;
+ opts->multiuser = false;
+ opts->fs_user_id = 0;
+ vfsopts->gid = 0;
+ /* by default, 0MB is reserved */
+ opts->reserved_mb = 0;
+ /* by default, gid derivation is off */
+ opts->gid_derivation = false;
+ opts->default_normal = false;
+ opts->nocache = false;
+
+ *debug = 0;
+
+ if (!options)
+ return 0;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+
+ if (!*p)
+ continue;
+
+ token = match_token(p, sdcardfs_tokens, args);
+
+ switch (token) {
+ case Opt_debug:
+ *debug = 1;
+ break;
+ case Opt_fsuid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_low_uid = option;
+ break;
+ case Opt_fsgid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_low_gid = option;
+ break;
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return 0;
+ vfsopts->gid = option;
+ break;
+ case Opt_userid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_user_id = option;
+ break;
+ case Opt_mask:
+ if (match_int(&args[0], &option))
+ return 0;
+ vfsopts->mask = option;
+ break;
+ case Opt_multiuser:
+ opts->multiuser = true;
+ break;
+ case Opt_reserved_mb:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->reserved_mb = option;
+ break;
+ case Opt_gid_derivation:
+ opts->gid_derivation = true;
+ break;
+ case Opt_default_normal:
+ opts->default_normal = true;
+ break;
+ case Opt_nocache:
+ opts->nocache = true;
+ break;
+ case Opt_unshared_obb:
+ opts->unshared_obb = true;
+ break;
+ /* unknown option */
+ default:
+ if (!silent)
+ pr_err("Unrecognized mount option \"%s\" or missing value", p);
+ return -EINVAL;
+ }
+ }
+
+ if (*debug) {
+ pr_info("sdcardfs : options - debug:%d\n", *debug);
+ pr_info("sdcardfs : options - uid:%d\n",
+ opts->fs_low_uid);
+ pr_info("sdcardfs : options - gid:%d\n",
+ opts->fs_low_gid);
+ }
+
+ return 0;
+}
+
+int parse_options_remount(struct super_block *sb, char *options, int silent,
+ struct sdcardfs_vfsmount_options *vfsopts)
+{
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+ int debug;
+
+ if (!options)
+ return 0;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+
+ if (!*p)
+ continue;
+
+ token = match_token(p, sdcardfs_tokens, args);
+
+ switch (token) {
+ case Opt_debug:
+ debug = 1;
+ break;
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return 0;
+ vfsopts->gid = option;
+
+ break;
+ case Opt_mask:
+ if (match_int(&args[0], &option))
+ return 0;
+ vfsopts->mask = option;
+ break;
+ case Opt_unshared_obb:
+ case Opt_default_normal:
+ case Opt_multiuser:
+ case Opt_userid:
+ case Opt_fsuid:
+ case Opt_fsgid:
+ case Opt_reserved_mb:
+ case Opt_gid_derivation:
+ if (!silent)
+ pr_warn("Option \"%s\" can't be changed during remount\n", p);
+ break;
+ /* unknown option */
+ default:
+ if (!silent)
+ pr_err("Unrecognized mount option \"%s\" or missing value", p);
+ return -EINVAL;
+ }
+ }
+
+ if (debug) {
+ pr_info("sdcardfs : options - debug:%d\n", debug);
+ pr_info("sdcardfs : options - gid:%d\n", vfsopts->gid);
+ pr_info("sdcardfs : options - mask:%d\n", vfsopts->mask);
+ }
+
+ return 0;
+}
+
+#if 0
+/*
+ * our custom d_alloc_root work-alike
+ *
+ * we can't use d_alloc_root if we want to use our own interpose function
+ * unchanged, so we simply call our own "fake" d_alloc_root
+ */
+static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb)
+{
+ struct dentry *ret = NULL;
+
+ if (sb) {
+ static const struct qstr name = {
+ .name = "/",
+ .len = 1
+ };
+
+ ret = d_alloc(NULL, &name);
+ if (ret) {
+ d_set_d_op(ret, &sdcardfs_ci_dops);
+ ret->d_sb = sb;
+ ret->d_parent = ret;
+ }
+ }
+ return ret;
+}
+#endif
+
+DEFINE_MUTEX(sdcardfs_super_list_lock);
+EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock);
+LIST_HEAD(sdcardfs_super_list);
+EXPORT_SYMBOL_GPL(sdcardfs_super_list);
+
+/*
+ * There is no need to lock the sdcardfs_super_info's rwsem as there is no
+ * way anyone can have a reference to the superblock at this point in time.
+ */
+static int sdcardfs_read_super(struct vfsmount *mnt, struct super_block *sb,
+ const char *dev_name, void *raw_data, int silent)
+{
+ int err = 0;
+ int debug;
+ struct super_block *lower_sb;
+ struct path lower_path;
+ struct sdcardfs_sb_info *sb_info;
+ struct sdcardfs_vfsmount_options *mnt_opt = mnt->data;
+ struct inode *inode;
+
+ pr_info("sdcardfs version 2.0\n");
+
+ if (!dev_name) {
+ pr_err("sdcardfs: read_super: missing dev_name argument\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ pr_info("sdcardfs: dev_name -> %s\n", dev_name);
+ pr_info("sdcardfs: options -> %s\n", (char *)raw_data);
+ pr_info("sdcardfs: mnt -> %p\n", mnt);
+
+ /* parse lower path */
+ err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
+ &lower_path);
+ if (err) {
+ pr_err("sdcardfs: error accessing lower directory '%s'\n", dev_name);
+ goto out;
+ }
+
+ /* allocate superblock private data */
+ sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL);
+ if (!SDCARDFS_SB(sb)) {
+ pr_crit("sdcardfs: read_super: out of memory\n");
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ sb_info = sb->s_fs_info;
+ /* parse options */
+ err = parse_options(sb, raw_data, silent, &debug, mnt_opt, &sb_info->options);
+ if (err) {
+ pr_err("sdcardfs: invalid options\n");
+ goto out_freesbi;
+ }
+
+ /* set the lower superblock field of upper superblock */
+ lower_sb = lower_path.dentry->d_sb;
+ atomic_inc(&lower_sb->s_active);
+ sdcardfs_set_lower_super(sb, lower_sb);
+
+ sb->s_stack_depth = lower_sb->s_stack_depth + 1;
+ if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+ pr_err("sdcardfs: maximum fs stacking depth exceeded\n");
+ err = -EINVAL;
+ goto out_sput;
+ }
+
+ /* inherit maxbytes from lower file system */
+ sb->s_maxbytes = lower_sb->s_maxbytes;
+
+ /*
+ * Our c/m/atime granularity is 1 ns because we may stack on file
+ * systems whose granularity is as good.
+ */
+ sb->s_time_gran = 1;
+
+ sb->s_magic = SDCARDFS_SUPER_MAGIC;
+ sb->s_op = &sdcardfs_sops;
+
+ /* get a new inode and allocate our root dentry */
+ inode = sdcardfs_iget(sb, d_inode(lower_path.dentry), 0);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto out_sput;
+ }
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root) {
+ err = -ENOMEM;
+ goto out_sput;
+ }
+ d_set_d_op(sb->s_root, &sdcardfs_ci_dops);
+
+ /* link the upper and lower dentries */
+ sb->s_root->d_fsdata = NULL;
+ err = new_dentry_private_data(sb->s_root);
+ if (err)
+ goto out_freeroot;
+
+ /* set the lower dentries for s_root */
+ sdcardfs_set_lower_path(sb->s_root, &lower_path);
+
+ /*
+ * No need to call interpose because we already have a positive
+ * dentry, which was instantiated by d_make_root. Just need to
+ * d_rehash it.
+ */
+ d_rehash(sb->s_root);
+
+ /* setup permission policy */
+ sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL);
+ mutex_lock(&sdcardfs_super_list_lock);
+ if (sb_info->options.multiuser) {
+ setup_derived_state(d_inode(sb->s_root), PERM_PRE_ROOT,
+ sb_info->options.fs_user_id, AID_ROOT);
+ snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name);
+ } else {
+ setup_derived_state(d_inode(sb->s_root), PERM_ROOT,
+ sb_info->options.fs_user_id, AID_ROOT);
+ snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name);
+ }
+ fixup_tmp_permissions(d_inode(sb->s_root));
+ sb_info->sb = sb;
+ list_add(&sb_info->list, &sdcardfs_super_list);
+ mutex_unlock(&sdcardfs_super_list_lock);
+
+ if (!silent)
+ pr_info("sdcardfs: mounted on top of %s type %s\n",
+ dev_name, lower_sb->s_type->name);
+ goto out; /* all is well */
+
+ /* no longer needed: free_dentry_private_data(sb->s_root); */
+out_freeroot:
+ dput(sb->s_root);
+ sb->s_root = NULL;
+out_sput:
+ /* drop refs we took earlier */
+ atomic_dec(&lower_sb->s_active);
+out_freesbi:
+ kfree(SDCARDFS_SB(sb));
+ sb->s_fs_info = NULL;
+out_free:
+ path_put(&lower_path);
+
+out:
+ return err;
+}
+
+struct sdcardfs_mount_private {
+ struct vfsmount *mnt;
+ const char *dev_name;
+ void *raw_data;
+};
+
+static int __sdcardfs_fill_super(
+ struct super_block *sb,
+ void *_priv, int silent)
+{
+ struct sdcardfs_mount_private *priv = _priv;
+
+ return sdcardfs_read_super(priv->mnt,
+ sb, priv->dev_name, priv->raw_data, silent);
+}
+
+static struct dentry *sdcardfs_mount(struct vfsmount *mnt,
+ struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *raw_data)
+{
+ struct sdcardfs_mount_private priv = {
+ .mnt = mnt,
+ .dev_name = dev_name,
+ .raw_data = raw_data
+ };
+
+ return mount_nodev(fs_type, flags,
+ &priv, __sdcardfs_fill_super);
+}
+
+static struct dentry *sdcardfs_mount_wrn(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *raw_data)
+{
+ WARN(1, "sdcardfs does not support mount. Use mount2.\n");
+ return ERR_PTR(-EINVAL);
+}
+
+void *sdcardfs_alloc_mnt_data(void)
+{
+ return kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL);
+}
+
+void sdcardfs_kill_sb(struct super_block *sb)
+{
+ struct sdcardfs_sb_info *sbi;
+
+ if (sb->s_magic == SDCARDFS_SUPER_MAGIC && sb->s_fs_info) {
+ sbi = SDCARDFS_SB(sb);
+ mutex_lock(&sdcardfs_super_list_lock);
+ list_del(&sbi->list);
+ mutex_unlock(&sdcardfs_super_list_lock);
+ }
+ kill_anon_super(sb);
+}
+
+static struct file_system_type sdcardfs_fs_type = {
+ .owner = THIS_MODULE,
+ .name = SDCARDFS_NAME,
+ .mount = sdcardfs_mount_wrn,
+ .mount2 = sdcardfs_mount,
+ .alloc_mnt_data = sdcardfs_alloc_mnt_data,
+ .kill_sb = sdcardfs_kill_sb,
+ .fs_flags = 0,
+};
+MODULE_ALIAS_FS(SDCARDFS_NAME);
+
+static int __init init_sdcardfs_fs(void)
+{
+ int err;
+
+ pr_info("Registering sdcardfs " SDCARDFS_VERSION "\n");
+
+ err = sdcardfs_init_inode_cache();
+ if (err)
+ goto out;
+ err = sdcardfs_init_dentry_cache();
+ if (err)
+ goto out;
+ err = packagelist_init();
+ if (err)
+ goto out;
+ err = register_filesystem(&sdcardfs_fs_type);
+out:
+ if (err) {
+ sdcardfs_destroy_inode_cache();
+ sdcardfs_destroy_dentry_cache();
+ packagelist_exit();
+ }
+ return err;
+}
+
+static void __exit exit_sdcardfs_fs(void)
+{
+ sdcardfs_destroy_inode_cache();
+ sdcardfs_destroy_dentry_cache();
+ packagelist_exit();
+ unregister_filesystem(&sdcardfs_fs_type);
+ pr_info("Completed sdcardfs module unload\n");
+}
+
+/* Original wrapfs authors */
+MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University (http://www.fsl.cs.sunysb.edu/)");
+
+/* Original sdcardfs authors */
+MODULE_AUTHOR("Woojoong Lee, Daeho Jeong, Kitae Lee, Yeongjin Gil System Memory Lab., Samsung Electronics");
+
+/* Current maintainer */
+MODULE_AUTHOR("Daniel Rosenberg, Google");
+MODULE_DESCRIPTION("Sdcardfs " SDCARDFS_VERSION);
+MODULE_LICENSE("GPL");
+
+module_init(init_sdcardfs_fs);
+module_exit(exit_sdcardfs_fs);
diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c
new file mode 100644
index 0000000..391d2a7
--- /dev/null
+++ b/fs/sdcardfs/mmap.c
@@ -0,0 +1,88 @@
+/*
+ * fs/sdcardfs/mmap.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ int err;
+ struct file *file;
+ const struct vm_operations_struct *lower_vm_ops;
+
+ file = (struct file *)vma->vm_private_data;
+ lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops;
+ BUG_ON(!lower_vm_ops);
+
+ err = lower_vm_ops->fault(vma, vmf);
+ return err;
+}
+
+static void sdcardfs_vm_open(struct vm_area_struct *vma)
+{
+ struct file *file = (struct file *)vma->vm_private_data;
+
+ get_file(file);
+}
+
+static void sdcardfs_vm_close(struct vm_area_struct *vma)
+{
+ struct file *file = (struct file *)vma->vm_private_data;
+
+ fput(file);
+}
+
+static int sdcardfs_page_mkwrite(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ int err = 0;
+ struct file *file;
+ const struct vm_operations_struct *lower_vm_ops;
+
+ file = (struct file *)vma->vm_private_data;
+ lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops;
+ BUG_ON(!lower_vm_ops);
+ if (!lower_vm_ops->page_mkwrite)
+ goto out;
+
+ err = lower_vm_ops->page_mkwrite(vma, vmf);
+out:
+ return err;
+}
+
+static ssize_t sdcardfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+ /*
+ * This function should never be called directly. We need it
+ * to exist, to get past a check in open_check_o_direct(),
+ * which is called from do_last().
+ */
+ return -EINVAL;
+}
+
+const struct address_space_operations sdcardfs_aops = {
+ .direct_IO = sdcardfs_direct_IO,
+};
+
+const struct vm_operations_struct sdcardfs_vm_ops = {
+ .fault = sdcardfs_fault,
+ .page_mkwrite = sdcardfs_page_mkwrite,
+ .open = sdcardfs_vm_open,
+ .close = sdcardfs_vm_close,
+};
diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h
new file mode 100644
index 0000000..85341e7
--- /dev/null
+++ b/fs/sdcardfs/multiuser.h
@@ -0,0 +1,53 @@
+/*
+ * fs/sdcardfs/multiuser.h
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#define AID_USER_OFFSET 100000 /* offset for uid ranges for each user */
+#define AID_APP_START 10000 /* first app user */
+#define AID_APP_END 19999 /* last app user */
+#define AID_CACHE_GID_START 20000 /* start of gids for apps to mark cached data */
+#define AID_EXT_GID_START 30000 /* start of gids for apps to mark external data */
+#define AID_EXT_CACHE_GID_START 40000 /* start of gids for apps to mark external cached data */
+#define AID_EXT_CACHE_GID_END 49999 /* end of gids for apps to mark external cached data */
+#define AID_SHARED_GID_START 50000 /* start of gids for apps in each user to share */
+
+typedef uid_t userid_t;
+typedef uid_t appid_t;
+
+static inline uid_t multiuser_get_uid(userid_t user_id, appid_t app_id)
+{
+ return (user_id * AID_USER_OFFSET) + (app_id % AID_USER_OFFSET);
+}
+
+static inline bool uid_is_app(uid_t uid)
+{
+ appid_t appid = uid % AID_USER_OFFSET;
+
+ return appid >= AID_APP_START && appid <= AID_APP_END;
+}
+
+static inline gid_t multiuser_get_ext_cache_gid(uid_t uid)
+{
+ return uid - AID_APP_START + AID_EXT_CACHE_GID_START;
+}
+
+static inline gid_t multiuser_get_ext_gid(uid_t uid)
+{
+ return uid - AID_APP_START + AID_EXT_GID_START;
+}
diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c
new file mode 100644
index 0000000..4b9a563
--- /dev/null
+++ b/fs/sdcardfs/packagelist.c
@@ -0,0 +1,882 @@
+/*
+ * fs/sdcardfs/packagelist.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include <linux/hashtable.h>
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/radix-tree.h>
+#include <linux/dcache.h>
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+struct hashtable_entry {
+ struct hlist_node hlist;
+ struct hlist_node dlist; /* for deletion cleanup */
+ struct qstr key;
+ atomic_t value;
+};
+
+static DEFINE_HASHTABLE(package_to_appid, 8);
+static DEFINE_HASHTABLE(package_to_userid, 8);
+static DEFINE_HASHTABLE(ext_to_groupid, 8);
+
+
+static struct kmem_cache *hashtable_entry_cachep;
+
+static unsigned int full_name_case_hash(const void *salt, const unsigned char *name, unsigned int len)
+{
+ unsigned long hash = init_name_hash(salt);
+
+ while (len--)
+ hash = partial_name_hash(tolower(*name++), hash);
+ return end_name_hash(hash);
+}
+
+static inline void qstr_init(struct qstr *q, const char *name)
+{
+ q->name = name;
+ q->len = strlen(q->name);
+ q->hash = full_name_case_hash(0, q->name, q->len);
+}
+
+static inline int qstr_copy(const struct qstr *src, struct qstr *dest)
+{
+ dest->name = kstrdup(src->name, GFP_KERNEL);
+ dest->hash_len = src->hash_len;
+ return !!dest->name;
+}
+
+
+static appid_t __get_appid(const struct qstr *key)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = key->hash;
+ appid_t ret_id;
+
+ rcu_read_lock();
+ hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key)) {
+ ret_id = atomic_read(&hash_cur->value);
+ rcu_read_unlock();
+ return ret_id;
+ }
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+appid_t get_appid(const char *key)
+{
+ struct qstr q;
+
+ qstr_init(&q, key);
+ return __get_appid(&q);
+}
+
+static appid_t __get_ext_gid(const struct qstr *key)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = key->hash;
+ appid_t ret_id;
+
+ rcu_read_lock();
+ hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key)) {
+ ret_id = atomic_read(&hash_cur->value);
+ rcu_read_unlock();
+ return ret_id;
+ }
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+appid_t get_ext_gid(const char *key)
+{
+ struct qstr q;
+
+ qstr_init(&q, key);
+ return __get_ext_gid(&q);
+}
+
+static appid_t __is_excluded(const struct qstr *app_name, userid_t user)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = app_name->hash;
+
+ rcu_read_lock();
+ hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) {
+ if (atomic_read(&hash_cur->value) == user &&
+ qstr_case_eq(app_name, &hash_cur->key)) {
+ rcu_read_unlock();
+ return 1;
+ }
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+appid_t is_excluded(const char *key, userid_t user)
+{
+ struct qstr q;
+ qstr_init(&q, key);
+ return __is_excluded(&q, user);
+}
+
+/* Kernel has already enforced everything we returned through
+ * derive_permissions_locked(), so this is used to lock down access
+ * even further, such as enforcing that apps hold sdcard_rw.
+ */
+int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name)
+{
+ struct qstr q_autorun = QSTR_LITERAL("autorun.inf");
+ struct qstr q__android_secure = QSTR_LITERAL(".android_secure");
+ struct qstr q_android_secure = QSTR_LITERAL("android_secure");
+
+ /* Always block security-sensitive files at root */
+ if (parent_node && SDCARDFS_I(parent_node)->data->perm == PERM_ROOT) {
+ if (qstr_case_eq(name, &q_autorun)
+ || qstr_case_eq(name, &q__android_secure)
+ || qstr_case_eq(name, &q_android_secure)) {
+ return 0;
+ }
+ }
+
+ /* Root always has access; access for any other UIDs should always
+ * be controlled through packages.list.
+ */
+ if (from_kuid(&init_user_ns, current_fsuid()) == 0)
+ return 1;
+
+ /* No extra permissions to enforce */
+ return 1;
+}
+
+static struct hashtable_entry *alloc_hashtable_entry(const struct qstr *key,
+ appid_t value)
+{
+ struct hashtable_entry *ret = kmem_cache_alloc(hashtable_entry_cachep,
+ GFP_KERNEL);
+ if (!ret)
+ return NULL;
+ INIT_HLIST_NODE(&ret->dlist);
+ INIT_HLIST_NODE(&ret->hlist);
+
+ if (!qstr_copy(key, &ret->key)) {
+ kmem_cache_free(hashtable_entry_cachep, ret);
+ return NULL;
+ }
+
+ atomic_set(&ret->value, value);
+ return ret;
+}
+
+static int insert_packagelist_appid_entry_locked(const struct qstr *key, appid_t value)
+{
+ struct hashtable_entry *hash_cur;
+ struct hashtable_entry *new_entry;
+ unsigned int hash = key->hash;
+
+ hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key)) {
+ atomic_set(&hash_cur->value, value);
+ return 0;
+ }
+ }
+ new_entry = alloc_hashtable_entry(key, value);
+ if (!new_entry)
+ return -ENOMEM;
+ hash_add_rcu(package_to_appid, &new_entry->hlist, hash);
+ return 0;
+}
+
+static int insert_ext_gid_entry_locked(const struct qstr *key, appid_t value)
+{
+ struct hashtable_entry *hash_cur;
+ struct hashtable_entry *new_entry;
+ unsigned int hash = key->hash;
+
+ /* An extension can only belong to one gid */
+ hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key))
+ return -EINVAL;
+ }
+ new_entry = alloc_hashtable_entry(key, value);
+ if (!new_entry)
+ return -ENOMEM;
+ hash_add_rcu(ext_to_groupid, &new_entry->hlist, hash);
+ return 0;
+}
+
+static int insert_userid_exclude_entry_locked(const struct qstr *key, userid_t value)
+{
+ struct hashtable_entry *hash_cur;
+ struct hashtable_entry *new_entry;
+ unsigned int hash = key->hash;
+
+ /* Only insert if not already present */
+ hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) {
+ if (atomic_read(&hash_cur->value) == value &&
+ qstr_case_eq(key, &hash_cur->key))
+ return 0;
+ }
+ new_entry = alloc_hashtable_entry(key, value);
+ if (!new_entry)
+ return -ENOMEM;
+ hash_add_rcu(package_to_userid, &new_entry->hlist, hash);
+ return 0;
+}
+
+static void fixup_all_perms_name(const struct qstr *key)
+{
+ struct sdcardfs_sb_info *sbinfo;
+ struct limit_search limit = {
+ .flags = BY_NAME,
+ .name = QSTR_INIT(key->name, key->len),
+ };
+ list_for_each_entry(sbinfo, &sdcardfs_super_list, list) {
+ if (sbinfo_has_sdcard_magic(sbinfo))
+ fixup_perms_recursive(sbinfo->sb->s_root, &limit);
+ }
+}
+
+static void fixup_all_perms_name_userid(const struct qstr *key, userid_t userid)
+{
+ struct sdcardfs_sb_info *sbinfo;
+ struct limit_search limit = {
+ .flags = BY_NAME | BY_USERID,
+ .name = QSTR_INIT(key->name, key->len),
+ .userid = userid,
+ };
+ list_for_each_entry(sbinfo, &sdcardfs_super_list, list) {
+ if (sbinfo_has_sdcard_magic(sbinfo))
+ fixup_perms_recursive(sbinfo->sb->s_root, &limit);
+ }
+}
+
+static void fixup_all_perms_userid(userid_t userid)
+{
+ struct sdcardfs_sb_info *sbinfo;
+ struct limit_search limit = {
+ .flags = BY_USERID,
+ .userid = userid,
+ };
+ list_for_each_entry(sbinfo, &sdcardfs_super_list, list) {
+ if (sbinfo_has_sdcard_magic(sbinfo))
+ fixup_perms_recursive(sbinfo->sb->s_root, &limit);
+ }
+}
+
+static int insert_packagelist_entry(const struct qstr *key, appid_t value)
+{
+ int err;
+
+ mutex_lock(&sdcardfs_super_list_lock);
+ err = insert_packagelist_appid_entry_locked(key, value);
+ if (!err)
+ fixup_all_perms_name(key);
+ mutex_unlock(&sdcardfs_super_list_lock);
+
+ return err;
+}
+
+static int insert_ext_gid_entry(const struct qstr *key, appid_t value)
+{
+ int err;
+
+ mutex_lock(&sdcardfs_super_list_lock);
+ err = insert_ext_gid_entry_locked(key, value);
+ mutex_unlock(&sdcardfs_super_list_lock);
+
+ return err;
+}
+
+static int insert_userid_exclude_entry(const struct qstr *key, userid_t value)
+{
+ int err;
+
+ mutex_lock(&sdcardfs_super_list_lock);
+ err = insert_userid_exclude_entry_locked(key, value);
+ if (!err)
+ fixup_all_perms_name_userid(key, value);
+ mutex_unlock(&sdcardfs_super_list_lock);
+
+ return err;
+}
+
+static void free_hashtable_entry(struct hashtable_entry *entry)
+{
+ kfree(entry->key.name);
+ kmem_cache_free(hashtable_entry_cachep, entry);
+}
+
+static void remove_packagelist_entry_locked(const struct qstr *key)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = key->hash;
+ struct hlist_node *h_t;
+ HLIST_HEAD(free_list);
+
+ hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key)) {
+ hash_del_rcu(&hash_cur->hlist);
+ hlist_add_head(&hash_cur->dlist, &free_list);
+ }
+ }
+ hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key)) {
+ hash_del_rcu(&hash_cur->hlist);
+ hlist_add_head(&hash_cur->dlist, &free_list);
+ break;
+ }
+ }
+ synchronize_rcu();
+ hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist)
+ free_hashtable_entry(hash_cur);
+}
+
+static void remove_packagelist_entry(const struct qstr *key)
+{
+ mutex_lock(&sdcardfs_super_list_lock);
+ remove_packagelist_entry_locked(key);
+ fixup_all_perms_name(key);
+ mutex_unlock(&sdcardfs_super_list_lock);
+}
+
+static void remove_ext_gid_entry_locked(const struct qstr *key, gid_t group)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = key->hash;
+
+ hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key) && atomic_read(&hash_cur->value) == group) {
+ hash_del_rcu(&hash_cur->hlist);
+ synchronize_rcu();
+ free_hashtable_entry(hash_cur);
+ break;
+ }
+ }
+}
+
+static void remove_ext_gid_entry(const struct qstr *key, gid_t group)
+{
+ mutex_lock(&sdcardfs_super_list_lock);
+ remove_ext_gid_entry_locked(key, group);
+ mutex_unlock(&sdcardfs_super_list_lock);
+}
+
+static void remove_userid_all_entry_locked(userid_t userid)
+{
+ struct hashtable_entry *hash_cur;
+ struct hlist_node *h_t;
+ HLIST_HEAD(free_list);
+ int i;
+
+ hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) {
+ if (atomic_read(&hash_cur->value) == userid) {
+ hash_del_rcu(&hash_cur->hlist);
+ hlist_add_head(&hash_cur->dlist, &free_list);
+ }
+ }
+ synchronize_rcu();
+ hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) {
+ free_hashtable_entry(hash_cur);
+ }
+}
+
+static void remove_userid_all_entry(userid_t userid)
+{
+ mutex_lock(&sdcardfs_super_list_lock);
+ remove_userid_all_entry_locked(userid);
+ fixup_all_perms_userid(userid);
+ mutex_unlock(&sdcardfs_super_list_lock);
+}
+
+static void remove_userid_exclude_entry_locked(const struct qstr *key, userid_t userid)
+{
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = key->hash;
+
+ hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(key, &hash_cur->key) &&
+ atomic_read(&hash_cur->value) == userid) {
+ hash_del_rcu(&hash_cur->hlist);
+ synchronize_rcu();
+ free_hashtable_entry(hash_cur);
+ break;
+ }
+ }
+}
+
+static void remove_userid_exclude_entry(const struct qstr *key, userid_t userid)
+{
+ mutex_lock(&sdcardfs_super_list_lock);
+ remove_userid_exclude_entry_locked(key, userid);
+ fixup_all_perms_name_userid(key, userid);
+ mutex_unlock(&sdcardfs_super_list_lock);
+}
+
+static void packagelist_destroy(void)
+{
+ struct hashtable_entry *hash_cur;
+ struct hlist_node *h_t;
+ HLIST_HEAD(free_list);
+ int i;
+
+ mutex_lock(&sdcardfs_super_list_lock);
+ hash_for_each_rcu(package_to_appid, i, hash_cur, hlist) {
+ hash_del_rcu(&hash_cur->hlist);
+ hlist_add_head(&hash_cur->dlist, &free_list);
+ }
+ hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) {
+ hash_del_rcu(&hash_cur->hlist);
+ hlist_add_head(&hash_cur->dlist, &free_list);
+ }
+ synchronize_rcu();
+ hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist)
+ free_hashtable_entry(hash_cur);
+ mutex_unlock(&sdcardfs_super_list_lock);
+ pr_info("sdcardfs: destroyed packagelist pkgld\n");
+}
+
+#define SDCARDFS_CONFIGFS_ATTR(_pfx, _name) \
+static struct configfs_attribute _pfx##attr_##_name = { \
+ .ca_name = __stringify(_name), \
+ .ca_mode = S_IRUGO | S_IWUGO, \
+ .ca_owner = THIS_MODULE, \
+ .show = _pfx##_name##_show, \
+ .store = _pfx##_name##_store, \
+}
+
+#define SDCARDFS_CONFIGFS_ATTR_RO(_pfx, _name) \
+static struct configfs_attribute _pfx##attr_##_name = { \
+ .ca_name = __stringify(_name), \
+ .ca_mode = S_IRUGO, \
+ .ca_owner = THIS_MODULE, \
+ .show = _pfx##_name##_show, \
+}
+
+#define SDCARDFS_CONFIGFS_ATTR_WO(_pfx, _name) \
+static struct configfs_attribute _pfx##attr_##_name = { \
+ .ca_name = __stringify(_name), \
+ .ca_mode = S_IWUGO, \
+ .ca_owner = THIS_MODULE, \
+ .store = _pfx##_name##_store, \
+}
+
+struct package_details {
+ struct config_item item;
+ struct qstr name;
+};
+
+static inline struct package_details *to_package_details(struct config_item *item)
+{
+ return item ? container_of(item, struct package_details, item) : NULL;
+}
+
+static ssize_t package_details_appid_show(struct config_item *item, char *page)
+{
+ return scnprintf(page, PAGE_SIZE, "%u\n", __get_appid(&to_package_details(item)->name));
+}
+
+static ssize_t package_details_appid_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ unsigned int tmp;
+ int ret;
+
+ ret = kstrtouint(page, 10, &tmp);
+ if (ret)
+ return ret;
+
+ ret = insert_packagelist_entry(&to_package_details(item)->name, tmp);
+
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static ssize_t package_details_excluded_userids_show(struct config_item *item,
+ char *page)
+{
+ struct package_details *package_details = to_package_details(item);
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = package_details->name.hash;
+ int count = 0;
+
+ rcu_read_lock();
+ hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) {
+ if (qstr_case_eq(&package_details->name, &hash_cur->key))
+ count += scnprintf(page + count, PAGE_SIZE - count,
+ "%d ", atomic_read(&hash_cur->value));
+ }
+ rcu_read_unlock();
+ if (count)
+ count--;
+ count += scnprintf(page + count, PAGE_SIZE - count, "\n");
+ return count;
+}
+
+static ssize_t package_details_excluded_userids_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ unsigned int tmp;
+ int ret;
+
+ ret = kstrtouint(page, 10, &tmp);
+ if (ret)
+ return ret;
+
+ ret = insert_userid_exclude_entry(&to_package_details(item)->name, tmp);
+
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static ssize_t package_details_clear_userid_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ unsigned int tmp;
+ int ret;
+
+ ret = kstrtouint(page, 10, &tmp);
+ if (ret)
+ return ret;
+ remove_userid_exclude_entry(&to_package_details(item)->name, tmp);
+ return count;
+}
+
+static void package_details_release(struct config_item *item)
+{
+ struct package_details *package_details = to_package_details(item);
+
+ pr_info("sdcardfs: removing %s\n", package_details->name.name);
+ remove_packagelist_entry(&package_details->name);
+ kfree(package_details->name.name);
+ kfree(package_details);
+}
+
+SDCARDFS_CONFIGFS_ATTR(package_details_, appid);
+SDCARDFS_CONFIGFS_ATTR(package_details_, excluded_userids);
+SDCARDFS_CONFIGFS_ATTR_WO(package_details_, clear_userid);
+
+static struct configfs_attribute *package_details_attrs[] = {
+ &package_details_attr_appid,
+ &package_details_attr_excluded_userids,
+ &package_details_attr_clear_userid,
+ NULL,
+};
+
+static struct configfs_item_operations package_details_item_ops = {
+ .release = package_details_release,
+};
+
+static struct config_item_type package_appid_type = {
+ .ct_item_ops = &package_details_item_ops,
+ .ct_attrs = package_details_attrs,
+ .ct_owner = THIS_MODULE,
+};
+
+struct extensions_value {
+ struct config_group group;
+ unsigned int num;
+};
+
+struct extension_details {
+ struct config_item item;
+ struct qstr name;
+ unsigned int num;
+};
+
+static inline struct extensions_value *to_extensions_value(struct config_item *item)
+{
+ return item ? container_of(to_config_group(item), struct extensions_value, group) : NULL;
+}
+
+static inline struct extension_details *to_extension_details(struct config_item *item)
+{
+ return item ? container_of(item, struct extension_details, item) : NULL;
+}
+
+static void extension_details_release(struct config_item *item)
+{
+ struct extension_details *extension_details = to_extension_details(item);
+
+ pr_info("sdcardfs: No longer mapping %s files to gid %d\n",
+ extension_details->name.name, extension_details->num);
+ remove_ext_gid_entry(&extension_details->name, extension_details->num);
+ kfree(extension_details->name.name);
+ kfree(extension_details);
+}
+
+static struct configfs_item_operations extension_details_item_ops = {
+ .release = extension_details_release,
+};
+
+static struct config_item_type extension_details_type = {
+ .ct_item_ops = &extension_details_item_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+static struct config_item *extension_details_make_item(struct config_group *group, const char *name)
+{
+ struct extensions_value *extensions_value = to_extensions_value(&group->cg_item);
+ struct extension_details *extension_details = kzalloc(sizeof(struct extension_details), GFP_KERNEL);
+ const char *tmp;
+ int ret;
+
+ if (!extension_details)
+ return ERR_PTR(-ENOMEM);
+
+ tmp = kstrdup(name, GFP_KERNEL);
+ if (!tmp) {
+ kfree(extension_details);
+ return ERR_PTR(-ENOMEM);
+ }
+ qstr_init(&extension_details->name, tmp);
+ extension_details->num = extensions_value->num;
+ ret = insert_ext_gid_entry(&extension_details->name, extensions_value->num);
+
+ if (ret) {
+ kfree(extension_details->name.name);
+ kfree(extension_details);
+ return ERR_PTR(ret);
+ }
+ config_item_init_type_name(&extension_details->item, name, &extension_details_type);
+
+ return &extension_details->item;
+}
+
+static struct configfs_group_operations extensions_value_group_ops = {
+ .make_item = extension_details_make_item,
+};
+
+static struct config_item_type extensions_name_type = {
+ .ct_group_ops = &extensions_value_group_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+static struct config_group *extensions_make_group(struct config_group *group, const char *name)
+{
+ struct extensions_value *extensions_value;
+ unsigned int tmp;
+ int ret;
+
+ extensions_value = kzalloc(sizeof(struct extensions_value), GFP_KERNEL);
+ if (!extensions_value)
+ return ERR_PTR(-ENOMEM);
+ ret = kstrtouint(name, 10, &tmp);
+ if (ret) {
+ kfree(extensions_value);
+ return ERR_PTR(ret);
+ }
+
+ extensions_value->num = tmp;
+ config_group_init_type_name(&extensions_value->group, name,
+ &extensions_name_type);
+ return &extensions_value->group;
+}
+
+static void extensions_drop_group(struct config_group *group, struct config_item *item)
+{
+ struct extensions_value *value = to_extensions_value(item);
+
+ pr_info("sdcardfs: No longer mapping any files to gid %d\n", value->num);
+ kfree(value);
+}
+
+static struct configfs_group_operations extensions_group_ops = {
+ .make_group = extensions_make_group,
+ .drop_item = extensions_drop_group,
+};
+
+static struct config_item_type extensions_type = {
+ .ct_group_ops = &extensions_group_ops,
+ .ct_owner = THIS_MODULE,
+};
+
+struct config_group extension_group = {
+ .cg_item = {
+ .ci_namebuf = "extensions",
+ .ci_type = &extensions_type,
+ },
+};
+
+static struct config_item *packages_make_item(struct config_group *group, const char *name)
+{
+ struct package_details *package_details;
+ const char *tmp;
+
+ package_details = kzalloc(sizeof(struct package_details), GFP_KERNEL);
+ if (!package_details)
+ return ERR_PTR(-ENOMEM);
+ tmp = kstrdup(name, GFP_KERNEL);
+ if (!tmp) {
+ kfree(package_details);
+ return ERR_PTR(-ENOMEM);
+ }
+ qstr_init(&package_details->name, tmp);
+ config_item_init_type_name(&package_details->item, name,
+ &package_appid_type);
+
+ return &package_details->item;
+}
+
+static ssize_t packages_list_show(struct config_item *item, char *page)
+{
+ struct hashtable_entry *hash_cur_app;
+ struct hashtable_entry *hash_cur_user;
+ int i;
+ int count = 0, written = 0;
+ const char errormsg[] = "<truncated>\n";
+ unsigned int hash;
+
+ rcu_read_lock();
+ hash_for_each_rcu(package_to_appid, i, hash_cur_app, hlist) {
+ written = scnprintf(page + count, PAGE_SIZE - sizeof(errormsg) - count, "%s %d\n",
+ hash_cur_app->key.name, atomic_read(&hash_cur_app->value));
+ hash = hash_cur_app->key.hash;
+ hash_for_each_possible_rcu(package_to_userid, hash_cur_user, hlist, hash) {
+ if (qstr_case_eq(&hash_cur_app->key, &hash_cur_user->key)) {
+ written += scnprintf(page + count + written - 1,
+ PAGE_SIZE - sizeof(errormsg) - count - written + 1,
+ " %d\n", atomic_read(&hash_cur_user->value)) - 1;
+ }
+ }
+ if (count + written == PAGE_SIZE - sizeof(errormsg) - 1) {
+ count += scnprintf(page + count, PAGE_SIZE - count, errormsg);
+ break;
+ }
+ count += written;
+ }
+ rcu_read_unlock();
+
+ return count;
+}
+
+static ssize_t packages_remove_userid_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ unsigned int tmp;
+ int ret;
+
+ ret = kstrtouint(page, 10, &tmp);
+ if (ret)
+ return ret;
+ remove_userid_all_entry(tmp);
+ return count;
+}
+
+static struct configfs_attribute packages_attr_packages_gid_list = {
+ .ca_name = "packages_gid.list",
+ .ca_mode = S_IRUGO,
+ .ca_owner = THIS_MODULE,
+ .show = packages_list_show,
+};
+
+SDCARDFS_CONFIGFS_ATTR_WO(packages_, remove_userid);
+
+static struct configfs_attribute *packages_attrs[] = {
+ &packages_attr_packages_gid_list,
+ &packages_attr_remove_userid,
+ NULL,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations packages_group_ops = {
+ .make_item = packages_make_item,
+};
+
+static struct config_item_type packages_type = {
+ .ct_group_ops = &packages_group_ops,
+ .ct_attrs = packages_attrs,
+ .ct_owner = THIS_MODULE,
+};
+
+struct config_group *sd_default_groups[] = {
+ &extension_group,
+ NULL,
+};
+
+static struct configfs_subsystem sdcardfs_packages = {
+ .su_group = {
+ .cg_item = {
+ .ci_namebuf = "sdcardfs",
+ .ci_type = &packages_type,
+ },
+ },
+};
+
+static int configfs_sdcardfs_init(void)
+{
+ int ret, i;
+ struct configfs_subsystem *subsys = &sdcardfs_packages;
+
+ config_group_init(&subsys->su_group);
+ for (i = 0; sd_default_groups[i]; i++) {
+ config_group_init(sd_default_groups[i]);
+ configfs_add_default_group(sd_default_groups[i], &subsys->su_group);
+ }
+ mutex_init(&subsys->su_mutex);
+ ret = configfs_register_subsystem(subsys);
+ if (ret) {
+ pr_err("Error %d while registering subsystem %s\n",
+ ret,
+ subsys->su_group.cg_item.ci_namebuf);
+ }
+ return ret;
+}
+
+static void configfs_sdcardfs_exit(void)
+{
+ configfs_unregister_subsystem(&sdcardfs_packages);
+}
+
+int packagelist_init(void)
+{
+ hashtable_entry_cachep =
+ kmem_cache_create("packagelist_hashtable_entry",
+ sizeof(struct hashtable_entry), 0, 0, NULL);
+ if (!hashtable_entry_cachep) {
+ pr_err("sdcardfs: failed creating pkgl_hashtable entry slab cache\n");
+ return -ENOMEM;
+ }
+
+ configfs_sdcardfs_init();
+ return 0;
+}
+
+void packagelist_exit(void)
+{
+ configfs_sdcardfs_exit();
+ packagelist_destroy();
+ kmem_cache_destroy(hashtable_entry_cachep);
+}
diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h
new file mode 100644
index 0000000..6219771
--- /dev/null
+++ b/fs/sdcardfs/sdcardfs.h
@@ -0,0 +1,654 @@
+/*
+ * fs/sdcardfs/sdcardfs.h
+ *
+ * The sdcardfs v2.0
+ * This file system replaces the sdcard daemon on Android
+ * On version 2.0, some of the daemon functions have been ported
+ * to support the multi-user concepts of Android 4.4
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#ifndef _SDCARDFS_H_
+#define _SDCARDFS_H_
+
+#include <linux/dcache.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/aio.h>
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include <linux/fs_stack.h>
+#include <linux/magic.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/security.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include "multiuser.h"
+
+/* the file system name */
+#define SDCARDFS_NAME "sdcardfs"
+
+/* sdcardfs root inode number */
+#define SDCARDFS_ROOT_INO 1
+
+/* useful for tracking code reachability */
+#define UDBG pr_default("DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__)
+
+#define SDCARDFS_DIRENT_SIZE 256
+
+/* temporary static uid settings for development */
+#define AID_ROOT 0 /* uid for accessing /mnt/sdcard & extSdcard */
+#define AID_MEDIA_RW 1023 /* internal media storage write access */
+
+#define AID_SDCARD_RW 1015 /* external storage write access */
+#define AID_SDCARD_R 1028 /* external storage read access */
+#define AID_SDCARD_PICS 1033 /* external storage photos access */
+#define AID_SDCARD_AV 1034 /* external storage audio/video access */
+#define AID_SDCARD_ALL 1035 /* access all users external storage */
+#define AID_MEDIA_OBB 1059 /* obb files */
+
+#define AID_SDCARD_IMAGE 1057
+
+#define AID_PACKAGE_INFO 1027
+
+
+/*
+ * Permissions are handled by our permission function.
+ * We don't want anyone who happens to look at our inode value to prematurely
+ * block access, so store more permissive values. These are probably never
+ * used.
+ */
+#define fixup_tmp_permissions(x) \
+ do { \
+ (x)->i_uid = make_kuid(&init_user_ns, \
+ SDCARDFS_I(x)->data->d_uid); \
+ (x)->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW); \
+ (x)->i_mode = ((x)->i_mode & S_IFMT) | 0775;\
+ } while (0)
+
+/* Android 5.0 support */
+
+/* Permission mode for a specific node. Controls how file permissions
+ * are derived for children nodes.
+ */
+typedef enum {
+ /* Nothing special; this node should just inherit from its parent. */
+ PERM_INHERIT,
+ /* This node is one level above a normal root; used for legacy layouts
+ * which use the first level to represent user_id.
+ */
+ PERM_PRE_ROOT,
+ /* This node is "/" */
+ PERM_ROOT,
+ /* This node is "/Android" */
+ PERM_ANDROID,
+ /* This node is "/Android/data" */
+ PERM_ANDROID_DATA,
+ /* This node is "/Android/obb" */
+ PERM_ANDROID_OBB,
+ /* This node is "/Android/media" */
+ PERM_ANDROID_MEDIA,
+ /* This node is "/Android/[data|media|obb]/[package]" */
+ PERM_ANDROID_PACKAGE,
+ /* This node is "/Android/[data|media|obb]/[package]/cache" */
+ PERM_ANDROID_PACKAGE_CACHE,
+} perm_t;
+
+struct sdcardfs_sb_info;
+struct sdcardfs_mount_options;
+struct sdcardfs_inode_info;
+struct sdcardfs_inode_data;
+
+/* Do not directly use this function. Use OVERRIDE_CRED() instead. */
+const struct cred *override_fsids(struct sdcardfs_sb_info *sbi,
+ struct sdcardfs_inode_data *data);
+/* Do not directly use this function, use REVERT_CRED() instead. */
+void revert_fsids(const struct cred *old_cred);
+
+/* operations vectors defined in specific files */
+extern const struct file_operations sdcardfs_main_fops;
+extern const struct file_operations sdcardfs_dir_fops;
+extern const struct inode_operations sdcardfs_main_iops;
+extern const struct inode_operations sdcardfs_dir_iops;
+extern const struct inode_operations sdcardfs_symlink_iops;
+extern const struct super_operations sdcardfs_sops;
+extern const struct dentry_operations sdcardfs_ci_dops;
+extern const struct address_space_operations sdcardfs_aops, sdcardfs_dummy_aops;
+extern const struct vm_operations_struct sdcardfs_vm_ops;
+
+extern int sdcardfs_init_inode_cache(void);
+extern void sdcardfs_destroy_inode_cache(void);
+extern int sdcardfs_init_dentry_cache(void);
+extern void sdcardfs_destroy_dentry_cache(void);
+extern int new_dentry_private_data(struct dentry *dentry);
+extern void free_dentry_private_data(struct dentry *dentry);
+extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags);
+extern struct inode *sdcardfs_iget(struct super_block *sb,
+ struct inode *lower_inode, userid_t id);
+extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb,
+ struct path *lower_path, userid_t id);
+
+/* file private data */
+struct sdcardfs_file_info {
+ struct file *lower_file;
+ const struct vm_operations_struct *lower_vm_ops;
+};
+
+struct sdcardfs_inode_data {
+ struct kref refcount;
+ bool abandoned;
+
+ perm_t perm;
+ userid_t userid;
+ uid_t d_uid;
+ bool under_android;
+ bool under_cache;
+ bool under_obb;
+};
+
+/* sdcardfs inode data in memory */
+struct sdcardfs_inode_info {
+ struct inode *lower_inode;
+ /* state derived based on current position in hierarchy */
+ struct sdcardfs_inode_data *data;
+
+ /* top folder for ownership */
+ spinlock_t top_lock;
+ struct sdcardfs_inode_data *top_data;
+
+ struct inode vfs_inode;
+};
+
+
+/* sdcardfs dentry data in memory */
+struct sdcardfs_dentry_info {
+ spinlock_t lock; /* protects lower_path */
+ struct path lower_path;
+ struct path orig_path;
+};
+
+struct sdcardfs_mount_options {
+ uid_t fs_low_uid;
+ gid_t fs_low_gid;
+ userid_t fs_user_id;
+ bool multiuser;
+ bool gid_derivation;
+ bool default_normal;
+ bool unshared_obb;
+ unsigned int reserved_mb;
+ bool nocache;
+};
+
+struct sdcardfs_vfsmount_options {
+ gid_t gid;
+ mode_t mask;
+};
+
+extern int parse_options_remount(struct super_block *sb, char *options, int silent,
+ struct sdcardfs_vfsmount_options *vfsopts);
+
+/* sdcardfs super-block data in memory */
+struct sdcardfs_sb_info {
+ struct super_block *sb;
+ struct super_block *lower_sb;
+ /* derived perm policy : some of options have been added
+ * to sdcardfs_mount_options (Android 4.4 support)
+ */
+ struct sdcardfs_mount_options options;
+ spinlock_t lock; /* protects obbpath */
+ char *obbpath_s;
+ struct path obbpath;
+ void *pkgl_id;
+ struct list_head list;
+};
+
+/*
+ * inode to private data
+ *
+ * Since we use containers and the struct inode is _inside_ the
+ * sdcardfs_inode_info structure, SDCARDFS_I will always (given a non-NULL
+ * inode pointer), return a valid non-NULL pointer.
+ */
+static inline struct sdcardfs_inode_info *SDCARDFS_I(const struct inode *inode)
+{
+ return container_of(inode, struct sdcardfs_inode_info, vfs_inode);
+}
+
+/* dentry to private data */
+#define SDCARDFS_D(dent) ((struct sdcardfs_dentry_info *)(dent)->d_fsdata)
+
+/* superblock to private data */
+#define SDCARDFS_SB(super) ((struct sdcardfs_sb_info *)(super)->s_fs_info)
+
+/* file to private Data */
+#define SDCARDFS_F(file) ((struct sdcardfs_file_info *)((file)->private_data))
+
+/* file to lower file */
+static inline struct file *sdcardfs_lower_file(const struct file *f)
+{
+ return SDCARDFS_F(f)->lower_file;
+}
+
+static inline void sdcardfs_set_lower_file(struct file *f, struct file *val)
+{
+ SDCARDFS_F(f)->lower_file = val;
+}
+
+/* inode to lower inode. */
+static inline struct inode *sdcardfs_lower_inode(const struct inode *i)
+{
+ return SDCARDFS_I(i)->lower_inode;
+}
+
+static inline void sdcardfs_set_lower_inode(struct inode *i, struct inode *val)
+{
+ SDCARDFS_I(i)->lower_inode = val;
+}
+
+/* superblock to lower superblock */
+static inline struct super_block *sdcardfs_lower_super(
+ const struct super_block *sb)
+{
+ return SDCARDFS_SB(sb)->lower_sb;
+}
+
+static inline void sdcardfs_set_lower_super(struct super_block *sb,
+ struct super_block *val)
+{
+ SDCARDFS_SB(sb)->lower_sb = val;
+}
+
+/* path based (dentry/mnt) macros */
+static inline void pathcpy(struct path *dst, const struct path *src)
+{
+ dst->dentry = src->dentry;
+ dst->mnt = src->mnt;
+}
+
+/* sdcardfs_get_pname functions calls path_get()
+ * therefore, the caller must call "proper" path_put functions
+ */
+#define SDCARDFS_DENT_FUNC(pname) \
+static inline void sdcardfs_get_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ pathcpy(pname, &SDCARDFS_D(dent)->pname); \
+ path_get(pname); \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_put_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ path_put(pname); \
+ return; \
+} \
+static inline void sdcardfs_set_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ pathcpy(&SDCARDFS_D(dent)->pname, pname); \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_reset_##pname(const struct dentry *dent) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ SDCARDFS_D(dent)->pname.dentry = NULL; \
+ SDCARDFS_D(dent)->pname.mnt = NULL; \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \
+{ \
+ struct path pname; \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ if (SDCARDFS_D(dent)->pname.dentry) { \
+ pathcpy(&pname, &SDCARDFS_D(dent)->pname); \
+ SDCARDFS_D(dent)->pname.dentry = NULL; \
+ SDCARDFS_D(dent)->pname.mnt = NULL; \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ path_put(&pname); \
+ } else \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+}
+
+SDCARDFS_DENT_FUNC(lower_path)
+SDCARDFS_DENT_FUNC(orig_path)
+
+static inline bool sbinfo_has_sdcard_magic(struct sdcardfs_sb_info *sbinfo)
+{
+ return sbinfo && sbinfo->sb
+ && sbinfo->sb->s_magic == SDCARDFS_SUPER_MAGIC;
+}
+
+static inline struct sdcardfs_inode_data *data_get(
+ struct sdcardfs_inode_data *data)
+{
+ if (data)
+ kref_get(&data->refcount);
+ return data;
+}
+
+static inline struct sdcardfs_inode_data *top_data_get(
+ struct sdcardfs_inode_info *info)
+{
+ struct sdcardfs_inode_data *top_data;
+
+ spin_lock(&info->top_lock);
+ top_data = data_get(info->top_data);
+ spin_unlock(&info->top_lock);
+ return top_data;
+}
+
+extern void data_release(struct kref *ref);
+
+static inline void data_put(struct sdcardfs_inode_data *data)
+{
+ kref_put(&data->refcount, data_release);
+}
+
+static inline void release_own_data(struct sdcardfs_inode_info *info)
+{
+ /*
+ * This happens exactly once per inode. At this point, the inode that
+ * originally held this data is about to be freed, and all references
+ * to it are held as a top value, and will likely be released soon.
+ */
+ info->data->abandoned = true;
+ data_put(info->data);
+}
+
+static inline void set_top(struct sdcardfs_inode_info *info,
+ struct sdcardfs_inode_info *top_owner)
+{
+ struct sdcardfs_inode_data *old_top;
+ struct sdcardfs_inode_data *new_top = NULL;
+
+ if (top_owner)
+ new_top = top_data_get(top_owner);
+
+ spin_lock(&info->top_lock);
+ old_top = info->top_data;
+ info->top_data = new_top;
+ if (old_top)
+ data_put(old_top);
+ spin_unlock(&info->top_lock);
+}
+
+static inline int get_gid(struct vfsmount *mnt,
+ struct super_block *sb,
+ struct sdcardfs_inode_data *data)
+{
+ struct sdcardfs_vfsmount_options *vfsopts = mnt->data;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(sb);
+
+ if (vfsopts->gid == AID_SDCARD_RW && !sbi->options.default_normal)
+ /* As an optimization, certain trusted system components only run
+ * as owner but operate across all users. Since we're now handing
+ * out the sdcard_rw GID only to trusted apps, we're okay relaxing
+ * the user boundary enforcement for the default view. The UIDs
+ * assigned to app directories are still multiuser aware.
+ */
+ return AID_SDCARD_RW;
+ else
+ return multiuser_get_uid(data->userid, vfsopts->gid);
+}
+
+static inline int get_mode(struct vfsmount *mnt,
+ struct sdcardfs_inode_info *info,
+ struct sdcardfs_inode_data *data)
+{
+ int owner_mode;
+ int filtered_mode;
+ struct sdcardfs_vfsmount_options *opts = mnt->data;
+ int visible_mode = 0775 & ~opts->mask;
+
+
+ if (data->perm == PERM_PRE_ROOT) {
+ /* Top of multi-user view should always be visible to ensure
+ * secondary users can traverse inside.
+ */
+ visible_mode = 0711;
+ } else if (data->under_android) {
+ /* Block "other" access to Android directories, since only apps
+ * belonging to a specific user should be in there; we still
+ * leave +x open for the default view.
+ */
+ if (opts->gid == AID_SDCARD_RW)
+ visible_mode = visible_mode & ~0006;
+ else
+ visible_mode = visible_mode & ~0007;
+ }
+ owner_mode = info->lower_inode->i_mode & 0700;
+ filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6));
+ return filtered_mode;
+}
+
+static inline int has_graft_path(const struct dentry *dent)
+{
+ int ret = 0;
+
+ spin_lock(&SDCARDFS_D(dent)->lock);
+ if (SDCARDFS_D(dent)->orig_path.dentry != NULL)
+ ret = 1;
+ spin_unlock(&SDCARDFS_D(dent)->lock);
+
+ return ret;
+}
+
+static inline void sdcardfs_get_real_lower(const struct dentry *dent,
+ struct path *real_lower)
+{
+ /* in case of a local obb dentry
+ * the orig_path should be returned
+ */
+ if (has_graft_path(dent))
+ sdcardfs_get_orig_path(dent, real_lower);
+ else
+ sdcardfs_get_lower_path(dent, real_lower);
+}
+
+static inline void sdcardfs_put_real_lower(const struct dentry *dent,
+ struct path *real_lower)
+{
+ if (has_graft_path(dent))
+ sdcardfs_put_orig_path(dent, real_lower);
+ else
+ sdcardfs_put_lower_path(dent, real_lower);
+}
+
+extern struct mutex sdcardfs_super_list_lock;
+extern struct list_head sdcardfs_super_list;
+
+/* for packagelist.c */
+extern appid_t get_appid(const char *app_name);
+extern appid_t get_ext_gid(const char *app_name);
+extern appid_t is_excluded(const char *app_name, userid_t userid);
+extern int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name);
+extern int packagelist_init(void);
+extern void packagelist_exit(void);
+
+/* for derived_perm.c */
+#define BY_NAME (1 << 0)
+#define BY_USERID (1 << 1)
+struct limit_search {
+ unsigned int flags;
+ struct qstr name;
+ userid_t userid;
+};
+
+extern void setup_derived_state(struct inode *inode, perm_t perm,
+ userid_t userid, uid_t uid);
+extern void get_derived_permission(struct dentry *parent, struct dentry *dentry);
+extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, const struct qstr *name);
+extern void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit);
+
+extern void update_derived_permission_lock(struct dentry *dentry);
+void fixup_lower_ownership(struct dentry *dentry, const char *name);
+extern int need_graft_path(struct dentry *dentry);
+extern int is_base_obbpath(struct dentry *dentry);
+extern int is_obbpath_invalid(struct dentry *dentry);
+extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path);
+
+/* locking helpers */
+static inline struct dentry *lock_parent(struct dentry *dentry)
+{
+ struct dentry *dir = dget_parent(dentry);
+
+ inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
+ return dir;
+}
+
+static inline void unlock_dir(struct dentry *dir)
+{
+ inode_unlock(d_inode(dir));
+ dput(dir);
+}
+
+static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t mode)
+{
+ int err;
+ struct dentry *dent;
+ struct iattr attrs;
+ struct path parent;
+
+ dent = kern_path_locked(path_s, &parent);
+ if (IS_ERR(dent)) {
+ err = PTR_ERR(dent);
+ if (err == -EEXIST)
+ err = 0;
+ goto out_unlock;
+ }
+
+ err = vfs_mkdir2(parent.mnt, d_inode(parent.dentry), dent, mode);
+ if (err) {
+ if (err == -EEXIST)
+ err = 0;
+ goto out_dput;
+ }
+
+ attrs.ia_uid = make_kuid(&init_user_ns, uid);
+ attrs.ia_gid = make_kgid(&init_user_ns, gid);
+ attrs.ia_valid = ATTR_UID | ATTR_GID;
+ inode_lock(d_inode(dent));
+ notify_change2(parent.mnt, dent, &attrs, NULL);
+ inode_unlock(d_inode(dent));
+
+out_dput:
+ dput(dent);
+
+out_unlock:
+ /* parent dentry locked by lookup_create */
+ inode_unlock(d_inode(parent.dentry));
+ path_put(&parent);
+ return err;
+}
+
+/*
+ * Return 1, if a disk has enough free space, otherwise 0.
+ * We assume that any files can not be overwritten.
+ */
+static inline int check_min_free_space(struct dentry *dentry, size_t size, int dir)
+{
+ int err;
+ struct path lower_path;
+ struct kstatfs statfs;
+ u64 avail;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ if (sbi->options.reserved_mb) {
+ /* Get fs stat of lower filesystem. */
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_statfs(&lower_path, &statfs);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+
+ if (unlikely(err))
+ return 0;
+
+ /* Invalid statfs informations. */
+ if (unlikely(statfs.f_bsize == 0))
+ return 0;
+
+ /* if you are checking directory, set size to f_bsize. */
+ if (unlikely(dir))
+ size = statfs.f_bsize;
+
+ /* available size */
+ avail = statfs.f_bavail * statfs.f_bsize;
+
+ /* not enough space */
+ if ((u64)size > avail)
+ return 0;
+
+ /* enough space */
+ if ((avail - size) > (sbi->options.reserved_mb * 1024 * 1024))
+ return 1;
+
+ return 0;
+ } else
+ return 1;
+}
+
+/*
+ * Copies attrs and maintains sdcardfs managed attrs
+ * Since our permission check handles all special permissions, set those to be open
+ */
+static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src)
+{
+ dest->i_mode = (src->i_mode & S_IFMT) | S_IRWXU | S_IRWXG |
+ S_IROTH | S_IXOTH; /* 0775 */
+ dest->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(dest)->data->d_uid);
+ dest->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW);
+ dest->i_rdev = src->i_rdev;
+ dest->i_atime = src->i_atime;
+ dest->i_mtime = src->i_mtime;
+ dest->i_ctime = src->i_ctime;
+ dest->i_blkbits = src->i_blkbits;
+ dest->i_flags = src->i_flags;
+ set_nlink(dest, src->i_nlink);
+}
+
+static inline bool str_case_eq(const char *s1, const char *s2)
+{
+ return !strcasecmp(s1, s2);
+}
+
+static inline bool str_n_case_eq(const char *s1, const char *s2, size_t len)
+{
+ return !strncasecmp(s1, s2, len);
+}
+
+static inline bool qstr_case_eq(const struct qstr *q1, const struct qstr *q2)
+{
+ return q1->len == q2->len && str_n_case_eq(q1->name, q2->name, q2->len);
+}
+
+#define QSTR_LITERAL(string) QSTR_INIT(string, sizeof(string)-1)
+
+#endif /* not _SDCARDFS_H_ */
diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c
new file mode 100644
index 0000000..140696e
--- /dev/null
+++ b/fs/sdcardfs/super.c
@@ -0,0 +1,333 @@
+/*
+ * fs/sdcardfs/super.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+/*
+ * The inode cache is used with alloc_inode for both our inode info and the
+ * vfs inode.
+ */
+static struct kmem_cache *sdcardfs_inode_cachep;
+
+/*
+ * To support the top references, we must track some data separately.
+ * An sdcardfs_inode_info always has a reference to its data, and once set up,
+ * also has a reference to its top. The top may be itself, in which case it
+ * holds two references to its data. When top is changed, it takes a ref to the
+ * new data and then drops the ref to the old data.
+ */
+static struct kmem_cache *sdcardfs_inode_data_cachep;
+
+void data_release(struct kref *ref)
+{
+ struct sdcardfs_inode_data *data =
+ container_of(ref, struct sdcardfs_inode_data, refcount);
+
+ kmem_cache_free(sdcardfs_inode_data_cachep, data);
+}
+
+/* final actions when unmounting a file system */
+static void sdcardfs_put_super(struct super_block *sb)
+{
+ struct sdcardfs_sb_info *spd;
+ struct super_block *s;
+
+ spd = SDCARDFS_SB(sb);
+ if (!spd)
+ return;
+
+ if (spd->obbpath_s) {
+ kfree(spd->obbpath_s);
+ path_put(&spd->obbpath);
+ }
+
+ /* decrement lower super references */
+ s = sdcardfs_lower_super(sb);
+ sdcardfs_set_lower_super(sb, NULL);
+ atomic_dec(&s->s_active);
+
+ kfree(spd);
+ sb->s_fs_info = NULL;
+}
+
+static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ int err;
+ struct path lower_path;
+ u32 min_blocks;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_statfs(&lower_path, buf);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+
+ if (sbi->options.reserved_mb) {
+ /* Invalid statfs informations. */
+ if (buf->f_bsize == 0) {
+ pr_err("Returned block size is zero.\n");
+ return -EINVAL;
+ }
+
+ min_blocks = ((sbi->options.reserved_mb * 1024 * 1024)/buf->f_bsize);
+ buf->f_blocks -= min_blocks;
+
+ if (buf->f_bavail > min_blocks)
+ buf->f_bavail -= min_blocks;
+ else
+ buf->f_bavail = 0;
+
+ /* Make reserved blocks invisiable to media storage */
+ buf->f_bfree = buf->f_bavail;
+ }
+
+ /* set return buf to our f/s to avoid confusing user-level utils */
+ buf->f_type = SDCARDFS_SUPER_MAGIC;
+
+ return err;
+}
+
+/*
+ * @flags: numeric mount options
+ * @options: mount options string
+ */
+static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options)
+{
+ int err = 0;
+
+ /*
+ * The VFS will take care of "ro" and "rw" flags among others. We
+ * can safely accept a few flags (RDONLY, MANDLOCK), and honor
+ * SILENT, but anything else left over is an error.
+ */
+ if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) {
+ pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+/*
+ * @mnt: mount point we are remounting
+ * @sb: superblock we are remounting
+ * @flags: numeric mount options
+ * @options: mount options string
+ */
+static int sdcardfs_remount_fs2(struct vfsmount *mnt, struct super_block *sb,
+ int *flags, char *options)
+{
+ int err = 0;
+
+ /*
+ * The VFS will take care of "ro" and "rw" flags among others. We
+ * can safely accept a few flags (RDONLY, MANDLOCK), and honor
+ * SILENT, but anything else left over is an error.
+ */
+ if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT | MS_REMOUNT)) != 0) {
+ pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags);
+ err = -EINVAL;
+ }
+ pr_info("Remount options were %s for vfsmnt %p.\n", options, mnt);
+ err = parse_options_remount(sb, options, *flags & ~MS_SILENT, mnt->data);
+
+
+ return err;
+}
+
+static void *sdcardfs_clone_mnt_data(void *data)
+{
+ struct sdcardfs_vfsmount_options *opt = kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL);
+ struct sdcardfs_vfsmount_options *old = data;
+
+ if (!opt)
+ return NULL;
+ opt->gid = old->gid;
+ opt->mask = old->mask;
+ return opt;
+}
+
+static void sdcardfs_copy_mnt_data(void *data, void *newdata)
+{
+ struct sdcardfs_vfsmount_options *old = data;
+ struct sdcardfs_vfsmount_options *new = newdata;
+
+ old->gid = new->gid;
+ old->mask = new->mask;
+}
+
+/*
+ * Called by iput() when the inode reference count reached zero
+ * and the inode is not hashed anywhere. Used to clear anything
+ * that needs to be, before the inode is completely destroyed and put
+ * on the inode free list.
+ */
+static void sdcardfs_evict_inode(struct inode *inode)
+{
+ struct inode *lower_inode;
+
+ truncate_inode_pages(&inode->i_data, 0);
+ set_top(SDCARDFS_I(inode), NULL);
+ clear_inode(inode);
+ /*
+ * Decrement a reference to a lower_inode, which was incremented
+ * by our read_inode when it was created initially.
+ */
+ lower_inode = sdcardfs_lower_inode(inode);
+ sdcardfs_set_lower_inode(inode, NULL);
+ iput(lower_inode);
+}
+
+static struct inode *sdcardfs_alloc_inode(struct super_block *sb)
+{
+ struct sdcardfs_inode_info *i;
+ struct sdcardfs_inode_data *d;
+
+ i = kmem_cache_alloc(sdcardfs_inode_cachep, GFP_KERNEL);
+ if (!i)
+ return NULL;
+
+ /* memset everything up to the inode to 0 */
+ memset(i, 0, offsetof(struct sdcardfs_inode_info, vfs_inode));
+
+ d = kmem_cache_alloc(sdcardfs_inode_data_cachep,
+ GFP_KERNEL | __GFP_ZERO);
+ if (!d) {
+ kmem_cache_free(sdcardfs_inode_cachep, i);
+ return NULL;
+ }
+
+ i->data = d;
+ kref_init(&d->refcount);
+ i->top_data = d;
+ spin_lock_init(&i->top_lock);
+ kref_get(&d->refcount);
+
+ i->vfs_inode.i_version = 1;
+ return &i->vfs_inode;
+}
+
+static void i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+
+ release_own_data(SDCARDFS_I(inode));
+ kmem_cache_free(sdcardfs_inode_cachep, SDCARDFS_I(inode));
+}
+
+static void sdcardfs_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, i_callback);
+}
+
+/* sdcardfs inode cache constructor */
+static void init_once(void *obj)
+{
+ struct sdcardfs_inode_info *i = obj;
+
+ inode_init_once(&i->vfs_inode);
+}
+
+int sdcardfs_init_inode_cache(void)
+{
+ sdcardfs_inode_cachep =
+ kmem_cache_create("sdcardfs_inode_cache",
+ sizeof(struct sdcardfs_inode_info), 0,
+ SLAB_RECLAIM_ACCOUNT, init_once);
+
+ if (!sdcardfs_inode_cachep)
+ return -ENOMEM;
+
+ sdcardfs_inode_data_cachep =
+ kmem_cache_create("sdcardfs_inode_data_cache",
+ sizeof(struct sdcardfs_inode_data), 0,
+ SLAB_RECLAIM_ACCOUNT, NULL);
+ if (!sdcardfs_inode_data_cachep) {
+ kmem_cache_destroy(sdcardfs_inode_cachep);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/* sdcardfs inode cache destructor */
+void sdcardfs_destroy_inode_cache(void)
+{
+ kmem_cache_destroy(sdcardfs_inode_data_cachep);
+ kmem_cache_destroy(sdcardfs_inode_cachep);
+}
+
+/*
+ * Used only in nfs, to kill any pending RPC tasks, so that subsequent
+ * code can actually succeed and won't leave tasks that need handling.
+ */
+static void sdcardfs_umount_begin(struct super_block *sb)
+{
+ struct super_block *lower_sb;
+
+ lower_sb = sdcardfs_lower_super(sb);
+ if (lower_sb && lower_sb->s_op && lower_sb->s_op->umount_begin)
+ lower_sb->s_op->umount_begin(lower_sb);
+}
+
+static int sdcardfs_show_options(struct vfsmount *mnt, struct seq_file *m,
+ struct dentry *root)
+{
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb);
+ struct sdcardfs_mount_options *opts = &sbi->options;
+ struct sdcardfs_vfsmount_options *vfsopts = mnt->data;
+
+ if (opts->fs_low_uid != 0)
+ seq_printf(m, ",fsuid=%u", opts->fs_low_uid);
+ if (opts->fs_low_gid != 0)
+ seq_printf(m, ",fsgid=%u", opts->fs_low_gid);
+ if (vfsopts->gid != 0)
+ seq_printf(m, ",gid=%u", vfsopts->gid);
+ if (opts->multiuser)
+ seq_puts(m, ",multiuser");
+ if (vfsopts->mask)
+ seq_printf(m, ",mask=%u", vfsopts->mask);
+ if (opts->fs_user_id)
+ seq_printf(m, ",userid=%u", opts->fs_user_id);
+ if (opts->gid_derivation)
+ seq_puts(m, ",derive_gid");
+ if (opts->default_normal)
+ seq_puts(m, ",default_normal");
+ if (opts->reserved_mb != 0)
+ seq_printf(m, ",reserved=%uMB", opts->reserved_mb);
+ if (opts->nocache)
+ seq_printf(m, ",nocache");
+
+ return 0;
+};
+
+const struct super_operations sdcardfs_sops = {
+ .put_super = sdcardfs_put_super,
+ .statfs = sdcardfs_statfs,
+ .remount_fs = sdcardfs_remount_fs,
+ .remount_fs2 = sdcardfs_remount_fs2,
+ .clone_mnt_data = sdcardfs_clone_mnt_data,
+ .copy_mnt_data = sdcardfs_copy_mnt_data,
+ .evict_inode = sdcardfs_evict_inode,
+ .umount_begin = sdcardfs_umount_begin,
+ .show_options2 = sdcardfs_show_options,
+ .alloc_inode = sdcardfs_alloc_inode,
+ .destroy_inode = sdcardfs_destroy_inode,
+ .drop_inode = generic_delete_inode,
+};
diff --git a/fs/super.c b/fs/super.c
index 377c439..bbf512c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -771,7 +771,8 @@ struct super_block *user_get_super(dev_t dev)
}
/**
- * do_remount_sb - asks filesystem to change mount options.
+ * do_remount_sb2 - asks filesystem to change mount options.
+ * @mnt: mount we are looking at
* @sb: superblock in question
* @flags: numeric part of options
* @data: the rest of options
@@ -779,7 +780,7 @@ struct super_block *user_get_super(dev_t dev)
*
* Alters the mount options of a mounted file system.
*/
-int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
+int do_remount_sb2(struct vfsmount *mnt, struct super_block *sb, int flags, void *data, int force)
{
int retval;
int remount_ro;
@@ -821,7 +822,16 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
}
}
- if (sb->s_op->remount_fs) {
+ if (mnt && sb->s_op->remount_fs2) {
+ retval = sb->s_op->remount_fs2(mnt, sb, &flags, data);
+ if (retval) {
+ if (!force)
+ goto cancel_readonly;
+ /* If forced remount, go ahead despite any errors */
+ WARN(1, "forced remount of a %s fs returned %i\n",
+ sb->s_type->name, retval);
+ }
+ } else if (sb->s_op->remount_fs) {
retval = sb->s_op->remount_fs(sb, &flags, data);
if (retval) {
if (!force)
@@ -853,12 +863,17 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
return retval;
}
+int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
+{
+ return do_remount_sb2(NULL, sb, flags, data, force);
+}
+
static void do_emergency_remount(struct work_struct *work)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
- list_for_each_entry(sb, &super_blocks, s_list) {
+ list_for_each_entry_reverse(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
sb->s_count++;
@@ -1178,7 +1193,7 @@ struct dentry *mount_single(struct file_system_type *fs_type,
EXPORT_SYMBOL(mount_single);
struct dentry *
-mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
+mount_fs(struct file_system_type *type, int flags, const char *name, struct vfsmount *mnt, void *data)
{
struct dentry *root;
struct super_block *sb;
@@ -1195,7 +1210,10 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
goto out_free_secdata;
}
- root = type->mount(type, flags, name, data);
+ if (type->mount2)
+ root = type->mount2(mnt, type, flags, name, data);
+ else
+ root = type->mount(type, flags, name, data);
if (IS_ERR(root)) {
error = PTR_ERR(root);
goto out_free_secdata;
diff --git a/fs/sync.c b/fs/sync.c
index 2a54c1f..5c2420c 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -218,6 +218,7 @@ static int do_fsync(unsigned int fd, int datasync)
if (f.file) {
ret = vfs_fsync(f.file, datasync);
fdput(f);
+ inc_syscfs(current);
}
return ret;
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index de63d4e..1b47013 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -496,7 +496,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
new_flags, vma->anon_vma,
vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
- NULL_VM_UFFD_CTX);
+ NULL_VM_UFFD_CTX,
+ vma_get_anon_name(vma));
if (prev)
vma = prev;
else
@@ -838,6 +839,18 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
goto out_unlock;
/*
+ * UFFDIO_COPY will fill file holes even without
+ * PROT_WRITE. This check enforces that if this is a
+ * MAP_SHARED, the process has write permission to the backing
+ * file. If VM_MAYWRITE is set it also enforces that on a
+ * MAP_SHARED vma: there is no F_WRITE_SEAL and no further
+ * F_WRITE_SEAL can be taken until the vma is destroyed.
+ */
+ ret = -EPERM;
+ if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
+ goto out_unlock;
+
+ /*
* Check that this vma isn't already owned by a
* different userfaultfd. We can't allow more than one
* userfaultfd to own a single vma simultaneously or we
@@ -862,6 +875,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
BUG_ON(vma->vm_ops);
BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
vma->vm_userfaultfd_ctx.ctx != ctx);
+ WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
/*
* Nothing to do: this vma is already registered into this
@@ -879,7 +893,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
- ((struct vm_userfaultfd_ctx){ ctx }));
+ ((struct vm_userfaultfd_ctx){ ctx }),
+ vma_get_anon_name(vma));
if (prev) {
vma = prev;
goto next;
@@ -1003,6 +1018,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
cond_resched();
BUG_ON(vma->vm_ops);
+ WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
/*
* Nothing to do: this vma is already registered into this
@@ -1019,7 +1035,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
- NULL_VM_UFFD_CTX);
+ NULL_VM_UFFD_CTX,
+ vma_get_anon_name(vma));
if (prev) {
vma = prev;
goto next;
diff --git a/fs/utimes.c b/fs/utimes.c
index 22307cd..87ce37b 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -91,7 +91,7 @@ static int utimes_common(struct path *path, struct timespec *times)
}
retry_deleg:
inode_lock(inode);
- error = notify_change(path->dentry, &newattrs, &delegated_inode);
+ error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
diff --git a/fs/xattr.c b/fs/xattr.c
index c0fd99c..e4c1cb9 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -130,7 +130,7 @@ xattr_permission(struct inode *inode, const char *name, int mask)
return -EPERM;
}
- return inode_permission(inode, mask);
+ return inode_permission2(ERR_PTR(-EOPNOTSUPP), inode, mask);
}
int
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 4df64a1..e02a3d9 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -27,6 +27,8 @@
* __kprobes_text_start, __kprobes_text_end
* __entry_text_start, __entry_text_end
* __ctors_start, __ctors_end
+ * __irqentry_text_start, __irqentry_text_end
+ * __softirqentry_text_start, __softirqentry_text_end
*/
extern char _text[], _stext[], _etext[];
extern char _data[], _sdata[], _edata[];
@@ -39,6 +41,8 @@ extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
extern char __entry_text_start[], __entry_text_end[];
extern char __start_rodata[], __end_rodata[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __softirqentry_text_start[], __softirqentry_text_end[];
/* Start and end of .ctors section - used for constructor calls. */
extern char __ctors_start[], __ctors_end[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3619856..63ba505 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -67,10 +67,12 @@
*/
#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
#define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
+#define TEXT_CFI_MAIN .text.cfi .text.[0-9a-zA-Z_]*.cfi
#define DATA_MAIN .data .data.[0-9a-zA-Z_]*
#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
#else
#define TEXT_MAIN .text
+#define TEXT_CFI_MAIN .text.cfi
#define DATA_MAIN .data
#define BSS_MAIN .bss
#endif
@@ -105,7 +107,7 @@
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
#define MCOUNT_REC() . = ALIGN(8); \
VMLINUX_SYMBOL(__start_mcount_loc) = .; \
- *(__mcount_loc) \
+ KEEP(*(__mcount_loc)) \
VMLINUX_SYMBOL(__stop_mcount_loc) = .;
#else
#define MCOUNT_REC()
@@ -139,10 +141,10 @@
#ifdef CONFIG_EVENT_TRACING
#define FTRACE_EVENTS() . = ALIGN(8); \
VMLINUX_SYMBOL(__start_ftrace_events) = .; \
- *(_ftrace_events) \
+ KEEP(*(_ftrace_events)) \
VMLINUX_SYMBOL(__stop_ftrace_events) = .; \
VMLINUX_SYMBOL(__start_ftrace_enum_maps) = .; \
- *(_ftrace_enum_map) \
+ KEEP(*(_ftrace_enum_map)) \
VMLINUX_SYMBOL(__stop_ftrace_enum_maps) = .;
#else
#define FTRACE_EVENTS()
@@ -185,8 +187,8 @@
#define _OF_TABLE_1(name) \
. = ALIGN(8); \
VMLINUX_SYMBOL(__##name##_of_table) = .; \
- *(__##name##_of_table) \
- *(__##name##_of_table_end)
+ KEEP(*(__##name##_of_table)) \
+ KEEP(*(__##name##_of_table_end))
#define CLKSRC_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
#define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
@@ -305,28 +307,28 @@
/* PCI quirks */ \
.pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \
- *(.pci_fixup_early) \
+ KEEP(*(.pci_fixup_early)) \
VMLINUX_SYMBOL(__end_pci_fixups_early) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_header) = .; \
- *(.pci_fixup_header) \
+ KEEP(*(.pci_fixup_header)) \
VMLINUX_SYMBOL(__end_pci_fixups_header) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_final) = .; \
- *(.pci_fixup_final) \
+ KEEP(*(.pci_fixup_final)) \
VMLINUX_SYMBOL(__end_pci_fixups_final) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_enable) = .; \
- *(.pci_fixup_enable) \
+ KEEP(*(.pci_fixup_enable)) \
VMLINUX_SYMBOL(__end_pci_fixups_enable) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_resume) = .; \
- *(.pci_fixup_resume) \
+ KEEP(*(.pci_fixup_resume)) \
VMLINUX_SYMBOL(__end_pci_fixups_resume) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_resume_early) = .; \
- *(.pci_fixup_resume_early) \
+ KEEP(*(.pci_fixup_resume_early)) \
VMLINUX_SYMBOL(__end_pci_fixups_resume_early) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_suspend) = .; \
- *(.pci_fixup_suspend) \
+ KEEP(*(.pci_fixup_suspend)) \
VMLINUX_SYMBOL(__end_pci_fixups_suspend) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_suspend_late) = .; \
- *(.pci_fixup_suspend_late) \
+ KEEP(*(.pci_fixup_suspend_late)) \
VMLINUX_SYMBOL(__end_pci_fixups_suspend_late) = .; \
} \
\
@@ -424,7 +426,7 @@
/* Built-in module parameters. */ \
__param : AT(ADDR(__param) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___param) = .; \
- *(__param) \
+ KEEP(*(__param)) \
VMLINUX_SYMBOL(__stop___param) = .; \
} \
\
@@ -464,6 +466,8 @@
*(TEXT_MAIN .text.fixup) \
*(.text.unlikely .text.unlikely.*) \
*(.text.unknown .text.unknown.*) \
+ *(.text..ftrace) \
+ *(TEXT_CFI_MAIN) \
*(.ref.text) \
MEM_KEEP(init.text) \
MEM_KEEP(exit.text) \
@@ -503,28 +507,20 @@
*(.entry.text) \
VMLINUX_SYMBOL(__entry_text_end) = .;
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
#define IRQENTRY_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__irqentry_text_start) = .; \
*(.irqentry.text) \
VMLINUX_SYMBOL(__irqentry_text_end) = .;
-#else
-#define IRQENTRY_TEXT
-#endif
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
#define SOFTIRQENTRY_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__softirqentry_text_start) = .; \
*(.softirqentry.text) \
VMLINUX_SYMBOL(__softirqentry_text_end) = .;
-#else
-#define SOFTIRQENTRY_TEXT
-#endif
/* Section used for early init (in .S files) */
-#define HEAD_TEXT *(.head.text)
+#define HEAD_TEXT KEEP(*(.head.text))
#define HEAD_TEXT_SECTION \
.head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { \
@@ -538,7 +534,7 @@
. = ALIGN(align); \
__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ex_table) = .; \
- *(__ex_table) \
+ KEEP(*(__ex_table)) \
VMLINUX_SYMBOL(__stop___ex_table) = .; \
}
@@ -569,7 +565,7 @@
MEM_DISCARD(init.data) \
KERNEL_CTORS() \
MCOUNT_REC() \
- *(.init.rodata) \
+ *(.init.rodata .init.rodata.*) \
FTRACE_EVENTS() \
TRACE_SYSCALLS() \
KPROBE_BLACKLIST() \
@@ -587,7 +583,7 @@
EARLYCON_TABLE()
#define INIT_TEXT \
- *(.init.text) \
+ *(.init.text .init.text.*) \
*(.text.startup) \
MEM_DISCARD(init.text)
@@ -604,7 +600,7 @@
MEM_DISCARD(exit.text)
#define EXIT_CALL \
- *(.exitcall.exit)
+ KEEP(*(.exitcall.exit))
/*
* bss (Block Started by Symbol) - uninitialized data
@@ -682,7 +678,7 @@
. = ALIGN(8); \
__bug_table : AT(ADDR(__bug_table) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___bug_table) = .; \
- *(__bug_table) \
+ KEEP(*(__bug_table)) \
VMLINUX_SYMBOL(__stop___bug_table) = .; \
}
#else
@@ -711,7 +707,7 @@
#define INIT_SETUP(initsetup_align) \
. = ALIGN(initsetup_align); \
VMLINUX_SYMBOL(__setup_start) = .; \
- *(.init.setup) \
+ KEEP(*(.init.setup)) \
VMLINUX_SYMBOL(__setup_end) = .;
#define INIT_CALLS_LEVEL(level) \
diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
new file mode 100644
index 0000000..d000aa2
--- /dev/null
+++ b/include/crypto/chacha.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values and helper functions for the ChaCha and XChaCha stream ciphers.
+ *
+ * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's
+ * security. Here they share the same key size, tfm context, and setkey
+ * function; only their IV size and encrypt/decrypt function differ.
+ *
+ * The ChaCha paper specifies 20, 12, and 8-round variants. In general, it is
+ * recommended to use the 20-round variant ChaCha20. However, the other
+ * variants can be needed in some performance-sensitive scenarios. The generic
+ * ChaCha code currently allows only the 20 and 12-round variants.
+ */
+
+#ifndef _CRYPTO_CHACHA_H
+#define _CRYPTO_CHACHA_H
+
+#include <linux/types.h>
+#include <linux/crypto.h>
+
+/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
+#define CHACHA_IV_SIZE 16
+
+#define CHACHA_KEY_SIZE 32
+#define CHACHA_BLOCK_SIZE 64
+
+/* 192-bit nonce, then 64-bit stream position */
+#define XCHACHA_IV_SIZE 32
+
+struct chacha_ctx {
+ u32 key[8];
+ int nrounds;
+};
+
+void chacha_block(u32 *state, u8 *stream, int nrounds);
+static inline void chacha20_block(u32 *state, u8 *stream)
+{
+ chacha_block(state, stream, 20);
+}
+void hchacha_block(const u32 *in, u32 *out, int nrounds);
+
+void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv);
+
+int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keysize);
+int crypto_chacha12_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keysize);
+
+int crypto_chacha_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes);
+int crypto_xchacha_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes);
+
+#endif /* _CRYPTO_CHACHA_H */
diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h
deleted file mode 100644
index 20d20f68..0000000
--- a/include/crypto/chacha20.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Common values for the ChaCha20 algorithm
- */
-
-#ifndef _CRYPTO_CHACHA20_H
-#define _CRYPTO_CHACHA20_H
-
-#include <linux/types.h>
-#include <linux/crypto.h>
-
-#define CHACHA20_IV_SIZE 16
-#define CHACHA20_KEY_SIZE 32
-#define CHACHA20_BLOCK_SIZE 64
-
-struct chacha20_ctx {
- u32 key[8];
-};
-
-void chacha20_block(u32 *state, void *stream);
-void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv);
-int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
- unsigned int keysize);
-int crypto_chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- struct scatterlist *src, unsigned int nbytes);
-
-#endif
diff --git a/include/crypto/nhpoly1305.h b/include/crypto/nhpoly1305.h
new file mode 100644
index 0000000..53c0442
--- /dev/null
+++ b/include/crypto/nhpoly1305.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values and helper functions for the NHPoly1305 hash function.
+ */
+
+#ifndef _NHPOLY1305_H
+#define _NHPOLY1305_H
+
+#include <crypto/hash.h>
+#include <crypto/poly1305.h>
+
+/* NH parameterization: */
+
+/* Endianness: little */
+/* Word size: 32 bits (works well on NEON, SSE2, AVX2) */
+
+/* Stride: 2 words (optimal on ARM32 NEON; works okay on other CPUs too) */
+#define NH_PAIR_STRIDE 2
+#define NH_MESSAGE_UNIT (NH_PAIR_STRIDE * 2 * sizeof(u32))
+
+/* Num passes (Toeplitz iteration count): 4, to give ε = 2^{-128} */
+#define NH_NUM_PASSES 4
+#define NH_HASH_BYTES (NH_NUM_PASSES * sizeof(u64))
+
+/* Max message size: 1024 bytes (32x compression factor) */
+#define NH_NUM_STRIDES 64
+#define NH_MESSAGE_WORDS (NH_PAIR_STRIDE * 2 * NH_NUM_STRIDES)
+#define NH_MESSAGE_BYTES (NH_MESSAGE_WORDS * sizeof(u32))
+#define NH_KEY_WORDS (NH_MESSAGE_WORDS + \
+ NH_PAIR_STRIDE * 2 * (NH_NUM_PASSES - 1))
+#define NH_KEY_BYTES (NH_KEY_WORDS * sizeof(u32))
+
+#define NHPOLY1305_KEY_SIZE (POLY1305_BLOCK_SIZE + NH_KEY_BYTES)
+
+struct nhpoly1305_key {
+ struct poly1305_key poly_key;
+ u32 nh_key[NH_KEY_WORDS];
+};
+
+struct nhpoly1305_state {
+
+ /* Running total of polynomial evaluation */
+ struct poly1305_state poly_state;
+
+ /* Partial block buffer */
+ u8 buffer[NH_MESSAGE_UNIT];
+ unsigned int buflen;
+
+ /*
+ * Number of bytes remaining until the current NH message reaches
+ * NH_MESSAGE_BYTES. When nonzero, 'nh_hash' holds the partial NH hash.
+ */
+ unsigned int nh_remaining;
+
+ __le64 nh_hash[NH_NUM_PASSES];
+};
+
+typedef void (*nh_t)(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES]);
+
+int crypto_nhpoly1305_setkey(struct crypto_shash *tfm,
+ const u8 *key, unsigned int keylen);
+
+int crypto_nhpoly1305_init(struct shash_desc *desc);
+int crypto_nhpoly1305_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen);
+int crypto_nhpoly1305_update_helper(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen,
+ nh_t nh_fn);
+int crypto_nhpoly1305_final(struct shash_desc *desc, u8 *dst);
+int crypto_nhpoly1305_final_helper(struct shash_desc *desc, u8 *dst,
+ nh_t nh_fn);
+
+#endif /* _NHPOLY1305_H */
diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h
index d586f74..0c0b83a 100644
--- a/include/crypto/poly1305.h
+++ b/include/crypto/poly1305.h
@@ -12,13 +12,21 @@
#define POLY1305_KEY_SIZE 32
#define POLY1305_DIGEST_SIZE 16
+struct poly1305_key {
+ u32 r[5]; /* key, base 2^26 */
+};
+
+struct poly1305_state {
+ u32 h[5]; /* accumulator, base 2^26 */
+};
+
struct poly1305_desc_ctx {
/* key */
- u32 r[5];
+ struct poly1305_key r;
/* finalize key */
u32 s[4];
/* accumulator */
- u32 h[5];
+ struct poly1305_state h;
/* partial buffer */
u8 buf[POLY1305_BLOCK_SIZE];
/* bytes used in partial buffer */
@@ -29,6 +37,22 @@ struct poly1305_desc_ctx {
bool sset;
};
+/*
+ * Poly1305 core functions. These implement the ε-almost-∆-universal hash
+ * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
+ * ("s key") at the end. They also only support block-aligned inputs.
+ */
+void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
+static inline void poly1305_core_init(struct poly1305_state *state)
+{
+ memset(state->h, 0, sizeof(state->h));
+}
+void poly1305_core_blocks(struct poly1305_state *state,
+ const struct poly1305_key *key,
+ const void *src, unsigned int nblocks);
+void poly1305_core_emit(const struct poly1305_state *state, void *dst);
+
+/* Crypto API helper functions for the Poly1305 MAC */
int crypto_poly1305_init(struct shash_desc *desc);
unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen);
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 9701f2d..a5696c1 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -144,6 +144,7 @@ struct __drm_crtcs_state {
struct drm_crtc *ptr;
struct drm_crtc_state *state;
struct drm_crtc_commit *commit;
+ s32 __user *out_fence_ptr;
};
struct __drm_connnectors_state {
@@ -316,6 +317,8 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
struct drm_crtc *crtc);
void drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state,
struct drm_framebuffer *fb);
+void drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
+ struct fence *fence);
int __must_check
drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
struct drm_crtc *crtc);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 0aa2925..f3d58c7 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -680,6 +680,35 @@ struct drm_crtc {
* context.
*/
struct drm_modeset_acquire_ctx *acquire_ctx;
+
+ /**
+ * @fence_context:
+ *
+ * timeline context used for fence operations.
+ */
+ unsigned int fence_context;
+
+ /**
+ * @fence_lock:
+ *
+ * spinlock to protect the fences in the fence_context.
+ */
+
+ spinlock_t fence_lock;
+ /**
+ * @fence_seqno:
+ *
+ * Seqno variable used as monotonic counter for the fences
+ * created on the CRTC's timeline.
+ */
+ unsigned long fence_seqno;
+
+ /**
+ * @timeline_name:
+ *
+ * The name of the CRTC's fence timeline.
+ */
+ char timeline_name[32];
};
/**
@@ -1160,6 +1189,17 @@ struct drm_mode_config {
*/
struct drm_property *prop_fb_id;
/**
+ * @prop_in_fence_fd: Sync File fd representing the incoming fences
+ * for a Plane.
+ */
+ struct drm_property *prop_in_fence_fd;
+ /**
+ * @prop_out_fence_ptr: Sync File fd pointer representing the
+ * outgoing fences for a CRTC. Userspace should provide a pointer to a
+ * value of type s32, and then cast that pointer to u64.
+ */
+ struct drm_property *prop_out_fence_ptr;
+ /**
* @prop_crtc_id: Default atomic plane property to specify the
* &drm_crtc.
*/
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index f313211..3b00f64 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -12,6 +12,8 @@ struct drm_fb_helper;
struct drm_device;
struct drm_file;
struct drm_mode_fb_cmd2;
+struct drm_plane;
+struct drm_plane_state;
struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
unsigned int preferred_bpp, unsigned int num_crtc,
@@ -41,6 +43,9 @@ struct drm_framebuffer *drm_fb_cma_create(struct drm_device *dev,
struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb,
unsigned int plane);
+int drm_fb_cma_prepare_fb(struct drm_plane *plane,
+ struct drm_plane_state *state);
+
#ifdef CONFIG_DEBUG_FS
struct seq_file;
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 8b4dc62..952ef84 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -65,7 +65,7 @@ struct drm_plane_state {
struct drm_crtc *crtc; /* do not write directly, use drm_atomic_set_crtc_for_plane() */
struct drm_framebuffer *fb; /* do not write directly, use drm_atomic_set_fb_for_plane() */
- struct fence *fence;
+ struct fence *fence; /* do not write directly, use drm_atomic_set_fence_for_plane() */
/* Signed dest location allows it to be partially off screen */
int32_t crtc_x, crtc_y;
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index 5d744ec..12babe9 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -48,9 +48,14 @@ extern void user_describe(const struct key *user, struct seq_file *m);
extern long user_read(const struct key *key,
char __user *buffer, size_t buflen);
-static inline const struct user_key_payload *user_key_payload(const struct key *key)
+static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key)
{
- return (struct user_key_payload *)rcu_dereference_key(key);
+ return (struct user_key_payload *)dereference_key_rcu(key);
+}
+
+static inline struct user_key_payload *user_key_payload_locked(const struct key *key)
+{
+ return (struct user_key_payload *)dereference_key_locked((struct key *)key);
}
#endif /* CONFIG_KEYS */
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
new file mode 100644
index 0000000..a460889
--- /dev/null
+++ b/include/linux/Kbuild
@@ -0,0 +1,2 @@
+header-y += if_pppolac.h
+header-y += if_pppopns.h
diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h
index 8c98113..eff56cb 100644
--- a/include/linux/amba/mmci.h
+++ b/include/linux/amba/mmci.h
@@ -5,6 +5,15 @@
#define AMBA_MMCI_H
#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+
+struct embedded_sdio_data {
+ struct sdio_cis cis;
+ struct sdio_cccr cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+};
/**
* struct mmci_platform_data - platform configuration for the MMCI
@@ -31,6 +40,7 @@ struct mmci_platform_data {
int gpio_wp;
int gpio_cd;
bool cd_invert;
+ struct embedded_sdio_data *embedded_sdio;
};
#endif
diff --git a/include/linux/android_aid.h b/include/linux/android_aid.h
new file mode 100644
index 0000000..6f1fa179
--- /dev/null
+++ b/include/linux/android_aid.h
@@ -0,0 +1,28 @@
+/* include/linux/android_aid.h
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_ANDROID_AID_H
+#define _LINUX_ANDROID_AID_H
+
+/* AIDs that the kernel treats differently */
+#define AID_OBSOLETE_000 KGIDT_INIT(3001) /* was NET_BT_ADMIN */
+#define AID_OBSOLETE_001 KGIDT_INIT(3002) /* was NET_BT */
+#define AID_INET KGIDT_INIT(3003)
+#define AID_NET_RAW KGIDT_INIT(3004)
+#define AID_NET_ADMIN KGIDT_INIT(3005)
+#define AID_NET_BW_STATS KGIDT_INIT(3006) /* read bandwidth statistics */
+#define AID_NET_BW_ACCT KGIDT_INIT(3007) /* change bandwidth statistics accounting */
+
+#endif
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 18863d5..9f721ee 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -160,6 +160,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
#define SMCCC_SMC_INST "smc #0"
#define SMCCC_HVC_INST "hvc #0"
+#define SMCCC_REG(n) asm("x" # n)
#elif defined(CONFIG_ARM)
#include <asm/opcodes-sec.h>
@@ -167,6 +168,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
#define SMCCC_SMC_INST __SMC(0)
#define SMCCC_HVC_INST __HVC(0)
+#define SMCCC_REG(n) asm("r" # n)
#endif
@@ -199,57 +201,57 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
#define __declare_arg_0(a0, res) \
struct arm_smccc_res *___res = res; \
- register unsigned long r0 asm("r0") = (u32)a0; \
- register unsigned long r1 asm("r1"); \
- register unsigned long r2 asm("r2"); \
- register unsigned long r3 asm("r3")
+ register unsigned long r0 SMCCC_REG(0) = (u32)a0; \
+ register unsigned long r1 SMCCC_REG(1); \
+ register unsigned long r2 SMCCC_REG(2); \
+ register unsigned long r3 SMCCC_REG(3)
#define __declare_arg_1(a0, a1, res) \
typeof(a1) __a1 = a1; \
struct arm_smccc_res *___res = res; \
- register unsigned long r0 asm("r0") = (u32)a0; \
- register unsigned long r1 asm("r1") = __a1; \
- register unsigned long r2 asm("r2"); \
- register unsigned long r3 asm("r3")
+ register unsigned long r0 SMCCC_REG(0) = (u32)a0; \
+ register unsigned long r1 SMCCC_REG(1) = __a1; \
+ register unsigned long r2 SMCCC_REG(2); \
+ register unsigned long r3 SMCCC_REG(3)
#define __declare_arg_2(a0, a1, a2, res) \
typeof(a1) __a1 = a1; \
typeof(a2) __a2 = a2; \
struct arm_smccc_res *___res = res; \
- register unsigned long r0 asm("r0") = (u32)a0; \
- register unsigned long r1 asm("r1") = __a1; \
- register unsigned long r2 asm("r2") = __a2; \
- register unsigned long r3 asm("r3")
+ register unsigned long r0 SMCCC_REG(0) = (u32)a0; \
+ register unsigned long r1 SMCCC_REG(1) = __a1; \
+ register unsigned long r2 SMCCC_REG(2) = __a2; \
+ register unsigned long r3 SMCCC_REG(3)
#define __declare_arg_3(a0, a1, a2, a3, res) \
typeof(a1) __a1 = a1; \
typeof(a2) __a2 = a2; \
typeof(a3) __a3 = a3; \
struct arm_smccc_res *___res = res; \
- register unsigned long r0 asm("r0") = (u32)a0; \
- register unsigned long r1 asm("r1") = __a1; \
- register unsigned long r2 asm("r2") = __a2; \
- register unsigned long r3 asm("r3") = __a3
+ register unsigned long r0 SMCCC_REG(0) = (u32)a0; \
+ register unsigned long r1 SMCCC_REG(1) = __a1; \
+ register unsigned long r2 SMCCC_REG(2) = __a2; \
+ register unsigned long r3 SMCCC_REG(3) = __a3
#define __declare_arg_4(a0, a1, a2, a3, a4, res) \
typeof(a4) __a4 = a4; \
__declare_arg_3(a0, a1, a2, a3, res); \
- register unsigned long r4 asm("r4") = __a4
+ register unsigned long r4 SMCCC_REG(4) = __a4
#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \
typeof(a5) __a5 = a5; \
__declare_arg_4(a0, a1, a2, a3, a4, res); \
- register unsigned long r5 asm("r5") = __a5
+ register unsigned long r5 SMCCC_REG(5) = __a5
#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \
typeof(a6) __a6 = a6; \
__declare_arg_5(a0, a1, a2, a3, a4, a5, res); \
- register unsigned long r6 asm("r6") = __a6
+ register unsigned long r6 SMCCC_REG(6) = __a6
#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \
typeof(a7) __a7 = a7; \
__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \
- register unsigned long r7 asm("r7") = __a7
+ register unsigned long r7 SMCCC_REG(7) = __a7
#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
#define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__)
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 34056ec..58b0786 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -136,6 +136,7 @@ struct bdi_writeback {
struct backing_dev_info {
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
+ unsigned long io_pages; /* max allowed IO size */
unsigned int capabilities; /* Device capabilities */
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index cd395ec..26b3fd3 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -25,6 +25,7 @@ typedef void (bio_end_io_t) (struct bio *);
struct bio {
struct bio *bi_next; /* request queue link */
struct block_device *bi_bdev;
+ unsigned short bi_write_hint;
int bi_error;
unsigned int bi_opf; /* bottom bits req flags,
* top bits REQ_OP. Use
@@ -116,9 +117,10 @@ struct bio {
#define BIO_BOUNCED 3 /* bio is a bounce bio */
#define BIO_USER_MAPPED 4 /* contains user pages */
#define BIO_NULL_MAPPED 5 /* contains invalid user pages */
-#define BIO_QUIET 6 /* Make BIO Quiet */
-#define BIO_CHAIN 7 /* chained bio, ->bi_remaining in effect */
-#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */
+#define BIO_WORKINGSET 6 /* contains userspace workingset pages */
+#define BIO_QUIET 7 /* Make BIO Quiet */
+#define BIO_CHAIN 8 /* chained bio, ->bi_remaining in effect */
+#define BIO_REFFED 9 /* bio has elevated ->bi_cnt */
/*
* Flags starting here get preserved by bio_reset() - this includes
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 848aab6..b5d23bc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -196,6 +196,9 @@ struct request {
/* for bidi */
struct request *next_rq;
+
+ ktime_t lat_hist_io_start;
+ int lat_hist_enabled;
};
#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS)
@@ -1726,6 +1729,62 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *,
extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *);
extern int bdev_dax_supported(struct super_block *, int);
extern bool bdev_dax_capable(struct block_device *);
+
+/*
+ * X-axis for IO latency histogram support.
+ */
+static const u_int64_t latency_x_axis_us[] = {
+ 100,
+ 200,
+ 300,
+ 400,
+ 500,
+ 600,
+ 700,
+ 800,
+ 900,
+ 1000,
+ 1200,
+ 1400,
+ 1600,
+ 1800,
+ 2000,
+ 2500,
+ 3000,
+ 4000,
+ 5000,
+ 6000,
+ 7000,
+ 9000,
+ 10000
+};
+
+#define BLK_IO_LAT_HIST_DISABLE 0
+#define BLK_IO_LAT_HIST_ENABLE 1
+#define BLK_IO_LAT_HIST_ZERO 2
+
+struct io_latency_state {
+ u_int64_t latency_y_axis[ARRAY_SIZE(latency_x_axis_us) + 1];
+ u_int64_t latency_elems;
+ u_int64_t latency_sum;
+};
+
+static inline void
+blk_update_latency_hist(struct io_latency_state *s, u_int64_t delta_us)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++)
+ if (delta_us < (u_int64_t)latency_x_axis_us[i])
+ break;
+ s->latency_y_axis[i]++;
+ s->latency_elems++;
+ s->latency_sum += delta_us;
+}
+
+ssize_t blk_latency_hist_show(char* name, struct io_latency_state *s,
+ char *buf, int buf_size);
+
#else /* CONFIG_BLOCK */
struct block_device;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
new file mode 100644
index 0000000..ed3bb3d
--- /dev/null
+++ b/include/linux/bpf-cgroup.h
@@ -0,0 +1,91 @@
+#ifndef _BPF_CGROUP_H
+#define _BPF_CGROUP_H
+
+#include <linux/jump_label.h>
+#include <uapi/linux/bpf.h>
+
+struct sock;
+struct cgroup;
+struct sk_buff;
+
+#ifdef CONFIG_CGROUP_BPF
+
+extern struct static_key_false cgroup_bpf_enabled_key;
+#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
+
+struct bpf_prog_list {
+ struct list_head node;
+ struct bpf_prog *prog;
+};
+
+struct bpf_prog_array;
+
+struct cgroup_bpf {
+ /* array of effective progs in this cgroup */
+ struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE];
+
+ /* attached progs to this cgroup and attach flags
+ * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
+ * have either zero or one element
+ * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
+ */
+ struct list_head progs[MAX_BPF_ATTACH_TYPE];
+ u32 flags[MAX_BPF_ATTACH_TYPE];
+
+ /* temp storage for effective prog array used by prog_attach/detach */
+ struct bpf_prog_array __rcu *inactive;
+};
+
+void cgroup_bpf_put(struct cgroup *cgrp);
+int cgroup_bpf_inherit(struct cgroup *cgrp);
+
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+
+/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+
+int __cgroup_bpf_run_filter(struct sock *sk,
+ struct sk_buff *skb,
+ enum bpf_attach_type type);
+
+/* Wrappers for __cgroup_bpf_run_filter() guarded by cgroup_bpf_enabled. */
+#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter(sk, skb, \
+ BPF_CGROUP_INET_INGRESS); \
+ \
+ __ret; \
+})
+
+#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled && sk && sk == skb->sk) { \
+ typeof(sk) __sk = sk_to_full_sk(sk); \
+ if (sk_fullsock(__sk)) \
+ __ret = __cgroup_bpf_run_filter(__sk, skb, \
+ BPF_CGROUP_INET_EGRESS); \
+ } \
+ __ret; \
+})
+
+#else
+
+struct cgroup_bpf {};
+static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
+static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
+
+#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
+
+#endif /* CONFIG_CGROUP_BPF */
+
+#endif /* _BPF_CGROUP_H */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7995940..30b808f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,6 +56,9 @@ struct bpf_map {
atomic_t refcnt;
atomic_t usercnt;
struct work_struct work;
+#ifdef CONFIG_SECURITY
+ void *security;
+#endif
};
struct bpf_map_type_list {
@@ -189,6 +192,9 @@ struct bpf_prog_aux {
struct bpf_map **used_maps;
struct bpf_prog *prog;
struct user_struct *user;
+#ifdef CONFIG_SECURITY
+ void *security;
+#endif
union {
struct work_struct work;
struct rcu_head rcu;
@@ -235,12 +241,67 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
+/* an array of programs to be executed under rcu_lock.
+ *
+ * Typical usage:
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ *
+ * the structure returned by bpf_prog_array_alloc() should be populated
+ * with program pointers and the last pointer must be NULL.
+ * The user has to keep refcnt on the program and make sure the program
+ * is removed from the array before bpf_prog_put().
+ * The 'struct bpf_prog_array *' should only be replaced with xchg()
+ * since other cpus are walking the array of pointers in parallel.
+ */
+struct bpf_prog_array {
+ struct rcu_head rcu;
+ struct bpf_prog *progs[0];
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+ struct bpf_prog *old_prog);
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array);
+
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
+ ({ \
+ struct bpf_prog **_prog, *__prog; \
+ struct bpf_prog_array *_array; \
+ u32 _ret = 1; \
+ rcu_read_lock(); \
+ _array = rcu_dereference(array); \
+ if (unlikely(check_non_null && !_array))\
+ goto _out; \
+ _prog = _array->progs; \
+ while ((__prog = READ_ONCE(*_prog))) { \
+ _ret &= func(__prog, ctx); \
+ _prog++; \
+ } \
+_out: \
+ rcu_read_unlock(); \
+ _ret; \
+ })
+
+#define BPF_PROG_RUN_ARRAY(array, ctx, func) \
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+
+#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
void bpf_register_prog_type(struct bpf_prog_type_list *tl);
void bpf_register_map_type(struct bpf_map_type_list *tl);
+extern const struct file_operations bpf_map_fops;
+extern const struct file_operations bpf_prog_fops;
+
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i);
@@ -258,11 +319,11 @@ void bpf_map_area_free(void *base);
extern int sysctl_unprivileged_bpf_disabled;
-int bpf_map_new_fd(struct bpf_map *map);
+int bpf_map_new_fd(struct bpf_map *map, int flags);
int bpf_prog_new_fd(struct bpf_prog *prog);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname);
+int bpf_obj_get_user(const char __user *pathname, int flags);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
@@ -277,6 +338,8 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
void bpf_fd_array_map_clear(struct bpf_map *map);
+int bpf_get_file_flag(int flags);
+
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
* Best-effort only. No barriers here, since it _will_ race with concurrent
@@ -295,6 +358,9 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
+
#else
static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl)
{
@@ -322,6 +388,16 @@ static inline struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
+static inline int bpf_obj_get_user(const char __user *pathname)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
+ enum bpf_prog_type type)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
#endif /* CONFIG_BPF_SYSCALL */
/* verifier prototypes for helper functions called from eBPF programs */
diff --git a/include/linux/bug.h b/include/linux/bug.h
index 0faae96..59bc010 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -126,4 +126,23 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr,
}
#endif /* CONFIG_GENERIC_BUG */
+
+/*
+ * Since detected data corruption should stop operation on the affected
+ * structures. Return value must be checked and sanely acted on by caller.
+ */
+static inline __must_check bool check_data_corruption(bool v) { return v; }
+#define CHECK_DATA_CORRUPTION(condition, fmt, ...) \
+ check_data_corruption(({ \
+ bool corruption = unlikely(condition); \
+ if (corruption) { \
+ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
+ pr_err(fmt, ##__VA_ARGS__); \
+ BUG(); \
+ } else \
+ WARN(1, fmt, ##__VA_ARGS__); \
+ } \
+ corruption; \
+ }))
+
#endif /* _LINUX_BUG_H */
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
new file mode 100644
index 0000000..e27033d
--- /dev/null
+++ b/include/linux/cfi.h
@@ -0,0 +1,38 @@
+#ifndef _LINUX_CFI_H
+#define _LINUX_CFI_H
+
+#include <linux/stringify.h>
+
+#ifdef CONFIG_CFI_CLANG
+#ifdef CONFIG_MODULES
+
+typedef void (*cfi_check_fn)(uint64_t, void *, void *);
+
+/* Compiler-generated function in each module, and the kernel */
+#define CFI_CHECK_FN __cfi_check
+#define CFI_CHECK_FN_NAME __stringify(CFI_CHECK_FN)
+
+extern void CFI_CHECK_FN(uint64_t, void *, void *);
+
+#ifdef CONFIG_CFI_CLANG_SHADOW
+extern void cfi_module_add(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr);
+
+extern void cfi_module_remove(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr);
+#else
+static inline void cfi_module_add(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr)
+{
+}
+
+static inline void cfi_module_remove(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr)
+{
+}
+#endif /* CONFIG_CFI_CLANG_SHADOW */
+
+#endif /* CONFIG_MODULES */
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _LINUX_CFI_H */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index b3e7da0..24688fa 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -16,6 +16,8 @@
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
+#include <linux/bpf-cgroup.h>
+#include <linux/psi_types.h>
#ifdef CONFIG_CGROUPS
@@ -27,6 +29,7 @@ struct kernfs_node;
struct kernfs_ops;
struct kernfs_open_file;
struct seq_file;
+struct poll_table_struct;
#define MAX_CGROUP_TYPE_NAMELEN 32
#define MAX_CGROUP_ROOT_NAMELEN 64
@@ -301,6 +304,12 @@ struct cgroup {
/* used to schedule release agent */
struct work_struct release_agent_work;
+ /* used to track pressure stalls */
+ struct psi_group psi;
+
+ /* used to store eBPF programs */
+ struct cgroup_bpf bpf;
+
/* ids of the ancestors at each level including self */
int ancestor_ids[];
};
@@ -385,6 +394,9 @@ struct cftype {
struct list_head node; /* anchored at ss->cfts */
struct kernfs_ops *kf_ops;
+ int (*open)(struct kernfs_open_file *of);
+ void (*release)(struct kernfs_open_file *of);
+
/*
* read_u64() is a shortcut for the common case of returning a
* single integer. Use it in place of read()
@@ -425,6 +437,9 @@ struct cftype {
ssize_t (*write)(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
+ unsigned int (*poll)(struct kernfs_open_file *of,
+ struct poll_table_struct *pt);
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lock_class_key lockdep_key;
#endif
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 75fbf93..2c25547 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -388,6 +388,16 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
percpu_ref_put_many(&css->refcnt, n);
}
+static inline void cgroup_get(struct cgroup *cgrp)
+{
+ css_get(&cgrp->self);
+}
+
+static inline bool cgroup_tryget(struct cgroup *cgrp)
+{
+ return css_tryget(&cgrp->self);
+}
+
static inline void cgroup_put(struct cgroup *cgrp)
{
css_put(&cgrp->self);
@@ -506,6 +516,20 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
return task_css(task, subsys_id)->cgroup;
}
+static inline struct cgroup *task_dfl_cgroup(struct task_struct *task)
+{
+ return task_css_set(task)->dfl_cgrp;
+}
+
+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+ struct cgroup_subsys_state *parent_css = cgrp->self.parent;
+
+ if (parent_css)
+ return container_of(parent_css, struct cgroup, self);
+ return NULL;
+}
+
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
@@ -596,6 +620,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
pr_cont_kernfs_path(cgrp->kn);
}
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+ return &cgrp->psi;
+}
+
static inline void cgroup_init_kthreadd(void)
{
/*
@@ -638,6 +667,16 @@ static inline int cgroup_init(void) { return 0; }
static inline void cgroup_init_kthreadd(void) {}
static inline void cgroup_kthread_ready(void) {}
+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+ return NULL;
+}
+
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+ return NULL;
+}
+
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
{
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 0df0336a..7f4a2a5 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -20,6 +20,10 @@ SUBSYS(cpu)
SUBSYS(cpuacct)
#endif
+#if IS_ENABLED(CONFIG_CGROUP_SCHEDTUNE)
+SUBSYS(schedtune)
+#endif
+
#if IS_ENABLED(CONFIG_BLK_CGROUP)
SUBSYS(io)
#endif
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 697988b..9ff8122 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -24,6 +24,23 @@
#undef __noretpoline
#endif
+#ifdef CONFIG_LTO_CLANG
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#define __norecordmcount \
+ __attribute__((__section__(".text..ftrace")))
+#endif
+
+#define __nocfi __attribute__((no_sanitize("cfi")))
+#endif
+
+/* all clang versions usable with the kernel support KASAN ABI version 5 */
+#define KASAN_ABI_VERSION 5
+
+/* emulate gcc's __SANITIZE_ADDRESS__ flag */
+#if __has_feature(address_sanitizer)
+#define __SANITIZE_ADDRESS__
+#endif
+
/*
* Not all versions of clang implement the the type-generic versions
* of the builtin overflow checkers. Fortunately, clang implements
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 824b1b9..d00e7b3 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -478,6 +478,14 @@ unsigned long read_word_at_a_time(const void *addr)
#define __visible
#endif
+#ifndef __norecordmcount
+#define __norecordmcount
+#endif
+
+#ifndef __nocfi
+#define __nocfi
+#endif
+
/*
* Assume alignment of return value.
*/
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e19bbc3..cf9ebc5 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -290,4 +290,11 @@ static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0;
extern bool cpu_mitigations_off(void);
extern bool cpu_mitigations_auto_nosmt(void);
+#define IDLE_START 1
+#define IDLE_END 2
+
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+void idle_notifier_call_chain(unsigned long val);
+
#endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9d9e0b5..f32c075 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -120,6 +120,14 @@ struct cpufreq_policy {
bool fast_switch_possible;
bool fast_switch_enabled;
+ /*
+ * Preferred average time interval between consecutive invocations of
+ * the driver to set the frequency for this policy. To be set by the
+ * scaling driver (0, which is the default, means no preference).
+ */
+ unsigned int up_transition_delay_us;
+ unsigned int down_transition_delay_us;
+
/* Cached frequency lookup from cpufreq_driver_resolve_freq. */
unsigned int cached_target_freq;
int cached_resolved_idx;
@@ -177,6 +185,7 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
int cpufreq_update_policy(unsigned int cpu);
bool have_governor_per_policy(void);
+bool cpufreq_driver_is_slow(void);
struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
@@ -351,6 +360,14 @@ struct cpufreq_driver {
*/
#define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5)
+/*
+ * Indicates that it is safe to call cpufreq_driver_target from
+ * non-interruptable context in scheduler hot paths. Drivers must
+ * opt-in to this flag, as the safe default is that they might sleep
+ * or be too slow for hot path use.
+ */
+#define CPUFREQ_DRIVER_FAST (1 << 6)
+
int cpufreq_register_driver(struct cpufreq_driver *driver_data);
int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
@@ -545,6 +562,32 @@ struct governor_attr {
ssize_t (*store)(struct gov_attr_set *attr_set, const char *buf,
size_t count);
};
+/* CPUFREQ DEFAULT GOVERNOR */
+/*
+ * Performance governor is fallback governor if any other gov failed to auto
+ * load due latency restrictions
+ */
+#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
+extern struct cpufreq_governor cpufreq_gov_performance;
+#endif
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_performance)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
+extern struct cpufreq_governor cpufreq_gov_powersave;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_powersave)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
+extern struct cpufreq_governor cpufreq_gov_userspace;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_userspace)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND)
+extern struct cpufreq_governor cpufreq_gov_ondemand;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_ondemand)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
+extern struct cpufreq_governor cpufreq_gov_conservative;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_SCHED)
+extern struct cpufreq_governor cpufreq_gov_sched;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_sched)
+#endif
/*********************************************************************
* FREQUENCY TABLE HELPERS *
@@ -878,4 +921,9 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
int cpufreq_generic_init(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table,
unsigned int transition_latency);
+
+struct sched_domain;
+unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu);
+unsigned long cpufreq_scale_max_freq_capacity(struct sched_domain *sd, int cpu);
+unsigned long cpufreq_scale_min_freq_capacity(struct sched_domain *sd, int cpu);
#endif /* _LINUX_CPUFREQ_H */
diff --git a/include/linux/cpufreq_times.h b/include/linux/cpufreq_times.h
new file mode 100644
index 0000000..3b12e17
--- /dev/null
+++ b/include/linux/cpufreq_times.h
@@ -0,0 +1,47 @@
+/* drivers/cpufreq/cpufreq_times.c
+ *
+ * Copyright (C) 2018 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_CPUFREQ_TIMES_H
+#define _LINUX_CPUFREQ_TIMES_H
+
+#include <linux/cpufreq.h>
+#include <linux/cputime.h>
+#include <linux/pid.h>
+
+#ifdef CONFIG_CPU_FREQ_TIMES
+void cpufreq_task_times_init(struct task_struct *p);
+void cpufreq_task_times_alloc(struct task_struct *p);
+void cpufreq_task_times_exit(struct task_struct *p);
+int proc_time_in_state_show(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *p);
+void cpufreq_acct_update_power(struct task_struct *p, cputime_t cputime);
+void cpufreq_times_create_policy(struct cpufreq_policy *policy);
+void cpufreq_times_record_transition(struct cpufreq_policy *policy,
+ unsigned int new_freq);
+void cpufreq_task_times_remove_uids(uid_t uid_start, uid_t uid_end);
+int single_uid_time_in_state_open(struct inode *inode, struct file *file);
+#else
+static inline void cpufreq_task_times_init(struct task_struct *p) {}
+static inline void cpufreq_task_times_alloc(struct task_struct *p) {}
+static inline void cpufreq_task_times_exit(struct task_struct *p) {}
+static inline void cpufreq_acct_update_power(struct task_struct *p,
+ u64 cputime) {}
+static inline void cpufreq_times_create_policy(struct cpufreq_policy *policy) {}
+static inline void cpufreq_times_record_transition(
+ struct cpufreq_policy *policy, unsigned int new_freq) {}
+static inline void cpufreq_task_times_remove_uids(uid_t uid_start,
+ uid_t uid_end) {}
+#endif /* CONFIG_CPU_FREQ_TIMES */
+#endif /* _LINUX_CPUFREQ_TIMES_H */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index bb31373..9a8eec9 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -207,7 +207,7 @@ static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv,
#endif
/* kernel/sched/idle.c */
-extern void sched_idle_set_state(struct cpuidle_state *idle_state);
+extern void sched_idle_set_state(struct cpuidle_state *idle_state, int index);
extern void default_idle_call(void);
#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 9de2696..81339e1 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/uaccess.h>
+#include <linux/completion.h>
/*
* Autoloaded crypto modules should only use a prefixed name to avoid allowing
@@ -478,6 +479,45 @@ struct crypto_alg {
} CRYPTO_MINALIGN_ATTR;
/*
+ * A helper struct for waiting for completion of async crypto ops
+ */
+struct crypto_wait {
+ struct completion completion;
+ int err;
+};
+
+/*
+ * Macro for declaring a crypto op async wait object on stack
+ */
+#define DECLARE_CRYPTO_WAIT(_wait) \
+ struct crypto_wait _wait = { \
+ COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 }
+
+/*
+ * Async ops completion helper functioons
+ */
+void crypto_req_done(struct crypto_async_request *req, int err);
+
+static inline int crypto_wait_req(int err, struct crypto_wait *wait)
+{
+ switch (err) {
+ case -EINPROGRESS:
+ case -EBUSY:
+ wait_for_completion(&wait->completion);
+ reinit_completion(&wait->completion);
+ err = wait->err;
+ break;
+ };
+
+ return err;
+}
+
+static inline void crypto_init_wait(struct crypto_wait *wait)
+{
+ init_completion(&wait->completion);
+}
+
+/*
* Algorithm registration interface.
*/
int crypto_register_alg(struct crypto_alg *alg);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index b757ee4..014d7f9 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -142,6 +142,7 @@ struct dentry_operations {
int (*d_manage)(struct dentry *, bool);
struct dentry *(*d_real)(struct dentry *, const struct inode *,
unsigned int);
+ void (*d_canonical_path)(const struct path *, struct path *);
} ____cacheline_aligned;
/*
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6cee17c..84c2f68 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,7 +29,48 @@
#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */
#ifdef CONFIG_TASK_DELAY_ACCT
+struct task_delay_info {
+ spinlock_t lock;
+ unsigned int flags; /* Private per-task flags */
+ /* For each stat XXX, add following, aligned appropriately
+ *
+ * struct timespec XXX_start, XXX_end;
+ * u64 XXX_delay;
+ * u32 XXX_count;
+ *
+ * Atomicity of updates to XXX_delay, XXX_count protected by
+ * single lock above (split into XXX_lock if contention is an issue).
+ */
+
+ /*
+ * XXX_count is incremented on every XXX operation, the delay
+ * associated with the operation is added to XXX_delay.
+ * XXX_delay contains the accumulated delay time in nanoseconds.
+ */
+ u64 blkio_start; /* Shared by blkio, swapin */
+ u64 blkio_delay; /* wait for sync block io completion */
+ u64 swapin_delay; /* wait for swapin block io completion */
+ u32 blkio_count; /* total count of the number of sync block */
+ /* io operations performed */
+ u32 swapin_count; /* total count of the number of swapin block */
+ /* io operations performed */
+
+ u64 freepages_start;
+ u64 freepages_delay; /* wait for memory reclaim */
+
+ u64 thrashing_start;
+ u64 thrashing_delay; /* wait for thrashing page */
+
+ u32 freepages_count; /* total count of memory reclaim */
+ u32 thrashing_count; /* total count of thrash waits */
+};
+#endif
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_TASK_DELAY_ACCT
extern int delayacct_on; /* Delay accounting turned on/off */
extern struct kmem_cache *delayacct_cache;
extern void delayacct_init(void);
@@ -41,6 +82,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
extern __u64 __delayacct_blkio_ticks(struct task_struct *);
extern void __delayacct_freepages_start(void);
extern void __delayacct_freepages_end(void);
+extern void __delayacct_thrashing_start(void);
+extern void __delayacct_thrashing_end(void);
static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
{
@@ -121,6 +164,18 @@ static inline void delayacct_freepages_end(void)
__delayacct_freepages_end();
}
+static inline void delayacct_thrashing_start(void)
+{
+ if (current->delays)
+ __delayacct_thrashing_start();
+}
+
+static inline void delayacct_thrashing_end(void)
+{
+ if (current->delays)
+ __delayacct_thrashing_end();
+}
+
#else
static inline void delayacct_set_flag(int flag)
{}
@@ -147,6 +202,10 @@ static inline void delayacct_freepages_start(void)
{}
static inline void delayacct_freepages_end(void)
{}
+static inline void delayacct_thrashing_start(void)
+{}
+static inline void delayacct_thrashing_end(void)
+{}
#endif /* CONFIG_TASK_DELAY_ACCT */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 165ddd4..e9157b9 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -408,6 +408,12 @@ void dm_set_mdptr(struct mapped_device *md, void *ptr);
void *dm_get_mdptr(struct mapped_device *md);
/*
+ * Export the device via the ioctl interface (uses mdptr).
+ */
+int dm_ioctl_export(struct mapped_device *md, const char *name,
+ const char *uuid);
+
+/*
* A device can still be used while suspended, but I/O is deferred.
*/
int dm_suspend(struct mapped_device *md, unsigned suspend_flags);
@@ -434,6 +440,13 @@ union map_info *dm_get_rq_mapinfo(struct request *rq);
struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
+void dm_lock_md_type(struct mapped_device *md);
+void dm_unlock_md_type(struct mapped_device *md);
+void dm_set_md_type(struct mapped_device *md, unsigned type);
+unsigned dm_get_md_type(struct mapped_device *md);
+int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
+unsigned dm_table_get_type(struct dm_table *t);
+
/*
* Geometry functions.
*/
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index e46e7d1..f574042 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/**
* include/linux/f2fs_fs.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef _LINUX_F2FS_FS_H
#define _LINUX_F2FS_FS_H
@@ -21,6 +18,7 @@
#define F2FS_BLKSIZE 4096 /* support only 4KB block */
#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */
#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
+#define F2FS_EXTENSION_LEN 8 /* max size of extension */
#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
@@ -32,13 +30,20 @@
/* 0, 1(node nid), 2(meta nid) are reserved node id */
#define F2FS_RESERVED_NODE_NUM 3
-#define F2FS_ROOT_INO(sbi) (sbi->root_ino_num)
-#define F2FS_NODE_INO(sbi) (sbi->node_ino_num)
-#define F2FS_META_INO(sbi) (sbi->meta_ino_num)
+#define F2FS_ROOT_INO(sbi) ((sbi)->root_ino_num)
+#define F2FS_NODE_INO(sbi) ((sbi)->node_ino_num)
+#define F2FS_META_INO(sbi) ((sbi)->meta_ino_num)
+
+#define F2FS_MAX_QUOTAS 3
+
+#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
+#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */
+#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */
+#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */
+#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1)
/* This flag is used by node and meta inodes, and by recovery */
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
-#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
/*
* For further optimization on multi-head logs, on-disk layout supports maximum
@@ -52,10 +57,17 @@
#define VERSION_LEN 256
#define MAX_VOLUME_NAME 512
+#define MAX_PATH_LEN 64
+#define MAX_DEVICES 8
/*
* For superblock
*/
+struct f2fs_device {
+ __u8 path[MAX_PATH_LEN];
+ __le32 total_segments;
+} __packed;
+
struct f2fs_super_block {
__le32 magic; /* Magic Number */
__le16 major_ver; /* Major Version */
@@ -87,19 +99,30 @@ struct f2fs_super_block {
__u8 uuid[16]; /* 128-bit uuid for volume */
__le16 volume_name[MAX_VOLUME_NAME]; /* volume name */
__le32 extension_count; /* # of extensions below */
- __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */
+ __u8 extension_list[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];/* extension array */
__le32 cp_payload;
__u8 version[VERSION_LEN]; /* the kernel version */
__u8 init_version[VERSION_LEN]; /* the initial kernel version */
__le32 feature; /* defined features */
__u8 encryption_level; /* versioning level for encryption */
__u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
- __u8 reserved[871]; /* valid reserved region */
+ struct f2fs_device devs[MAX_DEVICES]; /* device list */
+ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */
+ __u8 hot_ext_count; /* # of hot file extension */
+ __u8 reserved[310]; /* valid reserved region */
+ __le32 crc; /* checksum of superblock */
} __packed;
/*
* For checkpoint
*/
+#define CP_DISABLED_QUICK_FLAG 0x00002000
+#define CP_DISABLED_FLAG 0x00001000
+#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800
+#define CP_LARGE_NAT_BITMAP_FLAG 0x00000400
+#define CP_NOCRC_RECOVERY_FLAG 0x00000200
+#define CP_TRIMMED_FLAG 0x00000100
+#define CP_NAT_BITS_FLAG 0x00000080
#define CP_CRC_RECOVERY_FLAG 0x00000040
#define CP_FASTBOOT_FLAG 0x00000020
#define CP_FSCK_FLAG 0x00000010
@@ -146,7 +169,7 @@ struct f2fs_checkpoint {
*/
#define F2FS_ORPHANS_PER_BLOCK 1020
-#define GET_ORPHAN_BLOCKS(n) ((n + F2FS_ORPHANS_PER_BLOCK - 1) / \
+#define GET_ORPHAN_BLOCKS(n) (((n) + F2FS_ORPHANS_PER_BLOCK - 1) / \
F2FS_ORPHANS_PER_BLOCK)
struct f2fs_orphan_block {
@@ -164,12 +187,15 @@ struct f2fs_orphan_block {
struct f2fs_extent {
__le32 fofs; /* start file offset of the extent */
__le32 blk; /* start block address of the extent */
- __le32 len; /* lengh of the extent */
+ __le32 len; /* length of the extent */
} __packed;
#define F2FS_NAME_LEN 255
-#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */
+/* 200 bytes for inline xattrs by default */
+#define DEFAULT_INLINE_XATTR_ADDRS 50
#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */
+#define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \
+ get_extra_isize(inode))
#define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */
#define ADDRS_PER_INODE(inode) addrs_per_inode(inode)
#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */
@@ -189,9 +215,8 @@ struct f2fs_extent {
#define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */
#define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */
#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */
-
-#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
- F2FS_INLINE_XATTR_ADDRS - 1))
+#define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */
+#define F2FS_PIN_FILE 0x40 /* file should not be gced */
struct f2fs_inode {
__le16 i_mode; /* file mode */
@@ -209,7 +234,13 @@ struct f2fs_inode {
__le32 i_ctime_nsec; /* change time in nano scale */
__le32 i_mtime_nsec; /* modification time in nano scale */
__le32 i_generation; /* file version (for NFS) */
- __le32 i_current_depth; /* only for directory depth */
+ union {
+ __le32 i_current_depth; /* only for directory depth */
+ __le16 i_gc_failures; /*
+ * # of gc failures on pinned file.
+ * only for regular files.
+ */
+ };
__le32 i_xattr_nid; /* nid to save xattr */
__le32 i_flags; /* file attributes */
__le32 i_pino; /* parent inode number */
@@ -219,8 +250,18 @@ struct f2fs_inode {
struct f2fs_extent i_ext; /* caching a largest extent */
- __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */
-
+ union {
+ struct {
+ __le16 i_extra_isize; /* extra inode attribute size */
+ __le16 i_inline_xattr_size; /* inline xattr size, unit: 4 bytes */
+ __le32 i_projid; /* project id */
+ __le32 i_inode_checksum;/* inode meta checksum */
+ __le64 i_crtime; /* creation time */
+ __le32 i_crtime_nsec; /* creation time in nano scale */
+ __le32 i_extra_end[0]; /* for attribute size calculation */
+ } __packed;
+ __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */
+ };
__le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2),
double_indirect(1) node id */
} __packed;
@@ -244,7 +285,7 @@ enum {
struct node_footer {
__le32 nid; /* node id */
- __le32 ino; /* inode nunmber */
+ __le32 ino; /* inode number */
__le32 flag; /* include cold/fsync/dentry marks and offset */
__le64 cp_ver; /* checkpoint version */
__le32 next_blkaddr; /* next node page block address */
@@ -439,7 +480,7 @@ typedef __le32 f2fs_hash_t;
#define F2FS_SLOT_LEN 8
#define F2FS_SLOT_LEN_BITS 3
-#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
+#define GET_DENTRY_SLOTS(x) (((x) + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
/* MAX level for dir lookup */
#define MAX_DIR_HASH_DEPTH 63
@@ -448,13 +489,13 @@ typedef __le32 f2fs_hash_t;
#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
/*
- * space utilization of regular dentry and inline dentry
- * regular dentry inline dentry
- * bitmap 1 * 27 = 27 1 * 23 = 23
- * reserved 1 * 3 = 3 1 * 7 = 7
- * dentry 11 * 214 = 2354 11 * 182 = 2002
- * filename 8 * 214 = 1712 8 * 182 = 1456
- * total 4096 3488
+ * space utilization of regular dentry and inline dentry (w/o extra reservation)
+ * regular dentry inline dentry (def) inline dentry (min)
+ * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1
+ * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1
+ * dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22
+ * filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16
+ * total 4096 3488 40
*
* Note: there are more reserved space in inline dentry than in regular
* dentry, when converting inline dentry we should handle this carefully.
@@ -466,12 +507,13 @@ typedef __le32 f2fs_hash_t;
#define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
F2FS_SLOT_LEN) * \
NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
+#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */
/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */
struct f2fs_dir_entry {
__le32 hash_code; /* hash code of file name */
__le32 ino; /* inode number */
- __le16 name_len; /* lengh of file name */
+ __le16 name_len; /* length of file name */
__u8 file_type; /* file type */
} __packed;
@@ -484,24 +526,6 @@ struct f2fs_dentry_block {
__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
} __packed;
-/* for inline dir */
-#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \
- ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
- BITS_PER_BYTE + 1))
-#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \
- BITS_PER_BYTE - 1) / BITS_PER_BYTE)
-#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \
- ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
- NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE))
-
-/* inline directory entry structure */
-struct f2fs_inline_dentry {
- __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE];
- __u8 reserved[INLINE_RESERVED_SIZE];
- struct f2fs_dir_entry dentry[NR_INLINE_DENTRY];
- __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN];
-} __packed;
-
/* file types used in inode_info->flags */
enum {
F2FS_FT_UNKNOWN,
@@ -517,4 +541,6 @@ enum {
#define S_SHIFT 12
+#define F2FS_DEF_PROJID 0 /* default project ID */
+
#endif /* _LINUX_F2FS_FS_H */
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 9bb2c0c..7c9b78c 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -108,6 +108,7 @@ struct fence_cb {
* @get_driver_name: returns the driver name.
* @get_timeline_name: return the name of the context this fence belongs to.
* @enable_signaling: enable software signaling of fence.
+ * @disable_signaling: disable software signaling of fence (optional).
* @signaled: [optional] peek whether the fence is signaled, can be null.
* @wait: custom wait implementation, or fence_default_wait.
* @release: [optional] called on destruction of fence, can be null
@@ -167,6 +168,7 @@ struct fence_ops {
const char * (*get_driver_name)(struct fence *fence);
const char * (*get_timeline_name)(struct fence *fence);
bool (*enable_signaling)(struct fence *fence);
+ void (*disable_signaling)(struct fence *fence);
bool (*signaled)(struct fence *fence);
signed long (*wait)(struct fence *fence, bool intr, signed long timeout);
void (*release)(struct fence *fence);
@@ -183,6 +185,16 @@ void fence_release(struct kref *kref);
void fence_free(struct fence *fence);
/**
+ * fence_put - decreases refcount of the fence
+ * @fence: [in] fence to reduce refcount of
+ */
+static inline void fence_put(struct fence *fence)
+{
+ if (fence)
+ kref_put(&fence->refcount, fence_release);
+}
+
+/**
* fence_get - increases refcount of the fence
* @fence: [in] fence to increase refcount of
*
@@ -210,13 +222,49 @@ static inline struct fence *fence_get_rcu(struct fence *fence)
}
/**
- * fence_put - decreases refcount of the fence
- * @fence: [in] fence to reduce refcount of
+ * fence_get_rcu_safe - acquire a reference to an RCU tracked fence
+ * @fence: [in] pointer to fence to increase refcount of
+ *
+ * Function returns NULL if no refcount could be obtained, or the fence.
+ * This function handles acquiring a reference to a fence that may be
+ * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU),
+ * so long as the caller is using RCU on the pointer to the fence.
+ *
+ * An alternative mechanism is to employ a seqlock to protect a bunch of
+ * fences, such as used by struct reservation_object. When using a seqlock,
+ * the seqlock must be taken before and checked after a reference to the
+ * fence is acquired (as shown here).
+ *
+ * The caller is required to hold the RCU read lock.
*/
-static inline void fence_put(struct fence *fence)
+static inline struct fence *fence_get_rcu_safe(struct fence * __rcu *fencep)
{
- if (fence)
- kref_put(&fence->refcount, fence_release);
+ do {
+ struct fence *fence;
+
+ fence = rcu_dereference(*fencep);
+ if (!fence || !fence_get_rcu(fence))
+ return NULL;
+
+ /* The atomic_inc_not_zero() inside fence_get_rcu()
+ * provides a full memory barrier upon success (such as now).
+ * This is paired with the write barrier from assigning
+ * to the __rcu protected fence pointer so that if that
+ * pointer still matches the current fence, we know we
+ * have successfully acquire a reference to it. If it no
+ * longer matches, we are holding a reference to some other
+ * reallocated pointer. This is possible if the allocator
+ * is using a freelist like SLAB_DESTROY_BY_RCU where the
+ * fence remains valid for the RCU grace period, but it
+ * may be reallocated. When using such allocators, we are
+ * responsible for ensuring the reference we get is to
+ * the right fence, as below.
+ */
+ if (fence == rcu_access_pointer(*fencep))
+ return rcu_pointer_handoff(fence);
+
+ fence_put(fence);
+ } while (1);
}
int fence_signal(struct fence *fence);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0837d90..69e8e19 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -423,7 +423,7 @@ struct sk_filter {
struct bpf_prog *prog;
};
-#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi)
+#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi)
#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b8d65e0..681f0ac 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -21,6 +21,7 @@
#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
+#include <linux/fcntl.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
@@ -149,6 +150,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
+/* File is capable of returning -EAGAIN if I/O will block */
+#define FMODE_NOWAIT ((__force fmode_t)0x8000000)
+
/*
* Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
* that indicates that they should check the contents of the iovec are
@@ -321,6 +325,18 @@ struct page;
struct address_space;
struct writeback_control;
+/*
+ * Write life time hint values.
+ */
+enum rw_hint {
+ WRITE_LIFE_NOT_SET = 0,
+ WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE,
+ WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT,
+ WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM,
+ WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG,
+ WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME,
+};
+
#define IOCB_EVENTFD (1 << 0)
#define IOCB_APPEND (1 << 1)
#define IOCB_DIRECT (1 << 2)
@@ -328,6 +344,7 @@ struct writeback_control;
#define IOCB_DSYNC (1 << 4)
#define IOCB_SYNC (1 << 5)
#define IOCB_WRITE (1 << 6)
+#define IOCB_NOWAIT (1 << 7)
struct kiocb {
struct file *ki_filp;
@@ -335,6 +352,7 @@ struct kiocb {
void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
void *private;
int ki_flags;
+ enum rw_hint ki_hint;
};
static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -648,6 +666,7 @@ struct inode {
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
unsigned int i_blkbits;
+ enum rw_hint i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
@@ -1076,8 +1095,6 @@ struct file_lock_context {
#define OFFT_OFFSET_MAX INT_LIMIT(off_t)
#endif
-#include <linux/fcntl.h>
-
extern void send_sigio(struct fown_struct *fown, int fd, int band);
/*
@@ -1616,13 +1633,21 @@ extern bool inode_owner_or_capable(const struct inode *inode);
* VFS helper functions..
*/
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
+extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
+extern int vfs_mkdir2(struct vfsmount *, struct inode *, struct dentry *, umode_t);
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+extern int vfs_mknod2(struct vfsmount *, struct inode *, struct dentry *, umode_t, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
+extern int vfs_symlink2(struct vfsmount *, struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
+extern int vfs_link2(struct vfsmount *, struct dentry *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rmdir(struct inode *, struct dentry *);
+extern int vfs_rmdir2(struct vfsmount *, struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
+extern int vfs_unlink2(struct vfsmount *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
+extern int vfs_rename2(struct vfsmount *, struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
extern int vfs_whiteout(struct inode *, struct dentry *);
/*
@@ -1750,6 +1775,7 @@ struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
int (*permission) (struct inode *, int);
+ int (*permission2) (struct vfsmount *, struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
@@ -1764,6 +1790,7 @@ struct inode_operations {
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct dentry *, struct iattr *);
+ int (*setattr2) (struct vfsmount *, struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
@@ -1812,9 +1839,13 @@ struct super_operations {
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
+ int (*remount_fs2) (struct vfsmount *, struct super_block *, int *, char *);
+ void *(*clone_mnt_data) (void *);
+ void (*copy_mnt_data) (void *, void *);
void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct dentry *);
+ int (*show_options2)(struct vfsmount *,struct seq_file *, struct dentry *);
int (*show_devname)(struct seq_file *, struct dentry *);
int (*show_path)(struct seq_file *, struct dentry *);
int (*show_stats)(struct seq_file *, struct dentry *);
@@ -1851,6 +1882,7 @@ struct super_operations {
#else
#define S_DAX 0 /* Make all the DAX code disappear */
#endif
+#define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -1889,6 +1921,7 @@ struct super_operations {
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
#define IS_DAX(inode) ((inode)->i_flags & S_DAX)
+#define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED)
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
@@ -2052,6 +2085,9 @@ struct file_system_type {
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
+ struct dentry *(*mount2) (struct vfsmount *, struct file_system_type *, int,
+ const char *, void *);
+ void *(*alloc_mnt_data) (void);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
@@ -2350,6 +2386,8 @@ struct filename {
extern long vfs_truncate(const struct path *, loff_t);
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
+extern int do_truncate2(struct vfsmount *, struct dentry *, loff_t start,
+ unsigned int time_attrs, struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
@@ -2592,8 +2630,11 @@ extern void emergency_remount(void);
extern sector_t bmap(struct inode *, sector_t);
#endif
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
+extern int notify_change2(struct vfsmount *, struct dentry *, struct iattr *, struct inode **);
extern int inode_permission(struct inode *, int);
+extern int inode_permission2(struct vfsmount *, struct inode *, int);
extern int __inode_permission(struct inode *, int);
+extern int __inode_permission2(struct vfsmount *, struct inode *, int);
extern int generic_permission(struct inode *, int);
extern int __check_sticky(struct inode *dir, struct inode *inode);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
new file mode 100644
index 0000000..9e535af
--- /dev/null
+++ b/include/linux/fscrypt.h
@@ -0,0 +1,250 @@
+/*
+ * fscrypt.h: declarations for per-file encryption
+ *
+ * Filesystems that implement per-file encryption include this header
+ * file with the __FS_HAS_ENCRYPTION set according to whether that filesystem
+ * is being built with encryption support or not.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+#ifndef _LINUX_FSCRYPT_H
+#define _LINUX_FSCRYPT_H
+
+#include <linux/fs.h>
+
+#define FS_CRYPTO_BLOCK_SIZE 16
+
+struct fscrypt_ctx;
+struct fscrypt_info;
+
+struct fscrypt_str {
+ unsigned char *name;
+ u32 len;
+};
+
+struct fscrypt_name {
+ const struct qstr *usr_fname;
+ struct fscrypt_str disk_name;
+ u32 hash;
+ u32 minor_hash;
+ struct fscrypt_str crypto_buf;
+};
+
+#define FSTR_INIT(n, l) { .name = n, .len = l }
+#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len)
+#define fname_name(p) ((p)->disk_name.name)
+#define fname_len(p) ((p)->disk_name.len)
+
+#if __FS_HAS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
+
+/**
+ * fscrypt_require_key - require an inode's encryption key
+ * @inode: the inode we need the key for
+ *
+ * If the inode is encrypted, set up its encryption key if not already done.
+ * Then require that the key be present and return -ENOKEY otherwise.
+ *
+ * No locks are needed, and the key will live as long as the struct inode --- so
+ * it won't go away from under you.
+ *
+ * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
+ * if a problem occurred while setting up the encryption key.
+ */
+static inline int fscrypt_require_key(struct inode *inode)
+{
+ if (IS_ENCRYPTED(inode)) {
+ int err = fscrypt_get_encryption_info(inode);
+
+ if (err)
+ return err;
+ if (!fscrypt_has_encryption_key(inode))
+ return -ENOKEY;
+ }
+ return 0;
+}
+
+/**
+ * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory
+ * @old_dentry: an existing dentry for the inode being linked
+ * @dir: the target directory
+ * @dentry: negative dentry for the target filename
+ *
+ * A new link can only be added to an encrypted directory if the directory's
+ * encryption key is available --- since otherwise we'd have no way to encrypt
+ * the filename. Therefore, we first set up the directory's encryption key (if
+ * not already done) and return an error if it's unavailable.
+ *
+ * We also verify that the link will not violate the constraint that all files
+ * in an encrypted directory tree use the same encryption policy.
+ *
+ * Return: 0 on success, -ENOKEY if the directory's encryption key is missing,
+ * -EPERM if the link would result in an inconsistent encryption policy, or
+ * another -errno code.
+ */
+static inline int fscrypt_prepare_link(struct dentry *old_dentry,
+ struct inode *dir,
+ struct dentry *dentry)
+{
+ if (IS_ENCRYPTED(dir))
+ return __fscrypt_prepare_link(d_inode(old_dentry), dir);
+ return 0;
+}
+
+/**
+ * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories
+ * @old_dir: source directory
+ * @old_dentry: dentry for source file
+ * @new_dir: target directory
+ * @new_dentry: dentry for target location (may be negative unless exchanging)
+ * @flags: rename flags (we care at least about %RENAME_EXCHANGE)
+ *
+ * Prepare for ->rename() where the source and/or target directories may be
+ * encrypted. A new link can only be added to an encrypted directory if the
+ * directory's encryption key is available --- since otherwise we'd have no way
+ * to encrypt the filename. A rename to an existing name, on the other hand,
+ * *is* cryptographically possible without the key. However, we take the more
+ * conservative approach and just forbid all no-key renames.
+ *
+ * We also verify that the rename will not violate the constraint that all files
+ * in an encrypted directory tree use the same encryption policy.
+ *
+ * Return: 0 on success, -ENOKEY if an encryption key is missing, -EPERM if the
+ * rename would cause inconsistent encryption policies, or another -errno code.
+ */
+static inline int fscrypt_prepare_rename(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry,
+ unsigned int flags)
+{
+ if (IS_ENCRYPTED(old_dir) || IS_ENCRYPTED(new_dir))
+ return __fscrypt_prepare_rename(old_dir, old_dentry,
+ new_dir, new_dentry, flags);
+ return 0;
+}
+
+/**
+ * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory
+ * @dir: directory being searched
+ * @dentry: filename being looked up
+ * @flags: lookup flags
+ *
+ * Prepare for ->lookup() in a directory which may be encrypted. Lookups can be
+ * done with or without the directory's encryption key; without the key,
+ * filenames are presented in encrypted form. Therefore, we'll try to set up
+ * the directory's encryption key, but even without it the lookup can continue.
+ *
+ * To allow invalidating stale dentries if the directory's encryption key is
+ * added later, we also install a custom ->d_revalidate() method and use the
+ * DCACHE_ENCRYPTED_WITH_KEY flag to indicate whether a given dentry is a
+ * plaintext name (flag set) or a ciphertext name (flag cleared).
+ *
+ * Return: 0 on success, -errno if a problem occurred while setting up the
+ * encryption key
+ */
+static inline int fscrypt_prepare_lookup(struct inode *dir,
+ struct dentry *dentry,
+ unsigned int flags)
+{
+ if (IS_ENCRYPTED(dir))
+ return __fscrypt_prepare_lookup(dir, dentry);
+ return 0;
+}
+
+/**
+ * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes
+ * @dentry: dentry through which the inode is being changed
+ * @attr: attributes to change
+ *
+ * Prepare for ->setattr() on a possibly-encrypted inode. On an encrypted file,
+ * most attribute changes are allowed even without the encryption key. However,
+ * without the encryption key we do have to forbid truncates. This is needed
+ * because the size being truncated to may not be a multiple of the filesystem
+ * block size, and in that case we'd have to decrypt the final block, zero the
+ * portion past i_size, and re-encrypt it. (We *could* allow truncating to a
+ * filesystem block boundary, but it's simpler to just forbid all truncates ---
+ * and we already forbid all other contents modifications without the key.)
+ *
+ * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
+ * if a problem occurred while setting up the encryption key.
+ */
+static inline int fscrypt_prepare_setattr(struct dentry *dentry,
+ struct iattr *attr)
+{
+ if (attr->ia_valid & ATTR_SIZE)
+ return fscrypt_require_key(d_inode(dentry));
+ return 0;
+}
+
+/**
+ * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink
+ * @dir: directory in which the symlink is being created
+ * @target: plaintext symlink target
+ * @len: length of @target excluding null terminator
+ * @max_len: space the filesystem has available to store the symlink target
+ * @disk_link: (out) the on-disk symlink target being prepared
+ *
+ * This function computes the size the symlink target will require on-disk,
+ * stores it in @disk_link->len, and validates it against @max_len. An
+ * encrypted symlink may be longer than the original.
+ *
+ * Additionally, @disk_link->name is set to @target if the symlink will be
+ * unencrypted, but left NULL if the symlink will be encrypted. For encrypted
+ * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
+ * on-disk target later. (The reason for the two-step process is that some
+ * filesystems need to know the size of the symlink target before creating the
+ * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
+ *
+ * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
+ * -ENOKEY if the encryption key is missing, or another -errno code if a problem
+ * occurred while setting up the encryption key.
+ */
+static inline int fscrypt_prepare_symlink(struct inode *dir,
+ const char *target,
+ unsigned int len,
+ unsigned int max_len,
+ struct fscrypt_str *disk_link)
+{
+ if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir))
+ return __fscrypt_prepare_symlink(dir, len, max_len, disk_link);
+
+ disk_link->name = (unsigned char *)target;
+ disk_link->len = len + 1;
+ if (disk_link->len > max_len)
+ return -ENAMETOOLONG;
+ return 0;
+}
+
+/**
+ * fscrypt_encrypt_symlink - encrypt the symlink target if needed
+ * @inode: symlink inode
+ * @target: plaintext symlink target
+ * @len: length of @target excluding null terminator
+ * @disk_link: (in/out) the on-disk symlink target being prepared
+ *
+ * If the symlink target needs to be encrypted, then this function encrypts it
+ * into @disk_link->name. fscrypt_prepare_symlink() must have been called
+ * previously to compute @disk_link->len. If the filesystem did not allocate a
+ * buffer for @disk_link->name after calling fscrypt_prepare_link(), then one
+ * will be kmalloc()'ed and the filesystem will be responsible for freeing it.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static inline int fscrypt_encrypt_symlink(struct inode *inode,
+ const char *target,
+ unsigned int len,
+ struct fscrypt_str *disk_link)
+{
+ if (IS_ENCRYPTED(inode))
+ return __fscrypt_encrypt_symlink(inode, target, len, disk_link);
+ return 0;
+}
+
+#endif /* _LINUX_FSCRYPT_H */
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
new file mode 100644
index 0000000..cbec086
--- /dev/null
+++ b/include/linux/fscrypt_notsupp.h
@@ -0,0 +1,230 @@
+/*
+ * fscrypt_notsupp.h
+ *
+ * This stubs out the fscrypt functions for filesystems configured without
+ * encryption support.
+ *
+ * Do not include this file directly. Use fscrypt.h instead!
+ */
+#ifndef _LINUX_FSCRYPT_H
+#error "Incorrect include of linux/fscrypt_notsupp.h!"
+#endif
+
+#ifndef _LINUX_FSCRYPT_NOTSUPP_H
+#define _LINUX_FSCRYPT_NOTSUPP_H
+
+static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+{
+ return false;
+}
+
+static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+{
+ return false;
+}
+
+/* crypto.c */
+static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
+{
+}
+
+static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode,
+ gfp_t gfp_flags)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+ return;
+}
+
+static inline struct page *fscrypt_encrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len,
+ unsigned int offs,
+ u64 lblk_num, gfp_t gfp_flags)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int fscrypt_decrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len, unsigned int offs,
+ u64 lblk_num)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+}
+
+static inline void fscrypt_restore_control_page(struct page *page)
+{
+ return;
+}
+
+/* policy.c */
+static inline int fscrypt_ioctl_set_policy(struct file *filp,
+ const void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_has_permitted_context(struct inode *parent,
+ struct inode *child)
+{
+ return 0;
+}
+
+static inline int fscrypt_inherit_context(struct inode *parent,
+ struct inode *child,
+ void *fs_data, bool preload)
+{
+ return -EOPNOTSUPP;
+}
+
+/* keyinfo.c */
+static inline int fscrypt_get_encryption_info(struct inode *inode)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_put_encryption_info(struct inode *inode)
+{
+ return;
+}
+
+ /* fname.c */
+static inline int fscrypt_setup_filename(struct inode *dir,
+ const struct qstr *iname,
+ int lookup, struct fscrypt_name *fname)
+{
+ if (IS_ENCRYPTED(dir))
+ return -EOPNOTSUPP;
+
+ memset(fname, 0, sizeof(struct fscrypt_name));
+ fname->usr_fname = iname;
+ fname->disk_name.name = (unsigned char *)iname->name;
+ fname->disk_name.len = iname->len;
+ return 0;
+}
+
+static inline void fscrypt_free_filename(struct fscrypt_name *fname)
+{
+ return;
+}
+
+static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
+ u32 max_encrypted_len,
+ struct fscrypt_str *crypto_str)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
+{
+ return;
+}
+
+static inline int fscrypt_fname_disk_to_usr(struct inode *inode,
+ u32 hash, u32 minor_hash,
+ const struct fscrypt_str *iname,
+ struct fscrypt_str *oname)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
+ const u8 *de_name, u32 de_name_len)
+{
+ /* Encryption support disabled; use standard comparison */
+ if (de_name_len != fname->disk_name.len)
+ return false;
+ return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len);
+}
+
+/* bio.c */
+static inline void fscrypt_decrypt_bio(struct bio *bio)
+{
+}
+
+static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
+ struct bio *bio)
+{
+}
+
+static inline void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+ return;
+}
+
+static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+ sector_t pblk, unsigned int len)
+{
+ return -EOPNOTSUPP;
+}
+
+/* hooks.c */
+
+static inline int fscrypt_file_open(struct inode *inode, struct file *filp)
+{
+ if (IS_ENCRYPTED(inode))
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+static inline int __fscrypt_prepare_link(struct inode *inode,
+ struct inode *dir)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int __fscrypt_prepare_rename(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry,
+ unsigned int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int __fscrypt_prepare_lookup(struct inode *dir,
+ struct dentry *dentry)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int __fscrypt_prepare_symlink(struct inode *dir,
+ unsigned int len,
+ unsigned int max_len,
+ struct fscrypt_str *disk_link)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int __fscrypt_encrypt_symlink(struct inode *inode,
+ const char *target,
+ unsigned int len,
+ struct fscrypt_str *disk_link)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline const char *fscrypt_get_symlink(struct inode *inode,
+ const void *caddr,
+ unsigned int max_size,
+ struct delayed_call *done)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+#endif /* _LINUX_FSCRYPT_NOTSUPP_H */
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
new file mode 100644
index 0000000..99b6c52
--- /dev/null
+++ b/include/linux/fscrypt_supp.h
@@ -0,0 +1,203 @@
+/*
+ * fscrypt_supp.h
+ *
+ * Do not include this file directly. Use fscrypt.h instead!
+ */
+#ifndef _LINUX_FSCRYPT_H
+#error "Incorrect include of linux/fscrypt_supp.h!"
+#endif
+
+#ifndef _LINUX_FSCRYPT_SUPP_H
+#define _LINUX_FSCRYPT_SUPP_H
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+/*
+ * fscrypt superblock flags
+ */
+#define FS_CFLG_OWN_PAGES (1U << 1)
+
+/*
+ * crypto operations for filesystems
+ */
+struct fscrypt_operations {
+ unsigned int flags;
+ const char *key_prefix;
+ int (*get_context)(struct inode *, void *, size_t);
+ int (*set_context)(struct inode *, const void *, size_t, void *);
+ bool (*dummy_context)(struct inode *);
+ bool (*empty_dir)(struct inode *);
+ unsigned int max_namelen;
+};
+
+struct fscrypt_ctx {
+ union {
+ struct {
+ struct page *bounce_page; /* Ciphertext page */
+ struct page *control_page; /* Original page */
+ } w;
+ struct {
+ struct bio *bio;
+ struct work_struct work;
+ } r;
+ struct list_head free_list; /* Free list */
+ };
+ u8 flags; /* Flags */
+};
+
+static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+{
+ return (inode->i_crypt_info != NULL);
+}
+
+static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+{
+ return inode->i_sb->s_cop->dummy_context &&
+ inode->i_sb->s_cop->dummy_context(inode);
+}
+
+/* crypto.c */
+extern void fscrypt_enqueue_decrypt_work(struct work_struct *);
+extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
+extern void fscrypt_release_ctx(struct fscrypt_ctx *);
+extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
+ unsigned int, unsigned int,
+ u64, gfp_t);
+extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int,
+ unsigned int, u64);
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+ return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
+}
+
+extern void fscrypt_restore_control_page(struct page *);
+
+/* policy.c */
+extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
+extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
+extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
+extern int fscrypt_inherit_context(struct inode *, struct inode *,
+ void *, bool);
+/* keyinfo.c */
+extern int fscrypt_get_encryption_info(struct inode *);
+extern void fscrypt_put_encryption_info(struct inode *);
+
+/* fname.c */
+extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
+ int lookup, struct fscrypt_name *);
+
+static inline void fscrypt_free_filename(struct fscrypt_name *fname)
+{
+ kfree(fname->crypto_buf.name);
+}
+
+extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
+ struct fscrypt_str *);
+extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
+extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
+ const struct fscrypt_str *, struct fscrypt_str *);
+
+#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32
+
+/* Extracts the second-to-last ciphertext block; see explanation below */
+#define FSCRYPT_FNAME_DIGEST(name, len) \
+ ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \
+ FS_CRYPTO_BLOCK_SIZE))
+
+#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE
+
+/**
+ * fscrypt_digested_name - alternate identifier for an on-disk filename
+ *
+ * When userspace lists an encrypted directory without access to the key,
+ * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE
+ * bytes are shown in this abbreviated form (base64-encoded) rather than as the
+ * full ciphertext (base64-encoded). This is necessary to allow supporting
+ * filenames up to NAME_MAX bytes, since base64 encoding expands the length.
+ *
+ * To make it possible for filesystems to still find the correct directory entry
+ * despite not knowing the full on-disk name, we encode any filesystem-specific
+ * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups,
+ * followed by the second-to-last ciphertext block of the filename. Due to the
+ * use of the CBC-CTS encryption mode, the second-to-last ciphertext block
+ * depends on the full plaintext. (Note that ciphertext stealing causes the
+ * last two blocks to appear "flipped".) This makes accidental collisions very
+ * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they
+ * share the same filesystem-specific hashes.
+ *
+ * However, this scheme isn't immune to intentional collisions, which can be
+ * created by anyone able to create arbitrary plaintext filenames and view them
+ * without the key. Making the "digest" be a real cryptographic hash like
+ * SHA-256 over the full ciphertext would prevent this, although it would be
+ * less efficient and harder to implement, especially since the filesystem would
+ * need to calculate it for each directory entry examined during a search.
+ */
+struct fscrypt_digested_name {
+ u32 hash;
+ u32 minor_hash;
+ u8 digest[FSCRYPT_FNAME_DIGEST_SIZE];
+};
+
+/**
+ * fscrypt_match_name() - test whether the given name matches a directory entry
+ * @fname: the name being searched for
+ * @de_name: the name from the directory entry
+ * @de_name_len: the length of @de_name in bytes
+ *
+ * Normally @fname->disk_name will be set, and in that case we simply compare
+ * that to the name stored in the directory entry. The only exception is that
+ * if we don't have the key for an encrypted directory and a filename in it is
+ * very long, then we won't have the full disk_name and we'll instead need to
+ * match against the fscrypt_digested_name.
+ *
+ * Return: %true if the name matches, otherwise %false.
+ */
+static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
+ const u8 *de_name, u32 de_name_len)
+{
+ if (unlikely(!fname->disk_name.name)) {
+ const struct fscrypt_digested_name *n =
+ (const void *)fname->crypto_buf.name;
+ if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_'))
+ return false;
+ if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE)
+ return false;
+ return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len),
+ n->digest, FSCRYPT_FNAME_DIGEST_SIZE);
+ }
+
+ if (de_name_len != fname->disk_name.len)
+ return false;
+ return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len);
+}
+
+/* bio.c */
+extern void fscrypt_decrypt_bio(struct bio *);
+extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
+ struct bio *bio);
+extern void fscrypt_pullback_bio_page(struct page **, bool);
+extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
+ unsigned int);
+
+/* hooks.c */
+extern int fscrypt_file_open(struct inode *inode, struct file *filp);
+extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir);
+extern int __fscrypt_prepare_rename(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry,
+ unsigned int flags);
+extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry);
+extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
+ unsigned int max_len,
+ struct fscrypt_str *disk_link);
+extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
+ unsigned int len,
+ struct fscrypt_str *disk_link);
+extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
+ unsigned int max_size,
+ struct delayed_call *done);
+
+#endif /* _LINUX_FSCRYPT_SUPP_H */
diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h
deleted file mode 100644
index 3b1f17d..0000000
--- a/include/linux/fscrypto.h
+++ /dev/null
@@ -1,409 +0,0 @@
-/*
- * General per-file encryption definition
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-
-#ifndef _LINUX_FSCRYPTO_H
-#define _LINUX_FSCRYPTO_H
-
-#include <linux/key.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/bio.h>
-#include <linux/dcache.h>
-#include <crypto/skcipher.h>
-#include <uapi/linux/fs.h>
-
-#define FS_KEY_DERIVATION_NONCE_SIZE 16
-#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
-
-#define FS_POLICY_FLAGS_PAD_4 0x00
-#define FS_POLICY_FLAGS_PAD_8 0x01
-#define FS_POLICY_FLAGS_PAD_16 0x02
-#define FS_POLICY_FLAGS_PAD_32 0x03
-#define FS_POLICY_FLAGS_PAD_MASK 0x03
-#define FS_POLICY_FLAGS_VALID 0x03
-
-/* Encryption algorithms */
-#define FS_ENCRYPTION_MODE_INVALID 0
-#define FS_ENCRYPTION_MODE_AES_256_XTS 1
-#define FS_ENCRYPTION_MODE_AES_256_GCM 2
-#define FS_ENCRYPTION_MODE_AES_256_CBC 3
-#define FS_ENCRYPTION_MODE_AES_256_CTS 4
-
-/**
- * Encryption context for inode
- *
- * Protector format:
- * 1 byte: Protector format (1 = this version)
- * 1 byte: File contents encryption mode
- * 1 byte: File names encryption mode
- * 1 byte: Flags
- * 8 bytes: Master Key descriptor
- * 16 bytes: Encryption Key derivation nonce
- */
-struct fscrypt_context {
- u8 format;
- u8 contents_encryption_mode;
- u8 filenames_encryption_mode;
- u8 flags;
- u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
- u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
-} __packed;
-
-/* Encryption parameters */
-#define FS_XTS_TWEAK_SIZE 16
-#define FS_AES_128_ECB_KEY_SIZE 16
-#define FS_AES_256_GCM_KEY_SIZE 32
-#define FS_AES_256_CBC_KEY_SIZE 32
-#define FS_AES_256_CTS_KEY_SIZE 32
-#define FS_AES_256_XTS_KEY_SIZE 64
-#define FS_MAX_KEY_SIZE 64
-
-#define FS_KEY_DESC_PREFIX "fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE 8
-
-/* This is passed in from userspace into the kernel keyring */
-struct fscrypt_key {
- u32 mode;
- u8 raw[FS_MAX_KEY_SIZE];
- u32 size;
-} __packed;
-
-struct fscrypt_info {
- u8 ci_data_mode;
- u8 ci_filename_mode;
- u8 ci_flags;
- struct crypto_skcipher *ci_ctfm;
- u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
-#define FS_WRITE_PATH_FL 0x00000002
-
-struct fscrypt_ctx {
- union {
- struct {
- struct page *bounce_page; /* Ciphertext page */
- struct page *control_page; /* Original page */
- } w;
- struct {
- struct bio *bio;
- struct work_struct work;
- } r;
- struct list_head free_list; /* Free list */
- };
- u8 flags; /* Flags */
- u8 mode; /* Encryption mode for tfm */
-};
-
-struct fscrypt_completion_result {
- struct completion completion;
- int res;
-};
-
-#define DECLARE_FS_COMPLETION_RESULT(ecr) \
- struct fscrypt_completion_result ecr = { \
- COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-#define FS_FNAME_NUM_SCATTER_ENTRIES 4
-#define FS_CRYPTO_BLOCK_SIZE 16
-#define FS_FNAME_CRYPTO_DIGEST_SIZE 32
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct fscrypt_symlink_data {
- __le16 len;
- char encrypted_path[1];
-} __packed;
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 fscrypt_symlink_data_len(u32 l)
-{
- if (l < FS_CRYPTO_BLOCK_SIZE)
- l = FS_CRYPTO_BLOCK_SIZE;
- return (l + sizeof(struct fscrypt_symlink_data) - 1);
-}
-
-struct fscrypt_str {
- unsigned char *name;
- u32 len;
-};
-
-struct fscrypt_name {
- const struct qstr *usr_fname;
- struct fscrypt_str disk_name;
- u32 hash;
- u32 minor_hash;
- struct fscrypt_str crypto_buf;
-};
-
-#define FSTR_INIT(n, l) { .name = n, .len = l }
-#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len)
-#define fname_name(p) ((p)->disk_name.name)
-#define fname_len(p) ((p)->disk_name.len)
-
-/*
- * crypto opertions for filesystems
- */
-struct fscrypt_operations {
- int (*get_context)(struct inode *, void *, size_t);
- int (*key_prefix)(struct inode *, u8 **);
- int (*prepare_context)(struct inode *);
- int (*set_context)(struct inode *, const void *, size_t, void *);
- int (*dummy_context)(struct inode *);
- bool (*is_encrypted)(struct inode *);
- bool (*empty_dir)(struct inode *);
- unsigned (*max_namelen)(struct inode *);
-};
-
-static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
-{
- if (inode->i_sb->s_cop->dummy_context &&
- inode->i_sb->s_cop->dummy_context(inode))
- return true;
- return false;
-}
-
-static inline bool fscrypt_valid_contents_enc_mode(u32 mode)
-{
- return (mode == FS_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-static inline bool fscrypt_valid_filenames_enc_mode(u32 mode)
-{
- return (mode == FS_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
-{
- if (str->len == 1 && str->name[0] == '.')
- return true;
-
- if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
- return true;
-
- return false;
-}
-
-static inline struct page *fscrypt_control_page(struct page *page)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
- return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
-#else
- WARN_ON_ONCE(1);
- return ERR_PTR(-EINVAL);
-#endif
-}
-
-static inline int fscrypt_has_encryption_key(struct inode *inode)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
- return (inode->i_crypt_info != NULL);
-#else
- return 0;
-#endif
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
- spin_lock(&dentry->d_lock);
- dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
- spin_unlock(&dentry->d_lock);
-#endif
-}
-
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-extern const struct dentry_operations fscrypt_d_ops;
-#endif
-
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
- d_set_d_op(dentry, &fscrypt_d_ops);
-#endif
-}
-
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-/* crypto.c */
-extern struct kmem_cache *fscrypt_info_cachep;
-int fscrypt_initialize(void);
-
-extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t);
-extern void fscrypt_release_ctx(struct fscrypt_ctx *);
-extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t);
-extern int fscrypt_decrypt_page(struct page *);
-extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
-extern void fscrypt_pullback_bio_page(struct page **, bool);
-extern void fscrypt_restore_control_page(struct page *);
-extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t,
- unsigned int);
-/* policy.c */
-extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
-extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
-extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
-extern int fscrypt_inherit_context(struct inode *, struct inode *,
- void *, bool);
-/* keyinfo.c */
-extern int fscrypt_get_encryption_info(struct inode *);
-extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
-
-/* fname.c */
-extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
- int lookup, struct fscrypt_name *);
-extern void fscrypt_free_filename(struct fscrypt_name *);
-extern u32 fscrypt_fname_encrypted_size(struct inode *, u32);
-extern int fscrypt_fname_alloc_buffer(struct inode *, u32,
- struct fscrypt_str *);
-extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
-extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
- const struct fscrypt_str *, struct fscrypt_str *);
-extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
- struct fscrypt_str *);
-#endif
-
-/* crypto.c */
-static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i,
- gfp_t f)
-{
- return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c)
-{
- return;
-}
-
-static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i,
- struct page *p, gfp_t f)
-{
- return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline int fscrypt_notsupp_decrypt_page(struct page *p)
-{
- return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c,
- struct bio *b)
-{
- return;
-}
-
-static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b)
-{
- return;
-}
-
-static inline void fscrypt_notsupp_restore_control_page(struct page *p)
-{
- return;
-}
-
-static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p,
- sector_t s, unsigned int f)
-{
- return -EOPNOTSUPP;
-}
-
-/* policy.c */
-static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f,
- const void __user *arg)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f,
- void __user *arg)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_has_permitted_context(struct inode *p,
- struct inode *i)
-{
- return 0;
-}
-
-static inline int fscrypt_notsupp_inherit_context(struct inode *p,
- struct inode *i, void *v, bool b)
-{
- return -EOPNOTSUPP;
-}
-
-/* keyinfo.c */
-static inline int fscrypt_notsupp_get_encryption_info(struct inode *i)
-{
- return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_put_encryption_info(struct inode *i,
- struct fscrypt_info *f)
-{
- return;
-}
-
- /* fname.c */
-static inline int fscrypt_notsupp_setup_filename(struct inode *dir,
- const struct qstr *iname,
- int lookup, struct fscrypt_name *fname)
-{
- if (dir->i_sb->s_cop->is_encrypted(dir))
- return -EOPNOTSUPP;
-
- memset(fname, 0, sizeof(struct fscrypt_name));
- fname->usr_fname = iname;
- fname->disk_name.name = (unsigned char *)iname->name;
- fname->disk_name.len = iname->len;
- return 0;
-}
-
-static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname)
-{
- return;
-}
-
-static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s)
-{
- /* never happens */
- WARN_ON(1);
- return 0;
-}
-
-static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode,
- u32 ilen, struct fscrypt_str *crypto_str)
-{
- return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c)
-{
- return;
-}
-
-static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode,
- u32 hash, u32 minor_hash,
- const struct fscrypt_str *iname,
- struct fscrypt_str *oname)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode,
- const struct qstr *iname,
- struct fscrypt_str *oname)
-{
- return -EOPNOTSUPP;
-}
-#endif /* _LINUX_FSCRYPTO_H */
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index e5f03a4d..ff51592 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -213,12 +213,20 @@ static inline void fsnotify_modify(struct file *file)
static inline void fsnotify_open(struct file *file)
{
struct path *path = &file->f_path;
+ struct path lower_path;
struct inode *inode = path->dentry->d_inode;
+
__u32 mask = FS_OPEN;
if (S_ISDIR(inode->i_mode))
mask |= FS_ISDIR;
+ if (path->dentry->d_op && path->dentry->d_op->d_canonical_path) {
+ path->dentry->d_op->d_canonical_path(path, &lower_path);
+ fsnotify_parent(&lower_path, NULL, mask);
+ fsnotify(lower_path.dentry->d_inode, mask, &lower_path, FSNOTIFY_EVENT_PATH, NULL, 0);
+ path_put(&lower_path);
+ }
fsnotify_parent(path, NULL, mask);
fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
}
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b3d34d3..ab7938a 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -244,8 +244,16 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
return *this_cpu_ptr(ops->disabled);
}
+#ifdef CONFIG_CFI_CLANG
+/* Use a C stub with the correct type for CFI */
+static inline void ftrace_stub(unsigned long a0, unsigned long a1,
+ struct ftrace_ops *op, struct pt_regs *regs)
+{
+}
+#else
extern void ftrace_stub(unsigned long a0, unsigned long a1,
struct ftrace_ops *op, struct pt_regs *regs);
+#endif
#else /* !CONFIG_FUNCTION_TRACER */
/*
@@ -734,7 +742,8 @@ static inline unsigned long get_lock_parent_ip(void)
static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
#endif
-#ifdef CONFIG_PREEMPT_TRACER
+#if defined(CONFIG_PREEMPT_TRACER) || \
+ (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
extern void trace_preempt_on(unsigned long a0, unsigned long a1);
extern void trace_preempt_off(unsigned long a0, unsigned long a1);
#else
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index d11f56b..63dfa76 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -539,7 +539,7 @@ extern void __free_page_frag(void *addr);
void page_alloc_init(void);
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
void drain_all_pages(struct zone *zone);
-void drain_local_pages(struct zone *zone);
+void drain_local_pages(void *zone);
void page_alloc_init_late(void);
diff --git a/include/linux/gpio_event.h b/include/linux/gpio_event.h
new file mode 100644
index 0000000..2613fc5
--- /dev/null
+++ b/include/linux/gpio_event.h
@@ -0,0 +1,170 @@
+/* include/linux/gpio_event.h
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_GPIO_EVENT_H
+#define _LINUX_GPIO_EVENT_H
+
+#include <linux/input.h>
+
+struct gpio_event_input_devs {
+ int count;
+ struct input_dev *dev[];
+};
+enum {
+ GPIO_EVENT_FUNC_UNINIT = 0x0,
+ GPIO_EVENT_FUNC_INIT = 0x1,
+ GPIO_EVENT_FUNC_SUSPEND = 0x2,
+ GPIO_EVENT_FUNC_RESUME = 0x3,
+};
+struct gpio_event_info {
+ int (*func)(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info,
+ void **data, int func);
+ int (*event)(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info,
+ void **data, unsigned int dev, unsigned int type,
+ unsigned int code, int value); /* out events */
+ bool no_suspend;
+};
+
+struct gpio_event_platform_data {
+ const char *name;
+ struct gpio_event_info **info;
+ size_t info_count;
+ int (*power)(const struct gpio_event_platform_data *pdata, bool on);
+ const char *names[]; /* If name is NULL, names contain a NULL */
+ /* terminated list of input devices to create */
+};
+
+#define GPIO_EVENT_DEV_NAME "gpio-event"
+
+/* Key matrix */
+
+enum gpio_event_matrix_flags {
+ /* unset: drive active output low, set: drive active output high */
+ GPIOKPF_ACTIVE_HIGH = 1U << 0,
+ GPIOKPF_DEBOUNCE = 1U << 1,
+ GPIOKPF_REMOVE_SOME_PHANTOM_KEYS = 1U << 2,
+ GPIOKPF_REMOVE_PHANTOM_KEYS = GPIOKPF_REMOVE_SOME_PHANTOM_KEYS |
+ GPIOKPF_DEBOUNCE,
+ GPIOKPF_DRIVE_INACTIVE = 1U << 3,
+ GPIOKPF_LEVEL_TRIGGERED_IRQ = 1U << 4,
+ GPIOKPF_PRINT_UNMAPPED_KEYS = 1U << 16,
+ GPIOKPF_PRINT_MAPPED_KEYS = 1U << 17,
+ GPIOKPF_PRINT_PHANTOM_KEYS = 1U << 18,
+};
+
+#define MATRIX_CODE_BITS (10)
+#define MATRIX_KEY_MASK ((1U << MATRIX_CODE_BITS) - 1)
+#define MATRIX_KEY(dev, code) \
+ (((dev) << MATRIX_CODE_BITS) | (code & MATRIX_KEY_MASK))
+
+extern int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_matrix_info {
+ /* initialize to gpio_event_matrix_func */
+ struct gpio_event_info info;
+ /* size must be ninputs * noutputs */
+ const unsigned short *keymap;
+ unsigned int *input_gpios;
+ unsigned int *output_gpios;
+ unsigned int ninputs;
+ unsigned int noutputs;
+ /* time to wait before reading inputs after driving each output */
+ ktime_t settle_time;
+ /* time to wait before scanning the keypad a second time */
+ ktime_t debounce_delay;
+ ktime_t poll_time;
+ unsigned flags;
+};
+
+/* Directly connected inputs and outputs */
+
+enum gpio_event_direct_flags {
+ GPIOEDF_ACTIVE_HIGH = 1U << 0,
+/* GPIOEDF_USE_DOWN_IRQ = 1U << 1, */
+/* GPIOEDF_USE_IRQ = (1U << 2) | GPIOIDF_USE_DOWN_IRQ, */
+ GPIOEDF_PRINT_KEYS = 1U << 8,
+ GPIOEDF_PRINT_KEY_DEBOUNCE = 1U << 9,
+ GPIOEDF_PRINT_KEY_UNSTABLE = 1U << 10,
+};
+
+struct gpio_event_direct_entry {
+ uint32_t gpio:16;
+ uint32_t code:10;
+ uint32_t dev:6;
+};
+
+/* inputs */
+extern int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_input_info {
+ /* initialize to gpio_event_input_func */
+ struct gpio_event_info info;
+ ktime_t debounce_time;
+ ktime_t poll_time;
+ uint16_t flags;
+ uint16_t type;
+ const struct gpio_event_direct_entry *keymap;
+ size_t keymap_size;
+};
+
+/* outputs */
+extern int gpio_event_output_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+extern int gpio_event_output_event(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data,
+ unsigned int dev, unsigned int type,
+ unsigned int code, int value);
+struct gpio_event_output_info {
+ /* initialize to gpio_event_output_func and gpio_event_output_event */
+ struct gpio_event_info info;
+ uint16_t flags;
+ uint16_t type;
+ const struct gpio_event_direct_entry *keymap;
+ size_t keymap_size;
+};
+
+
+/* axes */
+
+enum gpio_event_axis_flags {
+ GPIOEAF_PRINT_UNKNOWN_DIRECTION = 1U << 16,
+ GPIOEAF_PRINT_RAW = 1U << 17,
+ GPIOEAF_PRINT_EVENT = 1U << 18,
+};
+
+extern int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_axis_info {
+ /* initialize to gpio_event_axis_func */
+ struct gpio_event_info info;
+ uint8_t count; /* number of gpios for this axis */
+ uint8_t dev; /* device index when using multiple input devices */
+ uint8_t type; /* EV_REL or EV_ABS */
+ uint16_t code;
+ uint16_t decoded_size;
+ uint16_t (*map)(struct gpio_event_axis_info *info, uint16_t in);
+ uint32_t *gpio;
+ uint32_t flags;
+};
+#define gpio_axis_2bit_gray_map gpio_axis_4bit_gray_map
+#define gpio_axis_3bit_gray_map gpio_axis_4bit_gray_map
+uint16_t gpio_axis_4bit_gray_map(
+ struct gpio_event_axis_info *info, uint16_t in);
+uint16_t gpio_axis_5bit_singletrack_map(
+ struct gpio_event_axis_info *info, uint16_t in);
+
+#endif
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 9816570..17c8bea 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -345,6 +345,7 @@ struct hid_item {
#define HID_GROUP_RMI 0x0100
#define HID_GROUP_WACOM 0x0101
#define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102
+#define HID_GROUP_STEAM 0x0103
/*
* This is the global environment of the parser. This information is
@@ -523,10 +524,12 @@ struct hid_device { /* device report descriptor */
* battery is non-NULL.
*/
struct power_supply *battery;
+ __s32 battery_capacity;
__s32 battery_min;
__s32 battery_max;
__s32 battery_report_type;
__s32 battery_report_id;
+ bool battery_reported;
#endif
unsigned int status; /* see STAT flags above */
diff --git a/include/linux/if_pppolac.h b/include/linux/if_pppolac.h
new file mode 100644
index 0000000..e40aa10
--- /dev/null
+++ b/include/linux/if_pppolac.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOLAC_H
+#define __LINUX_IF_PPPOLAC_H
+
+#include <uapi/linux/if_pppolac.h>
+
+#endif /* __LINUX_IF_PPPOLAC_H */
diff --git a/include/linux/if_pppopns.h b/include/linux/if_pppopns.h
new file mode 100644
index 0000000..4ac621a9
--- /dev/null
+++ b/include/linux/if_pppopns.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOPNS_H
+#define __LINUX_IF_PPPOPNS_H
+
+#include <uapi/linux/if_pppopns.h>
+
+#endif /* __LINUX_IF_PPPOPNS_H */
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index 24e9b36..2d7699d 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -43,6 +43,25 @@ struct pptp_opt {
u32 seq_sent, seq_recv;
int ppp_flags;
};
+
+struct pppolac_opt {
+ __u32 local;
+ __u32 remote;
+ __u32 recv_sequence;
+ __u32 xmit_sequence;
+ atomic_t sequencing;
+ int (*backlog_rcv)(struct sock *sk_udp, struct sk_buff *skb);
+};
+
+struct pppopns_opt {
+ __u16 local;
+ __u16 remote;
+ __u32 recv_sequence;
+ __u32 xmit_sequence;
+ void (*data_ready)(struct sock *sk_raw);
+ int (*backlog_rcv)(struct sock *sk_raw, struct sk_buff *skb);
+};
+
#include <net/sock.h>
struct pppox_sock {
@@ -53,6 +72,8 @@ struct pppox_sock {
union {
struct pppoe_opt pppoe;
struct pptp_opt pptp;
+ struct pppolac_opt lac;
+ struct pppopns_opt pns;
} proto;
__be16 num;
};
diff --git a/include/linux/init.h b/include/linux/init.h
index 0cca414..d4b13a4 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -46,7 +46,7 @@
/* These are for everybody (although not all archs will actually
discard it in modules) */
-#define __init __section(.init.text) __cold notrace __latent_entropy __noinitretpoline
+#define __init __section(.init.text) __cold notrace __latent_entropy __noinitretpoline __nocfi
#define __initdata __section(.init.data)
#define __initconst __section(.init.rodata)
#define __exitdata __section(.exit.data)
@@ -150,6 +150,15 @@ extern bool initcall_debug;
#ifndef __ASSEMBLY__
+#ifdef CONFIG_LTO_CLANG
+ /* prepend the variable name with __COUNTER__ to ensure correct ordering */
+ #define ___initcall_name2(c, fn, id) __initcall_##c##_##fn##id
+ #define ___initcall_name1(c, fn, id) ___initcall_name2(c, fn, id)
+ #define __initcall_name(fn, id) ___initcall_name1(__COUNTER__, fn, id)
+#else
+ #define __initcall_name(fn, id) __initcall_##fn##id
+#endif
+
/*
* initcalls are now grouped by functionality into separate
* subsections. Ordering inside the subsections is determined
@@ -167,7 +176,7 @@ extern bool initcall_debug;
*/
#define __define_initcall(fn, id) \
- static initcall_t __initcall_##fn##id __used \
+ static initcall_t __initcall_name(fn, id) __used \
__attribute__((__section__(".initcall" #id ".init"))) = fn;
/*
diff --git a/include/linux/initramfs.h b/include/linux/initramfs.h
new file mode 100644
index 0000000..fc7da63
--- /dev/null
+++ b/include/linux/initramfs.h
@@ -0,0 +1,32 @@
+/*
+ * include/linux/initramfs.h
+ *
+ * Copyright (C) 2015, Google
+ * Rom Lemarchand <romlem@android.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _LINUX_INITRAMFS_H
+#define _LINUX_INITRAMFS_H
+
+#include <linux/kconfig.h>
+
+#if IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+
+int __init default_rootfs(void);
+
+#endif
+
+#endif /* _LINUX_INITRAMFS_H */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 72f0721..999b7c3 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
#include <linux/atomic.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
+#include <asm/sections.h>
/*
* These correspond to the IORESOURCE_IRQ_* defines in
@@ -699,7 +700,6 @@ extern int early_irq_init(void);
extern int arch_probe_nr_irqs(void);
extern int arch_early_irq_init(void);
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
/*
* We want to know which function is an entrypoint of a hardirq or a softirq.
*/
@@ -707,16 +707,4 @@ extern int arch_early_irq_init(void);
#define __softirq_entry \
__attribute__((__section__(".softirqentry.text")))
-/* Limits of hardirq entrypoints */
-extern char __irqentry_text_start[];
-extern char __irqentry_text_end[];
-/* Limits of softirq entrypoints */
-extern char __softirqentry_text_start[];
-extern char __softirqentry_text_end[];
-
-#else
-#define __irq_entry
-#define __softirq_entry
-#endif
-
#endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index b9dfca55..8174c89 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -37,9 +37,11 @@ struct ipv6_devconf {
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
#ifdef CONFIG_IPV6_ROUTE_INFO
+ __s32 accept_ra_rt_info_min_plen;
__s32 accept_ra_rt_info_max_plen;
#endif
#endif
+ __s32 accept_ra_rt_table;
__s32 proxy_ndp;
__s32 accept_source_route;
__s32 accept_ra_from_local;
@@ -64,6 +66,7 @@ struct ipv6_devconf {
} stable_secret;
__s32 use_oif_addrs_only;
__s32 keep_addr_on_down;
+ __u32 addr_gen_mode;
struct ctl_table_header *sysctl_header;
};
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index c9df9e1..f40dfbd 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -31,16 +31,10 @@ static inline void *kasan_mem_to_shadow(const void *addr)
}
/* Enable reporting bugs after kasan_disable_current() */
-static inline void kasan_enable_current(void)
-{
- current->kasan_depth++;
-}
+extern void kasan_enable_current(void);
/* Disable reporting bugs for current task */
-static inline void kasan_disable_current(void)
-{
- current->kasan_depth--;
-}
+extern void kasan_disable_current(void);
void kasan_unpoison_shadow(const void *address, size_t size);
@@ -53,7 +47,7 @@ void kasan_free_pages(struct page *page, unsigned int order);
void kasan_cache_create(struct kmem_cache *cache, size_t *size,
unsigned long *flags);
void kasan_cache_shrink(struct kmem_cache *cache);
-void kasan_cache_destroy(struct kmem_cache *cache);
+void kasan_cache_shutdown(struct kmem_cache *cache);
void kasan_poison_slab(struct page *page);
void kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
@@ -82,6 +76,9 @@ size_t ksize(const void *);
static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
size_t kasan_metadata_size(struct kmem_cache *cache);
+bool kasan_save_enable_multi_shot(void);
+void kasan_restore_multi_shot(bool enabled);
+
#else /* CONFIG_KASAN */
static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
@@ -99,7 +96,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache,
size_t *size,
unsigned long *flags) {}
static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
-static inline void kasan_cache_destroy(struct kmem_cache *cache) {}
+static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
static inline void kasan_poison_slab(struct page *page) {}
static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index 2883ac9..87e2a44 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -7,19 +7,23 @@ struct task_struct;
#ifdef CONFIG_KCOV
-void kcov_task_init(struct task_struct *t);
-void kcov_task_exit(struct task_struct *t);
-
enum kcov_mode {
/* Coverage collection is not enabled yet. */
KCOV_MODE_DISABLED = 0,
+ /* KCOV was initialized, but tracing mode hasn't been chosen yet. */
+ KCOV_MODE_INIT = 1,
/*
* Tracing coverage collection mode.
* Covered PCs are collected in a per-task buffer.
*/
- KCOV_MODE_TRACE = 1,
+ KCOV_MODE_TRACE_PC = 2,
+ /* Collecting comparison operands mode. */
+ KCOV_MODE_TRACE_CMP = 3,
};
+void kcov_task_init(struct task_struct *t);
+void kcov_task_exit(struct task_struct *t);
+
#else
static inline void kcov_task_init(struct task_struct *t) {}
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 7056238..44e5293 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -24,6 +24,7 @@ struct seq_file;
struct vm_area_struct;
struct super_block;
struct file_system_type;
+struct poll_table_struct;
struct kernfs_open_node;
struct kernfs_iattrs;
@@ -46,6 +47,7 @@ enum kernfs_node_flag {
KERNFS_SUICIDAL = 0x0400,
KERNFS_SUICIDED = 0x0800,
KERNFS_EMPTY_DIR = 0x1000,
+ KERNFS_HAS_RELEASE = 0x2000,
};
/* @flags for kernfs_create_root() */
@@ -175,6 +177,7 @@ struct kernfs_open_file {
/* published fields */
struct kernfs_node *kn;
struct file *file;
+ struct seq_file *seq_file;
void *priv;
/* private fields, do not use outside kernfs proper */
@@ -186,11 +189,19 @@ struct kernfs_open_file {
size_t atomic_write_len;
bool mmapped;
+ bool released:1;
const struct vm_operations_struct *vm_ops;
};
struct kernfs_ops {
/*
+ * Optional open/release methods. Both are called with
+ * @of->seq_file populated.
+ */
+ int (*open)(struct kernfs_open_file *of);
+ void (*release)(struct kernfs_open_file *of);
+
+ /*
* Read is handled by either seq_file or raw_read().
*
* If seq_show() is present, seq_file path is active. Other seq
@@ -228,6 +239,9 @@ struct kernfs_ops {
ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
loff_t off);
+ unsigned int (*poll)(struct kernfs_open_file *of,
+ struct poll_table_struct *pt);
+
int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -315,6 +329,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
const char *new_name, const void *new_ns);
int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
+unsigned int kernfs_generic_poll(struct kernfs_open_file *of,
+ struct poll_table_struct *pt);
void kernfs_notify(struct kernfs_node *kn);
const void *kernfs_super_ns(struct super_block *sb);
diff --git a/include/linux/key.h b/include/linux/key.h
index ed9b44f..7e2d143 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -369,7 +369,10 @@ static inline bool key_is_negative(const struct key *key)
return key_read_state(key) < 0;
}
-#define rcu_dereference_key(KEY) \
+#define dereference_key_rcu(KEY) \
+ (rcu_dereference((KEY)->payload.rcu_data0))
+
+#define dereference_key_locked(KEY) \
(rcu_dereference_protected((KEY)->payload.rcu_data0, \
rwsem_is_locked(&((struct key *)(KEY))->sem)))
diff --git a/include/linux/keycombo.h b/include/linux/keycombo.h
new file mode 100644
index 0000000..c6db262
--- /dev/null
+++ b/include/linux/keycombo.h
@@ -0,0 +1,36 @@
+/*
+ * include/linux/keycombo.h - platform data structure for keycombo driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYCOMBO_H
+#define _LINUX_KEYCOMBO_H
+
+#define KEYCOMBO_NAME "keycombo"
+
+/*
+ * if key_down_fn and key_up_fn are both present, you are guaranteed that
+ * key_down_fn will return before key_up_fn is called, and that key_up_fn
+ * is called iff key_down_fn is called.
+ */
+struct keycombo_platform_data {
+ void (*key_down_fn)(void *);
+ void (*key_up_fn)(void *);
+ void *priv;
+ int key_down_delay; /* Time in ms */
+ int *keys_up;
+ int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYCOMBO_H */
diff --git a/include/linux/keyreset.h b/include/linux/keyreset.h
new file mode 100644
index 0000000..2e34afa
--- /dev/null
+++ b/include/linux/keyreset.h
@@ -0,0 +1,29 @@
+/*
+ * include/linux/keyreset.h - platform data structure for resetkeys driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYRESET_H
+#define _LINUX_KEYRESET_H
+
+#define KEYRESET_NAME "keyreset"
+
+struct keyreset_platform_data {
+ int (*reset_fn)(void);
+ int key_down_delay;
+ int *keys_up;
+ int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYRESET_H */
diff --git a/include/linux/kref.h b/include/linux/kref.h
index e2df6d3..7c88d86 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -24,6 +24,8 @@ struct kref {
atomic_t refcount;
};
+#define KREF_INIT(n) { .refcount = ATOMIC_INIT(n), }
+
/**
* kref_init - initialize object.
* @kref: object in question.
diff --git a/include/linux/list.h b/include/linux/list.h
index 6f93501..3ef3ade 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -28,27 +28,42 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
list->prev = list;
}
+#ifdef CONFIG_DEBUG_LIST
+extern bool __list_add_valid(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next);
+extern bool __list_del_entry_valid(struct list_head *entry);
+#else
+static inline bool __list_add_valid(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ return true;
+}
+static inline bool __list_del_entry_valid(struct list_head *entry)
+{
+ return true;
+}
+#endif
+
/*
* Insert a new entry between two known consecutive entries.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_add(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
+ if (!__list_add_valid(new, prev, next))
+ return;
+
next->prev = new;
new->next = next;
new->prev = prev;
WRITE_ONCE(prev->next, new);
}
-#else
-extern void __list_add(struct list_head *new,
- struct list_head *prev,
- struct list_head *next);
-#endif
/**
* list_add - add a new entry
@@ -96,22 +111,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next)
* Note: list_empty() on entry does not return true after this, the entry is
* in an undefined state.
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_del_entry(struct list_head *entry)
{
+ if (!__list_del_entry_valid(entry))
+ return;
+
__list_del(entry->prev, entry->next);
}
static inline void list_del(struct list_head *entry)
{
- __list_del(entry->prev, entry->next);
+ __list_del_entry(entry);
entry->next = LIST_POISON1;
entry->prev = LIST_POISON2;
}
-#else
-extern void __list_del_entry(struct list_head *entry);
-extern void list_del(struct list_head *entry);
-#endif
/**
* list_replace - replace old entry by new one
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 558adfa..121f2f2 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1328,7 +1328,40 @@
* @inode we wish to get the security context of.
* @ctx is a pointer in which to place the allocated security context.
* @ctxlen points to the place to put the length of @ctx.
- * This is the main security structure.
+ *
+ * Security hooks for using the eBPF maps and programs functionalities through
+ * eBPF syscalls.
+ *
+ * @bpf:
+ * Do a initial check for all bpf syscalls after the attribute is copied
+ * into the kernel. The actual security module can implement their own
+ * rules to check the specific cmd they need.
+ *
+ * @bpf_map:
+ * Do a check when the kernel generate and return a file descriptor for
+ * eBPF maps.
+ *
+ * @map: bpf map that we want to access
+ * @mask: the access flags
+ *
+ * @bpf_prog:
+ * Do a check when the kernel generate and return a file descriptor for
+ * eBPF programs.
+ *
+ * @prog: bpf prog that userspace want to use.
+ *
+ * @bpf_map_alloc_security:
+ * Initialize the security field inside bpf map.
+ *
+ * @bpf_map_free_security:
+ * Clean up the security information stored inside bpf map.
+ *
+ * @bpf_prog_alloc_security:
+ * Initialize the security field inside bpf program.
+ *
+ * @bpf_prog_free_security:
+ * Clean up the security information stored inside bpf prog.
+ *
*/
union security_list_options {
@@ -1652,6 +1685,17 @@ union security_list_options {
struct audit_context *actx);
void (*audit_rule_free)(void *lsmrule);
#endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+ int (*bpf)(int cmd, union bpf_attr *attr,
+ unsigned int size);
+ int (*bpf_map)(struct bpf_map *map, fmode_t fmode);
+ int (*bpf_prog)(struct bpf_prog *prog);
+ int (*bpf_map_alloc_security)(struct bpf_map *map);
+ void (*bpf_map_free_security)(struct bpf_map *map);
+ int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux);
+ void (*bpf_prog_free_security)(struct bpf_prog_aux *aux);
+#endif /* CONFIG_BPF_SYSCALL */
};
struct security_hook_heads {
@@ -1866,6 +1910,15 @@ struct security_hook_heads {
struct list_head audit_rule_match;
struct list_head audit_rule_free;
#endif /* CONFIG_AUDIT */
+#ifdef CONFIG_BPF_SYSCALL
+ struct list_head bpf;
+ struct list_head bpf_map;
+ struct list_head bpf_prog;
+ struct list_head bpf_map_alloc_security;
+ struct list_head bpf_map_free_security;
+ struct list_head bpf_prog_alloc_security;
+ struct list_head bpf_prog_free_security;
+#endif /* CONFIG_BPF_SYSCALL */
};
/*
diff --git a/include/linux/memory-state-time.h b/include/linux/memory-state-time.h
new file mode 100644
index 0000000..d2212b0
--- /dev/null
+++ b/include/linux/memory-state-time.h
@@ -0,0 +1,42 @@
+/* include/linux/memory-state-time.h
+ *
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/workqueue.h>
+
+#define UPDATE_MEMORY_STATE(BLOCK, VALUE) BLOCK->update_call(BLOCK, VALUE)
+
+struct memory_state_update_block;
+
+typedef void (*memory_state_update_fn_t)(struct memory_state_update_block *ub,
+ int value);
+
+/* This struct is populated when you pass it to a memory_state_register*
+ * function. The update_call function is used for an update and defined in the
+ * typedef memory_state_update_fn_t
+ */
+struct memory_state_update_block {
+ memory_state_update_fn_t update_call;
+ int id;
+};
+
+/* Register a frequency struct memory_state_update_block to provide updates to
+ * memory_state_time about frequency changes using its update_call function.
+ */
+struct memory_state_update_block *memory_state_register_frequency_source(void);
+
+/* Register a bandwidth struct memory_state_update_block to provide updates to
+ * memory_state_time about bandwidth changes using its update_call function.
+ */
+struct memory_state_update_block *memory_state_register_bandwidth_source(void);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7a4c035..6fe5214d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1162,6 +1162,7 @@ extern void pagefault_out_of_memory(void);
extern void show_free_areas(unsigned int flags);
extern bool skip_free_areas_node(unsigned int flags, int nid);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file);
int shmem_zero_setup(struct vm_area_struct *);
#ifdef CONFIG_SHMEM
bool shmem_mapping(struct address_space *mapping);
@@ -1803,6 +1804,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
return ptl;
}
+extern void __init pagecache_init(void);
+
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
@@ -2009,7 +2012,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start,
extern struct vm_area_struct *vma_merge(struct mm_struct *,
struct vm_area_struct *prev, unsigned long addr, unsigned long end,
unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
- struct mempolicy *, struct vm_userfaultfd_ctx);
+ struct mempolicy *, struct vm_userfaultfd_ctx, const char __user *);
extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
extern int split_vma(struct mm_struct *,
struct vm_area_struct *, unsigned long addr, int new_below);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 21b18b7..40cb898 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -331,11 +331,18 @@ struct vm_area_struct {
/*
* For areas with an address space and backing store,
* linkage into the address_space->i_mmap interval tree.
+ *
+ * For private anonymous mappings, a pointer to a null terminated string
+ * in the user process containing the name given to the vma, or NULL
+ * if unnamed.
*/
- struct {
- struct rb_node rb;
- unsigned long rb_subtree_last;
- } shared;
+ union {
+ struct {
+ struct rb_node rb;
+ unsigned long rb_subtree_last;
+ } shared;
+ const char __user *anon_name;
+ };
/*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
@@ -625,4 +632,13 @@ typedef struct {
unsigned long val;
} swp_entry_t;
+/* Return the name for an anonymous mapping or NULL for a file-backed mapping */
+static inline const char __user *vma_get_anon_name(struct vm_area_struct *vma)
+{
+ if (vma->vm_file)
+ return NULL;
+
+ return vma->anon_name;
+}
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 73fad83..510a73a 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -119,6 +119,9 @@ struct mmc_ext_csd {
u8 raw_pwr_cl_ddr_200_360; /* 253 */
u8 raw_bkops_status; /* 246 */
u8 raw_sectors[4]; /* 212 - 4 bytes */
+ u8 pre_eol_info; /* 267 */
+ u8 device_life_time_est_typ_a; /* 268 */
+ u8 device_life_time_est_typ_b; /* 269 */
unsigned int feature_support;
#define MMC_DISCARD_FEATURE BIT(0) /* CMD38 feature */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 2b953eb..46a4b79 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -142,6 +142,10 @@ struct mmc_request {
/* Allow other commands during this ongoing data transfer or busy wait */
bool cap_cmd_during_tfr;
+ ktime_t io_start;
+#ifdef CONFIG_BLOCK
+ int lat_hist_enabled;
+#endif
};
struct mmc_card;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 0b24394..1808b78 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -16,6 +16,7 @@
#include <linux/sched.h>
#include <linux/device.h>
#include <linux/fault-inject.h>
+#include <linux/blkdev.h>
#include <linux/mmc/core.h>
#include <linux/mmc/card.h>
@@ -397,6 +398,21 @@ struct mmc_host {
int dsr_req; /* DSR value is valid */
u32 dsr; /* optional driver stage (DSR) value */
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ struct {
+ struct sdio_cis *cis;
+ struct sdio_cccr *cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+ } embedded_sdio_data;
+#endif
+
+#ifdef CONFIG_BLOCK
+ int latency_hist_enabled;
+ struct io_latency_state io_lat_read;
+ struct io_latency_state io_lat_write;
+#endif
+
unsigned long private[0] ____cacheline_aligned;
};
@@ -406,6 +422,14 @@ void mmc_remove_host(struct mmc_host *);
void mmc_free_host(struct mmc_host *);
int mmc_of_parse(struct mmc_host *host);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+extern void mmc_set_embedded_sdio_data(struct mmc_host *host,
+ struct sdio_cis *cis,
+ struct sdio_cccr *cccr,
+ struct sdio_embedded_func *funcs,
+ int num_funcs);
+#endif
+
static inline void *mmc_priv(struct mmc_host *host)
{
return (void *)host->private;
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index c376209..a034d07 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -331,6 +331,9 @@ struct _mmc_csd {
#define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */
#define EXT_CSD_PWR_CL_DDR_200_360 253 /* RO */
#define EXT_CSD_FIRMWARE_VERSION 254 /* RO, 8 bytes */
+#define EXT_CSD_PRE_EOL_INFO 267 /* RO */
+#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A 268 /* RO */
+#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B 269 /* RO */
#define EXT_CSD_SUPPORTED_MODE 493 /* RO */
#define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */
#define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */
diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h
index 4a13920..6e2d6a1 100644
--- a/include/linux/mmc/pm.h
+++ b/include/linux/mmc/pm.h
@@ -26,5 +26,6 @@ typedef unsigned int mmc_pm_flag_t;
#define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */
#define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */
+#define MMC_PM_IGNORE_PM_NOTIFY (1 << 2) /* ignore mmc pm notify */
#endif /* LINUX_MMC_PM_H */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 97ca105..f563bcf 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -23,6 +23,14 @@ struct sdio_func;
typedef void (sdio_irq_handler_t)(struct sdio_func *);
/*
+ * Structure used to hold embedded SDIO device data from platform layer
+ */
+struct sdio_embedded_func {
+ uint8_t f_class;
+ uint32_t f_maxblksize;
+};
+
+/*
* SDIO function CIS tuple (unknown to the core)
*/
struct sdio_func_tuple {
@@ -128,6 +136,8 @@ extern int sdio_release_irq(struct sdio_func *func);
extern unsigned int sdio_align_size(struct sdio_func *func, unsigned int sz);
extern u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret);
+extern u8 sdio_readb_ext(struct sdio_func *func, unsigned int addr, int *err_ret,
+ unsigned in);
extern u16 sdio_readw(struct sdio_func *func, unsigned int addr, int *err_ret);
extern u32 sdio_readl(struct sdio_func *func, unsigned int addr, int *err_ret);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5c7645e..a78cb6b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -153,6 +153,7 @@ enum node_stat_item {
NR_PAGES_SCANNED, /* pages scanned since last reclaim */
WORKINGSET_REFAULT,
WORKINGSET_ACTIVATE,
+ WORKINGSET_RESTORE,
WORKINGSET_NODERECLAIM,
NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
diff --git a/include/linux/module.h b/include/linux/module.h
index 99f330ae..49f0aae 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -20,6 +20,7 @@
#include <linux/export.h>
#include <linux/extable.h> /* only as arch move module.h -> extable.h */
#include <linux/rbtree_latch.h>
+#include <linux/cfi.h>
#include <linux/percpu.h>
#include <asm/module.h>
@@ -349,6 +350,10 @@ struct module {
const unsigned long *crcs;
unsigned int num_syms;
+#ifdef CONFIG_CFI_CLANG
+ cfi_check_fn cfi_check;
+#endif
+
/* Kernel parameters. */
#ifdef CONFIG_SYSFS
struct mutex param_lock;
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 52666d9..060db5c 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -225,19 +225,11 @@ struct kparam_array
VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
/* Obsolete - use module_param_cb() */
-#define module_param_call(name, set, get, arg, perm) \
- static const struct kernel_param_ops __param_ops_##name = \
- { .flags = 0, (void *)set, (void *)get }; \
+#define module_param_call(name, _set, _get, arg, perm) \
+ static const struct kernel_param_ops __param_ops_##name = \
+ { .flags = 0, .set = _set, .get = _get }; \
__module_param_call(MODULE_PARAM_PREFIX, \
- name, &__param_ops_##name, arg, \
- (perm) + sizeof(__check_old_set_param(set))*0, -1, 0)
-
-/* We don't get oldget: it's often a new-style param_get_uint, etc. */
-static inline int
-__check_old_set_param(int (*oldset)(const char *, struct kernel_param *))
-{
- return 0;
-}
+ name, &__param_ops_##name, arg, perm, -1, 0)
#ifdef CONFIG_SYSFS
extern void kernel_param_lock(struct module *mod);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index e0f3a82..5615a9e 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -67,6 +67,7 @@ struct vfsmount {
struct dentry *mnt_root; /* root of the mounted tree */
struct super_block *mnt_sb; /* pointer to superblock */
int mnt_flags;
+ void *data;
};
struct file; /* forward dec */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index f29abda..cf437f5 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -78,8 +78,11 @@ extern struct dentry *user_path_create(int, const char __user *, struct path *,
extern void done_path_create(struct path *, struct dentry *);
extern struct dentry *kern_path_locked(const char *, struct path *);
extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int);
+extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
+ const char *, unsigned int, struct path *);
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
+extern struct dentry *lookup_one_len2(const char *, struct vfsmount *mnt, struct dentry *, int);
extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
extern int follow_down_one(struct path *);
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 69111fa..ee62bca 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -139,6 +139,7 @@ struct xt_match {
const char *table;
unsigned int matchsize;
+ unsigned int usersize;
#ifdef CONFIG_COMPAT
unsigned int compatsize;
#endif
@@ -179,6 +180,7 @@ struct xt_target {
const char *table;
unsigned int targetsize;
+ unsigned int usersize;
#ifdef CONFIG_COMPAT
unsigned int compatsize;
#endif
@@ -261,6 +263,13 @@ int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
bool inv_proto);
+int xt_match_to_user(const struct xt_entry_match *m,
+ struct xt_entry_match __user *u);
+int xt_target_to_user(const struct xt_entry_target *t,
+ struct xt_entry_target __user *u);
+int xt_data_to_user(void __user *dst, const void *src,
+ int usersize, int size);
+
void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
struct xt_counters_info *info, bool compat);
diff --git a/include/linux/netfilter/xt_quota2.h b/include/linux/netfilter/xt_quota2.h
new file mode 100644
index 0000000..eadc69033
--- /dev/null
+++ b/include/linux/netfilter/xt_quota2.h
@@ -0,0 +1,25 @@
+#ifndef _XT_QUOTA_H
+#define _XT_QUOTA_H
+
+enum xt_quota_flags {
+ XT_QUOTA_INVERT = 1 << 0,
+ XT_QUOTA_GROW = 1 << 1,
+ XT_QUOTA_PACKET = 1 << 2,
+ XT_QUOTA_NO_CHANGE = 1 << 3,
+ XT_QUOTA_MASK = 0x0F,
+};
+
+struct xt_quota_counter;
+
+struct xt_quota_mtinfo2 {
+ char name[15];
+ u_int8_t flags;
+
+ /* Comparison-invariant */
+ aligned_u64 quota;
+
+ /* Used internally by the kernel */
+ struct xt_quota_counter *master __attribute__((aligned(8)));
+};
+
+#endif /* _XT_QUOTA_H */
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 4341f32..501d461 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -63,6 +63,27 @@ extern int of_flat_dt_match(unsigned long node, const char *const *matches);
extern unsigned long of_get_flat_dt_root(void);
extern int of_get_flat_dt_size(void);
+/*
+ * early_init_dt_scan_chosen - scan the device tree for ramdisk and bootargs
+ *
+ * The boot arguments will be placed into the memory pointed to by @data.
+ * That memory should be COMMAND_LINE_SIZE big and initialized to be a valid
+ * (possibly empty) string. Logic for what will be in @data after this
+ * function finishes:
+ *
+ * - CONFIG_CMDLINE_FORCE=true
+ * CONFIG_CMDLINE
+ * - CONFIG_CMDLINE_EXTEND=true, @data is non-empty string
+ * @data + dt bootargs (even if dt bootargs are empty)
+ * - CONFIG_CMDLINE_EXTEND=true, @data is empty string
+ * CONFIG_CMDLINE + dt bootargs (even if dt bootargs are empty)
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=non-empty:
+ * dt bootargs
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is non-empty string
+ * @data is left unchanged
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is empty string
+ * CONFIG_CMDLINE (or "" if that's not defined)
+ */
extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data);
extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 38a47cc..24d76bb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -203,6 +203,22 @@
#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n) \
+ __ab_c_size(n, \
+ sizeof(*(p)->member) + __must_be_array((p)->member),\
+ sizeof(*(p)))
+
/** check_shl_overflow() - Calculate a left-shifted value and check overflow
*
* @a: Value to be shifted
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 896e419..9c3c8aa 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -73,12 +73,14 @@
*/
enum pageflags {
PG_locked, /* Page is locked. Don't touch. */
- PG_error,
+ PG_waiters, /* Page has waiters, check its waitqueue */
PG_referenced,
PG_uptodate,
PG_dirty,
PG_lru,
PG_active,
+ PG_workingset,
+ PG_error,
PG_slab,
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
PG_arch_1,
@@ -167,6 +169,9 @@ static __always_inline int PageCompound(struct page *page)
* for compound page all operations related to the page flag applied to
* head page.
*
+ * PF_ONLY_HEAD:
+ * for compound page, callers only ever operate on the head page.
+ *
* PF_NO_TAIL:
* modifications of the page flag must be done on small or head pages,
* checks can be done on tail pages too.
@@ -176,6 +181,9 @@ static __always_inline int PageCompound(struct page *page)
*/
#define PF_ANY(page, enforce) page
#define PF_HEAD(page, enforce) compound_head(page)
+#define PF_ONLY_HEAD(page, enforce) ({ \
+ VM_BUG_ON_PGFLAGS(PageTail(page), page); \
+ page;})
#define PF_NO_TAIL(page, enforce) ({ \
VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \
compound_head(page);})
@@ -253,6 +261,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
__PAGEFLAG(Locked, locked, PF_NO_TAIL)
+PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
PAGEFLAG(Referenced, referenced, PF_HEAD)
TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
@@ -262,6 +271,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
TESTCLEARFLAG(Active, active, PF_HEAD)
+PAGEFLAG(Workingset, workingset, PF_HEAD)
+ TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
__PAGEFLAG(Slab, slab, PF_NO_TAIL)
__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
@@ -751,6 +762,7 @@ static inline int page_has_private(struct page *page)
#undef PF_ANY
#undef PF_HEAD
+#undef PF_ONLY_HEAD
#undef PF_NO_TAIL
#undef PF_NO_COMPOUND
#endif /* !__GENERATING_BOUNDS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 35f4c4d..dfa6182 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -225,7 +225,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x)
__GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
}
-typedef int filler_t(void *, struct page *);
+typedef int filler_t(struct file *, struct page *);
pgoff_t page_cache_next_hole(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
@@ -238,6 +238,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
#define FGP_WRITE 0x00000008
#define FGP_NOFS 0x00000010
#define FGP_NOWAIT 0x00000020
+#define FGP_FOR_MMAP 0x00000040
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
int fgp_flags, gfp_t cache_gfp_mask);
@@ -341,8 +342,16 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages);
-unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
- int tag, unsigned int nr_pages, struct page **pages);
+unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
+ pgoff_t end, int tag, unsigned int nr_pages,
+ struct page **pages);
+static inline unsigned find_get_pages_tag(struct address_space *mapping,
+ pgoff_t *index, int tag, unsigned int nr_pages,
+ struct page **pages)
+{
+ return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag,
+ nr_pages, pages);
+}
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
int tag, unsigned int nr_entries,
struct page **entries, pgoff_t *indices);
@@ -369,7 +378,7 @@ extern int read_cache_pages(struct address_space *mapping,
static inline struct page *read_mapping_page(struct address_space *mapping,
pgoff_t index, void *data)
{
- filler_t *filler = (filler_t *)mapping->a_ops->readpage;
+ filler_t *filler = mapping->a_ops->readpage;
return read_cache_page(mapping, index, filler, data);
}
@@ -486,22 +495,14 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
* and for filesystems which need to wait on PG_private.
*/
extern void wait_on_page_bit(struct page *page, int bit_nr);
-
extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
-extern int wait_on_page_bit_killable_timeout(struct page *page,
- int bit_nr, unsigned long timeout);
+extern void wake_up_page_bit(struct page *page, int bit_nr);
-static inline int wait_on_page_locked_killable(struct page *page)
-{
- if (!PageLocked(page))
- return 0;
- return wait_on_page_bit_killable(compound_head(page), PG_locked);
-}
-
-extern wait_queue_head_t *page_waitqueue(struct page *page);
static inline void wake_up_page(struct page *page, int bit)
{
- __wake_up_bit(page_waitqueue(page), &page->flags, bit);
+ if (!PageWaiters(page))
+ return;
+ wake_up_page_bit(page, bit);
}
/*
@@ -517,6 +518,13 @@ static inline void wait_on_page_locked(struct page *page)
wait_on_page_bit(compound_head(page), PG_locked);
}
+static inline int wait_on_page_locked_killable(struct page *page)
+{
+ if (!PageLocked(page))
+ return 0;
+ return wait_on_page_bit_killable(compound_head(page), PG_locked);
+}
+
/*
* Wait for a page to complete writeback
*/
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index b45d391..cead441 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -29,9 +29,17 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec,
void pagevec_remove_exceptionals(struct pagevec *pvec);
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
pgoff_t start, unsigned nr_pages);
-unsigned pagevec_lookup_tag(struct pagevec *pvec,
- struct address_space *mapping, pgoff_t *index, int tag,
- unsigned nr_pages);
+unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
+ struct address_space *mapping, pgoff_t *index, pgoff_t end,
+ int tag);
+unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
+ struct address_space *mapping, pgoff_t *index, pgoff_t end,
+ int tag, unsigned max_pages);
+static inline unsigned pagevec_lookup_tag(struct pagevec *pvec,
+ struct address_space *mapping, pgoff_t *index, int tag)
+{
+ return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag);
+}
static inline void pagevec_init(struct pagevec *pvec, int cold)
{
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a7057b7..3f0055f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1173,6 +1173,11 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
int perf_event_max_stack_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+static inline bool perf_paranoid_any(void)
+{
+ return sysctl_perf_event_paranoid > 2;
+}
+
static inline bool perf_paranoid_tracepoint_raw(void)
{
return sysctl_perf_event_paranoid > -1;
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 97b745d..1d847d3 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -2,6 +2,7 @@
#define _LINUX_PID_H
#include <linux/rcupdate.h>
+#include <linux/wait.h>
enum pid_type
{
@@ -62,6 +63,8 @@ struct pid
unsigned int level;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
+ /* wait queue for pidfd notifications */
+ wait_queue_head_t wait_pidfd;
struct rcu_head rcu;
struct upid numbers[1];
};
@@ -74,6 +77,8 @@ struct pid_link
struct pid *pid;
};
+extern const struct file_operations pidfd_fops;
+
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
diff --git a/include/linux/platform_data/ds2482.h b/include/linux/platform_data/ds2482.h
new file mode 100644
index 0000000..5a6879e2a
--- /dev/null
+++ b/include/linux/platform_data/ds2482.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __PLATFORM_DATA_DS2482__
+#define __PLATFORM_DATA_DS2482__
+
+struct ds2482_platform_data {
+ int slpz_gpio;
+};
+
+#endif /* __PLATFORM_DATA_DS2482__ */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index ad97baf..29fc01a 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -18,6 +18,7 @@
#include <linux/leds.h>
#include <linux/spinlock.h>
#include <linux/notifier.h>
+#include <linux/types.h>
/*
* All voltages, currents, charges, energies, time and temperatures in uV,
@@ -148,6 +149,12 @@ enum power_supply_property {
POWER_SUPPLY_PROP_SCOPE,
POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT,
POWER_SUPPLY_PROP_CALIBRATE,
+ /* Local extensions */
+ POWER_SUPPLY_PROP_USB_HC,
+ POWER_SUPPLY_PROP_USB_OTG,
+ POWER_SUPPLY_PROP_CHARGE_ENABLED,
+ /* Local extensions of type int64_t */
+ POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT,
/* Properties of type `const char *' */
POWER_SUPPLY_PROP_MODEL_NAME,
POWER_SUPPLY_PROP_MANUFACTURER,
@@ -175,6 +182,7 @@ enum power_supply_notifier_events {
union power_supply_propval {
int intval;
const char *strval;
+ int64_t int64val;
};
struct device_node;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index b97bf2e..de3f442 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -41,6 +41,7 @@ extern void *proc_get_parent_data(const struct inode *);
extern void proc_remove(struct proc_dir_entry *);
extern void remove_proc_entry(const char *, struct proc_dir_entry *);
extern int remove_proc_subtree(const char *, struct proc_dir_entry *);
+extern struct pid *tgid_pidfd_to_pid(const struct file *file);
#else /* CONFIG_PROC_FS */
@@ -72,8 +73,19 @@ static inline void proc_remove(struct proc_dir_entry *de) {}
#define remove_proc_entry(name, parent) do {} while (0)
static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; }
+static inline struct pid *tgid_pidfd_to_pid(const struct file *file)
+{
+ return ERR_PTR(-EBADF);
+}
+
#endif /* CONFIG_PROC_FS */
+#ifdef CONFIG_PROC_UID
+extern void proc_register_uid(kuid_t uid);
+#else
+static inline void proc_register_uid(kuid_t uid) {}
+#endif
+
struct net;
static inline struct proc_dir_entry *proc_net_mkdir(
diff --git a/include/linux/psi.h b/include/linux/psi.h
new file mode 100644
index 0000000..b825fa5
--- /dev/null
+++ b/include/linux/psi.h
@@ -0,0 +1,63 @@
+#ifndef _LINUX_PSI_H
+#define _LINUX_PSI_H
+
+#include <linux/jump_label.h>
+#include <linux/psi_types.h>
+#include <linux/sched.h>
+#include <linux/poll.h>
+#include <linux/cgroup-defs.h>
+
+struct seq_file;
+struct css_set;
+
+#ifdef CONFIG_PSI
+
+extern struct static_key_false psi_disabled;
+
+void psi_init(void);
+
+void psi_task_change(struct task_struct *task, int clear, int set);
+
+void psi_memstall_tick(struct task_struct *task, int cpu);
+void psi_memstall_enter(unsigned long *flags);
+void psi_memstall_leave(unsigned long *flags);
+
+int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgrp);
+void psi_cgroup_free(struct cgroup *cgrp);
+void cgroup_move_task(struct task_struct *p, struct css_set *to);
+
+struct psi_trigger *psi_trigger_create(struct psi_group *group,
+ char *buf, size_t nbytes, enum psi_res res);
+void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);
+
+unsigned int psi_trigger_poll(void **trigger_ptr, struct file *file,
+ poll_table *wait);
+#endif
+
+#else /* CONFIG_PSI */
+
+static inline void psi_init(void) {}
+
+static inline void psi_memstall_enter(unsigned long *flags) {}
+static inline void psi_memstall_leave(unsigned long *flags) {}
+
+#ifdef CONFIG_CGROUPS
+static inline int psi_cgroup_alloc(struct cgroup *cgrp)
+{
+ return 0;
+}
+static inline void psi_cgroup_free(struct cgroup *cgrp)
+{
+}
+static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
+{
+ rcu_assign_pointer(p->cgroups, to);
+}
+#endif
+
+#endif /* CONFIG_PSI */
+
+#endif /* _LINUX_PSI_H */
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
new file mode 100644
index 0000000..07aaf9b
--- /dev/null
+++ b/include/linux/psi_types.h
@@ -0,0 +1,173 @@
+#ifndef _LINUX_PSI_TYPES_H
+#define _LINUX_PSI_TYPES_H
+
+#include <linux/kthread.h>
+#include <linux/seqlock.h>
+#include <linux/types.h>
+#include <linux/kref.h>
+#include <linux/wait.h>
+
+#ifdef CONFIG_PSI
+
+/* Tracked task states */
+enum psi_task_count {
+ NR_IOWAIT,
+ NR_MEMSTALL,
+ NR_RUNNING,
+ NR_PSI_TASK_COUNTS = 3,
+};
+
+/* Task state bitmasks */
+#define TSK_IOWAIT (1 << NR_IOWAIT)
+#define TSK_MEMSTALL (1 << NR_MEMSTALL)
+#define TSK_RUNNING (1 << NR_RUNNING)
+
+/* Resources that workloads could be stalled on */
+enum psi_res {
+ PSI_IO,
+ PSI_MEM,
+ PSI_CPU,
+ NR_PSI_RESOURCES = 3,
+};
+
+/*
+ * Pressure states for each resource:
+ *
+ * SOME: Stalled tasks & working tasks
+ * FULL: Stalled tasks & no working tasks
+ */
+enum psi_states {
+ PSI_IO_SOME,
+ PSI_IO_FULL,
+ PSI_MEM_SOME,
+ PSI_MEM_FULL,
+ PSI_CPU_SOME,
+ /* Only per-CPU, to weigh the CPU in the global average: */
+ PSI_NONIDLE,
+ NR_PSI_STATES = 6,
+};
+
+enum psi_aggregators {
+ PSI_AVGS = 0,
+ PSI_POLL,
+ NR_PSI_AGGREGATORS,
+};
+
+struct psi_group_cpu {
+ /* 1st cacheline updated by the scheduler */
+
+ /* Aggregator needs to know of concurrent changes */
+ seqcount_t seq ____cacheline_aligned_in_smp;
+
+ /* States of the tasks belonging to this group */
+ unsigned int tasks[NR_PSI_TASK_COUNTS];
+
+ /* Aggregate pressure state derived from the tasks */
+ u32 state_mask;
+
+ /* Period time sampling buckets for each state of interest (ns) */
+ u32 times[NR_PSI_STATES];
+
+ /* Time of last task change in this group (rq_clock) */
+ u64 state_start;
+
+ /* 2nd cacheline updated by the aggregator */
+
+ /* Delta detection against the sampling buckets */
+ u32 times_prev[NR_PSI_AGGREGATORS][NR_PSI_STATES]
+ ____cacheline_aligned_in_smp;
+};
+
+/* PSI growth tracking window */
+struct psi_window {
+ /* Window size in ns */
+ u64 size;
+
+ /* Start time of the current window in ns */
+ u64 start_time;
+
+ /* Value at the start of the window */
+ u64 start_value;
+
+ /* Value growth in the previous window */
+ u64 prev_growth;
+};
+
+struct psi_trigger {
+ /* PSI state being monitored by the trigger */
+ enum psi_states state;
+
+ /* User-spacified threshold in ns */
+ u64 threshold;
+
+ /* List node inside triggers list */
+ struct list_head node;
+
+ /* Backpointer needed during trigger destruction */
+ struct psi_group *group;
+
+ /* Wait queue for polling */
+ wait_queue_head_t event_wait;
+
+ /* Pending event flag */
+ int event;
+
+ /* Tracking window */
+ struct psi_window win;
+
+ /*
+ * Time last event was generated. Used for rate-limiting
+ * events to one per window
+ */
+ u64 last_event_time;
+
+ /* Refcounting to prevent premature destruction */
+ struct kref refcount;
+};
+
+struct psi_group {
+ /* Protects data used by the aggregator */
+ struct mutex avgs_lock;
+
+ /* Per-cpu task state & time tracking */
+ struct psi_group_cpu __percpu *pcpu;
+
+ /* Running pressure averages */
+ u64 avg_total[NR_PSI_STATES - 1];
+ u64 avg_last_update;
+ u64 avg_next_update;
+
+ /* Aggregator work control */
+ struct delayed_work avgs_work;
+
+ /* Total stall times and sampled pressure averages */
+ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1];
+ unsigned long avg[NR_PSI_STATES - 1][3];
+
+ /* Monitor work control */
+ atomic_t poll_scheduled;
+ struct kthread_worker __rcu *poll_kworker;
+ struct kthread_delayed_work poll_work;
+
+ /* Protects data used by the monitor */
+ struct mutex trigger_lock;
+
+ /* Configured polling triggers */
+ struct list_head triggers;
+ u32 nr_triggers[NR_PSI_STATES - 1];
+ u32 poll_states;
+ u64 poll_min_period;
+
+ /* Total stall times at the start of monitor activation */
+ u64 polling_total[NR_PSI_STATES - 1];
+ u64 polling_next_update;
+ u64 polling_until;
+};
+
+#else /* CONFIG_PSI */
+
+struct psi_group { };
+
+#endif /* CONFIG_PSI */
+
+#endif /* _LINUX_PSI_TYPES_H */
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 4058bf9..cb5edd6 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -80,6 +80,8 @@ void persistent_ram_free_old(struct persistent_ram_zone *prz);
ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
char *str, size_t len);
+void ramoops_console_write_buf(const char *buf, size_t size);
+
/*
* Ramoops platform data
* @mem_size memory size for ramoops
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 8beb98d..4f7a956 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -45,19 +45,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_add_rcu(struct list_head *new,
struct list_head *prev, struct list_head *next)
{
+ if (!__list_add_valid(new, prev, next))
+ return;
+
new->next = next;
new->prev = prev;
rcu_assign_pointer(list_next_rcu(prev), new);
next->prev = new;
}
-#else
-void __list_add_rcu(struct list_head *new,
- struct list_head *prev, struct list_head *next);
-#endif
/**
* list_add_rcu - add a new entry to rcu-protected list
diff --git a/include/linux/reservation.h b/include/linux/reservation.h
index b0f305e..bad7710 100644
--- a/include/linux/reservation.h
+++ b/include/linux/reservation.h
@@ -177,17 +177,14 @@ static inline struct fence *
reservation_object_get_excl_rcu(struct reservation_object *obj)
{
struct fence *fence;
- unsigned seq;
-retry:
- seq = read_seqcount_begin(&obj->seq);
+
+ if (!rcu_access_pointer(obj->fence_excl))
+ return NULL;
+
rcu_read_lock();
- fence = rcu_dereference(obj->fence_excl);
- if (read_seqcount_retry(&obj->seq, seq)) {
- rcu_read_unlock();
- goto retry;
- }
- fence = fence_get(fence);
+ fence = fence_get_rcu_safe(&obj->fence_excl);
rcu_read_unlock();
+
return fence;
}
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
new file mode 100644
index 0000000..0d905d8
--- /dev/null
+++ b/include/linux/restart_block.h
@@ -0,0 +1,51 @@
+/*
+ * Common syscall restarting data
+ */
+#ifndef __LINUX_RESTART_BLOCK_H
+#define __LINUX_RESTART_BLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct timespec;
+struct compat_timespec;
+struct pollfd;
+
+/*
+ * System call restart block.
+ */
+struct restart_block {
+ long (*fn)(struct restart_block *);
+ union {
+ /* For futex_wait and futex_wait_requeue_pi */
+ struct {
+ u32 __user *uaddr;
+ u32 val;
+ u32 flags;
+ u32 bitset;
+ u64 time;
+ u32 __user *uaddr2;
+ } futex;
+ /* For nanosleep */
+ struct {
+ clockid_t clockid;
+ struct timespec __user *rmtp;
+#ifdef CONFIG_COMPAT
+ struct compat_timespec __user *compat_rmtp;
+#endif
+ u64 expires;
+ } nanosleep;
+ /* For poll */
+ struct {
+ struct pollfd __user *ufds;
+ int nfds;
+ int has_timeout;
+ unsigned long tv_sec;
+ unsigned long tv_nsec;
+ } poll;
+ };
+};
+
+extern long do_no_restart_syscall(struct restart_block *parm);
+
+#endif /* __LINUX_RESTART_BLOCK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f094882..a00eb51 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -58,7 +58,6 @@ struct sched_param {
#include <linux/uidgid.h>
#include <linux/gfp.h>
#include <linux/magic.h>
-#include <linux/cgroup-defs.h>
#include <asm/processor.h>
@@ -139,31 +138,6 @@ struct nameidata;
#define VMACACHE_SIZE (1U << VMACACHE_BITS)
#define VMACACHE_MASK (VMACACHE_SIZE - 1)
-/*
- * These are the constant used to fake the fixed-point load-average
- * counting. Some notes:
- * - 11 bit fractions expand to 22 bits by the multiplies: this gives
- * a load-average precision of 10 bits integer + 11 bits fractional
- * - if you want to count load-averages more often, you need more
- * precision, or rounding will get you. With 2-second counting freq,
- * the EXP_n values would be 1981, 2034 and 2043 if still using only
- * 11 bit fractions.
- */
-extern unsigned long avenrun[]; /* Load averages */
-extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
-
-#define FSHIFT 11 /* nr of bits of precision */
-#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
-#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */
-#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
-#define EXP_5 2014 /* 1/exp(5sec/5min) */
-#define EXP_15 2037 /* 1/exp(5sec/15min) */
-
-#define CALC_LOAD(load,exp,n) \
- load *= exp; \
- load += n*(FIXED_1-exp); \
- load >>= FSHIFT;
-
extern unsigned long total_forks;
extern int nr_threads;
DECLARE_PER_CPU(unsigned long, process_counts);
@@ -173,8 +147,9 @@ extern bool single_task_running(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
-
-extern void calc_global_load(unsigned long ticks);
+#ifdef CONFIG_CPU_QUIET
+extern u64 nr_running_integral(unsigned int cpu);
+#endif
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void cpu_load_update_nohz_start(void);
@@ -315,6 +290,15 @@ extern char ___assert_task_state[1 - 2*!!(
/* Task command name length */
#define TASK_COMM_LEN 16
+enum task_event {
+ PUT_PREV_TASK = 0,
+ PICK_NEXT_TASK = 1,
+ TASK_WAKE = 2,
+ TASK_MIGRATE = 3,
+ TASK_UPDATE = 4,
+ IRQ_UPDATE = 5,
+};
+
#include <linux/spinlock.h>
/*
@@ -910,39 +894,7 @@ struct sched_info {
};
#endif /* CONFIG_SCHED_INFO */
-#ifdef CONFIG_TASK_DELAY_ACCT
-struct task_delay_info {
- spinlock_t lock;
- unsigned int flags; /* Private per-task flags */
-
- /* For each stat XXX, add following, aligned appropriately
- *
- * struct timespec XXX_start, XXX_end;
- * u64 XXX_delay;
- * u32 XXX_count;
- *
- * Atomicity of updates to XXX_delay, XXX_count protected by
- * single lock above (split into XXX_lock if contention is an issue).
- */
-
- /*
- * XXX_count is incremented on every XXX operation, the delay
- * associated with the operation is added to XXX_delay.
- * XXX_delay contains the accumulated delay time in nanoseconds.
- */
- u64 blkio_start; /* Shared by blkio, swapin */
- u64 blkio_delay; /* wait for sync block io completion */
- u64 swapin_delay; /* wait for swapin block io completion */
- u32 blkio_count; /* total count of the number of sync block */
- /* io operations performed */
- u32 swapin_count; /* total count of the number of swapin block */
- /* io operations performed */
-
- u64 freepages_start;
- u64 freepages_delay; /* wait for memory reclaim */
- u32 freepages_count; /* total count of memory reclaim */
-};
-#endif /* CONFIG_TASK_DELAY_ACCT */
+struct task_delay_info;
static inline int sched_info_on(void)
{
@@ -983,6 +935,14 @@ enum cpu_idle_type {
#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
+struct sched_capacity_reqs {
+ unsigned long cfs;
+ unsigned long rt;
+ unsigned long dl;
+
+ unsigned long total;
+};
+
/*
* Wake-queues are lists of tasks with a pending wakeup, whose
* callers have already marked the task as woken internally,
@@ -1046,6 +1006,7 @@ extern void wake_up_q(struct wake_q_head *head);
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
#define SD_NUMA 0x4000 /* cross-node balancing */
+#define SD_SHARE_CAP_STATES 0x8000 /* Domain members share capacity state */
#ifdef CONFIG_SCHED_SMT
static inline int cpu_smt_flags(void)
@@ -1078,8 +1039,57 @@ struct sched_domain_attr {
extern int sched_domain_level_max;
+struct capacity_state {
+ unsigned long cap; /* compute capacity */
+ unsigned long power; /* power consumption at this compute capacity */
+};
+
+struct idle_state {
+ unsigned long power; /* power consumption in this idle state */
+};
+
+struct sched_group_energy {
+ unsigned int nr_idle_states; /* number of idle states */
+ struct idle_state *idle_states; /* ptr to idle state array */
+ unsigned int nr_cap_states; /* number of capacity states */
+ struct capacity_state *cap_states; /* ptr to capacity state array */
+};
+
+unsigned long capacity_curr_of(int cpu);
+
struct sched_group;
+struct eas_stats {
+ /* select_idle_sibling() stats */
+ u64 sis_attempts;
+ u64 sis_idle;
+ u64 sis_cache_affine;
+ u64 sis_suff_cap;
+ u64 sis_idle_cpu;
+ u64 sis_count;
+
+ /* select_energy_cpu_brute() stats */
+ u64 secb_attempts;
+ u64 secb_sync;
+ u64 secb_idle_bt;
+ u64 secb_insuff_cap;
+ u64 secb_no_nrg_sav;
+ u64 secb_nrg_sav;
+ u64 secb_count;
+
+ /* find_best_target() stats */
+ u64 fbt_attempts;
+ u64 fbt_no_cpu;
+ u64 fbt_no_sd;
+ u64 fbt_pref_idle;
+ u64 fbt_count;
+
+ /* cas */
+ /* select_task_rq_fair() stats */
+ u64 cas_attempts;
+ u64 cas_count;
+};
+
struct sched_domain_shared {
atomic_t ref;
atomic_t nr_busy_cpus;
@@ -1148,6 +1158,8 @@ struct sched_domain {
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
+
+ struct eas_stats eas_stats;
#endif
#ifdef CONFIG_SCHED_DEBUG
char *name;
@@ -1185,6 +1197,8 @@ bool cpus_share_cache(int this_cpu, int that_cpu);
typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
typedef int (*sched_domain_flags_f)(void);
+typedef
+const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu);
#define SDTL_OVERLAP 0x01
@@ -1198,6 +1212,7 @@ struct sd_data {
struct sched_domain_topology_level {
sched_domain_mask_f mask;
sched_domain_flags_f sd_flags;
+ sched_domain_energy_f energy;
int flags;
int numa_level;
struct sd_data data;
@@ -1343,6 +1358,70 @@ struct sched_statistics {
u64 nr_wakeups_affine_attempts;
u64 nr_wakeups_passive;
u64 nr_wakeups_idle;
+
+ /* select_idle_sibling() */
+ u64 nr_wakeups_sis_attempts;
+ u64 nr_wakeups_sis_idle;
+ u64 nr_wakeups_sis_cache_affine;
+ u64 nr_wakeups_sis_suff_cap;
+ u64 nr_wakeups_sis_idle_cpu;
+ u64 nr_wakeups_sis_count;
+
+ /* energy_aware_wake_cpu() */
+ u64 nr_wakeups_secb_attempts;
+ u64 nr_wakeups_secb_sync;
+ u64 nr_wakeups_secb_idle_bt;
+ u64 nr_wakeups_secb_insuff_cap;
+ u64 nr_wakeups_secb_no_nrg_sav;
+ u64 nr_wakeups_secb_nrg_sav;
+ u64 nr_wakeups_secb_count;
+
+ /* find_best_target() */
+ u64 nr_wakeups_fbt_attempts;
+ u64 nr_wakeups_fbt_no_cpu;
+ u64 nr_wakeups_fbt_no_sd;
+ u64 nr_wakeups_fbt_pref_idle;
+ u64 nr_wakeups_fbt_count;
+
+ /* cas */
+ /* select_task_rq_fair() */
+ u64 nr_wakeups_cas_attempts;
+ u64 nr_wakeups_cas_count;
+};
+#endif
+
+#ifdef CONFIG_SCHED_WALT
+#define RAVG_HIST_SIZE_MAX 5
+
+/* ravg represents frequency scaled cpu-demand of tasks */
+struct ravg {
+ /*
+ * 'mark_start' marks the beginning of an event (task waking up, task
+ * starting to execute, task being preempted) within a window
+ *
+ * 'sum' represents how runnable a task has been within current
+ * window. It incorporates both running time and wait time and is
+ * frequency scaled.
+ *
+ * 'sum_history' keeps track of history of 'sum' seen over previous
+ * RAVG_HIST_SIZE windows. Windows where task was entirely sleeping are
+ * ignored.
+ *
+ * 'demand' represents maximum sum seen over previous
+ * sysctl_sched_ravg_hist_size windows. 'demand' could drive frequency
+ * demand for tasks.
+ *
+ * 'curr_window' represents task's contribution to cpu busy time
+ * statistics (rq->curr_runnable_sum) in current window
+ *
+ * 'prev_window' represents task's contribution to cpu busy time
+ * statistics (rq->prev_runnable_sum) in previous window
+ */
+ u64 mark_start;
+ u32 sum, demand;
+ u32 sum_history[RAVG_HIST_SIZE_MAX];
+ u32 curr_window, prev_window;
+ u16 active_windows;
};
#endif
@@ -1517,6 +1596,16 @@ struct task_struct {
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
+#ifdef CONFIG_SCHED_WALT
+ struct ravg ravg;
+ /*
+ * 'init_load_pct' represents the initial task load assigned to children
+ * of this task
+ */
+ u32 init_load_pct;
+ u64 last_sleep_ts;
+#endif
+
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
@@ -1579,6 +1668,10 @@ struct task_struct {
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_remote_wakeup:1;
+#ifdef CONFIG_PSI
+ unsigned sched_psi_wake_requeue:1;
+#endif
+
unsigned :0; /* force alignment to the next boundary */
/* unserialized, strictly 'current' */
@@ -1645,6 +1738,10 @@ struct task_struct {
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
+#ifdef CONFIG_CPU_FREQ_TIMES
+ u64 *time_in_state;
+ unsigned int max_state;
+#endif
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqcount_t vtime_seqcount;
@@ -1791,6 +1888,10 @@ struct task_struct {
unsigned long ptrace_message;
siginfo_t *last_siginfo; /* For ptrace use. */
struct task_io_accounting ioac;
+#ifdef CONFIG_PSI
+ /* Pressure stall state */
+ unsigned int psi_flags;
+#endif
#if defined(CONFIG_TASK_XACCT)
u64 acct_rss_mem1; /* accumulated rss usage */
u64 acct_vm_mem1; /* accumulated virtual memory usage */
@@ -1886,9 +1987,10 @@ struct task_struct {
struct page_frag task_frag;
-#ifdef CONFIG_TASK_DELAY_ACCT
- struct task_delay_info *delays;
+#ifdef CONFIG_TASK_DELAY_ACCT
+ struct task_delay_info *delays;
#endif
+
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
@@ -2298,6 +2400,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
+#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
@@ -3152,11 +3255,7 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
* subsystems needing threadgroup stability can hook into for
* synchronization.
*/
-static inline void threadgroup_change_begin(struct task_struct *tsk)
-{
- might_sleep();
- cgroup_threadgroup_change_begin(tsk);
-}
+extern void threadgroup_change_begin(struct task_struct *tsk);
/**
* threadgroup_change_end - mark the end of changes to a threadgroup
@@ -3164,10 +3263,7 @@ static inline void threadgroup_change_begin(struct task_struct *tsk)
*
* See threadgroup_change_begin().
*/
-static inline void threadgroup_change_end(struct task_struct *tsk)
-{
- cgroup_threadgroup_change_end(tsk);
-}
+extern void threadgroup_change_end(struct task_struct *tsk);
#ifdef CONFIG_THREAD_INFO_IN_TASK
@@ -3584,6 +3680,11 @@ static inline void inc_syscw(struct task_struct *tsk)
{
tsk->ioac.syscw++;
}
+
+static inline void inc_syscfs(struct task_struct *tsk)
+{
+ tsk->ioac.syscfs++;
+}
#else
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
@@ -3600,6 +3701,9 @@ static inline void inc_syscr(struct task_struct *tsk)
static inline void inc_syscw(struct task_struct *tsk)
{
}
+static inline void inc_syscfs(struct task_struct *tsk)
+{
+}
#endif
#ifndef TASK_SIZE_OF
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
new file mode 100644
index 0000000..208bbf2
--- /dev/null
+++ b/include/linux/sched/loadavg.h
@@ -0,0 +1,47 @@
+#ifndef _LINUX_SCHED_LOADAVG_H
+#define _LINUX_SCHED_LOADAVG_H
+
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ * - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ * a load-average precision of 10 bits integer + 11 bits fractional
+ * - if you want to count load-averages more often, you need more
+ * precision, or rounding will get you. With 2-second counting freq,
+ * the EXP_n values would be 1981, 2034 and 2043 if still using only
+ * 11 bit fractions.
+ */
+extern unsigned long avenrun[]; /* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
+
+#define FSHIFT 11 /* nr of bits of precision */
+#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
+#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */
+#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5 2014 /* 1/exp(5sec/5min) */
+#define EXP_15 2037 /* 1/exp(5sec/15min) */
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
+static inline unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+ unsigned long newload;
+
+ newload = load * exp + active * (FIXED_1 - exp);
+ if (active >= load)
+ newload += FIXED_1-1;
+
+ return newload / FIXED_1;
+}
+
+extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n);
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+extern void calc_global_load(unsigned long ticks);
+
+#endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index debcd4b..7840673 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -18,6 +18,14 @@ extern unsigned int sysctl_sched_latency;
extern unsigned int sysctl_sched_min_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
+extern unsigned int sysctl_sched_sync_hint_enable;
+extern unsigned int sysctl_sched_cstate_aware;
+#ifdef CONFIG_SCHED_WALT
+extern unsigned int sysctl_sched_use_walt_cpu_util;
+extern unsigned int sysctl_sched_use_walt_task_util;
+extern unsigned int sysctl_sched_walt_init_task_load_pct;
+extern unsigned int sysctl_sched_walt_cpu_high_irqload;
+#endif
enum sched_tunable_scaling {
SCHED_TUNABLESCALING_NONE,
@@ -56,6 +64,22 @@ extern int sysctl_sched_rt_runtime;
extern unsigned int sysctl_sched_cfs_bandwidth_slice;
#endif
+#ifdef CONFIG_SCHED_TUNE
+extern unsigned int sysctl_sched_cfs_boost;
+int sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length,
+ loff_t *ppos);
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+ return sysctl_sched_cfs_boost;
+}
+#else
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+ return 0;
+}
+#endif
+
#ifdef CONFIG_SCHED_AUTOGROUP
extern unsigned int sysctl_sched_autogroup_enabled;
#endif
diff --git a/include/linux/sched_energy.h b/include/linux/sched_energy.h
new file mode 100644
index 0000000..1daf3e1
--- /dev/null
+++ b/include/linux/sched_energy.h
@@ -0,0 +1,44 @@
+#ifndef _LINUX_SCHED_ENERGY_H
+#define _LINUX_SCHED_ENERGY_H
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+/*
+ * There doesn't seem to be an NR_CPUS style max number of sched domain
+ * levels so here's an arbitrary constant one for the moment.
+ *
+ * The levels alluded to here correspond to entries in struct
+ * sched_domain_topology_level that are meant to be populated by arch
+ * specific code (topology.c).
+ */
+#define NR_SD_LEVELS 8
+
+#define SD_LEVEL0 0
+#define SD_LEVEL1 1
+#define SD_LEVEL2 2
+#define SD_LEVEL3 3
+#define SD_LEVEL4 4
+#define SD_LEVEL5 5
+#define SD_LEVEL6 6
+#define SD_LEVEL7 7
+
+/*
+ * Convenience macro for iterating through said sd levels.
+ */
+#define for_each_possible_sd_level(level) \
+ for (level = 0; level < NR_SD_LEVELS; level++)
+
+#ifdef CONFIG_SMP
+
+extern struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS];
+
+void init_sched_energy_costs(void);
+
+#else
+
+#define init_sched_energy_costs() do { } while (0)
+
+#endif /* CONFIG_SMP */
+
+#endif
diff --git a/include/linux/security.h b/include/linux/security.h
index c2125e9..3632428 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1662,6 +1662,54 @@ static inline void securityfs_remove(struct dentry *dentry)
#endif
+#ifdef CONFIG_BPF_SYSCALL
+union bpf_attr;
+struct bpf_map;
+struct bpf_prog;
+struct bpf_prog_aux;
+#ifdef CONFIG_SECURITY
+extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
+extern int security_bpf_prog(struct bpf_prog *prog);
+extern int security_bpf_map_alloc(struct bpf_map *map);
+extern void security_bpf_map_free(struct bpf_map *map);
+extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
+extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
+#else
+static inline int security_bpf(int cmd, union bpf_attr *attr,
+ unsigned int size)
+{
+ return 0;
+}
+
+static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+ return 0;
+}
+
+static inline int security_bpf_prog(struct bpf_prog *prog)
+{
+ return 0;
+}
+
+static inline int security_bpf_map_alloc(struct bpf_map *map)
+{
+ return 0;
+}
+
+static inline void security_bpf_map_free(struct bpf_map *map)
+{ }
+
+static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+ return 0;
+}
+
+static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{ }
+#endif /* CONFIG_SECURITY */
+#endif /* CONFIG_BPF_SYSCALL */
+
#ifdef CONFIG_SECURITY
static inline char *alloc_secdata(void)
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index cd95b5e..695bb36 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -66,6 +66,7 @@ struct uart_ops {
void (*set_ldisc)(struct uart_port *, struct ktermios *);
void (*pm)(struct uart_port *, unsigned int state,
unsigned int oldstate);
+ void (*wake_peer)(struct uart_port *);
/*
* Return a string describing the type of the port
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index a0596ca0..a2f8109 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+u64 sock_gen_cookie(struct sock *sk);
int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 249dafc..90d8569 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -436,6 +436,7 @@ extern bool pm_get_wakeup_count(unsigned int *count, bool block);
extern bool pm_save_wakeup_count(unsigned int count);
extern void pm_wakep_autosleep_enabled(bool set);
extern void pm_print_active_wakeup_sources(void);
+extern void pm_get_active_wakeup_sources(char *pending_sources, size_t max);
static inline void lock_system_sleep(void)
{
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d13617c..1619a3c 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -245,7 +245,7 @@ struct swap_info_struct {
/* linux/mm/workingset.c */
void *workingset_eviction(struct address_space *mapping, struct page *page);
-bool workingset_refault(void *shadow);
+void workingset_refault(struct page *page, void *shadow);
void workingset_activation(struct page *page);
extern struct list_lru workingset_shadow_nodes;
diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h
index aa17ccf..35ec6c4 100644
--- a/include/linux/sync_file.h
+++ b/include/linux/sync_file.h
@@ -40,12 +40,13 @@ struct sync_file {
#endif
wait_queue_head_t wq;
+ unsigned long flags;
struct fence *fence;
struct fence_cb cb;
};
-#define POLL_ENABLED FENCE_FLAG_USER_BITS
+#define POLL_ENABLED 0
struct sync_file *sync_file_create(struct fence *fence);
struct fence *sync_file_get_fence(int fd);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91a740f..06c3550 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -205,6 +205,26 @@ extern struct trace_event_functions exit_syscall_print_funcs;
} \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+/*
+ * Called before coming back to user-mode. Returning to user-mode with an
+ * address limit different than USER_DS can allow to overwrite kernel memory.
+ */
+static inline void addr_limit_user_check(void)
+{
+#ifdef TIF_FSCHECK
+ if (!test_thread_flag(TIF_FSCHECK))
+ return;
+#endif
+
+ if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+ "Invalid address limit on user-mode return"))
+ force_sig(SIGKILL, current);
+
+#ifdef TIF_FSCHECK
+ clear_thread_flag(TIF_FSCHECK);
+#endif
+}
+
asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
qid_t id, void __user *addr);
asmlinkage long sys_time(time_t __user *tloc);
@@ -865,6 +885,7 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd,
struct file_handle __user *handle,
int flags);
asmlinkage long sys_setns(int fd, int nstype);
+asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags);
asmlinkage long sys_process_vm_readv(pid_t pid,
const struct iovec __user *lvec,
unsigned long liovcnt,
@@ -902,5 +923,8 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
unsigned long prot, int pkey);
asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
asmlinkage long sys_pkey_free(int pkey);
+asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
+ siginfo_t __user *info,
+ unsigned int flags);
#endif
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index d3c19f8..2839d62 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -532,7 +532,7 @@ static inline void sysfs_notify_dirent(struct kernfs_node *kn)
}
static inline struct kernfs_node *sysfs_get_dirent(struct kernfs_node *parent,
- const unsigned char *name)
+ const char *name)
{
return kernfs_find_and_get(parent, name);
}
diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h
index bdf855c..2dd338f 100644
--- a/include/linux/task_io_accounting.h
+++ b/include/linux/task_io_accounting.h
@@ -18,6 +18,8 @@ struct task_io_accounting {
u64 syscr;
/* # of write syscalls */
u64 syscw;
+ /* # of fsync syscalls */
+ u64 syscfs;
#endif /* CONFIG_TASK_XACCT */
#ifdef CONFIG_TASK_IO_ACCOUNTING
diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h
index 4d090f9..1b505c8 100644
--- a/include/linux/task_io_accounting_ops.h
+++ b/include/linux/task_io_accounting_ops.h
@@ -96,6 +96,7 @@ static inline void task_chr_io_accounting_add(struct task_io_accounting *dst,
dst->wchar += src->wchar;
dst->syscr += src->syscr;
dst->syscw += src->syscw;
+ dst->syscfs += src->syscfs;
}
#else
static inline void task_chr_io_accounting_add(struct task_io_accounting *dst,
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 53eb9fe..95b4be6 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -221,8 +221,9 @@ struct tcp_sock {
u8 tlp_retrans:1, /* TLP is a retransmission */
unused_1:7;
u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
+ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
- unused:6;
+ unused:5;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
thin_dupack : 1,/* Fast retransmit on first dupack */
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
new file mode 100644
index 0000000..a2b3dfc
--- /dev/null
+++ b/include/linux/tee_drv.h
@@ -0,0 +1,468 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __TEE_DRV_H
+#define __TEE_DRV_H
+
+#include <linux/types.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/tee.h>
+
+/*
+ * The file describes the API provided by the generic TEE driver to the
+ * specific TEE driver.
+ */
+
+#define TEE_SHM_MAPPED BIT(0) /* Memory mapped by the kernel */
+#define TEE_SHM_DMA_BUF BIT(1) /* Memory with dma-buf handle */
+#define TEE_SHM_EXT_DMA_BUF BIT(2) /* Memory with dma-buf handle */
+#define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */
+#define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */
+#define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */
+
+struct device;
+struct tee_device;
+struct tee_shm;
+struct tee_shm_pool;
+
+/**
+ * struct tee_context - driver specific context on file pointer data
+ * @teedev: pointer to this drivers struct tee_device
+ * @list_shm: List of shared memory object owned by this context
+ * @data: driver specific context data, managed by the driver
+ * @refcount: reference counter for this structure
+ * @releasing: flag that indicates if context is being released right now.
+ * It is needed to break circular dependency on context during
+ * shared memory release.
+ */
+struct tee_context {
+ struct tee_device *teedev;
+ struct list_head list_shm;
+ void *data;
+ struct kref refcount;
+ bool releasing;
+};
+
+struct tee_param_memref {
+ size_t shm_offs;
+ size_t size;
+ struct tee_shm *shm;
+};
+
+struct tee_param_value {
+ u64 a;
+ u64 b;
+ u64 c;
+};
+
+struct tee_param {
+ u64 attr;
+ union {
+ struct tee_param_memref memref;
+ struct tee_param_value value;
+ } u;
+};
+
+/**
+ * struct tee_driver_ops - driver operations vtable
+ * @get_version: returns version of driver
+ * @open: called when the device file is opened
+ * @release: release this open file
+ * @open_session: open a new session
+ * @close_session: close a session
+ * @invoke_func: invoke a trusted function
+ * @cancel_req: request cancel of an ongoing invoke or open
+ * @supp_revc: called for supplicant to get a command
+ * @supp_send: called for supplicant to send a response
+ * @shm_register: register shared memory buffer in TEE
+ * @shm_unregister: unregister shared memory buffer in TEE
+ */
+struct tee_driver_ops {
+ void (*get_version)(struct tee_device *teedev,
+ struct tee_ioctl_version_data *vers);
+ int (*open)(struct tee_context *ctx);
+ void (*release)(struct tee_context *ctx);
+ int (*open_session)(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param);
+ int (*close_session)(struct tee_context *ctx, u32 session);
+ int (*invoke_func)(struct tee_context *ctx,
+ struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param);
+ int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session);
+ int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param);
+ int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param);
+ int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm,
+ struct page **pages, size_t num_pages,
+ unsigned long start);
+ int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm);
+};
+
+/**
+ * struct tee_desc - Describes the TEE driver to the subsystem
+ * @name: name of driver
+ * @ops: driver operations vtable
+ * @owner: module providing the driver
+ * @flags: Extra properties of driver, defined by TEE_DESC_* below
+ */
+#define TEE_DESC_PRIVILEGED 0x1
+struct tee_desc {
+ const char *name;
+ const struct tee_driver_ops *ops;
+ struct module *owner;
+ u32 flags;
+};
+
+/**
+ * tee_device_alloc() - Allocate a new struct tee_device instance
+ * @teedesc: Descriptor for this driver
+ * @dev: Parent device for this device
+ * @pool: Shared memory pool, NULL if not used
+ * @driver_data: Private driver data for this device
+ *
+ * Allocates a new struct tee_device instance. The device is
+ * removed by tee_device_unregister().
+ *
+ * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure
+ */
+struct tee_device *tee_device_alloc(const struct tee_desc *teedesc,
+ struct device *dev,
+ struct tee_shm_pool *pool,
+ void *driver_data);
+
+/**
+ * tee_device_register() - Registers a TEE device
+ * @teedev: Device to register
+ *
+ * tee_device_unregister() need to be called to remove the @teedev if
+ * this function fails.
+ *
+ * @returns < 0 on failure
+ */
+int tee_device_register(struct tee_device *teedev);
+
+/**
+ * tee_device_unregister() - Removes a TEE device
+ * @teedev: Device to unregister
+ *
+ * This function should be called to remove the @teedev even if
+ * tee_device_register() hasn't been called yet. Does nothing if
+ * @teedev is NULL.
+ */
+void tee_device_unregister(struct tee_device *teedev);
+
+/**
+ * struct tee_shm - shared memory object
+ * @teedev: device used to allocate the object
+ * @ctx: context using the object, if NULL the context is gone
+ * @link link element
+ * @paddr: physical address of the shared memory
+ * @kaddr: virtual address of the shared memory
+ * @size: size of shared memory
+ * @offset: offset of buffer in user space
+ * @pages: locked pages from userspace
+ * @num_pages: number of locked pages
+ * @dmabuf: dmabuf used to for exporting to user space
+ * @flags: defined by TEE_SHM_* in tee_drv.h
+ * @id: unique id of a shared memory object on this device
+ *
+ * This pool is only supposed to be accessed directly from the TEE
+ * subsystem and from drivers that implements their own shm pool manager.
+ */
+struct tee_shm {
+ struct tee_device *teedev;
+ struct tee_context *ctx;
+ struct list_head link;
+ phys_addr_t paddr;
+ void *kaddr;
+ size_t size;
+ unsigned int offset;
+ struct page **pages;
+ size_t num_pages;
+ struct dma_buf *dmabuf;
+ u32 flags;
+ int id;
+};
+
+/**
+ * struct tee_shm_pool_mgr - shared memory manager
+ * @ops: operations
+ * @private_data: private data for the shared memory manager
+ */
+struct tee_shm_pool_mgr {
+ const struct tee_shm_pool_mgr_ops *ops;
+ void *private_data;
+};
+
+/**
+ * struct tee_shm_pool_mgr_ops - shared memory pool manager operations
+ * @alloc: called when allocating shared memory
+ * @free: called when freeing shared memory
+ * @destroy_poolmgr: called when destroying the pool manager
+ */
+struct tee_shm_pool_mgr_ops {
+ int (*alloc)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm,
+ size_t size);
+ void (*free)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm);
+ void (*destroy_poolmgr)(struct tee_shm_pool_mgr *poolmgr);
+};
+
+/**
+ * tee_shm_pool_alloc() - Create a shared memory pool from shm managers
+ * @priv_mgr: manager for driver private shared memory allocations
+ * @dmabuf_mgr: manager for dma-buf shared memory allocations
+ *
+ * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied
+ * in @dmabuf, others will use the range provided by @priv.
+ *
+ * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool *tee_shm_pool_alloc(struct tee_shm_pool_mgr *priv_mgr,
+ struct tee_shm_pool_mgr *dmabuf_mgr);
+
+/*
+ * tee_shm_pool_mgr_alloc_res_mem() - Create a shm manager for reserved
+ * memory
+ * @vaddr: Virtual address of start of pool
+ * @paddr: Physical address of start of pool
+ * @size: Size in bytes of the pool
+ *
+ * @returns pointer to a 'struct tee_shm_pool_mgr' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool_mgr *tee_shm_pool_mgr_alloc_res_mem(unsigned long vaddr,
+ phys_addr_t paddr,
+ size_t size,
+ int min_alloc_order);
+
+/**
+ * tee_shm_pool_mgr_destroy() - Free a shared memory manager
+ */
+static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm)
+{
+ poolm->ops->destroy_poolmgr(poolm);
+}
+
+/**
+ * struct tee_shm_pool_mem_info - holds information needed to create a shared
+ * memory pool
+ * @vaddr: Virtual address of start of pool
+ * @paddr: Physical address of start of pool
+ * @size: Size in bytes of the pool
+ */
+struct tee_shm_pool_mem_info {
+ unsigned long vaddr;
+ phys_addr_t paddr;
+ size_t size;
+};
+
+/**
+ * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved
+ * memory range
+ * @priv_info: Information for driver private shared memory pool
+ * @dmabuf_info: Information for dma-buf shared memory pool
+ *
+ * Start and end of pools will must be page aligned.
+ *
+ * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied
+ * in @dmabuf, others will use the range provided by @priv.
+ *
+ * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool *
+tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info,
+ struct tee_shm_pool_mem_info *dmabuf_info);
+
+/**
+ * tee_shm_pool_free() - Free a shared memory pool
+ * @pool: The shared memory pool to free
+ *
+ * The must be no remaining shared memory allocated from this pool when
+ * this function is called.
+ */
+void tee_shm_pool_free(struct tee_shm_pool *pool);
+
+/**
+ * tee_get_drvdata() - Return driver_data pointer
+ * @returns the driver_data pointer supplied to tee_register().
+ */
+void *tee_get_drvdata(struct tee_device *teedev);
+
+/**
+ * tee_shm_alloc() - Allocate shared memory
+ * @ctx: Context that allocates the shared memory
+ * @size: Requested size of shared memory
+ * @flags: Flags setting properties for the requested shared memory.
+ *
+ * Memory allocated as global shared memory is automatically freed when the
+ * TEE file pointer is closed. The @flags field uses the bits defined by
+ * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If
+ * TEE_SHM_DMA_BUF global shared memory will be allocated and associated
+ * with a dma-buf handle, else driver private memory.
+ *
+ * @returns a pointer to 'struct tee_shm'
+ */
+struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags);
+
+/**
+ * tee_shm_priv_alloc() - Allocate shared memory privately
+ * @dev: Device that allocates the shared memory
+ * @size: Requested size of shared memory
+ *
+ * Allocates shared memory buffer that is not associated with any client
+ * context. Such buffers are owned by TEE driver and used for internal calls.
+ *
+ * @returns a pointer to 'struct tee_shm'
+ */
+struct tee_shm *tee_shm_priv_alloc(struct tee_device *teedev, size_t size);
+
+/**
+ * tee_shm_register() - Register shared memory buffer
+ * @ctx: Context that registers the shared memory
+ * @addr: Address is userspace of the shared buffer
+ * @length: Length of the shared buffer
+ * @flags: Flags setting properties for the requested shared memory.
+ *
+ * @returns a pointer to 'struct tee_shm'
+ */
+struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
+ size_t length, u32 flags);
+
+/**
+ * tee_shm_is_registered() - Check if shared memory object in registered in TEE
+ * @shm: Shared memory handle
+ * @returns true if object is registered in TEE
+ */
+static inline bool tee_shm_is_registered(struct tee_shm *shm)
+{
+ return shm && (shm->flags & TEE_SHM_REGISTER);
+}
+
+/**
+ * tee_shm_free() - Free shared memory
+ * @shm: Handle to shared memory to free
+ */
+void tee_shm_free(struct tee_shm *shm);
+
+/**
+ * tee_shm_put() - Decrease reference count on a shared memory handle
+ * @shm: Shared memory handle
+ */
+void tee_shm_put(struct tee_shm *shm);
+
+/**
+ * tee_shm_va2pa() - Get physical address of a virtual address
+ * @shm: Shared memory handle
+ * @va: Virtual address to tranlsate
+ * @pa: Returned physical address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa);
+
+/**
+ * tee_shm_pa2va() - Get virtual address of a physical address
+ * @shm: Shared memory handle
+ * @pa: Physical address to tranlsate
+ * @va: Returned virtual address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va);
+
+/**
+ * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @returns virtual address of the shared memory + offs if offs is within
+ * the bounds of this shared memory, else an ERR_PTR
+ */
+void *tee_shm_get_va(struct tee_shm *shm, size_t offs);
+
+/**
+ * tee_shm_get_pa() - Get physical address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @pa: Physical address to return
+ * @returns 0 if offs is within the bounds of this shared memory, else an
+ * error code.
+ */
+int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa);
+
+/**
+ * tee_shm_get_size() - Get size of shared memory buffer
+ * @shm: Shared memory handle
+ * @returns size of shared memory
+ */
+static inline size_t tee_shm_get_size(struct tee_shm *shm)
+{
+ return shm->size;
+}
+
+/**
+ * tee_shm_get_pages() - Get list of pages that hold shared buffer
+ * @shm: Shared memory handle
+ * @num_pages: Number of pages will be stored there
+ * @returns pointer to pages array
+ */
+static inline struct page **tee_shm_get_pages(struct tee_shm *shm,
+ size_t *num_pages)
+{
+ *num_pages = shm->num_pages;
+ return shm->pages;
+}
+
+/**
+ * tee_shm_get_page_offset() - Get shared buffer offset from page start
+ * @shm: Shared memory handle
+ * @returns page offset of shared buffer
+ */
+static inline size_t tee_shm_get_page_offset(struct tee_shm *shm)
+{
+ return shm->offset;
+}
+
+/**
+ * tee_shm_get_id() - Get id of a shared memory object
+ * @shm: Shared memory handle
+ * @returns id
+ */
+static inline int tee_shm_get_id(struct tee_shm *shm)
+{
+ return shm->id;
+}
+
+/**
+ * tee_shm_get_from_id() - Find shared memory object and increase reference
+ * count
+ * @ctx: Context owning the shared memory
+ * @id: Id of shared memory object
+ * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure
+ */
+struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id);
+
+static inline bool tee_param_is_memref(struct tee_param *param)
+{
+ switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+#endif /*__TEE_DRV_H*/
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 5e64367..ce98a8e 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -9,51 +9,18 @@
#include <linux/types.h>
#include <linux/bug.h>
-
-struct timespec;
-struct compat_timespec;
+#include <linux/restart_block.h>
#ifdef CONFIG_THREAD_INFO_IN_TASK
+/*
+ * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the
+ * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels,
+ * including <asm/current.h> can cause a circular dependency on some platforms.
+ */
+#include <asm/current.h>
#define current_thread_info() ((struct thread_info *)current)
#endif
-/*
- * System call restart block.
- */
-struct restart_block {
- long (*fn)(struct restart_block *);
- union {
- /* For futex_wait and futex_wait_requeue_pi */
- struct {
- u32 __user *uaddr;
- u32 val;
- u32 flags;
- u32 bitset;
- u64 time;
- u32 __user *uaddr2;
- } futex;
- /* For nanosleep */
- struct {
- clockid_t clockid;
- struct timespec __user *rmtp;
-#ifdef CONFIG_COMPAT
- struct compat_timespec __user *compat_rmtp;
-#endif
- u64 expires;
- } nanosleep;
- /* For poll */
- struct {
- struct pollfd __user *ufds;
- int nfds;
- int has_timeout;
- unsigned long tv_sec;
- unsigned long tv_nsec;
- } poll;
- };
-};
-
-extern long do_no_restart_syscall(struct restart_block *parm);
-
#include <linux/bitops.h>
#include <asm/thread_info.h>
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 62be0786..78ec2eb 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void);
extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
+extern unsigned long tick_nohz_get_idle_calls(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 2c225d4..dfc80b7 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -51,7 +51,7 @@ struct tk_read_base {
* @clock_was_set_seq: The sequence number of clock was set events
* @cs_was_changed_seq: The sequence number of clocksource change events
* @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second
- * @raw_time: Monotonic raw base time in timespec64 format
+ * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
* @cycle_interval: Number of clock cycles in one NTP interval
* @xtime_interval: Number of clock shifted nano seconds in one NTP
* interval.
@@ -93,7 +93,7 @@ struct timekeeper {
unsigned int clock_was_set_seq;
u8 cs_was_changed_seq;
ktime_t next_leap_ktime;
- struct timespec64 raw_time;
+ u64 raw_sec;
/* The following members are for timekeeping internal use */
cycle_t cycle_interval;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 09168c5..361f8bf 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -249,6 +249,7 @@ static inline u64 ktime_get_raw_ns(void)
extern u64 ktime_get_mono_fast_ns(void);
extern u64 ktime_get_raw_fast_ns(void);
+extern u64 ktime_get_boot_fast_ns(void);
/*
* Timespec interfaces utilizing the ktime based ones
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index ba57266..426a19b 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,14 +272,37 @@ struct trace_event_call {
#ifdef CONFIG_PERF_EVENTS
int perf_refcount;
struct hlist_head __percpu *perf_events;
- struct bpf_prog *prog;
- struct perf_event *bpf_prog_owner;
+ struct bpf_prog_array __rcu *prog_array;
int (*perf_perm)(struct trace_event_call *,
struct perf_event *);
#endif
};
+#ifdef CONFIG_PERF_EVENTS
+static inline bool bpf_prog_array_valid(struct trace_event_call *call)
+{
+ /*
+ * This inline function checks whether call->prog_array
+ * is valid or not. The function is called in various places,
+ * outside rcu_read_lock/unlock, as a heuristic to speed up execution.
+ *
+ * If this function returns true, and later call->prog_array
+ * becomes false inside rcu_read_lock/unlock region,
+ * we bail out then. If this function return false,
+ * there is a risk that we might miss a few events if the checking
+ * were delayed until inside rcu_read_lock/unlock region and
+ * call->prog_array happened to become non-NULL then.
+ *
+ * Here, READ_ONCE() is used instead of rcu_access_pointer().
+ * rcu_access_pointer() requires the actual definition of
+ * "struct bpf_prog_array" while READ_ONCE() only needs
+ * a declaration of the same type.
+ */
+ return !!READ_ONCE(call->prog_array);
+}
+#endif
+
static inline const char *
trace_event_name(struct trace_event_call *call)
{
@@ -430,12 +453,23 @@ trace_trigger_soft_disabled(struct trace_event_file *file)
}
#ifdef CONFIG_BPF_EVENTS
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx);
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
+int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
+void perf_event_detach_bpf_prog(struct perf_event *event);
#else
-static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
return 1;
}
+
+static inline int
+perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void perf_event_detach_bpf_prog(struct perf_event *event) { }
+
#endif
enum {
@@ -506,6 +540,7 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
{
perf_tp_event(type, count, raw_data, size, regs, head, rctx, task);
}
+
#endif
#endif /* _LINUX_TRACE_EVENT_H */
diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h
new file mode 100644
index 0000000..c6df223
--- /dev/null
+++ b/include/linux/usb/class-dual-role.h
@@ -0,0 +1,129 @@
+#ifndef __LINUX_CLASS_DUAL_ROLE_H__
+#define __LINUX_CLASS_DUAL_ROLE_H__
+
+#include <linux/workqueue.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device;
+
+enum dual_role_supported_modes {
+ DUAL_ROLE_SUPPORTED_MODES_DFP_AND_UFP = 0,
+ DUAL_ROLE_SUPPORTED_MODES_DFP,
+ DUAL_ROLE_SUPPORTED_MODES_UFP,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_MODE_UFP = 0,
+ DUAL_ROLE_PROP_MODE_DFP,
+ DUAL_ROLE_PROP_MODE_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_MODE_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_PR_SRC = 0,
+ DUAL_ROLE_PROP_PR_SNK,
+ DUAL_ROLE_PROP_PR_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_PR_TOTAL,
+
+};
+
+enum {
+ DUAL_ROLE_PROP_DR_HOST = 0,
+ DUAL_ROLE_PROP_DR_DEVICE,
+ DUAL_ROLE_PROP_DR_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_DR_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_VCONN_SUPPLY_NO = 0,
+ DUAL_ROLE_PROP_VCONN_SUPPLY_YES,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL,
+};
+
+enum dual_role_property {
+ DUAL_ROLE_PROP_SUPPORTED_MODES = 0,
+ DUAL_ROLE_PROP_MODE,
+ DUAL_ROLE_PROP_PR,
+ DUAL_ROLE_PROP_DR,
+ DUAL_ROLE_PROP_VCONN_SUPPLY,
+};
+
+struct dual_role_phy_instance;
+
+/* Description of typec port */
+struct dual_role_phy_desc {
+ /* /sys/class/dual_role_usb/<name>/ */
+ const char *name;
+ enum dual_role_supported_modes supported_modes;
+ enum dual_role_property *properties;
+ size_t num_properties;
+
+ /* Callback for "cat /sys/class/dual_role_usb/<name>/<property>" */
+ int (*get_property)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val);
+ /* Callback for "echo <value> >
+ * /sys/class/dual_role_usb/<name>/<property>" */
+ int (*set_property)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val);
+ /* Decides whether userspace can change a specific property */
+ int (*property_is_writeable)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop);
+};
+
+struct dual_role_phy_instance {
+ const struct dual_role_phy_desc *desc;
+
+ /* Driver private data */
+ void *drv_data;
+
+ struct device dev;
+ struct work_struct changed_work;
+};
+
+#if IS_ENABLED(CONFIG_DUAL_ROLE_USB_INTF)
+extern void dual_role_instance_changed(struct dual_role_phy_instance
+ *dual_role);
+extern struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc);
+extern void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role);
+extern int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val);
+extern int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val);
+extern int dual_role_property_is_writeable(struct dual_role_phy_instance
+ *dual_role,
+ enum dual_role_property prop);
+extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role);
+#else /* CONFIG_DUAL_ROLE_USB_INTF */
+static inline void dual_role_instance_changed(struct dual_role_phy_instance
+ *dual_role){}
+static inline struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ return ERR_PTR(-ENOSYS);
+}
+static inline void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role){}
+static inline void *dual_role_get_drvdata(struct dual_role_phy_instance
+ *dual_role)
+{
+ return ERR_PTR(-ENOSYS);
+}
+#endif /* CONFIG_DUAL_ROLE_USB_INTF */
+#endif /* __LINUX_CLASS_DUAL_ROLE_H__ */
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 0ec7185..652d1b7 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -587,6 +587,7 @@ struct usb_function_instance {
struct config_group group;
struct list_head cfs_list;
struct usb_function_driver *fd;
+ struct usb_function *f;
int (*set_inst_name)(struct usb_function_instance *inst,
const char *name);
void (*free_func_inst)(struct usb_function_instance *inst);
diff --git a/include/linux/usb/f_accessory.h b/include/linux/usb/f_accessory.h
new file mode 100644
index 0000000..ebe3c4d
--- /dev/null
+++ b/include/linux/usb/f_accessory.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_ACCESSORY_H
+#define __LINUX_USB_F_ACCESSORY_H
+
+#include <uapi/linux/usb/f_accessory.h>
+
+#endif /* __LINUX_USB_F_ACCESSORY_H */
diff --git a/include/linux/usb/f_mtp.h b/include/linux/usb/f_mtp.h
new file mode 100644
index 0000000..4e84177
--- /dev/null
+++ b/include/linux/usb/f_mtp.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_MTP_H
+#define __LINUX_USB_F_MTP_H
+
+#include <uapi/linux/usb/f_mtp.h>
+
+#endif /* __LINUX_USB_F_MTP_H */
diff --git a/include/linux/verification.h b/include/linux/verification.h
index cfa4730..60ea906 100644
--- a/include/linux/verification.h
+++ b/include/linux/verification.h
@@ -32,9 +32,13 @@ enum key_being_used_for {
};
extern const char *const key_being_used_for[NR__KEY_BEING_USED_FOR];
-#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
-
struct key;
+struct public_key_signature;
+
+extern int verify_signature_one(const struct public_key_signature *sig,
+ struct key *trusted_keys, const char *keyid);
+
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
extern int verify_pkcs7_signature(const void *data, size_t len,
const void *raw_pkcs7, size_t pkcs7_len,
diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h
new file mode 100644
index 0000000..d84d8c3
--- /dev/null
+++ b/include/linux/wakeup_reason.h
@@ -0,0 +1,32 @@
+/*
+ * include/linux/wakeup_reason.h
+ *
+ * Logs the reason which caused the kernel to resume
+ * from the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_WAKEUP_REASON_H
+#define _LINUX_WAKEUP_REASON_H
+
+#define MAX_SUSPEND_ABORT_LEN 256
+
+void log_wakeup_reason(int irq);
+int check_wakeup_reason(int irq);
+
+#ifdef CONFIG_SUSPEND
+void log_suspend_abort_reason(const char *fmt, ...);
+#else
+static inline void log_suspend_abort_reason(const char *fmt, ...) { }
+#endif
+
+#endif /* _LINUX_WAKEUP_REASON_H */
diff --git a/include/linux/wlan_plat.h b/include/linux/wlan_plat.h
new file mode 100644
index 0000000..8e8b06f
--- /dev/null
+++ b/include/linux/wlan_plat.h
@@ -0,0 +1,30 @@
+/* include/linux/wlan_plat.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef _LINUX_WLAN_PLAT_H_
+#define _LINUX_WLAN_PLAT_H_
+
+#define WLAN_PLAT_NODFS_FLAG 0x01
+
+struct wifi_platform_data {
+ int (*set_power)(int val);
+ int (*set_reset)(int val);
+ int (*set_carddetect)(int val);
+ void *(*mem_prealloc)(int section, unsigned long size);
+ int (*get_mac_addr)(unsigned char *buf);
+ int (*get_wake_irq)(void);
+ void *(*get_country_code)(char *ccode, u32 flags);
+};
+
+#endif
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 8e880f7..b95c511 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -359,6 +359,8 @@ extern struct workqueue_struct *system_freezable_wq;
extern struct workqueue_struct *system_power_efficient_wq;
extern struct workqueue_struct *system_freezable_power_efficient_wq;
+extern bool wq_online;
+
extern struct workqueue_struct *
__alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6);
@@ -598,7 +600,7 @@ static inline bool schedule_delayed_work(struct delayed_work *dwork,
*/
static inline bool keventd_up(void)
{
- return system_wq != NULL;
+ return wq_online;
}
#ifndef CONFIG_SMP
@@ -635,4 +637,7 @@ int workqueue_online_cpu(unsigned int cpu);
int workqueue_offline_cpu(unsigned int cpu);
#endif
+int __init workqueue_init_early(void);
+int __init workqueue_init(void);
+
#endif
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 797100e..45ac8f2b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -362,7 +362,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
-void page_writeback_init(void);
void balance_dirty_pages_ratelimited(struct address_space *mapping);
bool wb_over_bg_thresh(struct bdi_writeback *wb);
diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h
new file mode 100644
index 0000000..9e1f42c
--- /dev/null
+++ b/include/linux/xxhash.h
@@ -0,0 +1,236 @@
+/*
+ * xxHash - Extremely Fast Hash algorithm
+ * Copyright (C) 2012-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at:
+ * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash source repository: https://github.com/Cyan4973/xxHash
+ */
+
+/*
+ * Notice extracted from xxHash homepage:
+ *
+ * xxHash is an extremely fast Hash algorithm, running at RAM speed limits.
+ * It also successfully passes all tests from the SMHasher suite.
+ *
+ * Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2
+ * Duo @3GHz)
+ *
+ * Name Speed Q.Score Author
+ * xxHash 5.4 GB/s 10
+ * CrapWow 3.2 GB/s 2 Andrew
+ * MumurHash 3a 2.7 GB/s 10 Austin Appleby
+ * SpookyHash 2.0 GB/s 10 Bob Jenkins
+ * SBox 1.4 GB/s 9 Bret Mulvey
+ * Lookup3 1.2 GB/s 9 Bob Jenkins
+ * SuperFastHash 1.2 GB/s 1 Paul Hsieh
+ * CityHash64 1.05 GB/s 10 Pike & Alakuijala
+ * FNV 0.55 GB/s 5 Fowler, Noll, Vo
+ * CRC32 0.43 GB/s 9
+ * MD5-32 0.33 GB/s 10 Ronald L. Rivest
+ * SHA1-32 0.28 GB/s 10
+ *
+ * Q.Score is a measure of quality of the hash function.
+ * It depends on successfully passing SMHasher test set.
+ * 10 is a perfect score.
+ *
+ * A 64-bits version, named xxh64 offers much better speed,
+ * but for 64-bits applications only.
+ * Name Speed on 64 bits Speed on 32 bits
+ * xxh64 13.8 GB/s 1.9 GB/s
+ * xxh32 6.8 GB/s 6.0 GB/s
+ */
+
+#ifndef XXHASH_H
+#define XXHASH_H
+
+#include <linux/types.h>
+
+/*-****************************
+ * Simple Hash Functions
+ *****************************/
+
+/**
+ * xxh32() - calculate the 32-bit hash of the input with a given seed.
+ *
+ * @input: The data to hash.
+ * @length: The length of the data to hash.
+ * @seed: The seed can be used to alter the result predictably.
+ *
+ * Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s
+ *
+ * Return: The 32-bit hash of the data.
+ */
+uint32_t xxh32(const void *input, size_t length, uint32_t seed);
+
+/**
+ * xxh64() - calculate the 64-bit hash of the input with a given seed.
+ *
+ * @input: The data to hash.
+ * @length: The length of the data to hash.
+ * @seed: The seed can be used to alter the result predictably.
+ *
+ * This function runs 2x faster on 64-bit systems, but slower on 32-bit systems.
+ *
+ * Return: The 64-bit hash of the data.
+ */
+uint64_t xxh64(const void *input, size_t length, uint64_t seed);
+
+/*-****************************
+ * Streaming Hash Functions
+ *****************************/
+
+/*
+ * These definitions are only meant to allow allocation of XXH state
+ * statically, on stack, or in a struct for example.
+ * Do not use members directly.
+ */
+
+/**
+ * struct xxh32_state - private xxh32 state, do not use members directly
+ */
+struct xxh32_state {
+ uint32_t total_len_32;
+ uint32_t large_len;
+ uint32_t v1;
+ uint32_t v2;
+ uint32_t v3;
+ uint32_t v4;
+ uint32_t mem32[4];
+ uint32_t memsize;
+};
+
+/**
+ * struct xxh32_state - private xxh64 state, do not use members directly
+ */
+struct xxh64_state {
+ uint64_t total_len;
+ uint64_t v1;
+ uint64_t v2;
+ uint64_t v3;
+ uint64_t v4;
+ uint64_t mem64[4];
+ uint32_t memsize;
+};
+
+/**
+ * xxh32_reset() - reset the xxh32 state to start a new hashing operation
+ *
+ * @state: The xxh32 state to reset.
+ * @seed: Initialize the hash state with this seed.
+ *
+ * Call this function on any xxh32_state to prepare for a new hashing operation.
+ */
+void xxh32_reset(struct xxh32_state *state, uint32_t seed);
+
+/**
+ * xxh32_update() - hash the data given and update the xxh32 state
+ *
+ * @state: The xxh32 state to update.
+ * @input: The data to hash.
+ * @length: The length of the data to hash.
+ *
+ * After calling xxh32_reset() call xxh32_update() as many times as necessary.
+ *
+ * Return: Zero on success, otherwise an error code.
+ */
+int xxh32_update(struct xxh32_state *state, const void *input, size_t length);
+
+/**
+ * xxh32_digest() - produce the current xxh32 hash
+ *
+ * @state: Produce the current xxh32 hash of this state.
+ *
+ * A hash value can be produced at any time. It is still possible to continue
+ * inserting input into the hash state after a call to xxh32_digest(), and
+ * generate new hashes later on, by calling xxh32_digest() again.
+ *
+ * Return: The xxh32 hash stored in the state.
+ */
+uint32_t xxh32_digest(const struct xxh32_state *state);
+
+/**
+ * xxh64_reset() - reset the xxh64 state to start a new hashing operation
+ *
+ * @state: The xxh64 state to reset.
+ * @seed: Initialize the hash state with this seed.
+ */
+void xxh64_reset(struct xxh64_state *state, uint64_t seed);
+
+/**
+ * xxh64_update() - hash the data given and update the xxh64 state
+ * @state: The xxh64 state to update.
+ * @input: The data to hash.
+ * @length: The length of the data to hash.
+ *
+ * After calling xxh64_reset() call xxh64_update() as many times as necessary.
+ *
+ * Return: Zero on success, otherwise an error code.
+ */
+int xxh64_update(struct xxh64_state *state, const void *input, size_t length);
+
+/**
+ * xxh64_digest() - produce the current xxh64 hash
+ *
+ * @state: Produce the current xxh64 hash of this state.
+ *
+ * A hash value can be produced at any time. It is still possible to continue
+ * inserting input into the hash state after a call to xxh64_digest(), and
+ * generate new hashes later on, by calling xxh64_digest() again.
+ *
+ * Return: The xxh64 hash stored in the state.
+ */
+uint64_t xxh64_digest(const struct xxh64_state *state);
+
+/*-**************************
+ * Utils
+ ***************************/
+
+/**
+ * xxh32_copy_state() - copy the source state into the destination state
+ *
+ * @src: The source xxh32 state.
+ * @dst: The destination xxh32 state.
+ */
+void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src);
+
+/**
+ * xxh64_copy_state() - copy the source state into the destination state
+ *
+ * @src: The source xxh64 state.
+ * @dst: The destination xxh64 state.
+ */
+void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src);
+
+#endif /* XXHASH_H */
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 57a8e98..2219cce 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -47,6 +47,8 @@ void zs_destroy_pool(struct zs_pool *pool);
unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags);
void zs_free(struct zs_pool *pool, unsigned long obj);
+size_t zs_huge_class_size(struct zs_pool *pool);
+
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
enum zs_mapmode mm);
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
diff --git a/include/linux/zstd.h b/include/linux/zstd.h
new file mode 100644
index 0000000..249575e
--- /dev/null
+++ b/include/linux/zstd.h
@@ -0,0 +1,1157 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+#ifndef ZSTD_H
+#define ZSTD_H
+
+/* ====== Dependency ======*/
+#include <linux/types.h> /* size_t */
+
+
+/*-*****************************************************************************
+ * Introduction
+ *
+ * zstd, short for Zstandard, is a fast lossless compression algorithm,
+ * targeting real-time compression scenarios at zlib-level and better
+ * compression ratios. The zstd compression library provides in-memory
+ * compression and decompression functions. The library supports compression
+ * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled
+ * ultra, should be used with caution, as they require more memory.
+ * Compression can be done in:
+ * - a single step, reusing a context (described as Explicit memory management)
+ * - unbounded multiple steps (described as Streaming compression)
+ * The compression ratio achievable on small data can be highly improved using
+ * compression with a dictionary in:
+ * - a single step (described as Simple dictionary API)
+ * - a single step, reusing a dictionary (described as Fast dictionary API)
+ ******************************************************************************/
+
+/*====== Helper functions ======*/
+
+/**
+ * enum ZSTD_ErrorCode - zstd error codes
+ *
+ * Functions that return size_t can be checked for errors using ZSTD_isError()
+ * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode().
+ */
+typedef enum {
+ ZSTD_error_no_error,
+ ZSTD_error_GENERIC,
+ ZSTD_error_prefix_unknown,
+ ZSTD_error_version_unsupported,
+ ZSTD_error_parameter_unknown,
+ ZSTD_error_frameParameter_unsupported,
+ ZSTD_error_frameParameter_unsupportedBy32bits,
+ ZSTD_error_frameParameter_windowTooLarge,
+ ZSTD_error_compressionParameter_unsupported,
+ ZSTD_error_init_missing,
+ ZSTD_error_memory_allocation,
+ ZSTD_error_stage_wrong,
+ ZSTD_error_dstSize_tooSmall,
+ ZSTD_error_srcSize_wrong,
+ ZSTD_error_corruption_detected,
+ ZSTD_error_checksum_wrong,
+ ZSTD_error_tableLog_tooLarge,
+ ZSTD_error_maxSymbolValue_tooLarge,
+ ZSTD_error_maxSymbolValue_tooSmall,
+ ZSTD_error_dictionary_corrupted,
+ ZSTD_error_dictionary_wrong,
+ ZSTD_error_dictionaryCreation_failed,
+ ZSTD_error_maxCode
+} ZSTD_ErrorCode;
+
+/**
+ * ZSTD_maxCLevel() - maximum compression level available
+ *
+ * Return: Maximum compression level available.
+ */
+int ZSTD_maxCLevel(void);
+/**
+ * ZSTD_compressBound() - maximum compressed size in worst case scenario
+ * @srcSize: The size of the data to compress.
+ *
+ * Return: The maximum compressed size in the worst case scenario.
+ */
+size_t ZSTD_compressBound(size_t srcSize);
+/**
+ * ZSTD_isError() - tells if a size_t function result is an error code
+ * @code: The function result to check for error.
+ *
+ * Return: Non-zero iff the code is an error.
+ */
+static __attribute__((unused)) unsigned int ZSTD_isError(size_t code)
+{
+ return code > (size_t)-ZSTD_error_maxCode;
+}
+/**
+ * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode
+ * @functionResult: The result of a function for which ZSTD_isError() is true.
+ *
+ * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0
+ * if the functionResult isn't an error.
+ */
+static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode(
+ size_t functionResult)
+{
+ if (!ZSTD_isError(functionResult))
+ return (ZSTD_ErrorCode)0;
+ return (ZSTD_ErrorCode)(0 - functionResult);
+}
+
+/**
+ * enum ZSTD_strategy - zstd compression search strategy
+ *
+ * From faster to stronger.
+ */
+typedef enum {
+ ZSTD_fast,
+ ZSTD_dfast,
+ ZSTD_greedy,
+ ZSTD_lazy,
+ ZSTD_lazy2,
+ ZSTD_btlazy2,
+ ZSTD_btopt,
+ ZSTD_btopt2
+} ZSTD_strategy;
+
+/**
+ * struct ZSTD_compressionParameters - zstd compression parameters
+ * @windowLog: Log of the largest match distance. Larger means more
+ * compression, and more memory needed during decompression.
+ * @chainLog: Fully searched segment. Larger means more compression, slower,
+ * and more memory (useless for fast).
+ * @hashLog: Dispatch table. Larger means more compression,
+ * slower, and more memory.
+ * @searchLog: Number of searches. Larger means more compression and slower.
+ * @searchLength: Match length searched. Larger means faster decompression,
+ * sometimes less compression.
+ * @targetLength: Acceptable match size for optimal parser (only). Larger means
+ * more compression, and slower.
+ * @strategy: The zstd compression strategy.
+ */
+typedef struct {
+ unsigned int windowLog;
+ unsigned int chainLog;
+ unsigned int hashLog;
+ unsigned int searchLog;
+ unsigned int searchLength;
+ unsigned int targetLength;
+ ZSTD_strategy strategy;
+} ZSTD_compressionParameters;
+
+/**
+ * struct ZSTD_frameParameters - zstd frame parameters
+ * @contentSizeFlag: Controls whether content size will be present in the frame
+ * header (when known).
+ * @checksumFlag: Controls whether a 32-bit checksum is generated at the end
+ * of the frame for error detection.
+ * @noDictIDFlag: Controls whether dictID will be saved into the frame header
+ * when using dictionary compression.
+ *
+ * The default value is all fields set to 0.
+ */
+typedef struct {
+ unsigned int contentSizeFlag;
+ unsigned int checksumFlag;
+ unsigned int noDictIDFlag;
+} ZSTD_frameParameters;
+
+/**
+ * struct ZSTD_parameters - zstd parameters
+ * @cParams: The compression parameters.
+ * @fParams: The frame parameters.
+ */
+typedef struct {
+ ZSTD_compressionParameters cParams;
+ ZSTD_frameParameters fParams;
+} ZSTD_parameters;
+
+/**
+ * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level
+ * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel().
+ * @estimatedSrcSize: The estimated source size to compress or 0 if unknown.
+ * @dictSize: The dictionary size or 0 if a dictionary isn't being used.
+ *
+ * Return: The selected ZSTD_compressionParameters.
+ */
+ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel,
+ unsigned long long estimatedSrcSize, size_t dictSize);
+
+/**
+ * ZSTD_getParams() - returns ZSTD_parameters for selected level
+ * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel().
+ * @estimatedSrcSize: The estimated source size to compress or 0 if unknown.
+ * @dictSize: The dictionary size or 0 if a dictionary isn't being used.
+ *
+ * The same as ZSTD_getCParams() except also selects the default frame
+ * parameters (all zero).
+ *
+ * Return: The selected ZSTD_parameters.
+ */
+ZSTD_parameters ZSTD_getParams(int compressionLevel,
+ unsigned long long estimatedSrcSize, size_t dictSize);
+
+/*-*************************************
+ * Explicit memory management
+ **************************************/
+
+/**
+ * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx
+ * @cParams: The compression parameters to be used for compression.
+ *
+ * If multiple compression parameters might be used, the caller must call
+ * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum
+ * size.
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initCCtx().
+ */
+size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams);
+
+/**
+ * struct ZSTD_CCtx - the zstd compression context
+ *
+ * When compressing many times it is recommended to allocate a context just once
+ * and reuse it for each successive compression operation.
+ */
+typedef struct ZSTD_CCtx_s ZSTD_CCtx;
+/**
+ * ZSTD_initCCtx() - initialize a zstd compression context
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to
+ * determine how large the workspace must be.
+ *
+ * Return: A compression context emplaced into workspace.
+ */
+ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize);
+
+/**
+ * ZSTD_compressCCtx() - compress src into dst
+ * @ctx: The context. Must have been initialized with a workspace at
+ * least as large as ZSTD_CCtxWorkspaceBound(params.cParams).
+ * @dst: The buffer to compress src into.
+ * @dstCapacity: The size of the destination buffer. May be any size, but
+ * ZSTD_compressBound(srcSize) is guaranteed to be large enough.
+ * @src: The data to compress.
+ * @srcSize: The size of the data to compress.
+ * @params: The parameters to use for compression. See ZSTD_getParams().
+ *
+ * Return: The compressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize, ZSTD_parameters params);
+
+/**
+ * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initDCtx().
+ */
+size_t ZSTD_DCtxWorkspaceBound(void);
+
+/**
+ * struct ZSTD_DCtx - the zstd decompression context
+ *
+ * When decompressing many times it is recommended to allocate a context just
+ * once and reuse it for each successive decompression operation.
+ */
+typedef struct ZSTD_DCtx_s ZSTD_DCtx;
+/**
+ * ZSTD_initDCtx() - initialize a zstd decompression context
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to
+ * determine how large the workspace must be.
+ *
+ * Return: A decompression context emplaced into workspace.
+ */
+ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize);
+
+/**
+ * ZSTD_decompressDCtx() - decompress zstd compressed src into dst
+ * @ctx: The decompression context.
+ * @dst: The buffer to decompress src into.
+ * @dstCapacity: The size of the destination buffer. Must be at least as large
+ * as the decompressed size. If the caller cannot upper bound the
+ * decompressed size, then it's better to use the streaming API.
+ * @src: The zstd compressed data to decompress. Multiple concatenated
+ * frames and skippable frames are allowed.
+ * @srcSize: The exact size of the data to decompress.
+ *
+ * Return: The decompressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+
+/*-************************
+ * Simple dictionary API
+ **************************/
+
+/**
+ * ZSTD_compress_usingDict() - compress src into dst using a dictionary
+ * @ctx: The context. Must have been initialized with a workspace at
+ * least as large as ZSTD_CCtxWorkspaceBound(params.cParams).
+ * @dst: The buffer to compress src into.
+ * @dstCapacity: The size of the destination buffer. May be any size, but
+ * ZSTD_compressBound(srcSize) is guaranteed to be large enough.
+ * @src: The data to compress.
+ * @srcSize: The size of the data to compress.
+ * @dict: The dictionary to use for compression.
+ * @dictSize: The size of the dictionary.
+ * @params: The parameters to use for compression. See ZSTD_getParams().
+ *
+ * Compression using a predefined dictionary. The same dictionary must be used
+ * during decompression.
+ *
+ * Return: The compressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize, const void *dict, size_t dictSize,
+ ZSTD_parameters params);
+
+/**
+ * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary
+ * @ctx: The decompression context.
+ * @dst: The buffer to decompress src into.
+ * @dstCapacity: The size of the destination buffer. Must be at least as large
+ * as the decompressed size. If the caller cannot upper bound the
+ * decompressed size, then it's better to use the streaming API.
+ * @src: The zstd compressed data to decompress. Multiple concatenated
+ * frames and skippable frames are allowed.
+ * @srcSize: The exact size of the data to decompress.
+ * @dict: The dictionary to use for decompression. The same dictionary
+ * must've been used to compress the data.
+ * @dictSize: The size of the dictionary.
+ *
+ * Return: The decompressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize, const void *dict, size_t dictSize);
+
+/*-**************************
+ * Fast dictionary API
+ ***************************/
+
+/**
+ * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict
+ * @cParams: The compression parameters to be used for compression.
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initCDict().
+ */
+size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams);
+
+/**
+ * struct ZSTD_CDict - a digested dictionary to be used for compression
+ */
+typedef struct ZSTD_CDict_s ZSTD_CDict;
+
+/**
+ * ZSTD_initCDict() - initialize a digested dictionary for compression
+ * @dictBuffer: The dictionary to digest. The buffer is referenced by the
+ * ZSTD_CDict so it must outlive the returned ZSTD_CDict.
+ * @dictSize: The size of the dictionary.
+ * @params: The parameters to use for compression. See ZSTD_getParams().
+ * @workspace: The workspace. It must outlive the returned ZSTD_CDict.
+ * @workspaceSize: The workspace size. Must be at least
+ * ZSTD_CDictWorkspaceBound(params.cParams).
+ *
+ * When compressing multiple messages / blocks with the same dictionary it is
+ * recommended to load it just once. The ZSTD_CDict merely references the
+ * dictBuffer, so it must outlive the returned ZSTD_CDict.
+ *
+ * Return: The digested dictionary emplaced into workspace.
+ */
+ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize,
+ ZSTD_parameters params, void *workspace, size_t workspaceSize);
+
+/**
+ * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict
+ * @ctx: The context. Must have been initialized with a workspace at
+ * least as large as ZSTD_CCtxWorkspaceBound(cParams) where
+ * cParams are the compression parameters used to initialize the
+ * cdict.
+ * @dst: The buffer to compress src into.
+ * @dstCapacity: The size of the destination buffer. May be any size, but
+ * ZSTD_compressBound(srcSize) is guaranteed to be large enough.
+ * @src: The data to compress.
+ * @srcSize: The size of the data to compress.
+ * @cdict: The digested dictionary to use for compression.
+ * @params: The parameters to use for compression. See ZSTD_getParams().
+ *
+ * Compression using a digested dictionary. The same dictionary must be used
+ * during decompression.
+ *
+ * Return: The compressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize, const ZSTD_CDict *cdict);
+
+
+/**
+ * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initDDict().
+ */
+size_t ZSTD_DDictWorkspaceBound(void);
+
+/**
+ * struct ZSTD_DDict - a digested dictionary to be used for decompression
+ */
+typedef struct ZSTD_DDict_s ZSTD_DDict;
+
+/**
+ * ZSTD_initDDict() - initialize a digested dictionary for decompression
+ * @dictBuffer: The dictionary to digest. The buffer is referenced by the
+ * ZSTD_DDict so it must outlive the returned ZSTD_DDict.
+ * @dictSize: The size of the dictionary.
+ * @workspace: The workspace. It must outlive the returned ZSTD_DDict.
+ * @workspaceSize: The workspace size. Must be at least
+ * ZSTD_DDictWorkspaceBound().
+ *
+ * When decompressing multiple messages / blocks with the same dictionary it is
+ * recommended to load it just once. The ZSTD_DDict merely references the
+ * dictBuffer, so it must outlive the returned ZSTD_DDict.
+ *
+ * Return: The digested dictionary emplaced into workspace.
+ */
+ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize,
+ void *workspace, size_t workspaceSize);
+
+/**
+ * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict
+ * @ctx: The decompression context.
+ * @dst: The buffer to decompress src into.
+ * @dstCapacity: The size of the destination buffer. Must be at least as large
+ * as the decompressed size. If the caller cannot upper bound the
+ * decompressed size, then it's better to use the streaming API.
+ * @src: The zstd compressed data to decompress. Multiple concatenated
+ * frames and skippable frames are allowed.
+ * @srcSize: The exact size of the data to decompress.
+ * @ddict: The digested dictionary to use for decompression. The same
+ * dictionary must've been used to compress the data.
+ *
+ * Return: The decompressed size or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst,
+ size_t dstCapacity, const void *src, size_t srcSize,
+ const ZSTD_DDict *ddict);
+
+
+/*-**************************
+ * Streaming
+ ***************************/
+
+/**
+ * struct ZSTD_inBuffer - input buffer for streaming
+ * @src: Start of the input buffer.
+ * @size: Size of the input buffer.
+ * @pos: Position where reading stopped. Will be updated.
+ * Necessarily 0 <= pos <= size.
+ */
+typedef struct ZSTD_inBuffer_s {
+ const void *src;
+ size_t size;
+ size_t pos;
+} ZSTD_inBuffer;
+
+/**
+ * struct ZSTD_outBuffer - output buffer for streaming
+ * @dst: Start of the output buffer.
+ * @size: Size of the output buffer.
+ * @pos: Position where writing stopped. Will be updated.
+ * Necessarily 0 <= pos <= size.
+ */
+typedef struct ZSTD_outBuffer_s {
+ void *dst;
+ size_t size;
+ size_t pos;
+} ZSTD_outBuffer;
+
+
+
+/*-*****************************************************************************
+ * Streaming compression - HowTo
+ *
+ * A ZSTD_CStream object is required to track streaming operation.
+ * Use ZSTD_initCStream() to initialize a ZSTD_CStream object.
+ * ZSTD_CStream objects can be reused multiple times on consecutive compression
+ * operations. It is recommended to re-use ZSTD_CStream in situations where many
+ * streaming operations will be achieved consecutively. Use one separate
+ * ZSTD_CStream per thread for parallel execution.
+ *
+ * Use ZSTD_compressStream() repetitively to consume input stream.
+ * The function will automatically update both `pos` fields.
+ * Note that it may not consume the entire input, in which case `pos < size`,
+ * and it's up to the caller to present again remaining data.
+ * It returns a hint for the preferred number of bytes to use as an input for
+ * the next function call.
+ *
+ * At any moment, it's possible to flush whatever data remains within internal
+ * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might
+ * still be some content left within the internal buffer if `output->size` is
+ * too small. It returns the number of bytes left in the internal buffer and
+ * must be called until it returns 0.
+ *
+ * ZSTD_endStream() instructs to finish a frame. It will perform a flush and
+ * write frame epilogue. The epilogue is required for decoders to consider a
+ * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush
+ * the full content if `output->size` is too small. In which case, call again
+ * ZSTD_endStream() to complete the flush. It returns the number of bytes left
+ * in the internal buffer and must be called until it returns 0.
+ ******************************************************************************/
+
+/**
+ * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream
+ * @cParams: The compression parameters to be used for compression.
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initCStream() and ZSTD_initCStream_usingCDict().
+ */
+size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams);
+
+/**
+ * struct ZSTD_CStream - the zstd streaming compression context
+ */
+typedef struct ZSTD_CStream_s ZSTD_CStream;
+
+/*===== ZSTD_CStream management functions =====*/
+/**
+ * ZSTD_initCStream() - initialize a zstd streaming compression context
+ * @params: The zstd compression parameters.
+ * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must
+ * pass the source size (zero means empty source). Otherwise,
+ * the caller may optionally pass the source size, or zero if
+ * unknown.
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace.
+ * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine
+ * how large the workspace must be.
+ *
+ * Return: The zstd streaming compression context.
+ */
+ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params,
+ unsigned long long pledgedSrcSize, void *workspace,
+ size_t workspaceSize);
+
+/**
+ * ZSTD_initCStream_usingCDict() - initialize a streaming compression context
+ * @cdict: The digested dictionary to use for compression.
+ * @pledgedSrcSize: Optionally the source size, or zero if unknown.
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound()
+ * with the cParams used to initialize the cdict to determine
+ * how large the workspace must be.
+ *
+ * Return: The zstd streaming compression context.
+ */
+ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict,
+ unsigned long long pledgedSrcSize, void *workspace,
+ size_t workspaceSize);
+
+/*===== Streaming compression functions =====*/
+/**
+ * ZSTD_resetCStream() - reset the context using parameters from creation
+ * @zcs: The zstd streaming compression context to reset.
+ * @pledgedSrcSize: Optionally the source size, or zero if unknown.
+ *
+ * Resets the context using the parameters from creation. Skips dictionary
+ * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame
+ * content size is always written into the frame header.
+ *
+ * Return: Zero or an error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize);
+/**
+ * ZSTD_compressStream() - streaming compress some of input into output
+ * @zcs: The zstd streaming compression context.
+ * @output: Destination buffer. `output->pos` is updated to indicate how much
+ * compressed data was written.
+ * @input: Source buffer. `input->pos` is updated to indicate how much data was
+ * read. Note that it may not consume the entire input, in which case
+ * `input->pos < input->size`, and it's up to the caller to present
+ * remaining data again.
+ *
+ * The `input` and `output` buffers may be any size. Guaranteed to make some
+ * forward progress if `input` and `output` are not empty.
+ *
+ * Return: A hint for the number of bytes to use as the input for the next
+ * function call or an error, which can be checked using
+ * ZSTD_isError().
+ */
+size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output,
+ ZSTD_inBuffer *input);
+/**
+ * ZSTD_flushStream() - flush internal buffers into output
+ * @zcs: The zstd streaming compression context.
+ * @output: Destination buffer. `output->pos` is updated to indicate how much
+ * compressed data was written.
+ *
+ * ZSTD_flushStream() must be called until it returns 0, meaning all the data
+ * has been flushed. Since ZSTD_flushStream() causes a block to be ended,
+ * calling it too often will degrade the compression ratio.
+ *
+ * Return: The number of bytes still present within internal buffers or an
+ * error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output);
+/**
+ * ZSTD_endStream() - flush internal buffers into output and end the frame
+ * @zcs: The zstd streaming compression context.
+ * @output: Destination buffer. `output->pos` is updated to indicate how much
+ * compressed data was written.
+ *
+ * ZSTD_endStream() must be called until it returns 0, meaning all the data has
+ * been flushed and the frame epilogue has been written.
+ *
+ * Return: The number of bytes still present within internal buffers or an
+ * error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output);
+
+/**
+ * ZSTD_CStreamInSize() - recommended size for the input buffer
+ *
+ * Return: The recommended size for the input buffer.
+ */
+size_t ZSTD_CStreamInSize(void);
+/**
+ * ZSTD_CStreamOutSize() - recommended size for the output buffer
+ *
+ * When the output buffer is at least this large, it is guaranteed to be large
+ * enough to flush at least one complete compressed block.
+ *
+ * Return: The recommended size for the output buffer.
+ */
+size_t ZSTD_CStreamOutSize(void);
+
+
+
+/*-*****************************************************************************
+ * Streaming decompression - HowTo
+ *
+ * A ZSTD_DStream object is required to track streaming operations.
+ * Use ZSTD_initDStream() to initialize a ZSTD_DStream object.
+ * ZSTD_DStream objects can be re-used multiple times.
+ *
+ * Use ZSTD_decompressStream() repetitively to consume your input.
+ * The function will update both `pos` fields.
+ * If `input->pos < input->size`, some input has not been consumed.
+ * It's up to the caller to present again remaining data.
+ * If `output->pos < output->size`, decoder has flushed everything it could.
+ * Returns 0 iff a frame is completely decoded and fully flushed.
+ * Otherwise it returns a suggested next input size that will never load more
+ * than the current frame.
+ ******************************************************************************/
+
+/**
+ * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream
+ * @maxWindowSize: The maximum window size allowed for compressed frames.
+ *
+ * Return: A lower bound on the size of the workspace that is passed to
+ * ZSTD_initDStream() and ZSTD_initDStream_usingDDict().
+ */
+size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize);
+
+/**
+ * struct ZSTD_DStream - the zstd streaming decompression context
+ */
+typedef struct ZSTD_DStream_s ZSTD_DStream;
+/*===== ZSTD_DStream management functions =====*/
+/**
+ * ZSTD_initDStream() - initialize a zstd streaming decompression context
+ * @maxWindowSize: The maximum window size allowed for compressed frames.
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace.
+ * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine
+ * how large the workspace must be.
+ *
+ * Return: The zstd streaming decompression context.
+ */
+ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace,
+ size_t workspaceSize);
+/**
+ * ZSTD_initDStream_usingDDict() - initialize streaming decompression context
+ * @maxWindowSize: The maximum window size allowed for compressed frames.
+ * @ddict: The digested dictionary to use for decompression.
+ * @workspace: The workspace to emplace the context into. It must outlive
+ * the returned context.
+ * @workspaceSize: The size of workspace.
+ * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine
+ * how large the workspace must be.
+ *
+ * Return: The zstd streaming decompression context.
+ */
+ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize,
+ const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize);
+
+/*===== Streaming decompression functions =====*/
+/**
+ * ZSTD_resetDStream() - reset the context using parameters from creation
+ * @zds: The zstd streaming decompression context to reset.
+ *
+ * Resets the context using the parameters from creation. Skips dictionary
+ * loading, since it can be reused.
+ *
+ * Return: Zero or an error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_resetDStream(ZSTD_DStream *zds);
+/**
+ * ZSTD_decompressStream() - streaming decompress some of input into output
+ * @zds: The zstd streaming decompression context.
+ * @output: Destination buffer. `output.pos` is updated to indicate how much
+ * decompressed data was written.
+ * @input: Source buffer. `input.pos` is updated to indicate how much data was
+ * read. Note that it may not consume the entire input, in which case
+ * `input.pos < input.size`, and it's up to the caller to present
+ * remaining data again.
+ *
+ * The `input` and `output` buffers may be any size. Guaranteed to make some
+ * forward progress if `input` and `output` are not empty.
+ * ZSTD_decompressStream() will not consume the last byte of the frame until
+ * the entire frame is flushed.
+ *
+ * Return: Returns 0 iff a frame is completely decoded and fully flushed.
+ * Otherwise returns a hint for the number of bytes to use as the input
+ * for the next function call or an error, which can be checked using
+ * ZSTD_isError(). The size hint will never load more than the frame.
+ */
+size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output,
+ ZSTD_inBuffer *input);
+
+/**
+ * ZSTD_DStreamInSize() - recommended size for the input buffer
+ *
+ * Return: The recommended size for the input buffer.
+ */
+size_t ZSTD_DStreamInSize(void);
+/**
+ * ZSTD_DStreamOutSize() - recommended size for the output buffer
+ *
+ * When the output buffer is at least this large, it is guaranteed to be large
+ * enough to flush at least one complete decompressed block.
+ *
+ * Return: The recommended size for the output buffer.
+ */
+size_t ZSTD_DStreamOutSize(void);
+
+
+/* --- Constants ---*/
+#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */
+#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U
+
+#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
+#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
+
+#define ZSTD_WINDOWLOG_MAX_32 27
+#define ZSTD_WINDOWLOG_MAX_64 27
+#define ZSTD_WINDOWLOG_MAX \
+ ((unsigned int)(sizeof(size_t) == 4 \
+ ? ZSTD_WINDOWLOG_MAX_32 \
+ : ZSTD_WINDOWLOG_MAX_64))
+#define ZSTD_WINDOWLOG_MIN 10
+#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX
+#define ZSTD_HASHLOG_MIN 6
+#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1)
+#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN
+#define ZSTD_HASHLOG3_MAX 17
+#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1)
+#define ZSTD_SEARCHLOG_MIN 1
+/* only for ZSTD_fast, other strategies are limited to 6 */
+#define ZSTD_SEARCHLENGTH_MAX 7
+/* only for ZSTD_btopt, other strategies are limited to 4 */
+#define ZSTD_SEARCHLENGTH_MIN 3
+#define ZSTD_TARGETLENGTH_MIN 4
+#define ZSTD_TARGETLENGTH_MAX 999
+
+/* for static allocation */
+#define ZSTD_FRAMEHEADERSIZE_MAX 18
+#define ZSTD_FRAMEHEADERSIZE_MIN 6
+static const size_t ZSTD_frameHeaderSize_prefix = 5;
+static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
+static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX;
+/* magic number + skippable frame length */
+static const size_t ZSTD_skippableHeaderSize = 8;
+
+
+/*-*************************************
+ * Compressed size functions
+ **************************************/
+
+/**
+ * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame
+ * @src: Source buffer. It should point to the start of a zstd encoded frame
+ * or a skippable frame.
+ * @srcSize: The size of the source buffer. It must be at least as large as the
+ * size of the frame.
+ *
+ * Return: The compressed size of the frame pointed to by `src` or an error,
+ * which can be check with ZSTD_isError().
+ * Suitable to pass to ZSTD_decompress() or similar functions.
+ */
+size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize);
+
+/*-*************************************
+ * Decompressed size functions
+ **************************************/
+/**
+ * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header
+ * @src: It should point to the start of a zstd encoded frame.
+ * @srcSize: The size of the source buffer. It must be at least as large as the
+ * frame header. `ZSTD_frameHeaderSize_max` is always large enough.
+ *
+ * Return: The frame content size stored in the frame header if known.
+ * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the
+ * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input.
+ */
+unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+
+/**
+ * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames
+ * @src: It should point to the start of a series of zstd encoded and/or
+ * skippable frames.
+ * @srcSize: The exact size of the series of frames.
+ *
+ * If any zstd encoded frame in the series doesn't have the frame content size
+ * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always
+ * set when using ZSTD_compress(). The decompressed size can be very large.
+ * If the source is untrusted, the decompressed size could be wrong or
+ * intentionally modified. Always ensure the result fits within the
+ * application's authorized limits. ZSTD_findDecompressedSize() handles multiple
+ * frames, and so it must traverse the input to read each frame header. This is
+ * efficient as most of the data is skipped, however it does mean that all frame
+ * data must be present and valid.
+ *
+ * Return: Decompressed size of all the data contained in the frames if known.
+ * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown.
+ * `ZSTD_CONTENTSIZE_ERROR` if an error occurred.
+ */
+unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize);
+
+/*-*************************************
+ * Advanced compression functions
+ **************************************/
+/**
+ * ZSTD_checkCParams() - ensure parameter values remain within authorized range
+ * @cParams: The zstd compression parameters.
+ *
+ * Return: Zero or an error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams);
+
+/**
+ * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize
+ * @srcSize: Optionally the estimated source size, or zero if unknown.
+ * @dictSize: Optionally the estimated dictionary size, or zero if unknown.
+ *
+ * Return: The optimized parameters.
+ */
+ZSTD_compressionParameters ZSTD_adjustCParams(
+ ZSTD_compressionParameters cParams, unsigned long long srcSize,
+ size_t dictSize);
+
+/*--- Advanced decompression functions ---*/
+
+/**
+ * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame
+ * @buffer: The source buffer to check.
+ * @size: The size of the source buffer, must be at least 4 bytes.
+ *
+ * Return: True iff the buffer starts with a zstd or skippable frame identifier.
+ */
+unsigned int ZSTD_isFrame(const void *buffer, size_t size);
+
+/**
+ * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary
+ * @dict: The dictionary buffer.
+ * @dictSize: The size of the dictionary buffer.
+ *
+ * Return: The dictionary id stored within the dictionary or 0 if the
+ * dictionary is not a zstd dictionary. If it returns 0 the
+ * dictionary can still be loaded as a content-only dictionary.
+ */
+unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize);
+
+/**
+ * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict
+ * @ddict: The ddict to find the id of.
+ *
+ * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not
+ * a zstd dictionary. If it returns 0 `ddict` will be loaded as a
+ * content-only dictionary.
+ */
+unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict);
+
+/**
+ * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame
+ * @src: Source buffer. It must be a zstd encoded frame.
+ * @srcSize: The size of the source buffer. It must be at least as large as the
+ * frame header. `ZSTD_frameHeaderSize_max` is always large enough.
+ *
+ * Return: The dictionary id required to decompress the frame stored within
+ * `src` or 0 if the dictionary id could not be decoded. It can return
+ * 0 if the frame does not require a dictionary, the dictionary id
+ * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize`
+ * is too small.
+ */
+unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize);
+
+/**
+ * struct ZSTD_frameParams - zstd frame parameters stored in the frame header
+ * @frameContentSize: The frame content size, or 0 if not present.
+ * @windowSize: The window size, or 0 if the frame is a skippable frame.
+ * @dictID: The dictionary id, or 0 if not present.
+ * @checksumFlag: Whether a checksum was used.
+ */
+typedef struct {
+ unsigned long long frameContentSize;
+ unsigned int windowSize;
+ unsigned int dictID;
+ unsigned int checksumFlag;
+} ZSTD_frameParams;
+
+/**
+ * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame
+ * @fparamsPtr: On success the frame parameters are written here.
+ * @src: The source buffer. It must point to a zstd or skippable frame.
+ * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is
+ * always large enough to succeed.
+ *
+ * Return: 0 on success. If more data is required it returns how many bytes
+ * must be provided to make forward progress. Otherwise it returns
+ * an error, which can be checked using ZSTD_isError().
+ */
+size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src,
+ size_t srcSize);
+
+/*-*****************************************************************************
+ * Buffer-less and synchronous inner streaming functions
+ *
+ * This is an advanced API, giving full control over buffer management, for
+ * users which need direct control over memory.
+ * But it's also a complex one, with many restrictions (documented below).
+ * Prefer using normal streaming API for an easier experience
+ ******************************************************************************/
+
+/*-*****************************************************************************
+ * Buffer-less streaming compression (synchronous mode)
+ *
+ * A ZSTD_CCtx object is required to track streaming operations.
+ * Use ZSTD_initCCtx() to initialize a context.
+ * ZSTD_CCtx object can be re-used multiple times within successive compression
+ * operations.
+ *
+ * Start by initializing a context.
+ * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary
+ * compression,
+ * or ZSTD_compressBegin_advanced(), for finer parameter control.
+ * It's also possible to duplicate a reference context which has already been
+ * initialized, using ZSTD_copyCCtx()
+ *
+ * Then, consume your input using ZSTD_compressContinue().
+ * There are some important considerations to keep in mind when using this
+ * advanced function :
+ * - ZSTD_compressContinue() has no internal buffer. It uses externally provided
+ * buffer only.
+ * - Interface is synchronous : input is consumed entirely and produce 1+
+ * (or more) compressed blocks.
+ * - Caller must ensure there is enough space in `dst` to store compressed data
+ * under worst case scenario. Worst case evaluation is provided by
+ * ZSTD_compressBound().
+ * ZSTD_compressContinue() doesn't guarantee recover after a failed
+ * compression.
+ * - ZSTD_compressContinue() presumes prior input ***is still accessible and
+ * unmodified*** (up to maximum distance size, see WindowLog).
+ * It remembers all previous contiguous blocks, plus one separated memory
+ * segment (which can itself consists of multiple contiguous blocks)
+ * - ZSTD_compressContinue() detects that prior input has been overwritten when
+ * `src` buffer overlaps. In which case, it will "discard" the relevant memory
+ * section from its history.
+ *
+ * Finish a frame with ZSTD_compressEnd(), which will write the last block(s)
+ * and optional checksum. It's possible to use srcSize==0, in which case, it
+ * will write a final empty block to end the frame. Without last block mark,
+ * frames will be considered unfinished (corrupted) by decoders.
+ *
+ * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new
+ * frame.
+ ******************************************************************************/
+
+/*===== Buffer-less streaming compression functions =====*/
+size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel);
+size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict,
+ size_t dictSize, int compressionLevel);
+size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict,
+ size_t dictSize, ZSTD_parameters params,
+ unsigned long long pledgedSrcSize);
+size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx,
+ unsigned long long pledgedSrcSize);
+size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict,
+ unsigned long long pledgedSrcSize);
+size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+
+
+
+/*-*****************************************************************************
+ * Buffer-less streaming decompression (synchronous mode)
+ *
+ * A ZSTD_DCtx object is required to track streaming operations.
+ * Use ZSTD_initDCtx() to initialize a context.
+ * A ZSTD_DCtx object can be re-used multiple times.
+ *
+ * First typical operation is to retrieve frame parameters, using
+ * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide
+ * important information to correctly decode the frame, such as the minimum
+ * rolling buffer size to allocate to decompress data (`windowSize`), and the
+ * dictionary ID used.
+ * Note: content size is optional, it may not be present. 0 means unknown.
+ * Note that these values could be wrong, either because of data malformation,
+ * or because an attacker is spoofing deliberate false information. As a
+ * consequence, check that values remain within valid application range,
+ * especially `windowSize`, before allocation. Each application can set its own
+ * limit, depending on local restrictions. For extended interoperability, it is
+ * recommended to support at least 8 MB.
+ * Frame parameters are extracted from the beginning of the compressed frame.
+ * Data fragment must be large enough to ensure successful decoding, typically
+ * `ZSTD_frameHeaderSize_max` bytes.
+ * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled.
+ * >0: `srcSize` is too small, provide at least this many bytes.
+ * errorCode, which can be tested using ZSTD_isError().
+ *
+ * Start decompression, with ZSTD_decompressBegin() or
+ * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared
+ * context, using ZSTD_copyDCtx().
+ *
+ * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue()
+ * alternatively.
+ * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize'
+ * to ZSTD_decompressContinue().
+ * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will
+ * fail.
+ *
+ * The result of ZSTD_decompressContinue() is the number of bytes regenerated
+ * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an
+ * error; it just means ZSTD_decompressContinue() has decoded some metadata
+ * item. It can also be an error code, which can be tested with ZSTD_isError().
+ *
+ * ZSTD_decompressContinue() needs previous data blocks during decompression, up
+ * to `windowSize`. They should preferably be located contiguously, prior to
+ * current block. Alternatively, a round buffer of sufficient size is also
+ * possible. Sufficient size is determined by frame parameters.
+ * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't
+ * follow each other, make sure that either the compressor breaks contiguity at
+ * the same place, or that previous contiguous segment is large enough to
+ * properly handle maximum back-reference.
+ *
+ * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero.
+ * Context can then be reset to start a new decompression.
+ *
+ * Note: it's possible to know if next input to present is a header or a block,
+ * using ZSTD_nextInputType(). This information is not required to properly
+ * decode a frame.
+ *
+ * == Special case: skippable frames ==
+ *
+ * Skippable frames allow integration of user-defined data into a flow of
+ * concatenated frames. Skippable frames will be ignored (skipped) by a
+ * decompressor. The format of skippable frames is as follows:
+ * a) Skippable frame ID - 4 Bytes, Little endian format, any value from
+ * 0x184D2A50 to 0x184D2A5F
+ * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
+ * c) Frame Content - any content (User Data) of length equal to Frame Size
+ * For skippable frames ZSTD_decompressContinue() always returns 0.
+ * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0
+ * what means that a frame is skippable.
+ * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might
+ * actually be a zstd encoded frame with no content. For purposes of
+ * decompression, it is valid in both cases to skip the frame using
+ * ZSTD_findFrameCompressedSize() to find its size in bytes.
+ * It also returns frame size as fparamsPtr->frameContentSize.
+ ******************************************************************************/
+
+/*===== Buffer-less streaming decompression functions =====*/
+size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx);
+size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict,
+ size_t dictSize);
+void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx);
+size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx);
+size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+typedef enum {
+ ZSTDnit_frameHeader,
+ ZSTDnit_blockHeader,
+ ZSTDnit_block,
+ ZSTDnit_lastBlock,
+ ZSTDnit_checksum,
+ ZSTDnit_skippableFrame
+} ZSTD_nextInputType_e;
+ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx);
+
+/*-*****************************************************************************
+ * Block functions
+ *
+ * Block functions produce and decode raw zstd blocks, without frame metadata.
+ * Frame metadata cost is typically ~18 bytes, which can be non-negligible for
+ * very small blocks (< 100 bytes). User will have to take in charge required
+ * information to regenerate data, such as compressed and content sizes.
+ *
+ * A few rules to respect:
+ * - Compressing and decompressing require a context structure
+ * + Use ZSTD_initCCtx() and ZSTD_initDCtx()
+ * - It is necessary to init context before starting
+ * + compression : ZSTD_compressBegin()
+ * + decompression : ZSTD_decompressBegin()
+ * + variants _usingDict() are also allowed
+ * + copyCCtx() and copyDCtx() work too
+ * - Block size is limited, it must be <= ZSTD_getBlockSizeMax()
+ * + If you need to compress more, cut data into multiple blocks
+ * + Consider using the regular ZSTD_compress() instead, as frame metadata
+ * costs become negligible when source size is large.
+ * - When a block is considered not compressible enough, ZSTD_compressBlock()
+ * result will be zero. In which case, nothing is produced into `dst`.
+ * + User must test for such outcome and deal directly with uncompressed data
+ * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!!
+ * + In case of multiple successive blocks, decoder must be informed of
+ * uncompressed block existence to follow proper history. Use
+ * ZSTD_insertBlock() in such a case.
+ ******************************************************************************/
+
+/* Define for static allocation */
+#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024)
+/*===== Raw zstd block functions =====*/
+size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx);
+size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity,
+ const void *src, size_t srcSize);
+size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart,
+ size_t blockSize);
+
+#endif /* ZSTD_H */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 34ea021..8e2362c 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -246,6 +246,8 @@ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset)
void addrconf_prefix_rcv(struct net_device *dev,
u8 *opt, int len, bool sllao);
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table);
+
/*
* anycast prototypes (anycast.c)
*/
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 0b0ad79..b4eee18 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -8,6 +8,11 @@
#include <net/flow.h>
#include <net/rtnetlink.h>
+struct fib_kuid_range {
+ kuid_t start;
+ kuid_t end;
+};
+
struct fib_rule {
struct list_head list;
int iifindex;
@@ -30,6 +35,7 @@ struct fib_rule {
int suppress_prefixlen;
char iifname[IFNAMSIZ];
char oifname[IFNAMSIZ];
+ struct fib_kuid_range uid_range;
struct rcu_head rcu;
};
@@ -93,7 +99,8 @@ struct fib_rules_ops {
[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
[FRA_GOTO] = { .type = NLA_U32 }, \
- [FRA_L3MDEV] = { .type = NLA_U8 }
+ [FRA_L3MDEV] = { .type = NLA_U8 }, \
+ [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }
static inline void fib_rule_get(struct fib_rule *rule)
{
diff --git a/include/net/flow.h b/include/net/flow.h
index 035aa77..6fc3e13 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -11,6 +11,7 @@
#include <linux/in6.h>
#include <linux/atomic.h>
#include <net/flow_dissector.h>
+#include <linux/uidgid.h>
/*
* ifindex generation is per-net namespace, and loopback is
@@ -24,6 +25,10 @@ struct flowi_tunnel {
__be64 tun_id;
};
+struct flowi_xfrm {
+ __u32 if_id;
+};
+
struct flowi_common {
int flowic_oif;
int flowic_iif;
@@ -37,6 +42,8 @@ struct flowi_common {
#define FLOWI_FLAG_SKIP_NH_OIF 0x04
__u32 flowic_secid;
struct flowi_tunnel flowic_tun_key;
+ struct flowi_xfrm xfrm;
+ kuid_t flowic_uid;
};
union flowi_uli {
@@ -74,6 +81,8 @@ struct flowi4 {
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
#define flowi4_tun_key __fl_common.flowic_tun_key
+#define flowi4_uid __fl_common.flowic_uid
+#define flowi4_xfrm __fl_common.xfrm
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -93,7 +102,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ kuid_t uid)
{
fl4->flowi4_oif = oif;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
@@ -104,6 +114,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
fl4->flowi4_tun_key.tun_id = 0;
+ fl4->flowi4_xfrm.if_id = 0;
+ fl4->flowi4_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
@@ -131,6 +143,8 @@ struct flowi6 {
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
#define flowi6_tun_key __fl_common.flowic_tun_key
+#define flowi6_uid __fl_common.flowic_uid
+#define flowi6_xfrm __fl_common.xfrm
struct in6_addr daddr;
struct in6_addr saddr;
/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -176,6 +190,8 @@ struct flowi {
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
#define flowi_tun_key u.__fl_common.flowic_tun_key
+#define flowi_uid u.__fl_common.flowic_uid
+#define flowi_xfrm u.__fl_common.xfrm
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index b0576cb..6aee7a8 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -204,7 +204,6 @@ struct inet6_dev {
__s32 rs_interval; /* in jiffies */
__u8 rs_probes;
- __u8 addr_gen_mode;
unsigned long tstamp; /* ipv6InterfaceTable update timestamp */
struct rcu_head rcu;
};
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6213a90..c2865f5 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -206,7 +206,11 @@ struct inet_sock {
transparent:1,
mc_all:1,
nodefrag:1;
- __u8 bind_address_no_port:1;
+ __u8 bind_address_no_port:1,
+ defer_connect:1; /* Indicates that fastopen_connect is set
+ * and cookie exists so we defer connect
+ * until first data frame is written
+ */
__u8 rcv_tos;
__u8 convert_csum;
int uc_index;
diff --git a/include/net/ip.h b/include/net/ip.h
index f987eaf..6ff61cf 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -180,6 +180,7 @@ struct ip_reply_arg {
/* -1 if not needed */
int bound_dev_if;
u8 tos;
+ kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e45b628..96cc703 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -142,9 +142,10 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr);
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
- u32 mark);
+ u32 mark, kuid_t uid);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
-void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+ kuid_t uid);
void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
u32 mark);
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk);
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index be1fe228..db78894 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -36,6 +36,8 @@ enum {
ND_OPT_RDNSS = 25, /* RFC5006 */
ND_OPT_DNSSL = 31, /* RFC6106 */
ND_OPT_6CO = 34, /* RFC6775 */
+ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */
+ ND_OPT_PREF64 = 38, /* RFC8781 */
__ND_OPT_MAX
};
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 7befec5..1faf2fd 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -306,7 +306,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
struct kernel_param;
-int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
+int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp);
int nf_conntrack_hash_resize(unsigned int hashsize);
extern struct hlist_nulls_head *nf_conntrack_hash;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index af1c5e7..b0905b2 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -112,6 +112,7 @@ struct netns_ipv4 {
int sysctl_tcp_orphan_retries;
int sysctl_tcp_fin_timeout;
unsigned int sysctl_tcp_notsent_lowat;
+ int sysctl_tcp_default_init_rwnd;
int sysctl_igmp_max_memberships;
int sysctl_igmp_max_msf;
diff --git a/include/net/route.h b/include/net/route.h
index b8488ef..2702b7a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -154,7 +154,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
RT_SCOPE_UNIVERSE, proto,
sk ? inet_sk_flowi_flags(sk) : 0,
- daddr, saddr, dport, sport);
+ daddr, saddr, dport, sport, sock_net_uid(net, sk));
if (sk)
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
@@ -270,7 +270,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
flow_flags |= FLOWI_FLAG_ANYSRC;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
- protocol, flow_flags, dst, src, dport, sport);
+ protocol, flow_flags, dst, src, dport, sport,
+ sk->sk_uid);
}
static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/include/net/sock.h b/include/net/sock.h
index d0e1891..8fe71ee 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -420,6 +420,7 @@ struct sock {
u32 sk_max_ack_backlog;
__u32 sk_priority;
__u32 sk_mark;
+ kuid_t sk_uid;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
@@ -1665,6 +1666,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
sk->sk_wq = parent->wq;
parent->sk = sk;
sk_set_socket(sk, parent);
+ sk->sk_uid = SOCK_INODE(parent)->i_uid;
security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
@@ -1672,6 +1674,11 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
+static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
+{
+ return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+}
+
static inline u32 net_tx_rndhash(void)
{
u32 v = prandom_u32();
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f26f075..8361ec6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1253,7 +1253,7 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
rx_opt->num_sacks = 0;
}
-u32 tcp_default_init_rwnd(u32 mss);
+u32 tcp_default_init_rwnd(struct net *net, u32 mss);
void tcp_cwnd_restart(struct sock *sk, s32 delta);
static inline void tcp_slow_start_after_idle_check(struct sock *sk)
@@ -1269,7 +1269,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
}
/* Determine a window scaling and initial window to offer. */
-void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
+void tcp_select_initial_window(struct net *net,
+ int __space, __u32 mss, __u32 *rcv_wnd,
__u32 *window_clamp, int wscale_ok,
__u8 *rcv_wscale, __u32 init_rcv_wnd);
@@ -1518,6 +1519,9 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct tcp_fastopen_cookie *foc,
struct dst_entry *dst);
void tcp_fastopen_init_key_once(bool publish);
+bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
+ struct tcp_fastopen_cookie *cookie);
+bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
#define TCP_FASTOPEN_KEY_LENGTH 16
static inline void tcp_init_send_head(struct sock *sk)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b2a405c..0a4ba0d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -21,6 +21,7 @@
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/flow.h>
+#include <net/gro_cells.h>
#include <linux/interrupt.h>
@@ -136,6 +137,7 @@ struct xfrm_state {
struct xfrm_id id;
struct xfrm_selector sel;
struct xfrm_mark mark;
+ u32 if_id;
u32 tfcpad;
u32 genid;
@@ -155,6 +157,7 @@ struct xfrm_state {
int header_len;
int trailer_len;
u32 extra_flags;
+ struct xfrm_mark smark;
} props;
struct xfrm_lifetime_cfg lft;
@@ -274,6 +277,13 @@ struct xfrm_replay {
int (*overflow)(struct xfrm_state *x, struct sk_buff *skb);
};
+struct xfrm_if_cb {
+ struct xfrm_if *(*decode_session)(struct sk_buff *skb);
+};
+
+void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
+void xfrm_if_unregister_cb(void);
+
struct net_device;
struct xfrm_type;
struct xfrm_dst;
@@ -284,10 +294,12 @@ struct xfrm_policy_afinfo {
struct dst_entry *(*dst_lookup)(struct net *net,
int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr);
+ const xfrm_address_t *daddr,
+ u32 mark);
int (*get_saddr)(struct net *net, int oif,
xfrm_address_t *saddr,
- xfrm_address_t *daddr);
+ xfrm_address_t *daddr,
+ u32 mark);
void (*decode_session)(struct sk_buff *skb,
struct flowi *fl,
int reverse);
@@ -531,6 +543,7 @@ struct xfrm_policy {
atomic_t genid;
u32 priority;
u32 index;
+ u32 if_id;
struct xfrm_mark mark;
struct xfrm_selector selector;
struct xfrm_lifetime_cfg lft;
@@ -964,6 +977,22 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
+struct xfrm_if_parms {
+ char name[IFNAMSIZ]; /* name of XFRM device */
+ int link; /* ifindex of underlying L2 interface */
+ u32 if_id; /* interface identifyer */
+};
+
+struct xfrm_if {
+ struct xfrm_if __rcu *next; /* next interface in list */
+ struct net_device *dev; /* virtual device associated with interface */
+ struct net_device *phydev; /* physical device */
+ struct net *net; /* netns for packet i/o */
+ struct xfrm_if_parms p; /* interface parms */
+
+ struct gro_cells gro_cells;
+};
+
struct sec_path {
atomic_t refcnt;
int len;
@@ -1163,12 +1192,12 @@ void xfrm_garbage_collect(struct net *net);
static inline void xfrm_sk_free_policy(struct sock *sk) {}
static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; }
-static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }
-static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; }
+static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }
+static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; }
static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
-{
- return 1;
-}
+{
+ return 1;
+}
static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
{
return 1;
@@ -1255,7 +1284,7 @@ __xfrm6_state_addr_check(const struct xfrm_state *x,
{
if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) &&
(ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) ||
- ipv6_addr_any((struct in6_addr *)saddr) ||
+ ipv6_addr_any((struct in6_addr *)saddr) ||
ipv6_addr_any((struct in6_addr *)&x->props.saddr)))
return 1;
return 0;
@@ -1448,7 +1477,7 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
struct xfrm_tmpl *tmpl,
struct xfrm_policy *pol, int *err,
unsigned short family);
-struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
+struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
xfrm_address_t *daddr,
xfrm_address_t *saddr,
unsigned short family,
@@ -1577,7 +1606,7 @@ int xfrm_user_policy(struct sock *sk, int optname,
static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
{
return -ENOPROTOOPT;
-}
+}
static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
{
@@ -1595,20 +1624,20 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
void *);
void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net);
int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
+struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
u8 type, int dir,
struct xfrm_selector *sel,
struct xfrm_sec_ctx *ctx, int delete,
int *err);
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir,
- u32 id, int delete, int *err);
+struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8,
+ int dir, u32 id, int delete, int *err);
int xfrm_policy_flush(struct net *net, u8 type, bool task_valid);
void xfrm_policy_hash_rebuild(struct net *net);
u32 xfrm_get_acqseq(void);
int verify_spi_info(u8 proto, u32 min, u32 max);
int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark,
- u8 mode, u32 reqid, u8 proto,
+ u8 mode, u32 reqid, u32 if_id, u8 proto,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr, int create,
unsigned short family);
@@ -1798,6 +1827,22 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m)
return ret;
}
+static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x)
+{
+ struct xfrm_mark *m = &x->props.smark;
+
+ return (m->v & m->m) | (mark & ~m->m);
+}
+
+static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id)
+{
+ int ret = 0;
+
+ if (if_id)
+ ret = nla_put_u32(skb, XFRMA_IF_ID, if_id);
+ return ret;
+}
+
static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
unsigned int family)
{
@@ -1818,4 +1863,37 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
return 0;
}
+
+extern const int xfrm_msg_min[XFRM_NR_MSGTYPES];
+extern const struct nla_policy xfrma_policy[XFRMA_MAX+1];
+
+struct xfrm_translator {
+ /* Allocate frag_list and put compat translation there */
+ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src);
+
+ /* Allocate nlmsg with 64-bit translaton of received 32-bit message */
+ struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh,
+ int maxtype, const struct nla_policy *policy);
+
+ /* Translate 32-bit user_policy from sockptr */
+ int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen);
+
+ struct module *owner;
+};
+
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+extern int xfrm_register_translator(struct xfrm_translator *xtr);
+extern int xfrm_unregister_translator(struct xfrm_translator *xtr);
+extern struct xfrm_translator *xfrm_get_translator(void);
+extern void xfrm_put_translator(struct xfrm_translator *xtr);
+#else
+static inline struct xfrm_translator *xfrm_get_translator(void)
+{
+ return NULL;
+}
+static inline void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+}
+#endif
+
#endif /* _NET_XFRM_H */
diff --git a/include/trace/events/android_fs.h b/include/trace/events/android_fs.h
new file mode 100644
index 0000000..4950953
--- /dev/null
+++ b/include/trace/events/android_fs.h
@@ -0,0 +1,65 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM android_fs
+
+#if !defined(_TRACE_ANDROID_FS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ANDROID_FS_H
+
+#include <linux/tracepoint.h>
+#include <trace/events/android_fs_template.h>
+
+DEFINE_EVENT(android_fs_data_start_template, android_fs_dataread_start,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes,
+ pid_t pid, char *pathname, char *command),
+ TP_ARGS(inode, offset, bytes, pid, pathname, command));
+
+DEFINE_EVENT(android_fs_data_end_template, android_fs_dataread_end,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes),
+ TP_ARGS(inode, offset, bytes));
+
+DEFINE_EVENT(android_fs_data_start_template, android_fs_datawrite_start,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes,
+ pid_t pid, char *pathname, char *command),
+ TP_ARGS(inode, offset, bytes, pid, pathname, command));
+
+DEFINE_EVENT(android_fs_data_end_template, android_fs_datawrite_end,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes),
+ TP_ARGS(inode, offset, bytes));
+
+#endif /* _TRACE_ANDROID_FS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
+#ifndef ANDROID_FSTRACE_GET_PATHNAME
+#define ANDROID_FSTRACE_GET_PATHNAME
+
+/* Sizes an on-stack array, so careful if sizing this up ! */
+#define MAX_TRACE_PATHBUF_LEN 256
+
+static inline char *
+android_fstrace_get_pathname(char *buf, int buflen, struct inode *inode)
+{
+ char *path;
+ struct dentry *d;
+
+ /*
+ * d_obtain_alias() will either iput() if it locates an existing
+ * dentry or transfer the reference to the new dentry created.
+ * So get an extra reference here.
+ */
+ ihold(inode);
+ d = d_obtain_alias(inode);
+ if (likely(!IS_ERR(d))) {
+ path = dentry_path_raw(d, buf, buflen);
+ if (unlikely(IS_ERR(path))) {
+ strcpy(buf, "ERROR");
+ path = buf;
+ }
+ dput(d);
+ } else {
+ strcpy(buf, "ERROR");
+ path = buf;
+ }
+ return path;
+}
+#endif
diff --git a/include/trace/events/android_fs_template.h b/include/trace/events/android_fs_template.h
new file mode 100644
index 0000000..b23d17b
--- /dev/null
+++ b/include/trace/events/android_fs_template.h
@@ -0,0 +1,64 @@
+#if !defined(_TRACE_ANDROID_FS_TEMPLATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ANDROID_FS_TEMPLATE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(android_fs_data_start_template,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes,
+ pid_t pid, char *pathname, char *command),
+ TP_ARGS(inode, offset, bytes, pid, pathname, command),
+ TP_STRUCT__entry(
+ __string(pathbuf, pathname);
+ __field(loff_t, offset);
+ __field(int, bytes);
+ __field(loff_t, i_size);
+ __string(cmdline, command);
+ __field(pid_t, pid);
+ __field(ino_t, ino);
+ ),
+ TP_fast_assign(
+ {
+ /*
+ * Replace the spaces in filenames and cmdlines
+ * because this screws up the tooling that parses
+ * the traces.
+ */
+ __assign_str(pathbuf, pathname);
+ (void)strreplace(__get_str(pathbuf), ' ', '_');
+ __entry->offset = offset;
+ __entry->bytes = bytes;
+ __entry->i_size = i_size_read(inode);
+ __assign_str(cmdline, command);
+ (void)strreplace(__get_str(cmdline), ' ', '_');
+ __entry->pid = pid;
+ __entry->ino = inode->i_ino;
+ }
+ ),
+ TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s,"
+ " pid %d, i_size %llu, ino %lu",
+ __get_str(pathbuf), __entry->offset, __entry->bytes,
+ __get_str(cmdline), __entry->pid, __entry->i_size,
+ (unsigned long) __entry->ino)
+);
+
+DECLARE_EVENT_CLASS(android_fs_data_end_template,
+ TP_PROTO(struct inode *inode, loff_t offset, int bytes),
+ TP_ARGS(inode, offset, bytes),
+ TP_STRUCT__entry(
+ __field(ino_t, ino);
+ __field(loff_t, offset);
+ __field(int, bytes);
+ ),
+ TP_fast_assign(
+ {
+ __entry->ino = inode->i_ino;
+ __entry->offset = offset;
+ __entry->bytes = bytes;
+ }
+ ),
+ TP_printk("ino %lu, offset %llu, bytes %d",
+ (unsigned long) __entry->ino,
+ __entry->offset, __entry->bytes)
+);
+
+#endif /* _TRACE_ANDROID_FS_TEMPLATE_H */
diff --git a/include/trace/events/cpufreq_interactive.h b/include/trace/events/cpufreq_interactive.h
new file mode 100644
index 0000000..faecc0b
--- /dev/null
+++ b/include/trace/events/cpufreq_interactive.h
@@ -0,0 +1,112 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpufreq_interactive
+
+#if !defined(_TRACE_CPUFREQ_INTERACTIVE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUFREQ_INTERACTIVE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(set,
+ TP_PROTO(u32 cpu_id, unsigned long targfreq,
+ unsigned long actualfreq),
+ TP_ARGS(cpu_id, targfreq, actualfreq),
+
+ TP_STRUCT__entry(
+ __field(u32, cpu_id)
+ __field(unsigned long, targfreq)
+ __field(unsigned long, actualfreq)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu_id = (u32)cpu_id;
+ __entry->targfreq = targfreq;
+ __entry->actualfreq = actualfreq;
+ ),
+
+ TP_printk("cpu=%u targ=%lu actual=%lu",
+ __entry->cpu_id, __entry->targfreq,
+ __entry->actualfreq)
+);
+
+DEFINE_EVENT(set, cpufreq_interactive_setspeed,
+ TP_PROTO(u32 cpu_id, unsigned long targfreq,
+ unsigned long actualfreq),
+ TP_ARGS(cpu_id, targfreq, actualfreq)
+);
+
+DECLARE_EVENT_CLASS(loadeval,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, cpu_id)
+ __field(unsigned long, load)
+ __field(unsigned long, curtarg)
+ __field(unsigned long, curactual)
+ __field(unsigned long, newtarg)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu_id = cpu_id;
+ __entry->load = load;
+ __entry->curtarg = curtarg;
+ __entry->curactual = curactual;
+ __entry->newtarg = newtarg;
+ ),
+
+ TP_printk("cpu=%lu load=%lu cur=%lu actual=%lu targ=%lu",
+ __entry->cpu_id, __entry->load, __entry->curtarg,
+ __entry->curactual, __entry->newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_target,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_already,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_notyet,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+TRACE_EVENT(cpufreq_interactive_boost,
+ TP_PROTO(const char *s),
+ TP_ARGS(s),
+ TP_STRUCT__entry(
+ __string(s, s)
+ ),
+ TP_fast_assign(
+ __assign_str(s, s);
+ ),
+ TP_printk("%s", __get_str(s))
+);
+
+TRACE_EVENT(cpufreq_interactive_unboost,
+ TP_PROTO(const char *s),
+ TP_ARGS(s),
+ TP_STRUCT__entry(
+ __string(s, s)
+ ),
+ TP_fast_assign(
+ __assign_str(s, s);
+ ),
+ TP_printk("%s", __get_str(s))
+);
+
+#endif /* _TRACE_CPUFREQ_INTERACTIVE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/cpufreq_sched.h b/include/trace/events/cpufreq_sched.h
new file mode 100644
index 0000000..a46cd08
--- /dev/null
+++ b/include/trace/events/cpufreq_sched.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2015 Steve Muckle <smuckle@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpufreq_sched
+
+#if !defined(_TRACE_CPUFREQ_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUFREQ_SCHED_H
+
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(cpufreq_sched_throttled,
+ TP_PROTO(unsigned int rem),
+ TP_ARGS(rem),
+ TP_STRUCT__entry(
+ __field( unsigned int, rem)
+ ),
+ TP_fast_assign(
+ __entry->rem = rem;
+ ),
+ TP_printk("throttled - %d usec remaining", __entry->rem)
+);
+
+TRACE_EVENT(cpufreq_sched_request_opp,
+ TP_PROTO(int cpu,
+ unsigned long capacity,
+ unsigned int freq_new,
+ unsigned int requested_freq),
+ TP_ARGS(cpu, capacity, freq_new, requested_freq),
+ TP_STRUCT__entry(
+ __field( int, cpu)
+ __field( unsigned long, capacity)
+ __field( unsigned int, freq_new)
+ __field( unsigned int, requested_freq)
+ ),
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->capacity = capacity;
+ __entry->freq_new = freq_new;
+ __entry->requested_freq = requested_freq;
+ ),
+ TP_printk("cpu %d cap change, cluster cap request %ld => OPP %d "
+ "(cur %d)",
+ __entry->cpu, __entry->capacity, __entry->freq_new,
+ __entry->requested_freq)
+);
+
+TRACE_EVENT(cpufreq_sched_update_capacity,
+ TP_PROTO(int cpu,
+ bool request,
+ struct sched_capacity_reqs *scr,
+ unsigned long new_capacity),
+ TP_ARGS(cpu, request, scr, new_capacity),
+ TP_STRUCT__entry(
+ __field( int, cpu)
+ __field( bool, request)
+ __field( unsigned long, cfs)
+ __field( unsigned long, rt)
+ __field( unsigned long, dl)
+ __field( unsigned long, total)
+ __field( unsigned long, new_total)
+ ),
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->request = request;
+ __entry->cfs = scr->cfs;
+ __entry->rt = scr->rt;
+ __entry->dl = scr->dl;
+ __entry->total = scr->total;
+ __entry->new_total = new_capacity;
+ ),
+ TP_printk("cpu=%d set_cap=%d cfs=%ld rt=%ld dl=%ld old_tot=%ld "
+ "new_tot=%ld",
+ __entry->cpu, __entry->request, __entry->cfs, __entry->rt,
+ __entry->dl, __entry->total, __entry->new_total)
+);
+
+#endif /* _TRACE_CPUFREQ_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 903a091..e238f54 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -6,8 +6,8 @@
#include <linux/tracepoint.h>
-#define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev)
-#define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino
+#define show_dev(dev) MAJOR(dev), MINOR(dev)
+#define show_dev_ino(entry) show_dev(entry->dev), (unsigned long)entry->ino
TRACE_DEFINE_ENUM(NODE);
TRACE_DEFINE_ENUM(DATA);
@@ -15,6 +15,8 @@ TRACE_DEFINE_ENUM(META);
TRACE_DEFINE_ENUM(META_FLUSH);
TRACE_DEFINE_ENUM(INMEM);
TRACE_DEFINE_ENUM(INMEM_DROP);
+TRACE_DEFINE_ENUM(INMEM_INVALIDATE);
+TRACE_DEFINE_ENUM(INMEM_REVOKE);
TRACE_DEFINE_ENUM(IPU);
TRACE_DEFINE_ENUM(OPU);
TRACE_DEFINE_ENUM(CURSEG_HOT_DATA);
@@ -42,6 +44,7 @@ TRACE_DEFINE_ENUM(CP_FASTBOOT);
TRACE_DEFINE_ENUM(CP_SYNC);
TRACE_DEFINE_ENUM(CP_RECOVERY);
TRACE_DEFINE_ENUM(CP_DISCARD);
+TRACE_DEFINE_ENUM(CP_TRIMMED);
#define show_block_type(type) \
__print_symbolic(type, \
@@ -51,32 +54,40 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
{ META_FLUSH, "META_FLUSH" }, \
{ INMEM, "INMEM" }, \
{ INMEM_DROP, "INMEM_DROP" }, \
+ { INMEM_INVALIDATE, "INMEM_INVALIDATE" }, \
{ INMEM_REVOKE, "INMEM_REVOKE" }, \
{ IPU, "IN-PLACE" }, \
{ OPU, "OUT-OF-PLACE" })
-#define F2FS_BIO_FLAG_MASK(t) (t & (REQ_RAHEAD | WRITE_FLUSH_FUA))
-#define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO))
+#define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_META | REQ_PRIO | \
+ REQ_PREFLUSH | REQ_FUA)
+#define F2FS_BIO_FLAG_MASK(t) (t & F2FS_OP_FLAGS)
-#define show_bio_type(op_flags) show_bio_op_flags(op_flags), \
- show_bio_extra(op_flags)
+#define show_bio_type(op,op_flags) show_bio_op(op), \
+ show_bio_op_flags(op_flags)
+
+#define show_bio_op(op) \
+ __print_symbolic(op, \
+ { REQ_OP_READ, "READ" }, \
+ { REQ_OP_WRITE, "WRITE" }, \
+ { REQ_OP_DISCARD, "DISCARD" }, \
+ { REQ_OP_SECURE_ERASE, "SECURE_ERASE" }, \
+ { REQ_OP_WRITE_SAME, "WRITE_SAME" })
#define show_bio_op_flags(flags) \
- __print_symbolic(F2FS_BIO_FLAG_MASK(flags), \
- { 0, "WRITE" }, \
- { REQ_RAHEAD, "READAHEAD" }, \
- { READ_SYNC, "READ_SYNC" }, \
- { WRITE_SYNC, "WRITE_SYNC" }, \
- { WRITE_FLUSH, "WRITE_FLUSH" }, \
- { WRITE_FUA, "WRITE_FUA" }, \
- { WRITE_FLUSH_FUA, "WRITE_FLUSH_FUA" })
+ __print_flags(F2FS_BIO_FLAG_MASK(flags), "|", \
+ { REQ_RAHEAD, "R" }, \
+ { REQ_SYNC, "S" }, \
+ { REQ_META, "M" }, \
+ { REQ_PRIO, "P" }, \
+ { REQ_PREFLUSH, "PF" }, \
+ { REQ_FUA, "FUA" })
-#define show_bio_extra(type) \
- __print_symbolic(F2FS_BIO_EXTRA_MASK(type), \
- { REQ_META, "(M)" }, \
- { REQ_PRIO, "(P)" }, \
- { REQ_META | REQ_PRIO, "(MP)" }, \
- { 0, " \b" })
+#define show_block_temp(temp) \
+ __print_symbolic(temp, \
+ { HOT, "HOT" }, \
+ { WARM, "WARM" }, \
+ { COLD, "COLD" })
#define show_data_type(type) \
__print_symbolic(type, \
@@ -109,13 +120,39 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
{ GC_CB, "Cost-Benefit" })
#define show_cpreason(type) \
- __print_symbolic(type, \
+ __print_flags(type, "|", \
{ CP_UMOUNT, "Umount" }, \
{ CP_FASTBOOT, "Fastboot" }, \
{ CP_SYNC, "Sync" }, \
{ CP_RECOVERY, "Recovery" }, \
- { CP_DISCARD, "Discard" })
+ { CP_DISCARD, "Discard" }, \
+ { CP_UMOUNT, "Umount" }, \
+ { CP_TRIMMED, "Trimmed" })
+#define show_fsync_cpreason(type) \
+ __print_symbolic(type, \
+ { CP_NO_NEEDED, "no needed" }, \
+ { CP_NON_REGULAR, "non regular" }, \
+ { CP_HARDLINK, "hardlink" }, \
+ { CP_SB_NEED_CP, "sb needs cp" }, \
+ { CP_WRONG_PINO, "wrong pino" }, \
+ { CP_NO_SPC_ROLL, "no space roll forward" }, \
+ { CP_NODE_NEED_CP, "node needs cp" }, \
+ { CP_FASTBOOT_MODE, "fastboot mode" }, \
+ { CP_SPEC_LOG_NUM, "log type is 2" }, \
+ { CP_RECOVER_DIR, "dir needs recovery" })
+
+#define show_shutdown_mode(type) \
+ __print_symbolic(type, \
+ { F2FS_GOING_DOWN_FULLSYNC, "full sync" }, \
+ { F2FS_GOING_DOWN_METASYNC, "meta sync" }, \
+ { F2FS_GOING_DOWN_NOSYNC, "no sync" }, \
+ { F2FS_GOING_DOWN_METAFLUSH, "meta flush" }, \
+ { F2FS_GOING_DOWN_NEED_FSCK, "need fsck" })
+
+struct f2fs_sb_info;
+struct f2fs_io_info;
+struct extent_info;
struct victim_sel_policy;
struct f2fs_map_blocks;
@@ -190,14 +227,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
TRACE_EVENT(f2fs_sync_file_exit,
- TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
+ TP_PROTO(struct inode *inode, int cp_reason, int datasync, int ret),
- TP_ARGS(inode, need_cp, datasync, ret),
+ TP_ARGS(inode, cp_reason, datasync, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
- __field(int, need_cp)
+ __field(int, cp_reason)
__field(int, datasync)
__field(int, ret)
),
@@ -205,15 +242,15 @@ TRACE_EVENT(f2fs_sync_file_exit,
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
- __entry->need_cp = need_cp;
+ __entry->cp_reason = cp_reason;
__entry->datasync = datasync;
__entry->ret = ret;
),
- TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, "
+ TP_printk("dev = (%d,%d), ino = %lu, cp_reason: %s, "
"datasync = %d, ret = %d",
show_dev_ino(__entry),
- __entry->need_cp ? "needed" : "not needed",
+ show_fsync_cpreason(__entry->cp_reason),
__entry->datasync,
__entry->ret)
);
@@ -237,7 +274,7 @@ TRACE_EVENT(f2fs_sync_fs,
),
TP_printk("dev = (%d,%d), superblock is %s, wait = %d",
- show_dev(__entry),
+ show_dev(__entry->dev),
__entry->dirty ? "dirty" : "not dirty",
__entry->wait)
);
@@ -307,6 +344,13 @@ DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit,
TP_ARGS(inode, ret)
);
+DEFINE_EVENT(f2fs__inode_exit, f2fs_drop_inode,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
DEFINE_EVENT(f2fs__inode, f2fs_truncate,
TP_PROTO(struct inode *inode),
@@ -493,6 +537,9 @@ TRACE_EVENT(f2fs_map_blocks,
__field(block_t, m_lblk)
__field(block_t, m_pblk)
__field(unsigned int, m_len)
+ __field(unsigned int, m_flags)
+ __field(int, m_seg_type)
+ __field(bool, m_may_create)
__field(int, ret)
),
@@ -502,28 +549,35 @@ TRACE_EVENT(f2fs_map_blocks,
__entry->m_lblk = map->m_lblk;
__entry->m_pblk = map->m_pblk;
__entry->m_len = map->m_len;
+ __entry->m_flags = map->m_flags;
+ __entry->m_seg_type = map->m_seg_type;
+ __entry->m_may_create = map->m_may_create;
__entry->ret = ret;
),
TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
- "start blkaddr = 0x%llx, len = 0x%llx, err = %d",
+ "start blkaddr = 0x%llx, len = 0x%llx, flags = %u,"
+ "seg_type = %d, may_create = %d, err = %d",
show_dev_ino(__entry),
(unsigned long long)__entry->m_lblk,
(unsigned long long)__entry->m_pblk,
(unsigned long long)__entry->m_len,
+ __entry->m_flags,
+ __entry->m_seg_type,
+ __entry->m_may_create,
__entry->ret)
);
TRACE_EVENT(f2fs_background_gc,
- TP_PROTO(struct super_block *sb, long wait_ms,
+ TP_PROTO(struct super_block *sb, unsigned int wait_ms,
unsigned int prefree, unsigned int free),
TP_ARGS(sb, wait_ms, prefree, free),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(long, wait_ms)
+ __field(unsigned int, wait_ms)
__field(unsigned int, prefree)
__field(unsigned int, free)
),
@@ -535,13 +589,120 @@ TRACE_EVENT(f2fs_background_gc,
__entry->free = free;
),
- TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
- show_dev(__entry),
+ TP_printk("dev = (%d,%d), wait_ms = %u, prefree = %u, free = %u",
+ show_dev(__entry->dev),
__entry->wait_ms,
__entry->prefree,
__entry->free)
);
+TRACE_EVENT(f2fs_gc_begin,
+
+ TP_PROTO(struct super_block *sb, bool sync, bool background,
+ long long dirty_nodes, long long dirty_dents,
+ long long dirty_imeta, unsigned int free_sec,
+ unsigned int free_seg, int reserved_seg,
+ unsigned int prefree_seg),
+
+ TP_ARGS(sb, sync, background, dirty_nodes, dirty_dents, dirty_imeta,
+ free_sec, free_seg, reserved_seg, prefree_seg),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(bool, sync)
+ __field(bool, background)
+ __field(long long, dirty_nodes)
+ __field(long long, dirty_dents)
+ __field(long long, dirty_imeta)
+ __field(unsigned int, free_sec)
+ __field(unsigned int, free_seg)
+ __field(int, reserved_seg)
+ __field(unsigned int, prefree_seg)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->sync = sync;
+ __entry->background = background;
+ __entry->dirty_nodes = dirty_nodes;
+ __entry->dirty_dents = dirty_dents;
+ __entry->dirty_imeta = dirty_imeta;
+ __entry->free_sec = free_sec;
+ __entry->free_seg = free_seg;
+ __entry->reserved_seg = reserved_seg;
+ __entry->prefree_seg = prefree_seg;
+ ),
+
+ TP_printk("dev = (%d,%d), sync = %d, background = %d, nodes = %lld, "
+ "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, "
+ "rsv_seg:%d, prefree_seg:%u",
+ show_dev(__entry->dev),
+ __entry->sync,
+ __entry->background,
+ __entry->dirty_nodes,
+ __entry->dirty_dents,
+ __entry->dirty_imeta,
+ __entry->free_sec,
+ __entry->free_seg,
+ __entry->reserved_seg,
+ __entry->prefree_seg)
+);
+
+TRACE_EVENT(f2fs_gc_end,
+
+ TP_PROTO(struct super_block *sb, int ret, int seg_freed,
+ int sec_freed, long long dirty_nodes,
+ long long dirty_dents, long long dirty_imeta,
+ unsigned int free_sec, unsigned int free_seg,
+ int reserved_seg, unsigned int prefree_seg),
+
+ TP_ARGS(sb, ret, seg_freed, sec_freed, dirty_nodes, dirty_dents,
+ dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, ret)
+ __field(int, seg_freed)
+ __field(int, sec_freed)
+ __field(long long, dirty_nodes)
+ __field(long long, dirty_dents)
+ __field(long long, dirty_imeta)
+ __field(unsigned int, free_sec)
+ __field(unsigned int, free_seg)
+ __field(int, reserved_seg)
+ __field(unsigned int, prefree_seg)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->ret = ret;
+ __entry->seg_freed = seg_freed;
+ __entry->sec_freed = sec_freed;
+ __entry->dirty_nodes = dirty_nodes;
+ __entry->dirty_dents = dirty_dents;
+ __entry->dirty_imeta = dirty_imeta;
+ __entry->free_sec = free_sec;
+ __entry->free_seg = free_seg;
+ __entry->reserved_seg = reserved_seg;
+ __entry->prefree_seg = prefree_seg;
+ ),
+
+ TP_printk("dev = (%d,%d), ret = %d, seg_freed = %d, sec_freed = %d, "
+ "nodes = %lld, dents = %lld, imeta = %lld, free_sec:%u, "
+ "free_seg:%u, rsv_seg:%d, prefree_seg:%u",
+ show_dev(__entry->dev),
+ __entry->ret,
+ __entry->seg_freed,
+ __entry->sec_freed,
+ __entry->dirty_nodes,
+ __entry->dirty_dents,
+ __entry->dirty_imeta,
+ __entry->free_sec,
+ __entry->free_seg,
+ __entry->reserved_seg,
+ __entry->prefree_seg)
+);
+
TRACE_EVENT(f2fs_get_victim,
TP_PROTO(struct super_block *sb, int type, int gc_type,
@@ -557,6 +718,7 @@ TRACE_EVENT(f2fs_get_victim,
__field(int, alloc_mode)
__field(int, gc_mode)
__field(unsigned int, victim)
+ __field(unsigned int, cost)
__field(unsigned int, ofs_unit)
__field(unsigned int, pre_victim)
__field(unsigned int, prefree)
@@ -570,26 +732,114 @@ TRACE_EVENT(f2fs_get_victim,
__entry->alloc_mode = p->alloc_mode;
__entry->gc_mode = p->gc_mode;
__entry->victim = p->min_segno;
+ __entry->cost = p->min_cost;
__entry->ofs_unit = p->ofs_unit;
__entry->pre_victim = pre_victim;
__entry->prefree = prefree;
__entry->free = free;
),
- TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u "
- "ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u",
- show_dev(__entry),
+ TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), "
+ "victim = %u, cost = %u, ofs_unit = %u, "
+ "pre_victim_secno = %d, prefree = %u, free = %u",
+ show_dev(__entry->dev),
show_data_type(__entry->type),
show_gc_type(__entry->gc_type),
show_alloc_mode(__entry->alloc_mode),
show_victim_policy(__entry->gc_mode),
__entry->victim,
+ __entry->cost,
__entry->ofs_unit,
(int)__entry->pre_victim,
__entry->prefree,
__entry->free)
);
+TRACE_EVENT(f2fs_lookup_start,
+
+ TP_PROTO(struct inode *dir, struct dentry *dentry, unsigned int flags),
+
+ TP_ARGS(dir, dentry, flags),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(const char *, name)
+ __field(unsigned int, flags)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dir->i_sb->s_dev;
+ __entry->ino = dir->i_ino;
+ __entry->name = dentry->d_name.name;
+ __entry->flags = flags;
+ ),
+
+ TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u",
+ show_dev_ino(__entry),
+ __entry->name,
+ __entry->flags)
+);
+
+TRACE_EVENT(f2fs_lookup_end,
+
+ TP_PROTO(struct inode *dir, struct dentry *dentry, nid_t ino,
+ int err),
+
+ TP_ARGS(dir, dentry, ino, err),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(const char *, name)
+ __field(nid_t, cino)
+ __field(int, err)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dir->i_sb->s_dev;
+ __entry->ino = dir->i_ino;
+ __entry->name = dentry->d_name.name;
+ __entry->cino = ino;
+ __entry->err = err;
+ ),
+
+ TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d",
+ show_dev_ino(__entry),
+ __entry->name,
+ __entry->cino,
+ __entry->err)
+);
+
+TRACE_EVENT(f2fs_readdir,
+
+ TP_PROTO(struct inode *dir, loff_t start_pos, loff_t end_pos, int err),
+
+ TP_ARGS(dir, start_pos, end_pos, err),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, start)
+ __field(loff_t, end)
+ __field(int, err)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dir->i_sb->s_dev;
+ __entry->ino = dir->i_ino;
+ __entry->start = start_pos;
+ __entry->end = end_pos;
+ __entry->err = err;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, start_pos:%llu, end_pos:%llu, err:%d",
+ show_dev_ino(__entry),
+ __entry->start,
+ __entry->end,
+ __entry->err)
+);
+
TRACE_EVENT(f2fs_fallocate,
TP_PROTO(struct inode *inode, int mode,
@@ -715,7 +965,7 @@ TRACE_EVENT(f2fs_reserve_new_blocks,
),
TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu",
- show_dev(__entry),
+ show_dev(__entry->dev),
(unsigned int)__entry->nid,
__entry->ofs_in_node,
(unsigned long long)__entry->count)
@@ -735,6 +985,7 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
__field(block_t, new_blkaddr)
__field(int, op)
__field(int, op_flags)
+ __field(int, temp)
__field(int, type)
),
@@ -746,16 +997,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
__entry->new_blkaddr = fio->new_blkaddr;
__entry->op = fio->op;
__entry->op_flags = fio->op_flags;
+ __entry->temp = fio->temp;
__entry->type = fio->type;
),
TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
- "oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s%s, type = %s",
+ "oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s_%s",
show_dev_ino(__entry),
(unsigned long)__entry->index,
(unsigned long long)__entry->old_blkaddr,
(unsigned long long)__entry->new_blkaddr,
- show_bio_type(__entry->op_flags),
+ show_bio_type(__entry->op, __entry->op_flags),
+ show_block_temp(__entry->temp),
show_block_type(__entry->type))
);
@@ -768,7 +1021,7 @@ DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
TP_CONDITION(page->mapping)
);
-DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_write,
TP_PROTO(struct page *page, struct f2fs_io_info *fio),
@@ -777,15 +1030,15 @@ DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
TP_CONDITION(page->mapping)
);
-DECLARE_EVENT_CLASS(f2fs__submit_bio,
+DECLARE_EVENT_CLASS(f2fs__bio,
- TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
- struct bio *bio),
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
- TP_ARGS(sb, fio, bio),
+ TP_ARGS(sb, type, bio),
TP_STRUCT__entry(
__field(dev_t, dev)
+ __field(dev_t, target)
__field(int, op)
__field(int, op_flags)
__field(int, type)
@@ -795,37 +1048,55 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
TP_fast_assign(
__entry->dev = sb->s_dev;
- __entry->op = fio->op;
- __entry->op_flags = fio->op_flags;
- __entry->type = fio->type;
+ __entry->target = bio->bi_bdev->bd_dev;
+ __entry->op = bio_op(bio);
+ __entry->op_flags = bio->bi_opf;
+ __entry->type = type;
__entry->sector = bio->bi_iter.bi_sector;
__entry->size = bio->bi_iter.bi_size;
),
- TP_printk("dev = (%d,%d), rw = %s%s, %s, sector = %lld, size = %u",
- show_dev(__entry),
- show_bio_type(__entry->op_flags),
+ TP_printk("dev = (%d,%d)/(%d,%d), rw = %s(%s), %s, sector = %lld, size = %u",
+ show_dev(__entry->target),
+ show_dev(__entry->dev),
+ show_bio_type(__entry->op, __entry->op_flags),
show_block_type(__entry->type),
(unsigned long long)__entry->sector,
__entry->size)
);
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_write_bio,
- TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
- struct bio *bio),
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
- TP_ARGS(sb, fio, bio),
+ TP_ARGS(sb, type, bio),
TP_CONDITION(bio)
);
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_read_bio,
- TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
- struct bio *bio),
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
- TP_ARGS(sb, fio, bio),
+ TP_ARGS(sb, type, bio),
+
+ TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_read_bio,
+
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+ TP_ARGS(sb, type, bio),
+
+ TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio,
+
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+ TP_ARGS(sb, type, bio),
TP_CONDITION(bio)
);
@@ -1084,16 +1355,16 @@ TRACE_EVENT(f2fs_write_checkpoint,
),
TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
- show_dev(__entry),
+ show_dev(__entry->dev),
show_cpreason(__entry->reason),
__entry->msg)
);
-TRACE_EVENT(f2fs_issue_discard,
+DECLARE_EVENT_CLASS(f2fs_discard,
- TP_PROTO(struct super_block *sb, block_t blkstart, block_t blklen),
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
- TP_ARGS(sb, blkstart, blklen),
+ TP_ARGS(dev, blkstart, blklen),
TP_STRUCT__entry(
__field(dev_t, dev)
@@ -1102,40 +1373,85 @@ TRACE_EVENT(f2fs_issue_discard,
),
TP_fast_assign(
- __entry->dev = sb->s_dev;
+ __entry->dev = dev->bd_dev;
__entry->blkstart = blkstart;
__entry->blklen = blklen;
),
TP_printk("dev = (%d,%d), blkstart = 0x%llx, blklen = 0x%llx",
- show_dev(__entry),
+ show_dev(__entry->dev),
(unsigned long long)__entry->blkstart,
(unsigned long long)__entry->blklen)
);
+DEFINE_EVENT(f2fs_discard, f2fs_queue_discard,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
+
+ TP_ARGS(dev, blkstart, blklen)
+);
+
+DEFINE_EVENT(f2fs_discard, f2fs_issue_discard,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
+
+ TP_ARGS(dev, blkstart, blklen)
+);
+
+DEFINE_EVENT(f2fs_discard, f2fs_remove_discard,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
+
+ TP_ARGS(dev, blkstart, blklen)
+);
+
+TRACE_EVENT(f2fs_issue_reset_zone,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart),
+
+ TP_ARGS(dev, blkstart),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(block_t, blkstart)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dev->bd_dev;
+ __entry->blkstart = blkstart;
+ ),
+
+ TP_printk("dev = (%d,%d), reset zone at block = 0x%llx",
+ show_dev(__entry->dev),
+ (unsigned long long)__entry->blkstart)
+);
+
TRACE_EVENT(f2fs_issue_flush,
- TP_PROTO(struct super_block *sb, unsigned int nobarrier,
- unsigned int flush_merge),
+ TP_PROTO(struct block_device *dev, unsigned int nobarrier,
+ unsigned int flush_merge, int ret),
- TP_ARGS(sb, nobarrier, flush_merge),
+ TP_ARGS(dev, nobarrier, flush_merge, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(unsigned int, nobarrier)
__field(unsigned int, flush_merge)
+ __field(int, ret)
),
TP_fast_assign(
- __entry->dev = sb->s_dev;
+ __entry->dev = dev->bd_dev;
__entry->nobarrier = nobarrier;
__entry->flush_merge = flush_merge;
+ __entry->ret = ret;
),
- TP_printk("dev = (%d,%d), %s %s",
- show_dev(__entry),
+ TP_printk("dev = (%d,%d), %s %s, ret = %d",
+ show_dev(__entry->dev),
__entry->nobarrier ? "skip (nobarrier)" : "issue",
- __entry->flush_merge ? " with flush_merge" : "")
+ __entry->flush_merge ? " with flush_merge" : "",
+ __entry->ret)
);
TRACE_EVENT(f2fs_lookup_extent_tree_start,
@@ -1248,7 +1564,7 @@ TRACE_EVENT(f2fs_shrink_extent_tree,
),
TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
- show_dev(__entry),
+ show_dev(__entry->dev),
__entry->node_cnt,
__entry->tree_cnt)
);
@@ -1295,7 +1611,7 @@ DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
),
TP_printk("dev = (%d,%d), %s, dirty count = %lld",
- show_dev(__entry),
+ show_dev(__entry->dev),
show_file_type(__entry->type),
__entry->count)
);
@@ -1314,6 +1630,30 @@ DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit,
TP_ARGS(sb, type, count)
);
+TRACE_EVENT(f2fs_shutdown,
+
+ TP_PROTO(struct f2fs_sb_info *sbi, unsigned int mode, int ret),
+
+ TP_ARGS(sbi, mode, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, mode)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sbi->sb->s_dev;
+ __entry->mode = mode;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), mode: %s, ret:%d",
+ show_dev(__entry->dev),
+ show_shutdown_mode(__entry->mode),
+ __entry->ret)
+);
+
#endif /* _TRACE_F2FS_H */
/* This part must be outside protection */
diff --git a/include/trace/events/gpu.h b/include/trace/events/gpu.h
new file mode 100644
index 0000000..7e15cdf
--- /dev/null
+++ b/include/trace/events/gpu.h
@@ -0,0 +1,143 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gpu
+
+#if !defined(_TRACE_GPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GPU_H
+
+#include <linux/tracepoint.h>
+#include <linux/time.h>
+
+#define show_secs_from_ns(ns) \
+ ({ \
+ u64 t = ns + (NSEC_PER_USEC / 2); \
+ do_div(t, NSEC_PER_SEC); \
+ t; \
+ })
+
+#define show_usecs_from_ns(ns) \
+ ({ \
+ u64 t = ns + (NSEC_PER_USEC / 2) ; \
+ u32 rem; \
+ do_div(t, NSEC_PER_USEC); \
+ rem = do_div(t, USEC_PER_SEC); \
+ })
+
+/*
+ * The gpu_sched_switch event indicates that a switch from one GPU context to
+ * another occurred on one of the GPU hardware blocks.
+ *
+ * The gpu_name argument identifies the GPU hardware block. Each independently
+ * scheduled GPU hardware block should have a different name. This may be used
+ * in different ways for different GPUs. For example, if a GPU includes
+ * multiple processing cores it may use names "GPU 0", "GPU 1", etc. If a GPU
+ * includes a separately scheduled 2D and 3D hardware block, it might use the
+ * names "2D" and "3D".
+ *
+ * The timestamp argument is the timestamp at which the switch occurred on the
+ * GPU. These timestamps are in units of nanoseconds and must use
+ * approximately the same time as sched_clock, though they need not come from
+ * any CPU clock. The timestamps for a single hardware block must be
+ * monotonically nondecreasing. This means that if a variable compensation
+ * offset is used to translate from some other clock to the sched_clock, then
+ * care must be taken when increasing that offset, and doing so may result in
+ * multiple events with the same timestamp.
+ *
+ * The next_ctx_id argument identifies the next context that was running on
+ * the GPU hardware block. A value of 0 indicates that the hardware block
+ * will be idle.
+ *
+ * The next_prio argument indicates the priority of the next context at the
+ * time of the event. The exact numeric values may mean different things for
+ * different GPUs, but they should follow the rule that lower values indicate a
+ * higher priority.
+ *
+ * The next_job_id argument identifies the batch of work that the GPU will be
+ * working on. This should correspond to a job_id that was previously traced
+ * as a gpu_job_enqueue event when the batch of work was created.
+ */
+TRACE_EVENT(gpu_sched_switch,
+
+ TP_PROTO(const char *gpu_name, u64 timestamp,
+ u32 next_ctx_id, s32 next_prio, u32 next_job_id),
+
+ TP_ARGS(gpu_name, timestamp, next_ctx_id, next_prio, next_job_id),
+
+ TP_STRUCT__entry(
+ __string( gpu_name, gpu_name )
+ __field( u64, timestamp )
+ __field( u32, next_ctx_id )
+ __field( s32, next_prio )
+ __field( u32, next_job_id )
+ ),
+
+ TP_fast_assign(
+ __assign_str(gpu_name, gpu_name);
+ __entry->timestamp = timestamp;
+ __entry->next_ctx_id = next_ctx_id;
+ __entry->next_prio = next_prio;
+ __entry->next_job_id = next_job_id;
+ ),
+
+ TP_printk("gpu_name=%s ts=%llu.%06lu next_ctx_id=%lu next_prio=%ld "
+ "next_job_id=%lu",
+ __get_str(gpu_name),
+ (unsigned long long)show_secs_from_ns(__entry->timestamp),
+ (unsigned long)show_usecs_from_ns(__entry->timestamp),
+ (unsigned long)__entry->next_ctx_id,
+ (long)__entry->next_prio,
+ (unsigned long)__entry->next_job_id)
+);
+
+/*
+ * The gpu_job_enqueue event indicates that a batch of work has been queued up
+ * to be processed by the GPU. This event is not intended to indicate that
+ * the batch of work has been submitted to the GPU hardware, but rather that
+ * it has been submitted to the GPU kernel driver.
+ *
+ * This event should be traced on the thread that initiated the work being
+ * queued. For example, if a batch of work is submitted to the kernel by a
+ * userland thread, the event should be traced on that thread.
+ *
+ * The ctx_id field identifies the GPU context in which the batch of work
+ * being queued is to be run.
+ *
+ * The job_id field identifies the batch of work being queued within the given
+ * GPU context. The first batch of work submitted for a given GPU context
+ * should have a job_id of 0, and each subsequent batch of work should
+ * increment the job_id by 1.
+ *
+ * The type field identifies the type of the job being enqueued. The job
+ * types may be different for different GPU hardware. For example, a GPU may
+ * differentiate between "2D", "3D", and "compute" jobs.
+ */
+TRACE_EVENT(gpu_job_enqueue,
+
+ TP_PROTO(u32 ctx_id, u32 job_id, const char *type),
+
+ TP_ARGS(ctx_id, job_id, type),
+
+ TP_STRUCT__entry(
+ __field( u32, ctx_id )
+ __field( u32, job_id )
+ __string( type, type )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx_id = ctx_id;
+ __entry->job_id = job_id;
+ __assign_str(type, type);
+ ),
+
+ TP_printk("ctx_id=%lu job_id=%lu type=%s",
+ (unsigned long)__entry->ctx_id,
+ (unsigned long)__entry->job_id,
+ __get_str(type))
+);
+
+#undef show_secs_from_ns
+#undef show_usecs_from_ns
+
+#endif /* _TRACE_GPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5a81ab4..61d41f2 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -81,12 +81,14 @@
#define __def_pageflag_names \
{1UL << PG_locked, "locked" }, \
+ {1UL << PG_waiters, "waiters" }, \
{1UL << PG_error, "error" }, \
{1UL << PG_referenced, "referenced" }, \
{1UL << PG_uptodate, "uptodate" }, \
{1UL << PG_dirty, "dirty" }, \
{1UL << PG_lru, "lru" }, \
{1UL << PG_active, "active" }, \
+ {1UL << PG_workingset, "workingset" }, \
{1UL << PG_slab, "slab" }, \
{1UL << PG_owner_priv_1, "owner_priv_1" }, \
{1UL << PG_arch_1, "arch_1" }, \
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 49cc7c3..89d009e 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -57,7 +57,7 @@ TRACE_EVENT(net_dev_start_xmit,
__entry->gso_type = skb_shinfo(skb)->gso_type;
),
- TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x",
+ TP_printk("dev=%s queue_mapping=%u skbaddr=%pK vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x",
__get_str(name), __entry->queue_mapping, __entry->skbaddr,
__entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci,
__entry->protocol, __entry->ip_summed, __entry->len,
@@ -90,7 +90,7 @@ TRACE_EVENT(net_dev_xmit,
__assign_str(name, dev->name);
),
- TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+ TP_printk("dev=%s skbaddr=%pK len=%u rc=%d",
__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
);
@@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS(net_dev_template,
__assign_str(name, skb->dev->name);
),
- TP_printk("dev=%s skbaddr=%p len=%u",
+ TP_printk("dev=%s skbaddr=%pK len=%u",
__get_str(name), __entry->skbaddr, __entry->len)
)
@@ -191,7 +191,7 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
__entry->gso_type = skb_shinfo(skb)->gso_type;
),
- TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
+ TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%pK vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
__get_str(name), __entry->napi_id, __entry->queue_mapping,
__entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto,
__entry->vlan_tci, __entry->protocol, __entry->ip_summed,
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 54e3aad..ec6f815 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -147,6 +147,38 @@ DEFINE_EVENT(cpu, cpu_frequency,
TP_ARGS(frequency, cpu_id)
);
+TRACE_EVENT(cpu_frequency_limits,
+
+ TP_PROTO(unsigned int max_freq, unsigned int min_freq,
+ unsigned int cpu_id),
+
+ TP_ARGS(max_freq, min_freq, cpu_id),
+
+ TP_STRUCT__entry(
+ __field( u32, min_freq )
+ __field( u32, max_freq )
+ __field( u32, cpu_id )
+ ),
+
+ TP_fast_assign(
+ __entry->min_freq = min_freq;
+ __entry->max_freq = max_freq;
+ __entry->cpu_id = cpu_id;
+ ),
+
+ TP_printk("min=%lu max=%lu cpu_id=%lu",
+ (unsigned long)__entry->min_freq,
+ (unsigned long)__entry->max_freq,
+ (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(cpu, cpu_capacity,
+
+ TP_PROTO(unsigned int capacity, unsigned int cpu_id),
+
+ TP_ARGS(capacity, cpu_id)
+);
+
TRACE_EVENT(device_pm_callback_start,
TP_PROTO(struct device *dev, const char *pm_ops, int event),
@@ -300,6 +332,25 @@ DEFINE_EVENT(clock, clock_set_rate,
TP_ARGS(name, state, cpu_id)
);
+TRACE_EVENT(clock_set_parent,
+
+ TP_PROTO(const char *name, const char *parent_name),
+
+ TP_ARGS(name, parent_name),
+
+ TP_STRUCT__entry(
+ __string( name, name )
+ __string( parent_name, parent_name )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, name);
+ __assign_str(parent_name, parent_name);
+ ),
+
+ TP_printk("%s parent=%s", __get_str(name), __get_str(parent_name))
+);
+
/*
* The power domain events are used for power domains transitions
*/
diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h
new file mode 100644
index 0000000..9c4eb33
--- /dev/null
+++ b/include/trace/events/preemptirq.h
@@ -0,0 +1,73 @@
+#ifdef CONFIG_PREEMPTIRQ_EVENTS
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM preemptirq
+
+#if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PREEMPTIRQ_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+#include <linux/string.h>
+#include <asm/sections.h>
+
+DECLARE_EVENT_CLASS(preemptirq_template,
+
+ TP_PROTO(unsigned long ip, unsigned long parent_ip),
+
+ TP_ARGS(ip, parent_ip),
+
+ TP_STRUCT__entry(
+ __field(u32, caller_offs)
+ __field(u32, parent_offs)
+ ),
+
+ TP_fast_assign(
+ __entry->caller_offs = (u32)(ip - (unsigned long)_stext);
+ __entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext);
+ ),
+
+ TP_printk("caller=%pF parent=%pF",
+ (void *)((unsigned long)(_stext) + __entry->caller_offs),
+ (void *)((unsigned long)(_stext) + __entry->parent_offs))
+);
+
+#ifndef CONFIG_PROVE_LOCKING
+DEFINE_EVENT(preemptirq_template, irq_disable,
+ TP_PROTO(unsigned long ip, unsigned long parent_ip),
+ TP_ARGS(ip, parent_ip));
+
+DEFINE_EVENT(preemptirq_template, irq_enable,
+ TP_PROTO(unsigned long ip, unsigned long parent_ip),
+ TP_ARGS(ip, parent_ip));
+#endif
+
+#ifdef CONFIG_DEBUG_PREEMPT
+DEFINE_EVENT(preemptirq_template, preempt_disable,
+ TP_PROTO(unsigned long ip, unsigned long parent_ip),
+ TP_ARGS(ip, parent_ip));
+
+DEFINE_EVENT(preemptirq_template, preempt_enable,
+ TP_PROTO(unsigned long ip, unsigned long parent_ip),
+ TP_ARGS(ip, parent_ip));
+#endif
+
+#endif /* _TRACE_PREEMPTIRQ_H */
+
+#include <trace/define_trace.h>
+
+#endif /* !CONFIG_PREEMPTIRQ_EVENTS */
+
+#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || defined(CONFIG_PROVE_LOCKING)
+#define trace_irq_enable(...)
+#define trace_irq_disable(...)
+#define trace_irq_enable_rcuidle(...)
+#define trace_irq_disable_rcuidle(...)
+#endif
+
+#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || !defined(CONFIG_DEBUG_PREEMPT)
+#define trace_preempt_enable(...)
+#define trace_preempt_disable(...)
+#define trace_preempt_enable_rcuidle(...)
+#define trace_preempt_disable_rcuidle(...)
+#endif
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9b90c57..e82c541 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -219,7 +219,7 @@ DECLARE_EVENT_CLASS(sched_process_template,
DEFINE_EVENT(sched_process_template, sched_process_free,
TP_PROTO(struct task_struct *p),
TP_ARGS(p));
-
+
/*
* Tracepoint for a task exiting:
@@ -374,6 +374,30 @@ DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
TP_ARGS(tsk, delay));
/*
+ * Tracepoint for recording the cause of uninterruptible sleep.
+ */
+TRACE_EVENT(sched_blocked_reason,
+
+ TP_PROTO(struct task_struct *tsk),
+
+ TP_ARGS(tsk),
+
+ TP_STRUCT__entry(
+ __field( pid_t, pid )
+ __field( void*, caller )
+ __field( bool, io_wait )
+ ),
+
+ TP_fast_assign(
+ __entry->pid = tsk->pid;
+ __entry->caller = (void*)get_wchan(tsk);
+ __entry->io_wait = tsk->in_iowait;
+ ),
+
+ TP_printk("pid=%d iowait=%d caller=%pS", __entry->pid, __entry->io_wait, __entry->caller)
+);
+
+/*
* Tracepoint for accounting runtime (time the task is executing
* on a CPU).
*/
@@ -562,6 +586,520 @@ TRACE_EVENT(sched_wake_idle_without_ipi,
TP_printk("cpu=%d", __entry->cpu)
);
+
+TRACE_EVENT(sched_contrib_scale_f,
+
+ TP_PROTO(int cpu, unsigned long freq_scale_factor,
+ unsigned long cpu_scale_factor),
+
+ TP_ARGS(cpu, freq_scale_factor, cpu_scale_factor),
+
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(unsigned long, freq_scale_factor)
+ __field(unsigned long, cpu_scale_factor)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->freq_scale_factor = freq_scale_factor;
+ __entry->cpu_scale_factor = cpu_scale_factor;
+ ),
+
+ TP_printk("cpu=%d freq_scale_factor=%lu cpu_scale_factor=%lu",
+ __entry->cpu, __entry->freq_scale_factor,
+ __entry->cpu_scale_factor)
+);
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SCHED_WALT
+extern unsigned int sysctl_sched_use_walt_cpu_util;
+extern unsigned int sysctl_sched_use_walt_task_util;
+extern unsigned int walt_ravg_window;
+extern bool walt_disabled;
+#endif
+
+/*
+ * Tracepoint for accounting sched averages for tasks.
+ */
+TRACE_EVENT(sched_load_avg_task,
+
+ TP_PROTO(struct task_struct *tsk, struct sched_avg *avg, void *_ravg),
+
+ TP_ARGS(tsk, avg, _ravg),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, cpu )
+ __field( unsigned long, load_avg )
+ __field( unsigned long, util_avg )
+ __field( unsigned long, util_avg_pelt )
+ __field( u32, util_avg_walt )
+ __field( u64, load_sum )
+ __field( u32, util_sum )
+ __field( u32, period_contrib )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->cpu = task_cpu(tsk);
+ __entry->load_avg = avg->load_avg;
+ __entry->util_avg = avg->util_avg;
+ __entry->load_sum = avg->load_sum;
+ __entry->util_sum = avg->util_sum;
+ __entry->period_contrib = avg->period_contrib;
+ __entry->util_avg_pelt = avg->util_avg;
+ __entry->util_avg_walt = 0;
+#ifdef CONFIG_SCHED_WALT
+ __entry->util_avg_walt = ((struct ravg*)_ravg)->demand /
+ (walt_ravg_window >> SCHED_CAPACITY_SHIFT);
+ if (!walt_disabled && sysctl_sched_use_walt_task_util)
+ __entry->util_avg = __entry->util_avg_walt;
+#endif
+ ),
+ TP_printk("comm=%s pid=%d cpu=%d load_avg=%lu util_avg=%lu "
+ "util_avg_pelt=%lu util_avg_walt=%u load_sum=%llu"
+ " util_sum=%u period_contrib=%u",
+ __entry->comm,
+ __entry->pid,
+ __entry->cpu,
+ __entry->load_avg,
+ __entry->util_avg,
+ __entry->util_avg_pelt,
+ __entry->util_avg_walt,
+ (u64)__entry->load_sum,
+ (u32)__entry->util_sum,
+ (u32)__entry->period_contrib)
+);
+
+/*
+ * Tracepoint for accounting sched averages for cpus.
+ */
+TRACE_EVENT(sched_load_avg_cpu,
+
+ TP_PROTO(int cpu, struct cfs_rq *cfs_rq),
+
+ TP_ARGS(cpu, cfs_rq),
+
+ TP_STRUCT__entry(
+ __field( int, cpu )
+ __field( unsigned long, load_avg )
+ __field( unsigned long, util_avg )
+ __field( unsigned long, util_avg_pelt )
+ __field( u32, util_avg_walt )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->load_avg = cfs_rq->avg.load_avg;
+ __entry->util_avg = cfs_rq->avg.util_avg;
+ __entry->util_avg_pelt = cfs_rq->avg.util_avg;
+ __entry->util_avg_walt = 0;
+#ifdef CONFIG_SCHED_WALT
+ __entry->util_avg_walt = div64_ul(cpu_rq(cpu)->prev_runnable_sum,
+ walt_ravg_window >> SCHED_CAPACITY_SHIFT);
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
+ __entry->util_avg = __entry->util_avg_walt;
+#endif
+ ),
+
+ TP_printk("cpu=%d load_avg=%lu util_avg=%lu "
+ "util_avg_pelt=%lu util_avg_walt=%u",
+ __entry->cpu, __entry->load_avg, __entry->util_avg,
+ __entry->util_avg_pelt, __entry->util_avg_walt)
+);
+
+/*
+ * Tracepoint for sched_tune_config settings
+ */
+TRACE_EVENT(sched_tune_config,
+
+ TP_PROTO(int boost),
+
+ TP_ARGS(boost),
+
+ TP_STRUCT__entry(
+ __field( int, boost )
+ ),
+
+ TP_fast_assign(
+ __entry->boost = boost;
+ ),
+
+ TP_printk("boost=%d ", __entry->boost)
+);
+
+/*
+ * Tracepoint for accounting CPU boosted utilization
+ */
+TRACE_EVENT(sched_boost_cpu,
+
+ TP_PROTO(int cpu, unsigned long util, long margin),
+
+ TP_ARGS(cpu, util, margin),
+
+ TP_STRUCT__entry(
+ __field( int, cpu )
+ __field( unsigned long, util )
+ __field(long, margin )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->util = util;
+ __entry->margin = margin;
+ ),
+
+ TP_printk("cpu=%d util=%lu margin=%ld",
+ __entry->cpu,
+ __entry->util,
+ __entry->margin)
+);
+
+/*
+ * Tracepoint for schedtune_tasks_update
+ */
+TRACE_EVENT(sched_tune_tasks_update,
+
+ TP_PROTO(struct task_struct *tsk, int cpu, int tasks, int idx,
+ int boost, int max_boost),
+
+ TP_ARGS(tsk, cpu, tasks, idx, boost, max_boost),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, cpu )
+ __field( int, tasks )
+ __field( int, idx )
+ __field( int, boost )
+ __field( int, max_boost )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->cpu = cpu;
+ __entry->tasks = tasks;
+ __entry->idx = idx;
+ __entry->boost = boost;
+ __entry->max_boost = max_boost;
+ ),
+
+ TP_printk("pid=%d comm=%s "
+ "cpu=%d tasks=%d idx=%d boost=%d max_boost=%d",
+ __entry->pid, __entry->comm,
+ __entry->cpu, __entry->tasks, __entry->idx,
+ __entry->boost, __entry->max_boost)
+);
+
+/*
+ * Tracepoint for schedtune_boostgroup_update
+ */
+TRACE_EVENT(sched_tune_boostgroup_update,
+
+ TP_PROTO(int cpu, int variation, int max_boost),
+
+ TP_ARGS(cpu, variation, max_boost),
+
+ TP_STRUCT__entry(
+ __field( int, cpu )
+ __field( int, variation )
+ __field( int, max_boost )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->variation = variation;
+ __entry->max_boost = max_boost;
+ ),
+
+ TP_printk("cpu=%d variation=%d max_boost=%d",
+ __entry->cpu, __entry->variation, __entry->max_boost)
+);
+
+/*
+ * Tracepoint for accounting task boosted utilization
+ */
+TRACE_EVENT(sched_boost_task,
+
+ TP_PROTO(struct task_struct *tsk, unsigned long util, long margin),
+
+ TP_ARGS(tsk, util, margin),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( unsigned long, util )
+ __field( long, margin )
+
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->util = util;
+ __entry->margin = margin;
+ ),
+
+ TP_printk("comm=%s pid=%d util=%lu margin=%ld",
+ __entry->comm, __entry->pid,
+ __entry->util,
+ __entry->margin)
+);
+
+/*
+ * Tracepoint for find_best_target
+ */
+TRACE_EVENT(sched_find_best_target,
+
+ TP_PROTO(struct task_struct *tsk, bool prefer_idle,
+ unsigned long min_util, int start_cpu,
+ int best_idle, int best_active, int target),
+
+ TP_ARGS(tsk, prefer_idle, min_util, start_cpu,
+ best_idle, best_active, target),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( unsigned long, min_util )
+ __field( bool, prefer_idle )
+ __field( int, start_cpu )
+ __field( int, best_idle )
+ __field( int, best_active )
+ __field( int, target )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->min_util = min_util;
+ __entry->prefer_idle = prefer_idle;
+ __entry->start_cpu = start_cpu;
+ __entry->best_idle = best_idle;
+ __entry->best_active = best_active;
+ __entry->target = target;
+ ),
+
+ TP_printk("pid=%d comm=%s prefer_idle=%d start_cpu=%d "
+ "best_idle=%d best_active=%d target=%d",
+ __entry->pid, __entry->comm,
+ __entry->prefer_idle, __entry->start_cpu,
+ __entry->best_idle, __entry->best_active,
+ __entry->target)
+);
+
+/*
+ * Tracepoint for schedtune_tasks_update
+ */
+TRACE_EVENT(sched_tune_filter,
+
+ TP_PROTO(int nrg_delta, int cap_delta,
+ int nrg_gain, int cap_gain,
+ int payoff, int region),
+
+ TP_ARGS(nrg_delta, cap_delta, nrg_gain, cap_gain, payoff, region),
+
+ TP_STRUCT__entry(
+ __field( int, nrg_delta )
+ __field( int, cap_delta )
+ __field( int, nrg_gain )
+ __field( int, cap_gain )
+ __field( int, payoff )
+ __field( int, region )
+ ),
+
+ TP_fast_assign(
+ __entry->nrg_delta = nrg_delta;
+ __entry->cap_delta = cap_delta;
+ __entry->nrg_gain = nrg_gain;
+ __entry->cap_gain = cap_gain;
+ __entry->payoff = payoff;
+ __entry->region = region;
+ ),
+
+ TP_printk("nrg_delta=%d cap_delta=%d nrg_gain=%d cap_gain=%d payoff=%d region=%d",
+ __entry->nrg_delta, __entry->cap_delta,
+ __entry->nrg_gain, __entry->cap_gain,
+ __entry->payoff, __entry->region)
+);
+
+/*
+ * Tracepoint for system overutilized flag
+ */
+TRACE_EVENT(sched_overutilized,
+
+ TP_PROTO(bool overutilized),
+
+ TP_ARGS(overutilized),
+
+ TP_STRUCT__entry(
+ __field( bool, overutilized )
+ ),
+
+ TP_fast_assign(
+ __entry->overutilized = overutilized;
+ ),
+
+ TP_printk("overutilized=%d",
+ __entry->overutilized ? 1 : 0)
+);
+#ifdef CONFIG_SCHED_WALT
+struct rq;
+
+TRACE_EVENT(walt_update_task_ravg,
+
+ TP_PROTO(struct task_struct *p, struct rq *rq, int evt,
+ u64 wallclock, u64 irqtime),
+
+ TP_ARGS(p, rq, evt, wallclock, irqtime),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( pid_t, cur_pid )
+ __field( u64, wallclock )
+ __field( u64, mark_start )
+ __field( u64, delta_m )
+ __field( u64, win_start )
+ __field( u64, delta )
+ __field( u64, irqtime )
+ __field( int, evt )
+ __field(unsigned int, demand )
+ __field(unsigned int, sum )
+ __field( int, cpu )
+ __field( u64, cs )
+ __field( u64, ps )
+ __field( u64, util )
+ __field( u32, curr_window )
+ __field( u32, prev_window )
+ __field( u64, nt_cs )
+ __field( u64, nt_ps )
+ __field( u32, active_windows )
+ ),
+
+ TP_fast_assign(
+ __entry->wallclock = wallclock;
+ __entry->win_start = rq->window_start;
+ __entry->delta = (wallclock - rq->window_start);
+ __entry->evt = evt;
+ __entry->cpu = rq->cpu;
+ __entry->cur_pid = rq->curr->pid;
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->mark_start = p->ravg.mark_start;
+ __entry->delta_m = (wallclock - p->ravg.mark_start);
+ __entry->demand = p->ravg.demand;
+ __entry->sum = p->ravg.sum;
+ __entry->irqtime = irqtime;
+ __entry->cs = rq->curr_runnable_sum;
+ __entry->ps = rq->prev_runnable_sum;
+ __entry->util = rq->prev_runnable_sum << SCHED_CAPACITY_SHIFT;
+ do_div(__entry->util, walt_ravg_window);
+ __entry->curr_window = p->ravg.curr_window;
+ __entry->prev_window = p->ravg.prev_window;
+ __entry->nt_cs = rq->nt_curr_runnable_sum;
+ __entry->nt_ps = rq->nt_prev_runnable_sum;
+ __entry->active_windows = p->ravg.active_windows;
+ ),
+
+ TP_printk("wc %llu ws %llu delta %llu event %d cpu %d cur_pid %d task %d (%s) ms %llu delta %llu demand %u sum %u irqtime %llu"
+ " cs %llu ps %llu util %llu cur_window %u prev_window %u active_wins %u"
+ , __entry->wallclock, __entry->win_start, __entry->delta,
+ __entry->evt, __entry->cpu, __entry->cur_pid,
+ __entry->pid, __entry->comm, __entry->mark_start,
+ __entry->delta_m, __entry->demand,
+ __entry->sum, __entry->irqtime,
+ __entry->cs, __entry->ps, __entry->util,
+ __entry->curr_window, __entry->prev_window,
+ __entry->active_windows
+ )
+);
+
+TRACE_EVENT(walt_update_history,
+
+ TP_PROTO(struct rq *rq, struct task_struct *p, u32 runtime, int samples,
+ int evt),
+
+ TP_ARGS(rq, p, runtime, samples, evt),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field(unsigned int, runtime )
+ __field( int, samples )
+ __field( int, evt )
+ __field( u64, demand )
+ __field( u64, walt_avg )
+ __field(unsigned int, pelt_avg )
+ __array( u32, hist, RAVG_HIST_SIZE_MAX)
+ __field( int, cpu )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->runtime = runtime;
+ __entry->samples = samples;
+ __entry->evt = evt;
+ __entry->demand = p->ravg.demand;
+ __entry->walt_avg = (__entry->demand << SCHED_CAPACITY_SHIFT);
+ __entry->walt_avg = div_u64(__entry->walt_avg,
+ walt_ravg_window);
+ __entry->pelt_avg = p->se.avg.util_avg;
+ memcpy(__entry->hist, p->ravg.sum_history,
+ RAVG_HIST_SIZE_MAX * sizeof(u32));
+ __entry->cpu = rq->cpu;
+ ),
+
+ TP_printk("%d (%s): runtime %u samples %d event %d demand %llu"
+ " walt %llu pelt %u (hist: %u %u %u %u %u) cpu %d",
+ __entry->pid, __entry->comm,
+ __entry->runtime, __entry->samples, __entry->evt,
+ __entry->demand,
+ __entry->walt_avg,
+ __entry->pelt_avg,
+ __entry->hist[0], __entry->hist[1],
+ __entry->hist[2], __entry->hist[3],
+ __entry->hist[4], __entry->cpu)
+);
+
+TRACE_EVENT(walt_migration_update_sum,
+
+ TP_PROTO(struct rq *rq, struct task_struct *p),
+
+ TP_ARGS(rq, p),
+
+ TP_STRUCT__entry(
+ __field(int, cpu )
+ __field(int, pid )
+ __field( u64, cs )
+ __field( u64, ps )
+ __field( s64, nt_cs )
+ __field( s64, nt_ps )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu_of(rq);
+ __entry->cs = rq->curr_runnable_sum;
+ __entry->ps = rq->prev_runnable_sum;
+ __entry->nt_cs = (s64)rq->nt_curr_runnable_sum;
+ __entry->nt_ps = (s64)rq->nt_prev_runnable_sum;
+ __entry->pid = p->pid;
+ ),
+
+ TP_printk("cpu %d: cs %llu ps %llu nt_cs %lld nt_ps %lld pid %d",
+ __entry->cpu, __entry->cs, __entry->ps,
+ __entry->nt_cs, __entry->nt_ps, __entry->pid)
+);
+#endif /* CONFIG_SCHED_WALT */
+
+#endif /* CONFIG_SMP */
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/include/trace/perf.h b/include/trace/perf.h
index 04fe68bb..14f127b6 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -34,7 +34,6 @@ perf_trace_##call(void *__data, proto) \
struct trace_event_call *event_call = __data; \
struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
struct trace_event_raw_##call *entry; \
- struct bpf_prog *prog = event_call->prog; \
struct pt_regs *__regs; \
u64 __count = 1; \
struct task_struct *__task = NULL; \
@@ -46,8 +45,9 @@ perf_trace_##call(void *__data, proto) \
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
\
head = this_cpu_ptr(event_call->perf_events); \
- if (!prog && __builtin_constant_p(!__task) && !__task && \
- hlist_empty(head)) \
+ if (!bpf_prog_array_valid(event_call) && \
+ __builtin_constant_p(!__task) && !__task && \
+ hlist_empty(head)) \
return; \
\
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 67d632f..2d078c2 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -92,4 +92,6 @@
#define SO_CNX_ADVICE 53
+#define SO_COOKIE 57
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 9b1462e..9fb4a57 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -730,9 +730,13 @@ __SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
#define __NR_pkey_free 290
__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
#undef __NR_syscalls
-#define __NR_syscalls 291
+#define __NR_syscalls 435
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index 41420e3..0631c50 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -33,11 +33,68 @@ enum {
BINDER_TYPE_HANDLE = B_PACK_CHARS('s', 'h', '*', B_TYPE_LARGE),
BINDER_TYPE_WEAK_HANDLE = B_PACK_CHARS('w', 'h', '*', B_TYPE_LARGE),
BINDER_TYPE_FD = B_PACK_CHARS('f', 'd', '*', B_TYPE_LARGE),
+ BINDER_TYPE_FDA = B_PACK_CHARS('f', 'd', 'a', B_TYPE_LARGE),
+ BINDER_TYPE_PTR = B_PACK_CHARS('p', 't', '*', B_TYPE_LARGE),
};
-enum {
+/**
+ * enum flat_binder_object_shifts: shift values for flat_binder_object_flags
+ * @FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT: shift for getting scheduler policy.
+ *
+ */
+enum flat_binder_object_shifts {
+ FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT = 9,
+};
+
+/**
+ * enum flat_binder_object_flags - flags for use in flat_binder_object.flags
+ */
+enum flat_binder_object_flags {
+ /**
+ * @FLAT_BINDER_FLAG_PRIORITY_MASK: bit-mask for min scheduler priority
+ *
+ * These bits can be used to set the minimum scheduler priority
+ * at which transactions into this node should run. Valid values
+ * in these bits depend on the scheduler policy encoded in
+ * @FLAT_BINDER_FLAG_SCHED_POLICY_MASK.
+ *
+ * For SCHED_NORMAL/SCHED_BATCH, the valid range is between [-20..19]
+ * For SCHED_FIFO/SCHED_RR, the value can run between [1..99]
+ */
FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff,
+ /**
+ * @FLAT_BINDER_FLAG_ACCEPTS_FDS: whether the node accepts fds.
+ */
FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100,
+ /**
+ * @FLAT_BINDER_FLAG_SCHED_POLICY_MASK: bit-mask for scheduling policy
+ *
+ * These two bits can be used to set the min scheduling policy at which
+ * transactions on this node should run. These match the UAPI
+ * scheduler policy values, eg:
+ * 00b: SCHED_NORMAL
+ * 01b: SCHED_FIFO
+ * 10b: SCHED_RR
+ * 11b: SCHED_BATCH
+ */
+ FLAT_BINDER_FLAG_SCHED_POLICY_MASK =
+ 3U << FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT,
+
+ /**
+ * @FLAT_BINDER_FLAG_INHERIT_RT: whether the node inherits RT policy
+ *
+ * Only when set, calls into this node will inherit a real-time
+ * scheduling policy from the caller (for synchronous transactions).
+ */
+ FLAT_BINDER_FLAG_INHERIT_RT = 0x800,
+
+ /**
+ * @FLAT_BINDER_FLAG_TXN_SECURITY_CTX: request security contexts
+ *
+ * Only when set, causes senders to include their security
+ * context
+ */
+ FLAT_BINDER_FLAG_TXN_SECURITY_CTX = 0x1000,
};
#ifdef BINDER_IPC_32BIT
@@ -48,6 +105,14 @@ typedef __u64 binder_size_t;
typedef __u64 binder_uintptr_t;
#endif
+/**
+ * struct binder_object_header - header shared by all binder metadata objects.
+ * @type: type of the object
+ */
+struct binder_object_header {
+ __u32 type;
+};
+
/*
* This is the flattened representation of a Binder object for transfer
* between processes. The 'offsets' supplied as part of a binder transaction
@@ -56,9 +121,8 @@ typedef __u64 binder_uintptr_t;
* between processes.
*/
struct flat_binder_object {
- /* 8 bytes for large_flat_header. */
- __u32 type;
- __u32 flags;
+ struct binder_object_header hdr;
+ __u32 flags;
/* 8 bytes of data. */
union {
@@ -70,6 +134,86 @@ struct flat_binder_object {
binder_uintptr_t cookie;
};
+/**
+ * struct binder_fd_object - describes a filedescriptor to be fixed up.
+ * @hdr: common header structure
+ * @pad_flags: padding to remain compatible with old userspace code
+ * @pad_binder: padding to remain compatible with old userspace code
+ * @fd: file descriptor
+ * @cookie: opaque data, used by user-space
+ */
+struct binder_fd_object {
+ struct binder_object_header hdr;
+ __u32 pad_flags;
+ union {
+ binder_uintptr_t pad_binder;
+ __u32 fd;
+ };
+
+ binder_uintptr_t cookie;
+};
+
+/* struct binder_buffer_object - object describing a userspace buffer
+ * @hdr: common header structure
+ * @flags: one or more BINDER_BUFFER_* flags
+ * @buffer: address of the buffer
+ * @length: length of the buffer
+ * @parent: index in offset array pointing to parent buffer
+ * @parent_offset: offset in @parent pointing to this buffer
+ *
+ * A binder_buffer object represents an object that the
+ * binder kernel driver can copy verbatim to the target
+ * address space. A buffer itself may be pointed to from
+ * within another buffer, meaning that the pointer inside
+ * that other buffer needs to be fixed up as well. This
+ * can be done by setting the BINDER_BUFFER_FLAG_HAS_PARENT
+ * flag in @flags, by setting @parent buffer to the index
+ * in the offset array pointing to the parent binder_buffer_object,
+ * and by setting @parent_offset to the offset in the parent buffer
+ * at which the pointer to this buffer is located.
+ */
+struct binder_buffer_object {
+ struct binder_object_header hdr;
+ __u32 flags;
+ binder_uintptr_t buffer;
+ binder_size_t length;
+ binder_size_t parent;
+ binder_size_t parent_offset;
+};
+
+enum {
+ BINDER_BUFFER_FLAG_HAS_PARENT = 0x01,
+};
+
+/* struct binder_fd_array_object - object describing an array of fds in a buffer
+ * @hdr: common header structure
+ * @pad: padding to ensure correct alignment
+ * @num_fds: number of file descriptors in the buffer
+ * @parent: index in offset array to buffer holding the fd array
+ * @parent_offset: start offset of fd array in the buffer
+ *
+ * A binder_fd_array object represents an array of file
+ * descriptors embedded in a binder_buffer_object. It is
+ * different from a regular binder_buffer_object because it
+ * describes a list of file descriptors to fix up, not an opaque
+ * blob of memory, and hence the kernel needs to treat it differently.
+ *
+ * An example of how this would be used is with Android's
+ * native_handle_t object, which is a struct with a list of integers
+ * and a list of file descriptors. The native_handle_t struct itself
+ * will be represented by a struct binder_buffer_objct, whereas the
+ * embedded list of file descriptors is represented by a
+ * struct binder_fd_array_object with that binder_buffer_object as
+ * a parent.
+ */
+struct binder_fd_array_object {
+ struct binder_object_header hdr;
+ __u32 pad;
+ binder_size_t num_fds;
+ binder_size_t parent;
+ binder_size_t parent_offset;
+};
+
/*
* On 64-bit platforms where user code may run in 32-bits the driver must
* translate the buffer (and local binder) addresses appropriately.
@@ -97,6 +241,28 @@ struct binder_version {
#define BINDER_CURRENT_PROTOCOL_VERSION 8
#endif
+/*
+ * Use with BINDER_GET_NODE_DEBUG_INFO, driver reads ptr, writes to all fields.
+ * Set ptr to NULL for the first call to get the info for the first node, and
+ * then repeat the call passing the previously returned value to get the next
+ * nodes. ptr will be 0 when there are no more nodes.
+ */
+struct binder_node_debug_info {
+ binder_uintptr_t ptr;
+ binder_uintptr_t cookie;
+ __u32 has_strong_ref;
+ __u32 has_weak_ref;
+};
+
+struct binder_node_info_for_ref {
+ __u32 handle;
+ __u32 strong_count;
+ __u32 weak_count;
+ __u32 reserved1;
+ __u32 reserved2;
+ __u32 reserved3;
+};
+
#define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read)
#define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64)
#define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32)
@@ -104,6 +270,9 @@ struct binder_version {
#define BINDER_SET_CONTEXT_MGR _IOW('b', 7, __s32)
#define BINDER_THREAD_EXIT _IOW('b', 8, __s32)
#define BINDER_VERSION _IOWR('b', 9, struct binder_version)
+#define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info)
+#define BINDER_GET_NODE_INFO_FOR_REF _IOWR('b', 12, struct binder_node_info_for_ref)
+#define BINDER_SET_CONTEXT_MGR_EXT _IOW('b', 13, struct flat_binder_object)
/*
* NOTE: Two special error codes you should check for when calling
@@ -162,6 +331,16 @@ struct binder_transaction_data {
} data;
};
+struct binder_transaction_data_secctx {
+ struct binder_transaction_data transaction_data;
+ binder_uintptr_t secctx;
+};
+
+struct binder_transaction_data_sg {
+ struct binder_transaction_data transaction_data;
+ binder_size_t buffers_size;
+};
+
struct binder_ptr_cookie {
binder_uintptr_t ptr;
binder_uintptr_t cookie;
@@ -192,6 +371,11 @@ enum binder_driver_return_protocol {
BR_OK = _IO('r', 1),
/* No parameters! */
+ BR_TRANSACTION_SEC_CTX = _IOR('r', 2,
+ struct binder_transaction_data_secctx),
+ /*
+ * binder_transaction_data_secctx: the received command.
+ */
BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data),
BR_REPLY = _IOR('r', 3, struct binder_transaction_data),
/*
@@ -346,6 +530,12 @@ enum binder_driver_command_protocol {
/*
* void *: cookie
*/
+
+ BC_TRANSACTION_SG = _IOW('c', 17, struct binder_transaction_data_sg),
+ BC_REPLY_SG = _IOW('c', 18, struct binder_transaction_data_sg),
+ /*
+ * binder_transaction_data_sg: the sent command.
+ */
};
#endif /* _UAPI_LINUX_BINDER_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f09c70b..67d7d77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -73,6 +73,8 @@ enum bpf_cmd {
BPF_PROG_LOAD,
BPF_OBJ_PIN,
BPF_OBJ_GET,
+ BPF_PROG_ATTACH,
+ BPF_PROG_DETACH,
};
enum bpf_map_type {
@@ -96,8 +98,59 @@ enum bpf_prog_type {
BPF_PROG_TYPE_TRACEPOINT,
BPF_PROG_TYPE_XDP,
BPF_PROG_TYPE_PERF_EVENT,
+ BPF_PROG_TYPE_CGROUP_SKB,
};
+enum bpf_attach_type {
+ BPF_CGROUP_INET_INGRESS,
+ BPF_CGROUP_INET_EGRESS,
+ __MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ * cgrp2 (OVERRIDE prog C) ->
+ * cgrp3 (MULTI prog D) ->
+ * cgrp4 (OVERRIDE prog E) ->
+ * cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+#define BPF_F_ALLOW_MULTI (1U << 1)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -107,6 +160,10 @@ enum bpf_prog_type {
#define BPF_F_NO_PREALLOC (1U << 0)
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY (1U << 3)
+#define BPF_F_WRONLY (1U << 4)
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
@@ -140,6 +197,14 @@ union bpf_attr {
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
+ __u32 file_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ __u32 target_fd; /* container object to attach to */
+ __u32 attach_bpf_fd; /* eBPF program to attach */
+ __u32 attach_type;
+ __u32 attach_flags;
};
} __attribute__((aligned(8)));
@@ -426,6 +491,67 @@ enum bpf_func_id {
*/
BPF_FUNC_set_hash_invalid,
+ /**
+ * int bpf_get_numa_node_id()
+ * Return: Id of current NUMA node.
+ */
+ BPF_FUNC_get_numa_node_id,
+
+ /**
+ * int bpf_skb_change_head()
+ * Grows headroom of skb and adjusts MAC header offset accordingly.
+ * Will extends/reallocae as required automatically.
+ * May change skb data pointer and will thus invalidate any check
+ * performed for direct packet access.
+ * @skb: pointer to skb
+ * @len: length of header to be pushed in front
+ * @flags: Flags (unused for now)
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_head,
+
+ /**
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ * Adjust the xdp_md.data by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data
+ * Return: 0 on success or negative on error
+ */
+ BPF_FUNC_xdp_adjust_head,
+
+ /**
+ * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * Copy a NUL terminated string from unsafe address. In case the string
+ * length is smaller than size, the target is not padded with further NUL
+ * bytes. In case the string length is larger than size, just count-1
+ * bytes are copied and the last byte is set to NUL.
+ * @dst: destination address
+ * @size: maximum number of bytes to copy, including the trailing NUL
+ * @unsafe_ptr: unsafe address
+ * Return:
+ * > 0 length of the string including the trailing NUL on success
+ * < 0 error
+ */
+ BPF_FUNC_probe_read_str,
+
+ /**
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ * Get the cookie for the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ * field is missing inside sk_buff
+ */
+ BPF_FUNC_get_socket_cookie,
+
+ /**
+ * u32 bpf_get_socket_uid(skb)
+ * Get the owner uid of the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: uid of the socket owner on success or 0 if the socket pointer
+ * inside sk_buff is NULL
+ */
+ BPF_FUNC_get_socket_uid,
+
__BPF_FUNC_MAX_ID,
};
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index beed138..f85ed3a 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -43,6 +43,27 @@
/* (1U << 31) is reserved for signed error codes */
/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWF_WRITE_LIFE_NOT_SET 0
+#define RWH_WRITE_LIFE_NONE 1
+#define RWH_WRITE_LIFE_SHORT 2
+#define RWH_WRITE_LIFE_MEDIUM 3
+#define RWH_WRITE_LIFE_LONG 4
+#define RWH_WRITE_LIFE_EXTREME 5
+
+/*
* Types of directory notifications that may be requested.
*/
#define DN_ACCESS 0x00000001 /* File accessed */
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 14404b3..bbf02a6 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -29,6 +29,11 @@ struct fib_rule_hdr {
__u32 flags;
};
+struct fib_rule_uid_range {
+ __u32 start;
+ __u32 end;
+};
+
enum {
FRA_UNSPEC,
FRA_DST, /* destination address */
@@ -51,6 +56,7 @@ enum {
FRA_OIFNAME,
FRA_PAD,
FRA_L3MDEV, /* iif or oif is l3mdev goto its table */
+ FRA_UID_RANGE, /* UID range */
__FRA_MAX
};
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 4749955..af8da91 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -237,6 +237,8 @@ struct fsxattr {
#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range)
#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range)
+#define FIDTRIM _IOWR('f', 128, struct fstrim_range) /* Deep discard trim */
+
#define FS_IOC_GETFLAGS _IOR('f', 1, long)
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
@@ -255,18 +257,51 @@ struct fsxattr {
/* Policy provided via an ioctl on the topmost directory */
#define FS_KEY_DESCRIPTOR_SIZE 8
+#define FS_POLICY_FLAGS_PAD_4 0x00
+#define FS_POLICY_FLAGS_PAD_8 0x01
+#define FS_POLICY_FLAGS_PAD_16 0x02
+#define FS_POLICY_FLAGS_PAD_32 0x03
+#define FS_POLICY_FLAGS_PAD_MASK 0x03
+#define FS_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */
+#define FS_POLICY_FLAGS_VALID 0x07
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID 0
+#define FS_ENCRYPTION_MODE_AES_256_XTS 1
+#define FS_ENCRYPTION_MODE_AES_256_GCM 2
+#define FS_ENCRYPTION_MODE_AES_256_CBC 3
+#define FS_ENCRYPTION_MODE_AES_256_CTS 4
+#define FS_ENCRYPTION_MODE_AES_128_CBC 5
+#define FS_ENCRYPTION_MODE_AES_128_CTS 6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_ADIANTUM 9
+
struct fscrypt_policy {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
-} __packed;
+};
#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX "fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE 8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE 64
+
+struct fscrypt_key {
+ __u32 mode;
+ __u8 raw[FS_MAX_KEY_SIZE];
+ __u32 size;
+};
+
/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
*
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 8ca749a..54d9bbb 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -377,6 +377,7 @@ enum fuse_opcode {
FUSE_READDIRPLUS = 44,
FUSE_RENAME2 = 45,
FUSE_LSEEK = 46,
+ FUSE_CANONICAL_PATH= 2016,
/* CUSE specific operations */
CUSE_INIT = 4096,
diff --git a/include/uapi/linux/hw_breakpoint.h b/include/uapi/linux/hw_breakpoint.h
index b04000a..2b65efd 100644
--- a/include/uapi/linux/hw_breakpoint.h
+++ b/include/uapi/linux/hw_breakpoint.h
@@ -4,7 +4,11 @@
enum {
HW_BREAKPOINT_LEN_1 = 1,
HW_BREAKPOINT_LEN_2 = 2,
+ HW_BREAKPOINT_LEN_3 = 3,
HW_BREAKPOINT_LEN_4 = 4,
+ HW_BREAKPOINT_LEN_5 = 5,
+ HW_BREAKPOINT_LEN_6 = 6,
+ HW_BREAKPOINT_LEN_7 = 7,
HW_BREAKPOINT_LEN_8 = 8,
};
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index b4fba66..a39a43b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -444,6 +444,16 @@ enum {
#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
+/* XFRM section */
+enum {
+ IFLA_XFRM_UNSPEC,
+ IFLA_XFRM_LINK,
+ IFLA_XFRM_IF_ID,
+ __IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
enum macsec_validation_type {
MACSEC_VALIDATE_DISABLED = 0,
MACSEC_VALIDATE_CHECK = 1,
diff --git a/include/uapi/linux/if_pppolac.h b/include/uapi/linux/if_pppolac.h
new file mode 100644
index 0000000..b7eb8153
--- /dev/null
+++ b/include/uapi/linux/if_pppolac.h
@@ -0,0 +1,33 @@
+/* include/uapi/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOLAC_H
+#define _UAPI_LINUX_IF_PPPOLAC_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppolac {
+ sa_family_t sa_family; /* AF_PPPOX */
+ unsigned int sa_protocol; /* PX_PROTO_OLAC */
+ int udp_socket;
+ struct __attribute__((packed)) {
+ __u16 tunnel, session;
+ } local, remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOLAC_H */
diff --git a/include/uapi/linux/if_pppopns.h b/include/uapi/linux/if_pppopns.h
new file mode 100644
index 0000000..a392b52
--- /dev/null
+++ b/include/uapi/linux/if_pppopns.h
@@ -0,0 +1,32 @@
+/* include/uapi/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOPNS_H
+#define _UAPI_LINUX_IF_PPPOPNS_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppopns {
+ sa_family_t sa_family; /* AF_PPPOX */
+ unsigned int sa_protocol; /* PX_PROTO_OPNS */
+ int tcp_socket;
+ __u16 local;
+ __u16 remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOPNS_H */
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index d37bbb1..6aad18a 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -24,6 +24,8 @@
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_pppol2tp.h>
+#include <linux/if_pppolac.h>
+#include <linux/if_pppopns.h>
#include <linux/in.h>
#include <linux/in6.h>
@@ -59,7 +61,9 @@ struct pptp_addr {
#define PX_PROTO_OE 0 /* Currently just PPPoE */
#define PX_PROTO_OL2TP 1 /* Now L2TP also */
#define PX_PROTO_PPTP 2
-#define PX_MAX_PROTO 3
+#define PX_PROTO_OLAC 3
+#define PX_PROTO_OPNS 4
+#define PX_MAX_PROTO 5
struct sockaddr_pppox {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index e794f7b..f561c0e 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -61,9 +61,14 @@ struct input_id {
* Note that input core does not clamp reported values to the
* [minimum, maximum] limits, such task is left to userspace.
*
- * Resolution for main axes (ABS_X, ABS_Y, ABS_Z) is reported in
- * units per millimeter (units/mm), resolution for rotational axes
- * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian.
+ * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z)
+ * is reported in units per millimeter (units/mm), resolution
+ * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported
+ * in units per radian.
+ * When INPUT_PROP_ACCELEROMETER is set the resolution changes.
+ * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in
+ * in units per g (units/g) and in units per degree per second
+ * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ).
*/
struct input_absinfo {
__s32 value;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 8c27723..c462f1d 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -164,6 +164,7 @@ enum {
DEVCONF_ACCEPT_DAD,
DEVCONF_FORCE_TLLAO,
DEVCONF_NDISC_NOTIFY,
+ DEVCONF_ACCEPT_RA_RT_TABLE,
DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
DEVCONF_SUPPRESS_FRAG_NDISC,
@@ -178,6 +179,12 @@ enum {
DEVCONF_DROP_UNSOLICITED_NA,
DEVCONF_KEEP_ADDR_ON_DOWN,
DEVCONF_RTR_SOLICIT_MAX_INTERVAL,
+ DEVCONF_SEG6_ENABLED,
+ DEVCONF_SEG6_REQUIRE_HMAC,
+ DEVCONF_ENHANCED_DAD,
+ DEVCONF_ADDR_GEN_MODE,
+ DEVCONF_DISABLE_POLICY,
+ DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h
index 574e22e..33b826b 100644
--- a/include/uapi/linux/kcov.h
+++ b/include/uapi/linux/kcov.h
@@ -7,4 +7,28 @@
#define KCOV_ENABLE _IO('c', 100)
#define KCOV_DISABLE _IO('c', 101)
+enum {
+ /*
+ * Tracing coverage collection mode.
+ * Covered PCs are collected in a per-task buffer.
+ * In new KCOV version the mode is chosen by calling
+ * ioctl(fd, KCOV_ENABLE, mode). In older versions the mode argument
+ * was supposed to be 0 in such a call. So, for reasons of backward
+ * compatibility, we have chosen the value KCOV_TRACE_PC to be 0.
+ */
+ KCOV_TRACE_PC = 0,
+ /* Collecting comparison operands mode. */
+ KCOV_TRACE_CMP = 1,
+};
+
+/*
+ * The format for the types of collected comparisons.
+ *
+ * Bit 0 shows whether one of the arguments is a compile-time constant.
+ * Bits 1 & 2 contain log2 of the argument size, up to 8 bytes.
+ */
+#define KCOV_CMP_CONST (1 << 0)
+#define KCOV_CMP_SIZE(n) ((n) << 1)
+#define KCOV_CMP_MASK KCOV_CMP_SIZE(3)
+
#endif /* _LINUX_KCOV_IOCTLS_H */
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index c8125ec..2bb48ed 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -24,6 +24,16 @@ enum {
LO_FLAGS_DIRECT_IO = 16,
};
+/* LO_FLAGS that can be set using LOOP_SET_STATUS(64) */
+#define LOOP_SET_STATUS_SETTABLE_FLAGS (LO_FLAGS_AUTOCLEAR | LO_FLAGS_PARTSCAN)
+
+/* LO_FLAGS that can be cleared using LOOP_SET_STATUS(64) */
+#define LOOP_SET_STATUS_CLEARABLE_FLAGS (LO_FLAGS_AUTOCLEAR)
+
+/* LO_FLAGS that can be set using LOOP_CONFIGURE */
+#define LOOP_CONFIGURE_SETTABLE_FLAGS (LO_FLAGS_READ_ONLY | LO_FLAGS_AUTOCLEAR \
+ | LO_FLAGS_PARTSCAN | LO_FLAGS_DIRECT_IO)
+
#include <asm/posix_types.h> /* for __kernel_old_dev_t */
#include <linux/types.h> /* for __u64 */
@@ -36,7 +46,7 @@ struct loop_info {
int lo_offset;
int lo_encrypt_type;
int lo_encrypt_key_size; /* ioctl w/o */
- int lo_flags; /* ioctl r/o */
+ int lo_flags;
char lo_name[LO_NAME_SIZE];
unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
unsigned long lo_init[2];
@@ -52,13 +62,29 @@ struct loop_info64 {
__u32 lo_number; /* ioctl r/o */
__u32 lo_encrypt_type;
__u32 lo_encrypt_key_size; /* ioctl w/o */
- __u32 lo_flags; /* ioctl r/o */
+ __u32 lo_flags;
__u8 lo_file_name[LO_NAME_SIZE];
__u8 lo_crypt_name[LO_NAME_SIZE];
__u8 lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
__u64 lo_init[2];
};
+/**
+ * struct loop_config - Complete configuration for a loop device.
+ * @fd: fd of the file to be used as a backing file for the loop device.
+ * @block_size: block size to use; ignored if 0.
+ * @info: struct loop_info64 to configure the loop device with.
+ *
+ * This structure is used with the LOOP_CONFIGURE ioctl, and can be used to
+ * atomically setup and configure all loop device parameters at once.
+ */
+struct loop_config {
+ __u32 fd;
+ __u32 block_size;
+ struct loop_info64 info;
+ __u64 __reserved[8];
+};
+
/*
* Loop filter types
*/
@@ -88,6 +114,8 @@ struct loop_info64 {
#define LOOP_CHANGE_FD 0x4C06
#define LOOP_SET_CAPACITY 0x4C07
#define LOOP_SET_DIRECT_IO 0x4C08
+#define LOOP_SET_BLOCK_SIZE 0x4C09
+#define LOOP_CONFIGURE 0x4C0A
/* /dev/loop-control interface */
#define LOOP_CTL_ADD 0x4C80
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 9bd5594..bd01769 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -53,6 +53,8 @@
#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
+#define SDCARDFS_SUPER_MAGIC 0x5dca2df5
+
#define SMB_SUPER_MAGIC 0x517B
#define CGROUP_SUPER_MAGIC 0x27e0eb
#define CGROUP2_SUPER_MAGIC 0x63677270
diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h
index 208ae93..faaa28b 100644
--- a/include/uapi/linux/netfilter/xt_IDLETIMER.h
+++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h
@@ -4,6 +4,7 @@
* Header file for Xtables timer target module.
*
* Copyright (C) 2004, 2010 Nokia Corporation
+ *
* Written by Timo Teras <ext-timo.teras@nokia.com>
*
* Converted to x_tables and forward-ported to 2.6.34
@@ -32,12 +33,19 @@
#include <linux/types.h>
#define MAX_IDLETIMER_LABEL_SIZE 28
+#define NLMSG_MAX_SIZE 64
+
+#define NL_EVENT_TYPE_INACTIVE 0
+#define NL_EVENT_TYPE_ACTIVE 1
struct idletimer_tg_info {
__u32 timeout;
char label[MAX_IDLETIMER_LABEL_SIZE];
+ /* Use netlink messages for notification in addition to sysfs */
+ __u8 send_nl_msg;
+
/* for kernel module internal use only */
struct idletimer_tg *timer __attribute__((aligned(8)));
};
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index 1fad2c2..da161b5 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -2,9 +2,11 @@
#define _XT_BPF_H
#include <linux/filter.h>
+#include <linux/limits.h>
#include <linux/types.h>
#define XT_BPF_MAX_NUM_INSTR 64
+#define XT_BPF_PATH_MAX (XT_BPF_MAX_NUM_INSTR * sizeof(struct sock_filter))
struct bpf_prog;
@@ -16,4 +18,24 @@ struct xt_bpf_info {
struct bpf_prog *filter __attribute__((aligned(8)));
};
+enum xt_bpf_modes {
+ XT_BPF_MODE_BYTECODE,
+ XT_BPF_MODE_FD_PINNED,
+ XT_BPF_MODE_FD_ELF,
+};
+#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED
+
+struct xt_bpf_info_v1 {
+ __u16 mode;
+ __u16 bpf_program_num_elem;
+ __s32 fd;
+ union {
+ struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
+ char path[XT_BPF_PATH_MAX];
+ };
+
+ /* only used in the kernel */
+ struct bpf_prog *filter __attribute__((aligned(8)));
+};
+
#endif /*_XT_BPF_H */
diff --git a/include/uapi/linux/netfilter/xt_socket.h b/include/uapi/linux/netfilter/xt_socket.h
index 87644f8..7f00df6 100644
--- a/include/uapi/linux/netfilter/xt_socket.h
+++ b/include/uapi/linux/netfilter/xt_socket.h
@@ -26,4 +26,11 @@ struct xt_socket_mtinfo3 {
| XT_SOCKET_NOWILDCARD \
| XT_SOCKET_RESTORESKMARK)
+struct sock *xt_socket_lookup_slow_v4(struct net *net,
+ const struct sk_buff *skb,
+ const struct net_device *indev);
+struct sock *xt_socket_lookup_slow_v6(struct net *net,
+ const struct sk_buff *skb,
+ const struct net_device *indev);
+
#endif /* _XT_SOCKET_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 64ec0d6..27e29bb 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -210,4 +210,7 @@ struct prctl_mm_map {
# define PR_SPEC_DISABLE (1UL << 2)
# define PR_SPEC_FORCE_DISABLE (1UL << 3)
+#define PR_SET_VMA 0x53564d41
+# define PR_SET_VMA_ANON_NAME 0
+
#endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 5a78be5..e14377f 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -318,6 +318,7 @@ enum rtattr_type_t {
RTA_ENCAP,
RTA_EXPIRES,
RTA_PAD,
+ RTA_UID,
__RTA_MAX
};
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 5f0fe01..ed6e31d9 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -9,6 +9,7 @@
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
+#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 954bd77..2c52de1 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -568,6 +568,7 @@ enum {
NET_IPV6_PROXY_NDP=23,
NET_IPV6_ACCEPT_SOURCE_ROUTE=25,
NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
+ NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
__NET_IPV6_MAX
};
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index 2466e55..b48f747 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -33,7 +33,7 @@
*/
-#define TASKSTATS_VERSION 8
+#define TASKSTATS_VERSION 9
#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
* in linux/sched.h */
@@ -163,6 +163,10 @@ struct taskstats {
/* Delay waiting for memory reclaim */
__u64 freepages_count;
__u64 freepages_delay_total;
+
+ /* Delay waiting for thrashing page */
+ __u64 thrashing_count;
+ __u64 thrashing_delay_total;
};
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 73ac0db..84a3eb2 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -116,6 +116,7 @@ enum {
#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
struct tcp_repair_opt {
__u32 opt_code;
diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h
new file mode 100644
index 0000000..4b9eb06
--- /dev/null
+++ b/include/uapi/linux/tee.h
@@ -0,0 +1,384 @@
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __TEE_H
+#define __TEE_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * This file describes the API provided by a TEE driver to user space.
+ *
+ * Each TEE driver defines a TEE specific protocol which is used for the
+ * data passed back and forth using TEE_IOC_CMD.
+ */
+
+/* Helpers to make the ioctl defines */
+#define TEE_IOC_MAGIC 0xa4
+#define TEE_IOC_BASE 0
+
+/* Flags relating to shared memory */
+#define TEE_IOCTL_SHM_MAPPED 0x1 /* memory mapped in normal world */
+#define TEE_IOCTL_SHM_DMA_BUF 0x2 /* dma-buf handle on shared memory */
+
+#define TEE_MAX_ARG_SIZE 1024
+
+#define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */
+#define TEE_GEN_CAP_PRIVILEGED (1 << 1)/* Privileged device (for supplicant) */
+#define TEE_GEN_CAP_REG_MEM (1 << 2)/* Supports registering shared memory */
+
+/*
+ * TEE Implementation ID
+ */
+#define TEE_IMPL_ID_OPTEE 1
+
+/*
+ * OP-TEE specific capabilities
+ */
+#define TEE_OPTEE_CAP_TZ (1 << 0)
+
+/**
+ * struct tee_ioctl_version_data - TEE version
+ * @impl_id: [out] TEE implementation id
+ * @impl_caps: [out] Implementation specific capabilities
+ * @gen_caps: [out] Generic capabilities, defined by TEE_GEN_CAPS_* above
+ *
+ * Identifies the TEE implementation, @impl_id is one of TEE_IMPL_ID_* above.
+ * @impl_caps is implementation specific, for example TEE_OPTEE_CAP_*
+ * is valid when @impl_id == TEE_IMPL_ID_OPTEE.
+ */
+struct tee_ioctl_version_data {
+ __u32 impl_id;
+ __u32 impl_caps;
+ __u32 gen_caps;
+};
+
+/**
+ * TEE_IOC_VERSION - query version of TEE
+ *
+ * Takes a tee_ioctl_version_data struct and returns with the TEE version
+ * data filled in.
+ */
+#define TEE_IOC_VERSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 0, \
+ struct tee_ioctl_version_data)
+
+/**
+ * struct tee_ioctl_shm_alloc_data - Shared memory allocate argument
+ * @size: [in/out] Size of shared memory to allocate
+ * @flags: [in/out] Flags to/from allocation.
+ * @id: [out] Identifier of the shared memory
+ *
+ * The flags field should currently be zero as input. Updated by the call
+ * with actual flags as defined by TEE_IOCTL_SHM_* above.
+ * This structure is used as argument for TEE_IOC_SHM_ALLOC below.
+ */
+struct tee_ioctl_shm_alloc_data {
+ __u64 size;
+ __u32 flags;
+ __s32 id;
+};
+
+/**
+ * TEE_IOC_SHM_ALLOC - allocate shared memory
+ *
+ * Allocates shared memory between the user space process and secure OS.
+ *
+ * Returns a file descriptor on success or < 0 on failure
+ *
+ * The returned file descriptor is used to map the shared memory into user
+ * space. The shared memory is freed when the descriptor is closed and the
+ * memory is unmapped.
+ */
+#define TEE_IOC_SHM_ALLOC _IOWR(TEE_IOC_MAGIC, TEE_IOC_BASE + 1, \
+ struct tee_ioctl_shm_alloc_data)
+
+/**
+ * struct tee_ioctl_buf_data - Variable sized buffer
+ * @buf_ptr: [in] A __user pointer to a buffer
+ * @buf_len: [in] Length of the buffer above
+ *
+ * Used as argument for TEE_IOC_OPEN_SESSION, TEE_IOC_INVOKE,
+ * TEE_IOC_SUPPL_RECV, and TEE_IOC_SUPPL_SEND below.
+ */
+struct tee_ioctl_buf_data {
+ __u64 buf_ptr;
+ __u64 buf_len;
+};
+
+/*
+ * Attributes for struct tee_ioctl_param, selects field in the union
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_NONE 0 /* parameter not used */
+
+/*
+ * These defines value parameters (struct tee_ioctl_param_value)
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT 1
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT 2
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT 3 /* input and output */
+
+/*
+ * These defines shared memory reference parameters (struct
+ * tee_ioctl_param_memref)
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT 5
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT 6
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT 7 /* input and output */
+
+/*
+ * Mask for the type part of the attribute, leaves room for more types
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MASK 0xff
+
+/* Meta parameter carrying extra information about the message. */
+#define TEE_IOCTL_PARAM_ATTR_META 0x100
+
+/* Mask of all known attr bits */
+#define TEE_IOCTL_PARAM_ATTR_MASK \
+ (TEE_IOCTL_PARAM_ATTR_TYPE_MASK | TEE_IOCTL_PARAM_ATTR_META)
+
+/*
+ * Matches TEEC_LOGIN_* in GP TEE Client API
+ * Are only defined for GP compliant TEEs
+ */
+#define TEE_IOCTL_LOGIN_PUBLIC 0
+#define TEE_IOCTL_LOGIN_USER 1
+#define TEE_IOCTL_LOGIN_GROUP 2
+#define TEE_IOCTL_LOGIN_APPLICATION 4
+#define TEE_IOCTL_LOGIN_USER_APPLICATION 5
+#define TEE_IOCTL_LOGIN_GROUP_APPLICATION 6
+
+/**
+ * struct tee_ioctl_param - parameter
+ * @attr: attributes
+ * @a: if a memref, offset into the shared memory object, else a value parameter
+ * @b: if a memref, size of the buffer, else a value parameter
+ * @c: if a memref, shared memory identifier, else a value parameter
+ *
+ * @attr & TEE_PARAM_ATTR_TYPE_MASK indicates if memref or value is used in
+ * the union. TEE_PARAM_ATTR_TYPE_VALUE_* indicates value and
+ * TEE_PARAM_ATTR_TYPE_MEMREF_* indicates memref. TEE_PARAM_ATTR_TYPE_NONE
+ * indicates that none of the members are used.
+ *
+ * Shared memory is allocated with TEE_IOC_SHM_ALLOC which returns an
+ * identifier representing the shared memory object. A memref can reference
+ * a part of a shared memory by specifying an offset (@a) and size (@b) of
+ * the object. To supply the entire shared memory object set the offset
+ * (@a) to 0 and size (@b) to the previously returned size of the object.
+ */
+struct tee_ioctl_param {
+ __u64 attr;
+ __u64 a;
+ __u64 b;
+ __u64 c;
+};
+
+#define TEE_IOCTL_UUID_LEN 16
+
+/**
+ * struct tee_ioctl_open_session_arg - Open session argument
+ * @uuid: [in] UUID of the Trusted Application
+ * @clnt_uuid: [in] UUID of client
+ * @clnt_login: [in] Login class of client, TEE_IOCTL_LOGIN_* above
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @session: [out] Session id
+ * @ret: [out] return value
+ * @ret_origin [out] origin of the return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_ioctl_open_session_arg {
+ __u8 uuid[TEE_IOCTL_UUID_LEN];
+ __u8 clnt_uuid[TEE_IOCTL_UUID_LEN];
+ __u32 clnt_login;
+ __u32 cancel_id;
+ __u32 session;
+ __u32 ret;
+ __u32 ret_origin;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_OPEN_SESSION - opens a session to a Trusted Application
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_ioctl_open_session_arg followed by any array of struct
+ * tee_ioctl_param
+ */
+#define TEE_IOC_OPEN_SESSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 2, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_ioctl_invoke_func_arg - Invokes a function in a Trusted
+ * Application
+ * @func: [in] Trusted Application function, specific to the TA
+ * @session: [in] Session id
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @ret: [out] return value
+ * @ret_origin [out] origin of the return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_ioctl_invoke_arg {
+ __u32 func;
+ __u32 session;
+ __u32 cancel_id;
+ __u32 ret;
+ __u32 ret_origin;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_INVOKE - Invokes a function in a Trusted Application
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_invoke_func_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_INVOKE _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 3, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_ioctl_cancel_arg - Cancels an open session or invoke ioctl
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @session: [in] Session id, if the session is opened, else set to 0
+ */
+struct tee_ioctl_cancel_arg {
+ __u32 cancel_id;
+ __u32 session;
+};
+
+/**
+ * TEE_IOC_CANCEL - Cancels an open session or invoke
+ */
+#define TEE_IOC_CANCEL _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 4, \
+ struct tee_ioctl_cancel_arg)
+
+/**
+ * struct tee_ioctl_close_session_arg - Closes an open session
+ * @session: [in] Session id
+ */
+struct tee_ioctl_close_session_arg {
+ __u32 session;
+};
+
+/**
+ * TEE_IOC_CLOSE_SESSION - Closes a session
+ */
+#define TEE_IOC_CLOSE_SESSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 5, \
+ struct tee_ioctl_close_session_arg)
+
+/**
+ * struct tee_iocl_supp_recv_arg - Receive a request for a supplicant function
+ * @func: [in] supplicant function
+ * @num_params [in/out] number of parameters following this struct
+ *
+ * @num_params is the number of params that tee-supplicant has room to
+ * receive when input, @num_params is the number of actual params
+ * tee-supplicant receives when output.
+ */
+struct tee_iocl_supp_recv_arg {
+ __u32 func;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_SUPPL_RECV - Receive a request for a supplicant function
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_iocl_supp_recv_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_SUPPL_RECV _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 6, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_iocl_supp_send_arg - Send a response to a received request
+ * @ret: [out] return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_iocl_supp_send_arg {
+ __u32 ret;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_SUPPL_SEND - Receive a request for a supplicant function
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_iocl_supp_send_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_SUPPL_SEND _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 7, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_ioctl_shm_register_data - Shared memory register argument
+ * @addr: [in] Start address of shared memory to register
+ * @length: [in/out] Length of shared memory to register
+ * @flags: [in/out] Flags to/from registration.
+ * @id: [out] Identifier of the shared memory
+ *
+ * The flags field should currently be zero as input. Updated by the call
+ * with actual flags as defined by TEE_IOCTL_SHM_* above.
+ * This structure is used as argument for TEE_IOC_SHM_REGISTER below.
+ */
+struct tee_ioctl_shm_register_data {
+ __u64 addr;
+ __u64 length;
+ __u32 flags;
+ __s32 id;
+};
+
+/**
+ * TEE_IOC_SHM_REGISTER - Register shared memory argument
+ *
+ * Registers shared memory between the user space process and secure OS.
+ *
+ * Returns a file descriptor on success or < 0 on failure
+ *
+ * The shared memory is unregisterred when the descriptor is closed.
+ */
+#define TEE_IOC_SHM_REGISTER _IOWR(TEE_IOC_MAGIC, TEE_IOC_BASE + 9, \
+ struct tee_ioctl_shm_register_data)
+/*
+ * Five syscalls are used when communicating with the TEE driver.
+ * open(): opens the device associated with the driver
+ * ioctl(): as described above operating on the file descriptor from open()
+ * close(): two cases
+ * - closes the device file descriptor
+ * - closes a file descriptor connected to allocated shared memory
+ * mmap(): maps shared memory into user space using information from struct
+ * tee_ioctl_shm_alloc_data
+ * munmap(): unmaps previously shared memory
+ */
+
+#endif /*__TEE_H*/
diff --git a/include/uapi/linux/usb/f_accessory.h b/include/uapi/linux/usb/f_accessory.h
new file mode 100644
index 0000000..0baeb7d
--- /dev/null
+++ b/include/uapi/linux/usb/f_accessory.h
@@ -0,0 +1,146 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_ACCESSORY_H
+#define _UAPI_LINUX_USB_F_ACCESSORY_H
+
+/* Use Google Vendor ID when in accessory mode */
+#define USB_ACCESSORY_VENDOR_ID 0x18D1
+
+
+/* Product ID to use when in accessory mode */
+#define USB_ACCESSORY_PRODUCT_ID 0x2D00
+
+/* Product ID to use when in accessory mode and adb is enabled */
+#define USB_ACCESSORY_ADB_PRODUCT_ID 0x2D01
+
+/* Indexes for strings sent by the host via ACCESSORY_SEND_STRING */
+#define ACCESSORY_STRING_MANUFACTURER 0
+#define ACCESSORY_STRING_MODEL 1
+#define ACCESSORY_STRING_DESCRIPTION 2
+#define ACCESSORY_STRING_VERSION 3
+#define ACCESSORY_STRING_URI 4
+#define ACCESSORY_STRING_SERIAL 5
+
+/* Control request for retrieving device's protocol version
+ *
+ * requestType: USB_DIR_IN | USB_TYPE_VENDOR
+ * request: ACCESSORY_GET_PROTOCOL
+ * value: 0
+ * index: 0
+ * data version number (16 bits little endian)
+ * 1 for original accessory support
+ * 2 adds HID and device to host audio support
+ */
+#define ACCESSORY_GET_PROTOCOL 51
+
+/* Control request for host to send a string to the device
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SEND_STRING
+ * value: 0
+ * index: string ID
+ * data zero terminated UTF8 string
+ *
+ * The device can later retrieve these strings via the
+ * ACCESSORY_GET_STRING_* ioctls
+ */
+#define ACCESSORY_SEND_STRING 52
+
+/* Control request for starting device in accessory mode.
+ * The host sends this after setting all its strings to the device.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_START
+ * value: 0
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_START 53
+
+/* Control request for registering a HID device.
+ * Upon registering, a unique ID is sent by the accessory in the
+ * value parameter. This ID will be used for future commands for
+ * the device
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_REGISTER_HID_DEVICE
+ * value: Accessory assigned ID for the HID device
+ * index: total length of the HID report descriptor
+ * data none
+ */
+#define ACCESSORY_REGISTER_HID 54
+
+/* Control request for unregistering a HID device.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_REGISTER_HID
+ * value: Accessory assigned ID for the HID device
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_UNREGISTER_HID 55
+
+/* Control request for sending the HID report descriptor.
+ * If the HID descriptor is longer than the endpoint zero max packet size,
+ * the descriptor will be sent in multiple ACCESSORY_SET_HID_REPORT_DESC
+ * commands. The data for the descriptor must be sent sequentially
+ * if multiple packets are needed.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SET_HID_REPORT_DESC
+ * value: Accessory assigned ID for the HID device
+ * index: offset of data in descriptor
+ * (needed when HID descriptor is too big for one packet)
+ * data the HID report descriptor
+ */
+#define ACCESSORY_SET_HID_REPORT_DESC 56
+
+/* Control request for sending HID events.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SEND_HID_EVENT
+ * value: Accessory assigned ID for the HID device
+ * index: 0
+ * data the HID report for the event
+ */
+#define ACCESSORY_SEND_HID_EVENT 57
+
+/* Control request for setting the audio mode.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SET_AUDIO_MODE
+ * value: 0 - no audio
+ * 1 - device to host, 44100 16-bit stereo PCM
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_SET_AUDIO_MODE 58
+
+/* ioctls for retrieving strings set by the host */
+#define ACCESSORY_GET_STRING_MANUFACTURER _IOW('M', 1, char[256])
+#define ACCESSORY_GET_STRING_MODEL _IOW('M', 2, char[256])
+#define ACCESSORY_GET_STRING_DESCRIPTION _IOW('M', 3, char[256])
+#define ACCESSORY_GET_STRING_VERSION _IOW('M', 4, char[256])
+#define ACCESSORY_GET_STRING_URI _IOW('M', 5, char[256])
+#define ACCESSORY_GET_STRING_SERIAL _IOW('M', 6, char[256])
+/* returns 1 if there is a start request pending */
+#define ACCESSORY_IS_START_REQUESTED _IO('M', 7)
+/* returns audio mode (set via the ACCESSORY_SET_AUDIO_MODE control request) */
+#define ACCESSORY_GET_AUDIO_MODE _IO('M', 8)
+
+#endif /* _UAPI_LINUX_USB_F_ACCESSORY_H */
diff --git a/include/uapi/linux/usb/f_mtp.h b/include/uapi/linux/usb/f_mtp.h
new file mode 100644
index 0000000..5032918
--- /dev/null
+++ b/include/uapi/linux/usb/f_mtp.h
@@ -0,0 +1,61 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_MTP_H
+#define _UAPI_LINUX_USB_F_MTP_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+struct mtp_file_range {
+ /* file descriptor for file to transfer */
+ int fd;
+ /* offset in file for start of transfer */
+ loff_t offset;
+ /* number of bytes to transfer */
+ int64_t length;
+ /* MTP command ID for data header,
+ * used only for MTP_SEND_FILE_WITH_HEADER
+ */
+ uint16_t command;
+ /* MTP transaction ID for data header,
+ * used only for MTP_SEND_FILE_WITH_HEADER
+ */
+ uint32_t transaction_id;
+};
+
+struct mtp_event {
+ /* size of the event */
+ size_t length;
+ /* event data to send */
+ void *data;
+};
+
+/* Sends the specified file range to the host */
+#define MTP_SEND_FILE _IOW('M', 0, struct mtp_file_range)
+/* Receives data from the host and writes it to a file.
+ * The file is created if it does not exist.
+ */
+#define MTP_RECEIVE_FILE _IOW('M', 1, struct mtp_file_range)
+/* Sends an event to the host via the interrupt endpoint */
+#define MTP_SEND_EVENT _IOW('M', 3, struct mtp_event)
+/* Sends the specified file range to the host,
+ * with a 12 byte MTP data packet header at the beginning.
+ */
+#define MTP_SEND_FILE_WITH_HEADER _IOW('M', 4, struct mtp_file_range)
+
+#endif /* _UAPI_LINUX_USB_F_MTP_H */
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 1fc62b2..4215bbdb 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -303,8 +303,13 @@ enum xfrm_attr_type_t {
XFRMA_PROTO, /* __u8 */
XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
XFRMA_PAD,
+ XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */
+ XFRMA_SET_MARK, /* __u32 */
+ XFRMA_SET_MARK_MASK, /* __u32 */
+ XFRMA_IF_ID, /* __u32 */
__XFRMA_MAX
+#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */
#define XFRMA_MAX (__XFRMA_MAX - 1)
};
diff --git a/init/Kconfig b/init/Kconfig
index 0a615bd..4db5724 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -400,6 +400,15 @@
If in doubt, say N here.
+config SCHED_WALT
+ bool "Support window based load tracking"
+ depends on SMP
+ help
+ This feature will allow the scheduler to maintain a tunable window
+ based set of metrics for tasks and runqueues. These metrics can be
+ used to guide task placement as well as task frequency requirements
+ for cpufreq governors.
+
config BSD_PROCESS_ACCT
bool "BSD Process Accounting"
depends on MULTIUSER
@@ -470,6 +479,45 @@
Say N if unsure.
+config PSI
+ bool "Pressure stall information tracking"
+ help
+ Collect metrics that indicate how overcommitted the CPU, memory,
+ and IO capacity are in the system.
+
+ If you say Y here, the kernel will create /proc/pressure/ with the
+ pressure statistics files cpu, memory, and io. These will indicate
+ the share of walltime in which some or all tasks in the system are
+ delayed due to contention of the respective resource.
+
+ In kernels with cgroup support, cgroups (cgroup2 only) will
+ have cpu.pressure, memory.pressure, and io.pressure files,
+ which aggregate pressure stalls for the grouped tasks only.
+
+ For more details see Documentation/accounting/psi.txt.
+
+ Say N if unsure.
+
+config PSI_DEFAULT_DISABLED
+ bool "Require boot parameter to enable pressure stall information tracking"
+ default n
+ depends on PSI
+ help
+ If set, pressure stall information tracking will be disabled
+ per default but can be enabled through passing psi=1 on the
+ kernel commandline during boot.
+
+ This feature adds some code to the task wakeup and sleep
+ paths of the scheduler. The overhead is too low to affect
+ common scheduling-intense workloads in practice (such as
+ webservers, memcache), but it does show up in artificial
+ scheduler stress tests, such as hackbench.
+
+ If you are paranoid and not sure what the kernel will be
+ used for, say Y.
+
+ Say N if unsure.
+
endmenu # "CPU/Task time and stats accounting"
menu "RCU Subsystem"
@@ -972,6 +1020,82 @@
if CGROUPS
+config CGROUP_DEBUG
+ bool "Example debug cgroup subsystem"
+ default n
+ help
+ This option enables a simple cgroup subsystem that
+ exports useful debugging information about the cgroups
+ framework.
+
+ Say N if unsure.
+
+config CGROUP_FREEZER
+ bool "Freezer cgroup subsystem"
+ help
+ Provides a way to freeze and unfreeze all tasks in a
+ cgroup.
+
+config CGROUP_PIDS
+ bool "PIDs cgroup subsystem"
+ help
+ Provides enforcement of process number limits in the scope of a
+ cgroup. Any attempt to fork more processes than is allowed in the
+ cgroup will fail. PIDs are fundamentally a global resource because it
+ is fairly trivial to reach PID exhaustion before you reach even a
+ conservative kmemcg limit. As a result, it is possible to grind a
+ system to halt without being limited by other cgroup policies. The
+ PIDs cgroup subsystem is designed to stop this from happening.
+
+ It should be noted that organisational operations (such as attaching
+ to a cgroup hierarchy will *not* be blocked by the PIDs subsystem),
+ since the PIDs limit only affects a process's ability to fork, not to
+ attach to a cgroup.
+
+config CGROUP_DEVICE
+ bool "Device controller for cgroups"
+ help
+ Provides a cgroup implementing whitelists for devices which
+ a process in the cgroup can mknod or open.
+
+config CPUSETS
+ bool "Cpuset support"
+ help
+ This option will let you create and manage CPUSETs which
+ allow dynamically partitioning a system into sets of CPUs and
+ Memory Nodes and assigning tasks to run only within those sets.
+ This is primarily useful on large SMP or NUMA systems.
+
+ Say N if unsure.
+
+config PROC_PID_CPUSET
+ bool "Include legacy /proc/<pid>/cpuset file"
+ depends on CPUSETS
+ default y
+
+config CGROUP_CPUACCT
+ bool "Simple CPU accounting cgroup subsystem"
+ help
+ Provides a simple Resource Controller for monitoring the
+ total CPU consumed by the tasks in a cgroup.
+
+config CGROUP_SCHEDTUNE
+ bool "CFS tasks boosting cgroup subsystem (EXPERIMENTAL)"
+ depends on SCHED_TUNE
+ help
+ This option provides the "schedtune" controller which improves the
+ flexibility of the task boosting mechanism by introducing the support
+ to define "per task" boost values.
+
+ This new controller:
+ 1. allows only a two layers hierarchy, where the root defines the
+ system-wide boost value and its direct childrens define each one a
+ different "class of tasks" to be boosted with a different value
+ 2. supports up to 16 different task classes, each one which could be
+ configured with a different boost value
+
+ Say N if unsure.
+
config PAGE_COUNTER
bool
@@ -1155,6 +1279,19 @@
Say N if unsure.
+config CGROUP_BPF
+ bool "Support for eBPF programs attached to cgroups"
+ depends on BPF_SYSCALL
+ select SOCK_CGROUP_DATA
+ help
+ Allow attaching eBPF programs to a cgroup using the bpf(2)
+ syscall command BPF_PROG_ATTACH.
+
+ In which context these programs are accessed depends on the type
+ of attachment. For instance, programs that are attached using
+ BPF_CGROUP_INET_INGRESS will be executed on the ingress path of
+ inet sockets.
+
config CGROUP_DEBUG
bool "Example controller"
default n
@@ -1164,6 +1301,10 @@
Say N.
+config SOCK_CGROUP_DATA
+ bool
+ default n
+
endif # CGROUPS
config CHECKPOINT_RESTORE
@@ -1249,6 +1390,43 @@
desktop applications. Task group autogeneration is currently based
upon task session.
+config SCHED_TUNE
+ bool "Boosting for CFS tasks (EXPERIMENTAL)"
+ depends on SMP
+ help
+ This option enables the system-wide support for task boosting.
+ When this support is enabled a new sysctl interface is exposed to
+ userspace via:
+ /proc/sys/kernel/sched_cfs_boost
+ which allows to set a system-wide boost value in range [0..100].
+
+ The currently boosting strategy is implemented in such a way that:
+ - a 0% boost value requires to operate in "standard" mode by
+ scheduling all tasks at the minimum capacities required by their
+ workload demand
+ - a 100% boost value requires to push at maximum the task
+ performances, "regardless" of the incurred energy consumption
+
+ A boost value in between these two boundaries is used to bias the
+ power/performance trade-off, the higher the boost value the more the
+ scheduler is biased toward performance boosting instead of energy
+ efficiency.
+
+ Since this support exposes a single system-wide knob, the specified
+ boost value is applied to all (CFS) tasks in the system.
+
+ If unsure, say N.
+
+config DEFAULT_USE_ENERGY_AWARE
+ bool "Default to enabling the Energy Aware Scheduler feature"
+ default n
+ help
+ This option defaults the ENERGY_AWARE scheduling feature to true,
+ as without SCHED_DEBUG set this feature can't be enabled or disabled
+ via sysctl.
+
+ Say N if unsure.
+
config SYSFS_DEPRECATED
bool "Enable deprecated sysfs features to support old userspace tools"
depends on SYSFS
@@ -1345,9 +1523,6 @@
config SYSCTL
bool
-config ANON_INODES
- bool
-
config HAVE_UID16
bool
@@ -1565,14 +1740,12 @@
config EPOLL
bool "Enable eventpoll support" if EXPERT
default y
- select ANON_INODES
help
Disabling this option will cause the kernel to be built without
support for epoll family of system calls.
config SIGNALFD
bool "Enable signalfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the signalfd() system call that allows to receive signals
@@ -1582,7 +1755,6 @@
config TIMERFD
bool "Enable timerfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the timerfd() system call that allows to receive timer
@@ -1592,7 +1764,6 @@
config EVENTFD
bool "Enable eventfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the eventfd() system call that allows to receive both
@@ -1603,7 +1774,6 @@
# syscall, maps, verifier
config BPF_SYSCALL
bool "Enable bpf() system call"
- select ANON_INODES
select BPF
default n
help
@@ -1648,7 +1818,6 @@
config USERFAULTFD
bool "Enable userfaultfd() system call"
- select ANON_INODES
depends on MMU
help
Enable the userfaultfd() system call that allows to intercept and
@@ -1700,7 +1869,6 @@
bool "Kernel performance events and counters"
default y if PROFILING
depends on HAVE_PERF_EVENTS
- select ANON_INODES
select IRQ_WORK
select SRCU
help
@@ -1760,6 +1928,20 @@
SLUB sysfs support. /sys/slab will not exist and there will be
no support for cache validation etc.
+config SLUB_MEMCG_SYSFS_ON
+ default n
+ bool "Enable memcg SLUB sysfs support by default" if EXPERT
+ depends on SLUB && SYSFS && MEMCG
+ help
+ SLUB creates a directory under /sys/kernel/slab for each
+ allocation cache to host info and debug files. If memory
+ cgroup is enabled, each cache can have per memory cgroup
+ caches. SLUB can create the same sysfs directories for these
+ caches under /sys/kernel/slab/CACHE/cgroup but it can lead
+ to a very high number of debug files being created. This is
+ controlled by slub_memcg_sysfs boot parameter and this
+ config option determines the parameter's default value.
+
config COMPAT_BRK
bool "Disable heap randomization"
default y
@@ -2107,7 +2289,7 @@
config MODULES_TREE_LOOKUP
def_bool y
- depends on PERF_EVENTS || TRACING
+ depends on PERF_EVENTS || TRACING || CFI_CLANG
config INIT_ALL_POSSIBLE
bool
diff --git a/init/Makefile b/init/Makefile
index c4fb455..d210b23 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -5,11 +5,8 @@
ccflags-y := -fno-function-sections -fno-data-sections
obj-y := main.o version.o mounts.o
-ifneq ($(CONFIG_BLK_DEV_INITRD),y)
obj-y += noinitramfs.o
-else
obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o
-endif
obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
ifneq ($(CONFIG_ARCH_INIT_TASK),y)
@@ -20,6 +17,7 @@
mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o
mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o
mounts-$(CONFIG_BLK_DEV_MD) += do_mounts_md.o
+mounts-$(CONFIG_BLK_DEV_DM) += do_mounts_dm.o
# dependencies on generated files need to be listed explicitly
$(obj)/version.o: include/generated/compile.h
diff --git a/init/do_mounts.c b/init/do_mounts.c
index dea5de9..1902a1c8 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -566,6 +566,7 @@ void __init prepare_namespace(void)
wait_for_device_probe();
md_run_setup();
+ dm_run_setup();
if (saved_root_name[0]) {
root_device_name = saved_root_name;
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 067af1d..ecb2757 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -74,3 +74,13 @@ void md_run_setup(void);
static inline void md_run_setup(void) {}
#endif
+
+#ifdef CONFIG_BLK_DEV_DM
+
+void dm_run_setup(void);
+
+#else
+
+static inline void dm_run_setup(void) {}
+
+#endif
diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c
new file mode 100644
index 0000000..af84b01
--- /dev/null
+++ b/init/do_mounts_dm.c
@@ -0,0 +1,470 @@
+/* do_mounts_dm.c
+ * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * All Rights Reserved.
+ * Based on do_mounts_md.c
+ *
+ * This file is released under the GPL.
+ */
+#include <linux/async.h>
+#include <linux/ctype.h>
+#include <linux/device-mapper.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+
+#include "do_mounts.h"
+
+#define DM_MAX_DEVICES 256
+#define DM_MAX_TARGETS 256
+#define DM_MAX_NAME 32
+#define DM_MAX_UUID 129
+#define DM_NO_UUID "none"
+
+#define DM_MSG_PREFIX "init"
+
+/* Separators used for parsing the dm= argument. */
+#define DM_FIELD_SEP " "
+#define DM_LINE_SEP ","
+#define DM_ANY_SEP DM_FIELD_SEP DM_LINE_SEP
+
+/*
+ * When the device-mapper and any targets are compiled into the kernel
+ * (not a module), one or more device-mappers may be created and used
+ * as the root device at boot time with the parameters given with the
+ * boot line dm=...
+ *
+ * Multiple device-mappers can be stacked specifing the number of
+ * devices. A device can have multiple targets if the the number of
+ * targets is specified.
+ *
+ * TODO(taysom:defect 32847)
+ * In the future, the <num> field will be mandatory.
+ *
+ * <device> ::= [<num>] <device-mapper>+
+ * <device-mapper> ::= <head> "," <target>+
+ * <head> ::= <name> <uuid> <mode> [<num>]
+ * <target> ::= <start> <length> <type> <options> ","
+ * <mode> ::= "ro" | "rw"
+ * <uuid> ::= xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx | "none"
+ * <type> ::= "verity" | "bootcache" | ...
+ *
+ * Example:
+ * 2 vboot none ro 1,
+ * 0 1768000 bootcache
+ * device=aa55b119-2a47-8c45-946a-5ac57765011f+1
+ * signature=76e9be054b15884a9fa85973e9cb274c93afadb6
+ * cache_start=1768000 max_blocks=100000 size_limit=23 max_trace=20000,
+ * vroot none ro 1,
+ * 0 1740800 verity payload=254:0 hashtree=254:0 hashstart=1740800 alg=sha1
+ * root_hexdigest=76e9be054b15884a9fa85973e9cb274c93afadb6
+ * salt=5b3549d54d6c7a3837b9b81ed72e49463a64c03680c47835bef94d768e5646fe
+ *
+ * Notes:
+ * 1. uuid is a label for the device and we set it to "none".
+ * 2. The <num> field will be optional initially and assumed to be 1.
+ * Once all the scripts that set these fields have been set, it will
+ * be made mandatory.
+ */
+
+struct dm_setup_target {
+ sector_t begin;
+ sector_t length;
+ char *type;
+ char *params;
+ /* simple singly linked list */
+ struct dm_setup_target *next;
+};
+
+struct dm_device {
+ int minor;
+ int ro;
+ char name[DM_MAX_NAME];
+ char uuid[DM_MAX_UUID];
+ unsigned long num_targets;
+ struct dm_setup_target *target;
+ int target_count;
+ struct dm_device *next;
+};
+
+struct dm_option {
+ char *start;
+ char *next;
+ size_t len;
+ char delim;
+};
+
+static struct {
+ unsigned long num_devices;
+ char *str;
+} dm_setup_args __initdata;
+
+static __initdata int dm_early_setup;
+
+static int __init get_dm_option(struct dm_option *opt, const char *accept)
+{
+ char *str = opt->next;
+ char *endp;
+
+ if (!str)
+ return 0;
+
+ str = skip_spaces(str);
+ opt->start = str;
+ endp = strpbrk(str, accept);
+ if (!endp) { /* act like strchrnul */
+ opt->len = strlen(str);
+ endp = str + opt->len;
+ } else {
+ opt->len = endp - str;
+ }
+ opt->delim = *endp;
+ if (*endp == 0) {
+ /* Don't advance past the nul. */
+ opt->next = endp;
+ } else {
+ opt->next = endp + 1;
+ }
+ return opt->len != 0;
+}
+
+static int __init dm_setup_cleanup(struct dm_device *devices)
+{
+ struct dm_device *dev = devices;
+
+ while (dev) {
+ struct dm_device *old_dev = dev;
+ struct dm_setup_target *target = dev->target;
+ while (target) {
+ struct dm_setup_target *old_target = target;
+ kfree(target->type);
+ kfree(target->params);
+ target = target->next;
+ kfree(old_target);
+ dev->target_count--;
+ }
+ BUG_ON(dev->target_count);
+ dev = dev->next;
+ kfree(old_dev);
+ }
+ return 0;
+}
+
+static char * __init dm_parse_device(struct dm_device *dev, char *str)
+{
+ struct dm_option opt;
+ size_t len;
+
+ /* Grab the logical name of the device to be exported to udev */
+ opt.next = str;
+ if (!get_dm_option(&opt, DM_FIELD_SEP)) {
+ DMERR("failed to parse device name");
+ goto parse_fail;
+ }
+ len = min(opt.len + 1, sizeof(dev->name));
+ strlcpy(dev->name, opt.start, len); /* includes nul */
+
+ /* Grab the UUID value or "none" */
+ if (!get_dm_option(&opt, DM_FIELD_SEP)) {
+ DMERR("failed to parse device uuid");
+ goto parse_fail;
+ }
+ len = min(opt.len + 1, sizeof(dev->uuid));
+ strlcpy(dev->uuid, opt.start, len);
+
+ /* Determine if the table/device will be read only or read-write */
+ get_dm_option(&opt, DM_ANY_SEP);
+ if (!strncmp("ro", opt.start, opt.len)) {
+ dev->ro = 1;
+ } else if (!strncmp("rw", opt.start, opt.len)) {
+ dev->ro = 0;
+ } else {
+ DMERR("failed to parse table mode");
+ goto parse_fail;
+ }
+
+ /* Optional number field */
+ /* XXX: The <num> field will be mandatory in the next round */
+ if (opt.delim == DM_FIELD_SEP[0]) {
+ if (!get_dm_option(&opt, DM_LINE_SEP))
+ return NULL;
+ dev->num_targets = simple_strtoul(opt.start, NULL, 10);
+ } else {
+ dev->num_targets = 1;
+ }
+ if (dev->num_targets > DM_MAX_TARGETS) {
+ DMERR("too many targets %lu > %d",
+ dev->num_targets, DM_MAX_TARGETS);
+ }
+ return opt.next;
+
+parse_fail:
+ return NULL;
+}
+
+static char * __init dm_parse_targets(struct dm_device *dev, char *str)
+{
+ struct dm_option opt;
+ struct dm_setup_target **target = &dev->target;
+ unsigned long num_targets = dev->num_targets;
+ unsigned long i;
+
+ /* Targets are defined as per the table format but with a
+ * comma as a newline separator. */
+ opt.next = str;
+ for (i = 0; i < num_targets; i++) {
+ *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL);
+ if (!*target) {
+ DMERR("failed to allocate memory for target %s<%ld>",
+ dev->name, i);
+ goto parse_fail;
+ }
+ dev->target_count++;
+
+ if (!get_dm_option(&opt, DM_FIELD_SEP)) {
+ DMERR("failed to parse starting sector"
+ " for target %s<%ld>", dev->name, i);
+ goto parse_fail;
+ }
+ (*target)->begin = simple_strtoull(opt.start, NULL, 10);
+
+ if (!get_dm_option(&opt, DM_FIELD_SEP)) {
+ DMERR("failed to parse length for target %s<%ld>",
+ dev->name, i);
+ goto parse_fail;
+ }
+ (*target)->length = simple_strtoull(opt.start, NULL, 10);
+
+ if (get_dm_option(&opt, DM_FIELD_SEP))
+ (*target)->type = kstrndup(opt.start, opt.len,
+ GFP_KERNEL);
+ if (!((*target)->type)) {
+ DMERR("failed to parse type for target %s<%ld>",
+ dev->name, i);
+ goto parse_fail;
+ }
+ if (get_dm_option(&opt, DM_LINE_SEP))
+ (*target)->params = kstrndup(opt.start, opt.len,
+ GFP_KERNEL);
+ if (!((*target)->params)) {
+ DMERR("failed to parse params for target %s<%ld>",
+ dev->name, i);
+ goto parse_fail;
+ }
+ target = &((*target)->next);
+ }
+ DMDEBUG("parsed %d targets", dev->target_count);
+
+ return opt.next;
+
+parse_fail:
+ return NULL;
+}
+
+static struct dm_device * __init dm_parse_args(void)
+{
+ struct dm_device *devices = NULL;
+ struct dm_device **tail = &devices;
+ struct dm_device *dev;
+ char *str = dm_setup_args.str;
+ unsigned long num_devices = dm_setup_args.num_devices;
+ unsigned long i;
+
+ if (!str)
+ return NULL;
+ for (i = 0; i < num_devices; i++) {
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev) {
+ DMERR("failed to allocated memory for dev");
+ goto error;
+ }
+ *tail = dev;
+ tail = &dev->next;
+ /*
+ * devices are given minor numbers 0 - n-1
+ * in the order they are found in the arg
+ * string.
+ */
+ dev->minor = i;
+ str = dm_parse_device(dev, str);
+ if (!str) /* NULL indicates error in parsing, bail */
+ goto error;
+
+ str = dm_parse_targets(dev, str);
+ if (!str)
+ goto error;
+ }
+ return devices;
+error:
+ dm_setup_cleanup(devices);
+ return NULL;
+}
+
+/*
+ * Parse the command-line parameters given our kernel, but do not
+ * actually try to invoke the DM device now; that is handled by
+ * dm_setup_drives after the low-level disk drivers have initialised.
+ * dm format is described at the top of the file.
+ *
+ * Because dm minor numbers are assigned in assending order starting with 0,
+ * You can assume the first device is /dev/dm-0, the next device is /dev/dm-1,
+ * and so forth.
+ */
+static int __init dm_setup(char *str)
+{
+ struct dm_option opt;
+ unsigned long num_devices;
+
+ if (!str) {
+ DMDEBUG("str is NULL");
+ goto parse_fail;
+ }
+ opt.next = str;
+ if (!get_dm_option(&opt, DM_FIELD_SEP))
+ goto parse_fail;
+ if (isdigit(opt.start[0])) { /* XXX: Optional number field */
+ num_devices = simple_strtoul(opt.start, NULL, 10);
+ str = opt.next;
+ } else {
+ num_devices = 1;
+ /* Don't advance str */
+ }
+ if (num_devices > DM_MAX_DEVICES) {
+ DMDEBUG("too many devices %lu > %d",
+ num_devices, DM_MAX_DEVICES);
+ }
+ dm_setup_args.str = str;
+ dm_setup_args.num_devices = num_devices;
+ DMINFO("will configure %lu devices", num_devices);
+ dm_early_setup = 1;
+ return 1;
+
+parse_fail:
+ DMWARN("Invalid arguments supplied to dm=.");
+ return 0;
+}
+
+static void __init dm_setup_drives(void)
+{
+ struct mapped_device *md = NULL;
+ struct dm_table *table = NULL;
+ struct dm_setup_target *target;
+ struct dm_device *dev;
+ char *uuid;
+ fmode_t fmode = FMODE_READ;
+ struct dm_device *devices;
+
+ devices = dm_parse_args();
+
+ for (dev = devices; dev; dev = dev->next) {
+ if (dm_create(dev->minor, &md)) {
+ DMDEBUG("failed to create the device");
+ goto dm_create_fail;
+ }
+ DMDEBUG("created device '%s'", dm_device_name(md));
+
+ /*
+ * In addition to flagging the table below, the disk must be
+ * set explicitly ro/rw.
+ */
+ set_disk_ro(dm_disk(md), dev->ro);
+
+ if (!dev->ro)
+ fmode |= FMODE_WRITE;
+ if (dm_table_create(&table, fmode, dev->target_count, md)) {
+ DMDEBUG("failed to create the table");
+ goto dm_table_create_fail;
+ }
+
+ dm_lock_md_type(md);
+
+ for (target = dev->target; target; target = target->next) {
+ DMINFO("adding target '%llu %llu %s %s'",
+ (unsigned long long) target->begin,
+ (unsigned long long) target->length,
+ target->type, target->params);
+ if (dm_table_add_target(table, target->type,
+ target->begin,
+ target->length,
+ target->params)) {
+ DMDEBUG("failed to add the target"
+ " to the table");
+ goto add_target_fail;
+ }
+ }
+ if (dm_table_complete(table)) {
+ DMDEBUG("failed to complete the table");
+ goto table_complete_fail;
+ }
+
+ /* Suspend the device so that we can bind it to the table. */
+ if (dm_suspend(md, 0)) {
+ DMDEBUG("failed to suspend the device pre-bind");
+ goto suspend_fail;
+ }
+
+ /* Initial table load: acquire type of table. */
+ dm_set_md_type(md, dm_table_get_type(table));
+
+ /* Setup md->queue to reflect md's type. */
+ if (dm_setup_md_queue(md, table)) {
+ DMWARN("unable to set up device queue for new table.");
+ goto setup_md_queue_fail;
+ }
+
+ /*
+ * Bind the table to the device. This is the only way
+ * to associate md->map with the table and set the disk
+ * capacity directly.
+ */
+ if (dm_swap_table(md, table)) { /* should return NULL. */
+ DMDEBUG("failed to bind the device to the table");
+ goto table_bind_fail;
+ }
+
+ /* Finally, resume and the device should be ready. */
+ if (dm_resume(md)) {
+ DMDEBUG("failed to resume the device");
+ goto resume_fail;
+ }
+
+ /* Export the dm device via the ioctl interface */
+ if (!strcmp(DM_NO_UUID, dev->uuid))
+ uuid = NULL;
+ if (dm_ioctl_export(md, dev->name, uuid)) {
+ DMDEBUG("failed to export device with given"
+ " name and uuid");
+ goto export_fail;
+ }
+
+ dm_unlock_md_type(md);
+
+ DMINFO("dm-%d is ready", dev->minor);
+ }
+ dm_setup_cleanup(devices);
+ return;
+
+export_fail:
+resume_fail:
+table_bind_fail:
+setup_md_queue_fail:
+suspend_fail:
+table_complete_fail:
+add_target_fail:
+ dm_unlock_md_type(md);
+dm_table_create_fail:
+ dm_put(md);
+dm_create_fail:
+ DMWARN("starting dm-%d (%s) failed",
+ dev->minor, dev->name);
+ dm_setup_cleanup(devices);
+}
+
+__setup("dm=", dm_setup);
+
+void __init dm_run_setup(void)
+{
+ if (!dm_early_setup)
+ return;
+ DMINFO("attempting early device configuration.");
+ dm_setup_drives();
+}
diff --git a/init/initramfs.c b/init/initramfs.c
index 981f286..bf3af10 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -18,6 +18,7 @@
#include <linux/dirent.h>
#include <linux/syscalls.h>
#include <linux/utime.h>
+#include <linux/initramfs.h>
#include <linux/file.h>
static ssize_t __init xwrite(int fd, const char *p, size_t count)
@@ -606,9 +607,28 @@ static void __init clean_rootfs(void)
}
#endif
+static int __initdata do_skip_initramfs;
+
+static int __init skip_initramfs_param(char *str)
+{
+ if (*str)
+ return 0;
+ do_skip_initramfs = 1;
+ return 1;
+}
+__setup("skip_initramfs", skip_initramfs_param);
+
static int __init populate_rootfs(void)
{
- char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
+ char *err;
+
+ if (do_skip_initramfs) {
+ if (initrd_start)
+ free_initrd();
+ return default_rootfs();
+ }
+
+ err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
if (err)
panic("%s", err); /* Failed to decompress INTERNAL initramfs */
if (initrd_start) {
diff --git a/init/main.c b/init/main.c
index 7ad0895..ef3395c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -553,6 +553,14 @@ asmlinkage __visible void __init start_kernel(void)
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
idr_init_cache();
+
+ /*
+ * Allow workqueue creation and work item queueing/cancelling
+ * early. Work item execution depends on kthreads and starts after
+ * workqueue_init().
+ */
+ workqueue_init_early();
+
rcu_init();
/* trace_printk() and trace points may be used after this */
@@ -638,9 +646,8 @@ asmlinkage __visible void __init start_kernel(void)
security_init();
dbg_late_init();
vfs_caches_init();
+ pagecache_init();
signals_init();
- /* rootfs populating might need page-writeback */
- page_writeback_init();
proc_root_init();
nsfs_init();
cpuset_init();
@@ -1009,6 +1016,8 @@ static noinline void __init kernel_init_freeable(void)
smp_prepare_cpus(setup_max_cpus);
+ workqueue_init();
+
do_pre_smp_initcalls();
lockup_detector_init();
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 267739d..bcc8bcb0 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -21,11 +21,16 @@
#include <linux/stat.h>
#include <linux/kdev_t.h>
#include <linux/syscalls.h>
+#include <linux/kconfig.h>
+#include <linux/initramfs.h>
/*
* Create a simple rootfs that is similar to the default initramfs
*/
-static int __init default_rootfs(void)
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+static
+#endif
+int __init default_rootfs(void)
{
int err;
@@ -49,4 +54,6 @@ static int __init default_rootfs(void)
printk(KERN_WARNING "Failed to create a rootfs\n");
return err;
}
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
rootfs_initcall(default_rootfs);
+#endif
diff --git a/init/version.c b/init/version.c
index fe41a63..5606341 100644
--- a/init/version.c
+++ b/init/version.c
@@ -23,9 +23,7 @@ int version_string(LINUX_VERSION_CODE);
#endif
struct uts_namespace init_uts_ns = {
- .kref = {
- .refcount = ATOMIC_INIT(2),
- },
+ .kref = KREF_INIT(2),
.name = {
.sysname = UTS_SYSNAME,
.nodename = UTS_NODENAME,
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 3f7dc5f..b3f22e6 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -752,7 +752,7 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
}
mode &= ~current_umask();
- ret = vfs_create(dir, path->dentry, mode, true);
+ ret = vfs_create2(path->mnt, dir, path->dentry, mode, true);
path->dentry->d_fsdata = NULL;
if (ret)
return ERR_PTR(ret);
@@ -768,7 +768,7 @@ static struct file *do_open(struct path *path, int oflag)
if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
return ERR_PTR(-EINVAL);
acc = oflag2acc[oflag & O_ACCMODE];
- if (inode_permission(d_inode(path->dentry), acc))
+ if (inode_permission2(path->mnt, d_inode(path->dentry), acc))
return ERR_PTR(-EACCES);
return dentry_open(path, oflag, current_cred());
}
@@ -801,7 +801,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
ro = mnt_want_write(mnt); /* we'll drop it in any case */
error = 0;
inode_lock(d_inode(root));
- path.dentry = lookup_one_len(name->name, root, strlen(name->name));
+ path.dentry = lookup_one_len2(name->name, mnt, root, strlen(name->name));
if (IS_ERR(path.dentry)) {
error = PTR_ERR(path.dentry);
goto out_putfd;
@@ -872,7 +872,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
if (err)
goto out_name;
inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT);
- dentry = lookup_one_len(name->name, mnt->mnt_root,
+ dentry = lookup_one_len2(name->name, mnt, mnt->mnt_root,
strlen(name->name));
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -884,7 +884,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
err = -ENOENT;
} else {
ihold(inode);
- err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL);
+ err = vfs_unlink2(mnt, d_inode(dentry->d_parent), dentry, NULL);
}
dput(dentry);
diff --git a/kernel/Makefile b/kernel/Makefile
index 92488cf..24e64f8 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -33,6 +33,9 @@
# cond_syscall is currently not LTO compatible
CFLAGS_sys_ni.o = $(DISABLE_LTO)
+# Don't instrument error handlers
+CFLAGS_cfi.o = $(DISABLE_CFI_CLANG)
+
obj-y += sched/
obj-y += locking/
obj-y += power/
@@ -99,6 +102,7 @@
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-$(CONFIG_CPU_PM) += cpu_pm.o
obj-$(CONFIG_BPF) += bpf/
+obj-$(CONFIG_CFI_CLANG) += cfi.o
obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 5a590f2..ad110b5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,3 +6,4 @@
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
+obj-$(CONFIG_CGROUP_BPF) += cgroup.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index eb43f7e..b30ca0f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -16,6 +16,9 @@
#include <linux/filter.h>
#include <linux/perf_event.h>
+#define ARRAY_CREATE_FLAG_MASK \
+ (BPF_F_RDONLY | BPF_F_WRONLY)
+
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
@@ -57,7 +60,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size == 0 || attr->map_flags)
+ attr->value_size == 0 ||
+ attr->map_flags & ~ARRAY_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
new file mode 100644
index 0000000..54c47a9
--- /dev/null
+++ b/kernel/bpf/cgroup.c
@@ -0,0 +1,427 @@
+/*
+ * Functions to manage eBPF programs attached to cgroups
+ *
+ * Copyright (c) 2016 Daniel Mack
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License. See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
+#include <net/sock.h>
+
+DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
+EXPORT_SYMBOL(cgroup_bpf_enabled_key);
+
+/**
+ * cgroup_bpf_put() - put references of all bpf programs
+ * @cgrp: the cgroup to modify
+ */
+void cgroup_bpf_put(struct cgroup *cgrp)
+{
+ unsigned int type;
+
+ for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ struct bpf_prog_list *pl, *tmp;
+
+ list_for_each_entry_safe(pl, tmp, progs, node) {
+ list_del(&pl->node);
+ bpf_prog_put(pl->prog);
+ kfree(pl);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ }
+ bpf_prog_array_free(cgrp->bpf.effective[type]);
+ }
+}
+
+/* count number of elements in the list.
+ * it's slow but the list cannot be long
+ */
+static u32 prog_list_length(struct list_head *head)
+{
+ struct bpf_prog_list *pl;
+ u32 cnt = 0;
+
+ list_for_each_entry(pl, head, node) {
+ if (!pl->prog)
+ continue;
+ cnt++;
+ }
+ return cnt;
+}
+
+/* if parent has non-overridable prog attached,
+ * disallow attaching new programs to the descendent cgroup.
+ * if parent has overridable or multi-prog, allow attaching
+ */
+static bool hierarchy_allows_attach(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ u32 new_flags)
+{
+ struct cgroup *p;
+
+ p = cgroup_parent(cgrp);
+ if (!p)
+ return true;
+ do {
+ u32 flags = p->bpf.flags[type];
+ u32 cnt;
+
+ if (flags & BPF_F_ALLOW_MULTI)
+ return true;
+ cnt = prog_list_length(&p->bpf.progs[type]);
+ WARN_ON_ONCE(cnt > 1);
+ if (cnt == 1)
+ return !!(flags & BPF_F_ALLOW_OVERRIDE);
+ p = cgroup_parent(p);
+ } while (p);
+ return true;
+}
+
+/* compute a chain of effective programs for a given cgroup:
+ * start from the list of programs in this cgroup and add
+ * all parent programs.
+ * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
+ * to programs in this cgroup
+ */
+static int compute_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ struct bpf_prog_array __rcu **array)
+{
+ struct bpf_prog_array __rcu *progs;
+ struct bpf_prog_list *pl;
+ struct cgroup *p = cgrp;
+ int cnt = 0;
+
+ /* count number of effective programs by walking parents */
+ do {
+ if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ cnt += prog_list_length(&p->bpf.progs[type]);
+ p = cgroup_parent(p);
+ } while (p);
+
+ progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+ if (!progs)
+ return -ENOMEM;
+
+ /* populate the array with effective progs */
+ cnt = 0;
+ p = cgrp;
+ do {
+ if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ list_for_each_entry(pl,
+ &p->bpf.progs[type], node) {
+ if (!pl->prog)
+ continue;
+ rcu_dereference_protected(progs, 1)->
+ progs[cnt++] = pl->prog;
+ }
+ p = cgroup_parent(p);
+ } while (p);
+
+ *array = progs;
+ return 0;
+}
+
+static void activate_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type,
+ struct bpf_prog_array __rcu *array)
+{
+ struct bpf_prog_array __rcu *old_array;
+
+ old_array = xchg(&cgrp->bpf.effective[type], array);
+ /* free prog array after grace period, since __cgroup_bpf_run_*()
+ * might be still walking the array
+ */
+ bpf_prog_array_free(old_array);
+}
+
+/**
+ * cgroup_bpf_inherit() - inherit effective programs from parent
+ * @cgrp: the cgroup to modify
+ */
+int cgroup_bpf_inherit(struct cgroup *cgrp)
+{
+/* has to use marco instead of const int, since compiler thinks
+ * that array below is variable length
+ */
+#define NR ARRAY_SIZE(cgrp->bpf.effective)
+ struct bpf_prog_array __rcu *arrays[NR] = {};
+ int i;
+
+ for (i = 0; i < NR; i++)
+ INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
+
+ for (i = 0; i < NR; i++)
+ if (compute_effective_progs(cgrp, i, &arrays[i]))
+ goto cleanup;
+
+ for (i = 0; i < NR; i++)
+ activate_effective_progs(cgrp, i, arrays[i]);
+
+ return 0;
+cleanup:
+ for (i = 0; i < NR; i++)
+ bpf_prog_array_free(arrays[i]);
+ return -ENOMEM;
+}
+
+#define BPF_CGROUP_MAX_PROGS 64
+
+/**
+ * __cgroup_bpf_attach() - Attach the program to a cgroup, and
+ * propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to attach
+ * @type: Type of attach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ struct bpf_prog *old_prog = NULL;
+ struct cgroup_subsys_state *css;
+ struct bpf_prog_list *pl;
+ bool pl_was_allocated;
+ u32 old_flags;
+ int err;
+
+ if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+ /* invalid combination */
+ return -EINVAL;
+
+ if (!hierarchy_allows_attach(cgrp, type, flags))
+ return -EPERM;
+
+ if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+ /* Disallow attaching non-overridable on top
+ * of existing overridable in this cgroup.
+ * Disallow attaching multi-prog if overridable or none
+ */
+ return -EPERM;
+
+ if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+ return -E2BIG;
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ list_for_each_entry(pl, progs, node)
+ if (pl->prog == prog)
+ /* disallow attaching the same prog twice */
+ return -EINVAL;
+
+ pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+ if (!pl)
+ return -ENOMEM;
+ pl_was_allocated = true;
+ pl->prog = prog;
+ list_add_tail(&pl->node, progs);
+ } else {
+ if (list_empty(progs)) {
+ pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+ if (!pl)
+ return -ENOMEM;
+ pl_was_allocated = true;
+ list_add_tail(&pl->node, progs);
+ } else {
+ pl = list_first_entry(progs, typeof(*pl), node);
+ old_prog = pl->prog;
+ pl_was_allocated = false;
+ }
+ pl->prog = prog;
+ }
+
+ old_flags = cgrp->bpf.flags[type];
+ cgrp->bpf.flags[type] = flags;
+
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
+ }
+
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ static_branch_inc(&cgroup_bpf_enabled_key);
+ if (old_prog) {
+ bpf_prog_put(old_prog);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ }
+ return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* and cleanup the prog list */
+ pl->prog = old_prog;
+ if (pl_was_allocated) {
+ list_del(&pl->node);
+ kfree(pl);
+ }
+ return err;
+}
+
+/**
+ * __cgroup_bpf_detach() - Detach the program from a cgroup, and
+ * propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to detach or NULL
+ * @type: Type of detach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 unused_flags)
+{
+ struct list_head *progs = &cgrp->bpf.progs[type];
+ u32 flags = cgrp->bpf.flags[type];
+ struct bpf_prog *old_prog = NULL;
+ struct cgroup_subsys_state *css;
+ struct bpf_prog_list *pl;
+ int err;
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ if (!prog)
+ /* to detach MULTI prog the user has to specify valid FD
+ * of the program to be detached
+ */
+ return -EINVAL;
+ } else {
+ if (list_empty(progs))
+ /* report error when trying to detach and nothing is attached */
+ return -ENOENT;
+ }
+
+ if (flags & BPF_F_ALLOW_MULTI) {
+ /* find the prog and detach it */
+ list_for_each_entry(pl, progs, node) {
+ if (pl->prog != prog)
+ continue;
+ old_prog = prog;
+ /* mark it deleted, so it's ignored while
+ * recomputing effective
+ */
+ pl->prog = NULL;
+ break;
+ }
+ if (!old_prog)
+ return -ENOENT;
+ } else {
+ /* to maintain backward compatibility NONE and OVERRIDE cgroups
+ * allow detaching with invalid FD (prog==NULL)
+ */
+ pl = list_first_entry(progs, typeof(*pl), node);
+ old_prog = pl->prog;
+ pl->prog = NULL;
+ }
+
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
+ }
+
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* now can actually delete it from this cgroup list */
+ list_del(&pl->node);
+ kfree(pl);
+ if (list_empty(progs))
+ /* last program was detached, reset flags to zero */
+ cgrp->bpf.flags[type] = 0;
+
+ bpf_prog_put(old_prog);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ /* and restore back old_prog */
+ pl->prog = old_prog;
+ return err;
+}
+
+/**
+ * __cgroup_bpf_run_filter() - Run a program for packet filtering
+ * @sk: The socket sending or receiving traffic
+ * @skb: The skb that is being sent or received
+ * @type: The type of program to be exectuted
+ *
+ * If no socket is passed, or the socket is not of type INET or INET6,
+ * this function does nothing and returns 0.
+ *
+ * The program type passed in via @type must be suitable for network
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter(struct sock *sk,
+ struct sk_buff *skb,
+ enum bpf_attach_type type)
+{
+ unsigned int offset = skb->data - skb_network_header(skb);
+ struct sock *save_sk;
+ struct cgroup *cgrp;
+ int ret;
+
+ if (!sk || !sk_fullsock(sk))
+ return 0;
+
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+ return 0;
+
+ cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ save_sk = skb->sk;
+ skb->sk = sk;
+ __skb_push(skb, offset);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
+ bpf_prog_run_save_cb);
+ __skb_pull(skb, offset);
+ skb->sk = save_sk;
+ return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index df2ebce..8def8ae 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -520,7 +520,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
*
* Decode and execute eBPF instructions.
*/
-static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
+static unsigned int __bpf_prog_run(const struct sk_buff *ctx, const struct bpf_insn *insn)
{
u64 stack[MAX_BPF_STACK / sizeof(u64)];
u64 regs[MAX_BPF_REG], tmp;
@@ -1069,6 +1069,118 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
+static unsigned int __bpf_prog_ret1(const struct sk_buff *ctx,
+ const struct bpf_insn *insn)
+{
+ return 1;
+}
+
+static struct bpf_prog_dummy {
+ struct bpf_prog prog;
+} dummy_bpf_prog = {
+ .prog = {
+ .bpf_func = __bpf_prog_ret1,
+ },
+};
+
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+ struct bpf_prog_array hdr;
+ struct bpf_prog *null_prog;
+} empty_prog_array = {
+ .null_prog = NULL,
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+ if (prog_cnt)
+ return kzalloc(sizeof(struct bpf_prog_array) +
+ sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ flags);
+
+ return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+ if (!progs ||
+ progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+ return;
+ kfree_rcu(progs, rcu);
+}
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+ struct bpf_prog *old_prog)
+{
+ struct bpf_prog **prog = progs->progs;
+
+ for (; *prog; prog++)
+ if (*prog == old_prog) {
+ WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ break;
+ }
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array)
+{
+ int new_prog_cnt, carry_prog_cnt = 0;
+ struct bpf_prog **existing_prog;
+ struct bpf_prog_array *array;
+ int new_prog_idx = 0;
+
+ /* Figure out how many existing progs we need to carry over to
+ * the new array.
+ */
+ if (old_array) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++) {
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ carry_prog_cnt++;
+ if (*existing_prog == include_prog)
+ return -EEXIST;
+ }
+ }
+
+ /* How many progs (not NULL) will be in the new array? */
+ new_prog_cnt = carry_prog_cnt;
+ if (include_prog)
+ new_prog_cnt += 1;
+
+ /* Do we have any prog (not NULL) in the new array? */
+ if (!new_prog_cnt) {
+ *new_array = NULL;
+ return 0;
+ }
+
+ /* +1 as the end of prog_array is marked with NULL */
+ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
+ if (!array)
+ return -ENOMEM;
+
+ /* Fill in the new prog array */
+ if (carry_prog_cnt) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++)
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ array->progs[new_prog_idx++] = *existing_prog;
+ }
+ if (include_prog)
+ array->progs[new_prog_idx++] = include_prog;
+ array->progs[new_prog_idx] = NULL;
+ *new_array = array;
+ return 0;
+}
+
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 1253261..998f746 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -15,6 +15,8 @@
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include "percpu_freelist.h"
+#define HTAB_CREATE_FLAG_MASK \
+ (BPF_F_NO_PREALLOC | BPF_F_RDONLY | BPF_F_WRONLY)
struct bucket {
struct hlist_nulls_head head;
@@ -161,7 +163,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
offsetof(struct htab_elem, hash_node.pprev));
- if (attr->map_flags & ~BPF_F_NO_PREALLOC)
+ if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
/* reserved bits should not be used */
return ERR_PTR(-EINVAL);
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1ed8473..002a0b9 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -255,7 +255,7 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
}
static void *bpf_obj_do_get(const struct filename *pathname,
- enum bpf_type *type)
+ enum bpf_type *type, int flags)
{
struct inode *inode;
struct path path;
@@ -267,7 +267,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
return ERR_PTR(ret);
inode = d_backing_inode(path.dentry);
- ret = inode_permission(inode, MAY_WRITE);
+ ret = inode_permission(inode, ACC_MODE(flags));
if (ret)
goto out;
@@ -286,18 +286,23 @@ static void *bpf_obj_do_get(const struct filename *pathname,
return ERR_PTR(ret);
}
-int bpf_obj_get_user(const char __user *pathname)
+int bpf_obj_get_user(const char __user *pathname, int flags)
{
enum bpf_type type = BPF_TYPE_UNSPEC;
struct filename *pname;
int ret = -ENOENT;
+ int f_flags;
void *raw;
+ f_flags = bpf_get_file_flag(flags);
+ if (f_flags < 0)
+ return f_flags;
+
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
- raw = bpf_obj_do_get(pname, &type);
+ raw = bpf_obj_do_get(pname, &type, f_flags);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
@@ -306,7 +311,7 @@ int bpf_obj_get_user(const char __user *pathname)
if (type == BPF_TYPE_PROG)
ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
- ret = bpf_map_new_fd(raw);
+ ret = bpf_map_new_fd(raw, f_flags);
else
goto out;
@@ -317,6 +322,42 @@ int bpf_obj_get_user(const char __user *pathname)
return ret;
}
+static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
+{
+ struct bpf_prog *prog;
+ int ret = inode_permission(inode, MAY_READ);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (inode->i_op == &bpf_map_iops)
+ return ERR_PTR(-EINVAL);
+ if (inode->i_op != &bpf_prog_iops)
+ return ERR_PTR(-EACCES);
+
+ prog = inode->i_private;
+
+ ret = security_bpf_prog(prog);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ return bpf_prog_inc(prog);
+}
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
+{
+ struct bpf_prog *prog;
+ struct path path;
+ int ret = kern_path(name, LOOKUP_FOLLOW, &path);
+ if (ret)
+ return ERR_PTR(ret);
+ prog = __get_prog_inode(d_backing_inode(path.dentry), type);
+ if (!IS_ERR(prog))
+ touch_atime(&path);
+ path_put(&path);
+ return prog;
+}
+EXPORT_SYMBOL(bpf_prog_get_type_path);
+
static void bpf_evict_inode(struct inode *inode)
{
enum bpf_type type;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a2a232d..6039db3 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -11,6 +11,9 @@
#include <linux/perf_event.h>
#include "percpu_freelist.h"
+#define STACK_CREATE_FLAG_MASK \
+ (BPF_F_RDONLY | BPF_F_WRONLY)
+
struct stack_map_bucket {
struct pcpu_freelist_node fnode;
u32 hash;
@@ -59,7 +62,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
- if (attr->map_flags)
+ if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
/* check sanity of attributes */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e103142..c92cf06 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -20,6 +20,8 @@
#include <linux/filter.h>
#include <linux/version.h>
+#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY)
+
DEFINE_PER_CPU(int, bpf_prog_active);
int sysctl_unprivileged_bpf_disabled __read_mostly;
@@ -119,6 +121,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
struct bpf_map *map = container_of(work, struct bpf_map, work);
bpf_map_uncharge_memlock(map);
+ security_bpf_map_free(map);
/* implementation dependent freeing */
map->ops->map_free(map);
}
@@ -178,17 +181,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
}
#endif
-static const struct file_operations bpf_map_fops = {
+static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,
+ loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_READ.
+ */
+ return -EINVAL;
+}
+
+static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
+ size_t siz, loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_WRITE.
+ */
+ return -EINVAL;
+}
+
+const struct file_operations bpf_map_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = bpf_map_show_fdinfo,
#endif
.release = bpf_map_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
};
-int bpf_map_new_fd(struct bpf_map *map)
+int bpf_map_new_fd(struct bpf_map *map, int flags)
{
+ int ret;
+
+ ret = security_bpf_map(map, OPEN_FMODE(flags));
+ if (ret < 0)
+ return ret;
+
return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
- O_RDWR | O_CLOEXEC);
+ flags | O_CLOEXEC);
+}
+
+int bpf_get_file_flag(int flags)
+{
+ if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))
+ return -EINVAL;
+ if (flags & BPF_F_RDONLY)
+ return O_RDONLY;
+ if (flags & BPF_F_WRONLY)
+ return O_WRONLY;
+ return O_RDWR;
}
/* helper macro to check that unused fields 'union bpf_attr' are zero */
@@ -204,12 +244,17 @@ int bpf_map_new_fd(struct bpf_map *map)
static int map_create(union bpf_attr *attr)
{
struct bpf_map *map;
+ int f_flags;
int err;
err = CHECK_ATTR(BPF_MAP_CREATE);
if (err)
return -EINVAL;
+ f_flags = bpf_get_file_flag(attr->map_flags);
+ if (f_flags < 0)
+ return f_flags;
+
/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
map = find_and_alloc_map(attr);
if (IS_ERR(map))
@@ -218,11 +263,15 @@ static int map_create(union bpf_attr *attr)
atomic_set(&map->refcnt, 1);
atomic_set(&map->usercnt, 1);
- err = bpf_map_charge_memlock(map);
+ err = security_bpf_map_alloc(map);
if (err)
goto free_map_nouncharge;
- err = bpf_map_new_fd(map);
+ err = bpf_map_charge_memlock(map);
+ if (err)
+ goto free_map_sec;
+
+ err = bpf_map_new_fd(map, f_flags);
if (err < 0)
/* failed to allocate fd */
goto free_map;
@@ -231,6 +280,8 @@ static int map_create(union bpf_attr *attr)
free_map:
bpf_map_uncharge_memlock(map);
+free_map_sec:
+ security_bpf_map_free(map);
free_map_nouncharge:
map->ops->map_free(map);
return err;
@@ -313,6 +364,11 @@ static int map_lookup_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
@@ -387,6 +443,11 @@ static int map_update_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
@@ -463,6 +524,11 @@ static int map_delete_elem(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
@@ -508,6 +574,11 @@ static int map_get_next_key(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
if (ukey) {
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
@@ -611,6 +682,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
free_used_maps(aux);
bpf_prog_uncharge_memlock(aux->prog);
+ security_bpf_prog_free(aux);
bpf_prog_free(aux->prog);
}
@@ -629,12 +701,20 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
return 0;
}
-static const struct file_operations bpf_prog_fops = {
+const struct file_operations bpf_prog_fops = {
.release = bpf_prog_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
};
int bpf_prog_new_fd(struct bpf_prog *prog)
{
+ int ret;
+
+ ret = security_bpf_prog(prog);
+ if (ret < 0)
+ return ret;
+
return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
O_RDWR | O_CLOEXEC);
}
@@ -726,7 +806,9 @@ static int bpf_prog_load(union bpf_attr *attr)
attr->kern_version != LINUX_VERSION_CODE)
return -EINVAL;
- if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN))
+ if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
+ type != BPF_PROG_TYPE_CGROUP_SKB &&
+ !capable(CAP_SYS_ADMIN))
return -EPERM;
/* plain bpf_prog allocation */
@@ -734,10 +816,14 @@ static int bpf_prog_load(union bpf_attr *attr)
if (!prog)
return -ENOMEM;
- err = bpf_prog_charge_memlock(prog);
+ err = security_bpf_prog_alloc(prog->aux);
if (err)
goto free_prog_nouncharge;
+ err = bpf_prog_charge_memlock(prog);
+ if (err)
+ goto free_prog_sec;
+
prog->len = attr->insn_cnt;
err = -EFAULT;
@@ -777,16 +863,18 @@ static int bpf_prog_load(union bpf_attr *attr)
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
+free_prog_sec:
+ security_bpf_prog_free(prog->aux);
free_prog_nouncharge:
bpf_prog_free(prog);
return err;
}
-#define BPF_OBJ_LAST_FIELD bpf_fd
+#define BPF_OBJ_LAST_FIELD file_flags
static int bpf_obj_pin(const union bpf_attr *attr)
{
- if (CHECK_ATTR(BPF_OBJ))
+ if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0)
return -EINVAL;
return bpf_obj_pin_user(attr->bpf_fd, u64_to_ptr(attr->pathname));
@@ -794,12 +882,105 @@ static int bpf_obj_pin(const union bpf_attr *attr)
static int bpf_obj_get(const union bpf_attr *attr)
{
- if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
+ if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 ||
+ attr->file_flags & ~BPF_OBJ_FLAG_MASK)
return -EINVAL;
- return bpf_obj_get_user(u64_to_ptr(attr->pathname));
+ return bpf_obj_get_user(u64_to_ptr(attr->pathname),
+ attr->file_flags);
}
+#ifdef CONFIG_CGROUP_BPF
+
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
+
+#define BPF_F_ATTACH_MASK \
+ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+
+static int bpf_prog_attach(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (CHECK_ATTR(BPF_PROG_ATTACH))
+ return -EINVAL;
+
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
+ return -EINVAL;
+
+ switch (attr->attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ prog = bpf_prog_get_type(attr->attach_bpf_fd,
+ BPF_PROG_TYPE_CGROUP_SKB);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp)) {
+ bpf_prog_put(prog);
+ return PTR_ERR(cgrp);
+ }
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ if (ret)
+ bpf_prog_put(prog);
+ cgroup_put(cgrp);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
+#define BPF_PROG_DETACH_LAST_FIELD attach_type
+
+static int bpf_prog_detach(const union bpf_attr *attr)
+{
+ enum bpf_prog_type ptype;
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (CHECK_ATTR(BPF_PROG_DETACH))
+ return -EINVAL;
+
+ switch (attr->attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ ptype = BPF_PROG_TYPE_CGROUP_SKB;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+ cgroup_put(cgrp);
+ return ret;
+}
+#endif /* CONFIG_CGROUP_BPF */
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr;
@@ -842,6 +1023,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
+ err = security_bpf(cmd, &attr, size);
+ if (err < 0)
+ return err;
+
switch (cmd) {
case BPF_MAP_CREATE:
err = map_create(&attr);
@@ -867,6 +1052,16 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
+
+#ifdef CONFIG_CGROUP_BPF
+ case BPF_PROG_ATTACH:
+ err = bpf_prog_attach(&attr);
+ break;
+ case BPF_PROG_DETACH:
+ err = bpf_prog_detach(&attr);
+ break;
+#endif
+
default:
err = -EINVAL;
break;
diff --git a/kernel/cfi.c b/kernel/cfi.c
new file mode 100644
index 0000000..5ea5da9
--- /dev/null
+++ b/kernel/cfi.c
@@ -0,0 +1,306 @@
+/*
+ * CFI (Control Flow Integrity) error and slowpath handling
+ *
+ * Copyright (C) 2017 Google, Inc.
+ */
+
+#include <linux/gfp.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/ratelimit.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+#include <asm/bug.h>
+#include <asm/cacheflush.h>
+#include <asm/memory.h>
+
+/* Compiler-defined handler names */
+#ifdef CONFIG_CFI_PERMISSIVE
+#define cfi_failure_handler __ubsan_handle_cfi_check_fail
+#define cfi_slowpath_handler __cfi_slowpath_diag
+#else /* enforcing */
+#define cfi_failure_handler __ubsan_handle_cfi_check_fail_abort
+#define cfi_slowpath_handler __cfi_slowpath
+#endif /* CONFIG_CFI_PERMISSIVE */
+
+static inline void handle_cfi_failure(void *ptr)
+{
+#ifdef CONFIG_CFI_PERMISSIVE
+ WARN_RATELIMIT(1, "CFI failure (target: [<%px>] %pF):\n", ptr, ptr);
+#else
+ pr_err("CFI failure (target: [<%px>] %pF):\n", ptr, ptr);
+ BUG();
+#endif
+}
+
+#ifdef CONFIG_MODULES
+#ifdef CONFIG_CFI_CLANG_SHADOW
+struct shadow_range {
+ /* Module address range */
+ unsigned long mod_min_addr;
+ unsigned long mod_max_addr;
+ /* Module page range */
+ unsigned long min_page;
+ unsigned long max_page;
+};
+
+#define SHADOW_ORDER 1
+#define SHADOW_PAGES (1 << SHADOW_ORDER)
+#define SHADOW_SIZE \
+ ((SHADOW_PAGES * PAGE_SIZE - sizeof(struct shadow_range)) / sizeof(u16))
+#define SHADOW_INVALID 0xFFFF
+
+struct cfi_shadow {
+ /* Page range covered by the shadow */
+ struct shadow_range r;
+ /* Page offsets to __cfi_check functions in modules */
+ u16 shadow[SHADOW_SIZE];
+};
+
+static DEFINE_SPINLOCK(shadow_update_lock);
+static struct cfi_shadow __rcu *cfi_shadow __read_mostly = NULL;
+
+static inline int ptr_to_shadow(const struct cfi_shadow *s, unsigned long ptr)
+{
+ unsigned long index;
+ unsigned long page = ptr >> PAGE_SHIFT;
+
+ if (unlikely(page < s->r.min_page))
+ return -1; /* Outside of module area */
+
+ index = page - s->r.min_page;
+
+ if (index >= SHADOW_SIZE)
+ return -1; /* Cannot be addressed with shadow */
+
+ return (int)index;
+}
+
+static inline unsigned long shadow_to_ptr(const struct cfi_shadow *s,
+ int index)
+{
+ BUG_ON(index < 0 || index >= SHADOW_SIZE);
+
+ if (unlikely(s->shadow[index] == SHADOW_INVALID))
+ return 0;
+
+ return (s->r.min_page + s->shadow[index]) << PAGE_SHIFT;
+}
+
+static inline unsigned long shadow_to_page(const struct cfi_shadow *s,
+ int index)
+{
+ BUG_ON(index < 0 || index >= SHADOW_SIZE);
+
+ return (s->r.min_page + index) << PAGE_SHIFT;
+}
+
+static void prepare_next_shadow(const struct cfi_shadow __rcu *prev,
+ struct cfi_shadow *next)
+{
+ int i, index, check;
+
+ /* Mark everything invalid */
+ memset(next->shadow, 0xFF, sizeof(next->shadow));
+
+ if (!prev)
+ return; /* No previous shadow */
+
+ /* If the base address didn't change, update is not needed */
+ if (prev->r.min_page == next->r.min_page) {
+ memcpy(next->shadow, prev->shadow, sizeof(next->shadow));
+ return;
+ }
+
+ /* Convert the previous shadow to the new address range */
+ for (i = 0; i < SHADOW_SIZE; ++i) {
+ if (prev->shadow[i] == SHADOW_INVALID)
+ continue;
+
+ index = ptr_to_shadow(next, shadow_to_page(prev, i));
+ if (index < 0)
+ continue;
+
+ check = ptr_to_shadow(next,
+ shadow_to_ptr(prev, prev->shadow[i]));
+ if (check < 0)
+ continue;
+
+ next->shadow[index] = (u16)check;
+ }
+}
+
+static void add_module_to_shadow(struct cfi_shadow *s, struct module *mod)
+{
+ unsigned long ptr;
+ unsigned long min_page_addr;
+ unsigned long max_page_addr;
+ unsigned long check = (unsigned long)mod->cfi_check;
+ int check_index = ptr_to_shadow(s, check);
+
+ BUG_ON((check & PAGE_MASK) != check); /* Must be page aligned */
+
+ if (check_index < 0)
+ return; /* Module not addressable with shadow */
+
+ min_page_addr = (unsigned long)mod->core_layout.base & PAGE_MASK;
+ max_page_addr = (unsigned long)mod->core_layout.base +
+ mod->core_layout.text_size;
+ max_page_addr &= PAGE_MASK;
+
+ /* For each page, store the check function index in the shadow */
+ for (ptr = min_page_addr; ptr <= max_page_addr; ptr += PAGE_SIZE) {
+ int index = ptr_to_shadow(s, ptr);
+ if (index >= 0) {
+ /* Assume a page only contains code for one module */
+ BUG_ON(s->shadow[index] != SHADOW_INVALID);
+ s->shadow[index] = (u16)check_index;
+ }
+ }
+}
+
+static void remove_module_from_shadow(struct cfi_shadow *s, struct module *mod)
+{
+ unsigned long ptr;
+ unsigned long min_page_addr;
+ unsigned long max_page_addr;
+
+ min_page_addr = (unsigned long)mod->core_layout.base & PAGE_MASK;
+ max_page_addr = (unsigned long)mod->core_layout.base +
+ mod->core_layout.text_size;
+ max_page_addr &= PAGE_MASK;
+
+ for (ptr = min_page_addr; ptr <= max_page_addr; ptr += PAGE_SIZE) {
+ int index = ptr_to_shadow(s, ptr);
+ if (index >= 0)
+ s->shadow[index] = SHADOW_INVALID;
+ }
+}
+
+typedef void (*update_shadow_fn)(struct cfi_shadow *, struct module *);
+
+static void update_shadow(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr, update_shadow_fn fn)
+{
+ struct cfi_shadow *prev;
+ struct cfi_shadow *next = (struct cfi_shadow *)
+ __get_free_pages(GFP_KERNEL, SHADOW_ORDER);
+
+ BUG_ON(!next);
+
+ next->r.mod_min_addr = min_addr;
+ next->r.mod_max_addr = max_addr;
+ next->r.min_page = min_addr >> PAGE_SHIFT;
+ next->r.max_page = max_addr >> PAGE_SHIFT;
+
+ spin_lock(&shadow_update_lock);
+ prev = rcu_dereference_protected(cfi_shadow, 1);
+ prepare_next_shadow(prev, next);
+
+ fn(next, mod);
+ set_memory_ro((unsigned long)next, SHADOW_PAGES);
+ rcu_assign_pointer(cfi_shadow, next);
+
+ spin_unlock(&shadow_update_lock);
+ synchronize_rcu();
+
+ if (prev) {
+ set_memory_rw((unsigned long)prev, SHADOW_PAGES);
+ free_pages((unsigned long)prev, SHADOW_ORDER);
+ }
+}
+
+void cfi_module_add(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr)
+{
+ update_shadow(mod, min_addr, max_addr, add_module_to_shadow);
+}
+EXPORT_SYMBOL(cfi_module_add);
+
+void cfi_module_remove(struct module *mod, unsigned long min_addr,
+ unsigned long max_addr)
+{
+ update_shadow(mod, min_addr, max_addr, remove_module_from_shadow);
+}
+EXPORT_SYMBOL(cfi_module_remove);
+
+static inline cfi_check_fn ptr_to_check_fn(const struct cfi_shadow __rcu *s,
+ unsigned long ptr)
+{
+ int index;
+
+ if (unlikely(!s))
+ return NULL; /* No shadow available */
+
+ if (ptr < s->r.mod_min_addr || ptr > s->r.mod_max_addr)
+ return NULL; /* Not in a mapped module */
+
+ index = ptr_to_shadow(s, ptr);
+ if (index < 0)
+ return NULL; /* Cannot be addressed with shadow */
+
+ return (cfi_check_fn)shadow_to_ptr(s, index);
+}
+#endif /* CONFIG_CFI_CLANG_SHADOW */
+
+static inline cfi_check_fn find_module_cfi_check(void *ptr)
+{
+ struct module *mod;
+
+ preempt_disable();
+ mod = __module_address((unsigned long)ptr);
+ preempt_enable();
+
+ if (mod)
+ return mod->cfi_check;
+
+ return CFI_CHECK_FN;
+}
+
+static inline cfi_check_fn find_cfi_check(void *ptr)
+{
+#ifdef CONFIG_CFI_CLANG_SHADOW
+ cfi_check_fn f;
+
+ if (!rcu_access_pointer(cfi_shadow))
+ return CFI_CHECK_FN; /* No loaded modules */
+
+ /* Look up the __cfi_check function to use */
+ rcu_read_lock();
+ f = ptr_to_check_fn(rcu_dereference(cfi_shadow), (unsigned long)ptr);
+ rcu_read_unlock();
+
+ if (f)
+ return f;
+
+ /*
+ * Fall back to find_module_cfi_check, which works also for a larger
+ * module address space, but is slower.
+ */
+#endif /* CONFIG_CFI_CLANG_SHADOW */
+
+ return find_module_cfi_check(ptr);
+}
+
+void cfi_slowpath_handler(uint64_t id, void *ptr, void *diag)
+{
+ cfi_check_fn check = find_cfi_check(ptr);
+
+ if (likely(check))
+ check(id, ptr, diag);
+ else /* Don't allow unchecked modules */
+ handle_cfi_failure(ptr);
+}
+EXPORT_SYMBOL(cfi_slowpath_handler);
+#endif /* CONFIG_MODULES */
+
+void cfi_failure_handler(void *data, void *ptr, void *vtable)
+{
+ handle_cfi_failure(ptr);
+}
+EXPORT_SYMBOL(cfi_failure_handler);
+
+void __cfi_check_fail(void *data, void *ptr)
+{
+ handle_cfi_failure(ptr);
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 684d02f..c0af0af 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -62,6 +62,7 @@
#include <linux/proc_ns.h>
#include <linux/nsproxy.h>
#include <linux/file.h>
+#include <linux/psi.h>
#include <net/sock.h>
#define CREATE_TRACE_POINTS
@@ -361,15 +362,6 @@ static void cgroup_idr_remove(struct idr *idr, int id)
spin_unlock_bh(&cgroup_idr_lock);
}
-static struct cgroup *cgroup_parent(struct cgroup *cgrp)
-{
- struct cgroup_subsys_state *parent_css = cgrp->self.parent;
-
- if (parent_css)
- return container_of(parent_css, struct cgroup, self);
- return NULL;
-}
-
/* subsystems visibly enabled on a cgroup */
static u16 cgroup_control(struct cgroup *cgrp)
{
@@ -487,17 +479,6 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
return !(cgrp->self.flags & CSS_ONLINE);
}
-static void cgroup_get(struct cgroup *cgrp)
-{
- WARN_ON_ONCE(cgroup_is_dead(cgrp));
- css_get(&cgrp->self);
-}
-
-static bool cgroup_tryget(struct cgroup *cgrp)
-{
- return css_tryget(&cgrp->self);
-}
-
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
{
struct cgroup *cgrp = of->kn->parent->priv;
@@ -781,7 +762,7 @@ static void css_set_move_task(struct task_struct *task,
*/
WARN_ON_ONCE(task->flags & PF_EXITING);
- rcu_assign_pointer(task->cgroups, to_cset);
+ cgroup_move_task(task, to_cset);
list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
&to_cset->tasks);
}
@@ -2039,6 +2020,9 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
if (ret)
goto destroy_root;
+ ret = cgroup_bpf_inherit(root_cgrp);
+ WARN_ON_ONCE(ret);
+
trace_cgroup_setup_root(root);
/*
@@ -2856,7 +2840,8 @@ static int cgroup_procs_write_permission(struct task_struct *task,
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
+ !uid_eq(cred->euid, tcred->suid) &&
+ !ns_capable(tcred->user_ns, CAP_SYS_NICE))
ret = -EACCES;
if (!ret && cgroup_on_dfl(dst_cgrp)) {
@@ -3504,6 +3489,96 @@ static int cgroup_events_show(struct seq_file *seq, void *v)
return 0;
}
+#ifdef CONFIG_PSI
+static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO);
+}
+static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM);
+}
+static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, enum psi_res res)
+{
+ struct psi_trigger *new;
+ struct cgroup *cgrp;
+
+ cgrp = cgroup_kn_lock_live(of->kn, false);
+ if (!cgrp)
+ return -ENODEV;
+
+ cgroup_get(cgrp);
+ cgroup_kn_unlock(of->kn);
+
+ new = psi_trigger_create(&cgrp->psi, buf, nbytes, res);
+ if (IS_ERR(new)) {
+ cgroup_put(cgrp);
+ return PTR_ERR(new);
+ }
+
+ psi_trigger_replace(&of->priv, new);
+
+ cgroup_put(cgrp);
+
+ return nbytes;
+}
+
+static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cgroup_pressure_write(of, buf, nbytes, PSI_IO);
+}
+
+static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cgroup_pressure_write(of, buf, nbytes, PSI_MEM);
+}
+
+static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
+}
+
+static unsigned int cgroup_pressure_poll(struct kernfs_open_file *of,
+ poll_table *pt)
+{
+ return psi_trigger_poll(&of->priv, of->file, pt);
+}
+
+static void cgroup_pressure_release(struct kernfs_open_file *of)
+{
+ psi_trigger_replace(&of->priv, NULL);
+}
+#endif /* CONFIG_PSI */
+
+static int cgroup_file_open(struct kernfs_open_file *of)
+{
+ struct cftype *cft = of->kn->priv;
+
+ if (cft->open)
+ return cft->open(of);
+ return 0;
+}
+
+static void cgroup_file_release(struct kernfs_open_file *of)
+{
+ struct cftype *cft = of->kn->priv;
+
+ if (cft->release)
+ cft->release(of);
+}
+
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
@@ -3542,6 +3617,16 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
return ret ?: nbytes;
}
+static unsigned int cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
+{
+ struct cftype *cft = of->kn->priv;
+
+ if (cft->poll)
+ return cft->poll(of, pt);
+
+ return kernfs_generic_poll(of, pt);
+}
+
static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
return seq_cft(seq)->seq_start(seq, ppos);
@@ -3554,7 +3639,8 @@ static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
- seq_cft(seq)->seq_stop(seq, v);
+ if (seq_cft(seq)->seq_stop)
+ seq_cft(seq)->seq_stop(seq, v);
}
static int cgroup_seqfile_show(struct seq_file *m, void *arg)
@@ -3576,13 +3662,19 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
static struct kernfs_ops cgroup_kf_single_ops = {
.atomic_write_len = PAGE_SIZE,
+ .open = cgroup_file_open,
+ .release = cgroup_file_release,
.write = cgroup_file_write,
+ .poll = cgroup_file_poll,
.seq_show = cgroup_seqfile_show,
};
static struct kernfs_ops cgroup_kf_ops = {
.atomic_write_len = PAGE_SIZE,
+ .open = cgroup_file_open,
+ .release = cgroup_file_release,
.write = cgroup_file_write,
+ .poll = cgroup_file_poll,
.seq_start = cgroup_seqfile_start,
.seq_next = cgroup_seqfile_next,
.seq_stop = cgroup_seqfile_stop,
@@ -4919,6 +5011,32 @@ static struct cftype cgroup_dfl_base_files[] = {
.file_offset = offsetof(struct cgroup, events_file),
.seq_show = cgroup_events_show,
},
+#ifdef CONFIG_PSI
+ {
+ .name = "io.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_io_pressure_show,
+ .write = cgroup_io_pressure_write,
+ .poll = cgroup_pressure_poll,
+ .release = cgroup_pressure_release,
+ },
+ {
+ .name = "memory.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_memory_pressure_show,
+ .write = cgroup_memory_pressure_write,
+ .poll = cgroup_pressure_poll,
+ .release = cgroup_pressure_release,
+ },
+ {
+ .name = "cpu.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_cpu_pressure_show,
+ .write = cgroup_cpu_pressure_write,
+ .poll = cgroup_pressure_poll,
+ .release = cgroup_pressure_release,
+ },
+#endif /* CONFIG_PSI */
{ } /* terminate */
};
@@ -5024,6 +5142,8 @@ static void css_free_work_fn(struct work_struct *work)
*/
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
+ if (cgroup_on_dfl(cgrp))
+ psi_cgroup_free(cgrp);
kfree(cgrp);
} else {
/*
@@ -5079,6 +5199,8 @@ static void css_release_work_fn(struct work_struct *work)
if (cgrp->kn)
RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv,
NULL);
+
+ cgroup_bpf_put(cgrp);
}
mutex_unlock(&cgroup_mutex);
@@ -5261,6 +5383,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
+ ret = cgroup_bpf_inherit(cgrp);
+ if (ret)
+ goto out_idr_free;
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -5291,10 +5416,18 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
if (!cgroup_on_dfl(cgrp))
cgrp->subtree_control = cgroup_control(cgrp);
+ if (cgroup_on_dfl(cgrp)) {
+ ret = psi_cgroup_alloc(cgrp);
+ if (ret)
+ goto out_idr_free;
+ }
+
cgroup_propagate_control(cgrp);
return cgrp;
+out_idr_free:
+ cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_cancel_ref:
percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
@@ -6524,6 +6657,29 @@ static __init int cgroup_namespaces_init(void)
}
subsys_initcall(cgroup_namespaces_init);
+#ifdef CONFIG_CGROUP_BPF
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+#endif /* CONFIG_CGROUP_BPF */
+
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *
debug_css_alloc(struct cgroup_subsys_state *parent_css)
diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config
deleted file mode 100644
index 1a8f34f..0000000
--- a/kernel/configs/android-base.config
+++ /dev/null
@@ -1,149 +0,0 @@
-# KEEP ALPHABETICALLY SORTED
-# CONFIG_DEVKMEM is not set
-# CONFIG_DEVMEM is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_MODULES is not set
-# CONFIG_OABI_COMPAT is not set
-# CONFIG_SYSVIPC is not set
-CONFIG_ANDROID=y
-CONFIG_ANDROID_BINDER_IPC=y
-CONFIG_ANDROID_LOW_MEMORY_KILLER=y
-CONFIG_ARMV8_DEPRECATED=y
-CONFIG_ASHMEM=y
-CONFIG_AUDIT=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_DEBUG=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_CP15_BARRIER_EMULATION=y
-CONFIG_DEFAULT_SECURITY_SELINUX=y
-CONFIG_EMBEDDED=y
-CONFIG_FB=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_INET=y
-CONFIG_INET_DIAG_DESTROY=y
-CONFIG_INET_ESP=y
-CONFIG_INET_XFRM_MODE_TUNNEL=y
-CONFIG_IP6_NF_FILTER=y
-CONFIG_IP6_NF_IPTABLES=y
-CONFIG_IP6_NF_MANGLE=y
-CONFIG_IP6_NF_RAW=y
-CONFIG_IP6_NF_TARGET_REJECT=y
-CONFIG_IPV6=y
-CONFIG_IPV6_MIP6=y
-CONFIG_IPV6_MULTIPLE_TABLES=y
-CONFIG_IPV6_OPTIMISTIC_DAD=y
-CONFIG_IPV6_ROUTER_PREF=y
-CONFIG_IPV6_ROUTE_INFO=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_ARPFILTER=y
-CONFIG_IP_NF_ARPTABLES=y
-CONFIG_IP_NF_ARP_MANGLE=y
-CONFIG_IP_NF_FILTER=y
-CONFIG_IP_NF_IPTABLES=y
-CONFIG_IP_NF_MANGLE=y
-CONFIG_IP_NF_MATCH_AH=y
-CONFIG_IP_NF_MATCH_ECN=y
-CONFIG_IP_NF_MATCH_TTL=y
-CONFIG_IP_NF_NAT=y
-CONFIG_IP_NF_RAW=y
-CONFIG_IP_NF_SECURITY=y
-CONFIG_IP_NF_TARGET_MASQUERADE=y
-CONFIG_IP_NF_TARGET_NETMAP=y
-CONFIG_IP_NF_TARGET_REDIRECT=y
-CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_NET=y
-CONFIG_NETDEVICES=y
-CONFIG_NETFILTER=y
-CONFIG_NETFILTER_TPROXY=y
-CONFIG_NETFILTER_XT_MATCH_COMMENT=y
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
-CONFIG_NETFILTER_XT_MATCH_HELPER=y
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
-CONFIG_NETFILTER_XT_MATCH_LENGTH=y
-CONFIG_NETFILTER_XT_MATCH_LIMIT=y
-CONFIG_NETFILTER_XT_MATCH_MAC=y
-CONFIG_NETFILTER_XT_MATCH_MARK=y
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
-CONFIG_NETFILTER_XT_MATCH_POLICY=y
-CONFIG_NETFILTER_XT_MATCH_QUOTA=y
-CONFIG_NETFILTER_XT_MATCH_SOCKET=y
-CONFIG_NETFILTER_XT_MATCH_STATE=y
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
-CONFIG_NETFILTER_XT_MATCH_STRING=y
-CONFIG_NETFILTER_XT_MATCH_TIME=y
-CONFIG_NETFILTER_XT_MATCH_U32=y
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
-CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
-CONFIG_NETFILTER_XT_TARGET_MARK=y
-CONFIG_NETFILTER_XT_TARGET_NFLOG=y
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
-CONFIG_NETFILTER_XT_TARGET_SECMARK=y
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
-CONFIG_NETFILTER_XT_TARGET_TPROXY=y
-CONFIG_NETFILTER_XT_TARGET_TRACE=y
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_CLS_U32=y
-CONFIG_NET_EMATCH=y
-CONFIG_NET_EMATCH_U32=y
-CONFIG_NET_KEY=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_HTB=y
-CONFIG_NF_CONNTRACK=y
-CONFIG_NF_CONNTRACK_AMANDA=y
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CONNTRACK_FTP=y
-CONFIG_NF_CONNTRACK_H323=y
-CONFIG_NF_CONNTRACK_IPV4=y
-CONFIG_NF_CONNTRACK_IPV6=y
-CONFIG_NF_CONNTRACK_IRC=y
-CONFIG_NF_CONNTRACK_NETBIOS_NS=y
-CONFIG_NF_CONNTRACK_PPTP=y
-CONFIG_NF_CONNTRACK_SANE=y
-CONFIG_NF_CONNTRACK_SECMARK=y
-CONFIG_NF_CONNTRACK_TFTP=y
-CONFIG_NF_CT_NETLINK=y
-CONFIG_NF_CT_PROTO_DCCP=y
-CONFIG_NF_CT_PROTO_SCTP=y
-CONFIG_NF_CT_PROTO_UDPLITE=y
-CONFIG_NF_NAT=y
-CONFIG_NO_HZ=y
-CONFIG_PACKET=y
-CONFIG_PM_AUTOSLEEP=y
-CONFIG_PM_WAKELOCKS=y
-CONFIG_PPP=y
-CONFIG_PPP_BSDCOMP=y
-CONFIG_PPP_DEFLATE=y
-CONFIG_PPP_MPPE=y
-CONFIG_PREEMPT=y
-CONFIG_QUOTA=y
-CONFIG_RTC_CLASS=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_SECCOMP=y
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SETEND_EMULATION=y
-CONFIG_STAGING=y
-CONFIG_SWP_EMULATION=y
-CONFIG_SYNC=y
-CONFIG_TUN=y
-CONFIG_UNIX=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_CONFIGFS=y
-CONFIG_USB_CONFIGFS_F_FS=y
-CONFIG_USB_CONFIGFS_F_MIDI=y
-CONFIG_USB_OTG_WAKELOCK=y
-CONFIG_XFRM_USER=y
diff --git a/kernel/configs/android-fetch-configs.sh b/kernel/configs/android-fetch-configs.sh
new file mode 100755
index 0000000..a5b56d4
--- /dev/null
+++ b/kernel/configs/android-fetch-configs.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+
+curl https://android.googlesource.com/kernel/configs/+archive/master/android-4.9.tar.gz | tar xzv
+
diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
deleted file mode 100644
index 297756b..0000000
--- a/kernel/configs/android-recommended.config
+++ /dev/null
@@ -1,125 +0,0 @@
-# KEEP ALPHABETICALLY SORTED
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_NF_CONNTRACK_SIP is not set
-# CONFIG_PM_WAKELOCKS_GC is not set
-# CONFIG_VT is not set
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_COMPACTION=y
-CONFIG_DEBUG_RODATA=y
-CONFIG_DM_CRYPT=y
-CONFIG_DM_UEVENT=y
-CONFIG_DM_VERITY=y
-CONFIG_DM_VERITY_FEC=y
-CONFIG_DRAGONRISE_FF=y
-CONFIG_ENABLE_DEFAULT_TRACERS=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_FUSE_FS=y
-CONFIG_GREENASIA_FF=y
-CONFIG_HIDRAW=y
-CONFIG_HID_A4TECH=y
-CONFIG_HID_ACRUX=y
-CONFIG_HID_ACRUX_FF=y
-CONFIG_HID_APPLE=y
-CONFIG_HID_BELKIN=y
-CONFIG_HID_CHERRY=y
-CONFIG_HID_CHICONY=y
-CONFIG_HID_CYPRESS=y
-CONFIG_HID_DRAGONRISE=y
-CONFIG_HID_ELECOM=y
-CONFIG_HID_EMS_FF=y
-CONFIG_HID_EZKEY=y
-CONFIG_HID_GREENASIA=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_HOLTEK=y
-CONFIG_HID_KENSINGTON=y
-CONFIG_HID_KEYTOUCH=y
-CONFIG_HID_KYE=y
-CONFIG_HID_LCPOWER=y
-CONFIG_HID_LOGITECH=y
-CONFIG_HID_LOGITECH_DJ=y
-CONFIG_HID_MAGICMOUSE=y
-CONFIG_HID_MICROSOFT=y
-CONFIG_HID_MONTEREY=y
-CONFIG_HID_MULTITOUCH=y
-CONFIG_HID_NTRIG=y
-CONFIG_HID_ORTEK=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_PICOLCD=y
-CONFIG_HID_PRIMAX=y
-CONFIG_HID_PRODIKEYS=y
-CONFIG_HID_ROCCAT=y
-CONFIG_HID_SAITEK=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SMARTJOYPLUS=y
-CONFIG_HID_SONY=y
-CONFIG_HID_SPEEDLINK=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_HID_THRUSTMASTER=y
-CONFIG_HID_TIVO=y
-CONFIG_HID_TOPSEED=y
-CONFIG_HID_TWINHAN=y
-CONFIG_HID_UCLOGIC=y
-CONFIG_HID_WACOM=y
-CONFIG_HID_WALTOP=y
-CONFIG_HID_WIIMOTE=y
-CONFIG_HID_ZEROPLUS=y
-CONFIG_HID_ZYDACRON=y
-CONFIG_INPUT_EVDEV=y
-CONFIG_INPUT_GPIO=y
-CONFIG_INPUT_JOYSTICK=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_TABLET=y
-CONFIG_INPUT_UINPUT=y
-CONFIG_ION=y
-CONFIG_JOYSTICK_XPAD=y
-CONFIG_JOYSTICK_XPAD_FF=y
-CONFIG_JOYSTICK_XPAD_LEDS=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_KSM=y
-CONFIG_LOGIG940_FF=y
-CONFIG_LOGIRUMBLEPAD2_FF=y
-CONFIG_LOGITECH_FF=y
-CONFIG_MD=y
-CONFIG_MEDIA_SUPPORT=y
-CONFIG_MSDOS_FS=y
-CONFIG_PANIC_TIMEOUT=5
-CONFIG_PANTHERLORD_FF=y
-CONFIG_PERF_EVENTS=y
-CONFIG_PM_DEBUG=y
-CONFIG_PM_RUNTIME=y
-CONFIG_PM_WAKELOCKS_LIMIT=0
-CONFIG_POWER_SUPPLY=y
-CONFIG_PSTORE=y
-CONFIG_PSTORE_CONSOLE=y
-CONFIG_PSTORE_RAM=y
-CONFIG_SCHEDSTATS=y
-CONFIG_SMARTJOYPLUS_FF=y
-CONFIG_SND=y
-CONFIG_SOUND=y
-CONFIG_SUSPEND_TIME=y
-CONFIG_TABLET_USB_ACECAD=y
-CONFIG_TABLET_USB_AIPTEK=y
-CONFIG_TABLET_USB_GTCO=y
-CONFIG_TABLET_USB_HANWANG=y
-CONFIG_TABLET_USB_KBTAB=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_TASK_XACCT=y
-CONFIG_TIMER_STATS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_UHID=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB_USBNET=y
-CONFIG_VFAT_FS=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e005209..b0beef3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1297,6 +1297,7 @@ void __weak arch_enable_nonboot_cpus_end(void)
void enable_nonboot_cpus(void)
{
int cpu, error;
+ struct device *cpu_device;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
@@ -1314,6 +1315,12 @@ void enable_nonboot_cpus(void)
trace_suspend_resume(TPS("CPU_ON"), cpu, false);
if (!error) {
pr_info("CPU%d is up\n", cpu);
+ cpu_device = get_cpu_device(cpu);
+ if (!cpu_device)
+ pr_err("%s: failed to get cpu%d device\n",
+ __func__, cpu);
+ else
+ kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
continue;
}
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
@@ -2284,3 +2291,23 @@ bool cpu_mitigations_auto_nosmt(void)
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
+
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+
+void idle_notifier_call_chain(unsigned long val)
+{
+ atomic_notifier_call_chain(&idle_notifier, val, NULL);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_call_chain);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 511b1dd..194e2f2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -100,6 +100,7 @@ struct cpuset {
/* user-configured CPUs and Memory Nodes allow to tasks */
cpumask_var_t cpus_allowed;
+ cpumask_var_t cpus_requested;
nodemask_t mems_allowed;
/* effective CPUs and Memory Nodes allow to tasks */
@@ -399,7 +400,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
- return cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
+ return cpumask_subset(p->cpus_requested, q->cpus_requested) &&
nodes_subset(p->mems_allowed, q->mems_allowed) &&
is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
is_mem_exclusive(p) <= is_mem_exclusive(q);
@@ -499,7 +500,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
cpuset_for_each_child(c, css, par) {
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
c != cur &&
- cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
+ cpumask_intersects(trial->cpus_requested, c->cpus_requested))
goto out;
if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
c != cur &&
@@ -958,17 +959,18 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
} else {
- retval = cpulist_parse(buf, trialcs->cpus_allowed);
+ retval = cpulist_parse(buf, trialcs->cpus_requested);
if (retval < 0)
return retval;
- if (!cpumask_subset(trialcs->cpus_allowed,
- top_cpuset.cpus_allowed))
+ if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask))
return -EINVAL;
+
+ cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask);
}
/* Nothing to do if the cpus didn't change */
- if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
+ if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested))
return 0;
retval = validate_change(cs, trialcs);
@@ -977,6 +979,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, trialcs->cpus_requested);
spin_unlock_irq(&callback_lock);
/* use trialcs->cpus_allowed as a temp variable */
@@ -1761,7 +1764,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
switch (type) {
case FILE_CPULIST:
- seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed));
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested));
break;
case FILE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed));
@@ -1951,11 +1954,14 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
return ERR_PTR(-ENOMEM);
if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
goto free_cs;
+ if (!alloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL))
+ goto free_allowed;
if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
- goto free_cpus;
+ goto free_requested;
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cpumask_clear(cs->cpus_allowed);
+ cpumask_clear(cs->cpus_requested);
nodes_clear(cs->mems_allowed);
cpumask_clear(cs->effective_cpus);
nodes_clear(cs->effective_mems);
@@ -1964,7 +1970,9 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
return &cs->css;
-free_cpus:
+free_requested:
+ free_cpumask_var(cs->cpus_requested);
+free_allowed:
free_cpumask_var(cs->cpus_allowed);
free_cs:
kfree(cs);
@@ -2027,6 +2035,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
cs->mems_allowed = parent->mems_allowed;
cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, parent->cpus_requested);
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
@@ -2061,6 +2070,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
free_cpumask_var(cs->effective_cpus);
free_cpumask_var(cs->cpus_allowed);
+ free_cpumask_var(cs->cpus_requested);
kfree(cs);
}
@@ -2125,8 +2135,11 @@ int __init cpuset_init(void)
BUG();
if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
BUG();
+ if (!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL))
+ BUG();
cpumask_setall(top_cpuset.cpus_allowed);
+ cpumask_setall(top_cpuset.cpus_requested);
nodes_setall(top_cpuset.mems_allowed);
cpumask_setall(top_cpuset.effective_cpus);
nodes_setall(top_cpuset.effective_mems);
@@ -2260,7 +2273,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs)
goto retry;
}
- cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
+ cpumask_and(&new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus);
nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index ae39b01..4b53752 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
int i;
int diag, dtab_count;
int key, buf_size, ret;
-
+ static int last_crlf;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
if (diag)
@@ -237,6 +237,9 @@ static char *kdb_read(char *buffer, size_t bufsize)
return buffer;
if (key != 9)
tab = 0;
+ if (key != 10 && key != 13)
+ last_crlf = 0;
+
switch (key) {
case 8: /* backspace */
if (cp > buffer) {
@@ -254,7 +257,12 @@ static char *kdb_read(char *buffer, size_t bufsize)
*cp = tmp;
}
break;
- case 13: /* enter */
+ case 10: /* new line */
+ case 13: /* carriage return */
+ /* handle \n after \r */
+ if (last_crlf && last_crlf != key)
+ break;
+ last_crlf = key;
*lastchar++ = '\n';
*lastchar++ = '\0';
if (!KDB_STATE(KGDB_TRANS)) {
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index a52a6da..15880fc 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -18,6 +18,7 @@
#include <linux/kmsg_dump.h>
#include <linux/reboot.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/sysrq.h>
#include <linux/smp.h>
#include <linux/utsname.h>
@@ -2584,16 +2585,11 @@ static int kdb_summary(int argc, const char **argv)
}
kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60);
- /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n",
LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]),
LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]),
LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2]));
-#undef LOAD_INT
-#undef LOAD_FRAC
+
/* Display in kilobytes */
#define K(x) ((x) << (PAGE_SHIFT - 10))
kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n"
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 435c14a..3fde7df 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -124,9 +124,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
+ tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
+ d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
+ d->thrashing_count += tsk->delays->thrashing_count;
spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
@@ -156,3 +159,14 @@ void __delayacct_freepages_end(void)
¤t->delays->freepages_count);
}
+void __delayacct_thrashing_start(void)
+{
+ current->delays->thrashing_start = ktime_get_ns();
+}
+
+void __delayacct_thrashing_end(void)
+{
+ delayacct_end(¤t->delays->thrashing_start,
+ ¤t->delays->thrashing_delay,
+ ¤t->delays->thrashing_count);
+}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d4a71d..929f82e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -395,8 +395,13 @@ static struct srcu_struct pmus_srcu;
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
+ * 3 - disallow all unpriv perf event use
*/
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
int sysctl_perf_event_paranoid __read_mostly = 2;
+#endif
/* Minimum for 512 kiB + 1 user control page */
int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -7729,11 +7734,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
struct pt_regs *regs, struct hlist_head *head,
struct task_struct *task)
{
- struct bpf_prog *prog = call->prog;
-
- if (prog) {
+ if (bpf_prog_array_valid(call)) {
*(struct pt_regs **)raw_data = regs;
- if (!trace_call_bpf(prog, raw_data) || hlist_empty(head)) {
+ if (!trace_call_bpf(call, raw_data) || hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
}
@@ -7918,6 +7921,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
{
bool is_kprobe, is_tracepoint;
struct bpf_prog *prog;
+ int ret;
if (event->attr.type == PERF_TYPE_HARDWARE ||
event->attr.type == PERF_TYPE_SOFTWARE)
@@ -7926,9 +7930,6 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -EINVAL;
- if (event->tp_event->prog)
- return -EEXIST;
-
is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE;
is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT;
if (!is_kprobe && !is_tracepoint)
@@ -7954,26 +7955,20 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
return -EACCES;
}
}
- event->tp_event->prog = prog;
- event->tp_event->bpf_prog_owner = event;
- return 0;
+ ret = perf_event_attach_bpf_prog(event, prog);
+ if (ret)
+ bpf_prog_put(prog);
+ return ret;
}
static void perf_event_free_bpf_prog(struct perf_event *event)
{
- struct bpf_prog *prog;
-
- perf_event_free_bpf_handler(event);
-
- if (!event->tp_event)
+ if (event->attr.type != PERF_TYPE_TRACEPOINT) {
+ perf_event_free_bpf_handler(event);
return;
-
- prog = event->tp_event->prog;
- if (prog && event->tp_event->bpf_prog_owner == event) {
- event->tp_event->prog = NULL;
- bpf_prog_put(prog);
}
+ perf_event_detach_bpf_prog(event);
}
#else
@@ -9712,6 +9707,9 @@ SYSCALL_DEFINE5(perf_event_open,
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
+ if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
diff --git a/kernel/exit.c b/kernel/exit.c
index 8716f07..5ebacd3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,6 +55,8 @@
#include <linux/shm.h>
#include <linux/kcov.h>
+#include "sched/tune.h"
+
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
@@ -684,6 +686,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
if (group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
+ tsk->exit_state = EXIT_ZOMBIE;
if (unlikely(tsk->ptrace)) {
int sig = thread_group_leader(tsk) &&
thread_group_empty(tsk) &&
@@ -792,6 +795,8 @@ void __noreturn do_exit(long code)
exit_signals(tsk); /* sets PF_EXITING */
+ schedtune_exit_task(tsk);
+
/* sync mm's RSS info before statistics gathering */
if (tsk->mm)
sync_mm_rss(tsk->mm);
diff --git a/kernel/fork.c b/kernel/fork.c
index 91349fd..ee8aa68 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -11,6 +11,7 @@
* management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
*/
+#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/unistd.h>
@@ -37,6 +38,7 @@
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/seccomp.h>
+#include <linux/seq_file.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
@@ -77,6 +79,7 @@
#include <linux/compiler.h>
#include <linux/sysctl.h>
#include <linux/kcov.h>
+#include <linux/cpufreq_times.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -342,6 +345,8 @@ void put_task_stack(struct task_struct *tsk)
void free_task(struct task_struct *tsk)
{
+ cpufreq_task_times_exit(tsk);
+
#ifndef CONFIG_THREAD_INFO_IN_TASK
/*
* The task is finally done with both the stack and thread_info,
@@ -1456,6 +1461,84 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
task->pids[type].pid = pid;
}
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+ struct pid *pid = file->private_data;
+
+ file->private_data = NULL;
+ put_pid(pid);
+ return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct pid_namespace *ns = file_inode(m->file)->i_sb->s_fs_info;
+ struct pid *pid = f->private_data;
+
+ seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+ seq_putc(m, '\n');
+}
+#endif
+
+/*
+ * Poll support for process exit notification.
+ */
+static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts)
+{
+ struct task_struct *task;
+ struct pid *pid = file->private_data;
+ int poll_flags = 0;
+
+ poll_wait(file, &pid->wait_pidfd, pts);
+
+ rcu_read_lock();
+ task = pid_task(pid, PIDTYPE_PID);
+ /*
+ * Inform pollers only when the whole thread group exits.
+ * If the thread group leader exits before all other threads in the
+ * group, then poll(2) should block, similar to the wait(2) family.
+ */
+ if (!task || (task->exit_state && thread_group_empty(task)))
+ poll_flags = POLLIN | POLLRDNORM;
+ rcu_read_unlock();
+
+ return poll_flags;
+}
+
+const struct file_operations pidfd_fops = {
+ .release = pidfd_release,
+ .poll = pidfd_poll,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = pidfd_show_fdinfo,
+#endif
+};
+
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid: struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ * On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+ int fd;
+
+ fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+ O_RDWR | O_CLOEXEC);
+ if (fd < 0)
+ put_pid(pid);
+
+ return fd;
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
@@ -1468,13 +1551,14 @@ static __latent_entropy struct task_struct *copy_process(
unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
+ int __user *parent_tidptr,
int __user *child_tidptr,
struct pid *pid,
int trace,
unsigned long tls,
int node)
{
- int retval;
+ int pidfd = -1, retval;
struct task_struct *p;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
@@ -1519,6 +1603,31 @@ static __latent_entropy struct task_struct *copy_process(
return ERR_PTR(-EINVAL);
}
+ if (clone_flags & CLONE_PIDFD) {
+ int reserved;
+
+ /*
+ * - CLONE_PARENT_SETTID is useless for pidfds and also
+ * parent_tidptr is used to return pidfds.
+ * - CLONE_DETACHED is blocked so that we can potentially
+ * reuse it later for CLONE_PIDFD.
+ * - CLONE_THREAD is blocked until someone really needs it.
+ */
+ if (clone_flags &
+ (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * Verify that parent_tidptr is sane so we can potentially
+ * reuse it later.
+ */
+ if (get_user(reserved, parent_tidptr))
+ return ERR_PTR(-EFAULT);
+
+ if (reserved != 0)
+ return ERR_PTR(-EINVAL);
+ }
+
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
@@ -1528,6 +1637,8 @@ static __latent_entropy struct task_struct *copy_process(
if (!p)
goto fork_out;
+ cpufreq_task_times_init(p);
+
/*
* This _must_ happen before we call free_task(), i.e. before we jump
* to any of the bad_fork_* labels. This is to avoid freeing
@@ -1597,6 +1708,10 @@ static __latent_entropy struct task_struct *copy_process(
p->default_timer_slack_ns = current->timer_slack_ns;
+#ifdef CONFIG_PSI
+ p->psi_flags = 0;
+#endif
+
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
@@ -1699,6 +1814,22 @@ static __latent_entropy struct task_struct *copy_process(
}
}
+ /*
+ * This has to happen after we've potentially unshared the file
+ * descriptor table (so that the pidfd doesn't leak into the child
+ * if the fd table isn't shared).
+ */
+ if (clone_flags & CLONE_PIDFD) {
+ retval = pidfd_create(pid);
+ if (retval < 0)
+ goto bad_fork_free_pid;
+
+ pidfd = retval;
+ retval = put_user(pidfd, parent_tidptr);
+ if (retval)
+ goto bad_fork_put_pidfd;
+ }
+
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
@@ -1748,7 +1879,7 @@ static __latent_entropy struct task_struct *copy_process(
*/
retval = cgroup_can_fork(p);
if (retval)
- goto bad_fork_free_pid;
+ goto bad_fork_cgroup_threadgroup_change_end;
/*
* From this point on we must avoid any synchronous user-space
@@ -1859,8 +1990,12 @@ static __latent_entropy struct task_struct *copy_process(
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
-bad_fork_free_pid:
+bad_fork_cgroup_threadgroup_change_end:
threadgroup_change_end(current);
+bad_fork_put_pidfd:
+ if (clone_flags & CLONE_PIDFD)
+ sys_close(pidfd);
+bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
@@ -1918,7 +2053,7 @@ static inline void init_idle_pids(struct pid_link *links)
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task->pids);
@@ -1963,7 +2098,7 @@ long _do_fork(unsigned long clone_flags,
trace = 0;
}
- p = copy_process(clone_flags, stack_start, stack_size,
+ p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
add_latent_entropy();
/*
@@ -1974,6 +2109,8 @@ long _do_fork(unsigned long clone_flags,
struct completion vfork;
struct pid *pid;
+ cpufreq_task_times_alloc(p);
+
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fafd1a3..a0c3365 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -306,6 +306,24 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf);
}
+#ifdef CONFIG_CFI_CLANG
+/*
+ * LLVM appends .cfi to function names when CONFIG_CFI_CLANG is enabled,
+ * which causes confusion and potentially breaks user space tools, so we
+ * will strip the postfix from expanded symbol names.
+ */
+static inline void cleanup_symbol_name(char *s)
+{
+ char *res;
+
+ res = strrchr(s, '.');
+ if (res && !strcmp(res, ".cfi"))
+ *res = '\0';
+}
+#else
+static inline void cleanup_symbol_name(char *s) {}
+#endif
+
/*
* Lookup an address
* - modname is set to NULL if it's in the kernel.
@@ -330,16 +348,23 @@ const char *kallsyms_lookup(unsigned long addr,
namebuf, KSYM_NAME_LEN);
if (modname)
*modname = NULL;
- return namebuf;
+ goto found;
}
/* See if it's in a module. */
- return module_address_lookup(addr, symbolsize, offset, modname,
- namebuf);
+ if (!module_address_lookup(addr, symbolsize, offset, modname,
+ namebuf))
+ return NULL;
+
+found:
+ cleanup_symbol_name(namebuf);
+ return namebuf;
}
int lookup_symbol_name(unsigned long addr, char *symname)
{
+ int res;
+
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
@@ -350,15 +375,23 @@ int lookup_symbol_name(unsigned long addr, char *symname)
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
- return 0;
+ goto found;
}
/* See if it's in a module. */
- return lookup_module_symbol_name(addr, symname);
+ res = lookup_module_symbol_name(addr, symname);
+ if (res)
+ return res;
+
+found:
+ cleanup_symbol_name(symname);
+ return 0;
}
int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
unsigned long *offset, char *modname, char *name)
{
+ int res;
+
name[0] = '\0';
name[KSYM_NAME_LEN - 1] = '\0';
@@ -370,10 +403,16 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
kallsyms_expand_symbol(get_symbol_offset(pos),
name, KSYM_NAME_LEN);
modname[0] = '\0';
- return 0;
+ goto found;
}
/* See if it's in a module. */
- return lookup_module_symbol_attrs(addr, size, offset, modname, name);
+ res = lookup_module_symbol_attrs(addr, size, offset, modname, name);
+ if (res)
+ return res;
+
+found:
+ cleanup_symbol_name(name);
+ return 0;
}
/* Look up a kernel symbol and return it in a text buffer. */
diff --git a/kernel/kcov.c b/kernel/kcov.c
index b0ec314..fad5144 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1,11 +1,16 @@
#define pr_fmt(fmt) "kcov: " fmt
#define DISABLE_BRANCH_PROFILING
+#include <linux/atomic.h>
#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/init.h>
#include <linux/mm.h>
+#include <linux/preempt.h>
#include <linux/printk.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -14,6 +19,10 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/kcov.h>
+#include <asm/setup.h>
+
+/* Number of 64-bit words written per one comparison: */
+#define KCOV_WORDS_PER_CMP 4
/*
* kcov descriptor (one per opened debugfs file).
@@ -21,7 +30,12 @@
* - initial state after open()
* - then there must be a single ioctl(KCOV_INIT_TRACE) call
* - then, mmap() call (several calls are allowed but not useful)
- * - then, repeated enable/disable for a task (only one task a time allowed)
+ * - then, ioctl(KCOV_ENABLE, arg), where arg is
+ * KCOV_TRACE_PC - to trace only the PCs
+ * or
+ * KCOV_TRACE_CMP - to trace only the comparison operands
+ * - then, ioctl(KCOV_DISABLE) to disable the task.
+ * Enabling/disabling ioctls can be repeated (only one task a time allowed).
*/
struct kcov {
/*
@@ -41,6 +55,36 @@ struct kcov {
struct task_struct *t;
};
+static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+{
+ enum kcov_mode mode;
+
+ /*
+ * We are interested in code coverage as a function of a syscall inputs,
+ * so we ignore code executed in interrupts.
+ */
+ if (!in_task())
+ return false;
+ mode = READ_ONCE(t->kcov_mode);
+ /*
+ * There is some code that runs in interrupts but for which
+ * in_interrupt() returns false (e.g. preempt_schedule_irq()).
+ * READ_ONCE()/barrier() effectively provides load-acquire wrt
+ * interrupts, there are paired barrier()/WRITE_ONCE() in
+ * kcov_ioctl_locked().
+ */
+ barrier();
+ return mode == needed_mode;
+}
+
+static unsigned long canonicalize_ip(unsigned long ip)
+{
+#ifdef CONFIG_RANDOMIZE_BASE
+ ip -= kaslr_offset();
+#endif
+ return ip;
+}
+
/*
* Entry point from instrumented code.
* This is called once per basic-block/edge.
@@ -48,46 +92,139 @@ struct kcov {
void notrace __sanitizer_cov_trace_pc(void)
{
struct task_struct *t;
- enum kcov_mode mode;
+ unsigned long *area;
+ unsigned long ip = canonicalize_ip(_RET_IP_);
+ unsigned long pos;
t = current;
- /*
- * We are interested in code coverage as a function of a syscall inputs,
- * so we ignore code executed in interrupts.
- * The checks for whether we are in an interrupt are open-coded, because
- * 1. We can't use in_interrupt() here, since it also returns true
- * when we are inside local_bh_disable() section.
- * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
- * since that leads to slower generated code (three separate tests,
- * one for each of the flags).
- */
- if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
- | NMI_MASK)))
+ if (!check_kcov_mode(KCOV_MODE_TRACE_PC, t))
return;
- mode = READ_ONCE(t->kcov_mode);
- if (mode == KCOV_MODE_TRACE) {
- unsigned long *area;
- unsigned long pos;
- /*
- * There is some code that runs in interrupts but for which
- * in_interrupt() returns false (e.g. preempt_schedule_irq()).
- * READ_ONCE()/barrier() effectively provides load-acquire wrt
- * interrupts, there are paired barrier()/WRITE_ONCE() in
- * kcov_ioctl_locked().
- */
- barrier();
- area = t->kcov_area;
- /* The first word is number of subsequent PCs. */
- pos = READ_ONCE(area[0]) + 1;
- if (likely(pos < t->kcov_size)) {
- area[pos] = _RET_IP_;
- WRITE_ONCE(area[0], pos);
- }
+ area = t->kcov_area;
+ /* The first 64-bit word is the number of subsequent PCs. */
+ pos = READ_ONCE(area[0]) + 1;
+ if (likely(pos < t->kcov_size)) {
+ area[pos] = ip;
+ WRITE_ONCE(area[0], pos);
}
}
EXPORT_SYMBOL(__sanitizer_cov_trace_pc);
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+static void write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip)
+{
+ struct task_struct *t;
+ u64 *area;
+ u64 count, start_index, end_pos, max_pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_CMP, t))
+ return;
+
+ ip = canonicalize_ip(ip);
+
+ /*
+ * We write all comparison arguments and types as u64.
+ * The buffer was allocated for t->kcov_size unsigned longs.
+ */
+ area = (u64 *)t->kcov_area;
+ max_pos = t->kcov_size * sizeof(unsigned long);
+
+ count = READ_ONCE(area[0]);
+
+ /* Every record is KCOV_WORDS_PER_CMP 64-bit words. */
+ start_index = 1 + count * KCOV_WORDS_PER_CMP;
+ end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64);
+ if (likely(end_pos <= max_pos)) {
+ area[start_index] = type;
+ area[start_index + 1] = arg1;
+ area[start_index + 2] = arg2;
+ area[start_index + 3] = ip;
+ WRITE_ONCE(area[0], count + 1);
+ }
+}
+
+void notrace __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp1);
+
+void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2);
+
+void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4);
+
+void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp8);
+
+void notrace __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp1);
+
+void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2);
+
+void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4);
+
+void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8);
+
+void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
+{
+ u64 i;
+ u64 count = cases[0];
+ u64 size = cases[1];
+ u64 type = KCOV_CMP_CONST;
+
+ switch (size) {
+ case 8:
+ type |= KCOV_CMP_SIZE(0);
+ break;
+ case 16:
+ type |= KCOV_CMP_SIZE(1);
+ break;
+ case 32:
+ type |= KCOV_CMP_SIZE(2);
+ break;
+ case 64:
+ type |= KCOV_CMP_SIZE(3);
+ break;
+ default:
+ return;
+ }
+ for (i = 0; i < count; i++)
+ write_comp_data(type, cases[i + 2], val, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
+#endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
+
static void kcov_get(struct kcov *kcov)
{
atomic_inc(&kcov->refcount);
@@ -125,6 +262,7 @@ void kcov_task_exit(struct task_struct *t)
/* Just to not leave dangling references behind. */
kcov_task_init(t);
kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
spin_unlock(&kcov->lock);
kcov_put(kcov);
}
@@ -143,7 +281,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
spin_lock(&kcov->lock);
size = kcov->size * sizeof(unsigned long);
- if (kcov->mode == KCOV_MODE_DISABLED || vma->vm_pgoff != 0 ||
+ if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 ||
vma->vm_end - vma->vm_start != size) {
res = -EINVAL;
goto exit;
@@ -172,6 +310,7 @@ static int kcov_open(struct inode *inode, struct file *filep)
kcov = kzalloc(sizeof(*kcov), GFP_KERNEL);
if (!kcov)
return -ENOMEM;
+ kcov->mode = KCOV_MODE_DISABLED;
atomic_set(&kcov->refcount, 1);
spin_lock_init(&kcov->lock);
filep->private_data = kcov;
@@ -207,7 +346,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
if (size < 2 || size > INT_MAX / sizeof(unsigned long))
return -EINVAL;
kcov->size = size;
- kcov->mode = KCOV_MODE_TRACE;
+ kcov->mode = KCOV_MODE_INIT;
return 0;
case KCOV_ENABLE:
/*
@@ -217,9 +356,19 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
* at task exit or voluntary by KCOV_DISABLE. After that it can
* be enabled for another task.
*/
- unused = arg;
- if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED ||
- kcov->area == NULL)
+ if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
+ return -EINVAL;
+ if (kcov->t != NULL)
+ return -EBUSY;
+ if (arg == KCOV_TRACE_PC)
+ kcov->mode = KCOV_MODE_TRACE_PC;
+ else if (arg == KCOV_TRACE_CMP)
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+ kcov->mode = KCOV_MODE_TRACE_CMP;
+#else
+ return -ENOTSUPP;
+#endif
+ else
return -EINVAL;
t = current;
if (kcov->t != NULL || t->kcov != NULL)
@@ -227,7 +376,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
/* Cache in task struct for performance. */
t->kcov_size = kcov->size;
t->kcov_area = kcov->area;
- /* See comment in __sanitizer_cov_trace_pc(). */
+ /* See comment in check_kcov_mode(). */
barrier();
WRITE_ONCE(t->kcov_mode, kcov->mode);
t->kcov = kcov;
@@ -245,6 +394,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
return -EINVAL;
kcov_task_init(t);
kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
kcov_put(kcov);
return 0;
default:
@@ -267,6 +417,7 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
static const struct file_operations kcov_fops = {
.open = kcov_open,
.unlocked_ioctl = kcov_ioctl,
+ .compat_ioctl = kcov_ioctl,
.mmap = kcov_mmap,
.release = kcov_close,
};
diff --git a/kernel/module.c b/kernel/module.c
index 0219301..edda715 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2099,6 +2099,8 @@ void __weak module_arch_freeing_init(struct module *mod)
{
}
+static void cfi_cleanup(struct module *mod);
+
/* Free a module, remove from lists, etc. */
static void free_module(struct module *mod)
{
@@ -2140,6 +2142,10 @@ static void free_module(struct module *mod)
/* This may be empty, but that's OK */
disable_ro_nx(&mod->init_layout);
+
+ /* Clean up CFI for the module. */
+ cfi_cleanup(mod);
+
module_arch_freeing_init(mod);
module_memfree(mod->init_layout.base);
kfree(mod->args);
@@ -3321,6 +3327,8 @@ int __weak module_finalize(const Elf_Ehdr *hdr,
return 0;
}
+static void cfi_init(struct module *mod);
+
static int post_relocation(struct module *mod, const struct load_info *info)
{
/* Sort exception table now relocations are done. */
@@ -3333,6 +3341,9 @@ static int post_relocation(struct module *mod, const struct load_info *info)
/* Setup kallsyms-specific fields. */
add_kallsyms(mod, info);
+ /* Setup CFI for the module. */
+ cfi_init(mod);
+
/* Arch-specific module finalizing. */
return module_finalize(info->hdr, info->sechdrs, mod);
}
@@ -4073,6 +4084,22 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
}
#endif /* CONFIG_KALLSYMS */
+static void cfi_init(struct module *mod)
+{
+#ifdef CONFIG_CFI_CLANG
+ mod->cfi_check =
+ (cfi_check_fn)mod_find_symname(mod, CFI_CHECK_FN_NAME);
+ cfi_module_add(mod, module_addr_min, module_addr_max);
+#endif
+}
+
+static void cfi_cleanup(struct module *mod)
+{
+#ifdef CONFIG_CFI_CLANG
+ cfi_module_remove(mod, module_addr_min, module_addr_max);
+#endif
+}
+
static char *module_flags(struct module *mod, char *buf)
{
int bx = 0;
diff --git a/kernel/panic.c b/kernel/panic.c
index 89198dc..5009676 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -600,7 +600,7 @@ EXPORT_SYMBOL(warn_slowpath_null);
*/
__visible void __stack_chk_fail(void)
{
- panic("stack-protector: Kernel stack is corrupted in: %p\n",
+ panic("stack-protector: Kernel stack is corrupted in: %pB\n",
__builtin_return_address(0));
}
EXPORT_SYMBOL(__stack_chk_fail);
diff --git a/kernel/pid.c b/kernel/pid.c
index fa704f8..2c19594 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -38,6 +38,7 @@
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>
+#include <linux/anon_inodes.h>
#define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
@@ -68,9 +69,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
* the scheme scales to up to 4 million PIDs, runtime.
*/
struct pid_namespace init_pid_ns = {
- .kref = {
- .refcount = ATOMIC_INIT(2),
- },
+ .kref = KREF_INIT(2),
.pidmap = {
[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
},
@@ -333,6 +332,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
for (type = 0; type < PIDTYPE_MAX; ++type)
INIT_HLIST_HEAD(&pid->tasks[type]);
+ init_waitqueue_head(&pid->wait_pidfd);
+
upid = pid->numbers + ns->level;
spin_lock_irq(&pidmap_lock);
if (!(ns->nr_hashed & PIDNS_HASH_ADDING))
@@ -566,6 +567,76 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
return pid;
}
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid: struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ * On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+ int fd;
+
+ fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+ O_RDWR | O_CLOEXEC);
+ if (fd < 0)
+ put_pid(pid);
+
+ return fd;
+}
+
+/**
+ * pidfd_open() - Open new pid file descriptor.
+ *
+ * @pid: pid for which to retrieve a pidfd
+ * @flags: flags to pass
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set for
+ * the process identified by @pid. Currently, the process identified by
+ * @pid must be a thread-group leader. This restriction currently exists
+ * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
+ * be used with CLONE_THREAD) and pidfd polling (only supports thread group
+ * leaders).
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ * On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
+{
+ int fd, ret;
+ struct pid *p;
+ struct task_struct *tsk;
+
+ if (flags)
+ return -EINVAL;
+
+ if (pid <= 0)
+ return -EINVAL;
+
+ p = find_get_pid(pid);
+ if (!p)
+ return -ESRCH;
+
+ ret = 0;
+ rcu_read_lock();
+ tsk = pid_task(p, PIDTYPE_PID);
+ /* Check that pid belongs to a group leader task */
+ if (!tsk || !thread_group_leader(tsk))
+ ret = -EINVAL;
+ rcu_read_unlock();
+
+ fd = ret ?: pidfd_create(p);
+ put_pid(p);
+ return fd;
+}
+
/*
* The pid hash table is scaled according to the amount of memory in the
* machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index dd2b5a4..826b733 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -1,6 +1,7 @@
config SUSPEND
bool "Suspend to RAM and standby"
depends on ARCH_SUSPEND_POSSIBLE
+ select RTC_LIB
default y
---help---
Allow the system to enter sleep states in which main memory is
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index eb4f717..80578f2 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -14,3 +14,5 @@
obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
+
+obj-$(CONFIG_SUSPEND) += wakeup_reason.o
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 8ea24de..9a12c83 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -18,6 +18,7 @@
#include <linux/workqueue.h>
#include <linux/kmod.h>
#include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
#include <linux/cpuset.h>
/*
@@ -35,6 +36,9 @@ static int try_to_freeze_tasks(bool user_only)
unsigned int elapsed_msecs;
bool wakeup = false;
int sleep_usecs = USEC_PER_MSEC;
+#ifdef CONFIG_PM_SLEEP
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+#endif
start = ktime_get_boottime();
@@ -64,6 +68,11 @@ static int try_to_freeze_tasks(bool user_only)
break;
if (pm_wakeup_pending()) {
+#ifdef CONFIG_PM_SLEEP
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
+#endif
wakeup = true;
break;
}
@@ -82,26 +91,27 @@ static int try_to_freeze_tasks(bool user_only)
elapsed = ktime_sub(end, start);
elapsed_msecs = ktime_to_ms(elapsed);
- if (todo) {
+ if (wakeup) {
pr_cont("\n");
- pr_err("Freezing of tasks %s after %d.%03d seconds "
- "(%d tasks refusing to freeze, wq_busy=%d):\n",
- wakeup ? "aborted" : "failed",
+ pr_err("Freezing of tasks aborted after %d.%03d seconds",
+ elapsed_msecs / 1000, elapsed_msecs % 1000);
+ } else if (todo) {
+ pr_cont("\n");
+ pr_err("Freezing of tasks failed after %d.%03d seconds"
+ " (%d tasks refusing to freeze, wq_busy=%d):\n",
elapsed_msecs / 1000, elapsed_msecs % 1000,
todo - wq_busy, wq_busy);
if (wq_busy)
show_workqueue_state();
- if (!wakeup) {
- read_lock(&tasklist_lock);
- for_each_process_thread(g, p) {
- if (p != current && !freezer_should_skip(p)
- && freezing(p) && !frozen(p))
- sched_show_task(p);
- }
- read_unlock(&tasklist_lock);
+ read_lock(&tasklist_lock);
+ for_each_process_thread(g, p) {
+ if (p != current && !freezer_should_skip(p)
+ && freezing(p) && !frozen(p))
+ sched_show_task(p);
}
+ read_unlock(&tasklist_lock);
} else {
pr_cont("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000,
elapsed_msecs % 1000);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6ccb08f..2d0c99b 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -26,9 +26,11 @@
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/ftrace.h>
+#include <linux/rtc.h>
#include <trace/events/power.h>
#include <linux/compiler.h>
#include <linux/moduleparam.h>
+#include <linux/wakeup_reason.h>
#include "power.h"
@@ -322,7 +324,8 @@ void __weak arch_suspend_enable_irqs(void)
*/
static int suspend_enter(suspend_state_t state, bool *wakeup)
{
- int error;
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+ int error, last_dev;
error = platform_suspend_prepare(state);
if (error)
@@ -330,7 +333,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
error = dpm_suspend_late(PMSG_SUSPEND);
if (error) {
+ last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+ last_dev %= REC_FAILED_NUM;
pr_err("PM: late suspend of devices failed\n");
+ log_suspend_abort_reason("%s device failed to power down",
+ suspend_stats.failed_devs[last_dev]);
goto Platform_finish;
}
error = platform_suspend_prepare_late(state);
@@ -339,7 +346,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
+ last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+ last_dev %= REC_FAILED_NUM;
pr_err("PM: noirq suspend of devices failed\n");
+ log_suspend_abort_reason("noirq suspend of %s device failed",
+ suspend_stats.failed_devs[last_dev]);
goto Platform_early_resume;
}
error = platform_suspend_prepare_noirq(state);
@@ -363,8 +374,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
}
error = disable_nonboot_cpus();
- if (error || suspend_test(TEST_CPUS))
+ if (error || suspend_test(TEST_CPUS)) {
+ log_suspend_abort_reason("Disabling non-boot cpus failed");
goto Enable_cpus;
+ }
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
@@ -380,6 +393,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
state, false);
events_check_enabled = false;
} else if (*wakeup) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
error = -EBUSY;
}
syscore_resume();
@@ -427,6 +443,7 @@ int suspend_devices_and_enter(suspend_state_t state)
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
pr_err("PM: Some devices failed to suspend, or early wake event detected\n");
+ log_suspend_abort_reason("Some devices failed to suspend, or early wake event detected");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
@@ -527,6 +544,18 @@ static int enter_state(suspend_state_t state)
return error;
}
+static void pm_suspend_marker(char *annotation)
+{
+ struct timespec ts;
+ struct rtc_time tm;
+
+ getnstimeofday(&ts);
+ rtc_time_to_tm(ts.tv_sec, &tm);
+ pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n",
+ annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
+}
+
/**
* pm_suspend - Externally visible function for suspending the system.
* @state: System sleep state to enter.
@@ -541,6 +570,7 @@ int pm_suspend(suspend_state_t state)
if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
return -EINVAL;
+ pm_suspend_marker("entry");
error = enter_state(state);
if (error) {
suspend_stats.fail++;
@@ -548,6 +578,7 @@ int pm_suspend(suspend_state_t state)
} else {
suspend_stats.success++;
}
+ pm_suspend_marker("exit");
return error;
}
EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c
new file mode 100644
index 0000000..252611f
--- /dev/null
+++ b/kernel/power/wakeup_reason.c
@@ -0,0 +1,225 @@
+/*
+ * kernel/power/wakeup_reason.c
+ *
+ * Logs the reasons which caused the kernel to resume from
+ * the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/wakeup_reason.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+
+
+#define MAX_WAKEUP_REASON_IRQS 32
+static int irq_list[MAX_WAKEUP_REASON_IRQS];
+static int irqcount;
+static bool suspend_abort;
+static char abort_reason[MAX_SUSPEND_ABORT_LEN];
+static struct kobject *wakeup_reason;
+static DEFINE_SPINLOCK(resume_reason_lock);
+
+static ktime_t last_monotime; /* monotonic time before last suspend */
+static ktime_t curr_monotime; /* monotonic time after last suspend */
+static ktime_t last_stime; /* monotonic boottime offset before last suspend */
+static ktime_t curr_stime; /* monotonic boottime offset after last suspend */
+
+static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ int irq_no, buf_offset = 0;
+ struct irq_desc *desc;
+ spin_lock(&resume_reason_lock);
+ if (suspend_abort) {
+ buf_offset = sprintf(buf, "Abort: %s", abort_reason);
+ } else {
+ for (irq_no = 0; irq_no < irqcount; irq_no++) {
+ desc = irq_to_desc(irq_list[irq_no]);
+ if (desc && desc->action && desc->action->name)
+ buf_offset += sprintf(buf + buf_offset, "%d %s\n",
+ irq_list[irq_no], desc->action->name);
+ else
+ buf_offset += sprintf(buf + buf_offset, "%d\n",
+ irq_list[irq_no]);
+ }
+ }
+ spin_unlock(&resume_reason_lock);
+ return buf_offset;
+}
+
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct timespec sleep_time;
+ struct timespec total_time;
+ struct timespec suspend_resume_time;
+
+ /*
+ * total_time is calculated from monotonic bootoffsets because
+ * unlike CLOCK_MONOTONIC it include the time spent in suspend state.
+ */
+ total_time = ktime_to_timespec(ktime_sub(curr_stime, last_stime));
+
+ /*
+ * suspend_resume_time is calculated as monotonic (CLOCK_MONOTONIC)
+ * time interval before entering suspend and post suspend.
+ */
+ suspend_resume_time = ktime_to_timespec(ktime_sub(curr_monotime, last_monotime));
+
+ /* sleep_time = total_time - suspend_resume_time */
+ sleep_time = timespec_sub(total_time, suspend_resume_time);
+
+ /* Export suspend_resume_time and sleep_time in pair here. */
+ return sprintf(buf, "%lu.%09lu %lu.%09lu\n",
+ suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec,
+ sleep_time.tv_sec, sleep_time.tv_nsec);
+}
+
+static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
+
+static struct attribute *attrs[] = {
+ &resume_reason.attr,
+ &suspend_time.attr,
+ NULL,
+};
+static struct attribute_group attr_group = {
+ .attrs = attrs,
+};
+
+/*
+ * logs all the wake up reasons to the kernel
+ * stores the irqs to expose them to the userspace via sysfs
+ */
+void log_wakeup_reason(int irq)
+{
+ struct irq_desc *desc;
+ desc = irq_to_desc(irq);
+ if (desc && desc->action && desc->action->name)
+ printk(KERN_INFO "Resume caused by IRQ %d, %s\n", irq,
+ desc->action->name);
+ else
+ printk(KERN_INFO "Resume caused by IRQ %d\n", irq);
+
+ spin_lock(&resume_reason_lock);
+ if (irqcount == MAX_WAKEUP_REASON_IRQS) {
+ spin_unlock(&resume_reason_lock);
+ printk(KERN_WARNING "Resume caused by more than %d IRQs\n",
+ MAX_WAKEUP_REASON_IRQS);
+ return;
+ }
+
+ irq_list[irqcount++] = irq;
+ spin_unlock(&resume_reason_lock);
+}
+
+int check_wakeup_reason(int irq)
+{
+ int irq_no;
+ int ret = false;
+
+ spin_lock(&resume_reason_lock);
+ for (irq_no = 0; irq_no < irqcount; irq_no++)
+ if (irq_list[irq_no] == irq) {
+ ret = true;
+ break;
+ }
+ spin_unlock(&resume_reason_lock);
+ return ret;
+}
+
+void log_suspend_abort_reason(const char *fmt, ...)
+{
+ va_list args;
+
+ spin_lock(&resume_reason_lock);
+
+ //Suspend abort reason has already been logged.
+ if (suspend_abort) {
+ spin_unlock(&resume_reason_lock);
+ return;
+ }
+
+ suspend_abort = true;
+ va_start(args, fmt);
+ vsnprintf(abort_reason, MAX_SUSPEND_ABORT_LEN, fmt, args);
+ va_end(args);
+ spin_unlock(&resume_reason_lock);
+}
+
+/* Detects a suspend and clears all the previous wake up reasons*/
+static int wakeup_reason_pm_event(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ spin_lock(&resume_reason_lock);
+ irqcount = 0;
+ suspend_abort = false;
+ spin_unlock(&resume_reason_lock);
+ /* monotonic time since boot */
+ last_monotime = ktime_get();
+ /* monotonic time since boot including the time spent in suspend */
+ last_stime = ktime_get_boottime();
+ break;
+ case PM_POST_SUSPEND:
+ /* monotonic time since boot */
+ curr_monotime = ktime_get();
+ /* monotonic time since boot including the time spent in suspend */
+ curr_stime = ktime_get_boottime();
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block wakeup_reason_pm_notifier_block = {
+ .notifier_call = wakeup_reason_pm_event,
+};
+
+/* Initializes the sysfs parameter
+ * registers the pm_event notifier
+ */
+int __init wakeup_reason_init(void)
+{
+ int retval;
+
+ retval = register_pm_notifier(&wakeup_reason_pm_notifier_block);
+ if (retval)
+ printk(KERN_WARNING "[%s] failed to register PM notifier %d\n",
+ __func__, retval);
+
+ wakeup_reason = kobject_create_and_add("wakeup_reasons", kernel_kobj);
+ if (!wakeup_reason) {
+ printk(KERN_WARNING "[%s] failed to create a sysfs kobject\n",
+ __func__);
+ return 1;
+ }
+ retval = sysfs_create_group(wakeup_reason, &attr_group);
+ if (retval) {
+ kobject_put(wakeup_reason);
+ printk(KERN_WARNING "[%s] failed to create a sysfs group %d\n",
+ __func__, retval);
+ }
+ return 0;
+}
+
+late_initcall(wakeup_reason_init);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 7acae2f..13f3823 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -56,6 +56,10 @@
#include "braille.h"
#include "internal.h"
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+extern void printascii(char *);
+#endif
+
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */
@@ -1833,6 +1837,10 @@ asmlinkage int vprintk_emit(int facility, int level,
}
}
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+ printascii(text);
+#endif
+
if (level == LOGLEVEL_DEFAULT)
level = default_message_loglevel;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 5e59b83..aeb0476 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,10 +18,13 @@
obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o energy.o
+obj-$(CONFIG_SCHED_WALT) += walt.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_SCHED_TUNE) += tune.o
obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
+obj-$(CONFIG_PSI) += psi.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c7c7ba8..ede5ef3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -75,6 +75,9 @@
#include <linux/compiler.h>
#include <linux/frame.h>
#include <linux/prefetch.h>
+#include <linux/cpufreq_times.h>
+#include <linux/sched/loadavg.h>
+#include <linux/cgroup-defs.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
@@ -90,6 +93,7 @@
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
+#include "walt.h"
DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -156,19 +160,16 @@ int sysctl_sched_rt_runtime = 950000;
/* cpus with isolated domains */
cpumask_var_t cpu_isolated_map;
-/*
- * this_rq_lock - lock this runqueue and disable interrupts.
- */
-static struct rq *this_rq_lock(void)
- __acquires(rq->lock)
+struct rq *
+lock_rq_of(struct task_struct *p, struct rq_flags *flags)
{
- struct rq *rq;
+ return task_rq_lock(p, flags);
+}
- local_irq_disable();
- rq = this_rq();
- raw_spin_lock(&rq->lock);
-
- return rq;
+void
+unlock_rq_of(struct rq *rq, struct task_struct *p, struct rq_flags *flags)
+{
+ task_rq_unlock(rq, p, flags);
}
/*
@@ -185,7 +186,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
rq = task_rq(p);
raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -225,7 +226,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
* pair with the WMB to ensure we must then also see migrating.
*/
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -755,16 +756,20 @@ static void set_load_weight(struct task_struct *p)
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- if (!(flags & ENQUEUE_RESTORE))
+ if (!(flags & ENQUEUE_RESTORE)) {
sched_info_queued(rq, p);
+ psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+ }
p->sched_class->enqueue_task(rq, p, flags);
}
static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- if (!(flags & DEQUEUE_SAVE))
+ if (!(flags & DEQUEUE_SAVE)) {
sched_info_dequeued(rq, p);
+ psi_dequeue(p, flags & DEQUEUE_SLEEP);
+ }
p->sched_class->dequeue_task(rq, p, flags);
}
@@ -998,7 +1003,9 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
p->on_rq = TASK_ON_RQ_MIGRATING;
dequeue_task(rq, p, 0);
+ double_lock_balance(rq, cpu_rq(new_cpu));
set_task_cpu(p, new_cpu);
+ double_unlock_balance(rq, cpu_rq(new_cpu));
raw_spin_unlock(&rq->lock);
rq = cpu_rq(new_cpu);
@@ -1196,9 +1203,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
* OK, since we're going to drop the lock immediately
* afterwards anyway.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
rq = move_queued_task(rq, p, dest_cpu);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
out:
task_rq_unlock(rq, p, &rf);
@@ -1254,6 +1261,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
p->sched_class->migrate_task_rq(p);
p->se.nr_migrations++;
perf_event_task_migrate(p);
+
+ walt_fixup_busy_time(p, new_cpu);
}
__set_task_cpu(p, new_cpu);
@@ -1269,7 +1278,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(dst_rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(dst_rq, p, 0);
@@ -1691,7 +1702,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
* Mark the task runnable and perform wakeup-preemption.
*/
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
check_preempt_curr(rq, p, wake_flags);
p->state = TASK_RUNNING;
@@ -1703,9 +1714,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
* Our task @p is fully woken up and running; so its safe to
* drop the rq->lock, hereafter rq is only used for statistics.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (rq->idle_stamp) {
@@ -1724,7 +1735,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
int en_flags = ENQUEUE_WAKEUP;
@@ -1739,7 +1750,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
#endif
ttwu_activate(rq, p, en_flags);
- ttwu_do_wakeup(rq, p, wake_flags, cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, rf);
}
/*
@@ -1758,7 +1769,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
if (task_on_rq_queued(p)) {
/* check_preempt_curr() may use rq clock */
update_rq_clock(rq);
- ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, &rf);
ret = 1;
}
__task_rq_unlock(rq, &rf);
@@ -1771,15 +1782,15 @@ void sched_ttwu_pending(void)
{
struct rq *rq = this_rq();
struct llist_node *llist = llist_del_all(&rq->wake_list);
- struct pin_cookie cookie;
struct task_struct *p;
unsigned long flags;
+ struct rq_flags rf;
if (!llist)
return;
raw_spin_lock_irqsave(&rq->lock, flags);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
while (llist) {
int wake_flags = 0;
@@ -1790,10 +1801,10 @@ void sched_ttwu_pending(void)
if (p->sched_remote_wakeup)
wake_flags = WF_MIGRATED;
- ttwu_do_activate(rq, p, wake_flags, cookie);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
}
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1882,7 +1893,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
- struct pin_cookie cookie;
+ struct rq_flags rf;
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
@@ -1893,9 +1904,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
#endif
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
- ttwu_do_activate(rq, p, wake_flags, cookie);
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_pin_lock(rq, &rf);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
}
@@ -2010,6 +2021,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
unsigned long flags;
int cpu, success = 0;
+#ifdef CONFIG_SMP
+ struct rq *rq;
+ u64 wallclock;
+#endif
/*
* If we are going to wake up a thread waiting for CONDITION we
@@ -2083,14 +2098,25 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
smp_cond_load_acquire(&p->on_cpu, !VAL);
+ rq = cpu_rq(task_cpu(p));
+
+ raw_spin_lock(&rq->lock);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
+ raw_spin_unlock(&rq->lock);
+
p->sched_contributes_to_load = !!task_contributes_to_load(p);
p->state = TASK_WAKING;
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
+
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
+ psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
}
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
@@ -2111,7 +2137,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* ensure that this_rq() is locked, @p is bound to this_rq() and not
* the current task.
*/
-static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
+static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
{
struct rq *rq = task_rq(p);
@@ -2128,11 +2154,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
* disabled avoiding further scheduler activity on it and we've
* not yet picked a replacement task.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&p->pi_lock);
raw_spin_lock(&rq->lock);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (!(p->state & TASK_NORMAL))
@@ -2140,10 +2166,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
trace_sched_waking(p);
- if (!task_on_rq_queued(p))
- ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ if (!task_on_rq_queued(p)) {
+ u64 wallclock = walt_ktime_clock();
- ttwu_do_wakeup(rq, p, 0, cookie);
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
+ ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
+
+ ttwu_do_wakeup(rq, p, 0, rf);
ttwu_stat(p, smp_processor_id(), 0);
out:
raw_spin_unlock(&p->pi_lock);
@@ -2206,7 +2237,12 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+#ifdef CONFIG_SCHED_WALT
+ p->last_sleep_ts = 0;
+#endif
+
INIT_LIST_HEAD(&p->se.group_node);
+ walt_init_new_task_load(p);
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = NULL;
@@ -2566,6 +2602,9 @@ void wake_up_new_task(struct task_struct *p)
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
+
+ walt_init_new_task_load(p);
+
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
/*
@@ -2579,9 +2618,12 @@ void wake_up_new_task(struct task_struct *p)
__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
post_init_entity_util_avg(&p->se);
- activate_task(rq, p, 0);
+ walt_mark_task_starting(p);
+
+ activate_task(rq, p, ENQUEUE_WAKEUP_NEW);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
@@ -2591,9 +2633,9 @@ void wake_up_new_task(struct task_struct *p)
* Nothing relies on rq->lock after this, so its fine to
* drop it.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
task_rq_unlock(rq, p, &rf);
@@ -2862,7 +2904,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
*/
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
- struct task_struct *next, struct pin_cookie cookie)
+ struct task_struct *next, struct rq_flags *rf)
{
struct mm_struct *mm, *oldmm;
@@ -2894,7 +2936,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
/* Here we just switch the register state and the stack. */
@@ -2966,6 +3008,36 @@ unsigned long nr_iowait_cpu(int cpu)
return atomic_read(&this->nr_iowait);
}
+#ifdef CONFIG_CPU_QUIET
+u64 nr_running_integral(unsigned int cpu)
+{
+ unsigned int seqcnt;
+ u64 integral;
+ struct rq *q;
+
+ if (cpu >= nr_cpu_ids)
+ return 0;
+
+ q = cpu_rq(cpu);
+
+ /*
+ * Update average to avoid reading stalled value if there were
+ * no run-queue changes for a long time. On the other hand if
+ * the changes are happening right now, just read current value
+ * directly.
+ */
+
+ seqcnt = read_seqcount_begin(&q->ave_seqcnt);
+ integral = do_nr_running_integral(q);
+ if (read_seqcount_retry(&q->ave_seqcnt, seqcnt)) {
+ read_seqcount_begin(&q->ave_seqcnt);
+ integral = q->nr_running_integral;
+ }
+
+ return integral;
+}
+#endif
+
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
struct rq *rq = this_rq();
@@ -3083,10 +3155,14 @@ void scheduler_tick(void)
sched_clock_tick();
raw_spin_lock(&rq->lock);
+ walt_set_window_start(rq);
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE,
+ walt_ktime_clock(), 0);
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
cpu_load_update_active(rq);
calc_global_load_tick(rq);
+ psi_task_tick(rq);
raw_spin_unlock(&rq->lock);
perf_event_task_tick();
@@ -3096,6 +3172,9 @@ void scheduler_tick(void)
trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
+
+ if (curr->sched_class == &fair_sched_class)
+ check_for_migration(rq, curr);
}
#ifdef CONFIG_NO_HZ_FULL
@@ -3258,7 +3337,7 @@ static inline void schedule_debug(struct task_struct *prev)
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
const struct sched_class *class = &fair_sched_class;
struct task_struct *p;
@@ -3269,20 +3348,20 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie
*/
if (likely(prev->sched_class == class &&
rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq, prev, cookie);
+ p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
/* assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
- p = idle_sched_class.pick_next_task(rq, prev, cookie);
+ p = idle_sched_class.pick_next_task(rq, prev, rf);
return p;
}
again:
for_each_class(class) {
- p = class->pick_next_task(rq, prev, cookie);
+ p = class->pick_next_task(rq, prev, rf);
if (p) {
if (unlikely(p == RETRY_TASK))
goto again;
@@ -3336,9 +3415,10 @@ static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
- struct pin_cookie cookie;
+ struct rq_flags rf;
struct rq *rq;
int cpu;
+ u64 wallclock;
cpu = smp_processor_id();
rq = cpu_rq(cpu);
@@ -3359,7 +3439,7 @@ static void __sched notrace __schedule(bool preempt)
*/
smp_mb__before_spinlock();
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
rq->clock_skip_update <<= 1; /* promote REQ to ACT */
@@ -3381,7 +3461,7 @@ static void __sched notrace __schedule(bool preempt)
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
- try_to_wake_up_local(to_wakeup, cookie);
+ try_to_wake_up_local(to_wakeup, &rf);
}
}
switch_count = &prev->nvcsw;
@@ -3390,20 +3470,27 @@ static void __sched notrace __schedule(bool preempt)
if (task_on_rq_queued(prev))
update_rq_clock(rq);
- next = pick_next_task(rq, prev, cookie);
+ next = pick_next_task(rq, prev, &rf);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(prev, rq, PUT_PREV_TASK, wallclock, 0);
+ walt_update_task_ravg(next, rq, PICK_NEXT_TASK, wallclock, 0);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq->clock_skip_update = 0;
if (likely(prev != next)) {
+#ifdef CONFIG_SCHED_WALT
+ if (!prev->on_rq)
+ prev->last_sleep_ts = wallclock;
+#endif
rq->nr_switches++;
rq->curr = next;
++*switch_count;
trace_sched_switch(preempt, prev, next);
- rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
+ rq = context_switch(rq, prev, next, &rf); /* unlocks the rq */
} else {
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irq(&rq->lock);
}
@@ -3652,6 +3739,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
* Idle task boosting is a nono in general. There is one
@@ -3749,6 +3837,8 @@ void set_user_nice(struct task_struct *p, long nice)
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
+
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
@@ -4182,6 +4272,7 @@ static int __sched_setscheduler(struct task_struct *p,
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
* Changing the policy of the stop threads its a very bad idea
@@ -4884,7 +4975,10 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
*/
SYSCALL_DEFINE0(sched_yield)
{
- struct rq *rq = this_rq_lock();
+ struct rq_flags rf;
+ struct rq *rq;
+
+ rq = this_rq_lock_irq(&rf);
schedstat_inc(rq->yld_count);
current->sched_class->yield_task(rq);
@@ -4893,9 +4987,8 @@ SYSCALL_DEFINE0(sched_yield)
* Since we are going to call schedule() anyway, there's
* no need to preempt or enable interrupts:
*/
- __release(rq->lock);
- spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
- do_raw_spin_unlock(&rq->lock);
+ preempt_disable();
+ rq_unlock(rq, &rf);
sched_preempt_enable_no_resched();
schedule();
@@ -5523,7 +5616,7 @@ static void migrate_tasks(struct rq *dead_rq)
{
struct rq *rq = dead_rq;
struct task_struct *next, *stop = rq->stop;
- struct pin_cookie cookie;
+ struct rq_flags rf;
int dest_cpu;
/*
@@ -5555,8 +5648,8 @@ static void migrate_tasks(struct rq *dead_rq)
/*
* pick_next_task assumes pinned rq->lock.
*/
- cookie = lockdep_pin_lock(&rq->lock);
- next = pick_next_task(rq, &fake_task, cookie);
+ rq_pin_lock(rq, &rf);
+ next = pick_next_task(rq, &fake_task, &rf);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
@@ -5569,7 +5662,7 @@ static void migrate_tasks(struct rq *dead_rq)
* because !cpu_active at this point, which means load-balance
* will not interfere. Also, stop-machine.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&next->pi_lock);
raw_spin_lock(&rq->lock);
@@ -5667,9 +5760,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
- if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
- " has parent");
return -1;
}
@@ -5711,7 +5801,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
printk(KERN_CONT " %*pbl",
cpumask_pr_args(sched_group_cpus(group)));
if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
- printk(KERN_CONT " (cpu_capacity = %d)",
+ printk(KERN_CONT " (cpu_capacity = %lu)",
group->sgc->capacity);
}
@@ -5764,8 +5854,12 @@ static inline bool sched_debug(void)
static int sd_degenerate(struct sched_domain *sd)
{
- if (cpumask_weight(sched_domain_span(sd)) == 1)
- return 1;
+ if (cpumask_weight(sched_domain_span(sd)) == 1) {
+ if (sd->groups->sge)
+ sd->flags &= ~SD_LOAD_BALANCE;
+ else
+ return 1;
+ }
/* Following flags need at least 2 groups */
if (sd->flags & (SD_LOAD_BALANCE |
@@ -5775,7 +5869,8 @@ static int sd_degenerate(struct sched_domain *sd)
SD_SHARE_CPUCAPACITY |
SD_ASYM_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
- SD_SHARE_POWERDOMAIN)) {
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES)) {
if (sd->groups != sd->groups->next)
return 0;
}
@@ -5808,7 +5903,12 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_PREFER_SIBLING |
- SD_SHARE_POWERDOMAIN);
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES);
+ if (parent->groups->sge) {
+ parent->flags &= ~SD_LOAD_BALANCE;
+ return 0;
+ }
if (nr_node_ids == 1)
pflags &= ~SD_SERIALIZE;
}
@@ -5906,6 +6006,11 @@ static int init_rootdomain(struct root_domain *rd)
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
+
+ init_max_cpu_capacity(&rd->max_cpu_capacity);
+
+ rd->max_cap_orig_cpu = rd->min_cap_orig_cpu = -1;
+
return 0;
free_rto_mask:
@@ -6017,11 +6122,14 @@ DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_ea);
+DEFINE_PER_CPU(struct sched_domain *, sd_scs);
static void update_top_cache_domain(int cpu)
{
struct sched_domain_shared *sds = NULL;
struct sched_domain *sd;
+ struct sched_domain *ea_sd = NULL;
int id = cpu;
int size = 1;
@@ -6042,6 +6150,17 @@ static void update_top_cache_domain(int cpu)
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+
+ for_each_domain(cpu, sd) {
+ if (sd->groups->sge)
+ ea_sd = sd;
+ else
+ break;
+ }
+ rcu_assign_pointer(per_cpu(sd_ea, cpu), ea_sd);
+
+ sd = highest_flag_domain(cpu, SD_SHARE_CAP_STATES);
+ rcu_assign_pointer(per_cpu(sd_scs, cpu), sd);
}
/*
@@ -6223,6 +6342,8 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
* die on a /0 trap.
*/
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+ sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
+ sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
/*
* Make sure the first group of this domain contains the
@@ -6351,6 +6472,66 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
}
/*
+ * Check that the per-cpu provided sd energy data is consistent for all cpus
+ * within the mask.
+ */
+static inline void check_sched_energy_data(int cpu, sched_domain_energy_f fn,
+ const struct cpumask *cpumask)
+{
+ const struct sched_group_energy * const sge = fn(cpu);
+ struct cpumask mask;
+ int i;
+
+ if (cpumask_weight(cpumask) <= 1)
+ return;
+
+ cpumask_xor(&mask, cpumask, get_cpu_mask(cpu));
+
+ for_each_cpu(i, &mask) {
+ const struct sched_group_energy * const e = fn(i);
+ int y;
+
+ BUG_ON(e->nr_idle_states != sge->nr_idle_states);
+
+ for (y = 0; y < (e->nr_idle_states); y++) {
+ BUG_ON(e->idle_states[y].power !=
+ sge->idle_states[y].power);
+ }
+
+ BUG_ON(e->nr_cap_states != sge->nr_cap_states);
+
+ for (y = 0; y < (e->nr_cap_states); y++) {
+ BUG_ON(e->cap_states[y].cap != sge->cap_states[y].cap);
+ BUG_ON(e->cap_states[y].power !=
+ sge->cap_states[y].power);
+ }
+ }
+}
+
+static void init_sched_energy(int cpu, struct sched_domain *sd,
+ sched_domain_energy_f fn)
+{
+ if (!(fn && fn(cpu)))
+ return;
+
+ if (cpu != group_balance_cpu(sd->groups))
+ return;
+
+ if (sd->child && !sd->child->groups->sge) {
+ pr_err("BUG: EAS setup broken for CPU%d\n", cpu);
+#ifdef CONFIG_SCHED_DEBUG
+ pr_err(" energy data on %s but not on %s domain\n",
+ sd->name, sd->child->name);
+#endif
+ return;
+ }
+
+ check_sched_energy_data(cpu, fn, sched_group_cpus(sd->groups));
+
+ sd->groups->sge = fn(cpu);
+}
+
+/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
@@ -6466,6 +6647,7 @@ static int sched_domains_curr_level;
* SD_NUMA - describes NUMA topologies
* SD_SHARE_POWERDOMAIN - describes shared power domain
* SD_ASYM_CPUCAPACITY - describes mixed capacity topologies
+ * SD_SHARE_CAP_STATES - describes shared capacity states
*
* Odd one out, which beside describing the topology has a quirk also
* prescribes the desired behaviour that goes along with it:
@@ -6478,7 +6660,8 @@ static int sched_domains_curr_level;
SD_NUMA | \
SD_ASYM_PACKING | \
SD_ASYM_CPUCAPACITY | \
- SD_SHARE_POWERDOMAIN)
+ SD_SHARE_POWERDOMAIN | \
+ SD_SHARE_CAP_STATES)
static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl,
@@ -7036,7 +7219,6 @@ static int build_sched_domains(const struct cpumask *cpu_map,
enum s_alloc alloc_state;
struct sched_domain *sd;
struct s_data d;
- struct rq *rq = NULL;
int i, ret = -ENOMEM;
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
@@ -7054,8 +7236,6 @@ static int build_sched_domains(const struct cpumask *cpu_map,
*per_cpu_ptr(d.sd, i) = sd;
if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
sd->flags |= SD_OVERLAP;
- if (cpumask_equal(cpu_map, sched_domain_span(sd)))
- break;
}
}
@@ -7075,10 +7255,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
/* Calculate CPU capacity for physical packages and nodes */
for (i = nr_cpumask_bits-1; i >= 0; i--) {
+ struct sched_domain_topology_level *tl = sched_domain_topology;
+
if (!cpumask_test_cpu(i, cpu_map))
continue;
- for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent, tl++) {
+ init_sched_energy(i, sd, tl->energy);
claim_allocations(i, sd);
init_sched_groups_capacity(i, sd);
}
@@ -7087,22 +7270,23 @@ static int build_sched_domains(const struct cpumask *cpu_map,
/* Attach the domains */
rcu_read_lock();
for_each_cpu(i, cpu_map) {
- rq = cpu_rq(i);
- sd = *per_cpu_ptr(d.sd, i);
+ int max_cpu = READ_ONCE(d.rd->max_cap_orig_cpu);
+ int min_cpu = READ_ONCE(d.rd->min_cap_orig_cpu);
- /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
- if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
- WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+ if ((max_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig >
+ cpu_rq(max_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->max_cap_orig_cpu, i);
+
+ if ((min_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig <
+ cpu_rq(min_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->min_cap_orig_cpu, i);
+
+ sd = *per_cpu_ptr(d.sd, i);
cpu_attach_domain(sd, d.rd, i);
}
rcu_read_unlock();
- if (rq && sched_debug_enabled) {
- pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
- cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
- }
-
ret = 0;
error:
__free_domain_allocs(&d, alloc_state, cpu_map);
@@ -7464,6 +7648,9 @@ int sched_cpu_dying(unsigned int cpu)
/* Handle pending wakeups and then migrate everything off */
sched_ttwu_pending();
raw_spin_lock_irqsave(&rq->lock, flags);
+
+ walt_migrate_sync_cpu(cpu);
+
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
@@ -7640,6 +7827,7 @@ void __init sched_init(void)
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
* How much cpu bandwidth does root_task_group get?
*
@@ -7679,11 +7867,17 @@ void __init sched_init(void)
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
+ rq->push_task = NULL;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
+#ifdef CONFIG_SCHED_WALT
+ rq->cur_irqload = 0;
+ rq->avg_irqload = 0;
+ rq->irqload_ts = 0;
+#endif
INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -7730,6 +7924,8 @@ void __init sched_init(void)
init_schedstats();
+ psi_init();
+
scheduler_running = 1;
}
@@ -7741,6 +7937,14 @@ static inline int preempt_count_equals(int preempt_offset)
return (nested == preempt_offset);
}
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+ __might_sleep_init_called = 1;
+ return 0;
+}
+early_initcall(__might_sleep_init);
+
void __might_sleep(const char *file, int line, int preempt_offset)
{
/*
@@ -7766,8 +7970,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
- !is_idle_task(current)) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ !is_idle_task(current)) || oops_in_progress)
+ return;
+ if (system_state != SYSTEM_RUNNING &&
+ (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
@@ -8397,6 +8603,17 @@ int sched_rr_handler(struct ctl_table *table, int write,
return ret;
}
+void threadgroup_change_begin(struct task_struct *tsk)
+{
+ might_sleep();
+ cgroup_threadgroup_change_begin(tsk);
+}
+
+void threadgroup_change_end(struct task_struct *tsk)
+{
+ cgroup_threadgroup_change_end(tsk);
+}
+
#ifdef CONFIG_CGROUP_SCHED
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -8461,6 +8678,7 @@ static void cpu_cgroup_fork(struct task_struct *task)
rq = task_rq_lock(task, &rf);
+ update_rq_clock(rq);
sched_change_group(task, TASK_SET_GROUP);
task_rq_unlock(rq, task, &rf);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index cb771c7..0526dc0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,14 +12,27 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cpufreq.h>
+#include <linux/kthread.h>
#include <linux/slab.h>
#include <trace/events/power.h>
#include "sched.h"
+#include "tune.h"
+
+unsigned long boosted_cpu_util(int cpu);
+
+/* Stub out fast switch routines present on mainline to reduce the backport
+ * overhead. */
+#define cpufreq_driver_fast_switch(x, y) 0
+#define cpufreq_enable_fast_switch(x)
+#define cpufreq_disable_fast_switch(x)
+#define LATENCY_MULTIPLIER (1000)
+#define SUGOV_KTHREAD_PRIORITY 50
struct sugov_tunables {
struct gov_attr_set attr_set;
- unsigned int rate_limit_us;
+ unsigned int up_rate_limit_us;
+ unsigned int down_rate_limit_us;
};
struct sugov_policy {
@@ -30,14 +43,18 @@ struct sugov_policy {
raw_spinlock_t update_lock; /* For shared policies */
u64 last_freq_update_time;
- s64 freq_update_delay_ns;
+ s64 min_rate_limit_ns;
+ s64 up_rate_delay_ns;
+ s64 down_rate_delay_ns;
unsigned int next_freq;
unsigned int cached_raw_freq;
/* The next fields are only needed if fast switch cannot be used. */
struct irq_work irq_work;
- struct work_struct work;
+ struct kthread_work work;
struct mutex work_lock;
+ struct kthread_worker worker;
+ struct task_struct *thread;
bool work_in_progress;
bool need_freq_update;
@@ -55,6 +72,11 @@ struct sugov_cpu {
unsigned long util;
unsigned long max;
unsigned int flags;
+
+ /* The field below is for single-CPU policies only. */
+#ifdef CONFIG_NO_HZ_COMMON
+ unsigned long saved_idle_calls;
+#endif
};
static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -79,7 +101,27 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
}
delta_ns = time - sg_policy->last_freq_update_time;
- return delta_ns >= sg_policy->freq_update_delay_ns;
+
+ /* No need to recalculate next freq for min_rate_limit_us at least */
+ return delta_ns >= sg_policy->min_rate_limit_ns;
+}
+
+static bool sugov_up_down_rate_limit(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
+{
+ s64 delta_ns;
+
+ delta_ns = time - sg_policy->last_freq_update_time;
+
+ if (next_freq > sg_policy->next_freq &&
+ delta_ns < sg_policy->up_rate_delay_ns)
+ return true;
+
+ if (next_freq < sg_policy->next_freq &&
+ delta_ns < sg_policy->down_rate_delay_ns)
+ return true;
+
+ return false;
}
static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
@@ -87,22 +129,26 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
{
struct cpufreq_policy *policy = sg_policy->policy;
+ if (sugov_up_down_rate_limit(sg_policy, time, next_freq)) {
+ /* Reset cached freq as next_freq isn't changed */
+ sg_policy->cached_raw_freq = 0;
+ return;
+ }
+
+ if (sg_policy->next_freq == next_freq)
+ return;
+
+ sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
if (policy->fast_switch_enabled) {
- if (sg_policy->next_freq == next_freq) {
- trace_cpu_frequency(policy->cur, smp_processor_id());
- return;
- }
- sg_policy->next_freq = next_freq;
next_freq = cpufreq_driver_fast_switch(policy, next_freq);
if (next_freq == CPUFREQ_ENTRY_INVALID)
return;
policy->cur = next_freq;
trace_cpu_frequency(next_freq, smp_processor_id());
- } else if (sg_policy->next_freq != next_freq) {
- sg_policy->next_freq = next_freq;
+ } else {
sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work);
}
@@ -110,7 +156,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
/**
* get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
* @util: Current CPU utilization.
* @max: CPU capacity.
*
@@ -130,10 +176,9 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
* next_freq (as calculated above) is returned, subject to policy min/max and
* cpufreq driver limitations.
*/
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
- unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+ unsigned long util, unsigned long max)
{
- struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
@@ -146,15 +191,36 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
return cpufreq_driver_resolve_freq(policy, freq);
}
-static void sugov_get_util(unsigned long *util, unsigned long *max)
+static inline bool use_pelt(void)
{
- struct rq *rq = this_rq();
- unsigned long cfs_max;
+#ifdef CONFIG_SCHED_WALT
+ return (!sysctl_sched_use_walt_cpu_util || walt_disabled);
+#else
+ return true;
+#endif
+}
- cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+static void sugov_get_util(unsigned long *util, unsigned long *max, u64 time)
+{
+ int cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long max_cap, rt;
+ s64 delta;
- *util = min(rq->cfs.avg.util_avg, cfs_max);
- *max = cfs_max;
+ max_cap = arch_scale_cpu_capacity(NULL, cpu);
+
+ sched_avg_update(rq);
+ delta = time - rq->age_stamp;
+ if (unlikely(delta < 0))
+ delta = 0;
+ rt = div64_u64(rq->rt_avg, sched_avg_period() + delta);
+ rt = (rt * max_cap) >> SCHED_CAPACITY_SHIFT;
+
+ *util = boosted_cpu_util(cpu);
+ if (likely(use_pelt()))
+ *util = min((*util + rt), max_cap);
+
+ *max = max_cap;
}
static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
@@ -187,6 +253,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
sg_cpu->iowait_boost >>= 1;
}
+#ifdef CONFIG_NO_HZ_COMMON
+static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+{
+ unsigned long idle_calls = tick_nohz_get_idle_calls();
+ bool ret = idle_calls == sg_cpu->saved_idle_calls;
+
+ sg_cpu->saved_idle_calls = idle_calls;
+ return ret;
+}
+#else
+static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+#endif /* CONFIG_NO_HZ_COMMON */
+
static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned int flags)
{
@@ -195,6 +274,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
struct cpufreq_policy *policy = sg_policy->policy;
unsigned long util, max;
unsigned int next_f;
+ bool busy;
sugov_set_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
@@ -202,40 +282,40 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
- if (flags & SCHED_CPUFREQ_RT_DL) {
+ busy = sugov_cpu_is_busy(sg_cpu);
+
+ if (flags & SCHED_CPUFREQ_DL) {
next_f = policy->cpuinfo.max_freq;
} else {
- sugov_get_util(&util, &max);
+ sugov_get_util(&util, &max, time);
sugov_iowait_boost(sg_cpu, &util, &max);
- next_f = get_next_freq(sg_cpu, util, max);
+ next_f = get_next_freq(sg_policy, util, max);
+ /*
+ * Do not reduce the frequency if the CPU has not been idle
+ * recently, as the reduction is likely to be premature then.
+ */
+ if (busy && next_f < sg_policy->next_freq) {
+ next_f = sg_policy->next_freq;
+
+ /* Reset cached freq as next_freq has changed */
+ sg_policy->cached_raw_freq = 0;
+ }
}
sugov_update_commit(sg_policy, time, next_f);
}
-static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
- unsigned long util, unsigned long max,
- unsigned int flags)
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
- unsigned int max_f = policy->cpuinfo.max_freq;
- u64 last_freq_update_time = sg_policy->last_freq_update_time;
+ unsigned long util = 0, max = 1;
unsigned int j;
- if (flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
-
- sugov_iowait_boost(sg_cpu, &util, &max);
-
for_each_cpu(j, policy->cpus) {
- struct sugov_cpu *j_sg_cpu;
+ struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
s64 delta_ns;
- if (j == smp_processor_id())
- continue;
-
- j_sg_cpu = &per_cpu(sugov_cpu, j);
/*
* If the CPU utilization was last updated before the previous
* frequency update and the time elapsed between the last update
@@ -243,13 +323,13 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
* enough, don't take the CPU into account as it probably is
* idle now (and clear iowait_boost for it).
*/
- delta_ns = last_freq_update_time - j_sg_cpu->last_update;
+ delta_ns = time - j_sg_cpu->last_update;
if (delta_ns > TICK_NSEC) {
j_sg_cpu->iowait_boost = 0;
continue;
}
- if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
+ if (j_sg_cpu->flags & SCHED_CPUFREQ_DL)
+ return policy->cpuinfo.max_freq;
j_util = j_sg_cpu->util;
j_max = j_sg_cpu->max;
@@ -261,7 +341,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
sugov_iowait_boost(j_sg_cpu, &util, &max);
}
- return get_next_freq(sg_cpu, util, max);
+ return get_next_freq(sg_policy, util, max);
}
static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -272,7 +352,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
unsigned long util, max;
unsigned int next_f;
- sugov_get_util(&util, &max);
+ sugov_get_util(&util, &max, time);
raw_spin_lock(&sg_policy->update_lock);
@@ -284,14 +364,18 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) {
- next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
+ if (flags & SCHED_CPUFREQ_DL)
+ next_f = sg_policy->policy->cpuinfo.max_freq;
+ else
+ next_f = sugov_next_freq_shared(sg_cpu, time);
+
sugov_update_commit(sg_policy, time, next_f);
}
raw_spin_unlock(&sg_policy->update_lock);
}
-static void sugov_work(struct work_struct *work)
+static void sugov_work(struct kthread_work *work)
{
struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
@@ -308,7 +392,21 @@ static void sugov_irq_work(struct irq_work *irq_work)
struct sugov_policy *sg_policy;
sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
- schedule_work_on(smp_processor_id(), &sg_policy->work);
+
+ /*
+ * For RT and deadline tasks, the schedutil governor shoots the
+ * frequency to maximum. Special care must be taken to ensure that this
+ * kthread doesn't result in the same behavior.
+ *
+ * This is (mostly) guaranteed by the work_in_progress flag. The flag is
+ * updated only at the end of the sugov_work() function and before that
+ * the schedutil governor rejects all other frequency scaling requests.
+ *
+ * There is a very rare case though, where the RT thread yields right
+ * after the work_in_progress flag is cleared. The effects of that are
+ * neglected for now.
+ */
+ kthread_queue_work(&sg_policy->worker, &sg_policy->work);
}
/************************** sysfs interface ************************/
@@ -321,15 +419,32 @@ static inline struct sugov_tunables *to_sugov_tunables(struct gov_attr_set *attr
return container_of(attr_set, struct sugov_tunables, attr_set);
}
-static ssize_t rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
+static DEFINE_MUTEX(min_rate_lock);
+
+static void update_min_rate_limit_us(struct sugov_policy *sg_policy)
+{
+ mutex_lock(&min_rate_lock);
+ sg_policy->min_rate_limit_ns = min(sg_policy->up_rate_delay_ns,
+ sg_policy->down_rate_delay_ns);
+ mutex_unlock(&min_rate_lock);
+}
+
+static ssize_t up_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
{
struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
- return sprintf(buf, "%u\n", tunables->rate_limit_us);
+ return sprintf(buf, "%u\n", tunables->up_rate_limit_us);
}
-static ssize_t rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf,
- size_t count)
+static ssize_t down_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+
+ return sprintf(buf, "%u\n", tunables->down_rate_limit_us);
+}
+
+static ssize_t up_rate_limit_us_store(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
{
struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
struct sugov_policy *sg_policy;
@@ -338,18 +453,42 @@ static ssize_t rate_limit_us_store(struct gov_attr_set *attr_set, const char *bu
if (kstrtouint(buf, 10, &rate_limit_us))
return -EINVAL;
- tunables->rate_limit_us = rate_limit_us;
+ tunables->up_rate_limit_us = rate_limit_us;
- list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook)
- sg_policy->freq_update_delay_ns = rate_limit_us * NSEC_PER_USEC;
+ list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) {
+ sg_policy->up_rate_delay_ns = rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
+ }
return count;
}
-static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us);
+static ssize_t down_rate_limit_us_store(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+ struct sugov_policy *sg_policy;
+ unsigned int rate_limit_us;
+
+ if (kstrtouint(buf, 10, &rate_limit_us))
+ return -EINVAL;
+
+ tunables->down_rate_limit_us = rate_limit_us;
+
+ list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) {
+ sg_policy->down_rate_delay_ns = rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
+ }
+
+ return count;
+}
+
+static struct governor_attr up_rate_limit_us = __ATTR_RW(up_rate_limit_us);
+static struct governor_attr down_rate_limit_us = __ATTR_RW(down_rate_limit_us);
static struct attribute *sugov_attributes[] = {
- &rate_limit_us.attr,
+ &up_rate_limit_us.attr,
+ &down_rate_limit_us.attr,
NULL
};
@@ -371,19 +510,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
return NULL;
sg_policy->policy = policy;
- init_irq_work(&sg_policy->irq_work, sugov_irq_work);
- INIT_WORK(&sg_policy->work, sugov_work);
- mutex_init(&sg_policy->work_lock);
raw_spin_lock_init(&sg_policy->update_lock);
return sg_policy;
}
static void sugov_policy_free(struct sugov_policy *sg_policy)
{
- mutex_destroy(&sg_policy->work_lock);
kfree(sg_policy);
}
+static int sugov_kthread_create(struct sugov_policy *sg_policy)
+{
+ struct task_struct *thread;
+ struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+ struct cpufreq_policy *policy = sg_policy->policy;
+ int ret;
+
+ /* kthread only required for slow path */
+ if (policy->fast_switch_enabled)
+ return 0;
+
+ kthread_init_work(&sg_policy->work, sugov_work);
+ kthread_init_worker(&sg_policy->worker);
+ thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
+ "sugov:%d",
+ cpumask_first(policy->related_cpus));
+ if (IS_ERR(thread)) {
+ pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
+ return PTR_ERR(thread);
+ }
+
+ ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, ¶m);
+ if (ret) {
+ kthread_stop(thread);
+ pr_warn("%s: failed to set SCHED_FIFO\n", __func__);
+ return ret;
+ }
+
+ sg_policy->thread = thread;
+ kthread_bind_mask(thread, policy->related_cpus);
+ init_irq_work(&sg_policy->irq_work, sugov_irq_work);
+ mutex_init(&sg_policy->work_lock);
+
+ wake_up_process(thread);
+
+ return 0;
+}
+
+static void sugov_kthread_stop(struct sugov_policy *sg_policy)
+{
+ /* kthread only required for slow path */
+ if (sg_policy->policy->fast_switch_enabled)
+ return;
+
+ kthread_flush_worker(&sg_policy->worker);
+ kthread_stop(sg_policy->thread);
+ mutex_destroy(&sg_policy->work_lock);
+}
+
static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
{
struct sugov_tunables *tunables;
@@ -409,23 +593,30 @@ static int sugov_init(struct cpufreq_policy *policy)
{
struct sugov_policy *sg_policy;
struct sugov_tunables *tunables;
- unsigned int lat;
int ret = 0;
/* State should be equivalent to EXIT */
if (policy->governor_data)
return -EBUSY;
+ cpufreq_enable_fast_switch(policy);
+
sg_policy = sugov_policy_alloc(policy);
- if (!sg_policy)
- return -ENOMEM;
+ if (!sg_policy) {
+ ret = -ENOMEM;
+ goto disable_fast_switch;
+ }
+
+ ret = sugov_kthread_create(sg_policy);
+ if (ret)
+ goto free_sg_policy;
mutex_lock(&global_tunables_lock);
if (global_tunables) {
if (WARN_ON(have_governor_per_policy())) {
ret = -EINVAL;
- goto free_sg_policy;
+ goto stop_kthread;
}
policy->governor_data = sg_policy;
sg_policy->tunables = global_tunables;
@@ -437,13 +628,23 @@ static int sugov_init(struct cpufreq_policy *policy)
tunables = sugov_tunables_alloc(sg_policy);
if (!tunables) {
ret = -ENOMEM;
- goto free_sg_policy;
+ goto stop_kthread;
}
- tunables->rate_limit_us = LATENCY_MULTIPLIER;
- lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
- if (lat)
- tunables->rate_limit_us *= lat;
+ if (policy->up_transition_delay_us && policy->down_transition_delay_us) {
+ tunables->up_rate_limit_us = policy->up_transition_delay_us;
+ tunables->down_rate_limit_us = policy->down_transition_delay_us;
+ } else {
+ unsigned int lat;
+
+ tunables->up_rate_limit_us = LATENCY_MULTIPLIER;
+ tunables->down_rate_limit_us = LATENCY_MULTIPLIER;
+ lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+ if (lat) {
+ tunables->up_rate_limit_us *= lat;
+ tunables->down_rate_limit_us *= lat;
+ }
+ }
policy->governor_data = sg_policy;
sg_policy->tunables = tunables;
@@ -454,20 +655,25 @@ static int sugov_init(struct cpufreq_policy *policy)
if (ret)
goto fail;
- out:
+out:
mutex_unlock(&global_tunables_lock);
-
- cpufreq_enable_fast_switch(policy);
return 0;
- fail:
+fail:
policy->governor_data = NULL;
sugov_tunables_free(tunables);
+ stop_kthread:
+ sugov_kthread_stop(sg_policy);
+
free_sg_policy:
mutex_unlock(&global_tunables_lock);
sugov_policy_free(sg_policy);
+
+disable_fast_switch:
+ cpufreq_disable_fast_switch(policy);
+
pr_err("initialization failed (error %d)\n", ret);
return ret;
}
@@ -478,8 +684,6 @@ static void sugov_exit(struct cpufreq_policy *policy)
struct sugov_tunables *tunables = sg_policy->tunables;
unsigned int count;
- cpufreq_disable_fast_switch(policy);
-
mutex_lock(&global_tunables_lock);
count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
@@ -489,7 +693,10 @@ static void sugov_exit(struct cpufreq_policy *policy)
mutex_unlock(&global_tunables_lock);
+ sugov_kthread_stop(sg_policy);
sugov_policy_free(sg_policy);
+
+ cpufreq_disable_fast_switch(policy);
}
static int sugov_start(struct cpufreq_policy *policy)
@@ -497,7 +704,11 @@ static int sugov_start(struct cpufreq_policy *policy)
struct sugov_policy *sg_policy = policy->governor_data;
unsigned int cpu;
- sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
+ sg_policy->up_rate_delay_ns =
+ sg_policy->tunables->up_rate_limit_us * NSEC_PER_USEC;
+ sg_policy->down_rate_delay_ns =
+ sg_policy->tunables->down_rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
sg_policy->last_freq_update_time = 0;
sg_policy->next_freq = UINT_MAX;
sg_policy->work_in_progress = false;
@@ -509,7 +720,7 @@ static int sugov_start(struct cpufreq_policy *policy)
memset(sg_cpu, 0, sizeof(*sg_cpu));
sg_cpu->sg_policy = sg_policy;
- sg_cpu->flags = SCHED_CPUFREQ_RT;
+ sg_cpu->flags = SCHED_CPUFREQ_DL;
sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
policy_is_shared(policy) ?
@@ -529,8 +740,10 @@ static void sugov_stop(struct cpufreq_policy *policy)
synchronize_sched();
- irq_work_sync(&sg_policy->irq_work);
- cancel_work_sync(&sg_policy->work);
+ if (!policy->fast_switch_enabled) {
+ irq_work_sync(&sg_policy->irq_work);
+ kthread_cancel_work_sync(&sg_policy->work);
+ }
}
static void sugov_limits(struct cpufreq_policy *policy)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 448d642..1a15aac 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -4,11 +4,12 @@
#include <linux/kernel_stat.h>
#include <linux/static_key.h>
#include <linux/context_tracking.h>
+#include <linux/cpufreq_times.h>
#include "sched.h"
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif
-
+#include "walt.h"
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -58,11 +59,18 @@ void irqtime_account_irq(struct task_struct *curr)
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
s64 delta;
int cpu;
+#ifdef CONFIG_SCHED_WALT
+ u64 wallclock;
+ bool account = true;
+#endif
if (!sched_clock_irqtime)
return;
cpu = smp_processor_id();
+#ifdef CONFIG_SCHED_WALT
+ wallclock = sched_clock_cpu(cpu);
+#endif
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
@@ -76,6 +84,13 @@ void irqtime_account_irq(struct task_struct *curr)
irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
+#ifdef CONFIG_SCHED_WALT
+ else
+ account = false;
+
+ if (account)
+ walt_account_irqtime(cpu, curr, delta, wallclock);
+#endif
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
@@ -139,6 +154,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
/* Account for user time used */
acct_account_cputime(p);
+
+ /* Account power usage for user time */
+ cpufreq_acct_update_power(p, cputime);
}
/*
@@ -189,6 +207,9 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
/* Account for system time used */
acct_account_cputime(p);
+
+ /* Account power usage for system time */
+ cpufreq_acct_update_power(p, cputime);
}
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3042927..60ab536 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -18,6 +18,8 @@
#include <linux/slab.h>
+#include "walt.h"
+
struct dl_bandwidth def_dl_bandwidth;
static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
@@ -748,9 +750,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
* Nothing relies on rq->lock after this, so its safe to drop
* rq->lock.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
push_dl_task(rq);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
@@ -947,6 +949,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
add_nr_running(rq_of_dl_rq(dl_rq), 1);
+ walt_inc_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se));
inc_dl_deadline(dl_rq, deadline);
inc_dl_migration(dl_se, dl_rq);
@@ -961,6 +964,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+ walt_dec_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se));
dec_dl_deadline(dl_rq, dl_se->deadline);
dec_dl_migration(dl_se, dl_rq);
@@ -1245,7 +1249,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
}
struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
struct task_struct *p;
@@ -1260,9 +1264,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_dl_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
/*
* pull_rt_task() can drop (and re-acquire) rq->lock; this
* means a stop task can slip in, in which case we need to
@@ -1628,7 +1632,9 @@ static int push_dl_task(struct rq *rq)
}
deactivate_task(rq, next_task, 0);
+ next_task->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(next_task, later_rq->cpu);
+ next_task->on_rq = TASK_ON_RQ_QUEUED;
activate_task(later_rq, next_task, 0);
ret = 1;
@@ -1716,7 +1722,9 @@ static void pull_dl_task(struct rq *this_rq)
resched = true;
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, this_cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(this_rq, p, 0);
dmin = p->dl.deadline;
@@ -1929,6 +1937,9 @@ const struct sched_class dl_sched_class = {
.switched_to = switched_to_dl,
.update_curr = update_curr_dl,
+#ifdef CONFIG_SCHED_WALT
+ .fixup_cumulative_runnable_avg = walt_fixup_cumulative_runnable_avg,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fa178b6..f621b3a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -261,9 +261,60 @@ set_table_entry(struct ctl_table *entry,
}
static struct ctl_table *
+sd_alloc_ctl_energy_table(struct sched_group_energy *sge)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(5);
+
+ if (table == NULL)
+ return NULL;
+
+ set_table_entry(&table[0], "nr_idle_states", &sge->nr_idle_states,
+ sizeof(int), 0444, proc_dointvec_minmax, false);
+ set_table_entry(&table[1], "idle_states", &sge->idle_states[0].power,
+ sge->nr_idle_states*sizeof(struct idle_state), 0444,
+ proc_doulongvec_minmax, false);
+ set_table_entry(&table[2], "nr_cap_states", &sge->nr_cap_states,
+ sizeof(int), 0444, proc_dointvec_minmax, false);
+ set_table_entry(&table[3], "cap_states", &sge->cap_states[0].cap,
+ sge->nr_cap_states*sizeof(struct capacity_state), 0444,
+ proc_doulongvec_minmax, false);
+
+ return table;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_group_table(struct sched_group *sg)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(2);
+
+ if (table == NULL)
+ return NULL;
+
+ table->procname = kstrdup("energy", GFP_KERNEL);
+ table->mode = 0555;
+ table->child = sd_alloc_ctl_energy_table((struct sched_group_energy *)sg->sge);
+
+ return table;
+}
+
+static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
- struct ctl_table *table = sd_alloc_ctl_entry(14);
+ struct ctl_table *table;
+ unsigned int nr_entries = 14;
+
+ int i = 0;
+ struct sched_group *sg = sd->groups;
+
+ if (sg->sge) {
+ int nr_sgs = 0;
+
+ do {} while (nr_sgs++, sg = sg->next, sg != sd->groups);
+
+ nr_entries += nr_sgs;
+ }
+
+ table = sd_alloc_ctl_entry(nr_entries);
if (table == NULL)
return NULL;
@@ -296,7 +347,19 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[12], "name", sd->name,
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
- /* &table[13] is terminator */
+ sg = sd->groups;
+ if (sg->sge) {
+ char buf[32];
+ struct ctl_table *entry = &table[13];
+
+ do {
+ snprintf(buf, 32, "group%d", i);
+ entry->procname = kstrdup(buf, GFP_KERNEL);
+ entry->mode = 0555;
+ entry->child = sd_alloc_ctl_group_table(sg);
+ } while (entry++, i++, sg = sg->next, sg != sd->groups);
+ }
+ /* &table[nr_entries-1] is terminator */
return table;
}
@@ -918,7 +981,33 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
-
+ /* eas */
+ /* select_idle_sibling() */
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_attempts);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_idle);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_cache_affine);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_suff_cap);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_idle_cpu);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sis_count);
+ /* select_energy_cpu_brute() */
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_attempts);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_sync);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_idle_bt);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_insuff_cap);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_no_nrg_sav);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_nrg_sav);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_secb_count);
+ /* find_best_target() */
+ P_SCHEDSTAT(se.statistics.nr_wakeups_fbt_attempts);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_fbt_no_cpu);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_fbt_no_sd);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_fbt_pref_idle);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_fbt_count);
+ /* cas */
+ /* select_task_rq_fair() */
+ P_SCHEDSTAT(se.statistics.nr_wakeups_cas_attempts);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_cas_count);
+
avg_atom = p->se.sum_exec_runtime;
if (nr_switches)
avg_atom = div64_ul(avg_atom, nr_switches);
diff --git a/kernel/sched/energy.c b/kernel/sched/energy.c
new file mode 100644
index 0000000..b0656b7
--- /dev/null
+++ b/kernel/sched/energy.c
@@ -0,0 +1,124 @@
+/*
+ * Obtain energy cost data from DT and populate relevant scheduler data
+ * structures.
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#define pr_fmt(fmt) "sched-energy: " fmt
+
+#define DEBUG
+
+#include <linux/gfp.h>
+#include <linux/of.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/sched_energy.h>
+#include <linux/stddef.h>
+
+struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS];
+
+static void free_resources(void)
+{
+ int cpu, sd_level;
+ struct sched_group_energy *sge;
+
+ for_each_possible_cpu(cpu) {
+ for_each_possible_sd_level(sd_level) {
+ sge = sge_array[cpu][sd_level];
+ if (sge) {
+ kfree(sge->cap_states);
+ kfree(sge->idle_states);
+ kfree(sge);
+ }
+ }
+ }
+}
+
+void init_sched_energy_costs(void)
+{
+ struct device_node *cn, *cp;
+ struct capacity_state *cap_states;
+ struct idle_state *idle_states;
+ struct sched_group_energy *sge;
+ const struct property *prop;
+ int sd_level, i, nstates, cpu;
+ const __be32 *val;
+
+ for_each_possible_cpu(cpu) {
+ cn = of_get_cpu_node(cpu, NULL);
+ if (!cn) {
+ pr_warn("CPU device node missing for CPU %d\n", cpu);
+ return;
+ }
+
+ if (!of_find_property(cn, "sched-energy-costs", NULL)) {
+ pr_warn("CPU device node has no sched-energy-costs\n");
+ return;
+ }
+
+ for_each_possible_sd_level(sd_level) {
+ cp = of_parse_phandle(cn, "sched-energy-costs", sd_level);
+ if (!cp)
+ break;
+
+ prop = of_find_property(cp, "busy-cost-data", NULL);
+ if (!prop || !prop->value) {
+ pr_warn("No busy-cost data, skipping sched_energy init\n");
+ goto out;
+ }
+
+ sge = kcalloc(1, sizeof(struct sched_group_energy),
+ GFP_NOWAIT);
+
+ nstates = (prop->length / sizeof(u32)) / 2;
+ cap_states = kcalloc(nstates,
+ sizeof(struct capacity_state),
+ GFP_NOWAIT);
+
+ for (i = 0, val = prop->value; i < nstates; i++) {
+ cap_states[i].cap = be32_to_cpup(val++);
+ cap_states[i].power = be32_to_cpup(val++);
+ }
+
+ sge->nr_cap_states = nstates;
+ sge->cap_states = cap_states;
+
+ prop = of_find_property(cp, "idle-cost-data", NULL);
+ if (!prop || !prop->value) {
+ pr_warn("No idle-cost data, skipping sched_energy init\n");
+ goto out;
+ }
+
+ nstates = (prop->length / sizeof(u32));
+ idle_states = kcalloc(nstates,
+ sizeof(struct idle_state),
+ GFP_NOWAIT);
+
+ for (i = 0, val = prop->value; i < nstates; i++)
+ idle_states[i].power = be32_to_cpup(val++);
+
+ sge->nr_idle_states = nstates;
+ sge->idle_states = idle_states;
+
+ sge_array[cpu][sd_level] = sge;
+ }
+ }
+
+ pr_info("Sched-energy-costs installed from DT\n");
+ return;
+
+out:
+ free_resources();
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5a349fc..895d43b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -30,10 +30,13 @@
#include <linux/mempolicy.h>
#include <linux/migrate.h>
#include <linux/task_work.h>
+#include <linux/module.h>
#include <trace/events/sched.h>
#include "sched.h"
+#include "tune.h"
+#include "walt.h"
/*
* Targeted preemption latency for CPU-bound tasks:
@@ -50,6 +53,15 @@
unsigned int sysctl_sched_latency = 6000000ULL;
unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+unsigned int sysctl_sched_sync_hint_enable = 1;
+unsigned int sysctl_sched_cstate_aware = 1;
+
+#ifdef CONFIG_SCHED_WALT
+unsigned int sysctl_sched_use_walt_cpu_util = 1;
+unsigned int sysctl_sched_use_walt_task_util = 1;
+__read_mostly unsigned int sysctl_sched_walt_cpu_high_irqload =
+ (10 * NSEC_PER_MSEC);
+#endif
/*
* The initial- and re-scaling of tunables is configurable
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
@@ -116,7 +128,7 @@ unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
/*
* The margin used when comparing utilization with CPU capacity:
- * util * 1024 < capacity * margin
+ * util * margin < capacity * 1024
*/
unsigned int capacity_margin = 1280; /* ~20% */
@@ -290,19 +302,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (!cfs_rq->on_list) {
+ struct rq *rq = rq_of(cfs_rq);
+ int cpu = cpu_of(rq);
/*
* Ensure we either appear before our parent (if already
* enqueued) or force our parent to appear after us when it is
- * enqueued. The fact that we always enqueue bottom-up
- * reduces this to two cases.
+ * enqueued. The fact that we always enqueue bottom-up
+ * reduces this to two cases and a special case for the root
+ * cfs_rq. Furthermore, it also means that we will always reset
+ * tmp_alone_branch either when the branch is connected
+ * to a tree or when we reach the beg of the tree
*/
if (cfs_rq->tg->parent &&
- cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
- list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
- } else {
+ cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+ /*
+ * If parent is already on the list, we add the child
+ * just before. Thanks to circular linked property of
+ * the list, this means to put the child at the tail
+ * of the list that starts by parent.
+ */
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
+ &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+ /*
+ * The branch is now connected to its tree so we can
+ * reset tmp_alone_branch to the beginning of the
+ * list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else if (!cfs_rq->tg->parent) {
+ /*
+ * cfs rq without parent should be put
+ * at the tail of the list.
+ */
+ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+ &rq->leaf_cfs_rq_list);
+ /*
+ * We have reach the beg of a tree so we can reset
+ * tmp_alone_branch to the beginning of the list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else {
+ /*
+ * The parent has not already been added so we want to
+ * make sure that it will be put after us.
+ * tmp_alone_branch points to the beg of the branch
+ * where we will add parent.
+ */
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+ rq->tmp_alone_branch);
+ /*
+ * update tmp_alone_branch to points to the new beg
+ * of the branch
+ */
+ rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
}
cfs_rq->on_list = 1;
@@ -699,6 +751,7 @@ void init_entity_runnable_average(struct sched_entity *se)
if (entity_is_task(se))
sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
+
/*
* At this point, util_avg won't be used in select_task_rq_fair anyway
*/
@@ -708,9 +761,7 @@ void init_entity_runnable_average(struct sched_entity *se)
}
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
-static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force);
-static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+static void attach_entity_cfs_rq(struct sched_entity *se);
/*
* With new tasks being created, their initial util_avgs are extrapolated
@@ -742,7 +793,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
- u64 now = cfs_rq_clock_task(cfs_rq);
if (cap > 0) {
if (cfs_rq->avg.util_avg != 0) {
@@ -770,14 +820,12 @@ void post_init_entity_util_avg(struct sched_entity *se)
* such that the next switched_to_fair() has the
* expected state.
*/
- se->avg.last_update_time = now;
+ se->avg.last_update_time = cfs_rq_clock_task(cfs_rq);
return;
}
}
- update_cfs_rq_load_avg(now, cfs_rq, false);
- attach_entity_load_avg(cfs_rq, se);
- update_tg_load_avg(cfs_rq, false);
+ attach_entity_cfs_rq(se);
}
#else /* !CONFIG_SMP */
@@ -937,6 +985,7 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
trace_sched_stat_blocked(tsk, delta);
+ trace_sched_blocked_reason(tsk);
/*
* Blocking time is in units of nanosecs, so shift by
@@ -2666,16 +2715,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
struct task_group *tg;
- struct sched_entity *se;
long shares;
- tg = cfs_rq->tg;
- se = tg->se[cpu_of(rq_of(cfs_rq))];
- if (!se || throttled_hierarchy(cfs_rq))
+ if (!cfs_rq)
return;
+
+ if (throttled_hierarchy(cfs_rq))
+ return;
+
+ tg = cfs_rq->tg;
+
#ifndef CONFIG_SMP
if (likely(se->load.weight == tg->shares))
return;
@@ -2684,8 +2737,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
reweight_entity(cfs_rq_of(se), se, shares);
}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2836,6 +2890,7 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
scale_freq = arch_scale_freq_capacity(NULL, cpu);
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+ trace_sched_contrib_scale_f(cpu, scale_freq, scale_cpu);
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->period_contrib;
@@ -2911,6 +2966,26 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
return decayed;
}
+/*
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(_val) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ \
+ res = var + val; \
+ \
+ if (val < 0 && res > var) \
+ res = 0; \
+ \
+ WRITE_ONCE(*ptr, res); \
+} while (0)
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/**
* update_tg_load_avg - update the tg's load avg
@@ -2990,8 +3065,168 @@ void set_task_rq_fair(struct sched_entity *se,
se->avg.last_update_time = n_last_update_time;
}
}
+
+/* Take into account change of utilization of a child task group */
+static inline void
+update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+ long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /* Set new sched_entity's utilization */
+ se->avg.util_avg = gcfs_rq->avg.util_avg;
+ se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq utilization */
+ add_positive(&cfs_rq->avg.util_avg, delta);
+ cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+}
+
+/* Take into account change of load of a child task group */
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+ long delta, load = gcfs_rq->avg.load_avg;
+
+ /*
+ * If the load of group cfs_rq is null, the load of the
+ * sched_entity will also be null so we can skip the formula
+ */
+ if (load) {
+ long tg_load;
+
+ /* Get tg's load and ensure tg_load > 0 */
+ tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
+
+ /* Ensure tg_load >= load and updated with current load*/
+ tg_load -= gcfs_rq->tg_load_avg_contrib;
+ tg_load += load;
+
+ /*
+ * We need to compute a correction term in the case that the
+ * task group is consuming more CPU than a task of equal
+ * weight. A task with a weight equals to tg->shares will have
+ * a load less or equal to scale_load_down(tg->shares).
+ * Similarly, the sched_entities that represent the task group
+ * at parent level, can't have a load higher than
+ * scale_load_down(tg->shares). And the Sum of sched_entities'
+ * load must be <= scale_load_down(tg->shares).
+ */
+ if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
+ /* scale gcfs_rq's load into tg's shares*/
+ load *= scale_load_down(gcfs_rq->tg->shares);
+ load /= tg_load;
+ }
+ }
+
+ delta = load - se->avg.load_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /* Set new sched_entity's load */
+ se->avg.load_avg = load;
+ se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq load */
+ add_positive(&cfs_rq->avg.load_avg, delta);
+ cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+
+ /*
+ * If the sched_entity is already enqueued, we also have to update the
+ * runnable load avg.
+ */
+ if (se->on_rq) {
+ /* Update parent cfs_rq runnable_load_avg */
+ add_positive(&cfs_rq->runnable_load_avg, delta);
+ cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
+ }
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
+{
+ cfs_rq->propagate_avg = 1;
+}
+
+static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
+
+ if (!cfs_rq->propagate_avg)
+ return 0;
+
+ cfs_rq->propagate_avg = 0;
+ return 1;
+}
+
+/* Update task and its cfs_rq load average */
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq;
+
+ if (entity_is_task(se))
+ return 0;
+
+ if (!test_and_clear_tg_cfs_propagate(se))
+ return 0;
+
+ cfs_rq = cfs_rq_of(se);
+
+ set_tg_cfs_propagate(cfs_rq);
+
+ update_tg_cfs_util(cfs_rq, se);
+ update_tg_cfs_load(cfs_rq, se);
+
+ return 1;
+}
+
+/*
+ * Check if we need to update the load and the utilization of a blocked
+ * group_entity:
+ */
+static inline bool skip_blocked_update(struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+
+ /*
+ * If sched_entity still have not zero load or utilization, we have to
+ * decay it:
+ */
+ if (se->avg.load_avg || se->avg.util_avg)
+ return false;
+
+ /*
+ * If there is a pending propagation, we have to update the load and
+ * the utilization of the sched_entity:
+ */
+ if (gcfs_rq->propagate_avg)
+ return false;
+
+ /*
+ * Otherwise, the load and the utilization of the sched_entity is
+ * already zero and there is no pending propagation, so it will be a
+ * waste of time to try to decay it:
+ */
+ return true;
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
+
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
+
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+ return 0;
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
+
#endif /* CONFIG_FAIR_GROUP_SCHED */
static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
@@ -3062,6 +3297,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
sub_positive(&sa->load_avg, r);
sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed_load = 1;
+ set_tg_cfs_propagate(cfs_rq);
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
@@ -3069,6 +3305,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
removed_util = 1;
+ set_tg_cfs_propagate(cfs_rq);
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -3082,27 +3319,51 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
if (update_freq && (decayed || removed_util))
cfs_rq_util_change(cfs_rq);
+ /* Trace CPU load, unless cfs_rq belongs to a non-root task_group */
+ if (cfs_rq == &rq_of(cfs_rq)->cfs)
+ trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
+
return decayed || removed_load;
}
+/*
+ * Optional action to be done while updating the load average
+ */
+#define UPDATE_TG 0x1
+#define SKIP_AGE_LOAD 0x2
+
/* Update task and its cfs_rq load average */
-static inline void update_load_avg(struct sched_entity *se, int update_tg)
+static inline void update_load_avg(struct sched_entity *se, int flags)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 now = cfs_rq_clock_task(cfs_rq);
struct rq *rq = rq_of(cfs_rq);
int cpu = cpu_of(rq);
+ int decayed;
+ void *ptr = NULL;
/*
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
- __update_load_avg(now, cpu, &se->avg,
+ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
+ __update_load_avg(now, cpu, &se->avg,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
+ }
- if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg)
+ decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
+ decayed |= propagate_entity_load_avg(se);
+
+ if (decayed && (flags & UPDATE_TG))
update_tg_load_avg(cfs_rq, 0);
+
+ if (entity_is_task(se)) {
+#ifdef CONFIG_SCHED_WALT
+ ptr = (void *)&(task_of(se)->ravg);
+#endif
+ trace_sched_load_avg_task(task_of(se), &se->avg, ptr);
+ }
}
/**
@@ -3115,31 +3376,12 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
*/
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (!sched_feat(ATTACH_AGE_LOAD))
- goto skip_aging;
-
- /*
- * If we got migrated (either between CPUs or between cgroups) we'll
- * have aged the average right before clearing @last_update_time.
- *
- * Or we're fresh through post_init_entity_util_avg().
- */
- if (se->avg.last_update_time) {
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, 0, 0, NULL);
-
- /*
- * XXX: we could have just aged the entire load away if we've been
- * absent from the fair class for too long.
- */
- }
-
-skip_aging:
se->avg.last_update_time = cfs_rq->avg.last_update_time;
cfs_rq->avg.load_avg += se->avg.load_avg;
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+ set_tg_cfs_propagate(cfs_rq);
cfs_rq_util_change(cfs_rq);
}
@@ -3154,14 +3396,12 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
*/
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+ set_tg_cfs_propagate(cfs_rq);
cfs_rq_util_change(cfs_rq);
}
@@ -3171,34 +3411,20 @@ static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct sched_avg *sa = &se->avg;
- u64 now = cfs_rq_clock_task(cfs_rq);
- int migrated, decayed;
-
- migrated = !sa->last_update_time;
- if (!migrated) {
- __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
- se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
- }
-
- decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated);
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
- if (migrated)
+ if (!sa->last_update_time) {
attach_entity_load_avg(cfs_rq, se);
-
- if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
+ }
}
/* Remove the runnable load generated by se from cfs_rq's runnable load average */
static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- update_load_avg(se, 1);
-
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
@@ -3227,13 +3453,25 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
#endif
/*
+ * Synchronize entity load avg of dequeued entity without locking
+ * the previous rq.
+ */
+void sync_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 last_update_time;
+
+ last_update_time = cfs_rq_last_update_time(cfs_rq);
+ __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+}
+
+/*
* Task first catches up with cfs_rq, and then subtract
* itself from the cfs_rq (task must be off the queue now).
*/
void remove_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 last_update_time;
/*
* tasks cannot exit without having gone through wake_up_new_task() ->
@@ -3245,9 +3483,7 @@ void remove_entity_load_avg(struct sched_entity *se)
* calls this.
*/
- last_update_time = cfs_rq_last_update_time(cfs_rq);
-
- __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+ sync_entity_load_avg(se);
atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
}
@@ -3272,7 +3508,10 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
return 0;
}
-static inline void update_load_avg(struct sched_entity *se, int not_used)
+#define UPDATE_TG 0x0
+#define SKIP_AGE_LOAD 0x0
+
+static inline void update_load_avg(struct sched_entity *se, int not_used1)
{
cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
}
@@ -3417,9 +3656,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (renorm && !curr)
se->vruntime += cfs_rq->min_vruntime;
+ /*
+ * When enqueuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Add its load to cfs_rq->runnable_avg
+ * - For group_entity, update its weight to reflect the new share of
+ * its group cfs_rq
+ * - Add its new weight to cfs_rq->load.weight
+ */
+ update_load_avg(se, UPDATE_TG);
enqueue_entity_load_avg(cfs_rq, se);
+ update_cfs_shares(se);
account_entity_enqueue(cfs_rq, se);
- update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP)
place_entity(cfs_rq, se, 0);
@@ -3491,6 +3739,16 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+
+ /*
+ * When dequeuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Substract its load from the cfs_rq->runnable_avg.
+ * - Substract its previous weight from cfs_rq->load.weight.
+ * - For group entity, update its weight to reflect the new share
+ * of its group cfs_rq.
+ */
+ update_load_avg(se, UPDATE_TG);
dequeue_entity_load_avg(cfs_rq, se);
update_stats_dequeue(cfs_rq, se, flags);
@@ -3514,7 +3772,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
/*
* Now advance min_vruntime if @se was the entity holding it back,
@@ -3578,7 +3836,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
- update_load_avg(se, 1);
+ update_load_avg(se, UPDATE_TG);
}
update_stats_curr_start(cfs_rq, se);
@@ -3696,8 +3954,8 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
/*
* Ensure that runnable average is periodically updated.
*/
- update_load_avg(curr, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(curr, UPDATE_TG);
+ update_cfs_shares(curr);
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -3958,6 +4216,23 @@ static int tg_throttle_down(struct task_group *tg, void *data)
return 0;
}
+#ifdef CONFIG_SCHED_WALT
+static inline void walt_propagate_cumulative_runnable_avg(u64 *accumulated,
+ u64 value, bool add)
+{
+ if (add)
+ *accumulated += value;
+ else
+ *accumulated -= value;
+}
+#else
+/*
+ * Provide a nop definition since cumulative_runnable_avg is not
+ * available in rq or cfs_rq when WALT is not enabled.
+ */
+#define walt_propagate_cumulative_runnable_avg(...)
+#endif
+
static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
@@ -3983,13 +4258,21 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
if (dequeue)
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
qcfs_rq->h_nr_running -= task_delta;
+ walt_propagate_cumulative_runnable_avg(
+ &qcfs_rq->cumulative_runnable_avg,
+ cfs_rq->cumulative_runnable_avg, false);
+
if (qcfs_rq->load.weight)
dequeue = 0;
}
- if (!se)
+ if (!se) {
sub_nr_running(rq, task_delta);
+ walt_propagate_cumulative_runnable_avg(
+ &rq->cumulative_runnable_avg,
+ cfs_rq->cumulative_runnable_avg, false);
+ }
cfs_rq->throttled = 1;
cfs_rq->throttled_clock = rq_clock(rq);
@@ -4023,6 +4306,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct sched_entity *se;
int enqueue = 1;
long task_delta;
+ struct cfs_rq *tcfs_rq __maybe_unused = cfs_rq;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4050,13 +4334,20 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
if (enqueue)
enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
cfs_rq->h_nr_running += task_delta;
+ walt_propagate_cumulative_runnable_avg(
+ &cfs_rq->cumulative_runnable_avg,
+ tcfs_rq->cumulative_runnable_avg, true);
if (cfs_rq_throttled(cfs_rq))
break;
}
- if (!se)
+ if (!se) {
add_nr_running(rq, task_delta);
+ walt_propagate_cumulative_runnable_avg(
+ &rq->cumulative_runnable_avg,
+ tcfs_rq->cumulative_runnable_avg, true);
+ }
/* determine whether we need to wake up potentially idle cpu */
if (rq->curr == rq->idle && rq->cfs.nr_running)
@@ -4506,6 +4797,30 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
}
}
+#ifdef CONFIG_SCHED_WALT
+static void walt_fixup_cumulative_runnable_avg_fair(struct rq *rq,
+ struct task_struct *p,
+ u64 new_task_load)
+{
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *se = &p->se;
+ s64 task_load_delta = (s64)new_task_load - p->ravg.demand;
+
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ cfs_rq->cumulative_runnable_avg += task_load_delta;
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+ }
+
+ /* Fix up rq only if we didn't find any throttled cfs_rq */
+ if (!se)
+ walt_fixup_cumulative_runnable_avg(rq, p, new_task_load);
+}
+
+#endif /* CONFIG_SCHED_WALT */
+
#else /* CONFIG_CFS_BANDWIDTH */
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
@@ -4548,6 +4863,9 @@ static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
static inline void update_runtime_enabled(struct rq *rq) {}
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+#define walt_fixup_cumulative_runnable_avg_fair \
+ walt_fixup_cumulative_runnable_avg
+
#endif /* CONFIG_CFS_BANDWIDTH */
/**************************************************
@@ -4602,6 +4920,14 @@ static inline void hrtick_update(struct rq *rq)
}
#endif
+#ifdef CONFIG_SMP
+static bool __cpu_overutilized(int cpu, int delta);
+static bool cpu_overutilized(int cpu);
+unsigned long boosted_cpu_util(int cpu);
+#else
+#define boosted_cpu_util(cpu) cpu_util_freq(cpu)
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
@@ -4612,6 +4938,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+#ifdef CONFIG_SMP
+ int task_new = flags & ENQUEUE_WAKEUP_NEW;
+#endif
/*
* If in_iowait is set, the code below may not trigger any cpufreq
@@ -4636,6 +4965,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
flags = ENQUEUE_WAKEUP;
}
@@ -4643,17 +4973,49 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
}
if (!se)
add_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting.
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ *
+ * We do it also in the case where we enqueue a throttled task;
+ * we could argue that a throttled task should not boost a CPU,
+ * however:
+ * a) properly implementing CPU boosting considering throttled
+ * tasks will increase a lot the complexity of the solution
+ * b) it's not easy to quantify the benefits introduced by
+ * such a more complex solution.
+ * Thus, for the time being we go for the simple solution and boost
+ * also for throttled RQs.
+ */
+ schedtune_enqueue_task(p, cpu_of(rq));
+
+ if (!se) {
+ walt_inc_cumulative_runnable_avg(rq, p);
+ if (!task_new && !rq->rd->overutilized &&
+ cpu_overutilized(rq->cpu)) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+ }
+
+#endif /* CONFIG_SMP */
hrtick_update(rq);
}
@@ -4683,6 +5045,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
@@ -4702,17 +5065,33 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
}
if (!se)
sub_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ */
+ schedtune_dequeue_task(p, cpu_of(rq));
+
+ if (!se)
+ walt_dec_cumulative_runnable_avg(rq, p);
+#endif /* CONFIG_SMP */
+
hrtick_update(rq);
}
@@ -5019,15 +5398,6 @@ static unsigned long target_load(int cpu, int type)
return max(rq->cpu_load[type-1], total);
}
-static unsigned long capacity_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity;
-}
-
-static unsigned long capacity_orig_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity_orig;
-}
static unsigned long cpu_avg_load_per_task(int cpu)
{
@@ -5179,6 +5549,533 @@ static void record_wakee(struct task_struct *p)
}
/*
+ * Returns the current capacity of cpu after applying both
+ * cpu and freq scaling.
+ */
+unsigned long capacity_curr_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity_orig *
+ arch_scale_freq_capacity(NULL, cpu)
+ >> SCHED_CAPACITY_SHIFT;
+}
+
+/*
+ * Returns the current capacity of cpu after applying both
+ * cpu and min freq scaling.
+ */
+unsigned long capacity_min_of(int cpu)
+{
+ if (!sched_feat(MIN_CAPACITY_CAPPING))
+ return 0;
+ return arch_scale_cpu_capacity(NULL, cpu) *
+ arch_scale_min_freq_capacity(NULL, cpu)
+ >> SCHED_CAPACITY_SHIFT;
+}
+
+
+static inline bool energy_aware(void)
+{
+ return sched_feat(ENERGY_AWARE);
+}
+
+/*
+ * CPU candidates.
+ *
+ * These are labels to reference CPU candidates for an energy_diff.
+ * Currently we support only two possible candidates: the task's previous CPU
+ * and another candiate CPU.
+ * More advanced/aggressive EAS selection policies can consider more
+ * candidates.
+ */
+#define EAS_CPU_PRV 0
+#define EAS_CPU_NXT 1
+#define EAS_CPU_BKP 2
+#define EAS_CPU_CNT 3
+
+/*
+ * energy_diff - supports the computation of the estimated energy impact in
+ * moving a "task"'s "util_delta" between different CPU candidates.
+ */
+struct energy_env {
+ /* Utilization to move */
+ struct task_struct *p;
+ int util_delta;
+
+ /* Mask of CPUs candidates to evaluate */
+ cpumask_t cpus_mask;
+
+ /* CPU candidates to evaluate */
+ struct {
+
+ /* CPU ID, must be in cpus_mask */
+ int cpu_id;
+
+ /*
+ * Index (into sched_group_energy::cap_states) of the OPP the
+ * CPU needs to run at if the task is placed on it.
+ * This includes the both active and blocked load, due to
+ * other tasks on this CPU, as well as the task's own
+ * utilization.
+ */
+ int cap_idx;
+ int cap;
+
+ /* Estimated system energy */
+ unsigned int energy;
+
+ /* Estimated energy variation wrt EAS_CPU_PRV */
+ int nrg_delta;
+
+ } cpu[EAS_CPU_CNT];
+
+ /*
+ * Index (into energy_env::cpu) of the morst energy efficient CPU for
+ * the specified energy_env::task
+ */
+ int next_idx;
+
+ /* Support data */
+ struct sched_group *sg_top;
+ struct sched_group *sg_cap;
+ struct sched_group *sg;
+};
+
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+/*
+ * __cpu_norm_util() returns the cpu util relative to a specific capacity,
+ * i.e. it's busy ratio, in the range [0..SCHED_LOAD_SCALE], which is useful for
+ * energy calculations.
+ *
+ * Since util is a scale-invariant utilization defined as:
+ *
+ * util ~ (curr_freq/max_freq)*1024 * capacity_orig/1024 * running_time/time
+ *
+ * the normalized util can be found using the specific capacity.
+ *
+ * capacity = capacity_orig * curr_freq/max_freq
+ *
+ * norm_util = running_time/time ~ util/capacity
+ */
+static unsigned long __cpu_norm_util(unsigned long util, unsigned long capacity)
+{
+ if (util >= capacity)
+ return SCHED_CAPACITY_SCALE;
+
+ return (util << SCHED_CAPACITY_SHIFT)/capacity;
+}
+
+static unsigned long group_max_util(struct energy_env *eenv, int cpu_idx)
+{
+ unsigned long max_util = 0;
+ unsigned long util;
+ int cpu;
+
+ for_each_cpu(cpu, sched_group_cpus(eenv->sg_cap)) {
+ util = cpu_util_wake(cpu, eenv->p);
+
+ /*
+ * If we are looking at the target CPU specified by the eenv,
+ * then we should add the (estimated) utilization of the task
+ * assuming we will wake it up on that CPU.
+ */
+ if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id))
+ util += eenv->util_delta;
+
+ max_util = max(max_util, util);
+
+ /*
+ * Take into account any minimum frequency imposed
+ * elsewhere which limits the energy states available
+ * If the MIN_CAPACITY_CAPPING feature is not enabled
+ * capacity_min_of will return 0 (not capped).
+ */
+ max_util = max(max_util, capacity_min_of(cpu));
+
+ }
+
+ return max_util;
+}
+
+/*
+ * group_norm_util() returns the approximated group util relative to it's
+ * current capacity (busy ratio), in the range [0..SCHED_LOAD_SCALE], for use
+ * in energy calculations.
+ *
+ * Since task executions may or may not overlap in time in the group the true
+ * normalized util is between MAX(cpu_norm_util(i)) and SUM(cpu_norm_util(i))
+ * when iterating over all CPUs in the group.
+ * The latter estimate is used as it leads to a more pessimistic energy
+ * estimate (more busy).
+ */
+static unsigned
+long group_norm_util(struct energy_env *eenv, int cpu_idx)
+{
+ unsigned long capacity = eenv->cpu[cpu_idx].cap;
+ unsigned long util, util_sum = 0;
+ int cpu;
+
+ for_each_cpu(cpu, sched_group_cpus(eenv->sg)) {
+ util = cpu_util_wake(cpu, eenv->p);
+
+ /*
+ * If we are looking at the target CPU specified by the eenv,
+ * then we should add the (estimated) utilization of the task
+ * assuming we will wake it up on that CPU.
+ */
+ if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id))
+ util += eenv->util_delta;
+
+ util_sum += __cpu_norm_util(util, capacity);
+ }
+
+ return min_t(unsigned long, util_sum, SCHED_CAPACITY_SCALE);
+}
+
+static int find_new_capacity(struct energy_env *eenv, int cpu_idx)
+{
+ const struct sched_group_energy *sge = eenv->sg->sge;
+ int idx, max_idx = sge->nr_cap_states - 1;
+ unsigned long util = group_max_util(eenv, cpu_idx);
+
+ /* default is max_cap if we don't find a match */
+ eenv->cpu[cpu_idx].cap_idx = max_idx;
+ eenv->cpu[cpu_idx].cap = sge->cap_states[max_idx].cap;
+
+ for (idx = 0; idx < sge->nr_cap_states; idx++) {
+ if (sge->cap_states[idx].cap >= util) {
+ /* Keep track of SG's capacity */
+ eenv->cpu[cpu_idx].cap_idx = idx;
+ eenv->cpu[cpu_idx].cap = sge->cap_states[idx].cap;
+ break;
+ }
+ }
+
+ return eenv->cpu[cpu_idx].cap_idx;
+}
+
+static int group_idle_state(struct energy_env *eenv, int cpu_idx)
+{
+ struct sched_group *sg = eenv->sg;
+ int i, state = INT_MAX;
+ int src_in_grp, dst_in_grp;
+ long grp_util = 0;
+
+ /* Find the shallowest idle state in the sched group. */
+ for_each_cpu(i, sched_group_cpus(sg))
+ state = min(state, idle_get_state_idx(cpu_rq(i)));
+
+ /* Take non-cpuidle idling into account (active idle/arch_cpu_idle()) */
+ state++;
+
+ src_in_grp = cpumask_test_cpu(eenv->cpu[EAS_CPU_PRV].cpu_id,
+ sched_group_cpus(sg));
+ dst_in_grp = cpumask_test_cpu(eenv->cpu[cpu_idx].cpu_id,
+ sched_group_cpus(sg));
+ if (src_in_grp == dst_in_grp) {
+ /* both CPUs under consideration are in the same group or not in
+ * either group, migration should leave idle state the same.
+ */
+ goto end;
+ }
+
+ /*
+ * Try to estimate if a deeper idle state is
+ * achievable when we move the task.
+ */
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ grp_util += cpu_util_wake(i, eenv->p);
+ if (unlikely(i == eenv->cpu[cpu_idx].cpu_id))
+ grp_util += eenv->util_delta;
+ }
+
+ if (grp_util <=
+ ((long)sg->sgc->max_capacity * (int)sg->group_weight)) {
+ /* after moving, this group is at most partly
+ * occupied, so it should have some idle time.
+ */
+ int max_idle_state_idx = sg->sge->nr_idle_states - 2;
+ int new_state = grp_util * max_idle_state_idx;
+ if (grp_util <= 0)
+ /* group will have no util, use lowest state */
+ new_state = max_idle_state_idx + 1;
+ else {
+ /* for partially idle, linearly map util to idle
+ * states, excluding the lowest one. This does not
+ * correspond to the state we expect to enter in
+ * reality, but an indication of what might happen.
+ */
+ new_state = min(max_idle_state_idx, (int)
+ (new_state / sg->sgc->max_capacity));
+ new_state = max_idle_state_idx - new_state;
+ }
+ state = new_state;
+ } else {
+ /* After moving, the group will be fully occupied
+ * so assume it will not be idle at all.
+ */
+ state = 0;
+ }
+end:
+ return state;
+}
+
+/*
+ * calc_sg_energy: compute energy for the eenv's SG (i.e. eenv->sg).
+ *
+ * This works in iterations to compute the SG's energy for each CPU
+ * candidate defined by the energy_env's cpu array.
+ *
+ * NOTE: in the following computations for busy_energy and idle_energy we do
+ * not shift by SCHED_CAPACITY_SHIFT in order to reduce rounding errors.
+ * The required scaling will be performed just one time, by the calling
+ * functions, once we accumulated the contributons for all the SGs.
+ */
+static void calc_sg_energy(struct energy_env *eenv)
+{
+ struct sched_group *sg = eenv->sg;
+ int busy_energy, idle_energy;
+ unsigned int busy_power;
+ unsigned int idle_power;
+ unsigned long sg_util;
+ int cap_idx, idle_idx;
+ int total_energy = 0;
+ int cpu_idx;
+
+ for (cpu_idx = EAS_CPU_PRV; cpu_idx < EAS_CPU_CNT; ++cpu_idx) {
+
+
+ if (eenv->cpu[cpu_idx].cpu_id == -1)
+ continue;
+ /* Compute ACTIVE energy */
+ cap_idx = find_new_capacity(eenv, cpu_idx);
+ busy_power = sg->sge->cap_states[cap_idx].power;
+ /*
+ * in order to calculate cpu_norm_util, we need to know which
+ * capacity level the group will be at, so calculate that first
+ */
+ sg_util = group_norm_util(eenv, cpu_idx);
+
+ busy_energy = sg_util * busy_power;
+
+ /* Compute IDLE energy */
+ idle_idx = group_idle_state(eenv, cpu_idx);
+ idle_power = sg->sge->idle_states[idle_idx].power;
+
+ idle_energy = SCHED_CAPACITY_SCALE - sg_util;
+ idle_energy *= idle_power;
+
+ total_energy = busy_energy + idle_energy;
+ eenv->cpu[cpu_idx].energy += total_energy;
+ }
+}
+
+/*
+ * compute_energy() computes the absolute variation in energy consumption by
+ * moving eenv.util_delta from EAS_CPU_PRV to EAS_CPU_NXT.
+ *
+ * NOTE: compute_energy() may fail when racing with sched_domain updates, in
+ * which case we abort by returning -EINVAL.
+ */
+static int compute_energy(struct energy_env *eenv)
+{
+ struct cpumask visit_cpus;
+ int cpu_count;
+
+ WARN_ON(!eenv->sg_top->sge);
+
+ cpumask_copy(&visit_cpus, sched_group_cpus(eenv->sg_top));
+ /* If a cpu is hotplugged in while we are in this function,
+ * it does not appear in the existing visit_cpus mask
+ * which came from the sched_group pointer of the
+ * sched_domain pointed at by sd_ea for either the prev
+ * or next cpu and was dereferenced in __energy_diff.
+ * Since we will dereference sd_scs later as we iterate
+ * through the CPUs we expect to visit, new CPUs can
+ * be present which are not in the visit_cpus mask.
+ * Guard this with cpu_count.
+ */
+ cpu_count = cpumask_weight(&visit_cpus);
+
+ while (!cpumask_empty(&visit_cpus)) {
+ struct sched_group *sg_shared_cap = NULL;
+ int cpu = cpumask_first(&visit_cpus);
+ struct sched_domain *sd;
+
+ /*
+ * Is the group utilization affected by cpus outside this
+ * sched_group?
+ * This sd may have groups with cpus which were not present
+ * when we took visit_cpus.
+ */
+ sd = rcu_dereference(per_cpu(sd_scs, cpu));
+ if (sd && sd->parent)
+ sg_shared_cap = sd->parent->groups;
+
+ for_each_domain(cpu, sd) {
+ struct sched_group *sg = sd->groups;
+
+ /* Has this sched_domain already been visited? */
+ if (sd->child && group_first_cpu(sg) != cpu)
+ break;
+
+ do {
+ eenv->sg_cap = sg;
+ if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
+ eenv->sg_cap = sg_shared_cap;
+
+ /*
+ * Compute the energy for all the candidate
+ * CPUs in the current visited SG.
+ */
+ eenv->sg = sg;
+ calc_sg_energy(eenv);
+
+ if (!sd->child) {
+ /*
+ * cpu_count here is the number of
+ * cpus we expect to visit in this
+ * calculation. If we race against
+ * hotplug, we can have extra cpus
+ * added to the groups we are
+ * iterating which do not appear in
+ * the visit_cpus mask. In that case
+ * we are not able to calculate energy
+ * without restarting so we will bail
+ * out and use prev_cpu this time.
+ */
+ if (!cpu_count)
+ return -EINVAL;
+ cpumask_xor(&visit_cpus, &visit_cpus, sched_group_cpus(sg));
+ cpu_count--;
+ }
+
+ if (cpumask_equal(sched_group_cpus(sg), sched_group_cpus(eenv->sg_top)) &&
+ sd->child)
+ goto next_cpu;
+
+ } while (sg = sg->next, sg != sd->groups);
+ }
+
+ /*
+ * If we raced with hotplug and got an sd NULL-pointer;
+ * returning a wrong energy estimation is better than
+ * entering an infinite loop.
+ * Specifically: If a cpu is unplugged after we took
+ * the visit_cpus mask, it no longer has an sd_scs
+ * pointer, so when we dereference it, we get NULL.
+ */
+ if (cpumask_test_cpu(cpu, &visit_cpus))
+ return -EINVAL;
+next_cpu:
+ cpumask_clear_cpu(cpu, &visit_cpus);
+ continue;
+ }
+
+ return 0;
+}
+
+static inline bool cpu_in_sg(struct sched_group *sg, int cpu)
+{
+ return cpu != -1 && cpumask_test_cpu(cpu, sched_group_cpus(sg));
+}
+
+/*
+ * select_energy_cpu_idx(): estimate the energy impact of changing the
+ * utilization distribution.
+ *
+ * The eenv parameter specifies the changes: utilisation amount and a pair of
+ * possible CPU candidates (the previous CPU and a different target CPU).
+ *
+ * This function returns the index of a CPU candidate specified by the
+ * energy_env which corresponds to the first CPU saving energy.
+ * Thus, 0 (EAS_CPU_PRV) means that non of the CPU candidate is more energy
+ * efficient than running on prev_cpu. This is also the value returned in case
+ * of abort due to error conditions during the computations.
+ * A value greater than zero means that the first energy-efficient CPU is the
+ * one represented by eenv->cpu[eenv->next_idx].cpu_id.
+ */
+static inline int select_energy_cpu_idx(struct energy_env *eenv)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int sd_cpu = -1;
+ int cpu_idx;
+ int margin;
+
+ sd_cpu = eenv->cpu[EAS_CPU_PRV].cpu_id;
+ sd = rcu_dereference(per_cpu(sd_ea, sd_cpu));
+ if (!sd)
+ return EAS_CPU_PRV;
+
+ cpumask_clear(&eenv->cpus_mask);
+ for (cpu_idx = EAS_CPU_PRV; cpu_idx < EAS_CPU_CNT; ++cpu_idx) {
+ int cpu = eenv->cpu[cpu_idx].cpu_id;
+
+ if (cpu < 0)
+ continue;
+ cpumask_set_cpu(cpu, &eenv->cpus_mask);
+ }
+
+ sg = sd->groups;
+ do {
+ /* Skip SGs which do not contains a candidate CPU */
+ if (!cpumask_intersects(&eenv->cpus_mask, sched_group_cpus(sg)))
+ continue;
+
+ eenv->sg_top = sg;
+ /* energy is unscaled to reduce rounding errors */
+ if (compute_energy(eenv) == -EINVAL)
+ return EAS_CPU_PRV;
+
+ } while (sg = sg->next, sg != sd->groups);
+
+ /* Scale energy before comparisons */
+ for (cpu_idx = EAS_CPU_PRV; cpu_idx < EAS_CPU_CNT; ++cpu_idx)
+ eenv->cpu[cpu_idx].energy >>= SCHED_CAPACITY_SHIFT;
+
+ /*
+ * Compute the dead-zone margin used to prevent too many task
+ * migrations with negligible energy savings.
+ * An energy saving is considered meaningful if it reduces the energy
+ * consumption of EAS_CPU_PRV CPU candidate by at least ~1.56%
+ */
+ margin = eenv->cpu[EAS_CPU_PRV].energy >> 6;
+
+ /*
+ * By default the EAS_CPU_PRV CPU is considered the most energy
+ * efficient, with a 0 energy variation.
+ */
+ eenv->next_idx = EAS_CPU_PRV;
+
+ /*
+ * Compare the other CPU candidates to find a CPU which can be
+ * more energy efficient then EAS_CPU_PRV
+ */
+ for (cpu_idx = EAS_CPU_NXT; cpu_idx < EAS_CPU_CNT; ++cpu_idx) {
+ /* Skip not valid scheduled candidates */
+ if (eenv->cpu[cpu_idx].cpu_id < 0)
+ continue;
+ /* Compute energy delta wrt EAS_CPU_PRV */
+ eenv->cpu[cpu_idx].nrg_delta =
+ eenv->cpu[cpu_idx].energy -
+ eenv->cpu[EAS_CPU_PRV].energy;
+ /* filter energy variations within the dead-zone margin */
+ if (abs(eenv->cpu[cpu_idx].nrg_delta) < margin)
+ eenv->cpu[cpu_idx].nrg_delta = 0;
+ /* update the schedule candidate with min(nrg_delta) */
+ if (eenv->cpu[cpu_idx].nrg_delta <
+ eenv->cpu[eenv->next_idx].nrg_delta) {
+ eenv->next_idx = cpu_idx;
+ if (sched_feat(FBT_STRICT_ORDER))
+ break;
+ }
+ }
+
+ return eenv->next_idx;
+}
+
+/*
* Detect M:N waker/wakee relationships via a switching-frequency heuristic.
*
* A waker of many should wake a different task than the one last awakened
@@ -5274,24 +6171,180 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
return 1;
}
+static inline unsigned long task_util(struct task_struct *p)
+{
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_task_util) {
+ unsigned long demand = p->ravg.demand;
+ return (demand << SCHED_CAPACITY_SHIFT) / walt_ravg_window;
+ }
+#endif
+ return p->se.avg.util_avg;
+}
+
+static inline unsigned long boosted_task_util(struct task_struct *p);
+
+static inline bool __task_fits(struct task_struct *p, int cpu, int util)
+{
+ unsigned long capacity = capacity_of(cpu);
+
+ util += boosted_task_util(p);
+
+ return (capacity * 1024) > (util * capacity_margin);
+}
+
+static inline bool task_fits_max(struct task_struct *p, int cpu)
+{
+ unsigned long capacity = capacity_of(cpu);
+ unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+ if (capacity == max_capacity)
+ return true;
+
+ if (capacity * capacity_margin > max_capacity * 1024)
+ return true;
+
+ return __task_fits(p, cpu, 0);
+}
+
+static bool __cpu_overutilized(int cpu, int delta)
+{
+ return (capacity_of(cpu) * 1024) < ((cpu_util(cpu) + delta) * capacity_margin);
+}
+
+static bool cpu_overutilized(int cpu)
+{
+ return __cpu_overutilized(cpu, 0);
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+struct reciprocal_value schedtune_spc_rdiv;
+
+static long
+schedtune_margin(unsigned long signal, long boost)
+{
+ long long margin = 0;
+
+ /*
+ * Signal proportional compensation (SPC)
+ *
+ * The Boost (B) value is used to compute a Margin (M) which is
+ * proportional to the complement of the original Signal (S):
+ * M = B * (SCHED_CAPACITY_SCALE - S)
+ * The obtained M could be used by the caller to "boost" S.
+ */
+ if (boost >= 0) {
+ margin = SCHED_CAPACITY_SCALE - signal;
+ margin *= boost;
+ } else {
+ margin = -signal * boost;
+ }
+
+ margin = reciprocal_divide(margin, schedtune_spc_rdiv);
+ if (boost < 0)
+ margin *= -1;
+
+ return margin;
+}
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ int boost = schedtune_cpu_boost(cpu);
+
+ if (boost == 0)
+ return 0;
+
+ return schedtune_margin(util, boost);
+}
+
+static inline long
+schedtune_task_margin(struct task_struct *p)
+{
+ int boost = schedtune_task_boost(p);
+ unsigned long util;
+ long margin;
+
+ if (boost == 0)
+ return 0;
+
+ util = task_util(p);
+ margin = schedtune_margin(util, boost);
+
+ return margin;
+}
+
+#else /* CONFIG_SCHED_TUNE */
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ return 0;
+}
+
+static inline int
+schedtune_task_margin(struct task_struct *p)
+{
+ return 0;
+}
+
+#endif /* CONFIG_SCHED_TUNE */
+
+unsigned long
+boosted_cpu_util(int cpu)
+{
+ unsigned long util = cpu_util_freq(cpu);
+ long margin = schedtune_cpu_margin(util, cpu);
+
+ trace_sched_boost_cpu(cpu, util, margin);
+
+ return util + margin;
+}
+
+static inline unsigned long
+boosted_task_util(struct task_struct *p)
+{
+ unsigned long util = task_util(p);
+ long margin = schedtune_task_margin(p);
+
+ trace_sched_boost_task(p, util, margin);
+
+ return util + margin;
+}
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+ return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+}
+
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
+ *
+ * Assumes p is allowed on at least one CPU in sd.
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
- unsigned long min_load = ULONG_MAX, this_load = 0;
+ struct sched_group *most_spare_sg = NULL;
+ unsigned long min_runnable_load = ULONG_MAX;
+ unsigned long this_runnable_load = ULONG_MAX;
+ unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
+ unsigned long most_spare = 0, this_spare = 0;
int load_idx = sd->forkexec_idx;
- int imbalance = 100 + (sd->imbalance_pct-100)/2;
+ int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
+ unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
+ (sd->imbalance_pct-100) / 100;
if (sd_flag & SD_BALANCE_WAKE)
load_idx = sd->wake_idx;
do {
- unsigned long load, avg_load;
+ unsigned long load, avg_load, runnable_load;
+ unsigned long spare_cap, max_spare_cap;
int local_group;
int i;
@@ -5303,8 +6356,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
- /* Tally up the load of all CPUs in the group */
+ /*
+ * Tally up the load of all CPUs in the group and find
+ * the group containing the CPU with most spare capacity.
+ */
avg_load = 0;
+ runnable_load = 0;
+ max_spare_cap = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
@@ -5313,30 +6371,85 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
else
load = target_load(i, load_idx);
- avg_load += load;
+ runnable_load += load;
+
+ avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
+
+ spare_cap = capacity_spare_wake(i, p);
+
+ if (spare_cap > max_spare_cap)
+ max_spare_cap = spare_cap;
}
/* Adjust by relative CPU capacity of the group */
- avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity;
+ avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
+ group->sgc->capacity;
+ runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
+ group->sgc->capacity;
if (local_group) {
- this_load = avg_load;
- } else if (avg_load < min_load) {
- min_load = avg_load;
- idlest = group;
+ this_runnable_load = runnable_load;
+ this_avg_load = avg_load;
+ this_spare = max_spare_cap;
+ } else {
+ if (min_runnable_load > (runnable_load + imbalance)) {
+ /*
+ * The runnable load is significantly smaller
+ * so we can pick this new cpu
+ */
+ min_runnable_load = runnable_load;
+ min_avg_load = avg_load;
+ idlest = group;
+ } else if ((runnable_load < (min_runnable_load + imbalance)) &&
+ (100*min_avg_load > imbalance_scale*avg_load)) {
+ /*
+ * The runnable loads are close so we take
+ * into account blocked load through avg_load
+ * which is blocked + runnable load
+ */
+ min_avg_load = avg_load;
+ idlest = group;
+ }
+
+ if (most_spare < max_spare_cap) {
+ most_spare = max_spare_cap;
+ most_spare_sg = group;
+ }
}
} while (group = group->next, group != sd->groups);
- if (!idlest || 100*this_load < imbalance*min_load)
+ /*
+ * The cross-over point between using spare capacity or least load
+ * is too conservative for high utilization tasks on partially
+ * utilized systems if we require spare_capacity > task_util(p),
+ * so we allow for some task stuffing by using
+ * spare_capacity > task_util(p)/2.
+ * spare capacity can't be used for fork because the utilization has
+ * not been set yet as it need to get a rq to init the utilization
+ */
+ if (sd_flag & SD_BALANCE_FORK)
+ goto skip_spare;
+
+ if (this_spare > task_util(p) / 2 &&
+ imbalance_scale*this_spare > 100*most_spare)
+ return NULL;
+ else if (most_spare > task_util(p) / 2)
+ return most_spare_sg;
+
+skip_spare:
+ if (!idlest ||
+ (min_runnable_load > (this_runnable_load + imbalance)) ||
+ ((this_runnable_load < (min_runnable_load + imbalance)) &&
+ (100*this_avg_load < imbalance_scale*min_avg_load)))
return NULL;
return idlest;
}
/*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ * find_idlest_group_cpu - find the idlest cpu among the cpus in group.
*/
static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
unsigned long load, min_load = ULONG_MAX;
unsigned int min_exit_latency = UINT_MAX;
@@ -5385,6 +6498,68 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
}
+static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
+ int cpu, int prev_cpu, int sd_flag)
+{
+ int wu = sd_flag & SD_BALANCE_WAKE;
+ int cas_cpu = -1;
+ int new_cpu = cpu;
+
+ if (wu) {
+ schedstat_inc(p->se.statistics.nr_wakeups_cas_attempts);
+ schedstat_inc(this_rq()->eas_stats.cas_attempts);
+ }
+
+ if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+ return prev_cpu;
+
+ while (sd) {
+ struct sched_group *group;
+ struct sched_domain *tmp;
+ int weight;
+
+ if (wu)
+ schedstat_inc(sd->eas_stats.cas_attempts);
+
+ if (!(sd->flags & sd_flag)) {
+ sd = sd->child;
+ continue;
+ }
+
+ group = find_idlest_group(sd, p, cpu, sd_flag);
+ if (!group) {
+ sd = sd->child;
+ continue;
+ }
+
+ new_cpu = find_idlest_group_cpu(group, p, cpu);
+ if (new_cpu == cpu) {
+ /* Now try balancing at a lower domain level of cpu */
+ sd = sd->child;
+ continue;
+ }
+
+ /* Now try balancing at a lower domain level of new_cpu */
+ cpu = cas_cpu = new_cpu;
+ weight = sd->span_weight;
+ sd = NULL;
+ for_each_domain(cpu, tmp) {
+ if (weight <= tmp->span_weight)
+ break;
+ if (tmp->flags & sd_flag)
+ sd = tmp;
+ }
+ /* while loop will break here if sd == NULL */
+ }
+
+ if (wu && (cas_cpu >= 0)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_cas_count);
+ schedstat_inc(this_rq()->eas_stats.cas_count);
+ }
+
+ return new_cpu;
+}
+
#ifdef CONFIG_SCHED_SMT
static inline void set_idle_cores(int cpu, int val)
@@ -5552,96 +6727,583 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
struct sched_domain *sd;
- int i;
+ struct sched_group *sg;
+ int i = task_cpu(p);
+ int best_idle_cpu = -1;
+ int best_idle_cstate = INT_MAX;
+ unsigned long best_idle_capacity = ULONG_MAX;
- if (idle_cpu(target))
- return target;
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_attempts);
+ schedstat_inc(this_rq()->eas_stats.sis_attempts);
+
+ if (!sysctl_sched_cstate_aware) {
+ if (idle_cpu(target)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_idle);
+ schedstat_inc(this_rq()->eas_stats.sis_idle);
+ return target;
+ }
+
+ /*
+ * If the prevous cpu is cache affine and idle, don't be stupid.
+ */
+ if (i != target && cpus_share_cache(i, target) && idle_cpu(i)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_cache_affine);
+ schedstat_inc(this_rq()->eas_stats.sis_cache_affine);
+ return i;
+ }
+
+ sd = rcu_dereference(per_cpu(sd_llc, target));
+ if (!sd)
+ return target;
+
+ i = select_idle_core(p, sd, target);
+ if ((unsigned)i < nr_cpumask_bits)
+ return i;
+
+ i = select_idle_cpu(p, sd, target);
+ if ((unsigned)i < nr_cpumask_bits)
+ return i;
+
+ i = select_idle_smt(p, sd, target);
+ if ((unsigned)i < nr_cpumask_bits)
+ return i;
+ }
/*
- * If the previous cpu is cache affine and idle, don't be stupid.
+ * Otherwise, iterate the domains and find an elegible idle cpu.
*/
- if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
- return prev;
-
sd = rcu_dereference(per_cpu(sd_llc, target));
- if (!sd)
- return target;
+ for_each_lower_domain(sd) {
+ sg = sd->groups;
+ do {
+ if (!cpumask_intersects(sched_group_cpus(sg),
+ tsk_cpus_allowed(p)))
+ goto next;
- i = select_idle_core(p, sd, target);
- if ((unsigned)i < nr_cpumask_bits)
- return i;
- i = select_idle_cpu(p, sd, target);
- if ((unsigned)i < nr_cpumask_bits)
- return i;
+ if (sysctl_sched_cstate_aware) {
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+ unsigned long new_usage = boosted_task_util(p);
+ unsigned long capacity_orig = capacity_orig_of(i);
- i = select_idle_smt(p, sd, target);
- if ((unsigned)i < nr_cpumask_bits)
- return i;
+ if (new_usage > capacity_orig || !idle_cpu(i))
+ goto next;
+
+ if (i == target && new_usage <= capacity_curr_of(target)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_suff_cap);
+ schedstat_inc(this_rq()->eas_stats.sis_suff_cap);
+ schedstat_inc(sd->eas_stats.sis_suff_cap);
+ return target;
+ }
+
+ if (idle_idx < best_idle_cstate &&
+ capacity_orig <= best_idle_capacity) {
+ best_idle_cpu = i;
+ best_idle_cstate = idle_idx;
+ best_idle_capacity = capacity_orig;
+ }
+ }
+ } else {
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ if (i == target || !idle_cpu(i))
+ goto next;
+ }
+
+ target = cpumask_first_and(sched_group_cpus(sg),
+ tsk_cpus_allowed(p));
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_idle_cpu);
+ schedstat_inc(this_rq()->eas_stats.sis_idle_cpu);
+ schedstat_inc(sd->eas_stats.sis_idle_cpu);
+ goto done;
+ }
+next:
+ sg = sg->next;
+ } while (sg != sd->groups);
+ }
+
+ if (best_idle_cpu >= 0)
+ target = best_idle_cpu;
+
+done:
+ schedstat_inc(p->se.statistics.nr_wakeups_sis_count);
+ schedstat_inc(this_rq()->eas_stats.sis_count);
return target;
}
-
+
/*
- * cpu_util returns the amount of capacity of a CPU that is used by CFS
- * tasks. The unit of the return value must be the one of capacity so we can
- * compare the utilization with the capacity of the CPU that is available for
- * CFS task (ie cpu_capacity).
- *
- * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
- * recent utilization of currently non-runnable tasks on a CPU. It represents
- * the amount of utilization of a CPU in the range [0..capacity_orig] where
- * capacity_orig is the cpu_capacity available at the highest frequency
- * (arch_scale_freq_capacity()).
- * The utilization of a CPU converges towards a sum equal to or less than the
- * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
- * the running time on this CPU scaled by capacity_curr.
- *
- * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
- * higher than capacity_orig because of unfortunate rounding in
- * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
- * the average stabilizes with the new running time. We need to check that the
- * utilization stays within the range of [0..capacity_orig] and cap it if
- * necessary. Without utilization capping, a group could be seen as overloaded
- * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
- * available capacity. We allow utilization to overshoot capacity_curr (but not
- * capacity_orig) as it useful for predicting the capacity required after task
- * migrations (scheduler-driven DVFS).
+ * cpu_util_wake: Compute cpu utilization with any contributions from
+ * the waking task p removed. check_for_migration() looks for a better CPU of
+ * rq->curr. For that case we should return cpu util with contributions from
+ * currently running task p removed.
*/
-static int cpu_util(int cpu)
+static int cpu_util_wake(int cpu, struct task_struct *p)
{
- unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
- unsigned long capacity = capacity_orig_of(cpu);
+ unsigned long util, capacity;
+
+#ifdef CONFIG_SCHED_WALT
+ /*
+ * WALT does not decay idle tasks in the same manner
+ * as PELT, so it makes little sense to subtract task
+ * utilization from cpu utilization. Instead just use
+ * cpu_util for this case.
+ */
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util &&
+ p->state == TASK_WAKING)
+ return cpu_util(cpu);
+#endif
+ /* Task has no contribution or is new */
+ if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
+ return cpu_util(cpu);
+
+ capacity = capacity_orig_of(cpu);
+ util = max_t(long, cpu_util(cpu) - task_util(p), 0);
return (util >= capacity) ? capacity : util;
}
-static inline int task_util(struct task_struct *p)
+static int start_cpu(bool boosted)
{
- return p->se.avg.util_avg;
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+
+ return boosted ? rd->max_cap_orig_cpu : rd->min_cap_orig_cpu;
+}
+
+static inline int find_best_target(struct task_struct *p, int *backup_cpu,
+ bool boosted, bool prefer_idle)
+{
+ unsigned long best_idle_min_cap_orig = ULONG_MAX;
+ unsigned long min_util = boosted_task_util(p);
+ unsigned long target_capacity = ULONG_MAX;
+ unsigned long min_wake_util = ULONG_MAX;
+ unsigned long target_max_spare_cap = 0;
+ unsigned long target_util = ULONG_MAX;
+ unsigned long best_active_util = ULONG_MAX;
+ unsigned long target_idle_max_spare_cap = 0;
+ int best_idle_cstate = INT_MAX;
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int best_active_cpu = -1;
+ int best_idle_cpu = -1;
+ int target_cpu = -1;
+ int cpu, i;
+
+ *backup_cpu = -1;
+
+ schedstat_inc(p->se.statistics.nr_wakeups_fbt_attempts);
+ schedstat_inc(this_rq()->eas_stats.fbt_attempts);
+
+ /* Find start CPU based on boost value */
+ cpu = start_cpu(boosted);
+ if (cpu < 0) {
+ schedstat_inc(p->se.statistics.nr_wakeups_fbt_no_cpu);
+ schedstat_inc(this_rq()->eas_stats.fbt_no_cpu);
+ return -1;
+ }
+
+ /* Find SD for the start CPU */
+ sd = rcu_dereference(per_cpu(sd_ea, cpu));
+ if (!sd) {
+ schedstat_inc(p->se.statistics.nr_wakeups_fbt_no_sd);
+ schedstat_inc(this_rq()->eas_stats.fbt_no_sd);
+ return -1;
+ }
+
+ /* Scan CPUs in all SDs */
+ sg = sd->groups;
+ do {
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ unsigned long capacity_curr = capacity_curr_of(i);
+ unsigned long capacity_orig = capacity_orig_of(i);
+ unsigned long wake_util, new_util, min_capped_util;
+
+ if (!cpu_online(i))
+ continue;
+
+ if (walt_cpu_high_irqload(i))
+ continue;
+
+ /*
+ * p's blocked utilization is still accounted for on prev_cpu
+ * so prev_cpu will receive a negative bias due to the double
+ * accounting. However, the blocked utilization may be zero.
+ */
+ wake_util = cpu_util_wake(i, p);
+ new_util = wake_util + task_util(p);
+
+ /*
+ * Ensure minimum capacity to grant the required boost.
+ * The target CPU can be already at a capacity level higher
+ * than the one required to boost the task.
+ */
+ new_util = max(min_util, new_util);
+
+ /*
+ * Include minimum capacity constraint:
+ * new_util contains the required utilization including
+ * boost. min_capped_util also takes into account a
+ * minimum capacity cap imposed on the CPU by external
+ * actors.
+ */
+ min_capped_util = max(new_util, capacity_min_of(i));
+
+ if (new_util > capacity_orig)
+ continue;
+
+ /*
+ * Case A) Latency sensitive tasks
+ *
+ * Unconditionally favoring tasks that prefer idle CPU to
+ * improve latency.
+ *
+ * Looking for:
+ * - an idle CPU, whatever its idle_state is, since
+ * the first CPUs we explore are more likely to be
+ * reserved for latency sensitive tasks.
+ * - a non idle CPU where the task fits in its current
+ * capacity and has the maximum spare capacity.
+ * - a non idle CPU with lower contention from other
+ * tasks and running at the lowest possible OPP.
+ *
+ * The last two goals tries to favor a non idle CPU
+ * where the task can run as if it is "almost alone".
+ * A maximum spare capacity CPU is favoured since
+ * the task already fits into that CPU's capacity
+ * without waiting for an OPP chance.
+ *
+ * The following code path is the only one in the CPUs
+ * exploration loop which is always used by
+ * prefer_idle tasks. It exits the loop with wither a
+ * best_active_cpu or a target_cpu which should
+ * represent an optimal choice for latency sensitive
+ * tasks.
+ */
+ if (prefer_idle) {
+
+ /*
+ * Case A.1: IDLE CPU
+ * Return the first IDLE CPU we find.
+ */
+ if (idle_cpu(i)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_fbt_pref_idle);
+ schedstat_inc(this_rq()->eas_stats.fbt_pref_idle);
+
+ trace_sched_find_best_target(p,
+ prefer_idle, min_util,
+ cpu, best_idle_cpu,
+ best_active_cpu, i);
+
+ return i;
+ }
+
+ /*
+ * Case A.2: Target ACTIVE CPU
+ * Favor CPUs with max spare capacity.
+ */
+ if ((capacity_curr > new_util) &&
+ (capacity_orig - new_util > target_max_spare_cap)) {
+ target_max_spare_cap = capacity_orig - new_util;
+ target_cpu = i;
+ continue;
+ }
+ if (target_cpu != -1)
+ continue;
+
+
+ /*
+ * Case A.3: Backup ACTIVE CPU
+ * Favor CPUs with:
+ * - lower utilization due to other tasks
+ * - lower utilization with the task in
+ */
+ if (wake_util > min_wake_util)
+ continue;
+ if (new_util > best_active_util)
+ continue;
+ min_wake_util = wake_util;
+ best_active_util = new_util;
+ best_active_cpu = i;
+ continue;
+ }
+
+ /*
+ * Enforce EAS mode
+ *
+ * For non latency sensitive tasks, skip CPUs that
+ * will be overutilized by moving the task there.
+ *
+ * The goal here is to remain in EAS mode as long as
+ * possible at least for !prefer_idle tasks.
+ */
+ if ((new_util * capacity_margin) >
+ (capacity_orig * SCHED_CAPACITY_SCALE))
+ continue;
+
+ /*
+ * Case B) Non latency sensitive tasks on IDLE CPUs.
+ *
+ * Find an optimal backup IDLE CPU for non latency
+ * sensitive tasks.
+ *
+ * Looking for:
+ * - minimizing the capacity_orig,
+ * i.e. preferring LITTLE CPUs
+ * - favoring shallowest idle states
+ * i.e. avoid to wakeup deep-idle CPUs
+ *
+ * The following code path is used by non latency
+ * sensitive tasks if IDLE CPUs are available. If at
+ * least one of such CPUs are available it sets the
+ * best_idle_cpu to the most suitable idle CPU to be
+ * selected.
+ *
+ * If idle CPUs are available, favour these CPUs to
+ * improve performances by spreading tasks.
+ * Indeed, the energy_diff() computed by the caller
+ * will take care to ensure the minimization of energy
+ * consumptions without affecting performance.
+ */
+ if (idle_cpu(i)) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+
+ /* Select idle CPU with lower cap_orig */
+ if (capacity_orig > best_idle_min_cap_orig)
+ continue;
+ /* Favor CPUs that won't end up running at a
+ * high OPP.
+ */
+ if ((capacity_orig - min_capped_util) <
+ target_idle_max_spare_cap)
+ continue;
+
+ /*
+ * Skip CPUs in deeper idle state, but only
+ * if they are also less energy efficient.
+ * IOW, prefer a deep IDLE LITTLE CPU vs a
+ * shallow idle big CPU.
+ */
+ if (sysctl_sched_cstate_aware &&
+ best_idle_cstate <= idle_idx)
+ continue;
+
+ /* Keep track of best idle CPU */
+ best_idle_min_cap_orig = capacity_orig;
+ target_idle_max_spare_cap = capacity_orig -
+ min_capped_util;
+ best_idle_cstate = idle_idx;
+ best_idle_cpu = i;
+ continue;
+ }
+
+ /*
+ * Case C) Non latency sensitive tasks on ACTIVE CPUs.
+ *
+ * Pack tasks in the most energy efficient capacities.
+ *
+ * This task packing strategy prefers more energy
+ * efficient CPUs (i.e. pack on smaller maximum
+ * capacity CPUs) while also trying to spread tasks to
+ * run them all at the lower OPP.
+ *
+ * This assumes for example that it's more energy
+ * efficient to run two tasks on two CPUs at a lower
+ * OPP than packing both on a single CPU but running
+ * that CPU at an higher OPP.
+ *
+ * Thus, this case keep track of the CPU with the
+ * smallest maximum capacity and highest spare maximum
+ * capacity.
+ */
+
+ /* Favor CPUs with smaller capacity */
+ if (capacity_orig > target_capacity)
+ continue;
+
+ /* Favor CPUs with maximum spare capacity */
+ if ((capacity_orig - min_capped_util) <
+ target_max_spare_cap)
+ continue;
+
+ target_max_spare_cap = capacity_orig - min_capped_util;
+ target_capacity = capacity_orig;
+ target_util = new_util;
+ target_cpu = i;
+ }
+
+ } while (sg = sg->next, sg != sd->groups);
+
+ /*
+ * For non latency sensitive tasks, cases B and C in the previous loop,
+ * we pick the best IDLE CPU only if we was not able to find a target
+ * ACTIVE CPU.
+ *
+ * Policies priorities:
+ *
+ * - prefer_idle tasks:
+ *
+ * a) IDLE CPU available, we return immediately
+ * b) ACTIVE CPU where task fits and has the bigger maximum spare
+ * capacity (i.e. target_cpu)
+ * c) ACTIVE CPU with less contention due to other tasks
+ * (i.e. best_active_cpu)
+ *
+ * - NON prefer_idle tasks:
+ *
+ * a) ACTIVE CPU: target_cpu
+ * b) IDLE CPU: best_idle_cpu
+ */
+ if (target_cpu == -1)
+ target_cpu = prefer_idle
+ ? best_active_cpu
+ : best_idle_cpu;
+ else
+ *backup_cpu = prefer_idle
+ ? best_active_cpu
+ : best_idle_cpu;
+
+ trace_sched_find_best_target(p, prefer_idle, min_util, cpu,
+ best_idle_cpu, best_active_cpu,
+ target_cpu);
+
+ schedstat_inc(p->se.statistics.nr_wakeups_fbt_count);
+ schedstat_inc(this_rq()->eas_stats.fbt_count);
+
+ return target_cpu;
}
/*
* Disable WAKE_AFFINE in the case where task @p doesn't fit in the
* capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
- *
+ *
* In that case WAKE_AFFINE doesn't make sense and we'll let
* BALANCE_WAKE sort things out.
*/
static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
{
long min_cap, max_cap;
-
min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
- max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
-
+ max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;
/* Minimum capacity is close to max, no need to abort wake_affine */
if (max_cap - min_cap < max_cap >> 3)
return 0;
+ /* Bring task utilization in sync with prev_cpu */
+ sync_entity_load_avg(&p->se);
+
return min_cap * 1024 < task_util(p) * capacity_margin;
}
+static int select_energy_cpu_brute(struct task_struct *p, int prev_cpu, int sync)
+{
+ bool boosted, prefer_idle;
+ struct sched_domain *sd;
+ int target_cpu;
+ int backup_cpu;
+ int next_cpu;
+
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_attempts);
+ schedstat_inc(this_rq()->eas_stats.secb_attempts);
+
+ if (sysctl_sched_sync_hint_enable && sync) {
+ int cpu = smp_processor_id();
+
+ if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_sync);
+ schedstat_inc(this_rq()->eas_stats.secb_sync);
+ return cpu;
+ }
+ }
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ boosted = schedtune_task_boost(p) > 0;
+ prefer_idle = schedtune_prefer_idle(p) > 0;
+#else
+ boosted = get_sysctl_sched_cfs_boost() > 0;
+ prefer_idle = 0;
+#endif
+
+ rcu_read_lock();
+
+ sd = rcu_dereference(per_cpu(sd_ea, prev_cpu));
+ if (!sd) {
+ target_cpu = prev_cpu;
+ goto unlock;
+ }
+
+ sync_entity_load_avg(&p->se);
+
+ /* Find a cpu with sufficient capacity */
+ next_cpu = find_best_target(p, &backup_cpu, boosted, prefer_idle);
+ if (next_cpu == -1) {
+ target_cpu = prev_cpu;
+ goto unlock;
+ }
+
+ /* Unconditionally prefer IDLE CPUs for boosted/prefer_idle tasks */
+ if ((boosted || prefer_idle) && idle_cpu(next_cpu)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_idle_bt);
+ schedstat_inc(this_rq()->eas_stats.secb_idle_bt);
+ target_cpu = next_cpu;
+ goto unlock;
+ }
+
+ target_cpu = prev_cpu;
+ if (next_cpu != prev_cpu) {
+ int delta = 0;
+ struct energy_env eenv = {
+ .p = p,
+ .util_delta = task_util(p),
+ /* Task's previous CPU candidate */
+ .cpu[EAS_CPU_PRV] = {
+ .cpu_id = prev_cpu,
+ },
+ /* Main alternative CPU candidate */
+ .cpu[EAS_CPU_NXT] = {
+ .cpu_id = next_cpu,
+ },
+ /* Backup alternative CPU candidate */
+ .cpu[EAS_CPU_BKP] = {
+ .cpu_id = backup_cpu,
+ },
+ };
+
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util &&
+ p->state == TASK_WAKING)
+ delta = task_util(p);
+#endif
+ /* Not enough spare capacity on previous cpu */
+ if (__cpu_overutilized(prev_cpu, delta)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_insuff_cap);
+ schedstat_inc(this_rq()->eas_stats.secb_insuff_cap);
+ target_cpu = next_cpu;
+ goto unlock;
+ }
+
+ /* Check if EAS_CPU_NXT is a more energy efficient CPU */
+ if (select_energy_cpu_idx(&eenv) != EAS_CPU_PRV) {
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_nrg_sav);
+ schedstat_inc(this_rq()->eas_stats.secb_nrg_sav);
+ target_cpu = eenv.cpu[eenv.next_idx].cpu_id;
+ goto unlock;
+ }
+
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_no_nrg_sav);
+ schedstat_inc(this_rq()->eas_stats.secb_no_nrg_sav);
+ target_cpu = prev_cpu;
+ goto unlock;
+ }
+
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_count);
+ schedstat_inc(this_rq()->eas_stats.secb_count);
+
+unlock:
+ rcu_read_unlock();
+ return target_cpu;
+}
+
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -5665,10 +7327,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
- want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
- && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+ want_affine = (!wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
+ cpumask_test_cpu(cpu, tsk_cpus_allowed(p)));
}
+ if (energy_aware() && !(cpu_rq(prev_cpu)->rd->overutilized))
+ return select_energy_cpu_brute(p, prev_cpu, sync);
+
rcu_read_lock();
for_each_domain(cpu, tmp) {
if (!(tmp->flags & SD_LOAD_BALANCE))
@@ -5696,43 +7361,21 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
new_cpu = cpu;
}
+ if (sd && !(sd_flag & SD_BALANCE_FORK)) {
+ /*
+ * We're going to need the task's util for capacity_spare_wake
+ * in find_idlest_group. Sync it up to prev_cpu's
+ * last_update_time.
+ */
+ sync_entity_load_avg(&p->se);
+ }
+
if (!sd) {
if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
- } else while (sd) {
- struct sched_group *group;
- int weight;
-
- if (!(sd->flags & sd_flag)) {
- sd = sd->child;
- continue;
- }
-
- group = find_idlest_group(sd, p, cpu, sd_flag);
- if (!group) {
- sd = sd->child;
- continue;
- }
-
- new_cpu = find_idlest_cpu(group, p, cpu);
- if (new_cpu == -1 || new_cpu == cpu) {
- /* Now try balancing at a lower domain level of cpu */
- sd = sd->child;
- continue;
- }
-
- /* Now try balancing at a lower domain level of new_cpu */
- cpu = new_cpu;
- weight = sd->span_weight;
- sd = NULL;
- for_each_domain(cpu, tmp) {
- if (weight <= tmp->span_weight)
- break;
- if (tmp->flags & sd_flag)
- sd = tmp;
- }
- /* while loop will break here if sd == NULL */
+ } else {
+ new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
}
rcu_read_unlock();
@@ -5792,6 +7435,8 @@ static void task_dead_fair(struct task_struct *p)
{
remove_entity_load_avg(&p->se);
}
+#else
+#define task_fits_max(p, cpu) true
#endif /* CONFIG_SMP */
static unsigned long
@@ -5955,7 +7600,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
}
static struct task_struct *
-pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
@@ -6038,6 +7683,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie c
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
simple:
cfs_rq = &rq->cfs;
@@ -6059,18 +7706,21 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie c
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
idle:
+ rq->misfit_task = 0;
/*
* This is OK, because current is on_cpu, which avoids it being picked
* for load-balance and preemption/IRQs are still disabled avoiding
* further scheduler activity on it and we're being very careful to
* re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
new_tasks = idle_balance(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
@@ -6274,6 +7924,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
enum fbq_type { regular, remote, all };
+enum group_type {
+ group_other = 0,
+ group_misfit_task,
+ group_imbalanced,
+ group_overloaded,
+};
+
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
#define LBF_DST_PINNED 0x04
@@ -6292,6 +7949,7 @@ struct lb_env {
int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
+ unsigned int src_grp_nr_running;
/* The set of CPUs under consideration for load-balancing */
struct cpumask *cpus;
@@ -6302,6 +7960,7 @@ struct lb_env {
unsigned int loop_max;
enum fbq_type fbq_type;
+ enum group_type busiest_group_type;
struct list_head tasks;
};
@@ -6483,7 +8142,9 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(env->src_rq, p, 0);
+ double_lock_balance(env->src_rq, env->dst_rq);
set_task_cpu(p, env->dst_cpu);
+ double_unlock_balance(env->src_rq, env->dst_rq);
}
/*
@@ -6675,12 +8336,19 @@ static void update_blocked_averages(int cpu)
* list_add_leaf_cfs_rq() for details.
*/
for_each_leaf_cfs_rq(rq, cfs_rq) {
+ struct sched_entity *se;
+
/* throttled entities do not contribute to load */
if (throttled_hierarchy(cfs_rq))
continue;
if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
update_tg_load_avg(cfs_rq, 0);
+
+ /* Propagate pending load changes to the parent, if any: */
+ se = cfs_rq->tg->se[cpu];
+ if (se && !skip_blocked_update(se))
+ update_load_avg(se, 0);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -6752,12 +8420,6 @@ static unsigned long task_h_load(struct task_struct *p)
/********** Helpers for find_busiest_group ************************/
-enum group_type {
- group_other = 0,
- group_imbalanced,
- group_overloaded,
-};
-
/*
* sg_lb_stats - stats of a sched_group required for load_balancing
*/
@@ -6773,6 +8435,7 @@ struct sg_lb_stats {
unsigned int group_weight;
enum group_type group_type;
int group_no_capacity;
+ int group_misfit_task; /* A cpu has a task too big for its capacity */
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
@@ -6870,13 +8533,46 @@ static unsigned long scale_rt_capacity(int cpu)
return 1;
}
+void init_max_cpu_capacity(struct max_cpu_capacity *mcc)
+{
+ raw_spin_lock_init(&mcc->lock);
+ mcc->val = 0;
+ mcc->cpu = -1;
+}
+
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
+ struct max_cpu_capacity *mcc;
+ unsigned long max_capacity;
+ int max_cap_cpu;
+ unsigned long flags;
cpu_rq(cpu)->cpu_capacity_orig = capacity;
+ capacity *= arch_scale_max_freq_capacity(sd, cpu);
+ capacity >>= SCHED_CAPACITY_SHIFT;
+
+ mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;
+
+ raw_spin_lock_irqsave(&mcc->lock, flags);
+ max_capacity = mcc->val;
+ max_cap_cpu = mcc->cpu;
+
+ if ((max_capacity > capacity && max_cap_cpu == cpu) ||
+ (max_capacity < capacity)) {
+ mcc->val = capacity;
+ mcc->cpu = cpu;
+#ifdef CONFIG_SCHED_DEBUG
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+ pr_info("CPU%d: update max cpu_capacity %lu\n", cpu, capacity);
+ goto skip_unlock;
+#endif
+ }
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+
+skip_unlock: __attribute__ ((unused));
capacity *= scale_rt_capacity(cpu);
capacity >>= SCHED_CAPACITY_SHIFT;
@@ -6885,13 +8581,15 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
cpu_rq(cpu)->cpu_capacity = capacity;
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = capacity;
+ sdg->sgc->min_capacity = capacity;
}
void update_group_capacity(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long capacity;
+ unsigned long capacity, max_capacity, min_capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
@@ -6904,6 +8602,8 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
}
capacity = 0;
+ max_capacity = 0;
+ min_capacity = ULONG_MAX;
if (child->flags & SD_OVERLAP) {
/*
@@ -6928,11 +8628,13 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
*/
if (unlikely(!rq->sd)) {
capacity += capacity_of(cpu);
- continue;
+ } else {
+ sgc = rq->sd->groups->sgc;
+ capacity += sgc->capacity;
}
- sgc = rq->sd->groups->sgc;
- capacity += sgc->capacity;
+ max_capacity = max(capacity, max_capacity);
+ min_capacity = min(capacity, min_capacity);
}
} else {
/*
@@ -6942,12 +8644,18 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
group = child->groups;
do {
- capacity += group->sgc->capacity;
+ struct sched_group_capacity *sgc = group->sgc;
+
+ capacity += sgc->capacity;
+ max_capacity = max(sgc->max_capacity, max_capacity);
+ min_capacity = min(sgc->min_capacity, min_capacity);
group = group->next;
} while (group != child->groups);
}
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = max_capacity;
+ sdg->sgc->min_capacity = min_capacity;
}
/*
@@ -7042,6 +8750,17 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
return false;
}
+/*
+ * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-cpu capacity than sched_group ref.
+ */
+static inline bool
+group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+ return sg->sgc->max_capacity + capacity_margin - SCHED_CAPACITY_SCALE <
+ ref->sgc->max_capacity;
+}
+
static inline enum
group_type group_classify(struct sched_group *group,
struct sg_lb_stats *sgs)
@@ -7052,9 +8771,44 @@ group_type group_classify(struct sched_group *group,
if (sg_imbalanced(group))
return group_imbalanced;
+ if (sgs->group_misfit_task)
+ return group_misfit_task;
+
return group_other;
}
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * idle load balancing data
+ * - used by the nohz balance, but we want it available here
+ * so that we can see which CPUs have no tick.
+ */
+static struct {
+ cpumask_var_t idle_cpus_mask;
+ atomic_t nr_cpus;
+ unsigned long next_balance; /* in jiffy units */
+} nohz ____cacheline_aligned;
+
+static inline void update_cpu_stats_if_tickless(struct rq *rq)
+{
+ /* only called from update_sg_lb_stats when irqs are disabled */
+ if (cpumask_test_cpu(rq->cpu, nohz.idle_cpus_mask)) {
+ /* rate limit updates to once-per-jiffie at most */
+ if (READ_ONCE(jiffies) <= rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+ cpu_load_update_idle(rq);
+ update_cfs_rq_load_avg(rq->clock_task, &rq->cfs, false);
+ raw_spin_unlock(&rq->lock);
+ }
+}
+
+#else
+static inline void update_cpu_stats_if_tickless(struct rq *rq) { }
+#endif
+
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
@@ -7063,11 +8817,12 @@ group_type group_classify(struct sched_group *group,
* @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
* @overload: Indicate more than one runnable task for any CPU.
+ * @overutilized: Indicate overutilization for any CPU.
*/
static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs,
- bool *overload)
+ bool *overload, bool *overutilized)
{
unsigned long load;
int i, nr_running;
@@ -7077,6 +8832,12 @@ static inline void update_sg_lb_stats(struct lb_env *env,
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
+ /* if we are entering idle and there are CPUs with
+ * their tick stopped, do an update for them
+ */
+ if (env->idle == CPU_NEWLY_IDLE)
+ update_cpu_stats_if_tickless(rq);
+
/* Bias balancing toward cpus of our domain */
if (local_group)
load = target_load(i, load_idx);
@@ -7101,6 +8862,12 @@ static inline void update_sg_lb_stats(struct lb_env *env,
*/
if (!nr_running && idle_cpu(i))
sgs->idle_cpus++;
+
+ if (cpu_overutilized(i)) {
+ *overutilized = true;
+ if (!sgs->group_misfit_task && rq->misfit_task)
+ sgs->group_misfit_task = capacity_of(i);
+ }
}
/* Adjust by relative CPU capacity of the group */
@@ -7142,9 +8909,31 @@ static bool update_sd_pick_busiest(struct lb_env *env,
if (sgs->group_type < busiest->group_type)
return false;
+ /*
+ * Candidate sg doesn't face any serious load-balance problems
+ * so don't pick it if the local sg is already filled up.
+ */
+ if (sgs->group_type == group_other &&
+ !group_has_capacity(env, &sds->local_stat))
+ return false;
+
if (sgs->avg_load <= busiest->avg_load)
return false;
+ if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
+ goto asym_packing;
+
+ /*
+ * Candidate sg has no more than one task per CPU and
+ * has higher per-CPU capacity. Migrating tasks to less
+ * capable CPUs may harm throughput. Maximize throughput,
+ * power/energy consequences are not considered.
+ */
+ if (sgs->sum_nr_running <= sgs->group_weight &&
+ group_smaller_cpu_capacity(sds->local, sg))
+ return false;
+
+asym_packing:
/* This is the busiest node in its class. */
if (!(env->sd->flags & SD_ASYM_PACKING))
return true;
@@ -7199,6 +8988,9 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
}
#endif /* CONFIG_NUMA_BALANCING */
+#define lb_sd_parent(sd) \
+ (sd->parent && sd->parent->groups != sd->parent->groups->next)
+
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
@@ -7210,7 +9002,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
- bool overload = false;
+ bool overload = false, overutilized = false;
if (child && child->flags & SD_PREFER_SIBLING)
prefer_sibling = 1;
@@ -7232,7 +9024,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
}
update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
- &overload);
+ &overload, &overutilized);
if (local_group)
goto next_group;
@@ -7254,6 +9046,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
sgs->group_type = group_classify(sg, sgs);
}
+ /*
+ * Ignore task groups with misfit tasks if local group has no
+ * capacity or if per-cpu capacity isn't higher.
+ */
+ if (sgs->group_type == group_misfit_task &&
+ (!group_has_capacity(env, &sds->local_stat) ||
+ !group_smaller_cpu_capacity(sg, sds->local)))
+ sgs->group_type = group_other;
+
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
sds->busiest = sg;
sds->busiest_stat = *sgs;
@@ -7270,10 +9071,23 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
if (env->sd->flags & SD_NUMA)
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
- if (!env->sd->parent) {
+ env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;
+
+ if (!lb_sd_parent(env->sd)) {
/* update overload indicator if we are at root domain */
if (env->dst_rq->rd->overload != overload)
env->dst_rq->rd->overload = overload;
+
+ /* Update over-utilization (tipping point, U >= 0) indicator */
+ if (env->dst_rq->rd->overutilized != overutilized) {
+ env->dst_rq->rd->overutilized = overutilized;
+ trace_sched_overutilized(overutilized);
+ }
+ } else {
+ if (!env->dst_rq->rd->overutilized && overutilized) {
+ env->dst_rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
}
}
@@ -7426,6 +9240,22 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
*/
if (busiest->avg_load <= sds->avg_load ||
local->avg_load >= sds->avg_load) {
+ /* Misfitting tasks should be migrated in any case */
+ if (busiest->group_type == group_misfit_task) {
+ env->imbalance = busiest->group_misfit_task;
+ return;
+ }
+
+ /*
+ * Busiest group is overloaded, local is not, use the spare
+ * cycles to maximize throughput
+ */
+ if (busiest->group_type == group_overloaded &&
+ local->group_type <= group_misfit_task) {
+ env->imbalance = busiest->load_per_task;
+ return;
+ }
+
env->imbalance = 0;
return fix_small_imbalance(env, sds);
}
@@ -7459,6 +9289,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
(sds->avg_load - local->avg_load) * local->group_capacity
) / SCHED_CAPACITY_SCALE;
+ /* Boost imbalance to allow misfit task to be balanced. */
+ if (busiest->group_type == group_misfit_task)
+ env->imbalance = max_t(long, env->imbalance,
+ busiest->group_misfit_task);
+
/*
* if *imbalance is less than the average load per runnable task
* there is no guarantee that any tasks will be moved so we'll have
@@ -7494,6 +9329,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* this level.
*/
update_sd_lb_stats(env, &sds);
+
+ if (energy_aware() && !env->dst_rq->rd->overutilized)
+ goto out_balanced;
+
local = &sds.local_stat;
busiest = &sds.busiest_stat;
@@ -7516,11 +9355,19 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
if (busiest->group_type == group_imbalanced)
goto force_balance;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
- if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+ /*
+ * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
+ * capacities from resulting in underutilization due to avg_load.
+ */
+ if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
busiest->group_no_capacity)
goto force_balance;
+ /* Misfitting tasks should be dealt with regardless of the avg load */
+ if (busiest->group_type == group_misfit_task) {
+ goto force_balance;
+ }
+
/*
* If the local group is busier than the selected busiest group
* don't try and pull any tasks.
@@ -7544,7 +9391,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* might end up to just move the imbalance on another group
*/
if ((busiest->group_type != group_overloaded) &&
- (local->idle_cpus <= (busiest->idle_cpus + 1)))
+ (local->idle_cpus <= (busiest->idle_cpus + 1)) &&
+ !group_smaller_cpu_capacity(sds.busiest, sds.local))
goto out_balanced;
} else {
/*
@@ -7557,6 +9405,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
}
force_balance:
+ env->busiest_group_type = busiest->group_type;
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(env, &sds);
return sds.busiest;
@@ -7615,7 +9464,8 @@ static struct rq *find_busiest_queue(struct lb_env *env,
*/
if (rq->nr_running == 1 && wl > env->imbalance &&
- !check_cpu_capacity(rq, env->sd))
+ !check_cpu_capacity(rq, env->sd) &&
+ env->busiest_group_type != group_misfit_task)
continue;
/*
@@ -7673,6 +9523,14 @@ static int need_active_balance(struct lb_env *env)
return 1;
}
+ if ((capacity_of(env->src_cpu) < capacity_of(env->dst_cpu)) &&
+ ((capacity_orig_of(env->src_cpu) < capacity_orig_of(env->dst_cpu))) &&
+ env->src_rq->cfs.h_nr_running == 1 &&
+ cpu_overutilized(env->src_cpu) &&
+ !cpu_overutilized(env->dst_cpu)) {
+ return 1;
+ }
+
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}
@@ -7721,7 +9579,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
int *continue_balancing)
{
int ld_moved, cur_ld_moved, active_balance = 0;
- struct sched_domain *sd_parent = sd->parent;
+ struct sched_domain *sd_parent = lb_sd_parent(sd) ? sd->parent : NULL;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
@@ -7788,6 +9646,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
more_balance:
raw_spin_lock_irqsave(&busiest->lock, flags);
+ update_rq_clock(busiest);
/*
* cur_ld_moved - load moved in current iteration
@@ -7885,7 +9744,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
* excessive cache_hot migrations and active balances.
*/
if (idle != CPU_NEWLY_IDLE)
- sd->nr_balance_failed++;
+ if (env.src_grp_nr_running > 1)
+ sd->nr_balance_failed++;
if (need_active_balance(&env)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
@@ -8032,8 +9892,9 @@ static int idle_balance(struct rq *this_rq)
*/
this_rq->idle_stamp = rq_clock(this_rq);
- if (this_rq->avg_idle < sysctl_sched_migration_cost ||
- !this_rq->rd->overload) {
+ if (!energy_aware() &&
+ (this_rq->avg_idle < sysctl_sched_migration_cost ||
+ !this_rq->rd->overload)) {
rcu_read_lock();
sd = rcu_dereference_check_sched_domain(this_rq->sd);
if (sd)
@@ -8124,8 +9985,18 @@ static int active_load_balance_cpu_stop(void *data)
int busiest_cpu = cpu_of(busiest_rq);
int target_cpu = busiest_rq->push_cpu;
struct rq *target_rq = cpu_rq(target_cpu);
- struct sched_domain *sd;
+ struct sched_domain *sd = NULL;
struct task_struct *p = NULL;
+ struct task_struct *push_task = NULL;
+ int push_task_detached = 0;
+ struct lb_env env = {
+ .sd = sd,
+ .dst_cpu = target_cpu,
+ .dst_rq = target_rq,
+ .src_cpu = busiest_rq->cpu,
+ .src_rq = busiest_rq,
+ .idle = CPU_IDLE,
+ };
raw_spin_lock_irq(&busiest_rq->lock);
@@ -8145,6 +10016,17 @@ static int active_load_balance_cpu_stop(void *data)
*/
BUG_ON(busiest_rq == target_rq);
+ push_task = busiest_rq->push_task;
+ if (push_task) {
+ if (task_on_rq_queued(push_task) &&
+ task_cpu(push_task) == busiest_cpu &&
+ cpu_online(target_cpu)) {
+ detach_task(push_task, &env);
+ push_task_detached = 1;
+ }
+ goto out_unlock;
+ }
+
/* Search for an sd spanning us and the target CPU. */
rcu_read_lock();
for_each_domain(target_cpu, sd) {
@@ -8154,16 +10036,9 @@ static int active_load_balance_cpu_stop(void *data)
}
if (likely(sd)) {
- struct lb_env env = {
- .sd = sd,
- .dst_cpu = target_cpu,
- .dst_rq = target_rq,
- .src_cpu = busiest_rq->cpu,
- .src_rq = busiest_rq,
- .idle = CPU_IDLE,
- };
-
+ env.sd = sd;
schedstat_inc(sd->alb_count);
+ update_rq_clock(busiest_rq);
p = detach_one_task(&env);
if (p) {
@@ -8177,8 +10052,18 @@ static int active_load_balance_cpu_stop(void *data)
rcu_read_unlock();
out_unlock:
busiest_rq->active_balance = 0;
+
+ if (push_task)
+ busiest_rq->push_task = NULL;
+
raw_spin_unlock(&busiest_rq->lock);
+ if (push_task) {
+ if (push_task_detached)
+ attach_one_task(target_rq, push_task);
+ put_task_struct(push_task);
+ }
+
if (p)
attach_one_task(target_rq, p);
@@ -8199,12 +10084,6 @@ static inline int on_null_domain(struct rq *rq)
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
*/
-static struct {
- cpumask_var_t idle_cpus_mask;
- atomic_t nr_cpus;
- unsigned long next_balance; /* in jiffy units */
-} nohz ____cacheline_aligned;
-
static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
@@ -8538,9 +10417,14 @@ static inline bool nohz_kick_needed(struct rq *rq)
if (time_before(now, nohz.next_balance))
return false;
- if (rq->nr_running >= 2)
+ if (rq->nr_running >= 2 &&
+ (!energy_aware() || cpu_overutilized(cpu)))
return true;
+ /* Do idle load balance if there have misfit task */
+ if (energy_aware())
+ return rq->misfit_task;
+
rcu_read_lock();
sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
if (sds) {
@@ -8634,6 +10518,47 @@ static void rq_offline_fair(struct rq *rq)
unthrottle_offline_cfs_rqs(rq);
}
+static inline int
+kick_active_balance(struct rq *rq, struct task_struct *p, int new_cpu)
+{
+ int rc = 0;
+
+ /* Invoke active balance to force migrate currently running task */
+ raw_spin_lock(&rq->lock);
+ if (!rq->active_balance) {
+ rq->active_balance = 1;
+ rq->push_cpu = new_cpu;
+ get_task_struct(p);
+ rq->push_task = p;
+ rc = 1;
+ }
+ raw_spin_unlock(&rq->lock);
+
+ return rc;
+}
+
+void check_for_migration(struct rq *rq, struct task_struct *p)
+{
+ int new_cpu;
+ int active_balance;
+ int cpu = task_cpu(p);
+
+ if (energy_aware() && rq->misfit_task) {
+ if (rq->curr->state != TASK_RUNNING ||
+ rq->curr->nr_cpus_allowed == 1)
+ return;
+
+ new_cpu = select_energy_cpu_brute(p, cpu, 0);
+ if (capacity_orig_of(new_cpu) > capacity_orig_of(cpu)) {
+ active_balance = kick_active_balance(rq, p, new_cpu);
+ if (active_balance)
+ stop_one_cpu_nowait(cpu,
+ active_load_balance_cpu_stop,
+ rq, &rq->active_balance_work);
+ }
+ }
+}
+
#endif /* CONFIG_SMP */
/*
@@ -8651,6 +10576,16 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
+
+#ifdef CONFIG_SMP
+ if (!rq->rd->overutilized && cpu_overutilized(task_cpu(curr))) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+
+ rq->misfit_task = !task_fits_max(curr, rq->cpu);
+#endif
+
}
/*
@@ -8738,11 +10673,65 @@ static inline bool vruntime_normalized(struct task_struct *p)
return false;
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * Propagate the changes of the sched_entity across the tg tree to make it
+ * visible to the root
+ */
+static void propagate_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq;
+
+ /* Start to propagate at parent */
+ se = se->parent;
+
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+
+ update_load_avg(se, UPDATE_TG);
+ }
+}
+#else
+static void propagate_entity_cfs_rq(struct sched_entity *se) { }
+#endif
+
+static void detach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /* Catch up with the cfs_rq and remove our load when we leave */
+ update_load_avg(se, 0);
+ detach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+ propagate_entity_cfs_rq(se);
+}
+
+static void attach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * Since the real-depth could have been changed (only FAIR
+ * class maintain depth value), reset depth properly.
+ */
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+
+ /* Synchronize entity with its cfs_rq */
+ update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
+ attach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+ propagate_entity_cfs_rq(se);
+}
+
static void detach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 now = cfs_rq_clock_task(cfs_rq);
if (!vruntime_normalized(p)) {
/*
@@ -8753,30 +10742,15 @@ static void detach_task_cfs_rq(struct task_struct *p)
se->vruntime -= cfs_rq->min_vruntime;
}
- /* Catch up with the cfs_rq and remove our load when we leave */
- update_cfs_rq_load_avg(now, cfs_rq, false);
- detach_entity_load_avg(cfs_rq, se);
- update_tg_load_avg(cfs_rq, false);
+ detach_entity_cfs_rq(se);
}
static void attach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 now = cfs_rq_clock_task(cfs_rq);
-#ifdef CONFIG_FAIR_GROUP_SCHED
- /*
- * Since the real-depth could have been changed (only FAIR
- * class maintain depth value), reset depth properly.
- */
- se->depth = se->parent ? se->parent->depth + 1 : 0;
-#endif
-
- /* Synchronize task with its cfs_rq */
- update_cfs_rq_load_avg(now, cfs_rq, false);
- attach_entity_load_avg(cfs_rq, se);
- update_tg_load_avg(cfs_rq, false);
+ attach_entity_cfs_rq(se);
if (!vruntime_normalized(p))
se->vruntime += cfs_rq->min_vruntime;
@@ -8830,6 +10804,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
#ifdef CONFIG_SMP
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ cfs_rq->propagate_avg = 0;
+#endif
atomic_long_set(&cfs_rq->removed_load_avg, 0);
atomic_long_set(&cfs_rq->removed_util_avg, 0);
#endif
@@ -8938,7 +10915,8 @@ void online_fair_sched_group(struct task_group *tg)
se = tg->se[i];
raw_spin_lock_irq(&rq->lock);
- post_init_entity_util_avg(se);
+ update_rq_clock(rq);
+ attach_entity_cfs_rq(se);
sync_throttle(tg, i);
raw_spin_unlock_irq(&rq->lock);
}
@@ -9030,8 +11008,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
/* Possible calls to update_curr() need rq clock */
update_rq_clock(rq);
- for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se));
+ for_each_sched_entity(se) {
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -9111,6 +11091,10 @@ const struct sched_class fair_sched_class = {
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_change_group = task_change_group_fair,
#endif
+#ifdef CONFIG_SCHED_WALT
+ .fixup_cumulative_runnable_avg =
+ walt_fixup_cumulative_runnable_avg_fair,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1b3c818..c7f1bdd 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -74,3 +74,27 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
SCHED_FEAT(LB_MIN, false)
SCHED_FEAT(ATTACH_AGE_LOAD, true)
+/*
+ * Energy aware scheduling. Use platform energy model to guide scheduling
+ * decisions optimizing for energy efficiency.
+ */
+#ifdef CONFIG_DEFAULT_USE_ENERGY_AWARE
+SCHED_FEAT(ENERGY_AWARE, true)
+#else
+SCHED_FEAT(ENERGY_AWARE, false)
+#endif
+
+/*
+ * Minimum capacity capping. Keep track of minimum capacity factor when
+ * minimum frequency available to a policy is modified.
+ * If enabled, this can be used to inform the scheduler about capacity
+ * restrictions.
+ */
+SCHED_FEAT(MIN_CAPACITY_CAPPING, false)
+
+/*
+ * Enforce the priority of candidates selected by find_best_target()
+ * ON: If the target CPU saves any energy, use that.
+ * OFF: Use whichever of target or backup saves most.
+ */
+SCHED_FEAT(FBT_STRICT_ORDER, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 1d8718d..cf75f00 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -23,9 +23,10 @@ extern char __cpuidle_text_start[], __cpuidle_text_end[];
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
*/
-void sched_idle_set_state(struct cpuidle_state *idle_state)
+void sched_idle_set_state(struct cpuidle_state *idle_state, int index)
{
idle_set_state(this_rq(), idle_state);
+ idle_set_state_idx(this_rq(), index);
}
static int __read_mostly cpu_idle_force_poll;
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 5405d3f..0c00172 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
}
static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
put_prev_task(rq, prev);
update_idle_core(rq);
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index ec91fcc..5f3812c 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -7,6 +7,7 @@
*/
#include <linux/export.h>
+#include <linux/sched/loadavg.h>
#include "sched.h"
@@ -93,19 +94,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
return delta;
}
-/*
- * a1 = a0 * e + a * (1 - e)
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
*/
static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
{
- unsigned long newload;
+ unsigned long result = 1UL << frac_bits;
- newload = load * exp + active * (FIXED_1 - exp);
- if (active >= load)
- newload += FIXED_1-1;
+ if (n) {
+ for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+ }
- return newload / FIXED_1;
+ return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -227,75 +282,6 @@ static long calc_load_fold_idle(void)
return delta;
}
-/**
- * fixed_power_int - compute: x^n, in O(log n) time
- *
- * @x: base of the power
- * @frac_bits: fractional bits of @x
- * @n: power to raise @x to.
- *
- * By exploiting the relation between the definition of the natural power
- * function: x^n := x*x*...*x (x multiplied by itself for n times), and
- * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
- * (where: n_i \elem {0, 1}, the binary vector representing n),
- * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
- * of course trivially computable in O(log_2 n), the length of our binary
- * vector.
- */
-static unsigned long
-fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
-{
- unsigned long result = 1UL << frac_bits;
-
- if (n) {
- for (;;) {
- if (n & 1) {
- result *= x;
- result += 1UL << (frac_bits - 1);
- result >>= frac_bits;
- }
- n >>= 1;
- if (!n)
- break;
- x *= x;
- x += 1UL << (frac_bits - 1);
- x >>= frac_bits;
- }
- }
-
- return result;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- *
- * a2 = a1 * e + a * (1 - e)
- * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
- * = a0 * e^2 + a * (1 - e) * (1 + e)
- *
- * a3 = a2 * e + a * (1 - e)
- * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
- * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
- *
- * ...
- *
- * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
- * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
- * = a0 * e^n + a * (1 - e^n)
- *
- * [1] application of the geometric series:
- *
- * n 1 - x^(n+1)
- * S_n := \Sum x^i = -------------
- * i=0 1 - x
- */
-static unsigned long
-calc_load_n(unsigned long load, unsigned long exp,
- unsigned long active, unsigned int n)
-{
- return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
-}
-
/*
* NO_HZ can leave us missing all per-cpu ticks calling
* calc_load_account_active(), but since an idle CPU folds its delta into
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
new file mode 100644
index 0000000..e2a69e8
--- /dev/null
+++ b/kernel/sched/psi.c
@@ -0,0 +1,1292 @@
+/*
+ * Pressure stall information for CPU, memory and IO
+ *
+ * Copyright (c) 2018 Facebook, Inc.
+ * Author: Johannes Weiner <hannes@cmpxchg.org>
+ *
+ * Polling support by Suren Baghdasaryan <surenb@google.com>
+ * Copyright (c) 2018 Google, Inc.
+ *
+ * When CPU, memory and IO are contended, tasks experience delays that
+ * reduce throughput and introduce latencies into the workload. Memory
+ * and IO contention, in addition, can cause a full loss of forward
+ * progress in which the CPU goes idle.
+ *
+ * This code aggregates individual task delays into resource pressure
+ * metrics that indicate problems with both workload health and
+ * resource utilization.
+ *
+ * Model
+ *
+ * The time in which a task can execute on a CPU is our baseline for
+ * productivity. Pressure expresses the amount of time in which this
+ * potential cannot be realized due to resource contention.
+ *
+ * This concept of productivity has two components: the workload and
+ * the CPU. To measure the impact of pressure on both, we define two
+ * contention states for a resource: SOME and FULL.
+ *
+ * In the SOME state of a given resource, one or more tasks are
+ * delayed on that resource. This affects the workload's ability to
+ * perform work, but the CPU may still be executing other tasks.
+ *
+ * In the FULL state of a given resource, all non-idle tasks are
+ * delayed on that resource such that nobody is advancing and the CPU
+ * goes idle. This leaves both workload and CPU unproductive.
+ *
+ * (Naturally, the FULL state doesn't exist for the CPU resource.)
+ *
+ * SOME = nr_delayed_tasks != 0
+ * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0
+ *
+ * The percentage of wallclock time spent in those compound stall
+ * states gives pressure numbers between 0 and 100 for each resource,
+ * where the SOME percentage indicates workload slowdowns and the FULL
+ * percentage indicates reduced CPU utilization:
+ *
+ * %SOME = time(SOME) / period
+ * %FULL = time(FULL) / period
+ *
+ * Multiple CPUs
+ *
+ * The more tasks and available CPUs there are, the more work can be
+ * performed concurrently. This means that the potential that can go
+ * unrealized due to resource contention *also* scales with non-idle
+ * tasks and CPUs.
+ *
+ * Consider a scenario where 257 number crunching tasks are trying to
+ * run concurrently on 256 CPUs. If we simply aggregated the task
+ * states, we would have to conclude a CPU SOME pressure number of
+ * 100%, since *somebody* is waiting on a runqueue at all
+ * times. However, that is clearly not the amount of contention the
+ * workload is experiencing: only one out of 256 possible exceution
+ * threads will be contended at any given time, or about 0.4%.
+ *
+ * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any
+ * given time *one* of the tasks is delayed due to a lack of memory.
+ * Again, looking purely at the task state would yield a memory FULL
+ * pressure number of 0%, since *somebody* is always making forward
+ * progress. But again this wouldn't capture the amount of execution
+ * potential lost, which is 1 out of 4 CPUs, or 25%.
+ *
+ * To calculate wasted potential (pressure) with multiple processors,
+ * we have to base our calculation on the number of non-idle tasks in
+ * conjunction with the number of available CPUs, which is the number
+ * of potential execution threads. SOME becomes then the proportion of
+ * delayed tasks to possibe threads, and FULL is the share of possible
+ * threads that are unproductive due to delays:
+ *
+ * threads = min(nr_nonidle_tasks, nr_cpus)
+ * SOME = min(nr_delayed_tasks / threads, 1)
+ * FULL = (threads - min(nr_running_tasks, threads)) / threads
+ *
+ * For the 257 number crunchers on 256 CPUs, this yields:
+ *
+ * threads = min(257, 256)
+ * SOME = min(1 / 256, 1) = 0.4%
+ * FULL = (256 - min(257, 256)) / 256 = 0%
+ *
+ * For the 1 out of 4 memory-delayed tasks, this yields:
+ *
+ * threads = min(4, 4)
+ * SOME = min(1 / 4, 1) = 25%
+ * FULL = (4 - min(3, 4)) / 4 = 25%
+ *
+ * [ Substitute nr_cpus with 1, and you can see that it's a natural
+ * extension of the single-CPU model. ]
+ *
+ * Implementation
+ *
+ * To assess the precise time spent in each such state, we would have
+ * to freeze the system on task changes and start/stop the state
+ * clocks accordingly. Obviously that doesn't scale in practice.
+ *
+ * Because the scheduler aims to distribute the compute load evenly
+ * among the available CPUs, we can track task state locally to each
+ * CPU and, at much lower frequency, extrapolate the global state for
+ * the cumulative stall times and the running averages.
+ *
+ * For each runqueue, we track:
+ *
+ * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0)
+ * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu])
+ * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0)
+ *
+ * and then periodically aggregate:
+ *
+ * tNONIDLE = sum(tNONIDLE[i])
+ *
+ * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE
+ * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE
+ *
+ * %SOME = tSOME / period
+ * %FULL = tFULL / period
+ *
+ * This gives us an approximation of pressure that is practical
+ * cost-wise, yet way more sensitive and accurate than periodic
+ * sampling of the aggregate task states would be.
+ */
+
+#include "../workqueue_internal.h"
+#include <linux/sched/loadavg.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/seqlock.h>
+#include <linux/uaccess.h>
+#include <linux/cgroup.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/psi.h>
+#include "sched.h"
+
+static int psi_bug __read_mostly;
+
+DEFINE_STATIC_KEY_FALSE(psi_disabled);
+
+#ifdef CONFIG_PSI_DEFAULT_DISABLED
+static bool psi_enable;
+#else
+static bool psi_enable = true;
+#endif
+static int __init setup_psi(char *str)
+{
+ return kstrtobool(str, &psi_enable) == 0;
+}
+__setup("psi=", setup_psi);
+
+/* Running averages - we need to be higher-res than loadavg */
+#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */
+#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */
+#define EXP_60s 1981 /* 1/exp(2s/60s) */
+#define EXP_300s 2034 /* 1/exp(2s/300s) */
+
+/* PSI trigger definitions */
+#define WINDOW_MIN_US 500000 /* Min window size is 500ms */
+#define WINDOW_MAX_US 10000000 /* Max window size is 10s */
+#define UPDATES_PER_WINDOW 10 /* 10 updates per window */
+
+/* Sampling frequency in nanoseconds */
+static u64 psi_period __read_mostly;
+
+/* System-level pressure and stall tracking */
+static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu);
+static struct psi_group psi_system = {
+ .pcpu = &system_group_pcpu,
+};
+
+static void psi_avgs_work(struct work_struct *work);
+
+static void group_init(struct psi_group *group)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
+ group->avg_last_update = sched_clock();
+ group->avg_next_update = group->avg_last_update + psi_period;
+ INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
+ mutex_init(&group->avgs_lock);
+ /* Init trigger-related members */
+ atomic_set(&group->poll_scheduled, 0);
+ mutex_init(&group->trigger_lock);
+ INIT_LIST_HEAD(&group->triggers);
+ memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
+ group->poll_states = 0;
+ group->poll_min_period = U32_MAX;
+ memset(group->polling_total, 0, sizeof(group->polling_total));
+ group->polling_next_update = ULLONG_MAX;
+ group->polling_until = 0;
+ rcu_assign_pointer(group->poll_kworker, NULL);
+}
+
+void __init psi_init(void)
+{
+ if (!psi_enable) {
+ static_branch_enable(&psi_disabled);
+ return;
+ }
+
+ psi_period = jiffies_to_nsecs(PSI_FREQ);
+ group_init(&psi_system);
+}
+
+static bool test_state(unsigned int *tasks, enum psi_states state)
+{
+ switch (state) {
+ case PSI_IO_SOME:
+ return tasks[NR_IOWAIT];
+ case PSI_IO_FULL:
+ return tasks[NR_IOWAIT] && !tasks[NR_RUNNING];
+ case PSI_MEM_SOME:
+ return tasks[NR_MEMSTALL];
+ case PSI_MEM_FULL:
+ return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
+ case PSI_CPU_SOME:
+ return tasks[NR_RUNNING] > 1;
+ case PSI_NONIDLE:
+ return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
+ tasks[NR_RUNNING];
+ default:
+ return false;
+ }
+}
+
+static void get_recent_times(struct psi_group *group, int cpu,
+ enum psi_aggregators aggregator, u32 *times,
+ u32 *pchanged_states)
+{
+ struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+ u64 now, state_start;
+ enum psi_states s;
+ unsigned int seq;
+ u32 state_mask;
+
+ *pchanged_states = 0;
+
+ /* Snapshot a coherent view of the CPU state */
+ do {
+ seq = read_seqcount_begin(&groupc->seq);
+ now = cpu_clock(cpu);
+ memcpy(times, groupc->times, sizeof(groupc->times));
+ state_mask = groupc->state_mask;
+ state_start = groupc->state_start;
+ } while (read_seqcount_retry(&groupc->seq, seq));
+
+ /* Calculate state time deltas against the previous snapshot */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ u32 delta;
+ /*
+ * In addition to already concluded states, we also
+ * incorporate currently active states on the CPU,
+ * since states may last for many sampling periods.
+ *
+ * This way we keep our delta sampling buckets small
+ * (u32) and our reported pressure close to what's
+ * actually happening.
+ */
+ if (state_mask & (1 << s))
+ times[s] += now - state_start;
+
+ delta = times[s] - groupc->times_prev[aggregator][s];
+ groupc->times_prev[aggregator][s] = times[s];
+
+ times[s] = delta;
+ if (delta)
+ *pchanged_states |= (1 << s);
+ }
+}
+
+static void calc_avgs(unsigned long avg[3], int missed_periods,
+ u64 time, u64 period)
+{
+ unsigned long pct;
+
+ /* Fill in zeroes for periods of no activity */
+ if (missed_periods) {
+ avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods);
+ avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods);
+ avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods);
+ }
+
+ /* Sample the most recent active period */
+ pct = div_u64(time * 100, period);
+ pct *= FIXED_1;
+ avg[0] = calc_load(avg[0], EXP_10s, pct);
+ avg[1] = calc_load(avg[1], EXP_60s, pct);
+ avg[2] = calc_load(avg[2], EXP_300s, pct);
+}
+
+static void collect_percpu_times(struct psi_group *group,
+ enum psi_aggregators aggregator,
+ u32 *pchanged_states)
+{
+ u64 deltas[NR_PSI_STATES - 1] = { 0, };
+ unsigned long nonidle_total = 0;
+ u32 changed_states = 0;
+ int cpu;
+ int s;
+
+ /*
+ * Collect the per-cpu time buckets and average them into a
+ * single time sample that is normalized to wallclock time.
+ *
+ * For averaging, each CPU is weighted by its non-idle time in
+ * the sampling period. This eliminates artifacts from uneven
+ * loading, or even entirely idle CPUs.
+ */
+ for_each_possible_cpu(cpu) {
+ u32 times[NR_PSI_STATES];
+ u32 nonidle;
+ u32 cpu_changed_states;
+
+ get_recent_times(group, cpu, aggregator, times,
+ &cpu_changed_states);
+ changed_states |= cpu_changed_states;
+
+ nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]);
+ nonidle_total += nonidle;
+
+ for (s = 0; s < PSI_NONIDLE; s++)
+ deltas[s] += (u64)times[s] * nonidle;
+ }
+
+ /*
+ * Integrate the sample into the running statistics that are
+ * reported to userspace: the cumulative stall times and the
+ * decaying averages.
+ *
+ * Pressure percentages are sampled at PSI_FREQ. We might be
+ * called more often when the user polls more frequently than
+ * that; we might be called less often when there is no task
+ * activity, thus no data, and clock ticks are sporadic. The
+ * below handles both.
+ */
+
+ /* total= */
+ for (s = 0; s < NR_PSI_STATES - 1; s++)
+ group->total[aggregator][s] +=
+ div_u64(deltas[s], max(nonidle_total, 1UL));
+
+ if (pchanged_states)
+ *pchanged_states = changed_states;
+}
+
+static u64 update_averages(struct psi_group *group, u64 now)
+{
+ unsigned long missed_periods = 0;
+ u64 expires, period;
+ u64 avg_next_update;
+ int s;
+
+ /* avgX= */
+ expires = group->avg_next_update;
+ if (now - expires >= psi_period)
+ missed_periods = div_u64(now - expires, psi_period);
+
+ /*
+ * The periodic clock tick can get delayed for various
+ * reasons, especially on loaded systems. To avoid clock
+ * drift, we schedule the clock in fixed psi_period intervals.
+ * But the deltas we sample out of the per-cpu buckets above
+ * are based on the actual time elapsing between clock ticks.
+ */
+ avg_next_update = expires + ((1 + missed_periods) * psi_period);
+ period = now - (group->avg_last_update + (missed_periods * psi_period));
+ group->avg_last_update = now;
+
+ for (s = 0; s < NR_PSI_STATES - 1; s++) {
+ u32 sample;
+
+ sample = group->total[PSI_AVGS][s] - group->avg_total[s];
+ /*
+ * Due to the lockless sampling of the time buckets,
+ * recorded time deltas can slip into the next period,
+ * which under full pressure can result in samples in
+ * excess of the period length.
+ *
+ * We don't want to report non-sensical pressures in
+ * excess of 100%, nor do we want to drop such events
+ * on the floor. Instead we punt any overage into the
+ * future until pressure subsides. By doing this we
+ * don't underreport the occurring pressure curve, we
+ * just report it delayed by one period length.
+ *
+ * The error isn't cumulative. As soon as another
+ * delta slips from a period P to P+1, by definition
+ * it frees up its time T in P.
+ */
+ if (sample > period)
+ sample = period;
+ group->avg_total[s] += sample;
+ calc_avgs(group->avg[s], missed_periods, sample, period);
+ }
+
+ return avg_next_update;
+}
+
+static void psi_avgs_work(struct work_struct *work)
+{
+ struct delayed_work *dwork;
+ struct psi_group *group;
+ u32 changed_states;
+ bool nonidle;
+ u64 now;
+
+ dwork = to_delayed_work(work);
+ group = container_of(dwork, struct psi_group, avgs_work);
+
+ mutex_lock(&group->avgs_lock);
+
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_AVGS, &changed_states);
+ nonidle = changed_states & (1 << PSI_NONIDLE);
+ /*
+ * If there is task activity, periodically fold the per-cpu
+ * times and feed samples into the running averages. If things
+ * are idle and there is no data to process, stop the clock.
+ * Once restarted, we'll catch up the running averages in one
+ * go - see calc_avgs() and missed_periods.
+ */
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
+
+ if (nonidle) {
+ schedule_delayed_work(dwork, nsecs_to_jiffies(
+ group->avg_next_update - now) + 1);
+ }
+
+ mutex_unlock(&group->avgs_lock);
+}
+
+/* Trigger tracking window manupulations */
+static void window_reset(struct psi_window *win, u64 now, u64 value,
+ u64 prev_growth)
+{
+ win->start_time = now;
+ win->start_value = value;
+ win->prev_growth = prev_growth;
+}
+
+/*
+ * PSI growth tracking window update and growth calculation routine.
+ *
+ * This approximates a sliding tracking window by interpolating
+ * partially elapsed windows using historical growth data from the
+ * previous intervals. This minimizes memory requirements (by not storing
+ * all the intermediate values in the previous window) and simplifies
+ * the calculations. It works well because PSI signal changes only in
+ * positive direction and over relatively small window sizes the growth
+ * is close to linear.
+ */
+static u64 window_update(struct psi_window *win, u64 now, u64 value)
+{
+ u64 elapsed;
+ u64 growth;
+
+ elapsed = now - win->start_time;
+ growth = value - win->start_value;
+ /*
+ * After each tracking window passes win->start_value and
+ * win->start_time get reset and win->prev_growth stores
+ * the average per-window growth of the previous window.
+ * win->prev_growth is then used to interpolate additional
+ * growth from the previous window assuming it was linear.
+ */
+ if (elapsed > win->size)
+ window_reset(win, now, value, growth);
+ else {
+ u32 remaining;
+
+ remaining = win->size - elapsed;
+ growth += div64_u64(win->prev_growth * remaining, win->size);
+ }
+
+ return growth;
+}
+
+static void init_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+
+ list_for_each_entry(t, &group->triggers, node)
+ window_reset(&t->win, now,
+ group->total[PSI_POLL][t->state], 0);
+ memcpy(group->polling_total, group->total[PSI_POLL],
+ sizeof(group->polling_total));
+ group->polling_next_update = now + group->poll_min_period;
+}
+
+static u64 update_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+ bool new_stall = false;
+ u64 *total = group->total[PSI_POLL];
+
+ /*
+ * On subsequent updates, calculate growth deltas and let
+ * watchers know when their specified thresholds are exceeded.
+ */
+ list_for_each_entry(t, &group->triggers, node) {
+ u64 growth;
+
+ /* Check for stall activity */
+ if (group->polling_total[t->state] == total[t->state])
+ continue;
+
+ /*
+ * Multiple triggers might be looking at the same state,
+ * remember to update group->polling_total[] once we've
+ * been through all of them. Also remember to extend the
+ * polling time if we see new stall activity.
+ */
+ new_stall = true;
+
+ /* Calculate growth since last update */
+ growth = window_update(&t->win, now, total[t->state]);
+ if (growth < t->threshold)
+ continue;
+
+ /* Limit event signaling to once per window */
+ if (now < t->last_event_time + t->win.size)
+ continue;
+
+ /* Generate an event */
+ if (cmpxchg(&t->event, 0, 1) == 0)
+ wake_up_interruptible(&t->event_wait);
+ t->last_event_time = now;
+ }
+
+ if (new_stall)
+ memcpy(group->polling_total, total,
+ sizeof(group->polling_total));
+
+ return now + group->poll_min_period;
+}
+
+/*
+ * Schedule polling if it's not already scheduled. It's safe to call even from
+ * hotpath because even though kthread_queue_delayed_work takes worker->lock
+ * spinlock that spinlock is never contended due to poll_scheduled atomic
+ * preventing such competition.
+ */
+static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
+{
+ struct kthread_worker *kworker;
+
+ /* Do not reschedule if already scheduled */
+ if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+ return;
+
+ rcu_read_lock();
+
+ kworker = rcu_dereference(group->poll_kworker);
+ /*
+ * kworker might be NULL in case psi_trigger_destroy races with
+ * psi_task_change (hotpath) which can't use locks
+ */
+ if (likely(kworker))
+ kthread_queue_delayed_work(kworker, &group->poll_work, delay);
+ else
+ atomic_set(&group->poll_scheduled, 0);
+
+ rcu_read_unlock();
+}
+
+static void psi_poll_work(struct kthread_work *work)
+{
+ struct kthread_delayed_work *dwork;
+ struct psi_group *group;
+ u32 changed_states;
+ u64 now;
+
+ dwork = container_of(work, struct kthread_delayed_work, work);
+ group = container_of(dwork, struct psi_group, poll_work);
+
+ atomic_set(&group->poll_scheduled, 0);
+
+ mutex_lock(&group->trigger_lock);
+
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_POLL, &changed_states);
+
+ if (changed_states & group->poll_states) {
+ /* Initialize trigger windows when entering polling mode */
+ if (now > group->polling_until)
+ init_triggers(group, now);
+
+ /*
+ * Keep the monitor active for at least the duration of the
+ * minimum tracking window as long as monitor states are
+ * changing.
+ */
+ group->polling_until = now +
+ group->poll_min_period * UPDATES_PER_WINDOW;
+ }
+
+ if (now > group->polling_until) {
+ group->polling_next_update = ULLONG_MAX;
+ goto out;
+ }
+
+ if (now >= group->polling_next_update)
+ group->polling_next_update = update_triggers(group, now);
+
+ psi_schedule_poll_work(group,
+ nsecs_to_jiffies(group->polling_next_update - now) + 1);
+
+out:
+ mutex_unlock(&group->trigger_lock);
+}
+
+static void record_times(struct psi_group_cpu *groupc, int cpu,
+ bool memstall_tick)
+{
+ u32 delta;
+ u64 now;
+
+ now = cpu_clock(cpu);
+ delta = now - groupc->state_start;
+ groupc->state_start = now;
+
+ if (groupc->state_mask & (1 << PSI_IO_SOME)) {
+ groupc->times[PSI_IO_SOME] += delta;
+ if (groupc->state_mask & (1 << PSI_IO_FULL))
+ groupc->times[PSI_IO_FULL] += delta;
+ }
+
+ if (groupc->state_mask & (1 << PSI_MEM_SOME)) {
+ groupc->times[PSI_MEM_SOME] += delta;
+ if (groupc->state_mask & (1 << PSI_MEM_FULL))
+ groupc->times[PSI_MEM_FULL] += delta;
+ else if (memstall_tick) {
+ u32 sample;
+ /*
+ * Since we care about lost potential, a
+ * memstall is FULL when there are no other
+ * working tasks, but also when the CPU is
+ * actively reclaiming and nothing productive
+ * could run even if it were runnable.
+ *
+ * When the timer tick sees a reclaiming CPU,
+ * regardless of runnable tasks, sample a FULL
+ * tick (or less if it hasn't been a full tick
+ * since the last state change).
+ */
+ sample = min(delta, (u32)jiffies_to_nsecs(1));
+ groupc->times[PSI_MEM_FULL] += sample;
+ }
+ }
+
+ if (groupc->state_mask & (1 << PSI_CPU_SOME))
+ groupc->times[PSI_CPU_SOME] += delta;
+
+ if (groupc->state_mask & (1 << PSI_NONIDLE))
+ groupc->times[PSI_NONIDLE] += delta;
+}
+
+static u32 psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set)
+{
+ struct psi_group_cpu *groupc;
+ unsigned int t, m;
+ enum psi_states s;
+ u32 state_mask = 0;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+
+ /*
+ * First we assess the aggregate resource states this CPU's
+ * tasks have been in since the last change, and account any
+ * SOME and FULL time these may have resulted in.
+ *
+ * Then we update the task counts according to the state
+ * change requested through the @clear and @set bits.
+ */
+ write_seqcount_begin(&groupc->seq);
+
+ record_times(groupc, cpu, false);
+
+ for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
+ if (!(m & (1 << t)))
+ continue;
+ if (groupc->tasks[t] == 0 && !psi_bug) {
+ printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+ cpu, t, groupc->tasks[0],
+ groupc->tasks[1], groupc->tasks[2],
+ clear, set);
+ psi_bug = 1;
+ }
+ groupc->tasks[t]--;
+ }
+
+ for (t = 0; set; set &= ~(1 << t), t++)
+ if (set & (1 << t))
+ groupc->tasks[t]++;
+
+ /* Calculate state mask representing active states */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ if (test_state(groupc->tasks, s))
+ state_mask |= (1 << s);
+ }
+ groupc->state_mask = state_mask;
+
+ write_seqcount_end(&groupc->seq);
+
+ return state_mask;
+}
+
+static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+{
+#ifdef CONFIG_CGROUPS
+ struct cgroup *cgroup = NULL;
+
+ if (!*iter)
+ cgroup = task->cgroups->dfl_cgrp;
+ else if (*iter == &psi_system)
+ return NULL;
+ else
+ cgroup = cgroup_parent(*iter);
+
+ if (cgroup && cgroup_parent(cgroup)) {
+ *iter = cgroup;
+ return cgroup_psi(cgroup);
+ }
+#else
+ if (*iter)
+ return NULL;
+#endif
+ *iter = &psi_system;
+ return &psi_system;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+ int cpu = task_cpu(task);
+ struct psi_group *group;
+ bool wake_clock = true;
+ void *iter = NULL;
+
+ if (!task->pid)
+ return;
+
+ if (((task->psi_flags & set) ||
+ (task->psi_flags & clear) != clear) &&
+ !psi_bug) {
+ printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
+ task->pid, task->comm, cpu,
+ task->psi_flags, clear, set);
+ psi_bug = 1;
+ }
+
+ task->psi_flags &= ~clear;
+ task->psi_flags |= set;
+
+ /*
+ * Periodic aggregation shuts off if there is a period of no
+ * task changes, so we wake it back up if necessary. However,
+ * don't do this if the task change is the aggregation worker
+ * itself going to sleep, or we'll ping-pong forever.
+ */
+ if (unlikely((clear & TSK_RUNNING) &&
+ (task->flags & PF_WQ_WORKER) &&
+ wq_worker_last_func(task) == psi_avgs_work))
+ wake_clock = false;
+
+ while ((group = iterate_groups(task, &iter))) {
+ u32 state_mask = psi_group_change(group, cpu, clear, set);
+
+ if (state_mask & group->poll_states)
+ psi_schedule_poll_work(group, 1);
+
+ if (wake_clock && !delayed_work_pending(&group->avgs_work))
+ schedule_delayed_work(&group->avgs_work, PSI_FREQ);
+ }
+}
+
+void psi_memstall_tick(struct task_struct *task, int cpu)
+{
+ struct psi_group *group;
+ void *iter = NULL;
+
+ while ((group = iterate_groups(task, &iter))) {
+ struct psi_group_cpu *groupc;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+ write_seqcount_begin(&groupc->seq);
+ record_times(groupc, cpu, true);
+ write_seqcount_end(&groupc->seq);
+ }
+}
+
+/**
+ * psi_memstall_enter - mark the beginning of a memory stall section
+ * @flags: flags to handle nested sections
+ *
+ * Marks the calling task as being stalled due to a lack of memory,
+ * such as waiting for a refault or performing reclaim.
+ */
+void psi_memstall_enter(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ *flags = current->flags & PF_MEMSTALL;
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL setting & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we can
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags |= PF_MEMSTALL;
+ psi_task_change(current, 0, TSK_MEMSTALL);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+/**
+ * psi_memstall_leave - mark the end of an memory stall section
+ * @flags: flags to handle nested memdelay sections
+ *
+ * Marks the calling task as no longer stalled due to lack of memory.
+ */
+void psi_memstall_leave(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we could
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags &= ~PF_MEMSTALL;
+ psi_task_change(current, TSK_MEMSTALL, 0);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgroup)
+{
+ if (static_branch_likely(&psi_disabled))
+ return 0;
+
+ cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu);
+ if (!cgroup->psi.pcpu)
+ return -ENOMEM;
+ group_init(&cgroup->psi);
+ return 0;
+}
+
+void psi_cgroup_free(struct cgroup *cgroup)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ cancel_delayed_work_sync(&cgroup->psi.avgs_work);
+ free_percpu(cgroup->psi.pcpu);
+ /* All triggers must be removed by now */
+ WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n");
+}
+
+/**
+ * cgroup_move_task - move task to a different cgroup
+ * @task: the task
+ * @to: the target css_set
+ *
+ * Move task to a new cgroup and safely migrate its associated stall
+ * state between the different groups.
+ *
+ * This function acquires the task's rq lock to lock out concurrent
+ * changes to the task's scheduling state and - in case the task is
+ * running - concurrent changes to its stall state.
+ */
+void cgroup_move_task(struct task_struct *task, struct css_set *to)
+{
+ unsigned int task_flags = 0;
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled)) {
+ /*
+ * Lame to do this here, but the scheduler cannot be locked
+ * from the outside, so we move cgroups from inside sched/.
+ */
+ rcu_assign_pointer(task->cgroups, to);
+ return;
+ }
+
+ rq = task_rq_lock(task, &rf);
+
+ if (task_on_rq_queued(task))
+ task_flags = TSK_RUNNING;
+ else if (task->in_iowait)
+ task_flags = TSK_IOWAIT;
+
+ if (task->flags & PF_MEMSTALL)
+ task_flags |= TSK_MEMSTALL;
+
+ if (task_flags)
+ psi_task_change(task, task_flags, 0);
+
+ /* See comment above */
+ rcu_assign_pointer(task->cgroups, to);
+
+ if (task_flags)
+ psi_task_change(task, 0, task_flags);
+
+ task_rq_unlock(rq, task, &rf);
+}
+#endif /* CONFIG_CGROUPS */
+
+int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
+{
+ int full;
+ u64 now;
+
+ if (static_branch_likely(&psi_disabled))
+ return -EOPNOTSUPP;
+
+ /* Update averages before reporting them */
+ mutex_lock(&group->avgs_lock);
+ now = sched_clock();
+ collect_percpu_times(group, PSI_AVGS, NULL);
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
+ mutex_unlock(&group->avgs_lock);
+
+ for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+ unsigned long avg[3];
+ u64 total;
+ int w;
+
+ for (w = 0; w < 3; w++)
+ avg[w] = group->avg[res * 2 + full][w];
+ total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+ NSEC_PER_USEC);
+
+ seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
+ full ? "full" : "some",
+ LOAD_INT(avg[0]), LOAD_FRAC(avg[0]),
+ LOAD_INT(avg[1]), LOAD_FRAC(avg[1]),
+ LOAD_INT(avg[2]), LOAD_FRAC(avg[2]),
+ total);
+ }
+
+ return 0;
+}
+
+static int psi_io_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_IO);
+}
+
+static int psi_memory_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_MEM);
+}
+
+static int psi_cpu_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_CPU);
+}
+
+static int psi_io_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_io_show, NULL);
+}
+
+static int psi_memory_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_memory_show, NULL);
+}
+
+static int psi_cpu_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_cpu_show, NULL);
+}
+
+struct psi_trigger *psi_trigger_create(struct psi_group *group,
+ char *buf, size_t nbytes, enum psi_res res)
+{
+ struct psi_trigger *t;
+ enum psi_states state;
+ u32 threshold_us;
+ u32 window_us;
+
+ if (static_branch_likely(&psi_disabled))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_SOME + res * 2;
+ else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_FULL + res * 2;
+ else
+ return ERR_PTR(-EINVAL);
+
+ if (state >= PSI_NONIDLE)
+ return ERR_PTR(-EINVAL);
+
+ if (window_us < WINDOW_MIN_US ||
+ window_us > WINDOW_MAX_US)
+ return ERR_PTR(-EINVAL);
+
+ /* Check threshold */
+ if (threshold_us == 0 || threshold_us > window_us)
+ return ERR_PTR(-EINVAL);
+
+ t = kmalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return ERR_PTR(-ENOMEM);
+
+ t->group = group;
+ t->state = state;
+ t->threshold = threshold_us * NSEC_PER_USEC;
+ t->win.size = window_us * NSEC_PER_USEC;
+ window_reset(&t->win, 0, 0, 0);
+
+ t->event = 0;
+ t->last_event_time = 0;
+ init_waitqueue_head(&t->event_wait);
+ kref_init(&t->refcount);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!rcu_access_pointer(group->poll_kworker)) {
+ struct sched_param param = {
+ .sched_priority = 1,
+ };
+ struct kthread_worker *kworker;
+
+ kworker = kthread_create_worker(0, "psimon");
+ if (IS_ERR(kworker)) {
+ kfree(t);
+ mutex_unlock(&group->trigger_lock);
+ return ERR_CAST(kworker);
+ }
+ sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m);
+ kthread_init_delayed_work(&group->poll_work,
+ psi_poll_work);
+ rcu_assign_pointer(group->poll_kworker, kworker);
+ }
+
+ list_add(&t->node, &group->triggers);
+ group->poll_min_period = min(group->poll_min_period,
+ div_u64(t->win.size, UPDATES_PER_WINDOW));
+ group->nr_triggers[t->state]++;
+ group->poll_states |= (1 << t->state);
+
+ mutex_unlock(&group->trigger_lock);
+
+ return t;
+}
+
+static void psi_trigger_destroy(struct kref *ref)
+{
+ struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
+ struct psi_group *group = t->group;
+ struct kthread_worker *kworker_to_destroy = NULL;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ /*
+ * Wakeup waiters to stop polling. Can happen if cgroup is deleted
+ * from under a polling process.
+ */
+ wake_up_interruptible(&t->event_wait);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!list_empty(&t->node)) {
+ struct psi_trigger *tmp;
+ u64 period = ULLONG_MAX;
+
+ list_del(&t->node);
+ group->nr_triggers[t->state]--;
+ if (!group->nr_triggers[t->state])
+ group->poll_states &= ~(1 << t->state);
+ /* reset min update period for the remaining triggers */
+ list_for_each_entry(tmp, &group->triggers, node)
+ period = min(period, div_u64(tmp->win.size,
+ UPDATES_PER_WINDOW));
+ group->poll_min_period = period;
+ /* Destroy poll_kworker when the last trigger is destroyed */
+ if (group->poll_states == 0) {
+ group->polling_until = 0;
+ kworker_to_destroy = rcu_dereference_protected(
+ group->poll_kworker,
+ lockdep_is_held(&group->trigger_lock));
+ rcu_assign_pointer(group->poll_kworker, NULL);
+ }
+ }
+
+ mutex_unlock(&group->trigger_lock);
+
+ /*
+ * Wait for both *trigger_ptr from psi_trigger_replace and
+ * poll_kworker RCUs to complete their read-side critical sections
+ * before destroying the trigger and optionally the poll_kworker
+ */
+ synchronize_rcu();
+ /*
+ * Destroy the kworker after releasing trigger_lock to prevent a
+ * deadlock while waiting for psi_poll_work to acquire trigger_lock
+ */
+ if (kworker_to_destroy) {
+ /*
+ * After the RCU grace period has expired, the worker
+ * can no longer be found through group->poll_kworker.
+ * But it might have been already scheduled before
+ * that - deschedule it cleanly before destroying it.
+ */
+ kthread_cancel_delayed_work_sync(&group->poll_work);
+ atomic_set(&group->poll_scheduled, 0);
+
+ kthread_destroy_worker(kworker_to_destroy);
+ }
+ kfree(t);
+}
+
+void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new)
+{
+ struct psi_trigger *old = *trigger_ptr;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ rcu_assign_pointer(*trigger_ptr, new);
+ if (old)
+ kref_put(&old->refcount, psi_trigger_destroy);
+}
+
+unsigned int psi_trigger_poll(void **trigger_ptr, struct file *file,
+ poll_table *wait)
+{
+ unsigned int ret = DEFAULT_POLLMASK;
+ struct psi_trigger *t;
+
+ if (static_branch_likely(&psi_disabled))
+ return DEFAULT_POLLMASK | POLLERR | POLLPRI;
+
+ rcu_read_lock();
+
+ t = rcu_dereference(*(void __rcu __force **)trigger_ptr);
+ if (!t) {
+ rcu_read_unlock();
+ return DEFAULT_POLLMASK | POLLERR | POLLPRI;
+ }
+ kref_get(&t->refcount);
+
+ rcu_read_unlock();
+
+ poll_wait(file, &t->event_wait, wait);
+
+ if (cmpxchg(&t->event, 1, 0) == 1)
+ ret |= POLLPRI;
+
+ kref_put(&t->refcount, psi_trigger_destroy);
+
+ return ret;
+}
+
+static ssize_t psi_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, enum psi_res res)
+{
+ char buf[32];
+ size_t buf_size;
+ struct seq_file *seq;
+ struct psi_trigger *new;
+
+ if (static_branch_likely(&psi_disabled))
+ return -EOPNOTSUPP;
+
+ if (!nbytes)
+ return -EINVAL;
+
+ buf_size = min(nbytes, sizeof(buf));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size - 1] = '\0';
+
+ new = psi_trigger_create(&psi_system, buf, nbytes, res);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ seq = file->private_data;
+ /* Take seq->lock to protect seq->private from concurrent writes */
+ mutex_lock(&seq->lock);
+ psi_trigger_replace(&seq->private, new);
+ mutex_unlock(&seq->lock);
+
+ return nbytes;
+}
+
+static ssize_t psi_io_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_IO);
+}
+
+static ssize_t psi_memory_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_MEM);
+}
+
+static ssize_t psi_cpu_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_CPU);
+}
+
+static unsigned int psi_fop_poll(struct file *file, poll_table *wait)
+{
+ struct seq_file *seq = file->private_data;
+
+ return psi_trigger_poll(&seq->private, file, wait);
+}
+
+static int psi_fop_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+
+ psi_trigger_replace(&seq->private, NULL);
+ return single_release(inode, file);
+}
+
+static const struct file_operations psi_io_fops = {
+ .open = psi_io_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .write = psi_io_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
+};
+
+static const struct file_operations psi_memory_fops = {
+ .open = psi_memory_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .write = psi_memory_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
+};
+
+static const struct file_operations psi_cpu_fops = {
+ .open = psi_cpu_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .write = psi_cpu_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
+};
+
+static int __init psi_proc_init(void)
+{
+ proc_mkdir("pressure", NULL);
+ proc_create("pressure/io", 0, NULL, &psi_io_fops);
+ proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
+ proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+ return 0;
+}
+module_init(psi_proc_init);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 5034c41..8409ac7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -8,6 +8,8 @@
#include <linux/slab.h>
#include <linux/irq_work.h>
+#include "walt.h"
+
int sched_rr_timeslice = RR_TIMESLICE;
int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
@@ -889,6 +891,51 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se)
return rt_task_of(rt_se)->prio;
}
+static void dump_throttled_rt_tasks(struct rt_rq *rt_rq)
+{
+ struct rt_prio_array *array = &rt_rq->active;
+ struct sched_rt_entity *rt_se;
+ char buf[500];
+ char *pos = buf;
+ char *end = buf + sizeof(buf);
+ int idx;
+
+ pos += snprintf(pos, sizeof(buf),
+ "sched: RT throttling activated for rt_rq %p (cpu %d)\n",
+ rt_rq, cpu_of(rq_of_rt_rq(rt_rq)));
+
+ if (bitmap_empty(array->bitmap, MAX_RT_PRIO))
+ goto out;
+
+ pos += snprintf(pos, end - pos, "potential CPU hogs:\n");
+ idx = sched_find_first_bit(array->bitmap);
+ while (idx < MAX_RT_PRIO) {
+ list_for_each_entry(rt_se, array->queue + idx, run_list) {
+ struct task_struct *p;
+
+ if (!rt_entity_is_task(rt_se))
+ continue;
+
+ p = rt_task_of(rt_se);
+ if (pos < end)
+ pos += snprintf(pos, end - pos, "\t%s (%d)\n",
+ p->comm, p->pid);
+ }
+ idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx + 1);
+ }
+out:
+#ifdef CONFIG_PANIC_ON_RT_THROTTLING
+ /*
+ * Use pr_err() in the BUG() case since printk_sched() will
+ * not get flushed and deadlock is not a concern.
+ */
+ pr_err("%s", buf);
+ BUG();
+#else
+ printk_deferred("%s", buf);
+#endif
+}
+
static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
{
u64 runtime = sched_rt_runtime(rt_rq);
@@ -912,8 +959,14 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
* but accrue some time due to boosting.
*/
if (likely(rt_b->rt_runtime)) {
+ static bool once = false;
+
rt_rq->rt_throttled = 1;
- printk_deferred_once("sched: RT throttling activated\n");
+
+ if (!once) {
+ once = true;
+ dump_throttled_rt_tasks(rt_rq);
+ }
} else {
/*
* In case we did anyway, make it go away,
@@ -1314,6 +1367,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
rt_se->timeout = 0;
enqueue_rt_entity(rt_se, flags);
+ walt_inc_cumulative_runnable_avg(rq, p);
if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
enqueue_pushable_task(rq, p);
@@ -1325,6 +1379,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
update_curr_rt(rq);
dequeue_rt_entity(rt_se, flags);
+ walt_dec_cumulative_runnable_avg(rq, p);
dequeue_pushable_task(rq, p);
}
@@ -1515,7 +1570,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
}
static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
@@ -1527,9 +1582,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_rt_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
/*
* pull_rt_task() can drop (and re-acquire) rq->lock; this
* means a dl or stop task can slip in, in which case we need
@@ -1834,7 +1889,9 @@ static int push_rt_task(struct rq *rq)
}
deactivate_task(rq, next_task, 0);
+ next_task->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(next_task, lowest_rq->cpu);
+ next_task->on_rq = TASK_ON_RQ_QUEUED;
activate_task(lowest_rq, next_task, 0);
ret = 1;
@@ -2106,7 +2163,9 @@ static void pull_rt_task(struct rq *this_rq)
resched = true;
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, this_cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(this_rq, p, 0);
/*
* We continue with the search, just in
@@ -2361,6 +2420,9 @@ const struct sched_class rt_sched_class = {
.switched_to = switched_to_rt,
.update_curr = update_curr_rt,
+#ifdef CONFIG_SCHED_WALT
+ .fixup_cumulative_runnable_avg = walt_fixup_cumulative_runnable_avg,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 819bd5f..e33a557 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -8,6 +8,7 @@
#include <linux/kernel_stat.h>
#include <linux/binfmts.h>
#include <linux/mutex.h>
+#include <linux/psi.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
#include <linux/irq_work.h>
@@ -41,8 +42,10 @@ extern long calc_load_fold_active(struct rq *this_rq, long adjust);
#ifdef CONFIG_SMP
extern void cpu_load_update_active(struct rq *this_rq);
+extern void check_for_migration(struct rq *rq, struct task_struct *p);
#else
static inline void cpu_load_update_active(struct rq *this_rq) { }
+static inline void check_for_migration(struct rq *rq, struct task_struct *p) { }
#endif
#ifdef CONFIG_SCHED_SMT
@@ -241,6 +244,7 @@ extern struct mutex sched_domains_mutex;
#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
+#include <linux/psi.h>
struct cfs_rq;
struct rt_rq;
@@ -420,6 +424,7 @@ struct cfs_rq {
unsigned long runnable_load_avg;
#ifdef CONFIG_FAIR_GROUP_SCHED
unsigned long tg_load_avg_contrib;
+ unsigned long propagate_avg;
#endif
atomic_long_t removed_load_avg, removed_util_avg;
#ifndef CONFIG_64BIT
@@ -463,6 +468,9 @@ struct cfs_rq {
u64 throttled_clock_task_time;
int throttled, throttle_count;
struct list_head throttled_list;
+#ifdef CONFIG_SCHED_WALT
+ u64 cumulative_runnable_avg;
+#endif /* CONFIG_SCHED_WALT */
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
@@ -549,6 +557,12 @@ struct dl_rq {
#ifdef CONFIG_SMP
+struct max_cpu_capacity {
+ raw_spinlock_t lock;
+ unsigned long val;
+ int cpu;
+};
+
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
@@ -567,6 +581,9 @@ struct root_domain {
/* Indicate more than one runnable task for any CPU */
bool overload;
+ /* Indicate one or more cpus over-utilized (tipping point) */
+ bool overutilized;
+
/*
* The bit corresponding to a CPU gets set here if such CPU has more
* than one runnable -deadline task (as it is below for RT tasks).
@@ -596,7 +613,11 @@ struct root_domain {
cpumask_var_t rto_mask;
struct cpupri cpupri;
- unsigned long max_cpu_capacity;
+ /* Maximum cpu capacity in the system. */
+ struct max_cpu_capacity max_cpu_capacity;
+
+ /* First cpu with maximum and minimum original capacity */
+ int max_cap_orig_cpu, min_cap_orig_cpu;
};
extern struct root_domain def_root_domain;
@@ -630,6 +651,7 @@ struct rq {
#endif
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
+ unsigned int misfit_task;
#ifdef CONFIG_NO_HZ_COMMON
#ifdef CONFIG_SMP
unsigned long last_load_update_tick;
@@ -639,6 +661,14 @@ struct rq {
#ifdef CONFIG_NO_HZ_FULL
unsigned long last_sched_tick;
#endif
+
+#ifdef CONFIG_CPU_QUIET
+ /* time-based average load */
+ u64 nr_last_stamp;
+ u64 nr_running_integral;
+ seqcount_t ave_seqcnt;
+#endif
+
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
@@ -651,6 +681,7 @@ struct rq {
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
+ struct list_head *tmp_alone_branch;
#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
@@ -684,6 +715,7 @@ struct rq {
/* For active balancing */
int active_balance;
int push_cpu;
+ struct task_struct *push_task;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
@@ -700,6 +732,20 @@ struct rq {
u64 max_idle_balance_cost;
#endif
+#ifdef CONFIG_SCHED_WALT
+ u64 cumulative_runnable_avg;
+ u64 window_start;
+ u64 curr_runnable_sum;
+ u64 prev_runnable_sum;
+ u64 nt_curr_runnable_sum;
+ u64 nt_prev_runnable_sum;
+ u64 cur_irqload;
+ u64 avg_irqload;
+ u64 irqload_ts;
+ u64 cum_window_demand;
+#endif /* CONFIG_SCHED_WALT */
+
+
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
#endif
@@ -738,6 +784,9 @@ struct rq {
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
+#ifdef CONFIG_SMP
+ struct eas_stats eas_stats;
+#endif
#endif
#ifdef CONFIG_SMP
@@ -747,6 +796,7 @@ struct rq {
#ifdef CONFIG_CPU_IDLE
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
+ int idle_state_idx;
#endif
};
@@ -767,6 +817,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)
+extern void update_rq_clock(struct rq *rq);
+
static inline u64 __rq_clock_broken(struct rq *rq)
{
return READ_ONCE(rq->clock);
@@ -796,6 +848,118 @@ static inline void rq_clock_skip_update(struct rq *rq, bool skip)
rq->clock_skip_update &= ~RQCF_REQ_SKIP;
}
+struct rq_flags {
+ unsigned long flags;
+ struct pin_cookie cookie;
+};
+
+static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ rf->cookie = lockdep_pin_lock(&rq->lock);
+}
+
+static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ lockdep_unpin_lock(&rq->lock, rf->cookie);
+}
+
+static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ lockdep_repin_lock(&rq->lock, rf->cookie);
+}
+
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(rq->lock);
+
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(p->pi_lock)
+ __acquires(rq->lock);
+
+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+ __releases(rq->lock)
+ __releases(p->pi_lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+}
+
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irq(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline struct rq *
+this_rq_lock_irq(struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ local_irq_disable();
+ rq = this_rq();
+ rq_lock(rq, rf);
+ return rq;
+}
+
#ifdef CONFIG_NUMA
enum numa_topology_type {
NUMA_DIRECT,
@@ -896,6 +1060,8 @@ DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(struct sched_domain *, sd_ea);
+DECLARE_PER_CPU(struct sched_domain *, sd_scs);
struct sched_group_capacity {
atomic_t ref;
@@ -903,7 +1069,9 @@ struct sched_group_capacity {
* CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity
* for a single CPU.
*/
- unsigned int capacity;
+ unsigned long capacity;
+ unsigned long max_capacity; /* Max per-cpu capacity in group */
+ unsigned long min_capacity; /* Min per-CPU capacity in group */
unsigned long next_update;
int imbalance; /* XXX unrelated to capacity but shared group state */
@@ -916,6 +1084,7 @@ struct sched_group {
unsigned int group_weight;
struct sched_group_capacity *sgc;
+ const struct sched_group_energy *sge;
/*
* The CPUs this group covers.
@@ -1224,6 +1393,7 @@ extern const u32 sched_prio_to_wmult[40];
#else
#define ENQUEUE_MIGRATED 0x00
#endif
+#define ENQUEUE_WAKEUP_NEW 0x40
#define RETRY_TASK ((void *)-1UL)
@@ -1247,7 +1417,7 @@ struct sched_class {
*/
struct task_struct * (*pick_next_task) (struct rq *rq,
struct task_struct *prev,
- struct pin_cookie cookie);
+ struct rq_flags *rf);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
@@ -1289,6 +1459,11 @@ struct sched_class {
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_change_group) (struct task_struct *p, int type);
#endif
+#ifdef CONFIG_SCHED_WALT
+ void (*fixup_cumulative_runnable_avg)(struct rq *rq,
+ struct task_struct *task,
+ u64 new_task_load);
+#endif
};
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
@@ -1314,6 +1489,7 @@ extern const struct sched_class idle_sched_class;
#ifdef CONFIG_SMP
+extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc);
extern void update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
@@ -1334,6 +1510,17 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
SCHED_WARN_ON(!rcu_read_lock_held());
return rq->idle_state;
}
+
+static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx)
+{
+ rq->idle_state_idx = idle_state_idx;
+}
+
+static inline int idle_get_state_idx(struct rq *rq)
+{
+ WARN_ON(!rcu_read_lock_held());
+ return rq->idle_state_idx;
+}
#else
static inline void idle_set_state(struct rq *rq,
struct cpuidle_state *idle_state)
@@ -1344,6 +1531,15 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
return NULL;
}
+
+static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx)
+{
+}
+
+static inline int idle_get_state_idx(struct rq *rq)
+{
+ return -1;
+}
#endif
extern void sysrq_sched_debug_show(void);
@@ -1398,7 +1594,7 @@ static inline void sched_update_tick_dependency(struct rq *rq)
static inline void sched_update_tick_dependency(struct rq *rq) { }
#endif
-static inline void add_nr_running(struct rq *rq, unsigned count)
+static inline void __add_nr_running(struct rq *rq, unsigned count)
{
unsigned prev_nr = rq->nr_running;
@@ -1414,13 +1610,50 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
sched_update_tick_dependency(rq);
}
-static inline void sub_nr_running(struct rq *rq, unsigned count)
+static inline void __sub_nr_running(struct rq *rq, unsigned count)
{
rq->nr_running -= count;
/* Check if we still need preemption */
sched_update_tick_dependency(rq);
}
+#ifdef CONFIG_CPU_QUIET
+#define NR_AVE_SCALE(x) ((x) << FSHIFT)
+static inline u64 do_nr_running_integral(struct rq *rq)
+{
+ s64 nr, deltax;
+ u64 nr_running_integral = rq->nr_running_integral;
+
+ deltax = rq->clock_task - rq->nr_last_stamp;
+ nr = NR_AVE_SCALE(rq->nr_running);
+
+ nr_running_integral += nr * deltax;
+
+ return nr_running_integral;
+}
+
+static inline void add_nr_running(struct rq *rq, unsigned count)
+{
+ write_seqcount_begin(&rq->ave_seqcnt);
+ rq->nr_running_integral = do_nr_running_integral(rq);
+ rq->nr_last_stamp = rq->clock_task;
+ __add_nr_running(rq, count);
+ write_seqcount_end(&rq->ave_seqcnt);
+}
+
+static inline void sub_nr_running(struct rq *rq, unsigned count)
+{
+ write_seqcount_begin(&rq->ave_seqcnt);
+ rq->nr_running_integral = do_nr_running_integral(rq);
+ rq->nr_last_stamp = rq->clock_task;
+ __sub_nr_running(rq, count);
+ write_seqcount_end(&rq->ave_seqcnt);
+}
+#else
+#define add_nr_running __add_nr_running
+#define sub_nr_running __sub_nr_running
+#endif
+
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
@@ -1428,8 +1661,6 @@ static inline void rq_last_tick_reset(struct rq *rq)
#endif
}
-extern void update_rq_clock(struct rq *rq);
-
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
@@ -1482,6 +1713,26 @@ unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
}
#endif
+#ifndef arch_scale_max_freq_capacity
+static __always_inline
+unsigned long arch_scale_max_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ return SCHED_CAPACITY_SCALE;
+}
+#endif
+
+#ifndef arch_scale_min_freq_capacity
+static __always_inline
+unsigned long arch_scale_min_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ /*
+ * Multiplied with any capacity value, this scale factor will return
+ * 0, which represents an un-capped state
+ */
+ return 0;
+}
+#endif
+
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1493,43 +1744,95 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
}
#endif
+#ifdef CONFIG_SMP
+static inline unsigned long capacity_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity;
+}
+
+static inline unsigned long capacity_orig_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
+extern unsigned int sysctl_sched_use_walt_cpu_util;
+extern unsigned int walt_ravg_window;
+extern bool walt_disabled;
+
+/*
+ * cpu_util returns the amount of capacity of a CPU that is used by CFS
+ * tasks. The unit of the return value must be the one of capacity so we can
+ * compare the utilization with the capacity of the CPU that is available for
+ * CFS task (ie cpu_capacity).
+ *
+ * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
+ * recent utilization of currently non-runnable tasks on a CPU. It represents
+ * the amount of utilization of a CPU in the range [0..capacity_orig] where
+ * capacity_orig is the cpu_capacity available at the highest frequency
+ * (arch_scale_freq_capacity()).
+ * The utilization of a CPU converges towards a sum equal to or less than the
+ * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
+ * the running time on this CPU scaled by capacity_curr.
+ *
+ * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
+ * higher than capacity_orig because of unfortunate rounding in
+ * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
+ * the average stabilizes with the new running time. We need to check that the
+ * utilization stays within the range of [0..capacity_orig] and cap it if
+ * necessary. Without utilization capping, a group could be seen as overloaded
+ * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
+ * available capacity. We allow utilization to overshoot capacity_curr (but not
+ * capacity_orig) as it useful for predicting the capacity required after task
+ * migrations (scheduler-driven DVFS).
+ */
+static inline unsigned long __cpu_util(int cpu, int delta)
+{
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long capacity = capacity_orig_of(cpu);
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
+ util = div64_u64(cpu_rq(cpu)->cumulative_runnable_avg,
+ walt_ravg_window >> SCHED_CAPACITY_SHIFT);
+#endif
+ delta += util;
+ if (delta < 0)
+ return 0;
+
+ return (delta >= capacity) ? capacity : delta;
+}
+
+static inline unsigned long cpu_util(int cpu)
+{
+ return __cpu_util(cpu, 0);
+}
+
+static inline unsigned long cpu_util_freq(int cpu)
+{
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long capacity = capacity_orig_of(cpu);
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
+ util = div64_u64(cpu_rq(cpu)->prev_runnable_sum,
+ walt_ravg_window >> SCHED_CAPACITY_SHIFT);
+#endif
+ return (util >= capacity) ? capacity : util;
+}
+
+#endif
+
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
- sched_avg_update(rq);
}
#else
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
static inline void sched_avg_update(struct rq *rq) { }
#endif
-struct rq_flags {
- unsigned long flags;
- struct pin_cookie cookie;
-};
-
-struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(rq->lock);
-struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(p->pi_lock)
- __acquires(rq->lock);
-
-static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
- raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
- __releases(rq->lock)
- __releases(p->pi_lock)
-{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
- raw_spin_unlock(&rq->lock);
- raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-}
+extern struct rq *lock_rq_of(struct task_struct *p, struct rq_flags *flags);
+extern void unlock_rq_of(struct rq *rq, struct task_struct *p, struct rq_flags *flags);
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
@@ -1603,7 +1906,8 @@ static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
- raw_spin_unlock(&busiest->lock);
+ if (this_rq != busiest)
+ raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
@@ -1824,6 +2128,17 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
+#ifdef CONFIG_SCHED_WALT
+
+static inline bool
+walt_task_in_cum_window_demand(struct rq *rq, struct task_struct *p)
+{
+ return cpu_of(rq) == task_cpu(p) &&
+ (p->on_rq || p->last_sleep_ts >= rq->window_start);
+}
+
+#endif /* CONFIG_SCHED_WALT */
+
#ifdef arch_scale_freq_capacity
#ifndef arch_scale_freq_invariant
#define arch_scale_freq_invariant() (true)
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 87e2c9f..6d74a7c 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -12,6 +12,28 @@
*/
#define SCHEDSTAT_VERSION 15
+#ifdef CONFIG_SMP
+static inline void show_easstat(struct seq_file *seq, struct eas_stats *stats)
+{
+ /* eas-specific runqueue stats */
+ seq_printf(seq, "eas %llu %llu %llu %llu %llu %llu ",
+ stats->sis_attempts, stats->sis_idle, stats->sis_cache_affine,
+ stats->sis_suff_cap, stats->sis_idle_cpu, stats->sis_count);
+
+ seq_printf(seq, "%llu %llu %llu %llu %llu %llu %llu ",
+ stats->secb_attempts, stats->secb_sync, stats->secb_idle_bt,
+ stats->secb_insuff_cap, stats->secb_no_nrg_sav,
+ stats->secb_nrg_sav, stats->secb_count);
+
+ seq_printf(seq, "%llu %llu %llu %llu %llu ",
+ stats->fbt_attempts, stats->fbt_no_cpu, stats->fbt_no_sd,
+ stats->fbt_pref_idle, stats->fbt_count);
+
+ seq_printf(seq, "%llu %llu\n",
+ stats->cas_attempts, stats->cas_count);
+}
+#endif
+
static int show_schedstat(struct seq_file *seq, void *v)
{
int cpu;
@@ -40,6 +62,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
seq_printf(seq, "\n");
#ifdef CONFIG_SMP
+ show_easstat(seq, &rq->eas_stats);
+
/* domain-specific stats */
rcu_read_lock();
for_each_domain(cpu, sd) {
@@ -66,6 +90,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
sd->ttwu_wake_remote, sd->ttwu_move_affine,
sd->ttwu_move_balance);
+
+ show_easstat(seq, &sd->eas_stats);
}
rcu_read_unlock();
#endif
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 34659a8..3c0d8f1 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -54,6 +54,92 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
#define schedstat_val_or_zero(var) 0
#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_PSI
+/*
+ * PSI tracks state that persists across sleeps, such as iowaits and
+ * memory stalls. As a result, it has to distinguish between sleeps,
+ * where a task's runnable state changes, and requeues, where a task
+ * and its state are being moved between CPUs and runqueues.
+ */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup)
+{
+ int clear = 0, set = TSK_RUNNING;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (!wakeup || p->sched_psi_wake_requeue) {
+ if (p->flags & PF_MEMSTALL)
+ set |= TSK_MEMSTALL;
+ if (p->sched_psi_wake_requeue)
+ p->sched_psi_wake_requeue = 0;
+ } else {
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_dequeue(struct task_struct *p, bool sleep)
+{
+ int clear = TSK_RUNNING, set = 0;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (!sleep) {
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+ } else {
+ if (p->in_iowait)
+ set |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_ttwu_dequeue(struct task_struct *p)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+ /*
+ * Is the task being migrated during a wakeup? Make sure to
+ * deregister its sleep-persistent psi states from the old
+ * queue, and let psi_enqueue() know it has to requeue.
+ */
+ if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+ struct rq_flags rf;
+ struct rq *rq;
+ int clear = 0;
+
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+
+ rq = __task_rq_lock(p, &rf);
+ psi_task_change(p, clear, 0);
+ p->sched_psi_wake_requeue = 1;
+ __task_rq_unlock(rq, &rf);
+ }
+}
+
+static inline void psi_task_tick(struct rq *rq)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (unlikely(rq->curr->flags & PF_MEMSTALL))
+ psi_memstall_tick(rq->curr, cpu_of(rq));
+}
+#else /* CONFIG_PSI */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
+static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
+static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_task_tick(struct rq *rq) {}
+#endif /* CONFIG_PSI */
+
#ifdef CONFIG_SCHED_INFO
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 604297a..0e8a759 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -1,4 +1,5 @@
#include "sched.h"
+#include "walt.h"
/*
* stop-task scheduling class.
@@ -24,7 +25,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
}
static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *stop = rq->stop;
@@ -42,12 +43,14 @@ static void
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
add_nr_running(rq, 1);
+ walt_inc_cumulative_runnable_avg(rq, p);
}
static void
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
sub_nr_running(rq, 1);
+ walt_dec_cumulative_runnable_avg(rq, p);
}
static void yield_task_stop(struct rq *rq)
@@ -134,4 +137,7 @@ const struct sched_class stop_sched_class = {
.prio_changed = prio_changed_stop,
.switched_to = switched_to_stop,
.update_curr = update_curr_stop,
+#ifdef CONFIG_SCHED_WALT
+ .fixup_cumulative_runnable_avg = walt_fixup_cumulative_runnable_avg,
+#endif
};
diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
new file mode 100644
index 0000000..78b99bb
--- /dev/null
+++ b/kernel/sched/tune.c
@@ -0,0 +1,1027 @@
+#include <linux/cgroup.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+
+#include <trace/events/sched.h>
+
+#include "sched.h"
+#include "tune.h"
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+bool schedtune_initialized = false;
+#endif
+
+unsigned int sysctl_sched_cfs_boost __read_mostly;
+
+extern struct reciprocal_value schedtune_spc_rdiv;
+struct target_nrg schedtune_target_nrg;
+
+/* Performance Boost region (B) threshold params */
+static int perf_boost_idx;
+
+/* Performance Constraint region (C) threshold params */
+static int perf_constrain_idx;
+
+/**
+ * Performance-Energy (P-E) Space thresholds constants
+ */
+struct threshold_params {
+ int nrg_gain;
+ int cap_gain;
+};
+
+/*
+ * System specific P-E space thresholds constants
+ */
+static struct threshold_params
+threshold_gains[] = {
+ { 0, 5 }, /* < 10% */
+ { 1, 5 }, /* < 20% */
+ { 2, 5 }, /* < 30% */
+ { 3, 5 }, /* < 40% */
+ { 4, 5 }, /* < 50% */
+ { 5, 4 }, /* < 60% */
+ { 5, 3 }, /* < 70% */
+ { 5, 2 }, /* < 80% */
+ { 5, 1 }, /* < 90% */
+ { 5, 0 } /* <= 100% */
+};
+
+static int
+__schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ int perf_boost_idx, int perf_constrain_idx)
+{
+ int payoff = -INT_MAX;
+ int gain_idx = -1;
+
+ /* Performance Boost (B) region */
+ if (nrg_delta >= 0 && cap_delta > 0)
+ gain_idx = perf_boost_idx;
+ /* Performance Constraint (C) region */
+ else if (nrg_delta < 0 && cap_delta <= 0)
+ gain_idx = perf_constrain_idx;
+
+ /* Default: reject schedule candidate */
+ if (gain_idx == -1)
+ return payoff;
+
+ /*
+ * Evaluate "Performance Boost" vs "Energy Increase"
+ *
+ * - Performance Boost (B) region
+ *
+ * Condition: nrg_delta > 0 && cap_delta > 0
+ * Payoff criteria:
+ * cap_gain / nrg_gain < cap_delta / nrg_delta =
+ * cap_gain * nrg_delta < cap_delta * nrg_gain
+ * Note that since both nrg_gain and nrg_delta are positive, the
+ * inequality does not change. Thus:
+ *
+ * payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)
+ *
+ * - Performance Constraint (C) region
+ *
+ * Condition: nrg_delta < 0 && cap_delta < 0
+ * payoff criteria:
+ * cap_gain / nrg_gain > cap_delta / nrg_delta =
+ * cap_gain * nrg_delta < cap_delta * nrg_gain
+ * Note that since nrg_gain > 0 while nrg_delta < 0, the
+ * inequality change. Thus:
+ *
+ * payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)
+ *
+ * This means that, in case of same positive defined {cap,nrg}_gain
+ * for both the B and C regions, we can use the same payoff formula
+ * where a positive value represents the accept condition.
+ */
+ payoff = cap_delta * threshold_gains[gain_idx].nrg_gain;
+ payoff -= nrg_delta * threshold_gains[gain_idx].cap_gain;
+
+ return payoff;
+}
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+
+/*
+ * EAS scheduler tunables for task groups.
+ *
+ * When CGroup support is enabled, we have to synchronize two different
+ * paths:
+ * - slow path: where CGroups are created/updated/removed
+ * - fast path: where tasks in a CGroups are accounted
+ *
+ * The slow path tracks (a limited number of) CGroups and maps each on a
+ * "boost_group" index. The fastpath accounts tasks currently RUNNABLE on each
+ * "boost_group".
+ *
+ * Once a new CGroup is created, a boost group idx is assigned and the
+ * corresponding "boost_group" marked as valid on each CPU.
+ * Once a CGroup is release, the corresponding "boost_group" is marked as
+ * invalid on each CPU. The CPU boost value (boost_max) is aggregated by
+ * considering only valid boost_groups with a non null tasks counter.
+ *
+ * .:: Locking strategy
+ *
+ * The fast path uses a spin lock for each CPU boost_group which protects the
+ * tasks counter.
+ *
+ * The "valid" and "boost" values of each CPU boost_group is instead
+ * protected by the RCU lock provided by the CGroups callbacks. Thus, only the
+ * slow path can access and modify the boost_group attribtues of each CPU.
+ * The fast path will catch up the most updated values at the next scheduling
+ * event (i.e. enqueue/dequeue).
+ *
+ * |
+ * SLOW PATH | FAST PATH
+ * CGroup add/update/remove | Scheduler enqueue/dequeue events
+ * |
+ * |
+ * | DEFINE_PER_CPU(struct boost_groups)
+ * | +--------------+----+---+----+----+
+ * | | idle | | | | |
+ * | | boost_max | | | | |
+ * | +---->lock | | | | |
+ * struct schedtune allocated_groups | | | group[ ] | | | | |
+ * +------------------------------+ +-------+ | | +--+---------+-+----+---+----+----+
+ * | idx | | | | | | valid |
+ * | boots / prefer_idle | | | | | | boost |
+ * | perf_{boost/constraints}_idx | <---------+(*) | | | | tasks | <------------+
+ * | css | +-------+ | | +---------+ |
+ * +-+----------------------------+ | | | | | | |
+ * ^ | | | | | | |
+ * | +-------+ | | +---------+ |
+ * | | | | | | | |
+ * | | | | | | | |
+ * | +-------+ | | +---------+ |
+ * | zmalloc | | | | | | |
+ * | | | | | | | |
+ * | +-------+ | | +---------+ |
+ * + BOOSTGROUPS_COUNT | | BOOSTGROUPS_COUNT |
+ * schedtune_boostgroup_init() | + |
+ * | schedtune_{en,de}queue_task() |
+ * | +
+ * | schedtune_tasks_update()
+ * |
+ */
+
+/* SchdTune tunables for a group of tasks */
+struct schedtune {
+ /* SchedTune CGroup subsystem */
+ struct cgroup_subsys_state css;
+
+ /* Boost group allocated ID */
+ int idx;
+
+ /* Boost value for tasks on that SchedTune CGroup */
+ int boost;
+
+ /* Performance Boost (B) region threshold params */
+ int perf_boost_idx;
+
+ /* Performance Constraint (C) region threshold params */
+ int perf_constrain_idx;
+
+ /* Hint to bias scheduling of tasks on that SchedTune CGroup
+ * towards idle CPUs */
+ int prefer_idle;
+};
+
+static inline struct schedtune *css_st(struct cgroup_subsys_state *css)
+{
+ return css ? container_of(css, struct schedtune, css) : NULL;
+}
+
+static inline struct schedtune *task_schedtune(struct task_struct *tsk)
+{
+ return css_st(task_css(tsk, schedtune_cgrp_id));
+}
+
+static inline struct schedtune *parent_st(struct schedtune *st)
+{
+ return css_st(st->css.parent);
+}
+
+/*
+ * SchedTune root control group
+ * The root control group is used to defined a system-wide boosting tuning,
+ * which is applied to all tasks in the system.
+ * Task specific boost tuning could be specified by creating and
+ * configuring a child control group under the root one.
+ * By default, system-wide boosting is disabled, i.e. no boosting is applied
+ * to tasks which are not into a child control group.
+ */
+static struct schedtune
+root_schedtune = {
+ .boost = 0,
+ .perf_boost_idx = 0,
+ .perf_constrain_idx = 0,
+ .prefer_idle = 0,
+};
+
+int
+schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task)
+{
+ struct schedtune *ct;
+ int perf_boost_idx;
+ int perf_constrain_idx;
+
+ /* Optimal (O) region */
+ if (nrg_delta < 0 && cap_delta > 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, 1, 0);
+ return INT_MAX;
+ }
+
+ /* Suboptimal (S) region */
+ if (nrg_delta > 0 && cap_delta < 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, -1, 5);
+ return -INT_MAX;
+ }
+
+ /* Get task specific perf Boost/Constraints indexes */
+ rcu_read_lock();
+ ct = task_schedtune(task);
+ perf_boost_idx = ct->perf_boost_idx;
+ perf_constrain_idx = ct->perf_constrain_idx;
+ rcu_read_unlock();
+
+ return __schedtune_accept_deltas(nrg_delta, cap_delta,
+ perf_boost_idx, perf_constrain_idx);
+}
+
+/*
+ * Maximum number of boost groups to support
+ * When per-task boosting is used we still allow only limited number of
+ * boost groups for two main reasons:
+ * 1. on a real system we usually have only few classes of workloads which
+ * make sense to boost with different values (e.g. background vs foreground
+ * tasks, interactive vs low-priority tasks)
+ * 2. a limited number allows for a simpler and more memory/time efficient
+ * implementation especially for the computation of the per-CPU boost
+ * value
+ */
+#define BOOSTGROUPS_COUNT 5
+
+/* Array of configured boostgroups */
+static struct schedtune *allocated_group[BOOSTGROUPS_COUNT] = {
+ &root_schedtune,
+ NULL,
+};
+
+/* SchedTune boost groups
+ * Keep track of all the boost groups which impact on CPU, for example when a
+ * CPU has two RUNNABLE tasks belonging to two different boost groups and thus
+ * likely with different boost values.
+ * Since on each system we expect only a limited number of boost groups, here
+ * we use a simple array to keep track of the metrics required to compute the
+ * maximum per-CPU boosting value.
+ */
+struct boost_groups {
+ /* Maximum boost value for all RUNNABLE tasks on a CPU */
+ int boost_max;
+ struct {
+ /* True when this boost group maps an actual cgroup */
+ bool valid;
+ /* The boost for tasks on that boost group */
+ int boost;
+ /* Count of RUNNABLE tasks on that boost group */
+ unsigned tasks;
+ } group[BOOSTGROUPS_COUNT];
+ /* CPU's boost group locking */
+ raw_spinlock_t lock;
+};
+
+/* Boost groups affecting each CPU in the system */
+DEFINE_PER_CPU(struct boost_groups, cpu_boost_groups);
+
+static void
+schedtune_cpu_update(int cpu)
+{
+ struct boost_groups *bg;
+ int boost_max;
+ int idx;
+
+ bg = &per_cpu(cpu_boost_groups, cpu);
+
+ /* The root boost group is always active */
+ boost_max = bg->group[0].boost;
+ for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx) {
+
+ /* Ignore non boostgroups not mapping a cgroup */
+ if (!bg->group[idx].valid)
+ continue;
+
+ /*
+ * A boost group affects a CPU only if it has
+ * RUNNABLE tasks on that CPU
+ */
+ if (bg->group[idx].tasks == 0)
+ continue;
+
+ boost_max = max(boost_max, bg->group[idx].boost);
+ }
+
+ /* Ensures boost_max is non-negative when all cgroup boost values
+ * are neagtive. Avoids under-accounting of cpu capacity which may cause
+ * task stacking and frequency spikes.*/
+ boost_max = max(boost_max, 0);
+ bg->boost_max = boost_max;
+}
+
+static int
+schedtune_boostgroup_update(int idx, int boost)
+{
+ struct boost_groups *bg;
+ int cur_boost_max;
+ int old_boost;
+ int cpu;
+
+ /* Update per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+
+ /* CGroups are never associated to non active cgroups */
+ BUG_ON(!bg->group[idx].valid);
+
+ /*
+ * Keep track of current boost values to compute the per CPU
+ * maximum only when it has been affected by the new value of
+ * the updated boost group
+ */
+ cur_boost_max = bg->boost_max;
+ old_boost = bg->group[idx].boost;
+
+ /* Update the boost value of this boost group */
+ bg->group[idx].boost = boost;
+
+ /* Check if this update increase current max */
+ if (boost > cur_boost_max && bg->group[idx].tasks) {
+ bg->boost_max = boost;
+ trace_sched_tune_boostgroup_update(cpu, 1, bg->boost_max);
+ continue;
+ }
+
+ /* Check if this update has decreased current max */
+ if (cur_boost_max == old_boost && old_boost > boost) {
+ schedtune_cpu_update(cpu);
+ trace_sched_tune_boostgroup_update(cpu, -1, bg->boost_max);
+ continue;
+ }
+
+ trace_sched_tune_boostgroup_update(cpu, 0, bg->boost_max);
+ }
+
+ return 0;
+}
+
+#define ENQUEUE_TASK 1
+#define DEQUEUE_TASK -1
+
+static inline void
+schedtune_tasks_update(struct task_struct *p, int cpu, int idx, int task_count)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ int tasks = bg->group[idx].tasks + task_count;
+
+ /* Update boosted tasks count while avoiding to make it negative */
+ bg->group[idx].tasks = max(0, tasks);
+
+ trace_sched_tune_tasks_update(p, cpu, tasks, idx,
+ bg->group[idx].boost, bg->boost_max);
+
+ /* Boost group activation or deactivation on that RQ */
+ if (tasks == 1 || tasks == 0)
+ schedtune_cpu_update(cpu);
+}
+
+/*
+ * NOTE: This function must be called while holding the lock on the CPU RQ
+ */
+void schedtune_enqueue_task(struct task_struct *p, int cpu)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ unsigned long irq_flags;
+ struct schedtune *st;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ /*
+ * When a task is marked PF_EXITING by do_exit() it's going to be
+ * dequeued and enqueued multiple times in the exit path.
+ * Thus we avoid any further update, since we do not want to change
+ * CPU boosting while the task is exiting.
+ */
+ if (p->flags & PF_EXITING)
+ return;
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions for example on
+ * do_exit()::cgroup_exit() and task migration.
+ */
+ raw_spin_lock_irqsave(&bg->lock, irq_flags);
+ rcu_read_lock();
+
+ st = task_schedtune(p);
+ idx = st->idx;
+
+ schedtune_tasks_update(p, cpu, idx, ENQUEUE_TASK);
+
+ rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
+}
+
+int schedtune_can_attach(struct cgroup_taskset *tset)
+{
+ struct task_struct *task;
+ struct cgroup_subsys_state *css;
+ struct boost_groups *bg;
+ struct rq_flags irq_flags;
+ unsigned int cpu;
+ struct rq *rq;
+ int src_bg; /* Source boost group index */
+ int dst_bg; /* Destination boost group index */
+ int tasks;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+
+ cgroup_taskset_for_each(task, css, tset) {
+
+ /*
+ * Lock the CPU's RQ the task is enqueued to avoid race
+ * conditions with migration code while the task is being
+ * accounted
+ */
+ rq = lock_rq_of(task, &irq_flags);
+
+ if (!task->on_rq) {
+ unlock_rq_of(rq, task, &irq_flags);
+ continue;
+ }
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions on...
+ */
+ cpu = cpu_of(rq);
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ raw_spin_lock(&bg->lock);
+
+ dst_bg = css_st(css)->idx;
+ src_bg = task_schedtune(task)->idx;
+
+ /*
+ * Current task is not changing boostgroup, which can
+ * happen when the new hierarchy is in use.
+ */
+ if (unlikely(dst_bg == src_bg)) {
+ raw_spin_unlock(&bg->lock);
+ unlock_rq_of(rq, task, &irq_flags);
+ continue;
+ }
+
+ /*
+ * This is the case of a RUNNABLE task which is switching its
+ * current boost group.
+ */
+
+ /* Move task from src to dst boost group */
+ tasks = bg->group[src_bg].tasks - 1;
+ bg->group[src_bg].tasks = max(0, tasks);
+ bg->group[dst_bg].tasks += 1;
+
+ raw_spin_unlock(&bg->lock);
+ unlock_rq_of(rq, task, &irq_flags);
+
+ /* Update CPU boost group */
+ if (bg->group[src_bg].tasks == 0 || bg->group[dst_bg].tasks == 1)
+ schedtune_cpu_update(task_cpu(task));
+
+ }
+
+ return 0;
+}
+
+void schedtune_cancel_attach(struct cgroup_taskset *tset)
+{
+ /* This can happen only if SchedTune controller is mounted with
+ * other hierarchies ane one of them fails. Since usually SchedTune is
+ * mouted on its own hierarcy, for the time being we do not implement
+ * a proper rollback mechanism */
+ WARN(1, "SchedTune cancel attach not implemented");
+}
+
+/*
+ * NOTE: This function must be called while holding the lock on the CPU RQ
+ */
+void schedtune_dequeue_task(struct task_struct *p, int cpu)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ unsigned long irq_flags;
+ struct schedtune *st;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ /*
+ * When a task is marked PF_EXITING by do_exit() it's going to be
+ * dequeued and enqueued multiple times in the exit path.
+ * Thus we avoid any further update, since we do not want to change
+ * CPU boosting while the task is exiting.
+ * The last dequeue is already enforce by the do_exit() code path
+ * via schedtune_exit_task().
+ */
+ if (p->flags & PF_EXITING)
+ return;
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions on...
+ */
+ raw_spin_lock_irqsave(&bg->lock, irq_flags);
+ rcu_read_lock();
+
+ st = task_schedtune(p);
+ idx = st->idx;
+
+ schedtune_tasks_update(p, cpu, idx, DEQUEUE_TASK);
+
+ rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
+}
+
+void schedtune_exit_task(struct task_struct *tsk)
+{
+ struct schedtune *st;
+ struct rq_flags irq_flags;
+ unsigned int cpu;
+ struct rq *rq;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ rq = lock_rq_of(tsk, &irq_flags);
+ rcu_read_lock();
+
+ cpu = cpu_of(rq);
+ st = task_schedtune(tsk);
+ idx = st->idx;
+ schedtune_tasks_update(tsk, cpu, idx, DEQUEUE_TASK);
+
+ rcu_read_unlock();
+ unlock_rq_of(rq, tsk, &irq_flags);
+}
+
+int schedtune_cpu_boost(int cpu)
+{
+ struct boost_groups *bg;
+
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ return bg->boost_max;
+}
+
+int schedtune_task_boost(struct task_struct *p)
+{
+ struct schedtune *st;
+ int task_boost;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+ /* Get task boost value */
+ rcu_read_lock();
+ st = task_schedtune(p);
+ task_boost = st->boost;
+ rcu_read_unlock();
+
+ return task_boost;
+}
+
+int schedtune_prefer_idle(struct task_struct *p)
+{
+ struct schedtune *st;
+ int prefer_idle;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+ /* Get prefer_idle value */
+ rcu_read_lock();
+ st = task_schedtune(p);
+ prefer_idle = st->prefer_idle;
+ rcu_read_unlock();
+
+ return prefer_idle;
+}
+
+static u64
+prefer_idle_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ struct schedtune *st = css_st(css);
+
+ return st->prefer_idle;
+}
+
+static int
+prefer_idle_write(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 prefer_idle)
+{
+ struct schedtune *st = css_st(css);
+ st->prefer_idle = !!prefer_idle;
+
+ return 0;
+}
+
+static s64
+boost_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ struct schedtune *st = css_st(css);
+
+ return st->boost;
+}
+
+static int
+boost_write(struct cgroup_subsys_state *css, struct cftype *cft,
+ s64 boost)
+{
+ struct schedtune *st = css_st(css);
+ unsigned threshold_idx;
+ int boost_pct;
+
+ if (boost < -100 || boost > 100)
+ return -EINVAL;
+ boost_pct = boost;
+
+ /*
+ * Update threshold params for Performance Boost (B)
+ * and Performance Constraint (C) regions.
+ * The current implementatio uses the same cuts for both
+ * B and C regions.
+ */
+ threshold_idx = clamp(boost_pct, 0, 99) / 10;
+ st->perf_boost_idx = threshold_idx;
+ st->perf_constrain_idx = threshold_idx;
+
+ st->boost = boost;
+ if (css == &root_schedtune.css) {
+ sysctl_sched_cfs_boost = boost;
+ perf_boost_idx = threshold_idx;
+ perf_constrain_idx = threshold_idx;
+ }
+
+ /* Update CPU boost */
+ schedtune_boostgroup_update(st->idx, st->boost);
+
+ trace_sched_tune_config(st->boost);
+
+ return 0;
+}
+
+static struct cftype files[] = {
+ {
+ .name = "boost",
+ .read_s64 = boost_read,
+ .write_s64 = boost_write,
+ },
+ {
+ .name = "prefer_idle",
+ .read_u64 = prefer_idle_read,
+ .write_u64 = prefer_idle_write,
+ },
+ { } /* terminate */
+};
+
+static void
+schedtune_boostgroup_init(struct schedtune *st, int idx)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Initialize per CPUs boost group support */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ bg->group[idx].boost = 0;
+ bg->group[idx].valid = true;
+ }
+
+ /* Keep track of allocated boost groups */
+ allocated_group[idx] = st;
+ st->idx = idx;
+}
+
+static struct cgroup_subsys_state *
+schedtune_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+ struct schedtune *st;
+ int idx;
+
+ if (!parent_css)
+ return &root_schedtune.css;
+
+ /* Allow only single level hierachies */
+ if (parent_css != &root_schedtune.css) {
+ pr_err("Nested SchedTune boosting groups not allowed\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ /* Allow only a limited number of boosting groups */
+ for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx)
+ if (!allocated_group[idx])
+ break;
+ if (idx == BOOSTGROUPS_COUNT) {
+ pr_err("Trying to create more than %d SchedTune boosting groups\n",
+ BOOSTGROUPS_COUNT);
+ return ERR_PTR(-ENOSPC);
+ }
+
+ st = kzalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ goto out;
+
+ /* Initialize per CPUs boost group support */
+ schedtune_boostgroup_init(st, idx);
+
+ return &st->css;
+
+out:
+ return ERR_PTR(-ENOMEM);
+}
+
+static void
+schedtune_boostgroup_release(struct schedtune *st)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Reset per CPUs boost group support */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ bg->group[st->idx].valid = false;
+ bg->group[st->idx].boost = 0;
+ }
+
+ /* Keep track of allocated boost groups */
+ allocated_group[st->idx] = NULL;
+}
+
+static void
+schedtune_css_free(struct cgroup_subsys_state *css)
+{
+ struct schedtune *st = css_st(css);
+
+ /* Release per CPUs boost group support */
+ schedtune_boostgroup_release(st);
+ kfree(st);
+}
+
+struct cgroup_subsys schedtune_cgrp_subsys = {
+ .css_alloc = schedtune_css_alloc,
+ .css_free = schedtune_css_free,
+ .can_attach = schedtune_can_attach,
+ .cancel_attach = schedtune_cancel_attach,
+ .legacy_cftypes = files,
+ .early_init = 1,
+};
+
+static inline void
+schedtune_init_cgroups(void)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Initialize the per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ memset(bg, 0, sizeof(struct boost_groups));
+ bg->group[0].valid = true;
+ raw_spin_lock_init(&bg->lock);
+ }
+
+ pr_info("schedtune: configured to support %d boost groups\n",
+ BOOSTGROUPS_COUNT);
+
+ schedtune_initialized = true;
+}
+
+#else /* CONFIG_CGROUP_SCHEDTUNE */
+
+int
+schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task)
+{
+ /* Optimal (O) region */
+ if (nrg_delta < 0 && cap_delta > 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, 1, 0);
+ return INT_MAX;
+ }
+
+ /* Suboptimal (S) region */
+ if (nrg_delta > 0 && cap_delta < 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, -1, 5);
+ return -INT_MAX;
+ }
+
+ return __schedtune_accept_deltas(nrg_delta, cap_delta,
+ perf_boost_idx, perf_constrain_idx);
+}
+
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+int
+sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ unsigned threshold_idx;
+ int boost_pct;
+
+ if (ret || !write)
+ return ret;
+
+ if (sysctl_sched_cfs_boost < -100 || sysctl_sched_cfs_boost > 100)
+ return -EINVAL;
+ boost_pct = sysctl_sched_cfs_boost;
+
+ /*
+ * Update threshold params for Performance Boost (B)
+ * and Performance Constraint (C) regions.
+ * The current implementatio uses the same cuts for both
+ * B and C regions.
+ */
+ threshold_idx = clamp(boost_pct, 0, 99) / 10;
+ perf_boost_idx = threshold_idx;
+ perf_constrain_idx = threshold_idx;
+
+ return 0;
+}
+
+#ifdef CONFIG_SCHED_DEBUG
+static void
+schedtune_test_nrg(unsigned long delta_pwr)
+{
+ unsigned long test_delta_pwr;
+ unsigned long test_norm_pwr;
+ int idx;
+
+ /*
+ * Check normalization constants using some constant system
+ * energy values
+ */
+ pr_info("schedtune: verify normalization constants...\n");
+ for (idx = 0; idx < 6; ++idx) {
+ test_delta_pwr = delta_pwr >> idx;
+
+ /* Normalize on max energy for target platform */
+ test_norm_pwr = reciprocal_divide(
+ test_delta_pwr << SCHED_CAPACITY_SHIFT,
+ schedtune_target_nrg.rdiv);
+
+ pr_info("schedtune: max_pwr/2^%d: %4lu => norm_pwr: %5lu\n",
+ idx, test_delta_pwr, test_norm_pwr);
+ }
+}
+#else
+#define schedtune_test_nrg(delta_pwr)
+#endif
+
+/*
+ * Compute the min/max power consumption of a cluster and all its CPUs
+ */
+static void
+schedtune_add_cluster_nrg(
+ struct sched_domain *sd,
+ struct sched_group *sg,
+ struct target_nrg *ste)
+{
+ struct sched_domain *sd2;
+ struct sched_group *sg2;
+
+ struct cpumask *cluster_cpus;
+ char str[32];
+
+ unsigned long min_pwr;
+ unsigned long max_pwr;
+ int cpu;
+
+ /* Get Cluster energy using EM data for the first CPU */
+ cluster_cpus = sched_group_cpus(sg);
+ snprintf(str, 32, "CLUSTER[%*pbl]",
+ cpumask_pr_args(cluster_cpus));
+
+ min_pwr = sg->sge->idle_states[sg->sge->nr_idle_states - 1].power;
+ max_pwr = sg->sge->cap_states[sg->sge->nr_cap_states - 1].power;
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ str, min_pwr, max_pwr);
+
+ /*
+ * Keep track of this cluster's energy in the computation of the
+ * overall system energy
+ */
+ ste->min_power += min_pwr;
+ ste->max_power += max_pwr;
+
+ /* Get CPU energy using EM data for each CPU in the group */
+ for_each_cpu(cpu, cluster_cpus) {
+ /* Get a SD view for the specific CPU */
+ for_each_domain(cpu, sd2) {
+ /* Get the CPU group */
+ sg2 = sd2->groups;
+ min_pwr = sg2->sge->idle_states[sg2->sge->nr_idle_states - 1].power;
+ max_pwr = sg2->sge->cap_states[sg2->sge->nr_cap_states - 1].power;
+
+ ste->min_power += min_pwr;
+ ste->max_power += max_pwr;
+
+ snprintf(str, 32, "CPU[%d]", cpu);
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ str, min_pwr, max_pwr);
+
+ /*
+ * Assume we have EM data only at the CPU and
+ * the upper CLUSTER level
+ */
+ BUG_ON(!cpumask_equal(
+ sched_group_cpus(sg),
+ sched_group_cpus(sd2->parent->groups)
+ ));
+ break;
+ }
+ }
+}
+
+/*
+ * Initialize the constants required to compute normalized energy.
+ * The values of these constants depends on the EM data for the specific
+ * target system and topology.
+ * Thus, this function is expected to be called by the code
+ * that bind the EM to the topology information.
+ */
+static int
+schedtune_init(void)
+{
+ struct target_nrg *ste = &schedtune_target_nrg;
+ unsigned long delta_pwr = 0;
+ struct sched_domain *sd;
+ struct sched_group *sg;
+
+ pr_info("schedtune: init normalization constants...\n");
+ ste->max_power = 0;
+ ste->min_power = 0;
+
+ rcu_read_lock();
+
+ /*
+ * When EAS is in use, we always have a pointer to the highest SD
+ * which provides EM data.
+ */
+ sd = rcu_dereference(per_cpu(sd_ea, cpumask_first(cpu_online_mask)));
+ if (!sd) {
+ pr_info("schedtune: no energy model data\n");
+ goto nodata;
+ }
+
+ sg = sd->groups;
+ do {
+ schedtune_add_cluster_nrg(sd, sg, ste);
+ } while (sg = sg->next, sg != sd->groups);
+
+ rcu_read_unlock();
+
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ "SYSTEM", ste->min_power, ste->max_power);
+
+ /* Compute normalization constants */
+ delta_pwr = ste->max_power - ste->min_power;
+ ste->rdiv = reciprocal_value(delta_pwr);
+ pr_info("schedtune: using normalization constants mul: %u sh1: %u sh2: %u\n",
+ ste->rdiv.m, ste->rdiv.sh1, ste->rdiv.sh2);
+
+ schedtune_test_nrg(delta_pwr);
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ schedtune_init_cgroups();
+#else
+ pr_info("schedtune: configured to support global boosting only\n");
+#endif
+
+ schedtune_spc_rdiv = reciprocal_value(100);
+
+ return 0;
+
+nodata:
+ pr_warning("schedtune: disabled!\n");
+ rcu_read_unlock();
+ return -EINVAL;
+}
+postcore_initcall(schedtune_init);
diff --git a/kernel/sched/tune.h b/kernel/sched/tune.h
new file mode 100644
index 0000000..4f64417
--- /dev/null
+++ b/kernel/sched/tune.h
@@ -0,0 +1,55 @@
+
+#ifdef CONFIG_SCHED_TUNE
+
+#include <linux/reciprocal_div.h>
+
+/*
+ * System energy normalization constants
+ */
+struct target_nrg {
+ unsigned long min_power;
+ unsigned long max_power;
+ struct reciprocal_value rdiv;
+};
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+
+int schedtune_cpu_boost(int cpu);
+int schedtune_task_boost(struct task_struct *tsk);
+
+int schedtune_prefer_idle(struct task_struct *tsk);
+
+void schedtune_exit_task(struct task_struct *tsk);
+
+void schedtune_enqueue_task(struct task_struct *p, int cpu);
+void schedtune_dequeue_task(struct task_struct *p, int cpu);
+
+#else /* CONFIG_CGROUP_SCHEDTUNE */
+
+#define schedtune_cpu_boost(cpu) get_sysctl_sched_cfs_boost()
+#define schedtune_task_boost(tsk) get_sysctl_sched_cfs_boost()
+
+#define schedtune_exit_task(task) do { } while (0)
+
+#define schedtune_enqueue_task(task, cpu) do { } while (0)
+#define schedtune_dequeue_task(task, cpu) do { } while (0)
+
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+int schedtune_normalize_energy(int energy);
+int schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task);
+
+#else /* CONFIG_SCHED_TUNE */
+
+#define schedtune_cpu_boost(cpu) 0
+#define schedtune_task_boost(tsk) 0
+
+#define schedtune_exit_task(task) do { } while (0)
+
+#define schedtune_enqueue_task(task, cpu) do { } while (0)
+#define schedtune_dequeue_task(task, cpu) do { } while (0)
+
+#define schedtune_accept_deltas(nrg_delta, cap_delta, task) nrg_delta
+
+#endif /* CONFIG_SCHED_TUNE */
diff --git a/kernel/sched/walt.c b/kernel/sched/walt.c
new file mode 100644
index 0000000..5c7a9b4
--- /dev/null
+++ b/kernel/sched/walt.c
@@ -0,0 +1,904 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ *
+ * Window Assisted Load Tracking (WALT) implementation credits:
+ * Srivatsa Vaddagiri, Steve Muckle, Syed Rameez Mustafa, Joonwoo Park,
+ * Pavan Kumar Kondeti, Olav Haugan
+ *
+ * 2016-03-06: Integration with EAS/refactoring by Vikram Mulukutla
+ * and Todd Kjos
+ */
+
+#include <linux/acpi.h>
+#include <linux/syscore_ops.h>
+#include <trace/events/sched.h>
+#include "sched.h"
+#include "walt.h"
+
+#define WINDOW_STATS_RECENT 0
+#define WINDOW_STATS_MAX 1
+#define WINDOW_STATS_MAX_RECENT_AVG 2
+#define WINDOW_STATS_AVG 3
+#define WINDOW_STATS_INVALID_POLICY 4
+
+#define EXITING_TASK_MARKER 0xdeaddead
+
+static __read_mostly unsigned int walt_ravg_hist_size = 5;
+static __read_mostly unsigned int walt_window_stats_policy =
+ WINDOW_STATS_MAX_RECENT_AVG;
+static __read_mostly unsigned int walt_account_wait_time = 1;
+static __read_mostly unsigned int walt_freq_account_wait_time = 0;
+static __read_mostly unsigned int walt_io_is_busy = 0;
+
+unsigned int sysctl_sched_walt_init_task_load_pct = 15;
+
+/* true -> use PELT based load stats, false -> use window-based load stats */
+bool __read_mostly walt_disabled = false;
+
+/*
+ * Window size (in ns). Adjust for the tick size so that the window
+ * rollover occurs just before the tick boundary.
+ */
+__read_mostly unsigned int walt_ravg_window =
+ (20000000 / TICK_NSEC) * TICK_NSEC;
+#define MIN_SCHED_RAVG_WINDOW ((10000000 / TICK_NSEC) * TICK_NSEC)
+#define MAX_SCHED_RAVG_WINDOW ((1000000000 / TICK_NSEC) * TICK_NSEC)
+
+static unsigned int sync_cpu;
+static ktime_t ktime_last;
+static __read_mostly bool walt_ktime_suspended;
+
+static unsigned int task_load(struct task_struct *p)
+{
+ return p->ravg.demand;
+}
+
+static inline void fixup_cum_window_demand(struct rq *rq, s64 delta)
+{
+ rq->cum_window_demand += delta;
+ if (unlikely((s64)rq->cum_window_demand < 0))
+ rq->cum_window_demand = 0;
+}
+
+void
+walt_inc_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p)
+{
+ rq->cumulative_runnable_avg += p->ravg.demand;
+
+ /*
+ * Add a task's contribution to the cumulative window demand when
+ *
+ * (1) task is enqueued with on_rq = 1 i.e migration,
+ * prio/cgroup/class change.
+ * (2) task is waking for the first time in this window.
+ */
+ if (p->on_rq || (p->last_sleep_ts < rq->window_start))
+ fixup_cum_window_demand(rq, p->ravg.demand);
+}
+
+void
+walt_dec_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p)
+{
+ rq->cumulative_runnable_avg -= p->ravg.demand;
+ BUG_ON((s64)rq->cumulative_runnable_avg < 0);
+
+ /*
+ * on_rq will be 1 for sleeping tasks. So check if the task
+ * is migrating or dequeuing in RUNNING state to change the
+ * prio/cgroup/class.
+ */
+ if (task_on_rq_migrating(p) || p->state == TASK_RUNNING)
+ fixup_cum_window_demand(rq, -(s64)p->ravg.demand);
+}
+
+void
+walt_fixup_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p, u64 new_task_load)
+{
+ s64 task_load_delta = (s64)new_task_load - task_load(p);
+
+ rq->cumulative_runnable_avg += task_load_delta;
+ if ((s64)rq->cumulative_runnable_avg < 0)
+ panic("cra less than zero: tld: %lld, task_load(p) = %u\n",
+ task_load_delta, task_load(p));
+
+ fixup_cum_window_demand(rq, task_load_delta);
+}
+
+u64 walt_ktime_clock(void)
+{
+ if (unlikely(walt_ktime_suspended))
+ return ktime_to_ns(ktime_last);
+ return ktime_get_ns();
+}
+
+static void walt_resume(void)
+{
+ walt_ktime_suspended = false;
+}
+
+static int walt_suspend(void)
+{
+ ktime_last = ktime_get();
+ walt_ktime_suspended = true;
+ return 0;
+}
+
+static struct syscore_ops walt_syscore_ops = {
+ .resume = walt_resume,
+ .suspend = walt_suspend
+};
+
+static int __init walt_init_ops(void)
+{
+ register_syscore_ops(&walt_syscore_ops);
+ return 0;
+}
+late_initcall(walt_init_ops);
+
+#ifdef CONFIG_CFS_BANDWIDTH
+void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq,
+ struct task_struct *p)
+{
+ cfs_rq->cumulative_runnable_avg += p->ravg.demand;
+}
+
+void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq,
+ struct task_struct *p)
+{
+ cfs_rq->cumulative_runnable_avg -= p->ravg.demand;
+}
+#endif
+
+static int exiting_task(struct task_struct *p)
+{
+ if (p->flags & PF_EXITING) {
+ if (p->ravg.sum_history[0] != EXITING_TASK_MARKER) {
+ p->ravg.sum_history[0] = EXITING_TASK_MARKER;
+ }
+ return 1;
+ }
+ return 0;
+}
+
+static int __init set_walt_ravg_window(char *str)
+{
+ unsigned int adj_window;
+ bool no_walt = walt_disabled;
+
+ get_option(&str, &walt_ravg_window);
+
+ /* Adjust for CONFIG_HZ */
+ adj_window = (walt_ravg_window / TICK_NSEC) * TICK_NSEC;
+
+ /* Warn if we're a bit too far away from the expected window size */
+ WARN(adj_window < walt_ravg_window - NSEC_PER_MSEC,
+ "tick-adjusted window size %u, original was %u\n", adj_window,
+ walt_ravg_window);
+
+ walt_ravg_window = adj_window;
+
+ walt_disabled = walt_disabled ||
+ (walt_ravg_window < MIN_SCHED_RAVG_WINDOW ||
+ walt_ravg_window > MAX_SCHED_RAVG_WINDOW);
+
+ WARN(!no_walt && walt_disabled,
+ "invalid window size, disabling WALT\n");
+
+ return 0;
+}
+
+early_param("walt_ravg_window", set_walt_ravg_window);
+
+static void
+update_window_start(struct rq *rq, u64 wallclock)
+{
+ s64 delta;
+ int nr_windows;
+
+ delta = wallclock - rq->window_start;
+ /* If the MPM global timer is cleared, set delta as 0 to avoid kernel BUG happening */
+ if (delta < 0) {
+ delta = 0;
+ WARN_ONCE(1, "WALT wallclock appears to have gone backwards or reset\n");
+ }
+
+ if (delta < walt_ravg_window)
+ return;
+
+ nr_windows = div64_u64(delta, walt_ravg_window);
+ rq->window_start += (u64)nr_windows * (u64)walt_ravg_window;
+
+ rq->cum_window_demand = rq->cumulative_runnable_avg;
+}
+
+/*
+ * Translate absolute delta time accounted on a CPU
+ * to a scale where 1024 is the capacity of the most
+ * capable CPU running at FMAX
+ */
+static u64 scale_exec_time(u64 delta, struct rq *rq)
+{
+ unsigned long capcurr = capacity_curr_of(cpu_of(rq));
+
+ return (delta * capcurr) >> SCHED_CAPACITY_SHIFT;
+}
+
+static int cpu_is_waiting_on_io(struct rq *rq)
+{
+ if (!walt_io_is_busy)
+ return 0;
+
+ return atomic_read(&rq->nr_iowait);
+}
+
+void walt_account_irqtime(int cpu, struct task_struct *curr,
+ u64 delta, u64 wallclock)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags, nr_windows;
+ u64 cur_jiffies_ts;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+
+ /*
+ * cputime (wallclock) uses sched_clock so use the same here for
+ * consistency.
+ */
+ delta += sched_clock() - wallclock;
+ cur_jiffies_ts = get_jiffies_64();
+
+ if (is_idle_task(curr))
+ walt_update_task_ravg(curr, rq, IRQ_UPDATE, walt_ktime_clock(),
+ delta);
+
+ nr_windows = cur_jiffies_ts - rq->irqload_ts;
+
+ if (nr_windows) {
+ if (nr_windows < 10) {
+ /* Decay CPU's irqload by 3/4 for each window. */
+ rq->avg_irqload *= (3 * nr_windows);
+ rq->avg_irqload = div64_u64(rq->avg_irqload,
+ 4 * nr_windows);
+ } else {
+ rq->avg_irqload = 0;
+ }
+ rq->avg_irqload += rq->cur_irqload;
+ rq->cur_irqload = 0;
+ }
+
+ rq->cur_irqload += delta;
+ rq->irqload_ts = cur_jiffies_ts;
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+
+#define WALT_HIGH_IRQ_TIMEOUT 3
+
+u64 walt_irqload(int cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ s64 delta;
+ delta = get_jiffies_64() - rq->irqload_ts;
+
+ /*
+ * Current context can be preempted by irq and rq->irqload_ts can be
+ * updated by irq context so that delta can be negative.
+ * But this is okay and we can safely return as this means there
+ * was recent irq occurrence.
+ */
+
+ if (delta < WALT_HIGH_IRQ_TIMEOUT)
+ return rq->avg_irqload;
+ else
+ return 0;
+}
+
+int walt_cpu_high_irqload(int cpu) {
+ return walt_irqload(cpu) >= sysctl_sched_walt_cpu_high_irqload;
+}
+
+static int account_busy_for_cpu_time(struct rq *rq, struct task_struct *p,
+ u64 irqtime, int event)
+{
+ if (is_idle_task(p)) {
+ /* TASK_WAKE && TASK_MIGRATE is not possible on idle task! */
+ if (event == PICK_NEXT_TASK)
+ return 0;
+
+ /* PUT_PREV_TASK, TASK_UPDATE && IRQ_UPDATE are left */
+ return irqtime || cpu_is_waiting_on_io(rq);
+ }
+
+ if (event == TASK_WAKE)
+ return 0;
+
+ if (event == PUT_PREV_TASK || event == IRQ_UPDATE ||
+ event == TASK_UPDATE)
+ return 1;
+
+ /* Only TASK_MIGRATE && PICK_NEXT_TASK left */
+ return walt_freq_account_wait_time;
+}
+
+/*
+ * Account cpu activity in its busy time counters (rq->curr/prev_runnable_sum)
+ */
+static void update_cpu_busy_time(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime)
+{
+ int new_window, nr_full_windows = 0;
+ int p_is_curr_task = (p == rq->curr);
+ u64 mark_start = p->ravg.mark_start;
+ u64 window_start = rq->window_start;
+ u32 window_size = walt_ravg_window;
+ u64 delta;
+
+ new_window = mark_start < window_start;
+ if (new_window) {
+ nr_full_windows = div64_u64((window_start - mark_start),
+ window_size);
+ if (p->ravg.active_windows < USHRT_MAX)
+ p->ravg.active_windows++;
+ }
+
+ /* Handle per-task window rollover. We don't care about the idle
+ * task or exiting tasks. */
+ if (new_window && !is_idle_task(p) && !exiting_task(p)) {
+ u32 curr_window = 0;
+
+ if (!nr_full_windows)
+ curr_window = p->ravg.curr_window;
+
+ p->ravg.prev_window = curr_window;
+ p->ravg.curr_window = 0;
+ }
+
+ if (!account_busy_for_cpu_time(rq, p, irqtime, event)) {
+ /* account_busy_for_cpu_time() = 0, so no update to the
+ * task's current window needs to be made. This could be
+ * for example
+ *
+ * - a wakeup event on a task within the current
+ * window (!new_window below, no action required),
+ * - switching to a new task from idle (PICK_NEXT_TASK)
+ * in a new window where irqtime is 0 and we aren't
+ * waiting on IO */
+
+ if (!new_window)
+ return;
+
+ /* A new window has started. The RQ demand must be rolled
+ * over if p is the current task. */
+ if (p_is_curr_task) {
+ u64 prev_sum = 0;
+
+ /* p is either idle task or an exiting task */
+ if (!nr_full_windows) {
+ prev_sum = rq->curr_runnable_sum;
+ }
+
+ rq->prev_runnable_sum = prev_sum;
+ rq->curr_runnable_sum = 0;
+ }
+
+ return;
+ }
+
+ if (!new_window) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. No rollover
+ * since we didn't start a new window. An example of this is
+ * when a task starts execution and then sleeps within the
+ * same window. */
+
+ if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq))
+ delta = wallclock - mark_start;
+ else
+ delta = irqtime;
+ delta = scale_exec_time(delta, rq);
+ rq->curr_runnable_sum += delta;
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.curr_window += delta;
+
+ return;
+ }
+
+ if (!p_is_curr_task) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has also started, but p is not the current task, so the
+ * window is not rolled over - just split up and account
+ * as necessary into curr and prev. The window is only
+ * rolled over when a new window is processed for the current
+ * task.
+ *
+ * Irqtime can't be accounted by a task that isn't the
+ * currently running task. */
+
+ if (!nr_full_windows) {
+ /* A full window hasn't elapsed, account partial
+ * contribution to previous completed window. */
+ delta = scale_exec_time(window_start - mark_start, rq);
+ if (!exiting_task(p))
+ p->ravg.prev_window += delta;
+ } else {
+ /* Since at least one full window has elapsed,
+ * the contribution to the previous window is the
+ * full window (window_size). */
+ delta = scale_exec_time(window_size, rq);
+ if (!exiting_task(p))
+ p->ravg.prev_window = delta;
+ }
+ rq->prev_runnable_sum += delta;
+
+ /* Account piece of busy time in the current window. */
+ delta = scale_exec_time(wallclock - window_start, rq);
+ rq->curr_runnable_sum += delta;
+ if (!exiting_task(p))
+ p->ravg.curr_window = delta;
+
+ return;
+ }
+
+ if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq)) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has started and p is the current task so rollover is
+ * needed. If any of these three above conditions are true
+ * then this busy time can't be accounted as irqtime.
+ *
+ * Busy time for the idle task or exiting tasks need not
+ * be accounted.
+ *
+ * An example of this would be a task that starts execution
+ * and then sleeps once a new window has begun. */
+
+ if (!nr_full_windows) {
+ /* A full window hasn't elapsed, account partial
+ * contribution to previous completed window. */
+ delta = scale_exec_time(window_start - mark_start, rq);
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.prev_window += delta;
+
+ delta += rq->curr_runnable_sum;
+ } else {
+ /* Since at least one full window has elapsed,
+ * the contribution to the previous window is the
+ * full window (window_size). */
+ delta = scale_exec_time(window_size, rq);
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.prev_window = delta;
+
+ }
+ /*
+ * Rollover for normal runnable sum is done here by overwriting
+ * the values in prev_runnable_sum and curr_runnable_sum.
+ * Rollover for new task runnable sum has completed by previous
+ * if-else statement.
+ */
+ rq->prev_runnable_sum = delta;
+
+ /* Account piece of busy time in the current window. */
+ delta = scale_exec_time(wallclock - window_start, rq);
+ rq->curr_runnable_sum = delta;
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.curr_window = delta;
+
+ return;
+ }
+
+ if (irqtime) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has started and p is the current task so rollover is
+ * needed. The current task must be the idle task because
+ * irqtime is not accounted for any other task.
+ *
+ * Irqtime will be accounted each time we process IRQ activity
+ * after a period of idleness, so we know the IRQ busy time
+ * started at wallclock - irqtime. */
+
+ BUG_ON(!is_idle_task(p));
+ mark_start = wallclock - irqtime;
+
+ /* Roll window over. If IRQ busy time was just in the current
+ * window then that is all that need be accounted. */
+ rq->prev_runnable_sum = rq->curr_runnable_sum;
+ if (mark_start > window_start) {
+ rq->curr_runnable_sum = scale_exec_time(irqtime, rq);
+ return;
+ }
+
+ /* The IRQ busy time spanned multiple windows. Process the
+ * busy time preceding the current window start first. */
+ delta = window_start - mark_start;
+ if (delta > window_size)
+ delta = window_size;
+ delta = scale_exec_time(delta, rq);
+ rq->prev_runnable_sum += delta;
+
+ /* Process the remaining IRQ busy time in the current window. */
+ delta = wallclock - window_start;
+ rq->curr_runnable_sum = scale_exec_time(delta, rq);
+
+ return;
+ }
+
+ BUG();
+}
+
+static int account_busy_for_task_demand(struct task_struct *p, int event)
+{
+ /* No need to bother updating task demand for exiting tasks
+ * or the idle task. */
+ if (exiting_task(p) || is_idle_task(p))
+ return 0;
+
+ /* When a task is waking up it is completing a segment of non-busy
+ * time. Likewise, if wait time is not treated as busy time, then
+ * when a task begins to run or is migrated, it is not running and
+ * is completing a segment of non-busy time. */
+ if (event == TASK_WAKE || (!walt_account_wait_time &&
+ (event == PICK_NEXT_TASK || event == TASK_MIGRATE)))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Called when new window is starting for a task, to record cpu usage over
+ * recently concluded window(s). Normally 'samples' should be 1. It can be > 1
+ * when, say, a real-time task runs without preemption for several windows at a
+ * stretch.
+ */
+static void update_history(struct rq *rq, struct task_struct *p,
+ u32 runtime, int samples, int event)
+{
+ u32 *hist = &p->ravg.sum_history[0];
+ int ridx, widx;
+ u32 max = 0, avg, demand;
+ u64 sum = 0;
+
+ /* Ignore windows where task had no activity */
+ if (!runtime || is_idle_task(p) || exiting_task(p) || !samples)
+ goto done;
+
+ /* Push new 'runtime' value onto stack */
+ widx = walt_ravg_hist_size - 1;
+ ridx = widx - samples;
+ for (; ridx >= 0; --widx, --ridx) {
+ hist[widx] = hist[ridx];
+ sum += hist[widx];
+ if (hist[widx] > max)
+ max = hist[widx];
+ }
+
+ for (widx = 0; widx < samples && widx < walt_ravg_hist_size; widx++) {
+ hist[widx] = runtime;
+ sum += hist[widx];
+ if (hist[widx] > max)
+ max = hist[widx];
+ }
+
+ p->ravg.sum = 0;
+
+ if (walt_window_stats_policy == WINDOW_STATS_RECENT) {
+ demand = runtime;
+ } else if (walt_window_stats_policy == WINDOW_STATS_MAX) {
+ demand = max;
+ } else {
+ avg = div64_u64(sum, walt_ravg_hist_size);
+ if (walt_window_stats_policy == WINDOW_STATS_AVG)
+ demand = avg;
+ else
+ demand = max(avg, runtime);
+ }
+
+ /*
+ * A throttled deadline sched class task gets dequeued without
+ * changing p->on_rq. Since the dequeue decrements hmp stats
+ * avoid decrementing it here again.
+ *
+ * When window is rolled over, the cumulative window demand
+ * is reset to the cumulative runnable average (contribution from
+ * the tasks on the runqueue). If the current task is dequeued
+ * already, it's demand is not included in the cumulative runnable
+ * average. So add the task demand separately to cumulative window
+ * demand.
+ */
+ if (!task_has_dl_policy(p) || !p->dl.dl_throttled) {
+ if (task_on_rq_queued(p))
+ p->sched_class->fixup_cumulative_runnable_avg(rq, p,
+ demand);
+ else if (rq->curr == p)
+ fixup_cum_window_demand(rq, demand);
+ }
+
+ p->ravg.demand = demand;
+
+done:
+ trace_walt_update_history(rq, p, runtime, samples, event);
+ return;
+}
+
+static void add_to_task_demand(struct rq *rq, struct task_struct *p,
+ u64 delta)
+{
+ delta = scale_exec_time(delta, rq);
+ p->ravg.sum += delta;
+ if (unlikely(p->ravg.sum > walt_ravg_window))
+ p->ravg.sum = walt_ravg_window;
+}
+
+/*
+ * Account cpu demand of task and/or update task's cpu demand history
+ *
+ * ms = p->ravg.mark_start;
+ * wc = wallclock
+ * ws = rq->window_start
+ *
+ * Three possibilities:
+ *
+ * a) Task event is contained within one window.
+ * window_start < mark_start < wallclock
+ *
+ * ws ms wc
+ * | | |
+ * V V V
+ * |---------------|
+ *
+ * In this case, p->ravg.sum is updated *iff* event is appropriate
+ * (ex: event == PUT_PREV_TASK)
+ *
+ * b) Task event spans two windows.
+ * mark_start < window_start < wallclock
+ *
+ * ms ws wc
+ * | | |
+ * V V V
+ * -----|-------------------
+ *
+ * In this case, p->ravg.sum is updated with (ws - ms) *iff* event
+ * is appropriate, then a new window sample is recorded followed
+ * by p->ravg.sum being set to (wc - ws) *iff* event is appropriate.
+ *
+ * c) Task event spans more than two windows.
+ *
+ * ms ws_tmp ws wc
+ * | | | |
+ * V V V V
+ * ---|-------|-------|-------|-------|------
+ * | |
+ * |<------ nr_full_windows ------>|
+ *
+ * In this case, p->ravg.sum is updated with (ws_tmp - ms) first *iff*
+ * event is appropriate, window sample of p->ravg.sum is recorded,
+ * 'nr_full_window' samples of window_size is also recorded *iff*
+ * event is appropriate and finally p->ravg.sum is set to (wc - ws)
+ * *iff* event is appropriate.
+ *
+ * IMPORTANT : Leave p->ravg.mark_start unchanged, as update_cpu_busy_time()
+ * depends on it!
+ */
+static void update_task_demand(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock)
+{
+ u64 mark_start = p->ravg.mark_start;
+ u64 delta, window_start = rq->window_start;
+ int new_window, nr_full_windows;
+ u32 window_size = walt_ravg_window;
+
+ new_window = mark_start < window_start;
+ if (!account_busy_for_task_demand(p, event)) {
+ if (new_window)
+ /* If the time accounted isn't being accounted as
+ * busy time, and a new window started, only the
+ * previous window need be closed out with the
+ * pre-existing demand. Multiple windows may have
+ * elapsed, but since empty windows are dropped,
+ * it is not necessary to account those. */
+ update_history(rq, p, p->ravg.sum, 1, event);
+ return;
+ }
+
+ if (!new_window) {
+ /* The simple case - busy time contained within the existing
+ * window. */
+ add_to_task_demand(rq, p, wallclock - mark_start);
+ return;
+ }
+
+ /* Busy time spans at least two windows. Temporarily rewind
+ * window_start to first window boundary after mark_start. */
+ delta = window_start - mark_start;
+ nr_full_windows = div64_u64(delta, window_size);
+ window_start -= (u64)nr_full_windows * (u64)window_size;
+
+ /* Process (window_start - mark_start) first */
+ add_to_task_demand(rq, p, window_start - mark_start);
+
+ /* Push new sample(s) into task's demand history */
+ update_history(rq, p, p->ravg.sum, 1, event);
+ if (nr_full_windows)
+ update_history(rq, p, scale_exec_time(window_size, rq),
+ nr_full_windows, event);
+
+ /* Roll window_start back to current to process any remainder
+ * in current window. */
+ window_start += (u64)nr_full_windows * (u64)window_size;
+
+ /* Process (wallclock - window_start) next */
+ mark_start = window_start;
+ add_to_task_demand(rq, p, wallclock - mark_start);
+}
+
+/* Reflect task activity on its demand and cpu's busy time statistics */
+void walt_update_task_ravg(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime)
+{
+ if (walt_disabled || !rq->window_start)
+ return;
+
+ lockdep_assert_held(&rq->lock);
+
+ update_window_start(rq, wallclock);
+
+ if (!p->ravg.mark_start)
+ goto done;
+
+ update_task_demand(p, rq, event, wallclock);
+ update_cpu_busy_time(p, rq, event, wallclock, irqtime);
+
+done:
+ trace_walt_update_task_ravg(p, rq, event, wallclock, irqtime);
+
+ p->ravg.mark_start = wallclock;
+}
+
+static void reset_task_stats(struct task_struct *p)
+{
+ u32 sum = 0;
+
+ if (exiting_task(p))
+ sum = EXITING_TASK_MARKER;
+
+ memset(&p->ravg, 0, sizeof(struct ravg));
+ /* Retain EXITING_TASK marker */
+ p->ravg.sum_history[0] = sum;
+}
+
+void walt_mark_task_starting(struct task_struct *p)
+{
+ u64 wallclock;
+ struct rq *rq = task_rq(p);
+
+ if (!rq->window_start) {
+ reset_task_stats(p);
+ return;
+ }
+
+ wallclock = walt_ktime_clock();
+ p->ravg.mark_start = wallclock;
+}
+
+void walt_set_window_start(struct rq *rq)
+{
+ int cpu = cpu_of(rq);
+ struct rq *sync_rq = cpu_rq(sync_cpu);
+
+ if (likely(rq->window_start))
+ return;
+
+ if (cpu == sync_cpu) {
+ rq->window_start = 1;
+ } else {
+ raw_spin_unlock(&rq->lock);
+ double_rq_lock(rq, sync_rq);
+ rq->window_start = cpu_rq(sync_cpu)->window_start;
+ rq->curr_runnable_sum = rq->prev_runnable_sum = 0;
+ raw_spin_unlock(&sync_rq->lock);
+ }
+
+ rq->curr->ravg.mark_start = rq->window_start;
+}
+
+void walt_migrate_sync_cpu(int cpu)
+{
+ if (cpu == sync_cpu)
+ sync_cpu = smp_processor_id();
+}
+
+void walt_fixup_busy_time(struct task_struct *p, int new_cpu)
+{
+ struct rq *src_rq = task_rq(p);
+ struct rq *dest_rq = cpu_rq(new_cpu);
+ u64 wallclock;
+
+ if (!p->on_rq && p->state != TASK_WAKING)
+ return;
+
+ if (exiting_task(p)) {
+ return;
+ }
+
+ if (p->state == TASK_WAKING)
+ double_rq_lock(src_rq, dest_rq);
+
+ wallclock = walt_ktime_clock();
+
+ walt_update_task_ravg(task_rq(p)->curr, task_rq(p),
+ TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(dest_rq->curr, dest_rq,
+ TASK_UPDATE, wallclock, 0);
+
+ walt_update_task_ravg(p, task_rq(p), TASK_MIGRATE, wallclock, 0);
+
+ /*
+ * When a task is migrating during the wakeup, adjust
+ * the task's contribution towards cumulative window
+ * demand.
+ */
+ if (p->state == TASK_WAKING &&
+ p->last_sleep_ts >= src_rq->window_start) {
+ fixup_cum_window_demand(src_rq, -(s64)p->ravg.demand);
+ fixup_cum_window_demand(dest_rq, p->ravg.demand);
+ }
+
+ if (p->ravg.curr_window) {
+ src_rq->curr_runnable_sum -= p->ravg.curr_window;
+ dest_rq->curr_runnable_sum += p->ravg.curr_window;
+ }
+
+ if (p->ravg.prev_window) {
+ src_rq->prev_runnable_sum -= p->ravg.prev_window;
+ dest_rq->prev_runnable_sum += p->ravg.prev_window;
+ }
+
+ if ((s64)src_rq->prev_runnable_sum < 0) {
+ src_rq->prev_runnable_sum = 0;
+ WARN_ON(1);
+ }
+ if ((s64)src_rq->curr_runnable_sum < 0) {
+ src_rq->curr_runnable_sum = 0;
+ WARN_ON(1);
+ }
+
+ trace_walt_migration_update_sum(src_rq, p);
+ trace_walt_migration_update_sum(dest_rq, p);
+
+ if (p->state == TASK_WAKING)
+ double_rq_unlock(src_rq, dest_rq);
+}
+
+void walt_init_new_task_load(struct task_struct *p)
+{
+ int i;
+ u32 init_load_windows =
+ div64_u64((u64)sysctl_sched_walt_init_task_load_pct *
+ (u64)walt_ravg_window, 100);
+ u32 init_load_pct = current->init_load_pct;
+
+ p->init_load_pct = 0;
+ memset(&p->ravg, 0, sizeof(struct ravg));
+
+ if (init_load_pct) {
+ init_load_windows = div64_u64((u64)init_load_pct *
+ (u64)walt_ravg_window, 100);
+ }
+
+ p->ravg.demand = init_load_windows;
+ for (i = 0; i < RAVG_HIST_SIZE_MAX; ++i)
+ p->ravg.sum_history[i] = init_load_windows;
+}
diff --git a/kernel/sched/walt.h b/kernel/sched/walt.h
new file mode 100644
index 0000000..cb492f4
--- /dev/null
+++ b/kernel/sched/walt.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __WALT_H
+#define __WALT_H
+
+#ifdef CONFIG_SCHED_WALT
+
+void walt_update_task_ravg(struct task_struct *p, struct rq *rq, int event,
+ u64 wallclock, u64 irqtime);
+void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p);
+void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p);
+void walt_fixup_cumulative_runnable_avg(struct rq *rq, struct task_struct *p,
+ u64 new_task_load);
+
+void walt_fixup_busy_time(struct task_struct *p, int new_cpu);
+void walt_init_new_task_load(struct task_struct *p);
+void walt_mark_task_starting(struct task_struct *p);
+void walt_set_window_start(struct rq *rq);
+void walt_migrate_sync_cpu(int cpu);
+void walt_init_cpu_efficiency(void);
+u64 walt_ktime_clock(void);
+void walt_account_irqtime(int cpu, struct task_struct *curr, u64 delta,
+ u64 wallclock);
+
+u64 walt_irqload(int cpu);
+int walt_cpu_high_irqload(int cpu);
+
+#else /* CONFIG_SCHED_WALT */
+
+static inline void walt_update_task_ravg(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime) { }
+static inline void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { }
+static inline void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { }
+static inline void walt_fixup_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p,
+ u64 new_task_load) { }
+static inline void walt_fixup_busy_time(struct task_struct *p, int new_cpu) { }
+static inline void walt_init_new_task_load(struct task_struct *p) { }
+static inline void walt_mark_task_starting(struct task_struct *p) { }
+static inline void walt_set_window_start(struct rq *rq) { }
+static inline void walt_migrate_sync_cpu(int cpu) { }
+static inline void walt_init_cpu_efficiency(void) { }
+static inline u64 walt_ktime_clock(void) { return 0; }
+
+#define walt_cpu_high_irqload(cpu) false
+
+#endif /* CONFIG_SCHED_WALT */
+
+#if defined(CONFIG_CFS_BANDWIDTH) && defined(CONFIG_SCHED_WALT)
+void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p);
+void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p);
+#else
+static inline void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p) { }
+static inline void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p) { }
+#endif
+
+extern bool walt_disabled;
+
+#endif
diff --git a/kernel/signal.c b/kernel/signal.c
index bedca16..a82e3d0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -14,7 +14,9 @@
#include <linux/export.h>
#include <linux/init.h>
#include <linux/sched.h>
+#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/proc_fs.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/coredump.h>
@@ -1632,6 +1634,14 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
return ret;
}
+static void do_notify_pidfd(struct task_struct *task)
+{
+ struct pid *pid;
+
+ pid = task_pid(task);
+ wake_up_all(&pid->wait_pidfd);
+}
+
/*
* Let a parent know about the death of a child.
* For a stopped/continued status change, use do_notify_parent_cldstop instead.
@@ -1655,6 +1665,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
BUG_ON(!tsk->ptrace &&
(tsk->group_leader != tsk || !thread_group_empty(tsk)));
+ /* Wake up all pidfd waiters */
+ do_notify_pidfd(tsk);
+
if (sig != SIGCHLD) {
/*
* This is only possible if parent == real_parent.
@@ -2935,6 +2948,15 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
return ret;
}
+static inline void prepare_kill_siginfo(int sig, struct siginfo *info)
+{
+ info->si_signo = sig;
+ info->si_errno = 0;
+ info->si_code = SI_USER;
+ info->si_pid = task_tgid_vnr(current);
+ info->si_uid = from_kuid_munged(current_user_ns(), current_uid());
+}
+
/**
* sys_kill - send a signal to a process
* @pid: the PID of the process
@@ -2944,15 +2966,125 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
{
struct siginfo info;
- info.si_signo = sig;
- info.si_errno = 0;
- info.si_code = SI_USER;
- info.si_pid = task_tgid_vnr(current);
- info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
+ prepare_kill_siginfo(sig, &info);
return kill_something_info(sig, &info, pid);
}
+/*
+ * Verify that the signaler and signalee either are in the same pid namespace
+ * or that the signaler's pid namespace is an ancestor of the signalee's pid
+ * namespace.
+ */
+static bool access_pidfd_pidns(struct pid *pid)
+{
+ struct pid_namespace *active = task_active_pid_ns(current);
+ struct pid_namespace *p = ns_of_pid(pid);
+
+ for (;;) {
+ if (!p)
+ return false;
+ if (p == active)
+ break;
+ p = p->parent;
+ }
+
+ return true;
+}
+
+static struct pid *pidfd_to_pid(const struct file *file)
+{
+ if (file->f_op == &pidfd_fops)
+ return file->private_data;
+
+ return tgid_pidfd_to_pid(file);
+}
+
+static int copy_siginfo_from_user_any(siginfo_t *kinfo, siginfo_t __user *info)
+{
+#ifdef CONFIG_COMPAT
+ /*
+ * Avoid hooking up compat syscalls and instead handle necessary
+ * conversions here. Note, this is a stop-gap measure and should not be
+ * considered a generic solution.
+ */
+ if (in_compat_syscall())
+ return copy_siginfo_from_user32(
+ kinfo, (struct compat_siginfo __user *)info);
+#endif
+ return copy_from_user(kinfo, info, sizeof(siginfo_t));
+}
+
+/**
+ * sys_pidfd_send_signal - Signal a process through a pidfd
+ * @pidfd: file descriptor of the process
+ * @sig: signal to send
+ * @info: signal info
+ * @flags: future flags
+ *
+ * The syscall currently only signals via PIDTYPE_PID which covers
+ * kill(<positive-pid>, <signal>. It does not signal threads or process
+ * groups.
+ * In order to extend the syscall to threads and process groups the @flags
+ * argument should be used. In essence, the @flags argument will determine
+ * what is signaled and not the file descriptor itself. Put in other words,
+ * grouping is a property of the flags argument not a property of the file
+ * descriptor.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
+ siginfo_t __user *, info, unsigned int, flags)
+{
+ int ret;
+ struct fd f;
+ struct pid *pid;
+ siginfo_t kinfo;
+
+ /* Enforce flags be set to 0 until we add an extension. */
+ if (flags)
+ return -EINVAL;
+
+ f = fdget(pidfd);
+ if (!f.file)
+ return -EBADF;
+
+ /* Is this a pidfd? */
+ pid = pidfd_to_pid(f.file);
+ if (IS_ERR(pid)) {
+ ret = PTR_ERR(pid);
+ goto err;
+ }
+
+ ret = -EINVAL;
+ if (!access_pidfd_pidns(pid))
+ goto err;
+
+ if (info) {
+ ret = copy_siginfo_from_user_any(&kinfo, info);
+ if (unlikely(ret))
+ goto err;
+
+ ret = -EINVAL;
+ if (unlikely(sig != kinfo.si_signo))
+ goto err;
+
+ /* Only allow sending arbitrary signals to yourself. */
+ ret = -EPERM;
+ if ((task_pid(current) != pid) &&
+ (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
+ goto err;
+ } else {
+ prepare_kill_siginfo(sig, &kinfo);
+ }
+
+ ret = kill_pid_info(sig, &kinfo, pid);
+
+err:
+ fdput(f);
+ return ret;
+}
+
static int
do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
{
diff --git a/kernel/sys.c b/kernel/sys.c
index 546cdc9..f24ac77 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -41,6 +41,8 @@
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/mempolicy.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
@@ -49,6 +51,7 @@
#include <linux/binfmts.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/rcupdate.h>
#include <linux/uidgid.h>
#include <linux/cred.h>
@@ -2072,6 +2075,153 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
}
#endif
+#ifdef CONFIG_MMU
+static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end,
+ const char __user *name_addr)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ int error = 0;
+ pgoff_t pgoff;
+
+ if (name_addr == vma_get_anon_name(vma)) {
+ *prev = vma;
+ goto out;
+ }
+
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+ *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
+ vma->vm_file, pgoff, vma_policy(vma),
+ vma->vm_userfaultfd_ctx, name_addr);
+ if (*prev) {
+ vma = *prev;
+ goto success;
+ }
+
+ *prev = vma;
+
+ if (start != vma->vm_start) {
+ error = split_vma(mm, vma, start, 1);
+ if (error)
+ goto out;
+ }
+
+ if (end != vma->vm_end) {
+ error = split_vma(mm, vma, end, 0);
+ if (error)
+ goto out;
+ }
+
+success:
+ if (!vma->vm_file)
+ vma->anon_name = name_addr;
+
+out:
+ if (error == -ENOMEM)
+ error = -EAGAIN;
+ return error;
+}
+
+static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
+ unsigned long arg)
+{
+ unsigned long tmp;
+ struct vm_area_struct *vma, *prev;
+ int unmapped_error = 0;
+ int error = -EINVAL;
+
+ /*
+ * If the interval [start,end) covers some unmapped address
+ * ranges, just ignore them, but return -ENOMEM at the end.
+ * - this matches the handling in madvise.
+ */
+ vma = find_vma_prev(current->mm, start, &prev);
+ if (vma && start > vma->vm_start)
+ prev = vma;
+
+ for (;;) {
+ /* Still start < end. */
+ error = -ENOMEM;
+ if (!vma)
+ return error;
+
+ /* Here start < (end|vma->vm_end). */
+ if (start < vma->vm_start) {
+ unmapped_error = -ENOMEM;
+ start = vma->vm_start;
+ if (start >= end)
+ return error;
+ }
+
+ /* Here vma->vm_start <= start < (end|vma->vm_end) */
+ tmp = vma->vm_end;
+ if (end < tmp)
+ tmp = end;
+
+ /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+ error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
+ (const char __user *)arg);
+ if (error)
+ return error;
+ start = tmp;
+ if (prev && start < prev->vm_end)
+ start = prev->vm_end;
+ error = unmapped_error;
+ if (start >= end)
+ return error;
+ if (prev)
+ vma = prev->vm_next;
+ else /* madvise_remove dropped mmap_sem */
+ vma = find_vma(current->mm, start);
+ }
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ struct mm_struct *mm = current->mm;
+ int error;
+ unsigned long len;
+ unsigned long end;
+
+ if (start & ~PAGE_MASK)
+ return -EINVAL;
+ len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+ /* Check to see whether len was rounded up from small -ve to zero */
+ if (len_in && !len)
+ return -EINVAL;
+
+ end = start + len;
+ if (end < start)
+ return -EINVAL;
+
+ if (end == start)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+
+ switch (opt) {
+ case PR_SET_VMA_ANON_NAME:
+ error = prctl_set_vma_anon_name(start, end, arg);
+ break;
+ default:
+ error = -EINVAL;
+ }
+
+ up_write(&mm->mmap_sem);
+
+ return error;
+}
+#else /* CONFIG_MMU */
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ return -EINVAL;
+}
+#endif
+
int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
{
return -EINVAL;
@@ -2291,6 +2441,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
break;
+ case PR_SET_VMA:
+ error = prctl_set_vma(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 513e6da..4f66c8f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -105,6 +105,7 @@ extern char core_pattern[];
extern unsigned int core_pipe_limit;
#endif
extern int pid_max;
+extern int extra_free_kbytes;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
extern int latencytop_enabled;
@@ -310,6 +311,50 @@ static struct ctl_table kern_table[] = {
.extra2 = &max_sched_granularity_ns,
},
{
+ .procname = "sched_sync_hint_enable",
+ .data = &sysctl_sched_sync_hint_enable,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#ifdef CONFIG_SCHED_WALT
+ {
+ .procname = "sched_use_walt_cpu_util",
+ .data = &sysctl_sched_use_walt_cpu_util,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_use_walt_task_util",
+ .data = &sysctl_sched_use_walt_task_util,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_walt_init_task_load_pct",
+ .data = &sysctl_sched_walt_init_task_load_pct,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_walt_cpu_high_irqload",
+ .data = &sysctl_sched_walt_cpu_high_irqload,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
+ {
+ .procname = "sched_cstate_aware",
+ .data = &sysctl_sched_cstate_aware,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "sched_wakeup_granularity_ns",
.data = &sysctl_sched_wakeup_granularity,
.maxlen = sizeof(unsigned int),
@@ -452,6 +497,21 @@ static struct ctl_table kern_table[] = {
.extra1 = &one,
},
#endif
+#ifdef CONFIG_SCHED_TUNE
+ {
+ .procname = "sched_cfs_boost",
+ .data = &sysctl_sched_cfs_boost,
+ .maxlen = sizeof(sysctl_sched_cfs_boost),
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ .mode = 0444,
+#else
+ .mode = 0644,
+#endif
+ .proc_handler = &sysctl_sched_cfs_boost_handler,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
+#endif
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
@@ -1449,6 +1509,14 @@ static struct ctl_table vm_table[] = {
.extra2 = &one_thousand,
},
{
+ .procname = "extra_free_kbytes",
+ .data = &extra_free_kbytes,
+ .maxlen = sizeof(extra_free_kbytes),
+ .mode = 0644,
+ .proc_handler = min_free_kbytes_sysctl_handler,
+ .extra1 = &zero,
+ },
+ {
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b6bebe2..65aafad 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1009,6 +1009,18 @@ ktime_t tick_nohz_get_sleep_length(void)
return ts->sleep_length;
}
+/**
+ * tick_nohz_get_idle_calls - return the current idle calls counter value
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls(void)
+{
+ struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
+
+ return ts->idle_calls;
+}
+
static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e21b4d8..f29c4af 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
@@ -72,6 +73,10 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
tk->xtime_sec++;
}
+ while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) {
+ tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
+ tk->raw_sec++;
+ }
}
static inline struct timespec64 tk_xtime(struct timekeeper *tk)
@@ -285,12 +290,14 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
/* if changing clocks, convert xtime_nsec shift units */
if (old_clock) {
int shift_change = clock->shift - old_clock->shift;
- if (shift_change < 0)
+ if (shift_change < 0) {
tk->tkr_mono.xtime_nsec >>= -shift_change;
- else
+ tk->tkr_raw.xtime_nsec >>= -shift_change;
+ } else {
tk->tkr_mono.xtime_nsec <<= shift_change;
+ tk->tkr_raw.xtime_nsec <<= shift_change;
+ }
}
- tk->tkr_raw.xtime_nsec = 0;
tk->tkr_mono.shift = clock->shift;
tk->tkr_raw.shift = clock->shift;
@@ -444,6 +451,35 @@ u64 ktime_get_raw_fast_ns(void)
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ * CPU 0 CPU 1
+ * timekeeping_inject_sleeptime64()
+ * __timekeeping_inject_sleeptime(tk, delta);
+ * timestamp();
+ * timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated. Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+
+ return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
/* Suspend-time cycles value for halted fast timekeeper. */
static cycle_t cycles_at_suspend;
@@ -592,9 +628,6 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
nsec = (u32) tk->wall_to_monotonic.tv_nsec;
tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
- /* Update the monotonic raw base */
- tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time);
-
/*
* The sum of the nanoseconds portions of xtime and
* wall_to_monotonic can be greater/equal one second. Take
@@ -604,6 +637,9 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
if (nsec >= NSEC_PER_SEC)
seconds++;
tk->ktime_sec = seconds;
+
+ /* Update the monotonic raw base */
+ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC);
}
/* must hold timekeeper_lock */
@@ -645,7 +681,6 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
static void timekeeping_forward_now(struct timekeeper *tk)
{
cycle_t cycle_now, delta;
- s64 nsec;
cycle_now = tk_clock_read(&tk->tkr_mono);
delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
@@ -657,10 +692,13 @@ static void timekeeping_forward_now(struct timekeeper *tk)
/* If arch requires, add in get_arch_timeoffset() */
tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;
- tk_normalize_xtime(tk);
- nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift);
- timespec64_add_ns(&tk->raw_time, nsec);
+ tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult;
+
+ /* If arch requires, add in get_arch_timeoffset() */
+ tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift;
+
+ tk_normalize_xtime(tk);
}
/**
@@ -1383,19 +1421,18 @@ int timekeeping_notify(struct clocksource *clock)
void getrawmonotonic64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- struct timespec64 ts64;
unsigned long seq;
s64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
+ ts->tv_sec = tk->raw_sec;
nsecs = timekeeping_get_ns(&tk->tkr_raw);
- ts64 = tk->raw_time;
} while (read_seqcount_retry(&tk_core.seq, seq));
- timespec64_add_ns(&ts64, nsecs);
- *ts = ts64;
+ ts->tv_nsec = 0;
+ timespec64_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(getrawmonotonic64);
@@ -1519,8 +1556,7 @@ void __init timekeeping_init(void)
tk_setup_internals(tk, clock);
tk_set_xtime(tk, &now);
- tk->raw_time.tv_sec = 0;
- tk->raw_time.tv_nsec = 0;
+ tk->raw_sec = 0;
if (boot.tv_sec == 0 && boot.tv_nsec == 0)
boot = tk_xtime(tk);
@@ -2038,15 +2074,12 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
*clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
- tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
tk->tkr_raw.xtime_nsec -= snsec_per_sec;
- tk->raw_time.tv_sec++;
+ tk->raw_sec++;
}
- tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift;
- tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
/* Accumulate error between NTP and clock interval */
tk->ntp_error += tk->ntp_tick << shift;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2a96b06..5771ce7 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -72,6 +72,9 @@
select CONTEXT_SWITCH_TRACER
bool
+config GPU_TRACEPOINTS
+ bool
+
config CONTEXT_SWITCH_TRACER
bool
@@ -157,6 +160,17 @@
address on the current task structure into a stack of calls.
+config PREEMPTIRQ_EVENTS
+ bool "Enable trace events for preempt and irq disable/enable"
+ select TRACE_IRQFLAGS
+ depends on DEBUG_PREEMPT || !PROVE_LOCKING
+ default n
+ help
+ Enable tracing of disable and enable events for preemption and irqs.
+ For tracing preempt disable/enable events, DEBUG_PREEMPT must be
+ enabled. For tracing irq disable/enable events, PROVE_LOCKING must
+ be disabled.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
default n
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e579808..907c144 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -34,6 +34,7 @@
obj-$(CONFIG_TRACING_MAP) += tracing_map.o
obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o
obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
@@ -67,6 +68,7 @@
endif
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o
obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7cc06f2..a895b35 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,7 +17,7 @@
/**
* trace_call_bpf - invoke BPF program
- * @prog: BPF program
+ * @call: tracepoint event
* @ctx: opaque context pointer
*
* kprobe handlers execute BPF programs via this helper.
@@ -29,7 +29,7 @@
* 1 - store kprobe event into ring buffer
* Other values are reserved and currently alias to 1
*/
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
unsigned int ret;
@@ -49,9 +49,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
goto out;
}
- rcu_read_lock();
- ret = BPF_PROG_RUN(prog, ctx);
- rcu_read_unlock();
+ /*
+ * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
+ * to all call sites, we did a bpf_prog_array_valid() there to check
+ * whether call->prog_array is empty or not, which is
+ * a heurisitc to speed up execution.
+ *
+ * If bpf_prog_array_valid() fetched prog_array was
+ * non-NULL, we go into trace_call_bpf() and do the actual
+ * proper rcu_dereference() under RCU lock.
+ * If it turns out that prog_array is NULL then, we bail out.
+ * For the opposite, if the bpf_prog_array_valid() fetched pointer
+ * was NULL, you'll skip the prog_array with the risk of missing
+ * out of events when it was updated in between this and the
+ * rcu_dereference() which is accepted risk.
+ */
+ ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
out:
__this_cpu_dec(bpf_prog_active);
@@ -632,6 +645,65 @@ static const struct bpf_verifier_ops perf_event_prog_ops = {
.convert_ctx_access = pe_prog_convert_ctx_access,
};
+static DEFINE_MUTEX(bpf_event_mutex);
+
+int perf_event_attach_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ int ret = -EEXIST;
+
+ mutex_lock(&bpf_event_mutex);
+
+ if (event->prog)
+ goto out;
+
+ old_array = rcu_dereference_protected(event->tp_event->prog_array,
+ lockdep_is_held(&bpf_event_mutex));
+ ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+ if (ret < 0)
+ goto out;
+
+ /* set the new array to event->tp_event and set event->prog */
+ event->prog = prog;
+ rcu_assign_pointer(event->tp_event->prog_array, new_array);
+ bpf_prog_array_free(old_array);
+
+out:
+ mutex_unlock(&bpf_event_mutex);
+ return ret;
+}
+
+void perf_event_detach_bpf_prog(struct perf_event *event)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ int ret;
+
+ mutex_lock(&bpf_event_mutex);
+
+ if (!event->prog)
+ goto out;
+
+ old_array = rcu_dereference_protected(event->tp_event->prog_array,
+ lockdep_is_held(&bpf_event_mutex));
+
+ ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+ if (ret < 0) {
+ bpf_prog_array_delete_safe(old_array, event->prog);
+ } else {
+ rcu_assign_pointer(event->tp_event->prog_array, new_array);
+ bpf_prog_array_free(old_array);
+ }
+
+ bpf_prog_put(event->prog);
+ event->prog = NULL;
+
+out:
+ mutex_unlock(&bpf_event_mutex);
+}
+
static struct bpf_prog_type_list perf_event_tl = {
.ops = &perf_event_prog_ops,
.type = BPF_PROG_TYPE_PERF_EVENT,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 16ca877..d60b238 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -121,8 +121,9 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs);
#else
/* See comment below, where ftrace_ops_list_func is defined */
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
-#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs);
+#define ftrace_ops_list_func ftrace_ops_no_ops
#endif
/*
@@ -4898,9 +4899,9 @@ static int ftrace_cmp_ips(const void *a, const void *b)
return 0;
}
-static int ftrace_process_locs(struct module *mod,
- unsigned long *start,
- unsigned long *end)
+static int __norecordmcount ftrace_process_locs(struct module *mod,
+ unsigned long *start,
+ unsigned long *end)
{
struct ftrace_page *start_pg;
struct ftrace_page *pg;
@@ -5337,7 +5338,8 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
}
NOKPROBE_SYMBOL(ftrace_ops_list_func);
#else
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs)
{
__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
}
@@ -5764,14 +5766,17 @@ void ftrace_graph_graph_time_control(bool enable)
fgraph_graph_time = enable;
}
+void ftrace_graph_return_stub(struct ftrace_graph_ret *trace)
+{
+}
+
int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
{
return 0;
}
/* The callbacks that hook a function */
-trace_func_graph_ret_t ftrace_graph_return =
- (trace_func_graph_ret_t)ftrace_stub;
+trace_func_graph_ret_t ftrace_graph_return = ftrace_graph_return_stub;
trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
@@ -5999,7 +6004,7 @@ void unregister_ftrace_graph(void)
goto out;
ftrace_graph_active--;
- ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
+ ftrace_graph_return = ftrace_graph_return_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
__ftrace_graph_entry = ftrace_graph_entry_stub;
ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c
new file mode 100644
index 0000000..a4b3f00
--- /dev/null
+++ b/kernel/trace/gpu-traces.c
@@ -0,0 +1,23 @@
+/*
+ * GPU tracepoints
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/gpu.h>
+
+EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch);
+EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 005929d..ad33c1b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1128,6 +1128,7 @@ static struct {
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
+ { ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};
@@ -1610,6 +1611,7 @@ static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
unsigned *map_cmdline_to_pid;
+ unsigned *map_cmdline_to_tgid;
unsigned cmdline_num;
int cmdline_idx;
char *saved_cmdlines;
@@ -1643,12 +1645,23 @@ static int allocate_cmdlines_buffer(unsigned int val,
return -ENOMEM;
}
+ s->map_cmdline_to_tgid = kmalloc_array(val,
+ sizeof(*s->map_cmdline_to_tgid),
+ GFP_KERNEL);
+ if (!s->map_cmdline_to_tgid) {
+ kfree(s->map_cmdline_to_pid);
+ kfree(s->saved_cmdlines);
+ return -ENOMEM;
+ }
+
s->cmdline_idx = 0;
s->cmdline_num = val;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
sizeof(s->map_pid_to_cmdline));
memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
val * sizeof(*s->map_cmdline_to_pid));
+ memset(s->map_cmdline_to_tgid, NO_CMDLINE_MAP,
+ val * sizeof(*s->map_cmdline_to_tgid));
return 0;
}
@@ -1814,14 +1827,17 @@ static int trace_save_cmdline(struct task_struct *tsk)
if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
return 0;
+ preempt_disable();
/*
* It's not the end of the world if we don't get
* the lock, but we also don't want to spin
* nor do we want to disable interrupts,
* so if we miss here, then better luck next time.
*/
- if (!arch_spin_trylock(&trace_cmdline_lock))
+ if (!arch_spin_trylock(&trace_cmdline_lock)) {
+ preempt_enable();
return 0;
+ }
idx = savedcmd->map_pid_to_cmdline[tsk->pid];
if (idx == NO_CMDLINE_MAP) {
@@ -1844,8 +1860,9 @@ static int trace_save_cmdline(struct task_struct *tsk)
}
set_cmdline(idx, tsk->comm);
-
+ savedcmd->map_cmdline_to_tgid[idx] = tsk->tgid;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
return 1;
}
@@ -1887,6 +1904,35 @@ void trace_find_cmdline(int pid, char comm[])
preempt_enable();
}
+static int __find_tgid_locked(int pid)
+{
+ unsigned map;
+ int tgid;
+
+ map = savedcmd->map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ tgid = savedcmd->map_cmdline_to_tgid[map];
+ else
+ tgid = -1;
+
+ return tgid;
+}
+
+int trace_find_tgid(int pid)
+{
+ int tgid;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ tgid = __find_tgid_locked(pid);
+
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ return tgid;
+}
+
void tracing_record_cmdline(struct task_struct *tsk)
{
if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
@@ -2944,6 +2990,13 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
"# | | | | |\n");
}
+static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# TASK-PID TGID CPU# TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | | |\n");
+}
+
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
print_event_info(buf, m);
@@ -2956,6 +3009,18 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
"# | | | |||| | |\n");
}
+static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# _-----=> irqs-off\n");
+ seq_puts(m, "# / _----=> need-resched\n");
+ seq_puts(m, "# | / _---=> hardirq/softirq\n");
+ seq_puts(m, "# || / _--=> preempt-depth\n");
+ seq_puts(m, "# ||| / delay\n");
+ seq_puts(m, "# TASK-PID TGID CPU# |||| TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | |||| | |\n");
+}
+
void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
@@ -3269,9 +3334,15 @@ void trace_default_header(struct seq_file *m)
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_irq_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header_irq(iter->trace_buffer, m);
else
- print_func_help_header(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header(iter->trace_buffer, m);
}
}
}
@@ -4373,10 +4444,15 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
{
char buf[64];
int r;
+ unsigned int n;
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
- r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
+ n = savedcmd->cmdline_num;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ r = scnprintf(buf, sizeof(buf), "%u\n", n);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -4385,6 +4461,7 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
{
kfree(s->saved_cmdlines);
kfree(s->map_cmdline_to_pid);
+ kfree(s->map_cmdline_to_tgid);
kfree(s);
}
@@ -4401,10 +4478,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
return -ENOMEM;
}
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
savedcmd = s;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
free_saved_cmdlines_buffer(savedcmd_temp);
return 0;
@@ -4617,6 +4696,78 @@ static void trace_insert_enum_map(struct module *mod,
}
static ssize_t
+tracing_saved_tgids_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int i;
+ int *pids;
+ int n = 0;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ pids = kmalloc_array(savedcmd->cmdline_num, 2*sizeof(int), GFP_KERNEL);
+ if (!pids) {
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < savedcmd->cmdline_num; i++) {
+ int pid;
+
+ pid = savedcmd->map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ pids[n] = pid;
+ pids[n+1] = __find_tgid_locked(pid);
+ n += 2;
+ }
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ if (n == 0) {
+ kfree(pids);
+ return 0;
+ }
+
+ /* enough to hold max pair of pids + space, lr and nul */
+ len = n * 12;
+ file_buf = kmalloc(len, GFP_KERNEL);
+ if (!file_buf) {
+ kfree(pids);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+ for (i = 0; i < n && len > 0; i += 2) {
+ int r;
+
+ r = snprintf(buf, len, "%d %d\n", pids[i], pids[i+1]);
+ buf += r;
+ len -= r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, buf - file_buf);
+
+ kfree(file_buf);
+ kfree(pids);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_tgids_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_tgids_read,
+ .llseek = generic_file_llseek,
+};
+
+static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
@@ -7271,6 +7422,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
+ trace_create_file("saved_tgids", 0444, d_tracer,
+ tr, &tracing_saved_tgids_fops);
+
trace_create_file("trace_clock", 0644, d_tracer, tr,
&trace_clock_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d9b7910..1e8fd2d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -712,6 +712,7 @@ extern cycle_t ftrace_now(int cpu);
extern void trace_find_cmdline(int pid, char comm[]);
extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
+extern int trace_find_tgid(int pid);
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
@@ -1031,7 +1032,8 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
FUNCTION_FLAGS \
FGRAPH_FLAGS \
STACK_FLAGS \
- BRANCH_FLAGS
+ BRANCH_FLAGS \
+ C(TGID, "print-tgid"),
/*
* By defining C, we can make TRACE_FLAGS a list of bit names
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 01e7181..7461d51 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -65,6 +65,9 @@ struct fgraph_data {
#define TRACE_GRAPH_INDENT 2
+/* Flag options */
+#define TRACE_GRAPH_PRINT_FLAT 0x80
+
static unsigned int max_depth;
static struct tracer_opt trace_opts[] = {
@@ -88,6 +91,8 @@ static struct tracer_opt trace_opts[] = {
{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
/* Include time within nested functions */
{ TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) },
+ /* Use standard trace formatting rather than hierarchical */
+ { TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) },
{ } /* Empty entry */
};
@@ -1246,6 +1251,9 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
int cpu = iter->cpu;
int ret;
+ if (flags & TRACE_GRAPH_PRINT_FLAT)
+ return TRACE_TYPE_UNHANDLED;
+
if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
return TRACE_TYPE_HANDLED;
@@ -1303,13 +1311,6 @@ print_graph_function(struct trace_iterator *iter)
return print_graph_function_flags(iter, tracer_flags.val);
}
-static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags,
- struct trace_event *event)
-{
- return print_graph_function(iter);
-}
-
static void print_lat_header(struct seq_file *s, u32 flags)
{
static const char spaces[] = " " /* 16 spaces */
@@ -1378,6 +1379,11 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
struct trace_iterator *iter = s->private;
struct trace_array *tr = iter->tr;
+ if (flags & TRACE_GRAPH_PRINT_FLAT) {
+ trace_default_header(s);
+ return;
+ }
+
if (!(tr->trace_flags & TRACE_ITER_CONTEXT_INFO))
return;
@@ -1459,19 +1465,6 @@ func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
return 0;
}
-static struct trace_event_functions graph_functions = {
- .trace = print_graph_function_event,
-};
-
-static struct trace_event graph_trace_entry_event = {
- .type = TRACE_GRAPH_ENT,
- .funcs = &graph_functions,
-};
-
-static struct trace_event graph_trace_ret_event = {
- .type = TRACE_GRAPH_RET,
- .funcs = &graph_functions
-};
static struct tracer graph_trace __tracer_data = {
.name = "function_graph",
@@ -1548,16 +1541,6 @@ static __init int init_graph_trace(void)
{
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
- if (!register_trace_event(&graph_trace_entry_event)) {
- pr_warn("Warning: could not register graph trace events\n");
- return 1;
- }
-
- if (!register_trace_event(&graph_trace_ret_event)) {
- pr_warn("Warning: could not register graph trace events\n");
- return 1;
- }
-
return register_tracer(&graph_trace);
}
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 03cdff8..c180fe5 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -16,6 +16,10 @@
#include "trace.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/preemptirq.h>
+
+#if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER)
static struct trace_array *irqsoff_trace __read_mostly;
static int tracer_enabled __read_mostly;
@@ -451,63 +455,43 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1)
#else /* !CONFIG_PROVE_LOCKING */
/*
- * Stubs:
- */
-
-void trace_softirqs_on(unsigned long ip)
-{
-}
-
-void trace_softirqs_off(unsigned long ip)
-{
-}
-
-inline void print_irqtrace_events(struct task_struct *curr)
-{
-}
-
-/*
* We are only interested in hardirq on/off events:
*/
-void trace_hardirqs_on(void)
+static inline void tracer_hardirqs_on(void)
{
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
-EXPORT_SYMBOL(trace_hardirqs_on);
-void trace_hardirqs_off(void)
+static inline void tracer_hardirqs_off(void)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
-EXPORT_SYMBOL(trace_hardirqs_off);
-__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+static inline void tracer_hardirqs_on_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, caller_addr);
}
-EXPORT_SYMBOL(trace_hardirqs_on_caller);
-__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+static inline void tracer_hardirqs_off_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, caller_addr);
}
-EXPORT_SYMBOL(trace_hardirqs_off_caller);
#endif /* CONFIG_PROVE_LOCKING */
#endif /* CONFIG_IRQSOFF_TRACER */
#ifdef CONFIG_PREEMPT_TRACER
-void trace_preempt_on(unsigned long a0, unsigned long a1)
+static inline void tracer_preempt_on(unsigned long a0, unsigned long a1)
{
if (preempt_trace() && !irq_trace())
stop_critical_timing(a0, a1);
}
-void trace_preempt_off(unsigned long a0, unsigned long a1)
+static inline void tracer_preempt_off(unsigned long a0, unsigned long a1)
{
if (preempt_trace() && !irq_trace())
start_critical_timing(a0, a1);
@@ -769,3 +753,100 @@ __init static int init_irqsoff_tracer(void)
return 0;
}
core_initcall(init_irqsoff_tracer);
+#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */
+
+#ifndef CONFIG_IRQSOFF_TRACER
+static inline void tracer_hardirqs_on(void) { }
+static inline void tracer_hardirqs_off(void) { }
+static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { }
+static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { }
+#endif
+
+#ifndef CONFIG_PREEMPT_TRACER
+static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { }
+static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { }
+#endif
+
+/* Per-cpu variable to prevent redundant calls when IRQs already off */
+static DEFINE_PER_CPU(int, tracing_irq_cpu);
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PROVE_LOCKING)
+void trace_hardirqs_on(void)
+{
+ if (!this_cpu_read(tracing_irq_cpu))
+ return;
+
+ trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_on();
+
+ this_cpu_write(tracing_irq_cpu, 0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on);
+
+void trace_hardirqs_off(void)
+{
+ if (this_cpu_read(tracing_irq_cpu))
+ return;
+
+ this_cpu_write(tracing_irq_cpu, 1);
+
+ trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_off();
+}
+EXPORT_SYMBOL(trace_hardirqs_off);
+
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+{
+ if (!this_cpu_read(tracing_irq_cpu))
+ return;
+
+ trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
+ tracer_hardirqs_on_caller(caller_addr);
+
+ this_cpu_write(tracing_irq_cpu, 0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
+
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+{
+ if (this_cpu_read(tracing_irq_cpu))
+ return;
+
+ this_cpu_write(tracing_irq_cpu, 1);
+
+ trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
+ tracer_hardirqs_off_caller(caller_addr);
+}
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
+
+/*
+ * Stubs:
+ */
+
+void trace_softirqs_on(unsigned long ip)
+{
+}
+
+void trace_softirqs_off(unsigned long ip)
+{
+}
+
+inline void print_irqtrace_events(struct task_struct *curr)
+{
+}
+#endif
+
+#if defined(CONFIG_PREEMPT_TRACER) || \
+ (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
+void trace_preempt_on(unsigned long a0, unsigned long a1)
+{
+ trace_preempt_enable_rcuidle(a0, a1);
+ tracer_preempt_on(a0, a1);
+}
+
+void trace_preempt_off(unsigned long a0, unsigned long a1)
+{
+ trace_preempt_disable_rcuidle(a0, a1);
+ tracer_preempt_off(a0, a1);
+}
+#endif
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 3b4cd44..c49f046 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1142,13 +1142,12 @@ static void
kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct trace_event_call *call = &tk->tp.call;
- struct bpf_prog *prog = call->prog;
struct kprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
head = this_cpu_ptr(call->perf_events);
@@ -1178,13 +1177,12 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_event_call *call = &tk->tp.call;
- struct bpf_prog *prog = call->prog;
struct kretprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
head = this_cpu_ptr(call->perf_events);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 3fc2042..0346759 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -530,11 +530,21 @@ int trace_print_context(struct trace_iterator *iter)
unsigned long long t;
unsigned long secs, usec_rem;
char comm[TASK_COMM_LEN];
+ int tgid;
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+
+ if (tr->trace_flags & TRACE_ITER_TGID) {
+ tgid = trace_find_tgid(entry->pid);
+ if (tgid < 0)
+ trace_seq_puts(s, "(-----) ");
+ else
+ trace_seq_printf(s, "(%5d) ", tgid);
+ }
+
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
@@ -849,6 +859,174 @@ static struct trace_event trace_fn_event = {
.funcs = &trace_fn_funcs,
};
+/* TRACE_GRAPH_ENT */
+static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_puts(s, "graph_ent: func=");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->graph_ent.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ trace_seq_puts(s, "\n");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_printf(&iter->seq, "%lx %d\n",
+ field->graph_ent.func,
+ field->graph_ent.depth);
+ if (trace_seq_has_overflowed(&iter->seq))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD(s, field->graph_ent.func);
+ SEQ_PUT_HEX_FIELD(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD(s, field->graph_ent.func);
+ SEQ_PUT_FIELD(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ent_funcs = {
+ .trace = trace_graph_ent_trace,
+ .raw = trace_graph_ent_raw,
+ .hex = trace_graph_ent_hex,
+ .binary = trace_graph_ent_bin,
+};
+
+static struct trace_event trace_graph_ent_event = {
+ .type = TRACE_GRAPH_ENT,
+ .funcs = &trace_graph_ent_funcs,
+};
+
+/* TRACE_GRAPH_RET */
+static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, entry);
+
+ trace_seq_puts(s, "graph_ret: func=");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->ret.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ trace_seq_puts(s, "\n");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n",
+ field->ret.func,
+ field->ret.calltime,
+ field->ret.rettime,
+ field->ret.overrun,
+ field->ret.depth);
+ if (trace_seq_has_overflowed(&iter->seq))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD(s, field->ret.func);
+ SEQ_PUT_HEX_FIELD(s, field->ret.calltime);
+ SEQ_PUT_HEX_FIELD(s, field->ret.rettime);
+ SEQ_PUT_HEX_FIELD(s, field->ret.overrun);
+ SEQ_PUT_HEX_FIELD(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD(s, field->ret.func);
+ SEQ_PUT_FIELD(s, field->ret.calltime);
+ SEQ_PUT_FIELD(s, field->ret.rettime);
+ SEQ_PUT_FIELD(s, field->ret.overrun);
+ SEQ_PUT_FIELD(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ret_funcs = {
+ .trace = trace_graph_ret_trace,
+ .raw = trace_graph_ret_raw,
+ .hex = trace_graph_ret_hex,
+ .binary = trace_graph_ret_bin,
+};
+
+static struct trace_event trace_graph_ret_event = {
+ .type = TRACE_GRAPH_RET,
+ .funcs = &trace_graph_ret_funcs,
+};
+
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
@@ -1291,6 +1469,8 @@ static struct trace_event trace_print_event = {
static struct trace_event *events[] __initdata = {
&trace_fn_event,
+ &trace_graph_ent_event,
+ &trace_graph_ret_event,
&trace_ctx_event,
&trace_wake_event,
&trace_stack_event,
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e10395..8a90c45 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -564,6 +564,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
struct hlist_head *head;
+ bool valid_prog_array;
int syscall_nr;
int rctx;
int size;
@@ -579,7 +580,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
return;
head = this_cpu_ptr(sys_data->enter_event->perf_events);
- if (hlist_empty(head))
+ valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
+ if (!valid_prog_array && hlist_empty(head))
return;
/* get the size after alignment with the u32 buffer size field */
@@ -638,6 +640,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
struct hlist_head *head;
+ bool valid_prog_array;
int syscall_nr;
int rctx;
int size;
@@ -653,7 +656,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
return;
head = this_cpu_ptr(sys_data->exit_event->perf_events);
- if (hlist_empty(head))
+ valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
+ if (!valid_prog_array && hlist_empty(head))
return;
/* We can probably do that at build time */
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c6eee3d..6101dce 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -614,7 +614,7 @@ static int probes_seq_show(struct seq_file *m, void *v)
/* Don't print "0x (null)" when offset is 0 */
if (tu->offset) {
- seq_printf(m, "0x%p", (void *)tu->offset);
+ seq_printf(m, "0x%px", (void *)tu->offset);
} else {
switch (sizeof(void *)) {
case 4:
@@ -1119,13 +1119,12 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
{
struct trace_event_call *call = &tu->tp.call;
struct uprobe_trace_entry_head *entry;
- struct bpf_prog *prog = call->prog;
struct hlist_head *head;
void *data;
int size, esize;
int rctx;
- if (prog && !trace_call_bpf(prog, regs))
+ if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
return;
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
diff --git a/kernel/user.c b/kernel/user.c
index b069ccb..41e94e4 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
/*
@@ -201,6 +202,7 @@ struct user_struct *alloc_uid(kuid_t uid)
}
spin_unlock_irq(&uidhash_lock);
}
+ proc_register_uid(uid);
return up;
@@ -222,6 +224,7 @@ static int __init uid_cache_init(void)
spin_lock_irq(&uidhash_lock);
uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
spin_unlock_irq(&uidhash_lock);
+ proc_register_uid(GLOBAL_ROOT_UID);
return 0;
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 205c313..67df870 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -291,6 +291,8 @@ module_param_named(disable_numa, wq_disable_numa, bool, 0444);
static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
+bool wq_online; /* can kworkers be created yet? */
+
static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
@@ -910,6 +912,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
}
/**
+ * wq_worker_last_func - retrieve worker's last work function
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+ struct worker *worker = kthread_data(task);
+
+ return worker->last_func;
+}
+
+/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
@@ -2125,6 +2147,9 @@ __acquires(&pool->lock)
if (unlikely(cpu_intensive))
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
+ /* tag the worker for identification in schedule() */
+ worker->last_func = worker->current_func;
+
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
@@ -2587,6 +2612,9 @@ void flush_workqueue(struct workqueue_struct *wq)
};
int next_color;
+ if (WARN_ON(!wq_online))
+ return;
+
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
@@ -2847,6 +2875,9 @@ bool flush_work(struct work_struct *work)
{
struct wq_barrier barr;
+ if (WARN_ON(!wq_online))
+ return false;
+
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
@@ -2917,7 +2948,13 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
mark_work_canceling(work);
local_irq_restore(flags);
- flush_work(work);
+ /*
+ * This allows canceling during early boot. We know that @work
+ * isn't executing.
+ */
+ if (wq_online)
+ flush_work(work);
+
clear_work_data(work);
/*
@@ -3367,7 +3404,7 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
goto fail;
/* create and start the initial worker */
- if (!create_worker(pool))
+ if (wq_online && !create_worker(pool))
goto fail;
/* install */
@@ -3432,6 +3469,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
{
struct workqueue_struct *wq = pwq->wq;
bool freezable = wq->flags & WQ_FREEZABLE;
+ unsigned long flags;
/* for @wq->saved_max_active */
lockdep_assert_held(&wq->mutex);
@@ -3440,7 +3478,8 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
if (!freezable && pwq->max_active == wq->saved_max_active)
return;
- spin_lock_irq(&pwq->pool->lock);
+ /* this function can be called during early boot w/ irq disabled */
+ spin_lock_irqsave(&pwq->pool->lock, flags);
/*
* During [un]freezing, the caller is responsible for ensuring that
@@ -3470,7 +3509,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
pwq->max_active = 0;
}
- spin_unlock_irq(&pwq->pool->lock);
+ spin_unlock_irqrestore(&pwq->pool->lock, flags);
}
/* initialize newly alloced @pwq which is associated with @wq and @pool */
@@ -5536,7 +5575,17 @@ static void __init wq_numa_init(void)
wq_numa_enabled = true;
}
-static int __init init_workqueues(void)
+/**
+ * workqueue_init_early - early init for workqueue subsystem
+ *
+ * This is the first half of two-staged workqueue subsystem initialization
+ * and invoked as soon as the bare basics - memory allocation, cpumasks and
+ * idr are up. It sets up all the data structures and system workqueues
+ * and allows early boot code to create workqueues and queue/cancel work
+ * items. Actual work item execution starts only after kthreads can be
+ * created and scheduled right before early initcalls.
+ */
+int __init workqueue_init_early(void)
{
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int i, cpu;
@@ -5569,16 +5618,6 @@ static int __init init_workqueues(void)
}
}
- /* create the initial worker */
- for_each_online_cpu(cpu) {
- struct worker_pool *pool;
-
- for_each_cpu_worker_pool(pool, cpu) {
- pool->flags &= ~POOL_DISASSOCIATED;
- BUG_ON(!create_worker(pool));
- }
- }
-
/* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
@@ -5615,8 +5654,36 @@ static int __init init_workqueues(void)
!system_power_efficient_wq ||
!system_freezable_power_efficient_wq);
+ return 0;
+}
+
+/**
+ * workqueue_init - bring workqueue subsystem fully online
+ *
+ * This is the latter half of two-staged workqueue subsystem initialization
+ * and invoked as soon as kthreads can be created and scheduled.
+ * Workqueues have been created and work items queued on them, but there
+ * are no kworkers executing the work items yet. Populate the worker pools
+ * with the initial workers and enable future kworker creations.
+ */
+int __init workqueue_init(void)
+{
+ struct worker_pool *pool;
+ int cpu, bkt;
+
+ /* create the initial workers */
+ for_each_online_cpu(cpu) {
+ for_each_cpu_worker_pool(pool, cpu) {
+ pool->flags &= ~POOL_DISASSOCIATED;
+ BUG_ON(!create_worker(pool));
+ }
+ }
+
+ hash_for_each(unbound_pool_hash, bkt, pool, hash_node)
+ BUG_ON(!create_worker(pool));
+
+ wq_online = true;
wq_watchdog_init();
return 0;
}
-early_initcall(init_workqueues);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 29fa81f..c7f7db1 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -53,6 +53,9 @@ struct worker {
/* used only by rescuers to point to the target workqueue */
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
+
+ /* used by the scheduler to determine a worker's last known identity */
+ work_func_t last_func;
};
/**
@@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void)
/*
* Scheduler hooks for concurrency managed workqueue. Only to be used from
- * sched/core.c and workqueue.c.
+ * sched/ and workqueue.c.
*/
void wq_worker_waking_up(struct task_struct *task, int cpu);
struct task_struct *wq_worker_sleeping(struct task_struct *task);
+work_func_t wq_worker_last_func(struct task_struct *task);
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index 260a80e..8deab4f 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -185,6 +185,9 @@
when they need to do cyclic redundancy check according CRC8
algorithm. Module will be called crc8.
+config XXHASH
+ tristate
+
config AUDIT_GENERIC
bool
depends on AUDIT && !AUDIT_ARCH
@@ -239,6 +242,14 @@
config LZ4_DECOMPRESS
tristate
+config ZSTD_COMPRESS
+ select XXHASH
+ tristate
+
+config ZSTD_DECOMPRESS
+ select XXHASH
+ tristate
+
source "lib/xz/Kconfig"
#
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index bc5ff3a..93d7206 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -922,6 +922,15 @@
bool
default n
+config PANIC_ON_RT_THROTTLING
+ bool "Panic on RT throttling"
+ help
+ Say Y here to enable the kernel to panic when a realtime
+ runqueue is throttled. This may be useful for detecting
+ and debugging RT throttling issues.
+
+ Say N if unsure.
+
config SCHEDSTATS
bool "Collect scheduler statistics"
depends on DEBUG_KERNEL && PROC_FS
@@ -1963,6 +1972,16 @@
If unsure, say N.
+config BUG_ON_DATA_CORRUPTION
+ bool "Trigger a BUG when data corruption is detected"
+ select CONFIG_DEBUG_LIST
+ help
+ Select this option if the kernel should BUG when it encounters
+ data corruption in kernel memory structures when they get checked
+ for validity.
+
+ If unsure, say N.
+
source "samples/Kconfig"
source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index 7a55c52..42cbb83 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -19,7 +19,7 @@
lib-y := ctype.o string.o vsprintf.o cmdline.o \
rbtree.o radix-tree.o dump_stack.o timerqueue.o\
idr.o int_sqrt.o extable.o \
- sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
+ sha1.o chacha.o md5.o irq_regs.o argv_split.o \
flex_proportions.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
earlycpio.o seq_buf.o siphash.o \
@@ -95,6 +95,7 @@
obj-$(CONFIG_CRC7) += crc7.o
obj-$(CONFIG_LIBCRC32C) += libcrc32c.o
obj-$(CONFIG_CRC8) += crc8.o
+obj-$(CONFIG_XXHASH) += xxhash.o
obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
obj-$(CONFIG_842_COMPRESS) += 842/
@@ -108,6 +109,8 @@
obj-$(CONFIG_LZ4_COMPRESS) += lz4/
obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
+obj-$(CONFIG_ZSTD_COMPRESS) += zstd/
+obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
obj-$(CONFIG_XZ_DEC) += xz/
obj-$(CONFIG_RAID6_PQ) += raid6/
diff --git a/lib/bug.c b/lib/bug.c
index bc3656e..dc7aa6b 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -177,7 +177,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
if (file)
pr_crit("kernel BUG at %s:%u!\n", file, line);
else
- pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n",
+ pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n",
(void *)bugaddr);
return BUG_TRAP_TYPE_BUG;
diff --git a/lib/chacha.c b/lib/chacha.c
new file mode 100644
index 0000000..a46d283
--- /dev/null
+++ b/lib/chacha.c
@@ -0,0 +1,117 @@
+/*
+ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <linux/cryptohash.h>
+#include <asm/unaligned.h>
+#include <crypto/chacha.h>
+
+static void chacha_permute(u32 *x, int nrounds)
+{
+ int i;
+
+ /* whitelist the allowed round counts */
+ WARN_ON_ONCE(nrounds != 20 && nrounds != 12);
+
+ for (i = 0; i < nrounds; i += 2) {
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16);
+
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12);
+
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8);
+
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7);
+
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16);
+
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12);
+
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8);
+
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7);
+ }
+}
+
+/**
+ * chacha_block - generate one keystream block and increment block counter
+ * @state: input state matrix (16 32-bit words)
+ * @stream: output keystream block (64 bytes)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * This is the ChaCha core, a function from 64-byte strings to 64-byte strings.
+ * The caller has already converted the endianness of the input. This function
+ * also handles incrementing the block counter in the input matrix.
+ */
+void chacha_block(u32 *state, u8 *stream, int nrounds)
+{
+ u32 x[16];
+ int i;
+
+ memcpy(x, state, 64);
+
+ chacha_permute(x, nrounds);
+
+ for (i = 0; i < ARRAY_SIZE(x); i++)
+ put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
+
+ state[12]++;
+}
+EXPORT_SYMBOL(chacha_block);
+
+/**
+ * hchacha_block - abbreviated ChaCha core, for XChaCha
+ * @in: input state matrix (16 32-bit words)
+ * @out: output (8 32-bit words)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
+ * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha
+ * skips the final addition of the initial state, and outputs only certain words
+ * of the state. It should not be used for streaming directly.
+ */
+void hchacha_block(const u32 *in, u32 *out, int nrounds)
+{
+ u32 x[16];
+
+ memcpy(x, in, 64);
+
+ chacha_permute(x, nrounds);
+
+ memcpy(&out[0], &x[0], 16);
+ memcpy(&out[4], &x[12], 16);
+}
+EXPORT_SYMBOL(hchacha_block);
diff --git a/lib/chacha20.c b/lib/chacha20.c
deleted file mode 100644
index 250ceed..0000000
--- a/lib/chacha20.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/bitops.h>
-#include <linux/cryptohash.h>
-#include <asm/unaligned.h>
-#include <crypto/chacha20.h>
-
-static inline u32 rotl32(u32 v, u8 n)
-{
- return (v << n) | (v >> (sizeof(v) * 8 - n));
-}
-
-extern void chacha20_block(u32 *state, void *stream)
-{
- u32 x[16], *out = stream;
- int i;
-
- for (i = 0; i < ARRAY_SIZE(x); i++)
- x[i] = state[i];
-
- for (i = 0; i < 20; i += 2) {
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 16);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 16);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 16);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 16);
-
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 12);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 12);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 12);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 12);
-
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 8);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 8);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 8);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 8);
-
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 7);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 7);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 7);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 7);
-
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 16);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 16);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 16);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 16);
-
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 12);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 12);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 12);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 12);
-
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 8);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 8);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 8);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 8);
-
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 7);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 7);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 7);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 7);
- }
-
- for (i = 0; i < ARRAY_SIZE(x); i++)
- out[i] = cpu_to_le32(x[i] + state[i]);
-
- state[12]++;
-}
-EXPORT_SYMBOL(chacha20_block);
diff --git a/lib/digsig.c b/lib/digsig.c
index a876156..6ba6fcd 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -85,7 +85,7 @@ static int digsig_verify_rsa(struct key *key,
struct pubkey_hdr *pkh;
down_read(&key->sem);
- ukp = user_key_payload(key);
+ ukp = user_key_payload_locked(key);
if (!ukp) {
/* key was revoked before we acquired its semaphore */
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 3859bf6..a34db8d 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -2,8 +2,7 @@
* Copyright 2006, Red Hat, Inc., Dave Jones
* Released under the General Public License (GPL).
*
- * This file contains the linked list implementations for
- * DEBUG_LIST.
+ * This file contains the linked list validation for DEBUG_LIST.
*/
#include <linux/export.h>
@@ -13,88 +12,51 @@
#include <linux/rculist.h>
/*
- * Insert a new entry between two known consecutive entries.
- *
- * This is only for internal list manipulation where we know
- * the prev/next entries already!
+ * Check that the data structures for the list manipulations are reasonably
+ * valid. Failures here indicate memory corruption (and possibly an exploit
+ * attempt).
*/
-void __list_add(struct list_head *new,
- struct list_head *prev,
- struct list_head *next)
+bool __list_add_valid(struct list_head *new, struct list_head *prev,
+ struct list_head *next)
{
- WARN(next->prev != prev,
- "list_add corruption. next->prev should be "
- "prev (%p), but was %p. (next=%p).\n",
- prev, next->prev, next);
- WARN(prev->next != next,
- "list_add corruption. prev->next should be "
- "next (%p), but was %p. (prev=%p).\n",
- next, prev->next, prev);
- WARN(new == prev || new == next,
- "list_add double add: new=%p, prev=%p, next=%p.\n",
- new, prev, next);
- next->prev = new;
- new->next = next;
- new->prev = prev;
- WRITE_ONCE(prev->next, new);
-}
-EXPORT_SYMBOL(__list_add);
+ if (CHECK_DATA_CORRUPTION(next->prev != prev,
+ "list_add corruption. next->prev should be prev (%p), but was %p. (next=%p).\n",
+ prev, next->prev, next) ||
+ CHECK_DATA_CORRUPTION(prev->next != next,
+ "list_add corruption. prev->next should be next (%p), but was %p. (prev=%p).\n",
+ next, prev->next, prev) ||
+ CHECK_DATA_CORRUPTION(new == prev || new == next,
+ "list_add double add: new=%p, prev=%p, next=%p.\n",
+ new, prev, next))
+ return false;
-void __list_del_entry(struct list_head *entry)
+ return true;
+}
+EXPORT_SYMBOL(__list_add_valid);
+
+bool __list_del_entry_valid(struct list_head *entry)
{
struct list_head *prev, *next;
prev = entry->prev;
next = entry->next;
- if (WARN(next == LIST_POISON1,
- "list_del corruption, %p->next is LIST_POISON1 (%p)\n",
- entry, LIST_POISON1) ||
- WARN(prev == LIST_POISON2,
- "list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
- entry, LIST_POISON2) ||
- WARN(prev->next != entry,
- "list_del corruption. prev->next should be %p, "
- "but was %p\n", entry, prev->next) ||
- WARN(next->prev != entry,
- "list_del corruption. next->prev should be %p, "
- "but was %p\n", entry, next->prev))
- return;
+ if (CHECK_DATA_CORRUPTION(next == LIST_POISON1,
+ "list_del corruption, %p->next is LIST_POISON1 (%p)\n",
+ entry, LIST_POISON1) ||
+ CHECK_DATA_CORRUPTION(prev == LIST_POISON2,
+ "list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
+ entry, LIST_POISON2) ||
+ CHECK_DATA_CORRUPTION(prev->next != entry,
+ "list_del corruption. prev->next should be %p, but was %p\n",
+ entry, prev->next) ||
+ CHECK_DATA_CORRUPTION(next->prev != entry,
+ "list_del corruption. next->prev should be %p, but was %p\n",
+ entry, next->prev))
+ return false;
- __list_del(prev, next);
-}
-EXPORT_SYMBOL(__list_del_entry);
+ return true;
-/**
- * list_del - deletes entry from list.
- * @entry: the element to delete from the list.
- * Note: list_empty on entry does not return true after this, the entry is
- * in an undefined state.
- */
-void list_del(struct list_head *entry)
-{
- __list_del_entry(entry);
- entry->next = LIST_POISON1;
- entry->prev = LIST_POISON2;
}
-EXPORT_SYMBOL(list_del);
-
-/*
- * RCU variants.
- */
-void __list_add_rcu(struct list_head *new,
- struct list_head *prev, struct list_head *next)
-{
- WARN(next->prev != prev,
- "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n",
- prev, next->prev, next);
- WARN(prev->next != next,
- "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n",
- next, prev->next, prev);
- new->next = next;
- new->prev = prev;
- rcu_assign_pointer(list_next_rcu(prev), new);
- next->prev = new;
-}
-EXPORT_SYMBOL(__list_add_rcu);
+EXPORT_SYMBOL(__list_del_entry_valid);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 6e76a448..c0b65e0 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -19,6 +19,7 @@
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/module.h>
+#include <linux/kasan.h>
/*
* Note: test functions are marked noinline so that their names appear in
@@ -440,8 +441,34 @@ static noinline void __init use_after_scope_test(void)
p[1023] = 1;
}
+static noinline void __init kasan_alloca_oob_left(void)
+{
+ volatile int i = 10;
+ char alloca_array[i];
+ char *p = alloca_array - 1;
+
+ pr_info("out-of-bounds to left on alloca\n");
+ *(volatile char *)p;
+}
+
+static noinline void __init kasan_alloca_oob_right(void)
+{
+ volatile int i = 10;
+ char alloca_array[i];
+ char *p = alloca_array + i;
+
+ pr_info("out-of-bounds to right on alloca\n");
+ *(volatile char *)p;
+}
+
static int __init kmalloc_tests_init(void)
{
+ /*
+ * Temporarily enable multi-shot mode. Otherwise, we'd only get a
+ * report for the first case.
+ */
+ bool multishot = kasan_save_enable_multi_shot();
+
kmalloc_oob_right();
kmalloc_oob_left();
kmalloc_node_oob_right();
@@ -463,9 +490,14 @@ static int __init kmalloc_tests_init(void)
kmem_cache_oob();
kasan_stack_oob();
kasan_global_oob();
+ kasan_alloca_oob_left();
+ kasan_alloca_oob_right();
ksize_unpoisons_memory();
copy_user_test();
use_after_scope_test();
+
+ kasan_restore_multi_shot(multishot);
+
return -EAGAIN;
}
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 563f10e..71ebfa4 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -24,24 +24,6 @@
#define PAD_SIZE 16
#define FILL_CHAR '$'
-#define PTR1 ((void*)0x01234567)
-#define PTR2 ((void*)(long)(int)0xfedcba98)
-
-#if BITS_PER_LONG == 64
-#define PTR1_ZEROES "000000000"
-#define PTR1_SPACES " "
-#define PTR1_STR "1234567"
-#define PTR2_STR "fffffffffedcba98"
-#define PTR_WIDTH 16
-#else
-#define PTR1_ZEROES "0"
-#define PTR1_SPACES " "
-#define PTR1_STR "1234567"
-#define PTR2_STR "fedcba98"
-#define PTR_WIDTH 8
-#endif
-#define PTR_WIDTH_STR stringify(PTR_WIDTH)
-
static unsigned total_tests __initdata;
static unsigned failed_tests __initdata;
static char *test_buffer __initdata;
@@ -217,30 +199,79 @@ test_string(void)
test("a | | ", "%-3.s|%-3.0s|%-3.*s", "a", "b", 0, "c");
}
+#define PLAIN_BUF_SIZE 64 /* leave some space so we don't oops */
+
+#if BITS_PER_LONG == 64
+
+#define PTR_WIDTH 16
+#define PTR ((void *)0xffff0123456789ab)
+#define PTR_STR "ffff0123456789ab"
+#define ZEROS "00000000" /* hex 32 zero bits */
+
+static int __init
+plain_format(void)
+{
+ char buf[PLAIN_BUF_SIZE];
+ int nchars;
+
+ nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
+
+ if (nchars != PTR_WIDTH || strncmp(buf, ZEROS, strlen(ZEROS)) != 0)
+ return -1;
+
+ return 0;
+}
+
+#else
+
+#define PTR_WIDTH 8
+#define PTR ((void *)0x456789ab)
+#define PTR_STR "456789ab"
+
+static int __init
+plain_format(void)
+{
+ /* Format is implicitly tested for 32 bit machines by plain_hash() */
+ return 0;
+}
+
+#endif /* BITS_PER_LONG == 64 */
+
+static int __init
+plain_hash(void)
+{
+ char buf[PLAIN_BUF_SIZE];
+ int nchars;
+
+ nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
+
+ if (nchars != PTR_WIDTH || strncmp(buf, PTR_STR, PTR_WIDTH) == 0)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * We can't use test() to test %p because we don't know what output to expect
+ * after an address is hashed.
+ */
static void __init
plain(void)
{
- test(PTR1_ZEROES PTR1_STR " " PTR2_STR, "%p %p", PTR1, PTR2);
- /*
- * The field width is overloaded for some %p extensions to
- * pass another piece of information. For plain pointers, the
- * behaviour is slightly odd: One cannot pass either the 0
- * flag nor a precision to %p without gcc complaining, and if
- * one explicitly gives a field width, the number is no longer
- * zero-padded.
- */
- test("|" PTR1_STR PTR1_SPACES " | " PTR1_SPACES PTR1_STR "|",
- "|%-*p|%*p|", PTR_WIDTH+2, PTR1, PTR_WIDTH+2, PTR1);
- test("|" PTR2_STR " | " PTR2_STR "|",
- "|%-*p|%*p|", PTR_WIDTH+2, PTR2, PTR_WIDTH+2, PTR2);
+ int err;
- /*
- * Unrecognized %p extensions are treated as plain %p, but the
- * alphanumeric suffix is ignored (that is, does not occur in
- * the output.)
- */
- test("|"PTR1_ZEROES PTR1_STR"|", "|%p0y|", PTR1);
- test("|"PTR2_STR"|", "|%p0y|", PTR2);
+ err = plain_hash();
+ if (err) {
+ pr_warn("plain 'p' does not appear to be hashed\n");
+ failed_tests++;
+ return;
+ }
+
+ err = plain_format();
+ if (err) {
+ pr_warn("hashing plain 'p' has unexpected format\n");
+ failed_tests++;
+ }
}
static void __init
@@ -251,6 +282,7 @@ symbol_ptr(void)
static void __init
kernel_ptr(void)
{
+ /* We can't test this without access to kptr_restrict. */
}
static void __init
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 79ba3cc..43f9b90 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -32,6 +32,8 @@
#include <linux/cred.h>
#include <linux/uuid.h>
#include <net/addrconf.h>
+#include <linux/siphash.h>
+#include <linux/compiler.h>
#ifdef CONFIG_BLOCK
#include <linux/blkdev.h>
#endif
@@ -1342,6 +1344,59 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
return string(buf, end, uuid, spec);
}
+int kptr_restrict __read_mostly;
+
+static noinline_for_stack
+char *restricted_pointer(char *buf, char *end, const void *ptr,
+ struct printf_spec spec)
+{
+ spec.base = 16;
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = 2 * sizeof(ptr);
+ spec.flags |= ZEROPAD;
+ }
+
+ switch (kptr_restrict) {
+ case 0:
+ /* Always print %pK values */
+ break;
+ case 1: {
+ const struct cred *cred;
+
+ /*
+ * kptr_restrict==1 cannot be used in IRQ context
+ * because its test for CAP_SYSLOG would be meaningless.
+ */
+ if (in_irq() || in_serving_softirq() || in_nmi())
+ return string(buf, end, "pK-error", spec);
+
+ /*
+ * Only print the real pointer value if the current
+ * process has CAP_SYSLOG and is running with the
+ * same credentials it started with. This is because
+ * access to files is checked at open() time, but %pK
+ * checks permission at read() time. We don't want to
+ * leak pointer values if a binary opens a file using
+ * %pK and then elevates privileges before reading it.
+ */
+ cred = current_cred();
+ if (!has_capability_noaudit(current, CAP_SYSLOG) ||
+ !uid_eq(cred->euid, cred->uid) ||
+ !gid_eq(cred->egid, cred->gid))
+ ptr = NULL;
+ break;
+ }
+ case 2:
+ default:
+ /* Always print 0's for %pK */
+ ptr = NULL;
+ break;
+ }
+
+ return number(buf, end, (unsigned long)ptr, spec);
+}
+
static noinline_for_stack
char *netdev_bits(char *buf, char *end, const void *addr, const char *fmt)
{
@@ -1467,7 +1522,86 @@ char *flags_string(char *buf, char *end, void *flags_ptr, const char *fmt)
return format_flags(buf, end, flags, names);
}
-int kptr_restrict __read_mostly;
+static noinline_for_stack
+char *pointer_string(char *buf, char *end, const void *ptr,
+ struct printf_spec spec)
+{
+ spec.base = 16;
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = 2 * sizeof(ptr);
+ spec.flags |= ZEROPAD;
+ }
+
+ return number(buf, end, (unsigned long int)ptr, spec);
+}
+
+static bool have_filled_random_ptr_key __read_mostly;
+static siphash_key_t ptr_key __read_mostly;
+
+static void fill_random_ptr_key(struct random_ready_callback *unused)
+{
+ get_random_bytes(&ptr_key, sizeof(ptr_key));
+ /*
+ * have_filled_random_ptr_key==true is dependent on get_random_bytes().
+ * ptr_to_id() needs to see have_filled_random_ptr_key==true
+ * after get_random_bytes() returns.
+ */
+ smp_mb();
+ WRITE_ONCE(have_filled_random_ptr_key, true);
+}
+
+static struct random_ready_callback random_ready = {
+ .func = fill_random_ptr_key
+};
+
+static int __init initialize_ptr_random(void)
+{
+ int ret = add_random_ready_callback(&random_ready);
+
+ if (!ret) {
+ return 0;
+ } else if (ret == -EALREADY) {
+ fill_random_ptr_key(&random_ready);
+ return 0;
+ }
+
+ return ret;
+}
+early_initcall(initialize_ptr_random);
+
+/* Maps a pointer to a 32 bit unique identifier. */
+static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
+{
+ unsigned long hashval;
+ const int default_width = 2 * sizeof(ptr);
+
+ if (unlikely(!have_filled_random_ptr_key)) {
+ spec.field_width = default_width;
+ /* string length must be less than default_width */
+ return string(buf, end, "(ptrval)", spec);
+ }
+
+#ifdef CONFIG_64BIT
+ hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key);
+ /*
+ * Mask off the first 32 bits, this makes explicit that we have
+ * modified the address (and 32 bits is plenty for a unique ID).
+ */
+ hashval = hashval & 0xffffffff;
+#else
+ hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key);
+#endif
+
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = default_width;
+ spec.flags |= ZEROPAD;
+ }
+ spec.base = 16;
+
+ return number(buf, end, hashval, spec);
+}
/*
* Show a '%p' thing. A kernel extension is that the '%p' is followed
@@ -1561,11 +1695,16 @@ int kptr_restrict __read_mostly;
* g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t
* v vma flags (VM_*) given as pointer to unsigned long
*
+ * - 'x' For printing the address. Equivalent to "%lx".
+ *
* ** Please update also Documentation/printk-formats.txt when making changes **
*
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
* pointer to the real address.
+ *
+ * Note: The default behaviour (unadorned %p) is to hash the address,
+ * rendering it useful as a unique identifier.
*/
static noinline_for_stack
char *pointer(const char *fmt, char *buf, char *end, void *ptr,
@@ -1655,47 +1794,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
return buf;
}
case 'K':
- switch (kptr_restrict) {
- case 0:
- /* Always print %pK values */
- break;
- case 1: {
- const struct cred *cred;
-
- /*
- * kptr_restrict==1 cannot be used in IRQ context
- * because its test for CAP_SYSLOG would be meaningless.
- */
- if (in_irq() || in_serving_softirq() || in_nmi()) {
- if (spec.field_width == -1)
- spec.field_width = default_width;
- return string(buf, end, "pK-error", spec);
- }
-
- /*
- * Only print the real pointer value if the current
- * process has CAP_SYSLOG and is running with the
- * same credentials it started with. This is because
- * access to files is checked at open() time, but %pK
- * checks permission at read() time. We don't want to
- * leak pointer values if a binary opens a file using
- * %pK and then elevates privileges before reading it.
- */
- cred = current_cred();
- if (!has_capability_noaudit(current, CAP_SYSLOG) ||
- !uid_eq(cred->euid, cred->uid) ||
- !gid_eq(cred->egid, cred->gid))
- ptr = NULL;
- break;
- }
- case 2:
- default:
- /* Always print 0's for %pK */
- ptr = NULL;
- break;
- }
- break;
-
+ return restricted_pointer(buf, end, ptr, spec);
case 'N':
return netdev_bits(buf, end, ptr, fmt);
case 'a':
@@ -1715,15 +1814,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
case 'G':
return flags_string(buf, end, ptr, fmt);
+ case 'x':
+ return pointer_string(buf, end, ptr, spec);
}
- spec.flags |= SMALL;
- if (spec.field_width == -1) {
- spec.field_width = default_width;
- spec.flags |= ZEROPAD;
- }
- spec.base = 16;
- return number(buf, end, (unsigned long) ptr, spec);
+ /* default is to _not_ leak addresses, hash before printing */
+ return ptr_to_id(buf, end, ptr, spec);
}
/*
diff --git a/lib/xxhash.c b/lib/xxhash.c
new file mode 100644
index 0000000..aa61e2a
--- /dev/null
+++ b/lib/xxhash.c
@@ -0,0 +1,500 @@
+/*
+ * xxHash - Extremely Fast Hash algorithm
+ * Copyright (C) 2012-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at:
+ * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash source repository: https://github.com/Cyan4973/xxHash
+ */
+
+#include <asm/unaligned.h>
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/xxhash.h>
+
+/*-*************************************
+ * Macros
+ **************************************/
+#define xxh_rotl32(x, r) ((x << r) | (x >> (32 - r)))
+#define xxh_rotl64(x, r) ((x << r) | (x >> (64 - r)))
+
+#ifdef __LITTLE_ENDIAN
+# define XXH_CPU_LITTLE_ENDIAN 1
+#else
+# define XXH_CPU_LITTLE_ENDIAN 0
+#endif
+
+/*-*************************************
+ * Constants
+ **************************************/
+static const uint32_t PRIME32_1 = 2654435761U;
+static const uint32_t PRIME32_2 = 2246822519U;
+static const uint32_t PRIME32_3 = 3266489917U;
+static const uint32_t PRIME32_4 = 668265263U;
+static const uint32_t PRIME32_5 = 374761393U;
+
+static const uint64_t PRIME64_1 = 11400714785074694791ULL;
+static const uint64_t PRIME64_2 = 14029467366897019727ULL;
+static const uint64_t PRIME64_3 = 1609587929392839161ULL;
+static const uint64_t PRIME64_4 = 9650029242287828579ULL;
+static const uint64_t PRIME64_5 = 2870177450012600261ULL;
+
+/*-**************************
+ * Utils
+ ***************************/
+void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src)
+{
+ memcpy(dst, src, sizeof(*dst));
+}
+EXPORT_SYMBOL(xxh32_copy_state);
+
+void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src)
+{
+ memcpy(dst, src, sizeof(*dst));
+}
+EXPORT_SYMBOL(xxh64_copy_state);
+
+/*-***************************
+ * Simple Hash Functions
+ ****************************/
+static uint32_t xxh32_round(uint32_t seed, const uint32_t input)
+{
+ seed += input * PRIME32_2;
+ seed = xxh_rotl32(seed, 13);
+ seed *= PRIME32_1;
+ return seed;
+}
+
+uint32_t xxh32(const void *input, const size_t len, const uint32_t seed)
+{
+ const uint8_t *p = (const uint8_t *)input;
+ const uint8_t *b_end = p + len;
+ uint32_t h32;
+
+ if (len >= 16) {
+ const uint8_t *const limit = b_end - 16;
+ uint32_t v1 = seed + PRIME32_1 + PRIME32_2;
+ uint32_t v2 = seed + PRIME32_2;
+ uint32_t v3 = seed + 0;
+ uint32_t v4 = seed - PRIME32_1;
+
+ do {
+ v1 = xxh32_round(v1, get_unaligned_le32(p));
+ p += 4;
+ v2 = xxh32_round(v2, get_unaligned_le32(p));
+ p += 4;
+ v3 = xxh32_round(v3, get_unaligned_le32(p));
+ p += 4;
+ v4 = xxh32_round(v4, get_unaligned_le32(p));
+ p += 4;
+ } while (p <= limit);
+
+ h32 = xxh_rotl32(v1, 1) + xxh_rotl32(v2, 7) +
+ xxh_rotl32(v3, 12) + xxh_rotl32(v4, 18);
+ } else {
+ h32 = seed + PRIME32_5;
+ }
+
+ h32 += (uint32_t)len;
+
+ while (p + 4 <= b_end) {
+ h32 += get_unaligned_le32(p) * PRIME32_3;
+ h32 = xxh_rotl32(h32, 17) * PRIME32_4;
+ p += 4;
+ }
+
+ while (p < b_end) {
+ h32 += (*p) * PRIME32_5;
+ h32 = xxh_rotl32(h32, 11) * PRIME32_1;
+ p++;
+ }
+
+ h32 ^= h32 >> 15;
+ h32 *= PRIME32_2;
+ h32 ^= h32 >> 13;
+ h32 *= PRIME32_3;
+ h32 ^= h32 >> 16;
+
+ return h32;
+}
+EXPORT_SYMBOL(xxh32);
+
+static uint64_t xxh64_round(uint64_t acc, const uint64_t input)
+{
+ acc += input * PRIME64_2;
+ acc = xxh_rotl64(acc, 31);
+ acc *= PRIME64_1;
+ return acc;
+}
+
+static uint64_t xxh64_merge_round(uint64_t acc, uint64_t val)
+{
+ val = xxh64_round(0, val);
+ acc ^= val;
+ acc = acc * PRIME64_1 + PRIME64_4;
+ return acc;
+}
+
+uint64_t xxh64(const void *input, const size_t len, const uint64_t seed)
+{
+ const uint8_t *p = (const uint8_t *)input;
+ const uint8_t *const b_end = p + len;
+ uint64_t h64;
+
+ if (len >= 32) {
+ const uint8_t *const limit = b_end - 32;
+ uint64_t v1 = seed + PRIME64_1 + PRIME64_2;
+ uint64_t v2 = seed + PRIME64_2;
+ uint64_t v3 = seed + 0;
+ uint64_t v4 = seed - PRIME64_1;
+
+ do {
+ v1 = xxh64_round(v1, get_unaligned_le64(p));
+ p += 8;
+ v2 = xxh64_round(v2, get_unaligned_le64(p));
+ p += 8;
+ v3 = xxh64_round(v3, get_unaligned_le64(p));
+ p += 8;
+ v4 = xxh64_round(v4, get_unaligned_le64(p));
+ p += 8;
+ } while (p <= limit);
+
+ h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) +
+ xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18);
+ h64 = xxh64_merge_round(h64, v1);
+ h64 = xxh64_merge_round(h64, v2);
+ h64 = xxh64_merge_round(h64, v3);
+ h64 = xxh64_merge_round(h64, v4);
+
+ } else {
+ h64 = seed + PRIME64_5;
+ }
+
+ h64 += (uint64_t)len;
+
+ while (p + 8 <= b_end) {
+ const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p));
+
+ h64 ^= k1;
+ h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4;
+ p += 8;
+ }
+
+ if (p + 4 <= b_end) {
+ h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1;
+ h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
+ p += 4;
+ }
+
+ while (p < b_end) {
+ h64 ^= (*p) * PRIME64_5;
+ h64 = xxh_rotl64(h64, 11) * PRIME64_1;
+ p++;
+ }
+
+ h64 ^= h64 >> 33;
+ h64 *= PRIME64_2;
+ h64 ^= h64 >> 29;
+ h64 *= PRIME64_3;
+ h64 ^= h64 >> 32;
+
+ return h64;
+}
+EXPORT_SYMBOL(xxh64);
+
+/*-**************************************************
+ * Advanced Hash Functions
+ ***************************************************/
+void xxh32_reset(struct xxh32_state *statePtr, const uint32_t seed)
+{
+ /* use a local state for memcpy() to avoid strict-aliasing warnings */
+ struct xxh32_state state;
+
+ memset(&state, 0, sizeof(state));
+ state.v1 = seed + PRIME32_1 + PRIME32_2;
+ state.v2 = seed + PRIME32_2;
+ state.v3 = seed + 0;
+ state.v4 = seed - PRIME32_1;
+ memcpy(statePtr, &state, sizeof(state));
+}
+EXPORT_SYMBOL(xxh32_reset);
+
+void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed)
+{
+ /* use a local state for memcpy() to avoid strict-aliasing warnings */
+ struct xxh64_state state;
+
+ memset(&state, 0, sizeof(state));
+ state.v1 = seed + PRIME64_1 + PRIME64_2;
+ state.v2 = seed + PRIME64_2;
+ state.v3 = seed + 0;
+ state.v4 = seed - PRIME64_1;
+ memcpy(statePtr, &state, sizeof(state));
+}
+EXPORT_SYMBOL(xxh64_reset);
+
+int xxh32_update(struct xxh32_state *state, const void *input, const size_t len)
+{
+ const uint8_t *p = (const uint8_t *)input;
+ const uint8_t *const b_end = p + len;
+
+ if (input == NULL)
+ return -EINVAL;
+
+ state->total_len_32 += (uint32_t)len;
+ state->large_len |= (len >= 16) | (state->total_len_32 >= 16);
+
+ if (state->memsize + len < 16) { /* fill in tmp buffer */
+ memcpy((uint8_t *)(state->mem32) + state->memsize, input, len);
+ state->memsize += (uint32_t)len;
+ return 0;
+ }
+
+ if (state->memsize) { /* some data left from previous update */
+ const uint32_t *p32 = state->mem32;
+
+ memcpy((uint8_t *)(state->mem32) + state->memsize, input,
+ 16 - state->memsize);
+
+ state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32));
+ p32++;
+ state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32));
+ p32++;
+ state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32));
+ p32++;
+ state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32));
+ p32++;
+
+ p += 16-state->memsize;
+ state->memsize = 0;
+ }
+
+ if (p <= b_end - 16) {
+ const uint8_t *const limit = b_end - 16;
+ uint32_t v1 = state->v1;
+ uint32_t v2 = state->v2;
+ uint32_t v3 = state->v3;
+ uint32_t v4 = state->v4;
+
+ do {
+ v1 = xxh32_round(v1, get_unaligned_le32(p));
+ p += 4;
+ v2 = xxh32_round(v2, get_unaligned_le32(p));
+ p += 4;
+ v3 = xxh32_round(v3, get_unaligned_le32(p));
+ p += 4;
+ v4 = xxh32_round(v4, get_unaligned_le32(p));
+ p += 4;
+ } while (p <= limit);
+
+ state->v1 = v1;
+ state->v2 = v2;
+ state->v3 = v3;
+ state->v4 = v4;
+ }
+
+ if (p < b_end) {
+ memcpy(state->mem32, p, (size_t)(b_end-p));
+ state->memsize = (uint32_t)(b_end-p);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(xxh32_update);
+
+uint32_t xxh32_digest(const struct xxh32_state *state)
+{
+ const uint8_t *p = (const uint8_t *)state->mem32;
+ const uint8_t *const b_end = (const uint8_t *)(state->mem32) +
+ state->memsize;
+ uint32_t h32;
+
+ if (state->large_len) {
+ h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) +
+ xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18);
+ } else {
+ h32 = state->v3 /* == seed */ + PRIME32_5;
+ }
+
+ h32 += state->total_len_32;
+
+ while (p + 4 <= b_end) {
+ h32 += get_unaligned_le32(p) * PRIME32_3;
+ h32 = xxh_rotl32(h32, 17) * PRIME32_4;
+ p += 4;
+ }
+
+ while (p < b_end) {
+ h32 += (*p) * PRIME32_5;
+ h32 = xxh_rotl32(h32, 11) * PRIME32_1;
+ p++;
+ }
+
+ h32 ^= h32 >> 15;
+ h32 *= PRIME32_2;
+ h32 ^= h32 >> 13;
+ h32 *= PRIME32_3;
+ h32 ^= h32 >> 16;
+
+ return h32;
+}
+EXPORT_SYMBOL(xxh32_digest);
+
+int xxh64_update(struct xxh64_state *state, const void *input, const size_t len)
+{
+ const uint8_t *p = (const uint8_t *)input;
+ const uint8_t *const b_end = p + len;
+
+ if (input == NULL)
+ return -EINVAL;
+
+ state->total_len += len;
+
+ if (state->memsize + len < 32) { /* fill in tmp buffer */
+ memcpy(((uint8_t *)state->mem64) + state->memsize, input, len);
+ state->memsize += (uint32_t)len;
+ return 0;
+ }
+
+ if (state->memsize) { /* tmp buffer is full */
+ uint64_t *p64 = state->mem64;
+
+ memcpy(((uint8_t *)p64) + state->memsize, input,
+ 32 - state->memsize);
+
+ state->v1 = xxh64_round(state->v1, get_unaligned_le64(p64));
+ p64++;
+ state->v2 = xxh64_round(state->v2, get_unaligned_le64(p64));
+ p64++;
+ state->v3 = xxh64_round(state->v3, get_unaligned_le64(p64));
+ p64++;
+ state->v4 = xxh64_round(state->v4, get_unaligned_le64(p64));
+
+ p += 32 - state->memsize;
+ state->memsize = 0;
+ }
+
+ if (p + 32 <= b_end) {
+ const uint8_t *const limit = b_end - 32;
+ uint64_t v1 = state->v1;
+ uint64_t v2 = state->v2;
+ uint64_t v3 = state->v3;
+ uint64_t v4 = state->v4;
+
+ do {
+ v1 = xxh64_round(v1, get_unaligned_le64(p));
+ p += 8;
+ v2 = xxh64_round(v2, get_unaligned_le64(p));
+ p += 8;
+ v3 = xxh64_round(v3, get_unaligned_le64(p));
+ p += 8;
+ v4 = xxh64_round(v4, get_unaligned_le64(p));
+ p += 8;
+ } while (p <= limit);
+
+ state->v1 = v1;
+ state->v2 = v2;
+ state->v3 = v3;
+ state->v4 = v4;
+ }
+
+ if (p < b_end) {
+ memcpy(state->mem64, p, (size_t)(b_end-p));
+ state->memsize = (uint32_t)(b_end - p);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(xxh64_update);
+
+uint64_t xxh64_digest(const struct xxh64_state *state)
+{
+ const uint8_t *p = (const uint8_t *)state->mem64;
+ const uint8_t *const b_end = (const uint8_t *)state->mem64 +
+ state->memsize;
+ uint64_t h64;
+
+ if (state->total_len >= 32) {
+ const uint64_t v1 = state->v1;
+ const uint64_t v2 = state->v2;
+ const uint64_t v3 = state->v3;
+ const uint64_t v4 = state->v4;
+
+ h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) +
+ xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18);
+ h64 = xxh64_merge_round(h64, v1);
+ h64 = xxh64_merge_round(h64, v2);
+ h64 = xxh64_merge_round(h64, v3);
+ h64 = xxh64_merge_round(h64, v4);
+ } else {
+ h64 = state->v3 + PRIME64_5;
+ }
+
+ h64 += (uint64_t)state->total_len;
+
+ while (p + 8 <= b_end) {
+ const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p));
+
+ h64 ^= k1;
+ h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4;
+ p += 8;
+ }
+
+ if (p + 4 <= b_end) {
+ h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1;
+ h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
+ p += 4;
+ }
+
+ while (p < b_end) {
+ h64 ^= (*p) * PRIME64_5;
+ h64 = xxh_rotl64(h64, 11) * PRIME64_1;
+ p++;
+ }
+
+ h64 ^= h64 >> 33;
+ h64 *= PRIME64_2;
+ h64 ^= h64 >> 29;
+ h64 *= PRIME64_3;
+ h64 ^= h64 >> 32;
+
+ return h64;
+}
+EXPORT_SYMBOL(xxh64_digest);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("xxHash");
diff --git a/lib/zstd/Makefile b/lib/zstd/Makefile
new file mode 100644
index 0000000..dd0a359
--- /dev/null
+++ b/lib/zstd/Makefile
@@ -0,0 +1,18 @@
+obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o
+obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o
+
+ccflags-y += -O3
+
+# Object files unique to zstd_compress and zstd_decompress
+zstd_compress-y := fse_compress.o huf_compress.o compress.o
+zstd_decompress-y := huf_decompress.o decompress.o
+
+# These object files are shared between the modules.
+# Always add them to zstd_compress.
+# Unless both zstd_compress and zstd_decompress are built in
+# then also add them to zstd_decompress.
+zstd_compress-y += entropy_common.o fse_decompress.o zstd_common.o
+
+ifneq ($(CONFIG_ZSTD_COMPRESS)$(CONFIG_ZSTD_DECOMPRESS),yy)
+ zstd_decompress-y += entropy_common.o fse_decompress.o zstd_common.o
+endif
diff --git a/lib/zstd/bitstream.h b/lib/zstd/bitstream.h
new file mode 100644
index 0000000..a826b99
--- /dev/null
+++ b/lib/zstd/bitstream.h
@@ -0,0 +1,374 @@
+/*
+ * bitstream
+ * Part of FSE library
+ * header file (to include)
+ * Copyright (C) 2013-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+#ifndef BITSTREAM_H_MODULE
+#define BITSTREAM_H_MODULE
+
+/*
+* This API consists of small unitary functions, which must be inlined for best performance.
+* Since link-time-optimization is not available for all compilers,
+* these functions are defined into a .h to be included.
+*/
+
+/*-****************************************
+* Dependencies
+******************************************/
+#include "error_private.h" /* error codes and messages */
+#include "mem.h" /* unaligned access routines */
+
+/*=========================================
+* Target specific
+=========================================*/
+#define STREAM_ACCUMULATOR_MIN_32 25
+#define STREAM_ACCUMULATOR_MIN_64 57
+#define STREAM_ACCUMULATOR_MIN ((U32)(ZSTD_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
+
+/*-******************************************
+* bitStream encoding API (write forward)
+********************************************/
+/* bitStream can mix input from multiple sources.
+* A critical property of these streams is that they encode and decode in **reverse** direction.
+* So the first bit sequence you add will be the last to be read, like a LIFO stack.
+*/
+typedef struct {
+ size_t bitContainer;
+ int bitPos;
+ char *startPtr;
+ char *ptr;
+ char *endPtr;
+} BIT_CStream_t;
+
+ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *dstBuffer, size_t dstCapacity);
+ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits);
+ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC);
+ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC);
+
+/* Start with initCStream, providing the size of buffer to write into.
+* bitStream will never write outside of this buffer.
+* `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
+*
+* bits are first added to a local register.
+* Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
+* Writing data into memory is an explicit operation, performed by the flushBits function.
+* Hence keep track how many bits are potentially stored into local register to avoid register overflow.
+* After a flushBits, a maximum of 7 bits might still be stored into local register.
+*
+* Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers.
+*
+* Last operation is to close the bitStream.
+* The function returns the final size of CStream in bytes.
+* If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable)
+*/
+
+/*-********************************************
+* bitStream decoding API (read backward)
+**********************************************/
+typedef struct {
+ size_t bitContainer;
+ unsigned bitsConsumed;
+ const char *ptr;
+ const char *start;
+} BIT_DStream_t;
+
+typedef enum {
+ BIT_DStream_unfinished = 0,
+ BIT_DStream_endOfBuffer = 1,
+ BIT_DStream_completed = 2,
+ BIT_DStream_overflow = 3
+} BIT_DStream_status; /* result of BIT_reloadDStream() */
+/* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
+
+ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize);
+ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, unsigned nbBits);
+ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD);
+ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *bitD);
+
+/* Start by invoking BIT_initDStream().
+* A chunk of the bitStream is then stored into a local register.
+* Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+* You can then retrieve bitFields stored into the local register, **in reverse order**.
+* Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
+* A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
+* Otherwise, it can be less than that, so proceed accordingly.
+* Checking if DStream has reached its end can be performed with BIT_endOfDStream().
+*/
+
+/*-****************************************
+* unsafe API
+******************************************/
+ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits);
+/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
+
+ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC);
+/* unsafe version; does not check buffer overflow */
+
+ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, unsigned nbBits);
+/* faster, but works only if nbBits >= 1 */
+
+/*-**************************************************************
+* Internal functions
+****************************************************************/
+ZSTD_STATIC unsigned BIT_highbit32(register U32 val) { return 31 - __builtin_clz(val); }
+
+/*===== Local Constants =====*/
+static const unsigned BIT_mask[] = {0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF,
+ 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF,
+ 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF}; /* up to 26 bits */
+
+/*-**************************************************************
+* bitStream encoding
+****************************************************************/
+/*! BIT_initCStream() :
+ * `dstCapacity` must be > sizeof(void*)
+ * @return : 0 if success,
+ otherwise an error code (can be tested using ERR_isError() ) */
+ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *startPtr, size_t dstCapacity)
+{
+ bitC->bitContainer = 0;
+ bitC->bitPos = 0;
+ bitC->startPtr = (char *)startPtr;
+ bitC->ptr = bitC->startPtr;
+ bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->ptr);
+ if (dstCapacity <= sizeof(bitC->ptr))
+ return ERROR(dstSize_tooSmall);
+ return 0;
+}
+
+/*! BIT_addBits() :
+ can add up to 26 bits into `bitC`.
+ Does not check for register overflow ! */
+ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits)
+{
+ bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
+ bitC->bitPos += nbBits;
+}
+
+/*! BIT_addBitsFast() :
+ * works only if `value` is _clean_, meaning all high bits above nbBits are 0 */
+ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits)
+{
+ bitC->bitContainer |= value << bitC->bitPos;
+ bitC->bitPos += nbBits;
+}
+
+/*! BIT_flushBitsFast() :
+ * unsafe version; does not check buffer overflow */
+ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC)
+{
+ size_t const nbBytes = bitC->bitPos >> 3;
+ ZSTD_writeLEST(bitC->ptr, bitC->bitContainer);
+ bitC->ptr += nbBytes;
+ bitC->bitPos &= 7;
+ bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
+}
+
+/*! BIT_flushBits() :
+ * safe version; check for buffer overflow, and prevents it.
+ * note : does not signal buffer overflow. This will be revealed later on using BIT_closeCStream() */
+ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC)
+{
+ size_t const nbBytes = bitC->bitPos >> 3;
+ ZSTD_writeLEST(bitC->ptr, bitC->bitContainer);
+ bitC->ptr += nbBytes;
+ if (bitC->ptr > bitC->endPtr)
+ bitC->ptr = bitC->endPtr;
+ bitC->bitPos &= 7;
+ bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
+}
+
+/*! BIT_closeCStream() :
+ * @return : size of CStream, in bytes,
+ or 0 if it could not fit into dstBuffer */
+ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC)
+{
+ BIT_addBitsFast(bitC, 1, 1); /* endMark */
+ BIT_flushBits(bitC);
+
+ if (bitC->ptr >= bitC->endPtr)
+ return 0; /* doesn't fit within authorized budget : cancel */
+
+ return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
+}
+
+/*-********************************************************
+* bitStream decoding
+**********************************************************/
+/*! BIT_initDStream() :
+* Initialize a BIT_DStream_t.
+* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
+* `srcSize` must be the *exact* size of the bitStream, in bytes.
+* @return : size of stream (== srcSize) or an errorCode if a problem is detected
+*/
+ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize)
+{
+ if (srcSize < 1) {
+ memset(bitD, 0, sizeof(*bitD));
+ return ERROR(srcSize_wrong);
+ }
+
+ if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */
+ bitD->start = (const char *)srcBuffer;
+ bitD->ptr = (const char *)srcBuffer + srcSize - sizeof(bitD->bitContainer);
+ bitD->bitContainer = ZSTD_readLEST(bitD->ptr);
+ {
+ BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1];
+ bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */
+ if (lastByte == 0)
+ return ERROR(GENERIC); /* endMark not present */
+ }
+ } else {
+ bitD->start = (const char *)srcBuffer;
+ bitD->ptr = bitD->start;
+ bitD->bitContainer = *(const BYTE *)(bitD->start);
+ switch (srcSize) {
+ case 7: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[6]) << (sizeof(bitD->bitContainer) * 8 - 16);
+ case 6: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[5]) << (sizeof(bitD->bitContainer) * 8 - 24);
+ case 5: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[4]) << (sizeof(bitD->bitContainer) * 8 - 32);
+ case 4: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[3]) << 24;
+ case 3: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[2]) << 16;
+ case 2: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[1]) << 8;
+ default:;
+ }
+ {
+ BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1];
+ bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
+ if (lastByte == 0)
+ return ERROR(GENERIC); /* endMark not present */
+ }
+ bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize) * 8;
+ }
+
+ return srcSize;
+}
+
+ZSTD_STATIC size_t BIT_getUpperBits(size_t bitContainer, U32 const start) { return bitContainer >> start; }
+
+ZSTD_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits) { return (bitContainer >> start) & BIT_mask[nbBits]; }
+
+ZSTD_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits) { return bitContainer & BIT_mask[nbBits]; }
+
+/*! BIT_lookBits() :
+ * Provides next n bits from local register.
+ * local register is not modified.
+ * On 32-bits, maxNbBits==24.
+ * On 64-bits, maxNbBits==56.
+ * @return : value extracted
+ */
+ZSTD_STATIC size_t BIT_lookBits(const BIT_DStream_t *bitD, U32 nbBits)
+{
+ U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1;
+ return ((bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> 1) >> ((bitMask - nbBits) & bitMask);
+}
+
+/*! BIT_lookBitsFast() :
+* unsafe version; only works only if nbBits >= 1 */
+ZSTD_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t *bitD, U32 nbBits)
+{
+ U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1;
+ return (bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> (((bitMask + 1) - nbBits) & bitMask);
+}
+
+ZSTD_STATIC void BIT_skipBits(BIT_DStream_t *bitD, U32 nbBits) { bitD->bitsConsumed += nbBits; }
+
+/*! BIT_readBits() :
+ * Read (consume) next n bits from local register and update.
+ * Pay attention to not read more than nbBits contained into local register.
+ * @return : extracted value.
+ */
+ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, U32 nbBits)
+{
+ size_t const value = BIT_lookBits(bitD, nbBits);
+ BIT_skipBits(bitD, nbBits);
+ return value;
+}
+
+/*! BIT_readBitsFast() :
+* unsafe version; only works only if nbBits >= 1 */
+ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, U32 nbBits)
+{
+ size_t const value = BIT_lookBitsFast(bitD, nbBits);
+ BIT_skipBits(bitD, nbBits);
+ return value;
+}
+
+/*! BIT_reloadDStream() :
+* Refill `bitD` from buffer previously set in BIT_initDStream() .
+* This function is safe, it guarantees it will not read beyond src buffer.
+* @return : status of `BIT_DStream_t` internal register.
+ if status == BIT_DStream_unfinished, internal register is filled with >= (sizeof(bitD->bitContainer)*8 - 7) bits */
+ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD)
+{
+ if (bitD->bitsConsumed > (sizeof(bitD->bitContainer) * 8)) /* should not happen => corruption detected */
+ return BIT_DStream_overflow;
+
+ if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) {
+ bitD->ptr -= bitD->bitsConsumed >> 3;
+ bitD->bitsConsumed &= 7;
+ bitD->bitContainer = ZSTD_readLEST(bitD->ptr);
+ return BIT_DStream_unfinished;
+ }
+ if (bitD->ptr == bitD->start) {
+ if (bitD->bitsConsumed < sizeof(bitD->bitContainer) * 8)
+ return BIT_DStream_endOfBuffer;
+ return BIT_DStream_completed;
+ }
+ {
+ U32 nbBytes = bitD->bitsConsumed >> 3;
+ BIT_DStream_status result = BIT_DStream_unfinished;
+ if (bitD->ptr - nbBytes < bitD->start) {
+ nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */
+ result = BIT_DStream_endOfBuffer;
+ }
+ bitD->ptr -= nbBytes;
+ bitD->bitsConsumed -= nbBytes * 8;
+ bitD->bitContainer = ZSTD_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD) */
+ return result;
+ }
+}
+
+/*! BIT_endOfDStream() :
+* @return Tells if DStream has exactly reached its end (all bits consumed).
+*/
+ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *DStream)
+{
+ return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer) * 8));
+}
+
+#endif /* BITSTREAM_H_MODULE */
diff --git a/lib/zstd/compress.c b/lib/zstd/compress.c
new file mode 100644
index 0000000..f9166cf
--- /dev/null
+++ b/lib/zstd/compress.c
@@ -0,0 +1,3484 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+/*-*************************************
+* Dependencies
+***************************************/
+#include "fse.h"
+#include "huf.h"
+#include "mem.h"
+#include "zstd_internal.h" /* includes zstd.h */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h> /* memset */
+
+/*-*************************************
+* Constants
+***************************************/
+static const U32 g_searchStrength = 8; /* control skip over incompressible data */
+#define HASH_READ_SIZE 8
+typedef enum { ZSTDcs_created = 0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e;
+
+/*-*************************************
+* Helper functions
+***************************************/
+size_t ZSTD_compressBound(size_t srcSize) { return FSE_compressBound(srcSize) + 12; }
+
+/*-*************************************
+* Sequence storage
+***************************************/
+static void ZSTD_resetSeqStore(seqStore_t *ssPtr)
+{
+ ssPtr->lit = ssPtr->litStart;
+ ssPtr->sequences = ssPtr->sequencesStart;
+ ssPtr->longLengthID = 0;
+}
+
+/*-*************************************
+* Context memory management
+***************************************/
+struct ZSTD_CCtx_s {
+ const BYTE *nextSrc; /* next block here to continue on curr prefix */
+ const BYTE *base; /* All regular indexes relative to this position */
+ const BYTE *dictBase; /* extDict indexes relative to this position */
+ U32 dictLimit; /* below that point, need extDict */
+ U32 lowLimit; /* below that point, no more data */
+ U32 nextToUpdate; /* index from which to continue dictionary update */
+ U32 nextToUpdate3; /* index from which to continue dictionary update */
+ U32 hashLog3; /* dispatch table : larger == faster, more memory */
+ U32 loadedDictEnd; /* index of end of dictionary */
+ U32 forceWindow; /* force back-references to respect limit of 1<<wLog, even for dictionary */
+ U32 forceRawDict; /* Force loading dictionary in "content-only" mode (no header analysis) */
+ ZSTD_compressionStage_e stage;
+ U32 rep[ZSTD_REP_NUM];
+ U32 repToConfirm[ZSTD_REP_NUM];
+ U32 dictID;
+ ZSTD_parameters params;
+ void *workSpace;
+ size_t workSpaceSize;
+ size_t blockSize;
+ U64 frameContentSize;
+ struct xxh64_state xxhState;
+ ZSTD_customMem customMem;
+
+ seqStore_t seqStore; /* sequences storage ptrs */
+ U32 *hashTable;
+ U32 *hashTable3;
+ U32 *chainTable;
+ HUF_CElt *hufTable;
+ U32 flagStaticTables;
+ HUF_repeat flagStaticHufTable;
+ FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
+ FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
+ FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
+ unsigned tmpCounters[HUF_COMPRESS_WORKSPACE_SIZE_U32];
+};
+
+size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams)
+{
+ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << cParams.windowLog);
+ U32 const divider = (cParams.searchLength == 3) ? 3 : 4;
+ size_t const maxNbSeq = blockSize / divider;
+ size_t const tokenSpace = blockSize + 11 * maxNbSeq;
+ size_t const chainSize = (cParams.strategy == ZSTD_fast) ? 0 : (1 << cParams.chainLog);
+ size_t const hSize = ((size_t)1) << cParams.hashLog;
+ U32 const hashLog3 = (cParams.searchLength > 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, cParams.windowLog);
+ size_t const h3Size = ((size_t)1) << hashLog3;
+ size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
+ size_t const optSpace =
+ ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) + (ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t));
+ size_t const workspaceSize = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace +
+ (((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btopt2)) ? optSpace : 0);
+
+ return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_CCtx)) + ZSTD_ALIGN(workspaceSize);
+}
+
+static ZSTD_CCtx *ZSTD_createCCtx_advanced(ZSTD_customMem customMem)
+{
+ ZSTD_CCtx *cctx;
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+ cctx = (ZSTD_CCtx *)ZSTD_malloc(sizeof(ZSTD_CCtx), customMem);
+ if (!cctx)
+ return NULL;
+ memset(cctx, 0, sizeof(ZSTD_CCtx));
+ cctx->customMem = customMem;
+ return cctx;
+}
+
+ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ ZSTD_CCtx *cctx = ZSTD_createCCtx_advanced(stackMem);
+ if (cctx) {
+ cctx->workSpace = ZSTD_stackAllocAll(cctx->customMem.opaque, &cctx->workSpaceSize);
+ }
+ return cctx;
+}
+
+size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx)
+{
+ if (cctx == NULL)
+ return 0; /* support free on NULL */
+ ZSTD_free(cctx->workSpace, cctx->customMem);
+ ZSTD_free(cctx, cctx->customMem);
+ return 0; /* reserved as a potential error code in the future */
+}
+
+const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx) /* hidden interface */ { return &(ctx->seqStore); }
+
+static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx *cctx) { return cctx->params; }
+
+/** ZSTD_checkParams() :
+ ensure param values remain within authorized range.
+ @return : 0, or an error code if one value is beyond authorized range */
+size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
+{
+#define CLAMPCHECK(val, min, max) \
+ { \
+ if ((val < min) | (val > max)) \
+ return ERROR(compressionParameter_unsupported); \
+ }
+ CLAMPCHECK(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
+ CLAMPCHECK(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
+ CLAMPCHECK(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
+ CLAMPCHECK(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
+ CLAMPCHECK(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
+ CLAMPCHECK(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
+ if ((U32)(cParams.strategy) > (U32)ZSTD_btopt2)
+ return ERROR(compressionParameter_unsupported);
+ return 0;
+}
+
+/** ZSTD_cycleLog() :
+ * condition for correct operation : hashLog > 1 */
+static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
+{
+ U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2);
+ return hashLog - btScale;
+}
+
+/** ZSTD_adjustCParams() :
+ optimize `cPar` for a given input (`srcSize` and `dictSize`).
+ mostly downsizing to reduce memory consumption and initialization.
+ Both `srcSize` and `dictSize` are optional (use 0 if unknown),
+ but if both are 0, no optimization can be done.
+ Note : cPar is considered validated at this stage. Use ZSTD_checkParams() to ensure that. */
+ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
+{
+ if (srcSize + dictSize == 0)
+ return cPar; /* no size information available : no adjustment */
+
+ /* resize params, to use less memory when necessary */
+ {
+ U32 const minSrcSize = (srcSize == 0) ? 500 : 0;
+ U64 const rSize = srcSize + dictSize + minSrcSize;
+ if (rSize < ((U64)1 << ZSTD_WINDOWLOG_MAX)) {
+ U32 const srcLog = MAX(ZSTD_HASHLOG_MIN, ZSTD_highbit32((U32)(rSize)-1) + 1);
+ if (cPar.windowLog > srcLog)
+ cPar.windowLog = srcLog;
+ }
+ }
+ if (cPar.hashLog > cPar.windowLog)
+ cPar.hashLog = cPar.windowLog;
+ {
+ U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy);
+ if (cycleLog > cPar.windowLog)
+ cPar.chainLog -= (cycleLog - cPar.windowLog);
+ }
+
+ if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN)
+ cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* required for frame header */
+
+ return cPar;
+}
+
+static U32 ZSTD_equivalentParams(ZSTD_parameters param1, ZSTD_parameters param2)
+{
+ return (param1.cParams.hashLog == param2.cParams.hashLog) & (param1.cParams.chainLog == param2.cParams.chainLog) &
+ (param1.cParams.strategy == param2.cParams.strategy) & ((param1.cParams.searchLength == 3) == (param2.cParams.searchLength == 3));
+}
+
+/*! ZSTD_continueCCtx() :
+ reuse CCtx without reset (note : requires no dictionary) */
+static size_t ZSTD_continueCCtx(ZSTD_CCtx *cctx, ZSTD_parameters params, U64 frameContentSize)
+{
+ U32 const end = (U32)(cctx->nextSrc - cctx->base);
+ cctx->params = params;
+ cctx->frameContentSize = frameContentSize;
+ cctx->lowLimit = end;
+ cctx->dictLimit = end;
+ cctx->nextToUpdate = end + 1;
+ cctx->stage = ZSTDcs_init;
+ cctx->dictID = 0;
+ cctx->loadedDictEnd = 0;
+ {
+ int i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ cctx->rep[i] = repStartValue[i];
+ }
+ cctx->seqStore.litLengthSum = 0; /* force reset of btopt stats */
+ xxh64_reset(&cctx->xxhState, 0);
+ return 0;
+}
+
+typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset, ZSTDcrp_fullReset } ZSTD_compResetPolicy_e;
+
+/*! ZSTD_resetCCtx_advanced() :
+ note : `params` must be validated */
+static size_t ZSTD_resetCCtx_advanced(ZSTD_CCtx *zc, ZSTD_parameters params, U64 frameContentSize, ZSTD_compResetPolicy_e const crp)
+{
+ if (crp == ZSTDcrp_continue)
+ if (ZSTD_equivalentParams(params, zc->params)) {
+ zc->flagStaticTables = 0;
+ zc->flagStaticHufTable = HUF_repeat_none;
+ return ZSTD_continueCCtx(zc, params, frameContentSize);
+ }
+
+ {
+ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog);
+ U32 const divider = (params.cParams.searchLength == 3) ? 3 : 4;
+ size_t const maxNbSeq = blockSize / divider;
+ size_t const tokenSpace = blockSize + 11 * maxNbSeq;
+ size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ? 0 : (1 << params.cParams.chainLog);
+ size_t const hSize = ((size_t)1) << params.cParams.hashLog;
+ U32 const hashLog3 = (params.cParams.searchLength > 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
+ size_t const h3Size = ((size_t)1) << hashLog3;
+ size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
+ void *ptr;
+
+ /* Check if workSpace is large enough, alloc a new one if needed */
+ {
+ size_t const optSpace = ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) +
+ (ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t));
+ size_t const neededSpace = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace +
+ (((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) ? optSpace : 0);
+ if (zc->workSpaceSize < neededSpace) {
+ ZSTD_free(zc->workSpace, zc->customMem);
+ zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
+ if (zc->workSpace == NULL)
+ return ERROR(memory_allocation);
+ zc->workSpaceSize = neededSpace;
+ }
+ }
+
+ if (crp != ZSTDcrp_noMemset)
+ memset(zc->workSpace, 0, tableSpace); /* reset tables only */
+ xxh64_reset(&zc->xxhState, 0);
+ zc->hashLog3 = hashLog3;
+ zc->hashTable = (U32 *)(zc->workSpace);
+ zc->chainTable = zc->hashTable + hSize;
+ zc->hashTable3 = zc->chainTable + chainSize;
+ ptr = zc->hashTable3 + h3Size;
+ zc->hufTable = (HUF_CElt *)ptr;
+ zc->flagStaticTables = 0;
+ zc->flagStaticHufTable = HUF_repeat_none;
+ ptr = ((U32 *)ptr) + 256; /* note : HUF_CElt* is incomplete type, size is simulated using U32 */
+
+ zc->nextToUpdate = 1;
+ zc->nextSrc = NULL;
+ zc->base = NULL;
+ zc->dictBase = NULL;
+ zc->dictLimit = 0;
+ zc->lowLimit = 0;
+ zc->params = params;
+ zc->blockSize = blockSize;
+ zc->frameContentSize = frameContentSize;
+ {
+ int i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ zc->rep[i] = repStartValue[i];
+ }
+
+ if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) {
+ zc->seqStore.litFreq = (U32 *)ptr;
+ zc->seqStore.litLengthFreq = zc->seqStore.litFreq + (1 << Litbits);
+ zc->seqStore.matchLengthFreq = zc->seqStore.litLengthFreq + (MaxLL + 1);
+ zc->seqStore.offCodeFreq = zc->seqStore.matchLengthFreq + (MaxML + 1);
+ ptr = zc->seqStore.offCodeFreq + (MaxOff + 1);
+ zc->seqStore.matchTable = (ZSTD_match_t *)ptr;
+ ptr = zc->seqStore.matchTable + ZSTD_OPT_NUM + 1;
+ zc->seqStore.priceTable = (ZSTD_optimal_t *)ptr;
+ ptr = zc->seqStore.priceTable + ZSTD_OPT_NUM + 1;
+ zc->seqStore.litLengthSum = 0;
+ }
+ zc->seqStore.sequencesStart = (seqDef *)ptr;
+ ptr = zc->seqStore.sequencesStart + maxNbSeq;
+ zc->seqStore.llCode = (BYTE *)ptr;
+ zc->seqStore.mlCode = zc->seqStore.llCode + maxNbSeq;
+ zc->seqStore.ofCode = zc->seqStore.mlCode + maxNbSeq;
+ zc->seqStore.litStart = zc->seqStore.ofCode + maxNbSeq;
+
+ zc->stage = ZSTDcs_init;
+ zc->dictID = 0;
+ zc->loadedDictEnd = 0;
+
+ return 0;
+ }
+}
+
+/* ZSTD_invalidateRepCodes() :
+ * ensures next compression will not use repcodes from previous block.
+ * Note : only works with regular variant;
+ * do not use with extDict variant ! */
+void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx)
+{
+ int i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ cctx->rep[i] = 0;
+}
+
+/*! ZSTD_copyCCtx() :
+* Duplicate an existing context `srcCCtx` into another one `dstCCtx`.
+* Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
+* @return : 0, or an error code */
+size_t ZSTD_copyCCtx(ZSTD_CCtx *dstCCtx, const ZSTD_CCtx *srcCCtx, unsigned long long pledgedSrcSize)
+{
+ if (srcCCtx->stage != ZSTDcs_init)
+ return ERROR(stage_wrong);
+
+ memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
+ {
+ ZSTD_parameters params = srcCCtx->params;
+ params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
+ ZSTD_resetCCtx_advanced(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset);
+ }
+
+ /* copy tables */
+ {
+ size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog);
+ size_t const hSize = ((size_t)1) << srcCCtx->params.cParams.hashLog;
+ size_t const h3Size = (size_t)1 << srcCCtx->hashLog3;
+ size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
+ memcpy(dstCCtx->workSpace, srcCCtx->workSpace, tableSpace);
+ }
+
+ /* copy dictionary offsets */
+ dstCCtx->nextToUpdate = srcCCtx->nextToUpdate;
+ dstCCtx->nextToUpdate3 = srcCCtx->nextToUpdate3;
+ dstCCtx->nextSrc = srcCCtx->nextSrc;
+ dstCCtx->base = srcCCtx->base;
+ dstCCtx->dictBase = srcCCtx->dictBase;
+ dstCCtx->dictLimit = srcCCtx->dictLimit;
+ dstCCtx->lowLimit = srcCCtx->lowLimit;
+ dstCCtx->loadedDictEnd = srcCCtx->loadedDictEnd;
+ dstCCtx->dictID = srcCCtx->dictID;
+
+ /* copy entropy tables */
+ dstCCtx->flagStaticTables = srcCCtx->flagStaticTables;
+ dstCCtx->flagStaticHufTable = srcCCtx->flagStaticHufTable;
+ if (srcCCtx->flagStaticTables) {
+ memcpy(dstCCtx->litlengthCTable, srcCCtx->litlengthCTable, sizeof(dstCCtx->litlengthCTable));
+ memcpy(dstCCtx->matchlengthCTable, srcCCtx->matchlengthCTable, sizeof(dstCCtx->matchlengthCTable));
+ memcpy(dstCCtx->offcodeCTable, srcCCtx->offcodeCTable, sizeof(dstCCtx->offcodeCTable));
+ }
+ if (srcCCtx->flagStaticHufTable) {
+ memcpy(dstCCtx->hufTable, srcCCtx->hufTable, 256 * 4);
+ }
+
+ return 0;
+}
+
+/*! ZSTD_reduceTable() :
+* reduce table indexes by `reducerValue` */
+static void ZSTD_reduceTable(U32 *const table, U32 const size, U32 const reducerValue)
+{
+ U32 u;
+ for (u = 0; u < size; u++) {
+ if (table[u] < reducerValue)
+ table[u] = 0;
+ else
+ table[u] -= reducerValue;
+ }
+}
+
+/*! ZSTD_reduceIndex() :
+* rescale all indexes to avoid future overflow (indexes are U32) */
+static void ZSTD_reduceIndex(ZSTD_CCtx *zc, const U32 reducerValue)
+{
+ {
+ U32 const hSize = 1 << zc->params.cParams.hashLog;
+ ZSTD_reduceTable(zc->hashTable, hSize, reducerValue);
+ }
+
+ {
+ U32 const chainSize = (zc->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->params.cParams.chainLog);
+ ZSTD_reduceTable(zc->chainTable, chainSize, reducerValue);
+ }
+
+ {
+ U32 const h3Size = (zc->hashLog3) ? 1 << zc->hashLog3 : 0;
+ ZSTD_reduceTable(zc->hashTable3, h3Size, reducerValue);
+ }
+}
+
+/*-*******************************************************
+* Block entropic compression
+*********************************************************/
+
+/* See doc/zstd_compression_format.md for detailed format description */
+
+size_t ZSTD_noCompressBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ if (srcSize + ZSTD_blockHeaderSize > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+ memcpy((BYTE *)dst + ZSTD_blockHeaderSize, src, srcSize);
+ ZSTD_writeLE24(dst, (U32)(srcSize << 2) + (U32)bt_raw);
+ return ZSTD_blockHeaderSize + srcSize;
+}
+
+static size_t ZSTD_noCompressLiterals(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ BYTE *const ostart = (BYTE * const)dst;
+ U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095);
+
+ if (srcSize + flSize > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+
+ switch (flSize) {
+ case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_basic + (srcSize << 3)); break;
+ case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_basic + (1 << 2) + (srcSize << 4))); break;
+ default: /*note : should not be necessary : flSize is within {1,2,3} */
+ case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_basic + (3 << 2) + (srcSize << 4))); break;
+ }
+
+ memcpy(ostart + flSize, src, srcSize);
+ return srcSize + flSize;
+}
+
+static size_t ZSTD_compressRleLiteralsBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ BYTE *const ostart = (BYTE * const)dst;
+ U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095);
+
+ (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
+
+ switch (flSize) {
+ case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_rle + (srcSize << 3)); break;
+ case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_rle + (1 << 2) + (srcSize << 4))); break;
+ default: /*note : should not be necessary : flSize is necessarily within {1,2,3} */
+ case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_rle + (3 << 2) + (srcSize << 4))); break;
+ }
+
+ ostart[flSize] = *(const BYTE *)src;
+ return flSize + 1;
+}
+
+static size_t ZSTD_minGain(size_t srcSize) { return (srcSize >> 6) + 2; }
+
+static size_t ZSTD_compressLiterals(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t const minGain = ZSTD_minGain(srcSize);
+ size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
+ BYTE *const ostart = (BYTE *)dst;
+ U32 singleStream = srcSize < 256;
+ symbolEncodingType_e hType = set_compressed;
+ size_t cLitSize;
+
+/* small ? don't even attempt compression (speed opt) */
+#define LITERAL_NOENTROPY 63
+ {
+ size_t const minLitSize = zc->flagStaticHufTable == HUF_repeat_valid ? 6 : LITERAL_NOENTROPY;
+ if (srcSize <= minLitSize)
+ return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+ }
+
+ if (dstCapacity < lhSize + 1)
+ return ERROR(dstSize_tooSmall); /* not enough space for compression */
+ {
+ HUF_repeat repeat = zc->flagStaticHufTable;
+ int const preferRepeat = zc->params.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+ if (repeat == HUF_repeat_valid && lhSize == 3)
+ singleStream = 1;
+ cLitSize = singleStream ? HUF_compress1X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters,
+ sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat)
+ : HUF_compress4X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters,
+ sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat);
+ if (repeat != HUF_repeat_none) {
+ hType = set_repeat;
+ } /* reused the existing table */
+ else {
+ zc->flagStaticHufTable = HUF_repeat_check;
+ } /* now have a table to reuse */
+ }
+
+ if ((cLitSize == 0) | (cLitSize >= srcSize - minGain)) {
+ zc->flagStaticHufTable = HUF_repeat_none;
+ return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+ }
+ if (cLitSize == 1) {
+ zc->flagStaticHufTable = HUF_repeat_none;
+ return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+ }
+
+ /* Build header */
+ switch (lhSize) {
+ case 3: /* 2 - 2 - 10 - 10 */
+ {
+ U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 14);
+ ZSTD_writeLE24(ostart, lhc);
+ break;
+ }
+ case 4: /* 2 - 2 - 14 - 14 */
+ {
+ U32 const lhc = hType + (2 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 18);
+ ZSTD_writeLE32(ostart, lhc);
+ break;
+ }
+ default: /* should not be necessary, lhSize is only {3,4,5} */
+ case 5: /* 2 - 2 - 18 - 18 */
+ {
+ U32 const lhc = hType + (3 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 22);
+ ZSTD_writeLE32(ostart, lhc);
+ ostart[4] = (BYTE)(cLitSize >> 10);
+ break;
+ }
+ }
+ return lhSize + cLitSize;
+}
+
+static const BYTE LL_Code[64] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 16, 17, 17, 18, 18,
+ 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23,
+ 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24};
+
+static const BYTE ML_Code[128] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
+ 26, 27, 28, 29, 30, 31, 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, 38, 38, 38, 38,
+ 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,
+ 40, 40, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 42, 42, 42, 42, 42, 42, 42, 42,
+ 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42};
+
+void ZSTD_seqToCodes(const seqStore_t *seqStorePtr)
+{
+ BYTE const LL_deltaCode = 19;
+ BYTE const ML_deltaCode = 36;
+ const seqDef *const sequences = seqStorePtr->sequencesStart;
+ BYTE *const llCodeTable = seqStorePtr->llCode;
+ BYTE *const ofCodeTable = seqStorePtr->ofCode;
+ BYTE *const mlCodeTable = seqStorePtr->mlCode;
+ U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+ U32 u;
+ for (u = 0; u < nbSeq; u++) {
+ U32 const llv = sequences[u].litLength;
+ U32 const mlv = sequences[u].matchLength;
+ llCodeTable[u] = (llv > 63) ? (BYTE)ZSTD_highbit32(llv) + LL_deltaCode : LL_Code[llv];
+ ofCodeTable[u] = (BYTE)ZSTD_highbit32(sequences[u].offset);
+ mlCodeTable[u] = (mlv > 127) ? (BYTE)ZSTD_highbit32(mlv) + ML_deltaCode : ML_Code[mlv];
+ }
+ if (seqStorePtr->longLengthID == 1)
+ llCodeTable[seqStorePtr->longLengthPos] = MaxLL;
+ if (seqStorePtr->longLengthID == 2)
+ mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
+}
+
+ZSTD_STATIC size_t ZSTD_compressSequences_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity)
+{
+ const int longOffsets = zc->params.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
+ const seqStore_t *seqStorePtr = &(zc->seqStore);
+ FSE_CTable *CTable_LitLength = zc->litlengthCTable;
+ FSE_CTable *CTable_OffsetBits = zc->offcodeCTable;
+ FSE_CTable *CTable_MatchLength = zc->matchlengthCTable;
+ U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */
+ const seqDef *const sequences = seqStorePtr->sequencesStart;
+ const BYTE *const ofCodeTable = seqStorePtr->ofCode;
+ const BYTE *const llCodeTable = seqStorePtr->llCode;
+ const BYTE *const mlCodeTable = seqStorePtr->mlCode;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstCapacity;
+ BYTE *op = ostart;
+ size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart;
+ BYTE *seqHead;
+
+ U32 *count;
+ S16 *norm;
+ U32 *workspace;
+ size_t workspaceSize = sizeof(zc->tmpCounters);
+ {
+ size_t spaceUsed32 = 0;
+ count = (U32 *)zc->tmpCounters + spaceUsed32;
+ spaceUsed32 += MaxSeq + 1;
+ norm = (S16 *)((U32 *)zc->tmpCounters + spaceUsed32);
+ spaceUsed32 += ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2;
+
+ workspace = (U32 *)zc->tmpCounters + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+ }
+
+ /* Compress literals */
+ {
+ const BYTE *const literals = seqStorePtr->litStart;
+ size_t const litSize = seqStorePtr->lit - literals;
+ size_t const cSize = ZSTD_compressLiterals(zc, op, dstCapacity, literals, litSize);
+ if (ZSTD_isError(cSize))
+ return cSize;
+ op += cSize;
+ }
+
+ /* Sequences Header */
+ if ((oend - op) < 3 /*max nbSeq Size*/ + 1 /*seqHead */)
+ return ERROR(dstSize_tooSmall);
+ if (nbSeq < 0x7F)
+ *op++ = (BYTE)nbSeq;
+ else if (nbSeq < LONGNBSEQ)
+ op[0] = (BYTE)((nbSeq >> 8) + 0x80), op[1] = (BYTE)nbSeq, op += 2;
+ else
+ op[0] = 0xFF, ZSTD_writeLE16(op + 1, (U16)(nbSeq - LONGNBSEQ)), op += 3;
+ if (nbSeq == 0)
+ return op - ostart;
+
+ /* seqHead : flags for FSE encoding type */
+ seqHead = op++;
+
+#define MIN_SEQ_FOR_DYNAMIC_FSE 64
+#define MAX_SEQ_FOR_STATIC_FSE 1000
+
+ /* convert length/distances into codes */
+ ZSTD_seqToCodes(seqStorePtr);
+
+ /* CTable for Literal Lengths */
+ {
+ U32 max = MaxLL;
+ size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace);
+ if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
+ *op++ = llCodeTable[0];
+ FSE_buildCTable_rle(CTable_LitLength, (BYTE)max);
+ LLtype = set_rle;
+ } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
+ LLtype = set_repeat;
+ } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (LL_defaultNormLog - 1)))) {
+ FSE_buildCTable_wksp(CTable_LitLength, LL_defaultNorm, MaxLL, LL_defaultNormLog, workspace, workspaceSize);
+ LLtype = set_basic;
+ } else {
+ size_t nbSeq_1 = nbSeq;
+ const U32 tableLog = FSE_optimalTableLog(LLFSELog, nbSeq, max);
+ if (count[llCodeTable[nbSeq - 1]] > 1) {
+ count[llCodeTable[nbSeq - 1]]--;
+ nbSeq_1--;
+ }
+ FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
+ {
+ size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
+ if (FSE_isError(NCountSize))
+ return NCountSize;
+ op += NCountSize;
+ }
+ FSE_buildCTable_wksp(CTable_LitLength, norm, max, tableLog, workspace, workspaceSize);
+ LLtype = set_compressed;
+ }
+ }
+
+ /* CTable for Offsets */
+ {
+ U32 max = MaxOff;
+ size_t const mostFrequent = FSE_countFast_wksp(count, &max, ofCodeTable, nbSeq, workspace);
+ if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
+ *op++ = ofCodeTable[0];
+ FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max);
+ Offtype = set_rle;
+ } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
+ Offtype = set_repeat;
+ } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (OF_defaultNormLog - 1)))) {
+ FSE_buildCTable_wksp(CTable_OffsetBits, OF_defaultNorm, MaxOff, OF_defaultNormLog, workspace, workspaceSize);
+ Offtype = set_basic;
+ } else {
+ size_t nbSeq_1 = nbSeq;
+ const U32 tableLog = FSE_optimalTableLog(OffFSELog, nbSeq, max);
+ if (count[ofCodeTable[nbSeq - 1]] > 1) {
+ count[ofCodeTable[nbSeq - 1]]--;
+ nbSeq_1--;
+ }
+ FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
+ {
+ size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
+ if (FSE_isError(NCountSize))
+ return NCountSize;
+ op += NCountSize;
+ }
+ FSE_buildCTable_wksp(CTable_OffsetBits, norm, max, tableLog, workspace, workspaceSize);
+ Offtype = set_compressed;
+ }
+ }
+
+ /* CTable for MatchLengths */
+ {
+ U32 max = MaxML;
+ size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace);
+ if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
+ *op++ = *mlCodeTable;
+ FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max);
+ MLtype = set_rle;
+ } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
+ MLtype = set_repeat;
+ } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (ML_defaultNormLog - 1)))) {
+ FSE_buildCTable_wksp(CTable_MatchLength, ML_defaultNorm, MaxML, ML_defaultNormLog, workspace, workspaceSize);
+ MLtype = set_basic;
+ } else {
+ size_t nbSeq_1 = nbSeq;
+ const U32 tableLog = FSE_optimalTableLog(MLFSELog, nbSeq, max);
+ if (count[mlCodeTable[nbSeq - 1]] > 1) {
+ count[mlCodeTable[nbSeq - 1]]--;
+ nbSeq_1--;
+ }
+ FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
+ {
+ size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
+ if (FSE_isError(NCountSize))
+ return NCountSize;
+ op += NCountSize;
+ }
+ FSE_buildCTable_wksp(CTable_MatchLength, norm, max, tableLog, workspace, workspaceSize);
+ MLtype = set_compressed;
+ }
+ }
+
+ *seqHead = (BYTE)((LLtype << 6) + (Offtype << 4) + (MLtype << 2));
+ zc->flagStaticTables = 0;
+
+ /* Encoding Sequences */
+ {
+ BIT_CStream_t blockStream;
+ FSE_CState_t stateMatchLength;
+ FSE_CState_t stateOffsetBits;
+ FSE_CState_t stateLitLength;
+
+ CHECK_E(BIT_initCStream(&blockStream, op, oend - op), dstSize_tooSmall); /* not enough space remaining */
+
+ /* first symbols */
+ FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq - 1]);
+ FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq - 1]);
+ FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq - 1]);
+ BIT_addBits(&blockStream, sequences[nbSeq - 1].litLength, LL_bits[llCodeTable[nbSeq - 1]]);
+ if (ZSTD_32bits())
+ BIT_flushBits(&blockStream);
+ BIT_addBits(&blockStream, sequences[nbSeq - 1].matchLength, ML_bits[mlCodeTable[nbSeq - 1]]);
+ if (ZSTD_32bits())
+ BIT_flushBits(&blockStream);
+ if (longOffsets) {
+ U32 const ofBits = ofCodeTable[nbSeq - 1];
+ int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1);
+ if (extraBits) {
+ BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, extraBits);
+ BIT_flushBits(&blockStream);
+ }
+ BIT_addBits(&blockStream, sequences[nbSeq - 1].offset >> extraBits, ofBits - extraBits);
+ } else {
+ BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, ofCodeTable[nbSeq - 1]);
+ }
+ BIT_flushBits(&blockStream);
+
+ {
+ size_t n;
+ for (n = nbSeq - 2; n < nbSeq; n--) { /* intentional underflow */
+ BYTE const llCode = llCodeTable[n];
+ BYTE const ofCode = ofCodeTable[n];
+ BYTE const mlCode = mlCodeTable[n];
+ U32 const llBits = LL_bits[llCode];
+ U32 const ofBits = ofCode; /* 32b*/ /* 64b*/
+ U32 const mlBits = ML_bits[mlCode];
+ /* (7)*/ /* (7)*/
+ FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */ /* 15 */
+ FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */
+ if (ZSTD_32bits())
+ BIT_flushBits(&blockStream); /* (7)*/
+ FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */
+ if (ZSTD_32bits() || (ofBits + mlBits + llBits >= 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
+ BIT_flushBits(&blockStream); /* (7)*/
+ BIT_addBits(&blockStream, sequences[n].litLength, llBits);
+ if (ZSTD_32bits() && ((llBits + mlBits) > 24))
+ BIT_flushBits(&blockStream);
+ BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
+ if (ZSTD_32bits())
+ BIT_flushBits(&blockStream); /* (7)*/
+ if (longOffsets) {
+ int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1);
+ if (extraBits) {
+ BIT_addBits(&blockStream, sequences[n].offset, extraBits);
+ BIT_flushBits(&blockStream); /* (7)*/
+ }
+ BIT_addBits(&blockStream, sequences[n].offset >> extraBits, ofBits - extraBits); /* 31 */
+ } else {
+ BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
+ }
+ BIT_flushBits(&blockStream); /* (7)*/
+ }
+ }
+
+ FSE_flushCState(&blockStream, &stateMatchLength);
+ FSE_flushCState(&blockStream, &stateOffsetBits);
+ FSE_flushCState(&blockStream, &stateLitLength);
+
+ {
+ size_t const streamSize = BIT_closeCStream(&blockStream);
+ if (streamSize == 0)
+ return ERROR(dstSize_tooSmall); /* not enough space */
+ op += streamSize;
+ }
+ }
+ return op - ostart;
+}
+
+ZSTD_STATIC size_t ZSTD_compressSequences(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, size_t srcSize)
+{
+ size_t const cSize = ZSTD_compressSequences_internal(zc, dst, dstCapacity);
+ size_t const minGain = ZSTD_minGain(srcSize);
+ size_t const maxCSize = srcSize - minGain;
+ /* If the srcSize <= dstCapacity, then there is enough space to write a
+ * raw uncompressed block. Since we ran out of space, the block must not
+ * be compressible, so fall back to a raw uncompressed block.
+ */
+ int const uncompressibleError = cSize == ERROR(dstSize_tooSmall) && srcSize <= dstCapacity;
+ int i;
+
+ if (ZSTD_isError(cSize) && !uncompressibleError)
+ return cSize;
+ if (cSize >= maxCSize || uncompressibleError) {
+ zc->flagStaticHufTable = HUF_repeat_none;
+ return 0;
+ }
+ /* confirm repcodes */
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ zc->rep[i] = zc->repToConfirm[i];
+ return cSize;
+}
+
+/*! ZSTD_storeSeq() :
+ Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
+ `offsetCode` : distance to match, or 0 == repCode.
+ `matchCode` : matchLength - MINMATCH
+*/
+ZSTD_STATIC void ZSTD_storeSeq(seqStore_t *seqStorePtr, size_t litLength, const void *literals, U32 offsetCode, size_t matchCode)
+{
+ /* copy Literals */
+ ZSTD_wildcopy(seqStorePtr->lit, literals, litLength);
+ seqStorePtr->lit += litLength;
+
+ /* literal Length */
+ if (litLength > 0xFFFF) {
+ seqStorePtr->longLengthID = 1;
+ seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+ }
+ seqStorePtr->sequences[0].litLength = (U16)litLength;
+
+ /* match offset */
+ seqStorePtr->sequences[0].offset = offsetCode + 1;
+
+ /* match Length */
+ if (matchCode > 0xFFFF) {
+ seqStorePtr->longLengthID = 2;
+ seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+ }
+ seqStorePtr->sequences[0].matchLength = (U16)matchCode;
+
+ seqStorePtr->sequences++;
+}
+
+/*-*************************************
+* Match length counter
+***************************************/
+static unsigned ZSTD_NbCommonBytes(register size_t val)
+{
+ if (ZSTD_isLittleEndian()) {
+ if (ZSTD_64bits()) {
+ return (__builtin_ctzll((U64)val) >> 3);
+ } else { /* 32 bits */
+ return (__builtin_ctz((U32)val) >> 3);
+ }
+ } else { /* Big Endian CPU */
+ if (ZSTD_64bits()) {
+ return (__builtin_clzll(val) >> 3);
+ } else { /* 32 bits */
+ return (__builtin_clz((U32)val) >> 3);
+ }
+ }
+}
+
+static size_t ZSTD_count(const BYTE *pIn, const BYTE *pMatch, const BYTE *const pInLimit)
+{
+ const BYTE *const pStart = pIn;
+ const BYTE *const pInLoopLimit = pInLimit - (sizeof(size_t) - 1);
+
+ while (pIn < pInLoopLimit) {
+ size_t const diff = ZSTD_readST(pMatch) ^ ZSTD_readST(pIn);
+ if (!diff) {
+ pIn += sizeof(size_t);
+ pMatch += sizeof(size_t);
+ continue;
+ }
+ pIn += ZSTD_NbCommonBytes(diff);
+ return (size_t)(pIn - pStart);
+ }
+ if (ZSTD_64bits())
+ if ((pIn < (pInLimit - 3)) && (ZSTD_read32(pMatch) == ZSTD_read32(pIn))) {
+ pIn += 4;
+ pMatch += 4;
+ }
+ if ((pIn < (pInLimit - 1)) && (ZSTD_read16(pMatch) == ZSTD_read16(pIn))) {
+ pIn += 2;
+ pMatch += 2;
+ }
+ if ((pIn < pInLimit) && (*pMatch == *pIn))
+ pIn++;
+ return (size_t)(pIn - pStart);
+}
+
+/** ZSTD_count_2segments() :
+* can count match length with `ip` & `match` in 2 different segments.
+* convention : on reaching mEnd, match count continue starting from iStart
+*/
+static size_t ZSTD_count_2segments(const BYTE *ip, const BYTE *match, const BYTE *iEnd, const BYTE *mEnd, const BYTE *iStart)
+{
+ const BYTE *const vEnd = MIN(ip + (mEnd - match), iEnd);
+ size_t const matchLength = ZSTD_count(ip, match, vEnd);
+ if (match + matchLength != mEnd)
+ return matchLength;
+ return matchLength + ZSTD_count(ip + matchLength, iStart, iEnd);
+}
+
+/*-*************************************
+* Hashes
+***************************************/
+static const U32 prime3bytes = 506832829U;
+static U32 ZSTD_hash3(U32 u, U32 h) { return ((u << (32 - 24)) * prime3bytes) >> (32 - h); }
+ZSTD_STATIC size_t ZSTD_hash3Ptr(const void *ptr, U32 h) { return ZSTD_hash3(ZSTD_readLE32(ptr), h); } /* only in zstd_opt.h */
+
+static const U32 prime4bytes = 2654435761U;
+static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32 - h); }
+static size_t ZSTD_hash4Ptr(const void *ptr, U32 h) { return ZSTD_hash4(ZSTD_read32(ptr), h); }
+
+static const U64 prime5bytes = 889523592379ULL;
+static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64 - 40)) * prime5bytes) >> (64 - h)); }
+static size_t ZSTD_hash5Ptr(const void *p, U32 h) { return ZSTD_hash5(ZSTD_readLE64(p), h); }
+
+static const U64 prime6bytes = 227718039650203ULL;
+static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64 - 48)) * prime6bytes) >> (64 - h)); }
+static size_t ZSTD_hash6Ptr(const void *p, U32 h) { return ZSTD_hash6(ZSTD_readLE64(p), h); }
+
+static const U64 prime7bytes = 58295818150454627ULL;
+static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64 - 56)) * prime7bytes) >> (64 - h)); }
+static size_t ZSTD_hash7Ptr(const void *p, U32 h) { return ZSTD_hash7(ZSTD_readLE64(p), h); }
+
+static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL;
+static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u)*prime8bytes) >> (64 - h)); }
+static size_t ZSTD_hash8Ptr(const void *p, U32 h) { return ZSTD_hash8(ZSTD_readLE64(p), h); }
+
+static size_t ZSTD_hashPtr(const void *p, U32 hBits, U32 mls)
+{
+ switch (mls) {
+ // case 3: return ZSTD_hash3Ptr(p, hBits);
+ default:
+ case 4: return ZSTD_hash4Ptr(p, hBits);
+ case 5: return ZSTD_hash5Ptr(p, hBits);
+ case 6: return ZSTD_hash6Ptr(p, hBits);
+ case 7: return ZSTD_hash7Ptr(p, hBits);
+ case 8: return ZSTD_hash8Ptr(p, hBits);
+ }
+}
+
+/*-*************************************
+* Fast Scan
+***************************************/
+static void ZSTD_fillHashTable(ZSTD_CCtx *zc, const void *end, const U32 mls)
+{
+ U32 *const hashTable = zc->hashTable;
+ U32 const hBits = zc->params.cParams.hashLog;
+ const BYTE *const base = zc->base;
+ const BYTE *ip = base + zc->nextToUpdate;
+ const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE;
+ const size_t fastHashFillStep = 3;
+
+ while (ip <= iend) {
+ hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base);
+ ip += fastHashFillStep;
+ }
+}
+
+FORCE_INLINE
+void ZSTD_compressBlock_fast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls)
+{
+ U32 *const hashTable = cctx->hashTable;
+ U32 const hBits = cctx->params.cParams.hashLog;
+ seqStore_t *seqStorePtr = &(cctx->seqStore);
+ const BYTE *const base = cctx->base;
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const U32 lowestIndex = cctx->dictLimit;
+ const BYTE *const lowest = base + lowestIndex;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - HASH_READ_SIZE;
+ U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1];
+ U32 offsetSaved = 0;
+
+ /* init */
+ ip += (ip == lowest);
+ {
+ U32 const maxRep = (U32)(ip - lowest);
+ if (offset_2 > maxRep)
+ offsetSaved = offset_2, offset_2 = 0;
+ if (offset_1 > maxRep)
+ offsetSaved = offset_1, offset_1 = 0;
+ }
+
+ /* Main Search Loop */
+ while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
+ size_t mLength;
+ size_t const h = ZSTD_hashPtr(ip, hBits, mls);
+ U32 const curr = (U32)(ip - base);
+ U32 const matchIndex = hashTable[h];
+ const BYTE *match = base + matchIndex;
+ hashTable[h] = curr; /* update hash table */
+
+ if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) {
+ mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4;
+ ip++;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
+ } else {
+ U32 offset;
+ if ((matchIndex <= lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) {
+ ip += ((ip - anchor) >> g_searchStrength) + 1;
+ continue;
+ }
+ mLength = ZSTD_count(ip + 4, match + 4, iend) + 4;
+ offset = (U32)(ip - match);
+ while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) {
+ ip--;
+ match--;
+ mLength++;
+ } /* catch up */
+ offset_2 = offset_1;
+ offset_1 = offset;
+
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
+ }
+
+ /* match found */
+ ip += mLength;
+ anchor = ip;
+
+ if (ip <= ilimit) {
+ /* Fill Table */
+ hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2; /* here because curr+2 could be > iend-8 */
+ hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base);
+ /* check immediate repcode */
+ while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
+ /* store sequence */
+ size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4;
+ {
+ U32 const tmpOff = offset_2;
+ offset_2 = offset_1;
+ offset_1 = tmpOff;
+ } /* swap offset_2 <=> offset_1 */
+ hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base);
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH);
+ ip += rLength;
+ anchor = ip;
+ continue; /* faster when present ... (?) */
+ }
+ }
+ }
+
+ /* save reps for next block */
+ cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved;
+ cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+static void ZSTD_compressBlock_fast(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ const U32 mls = ctx->params.cParams.searchLength;
+ switch (mls) {
+ default: /* includes case 3 */
+ case 4: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 4); return;
+ case 5: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 5); return;
+ case 6: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 6); return;
+ case 7: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 7); return;
+ }
+}
+
+static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls)
+{
+ U32 *hashTable = ctx->hashTable;
+ const U32 hBits = ctx->params.cParams.hashLog;
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const base = ctx->base;
+ const BYTE *const dictBase = ctx->dictBase;
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const U32 lowestIndex = ctx->lowLimit;
+ const BYTE *const dictStart = dictBase + lowestIndex;
+ const U32 dictLimit = ctx->dictLimit;
+ const BYTE *const lowPrefixPtr = base + dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
+
+ /* Search Loop */
+ while (ip < ilimit) { /* < instead of <=, because (ip+1) */
+ const size_t h = ZSTD_hashPtr(ip, hBits, mls);
+ const U32 matchIndex = hashTable[h];
+ const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base;
+ const BYTE *match = matchBase + matchIndex;
+ const U32 curr = (U32)(ip - base);
+ const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */
+ const BYTE *repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *repMatch = repBase + repIndex;
+ size_t mLength;
+ hashTable[h] = curr; /* update hash table */
+
+ if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) &&
+ (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) {
+ const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
+ mLength = ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repMatchEnd, lowPrefixPtr) + EQUAL_READ32;
+ ip++;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
+ } else {
+ if ((matchIndex < lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) {
+ ip += ((ip - anchor) >> g_searchStrength) + 1;
+ continue;
+ }
+ {
+ const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend;
+ const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
+ U32 offset;
+ mLength = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iend, matchEnd, lowPrefixPtr) + EQUAL_READ32;
+ while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) {
+ ip--;
+ match--;
+ mLength++;
+ } /* catch up */
+ offset = curr - matchIndex;
+ offset_2 = offset_1;
+ offset_1 = offset;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
+ }
+ }
+
+ /* found a match : store it */
+ ip += mLength;
+ anchor = ip;
+
+ if (ip <= ilimit) {
+ /* Fill Table */
+ hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2;
+ hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base);
+ /* check immediate repcode */
+ while (ip <= ilimit) {
+ U32 const curr2 = (U32)(ip - base);
+ U32 const repIndex2 = curr2 - offset_2;
+ const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
+ if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
+ && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) {
+ const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
+ size_t repLength2 =
+ ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32;
+ U32 tmpOffset = offset_2;
+ offset_2 = offset_1;
+ offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH);
+ hashTable[ZSTD_hashPtr(ip, hBits, mls)] = curr2;
+ ip += repLength2;
+ anchor = ip;
+ continue;
+ }
+ break;
+ }
+ }
+ }
+
+ /* save reps for next block */
+ ctx->repToConfirm[0] = offset_1;
+ ctx->repToConfirm[1] = offset_2;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ U32 const mls = ctx->params.cParams.searchLength;
+ switch (mls) {
+ default: /* includes case 3 */
+ case 4: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 4); return;
+ case 5: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 5); return;
+ case 6: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 6); return;
+ case 7: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 7); return;
+ }
+}
+
+/*-*************************************
+* Double Fast
+***************************************/
+static void ZSTD_fillDoubleHashTable(ZSTD_CCtx *cctx, const void *end, const U32 mls)
+{
+ U32 *const hashLarge = cctx->hashTable;
+ U32 const hBitsL = cctx->params.cParams.hashLog;
+ U32 *const hashSmall = cctx->chainTable;
+ U32 const hBitsS = cctx->params.cParams.chainLog;
+ const BYTE *const base = cctx->base;
+ const BYTE *ip = base + cctx->nextToUpdate;
+ const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE;
+ const size_t fastHashFillStep = 3;
+
+ while (ip <= iend) {
+ hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base);
+ hashLarge[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base);
+ ip += fastHashFillStep;
+ }
+}
+
+FORCE_INLINE
+void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls)
+{
+ U32 *const hashLong = cctx->hashTable;
+ const U32 hBitsL = cctx->params.cParams.hashLog;
+ U32 *const hashSmall = cctx->chainTable;
+ const U32 hBitsS = cctx->params.cParams.chainLog;
+ seqStore_t *seqStorePtr = &(cctx->seqStore);
+ const BYTE *const base = cctx->base;
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const U32 lowestIndex = cctx->dictLimit;
+ const BYTE *const lowest = base + lowestIndex;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - HASH_READ_SIZE;
+ U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1];
+ U32 offsetSaved = 0;
+
+ /* init */
+ ip += (ip == lowest);
+ {
+ U32 const maxRep = (U32)(ip - lowest);
+ if (offset_2 > maxRep)
+ offsetSaved = offset_2, offset_2 = 0;
+ if (offset_1 > maxRep)
+ offsetSaved = offset_1, offset_1 = 0;
+ }
+
+ /* Main Search Loop */
+ while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
+ size_t mLength;
+ size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8);
+ size_t const h = ZSTD_hashPtr(ip, hBitsS, mls);
+ U32 const curr = (U32)(ip - base);
+ U32 const matchIndexL = hashLong[h2];
+ U32 const matchIndexS = hashSmall[h];
+ const BYTE *matchLong = base + matchIndexL;
+ const BYTE *match = base + matchIndexS;
+ hashLong[h2] = hashSmall[h] = curr; /* update hash tables */
+
+ if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) { /* note : by construction, offset_1 <= curr */
+ mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4;
+ ip++;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
+ } else {
+ U32 offset;
+ if ((matchIndexL > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) {
+ mLength = ZSTD_count(ip + 8, matchLong + 8, iend) + 8;
+ offset = (U32)(ip - matchLong);
+ while (((ip > anchor) & (matchLong > lowest)) && (ip[-1] == matchLong[-1])) {
+ ip--;
+ matchLong--;
+ mLength++;
+ } /* catch up */
+ } else if ((matchIndexS > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) {
+ size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8);
+ U32 const matchIndex3 = hashLong[h3];
+ const BYTE *match3 = base + matchIndex3;
+ hashLong[h3] = curr + 1;
+ if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) {
+ mLength = ZSTD_count(ip + 9, match3 + 8, iend) + 8;
+ ip++;
+ offset = (U32)(ip - match3);
+ while (((ip > anchor) & (match3 > lowest)) && (ip[-1] == match3[-1])) {
+ ip--;
+ match3--;
+ mLength++;
+ } /* catch up */
+ } else {
+ mLength = ZSTD_count(ip + 4, match + 4, iend) + 4;
+ offset = (U32)(ip - match);
+ while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) {
+ ip--;
+ match--;
+ mLength++;
+ } /* catch up */
+ }
+ } else {
+ ip += ((ip - anchor) >> g_searchStrength) + 1;
+ continue;
+ }
+
+ offset_2 = offset_1;
+ offset_1 = offset;
+
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
+ }
+
+ /* match found */
+ ip += mLength;
+ anchor = ip;
+
+ if (ip <= ilimit) {
+ /* Fill Table */
+ hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] =
+ curr + 2; /* here because curr+2 could be > iend-8 */
+ hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base);
+
+ /* check immediate repcode */
+ while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
+ /* store sequence */
+ size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4;
+ {
+ U32 const tmpOff = offset_2;
+ offset_2 = offset_1;
+ offset_1 = tmpOff;
+ } /* swap offset_2 <=> offset_1 */
+ hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base);
+ hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base);
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH);
+ ip += rLength;
+ anchor = ip;
+ continue; /* faster when present ... (?) */
+ }
+ }
+ }
+
+ /* save reps for next block */
+ cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved;
+ cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+static void ZSTD_compressBlock_doubleFast(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ const U32 mls = ctx->params.cParams.searchLength;
+ switch (mls) {
+ default: /* includes case 3 */
+ case 4: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 4); return;
+ case 5: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 5); return;
+ case 6: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 6); return;
+ case 7: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 7); return;
+ }
+}
+
+static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls)
+{
+ U32 *const hashLong = ctx->hashTable;
+ U32 const hBitsL = ctx->params.cParams.hashLog;
+ U32 *const hashSmall = ctx->chainTable;
+ U32 const hBitsS = ctx->params.cParams.chainLog;
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const base = ctx->base;
+ const BYTE *const dictBase = ctx->dictBase;
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const U32 lowestIndex = ctx->lowLimit;
+ const BYTE *const dictStart = dictBase + lowestIndex;
+ const U32 dictLimit = ctx->dictLimit;
+ const BYTE *const lowPrefixPtr = base + dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
+
+ /* Search Loop */
+ while (ip < ilimit) { /* < instead of <=, because (ip+1) */
+ const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
+ const U32 matchIndex = hashSmall[hSmall];
+ const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base;
+ const BYTE *match = matchBase + matchIndex;
+
+ const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8);
+ const U32 matchLongIndex = hashLong[hLong];
+ const BYTE *matchLongBase = matchLongIndex < dictLimit ? dictBase : base;
+ const BYTE *matchLong = matchLongBase + matchLongIndex;
+
+ const U32 curr = (U32)(ip - base);
+ const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */
+ const BYTE *repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *repMatch = repBase + repIndex;
+ size_t mLength;
+ hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */
+
+ if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) &&
+ (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) {
+ const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
+ mLength = ZSTD_count_2segments(ip + 1 + 4, repMatch + 4, iend, repMatchEnd, lowPrefixPtr) + 4;
+ ip++;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
+ } else {
+ if ((matchLongIndex > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) {
+ const BYTE *matchEnd = matchLongIndex < dictLimit ? dictEnd : iend;
+ const BYTE *lowMatchPtr = matchLongIndex < dictLimit ? dictStart : lowPrefixPtr;
+ U32 offset;
+ mLength = ZSTD_count_2segments(ip + 8, matchLong + 8, iend, matchEnd, lowPrefixPtr) + 8;
+ offset = curr - matchLongIndex;
+ while (((ip > anchor) & (matchLong > lowMatchPtr)) && (ip[-1] == matchLong[-1])) {
+ ip--;
+ matchLong--;
+ mLength++;
+ } /* catch up */
+ offset_2 = offset_1;
+ offset_1 = offset;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
+
+ } else if ((matchIndex > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) {
+ size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8);
+ U32 const matchIndex3 = hashLong[h3];
+ const BYTE *const match3Base = matchIndex3 < dictLimit ? dictBase : base;
+ const BYTE *match3 = match3Base + matchIndex3;
+ U32 offset;
+ hashLong[h3] = curr + 1;
+ if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) {
+ const BYTE *matchEnd = matchIndex3 < dictLimit ? dictEnd : iend;
+ const BYTE *lowMatchPtr = matchIndex3 < dictLimit ? dictStart : lowPrefixPtr;
+ mLength = ZSTD_count_2segments(ip + 9, match3 + 8, iend, matchEnd, lowPrefixPtr) + 8;
+ ip++;
+ offset = curr + 1 - matchIndex3;
+ while (((ip > anchor) & (match3 > lowMatchPtr)) && (ip[-1] == match3[-1])) {
+ ip--;
+ match3--;
+ mLength++;
+ } /* catch up */
+ } else {
+ const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend;
+ const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
+ mLength = ZSTD_count_2segments(ip + 4, match + 4, iend, matchEnd, lowPrefixPtr) + 4;
+ offset = curr - matchIndex;
+ while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) {
+ ip--;
+ match--;
+ mLength++;
+ } /* catch up */
+ }
+ offset_2 = offset_1;
+ offset_1 = offset;
+ ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
+
+ } else {
+ ip += ((ip - anchor) >> g_searchStrength) + 1;
+ continue;
+ }
+ }
+
+ /* found a match : store it */
+ ip += mLength;
+ anchor = ip;
+
+ if (ip <= ilimit) {
+ /* Fill Table */
+ hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] = curr + 2;
+ hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = curr + 2;
+ hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base);
+ hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = (U32)(ip - 2 - base);
+ /* check immediate repcode */
+ while (ip <= ilimit) {
+ U32 const curr2 = (U32)(ip - base);
+ U32 const repIndex2 = curr2 - offset_2;
+ const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
+ if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
+ && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) {
+ const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
+ size_t const repLength2 =
+ ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32;
+ U32 tmpOffset = offset_2;
+ offset_2 = offset_1;
+ offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH);
+ hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = curr2;
+ hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = curr2;
+ ip += repLength2;
+ anchor = ip;
+ continue;
+ }
+ break;
+ }
+ }
+ }
+
+ /* save reps for next block */
+ ctx->repToConfirm[0] = offset_1;
+ ctx->repToConfirm[1] = offset_2;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+static void ZSTD_compressBlock_doubleFast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ U32 const mls = ctx->params.cParams.searchLength;
+ switch (mls) {
+ default: /* includes case 3 */
+ case 4: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 4); return;
+ case 5: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 5); return;
+ case 6: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 6); return;
+ case 7: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 7); return;
+ }
+}
+
+/*-*************************************
+* Binary Tree search
+***************************************/
+/** ZSTD_insertBt1() : add one or multiple positions to tree.
+* ip : assumed <= iend-8 .
+* @return : nb of positions added */
+static U32 ZSTD_insertBt1(ZSTD_CCtx *zc, const BYTE *const ip, const U32 mls, const BYTE *const iend, U32 nbCompares, U32 extDict)
+{
+ U32 *const hashTable = zc->hashTable;
+ U32 const hashLog = zc->params.cParams.hashLog;
+ size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
+ U32 *const bt = zc->chainTable;
+ U32 const btLog = zc->params.cParams.chainLog - 1;
+ U32 const btMask = (1 << btLog) - 1;
+ U32 matchIndex = hashTable[h];
+ size_t commonLengthSmaller = 0, commonLengthLarger = 0;
+ const BYTE *const base = zc->base;
+ const BYTE *const dictBase = zc->dictBase;
+ const U32 dictLimit = zc->dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const BYTE *match;
+ const U32 curr = (U32)(ip - base);
+ const U32 btLow = btMask >= curr ? 0 : curr - btMask;
+ U32 *smallerPtr = bt + 2 * (curr & btMask);
+ U32 *largerPtr = smallerPtr + 1;
+ U32 dummy32; /* to be nullified at the end */
+ U32 const windowLow = zc->lowLimit;
+ U32 matchEndIdx = curr + 8;
+ size_t bestLength = 8;
+
+ hashTable[h] = curr; /* Update Hash Table */
+
+ while (nbCompares-- && (matchIndex > windowLow)) {
+ U32 *const nextPtr = bt + 2 * (matchIndex & btMask);
+ size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
+
+ if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
+ match = base + matchIndex;
+ if (match[matchLength] == ip[matchLength])
+ matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1;
+ } else {
+ match = dictBase + matchIndex;
+ matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart);
+ if (matchIndex + matchLength >= dictLimit)
+ match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
+ }
+
+ if (matchLength > bestLength) {
+ bestLength = matchLength;
+ if (matchLength > matchEndIdx - matchIndex)
+ matchEndIdx = matchIndex + (U32)matchLength;
+ }
+
+ if (ip + matchLength == iend) /* equal : no way to know if inf or sup */
+ break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt the tree */
+
+ if (match[matchLength] < ip[matchLength]) { /* necessarily within correct buffer */
+ /* match is smaller than curr */
+ *smallerPtr = matchIndex; /* update smaller idx */
+ commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
+ if (matchIndex <= btLow) {
+ smallerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
+ matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */
+ } else {
+ /* match is larger than curr */
+ *largerPtr = matchIndex;
+ commonLengthLarger = matchLength;
+ if (matchIndex <= btLow) {
+ largerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ largerPtr = nextPtr;
+ matchIndex = nextPtr[0];
+ }
+ }
+
+ *smallerPtr = *largerPtr = 0;
+ if (bestLength > 384)
+ return MIN(192, (U32)(bestLength - 384)); /* speed optimization */
+ if (matchEndIdx > curr + 8)
+ return matchEndIdx - curr - 8;
+ return 1;
+}
+
+static size_t ZSTD_insertBtAndFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, size_t *offsetPtr, U32 nbCompares, const U32 mls,
+ U32 extDict)
+{
+ U32 *const hashTable = zc->hashTable;
+ U32 const hashLog = zc->params.cParams.hashLog;
+ size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
+ U32 *const bt = zc->chainTable;
+ U32 const btLog = zc->params.cParams.chainLog - 1;
+ U32 const btMask = (1 << btLog) - 1;
+ U32 matchIndex = hashTable[h];
+ size_t commonLengthSmaller = 0, commonLengthLarger = 0;
+ const BYTE *const base = zc->base;
+ const BYTE *const dictBase = zc->dictBase;
+ const U32 dictLimit = zc->dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const U32 curr = (U32)(ip - base);
+ const U32 btLow = btMask >= curr ? 0 : curr - btMask;
+ const U32 windowLow = zc->lowLimit;
+ U32 *smallerPtr = bt + 2 * (curr & btMask);
+ U32 *largerPtr = bt + 2 * (curr & btMask) + 1;
+ U32 matchEndIdx = curr + 8;
+ U32 dummy32; /* to be nullified at the end */
+ size_t bestLength = 0;
+
+ hashTable[h] = curr; /* Update Hash Table */
+
+ while (nbCompares-- && (matchIndex > windowLow)) {
+ U32 *const nextPtr = bt + 2 * (matchIndex & btMask);
+ size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
+ const BYTE *match;
+
+ if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
+ match = base + matchIndex;
+ if (match[matchLength] == ip[matchLength])
+ matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1;
+ } else {
+ match = dictBase + matchIndex;
+ matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart);
+ if (matchIndex + matchLength >= dictLimit)
+ match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
+ }
+
+ if (matchLength > bestLength) {
+ if (matchLength > matchEndIdx - matchIndex)
+ matchEndIdx = matchIndex + (U32)matchLength;
+ if ((4 * (int)(matchLength - bestLength)) > (int)(ZSTD_highbit32(curr - matchIndex + 1) - ZSTD_highbit32((U32)offsetPtr[0] + 1)))
+ bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex;
+ if (ip + matchLength == iend) /* equal : no way to know if inf or sup */
+ break; /* drop, to guarantee consistency (miss a little bit of compression) */
+ }
+
+ if (match[matchLength] < ip[matchLength]) {
+ /* match is smaller than curr */
+ *smallerPtr = matchIndex; /* update smaller idx */
+ commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
+ if (matchIndex <= btLow) {
+ smallerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
+ matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */
+ } else {
+ /* match is larger than curr */
+ *largerPtr = matchIndex;
+ commonLengthLarger = matchLength;
+ if (matchIndex <= btLow) {
+ largerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ largerPtr = nextPtr;
+ matchIndex = nextPtr[0];
+ }
+ }
+
+ *smallerPtr = *largerPtr = 0;
+
+ zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1;
+ return bestLength;
+}
+
+static void ZSTD_updateTree(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls)
+{
+ const BYTE *const base = zc->base;
+ const U32 target = (U32)(ip - base);
+ U32 idx = zc->nextToUpdate;
+
+ while (idx < target)
+ idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 0);
+}
+
+/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */
+static size_t ZSTD_BtFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls)
+{
+ if (ip < zc->base + zc->nextToUpdate)
+ return 0; /* skipped area */
+ ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls);
+ return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 0);
+}
+
+static size_t ZSTD_BtFindBestMatch_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */
+ const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 matchLengthSearch)
+{
+ switch (matchLengthSearch) {
+ default: /* includes case 3 */
+ case 4: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4);
+ case 5: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5);
+ case 7:
+ case 6: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6);
+ }
+}
+
+static void ZSTD_updateTree_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls)
+{
+ const BYTE *const base = zc->base;
+ const U32 target = (U32)(ip - base);
+ U32 idx = zc->nextToUpdate;
+
+ while (idx < target)
+ idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 1);
+}
+
+/** Tree updater, providing best match */
+static size_t ZSTD_BtFindBestMatch_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
+ const U32 mls)
+{
+ if (ip < zc->base + zc->nextToUpdate)
+ return 0; /* skipped area */
+ ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls);
+ return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 1);
+}
+
+static size_t ZSTD_BtFindBestMatch_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */
+ const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
+ const U32 matchLengthSearch)
+{
+ switch (matchLengthSearch) {
+ default: /* includes case 3 */
+ case 4: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4);
+ case 5: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5);
+ case 7:
+ case 6: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6);
+ }
+}
+
+/* *********************************
+* Hash Chain
+***********************************/
+#define NEXT_IN_CHAIN(d, mask) chainTable[(d)&mask]
+
+/* Update chains up to ip (excluded)
+ Assumption : always within prefix (i.e. not within extDict) */
+FORCE_INLINE
+U32 ZSTD_insertAndFindFirstIndex(ZSTD_CCtx *zc, const BYTE *ip, U32 mls)
+{
+ U32 *const hashTable = zc->hashTable;
+ const U32 hashLog = zc->params.cParams.hashLog;
+ U32 *const chainTable = zc->chainTable;
+ const U32 chainMask = (1 << zc->params.cParams.chainLog) - 1;
+ const BYTE *const base = zc->base;
+ const U32 target = (U32)(ip - base);
+ U32 idx = zc->nextToUpdate;
+
+ while (idx < target) { /* catch up */
+ size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls);
+ NEXT_IN_CHAIN(idx, chainMask) = hashTable[h];
+ hashTable[h] = idx;
+ idx++;
+ }
+
+ zc->nextToUpdate = target;
+ return hashTable[ZSTD_hashPtr(ip, hashLog, mls)];
+}
+
+/* inlining is important to hardwire a hot branch (template emulation) */
+FORCE_INLINE
+size_t ZSTD_HcFindBestMatch_generic(ZSTD_CCtx *zc, /* Index table will be updated */
+ const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls,
+ const U32 extDict)
+{
+ U32 *const chainTable = zc->chainTable;
+ const U32 chainSize = (1 << zc->params.cParams.chainLog);
+ const U32 chainMask = chainSize - 1;
+ const BYTE *const base = zc->base;
+ const BYTE *const dictBase = zc->dictBase;
+ const U32 dictLimit = zc->dictLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const U32 lowLimit = zc->lowLimit;
+ const U32 curr = (U32)(ip - base);
+ const U32 minChain = curr > chainSize ? curr - chainSize : 0;
+ int nbAttempts = maxNbAttempts;
+ size_t ml = EQUAL_READ32 - 1;
+
+ /* HC4 match finder */
+ U32 matchIndex = ZSTD_insertAndFindFirstIndex(zc, ip, mls);
+
+ for (; (matchIndex > lowLimit) & (nbAttempts > 0); nbAttempts--) {
+ const BYTE *match;
+ size_t currMl = 0;
+ if ((!extDict) || matchIndex >= dictLimit) {
+ match = base + matchIndex;
+ if (match[ml] == ip[ml]) /* potentially better */
+ currMl = ZSTD_count(ip, match, iLimit);
+ } else {
+ match = dictBase + matchIndex;
+ if (ZSTD_read32(match) == ZSTD_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */
+ currMl = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iLimit, dictEnd, prefixStart) + EQUAL_READ32;
+ }
+
+ /* save best solution */
+ if (currMl > ml) {
+ ml = currMl;
+ *offsetPtr = curr - matchIndex + ZSTD_REP_MOVE;
+ if (ip + currMl == iLimit)
+ break; /* best possible, and avoid read overflow*/
+ }
+
+ if (matchIndex <= minChain)
+ break;
+ matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask);
+ }
+
+ return ml;
+}
+
+FORCE_INLINE size_t ZSTD_HcFindBestMatch_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
+ const U32 matchLengthSearch)
+{
+ switch (matchLengthSearch) {
+ default: /* includes case 3 */
+ case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 0);
+ case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 0);
+ case 7:
+ case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 0);
+ }
+}
+
+FORCE_INLINE size_t ZSTD_HcFindBestMatch_extDict_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
+ const U32 matchLengthSearch)
+{
+ switch (matchLengthSearch) {
+ default: /* includes case 3 */
+ case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 1);
+ case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 1);
+ case 7:
+ case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 1);
+ }
+}
+
+/* *******************************
+* Common parser - lazy strategy
+*********************************/
+FORCE_INLINE
+void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth)
+{
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ const BYTE *const base = ctx->base + ctx->dictLimit;
+
+ U32 const maxSearches = 1 << ctx->params.cParams.searchLog;
+ U32 const mls = ctx->params.cParams.searchLength;
+
+ typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch);
+ searchMax_f const searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS : ZSTD_HcFindBestMatch_selectMLS;
+ U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1], savedOffset = 0;
+
+ /* init */
+ ip += (ip == base);
+ ctx->nextToUpdate3 = ctx->nextToUpdate;
+ {
+ U32 const maxRep = (U32)(ip - base);
+ if (offset_2 > maxRep)
+ savedOffset = offset_2, offset_2 = 0;
+ if (offset_1 > maxRep)
+ savedOffset = offset_1, offset_1 = 0;
+ }
+
+ /* Match Loop */
+ while (ip < ilimit) {
+ size_t matchLength = 0;
+ size_t offset = 0;
+ const BYTE *start = ip + 1;
+
+ /* check repCode */
+ if ((offset_1 > 0) & (ZSTD_read32(ip + 1) == ZSTD_read32(ip + 1 - offset_1))) {
+ /* repcode : we take it */
+ matchLength = ZSTD_count(ip + 1 + EQUAL_READ32, ip + 1 + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
+ if (depth == 0)
+ goto _storeSequence;
+ }
+
+ /* first search (depth 0) */
+ {
+ size_t offsetFound = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls);
+ if (ml2 > matchLength)
+ matchLength = ml2, start = ip, offset = offsetFound;
+ }
+
+ if (matchLength < EQUAL_READ32) {
+ ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */
+ continue;
+ }
+
+ /* let's try to find a better solution */
+ if (depth >= 1)
+ while (ip < ilimit) {
+ ip++;
+ if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) {
+ size_t const mlRep = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
+ int const gain2 = (int)(mlRep * 3);
+ int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1);
+ if ((mlRep >= EQUAL_READ32) && (gain2 > gain1))
+ matchLength = mlRep, offset = 0, start = ip;
+ }
+ {
+ size_t offset2 = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
+ int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
+ int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4);
+ if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
+ matchLength = ml2, offset = offset2, start = ip;
+ continue; /* search a better one */
+ }
+ }
+
+ /* let's find an even better one */
+ if ((depth == 2) && (ip < ilimit)) {
+ ip++;
+ if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) {
+ size_t const ml2 = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
+ int const gain2 = (int)(ml2 * 4);
+ int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1);
+ if ((ml2 >= EQUAL_READ32) && (gain2 > gain1))
+ matchLength = ml2, offset = 0, start = ip;
+ }
+ {
+ size_t offset2 = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
+ int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
+ int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7);
+ if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
+ matchLength = ml2, offset = offset2, start = ip;
+ continue;
+ }
+ }
+ }
+ break; /* nothing found : store previous solution */
+ }
+
+ /* NOTE:
+ * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior.
+ * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which
+ * overflows the pointer, which is undefined behavior.
+ */
+ /* catch up */
+ if (offset) {
+ while ((start > anchor) && (start > base + offset - ZSTD_REP_MOVE) &&
+ (start[-1] == (start-offset+ZSTD_REP_MOVE)[-1])) /* only search for offset within prefix */
+ {
+ start--;
+ matchLength++;
+ }
+ offset_2 = offset_1;
+ offset_1 = (U32)(offset - ZSTD_REP_MOVE);
+ }
+
+ /* store sequence */
+_storeSequence:
+ {
+ size_t const litLength = start - anchor;
+ ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH);
+ anchor = ip = start + matchLength;
+ }
+
+ /* check immediate repcode */
+ while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
+ /* store sequence */
+ matchLength = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_2, iend) + EQUAL_READ32;
+ offset = offset_2;
+ offset_2 = offset_1;
+ offset_1 = (U32)offset; /* swap repcodes */
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH);
+ ip += matchLength;
+ anchor = ip;
+ continue; /* faster when present ... (?) */
+ }
+ }
+
+ /* Save reps for next block */
+ ctx->repToConfirm[0] = offset_1 ? offset_1 : savedOffset;
+ ctx->repToConfirm[1] = offset_2 ? offset_2 : savedOffset;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+static void ZSTD_compressBlock_btlazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 1, 2); }
+
+static void ZSTD_compressBlock_lazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 2); }
+
+static void ZSTD_compressBlock_lazy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 1); }
+
+static void ZSTD_compressBlock_greedy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 0); }
+
+FORCE_INLINE
+void ZSTD_compressBlock_lazy_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth)
+{
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ const BYTE *const base = ctx->base;
+ const U32 dictLimit = ctx->dictLimit;
+ const U32 lowestIndex = ctx->lowLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const BYTE *const dictBase = ctx->dictBase;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const dictStart = dictBase + ctx->lowLimit;
+
+ const U32 maxSearches = 1 << ctx->params.cParams.searchLog;
+ const U32 mls = ctx->params.cParams.searchLength;
+
+ typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch);
+ searchMax_f searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS_extDict : ZSTD_HcFindBestMatch_extDict_selectMLS;
+
+ U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
+
+ /* init */
+ ctx->nextToUpdate3 = ctx->nextToUpdate;
+ ip += (ip == prefixStart);
+
+ /* Match Loop */
+ while (ip < ilimit) {
+ size_t matchLength = 0;
+ size_t offset = 0;
+ const BYTE *start = ip + 1;
+ U32 curr = (U32)(ip - base);
+
+ /* check repCode */
+ {
+ const U32 repIndex = (U32)(curr + 1 - offset_1);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ if (ZSTD_read32(ip + 1) == ZSTD_read32(repMatch)) {
+ /* repcode detected we should take it */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ matchLength =
+ ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32;
+ if (depth == 0)
+ goto _storeSequence;
+ }
+ }
+
+ /* first search (depth 0) */
+ {
+ size_t offsetFound = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls);
+ if (ml2 > matchLength)
+ matchLength = ml2, start = ip, offset = offsetFound;
+ }
+
+ if (matchLength < EQUAL_READ32) {
+ ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */
+ continue;
+ }
+
+ /* let's try to find a better solution */
+ if (depth >= 1)
+ while (ip < ilimit) {
+ ip++;
+ curr++;
+ /* check repCode */
+ if (offset) {
+ const U32 repIndex = (U32)(curr - offset_1);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
+ /* repcode detected */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ size_t const repLength =
+ ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) +
+ EQUAL_READ32;
+ int const gain2 = (int)(repLength * 3);
+ int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1);
+ if ((repLength >= EQUAL_READ32) && (gain2 > gain1))
+ matchLength = repLength, offset = 0, start = ip;
+ }
+ }
+
+ /* search match, depth 1 */
+ {
+ size_t offset2 = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
+ int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
+ int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4);
+ if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
+ matchLength = ml2, offset = offset2, start = ip;
+ continue; /* search a better one */
+ }
+ }
+
+ /* let's find an even better one */
+ if ((depth == 2) && (ip < ilimit)) {
+ ip++;
+ curr++;
+ /* check repCode */
+ if (offset) {
+ const U32 repIndex = (U32)(curr - offset_1);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
+ /* repcode detected */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ size_t repLength = ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend,
+ repEnd, prefixStart) +
+ EQUAL_READ32;
+ int gain2 = (int)(repLength * 4);
+ int gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1);
+ if ((repLength >= EQUAL_READ32) && (gain2 > gain1))
+ matchLength = repLength, offset = 0, start = ip;
+ }
+ }
+
+ /* search match, depth 2 */
+ {
+ size_t offset2 = 99999999;
+ size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
+ int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
+ int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7);
+ if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
+ matchLength = ml2, offset = offset2, start = ip;
+ continue;
+ }
+ }
+ }
+ break; /* nothing found : store previous solution */
+ }
+
+ /* catch up */
+ if (offset) {
+ U32 const matchIndex = (U32)((start - base) - (offset - ZSTD_REP_MOVE));
+ const BYTE *match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex;
+ const BYTE *const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart;
+ while ((start > anchor) && (match > mStart) && (start[-1] == match[-1])) {
+ start--;
+ match--;
+ matchLength++;
+ } /* catch up */
+ offset_2 = offset_1;
+ offset_1 = (U32)(offset - ZSTD_REP_MOVE);
+ }
+
+ /* store sequence */
+ _storeSequence : {
+ size_t const litLength = start - anchor;
+ ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH);
+ anchor = ip = start + matchLength;
+ }
+
+ /* check immediate repcode */
+ while (ip <= ilimit) {
+ const U32 repIndex = (U32)((ip - base) - offset_2);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
+ /* repcode detected we should take it */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ matchLength =
+ ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32;
+ offset = offset_2;
+ offset_2 = offset_1;
+ offset_1 = (U32)offset; /* swap offset history */
+ ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH);
+ ip += matchLength;
+ anchor = ip;
+ continue; /* faster when present ... (?) */
+ }
+ break;
+ }
+ }
+
+ /* Save reps for next block */
+ ctx->repToConfirm[0] = offset_1;
+ ctx->repToConfirm[1] = offset_2;
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+void ZSTD_compressBlock_greedy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 0); }
+
+static void ZSTD_compressBlock_lazy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 1);
+}
+
+static void ZSTD_compressBlock_lazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 2);
+}
+
+static void ZSTD_compressBlock_btlazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+ ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 1, 2);
+}
+
+/* The optimal parser */
+#include "zstd_opt.h"
+
+static void ZSTD_compressBlock_btopt(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+#ifdef ZSTD_OPT_H_91842398743
+ ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 0);
+#else
+ (void)ctx;
+ (void)src;
+ (void)srcSize;
+ return;
+#endif
+}
+
+static void ZSTD_compressBlock_btopt2(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+#ifdef ZSTD_OPT_H_91842398743
+ ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 1);
+#else
+ (void)ctx;
+ (void)src;
+ (void)srcSize;
+ return;
+#endif
+}
+
+static void ZSTD_compressBlock_btopt_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+#ifdef ZSTD_OPT_H_91842398743
+ ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 0);
+#else
+ (void)ctx;
+ (void)src;
+ (void)srcSize;
+ return;
+#endif
+}
+
+static void ZSTD_compressBlock_btopt2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
+{
+#ifdef ZSTD_OPT_H_91842398743
+ ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 1);
+#else
+ (void)ctx;
+ (void)src;
+ (void)srcSize;
+ return;
+#endif
+}
+
+typedef void (*ZSTD_blockCompressor)(ZSTD_CCtx *ctx, const void *src, size_t srcSize);
+
+static ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, int extDict)
+{
+ static const ZSTD_blockCompressor blockCompressor[2][8] = {
+ {ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy, ZSTD_compressBlock_lazy, ZSTD_compressBlock_lazy2,
+ ZSTD_compressBlock_btlazy2, ZSTD_compressBlock_btopt, ZSTD_compressBlock_btopt2},
+ {ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict, ZSTD_compressBlock_lazy_extDict,
+ ZSTD_compressBlock_lazy2_extDict, ZSTD_compressBlock_btlazy2_extDict, ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btopt2_extDict}};
+
+ return blockCompressor[extDict][(U32)strat];
+}
+
+static size_t ZSTD_compressBlock_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->params.cParams.strategy, zc->lowLimit < zc->dictLimit);
+ const BYTE *const base = zc->base;
+ const BYTE *const istart = (const BYTE *)src;
+ const U32 curr = (U32)(istart - base);
+ if (srcSize < MIN_CBLOCK_SIZE + ZSTD_blockHeaderSize + 1)
+ return 0; /* don't even attempt compression below a certain srcSize */
+ ZSTD_resetSeqStore(&(zc->seqStore));
+ if (curr > zc->nextToUpdate + 384)
+ zc->nextToUpdate = curr - MIN(192, (U32)(curr - zc->nextToUpdate - 384)); /* update tree not updated after finding very long rep matches */
+ blockCompressor(zc, src, srcSize);
+ return ZSTD_compressSequences(zc, dst, dstCapacity, srcSize);
+}
+
+/*! ZSTD_compress_generic() :
+* Compress a chunk of data into one or multiple blocks.
+* All blocks will be terminated, all input will be consumed.
+* Function will issue an error if there is not enough `dstCapacity` to hold the compressed content.
+* Frame is supposed already started (header already produced)
+* @return : compressed size, or an error code
+*/
+static size_t ZSTD_compress_generic(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 lastFrameChunk)
+{
+ size_t blockSize = cctx->blockSize;
+ size_t remaining = srcSize;
+ const BYTE *ip = (const BYTE *)src;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *op = ostart;
+ U32 const maxDist = 1 << cctx->params.cParams.windowLog;
+
+ if (cctx->params.fParams.checksumFlag && srcSize)
+ xxh64_update(&cctx->xxhState, src, srcSize);
+
+ while (remaining) {
+ U32 const lastBlock = lastFrameChunk & (blockSize >= remaining);
+ size_t cSize;
+
+ if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE)
+ return ERROR(dstSize_tooSmall); /* not enough space to store compressed block */
+ if (remaining < blockSize)
+ blockSize = remaining;
+
+ /* preemptive overflow correction */
+ if (cctx->lowLimit > (3U << 29)) {
+ U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->params.cParams.hashLog, cctx->params.cParams.strategy)) - 1;
+ U32 const curr = (U32)(ip - cctx->base);
+ U32 const newCurr = (curr & cycleMask) + (1 << cctx->params.cParams.windowLog);
+ U32 const correction = curr - newCurr;
+ ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_64 <= 30);
+ ZSTD_reduceIndex(cctx, correction);
+ cctx->base += correction;
+ cctx->dictBase += correction;
+ cctx->lowLimit -= correction;
+ cctx->dictLimit -= correction;
+ if (cctx->nextToUpdate < correction)
+ cctx->nextToUpdate = 0;
+ else
+ cctx->nextToUpdate -= correction;
+ }
+
+ if ((U32)(ip + blockSize - cctx->base) > cctx->loadedDictEnd + maxDist) {
+ /* enforce maxDist */
+ U32 const newLowLimit = (U32)(ip + blockSize - cctx->base) - maxDist;
+ if (cctx->lowLimit < newLowLimit)
+ cctx->lowLimit = newLowLimit;
+ if (cctx->dictLimit < cctx->lowLimit)
+ cctx->dictLimit = cctx->lowLimit;
+ }
+
+ cSize = ZSTD_compressBlock_internal(cctx, op + ZSTD_blockHeaderSize, dstCapacity - ZSTD_blockHeaderSize, ip, blockSize);
+ if (ZSTD_isError(cSize))
+ return cSize;
+
+ if (cSize == 0) { /* block is not compressible */
+ U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw) << 1) + (U32)(blockSize << 3);
+ if (blockSize + ZSTD_blockHeaderSize > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+ ZSTD_writeLE32(op, cBlockHeader24); /* no pb, 4th byte will be overwritten */
+ memcpy(op + ZSTD_blockHeaderSize, ip, blockSize);
+ cSize = ZSTD_blockHeaderSize + blockSize;
+ } else {
+ U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed) << 1) + (U32)(cSize << 3);
+ ZSTD_writeLE24(op, cBlockHeader24);
+ cSize += ZSTD_blockHeaderSize;
+ }
+
+ remaining -= blockSize;
+ dstCapacity -= cSize;
+ ip += blockSize;
+ op += cSize;
+ }
+
+ if (lastFrameChunk && (op > ostart))
+ cctx->stage = ZSTDcs_ending;
+ return op - ostart;
+}
+
+static size_t ZSTD_writeFrameHeader(void *dst, size_t dstCapacity, ZSTD_parameters params, U64 pledgedSrcSize, U32 dictID)
+{
+ BYTE *const op = (BYTE *)dst;
+ U32 const dictIDSizeCode = (dictID > 0) + (dictID >= 256) + (dictID >= 65536); /* 0-3 */
+ U32 const checksumFlag = params.fParams.checksumFlag > 0;
+ U32 const windowSize = 1U << params.cParams.windowLog;
+ U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize >= pledgedSrcSize);
+ BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
+ U32 const fcsCode =
+ params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
+ BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
+ size_t pos;
+
+ if (dstCapacity < ZSTD_frameHeaderSize_max)
+ return ERROR(dstSize_tooSmall);
+
+ ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
+ op[4] = frameHeaderDecriptionByte;
+ pos = 5;
+ if (!singleSegment)
+ op[pos++] = windowLogByte;
+ switch (dictIDSizeCode) {
+ default: /* impossible */
+ case 0: break;
+ case 1:
+ op[pos] = (BYTE)(dictID);
+ pos++;
+ break;
+ case 2:
+ ZSTD_writeLE16(op + pos, (U16)dictID);
+ pos += 2;
+ break;
+ case 3:
+ ZSTD_writeLE32(op + pos, dictID);
+ pos += 4;
+ break;
+ }
+ switch (fcsCode) {
+ default: /* impossible */
+ case 0:
+ if (singleSegment)
+ op[pos++] = (BYTE)(pledgedSrcSize);
+ break;
+ case 1:
+ ZSTD_writeLE16(op + pos, (U16)(pledgedSrcSize - 256));
+ pos += 2;
+ break;
+ case 2:
+ ZSTD_writeLE32(op + pos, (U32)(pledgedSrcSize));
+ pos += 4;
+ break;
+ case 3:
+ ZSTD_writeLE64(op + pos, (U64)(pledgedSrcSize));
+ pos += 8;
+ break;
+ }
+ return pos;
+}
+
+static size_t ZSTD_compressContinue_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 frame, U32 lastFrameChunk)
+{
+ const BYTE *const ip = (const BYTE *)src;
+ size_t fhSize = 0;
+
+ if (cctx->stage == ZSTDcs_created)
+ return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */
+
+ if (frame && (cctx->stage == ZSTDcs_init)) {
+ fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, cctx->frameContentSize, cctx->dictID);
+ if (ZSTD_isError(fhSize))
+ return fhSize;
+ dstCapacity -= fhSize;
+ dst = (char *)dst + fhSize;
+ cctx->stage = ZSTDcs_ongoing;
+ }
+
+ /* Check if blocks follow each other */
+ if (src != cctx->nextSrc) {
+ /* not contiguous */
+ ptrdiff_t const delta = cctx->nextSrc - ip;
+ cctx->lowLimit = cctx->dictLimit;
+ cctx->dictLimit = (U32)(cctx->nextSrc - cctx->base);
+ cctx->dictBase = cctx->base;
+ cctx->base -= delta;
+ cctx->nextToUpdate = cctx->dictLimit;
+ if (cctx->dictLimit - cctx->lowLimit < HASH_READ_SIZE)
+ cctx->lowLimit = cctx->dictLimit; /* too small extDict */
+ }
+
+ /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */
+ if ((ip + srcSize > cctx->dictBase + cctx->lowLimit) & (ip < cctx->dictBase + cctx->dictLimit)) {
+ ptrdiff_t const highInputIdx = (ip + srcSize) - cctx->dictBase;
+ U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)cctx->dictLimit) ? cctx->dictLimit : (U32)highInputIdx;
+ cctx->lowLimit = lowLimitMax;
+ }
+
+ cctx->nextSrc = ip + srcSize;
+
+ if (srcSize) {
+ size_t const cSize = frame ? ZSTD_compress_generic(cctx, dst, dstCapacity, src, srcSize, lastFrameChunk)
+ : ZSTD_compressBlock_internal(cctx, dst, dstCapacity, src, srcSize);
+ if (ZSTD_isError(cSize))
+ return cSize;
+ return cSize + fhSize;
+ } else
+ return fhSize;
+}
+
+size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 0);
+}
+
+size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx) { return MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << cctx->params.cParams.windowLog); }
+
+size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t const blockSizeMax = ZSTD_getBlockSizeMax(cctx);
+ if (srcSize > blockSizeMax)
+ return ERROR(srcSize_wrong);
+ return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0, 0);
+}
+
+/*! ZSTD_loadDictionaryContent() :
+ * @return : 0, or an error code
+ */
+static size_t ZSTD_loadDictionaryContent(ZSTD_CCtx *zc, const void *src, size_t srcSize)
+{
+ const BYTE *const ip = (const BYTE *)src;
+ const BYTE *const iend = ip + srcSize;
+
+ /* input becomes curr prefix */
+ zc->lowLimit = zc->dictLimit;
+ zc->dictLimit = (U32)(zc->nextSrc - zc->base);
+ zc->dictBase = zc->base;
+ zc->base += ip - zc->nextSrc;
+ zc->nextToUpdate = zc->dictLimit;
+ zc->loadedDictEnd = zc->forceWindow ? 0 : (U32)(iend - zc->base);
+
+ zc->nextSrc = iend;
+ if (srcSize <= HASH_READ_SIZE)
+ return 0;
+
+ switch (zc->params.cParams.strategy) {
+ case ZSTD_fast: ZSTD_fillHashTable(zc, iend, zc->params.cParams.searchLength); break;
+
+ case ZSTD_dfast: ZSTD_fillDoubleHashTable(zc, iend, zc->params.cParams.searchLength); break;
+
+ case ZSTD_greedy:
+ case ZSTD_lazy:
+ case ZSTD_lazy2:
+ if (srcSize >= HASH_READ_SIZE)
+ ZSTD_insertAndFindFirstIndex(zc, iend - HASH_READ_SIZE, zc->params.cParams.searchLength);
+ break;
+
+ case ZSTD_btlazy2:
+ case ZSTD_btopt:
+ case ZSTD_btopt2:
+ if (srcSize >= HASH_READ_SIZE)
+ ZSTD_updateTree(zc, iend - HASH_READ_SIZE, iend, 1 << zc->params.cParams.searchLog, zc->params.cParams.searchLength);
+ break;
+
+ default:
+ return ERROR(GENERIC); /* strategy doesn't exist; impossible */
+ }
+
+ zc->nextToUpdate = (U32)(iend - zc->base);
+ return 0;
+}
+
+/* Dictionaries that assign zero probability to symbols that show up causes problems
+ when FSE encoding. Refuse dictionaries that assign zero probability to symbols
+ that we may encounter during compression.
+ NOTE: This behavior is not standard and could be improved in the future. */
+static size_t ZSTD_checkDictNCount(short *normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue)
+{
+ U32 s;
+ if (dictMaxSymbolValue < maxSymbolValue)
+ return ERROR(dictionary_corrupted);
+ for (s = 0; s <= maxSymbolValue; ++s) {
+ if (normalizedCounter[s] == 0)
+ return ERROR(dictionary_corrupted);
+ }
+ return 0;
+}
+
+/* Dictionary format :
+ * See :
+ * https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md#dictionary-format
+ */
+/*! ZSTD_loadZstdDictionary() :
+ * @return : 0, or an error code
+ * assumptions : magic number supposed already checked
+ * dictSize supposed > 8
+ */
+static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize)
+{
+ const BYTE *dictPtr = (const BYTE *)dict;
+ const BYTE *const dictEnd = dictPtr + dictSize;
+ short offcodeNCount[MaxOff + 1];
+ unsigned offcodeMaxValue = MaxOff;
+
+ dictPtr += 4; /* skip magic number */
+ cctx->dictID = cctx->params.fParams.noDictIDFlag ? 0 : ZSTD_readLE32(dictPtr);
+ dictPtr += 4;
+
+ {
+ size_t const hufHeaderSize = HUF_readCTable_wksp(cctx->hufTable, 255, dictPtr, dictEnd - dictPtr, cctx->tmpCounters, sizeof(cctx->tmpCounters));
+ if (HUF_isError(hufHeaderSize))
+ return ERROR(dictionary_corrupted);
+ dictPtr += hufHeaderSize;
+ }
+
+ {
+ unsigned offcodeLog;
+ size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(offcodeHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (offcodeLog > OffFSELog)
+ return ERROR(dictionary_corrupted);
+ /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
+ CHECK_E(FSE_buildCTable_wksp(cctx->offcodeCTable, offcodeNCount, offcodeMaxValue, offcodeLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
+ dictionary_corrupted);
+ dictPtr += offcodeHeaderSize;
+ }
+
+ {
+ short matchlengthNCount[MaxML + 1];
+ unsigned matchlengthMaxValue = MaxML, matchlengthLog;
+ size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(matchlengthHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (matchlengthLog > MLFSELog)
+ return ERROR(dictionary_corrupted);
+ /* Every match length code must have non-zero probability */
+ CHECK_F(ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
+ CHECK_E(
+ FSE_buildCTable_wksp(cctx->matchlengthCTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
+ dictionary_corrupted);
+ dictPtr += matchlengthHeaderSize;
+ }
+
+ {
+ short litlengthNCount[MaxLL + 1];
+ unsigned litlengthMaxValue = MaxLL, litlengthLog;
+ size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(litlengthHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (litlengthLog > LLFSELog)
+ return ERROR(dictionary_corrupted);
+ /* Every literal length code must have non-zero probability */
+ CHECK_F(ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
+ CHECK_E(FSE_buildCTable_wksp(cctx->litlengthCTable, litlengthNCount, litlengthMaxValue, litlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
+ dictionary_corrupted);
+ dictPtr += litlengthHeaderSize;
+ }
+
+ if (dictPtr + 12 > dictEnd)
+ return ERROR(dictionary_corrupted);
+ cctx->rep[0] = ZSTD_readLE32(dictPtr + 0);
+ cctx->rep[1] = ZSTD_readLE32(dictPtr + 4);
+ cctx->rep[2] = ZSTD_readLE32(dictPtr + 8);
+ dictPtr += 12;
+
+ {
+ size_t const dictContentSize = (size_t)(dictEnd - dictPtr);
+ U32 offcodeMax = MaxOff;
+ if (dictContentSize <= ((U32)-1) - 128 KB) {
+ U32 const maxOffset = (U32)dictContentSize + 128 KB; /* The maximum offset that must be supported */
+ offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */
+ }
+ /* All offset values <= dictContentSize + 128 KB must be representable */
+ CHECK_F(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
+ /* All repCodes must be <= dictContentSize and != 0*/
+ {
+ U32 u;
+ for (u = 0; u < 3; u++) {
+ if (cctx->rep[u] == 0)
+ return ERROR(dictionary_corrupted);
+ if (cctx->rep[u] > dictContentSize)
+ return ERROR(dictionary_corrupted);
+ }
+ }
+
+ cctx->flagStaticTables = 1;
+ cctx->flagStaticHufTable = HUF_repeat_valid;
+ return ZSTD_loadDictionaryContent(cctx, dictPtr, dictContentSize);
+ }
+}
+
+/** ZSTD_compress_insertDictionary() :
+* @return : 0, or an error code */
+static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize)
+{
+ if ((dict == NULL) || (dictSize <= 8))
+ return 0;
+
+ /* dict as pure content */
+ if ((ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC) || (cctx->forceRawDict))
+ return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
+
+ /* dict as zstd dictionary */
+ return ZSTD_loadZstdDictionary(cctx, dict, dictSize);
+}
+
+/*! ZSTD_compressBegin_internal() :
+* @return : 0, or an error code */
+static size_t ZSTD_compressBegin_internal(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, U64 pledgedSrcSize)
+{
+ ZSTD_compResetPolicy_e const crp = dictSize ? ZSTDcrp_fullReset : ZSTDcrp_continue;
+ CHECK_F(ZSTD_resetCCtx_advanced(cctx, params, pledgedSrcSize, crp));
+ return ZSTD_compress_insertDictionary(cctx, dict, dictSize);
+}
+
+/*! ZSTD_compressBegin_advanced() :
+* @return : 0, or an error code */
+size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize)
+{
+ /* compression parameters verification and optimization */
+ CHECK_F(ZSTD_checkCParams(params.cParams));
+ return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, pledgedSrcSize);
+}
+
+size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, int compressionLevel)
+{
+ ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
+ return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, 0);
+}
+
+size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel) { return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); }
+
+/*! ZSTD_writeEpilogue() :
+* Ends a frame.
+* @return : nb of bytes written into dst (or an error code) */
+static size_t ZSTD_writeEpilogue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity)
+{
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *op = ostart;
+ size_t fhSize = 0;
+
+ if (cctx->stage == ZSTDcs_created)
+ return ERROR(stage_wrong); /* init missing */
+
+ /* special case : empty frame */
+ if (cctx->stage == ZSTDcs_init) {
+ fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, 0, 0);
+ if (ZSTD_isError(fhSize))
+ return fhSize;
+ dstCapacity -= fhSize;
+ op += fhSize;
+ cctx->stage = ZSTDcs_ongoing;
+ }
+
+ if (cctx->stage != ZSTDcs_ending) {
+ /* write one last empty block, make it the "last" block */
+ U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw) << 1) + 0;
+ if (dstCapacity < 4)
+ return ERROR(dstSize_tooSmall);
+ ZSTD_writeLE32(op, cBlockHeader24);
+ op += ZSTD_blockHeaderSize;
+ dstCapacity -= ZSTD_blockHeaderSize;
+ }
+
+ if (cctx->params.fParams.checksumFlag) {
+ U32 const checksum = (U32)xxh64_digest(&cctx->xxhState);
+ if (dstCapacity < 4)
+ return ERROR(dstSize_tooSmall);
+ ZSTD_writeLE32(op, checksum);
+ op += 4;
+ }
+
+ cctx->stage = ZSTDcs_created; /* return to "created but no init" status */
+ return op - ostart;
+}
+
+size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t endResult;
+ size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 1);
+ if (ZSTD_isError(cSize))
+ return cSize;
+ endResult = ZSTD_writeEpilogue(cctx, (char *)dst + cSize, dstCapacity - cSize);
+ if (ZSTD_isError(endResult))
+ return endResult;
+ return cSize + endResult;
+}
+
+static size_t ZSTD_compress_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
+ ZSTD_parameters params)
+{
+ CHECK_F(ZSTD_compressBegin_internal(cctx, dict, dictSize, params, srcSize));
+ return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
+}
+
+size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
+ ZSTD_parameters params)
+{
+ return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, dict, dictSize, params);
+}
+
+size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, ZSTD_parameters params)
+{
+ return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, NULL, 0, params);
+}
+
+/* ===== Dictionary API ===== */
+
+struct ZSTD_CDict_s {
+ void *dictBuffer;
+ const void *dictContent;
+ size_t dictContentSize;
+ ZSTD_CCtx *refContext;
+}; /* typedef'd tp ZSTD_CDict within "zstd.h" */
+
+size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams) { return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CDict)); }
+
+static ZSTD_CDict *ZSTD_createCDict_advanced(const void *dictBuffer, size_t dictSize, unsigned byReference, ZSTD_parameters params, ZSTD_customMem customMem)
+{
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+
+ {
+ ZSTD_CDict *const cdict = (ZSTD_CDict *)ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
+ ZSTD_CCtx *const cctx = ZSTD_createCCtx_advanced(customMem);
+
+ if (!cdict || !cctx) {
+ ZSTD_free(cdict, customMem);
+ ZSTD_freeCCtx(cctx);
+ return NULL;
+ }
+
+ if ((byReference) || (!dictBuffer) || (!dictSize)) {
+ cdict->dictBuffer = NULL;
+ cdict->dictContent = dictBuffer;
+ } else {
+ void *const internalBuffer = ZSTD_malloc(dictSize, customMem);
+ if (!internalBuffer) {
+ ZSTD_free(cctx, customMem);
+ ZSTD_free(cdict, customMem);
+ return NULL;
+ }
+ memcpy(internalBuffer, dictBuffer, dictSize);
+ cdict->dictBuffer = internalBuffer;
+ cdict->dictContent = internalBuffer;
+ }
+
+ {
+ size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0);
+ if (ZSTD_isError(errorCode)) {
+ ZSTD_free(cdict->dictBuffer, customMem);
+ ZSTD_free(cdict, customMem);
+ ZSTD_freeCCtx(cctx);
+ return NULL;
+ }
+ }
+
+ cdict->refContext = cctx;
+ cdict->dictContentSize = dictSize;
+ return cdict;
+ }
+}
+
+ZSTD_CDict *ZSTD_initCDict(const void *dict, size_t dictSize, ZSTD_parameters params, void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ return ZSTD_createCDict_advanced(dict, dictSize, 1, params, stackMem);
+}
+
+size_t ZSTD_freeCDict(ZSTD_CDict *cdict)
+{
+ if (cdict == NULL)
+ return 0; /* support free on NULL */
+ {
+ ZSTD_customMem const cMem = cdict->refContext->customMem;
+ ZSTD_freeCCtx(cdict->refContext);
+ ZSTD_free(cdict->dictBuffer, cMem);
+ ZSTD_free(cdict, cMem);
+ return 0;
+ }
+}
+
+static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict *cdict) { return ZSTD_getParamsFromCCtx(cdict->refContext); }
+
+size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize)
+{
+ if (cdict->dictContentSize)
+ CHECK_F(ZSTD_copyCCtx(cctx, cdict->refContext, pledgedSrcSize))
+ else {
+ ZSTD_parameters params = cdict->refContext->params;
+ params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
+ CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, params, pledgedSrcSize));
+ }
+ return 0;
+}
+
+/*! ZSTD_compress_usingCDict() :
+* Compression using a digested Dictionary.
+* Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times.
+* Note that compression level is decided during dictionary creation */
+size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_CDict *cdict)
+{
+ CHECK_F(ZSTD_compressBegin_usingCDict(cctx, cdict, srcSize));
+
+ if (cdict->refContext->params.fParams.contentSizeFlag == 1) {
+ cctx->params.fParams.contentSizeFlag = 1;
+ cctx->frameContentSize = srcSize;
+ } else {
+ cctx->params.fParams.contentSizeFlag = 0;
+ }
+
+ return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
+}
+
+/* ******************************************************************
+* Streaming
+********************************************************************/
+
+typedef enum { zcss_init, zcss_load, zcss_flush, zcss_final } ZSTD_cStreamStage;
+
+struct ZSTD_CStream_s {
+ ZSTD_CCtx *cctx;
+ ZSTD_CDict *cdictLocal;
+ const ZSTD_CDict *cdict;
+ char *inBuff;
+ size_t inBuffSize;
+ size_t inToCompress;
+ size_t inBuffPos;
+ size_t inBuffTarget;
+ size_t blockSize;
+ char *outBuff;
+ size_t outBuffSize;
+ size_t outBuffContentSize;
+ size_t outBuffFlushedSize;
+ ZSTD_cStreamStage stage;
+ U32 checksum;
+ U32 frameEnded;
+ U64 pledgedSrcSize;
+ U64 inputProcessed;
+ ZSTD_parameters params;
+ ZSTD_customMem customMem;
+}; /* typedef'd to ZSTD_CStream within "zstd.h" */
+
+size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams)
+{
+ size_t const inBuffSize = (size_t)1 << cParams.windowLog;
+ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, inBuffSize);
+ size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1;
+
+ return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize);
+}
+
+ZSTD_CStream *ZSTD_createCStream_advanced(ZSTD_customMem customMem)
+{
+ ZSTD_CStream *zcs;
+
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+
+ zcs = (ZSTD_CStream *)ZSTD_malloc(sizeof(ZSTD_CStream), customMem);
+ if (zcs == NULL)
+ return NULL;
+ memset(zcs, 0, sizeof(ZSTD_CStream));
+ memcpy(&zcs->customMem, &customMem, sizeof(ZSTD_customMem));
+ zcs->cctx = ZSTD_createCCtx_advanced(customMem);
+ if (zcs->cctx == NULL) {
+ ZSTD_freeCStream(zcs);
+ return NULL;
+ }
+ return zcs;
+}
+
+size_t ZSTD_freeCStream(ZSTD_CStream *zcs)
+{
+ if (zcs == NULL)
+ return 0; /* support free on NULL */
+ {
+ ZSTD_customMem const cMem = zcs->customMem;
+ ZSTD_freeCCtx(zcs->cctx);
+ zcs->cctx = NULL;
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = NULL;
+ ZSTD_free(zcs->inBuff, cMem);
+ zcs->inBuff = NULL;
+ ZSTD_free(zcs->outBuff, cMem);
+ zcs->outBuff = NULL;
+ ZSTD_free(zcs, cMem);
+ return 0;
+ }
+}
+
+/*====== Initialization ======*/
+
+size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
+size_t ZSTD_CStreamOutSize(void) { return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */; }
+
+static size_t ZSTD_resetCStream_internal(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize)
+{
+ if (zcs->inBuffSize == 0)
+ return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */
+
+ if (zcs->cdict)
+ CHECK_F(ZSTD_compressBegin_usingCDict(zcs->cctx, zcs->cdict, pledgedSrcSize))
+ else
+ CHECK_F(ZSTD_compressBegin_advanced(zcs->cctx, NULL, 0, zcs->params, pledgedSrcSize));
+
+ zcs->inToCompress = 0;
+ zcs->inBuffPos = 0;
+ zcs->inBuffTarget = zcs->blockSize;
+ zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
+ zcs->stage = zcss_load;
+ zcs->frameEnded = 0;
+ zcs->pledgedSrcSize = pledgedSrcSize;
+ zcs->inputProcessed = 0;
+ return 0; /* ready to go */
+}
+
+size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize)
+{
+
+ zcs->params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
+
+ return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
+}
+
+static size_t ZSTD_initCStream_advanced(ZSTD_CStream *zcs, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize)
+{
+ /* allocate buffers */
+ {
+ size_t const neededInBuffSize = (size_t)1 << params.cParams.windowLog;
+ if (zcs->inBuffSize < neededInBuffSize) {
+ zcs->inBuffSize = neededInBuffSize;
+ ZSTD_free(zcs->inBuff, zcs->customMem);
+ zcs->inBuff = (char *)ZSTD_malloc(neededInBuffSize, zcs->customMem);
+ if (zcs->inBuff == NULL)
+ return ERROR(memory_allocation);
+ }
+ zcs->blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, neededInBuffSize);
+ }
+ if (zcs->outBuffSize < ZSTD_compressBound(zcs->blockSize) + 1) {
+ zcs->outBuffSize = ZSTD_compressBound(zcs->blockSize) + 1;
+ ZSTD_free(zcs->outBuff, zcs->customMem);
+ zcs->outBuff = (char *)ZSTD_malloc(zcs->outBuffSize, zcs->customMem);
+ if (zcs->outBuff == NULL)
+ return ERROR(memory_allocation);
+ }
+
+ if (dict && dictSize >= 8) {
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0, params, zcs->customMem);
+ if (zcs->cdictLocal == NULL)
+ return ERROR(memory_allocation);
+ zcs->cdict = zcs->cdictLocal;
+ } else
+ zcs->cdict = NULL;
+
+ zcs->checksum = params.fParams.checksumFlag > 0;
+ zcs->params = params;
+
+ return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
+}
+
+ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ ZSTD_CStream *const zcs = ZSTD_createCStream_advanced(stackMem);
+ if (zcs) {
+ size_t const code = ZSTD_initCStream_advanced(zcs, NULL, 0, params, pledgedSrcSize);
+ if (ZSTD_isError(code)) {
+ return NULL;
+ }
+ }
+ return zcs;
+}
+
+ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize)
+{
+ ZSTD_parameters const params = ZSTD_getParamsFromCDict(cdict);
+ ZSTD_CStream *const zcs = ZSTD_initCStream(params, pledgedSrcSize, workspace, workspaceSize);
+ if (zcs) {
+ zcs->cdict = cdict;
+ if (ZSTD_isError(ZSTD_resetCStream_internal(zcs, pledgedSrcSize))) {
+ return NULL;
+ }
+ }
+ return zcs;
+}
+
+/*====== Compression ======*/
+
+typedef enum { zsf_gather, zsf_flush, zsf_end } ZSTD_flush_e;
+
+ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t const length = MIN(dstCapacity, srcSize);
+ memcpy(dst, src, length);
+ return length;
+}
+
+static size_t ZSTD_compressStream_generic(ZSTD_CStream *zcs, void *dst, size_t *dstCapacityPtr, const void *src, size_t *srcSizePtr, ZSTD_flush_e const flush)
+{
+ U32 someMoreWork = 1;
+ const char *const istart = (const char *)src;
+ const char *const iend = istart + *srcSizePtr;
+ const char *ip = istart;
+ char *const ostart = (char *)dst;
+ char *const oend = ostart + *dstCapacityPtr;
+ char *op = ostart;
+
+ while (someMoreWork) {
+ switch (zcs->stage) {
+ case zcss_init:
+ return ERROR(init_missing); /* call ZBUFF_compressInit() first ! */
+
+ case zcss_load:
+ /* complete inBuffer */
+ {
+ size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos;
+ size_t const loaded = ZSTD_limitCopy(zcs->inBuff + zcs->inBuffPos, toLoad, ip, iend - ip);
+ zcs->inBuffPos += loaded;
+ ip += loaded;
+ if ((zcs->inBuffPos == zcs->inToCompress) || (!flush && (toLoad != loaded))) {
+ someMoreWork = 0;
+ break; /* not enough input to get a full block : stop there, wait for more */
+ }
+ }
+ /* compress curr block (note : this stage cannot be stopped in the middle) */
+ {
+ void *cDst;
+ size_t cSize;
+ size_t const iSize = zcs->inBuffPos - zcs->inToCompress;
+ size_t oSize = oend - op;
+ if (oSize >= ZSTD_compressBound(iSize))
+ cDst = op; /* compress directly into output buffer (avoid flush stage) */
+ else
+ cDst = zcs->outBuff, oSize = zcs->outBuffSize;
+ cSize = (flush == zsf_end) ? ZSTD_compressEnd(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize)
+ : ZSTD_compressContinue(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize);
+ if (ZSTD_isError(cSize))
+ return cSize;
+ if (flush == zsf_end)
+ zcs->frameEnded = 1;
+ /* prepare next block */
+ zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
+ if (zcs->inBuffTarget > zcs->inBuffSize)
+ zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; /* note : inBuffSize >= blockSize */
+ zcs->inToCompress = zcs->inBuffPos;
+ if (cDst == op) {
+ op += cSize;
+ break;
+ } /* no need to flush */
+ zcs->outBuffContentSize = cSize;
+ zcs->outBuffFlushedSize = 0;
+ zcs->stage = zcss_flush; /* pass-through to flush stage */
+ }
+
+ case zcss_flush: {
+ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
+ size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
+ op += flushed;
+ zcs->outBuffFlushedSize += flushed;
+ if (toFlush != flushed) {
+ someMoreWork = 0;
+ break;
+ } /* dst too small to store flushed data : stop there */
+ zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
+ zcs->stage = zcss_load;
+ break;
+ }
+
+ case zcss_final:
+ someMoreWork = 0; /* do nothing */
+ break;
+
+ default:
+ return ERROR(GENERIC); /* impossible */
+ }
+ }
+
+ *srcSizePtr = ip - istart;
+ *dstCapacityPtr = op - ostart;
+ zcs->inputProcessed += *srcSizePtr;
+ if (zcs->frameEnded)
+ return 0;
+ {
+ size_t hintInSize = zcs->inBuffTarget - zcs->inBuffPos;
+ if (hintInSize == 0)
+ hintInSize = zcs->blockSize;
+ return hintInSize;
+ }
+}
+
+size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, ZSTD_inBuffer *input)
+{
+ size_t sizeRead = input->size - input->pos;
+ size_t sizeWritten = output->size - output->pos;
+ size_t const result =
+ ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, (const char *)(input->src) + input->pos, &sizeRead, zsf_gather);
+ input->pos += sizeRead;
+ output->pos += sizeWritten;
+ return result;
+}
+
+/*====== Finalize ======*/
+
+/*! ZSTD_flushStream() :
+* @return : amount of data remaining to flush */
+size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output)
+{
+ size_t srcSize = 0;
+ size_t sizeWritten = output->size - output->pos;
+ size_t const result = ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, &srcSize,
+ &srcSize, /* use a valid src address instead of NULL */
+ zsf_flush);
+ output->pos += sizeWritten;
+ if (ZSTD_isError(result))
+ return result;
+ return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
+}
+
+size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output)
+{
+ BYTE *const ostart = (BYTE *)(output->dst) + output->pos;
+ BYTE *const oend = (BYTE *)(output->dst) + output->size;
+ BYTE *op = ostart;
+
+ if ((zcs->pledgedSrcSize) && (zcs->inputProcessed != zcs->pledgedSrcSize))
+ return ERROR(srcSize_wrong); /* pledgedSrcSize not respected */
+
+ if (zcs->stage != zcss_final) {
+ /* flush whatever remains */
+ size_t srcSize = 0;
+ size_t sizeWritten = output->size - output->pos;
+ size_t const notEnded =
+ ZSTD_compressStream_generic(zcs, ostart, &sizeWritten, &srcSize, &srcSize, zsf_end); /* use a valid src address instead of NULL */
+ size_t const remainingToFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
+ op += sizeWritten;
+ if (remainingToFlush) {
+ output->pos += sizeWritten;
+ return remainingToFlush + ZSTD_BLOCKHEADERSIZE /* final empty block */ + (zcs->checksum * 4);
+ }
+ /* create epilogue */
+ zcs->stage = zcss_final;
+ zcs->outBuffContentSize = !notEnded ? 0 : ZSTD_compressEnd(zcs->cctx, zcs->outBuff, zcs->outBuffSize, NULL,
+ 0); /* write epilogue, including final empty block, into outBuff */
+ }
+
+ /* flush epilogue */
+ {
+ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
+ size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
+ op += flushed;
+ zcs->outBuffFlushedSize += flushed;
+ output->pos += op - ostart;
+ if (toFlush == flushed)
+ zcs->stage = zcss_init; /* end reached */
+ return toFlush - flushed;
+ }
+}
+
+/*-===== Pre-defined compression levels =====-*/
+
+#define ZSTD_DEFAULT_CLEVEL 1
+#define ZSTD_MAX_CLEVEL 22
+int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
+
+static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL + 1] = {
+ {
+ /* "default" */
+ /* W, C, H, S, L, TL, strat */
+ {18, 12, 12, 1, 7, 16, ZSTD_fast}, /* level 0 - never used */
+ {19, 13, 14, 1, 7, 16, ZSTD_fast}, /* level 1 */
+ {19, 15, 16, 1, 6, 16, ZSTD_fast}, /* level 2 */
+ {20, 16, 17, 1, 5, 16, ZSTD_dfast}, /* level 3.*/
+ {20, 18, 18, 1, 5, 16, ZSTD_dfast}, /* level 4.*/
+ {20, 15, 18, 3, 5, 16, ZSTD_greedy}, /* level 5 */
+ {21, 16, 19, 2, 5, 16, ZSTD_lazy}, /* level 6 */
+ {21, 17, 20, 3, 5, 16, ZSTD_lazy}, /* level 7 */
+ {21, 18, 20, 3, 5, 16, ZSTD_lazy2}, /* level 8 */
+ {21, 20, 20, 3, 5, 16, ZSTD_lazy2}, /* level 9 */
+ {21, 19, 21, 4, 5, 16, ZSTD_lazy2}, /* level 10 */
+ {22, 20, 22, 4, 5, 16, ZSTD_lazy2}, /* level 11 */
+ {22, 20, 22, 5, 5, 16, ZSTD_lazy2}, /* level 12 */
+ {22, 21, 22, 5, 5, 16, ZSTD_lazy2}, /* level 13 */
+ {22, 21, 22, 6, 5, 16, ZSTD_lazy2}, /* level 14 */
+ {22, 21, 21, 5, 5, 16, ZSTD_btlazy2}, /* level 15 */
+ {23, 22, 22, 5, 5, 16, ZSTD_btlazy2}, /* level 16 */
+ {23, 21, 22, 4, 5, 24, ZSTD_btopt}, /* level 17 */
+ {23, 23, 22, 6, 5, 32, ZSTD_btopt}, /* level 18 */
+ {23, 23, 22, 6, 3, 48, ZSTD_btopt}, /* level 19 */
+ {25, 25, 23, 7, 3, 64, ZSTD_btopt2}, /* level 20 */
+ {26, 26, 23, 7, 3, 256, ZSTD_btopt2}, /* level 21 */
+ {27, 27, 25, 9, 3, 512, ZSTD_btopt2}, /* level 22 */
+ },
+ {
+ /* for srcSize <= 256 KB */
+ /* W, C, H, S, L, T, strat */
+ {0, 0, 0, 0, 0, 0, ZSTD_fast}, /* level 0 - not used */
+ {18, 13, 14, 1, 6, 8, ZSTD_fast}, /* level 1 */
+ {18, 14, 13, 1, 5, 8, ZSTD_dfast}, /* level 2 */
+ {18, 16, 15, 1, 5, 8, ZSTD_dfast}, /* level 3 */
+ {18, 15, 17, 1, 5, 8, ZSTD_greedy}, /* level 4.*/
+ {18, 16, 17, 4, 5, 8, ZSTD_greedy}, /* level 5.*/
+ {18, 16, 17, 3, 5, 8, ZSTD_lazy}, /* level 6.*/
+ {18, 17, 17, 4, 4, 8, ZSTD_lazy}, /* level 7 */
+ {18, 17, 17, 4, 4, 8, ZSTD_lazy2}, /* level 8 */
+ {18, 17, 17, 5, 4, 8, ZSTD_lazy2}, /* level 9 */
+ {18, 17, 17, 6, 4, 8, ZSTD_lazy2}, /* level 10 */
+ {18, 18, 17, 6, 4, 8, ZSTD_lazy2}, /* level 11.*/
+ {18, 18, 17, 7, 4, 8, ZSTD_lazy2}, /* level 12.*/
+ {18, 19, 17, 6, 4, 8, ZSTD_btlazy2}, /* level 13 */
+ {18, 18, 18, 4, 4, 16, ZSTD_btopt}, /* level 14.*/
+ {18, 18, 18, 4, 3, 16, ZSTD_btopt}, /* level 15.*/
+ {18, 19, 18, 6, 3, 32, ZSTD_btopt}, /* level 16.*/
+ {18, 19, 18, 8, 3, 64, ZSTD_btopt}, /* level 17.*/
+ {18, 19, 18, 9, 3, 128, ZSTD_btopt}, /* level 18.*/
+ {18, 19, 18, 10, 3, 256, ZSTD_btopt}, /* level 19.*/
+ {18, 19, 18, 11, 3, 512, ZSTD_btopt2}, /* level 20.*/
+ {18, 19, 18, 12, 3, 512, ZSTD_btopt2}, /* level 21.*/
+ {18, 19, 18, 13, 3, 512, ZSTD_btopt2}, /* level 22.*/
+ },
+ {
+ /* for srcSize <= 128 KB */
+ /* W, C, H, S, L, T, strat */
+ {17, 12, 12, 1, 7, 8, ZSTD_fast}, /* level 0 - not used */
+ {17, 12, 13, 1, 6, 8, ZSTD_fast}, /* level 1 */
+ {17, 13, 16, 1, 5, 8, ZSTD_fast}, /* level 2 */
+ {17, 16, 16, 2, 5, 8, ZSTD_dfast}, /* level 3 */
+ {17, 13, 15, 3, 4, 8, ZSTD_greedy}, /* level 4 */
+ {17, 15, 17, 4, 4, 8, ZSTD_greedy}, /* level 5 */
+ {17, 16, 17, 3, 4, 8, ZSTD_lazy}, /* level 6 */
+ {17, 15, 17, 4, 4, 8, ZSTD_lazy2}, /* level 7 */
+ {17, 17, 17, 4, 4, 8, ZSTD_lazy2}, /* level 8 */
+ {17, 17, 17, 5, 4, 8, ZSTD_lazy2}, /* level 9 */
+ {17, 17, 17, 6, 4, 8, ZSTD_lazy2}, /* level 10 */
+ {17, 17, 17, 7, 4, 8, ZSTD_lazy2}, /* level 11 */
+ {17, 17, 17, 8, 4, 8, ZSTD_lazy2}, /* level 12 */
+ {17, 18, 17, 6, 4, 8, ZSTD_btlazy2}, /* level 13.*/
+ {17, 17, 17, 7, 3, 8, ZSTD_btopt}, /* level 14.*/
+ {17, 17, 17, 7, 3, 16, ZSTD_btopt}, /* level 15.*/
+ {17, 18, 17, 7, 3, 32, ZSTD_btopt}, /* level 16.*/
+ {17, 18, 17, 7, 3, 64, ZSTD_btopt}, /* level 17.*/
+ {17, 18, 17, 7, 3, 256, ZSTD_btopt}, /* level 18.*/
+ {17, 18, 17, 8, 3, 256, ZSTD_btopt}, /* level 19.*/
+ {17, 18, 17, 9, 3, 256, ZSTD_btopt2}, /* level 20.*/
+ {17, 18, 17, 10, 3, 256, ZSTD_btopt2}, /* level 21.*/
+ {17, 18, 17, 11, 3, 512, ZSTD_btopt2}, /* level 22.*/
+ },
+ {
+ /* for srcSize <= 16 KB */
+ /* W, C, H, S, L, T, strat */
+ {14, 12, 12, 1, 7, 6, ZSTD_fast}, /* level 0 - not used */
+ {14, 14, 14, 1, 6, 6, ZSTD_fast}, /* level 1 */
+ {14, 14, 14, 1, 4, 6, ZSTD_fast}, /* level 2 */
+ {14, 14, 14, 1, 4, 6, ZSTD_dfast}, /* level 3.*/
+ {14, 14, 14, 4, 4, 6, ZSTD_greedy}, /* level 4.*/
+ {14, 14, 14, 3, 4, 6, ZSTD_lazy}, /* level 5.*/
+ {14, 14, 14, 4, 4, 6, ZSTD_lazy2}, /* level 6 */
+ {14, 14, 14, 5, 4, 6, ZSTD_lazy2}, /* level 7 */
+ {14, 14, 14, 6, 4, 6, ZSTD_lazy2}, /* level 8.*/
+ {14, 15, 14, 6, 4, 6, ZSTD_btlazy2}, /* level 9.*/
+ {14, 15, 14, 3, 3, 6, ZSTD_btopt}, /* level 10.*/
+ {14, 15, 14, 6, 3, 8, ZSTD_btopt}, /* level 11.*/
+ {14, 15, 14, 6, 3, 16, ZSTD_btopt}, /* level 12.*/
+ {14, 15, 14, 6, 3, 24, ZSTD_btopt}, /* level 13.*/
+ {14, 15, 15, 6, 3, 48, ZSTD_btopt}, /* level 14.*/
+ {14, 15, 15, 6, 3, 64, ZSTD_btopt}, /* level 15.*/
+ {14, 15, 15, 6, 3, 96, ZSTD_btopt}, /* level 16.*/
+ {14, 15, 15, 6, 3, 128, ZSTD_btopt}, /* level 17.*/
+ {14, 15, 15, 6, 3, 256, ZSTD_btopt}, /* level 18.*/
+ {14, 15, 15, 7, 3, 256, ZSTD_btopt}, /* level 19.*/
+ {14, 15, 15, 8, 3, 256, ZSTD_btopt2}, /* level 20.*/
+ {14, 15, 15, 9, 3, 256, ZSTD_btopt2}, /* level 21.*/
+ {14, 15, 15, 10, 3, 256, ZSTD_btopt2}, /* level 22.*/
+ },
+};
+
+/*! ZSTD_getCParams() :
+* @return ZSTD_compressionParameters structure for a selected compression level, `srcSize` and `dictSize`.
+* Size values are optional, provide 0 if not known or unused */
+ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
+{
+ ZSTD_compressionParameters cp;
+ size_t const addedSize = srcSize ? 0 : 500;
+ U64 const rSize = srcSize + dictSize ? srcSize + dictSize + addedSize : (U64)-1;
+ U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); /* intentional underflow for srcSizeHint == 0 */
+ if (compressionLevel <= 0)
+ compressionLevel = ZSTD_DEFAULT_CLEVEL; /* 0 == default; no negative compressionLevel yet */
+ if (compressionLevel > ZSTD_MAX_CLEVEL)
+ compressionLevel = ZSTD_MAX_CLEVEL;
+ cp = ZSTD_defaultCParameters[tableID][compressionLevel];
+ if (ZSTD_32bits()) { /* auto-correction, for 32-bits mode */
+ if (cp.windowLog > ZSTD_WINDOWLOG_MAX)
+ cp.windowLog = ZSTD_WINDOWLOG_MAX;
+ if (cp.chainLog > ZSTD_CHAINLOG_MAX)
+ cp.chainLog = ZSTD_CHAINLOG_MAX;
+ if (cp.hashLog > ZSTD_HASHLOG_MAX)
+ cp.hashLog = ZSTD_HASHLOG_MAX;
+ }
+ cp = ZSTD_adjustCParams(cp, srcSize, dictSize);
+ return cp;
+}
+
+/*! ZSTD_getParams() :
+* same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`).
+* All fields of `ZSTD_frameParameters` are set to default (0) */
+ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
+{
+ ZSTD_parameters params;
+ ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSize, dictSize);
+ memset(¶ms, 0, sizeof(params));
+ params.cParams = cParams;
+ return params;
+}
+
+EXPORT_SYMBOL(ZSTD_maxCLevel);
+EXPORT_SYMBOL(ZSTD_compressBound);
+
+EXPORT_SYMBOL(ZSTD_CCtxWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initCCtx);
+EXPORT_SYMBOL(ZSTD_compressCCtx);
+EXPORT_SYMBOL(ZSTD_compress_usingDict);
+
+EXPORT_SYMBOL(ZSTD_CDictWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initCDict);
+EXPORT_SYMBOL(ZSTD_compress_usingCDict);
+
+EXPORT_SYMBOL(ZSTD_CStreamWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initCStream);
+EXPORT_SYMBOL(ZSTD_initCStream_usingCDict);
+EXPORT_SYMBOL(ZSTD_resetCStream);
+EXPORT_SYMBOL(ZSTD_compressStream);
+EXPORT_SYMBOL(ZSTD_flushStream);
+EXPORT_SYMBOL(ZSTD_endStream);
+EXPORT_SYMBOL(ZSTD_CStreamInSize);
+EXPORT_SYMBOL(ZSTD_CStreamOutSize);
+
+EXPORT_SYMBOL(ZSTD_getCParams);
+EXPORT_SYMBOL(ZSTD_getParams);
+EXPORT_SYMBOL(ZSTD_checkCParams);
+EXPORT_SYMBOL(ZSTD_adjustCParams);
+
+EXPORT_SYMBOL(ZSTD_compressBegin);
+EXPORT_SYMBOL(ZSTD_compressBegin_usingDict);
+EXPORT_SYMBOL(ZSTD_compressBegin_advanced);
+EXPORT_SYMBOL(ZSTD_copyCCtx);
+EXPORT_SYMBOL(ZSTD_compressBegin_usingCDict);
+EXPORT_SYMBOL(ZSTD_compressContinue);
+EXPORT_SYMBOL(ZSTD_compressEnd);
+
+EXPORT_SYMBOL(ZSTD_getBlockSizeMax);
+EXPORT_SYMBOL(ZSTD_compressBlock);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Zstd Compressor");
diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
new file mode 100644
index 0000000..b178467
--- /dev/null
+++ b/lib/zstd/decompress.c
@@ -0,0 +1,2528 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+/* ***************************************************************
+* Tuning parameters
+*****************************************************************/
+/*!
+* MAXWINDOWSIZE_DEFAULT :
+* maximum window size accepted by DStream, by default.
+* Frames requiring more memory will be rejected.
+*/
+#ifndef ZSTD_MAXWINDOWSIZE_DEFAULT
+#define ZSTD_MAXWINDOWSIZE_DEFAULT ((1 << ZSTD_WINDOWLOG_MAX) + 1) /* defined within zstd.h */
+#endif
+
+/*-*******************************************************
+* Dependencies
+*********************************************************/
+#include "fse.h"
+#include "huf.h"
+#include "mem.h" /* low level memory routines */
+#include "zstd_internal.h"
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h> /* memcpy, memmove, memset */
+
+#define ZSTD_PREFETCH(ptr) __builtin_prefetch(ptr, 0, 0)
+
+/*-*************************************
+* Macros
+***************************************/
+#define ZSTD_isError ERR_isError /* for inlining */
+#define FSE_isError ERR_isError
+#define HUF_isError ERR_isError
+
+/*_*******************************************************
+* Memory operations
+**********************************************************/
+static void ZSTD_copy4(void *dst, const void *src) { memcpy(dst, src, 4); }
+
+/*-*************************************************************
+* Context management
+***************************************************************/
+typedef enum {
+ ZSTDds_getFrameHeaderSize,
+ ZSTDds_decodeFrameHeader,
+ ZSTDds_decodeBlockHeader,
+ ZSTDds_decompressBlock,
+ ZSTDds_decompressLastBlock,
+ ZSTDds_checkChecksum,
+ ZSTDds_decodeSkippableHeader,
+ ZSTDds_skipFrame
+} ZSTD_dStage;
+
+typedef struct {
+ FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)];
+ FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
+ FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)];
+ HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)]; /* can accommodate HUF_decompress4X */
+ U64 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32 / 2];
+ U32 rep[ZSTD_REP_NUM];
+} ZSTD_entropyTables_t;
+
+struct ZSTD_DCtx_s {
+ const FSE_DTable *LLTptr;
+ const FSE_DTable *MLTptr;
+ const FSE_DTable *OFTptr;
+ const HUF_DTable *HUFptr;
+ ZSTD_entropyTables_t entropy;
+ const void *previousDstEnd; /* detect continuity */
+ const void *base; /* start of curr segment */
+ const void *vBase; /* virtual start of previous segment if it was just before curr one */
+ const void *dictEnd; /* end of previous segment */
+ size_t expected;
+ ZSTD_frameParams fParams;
+ blockType_e bType; /* used in ZSTD_decompressContinue(), to transfer blockType between header decoding and block decoding stages */
+ ZSTD_dStage stage;
+ U32 litEntropy;
+ U32 fseEntropy;
+ struct xxh64_state xxhState;
+ size_t headerSize;
+ U32 dictID;
+ const BYTE *litPtr;
+ ZSTD_customMem customMem;
+ size_t litSize;
+ size_t rleSize;
+ BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH];
+ BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
+}; /* typedef'd to ZSTD_DCtx within "zstd.h" */
+
+size_t ZSTD_DCtxWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DCtx)); }
+
+size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx)
+{
+ dctx->expected = ZSTD_frameHeaderSize_prefix;
+ dctx->stage = ZSTDds_getFrameHeaderSize;
+ dctx->previousDstEnd = NULL;
+ dctx->base = NULL;
+ dctx->vBase = NULL;
+ dctx->dictEnd = NULL;
+ dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
+ dctx->litEntropy = dctx->fseEntropy = 0;
+ dctx->dictID = 0;
+ ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue));
+ memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue)); /* initial repcodes */
+ dctx->LLTptr = dctx->entropy.LLTable;
+ dctx->MLTptr = dctx->entropy.MLTable;
+ dctx->OFTptr = dctx->entropy.OFTable;
+ dctx->HUFptr = dctx->entropy.hufTable;
+ return 0;
+}
+
+ZSTD_DCtx *ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
+{
+ ZSTD_DCtx *dctx;
+
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+
+ dctx = (ZSTD_DCtx *)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem);
+ if (!dctx)
+ return NULL;
+ memcpy(&dctx->customMem, &customMem, sizeof(customMem));
+ ZSTD_decompressBegin(dctx);
+ return dctx;
+}
+
+ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ return ZSTD_createDCtx_advanced(stackMem);
+}
+
+size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx)
+{
+ if (dctx == NULL)
+ return 0; /* support free on NULL */
+ ZSTD_free(dctx, dctx->customMem);
+ return 0; /* reserved as a potential error code in the future */
+}
+
+void ZSTD_copyDCtx(ZSTD_DCtx *dstDCtx, const ZSTD_DCtx *srcDCtx)
+{
+ size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max;
+ memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize); /* no need to copy workspace */
+}
+
+static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict);
+
+/*-*************************************************************
+* Decompression section
+***************************************************************/
+
+/*! ZSTD_isFrame() :
+ * Tells if the content of `buffer` starts with a valid Frame Identifier.
+ * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0.
+ * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled.
+ * Note 3 : Skippable Frame Identifiers are considered valid. */
+unsigned ZSTD_isFrame(const void *buffer, size_t size)
+{
+ if (size < 4)
+ return 0;
+ {
+ U32 const magic = ZSTD_readLE32(buffer);
+ if (magic == ZSTD_MAGICNUMBER)
+ return 1;
+ if ((magic & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START)
+ return 1;
+ }
+ return 0;
+}
+
+/** ZSTD_frameHeaderSize() :
+* srcSize must be >= ZSTD_frameHeaderSize_prefix.
+* @return : size of the Frame Header */
+static size_t ZSTD_frameHeaderSize(const void *src, size_t srcSize)
+{
+ if (srcSize < ZSTD_frameHeaderSize_prefix)
+ return ERROR(srcSize_wrong);
+ {
+ BYTE const fhd = ((const BYTE *)src)[4];
+ U32 const dictID = fhd & 3;
+ U32 const singleSegment = (fhd >> 5) & 1;
+ U32 const fcsId = fhd >> 6;
+ return ZSTD_frameHeaderSize_prefix + !singleSegment + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] + (singleSegment && !fcsId);
+ }
+}
+
+/** ZSTD_getFrameParams() :
+* decode Frame Header, or require larger `srcSize`.
+* @return : 0, `fparamsPtr` is correctly filled,
+* >0, `srcSize` is too small, result is expected `srcSize`,
+* or an error code, which can be tested using ZSTD_isError() */
+size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, size_t srcSize)
+{
+ const BYTE *ip = (const BYTE *)src;
+
+ if (srcSize < ZSTD_frameHeaderSize_prefix)
+ return ZSTD_frameHeaderSize_prefix;
+ if (ZSTD_readLE32(src) != ZSTD_MAGICNUMBER) {
+ if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+ if (srcSize < ZSTD_skippableHeaderSize)
+ return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */
+ memset(fparamsPtr, 0, sizeof(*fparamsPtr));
+ fparamsPtr->frameContentSize = ZSTD_readLE32((const char *)src + 4);
+ fparamsPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
+ return 0;
+ }
+ return ERROR(prefix_unknown);
+ }
+
+ /* ensure there is enough `srcSize` to fully read/decode frame header */
+ {
+ size_t const fhsize = ZSTD_frameHeaderSize(src, srcSize);
+ if (srcSize < fhsize)
+ return fhsize;
+ }
+
+ {
+ BYTE const fhdByte = ip[4];
+ size_t pos = 5;
+ U32 const dictIDSizeCode = fhdByte & 3;
+ U32 const checksumFlag = (fhdByte >> 2) & 1;
+ U32 const singleSegment = (fhdByte >> 5) & 1;
+ U32 const fcsID = fhdByte >> 6;
+ U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX;
+ U32 windowSize = 0;
+ U32 dictID = 0;
+ U64 frameContentSize = 0;
+ if ((fhdByte & 0x08) != 0)
+ return ERROR(frameParameter_unsupported); /* reserved bits, which must be zero */
+ if (!singleSegment) {
+ BYTE const wlByte = ip[pos++];
+ U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
+ if (windowLog > ZSTD_WINDOWLOG_MAX)
+ return ERROR(frameParameter_windowTooLarge); /* avoids issue with 1 << windowLog */
+ windowSize = (1U << windowLog);
+ windowSize += (windowSize >> 3) * (wlByte & 7);
+ }
+
+ switch (dictIDSizeCode) {
+ default: /* impossible */
+ case 0: break;
+ case 1:
+ dictID = ip[pos];
+ pos++;
+ break;
+ case 2:
+ dictID = ZSTD_readLE16(ip + pos);
+ pos += 2;
+ break;
+ case 3:
+ dictID = ZSTD_readLE32(ip + pos);
+ pos += 4;
+ break;
+ }
+ switch (fcsID) {
+ default: /* impossible */
+ case 0:
+ if (singleSegment)
+ frameContentSize = ip[pos];
+ break;
+ case 1: frameContentSize = ZSTD_readLE16(ip + pos) + 256; break;
+ case 2: frameContentSize = ZSTD_readLE32(ip + pos); break;
+ case 3: frameContentSize = ZSTD_readLE64(ip + pos); break;
+ }
+ if (!windowSize)
+ windowSize = (U32)frameContentSize;
+ if (windowSize > windowSizeMax)
+ return ERROR(frameParameter_windowTooLarge);
+ fparamsPtr->frameContentSize = frameContentSize;
+ fparamsPtr->windowSize = windowSize;
+ fparamsPtr->dictID = dictID;
+ fparamsPtr->checksumFlag = checksumFlag;
+ }
+ return 0;
+}
+
+/** ZSTD_getFrameContentSize() :
+* compatible with legacy mode
+* @return : decompressed size of the single frame pointed to be `src` if known, otherwise
+* - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+* - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
+unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
+{
+ {
+ ZSTD_frameParams fParams;
+ if (ZSTD_getFrameParams(&fParams, src, srcSize) != 0)
+ return ZSTD_CONTENTSIZE_ERROR;
+ if (fParams.windowSize == 0) {
+ /* Either skippable or empty frame, size == 0 either way */
+ return 0;
+ } else if (fParams.frameContentSize != 0) {
+ return fParams.frameContentSize;
+ } else {
+ return ZSTD_CONTENTSIZE_UNKNOWN;
+ }
+ }
+}
+
+/** ZSTD_findDecompressedSize() :
+ * compatible with legacy mode
+ * `srcSize` must be the exact length of some number of ZSTD compressed and/or
+ * skippable frames
+ * @return : decompressed size of the frames contained */
+unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize)
+{
+ {
+ unsigned long long totalDstSize = 0;
+ while (srcSize >= ZSTD_frameHeaderSize_prefix) {
+ const U32 magicNumber = ZSTD_readLE32(src);
+
+ if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+ size_t skippableSize;
+ if (srcSize < ZSTD_skippableHeaderSize)
+ return ERROR(srcSize_wrong);
+ skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize;
+ if (srcSize < skippableSize) {
+ return ZSTD_CONTENTSIZE_ERROR;
+ }
+
+ src = (const BYTE *)src + skippableSize;
+ srcSize -= skippableSize;
+ continue;
+ }
+
+ {
+ unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
+ if (ret >= ZSTD_CONTENTSIZE_ERROR)
+ return ret;
+
+ /* check for overflow */
+ if (totalDstSize + ret < totalDstSize)
+ return ZSTD_CONTENTSIZE_ERROR;
+ totalDstSize += ret;
+ }
+ {
+ size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
+ if (ZSTD_isError(frameSrcSize)) {
+ return ZSTD_CONTENTSIZE_ERROR;
+ }
+
+ src = (const BYTE *)src + frameSrcSize;
+ srcSize -= frameSrcSize;
+ }
+ }
+
+ if (srcSize) {
+ return ZSTD_CONTENTSIZE_ERROR;
+ }
+
+ return totalDstSize;
+ }
+}
+
+/** ZSTD_decodeFrameHeader() :
+* `headerSize` must be the size provided by ZSTD_frameHeaderSize().
+* @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */
+static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx *dctx, const void *src, size_t headerSize)
+{
+ size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize);
+ if (ZSTD_isError(result))
+ return result; /* invalid header */
+ if (result > 0)
+ return ERROR(srcSize_wrong); /* headerSize too small */
+ if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID))
+ return ERROR(dictionary_wrong);
+ if (dctx->fParams.checksumFlag)
+ xxh64_reset(&dctx->xxhState, 0);
+ return 0;
+}
+
+typedef struct {
+ blockType_e blockType;
+ U32 lastBlock;
+ U32 origSize;
+} blockProperties_t;
+
+/*! ZSTD_getcBlockSize() :
+* Provides the size of compressed block from block header `src` */
+size_t ZSTD_getcBlockSize(const void *src, size_t srcSize, blockProperties_t *bpPtr)
+{
+ if (srcSize < ZSTD_blockHeaderSize)
+ return ERROR(srcSize_wrong);
+ {
+ U32 const cBlockHeader = ZSTD_readLE24(src);
+ U32 const cSize = cBlockHeader >> 3;
+ bpPtr->lastBlock = cBlockHeader & 1;
+ bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
+ bpPtr->origSize = cSize; /* only useful for RLE */
+ if (bpPtr->blockType == bt_rle)
+ return 1;
+ if (bpPtr->blockType == bt_reserved)
+ return ERROR(corruption_detected);
+ return cSize;
+ }
+}
+
+static size_t ZSTD_copyRawBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ if (srcSize > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+ memcpy(dst, src, srcSize);
+ return srcSize;
+}
+
+static size_t ZSTD_setRleBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize, size_t regenSize)
+{
+ if (srcSize != 1)
+ return ERROR(srcSize_wrong);
+ if (regenSize > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+ memset(dst, *(const BYTE *)src, regenSize);
+ return regenSize;
+}
+
+/*! ZSTD_decodeLiteralsBlock() :
+ @return : nb of bytes read from src (< srcSize ) */
+size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize) /* note : srcSize < BLOCKSIZE */
+{
+ if (srcSize < MIN_CBLOCK_SIZE)
+ return ERROR(corruption_detected);
+
+ {
+ const BYTE *const istart = (const BYTE *)src;
+ symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
+
+ switch (litEncType) {
+ case set_repeat:
+ if (dctx->litEntropy == 0)
+ return ERROR(dictionary_corrupted);
+ /* fall-through */
+ case set_compressed:
+ if (srcSize < 5)
+ return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
+ {
+ size_t lhSize, litSize, litCSize;
+ U32 singleStream = 0;
+ U32 const lhlCode = (istart[0] >> 2) & 3;
+ U32 const lhc = ZSTD_readLE32(istart);
+ switch (lhlCode) {
+ case 0:
+ case 1:
+ default: /* note : default is impossible, since lhlCode into [0..3] */
+ /* 2 - 2 - 10 - 10 */
+ singleStream = !lhlCode;
+ lhSize = 3;
+ litSize = (lhc >> 4) & 0x3FF;
+ litCSize = (lhc >> 14) & 0x3FF;
+ break;
+ case 2:
+ /* 2 - 2 - 14 - 14 */
+ lhSize = 4;
+ litSize = (lhc >> 4) & 0x3FFF;
+ litCSize = lhc >> 18;
+ break;
+ case 3:
+ /* 2 - 2 - 18 - 18 */
+ lhSize = 5;
+ litSize = (lhc >> 4) & 0x3FFFF;
+ litCSize = (lhc >> 22) + (istart[4] << 10);
+ break;
+ }
+ if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX)
+ return ERROR(corruption_detected);
+ if (litCSize + lhSize > srcSize)
+ return ERROR(corruption_detected);
+
+ if (HUF_isError(
+ (litEncType == set_repeat)
+ ? (singleStream ? HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr)
+ : HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr))
+ : (singleStream
+ ? HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize,
+ dctx->entropy.workspace, sizeof(dctx->entropy.workspace))
+ : HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize,
+ dctx->entropy.workspace, sizeof(dctx->entropy.workspace)))))
+ return ERROR(corruption_detected);
+
+ dctx->litPtr = dctx->litBuffer;
+ dctx->litSize = litSize;
+ dctx->litEntropy = 1;
+ if (litEncType == set_compressed)
+ dctx->HUFptr = dctx->entropy.hufTable;
+ memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
+ return litCSize + lhSize;
+ }
+
+ case set_basic: {
+ size_t litSize, lhSize;
+ U32 const lhlCode = ((istart[0]) >> 2) & 3;
+ switch (lhlCode) {
+ case 0:
+ case 2:
+ default: /* note : default is impossible, since lhlCode into [0..3] */
+ lhSize = 1;
+ litSize = istart[0] >> 3;
+ break;
+ case 1:
+ lhSize = 2;
+ litSize = ZSTD_readLE16(istart) >> 4;
+ break;
+ case 3:
+ lhSize = 3;
+ litSize = ZSTD_readLE24(istart) >> 4;
+ break;
+ }
+
+ if (lhSize + litSize + WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */
+ if (litSize + lhSize > srcSize)
+ return ERROR(corruption_detected);
+ memcpy(dctx->litBuffer, istart + lhSize, litSize);
+ dctx->litPtr = dctx->litBuffer;
+ dctx->litSize = litSize;
+ memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
+ return lhSize + litSize;
+ }
+ /* direct reference into compressed stream */
+ dctx->litPtr = istart + lhSize;
+ dctx->litSize = litSize;
+ return lhSize + litSize;
+ }
+
+ case set_rle: {
+ U32 const lhlCode = ((istart[0]) >> 2) & 3;
+ size_t litSize, lhSize;
+ switch (lhlCode) {
+ case 0:
+ case 2:
+ default: /* note : default is impossible, since lhlCode into [0..3] */
+ lhSize = 1;
+ litSize = istart[0] >> 3;
+ break;
+ case 1:
+ lhSize = 2;
+ litSize = ZSTD_readLE16(istart) >> 4;
+ break;
+ case 3:
+ lhSize = 3;
+ litSize = ZSTD_readLE24(istart) >> 4;
+ if (srcSize < 4)
+ return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
+ break;
+ }
+ if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX)
+ return ERROR(corruption_detected);
+ memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
+ dctx->litPtr = dctx->litBuffer;
+ dctx->litSize = litSize;
+ return lhSize + 1;
+ }
+ default:
+ return ERROR(corruption_detected); /* impossible */
+ }
+ }
+}
+
+typedef union {
+ FSE_decode_t realData;
+ U32 alignedBy4;
+} FSE_decode_t4;
+
+static const FSE_decode_t4 LL_defaultDTable[(1 << LL_DEFAULTNORMLOG) + 1] = {
+ {{LL_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
+ {{0, 0, 4}}, /* 0 : base, symbol, bits */
+ {{16, 0, 4}},
+ {{32, 1, 5}},
+ {{0, 3, 5}},
+ {{0, 4, 5}},
+ {{0, 6, 5}},
+ {{0, 7, 5}},
+ {{0, 9, 5}},
+ {{0, 10, 5}},
+ {{0, 12, 5}},
+ {{0, 14, 6}},
+ {{0, 16, 5}},
+ {{0, 18, 5}},
+ {{0, 19, 5}},
+ {{0, 21, 5}},
+ {{0, 22, 5}},
+ {{0, 24, 5}},
+ {{32, 25, 5}},
+ {{0, 26, 5}},
+ {{0, 27, 6}},
+ {{0, 29, 6}},
+ {{0, 31, 6}},
+ {{32, 0, 4}},
+ {{0, 1, 4}},
+ {{0, 2, 5}},
+ {{32, 4, 5}},
+ {{0, 5, 5}},
+ {{32, 7, 5}},
+ {{0, 8, 5}},
+ {{32, 10, 5}},
+ {{0, 11, 5}},
+ {{0, 13, 6}},
+ {{32, 16, 5}},
+ {{0, 17, 5}},
+ {{32, 19, 5}},
+ {{0, 20, 5}},
+ {{32, 22, 5}},
+ {{0, 23, 5}},
+ {{0, 25, 4}},
+ {{16, 25, 4}},
+ {{32, 26, 5}},
+ {{0, 28, 6}},
+ {{0, 30, 6}},
+ {{48, 0, 4}},
+ {{16, 1, 4}},
+ {{32, 2, 5}},
+ {{32, 3, 5}},
+ {{32, 5, 5}},
+ {{32, 6, 5}},
+ {{32, 8, 5}},
+ {{32, 9, 5}},
+ {{32, 11, 5}},
+ {{32, 12, 5}},
+ {{0, 15, 6}},
+ {{32, 17, 5}},
+ {{32, 18, 5}},
+ {{32, 20, 5}},
+ {{32, 21, 5}},
+ {{32, 23, 5}},
+ {{32, 24, 5}},
+ {{0, 35, 6}},
+ {{0, 34, 6}},
+ {{0, 33, 6}},
+ {{0, 32, 6}},
+}; /* LL_defaultDTable */
+
+static const FSE_decode_t4 ML_defaultDTable[(1 << ML_DEFAULTNORMLOG) + 1] = {
+ {{ML_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
+ {{0, 0, 6}}, /* 0 : base, symbol, bits */
+ {{0, 1, 4}},
+ {{32, 2, 5}},
+ {{0, 3, 5}},
+ {{0, 5, 5}},
+ {{0, 6, 5}},
+ {{0, 8, 5}},
+ {{0, 10, 6}},
+ {{0, 13, 6}},
+ {{0, 16, 6}},
+ {{0, 19, 6}},
+ {{0, 22, 6}},
+ {{0, 25, 6}},
+ {{0, 28, 6}},
+ {{0, 31, 6}},
+ {{0, 33, 6}},
+ {{0, 35, 6}},
+ {{0, 37, 6}},
+ {{0, 39, 6}},
+ {{0, 41, 6}},
+ {{0, 43, 6}},
+ {{0, 45, 6}},
+ {{16, 1, 4}},
+ {{0, 2, 4}},
+ {{32, 3, 5}},
+ {{0, 4, 5}},
+ {{32, 6, 5}},
+ {{0, 7, 5}},
+ {{0, 9, 6}},
+ {{0, 12, 6}},
+ {{0, 15, 6}},
+ {{0, 18, 6}},
+ {{0, 21, 6}},
+ {{0, 24, 6}},
+ {{0, 27, 6}},
+ {{0, 30, 6}},
+ {{0, 32, 6}},
+ {{0, 34, 6}},
+ {{0, 36, 6}},
+ {{0, 38, 6}},
+ {{0, 40, 6}},
+ {{0, 42, 6}},
+ {{0, 44, 6}},
+ {{32, 1, 4}},
+ {{48, 1, 4}},
+ {{16, 2, 4}},
+ {{32, 4, 5}},
+ {{32, 5, 5}},
+ {{32, 7, 5}},
+ {{32, 8, 5}},
+ {{0, 11, 6}},
+ {{0, 14, 6}},
+ {{0, 17, 6}},
+ {{0, 20, 6}},
+ {{0, 23, 6}},
+ {{0, 26, 6}},
+ {{0, 29, 6}},
+ {{0, 52, 6}},
+ {{0, 51, 6}},
+ {{0, 50, 6}},
+ {{0, 49, 6}},
+ {{0, 48, 6}},
+ {{0, 47, 6}},
+ {{0, 46, 6}},
+}; /* ML_defaultDTable */
+
+static const FSE_decode_t4 OF_defaultDTable[(1 << OF_DEFAULTNORMLOG) + 1] = {
+ {{OF_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
+ {{0, 0, 5}}, /* 0 : base, symbol, bits */
+ {{0, 6, 4}},
+ {{0, 9, 5}},
+ {{0, 15, 5}},
+ {{0, 21, 5}},
+ {{0, 3, 5}},
+ {{0, 7, 4}},
+ {{0, 12, 5}},
+ {{0, 18, 5}},
+ {{0, 23, 5}},
+ {{0, 5, 5}},
+ {{0, 8, 4}},
+ {{0, 14, 5}},
+ {{0, 20, 5}},
+ {{0, 2, 5}},
+ {{16, 7, 4}},
+ {{0, 11, 5}},
+ {{0, 17, 5}},
+ {{0, 22, 5}},
+ {{0, 4, 5}},
+ {{16, 8, 4}},
+ {{0, 13, 5}},
+ {{0, 19, 5}},
+ {{0, 1, 5}},
+ {{16, 6, 4}},
+ {{0, 10, 5}},
+ {{0, 16, 5}},
+ {{0, 28, 5}},
+ {{0, 27, 5}},
+ {{0, 26, 5}},
+ {{0, 25, 5}},
+ {{0, 24, 5}},
+}; /* OF_defaultDTable */
+
+/*! ZSTD_buildSeqTable() :
+ @return : nb bytes read from src,
+ or an error code if it fails, testable with ZSTD_isError()
+*/
+static size_t ZSTD_buildSeqTable(FSE_DTable *DTableSpace, const FSE_DTable **DTablePtr, symbolEncodingType_e type, U32 max, U32 maxLog, const void *src,
+ size_t srcSize, const FSE_decode_t4 *defaultTable, U32 flagRepeatTable, void *workspace, size_t workspaceSize)
+{
+ const void *const tmpPtr = defaultTable; /* bypass strict aliasing */
+ switch (type) {
+ case set_rle:
+ if (!srcSize)
+ return ERROR(srcSize_wrong);
+ if ((*(const BYTE *)src) > max)
+ return ERROR(corruption_detected);
+ FSE_buildDTable_rle(DTableSpace, *(const BYTE *)src);
+ *DTablePtr = DTableSpace;
+ return 1;
+ case set_basic: *DTablePtr = (const FSE_DTable *)tmpPtr; return 0;
+ case set_repeat:
+ if (!flagRepeatTable)
+ return ERROR(corruption_detected);
+ return 0;
+ default: /* impossible */
+ case set_compressed: {
+ U32 tableLog;
+ S16 *norm = (S16 *)workspace;
+ size_t const spaceUsed32 = ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(GENERIC);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+ {
+ size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
+ if (FSE_isError(headerSize))
+ return ERROR(corruption_detected);
+ if (tableLog > maxLog)
+ return ERROR(corruption_detected);
+ FSE_buildDTable_wksp(DTableSpace, norm, max, tableLog, workspace, workspaceSize);
+ *DTablePtr = DTableSpace;
+ return headerSize;
+ }
+ }
+ }
+}
+
+size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx *dctx, int *nbSeqPtr, const void *src, size_t srcSize)
+{
+ const BYTE *const istart = (const BYTE *const)src;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *ip = istart;
+
+ /* check */
+ if (srcSize < MIN_SEQUENCES_SIZE)
+ return ERROR(srcSize_wrong);
+
+ /* SeqHead */
+ {
+ int nbSeq = *ip++;
+ if (!nbSeq) {
+ *nbSeqPtr = 0;
+ return 1;
+ }
+ if (nbSeq > 0x7F) {
+ if (nbSeq == 0xFF) {
+ if (ip + 2 > iend)
+ return ERROR(srcSize_wrong);
+ nbSeq = ZSTD_readLE16(ip) + LONGNBSEQ, ip += 2;
+ } else {
+ if (ip >= iend)
+ return ERROR(srcSize_wrong);
+ nbSeq = ((nbSeq - 0x80) << 8) + *ip++;
+ }
+ }
+ *nbSeqPtr = nbSeq;
+ }
+
+ /* FSE table descriptors */
+ if (ip + 4 > iend)
+ return ERROR(srcSize_wrong); /* minimum possible size */
+ {
+ symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
+ symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
+ symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
+ ip++;
+
+ /* Build DTables */
+ {
+ size_t const llhSize = ZSTD_buildSeqTable(dctx->entropy.LLTable, &dctx->LLTptr, LLtype, MaxLL, LLFSELog, ip, iend - ip,
+ LL_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
+ if (ZSTD_isError(llhSize))
+ return ERROR(corruption_detected);
+ ip += llhSize;
+ }
+ {
+ size_t const ofhSize = ZSTD_buildSeqTable(dctx->entropy.OFTable, &dctx->OFTptr, OFtype, MaxOff, OffFSELog, ip, iend - ip,
+ OF_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
+ if (ZSTD_isError(ofhSize))
+ return ERROR(corruption_detected);
+ ip += ofhSize;
+ }
+ {
+ size_t const mlhSize = ZSTD_buildSeqTable(dctx->entropy.MLTable, &dctx->MLTptr, MLtype, MaxML, MLFSELog, ip, iend - ip,
+ ML_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
+ if (ZSTD_isError(mlhSize))
+ return ERROR(corruption_detected);
+ ip += mlhSize;
+ }
+ }
+
+ return ip - istart;
+}
+
+typedef struct {
+ size_t litLength;
+ size_t matchLength;
+ size_t offset;
+ const BYTE *match;
+} seq_t;
+
+typedef struct {
+ BIT_DStream_t DStream;
+ FSE_DState_t stateLL;
+ FSE_DState_t stateOffb;
+ FSE_DState_t stateML;
+ size_t prevOffset[ZSTD_REP_NUM];
+ const BYTE *base;
+ size_t pos;
+ uPtrDiff gotoDict;
+} seqState_t;
+
+FORCE_NOINLINE
+size_t ZSTD_execSequenceLast7(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
+ const BYTE *const vBase, const BYTE *const dictEnd)
+{
+ BYTE *const oLitEnd = op + sequence.litLength;
+ size_t const sequenceLength = sequence.litLength + sequence.matchLength;
+ BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
+ BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
+ const BYTE *const iLitEnd = *litPtr + sequence.litLength;
+ const BYTE *match = oLitEnd - sequence.offset;
+
+ /* check */
+ if (oMatchEnd > oend)
+ return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
+ if (iLitEnd > litLimit)
+ return ERROR(corruption_detected); /* over-read beyond lit buffer */
+ if (oLitEnd <= oend_w)
+ return ERROR(GENERIC); /* Precondition */
+
+ /* copy literals */
+ if (op < oend_w) {
+ ZSTD_wildcopy(op, *litPtr, oend_w - op);
+ *litPtr += oend_w - op;
+ op = oend_w;
+ }
+ while (op < oLitEnd)
+ *op++ = *(*litPtr)++;
+
+ /* copy Match */
+ if (sequence.offset > (size_t)(oLitEnd - base)) {
+ /* offset beyond prefix */
+ if (sequence.offset > (size_t)(oLitEnd - vBase))
+ return ERROR(corruption_detected);
+ match = dictEnd - (base - match);
+ if (match + sequence.matchLength <= dictEnd) {
+ memmove(oLitEnd, match, sequence.matchLength);
+ return sequenceLength;
+ }
+ /* span extDict & currPrefixSegment */
+ {
+ size_t const length1 = dictEnd - match;
+ memmove(oLitEnd, match, length1);
+ op = oLitEnd + length1;
+ sequence.matchLength -= length1;
+ match = base;
+ }
+ }
+ while (op < oMatchEnd)
+ *op++ = *match++;
+ return sequenceLength;
+}
+
+static seq_t ZSTD_decodeSequence(seqState_t *seqState)
+{
+ seq_t seq;
+
+ U32 const llCode = FSE_peekSymbol(&seqState->stateLL);
+ U32 const mlCode = FSE_peekSymbol(&seqState->stateML);
+ U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */
+
+ U32 const llBits = LL_bits[llCode];
+ U32 const mlBits = ML_bits[mlCode];
+ U32 const ofBits = ofCode;
+ U32 const totalBits = llBits + mlBits + ofBits;
+
+ static const U32 LL_base[MaxLL + 1] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18,
+ 20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000};
+
+ static const U32 ML_base[MaxML + 1] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+ 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 39, 41,
+ 43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003};
+
+ static const U32 OF_base[MaxOff + 1] = {0, 1, 1, 5, 0xD, 0x1D, 0x3D, 0x7D, 0xFD, 0x1FD,
+ 0x3FD, 0x7FD, 0xFFD, 0x1FFD, 0x3FFD, 0x7FFD, 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD,
+ 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD};
+
+ /* sequence */
+ {
+ size_t offset;
+ if (!ofCode)
+ offset = 0;
+ else {
+ offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <= (ZSTD_WINDOWLOG_MAX-1) bits */
+ if (ZSTD_32bits())
+ BIT_reloadDStream(&seqState->DStream);
+ }
+
+ if (ofCode <= 1) {
+ offset += (llCode == 0);
+ if (offset) {
+ size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset];
+ temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */
+ if (offset != 1)
+ seqState->prevOffset[2] = seqState->prevOffset[1];
+ seqState->prevOffset[1] = seqState->prevOffset[0];
+ seqState->prevOffset[0] = offset = temp;
+ } else {
+ offset = seqState->prevOffset[0];
+ }
+ } else {
+ seqState->prevOffset[2] = seqState->prevOffset[1];
+ seqState->prevOffset[1] = seqState->prevOffset[0];
+ seqState->prevOffset[0] = offset;
+ }
+ seq.offset = offset;
+ }
+
+ seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */
+ if (ZSTD_32bits() && (mlBits + llBits > 24))
+ BIT_reloadDStream(&seqState->DStream);
+
+ seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */
+ if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
+ BIT_reloadDStream(&seqState->DStream);
+
+ /* ANS state update */
+ FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */
+ FSE_updateState(&seqState->stateML, &seqState->DStream); /* <= 9 bits */
+ if (ZSTD_32bits())
+ BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */
+ FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <= 8 bits */
+
+ seq.match = NULL;
+
+ return seq;
+}
+
+FORCE_INLINE
+size_t ZSTD_execSequence(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
+ const BYTE *const vBase, const BYTE *const dictEnd)
+{
+ BYTE *const oLitEnd = op + sequence.litLength;
+ size_t const sequenceLength = sequence.litLength + sequence.matchLength;
+ BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
+ BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
+ const BYTE *const iLitEnd = *litPtr + sequence.litLength;
+ const BYTE *match = oLitEnd - sequence.offset;
+
+ /* check */
+ if (oMatchEnd > oend)
+ return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
+ if (iLitEnd > litLimit)
+ return ERROR(corruption_detected); /* over-read beyond lit buffer */
+ if (oLitEnd > oend_w)
+ return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd);
+
+ /* copy Literals */
+ ZSTD_copy8(op, *litPtr);
+ if (sequence.litLength > 8)
+ ZSTD_wildcopy(op + 8, (*litPtr) + 8,
+ sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+ op = oLitEnd;
+ *litPtr = iLitEnd; /* update for next sequence */
+
+ /* copy Match */
+ if (sequence.offset > (size_t)(oLitEnd - base)) {
+ /* offset beyond prefix */
+ if (sequence.offset > (size_t)(oLitEnd - vBase))
+ return ERROR(corruption_detected);
+ match = dictEnd + (match - base);
+ if (match + sequence.matchLength <= dictEnd) {
+ memmove(oLitEnd, match, sequence.matchLength);
+ return sequenceLength;
+ }
+ /* span extDict & currPrefixSegment */
+ {
+ size_t const length1 = dictEnd - match;
+ memmove(oLitEnd, match, length1);
+ op = oLitEnd + length1;
+ sequence.matchLength -= length1;
+ match = base;
+ if (op > oend_w || sequence.matchLength < MINMATCH) {
+ U32 i;
+ for (i = 0; i < sequence.matchLength; ++i)
+ op[i] = match[i];
+ return sequenceLength;
+ }
+ }
+ }
+ /* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */
+
+ /* match within prefix */
+ if (sequence.offset < 8) {
+ /* close range match, overlap */
+ static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */
+ static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */
+ int const sub2 = dec64table[sequence.offset];
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += dec32table[sequence.offset];
+ ZSTD_copy4(op + 4, match);
+ match -= sub2;
+ } else {
+ ZSTD_copy8(op, match);
+ }
+ op += 8;
+ match += 8;
+
+ if (oMatchEnd > oend - (16 - MINMATCH)) {
+ if (op < oend_w) {
+ ZSTD_wildcopy(op, match, oend_w - op);
+ match += oend_w - op;
+ op = oend_w;
+ }
+ while (op < oMatchEnd)
+ *op++ = *match++;
+ } else {
+ ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */
+ }
+ return sequenceLength;
+}
+
+static size_t ZSTD_decompressSequences(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize)
+{
+ const BYTE *ip = (const BYTE *)seqStart;
+ const BYTE *const iend = ip + seqSize;
+ BYTE *const ostart = (BYTE * const)dst;
+ BYTE *const oend = ostart + maxDstSize;
+ BYTE *op = ostart;
+ const BYTE *litPtr = dctx->litPtr;
+ const BYTE *const litEnd = litPtr + dctx->litSize;
+ const BYTE *const base = (const BYTE *)(dctx->base);
+ const BYTE *const vBase = (const BYTE *)(dctx->vBase);
+ const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd);
+ int nbSeq;
+
+ /* Build Decoding Tables */
+ {
+ size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
+ if (ZSTD_isError(seqHSize))
+ return seqHSize;
+ ip += seqHSize;
+ }
+
+ /* Regen sequences */
+ if (nbSeq) {
+ seqState_t seqState;
+ dctx->fseEntropy = 1;
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ seqState.prevOffset[i] = dctx->entropy.rep[i];
+ }
+ CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected);
+ FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
+ FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
+ FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
+
+ for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq;) {
+ nbSeq--;
+ {
+ seq_t const sequence = ZSTD_decodeSequence(&seqState);
+ size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd);
+ if (ZSTD_isError(oneSeqSize))
+ return oneSeqSize;
+ op += oneSeqSize;
+ }
+ }
+
+ /* check if reached exact end */
+ if (nbSeq)
+ return ERROR(corruption_detected);
+ /* save reps for next block */
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]);
+ }
+ }
+
+ /* last literal segment */
+ {
+ size_t const lastLLSize = litEnd - litPtr;
+ if (lastLLSize > (size_t)(oend - op))
+ return ERROR(dstSize_tooSmall);
+ memcpy(op, litPtr, lastLLSize);
+ op += lastLLSize;
+ }
+
+ return op - ostart;
+}
+
+FORCE_INLINE seq_t ZSTD_decodeSequenceLong_generic(seqState_t *seqState, int const longOffsets)
+{
+ seq_t seq;
+
+ U32 const llCode = FSE_peekSymbol(&seqState->stateLL);
+ U32 const mlCode = FSE_peekSymbol(&seqState->stateML);
+ U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */
+
+ U32 const llBits = LL_bits[llCode];
+ U32 const mlBits = ML_bits[mlCode];
+ U32 const ofBits = ofCode;
+ U32 const totalBits = llBits + mlBits + ofBits;
+
+ static const U32 LL_base[MaxLL + 1] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18,
+ 20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000};
+
+ static const U32 ML_base[MaxML + 1] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+ 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 39, 41,
+ 43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003};
+
+ static const U32 OF_base[MaxOff + 1] = {0, 1, 1, 5, 0xD, 0x1D, 0x3D, 0x7D, 0xFD, 0x1FD,
+ 0x3FD, 0x7FD, 0xFFD, 0x1FFD, 0x3FFD, 0x7FFD, 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD,
+ 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD};
+
+ /* sequence */
+ {
+ size_t offset;
+ if (!ofCode)
+ offset = 0;
+ else {
+ if (longOffsets) {
+ int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN);
+ offset = OF_base[ofCode] + (BIT_readBitsFast(&seqState->DStream, ofBits - extraBits) << extraBits);
+ if (ZSTD_32bits() || extraBits)
+ BIT_reloadDStream(&seqState->DStream);
+ if (extraBits)
+ offset += BIT_readBitsFast(&seqState->DStream, extraBits);
+ } else {
+ offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <= (ZSTD_WINDOWLOG_MAX-1) bits */
+ if (ZSTD_32bits())
+ BIT_reloadDStream(&seqState->DStream);
+ }
+ }
+
+ if (ofCode <= 1) {
+ offset += (llCode == 0);
+ if (offset) {
+ size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset];
+ temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */
+ if (offset != 1)
+ seqState->prevOffset[2] = seqState->prevOffset[1];
+ seqState->prevOffset[1] = seqState->prevOffset[0];
+ seqState->prevOffset[0] = offset = temp;
+ } else {
+ offset = seqState->prevOffset[0];
+ }
+ } else {
+ seqState->prevOffset[2] = seqState->prevOffset[1];
+ seqState->prevOffset[1] = seqState->prevOffset[0];
+ seqState->prevOffset[0] = offset;
+ }
+ seq.offset = offset;
+ }
+
+ seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */
+ if (ZSTD_32bits() && (mlBits + llBits > 24))
+ BIT_reloadDStream(&seqState->DStream);
+
+ seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */
+ if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
+ BIT_reloadDStream(&seqState->DStream);
+
+ {
+ size_t const pos = seqState->pos + seq.litLength;
+ seq.match = seqState->base + pos - seq.offset; /* single memory segment */
+ if (seq.offset > pos)
+ seq.match += seqState->gotoDict; /* separate memory segment */
+ seqState->pos = pos + seq.matchLength;
+ }
+
+ /* ANS state update */
+ FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */
+ FSE_updateState(&seqState->stateML, &seqState->DStream); /* <= 9 bits */
+ if (ZSTD_32bits())
+ BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */
+ FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <= 8 bits */
+
+ return seq;
+}
+
+static seq_t ZSTD_decodeSequenceLong(seqState_t *seqState, unsigned const windowSize)
+{
+ if (ZSTD_highbit32(windowSize) > STREAM_ACCUMULATOR_MIN) {
+ return ZSTD_decodeSequenceLong_generic(seqState, 1);
+ } else {
+ return ZSTD_decodeSequenceLong_generic(seqState, 0);
+ }
+}
+
+FORCE_INLINE
+size_t ZSTD_execSequenceLong(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
+ const BYTE *const vBase, const BYTE *const dictEnd)
+{
+ BYTE *const oLitEnd = op + sequence.litLength;
+ size_t const sequenceLength = sequence.litLength + sequence.matchLength;
+ BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
+ BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
+ const BYTE *const iLitEnd = *litPtr + sequence.litLength;
+ const BYTE *match = sequence.match;
+
+ /* check */
+ if (oMatchEnd > oend)
+ return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
+ if (iLitEnd > litLimit)
+ return ERROR(corruption_detected); /* over-read beyond lit buffer */
+ if (oLitEnd > oend_w)
+ return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd);
+
+ /* copy Literals */
+ ZSTD_copy8(op, *litPtr);
+ if (sequence.litLength > 8)
+ ZSTD_wildcopy(op + 8, (*litPtr) + 8,
+ sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+ op = oLitEnd;
+ *litPtr = iLitEnd; /* update for next sequence */
+
+ /* copy Match */
+ if (sequence.offset > (size_t)(oLitEnd - base)) {
+ /* offset beyond prefix */
+ if (sequence.offset > (size_t)(oLitEnd - vBase))
+ return ERROR(corruption_detected);
+ if (match + sequence.matchLength <= dictEnd) {
+ memmove(oLitEnd, match, sequence.matchLength);
+ return sequenceLength;
+ }
+ /* span extDict & currPrefixSegment */
+ {
+ size_t const length1 = dictEnd - match;
+ memmove(oLitEnd, match, length1);
+ op = oLitEnd + length1;
+ sequence.matchLength -= length1;
+ match = base;
+ if (op > oend_w || sequence.matchLength < MINMATCH) {
+ U32 i;
+ for (i = 0; i < sequence.matchLength; ++i)
+ op[i] = match[i];
+ return sequenceLength;
+ }
+ }
+ }
+ /* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */
+
+ /* match within prefix */
+ if (sequence.offset < 8) {
+ /* close range match, overlap */
+ static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */
+ static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */
+ int const sub2 = dec64table[sequence.offset];
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += dec32table[sequence.offset];
+ ZSTD_copy4(op + 4, match);
+ match -= sub2;
+ } else {
+ ZSTD_copy8(op, match);
+ }
+ op += 8;
+ match += 8;
+
+ if (oMatchEnd > oend - (16 - MINMATCH)) {
+ if (op < oend_w) {
+ ZSTD_wildcopy(op, match, oend_w - op);
+ match += oend_w - op;
+ op = oend_w;
+ }
+ while (op < oMatchEnd)
+ *op++ = *match++;
+ } else {
+ ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */
+ }
+ return sequenceLength;
+}
+
+static size_t ZSTD_decompressSequencesLong(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize)
+{
+ const BYTE *ip = (const BYTE *)seqStart;
+ const BYTE *const iend = ip + seqSize;
+ BYTE *const ostart = (BYTE * const)dst;
+ BYTE *const oend = ostart + maxDstSize;
+ BYTE *op = ostart;
+ const BYTE *litPtr = dctx->litPtr;
+ const BYTE *const litEnd = litPtr + dctx->litSize;
+ const BYTE *const base = (const BYTE *)(dctx->base);
+ const BYTE *const vBase = (const BYTE *)(dctx->vBase);
+ const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd);
+ unsigned const windowSize = dctx->fParams.windowSize;
+ int nbSeq;
+
+ /* Build Decoding Tables */
+ {
+ size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
+ if (ZSTD_isError(seqHSize))
+ return seqHSize;
+ ip += seqHSize;
+ }
+
+ /* Regen sequences */
+ if (nbSeq) {
+#define STORED_SEQS 4
+#define STOSEQ_MASK (STORED_SEQS - 1)
+#define ADVANCED_SEQS 4
+ seq_t *sequences = (seq_t *)dctx->entropy.workspace;
+ int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS);
+ seqState_t seqState;
+ int seqNb;
+ ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.workspace) >= sizeof(seq_t) * STORED_SEQS);
+ dctx->fseEntropy = 1;
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ seqState.prevOffset[i] = dctx->entropy.rep[i];
+ }
+ seqState.base = base;
+ seqState.pos = (size_t)(op - base);
+ seqState.gotoDict = (uPtrDiff)dictEnd - (uPtrDiff)base; /* cast to avoid undefined behaviour */
+ CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected);
+ FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
+ FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
+ FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
+
+ /* prepare in advance */
+ for (seqNb = 0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && seqNb < seqAdvance; seqNb++) {
+ sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize);
+ }
+ if (seqNb < seqAdvance)
+ return ERROR(corruption_detected);
+
+ /* decode and decompress */
+ for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && seqNb < nbSeq; seqNb++) {
+ seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize);
+ size_t const oneSeqSize =
+ ZSTD_execSequenceLong(op, oend, sequences[(seqNb - ADVANCED_SEQS) & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
+ if (ZSTD_isError(oneSeqSize))
+ return oneSeqSize;
+ ZSTD_PREFETCH(sequence.match);
+ sequences[seqNb & STOSEQ_MASK] = sequence;
+ op += oneSeqSize;
+ }
+ if (seqNb < nbSeq)
+ return ERROR(corruption_detected);
+
+ /* finish queue */
+ seqNb -= seqAdvance;
+ for (; seqNb < nbSeq; seqNb++) {
+ size_t const oneSeqSize = ZSTD_execSequenceLong(op, oend, sequences[seqNb & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
+ if (ZSTD_isError(oneSeqSize))
+ return oneSeqSize;
+ op += oneSeqSize;
+ }
+
+ /* save reps for next block */
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]);
+ }
+ }
+
+ /* last literal segment */
+ {
+ size_t const lastLLSize = litEnd - litPtr;
+ if (lastLLSize > (size_t)(oend - op))
+ return ERROR(dstSize_tooSmall);
+ memcpy(op, litPtr, lastLLSize);
+ op += lastLLSize;
+ }
+
+ return op - ostart;
+}
+
+static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{ /* blockType == blockCompressed */
+ const BYTE *ip = (const BYTE *)src;
+
+ if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX)
+ return ERROR(srcSize_wrong);
+
+ /* Decode literals section */
+ {
+ size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
+ if (ZSTD_isError(litCSize))
+ return litCSize;
+ ip += litCSize;
+ srcSize -= litCSize;
+ }
+ if (sizeof(size_t) > 4) /* do not enable prefetching on 32-bits x86, as it's performance detrimental */
+ /* likely because of register pressure */
+ /* if that's the correct cause, then 32-bits ARM should be affected differently */
+ /* it would be good to test this on ARM real hardware, to see if prefetch version improves speed */
+ if (dctx->fParams.windowSize > (1 << 23))
+ return ZSTD_decompressSequencesLong(dctx, dst, dstCapacity, ip, srcSize);
+ return ZSTD_decompressSequences(dctx, dst, dstCapacity, ip, srcSize);
+}
+
+static void ZSTD_checkContinuity(ZSTD_DCtx *dctx, const void *dst)
+{
+ if (dst != dctx->previousDstEnd) { /* not contiguous */
+ dctx->dictEnd = dctx->previousDstEnd;
+ dctx->vBase = (const char *)dst - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base));
+ dctx->base = dst;
+ dctx->previousDstEnd = dst;
+ }
+}
+
+size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t dSize;
+ ZSTD_checkContinuity(dctx, dst);
+ dSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize);
+ dctx->previousDstEnd = (char *)dst + dSize;
+ return dSize;
+}
+
+/** ZSTD_insertBlock() :
+ insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
+size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, size_t blockSize)
+{
+ ZSTD_checkContinuity(dctx, blockStart);
+ dctx->previousDstEnd = (const char *)blockStart + blockSize;
+ return blockSize;
+}
+
+size_t ZSTD_generateNxBytes(void *dst, size_t dstCapacity, BYTE byte, size_t length)
+{
+ if (length > dstCapacity)
+ return ERROR(dstSize_tooSmall);
+ memset(dst, byte, length);
+ return length;
+}
+
+/** ZSTD_findFrameCompressedSize() :
+ * compatible with legacy mode
+ * `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame
+ * `srcSize` must be at least as large as the frame contained
+ * @return : the compressed size of the frame starting at `src` */
+size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
+{
+ if (srcSize >= ZSTD_skippableHeaderSize && (ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+ return ZSTD_skippableHeaderSize + ZSTD_readLE32((const BYTE *)src + 4);
+ } else {
+ const BYTE *ip = (const BYTE *)src;
+ const BYTE *const ipstart = ip;
+ size_t remainingSize = srcSize;
+ ZSTD_frameParams fParams;
+
+ size_t const headerSize = ZSTD_frameHeaderSize(ip, remainingSize);
+ if (ZSTD_isError(headerSize))
+ return headerSize;
+
+ /* Frame Header */
+ {
+ size_t const ret = ZSTD_getFrameParams(&fParams, ip, remainingSize);
+ if (ZSTD_isError(ret))
+ return ret;
+ if (ret > 0)
+ return ERROR(srcSize_wrong);
+ }
+
+ ip += headerSize;
+ remainingSize -= headerSize;
+
+ /* Loop on each block */
+ while (1) {
+ blockProperties_t blockProperties;
+ size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
+ if (ZSTD_isError(cBlockSize))
+ return cBlockSize;
+
+ if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
+ return ERROR(srcSize_wrong);
+
+ ip += ZSTD_blockHeaderSize + cBlockSize;
+ remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
+
+ if (blockProperties.lastBlock)
+ break;
+ }
+
+ if (fParams.checksumFlag) { /* Frame content checksum */
+ if (remainingSize < 4)
+ return ERROR(srcSize_wrong);
+ ip += 4;
+ remainingSize -= 4;
+ }
+
+ return ip - ipstart;
+ }
+}
+
+/*! ZSTD_decompressFrame() :
+* @dctx must be properly initialized */
+static size_t ZSTD_decompressFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void **srcPtr, size_t *srcSizePtr)
+{
+ const BYTE *ip = (const BYTE *)(*srcPtr);
+ BYTE *const ostart = (BYTE * const)dst;
+ BYTE *const oend = ostart + dstCapacity;
+ BYTE *op = ostart;
+ size_t remainingSize = *srcSizePtr;
+
+ /* check */
+ if (remainingSize < ZSTD_frameHeaderSize_min + ZSTD_blockHeaderSize)
+ return ERROR(srcSize_wrong);
+
+ /* Frame Header */
+ {
+ size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_frameHeaderSize_prefix);
+ if (ZSTD_isError(frameHeaderSize))
+ return frameHeaderSize;
+ if (remainingSize < frameHeaderSize + ZSTD_blockHeaderSize)
+ return ERROR(srcSize_wrong);
+ CHECK_F(ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize));
+ ip += frameHeaderSize;
+ remainingSize -= frameHeaderSize;
+ }
+
+ /* Loop on each block */
+ while (1) {
+ size_t decodedSize;
+ blockProperties_t blockProperties;
+ size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
+ if (ZSTD_isError(cBlockSize))
+ return cBlockSize;
+
+ ip += ZSTD_blockHeaderSize;
+ remainingSize -= ZSTD_blockHeaderSize;
+ if (cBlockSize > remainingSize)
+ return ERROR(srcSize_wrong);
+
+ switch (blockProperties.blockType) {
+ case bt_compressed: decodedSize = ZSTD_decompressBlock_internal(dctx, op, oend - op, ip, cBlockSize); break;
+ case bt_raw: decodedSize = ZSTD_copyRawBlock(op, oend - op, ip, cBlockSize); break;
+ case bt_rle: decodedSize = ZSTD_generateNxBytes(op, oend - op, *ip, blockProperties.origSize); break;
+ case bt_reserved:
+ default: return ERROR(corruption_detected);
+ }
+
+ if (ZSTD_isError(decodedSize))
+ return decodedSize;
+ if (dctx->fParams.checksumFlag)
+ xxh64_update(&dctx->xxhState, op, decodedSize);
+ op += decodedSize;
+ ip += cBlockSize;
+ remainingSize -= cBlockSize;
+ if (blockProperties.lastBlock)
+ break;
+ }
+
+ if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
+ U32 const checkCalc = (U32)xxh64_digest(&dctx->xxhState);
+ U32 checkRead;
+ if (remainingSize < 4)
+ return ERROR(checksum_wrong);
+ checkRead = ZSTD_readLE32(ip);
+ if (checkRead != checkCalc)
+ return ERROR(checksum_wrong);
+ ip += 4;
+ remainingSize -= 4;
+ }
+
+ /* Allow caller to get size read */
+ *srcPtr = ip;
+ *srcSizePtr = remainingSize;
+ return op - ostart;
+}
+
+static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict);
+static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict);
+
+static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
+ const ZSTD_DDict *ddict)
+{
+ void *const dststart = dst;
+
+ if (ddict) {
+ if (dict) {
+ /* programmer error, these two cases should be mutually exclusive */
+ return ERROR(GENERIC);
+ }
+
+ dict = ZSTD_DDictDictContent(ddict);
+ dictSize = ZSTD_DDictDictSize(ddict);
+ }
+
+ while (srcSize >= ZSTD_frameHeaderSize_prefix) {
+ U32 magicNumber;
+
+ magicNumber = ZSTD_readLE32(src);
+ if (magicNumber != ZSTD_MAGICNUMBER) {
+ if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+ size_t skippableSize;
+ if (srcSize < ZSTD_skippableHeaderSize)
+ return ERROR(srcSize_wrong);
+ skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize;
+ if (srcSize < skippableSize) {
+ return ERROR(srcSize_wrong);
+ }
+
+ src = (const BYTE *)src + skippableSize;
+ srcSize -= skippableSize;
+ continue;
+ } else {
+ return ERROR(prefix_unknown);
+ }
+ }
+
+ if (ddict) {
+ /* we were called from ZSTD_decompress_usingDDict */
+ ZSTD_refDDict(dctx, ddict);
+ } else {
+ /* this will initialize correctly with no dict if dict == NULL, so
+ * use this in all cases but ddict */
+ CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
+ }
+ ZSTD_checkContinuity(dctx, dst);
+
+ {
+ const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, &src, &srcSize);
+ if (ZSTD_isError(res))
+ return res;
+ /* don't need to bounds check this, ZSTD_decompressFrame will have
+ * already */
+ dst = (BYTE *)dst + res;
+ dstCapacity -= res;
+ }
+ }
+
+ if (srcSize)
+ return ERROR(srcSize_wrong); /* input not entirely consumed */
+
+ return (BYTE *)dst - (BYTE *)dststart;
+}
+
+size_t ZSTD_decompress_usingDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize)
+{
+ return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL);
+}
+
+size_t ZSTD_decompressDCtx(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0);
+}
+
+/*-**************************************
+* Advanced Streaming Decompression API
+* Bufferless and synchronous
+****************************************/
+size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx) { return dctx->expected; }
+
+ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx)
+{
+ switch (dctx->stage) {
+ default: /* should not happen */
+ case ZSTDds_getFrameHeaderSize:
+ case ZSTDds_decodeFrameHeader: return ZSTDnit_frameHeader;
+ case ZSTDds_decodeBlockHeader: return ZSTDnit_blockHeader;
+ case ZSTDds_decompressBlock: return ZSTDnit_block;
+ case ZSTDds_decompressLastBlock: return ZSTDnit_lastBlock;
+ case ZSTDds_checkChecksum: return ZSTDnit_checksum;
+ case ZSTDds_decodeSkippableHeader:
+ case ZSTDds_skipFrame: return ZSTDnit_skippableFrame;
+ }
+}
+
+int ZSTD_isSkipFrame(ZSTD_DCtx *dctx) { return dctx->stage == ZSTDds_skipFrame; } /* for zbuff */
+
+/** ZSTD_decompressContinue() :
+* @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
+* or an error code, which can be tested using ZSTD_isError() */
+size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ /* Sanity check */
+ if (srcSize != dctx->expected)
+ return ERROR(srcSize_wrong);
+ if (dstCapacity)
+ ZSTD_checkContinuity(dctx, dst);
+
+ switch (dctx->stage) {
+ case ZSTDds_getFrameHeaderSize:
+ if (srcSize != ZSTD_frameHeaderSize_prefix)
+ return ERROR(srcSize_wrong); /* impossible */
+ if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
+ memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
+ dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix; /* magic number + skippable frame length */
+ dctx->stage = ZSTDds_decodeSkippableHeader;
+ return 0;
+ }
+ dctx->headerSize = ZSTD_frameHeaderSize(src, ZSTD_frameHeaderSize_prefix);
+ if (ZSTD_isError(dctx->headerSize))
+ return dctx->headerSize;
+ memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
+ if (dctx->headerSize > ZSTD_frameHeaderSize_prefix) {
+ dctx->expected = dctx->headerSize - ZSTD_frameHeaderSize_prefix;
+ dctx->stage = ZSTDds_decodeFrameHeader;
+ return 0;
+ }
+ dctx->expected = 0; /* not necessary to copy more */
+
+ case ZSTDds_decodeFrameHeader:
+ memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
+ CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
+ dctx->expected = ZSTD_blockHeaderSize;
+ dctx->stage = ZSTDds_decodeBlockHeader;
+ return 0;
+
+ case ZSTDds_decodeBlockHeader: {
+ blockProperties_t bp;
+ size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
+ if (ZSTD_isError(cBlockSize))
+ return cBlockSize;
+ dctx->expected = cBlockSize;
+ dctx->bType = bp.blockType;
+ dctx->rleSize = bp.origSize;
+ if (cBlockSize) {
+ dctx->stage = bp.lastBlock ? ZSTDds_decompressLastBlock : ZSTDds_decompressBlock;
+ return 0;
+ }
+ /* empty block */
+ if (bp.lastBlock) {
+ if (dctx->fParams.checksumFlag) {
+ dctx->expected = 4;
+ dctx->stage = ZSTDds_checkChecksum;
+ } else {
+ dctx->expected = 0; /* end of frame */
+ dctx->stage = ZSTDds_getFrameHeaderSize;
+ }
+ } else {
+ dctx->expected = 3; /* go directly to next header */
+ dctx->stage = ZSTDds_decodeBlockHeader;
+ }
+ return 0;
+ }
+ case ZSTDds_decompressLastBlock:
+ case ZSTDds_decompressBlock: {
+ size_t rSize;
+ switch (dctx->bType) {
+ case bt_compressed: rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize); break;
+ case bt_raw: rSize = ZSTD_copyRawBlock(dst, dstCapacity, src, srcSize); break;
+ case bt_rle: rSize = ZSTD_setRleBlock(dst, dstCapacity, src, srcSize, dctx->rleSize); break;
+ case bt_reserved: /* should never happen */
+ default: return ERROR(corruption_detected);
+ }
+ if (ZSTD_isError(rSize))
+ return rSize;
+ if (dctx->fParams.checksumFlag)
+ xxh64_update(&dctx->xxhState, dst, rSize);
+
+ if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */
+ if (dctx->fParams.checksumFlag) { /* another round for frame checksum */
+ dctx->expected = 4;
+ dctx->stage = ZSTDds_checkChecksum;
+ } else {
+ dctx->expected = 0; /* ends here */
+ dctx->stage = ZSTDds_getFrameHeaderSize;
+ }
+ } else {
+ dctx->stage = ZSTDds_decodeBlockHeader;
+ dctx->expected = ZSTD_blockHeaderSize;
+ dctx->previousDstEnd = (char *)dst + rSize;
+ }
+ return rSize;
+ }
+ case ZSTDds_checkChecksum: {
+ U32 const h32 = (U32)xxh64_digest(&dctx->xxhState);
+ U32 const check32 = ZSTD_readLE32(src); /* srcSize == 4, guaranteed by dctx->expected */
+ if (check32 != h32)
+ return ERROR(checksum_wrong);
+ dctx->expected = 0;
+ dctx->stage = ZSTDds_getFrameHeaderSize;
+ return 0;
+ }
+ case ZSTDds_decodeSkippableHeader: {
+ memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
+ dctx->expected = ZSTD_readLE32(dctx->headerBuffer + 4);
+ dctx->stage = ZSTDds_skipFrame;
+ return 0;
+ }
+ case ZSTDds_skipFrame: {
+ dctx->expected = 0;
+ dctx->stage = ZSTDds_getFrameHeaderSize;
+ return 0;
+ }
+ default:
+ return ERROR(GENERIC); /* impossible */
+ }
+}
+
+static size_t ZSTD_refDictContent(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
+{
+ dctx->dictEnd = dctx->previousDstEnd;
+ dctx->vBase = (const char *)dict - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base));
+ dctx->base = dict;
+ dctx->previousDstEnd = (const char *)dict + dictSize;
+ return 0;
+}
+
+/* ZSTD_loadEntropy() :
+ * dict : must point at beginning of a valid zstd dictionary
+ * @return : size of entropy tables read */
+static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t *entropy, const void *const dict, size_t const dictSize)
+{
+ const BYTE *dictPtr = (const BYTE *)dict;
+ const BYTE *const dictEnd = dictPtr + dictSize;
+
+ if (dictSize <= 8)
+ return ERROR(dictionary_corrupted);
+ dictPtr += 8; /* skip header = magic + dictID */
+
+ {
+ size_t const hSize = HUF_readDTableX4_wksp(entropy->hufTable, dictPtr, dictEnd - dictPtr, entropy->workspace, sizeof(entropy->workspace));
+ if (HUF_isError(hSize))
+ return ERROR(dictionary_corrupted);
+ dictPtr += hSize;
+ }
+
+ {
+ short offcodeNCount[MaxOff + 1];
+ U32 offcodeMaxValue = MaxOff, offcodeLog;
+ size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(offcodeHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (offcodeLog > OffFSELog)
+ return ERROR(dictionary_corrupted);
+ CHECK_E(FSE_buildDTable_wksp(entropy->OFTable, offcodeNCount, offcodeMaxValue, offcodeLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
+ dictPtr += offcodeHeaderSize;
+ }
+
+ {
+ short matchlengthNCount[MaxML + 1];
+ unsigned matchlengthMaxValue = MaxML, matchlengthLog;
+ size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(matchlengthHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (matchlengthLog > MLFSELog)
+ return ERROR(dictionary_corrupted);
+ CHECK_E(FSE_buildDTable_wksp(entropy->MLTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
+ dictPtr += matchlengthHeaderSize;
+ }
+
+ {
+ short litlengthNCount[MaxLL + 1];
+ unsigned litlengthMaxValue = MaxLL, litlengthLog;
+ size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr);
+ if (FSE_isError(litlengthHeaderSize))
+ return ERROR(dictionary_corrupted);
+ if (litlengthLog > LLFSELog)
+ return ERROR(dictionary_corrupted);
+ CHECK_E(FSE_buildDTable_wksp(entropy->LLTable, litlengthNCount, litlengthMaxValue, litlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
+ dictPtr += litlengthHeaderSize;
+ }
+
+ if (dictPtr + 12 > dictEnd)
+ return ERROR(dictionary_corrupted);
+ {
+ int i;
+ size_t const dictContentSize = (size_t)(dictEnd - (dictPtr + 12));
+ for (i = 0; i < 3; i++) {
+ U32 const rep = ZSTD_readLE32(dictPtr);
+ dictPtr += 4;
+ if (rep == 0 || rep >= dictContentSize)
+ return ERROR(dictionary_corrupted);
+ entropy->rep[i] = rep;
+ }
+ }
+
+ return dictPtr - (const BYTE *)dict;
+}
+
+static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
+{
+ if (dictSize < 8)
+ return ZSTD_refDictContent(dctx, dict, dictSize);
+ {
+ U32 const magic = ZSTD_readLE32(dict);
+ if (magic != ZSTD_DICT_MAGIC) {
+ return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */
+ }
+ }
+ dctx->dictID = ZSTD_readLE32((const char *)dict + 4);
+
+ /* load entropy tables */
+ {
+ size_t const eSize = ZSTD_loadEntropy(&dctx->entropy, dict, dictSize);
+ if (ZSTD_isError(eSize))
+ return ERROR(dictionary_corrupted);
+ dict = (const char *)dict + eSize;
+ dictSize -= eSize;
+ }
+ dctx->litEntropy = dctx->fseEntropy = 1;
+
+ /* reference dictionary content */
+ return ZSTD_refDictContent(dctx, dict, dictSize);
+}
+
+size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
+{
+ CHECK_F(ZSTD_decompressBegin(dctx));
+ if (dict && dictSize)
+ CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted);
+ return 0;
+}
+
+/* ====== ZSTD_DDict ====== */
+
+struct ZSTD_DDict_s {
+ void *dictBuffer;
+ const void *dictContent;
+ size_t dictSize;
+ ZSTD_entropyTables_t entropy;
+ U32 dictID;
+ U32 entropyPresent;
+ ZSTD_customMem cMem;
+}; /* typedef'd to ZSTD_DDict within "zstd.h" */
+
+size_t ZSTD_DDictWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DDict)); }
+
+static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict) { return ddict->dictContent; }
+
+static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict) { return ddict->dictSize; }
+
+static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict)
+{
+ ZSTD_decompressBegin(dstDCtx); /* init */
+ if (ddict) { /* support refDDict on NULL */
+ dstDCtx->dictID = ddict->dictID;
+ dstDCtx->base = ddict->dictContent;
+ dstDCtx->vBase = ddict->dictContent;
+ dstDCtx->dictEnd = (const BYTE *)ddict->dictContent + ddict->dictSize;
+ dstDCtx->previousDstEnd = dstDCtx->dictEnd;
+ if (ddict->entropyPresent) {
+ dstDCtx->litEntropy = 1;
+ dstDCtx->fseEntropy = 1;
+ dstDCtx->LLTptr = ddict->entropy.LLTable;
+ dstDCtx->MLTptr = ddict->entropy.MLTable;
+ dstDCtx->OFTptr = ddict->entropy.OFTable;
+ dstDCtx->HUFptr = ddict->entropy.hufTable;
+ dstDCtx->entropy.rep[0] = ddict->entropy.rep[0];
+ dstDCtx->entropy.rep[1] = ddict->entropy.rep[1];
+ dstDCtx->entropy.rep[2] = ddict->entropy.rep[2];
+ } else {
+ dstDCtx->litEntropy = 0;
+ dstDCtx->fseEntropy = 0;
+ }
+ }
+}
+
+static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict *ddict)
+{
+ ddict->dictID = 0;
+ ddict->entropyPresent = 0;
+ if (ddict->dictSize < 8)
+ return 0;
+ {
+ U32 const magic = ZSTD_readLE32(ddict->dictContent);
+ if (magic != ZSTD_DICT_MAGIC)
+ return 0; /* pure content mode */
+ }
+ ddict->dictID = ZSTD_readLE32((const char *)ddict->dictContent + 4);
+
+ /* load entropy tables */
+ CHECK_E(ZSTD_loadEntropy(&ddict->entropy, ddict->dictContent, ddict->dictSize), dictionary_corrupted);
+ ddict->entropyPresent = 1;
+ return 0;
+}
+
+static ZSTD_DDict *ZSTD_createDDict_advanced(const void *dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem)
+{
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+
+ {
+ ZSTD_DDict *const ddict = (ZSTD_DDict *)ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
+ if (!ddict)
+ return NULL;
+ ddict->cMem = customMem;
+
+ if ((byReference) || (!dict) || (!dictSize)) {
+ ddict->dictBuffer = NULL;
+ ddict->dictContent = dict;
+ } else {
+ void *const internalBuffer = ZSTD_malloc(dictSize, customMem);
+ if (!internalBuffer) {
+ ZSTD_freeDDict(ddict);
+ return NULL;
+ }
+ memcpy(internalBuffer, dict, dictSize);
+ ddict->dictBuffer = internalBuffer;
+ ddict->dictContent = internalBuffer;
+ }
+ ddict->dictSize = dictSize;
+ ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
+ /* parse dictionary content */
+ {
+ size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict);
+ if (ZSTD_isError(errorCode)) {
+ ZSTD_freeDDict(ddict);
+ return NULL;
+ }
+ }
+
+ return ddict;
+ }
+}
+
+/*! ZSTD_initDDict() :
+* Create a digested dictionary, to start decompression without startup delay.
+* `dict` content is copied inside DDict.
+* Consequently, `dict` can be released after `ZSTD_DDict` creation */
+ZSTD_DDict *ZSTD_initDDict(const void *dict, size_t dictSize, void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ return ZSTD_createDDict_advanced(dict, dictSize, 1, stackMem);
+}
+
+size_t ZSTD_freeDDict(ZSTD_DDict *ddict)
+{
+ if (ddict == NULL)
+ return 0; /* support free on NULL */
+ {
+ ZSTD_customMem const cMem = ddict->cMem;
+ ZSTD_free(ddict->dictBuffer, cMem);
+ ZSTD_free(ddict, cMem);
+ return 0;
+ }
+}
+
+/*! ZSTD_getDictID_fromDict() :
+ * Provides the dictID stored within dictionary.
+ * if @return == 0, the dictionary is not conformant with Zstandard specification.
+ * It can still be loaded, but as a content-only dictionary. */
+unsigned ZSTD_getDictID_fromDict(const void *dict, size_t dictSize)
+{
+ if (dictSize < 8)
+ return 0;
+ if (ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC)
+ return 0;
+ return ZSTD_readLE32((const char *)dict + 4);
+}
+
+/*! ZSTD_getDictID_fromDDict() :
+ * Provides the dictID of the dictionary loaded into `ddict`.
+ * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict)
+{
+ if (ddict == NULL)
+ return 0;
+ return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize);
+}
+
+/*! ZSTD_getDictID_fromFrame() :
+ * Provides the dictID required to decompressed the frame stored within `src`.
+ * If @return == 0, the dictID could not be decoded.
+ * This could for one of the following reasons :
+ * - The frame does not require a dictionary to be decoded (most common case).
+ * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ * Note : this use case also happens when using a non-conformant dictionary.
+ * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ * - This is not a Zstandard frame.
+ * When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */
+unsigned ZSTD_getDictID_fromFrame(const void *src, size_t srcSize)
+{
+ ZSTD_frameParams zfp = {0, 0, 0, 0};
+ size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize);
+ if (ZSTD_isError(hError))
+ return 0;
+ return zfp.dictID;
+}
+
+/*! ZSTD_decompress_usingDDict() :
+* Decompression using a pre-digested Dictionary
+* Use dictionary without significant overhead. */
+size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_DDict *ddict)
+{
+ /* pass content and size in case legacy frames are encountered */
+ return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, NULL, 0, ddict);
+}
+
+/*=====================================
+* Streaming decompression
+*====================================*/
+
+typedef enum { zdss_init, zdss_loadHeader, zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
+
+/* *** Resource management *** */
+struct ZSTD_DStream_s {
+ ZSTD_DCtx *dctx;
+ ZSTD_DDict *ddictLocal;
+ const ZSTD_DDict *ddict;
+ ZSTD_frameParams fParams;
+ ZSTD_dStreamStage stage;
+ char *inBuff;
+ size_t inBuffSize;
+ size_t inPos;
+ size_t maxWindowSize;
+ char *outBuff;
+ size_t outBuffSize;
+ size_t outStart;
+ size_t outEnd;
+ size_t blockSize;
+ BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; /* tmp buffer to store frame header */
+ size_t lhSize;
+ ZSTD_customMem customMem;
+ void *legacyContext;
+ U32 previousLegacyVersion;
+ U32 legacyVersion;
+ U32 hostageByte;
+}; /* typedef'd to ZSTD_DStream within "zstd.h" */
+
+size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize)
+{
+ size_t const blockSize = MIN(maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ size_t const inBuffSize = blockSize;
+ size_t const outBuffSize = maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
+ return ZSTD_DCtxWorkspaceBound() + ZSTD_ALIGN(sizeof(ZSTD_DStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize);
+}
+
+static ZSTD_DStream *ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+{
+ ZSTD_DStream *zds;
+
+ if (!customMem.customAlloc || !customMem.customFree)
+ return NULL;
+
+ zds = (ZSTD_DStream *)ZSTD_malloc(sizeof(ZSTD_DStream), customMem);
+ if (zds == NULL)
+ return NULL;
+ memset(zds, 0, sizeof(ZSTD_DStream));
+ memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem));
+ zds->dctx = ZSTD_createDCtx_advanced(customMem);
+ if (zds->dctx == NULL) {
+ ZSTD_freeDStream(zds);
+ return NULL;
+ }
+ zds->stage = zdss_init;
+ zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
+ return zds;
+}
+
+ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
+ ZSTD_DStream *zds = ZSTD_createDStream_advanced(stackMem);
+ if (!zds) {
+ return NULL;
+ }
+
+ zds->maxWindowSize = maxWindowSize;
+ zds->stage = zdss_loadHeader;
+ zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
+ ZSTD_freeDDict(zds->ddictLocal);
+ zds->ddictLocal = NULL;
+ zds->ddict = zds->ddictLocal;
+ zds->legacyVersion = 0;
+ zds->hostageByte = 0;
+
+ {
+ size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
+
+ zds->inBuff = (char *)ZSTD_malloc(blockSize, zds->customMem);
+ zds->inBuffSize = blockSize;
+ zds->outBuff = (char *)ZSTD_malloc(neededOutSize, zds->customMem);
+ zds->outBuffSize = neededOutSize;
+ if (zds->inBuff == NULL || zds->outBuff == NULL) {
+ ZSTD_freeDStream(zds);
+ return NULL;
+ }
+ }
+ return zds;
+}
+
+ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize)
+{
+ ZSTD_DStream *zds = ZSTD_initDStream(maxWindowSize, workspace, workspaceSize);
+ if (zds) {
+ zds->ddict = ddict;
+ }
+ return zds;
+}
+
+size_t ZSTD_freeDStream(ZSTD_DStream *zds)
+{
+ if (zds == NULL)
+ return 0; /* support free on null */
+ {
+ ZSTD_customMem const cMem = zds->customMem;
+ ZSTD_freeDCtx(zds->dctx);
+ zds->dctx = NULL;
+ ZSTD_freeDDict(zds->ddictLocal);
+ zds->ddictLocal = NULL;
+ ZSTD_free(zds->inBuff, cMem);
+ zds->inBuff = NULL;
+ ZSTD_free(zds->outBuff, cMem);
+ zds->outBuff = NULL;
+ ZSTD_free(zds, cMem);
+ return 0;
+ }
+}
+
+/* *** Initialization *** */
+
+size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; }
+size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
+
+size_t ZSTD_resetDStream(ZSTD_DStream *zds)
+{
+ zds->stage = zdss_loadHeader;
+ zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
+ zds->legacyVersion = 0;
+ zds->hostageByte = 0;
+ return ZSTD_frameHeaderSize_prefix;
+}
+
+/* ***** Decompression ***** */
+
+ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
+{
+ size_t const length = MIN(dstCapacity, srcSize);
+ memcpy(dst, src, length);
+ return length;
+}
+
+size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inBuffer *input)
+{
+ const char *const istart = (const char *)(input->src) + input->pos;
+ const char *const iend = (const char *)(input->src) + input->size;
+ const char *ip = istart;
+ char *const ostart = (char *)(output->dst) + output->pos;
+ char *const oend = (char *)(output->dst) + output->size;
+ char *op = ostart;
+ U32 someMoreWork = 1;
+
+ while (someMoreWork) {
+ switch (zds->stage) {
+ case zdss_init:
+ ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
+ /* fall-through */
+
+ case zdss_loadHeader: {
+ size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
+ if (ZSTD_isError(hSize))
+ return hSize;
+ if (hSize != 0) { /* need more input */
+ size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */
+ if (toLoad > (size_t)(iend - ip)) { /* not enough input to load full header */
+ memcpy(zds->headerBuffer + zds->lhSize, ip, iend - ip);
+ zds->lhSize += iend - ip;
+ input->pos = input->size;
+ return (MAX(ZSTD_frameHeaderSize_min, hSize) - zds->lhSize) +
+ ZSTD_blockHeaderSize; /* remaining header bytes + next block header */
+ }
+ memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad);
+ zds->lhSize = hSize;
+ ip += toLoad;
+ break;
+ }
+
+ /* check for single-pass mode opportunity */
+ if (zds->fParams.frameContentSize && zds->fParams.windowSize /* skippable frame if == 0 */
+ && (U64)(size_t)(oend - op) >= zds->fParams.frameContentSize) {
+ size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend - istart);
+ if (cSize <= (size_t)(iend - istart)) {
+ size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend - op, istart, cSize, zds->ddict);
+ if (ZSTD_isError(decompressedSize))
+ return decompressedSize;
+ ip = istart + cSize;
+ op += decompressedSize;
+ zds->dctx->expected = 0;
+ zds->stage = zdss_init;
+ someMoreWork = 0;
+ break;
+ }
+ }
+
+ /* Consume header */
+ ZSTD_refDDict(zds->dctx, zds->ddict);
+ {
+ size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); /* == ZSTD_frameHeaderSize_prefix */
+ CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size));
+ {
+ size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer + h1Size, h2Size));
+ }
+ }
+
+ zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
+ if (zds->fParams.windowSize > zds->maxWindowSize)
+ return ERROR(frameParameter_windowTooLarge);
+
+ /* Buffers are preallocated, but double check */
+ {
+ size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
+ if (zds->inBuffSize < blockSize) {
+ return ERROR(GENERIC);
+ }
+ if (zds->outBuffSize < neededOutSize) {
+ return ERROR(GENERIC);
+ }
+ zds->blockSize = blockSize;
+ }
+ zds->stage = zdss_read;
+ }
+ /* pass-through */
+
+ case zdss_read: {
+ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ if (neededInSize == 0) { /* end of frame */
+ zds->stage = zdss_init;
+ someMoreWork = 0;
+ break;
+ }
+ if ((size_t)(iend - ip) >= neededInSize) { /* decode directly from src */
+ const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
+ size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart,
+ (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart), ip, neededInSize);
+ if (ZSTD_isError(decodedSize))
+ return decodedSize;
+ ip += neededInSize;
+ if (!decodedSize && !isSkipFrame)
+ break; /* this was just a header */
+ zds->outEnd = zds->outStart + decodedSize;
+ zds->stage = zdss_flush;
+ break;
+ }
+ if (ip == iend) {
+ someMoreWork = 0;
+ break;
+ } /* no more input */
+ zds->stage = zdss_load;
+ /* pass-through */
+ }
+
+ case zdss_load: {
+ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ size_t const toLoad = neededInSize - zds->inPos; /* should always be <= remaining space within inBuff */
+ size_t loadedSize;
+ if (toLoad > zds->inBuffSize - zds->inPos)
+ return ERROR(corruption_detected); /* should never happen */
+ loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend - ip);
+ ip += loadedSize;
+ zds->inPos += loadedSize;
+ if (loadedSize < toLoad) {
+ someMoreWork = 0;
+ break;
+ } /* not enough input, wait for more */
+
+ /* decode loaded input */
+ {
+ const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
+ size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart,
+ zds->inBuff, neededInSize);
+ if (ZSTD_isError(decodedSize))
+ return decodedSize;
+ zds->inPos = 0; /* input is consumed */
+ if (!decodedSize && !isSkipFrame) {
+ zds->stage = zdss_read;
+ break;
+ } /* this was just a header */
+ zds->outEnd = zds->outStart + decodedSize;
+ zds->stage = zdss_flush;
+ /* pass-through */
+ }
+ }
+
+ case zdss_flush: {
+ size_t const toFlushSize = zds->outEnd - zds->outStart;
+ size_t const flushedSize = ZSTD_limitCopy(op, oend - op, zds->outBuff + zds->outStart, toFlushSize);
+ op += flushedSize;
+ zds->outStart += flushedSize;
+ if (flushedSize == toFlushSize) { /* flush completed */
+ zds->stage = zdss_read;
+ if (zds->outStart + zds->blockSize > zds->outBuffSize)
+ zds->outStart = zds->outEnd = 0;
+ break;
+ }
+ /* cannot complete flush */
+ someMoreWork = 0;
+ break;
+ }
+ default:
+ return ERROR(GENERIC); /* impossible */
+ }
+ }
+
+ /* result */
+ input->pos += (size_t)(ip - istart);
+ output->pos += (size_t)(op - ostart);
+ {
+ size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ if (!nextSrcSizeHint) { /* frame fully decoded */
+ if (zds->outEnd == zds->outStart) { /* output fully flushed */
+ if (zds->hostageByte) {
+ if (input->pos >= input->size) {
+ zds->stage = zdss_read;
+ return 1;
+ } /* can't release hostage (not present) */
+ input->pos++; /* release hostage */
+ }
+ return 0;
+ }
+ if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
+ input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */
+ zds->hostageByte = 1;
+ }
+ return 1;
+ }
+ nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block); /* preload header of next block */
+ if (zds->inPos > nextSrcSizeHint)
+ return ERROR(GENERIC); /* should never happen */
+ nextSrcSizeHint -= zds->inPos; /* already loaded*/
+ return nextSrcSizeHint;
+ }
+}
+
+EXPORT_SYMBOL(ZSTD_DCtxWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initDCtx);
+EXPORT_SYMBOL(ZSTD_decompressDCtx);
+EXPORT_SYMBOL(ZSTD_decompress_usingDict);
+
+EXPORT_SYMBOL(ZSTD_DDictWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initDDict);
+EXPORT_SYMBOL(ZSTD_decompress_usingDDict);
+
+EXPORT_SYMBOL(ZSTD_DStreamWorkspaceBound);
+EXPORT_SYMBOL(ZSTD_initDStream);
+EXPORT_SYMBOL(ZSTD_initDStream_usingDDict);
+EXPORT_SYMBOL(ZSTD_resetDStream);
+EXPORT_SYMBOL(ZSTD_decompressStream);
+EXPORT_SYMBOL(ZSTD_DStreamInSize);
+EXPORT_SYMBOL(ZSTD_DStreamOutSize);
+
+EXPORT_SYMBOL(ZSTD_findFrameCompressedSize);
+EXPORT_SYMBOL(ZSTD_getFrameContentSize);
+EXPORT_SYMBOL(ZSTD_findDecompressedSize);
+
+EXPORT_SYMBOL(ZSTD_isFrame);
+EXPORT_SYMBOL(ZSTD_getDictID_fromDict);
+EXPORT_SYMBOL(ZSTD_getDictID_fromDDict);
+EXPORT_SYMBOL(ZSTD_getDictID_fromFrame);
+
+EXPORT_SYMBOL(ZSTD_getFrameParams);
+EXPORT_SYMBOL(ZSTD_decompressBegin);
+EXPORT_SYMBOL(ZSTD_decompressBegin_usingDict);
+EXPORT_SYMBOL(ZSTD_copyDCtx);
+EXPORT_SYMBOL(ZSTD_nextSrcSizeToDecompress);
+EXPORT_SYMBOL(ZSTD_decompressContinue);
+EXPORT_SYMBOL(ZSTD_nextInputType);
+
+EXPORT_SYMBOL(ZSTD_decompressBlock);
+EXPORT_SYMBOL(ZSTD_insertBlock);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Zstd Decompressor");
diff --git a/lib/zstd/entropy_common.c b/lib/zstd/entropy_common.c
new file mode 100644
index 0000000..2b0a643
--- /dev/null
+++ b/lib/zstd/entropy_common.c
@@ -0,0 +1,243 @@
+/*
+ * Common functions of New Generation Entropy library
+ * Copyright (C) 2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+
+/* *************************************
+* Dependencies
+***************************************/
+#include "error_private.h" /* ERR_*, ERROR */
+#include "fse.h"
+#include "huf.h"
+#include "mem.h"
+
+/*=== Version ===*/
+unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
+
+/*=== Error Management ===*/
+unsigned FSE_isError(size_t code) { return ERR_isError(code); }
+
+unsigned HUF_isError(size_t code) { return ERR_isError(code); }
+
+/*-**************************************************************
+* FSE NCount encoding-decoding
+****************************************************************/
+size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSVPtr, unsigned *tableLogPtr, const void *headerBuffer, size_t hbSize)
+{
+ const BYTE *const istart = (const BYTE *)headerBuffer;
+ const BYTE *const iend = istart + hbSize;
+ const BYTE *ip = istart;
+ int nbBits;
+ int remaining;
+ int threshold;
+ U32 bitStream;
+ int bitCount;
+ unsigned charnum = 0;
+ int previous0 = 0;
+
+ if (hbSize < 4)
+ return ERROR(srcSize_wrong);
+ bitStream = ZSTD_readLE32(ip);
+ nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */
+ if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX)
+ return ERROR(tableLog_tooLarge);
+ bitStream >>= 4;
+ bitCount = 4;
+ *tableLogPtr = nbBits;
+ remaining = (1 << nbBits) + 1;
+ threshold = 1 << nbBits;
+ nbBits++;
+
+ while ((remaining > 1) & (charnum <= *maxSVPtr)) {
+ if (previous0) {
+ unsigned n0 = charnum;
+ while ((bitStream & 0xFFFF) == 0xFFFF) {
+ n0 += 24;
+ if (ip < iend - 5) {
+ ip += 2;
+ bitStream = ZSTD_readLE32(ip) >> bitCount;
+ } else {
+ bitStream >>= 16;
+ bitCount += 16;
+ }
+ }
+ while ((bitStream & 3) == 3) {
+ n0 += 3;
+ bitStream >>= 2;
+ bitCount += 2;
+ }
+ n0 += bitStream & 3;
+ bitCount += 2;
+ if (n0 > *maxSVPtr)
+ return ERROR(maxSymbolValue_tooSmall);
+ while (charnum < n0)
+ normalizedCounter[charnum++] = 0;
+ if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
+ ip += bitCount >> 3;
+ bitCount &= 7;
+ bitStream = ZSTD_readLE32(ip) >> bitCount;
+ } else {
+ bitStream >>= 2;
+ }
+ }
+ {
+ int const max = (2 * threshold - 1) - remaining;
+ int count;
+
+ if ((bitStream & (threshold - 1)) < (U32)max) {
+ count = bitStream & (threshold - 1);
+ bitCount += nbBits - 1;
+ } else {
+ count = bitStream & (2 * threshold - 1);
+ if (count >= threshold)
+ count -= max;
+ bitCount += nbBits;
+ }
+
+ count--; /* extra accuracy */
+ remaining -= count < 0 ? -count : count; /* -1 means +1 */
+ normalizedCounter[charnum++] = (short)count;
+ previous0 = !count;
+ while (remaining < threshold) {
+ nbBits--;
+ threshold >>= 1;
+ }
+
+ if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
+ ip += bitCount >> 3;
+ bitCount &= 7;
+ } else {
+ bitCount -= (int)(8 * (iend - 4 - ip));
+ ip = iend - 4;
+ }
+ bitStream = ZSTD_readLE32(ip) >> (bitCount & 31);
+ }
+ } /* while ((remaining>1) & (charnum<=*maxSVPtr)) */
+ if (remaining != 1)
+ return ERROR(corruption_detected);
+ if (bitCount > 32)
+ return ERROR(corruption_detected);
+ *maxSVPtr = charnum - 1;
+
+ ip += (bitCount + 7) >> 3;
+ return ip - istart;
+}
+
+/*! HUF_readStats() :
+ Read compact Huffman tree, saved by HUF_writeCTable().
+ `huffWeight` is destination buffer.
+ `rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
+ @return : size read from `src` , or an error Code .
+ Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
+*/
+size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
+{
+ U32 weightTotal;
+ const BYTE *ip = (const BYTE *)src;
+ size_t iSize;
+ size_t oSize;
+
+ if (!srcSize)
+ return ERROR(srcSize_wrong);
+ iSize = ip[0];
+ /* memset(huffWeight, 0, hwSize); */ /* is not necessary, even though some analyzer complain ... */
+
+ if (iSize >= 128) { /* special header */
+ oSize = iSize - 127;
+ iSize = ((oSize + 1) / 2);
+ if (iSize + 1 > srcSize)
+ return ERROR(srcSize_wrong);
+ if (oSize >= hwSize)
+ return ERROR(corruption_detected);
+ ip += 1;
+ {
+ U32 n;
+ for (n = 0; n < oSize; n += 2) {
+ huffWeight[n] = ip[n / 2] >> 4;
+ huffWeight[n + 1] = ip[n / 2] & 15;
+ }
+ }
+ } else { /* header compressed with FSE (normal case) */
+ if (iSize + 1 > srcSize)
+ return ERROR(srcSize_wrong);
+ oSize = FSE_decompress_wksp(huffWeight, hwSize - 1, ip + 1, iSize, 6, workspace, workspaceSize); /* max (hwSize-1) values decoded, as last one is implied */
+ if (FSE_isError(oSize))
+ return oSize;
+ }
+
+ /* collect weight stats */
+ memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32));
+ weightTotal = 0;
+ {
+ U32 n;
+ for (n = 0; n < oSize; n++) {
+ if (huffWeight[n] >= HUF_TABLELOG_MAX)
+ return ERROR(corruption_detected);
+ rankStats[huffWeight[n]]++;
+ weightTotal += (1 << huffWeight[n]) >> 1;
+ }
+ }
+ if (weightTotal == 0)
+ return ERROR(corruption_detected);
+
+ /* get last non-null symbol weight (implied, total must be 2^n) */
+ {
+ U32 const tableLog = BIT_highbit32(weightTotal) + 1;
+ if (tableLog > HUF_TABLELOG_MAX)
+ return ERROR(corruption_detected);
+ *tableLogPtr = tableLog;
+ /* determine last weight */
+ {
+ U32 const total = 1 << tableLog;
+ U32 const rest = total - weightTotal;
+ U32 const verif = 1 << BIT_highbit32(rest);
+ U32 const lastWeight = BIT_highbit32(rest) + 1;
+ if (verif != rest)
+ return ERROR(corruption_detected); /* last value must be a clean power of 2 */
+ huffWeight[oSize] = (BYTE)lastWeight;
+ rankStats[lastWeight]++;
+ }
+ }
+
+ /* check tree construction validity */
+ if ((rankStats[1] < 2) || (rankStats[1] & 1))
+ return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */
+
+ /* results */
+ *nbSymbolsPtr = (U32)(oSize + 1);
+ return iSize + 1;
+}
diff --git a/lib/zstd/error_private.h b/lib/zstd/error_private.h
new file mode 100644
index 0000000..1a60b31
--- /dev/null
+++ b/lib/zstd/error_private.h
@@ -0,0 +1,53 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+/* Note : this module is expected to remain private, do not expose it */
+
+#ifndef ERROR_H_MODULE
+#define ERROR_H_MODULE
+
+/* ****************************************
+* Dependencies
+******************************************/
+#include <linux/types.h> /* size_t */
+#include <linux/zstd.h> /* enum list */
+
+/* ****************************************
+* Compiler-specific
+******************************************/
+#define ERR_STATIC static __attribute__((unused))
+
+/*-****************************************
+* Customization (error_public.h)
+******************************************/
+typedef ZSTD_ErrorCode ERR_enum;
+#define PREFIX(name) ZSTD_error_##name
+
+/*-****************************************
+* Error codes handling
+******************************************/
+#define ERROR(name) ((size_t)-PREFIX(name))
+
+ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
+
+ERR_STATIC ERR_enum ERR_getErrorCode(size_t code)
+{
+ if (!ERR_isError(code))
+ return (ERR_enum)0;
+ return (ERR_enum)(0 - code);
+}
+
+#endif /* ERROR_H_MODULE */
diff --git a/lib/zstd/fse.h b/lib/zstd/fse.h
new file mode 100644
index 0000000..7460ab0
--- /dev/null
+++ b/lib/zstd/fse.h
@@ -0,0 +1,575 @@
+/*
+ * FSE : Finite State Entropy codec
+ * Public Prototypes declaration
+ * Copyright (C) 2013-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+#ifndef FSE_H
+#define FSE_H
+
+/*-*****************************************
+* Dependencies
+******************************************/
+#include <linux/types.h> /* size_t, ptrdiff_t */
+
+/*-*****************************************
+* FSE_PUBLIC_API : control library symbols visibility
+******************************************/
+#define FSE_PUBLIC_API
+
+/*------ Version ------*/
+#define FSE_VERSION_MAJOR 0
+#define FSE_VERSION_MINOR 9
+#define FSE_VERSION_RELEASE 0
+
+#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
+#define FSE_QUOTE(str) #str
+#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
+#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
+
+#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR * 100 * 100 + FSE_VERSION_MINOR * 100 + FSE_VERSION_RELEASE)
+FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */
+
+/*-*****************************************
+* Tool functions
+******************************************/
+FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */
+
+/* Error Management */
+FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */
+
+/*-*****************************************
+* FSE detailed API
+******************************************/
+/*!
+FSE_compress() does the following:
+1. count symbol occurrence from source[] into table count[]
+2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog)
+3. save normalized counters to memory buffer using writeNCount()
+4. build encoding table 'CTable' from normalized counters
+5. encode the data stream using encoding table 'CTable'
+
+FSE_decompress() does the following:
+1. read normalized counters with readNCount()
+2. build decoding table 'DTable' from normalized counters
+3. decode the data stream using decoding table 'DTable'
+
+The following API allows targeting specific sub-functions for advanced tasks.
+For example, it's possible to compress several blocks using the same 'CTable',
+or to save and provide normalized distribution using external method.
+*/
+
+/* *** COMPRESSION *** */
+/*! FSE_optimalTableLog():
+ dynamically downsize 'tableLog' when conditions are met.
+ It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
+ @return : recommended tableLog (necessarily <= 'maxTableLog') */
+FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+
+/*! FSE_normalizeCount():
+ normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
+ 'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
+ @return : tableLog,
+ or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t srcSize, unsigned maxSymbolValue);
+
+/*! FSE_NCountWriteBound():
+ Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
+ Typically useful for allocation purpose. */
+FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
+
+/*! FSE_writeNCount():
+ Compactly save 'normalizedCounter' into 'buffer'.
+ @return : size of the compressed table,
+ or an errorCode, which can be tested using FSE_isError(). */
+FSE_PUBLIC_API size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+
+/*! Constructor and Destructor of FSE_CTable.
+ Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
+typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */
+
+/*! FSE_compress_usingCTable():
+ Compress `src` using `ct` into `dst` which must be already allocated.
+ @return : size of compressed data (<= `dstCapacity`),
+ or 0 if compressed data could not fit into `dst`,
+ or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_compress_usingCTable(void *dst, size_t dstCapacity, const void *src, size_t srcSize, const FSE_CTable *ct);
+
+/*!
+Tutorial :
+----------
+The first step is to count all symbols. FSE_count() does this job very fast.
+Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells.
+'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0]
+maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value)
+FSE_count() will return the number of occurrence of the most frequent symbol.
+This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
+
+The next step is to normalize the frequencies.
+FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'.
+It also guarantees a minimum of 1 to any Symbol with frequency >= 1.
+You can use 'tableLog'==0 to mean "use default tableLog value".
+If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(),
+which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default").
+
+The result of FSE_normalizeCount() will be saved into a table,
+called 'normalizedCounter', which is a table of signed short.
+'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells.
+The return value is tableLog if everything proceeded as expected.
+It is 0 if there is a single symbol within distribution.
+If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()).
+
+'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount().
+'buffer' must be already allocated.
+For guaranteed success, buffer size must be at least FSE_headerBound().
+The result of the function is the number of bytes written into 'buffer'.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small).
+
+'normalizedCounter' can then be used to create the compression table 'CTable'.
+The space required by 'CTable' must be already allocated, using FSE_createCTable().
+You can then use FSE_buildCTable() to fill 'CTable'.
+If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()).
+
+'CTable' can then be used to compress 'src', with FSE_compress_usingCTable().
+Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize'
+The function returns the size of compressed data (without header), necessarily <= `dstCapacity`.
+If it returns '0', compressed data could not fit into 'dst'.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
+*/
+
+/* *** DECOMPRESSION *** */
+
+/*! FSE_readNCount():
+ Read compactly saved 'normalizedCounter' from 'rBuffer'.
+ @return : size read from 'rBuffer',
+ or an errorCode, which can be tested using FSE_isError().
+ maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
+FSE_PUBLIC_API size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSymbolValuePtr, unsigned *tableLogPtr, const void *rBuffer, size_t rBuffSize);
+
+/*! Constructor and Destructor of FSE_DTable.
+ Note that its size depends on 'tableLog' */
+typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */
+
+/*! FSE_buildDTable():
+ Builds 'dt', which must be already allocated, using FSE_createDTable().
+ return : 0, or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize);
+
+/*! FSE_decompress_usingDTable():
+ Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
+ into `dst` which must be already allocated.
+ @return : size of regenerated data (necessarily <= `dstCapacity`),
+ or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt);
+
+/*!
+Tutorial :
+----------
+(Note : these functions only decompress FSE-compressed blocks.
+ If block is uncompressed, use memcpy() instead
+ If block is a single repeated byte, use memset() instead )
+
+The first step is to obtain the normalized frequencies of symbols.
+This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount().
+'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short.
+In practice, that means it's necessary to know 'maxSymbolValue' beforehand,
+or size the table to handle worst case situations (typically 256).
+FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'.
+The result of FSE_readNCount() is the number of bytes read from 'rBuffer'.
+Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that.
+If there is an error, the function will return an error code, which can be tested using FSE_isError().
+
+The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'.
+This is performed by the function FSE_buildDTable().
+The space required by 'FSE_DTable' must be already allocated using FSE_createDTable().
+If there is an error, the function will return an error code, which can be tested using FSE_isError().
+
+`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable().
+`cSrcSize` must be strictly correct, otherwise decompression will fail.
+FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`).
+If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small)
+*/
+
+/* *** Dependency *** */
+#include "bitstream.h"
+
+/* *****************************************
+* Static allocation
+*******************************************/
+/* FSE buffer bounds */
+#define FSE_NCOUNTBOUND 512
+#define FSE_BLOCKBOUND(size) (size + (size >> 7))
+#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
+
+/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */
+#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1 << (maxTableLog - 1)) + ((maxSymbolValue + 1) * 2))
+#define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1 << maxTableLog))
+
+/* *****************************************
+* FSE advanced API
+*******************************************/
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned
+ */
+size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace);
+
+/* FSE_countFast_wksp() :
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` must be a table of minimum `1024` unsigned
+ */
+size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize, unsigned *workSpace);
+
+/*! FSE_count_simple
+ * Same as FSE_countFast(), but does not use any additional memory (not even on stack).
+ * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`).
+*/
+size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize);
+
+unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
+/**< same as FSE_optimalTableLog(), which used `minus==2` */
+
+size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits);
+/**< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
+
+size_t FSE_buildCTable_rle(FSE_CTable *ct, unsigned char symbolValue);
+/**< build a fake FSE_CTable, designed to compress always the same symbolValue */
+
+/* FSE_buildCTable_wksp() :
+ * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
+ * `wkspSize` must be >= `(1<<tableLog)`.
+ */
+size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, size_t wkspSize);
+
+size_t FSE_buildDTable_raw(FSE_DTable *dt, unsigned nbBits);
+/**< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
+
+size_t FSE_buildDTable_rle(FSE_DTable *dt, unsigned char symbolValue);
+/**< build a fake FSE_DTable, designed to always generate the same symbolValue */
+
+size_t FSE_decompress_wksp(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, unsigned maxLog, void *workspace, size_t workspaceSize);
+/**< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DTABLE_SIZE_U32(maxLog)` */
+
+/* *****************************************
+* FSE symbol compression API
+*******************************************/
+/*!
+ This API consists of small unitary functions, which highly benefit from being inlined.
+ Hence their body are included in next section.
+*/
+typedef struct {
+ ptrdiff_t value;
+ const void *stateTable;
+ const void *symbolTT;
+ unsigned stateLog;
+} FSE_CState_t;
+
+static void FSE_initCState(FSE_CState_t *CStatePtr, const FSE_CTable *ct);
+
+static void FSE_encodeSymbol(BIT_CStream_t *bitC, FSE_CState_t *CStatePtr, unsigned symbol);
+
+static void FSE_flushCState(BIT_CStream_t *bitC, const FSE_CState_t *CStatePtr);
+
+/**<
+These functions are inner components of FSE_compress_usingCTable().
+They allow the creation of custom streams, mixing multiple tables and bit sources.
+
+A key property to keep in mind is that encoding and decoding are done **in reverse direction**.
+So the first symbol you will encode is the last you will decode, like a LIFO stack.
+
+You will need a few variables to track your CStream. They are :
+
+FSE_CTable ct; // Provided by FSE_buildCTable()
+BIT_CStream_t bitStream; // bitStream tracking structure
+FSE_CState_t state; // State tracking structure (can have several)
+
+
+The first thing to do is to init bitStream and state.
+ size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize);
+ FSE_initCState(&state, ct);
+
+Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError();
+You can then encode your input data, byte after byte.
+FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time.
+Remember decoding will be done in reverse direction.
+ FSE_encodeByte(&bitStream, &state, symbol);
+
+At any time, you can also add any bit sequence.
+Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders
+ BIT_addBits(&bitStream, bitField, nbBits);
+
+The above methods don't commit data to memory, they just store it into local register, for speed.
+Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+Writing data to memory is a manual operation, performed by the flushBits function.
+ BIT_flushBits(&bitStream);
+
+Your last FSE encoding operation shall be to flush your last state value(s).
+ FSE_flushState(&bitStream, &state);
+
+Finally, you must close the bitStream.
+The function returns the size of CStream in bytes.
+If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible)
+If there is an error, it returns an errorCode (which can be tested using FSE_isError()).
+ size_t size = BIT_closeCStream(&bitStream);
+*/
+
+/* *****************************************
+* FSE symbol decompression API
+*******************************************/
+typedef struct {
+ size_t state;
+ const void *table; /* precise table may vary, depending on U16 */
+} FSE_DState_t;
+
+static void FSE_initDState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD, const FSE_DTable *dt);
+
+static unsigned char FSE_decodeSymbol(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD);
+
+static unsigned FSE_endOfDState(const FSE_DState_t *DStatePtr);
+
+/**<
+Let's now decompose FSE_decompress_usingDTable() into its unitary components.
+You will decode FSE-encoded symbols from the bitStream,
+and also any other bitFields you put in, **in reverse order**.
+
+You will need a few variables to track your bitStream. They are :
+
+BIT_DStream_t DStream; // Stream context
+FSE_DState_t DState; // State context. Multiple ones are possible
+FSE_DTable* DTablePtr; // Decoding table, provided by FSE_buildDTable()
+
+The first thing to do is to init the bitStream.
+ errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize);
+
+You should then retrieve your initial state(s)
+(in reverse flushing order if you have several ones) :
+ errorCode = FSE_initDState(&DState, &DStream, DTablePtr);
+
+You can then decode your data, symbol after symbol.
+For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'.
+Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out).
+ unsigned char symbol = FSE_decodeSymbol(&DState, &DStream);
+
+You can retrieve any bitfield you eventually stored into the bitStream (in reverse order)
+Note : maximum allowed nbBits is 25, for 32-bits compatibility
+ size_t bitField = BIT_readBits(&DStream, nbBits);
+
+All above operations only read from local register (which size depends on size_t).
+Refueling the register from memory is manually performed by the reload method.
+ endSignal = FSE_reloadDStream(&DStream);
+
+BIT_reloadDStream() result tells if there is still some more data to read from DStream.
+BIT_DStream_unfinished : there is still some data left into the DStream.
+BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled.
+BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed.
+BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted.
+
+When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop,
+to properly detect the exact end of stream.
+After each decoded symbol, check if DStream is fully consumed using this simple test :
+ BIT_reloadDStream(&DStream) >= BIT_DStream_completed
+
+When it's done, verify decompression is fully completed, by checking both DStream and the relevant states.
+Checking if DStream has reached its end is performed by :
+ BIT_endOfDStream(&DStream);
+Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible.
+ FSE_endOfDState(&DState);
+*/
+
+/* *****************************************
+* FSE unsafe API
+*******************************************/
+static unsigned char FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD);
+/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */
+
+/* *****************************************
+* Implementation of inlined functions
+*******************************************/
+typedef struct {
+ int deltaFindState;
+ U32 deltaNbBits;
+} FSE_symbolCompressionTransform; /* total 8 bytes */
+
+ZSTD_STATIC void FSE_initCState(FSE_CState_t *statePtr, const FSE_CTable *ct)
+{
+ const void *ptr = ct;
+ const U16 *u16ptr = (const U16 *)ptr;
+ const U32 tableLog = ZSTD_read16(ptr);
+ statePtr->value = (ptrdiff_t)1 << tableLog;
+ statePtr->stateTable = u16ptr + 2;
+ statePtr->symbolTT = ((const U32 *)ct + 1 + (tableLog ? (1 << (tableLog - 1)) : 1));
+ statePtr->stateLog = tableLog;
+}
+
+/*! FSE_initCState2() :
+* Same as FSE_initCState(), but the first symbol to include (which will be the last to be read)
+* uses the smallest state value possible, saving the cost of this symbol */
+ZSTD_STATIC void FSE_initCState2(FSE_CState_t *statePtr, const FSE_CTable *ct, U32 symbol)
+{
+ FSE_initCState(statePtr, ct);
+ {
+ const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol];
+ const U16 *stateTable = (const U16 *)(statePtr->stateTable);
+ U32 nbBitsOut = (U32)((symbolTT.deltaNbBits + (1 << 15)) >> 16);
+ statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits;
+ statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+ }
+}
+
+ZSTD_STATIC void FSE_encodeSymbol(BIT_CStream_t *bitC, FSE_CState_t *statePtr, U32 symbol)
+{
+ const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol];
+ const U16 *const stateTable = (const U16 *)(statePtr->stateTable);
+ U32 nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
+ BIT_addBits(bitC, statePtr->value, nbBitsOut);
+ statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+}
+
+ZSTD_STATIC void FSE_flushCState(BIT_CStream_t *bitC, const FSE_CState_t *statePtr)
+{
+ BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
+ BIT_flushBits(bitC);
+}
+
+/* ====== Decompression ====== */
+
+typedef struct {
+ U16 tableLog;
+ U16 fastMode;
+} FSE_DTableHeader; /* sizeof U32 */
+
+typedef struct {
+ unsigned short newState;
+ unsigned char symbol;
+ unsigned char nbBits;
+} FSE_decode_t; /* size == U32 */
+
+ZSTD_STATIC void FSE_initDState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD, const FSE_DTable *dt)
+{
+ const void *ptr = dt;
+ const FSE_DTableHeader *const DTableH = (const FSE_DTableHeader *)ptr;
+ DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
+ BIT_reloadDStream(bitD);
+ DStatePtr->table = dt + 1;
+}
+
+ZSTD_STATIC BYTE FSE_peekSymbol(const FSE_DState_t *DStatePtr)
+{
+ FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
+ return DInfo.symbol;
+}
+
+ZSTD_STATIC void FSE_updateState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
+{
+ FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
+ U32 const nbBits = DInfo.nbBits;
+ size_t const lowBits = BIT_readBits(bitD, nbBits);
+ DStatePtr->state = DInfo.newState + lowBits;
+}
+
+ZSTD_STATIC BYTE FSE_decodeSymbol(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
+{
+ FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
+ U32 const nbBits = DInfo.nbBits;
+ BYTE const symbol = DInfo.symbol;
+ size_t const lowBits = BIT_readBits(bitD, nbBits);
+
+ DStatePtr->state = DInfo.newState + lowBits;
+ return symbol;
+}
+
+/*! FSE_decodeSymbolFast() :
+ unsafe, only works if no symbol has a probability > 50% */
+ZSTD_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
+{
+ FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
+ U32 const nbBits = DInfo.nbBits;
+ BYTE const symbol = DInfo.symbol;
+ size_t const lowBits = BIT_readBitsFast(bitD, nbBits);
+
+ DStatePtr->state = DInfo.newState + lowBits;
+ return symbol;
+}
+
+ZSTD_STATIC unsigned FSE_endOfDState(const FSE_DState_t *DStatePtr) { return DStatePtr->state == 0; }
+
+/* **************************************************************
+* Tuning parameters
+****************************************************************/
+/*!MEMORY_USAGE :
+* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+* Increasing memory usage improves compression ratio
+* Reduced memory usage can improve speed, due to cache effect
+* Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
+#ifndef FSE_MAX_MEMORY_USAGE
+#define FSE_MAX_MEMORY_USAGE 14
+#endif
+#ifndef FSE_DEFAULT_MEMORY_USAGE
+#define FSE_DEFAULT_MEMORY_USAGE 13
+#endif
+
+/*!FSE_MAX_SYMBOL_VALUE :
+* Maximum symbol value authorized.
+* Required for proper stack allocation */
+#ifndef FSE_MAX_SYMBOL_VALUE
+#define FSE_MAX_SYMBOL_VALUE 255
+#endif
+
+/* **************************************************************
+* template functions type & suffix
+****************************************************************/
+#define FSE_FUNCTION_TYPE BYTE
+#define FSE_FUNCTION_EXTENSION
+#define FSE_DECODE_TYPE FSE_decode_t
+
+/* ***************************************************************
+* Constants
+*****************************************************************/
+#define FSE_MAX_TABLELOG (FSE_MAX_MEMORY_USAGE - 2)
+#define FSE_MAX_TABLESIZE (1U << FSE_MAX_TABLELOG)
+#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE - 1)
+#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE - 2)
+#define FSE_MIN_TABLELOG 5
+
+#define FSE_TABLELOG_ABSOLUTE_MAX 15
+#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX
+#error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported"
+#endif
+
+#define FSE_TABLESTEP(tableSize) ((tableSize >> 1) + (tableSize >> 3) + 3)
+
+#endif /* FSE_H */
diff --git a/lib/zstd/fse_compress.c b/lib/zstd/fse_compress.c
new file mode 100644
index 0000000..ef3d174
--- /dev/null
+++ b/lib/zstd/fse_compress.c
@@ -0,0 +1,795 @@
+/*
+ * FSE : Finite State Entropy encoder
+ * Copyright (C) 2013-2015, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+
+/* **************************************************************
+* Compiler specifics
+****************************************************************/
+#define FORCE_INLINE static __always_inline
+
+/* **************************************************************
+* Includes
+****************************************************************/
+#include "bitstream.h"
+#include "fse.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/string.h> /* memcpy, memset */
+
+/* **************************************************************
+* Error Management
+****************************************************************/
+#define FSE_STATIC_ASSERT(c) \
+ { \
+ enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
+ } /* use only *after* variable declarations */
+
+/* **************************************************************
+* Templates
+****************************************************************/
+/*
+ designed to be included
+ for type-specific functions (template emulation in C)
+ Objective is to write these functions only once, for improved maintenance
+*/
+
+/* safety checks */
+#ifndef FSE_FUNCTION_EXTENSION
+#error "FSE_FUNCTION_EXTENSION must be defined"
+#endif
+#ifndef FSE_FUNCTION_TYPE
+#error "FSE_FUNCTION_TYPE must be defined"
+#endif
+
+/* Function names */
+#define FSE_CAT(X, Y) X##Y
+#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y)
+#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y)
+
+/* Function templates */
+
+/* FSE_buildCTable_wksp() :
+ * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
+ * wkspSize should be sized to handle worst case situation, which is `1<<max_tableLog * sizeof(FSE_FUNCTION_TYPE)`
+ * workSpace must also be properly aligned with FSE_FUNCTION_TYPE requirements
+ */
+size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize)
+{
+ U32 const tableSize = 1 << tableLog;
+ U32 const tableMask = tableSize - 1;
+ void *const ptr = ct;
+ U16 *const tableU16 = ((U16 *)ptr) + 2;
+ void *const FSCT = ((U32 *)ptr) + 1 /* header */ + (tableLog ? tableSize >> 1 : 1);
+ FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT);
+ U32 const step = FSE_TABLESTEP(tableSize);
+ U32 highThreshold = tableSize - 1;
+
+ U32 *cumul;
+ FSE_FUNCTION_TYPE *tableSymbol;
+ size_t spaceUsed32 = 0;
+
+ cumul = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += FSE_MAX_SYMBOL_VALUE + 2;
+ tableSymbol = (FSE_FUNCTION_TYPE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(sizeof(FSE_FUNCTION_TYPE) * ((size_t)1 << tableLog), sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ /* CTable header */
+ tableU16[-2] = (U16)tableLog;
+ tableU16[-1] = (U16)maxSymbolValue;
+
+ /* For explanations on how to distribute symbol values over the table :
+ * http://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */
+
+ /* symbol start positions */
+ {
+ U32 u;
+ cumul[0] = 0;
+ for (u = 1; u <= maxSymbolValue + 1; u++) {
+ if (normalizedCounter[u - 1] == -1) { /* Low proba symbol */
+ cumul[u] = cumul[u - 1] + 1;
+ tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u - 1);
+ } else {
+ cumul[u] = cumul[u - 1] + normalizedCounter[u - 1];
+ }
+ }
+ cumul[maxSymbolValue + 1] = tableSize + 1;
+ }
+
+ /* Spread symbols */
+ {
+ U32 position = 0;
+ U32 symbol;
+ for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
+ int nbOccurences;
+ for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
+ tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
+ position = (position + step) & tableMask;
+ while (position > highThreshold)
+ position = (position + step) & tableMask; /* Low proba area */
+ }
+ }
+
+ if (position != 0)
+ return ERROR(GENERIC); /* Must have gone through all positions */
+ }
+
+ /* Build table */
+ {
+ U32 u;
+ for (u = 0; u < tableSize; u++) {
+ FSE_FUNCTION_TYPE s = tableSymbol[u]; /* note : static analyzer may not understand tableSymbol is properly initialized */
+ tableU16[cumul[s]++] = (U16)(tableSize + u); /* TableU16 : sorted by symbol order; gives next state value */
+ }
+ }
+
+ /* Build Symbol Transformation Table */
+ {
+ unsigned total = 0;
+ unsigned s;
+ for (s = 0; s <= maxSymbolValue; s++) {
+ switch (normalizedCounter[s]) {
+ case 0: break;
+
+ case -1:
+ case 1:
+ symbolTT[s].deltaNbBits = (tableLog << 16) - (1 << tableLog);
+ symbolTT[s].deltaFindState = total - 1;
+ total++;
+ break;
+ default: {
+ U32 const maxBitsOut = tableLog - BIT_highbit32(normalizedCounter[s] - 1);
+ U32 const minStatePlus = normalizedCounter[s] << maxBitsOut;
+ symbolTT[s].deltaNbBits = (maxBitsOut << 16) - minStatePlus;
+ symbolTT[s].deltaFindState = total - normalizedCounter[s];
+ total += normalizedCounter[s];
+ }
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*-**************************************************************
+* FSE NCount encoding-decoding
+****************************************************************/
+size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog)
+{
+ size_t const maxHeaderSize = (((maxSymbolValue + 1) * tableLog) >> 3) + 3;
+ return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND; /* maxSymbolValue==0 ? use default */
+}
+
+static size_t FSE_writeNCount_generic(void *header, size_t headerBufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
+ unsigned writeIsSafe)
+{
+ BYTE *const ostart = (BYTE *)header;
+ BYTE *out = ostart;
+ BYTE *const oend = ostart + headerBufferSize;
+ int nbBits;
+ const int tableSize = 1 << tableLog;
+ int remaining;
+ int threshold;
+ U32 bitStream;
+ int bitCount;
+ unsigned charnum = 0;
+ int previous0 = 0;
+
+ bitStream = 0;
+ bitCount = 0;
+ /* Table Size */
+ bitStream += (tableLog - FSE_MIN_TABLELOG) << bitCount;
+ bitCount += 4;
+
+ /* Init */
+ remaining = tableSize + 1; /* +1 for extra accuracy */
+ threshold = tableSize;
+ nbBits = tableLog + 1;
+
+ while (remaining > 1) { /* stops at 1 */
+ if (previous0) {
+ unsigned start = charnum;
+ while (!normalizedCounter[charnum])
+ charnum++;
+ while (charnum >= start + 24) {
+ start += 24;
+ bitStream += 0xFFFFU << bitCount;
+ if ((!writeIsSafe) && (out > oend - 2))
+ return ERROR(dstSize_tooSmall); /* Buffer overflow */
+ out[0] = (BYTE)bitStream;
+ out[1] = (BYTE)(bitStream >> 8);
+ out += 2;
+ bitStream >>= 16;
+ }
+ while (charnum >= start + 3) {
+ start += 3;
+ bitStream += 3 << bitCount;
+ bitCount += 2;
+ }
+ bitStream += (charnum - start) << bitCount;
+ bitCount += 2;
+ if (bitCount > 16) {
+ if ((!writeIsSafe) && (out > oend - 2))
+ return ERROR(dstSize_tooSmall); /* Buffer overflow */
+ out[0] = (BYTE)bitStream;
+ out[1] = (BYTE)(bitStream >> 8);
+ out += 2;
+ bitStream >>= 16;
+ bitCount -= 16;
+ }
+ }
+ {
+ int count = normalizedCounter[charnum++];
+ int const max = (2 * threshold - 1) - remaining;
+ remaining -= count < 0 ? -count : count;
+ count++; /* +1 for extra accuracy */
+ if (count >= threshold)
+ count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */
+ bitStream += count << bitCount;
+ bitCount += nbBits;
+ bitCount -= (count < max);
+ previous0 = (count == 1);
+ if (remaining < 1)
+ return ERROR(GENERIC);
+ while (remaining < threshold)
+ nbBits--, threshold >>= 1;
+ }
+ if (bitCount > 16) {
+ if ((!writeIsSafe) && (out > oend - 2))
+ return ERROR(dstSize_tooSmall); /* Buffer overflow */
+ out[0] = (BYTE)bitStream;
+ out[1] = (BYTE)(bitStream >> 8);
+ out += 2;
+ bitStream >>= 16;
+ bitCount -= 16;
+ }
+ }
+
+ /* flush remaining bitStream */
+ if ((!writeIsSafe) && (out > oend - 2))
+ return ERROR(dstSize_tooSmall); /* Buffer overflow */
+ out[0] = (BYTE)bitStream;
+ out[1] = (BYTE)(bitStream >> 8);
+ out += (bitCount + 7) / 8;
+
+ if (charnum > maxSymbolValue + 1)
+ return ERROR(GENERIC);
+
+ return (out - ostart);
+}
+
+size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
+{
+ if (tableLog > FSE_MAX_TABLELOG)
+ return ERROR(tableLog_tooLarge); /* Unsupported */
+ if (tableLog < FSE_MIN_TABLELOG)
+ return ERROR(GENERIC); /* Unsupported */
+
+ if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog))
+ return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0);
+
+ return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1);
+}
+
+/*-**************************************************************
+* Counting histogram
+****************************************************************/
+/*! FSE_count_simple
+ This function counts byte values within `src`, and store the histogram into table `count`.
+ It doesn't use any additional memory.
+ But this function is unsafe : it doesn't check that all values within `src` can fit into `count`.
+ For this reason, prefer using a table `count` with 256 elements.
+ @return : count of most numerous element
+*/
+size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize)
+{
+ const BYTE *ip = (const BYTE *)src;
+ const BYTE *const end = ip + srcSize;
+ unsigned maxSymbolValue = *maxSymbolValuePtr;
+ unsigned max = 0;
+
+ memset(count, 0, (maxSymbolValue + 1) * sizeof(*count));
+ if (srcSize == 0) {
+ *maxSymbolValuePtr = 0;
+ return 0;
+ }
+
+ while (ip < end)
+ count[*ip++]++;
+
+ while (!count[maxSymbolValue])
+ maxSymbolValue--;
+ *maxSymbolValuePtr = maxSymbolValue;
+
+ {
+ U32 s;
+ for (s = 0; s <= maxSymbolValue; s++)
+ if (count[s] > max)
+ max = count[s];
+ }
+
+ return (size_t)max;
+}
+
+/* FSE_count_parallel_wksp() :
+ * Same as FSE_count_parallel(), but using an externally provided scratch buffer.
+ * `workSpace` size must be a minimum of `1024 * sizeof(unsigned)`` */
+static size_t FSE_count_parallel_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned checkMax,
+ unsigned *const workSpace)
+{
+ const BYTE *ip = (const BYTE *)source;
+ const BYTE *const iend = ip + sourceSize;
+ unsigned maxSymbolValue = *maxSymbolValuePtr;
+ unsigned max = 0;
+ U32 *const Counting1 = workSpace;
+ U32 *const Counting2 = Counting1 + 256;
+ U32 *const Counting3 = Counting2 + 256;
+ U32 *const Counting4 = Counting3 + 256;
+
+ memset(Counting1, 0, 4 * 256 * sizeof(unsigned));
+
+ /* safety checks */
+ if (!sourceSize) {
+ memset(count, 0, maxSymbolValue + 1);
+ *maxSymbolValuePtr = 0;
+ return 0;
+ }
+ if (!maxSymbolValue)
+ maxSymbolValue = 255; /* 0 == default */
+
+ /* by stripes of 16 bytes */
+ {
+ U32 cached = ZSTD_read32(ip);
+ ip += 4;
+ while (ip < iend - 15) {
+ U32 c = cached;
+ cached = ZSTD_read32(ip);
+ ip += 4;
+ Counting1[(BYTE)c]++;
+ Counting2[(BYTE)(c >> 8)]++;
+ Counting3[(BYTE)(c >> 16)]++;
+ Counting4[c >> 24]++;
+ c = cached;
+ cached = ZSTD_read32(ip);
+ ip += 4;
+ Counting1[(BYTE)c]++;
+ Counting2[(BYTE)(c >> 8)]++;
+ Counting3[(BYTE)(c >> 16)]++;
+ Counting4[c >> 24]++;
+ c = cached;
+ cached = ZSTD_read32(ip);
+ ip += 4;
+ Counting1[(BYTE)c]++;
+ Counting2[(BYTE)(c >> 8)]++;
+ Counting3[(BYTE)(c >> 16)]++;
+ Counting4[c >> 24]++;
+ c = cached;
+ cached = ZSTD_read32(ip);
+ ip += 4;
+ Counting1[(BYTE)c]++;
+ Counting2[(BYTE)(c >> 8)]++;
+ Counting3[(BYTE)(c >> 16)]++;
+ Counting4[c >> 24]++;
+ }
+ ip -= 4;
+ }
+
+ /* finish last symbols */
+ while (ip < iend)
+ Counting1[*ip++]++;
+
+ if (checkMax) { /* verify stats will fit into destination table */
+ U32 s;
+ for (s = 255; s > maxSymbolValue; s--) {
+ Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
+ if (Counting1[s])
+ return ERROR(maxSymbolValue_tooSmall);
+ }
+ }
+
+ {
+ U32 s;
+ for (s = 0; s <= maxSymbolValue; s++) {
+ count[s] = Counting1[s] + Counting2[s] + Counting3[s] + Counting4[s];
+ if (count[s] > max)
+ max = count[s];
+ }
+ }
+
+ while (!count[maxSymbolValue])
+ maxSymbolValue--;
+ *maxSymbolValuePtr = maxSymbolValue;
+ return (size_t)max;
+}
+
+/* FSE_countFast_wksp() :
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned */
+size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace)
+{
+ if (sourceSize < 1500)
+ return FSE_count_simple(count, maxSymbolValuePtr, source, sourceSize);
+ return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 0, workSpace);
+}
+
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned */
+size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace)
+{
+ if (*maxSymbolValuePtr < 255)
+ return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 1, workSpace);
+ *maxSymbolValuePtr = 255;
+ return FSE_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace);
+}
+
+/*-**************************************************************
+* FSE Compression Code
+****************************************************************/
+/*! FSE_sizeof_CTable() :
+ FSE_CTable is a variable size structure which contains :
+ `U16 tableLog;`
+ `U16 maxSymbolValue;`
+ `U16 nextStateNumber[1 << tableLog];` // This size is variable
+ `FSE_symbolCompressionTransform symbolTT[maxSymbolValue+1];` // This size is variable
+Allocation is manual (C standard does not support variable-size structures).
+*/
+size_t FSE_sizeof_CTable(unsigned maxSymbolValue, unsigned tableLog)
+{
+ if (tableLog > FSE_MAX_TABLELOG)
+ return ERROR(tableLog_tooLarge);
+ return FSE_CTABLE_SIZE_U32(tableLog, maxSymbolValue) * sizeof(U32);
+}
+
+/* provides the minimum logSize to safely represent a distribution */
+static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue)
+{
+ U32 minBitsSrc = BIT_highbit32((U32)(srcSize - 1)) + 1;
+ U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2;
+ U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
+ return minBits;
+}
+
+unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus)
+{
+ U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus;
+ U32 tableLog = maxTableLog;
+ U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
+ if (tableLog == 0)
+ tableLog = FSE_DEFAULT_TABLELOG;
+ if (maxBitsSrc < tableLog)
+ tableLog = maxBitsSrc; /* Accuracy can be reduced */
+ if (minBits > tableLog)
+ tableLog = minBits; /* Need a minimum to safely represent all symbol values */
+ if (tableLog < FSE_MIN_TABLELOG)
+ tableLog = FSE_MIN_TABLELOG;
+ if (tableLog > FSE_MAX_TABLELOG)
+ tableLog = FSE_MAX_TABLELOG;
+ return tableLog;
+}
+
+unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
+{
+ return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2);
+}
+
+/* Secondary normalization method.
+ To be used when primary method fails. */
+
+static size_t FSE_normalizeM2(short *norm, U32 tableLog, const unsigned *count, size_t total, U32 maxSymbolValue)
+{
+ short const NOT_YET_ASSIGNED = -2;
+ U32 s;
+ U32 distributed = 0;
+ U32 ToDistribute;
+
+ /* Init */
+ U32 const lowThreshold = (U32)(total >> tableLog);
+ U32 lowOne = (U32)((total * 3) >> (tableLog + 1));
+
+ for (s = 0; s <= maxSymbolValue; s++) {
+ if (count[s] == 0) {
+ norm[s] = 0;
+ continue;
+ }
+ if (count[s] <= lowThreshold) {
+ norm[s] = -1;
+ distributed++;
+ total -= count[s];
+ continue;
+ }
+ if (count[s] <= lowOne) {
+ norm[s] = 1;
+ distributed++;
+ total -= count[s];
+ continue;
+ }
+
+ norm[s] = NOT_YET_ASSIGNED;
+ }
+ ToDistribute = (1 << tableLog) - distributed;
+
+ if ((total / ToDistribute) > lowOne) {
+ /* risk of rounding to zero */
+ lowOne = (U32)((total * 3) / (ToDistribute * 2));
+ for (s = 0; s <= maxSymbolValue; s++) {
+ if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) {
+ norm[s] = 1;
+ distributed++;
+ total -= count[s];
+ continue;
+ }
+ }
+ ToDistribute = (1 << tableLog) - distributed;
+ }
+
+ if (distributed == maxSymbolValue + 1) {
+ /* all values are pretty poor;
+ probably incompressible data (should have already been detected);
+ find max, then give all remaining points to max */
+ U32 maxV = 0, maxC = 0;
+ for (s = 0; s <= maxSymbolValue; s++)
+ if (count[s] > maxC)
+ maxV = s, maxC = count[s];
+ norm[maxV] += (short)ToDistribute;
+ return 0;
+ }
+
+ if (total == 0) {
+ /* all of the symbols were low enough for the lowOne or lowThreshold */
+ for (s = 0; ToDistribute > 0; s = (s + 1) % (maxSymbolValue + 1))
+ if (norm[s] > 0)
+ ToDistribute--, norm[s]++;
+ return 0;
+ }
+
+ {
+ U64 const vStepLog = 62 - tableLog;
+ U64 const mid = (1ULL << (vStepLog - 1)) - 1;
+ U64 const rStep = div_u64((((U64)1 << vStepLog) * ToDistribute) + mid, (U32)total); /* scale on remaining */
+ U64 tmpTotal = mid;
+ for (s = 0; s <= maxSymbolValue; s++) {
+ if (norm[s] == NOT_YET_ASSIGNED) {
+ U64 const end = tmpTotal + (count[s] * rStep);
+ U32 const sStart = (U32)(tmpTotal >> vStepLog);
+ U32 const sEnd = (U32)(end >> vStepLog);
+ U32 const weight = sEnd - sStart;
+ if (weight < 1)
+ return ERROR(GENERIC);
+ norm[s] = (short)weight;
+ tmpTotal = end;
+ }
+ }
+ }
+
+ return 0;
+}
+
+size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t total, unsigned maxSymbolValue)
+{
+ /* Sanity checks */
+ if (tableLog == 0)
+ tableLog = FSE_DEFAULT_TABLELOG;
+ if (tableLog < FSE_MIN_TABLELOG)
+ return ERROR(GENERIC); /* Unsupported size */
+ if (tableLog > FSE_MAX_TABLELOG)
+ return ERROR(tableLog_tooLarge); /* Unsupported size */
+ if (tableLog < FSE_minTableLog(total, maxSymbolValue))
+ return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */
+
+ {
+ U32 const rtbTable[] = {0, 473195, 504333, 520860, 550000, 700000, 750000, 830000};
+ U64 const scale = 62 - tableLog;
+ U64 const step = div_u64((U64)1 << 62, (U32)total); /* <== here, one division ! */
+ U64 const vStep = 1ULL << (scale - 20);
+ int stillToDistribute = 1 << tableLog;
+ unsigned s;
+ unsigned largest = 0;
+ short largestP = 0;
+ U32 lowThreshold = (U32)(total >> tableLog);
+
+ for (s = 0; s <= maxSymbolValue; s++) {
+ if (count[s] == total)
+ return 0; /* rle special case */
+ if (count[s] == 0) {
+ normalizedCounter[s] = 0;
+ continue;
+ }
+ if (count[s] <= lowThreshold) {
+ normalizedCounter[s] = -1;
+ stillToDistribute--;
+ } else {
+ short proba = (short)((count[s] * step) >> scale);
+ if (proba < 8) {
+ U64 restToBeat = vStep * rtbTable[proba];
+ proba += (count[s] * step) - ((U64)proba << scale) > restToBeat;
+ }
+ if (proba > largestP)
+ largestP = proba, largest = s;
+ normalizedCounter[s] = proba;
+ stillToDistribute -= proba;
+ }
+ }
+ if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) {
+ /* corner case, need another normalization method */
+ size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue);
+ if (FSE_isError(errorCode))
+ return errorCode;
+ } else
+ normalizedCounter[largest] += (short)stillToDistribute;
+ }
+
+ return tableLog;
+}
+
+/* fake FSE_CTable, for raw (uncompressed) input */
+size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits)
+{
+ const unsigned tableSize = 1 << nbBits;
+ const unsigned tableMask = tableSize - 1;
+ const unsigned maxSymbolValue = tableMask;
+ void *const ptr = ct;
+ U16 *const tableU16 = ((U16 *)ptr) + 2;
+ void *const FSCT = ((U32 *)ptr) + 1 /* header */ + (tableSize >> 1); /* assumption : tableLog >= 1 */
+ FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT);
+ unsigned s;
+
+ /* Sanity checks */
+ if (nbBits < 1)
+ return ERROR(GENERIC); /* min size */
+
+ /* header */
+ tableU16[-2] = (U16)nbBits;
+ tableU16[-1] = (U16)maxSymbolValue;
+
+ /* Build table */
+ for (s = 0; s < tableSize; s++)
+ tableU16[s] = (U16)(tableSize + s);
+
+ /* Build Symbol Transformation Table */
+ {
+ const U32 deltaNbBits = (nbBits << 16) - (1 << nbBits);
+ for (s = 0; s <= maxSymbolValue; s++) {
+ symbolTT[s].deltaNbBits = deltaNbBits;
+ symbolTT[s].deltaFindState = s - 1;
+ }
+ }
+
+ return 0;
+}
+
+/* fake FSE_CTable, for rle input (always same symbol) */
+size_t FSE_buildCTable_rle(FSE_CTable *ct, BYTE symbolValue)
+{
+ void *ptr = ct;
+ U16 *tableU16 = ((U16 *)ptr) + 2;
+ void *FSCTptr = (U32 *)ptr + 2;
+ FSE_symbolCompressionTransform *symbolTT = (FSE_symbolCompressionTransform *)FSCTptr;
+
+ /* header */
+ tableU16[-2] = (U16)0;
+ tableU16[-1] = (U16)symbolValue;
+
+ /* Build table */
+ tableU16[0] = 0;
+ tableU16[1] = 0; /* just in case */
+
+ /* Build Symbol Transformation Table */
+ symbolTT[symbolValue].deltaNbBits = 0;
+ symbolTT[symbolValue].deltaFindState = 0;
+
+ return 0;
+}
+
+static size_t FSE_compress_usingCTable_generic(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct, const unsigned fast)
+{
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *ip = iend;
+
+ BIT_CStream_t bitC;
+ FSE_CState_t CState1, CState2;
+
+ /* init */
+ if (srcSize <= 2)
+ return 0;
+ {
+ size_t const initError = BIT_initCStream(&bitC, dst, dstSize);
+ if (FSE_isError(initError))
+ return 0; /* not enough space available to write a bitstream */
+ }
+
+#define FSE_FLUSHBITS(s) (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s))
+
+ if (srcSize & 1) {
+ FSE_initCState2(&CState1, ct, *--ip);
+ FSE_initCState2(&CState2, ct, *--ip);
+ FSE_encodeSymbol(&bitC, &CState1, *--ip);
+ FSE_FLUSHBITS(&bitC);
+ } else {
+ FSE_initCState2(&CState2, ct, *--ip);
+ FSE_initCState2(&CState1, ct, *--ip);
+ }
+
+ /* join to mod 4 */
+ srcSize -= 2;
+ if ((sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) && (srcSize & 2)) { /* test bit 2 */
+ FSE_encodeSymbol(&bitC, &CState2, *--ip);
+ FSE_encodeSymbol(&bitC, &CState1, *--ip);
+ FSE_FLUSHBITS(&bitC);
+ }
+
+ /* 2 or 4 encoding per loop */
+ while (ip > istart) {
+
+ FSE_encodeSymbol(&bitC, &CState2, *--ip);
+
+ if (sizeof(bitC.bitContainer) * 8 < FSE_MAX_TABLELOG * 2 + 7) /* this test must be static */
+ FSE_FLUSHBITS(&bitC);
+
+ FSE_encodeSymbol(&bitC, &CState1, *--ip);
+
+ if (sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) { /* this test must be static */
+ FSE_encodeSymbol(&bitC, &CState2, *--ip);
+ FSE_encodeSymbol(&bitC, &CState1, *--ip);
+ }
+
+ FSE_FLUSHBITS(&bitC);
+ }
+
+ FSE_flushCState(&bitC, &CState2);
+ FSE_flushCState(&bitC, &CState1);
+ return BIT_closeCStream(&bitC);
+}
+
+size_t FSE_compress_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct)
+{
+ unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize));
+
+ if (fast)
+ return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1);
+ else
+ return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0);
+}
+
+size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
new file mode 100644
index 0000000..a84300e
--- /dev/null
+++ b/lib/zstd/fse_decompress.c
@@ -0,0 +1,332 @@
+/*
+ * FSE : Finite State Entropy decoder
+ * Copyright (C) 2013-2015, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+
+/* **************************************************************
+* Compiler specifics
+****************************************************************/
+#define FORCE_INLINE static __always_inline
+
+/* **************************************************************
+* Includes
+****************************************************************/
+#include "bitstream.h"
+#include "fse.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/string.h> /* memcpy, memset */
+
+/* **************************************************************
+* Error Management
+****************************************************************/
+#define FSE_isError ERR_isError
+#define FSE_STATIC_ASSERT(c) \
+ { \
+ enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
+ } /* use only *after* variable declarations */
+
+/* check and forward error code */
+#define CHECK_F(f) \
+ { \
+ size_t const e = f; \
+ if (FSE_isError(e)) \
+ return e; \
+ }
+
+/* **************************************************************
+* Templates
+****************************************************************/
+/*
+ designed to be included
+ for type-specific functions (template emulation in C)
+ Objective is to write these functions only once, for improved maintenance
+*/
+
+/* safety checks */
+#ifndef FSE_FUNCTION_EXTENSION
+#error "FSE_FUNCTION_EXTENSION must be defined"
+#endif
+#ifndef FSE_FUNCTION_TYPE
+#error "FSE_FUNCTION_TYPE must be defined"
+#endif
+
+/* Function names */
+#define FSE_CAT(X, Y) X##Y
+#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y)
+#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y)
+
+/* Function templates */
+
+size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize)
+{
+ void *const tdPtr = dt + 1; /* because *dt is unsigned, 32-bits aligned on 32-bits */
+ FSE_DECODE_TYPE *const tableDecode = (FSE_DECODE_TYPE *)(tdPtr);
+ U16 *symbolNext = (U16 *)workspace;
+
+ U32 const maxSV1 = maxSymbolValue + 1;
+ U32 const tableSize = 1 << tableLog;
+ U32 highThreshold = tableSize - 1;
+
+ /* Sanity Checks */
+ if (workspaceSize < sizeof(U16) * (FSE_MAX_SYMBOL_VALUE + 1))
+ return ERROR(tableLog_tooLarge);
+ if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE)
+ return ERROR(maxSymbolValue_tooLarge);
+ if (tableLog > FSE_MAX_TABLELOG)
+ return ERROR(tableLog_tooLarge);
+
+ /* Init, lay down lowprob symbols */
+ {
+ FSE_DTableHeader DTableH;
+ DTableH.tableLog = (U16)tableLog;
+ DTableH.fastMode = 1;
+ {
+ S16 const largeLimit = (S16)(1 << (tableLog - 1));
+ U32 s;
+ for (s = 0; s < maxSV1; s++) {
+ if (normalizedCounter[s] == -1) {
+ tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s;
+ symbolNext[s] = 1;
+ } else {
+ if (normalizedCounter[s] >= largeLimit)
+ DTableH.fastMode = 0;
+ symbolNext[s] = normalizedCounter[s];
+ }
+ }
+ }
+ memcpy(dt, &DTableH, sizeof(DTableH));
+ }
+
+ /* Spread symbols */
+ {
+ U32 const tableMask = tableSize - 1;
+ U32 const step = FSE_TABLESTEP(tableSize);
+ U32 s, position = 0;
+ for (s = 0; s < maxSV1; s++) {
+ int i;
+ for (i = 0; i < normalizedCounter[s]; i++) {
+ tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s;
+ position = (position + step) & tableMask;
+ while (position > highThreshold)
+ position = (position + step) & tableMask; /* lowprob area */
+ }
+ }
+ if (position != 0)
+ return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
+ }
+
+ /* Build Decoding table */
+ {
+ U32 u;
+ for (u = 0; u < tableSize; u++) {
+ FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol);
+ U16 nextState = symbolNext[symbol]++;
+ tableDecode[u].nbBits = (BYTE)(tableLog - BIT_highbit32((U32)nextState));
+ tableDecode[u].newState = (U16)((nextState << tableDecode[u].nbBits) - tableSize);
+ }
+ }
+
+ return 0;
+}
+
+/*-*******************************************************
+* Decompression (Byte symbols)
+*********************************************************/
+size_t FSE_buildDTable_rle(FSE_DTable *dt, BYTE symbolValue)
+{
+ void *ptr = dt;
+ FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr;
+ void *dPtr = dt + 1;
+ FSE_decode_t *const cell = (FSE_decode_t *)dPtr;
+
+ DTableH->tableLog = 0;
+ DTableH->fastMode = 0;
+
+ cell->newState = 0;
+ cell->symbol = symbolValue;
+ cell->nbBits = 0;
+
+ return 0;
+}
+
+size_t FSE_buildDTable_raw(FSE_DTable *dt, unsigned nbBits)
+{
+ void *ptr = dt;
+ FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr;
+ void *dPtr = dt + 1;
+ FSE_decode_t *const dinfo = (FSE_decode_t *)dPtr;
+ const unsigned tableSize = 1 << nbBits;
+ const unsigned tableMask = tableSize - 1;
+ const unsigned maxSV1 = tableMask + 1;
+ unsigned s;
+
+ /* Sanity checks */
+ if (nbBits < 1)
+ return ERROR(GENERIC); /* min size */
+
+ /* Build Decoding Table */
+ DTableH->tableLog = (U16)nbBits;
+ DTableH->fastMode = 1;
+ for (s = 0; s < maxSV1; s++) {
+ dinfo[s].newState = 0;
+ dinfo[s].symbol = (BYTE)s;
+ dinfo[s].nbBits = (BYTE)nbBits;
+ }
+
+ return 0;
+}
+
+FORCE_INLINE size_t FSE_decompress_usingDTable_generic(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt,
+ const unsigned fast)
+{
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *op = ostart;
+ BYTE *const omax = op + maxDstSize;
+ BYTE *const olimit = omax - 3;
+
+ BIT_DStream_t bitD;
+ FSE_DState_t state1;
+ FSE_DState_t state2;
+
+ /* Init */
+ CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize));
+
+ FSE_initDState(&state1, &bitD, dt);
+ FSE_initDState(&state2, &bitD, dt);
+
+#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
+
+ /* 4 symbols per loop */
+ for (; (BIT_reloadDStream(&bitD) == BIT_DStream_unfinished) & (op < olimit); op += 4) {
+ op[0] = FSE_GETSYMBOL(&state1);
+
+ if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
+ BIT_reloadDStream(&bitD);
+
+ op[1] = FSE_GETSYMBOL(&state2);
+
+ if (FSE_MAX_TABLELOG * 4 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
+ {
+ if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) {
+ op += 2;
+ break;
+ }
+ }
+
+ op[2] = FSE_GETSYMBOL(&state1);
+
+ if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
+ BIT_reloadDStream(&bitD);
+
+ op[3] = FSE_GETSYMBOL(&state2);
+ }
+
+ /* tail */
+ /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */
+ while (1) {
+ if (op > (omax - 2))
+ return ERROR(dstSize_tooSmall);
+ *op++ = FSE_GETSYMBOL(&state1);
+ if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) {
+ *op++ = FSE_GETSYMBOL(&state2);
+ break;
+ }
+
+ if (op > (omax - 2))
+ return ERROR(dstSize_tooSmall);
+ *op++ = FSE_GETSYMBOL(&state2);
+ if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) {
+ *op++ = FSE_GETSYMBOL(&state1);
+ break;
+ }
+ }
+
+ return op - ostart;
+}
+
+size_t FSE_decompress_usingDTable(void *dst, size_t originalSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt)
+{
+ const void *ptr = dt;
+ const FSE_DTableHeader *DTableH = (const FSE_DTableHeader *)ptr;
+ const U32 fastMode = DTableH->fastMode;
+
+ /* select fast mode (static) */
+ if (fastMode)
+ return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1);
+ return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0);
+}
+
+size_t FSE_decompress_wksp(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, unsigned maxLog, void *workspace, size_t workspaceSize)
+{
+ const BYTE *const istart = (const BYTE *)cSrc;
+ const BYTE *ip = istart;
+ unsigned tableLog;
+ unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
+ size_t NCountLength;
+
+ FSE_DTable *dt;
+ short *counting;
+ size_t spaceUsed32 = 0;
+
+ FSE_STATIC_ASSERT(sizeof(FSE_DTable) == sizeof(U32));
+
+ dt = (FSE_DTable *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += FSE_DTABLE_SIZE_U32(maxLog);
+ counting = (short *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(sizeof(short) * (FSE_MAX_SYMBOL_VALUE + 1), sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ /* normal FSE decoding mode */
+ NCountLength = FSE_readNCount(counting, &maxSymbolValue, &tableLog, istart, cSrcSize);
+ if (FSE_isError(NCountLength))
+ return NCountLength;
+ // if (NCountLength >= cSrcSize) return ERROR(srcSize_wrong); /* too small input size; supposed to be already checked in NCountLength, only remaining
+ // case : NCountLength==cSrcSize */
+ if (tableLog > maxLog)
+ return ERROR(tableLog_tooLarge);
+ ip += NCountLength;
+ cSrcSize -= NCountLength;
+
+ CHECK_F(FSE_buildDTable_wksp(dt, counting, maxSymbolValue, tableLog, workspace, workspaceSize));
+
+ return FSE_decompress_usingDTable(dst, dstCapacity, ip, cSrcSize, dt); /* always return, even if it is an error code */
+}
diff --git a/lib/zstd/huf.h b/lib/zstd/huf.h
new file mode 100644
index 0000000..2143da2
--- /dev/null
+++ b/lib/zstd/huf.h
@@ -0,0 +1,212 @@
+/*
+ * Huffman coder, part of New Generation Entropy library
+ * header file
+ * Copyright (C) 2013-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+#ifndef HUF_H_298734234
+#define HUF_H_298734234
+
+/* *** Dependencies *** */
+#include <linux/types.h> /* size_t */
+
+/* *** Tool functions *** */
+#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
+size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
+
+/* Error Management */
+unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
+
+/* *** Advanced function *** */
+
+/** HUF_compress4X_wksp() :
+* Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */
+size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
+ size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
+
+/* *** Dependencies *** */
+#include "mem.h" /* U32 */
+
+/* *** Constants *** */
+#define HUF_TABLELOG_MAX 12 /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
+#define HUF_TABLELOG_DEFAULT 11 /* tableLog by default, when not specified */
+#define HUF_SYMBOLVALUE_MAX 255
+
+#define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
+#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
+#error "HUF_TABLELOG_MAX is too large !"
+#endif
+
+/* ****************************************
+* Static allocation
+******************************************/
+/* HUF buffer bounds */
+#define HUF_CTABLEBOUND 129
+#define HUF_BLOCKBOUND(size) (size + (size >> 8) + 8) /* only true if incompressible pre-filtered with fast heuristic */
+#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
+
+/* static allocation of HUF's Compression Table */
+#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \
+ U32 name##hb[maxSymbolValue + 1]; \
+ void *name##hv = &(name##hb); \
+ HUF_CElt *name = (HUF_CElt *)(name##hv) /* no final ; */
+
+/* static allocation of HUF's DTable */
+typedef U32 HUF_DTable;
+#define HUF_DTABLE_SIZE(maxTableLog) (1 + (1 << (maxTableLog)))
+#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = {((U32)((maxTableLog)-1) * 0x01000001)}
+#define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = {((U32)(maxTableLog)*0x01000001)}
+
+/* The workspace must have alignment at least 4 and be at least this large */
+#define HUF_COMPRESS_WORKSPACE_SIZE (6 << 10)
+#define HUF_COMPRESS_WORKSPACE_SIZE_U32 (HUF_COMPRESS_WORKSPACE_SIZE / sizeof(U32))
+
+/* The workspace must have alignment at least 4 and be at least this large */
+#define HUF_DECOMPRESS_WORKSPACE_SIZE (3 << 10)
+#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
+
+/* ****************************************
+* Advanced decompression functions
+******************************************/
+size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize); /**< decodes RLE and uncompressed */
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
+ size_t workspaceSize); /**< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
+ size_t workspaceSize); /**< single-symbol decoder */
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
+ size_t workspaceSize); /**< double-symbols decoder */
+
+/* ****************************************
+* HUF detailed API
+******************************************/
+/*!
+HUF_compress() does the following:
+1. count symbol occurrence from source[] into table count[] using FSE_count()
+2. (optional) refine tableLog using HUF_optimalTableLog()
+3. build Huffman table from count using HUF_buildCTable()
+4. save Huffman table to memory buffer using HUF_writeCTable_wksp()
+5. encode the data stream using HUF_compress4X_usingCTable()
+
+The following API allows targeting specific sub-functions for advanced tasks.
+For example, it's possible to compress several blocks using the same 'CTable',
+or to save and regenerate 'CTable' using external methods.
+*/
+/* FSE_count() : find it within "fse.h" */
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */
+size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, unsigned maxSymbolValue, unsigned huffLog, void *workspace, size_t workspaceSize);
+size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
+
+typedef enum {
+ HUF_repeat_none, /**< Cannot use the previous table */
+ HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
+ 4}X_repeat */
+ HUF_repeat_valid /**< Can use the previous table and it is asumed to be valid */
+} HUF_repeat;
+/** HUF_compress4X_repeat() :
+* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+* If it uses hufTable it does not modify hufTable or repeat.
+* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+* If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
+ size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
+ int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
+
+/** HUF_buildCTable_wksp() :
+ * Same as HUF_buildCTable(), but using externally allocated scratch buffer.
+ * `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned.
+ */
+size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize);
+
+/*! HUF_readStats() :
+ Read compact Huffman tree, saved by HUF_writeCTable().
+ `huffWeight` is destination buffer.
+ @return : size read from `src` , or an error Code .
+ Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */
+size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize,
+ void *workspace, size_t workspaceSize);
+
+/** HUF_readCTable() :
+* Loading a CTable saved with HUF_writeCTable() */
+size_t HUF_readCTable_wksp(HUF_CElt *CTable, unsigned maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
+
+/*
+HUF_decompress() does the following:
+1. select the decompression algorithm (X2, X4) based on pre-computed heuristics
+2. build Huffman table from save, using HUF_readDTableXn()
+3. decode 1 or 4 segments in parallel using HUF_decompressSXn_usingDTable
+*/
+
+/** HUF_selectDecoder() :
+* Tells which decoder is likely to decode faster,
+* based on a set of pre-determined metrics.
+* @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
+* Assumption : 0 < cSrcSize < dstSize <= 128 KB */
+U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize);
+
+size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
+size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
+
+size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
+size_t HUF_decompress4X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
+size_t HUF_decompress4X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
+
+/* single stream variants */
+
+size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
+ size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
+size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
+/** HUF_compress1X_repeat() :
+* Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+* If it uses hufTable it does not modify hufTable or repeat.
+* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+* If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
+ size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
+ int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
+
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize);
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
+ size_t workspaceSize); /**< single-symbol decoder */
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
+ size_t workspaceSize); /**< double-symbols decoder */
+
+size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize,
+ const HUF_DTable *DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
+size_t HUF_decompress1X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
+size_t HUF_decompress1X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
+
+#endif /* HUF_H_298734234 */
diff --git a/lib/zstd/huf_compress.c b/lib/zstd/huf_compress.c
new file mode 100644
index 0000000..40055a7
--- /dev/null
+++ b/lib/zstd/huf_compress.c
@@ -0,0 +1,770 @@
+/*
+ * Huffman encoder, part of New Generation Entropy library
+ * Copyright (C) 2013-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+
+/* **************************************************************
+* Includes
+****************************************************************/
+#include "bitstream.h"
+#include "fse.h" /* header compression */
+#include "huf.h"
+#include <linux/kernel.h>
+#include <linux/string.h> /* memcpy, memset */
+
+/* **************************************************************
+* Error Management
+****************************************************************/
+#define HUF_STATIC_ASSERT(c) \
+ { \
+ enum { HUF_static_assert = 1 / (int)(!!(c)) }; \
+ } /* use only *after* variable declarations */
+#define CHECK_V_F(e, f) \
+ size_t const e = f; \
+ if (ERR_isError(e)) \
+ return f
+#define CHECK_F(f) \
+ { \
+ CHECK_V_F(_var_err__, f); \
+ }
+
+/* **************************************************************
+* Utils
+****************************************************************/
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
+{
+ return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 1);
+}
+
+/* *******************************************************
+* HUF : Huffman block compression
+*********************************************************/
+/* HUF_compressWeights() :
+ * Same as FSE_compress(), but dedicated to huff0's weights compression.
+ * The use case needs much less stack memory.
+ * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
+ */
+#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
+size_t HUF_compressWeights_wksp(void *dst, size_t dstSize, const void *weightTable, size_t wtSize, void *workspace, size_t workspaceSize)
+{
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *op = ostart;
+ BYTE *const oend = ostart + dstSize;
+
+ U32 maxSymbolValue = HUF_TABLELOG_MAX;
+ U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER;
+
+ FSE_CTable *CTable;
+ U32 *count;
+ S16 *norm;
+ size_t spaceUsed32 = 0;
+
+ HUF_STATIC_ASSERT(sizeof(FSE_CTable) == sizeof(U32));
+
+ CTable = (FSE_CTable *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX);
+ count = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_MAX + 1;
+ norm = (S16 *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(sizeof(S16) * (HUF_TABLELOG_MAX + 1), sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ /* init conditions */
+ if (wtSize <= 1)
+ return 0; /* Not compressible */
+
+ /* Scan input and build symbol stats */
+ {
+ CHECK_V_F(maxCount, FSE_count_simple(count, &maxSymbolValue, weightTable, wtSize));
+ if (maxCount == wtSize)
+ return 1; /* only a single symbol in src : rle */
+ if (maxCount == 1)
+ return 0; /* each symbol present maximum once => not compressible */
+ }
+
+ tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
+ CHECK_F(FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue));
+
+ /* Write table description header */
+ {
+ CHECK_V_F(hSize, FSE_writeNCount(op, oend - op, norm, maxSymbolValue, tableLog));
+ op += hSize;
+ }
+
+ /* Compress */
+ CHECK_F(FSE_buildCTable_wksp(CTable, norm, maxSymbolValue, tableLog, workspace, workspaceSize));
+ {
+ CHECK_V_F(cSize, FSE_compress_usingCTable(op, oend - op, weightTable, wtSize, CTable));
+ if (cSize == 0)
+ return 0; /* not enough space for compressed data */
+ op += cSize;
+ }
+
+ return op - ostart;
+}
+
+struct HUF_CElt_s {
+ U16 val;
+ BYTE nbBits;
+}; /* typedef'd to HUF_CElt within "huf.h" */
+
+/*! HUF_writeCTable_wksp() :
+ `CTable` : Huffman tree to save, using huf representation.
+ @return : size of saved CTable */
+size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, U32 maxSymbolValue, U32 huffLog, void *workspace, size_t workspaceSize)
+{
+ BYTE *op = (BYTE *)dst;
+ U32 n;
+
+ BYTE *bitsToWeight;
+ BYTE *huffWeight;
+ size_t spaceUsed32 = 0;
+
+ bitsToWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(HUF_TABLELOG_MAX + 1, sizeof(U32)) >> 2;
+ huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ /* check conditions */
+ if (maxSymbolValue > HUF_SYMBOLVALUE_MAX)
+ return ERROR(maxSymbolValue_tooLarge);
+
+ /* convert to weight */
+ bitsToWeight[0] = 0;
+ for (n = 1; n < huffLog + 1; n++)
+ bitsToWeight[n] = (BYTE)(huffLog + 1 - n);
+ for (n = 0; n < maxSymbolValue; n++)
+ huffWeight[n] = bitsToWeight[CTable[n].nbBits];
+
+ /* attempt weights compression by FSE */
+ {
+ CHECK_V_F(hSize, HUF_compressWeights_wksp(op + 1, maxDstSize - 1, huffWeight, maxSymbolValue, workspace, workspaceSize));
+ if ((hSize > 1) & (hSize < maxSymbolValue / 2)) { /* FSE compressed */
+ op[0] = (BYTE)hSize;
+ return hSize + 1;
+ }
+ }
+
+ /* write raw values as 4-bits (max : 15) */
+ if (maxSymbolValue > (256 - 128))
+ return ERROR(GENERIC); /* should not happen : likely means source cannot be compressed */
+ if (((maxSymbolValue + 1) / 2) + 1 > maxDstSize)
+ return ERROR(dstSize_tooSmall); /* not enough space within dst buffer */
+ op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue - 1));
+ huffWeight[maxSymbolValue] = 0; /* to be sure it doesn't cause msan issue in final combination */
+ for (n = 0; n < maxSymbolValue; n += 2)
+ op[(n / 2) + 1] = (BYTE)((huffWeight[n] << 4) + huffWeight[n + 1]);
+ return ((maxSymbolValue + 1) / 2) + 1;
+}
+
+size_t HUF_readCTable_wksp(HUF_CElt *CTable, U32 maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
+{
+ U32 *rankVal;
+ BYTE *huffWeight;
+ U32 tableLog = 0;
+ U32 nbSymbols = 0;
+ size_t readSize;
+ size_t spaceUsed32 = 0;
+
+ rankVal = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+ huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ /* get symbol weights */
+ readSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
+ if (ERR_isError(readSize))
+ return readSize;
+
+ /* check result */
+ if (tableLog > HUF_TABLELOG_MAX)
+ return ERROR(tableLog_tooLarge);
+ if (nbSymbols > maxSymbolValue + 1)
+ return ERROR(maxSymbolValue_tooSmall);
+
+ /* Prepare base value per rank */
+ {
+ U32 n, nextRankStart = 0;
+ for (n = 1; n <= tableLog; n++) {
+ U32 curr = nextRankStart;
+ nextRankStart += (rankVal[n] << (n - 1));
+ rankVal[n] = curr;
+ }
+ }
+
+ /* fill nbBits */
+ {
+ U32 n;
+ for (n = 0; n < nbSymbols; n++) {
+ const U32 w = huffWeight[n];
+ CTable[n].nbBits = (BYTE)(tableLog + 1 - w);
+ }
+ }
+
+ /* fill val */
+ {
+ U16 nbPerRank[HUF_TABLELOG_MAX + 2] = {0}; /* support w=0=>n=tableLog+1 */
+ U16 valPerRank[HUF_TABLELOG_MAX + 2] = {0};
+ {
+ U32 n;
+ for (n = 0; n < nbSymbols; n++)
+ nbPerRank[CTable[n].nbBits]++;
+ }
+ /* determine stating value per rank */
+ valPerRank[tableLog + 1] = 0; /* for w==0 */
+ {
+ U16 min = 0;
+ U32 n;
+ for (n = tableLog; n > 0; n--) { /* start at n=tablelog <-> w=1 */
+ valPerRank[n] = min; /* get starting value within each rank */
+ min += nbPerRank[n];
+ min >>= 1;
+ }
+ }
+ /* assign value within rank, symbol order */
+ {
+ U32 n;
+ for (n = 0; n <= maxSymbolValue; n++)
+ CTable[n].val = valPerRank[CTable[n].nbBits]++;
+ }
+ }
+
+ return readSize;
+}
+
+typedef struct nodeElt_s {
+ U32 count;
+ U16 parent;
+ BYTE byte;
+ BYTE nbBits;
+} nodeElt;
+
+static U32 HUF_setMaxHeight(nodeElt *huffNode, U32 lastNonNull, U32 maxNbBits)
+{
+ const U32 largestBits = huffNode[lastNonNull].nbBits;
+ if (largestBits <= maxNbBits)
+ return largestBits; /* early exit : no elt > maxNbBits */
+
+ /* there are several too large elements (at least >= 2) */
+ {
+ int totalCost = 0;
+ const U32 baseCost = 1 << (largestBits - maxNbBits);
+ U32 n = lastNonNull;
+
+ while (huffNode[n].nbBits > maxNbBits) {
+ totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits));
+ huffNode[n].nbBits = (BYTE)maxNbBits;
+ n--;
+ } /* n stops at huffNode[n].nbBits <= maxNbBits */
+ while (huffNode[n].nbBits == maxNbBits)
+ n--; /* n end at index of smallest symbol using < maxNbBits */
+
+ /* renorm totalCost */
+ totalCost >>= (largestBits - maxNbBits); /* note : totalCost is necessarily a multiple of baseCost */
+
+ /* repay normalized cost */
+ {
+ U32 const noSymbol = 0xF0F0F0F0;
+ U32 rankLast[HUF_TABLELOG_MAX + 2];
+ int pos;
+
+ /* Get pos of last (smallest) symbol per rank */
+ memset(rankLast, 0xF0, sizeof(rankLast));
+ {
+ U32 currNbBits = maxNbBits;
+ for (pos = n; pos >= 0; pos--) {
+ if (huffNode[pos].nbBits >= currNbBits)
+ continue;
+ currNbBits = huffNode[pos].nbBits; /* < maxNbBits */
+ rankLast[maxNbBits - currNbBits] = pos;
+ }
+ }
+
+ while (totalCost > 0) {
+ U32 nBitsToDecrease = BIT_highbit32(totalCost) + 1;
+ for (; nBitsToDecrease > 1; nBitsToDecrease--) {
+ U32 highPos = rankLast[nBitsToDecrease];
+ U32 lowPos = rankLast[nBitsToDecrease - 1];
+ if (highPos == noSymbol)
+ continue;
+ if (lowPos == noSymbol)
+ break;
+ {
+ U32 const highTotal = huffNode[highPos].count;
+ U32 const lowTotal = 2 * huffNode[lowPos].count;
+ if (highTotal <= lowTotal)
+ break;
+ }
+ }
+ /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */
+ /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+ while ((nBitsToDecrease <= HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))
+ nBitsToDecrease++;
+ totalCost -= 1 << (nBitsToDecrease - 1);
+ if (rankLast[nBitsToDecrease - 1] == noSymbol)
+ rankLast[nBitsToDecrease - 1] = rankLast[nBitsToDecrease]; /* this rank is no longer empty */
+ huffNode[rankLast[nBitsToDecrease]].nbBits++;
+ if (rankLast[nBitsToDecrease] == 0) /* special case, reached largest symbol */
+ rankLast[nBitsToDecrease] = noSymbol;
+ else {
+ rankLast[nBitsToDecrease]--;
+ if (huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits - nBitsToDecrease)
+ rankLast[nBitsToDecrease] = noSymbol; /* this rank is now empty */
+ }
+ } /* while (totalCost > 0) */
+
+ while (totalCost < 0) { /* Sometimes, cost correction overshoot */
+ if (rankLast[1] == noSymbol) { /* special case : no rank 1 symbol (using maxNbBits-1); let's create one from largest rank 0
+ (using maxNbBits) */
+ while (huffNode[n].nbBits == maxNbBits)
+ n--;
+ huffNode[n + 1].nbBits--;
+ rankLast[1] = n + 1;
+ totalCost++;
+ continue;
+ }
+ huffNode[rankLast[1] + 1].nbBits--;
+ rankLast[1]++;
+ totalCost++;
+ }
+ }
+ } /* there are several too large elements (at least >= 2) */
+
+ return maxNbBits;
+}
+
+typedef struct {
+ U32 base;
+ U32 curr;
+} rankPos;
+
+static void HUF_sort(nodeElt *huffNode, const U32 *count, U32 maxSymbolValue)
+{
+ rankPos rank[32];
+ U32 n;
+
+ memset(rank, 0, sizeof(rank));
+ for (n = 0; n <= maxSymbolValue; n++) {
+ U32 r = BIT_highbit32(count[n] + 1);
+ rank[r].base++;
+ }
+ for (n = 30; n > 0; n--)
+ rank[n - 1].base += rank[n].base;
+ for (n = 0; n < 32; n++)
+ rank[n].curr = rank[n].base;
+ for (n = 0; n <= maxSymbolValue; n++) {
+ U32 const c = count[n];
+ U32 const r = BIT_highbit32(c + 1) + 1;
+ U32 pos = rank[r].curr++;
+ while ((pos > rank[r].base) && (c > huffNode[pos - 1].count))
+ huffNode[pos] = huffNode[pos - 1], pos--;
+ huffNode[pos].count = c;
+ huffNode[pos].byte = (BYTE)n;
+ }
+}
+
+/** HUF_buildCTable_wksp() :
+ * Same as HUF_buildCTable(), but using externally allocated scratch buffer.
+ * `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned.
+ */
+#define STARTNODE (HUF_SYMBOLVALUE_MAX + 1)
+typedef nodeElt huffNodeTable[2 * HUF_SYMBOLVALUE_MAX + 1 + 1];
+size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize)
+{
+ nodeElt *const huffNode0 = (nodeElt *)workSpace;
+ nodeElt *const huffNode = huffNode0 + 1;
+ U32 n, nonNullRank;
+ int lowS, lowN;
+ U16 nodeNb = STARTNODE;
+ U32 nodeRoot;
+
+ /* safety checks */
+ if (wkspSize < sizeof(huffNodeTable))
+ return ERROR(GENERIC); /* workSpace is not large enough */
+ if (maxNbBits == 0)
+ maxNbBits = HUF_TABLELOG_DEFAULT;
+ if (maxSymbolValue > HUF_SYMBOLVALUE_MAX)
+ return ERROR(GENERIC);
+ memset(huffNode0, 0, sizeof(huffNodeTable));
+
+ /* sort, decreasing order */
+ HUF_sort(huffNode, count, maxSymbolValue);
+
+ /* init for parents */
+ nonNullRank = maxSymbolValue;
+ while (huffNode[nonNullRank].count == 0)
+ nonNullRank--;
+ lowS = nonNullRank;
+ nodeRoot = nodeNb + lowS - 1;
+ lowN = nodeNb;
+ huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS - 1].count;
+ huffNode[lowS].parent = huffNode[lowS - 1].parent = nodeNb;
+ nodeNb++;
+ lowS -= 2;
+ for (n = nodeNb; n <= nodeRoot; n++)
+ huffNode[n].count = (U32)(1U << 30);
+ huffNode0[0].count = (U32)(1U << 31); /* fake entry, strong barrier */
+
+ /* create parents */
+ while (nodeNb <= nodeRoot) {
+ U32 n1 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
+ U32 n2 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
+ huffNode[nodeNb].count = huffNode[n1].count + huffNode[n2].count;
+ huffNode[n1].parent = huffNode[n2].parent = nodeNb;
+ nodeNb++;
+ }
+
+ /* distribute weights (unlimited tree height) */
+ huffNode[nodeRoot].nbBits = 0;
+ for (n = nodeRoot - 1; n >= STARTNODE; n--)
+ huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1;
+ for (n = 0; n <= nonNullRank; n++)
+ huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1;
+
+ /* enforce maxTableLog */
+ maxNbBits = HUF_setMaxHeight(huffNode, nonNullRank, maxNbBits);
+
+ /* fill result into tree (val, nbBits) */
+ {
+ U16 nbPerRank[HUF_TABLELOG_MAX + 1] = {0};
+ U16 valPerRank[HUF_TABLELOG_MAX + 1] = {0};
+ if (maxNbBits > HUF_TABLELOG_MAX)
+ return ERROR(GENERIC); /* check fit into table */
+ for (n = 0; n <= nonNullRank; n++)
+ nbPerRank[huffNode[n].nbBits]++;
+ /* determine stating value per rank */
+ {
+ U16 min = 0;
+ for (n = maxNbBits; n > 0; n--) {
+ valPerRank[n] = min; /* get starting value within each rank */
+ min += nbPerRank[n];
+ min >>= 1;
+ }
+ }
+ for (n = 0; n <= maxSymbolValue; n++)
+ tree[huffNode[n].byte].nbBits = huffNode[n].nbBits; /* push nbBits per symbol, symbol order */
+ for (n = 0; n <= maxSymbolValue; n++)
+ tree[n].val = valPerRank[tree[n].nbBits]++; /* assign value within rank, symbol order */
+ }
+
+ return maxNbBits;
+}
+
+static size_t HUF_estimateCompressedSize(HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue)
+{
+ size_t nbBits = 0;
+ int s;
+ for (s = 0; s <= (int)maxSymbolValue; ++s) {
+ nbBits += CTable[s].nbBits * count[s];
+ }
+ return nbBits >> 3;
+}
+
+static int HUF_validateCTable(const HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue)
+{
+ int bad = 0;
+ int s;
+ for (s = 0; s <= (int)maxSymbolValue; ++s) {
+ bad |= (count[s] != 0) & (CTable[s].nbBits == 0);
+ }
+ return !bad;
+}
+
+static void HUF_encodeSymbol(BIT_CStream_t *bitCPtr, U32 symbol, const HUF_CElt *CTable)
+{
+ BIT_addBitsFast(bitCPtr, CTable[symbol].val, CTable[symbol].nbBits);
+}
+
+size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); }
+
+#define HUF_FLUSHBITS(s) BIT_flushBits(s)
+
+#define HUF_FLUSHBITS_1(stream) \
+ if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 2 + 7) \
+ HUF_FLUSHBITS(stream)
+
+#define HUF_FLUSHBITS_2(stream) \
+ if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 4 + 7) \
+ HUF_FLUSHBITS(stream)
+
+size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable)
+{
+ const BYTE *ip = (const BYTE *)src;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ BYTE *op = ostart;
+ size_t n;
+ BIT_CStream_t bitC;
+
+ /* init */
+ if (dstSize < 8)
+ return 0; /* not enough space to compress */
+ {
+ size_t const initErr = BIT_initCStream(&bitC, op, oend - op);
+ if (HUF_isError(initErr))
+ return 0;
+ }
+
+ n = srcSize & ~3; /* join to mod 4 */
+ switch (srcSize & 3) {
+ case 3: HUF_encodeSymbol(&bitC, ip[n + 2], CTable); HUF_FLUSHBITS_2(&bitC);
+ case 2: HUF_encodeSymbol(&bitC, ip[n + 1], CTable); HUF_FLUSHBITS_1(&bitC);
+ case 1: HUF_encodeSymbol(&bitC, ip[n + 0], CTable); HUF_FLUSHBITS(&bitC);
+ case 0:
+ default:;
+ }
+
+ for (; n > 0; n -= 4) { /* note : n&3==0 at this stage */
+ HUF_encodeSymbol(&bitC, ip[n - 1], CTable);
+ HUF_FLUSHBITS_1(&bitC);
+ HUF_encodeSymbol(&bitC, ip[n - 2], CTable);
+ HUF_FLUSHBITS_2(&bitC);
+ HUF_encodeSymbol(&bitC, ip[n - 3], CTable);
+ HUF_FLUSHBITS_1(&bitC);
+ HUF_encodeSymbol(&bitC, ip[n - 4], CTable);
+ HUF_FLUSHBITS(&bitC);
+ }
+
+ return BIT_closeCStream(&bitC);
+}
+
+size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable)
+{
+ size_t const segmentSize = (srcSize + 3) / 4; /* first 3 segments */
+ const BYTE *ip = (const BYTE *)src;
+ const BYTE *const iend = ip + srcSize;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ BYTE *op = ostart;
+
+ if (dstSize < 6 + 1 + 1 + 1 + 8)
+ return 0; /* minimum space to compress successfully */
+ if (srcSize < 12)
+ return 0; /* no saving possible : too small input */
+ op += 6; /* jumpTable */
+
+ {
+ CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
+ if (cSize == 0)
+ return 0;
+ ZSTD_writeLE16(ostart, (U16)cSize);
+ op += cSize;
+ }
+
+ ip += segmentSize;
+ {
+ CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
+ if (cSize == 0)
+ return 0;
+ ZSTD_writeLE16(ostart + 2, (U16)cSize);
+ op += cSize;
+ }
+
+ ip += segmentSize;
+ {
+ CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
+ if (cSize == 0)
+ return 0;
+ ZSTD_writeLE16(ostart + 4, (U16)cSize);
+ op += cSize;
+ }
+
+ ip += segmentSize;
+ {
+ CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, iend - ip, CTable));
+ if (cSize == 0)
+ return 0;
+ op += cSize;
+ }
+
+ return op - ostart;
+}
+
+static size_t HUF_compressCTable_internal(BYTE *const ostart, BYTE *op, BYTE *const oend, const void *src, size_t srcSize, unsigned singleStream,
+ const HUF_CElt *CTable)
+{
+ size_t const cSize =
+ singleStream ? HUF_compress1X_usingCTable(op, oend - op, src, srcSize, CTable) : HUF_compress4X_usingCTable(op, oend - op, src, srcSize, CTable);
+ if (HUF_isError(cSize)) {
+ return cSize;
+ }
+ if (cSize == 0) {
+ return 0;
+ } /* uncompressible */
+ op += cSize;
+ /* check compressibility */
+ if ((size_t)(op - ostart) >= srcSize - 1) {
+ return 0;
+ }
+ return op - ostart;
+}
+
+/* `workSpace` must a table of at least 1024 unsigned */
+static size_t HUF_compress_internal(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog,
+ unsigned singleStream, void *workSpace, size_t wkspSize, HUF_CElt *oldHufTable, HUF_repeat *repeat, int preferRepeat)
+{
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ BYTE *op = ostart;
+
+ U32 *count;
+ size_t const countSize = sizeof(U32) * (HUF_SYMBOLVALUE_MAX + 1);
+ HUF_CElt *CTable;
+ size_t const CTableSize = sizeof(HUF_CElt) * (HUF_SYMBOLVALUE_MAX + 1);
+
+ /* checks & inits */
+ if (wkspSize < sizeof(huffNodeTable) + countSize + CTableSize)
+ return ERROR(GENERIC);
+ if (!srcSize)
+ return 0; /* Uncompressed (note : 1 means rle, so first byte must be correct) */
+ if (!dstSize)
+ return 0; /* cannot fit within dst budget */
+ if (srcSize > HUF_BLOCKSIZE_MAX)
+ return ERROR(srcSize_wrong); /* curr block size limit */
+ if (huffLog > HUF_TABLELOG_MAX)
+ return ERROR(tableLog_tooLarge);
+ if (!maxSymbolValue)
+ maxSymbolValue = HUF_SYMBOLVALUE_MAX;
+ if (!huffLog)
+ huffLog = HUF_TABLELOG_DEFAULT;
+
+ count = (U32 *)workSpace;
+ workSpace = (BYTE *)workSpace + countSize;
+ wkspSize -= countSize;
+ CTable = (HUF_CElt *)workSpace;
+ workSpace = (BYTE *)workSpace + CTableSize;
+ wkspSize -= CTableSize;
+
+ /* Heuristic : If we don't need to check the validity of the old table use the old table for small inputs */
+ if (preferRepeat && repeat && *repeat == HUF_repeat_valid) {
+ return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
+ }
+
+ /* Scan input and build symbol stats */
+ {
+ CHECK_V_F(largest, FSE_count_wksp(count, &maxSymbolValue, (const BYTE *)src, srcSize, (U32 *)workSpace));
+ if (largest == srcSize) {
+ *ostart = ((const BYTE *)src)[0];
+ return 1;
+ } /* single symbol, rle */
+ if (largest <= (srcSize >> 7) + 1)
+ return 0; /* Fast heuristic : not compressible enough */
+ }
+
+ /* Check validity of previous table */
+ if (repeat && *repeat == HUF_repeat_check && !HUF_validateCTable(oldHufTable, count, maxSymbolValue)) {
+ *repeat = HUF_repeat_none;
+ }
+ /* Heuristic : use existing table for small inputs */
+ if (preferRepeat && repeat && *repeat != HUF_repeat_none) {
+ return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
+ }
+
+ /* Build Huffman Tree */
+ huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
+ {
+ CHECK_V_F(maxBits, HUF_buildCTable_wksp(CTable, count, maxSymbolValue, huffLog, workSpace, wkspSize));
+ huffLog = (U32)maxBits;
+ /* Zero the unused symbols so we can check it for validity */
+ memset(CTable + maxSymbolValue + 1, 0, CTableSize - (maxSymbolValue + 1) * sizeof(HUF_CElt));
+ }
+
+ /* Write table description header */
+ {
+ CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, CTable, maxSymbolValue, huffLog, workSpace, wkspSize));
+ /* Check if using the previous table will be beneficial */
+ if (repeat && *repeat != HUF_repeat_none) {
+ size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, count, maxSymbolValue);
+ size_t const newSize = HUF_estimateCompressedSize(CTable, count, maxSymbolValue);
+ if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) {
+ return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
+ }
+ }
+ /* Use the new table */
+ if (hSize + 12ul >= srcSize) {
+ return 0;
+ }
+ op += hSize;
+ if (repeat) {
+ *repeat = HUF_repeat_none;
+ }
+ if (oldHufTable) {
+ memcpy(oldHufTable, CTable, CTableSize);
+ } /* Save the new table */
+ }
+ return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, CTable);
+}
+
+size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
+ size_t wkspSize)
+{
+ return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, NULL, NULL, 0);
+}
+
+size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
+ size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat)
+{
+ return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, hufTable, repeat,
+ preferRepeat);
+}
+
+size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
+ size_t wkspSize)
+{
+ return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, NULL, NULL, 0);
+}
+
+size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
+ size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat)
+{
+ return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, hufTable, repeat,
+ preferRepeat);
+}
diff --git a/lib/zstd/huf_decompress.c b/lib/zstd/huf_decompress.c
new file mode 100644
index 0000000..6526482
--- /dev/null
+++ b/lib/zstd/huf_decompress.c
@@ -0,0 +1,960 @@
+/*
+ * Huffman decoder, part of New Generation Entropy library
+ * Copyright (C) 2013-2016, Yann Collet.
+ *
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ */
+
+/* **************************************************************
+* Compiler specifics
+****************************************************************/
+#define FORCE_INLINE static __always_inline
+
+/* **************************************************************
+* Dependencies
+****************************************************************/
+#include "bitstream.h" /* BIT_* */
+#include "fse.h" /* header compression */
+#include "huf.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/string.h> /* memcpy, memset */
+
+/* **************************************************************
+* Error Management
+****************************************************************/
+#define HUF_STATIC_ASSERT(c) \
+ { \
+ enum { HUF_static_assert = 1 / (int)(!!(c)) }; \
+ } /* use only *after* variable declarations */
+
+/*-***************************/
+/* generic DTableDesc */
+/*-***************************/
+
+typedef struct {
+ BYTE maxTableLog;
+ BYTE tableType;
+ BYTE tableLog;
+ BYTE reserved;
+} DTableDesc;
+
+static DTableDesc HUF_getDTableDesc(const HUF_DTable *table)
+{
+ DTableDesc dtd;
+ memcpy(&dtd, table, sizeof(dtd));
+ return dtd;
+}
+
+/*-***************************/
+/* single-symbol decoding */
+/*-***************************/
+
+typedef struct {
+ BYTE byte;
+ BYTE nbBits;
+} HUF_DEltX2; /* single-symbol decoding */
+
+size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
+{
+ U32 tableLog = 0;
+ U32 nbSymbols = 0;
+ size_t iSize;
+ void *const dtPtr = DTable + 1;
+ HUF_DEltX2 *const dt = (HUF_DEltX2 *)dtPtr;
+
+ U32 *rankVal;
+ BYTE *huffWeight;
+ size_t spaceUsed32 = 0;
+
+ rankVal = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+ huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
+ /* memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */
+
+ iSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
+ if (HUF_isError(iSize))
+ return iSize;
+
+ /* Table header */
+ {
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ if (tableLog > (U32)(dtd.maxTableLog + 1))
+ return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */
+ dtd.tableType = 0;
+ dtd.tableLog = (BYTE)tableLog;
+ memcpy(DTable, &dtd, sizeof(dtd));
+ }
+
+ /* Calculate starting value for each rank */
+ {
+ U32 n, nextRankStart = 0;
+ for (n = 1; n < tableLog + 1; n++) {
+ U32 const curr = nextRankStart;
+ nextRankStart += (rankVal[n] << (n - 1));
+ rankVal[n] = curr;
+ }
+ }
+
+ /* fill DTable */
+ {
+ U32 n;
+ for (n = 0; n < nbSymbols; n++) {
+ U32 const w = huffWeight[n];
+ U32 const length = (1 << w) >> 1;
+ U32 u;
+ HUF_DEltX2 D;
+ D.byte = (BYTE)n;
+ D.nbBits = (BYTE)(tableLog + 1 - w);
+ for (u = rankVal[w]; u < rankVal[w] + length; u++)
+ dt[u] = D;
+ rankVal[w] += length;
+ }
+ }
+
+ return iSize;
+}
+
+static BYTE HUF_decodeSymbolX2(BIT_DStream_t *Dstream, const HUF_DEltX2 *dt, const U32 dtLog)
+{
+ size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */
+ BYTE const c = dt[val].byte;
+ BIT_skipBits(Dstream, dt[val].nbBits);
+ return c;
+}
+
+#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) *ptr++ = HUF_decodeSymbolX2(DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \
+ if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \
+ HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
+
+#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \
+ if (ZSTD_64bits()) \
+ HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
+
+FORCE_INLINE size_t HUF_decodeStreamX2(BYTE *p, BIT_DStream_t *const bitDPtr, BYTE *const pEnd, const HUF_DEltX2 *const dt, const U32 dtLog)
+{
+ BYTE *const pStart = p;
+
+ /* up to 4 symbols at a time */
+ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p <= pEnd - 4)) {
+ HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+ HUF_DECODE_SYMBOLX2_1(p, bitDPtr);
+ HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+ HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+ }
+
+ /* closer to the end */
+ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p < pEnd))
+ HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+
+ /* no more data to retrieve from bitstream, hence no need to reload */
+ while (p < pEnd)
+ HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+
+ return pEnd - pStart;
+}
+
+static size_t HUF_decompress1X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ BYTE *op = (BYTE *)dst;
+ BYTE *const oend = op + dstSize;
+ const void *dtPtr = DTable + 1;
+ const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr;
+ BIT_DStream_t bitD;
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ U32 const dtLog = dtd.tableLog;
+
+ {
+ size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+
+ HUF_decodeStreamX2(op, &bitD, oend, dt, dtLog);
+
+ /* check */
+ if (!BIT_endOfDStream(&bitD))
+ return ERROR(corruption_detected);
+
+ return dstSize;
+}
+
+size_t HUF_decompress1X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ if (dtd.tableType != 0)
+ return ERROR(GENERIC);
+ return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
+}
+
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ const BYTE *ip = (const BYTE *)cSrc;
+
+ size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize);
+ if (HUF_isError(hSize))
+ return hSize;
+ if (hSize >= cSrcSize)
+ return ERROR(srcSize_wrong);
+ ip += hSize;
+ cSrcSize -= hSize;
+
+ return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx);
+}
+
+static size_t HUF_decompress4X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ /* Check */
+ if (cSrcSize < 10)
+ return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */
+
+ {
+ const BYTE *const istart = (const BYTE *)cSrc;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ const void *const dtPtr = DTable + 1;
+ const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr;
+
+ /* Init */
+ BIT_DStream_t bitD1;
+ BIT_DStream_t bitD2;
+ BIT_DStream_t bitD3;
+ BIT_DStream_t bitD4;
+ size_t const length1 = ZSTD_readLE16(istart);
+ size_t const length2 = ZSTD_readLE16(istart + 2);
+ size_t const length3 = ZSTD_readLE16(istart + 4);
+ size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+ const BYTE *const istart1 = istart + 6; /* jumpTable */
+ const BYTE *const istart2 = istart1 + length1;
+ const BYTE *const istart3 = istart2 + length2;
+ const BYTE *const istart4 = istart3 + length3;
+ const size_t segmentSize = (dstSize + 3) / 4;
+ BYTE *const opStart2 = ostart + segmentSize;
+ BYTE *const opStart3 = opStart2 + segmentSize;
+ BYTE *const opStart4 = opStart3 + segmentSize;
+ BYTE *op1 = ostart;
+ BYTE *op2 = opStart2;
+ BYTE *op3 = opStart3;
+ BYTE *op4 = opStart4;
+ U32 endSignal;
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ U32 const dtLog = dtd.tableLog;
+
+ if (length4 > cSrcSize)
+ return ERROR(corruption_detected); /* overflow */
+ {
+ size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+
+ /* 16-32 symbols per loop (4-8 symbols per stream) */
+ endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+ for (; (endSignal == BIT_DStream_unfinished) && (op4 < (oend - 7));) {
+ HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+ HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+ HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+ HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+ HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
+ HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
+ HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
+ HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
+ HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+ HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+ HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+ HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+ HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
+ HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
+ HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
+ HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
+ endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+ }
+
+ /* check corruption */
+ if (op1 > opStart2)
+ return ERROR(corruption_detected);
+ if (op2 > opStart3)
+ return ERROR(corruption_detected);
+ if (op3 > opStart4)
+ return ERROR(corruption_detected);
+ /* note : op4 supposed already verified within main loop */
+
+ /* finish bitStreams one by one */
+ HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
+ HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
+ HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
+ HUF_decodeStreamX2(op4, &bitD4, oend, dt, dtLog);
+
+ /* check */
+ endSignal = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+ if (!endSignal)
+ return ERROR(corruption_detected);
+
+ /* decoded size */
+ return dstSize;
+ }
+}
+
+size_t HUF_decompress4X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ if (dtd.tableType != 0)
+ return ERROR(GENERIC);
+ return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
+}
+
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ const BYTE *ip = (const BYTE *)cSrc;
+
+ size_t const hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize);
+ if (HUF_isError(hSize))
+ return hSize;
+ if (hSize >= cSrcSize)
+ return ERROR(srcSize_wrong);
+ ip += hSize;
+ cSrcSize -= hSize;
+
+ return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
+}
+
+/* *************************/
+/* double-symbols decoding */
+/* *************************/
+typedef struct {
+ U16 sequence;
+ BYTE nbBits;
+ BYTE length;
+} HUF_DEltX4; /* double-symbols decoding */
+
+typedef struct {
+ BYTE symbol;
+ BYTE weight;
+} sortedSymbol_t;
+
+/* HUF_fillDTableX4Level2() :
+ * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */
+static void HUF_fillDTableX4Level2(HUF_DEltX4 *DTable, U32 sizeLog, const U32 consumed, const U32 *rankValOrigin, const int minWeight,
+ const sortedSymbol_t *sortedSymbols, const U32 sortedListSize, U32 nbBitsBaseline, U16 baseSeq)
+{
+ HUF_DEltX4 DElt;
+ U32 rankVal[HUF_TABLELOG_MAX + 1];
+
+ /* get pre-calculated rankVal */
+ memcpy(rankVal, rankValOrigin, sizeof(rankVal));
+
+ /* fill skipped values */
+ if (minWeight > 1) {
+ U32 i, skipSize = rankVal[minWeight];
+ ZSTD_writeLE16(&(DElt.sequence), baseSeq);
+ DElt.nbBits = (BYTE)(consumed);
+ DElt.length = 1;
+ for (i = 0; i < skipSize; i++)
+ DTable[i] = DElt;
+ }
+
+ /* fill DTable */
+ {
+ U32 s;
+ for (s = 0; s < sortedListSize; s++) { /* note : sortedSymbols already skipped */
+ const U32 symbol = sortedSymbols[s].symbol;
+ const U32 weight = sortedSymbols[s].weight;
+ const U32 nbBits = nbBitsBaseline - weight;
+ const U32 length = 1 << (sizeLog - nbBits);
+ const U32 start = rankVal[weight];
+ U32 i = start;
+ const U32 end = start + length;
+
+ ZSTD_writeLE16(&(DElt.sequence), (U16)(baseSeq + (symbol << 8)));
+ DElt.nbBits = (BYTE)(nbBits + consumed);
+ DElt.length = 2;
+ do {
+ DTable[i++] = DElt;
+ } while (i < end); /* since length >= 1 */
+
+ rankVal[weight] += length;
+ }
+ }
+}
+
+typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1];
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+
+static void HUF_fillDTableX4(HUF_DEltX4 *DTable, const U32 targetLog, const sortedSymbol_t *sortedList, const U32 sortedListSize, const U32 *rankStart,
+ rankVal_t rankValOrigin, const U32 maxWeight, const U32 nbBitsBaseline)
+{
+ U32 rankVal[HUF_TABLELOG_MAX + 1];
+ const int scaleLog = nbBitsBaseline - targetLog; /* note : targetLog >= srcLog, hence scaleLog <= 1 */
+ const U32 minBits = nbBitsBaseline - maxWeight;
+ U32 s;
+
+ memcpy(rankVal, rankValOrigin, sizeof(rankVal));
+
+ /* fill DTable */
+ for (s = 0; s < sortedListSize; s++) {
+ const U16 symbol = sortedList[s].symbol;
+ const U32 weight = sortedList[s].weight;
+ const U32 nbBits = nbBitsBaseline - weight;
+ const U32 start = rankVal[weight];
+ const U32 length = 1 << (targetLog - nbBits);
+
+ if (targetLog - nbBits >= minBits) { /* enough room for a second symbol */
+ U32 sortedRank;
+ int minWeight = nbBits + scaleLog;
+ if (minWeight < 1)
+ minWeight = 1;
+ sortedRank = rankStart[minWeight];
+ HUF_fillDTableX4Level2(DTable + start, targetLog - nbBits, nbBits, rankValOrigin[nbBits], minWeight, sortedList + sortedRank,
+ sortedListSize - sortedRank, nbBitsBaseline, symbol);
+ } else {
+ HUF_DEltX4 DElt;
+ ZSTD_writeLE16(&(DElt.sequence), symbol);
+ DElt.nbBits = (BYTE)(nbBits);
+ DElt.length = 1;
+ {
+ U32 const end = start + length;
+ U32 u;
+ for (u = start; u < end; u++)
+ DTable[u] = DElt;
+ }
+ }
+ rankVal[weight] += length;
+ }
+}
+
+size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
+{
+ U32 tableLog, maxW, sizeOfSort, nbSymbols;
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ U32 const maxTableLog = dtd.maxTableLog;
+ size_t iSize;
+ void *dtPtr = DTable + 1; /* force compiler to avoid strict-aliasing */
+ HUF_DEltX4 *const dt = (HUF_DEltX4 *)dtPtr;
+ U32 *rankStart;
+
+ rankValCol_t *rankVal;
+ U32 *rankStats;
+ U32 *rankStart0;
+ sortedSymbol_t *sortedSymbol;
+ BYTE *weightList;
+ size_t spaceUsed32 = 0;
+
+ HUF_STATIC_ASSERT((sizeof(rankValCol_t) & 3) == 0);
+
+ rankVal = (rankValCol_t *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
+ rankStats = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_MAX + 1;
+ rankStart0 = (U32 *)workspace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_MAX + 2;
+ sortedSymbol = (sortedSymbol_t *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
+ weightList = (BYTE *)((U32 *)workspace + spaceUsed32);
+ spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > workspaceSize)
+ return ERROR(tableLog_tooLarge);
+ workspace = (U32 *)workspace + spaceUsed32;
+ workspaceSize -= (spaceUsed32 << 2);
+
+ rankStart = rankStart0 + 1;
+ memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
+
+ HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */
+ if (maxTableLog > HUF_TABLELOG_MAX)
+ return ERROR(tableLog_tooLarge);
+ /* memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */
+
+ iSize = HUF_readStats_wksp(weightList, HUF_SYMBOLVALUE_MAX + 1, rankStats, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
+ if (HUF_isError(iSize))
+ return iSize;
+
+ /* check result */
+ if (tableLog > maxTableLog)
+ return ERROR(tableLog_tooLarge); /* DTable can't fit code depth */
+
+ /* find maxWeight */
+ for (maxW = tableLog; rankStats[maxW] == 0; maxW--) {
+ } /* necessarily finds a solution before 0 */
+
+ /* Get start index of each weight */
+ {
+ U32 w, nextRankStart = 0;
+ for (w = 1; w < maxW + 1; w++) {
+ U32 curr = nextRankStart;
+ nextRankStart += rankStats[w];
+ rankStart[w] = curr;
+ }
+ rankStart[0] = nextRankStart; /* put all 0w symbols at the end of sorted list*/
+ sizeOfSort = nextRankStart;
+ }
+
+ /* sort symbols by weight */
+ {
+ U32 s;
+ for (s = 0; s < nbSymbols; s++) {
+ U32 const w = weightList[s];
+ U32 const r = rankStart[w]++;
+ sortedSymbol[r].symbol = (BYTE)s;
+ sortedSymbol[r].weight = (BYTE)w;
+ }
+ rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */
+ }
+
+ /* Build rankVal */
+ {
+ U32 *const rankVal0 = rankVal[0];
+ {
+ int const rescale = (maxTableLog - tableLog) - 1; /* tableLog <= maxTableLog */
+ U32 nextRankVal = 0;
+ U32 w;
+ for (w = 1; w < maxW + 1; w++) {
+ U32 curr = nextRankVal;
+ nextRankVal += rankStats[w] << (w + rescale);
+ rankVal0[w] = curr;
+ }
+ }
+ {
+ U32 const minBits = tableLog + 1 - maxW;
+ U32 consumed;
+ for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) {
+ U32 *const rankValPtr = rankVal[consumed];
+ U32 w;
+ for (w = 1; w < maxW + 1; w++) {
+ rankValPtr[w] = rankVal0[w] >> consumed;
+ }
+ }
+ }
+ }
+
+ HUF_fillDTableX4(dt, maxTableLog, sortedSymbol, sizeOfSort, rankStart0, rankVal, maxW, tableLog + 1);
+
+ dtd.tableLog = (BYTE)maxTableLog;
+ dtd.tableType = 1;
+ memcpy(DTable, &dtd, sizeof(dtd));
+ return iSize;
+}
+
+static U32 HUF_decodeSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog)
+{
+ size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */
+ memcpy(op, dt + val, 2);
+ BIT_skipBits(DStream, dt[val].nbBits);
+ return dt[val].length;
+}
+
+static U32 HUF_decodeLastSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog)
+{
+ size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */
+ memcpy(op, dt + val, 1);
+ if (dt[val].length == 1)
+ BIT_skipBits(DStream, dt[val].nbBits);
+ else {
+ if (DStream->bitsConsumed < (sizeof(DStream->bitContainer) * 8)) {
+ BIT_skipBits(DStream, dt[val].nbBits);
+ if (DStream->bitsConsumed > (sizeof(DStream->bitContainer) * 8))
+ /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+ DStream->bitsConsumed = (sizeof(DStream->bitContainer) * 8);
+ }
+ }
+ return 1;
+}
+
+#define HUF_DECODE_SYMBOLX4_0(ptr, DStreamPtr) ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX4_1(ptr, DStreamPtr) \
+ if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \
+ ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX4_2(ptr, DStreamPtr) \
+ if (ZSTD_64bits()) \
+ ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
+
+FORCE_INLINE size_t HUF_decodeStreamX4(BYTE *p, BIT_DStream_t *bitDPtr, BYTE *const pEnd, const HUF_DEltX4 *const dt, const U32 dtLog)
+{
+ BYTE *const pStart = p;
+
+ /* up to 8 symbols at a time */
+ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd - (sizeof(bitDPtr->bitContainer) - 1))) {
+ HUF_DECODE_SYMBOLX4_2(p, bitDPtr);
+ HUF_DECODE_SYMBOLX4_1(p, bitDPtr);
+ HUF_DECODE_SYMBOLX4_2(p, bitDPtr);
+ HUF_DECODE_SYMBOLX4_0(p, bitDPtr);
+ }
+
+ /* closer to end : up to 2 symbols at a time */
+ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd - 2))
+ HUF_DECODE_SYMBOLX4_0(p, bitDPtr);
+
+ while (p <= pEnd - 2)
+ HUF_DECODE_SYMBOLX4_0(p, bitDPtr); /* no need to reload : reached the end of DStream */
+
+ if (p < pEnd)
+ p += HUF_decodeLastSymbolX4(p, bitDPtr, dt, dtLog);
+
+ return p - pStart;
+}
+
+static size_t HUF_decompress1X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ BIT_DStream_t bitD;
+
+ /* Init */
+ {
+ size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+
+ /* decode */
+ {
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ const void *const dtPtr = DTable + 1; /* force compiler to not use strict-aliasing */
+ const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr;
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ HUF_decodeStreamX4(ostart, &bitD, oend, dt, dtd.tableLog);
+ }
+
+ /* check */
+ if (!BIT_endOfDStream(&bitD))
+ return ERROR(corruption_detected);
+
+ /* decoded size */
+ return dstSize;
+}
+
+size_t HUF_decompress1X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ if (dtd.tableType != 1)
+ return ERROR(GENERIC);
+ return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
+}
+
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ const BYTE *ip = (const BYTE *)cSrc;
+
+ size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize);
+ if (HUF_isError(hSize))
+ return hSize;
+ if (hSize >= cSrcSize)
+ return ERROR(srcSize_wrong);
+ ip += hSize;
+ cSrcSize -= hSize;
+
+ return HUF_decompress1X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx);
+}
+
+static size_t HUF_decompress4X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ if (cSrcSize < 10)
+ return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */
+
+ {
+ const BYTE *const istart = (const BYTE *)cSrc;
+ BYTE *const ostart = (BYTE *)dst;
+ BYTE *const oend = ostart + dstSize;
+ const void *const dtPtr = DTable + 1;
+ const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr;
+
+ /* Init */
+ BIT_DStream_t bitD1;
+ BIT_DStream_t bitD2;
+ BIT_DStream_t bitD3;
+ BIT_DStream_t bitD4;
+ size_t const length1 = ZSTD_readLE16(istart);
+ size_t const length2 = ZSTD_readLE16(istart + 2);
+ size_t const length3 = ZSTD_readLE16(istart + 4);
+ size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+ const BYTE *const istart1 = istart + 6; /* jumpTable */
+ const BYTE *const istart2 = istart1 + length1;
+ const BYTE *const istart3 = istart2 + length2;
+ const BYTE *const istart4 = istart3 + length3;
+ size_t const segmentSize = (dstSize + 3) / 4;
+ BYTE *const opStart2 = ostart + segmentSize;
+ BYTE *const opStart3 = opStart2 + segmentSize;
+ BYTE *const opStart4 = opStart3 + segmentSize;
+ BYTE *op1 = ostart;
+ BYTE *op2 = opStart2;
+ BYTE *op3 = opStart3;
+ BYTE *op4 = opStart4;
+ U32 endSignal;
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ U32 const dtLog = dtd.tableLog;
+
+ if (length4 > cSrcSize)
+ return ERROR(corruption_detected); /* overflow */
+ {
+ size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+ {
+ size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4);
+ if (HUF_isError(errorCode))
+ return errorCode;
+ }
+
+ /* 16-32 symbols per loop (4-8 symbols per stream) */
+ endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+ for (; (endSignal == BIT_DStream_unfinished) & (op4 < (oend - (sizeof(bitD4.bitContainer) - 1)));) {
+ HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
+ HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
+ HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
+ HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
+ HUF_DECODE_SYMBOLX4_1(op1, &bitD1);
+ HUF_DECODE_SYMBOLX4_1(op2, &bitD2);
+ HUF_DECODE_SYMBOLX4_1(op3, &bitD3);
+ HUF_DECODE_SYMBOLX4_1(op4, &bitD4);
+ HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
+ HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
+ HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
+ HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
+ HUF_DECODE_SYMBOLX4_0(op1, &bitD1);
+ HUF_DECODE_SYMBOLX4_0(op2, &bitD2);
+ HUF_DECODE_SYMBOLX4_0(op3, &bitD3);
+ HUF_DECODE_SYMBOLX4_0(op4, &bitD4);
+
+ endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+ }
+
+ /* check corruption */
+ if (op1 > opStart2)
+ return ERROR(corruption_detected);
+ if (op2 > opStart3)
+ return ERROR(corruption_detected);
+ if (op3 > opStart4)
+ return ERROR(corruption_detected);
+ /* note : op4 already verified within main loop */
+
+ /* finish bitStreams one by one */
+ HUF_decodeStreamX4(op1, &bitD1, opStart2, dt, dtLog);
+ HUF_decodeStreamX4(op2, &bitD2, opStart3, dt, dtLog);
+ HUF_decodeStreamX4(op3, &bitD3, opStart4, dt, dtLog);
+ HUF_decodeStreamX4(op4, &bitD4, oend, dt, dtLog);
+
+ /* check */
+ {
+ U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+ if (!endCheck)
+ return ERROR(corruption_detected);
+ }
+
+ /* decoded size */
+ return dstSize;
+ }
+}
+
+size_t HUF_decompress4X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc dtd = HUF_getDTableDesc(DTable);
+ if (dtd.tableType != 1)
+ return ERROR(GENERIC);
+ return HUF_decompress4X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
+}
+
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ const BYTE *ip = (const BYTE *)cSrc;
+
+ size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize);
+ if (HUF_isError(hSize))
+ return hSize;
+ if (hSize >= cSrcSize)
+ return ERROR(srcSize_wrong);
+ ip += hSize;
+ cSrcSize -= hSize;
+
+ return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
+}
+
+/* ********************************/
+/* Generic decompression selector */
+/* ********************************/
+
+size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ return dtd.tableType ? HUF_decompress1X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable)
+ : HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable);
+}
+
+size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
+{
+ DTableDesc const dtd = HUF_getDTableDesc(DTable);
+ return dtd.tableType ? HUF_decompress4X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable)
+ : HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable);
+}
+
+typedef struct {
+ U32 tableTime;
+ U32 decode256Time;
+} algo_time_t;
+static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] = {
+ /* single, double, quad */
+ {{0, 0}, {1, 1}, {2, 2}}, /* Q==0 : impossible */
+ {{0, 0}, {1, 1}, {2, 2}}, /* Q==1 : impossible */
+ {{38, 130}, {1313, 74}, {2151, 38}}, /* Q == 2 : 12-18% */
+ {{448, 128}, {1353, 74}, {2238, 41}}, /* Q == 3 : 18-25% */
+ {{556, 128}, {1353, 74}, {2238, 47}}, /* Q == 4 : 25-32% */
+ {{714, 128}, {1418, 74}, {2436, 53}}, /* Q == 5 : 32-38% */
+ {{883, 128}, {1437, 74}, {2464, 61}}, /* Q == 6 : 38-44% */
+ {{897, 128}, {1515, 75}, {2622, 68}}, /* Q == 7 : 44-50% */
+ {{926, 128}, {1613, 75}, {2730, 75}}, /* Q == 8 : 50-56% */
+ {{947, 128}, {1729, 77}, {3359, 77}}, /* Q == 9 : 56-62% */
+ {{1107, 128}, {2083, 81}, {4006, 84}}, /* Q ==10 : 62-69% */
+ {{1177, 128}, {2379, 87}, {4785, 88}}, /* Q ==11 : 69-75% */
+ {{1242, 128}, {2415, 93}, {5155, 84}}, /* Q ==12 : 75-81% */
+ {{1349, 128}, {2644, 106}, {5260, 106}}, /* Q ==13 : 81-87% */
+ {{1455, 128}, {2422, 124}, {4174, 124}}, /* Q ==14 : 87-93% */
+ {{722, 128}, {1891, 145}, {1936, 146}}, /* Q ==15 : 93-99% */
+};
+
+/** HUF_selectDecoder() :
+* Tells which decoder is likely to decode faster,
+* based on a set of pre-determined metrics.
+* @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
+* Assumption : 0 < cSrcSize < dstSize <= 128 KB */
+U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize)
+{
+ /* decoder timing evaluation */
+ U32 const Q = (U32)(cSrcSize * 16 / dstSize); /* Q < 16 since dstSize > cSrcSize */
+ U32 const D256 = (U32)(dstSize >> 8);
+ U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
+ U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
+ DTime1 += DTime1 >> 3; /* advantage to algorithm using less memory, for cache eviction */
+
+ return DTime1 < DTime0;
+}
+
+typedef size_t (*decompressionAlgo)(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize);
+
+size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ /* validation checks */
+ if (dstSize == 0)
+ return ERROR(dstSize_tooSmall);
+ if (cSrcSize > dstSize)
+ return ERROR(corruption_detected); /* invalid */
+ if (cSrcSize == dstSize) {
+ memcpy(dst, cSrc, dstSize);
+ return dstSize;
+ } /* not compressed */
+ if (cSrcSize == 1) {
+ memset(dst, *(const BYTE *)cSrc, dstSize);
+ return dstSize;
+ } /* RLE */
+
+ {
+ U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+ return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
+ : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
+ }
+}
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ /* validation checks */
+ if (dstSize == 0)
+ return ERROR(dstSize_tooSmall);
+ if ((cSrcSize >= dstSize) || (cSrcSize <= 1))
+ return ERROR(corruption_detected); /* invalid */
+
+ {
+ U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+ return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
+ : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
+ }
+}
+
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
+{
+ /* validation checks */
+ if (dstSize == 0)
+ return ERROR(dstSize_tooSmall);
+ if (cSrcSize > dstSize)
+ return ERROR(corruption_detected); /* invalid */
+ if (cSrcSize == dstSize) {
+ memcpy(dst, cSrc, dstSize);
+ return dstSize;
+ } /* not compressed */
+ if (cSrcSize == 1) {
+ memset(dst, *(const BYTE *)cSrc, dstSize);
+ return dstSize;
+ } /* RLE */
+
+ {
+ U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+ return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
+ : HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
+ }
+}
diff --git a/lib/zstd/mem.h b/lib/zstd/mem.h
new file mode 100644
index 0000000..3a0f34c
--- /dev/null
+++ b/lib/zstd/mem.h
@@ -0,0 +1,151 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+#ifndef MEM_H_MODULE
+#define MEM_H_MODULE
+
+/*-****************************************
+* Dependencies
+******************************************/
+#include <asm/unaligned.h>
+#include <linux/string.h> /* memcpy */
+#include <linux/types.h> /* size_t, ptrdiff_t */
+
+/*-****************************************
+* Compiler specifics
+******************************************/
+#define ZSTD_STATIC static __inline __attribute__((unused))
+
+/*-**************************************************************
+* Basic Types
+*****************************************************************/
+typedef uint8_t BYTE;
+typedef uint16_t U16;
+typedef int16_t S16;
+typedef uint32_t U32;
+typedef int32_t S32;
+typedef uint64_t U64;
+typedef int64_t S64;
+typedef ptrdiff_t iPtrDiff;
+typedef uintptr_t uPtrDiff;
+
+/*-**************************************************************
+* Memory I/O
+*****************************************************************/
+ZSTD_STATIC unsigned ZSTD_32bits(void) { return sizeof(size_t) == 4; }
+ZSTD_STATIC unsigned ZSTD_64bits(void) { return sizeof(size_t) == 8; }
+
+#if defined(__LITTLE_ENDIAN)
+#define ZSTD_LITTLE_ENDIAN 1
+#else
+#define ZSTD_LITTLE_ENDIAN 0
+#endif
+
+ZSTD_STATIC unsigned ZSTD_isLittleEndian(void) { return ZSTD_LITTLE_ENDIAN; }
+
+ZSTD_STATIC U16 ZSTD_read16(const void *memPtr) { return get_unaligned((const U16 *)memPtr); }
+
+ZSTD_STATIC U32 ZSTD_read32(const void *memPtr) { return get_unaligned((const U32 *)memPtr); }
+
+ZSTD_STATIC U64 ZSTD_read64(const void *memPtr) { return get_unaligned((const U64 *)memPtr); }
+
+ZSTD_STATIC size_t ZSTD_readST(const void *memPtr) { return get_unaligned((const size_t *)memPtr); }
+
+ZSTD_STATIC void ZSTD_write16(void *memPtr, U16 value) { put_unaligned(value, (U16 *)memPtr); }
+
+ZSTD_STATIC void ZSTD_write32(void *memPtr, U32 value) { put_unaligned(value, (U32 *)memPtr); }
+
+ZSTD_STATIC void ZSTD_write64(void *memPtr, U64 value) { put_unaligned(value, (U64 *)memPtr); }
+
+/*=== Little endian r/w ===*/
+
+ZSTD_STATIC U16 ZSTD_readLE16(const void *memPtr) { return get_unaligned_le16(memPtr); }
+
+ZSTD_STATIC void ZSTD_writeLE16(void *memPtr, U16 val) { put_unaligned_le16(val, memPtr); }
+
+ZSTD_STATIC U32 ZSTD_readLE24(const void *memPtr) { return ZSTD_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16); }
+
+ZSTD_STATIC void ZSTD_writeLE24(void *memPtr, U32 val)
+{
+ ZSTD_writeLE16(memPtr, (U16)val);
+ ((BYTE *)memPtr)[2] = (BYTE)(val >> 16);
+}
+
+ZSTD_STATIC U32 ZSTD_readLE32(const void *memPtr) { return get_unaligned_le32(memPtr); }
+
+ZSTD_STATIC void ZSTD_writeLE32(void *memPtr, U32 val32) { put_unaligned_le32(val32, memPtr); }
+
+ZSTD_STATIC U64 ZSTD_readLE64(const void *memPtr) { return get_unaligned_le64(memPtr); }
+
+ZSTD_STATIC void ZSTD_writeLE64(void *memPtr, U64 val64) { put_unaligned_le64(val64, memPtr); }
+
+ZSTD_STATIC size_t ZSTD_readLEST(const void *memPtr)
+{
+ if (ZSTD_32bits())
+ return (size_t)ZSTD_readLE32(memPtr);
+ else
+ return (size_t)ZSTD_readLE64(memPtr);
+}
+
+ZSTD_STATIC void ZSTD_writeLEST(void *memPtr, size_t val)
+{
+ if (ZSTD_32bits())
+ ZSTD_writeLE32(memPtr, (U32)val);
+ else
+ ZSTD_writeLE64(memPtr, (U64)val);
+}
+
+/*=== Big endian r/w ===*/
+
+ZSTD_STATIC U32 ZSTD_readBE32(const void *memPtr) { return get_unaligned_be32(memPtr); }
+
+ZSTD_STATIC void ZSTD_writeBE32(void *memPtr, U32 val32) { put_unaligned_be32(val32, memPtr); }
+
+ZSTD_STATIC U64 ZSTD_readBE64(const void *memPtr) { return get_unaligned_be64(memPtr); }
+
+ZSTD_STATIC void ZSTD_writeBE64(void *memPtr, U64 val64) { put_unaligned_be64(val64, memPtr); }
+
+ZSTD_STATIC size_t ZSTD_readBEST(const void *memPtr)
+{
+ if (ZSTD_32bits())
+ return (size_t)ZSTD_readBE32(memPtr);
+ else
+ return (size_t)ZSTD_readBE64(memPtr);
+}
+
+ZSTD_STATIC void ZSTD_writeBEST(void *memPtr, size_t val)
+{
+ if (ZSTD_32bits())
+ ZSTD_writeBE32(memPtr, (U32)val);
+ else
+ ZSTD_writeBE64(memPtr, (U64)val);
+}
+
+/* function safe only for comparisons */
+ZSTD_STATIC U32 ZSTD_readMINMATCH(const void *memPtr, U32 length)
+{
+ switch (length) {
+ default:
+ case 4: return ZSTD_read32(memPtr);
+ case 3:
+ if (ZSTD_isLittleEndian())
+ return ZSTD_read32(memPtr) << 8;
+ else
+ return ZSTD_read32(memPtr) >> 8;
+ }
+}
+
+#endif /* MEM_H_MODULE */
diff --git a/lib/zstd/zstd_common.c b/lib/zstd/zstd_common.c
new file mode 100644
index 0000000..a282624
--- /dev/null
+++ b/lib/zstd/zstd_common.c
@@ -0,0 +1,75 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+/*-*************************************
+* Dependencies
+***************************************/
+#include "error_private.h"
+#include "zstd_internal.h" /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */
+#include <linux/kernel.h>
+
+/*=**************************************************************
+* Custom allocator
+****************************************************************/
+
+#define stack_push(stack, size) \
+ ({ \
+ void *const ptr = ZSTD_PTR_ALIGN((stack)->ptr); \
+ (stack)->ptr = (char *)ptr + (size); \
+ (stack)->ptr <= (stack)->end ? ptr : NULL; \
+ })
+
+ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize)
+{
+ ZSTD_customMem stackMem = {ZSTD_stackAlloc, ZSTD_stackFree, workspace};
+ ZSTD_stack *stack = (ZSTD_stack *)workspace;
+ /* Verify preconditions */
+ if (!workspace || workspaceSize < sizeof(ZSTD_stack) || workspace != ZSTD_PTR_ALIGN(workspace)) {
+ ZSTD_customMem error = {NULL, NULL, NULL};
+ return error;
+ }
+ /* Initialize the stack */
+ stack->ptr = workspace;
+ stack->end = (char *)workspace + workspaceSize;
+ stack_push(stack, sizeof(ZSTD_stack));
+ return stackMem;
+}
+
+void *ZSTD_stackAllocAll(void *opaque, size_t *size)
+{
+ ZSTD_stack *stack = (ZSTD_stack *)opaque;
+ *size = (BYTE const *)stack->end - (BYTE *)ZSTD_PTR_ALIGN(stack->ptr);
+ return stack_push(stack, *size);
+}
+
+void *ZSTD_stackAlloc(void *opaque, size_t size)
+{
+ ZSTD_stack *stack = (ZSTD_stack *)opaque;
+ return stack_push(stack, size);
+}
+void ZSTD_stackFree(void *opaque, void *address)
+{
+ (void)opaque;
+ (void)address;
+}
+
+void *ZSTD_malloc(size_t size, ZSTD_customMem customMem) { return customMem.customAlloc(customMem.opaque, size); }
+
+void ZSTD_free(void *ptr, ZSTD_customMem customMem)
+{
+ if (ptr != NULL)
+ customMem.customFree(customMem.opaque, ptr);
+}
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
new file mode 100644
index 0000000..1a79fab
--- /dev/null
+++ b/lib/zstd/zstd_internal.h
@@ -0,0 +1,263 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+#ifndef ZSTD_CCOMMON_H_MODULE
+#define ZSTD_CCOMMON_H_MODULE
+
+/*-*******************************************************
+* Compiler specifics
+*********************************************************/
+#define FORCE_INLINE static __always_inline
+#define FORCE_NOINLINE static noinline
+
+/*-*************************************
+* Dependencies
+***************************************/
+#include "error_private.h"
+#include "mem.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/xxhash.h>
+#include <linux/zstd.h>
+
+/*-*************************************
+* shared macros
+***************************************/
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+#define MAX(a, b) ((a) > (b) ? (a) : (b))
+#define CHECK_F(f) \
+ { \
+ size_t const errcod = f; \
+ if (ERR_isError(errcod)) \
+ return errcod; \
+ } /* check and Forward error code */
+#define CHECK_E(f, e) \
+ { \
+ size_t const errcod = f; \
+ if (ERR_isError(errcod)) \
+ return ERROR(e); \
+ } /* check and send Error code */
+#define ZSTD_STATIC_ASSERT(c) \
+ { \
+ enum { ZSTD_static_assert = 1 / (int)(!!(c)) }; \
+ }
+
+/*-*************************************
+* Common constants
+***************************************/
+#define ZSTD_OPT_NUM (1 << 12)
+#define ZSTD_DICT_MAGIC 0xEC30A437 /* v0.7+ */
+
+#define ZSTD_REP_NUM 3 /* number of repcodes */
+#define ZSTD_REP_CHECK (ZSTD_REP_NUM) /* number of repcodes to check by the optimal parser */
+#define ZSTD_REP_MOVE (ZSTD_REP_NUM - 1)
+#define ZSTD_REP_MOVE_OPT (ZSTD_REP_NUM)
+static const U32 repStartValue[ZSTD_REP_NUM] = {1, 4, 8};
+
+#define KB *(1 << 10)
+#define MB *(1 << 20)
+#define GB *(1U << 30)
+
+#define BIT7 128
+#define BIT6 64
+#define BIT5 32
+#define BIT4 16
+#define BIT1 2
+#define BIT0 1
+
+#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10
+static const size_t ZSTD_fcs_fieldSize[4] = {0, 2, 4, 8};
+static const size_t ZSTD_did_fieldSize[4] = {0, 1, 2, 4};
+
+#define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */
+static const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE;
+typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
+
+#define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */
+#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */
+
+#define HufLog 12
+typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
+
+#define LONGNBSEQ 0x7F00
+
+#define MINMATCH 3
+#define EQUAL_READ32 4
+
+#define Litbits 8
+#define MaxLit ((1 << Litbits) - 1)
+#define MaxML 52
+#define MaxLL 35
+#define MaxOff 28
+#define MaxSeq MAX(MaxLL, MaxML) /* Assumption : MaxOff < MaxLL,MaxML */
+#define MLFSELog 9
+#define LLFSELog 9
+#define OffFSELog 8
+
+static const U32 LL_bits[MaxLL + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
+static const S16 LL_defaultNorm[MaxLL + 1] = {4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 1, 1, 1, 1, -1, -1, -1, -1};
+#define LL_DEFAULTNORMLOG 6 /* for static allocation */
+static const U32 LL_defaultNormLog = LL_DEFAULTNORMLOG;
+
+static const U32 ML_bits[MaxML + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
+static const S16 ML_defaultNorm[MaxML + 1] = {1, 4, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1, -1, -1};
+#define ML_DEFAULTNORMLOG 6 /* for static allocation */
+static const U32 ML_defaultNormLog = ML_DEFAULTNORMLOG;
+
+static const S16 OF_defaultNorm[MaxOff + 1] = {1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1};
+#define OF_DEFAULTNORMLOG 5 /* for static allocation */
+static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
+
+/*-*******************************************
+* Shared functions to include for inlining
+*********************************************/
+ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
+ memcpy(dst, src, 8);
+}
+/*! ZSTD_wildcopy() :
+* custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */
+#define WILDCOPY_OVERLENGTH 8
+ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length)
+{
+ const BYTE* ip = (const BYTE*)src;
+ BYTE* op = (BYTE*)dst;
+ BYTE* const oend = op + length;
+ /* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
+ * Avoid the bad case where the loop only runs once by handling the
+ * special case separately. This doesn't trigger the bug because it
+ * doesn't involve pointer/integer overflow.
+ */
+ if (length <= 8)
+ return ZSTD_copy8(dst, src);
+ do {
+ ZSTD_copy8(op, ip);
+ op += 8;
+ ip += 8;
+ } while (op < oend);
+}
+
+/*-*******************************************
+* Private interfaces
+*********************************************/
+typedef struct ZSTD_stats_s ZSTD_stats_t;
+
+typedef struct {
+ U32 off;
+ U32 len;
+} ZSTD_match_t;
+
+typedef struct {
+ U32 price;
+ U32 off;
+ U32 mlen;
+ U32 litlen;
+ U32 rep[ZSTD_REP_NUM];
+} ZSTD_optimal_t;
+
+typedef struct seqDef_s {
+ U32 offset;
+ U16 litLength;
+ U16 matchLength;
+} seqDef;
+
+typedef struct {
+ seqDef *sequencesStart;
+ seqDef *sequences;
+ BYTE *litStart;
+ BYTE *lit;
+ BYTE *llCode;
+ BYTE *mlCode;
+ BYTE *ofCode;
+ U32 longLengthID; /* 0 == no longLength; 1 == Lit.longLength; 2 == Match.longLength; */
+ U32 longLengthPos;
+ /* opt */
+ ZSTD_optimal_t *priceTable;
+ ZSTD_match_t *matchTable;
+ U32 *matchLengthFreq;
+ U32 *litLengthFreq;
+ U32 *litFreq;
+ U32 *offCodeFreq;
+ U32 matchLengthSum;
+ U32 matchSum;
+ U32 litLengthSum;
+ U32 litSum;
+ U32 offCodeSum;
+ U32 log2matchLengthSum;
+ U32 log2matchSum;
+ U32 log2litLengthSum;
+ U32 log2litSum;
+ U32 log2offCodeSum;
+ U32 factor;
+ U32 staticPrices;
+ U32 cachedPrice;
+ U32 cachedLitLength;
+ const BYTE *cachedLiterals;
+} seqStore_t;
+
+const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx);
+void ZSTD_seqToCodes(const seqStore_t *seqStorePtr);
+int ZSTD_isSkipFrame(ZSTD_DCtx *dctx);
+
+/*= Custom memory allocation functions */
+typedef void *(*ZSTD_allocFunction)(void *opaque, size_t size);
+typedef void (*ZSTD_freeFunction)(void *opaque, void *address);
+typedef struct {
+ ZSTD_allocFunction customAlloc;
+ ZSTD_freeFunction customFree;
+ void *opaque;
+} ZSTD_customMem;
+
+void *ZSTD_malloc(size_t size, ZSTD_customMem customMem);
+void ZSTD_free(void *ptr, ZSTD_customMem customMem);
+
+/*====== stack allocation ======*/
+
+typedef struct {
+ void *ptr;
+ const void *end;
+} ZSTD_stack;
+
+#define ZSTD_ALIGN(x) ALIGN(x, sizeof(size_t))
+#define ZSTD_PTR_ALIGN(p) PTR_ALIGN(p, sizeof(size_t))
+
+ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize);
+
+void *ZSTD_stackAllocAll(void *opaque, size_t *size);
+void *ZSTD_stackAlloc(void *opaque, size_t size);
+void ZSTD_stackFree(void *opaque, void *address);
+
+/*====== common function ======*/
+
+ZSTD_STATIC U32 ZSTD_highbit32(U32 val) { return 31 - __builtin_clz(val); }
+
+/* hidden functions */
+
+/* ZSTD_invalidateRepCodes() :
+ * ensures next compression will not use repcodes from previous block.
+ * Note : only works with regular variant;
+ * do not use with extDict variant ! */
+void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx);
+
+size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx);
+size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx);
+size_t ZSTD_freeCDict(ZSTD_CDict *cdict);
+size_t ZSTD_freeDDict(ZSTD_DDict *cdict);
+size_t ZSTD_freeCStream(ZSTD_CStream *zcs);
+size_t ZSTD_freeDStream(ZSTD_DStream *zds);
+
+#endif /* ZSTD_CCOMMON_H_MODULE */
diff --git a/lib/zstd/zstd_opt.h b/lib/zstd/zstd_opt.h
new file mode 100644
index 0000000..55e1b4c
--- /dev/null
+++ b/lib/zstd/zstd_opt.h
@@ -0,0 +1,1014 @@
+/**
+ * Copyright (c) 2016-present, Przemyslaw Skibinski, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd.
+ * An additional grant of patent rights can be found in the PATENTS file in the
+ * same directory.
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation. This program is dual-licensed; you may select
+ * either version 2 of the GNU General Public License ("GPL") or BSD license
+ * ("BSD").
+ */
+
+/* Note : this file is intended to be included within zstd_compress.c */
+
+#ifndef ZSTD_OPT_H_91842398743
+#define ZSTD_OPT_H_91842398743
+
+#define ZSTD_LITFREQ_ADD 2
+#define ZSTD_FREQ_DIV 4
+#define ZSTD_MAX_PRICE (1 << 30)
+
+/*-*************************************
+* Price functions for optimal parser
+***************************************/
+FORCE_INLINE void ZSTD_setLog2Prices(seqStore_t *ssPtr)
+{
+ ssPtr->log2matchLengthSum = ZSTD_highbit32(ssPtr->matchLengthSum + 1);
+ ssPtr->log2litLengthSum = ZSTD_highbit32(ssPtr->litLengthSum + 1);
+ ssPtr->log2litSum = ZSTD_highbit32(ssPtr->litSum + 1);
+ ssPtr->log2offCodeSum = ZSTD_highbit32(ssPtr->offCodeSum + 1);
+ ssPtr->factor = 1 + ((ssPtr->litSum >> 5) / ssPtr->litLengthSum) + ((ssPtr->litSum << 1) / (ssPtr->litSum + ssPtr->matchSum));
+}
+
+ZSTD_STATIC void ZSTD_rescaleFreqs(seqStore_t *ssPtr, const BYTE *src, size_t srcSize)
+{
+ unsigned u;
+
+ ssPtr->cachedLiterals = NULL;
+ ssPtr->cachedPrice = ssPtr->cachedLitLength = 0;
+ ssPtr->staticPrices = 0;
+
+ if (ssPtr->litLengthSum == 0) {
+ if (srcSize <= 1024)
+ ssPtr->staticPrices = 1;
+
+ for (u = 0; u <= MaxLit; u++)
+ ssPtr->litFreq[u] = 0;
+ for (u = 0; u < srcSize; u++)
+ ssPtr->litFreq[src[u]]++;
+
+ ssPtr->litSum = 0;
+ ssPtr->litLengthSum = MaxLL + 1;
+ ssPtr->matchLengthSum = MaxML + 1;
+ ssPtr->offCodeSum = (MaxOff + 1);
+ ssPtr->matchSum = (ZSTD_LITFREQ_ADD << Litbits);
+
+ for (u = 0; u <= MaxLit; u++) {
+ ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> ZSTD_FREQ_DIV);
+ ssPtr->litSum += ssPtr->litFreq[u];
+ }
+ for (u = 0; u <= MaxLL; u++)
+ ssPtr->litLengthFreq[u] = 1;
+ for (u = 0; u <= MaxML; u++)
+ ssPtr->matchLengthFreq[u] = 1;
+ for (u = 0; u <= MaxOff; u++)
+ ssPtr->offCodeFreq[u] = 1;
+ } else {
+ ssPtr->matchLengthSum = 0;
+ ssPtr->litLengthSum = 0;
+ ssPtr->offCodeSum = 0;
+ ssPtr->matchSum = 0;
+ ssPtr->litSum = 0;
+
+ for (u = 0; u <= MaxLit; u++) {
+ ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> (ZSTD_FREQ_DIV + 1));
+ ssPtr->litSum += ssPtr->litFreq[u];
+ }
+ for (u = 0; u <= MaxLL; u++) {
+ ssPtr->litLengthFreq[u] = 1 + (ssPtr->litLengthFreq[u] >> (ZSTD_FREQ_DIV + 1));
+ ssPtr->litLengthSum += ssPtr->litLengthFreq[u];
+ }
+ for (u = 0; u <= MaxML; u++) {
+ ssPtr->matchLengthFreq[u] = 1 + (ssPtr->matchLengthFreq[u] >> ZSTD_FREQ_DIV);
+ ssPtr->matchLengthSum += ssPtr->matchLengthFreq[u];
+ ssPtr->matchSum += ssPtr->matchLengthFreq[u] * (u + 3);
+ }
+ ssPtr->matchSum *= ZSTD_LITFREQ_ADD;
+ for (u = 0; u <= MaxOff; u++) {
+ ssPtr->offCodeFreq[u] = 1 + (ssPtr->offCodeFreq[u] >> ZSTD_FREQ_DIV);
+ ssPtr->offCodeSum += ssPtr->offCodeFreq[u];
+ }
+ }
+
+ ZSTD_setLog2Prices(ssPtr);
+}
+
+FORCE_INLINE U32 ZSTD_getLiteralPrice(seqStore_t *ssPtr, U32 litLength, const BYTE *literals)
+{
+ U32 price, u;
+
+ if (ssPtr->staticPrices)
+ return ZSTD_highbit32((U32)litLength + 1) + (litLength * 6);
+
+ if (litLength == 0)
+ return ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[0] + 1);
+
+ /* literals */
+ if (ssPtr->cachedLiterals == literals) {
+ U32 const additional = litLength - ssPtr->cachedLitLength;
+ const BYTE *literals2 = ssPtr->cachedLiterals + ssPtr->cachedLitLength;
+ price = ssPtr->cachedPrice + additional * ssPtr->log2litSum;
+ for (u = 0; u < additional; u++)
+ price -= ZSTD_highbit32(ssPtr->litFreq[literals2[u]] + 1);
+ ssPtr->cachedPrice = price;
+ ssPtr->cachedLitLength = litLength;
+ } else {
+ price = litLength * ssPtr->log2litSum;
+ for (u = 0; u < litLength; u++)
+ price -= ZSTD_highbit32(ssPtr->litFreq[literals[u]] + 1);
+
+ if (litLength >= 12) {
+ ssPtr->cachedLiterals = literals;
+ ssPtr->cachedPrice = price;
+ ssPtr->cachedLitLength = litLength;
+ }
+ }
+
+ /* literal Length */
+ {
+ const BYTE LL_deltaCode = 19;
+ const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength];
+ price += LL_bits[llCode] + ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[llCode] + 1);
+ }
+
+ return price;
+}
+
+FORCE_INLINE U32 ZSTD_getPrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength, const int ultra)
+{
+ /* offset */
+ U32 price;
+ BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1);
+
+ if (seqStorePtr->staticPrices)
+ return ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + ZSTD_highbit32((U32)matchLength + 1) + 16 + offCode;
+
+ price = offCode + seqStorePtr->log2offCodeSum - ZSTD_highbit32(seqStorePtr->offCodeFreq[offCode] + 1);
+ if (!ultra && offCode >= 20)
+ price += (offCode - 19) * 2;
+
+ /* match Length */
+ {
+ const BYTE ML_deltaCode = 36;
+ const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength];
+ price += ML_bits[mlCode] + seqStorePtr->log2matchLengthSum - ZSTD_highbit32(seqStorePtr->matchLengthFreq[mlCode] + 1);
+ }
+
+ return price + ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + seqStorePtr->factor;
+}
+
+ZSTD_STATIC void ZSTD_updatePrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength)
+{
+ U32 u;
+
+ /* literals */
+ seqStorePtr->litSum += litLength * ZSTD_LITFREQ_ADD;
+ for (u = 0; u < litLength; u++)
+ seqStorePtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
+
+ /* literal Length */
+ {
+ const BYTE LL_deltaCode = 19;
+ const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength];
+ seqStorePtr->litLengthFreq[llCode]++;
+ seqStorePtr->litLengthSum++;
+ }
+
+ /* match offset */
+ {
+ BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1);
+ seqStorePtr->offCodeSum++;
+ seqStorePtr->offCodeFreq[offCode]++;
+ }
+
+ /* match Length */
+ {
+ const BYTE ML_deltaCode = 36;
+ const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength];
+ seqStorePtr->matchLengthFreq[mlCode]++;
+ seqStorePtr->matchLengthSum++;
+ }
+
+ ZSTD_setLog2Prices(seqStorePtr);
+}
+
+#define SET_PRICE(pos, mlen_, offset_, litlen_, price_) \
+ { \
+ while (last_pos < pos) { \
+ opt[last_pos + 1].price = ZSTD_MAX_PRICE; \
+ last_pos++; \
+ } \
+ opt[pos].mlen = mlen_; \
+ opt[pos].off = offset_; \
+ opt[pos].litlen = litlen_; \
+ opt[pos].price = price_; \
+ }
+
+/* Update hashTable3 up to ip (excluded)
+ Assumption : always within prefix (i.e. not within extDict) */
+FORCE_INLINE
+U32 ZSTD_insertAndFindFirstIndexHash3(ZSTD_CCtx *zc, const BYTE *ip)
+{
+ U32 *const hashTable3 = zc->hashTable3;
+ U32 const hashLog3 = zc->hashLog3;
+ const BYTE *const base = zc->base;
+ U32 idx = zc->nextToUpdate3;
+ const U32 target = zc->nextToUpdate3 = (U32)(ip - base);
+ const size_t hash3 = ZSTD_hash3Ptr(ip, hashLog3);
+
+ while (idx < target) {
+ hashTable3[ZSTD_hash3Ptr(base + idx, hashLog3)] = idx;
+ idx++;
+ }
+
+ return hashTable3[hash3];
+}
+
+/*-*************************************
+* Binary Tree search
+***************************************/
+static U32 ZSTD_insertBtAndGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, U32 nbCompares, const U32 mls, U32 extDict,
+ ZSTD_match_t *matches, const U32 minMatchLen)
+{
+ const BYTE *const base = zc->base;
+ const U32 curr = (U32)(ip - base);
+ const U32 hashLog = zc->params.cParams.hashLog;
+ const size_t h = ZSTD_hashPtr(ip, hashLog, mls);
+ U32 *const hashTable = zc->hashTable;
+ U32 matchIndex = hashTable[h];
+ U32 *const bt = zc->chainTable;
+ const U32 btLog = zc->params.cParams.chainLog - 1;
+ const U32 btMask = (1U << btLog) - 1;
+ size_t commonLengthSmaller = 0, commonLengthLarger = 0;
+ const BYTE *const dictBase = zc->dictBase;
+ const U32 dictLimit = zc->dictLimit;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const U32 btLow = btMask >= curr ? 0 : curr - btMask;
+ const U32 windowLow = zc->lowLimit;
+ U32 *smallerPtr = bt + 2 * (curr & btMask);
+ U32 *largerPtr = bt + 2 * (curr & btMask) + 1;
+ U32 matchEndIdx = curr + 8;
+ U32 dummy32; /* to be nullified at the end */
+ U32 mnum = 0;
+
+ const U32 minMatch = (mls == 3) ? 3 : 4;
+ size_t bestLength = minMatchLen - 1;
+
+ if (minMatch == 3) { /* HC3 match finder */
+ U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(zc, ip);
+ if (matchIndex3 > windowLow && (curr - matchIndex3 < (1 << 18))) {
+ const BYTE *match;
+ size_t currMl = 0;
+ if ((!extDict) || matchIndex3 >= dictLimit) {
+ match = base + matchIndex3;
+ if (match[bestLength] == ip[bestLength])
+ currMl = ZSTD_count(ip, match, iLimit);
+ } else {
+ match = dictBase + matchIndex3;
+ if (ZSTD_readMINMATCH(match, MINMATCH) ==
+ ZSTD_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
+ currMl = ZSTD_count_2segments(ip + MINMATCH, match + MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH;
+ }
+
+ /* save best solution */
+ if (currMl > bestLength) {
+ bestLength = currMl;
+ matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex3;
+ matches[mnum].len = (U32)currMl;
+ mnum++;
+ if (currMl > ZSTD_OPT_NUM)
+ goto update;
+ if (ip + currMl == iLimit)
+ goto update; /* best possible, and avoid read overflow*/
+ }
+ }
+ }
+
+ hashTable[h] = curr; /* Update Hash Table */
+
+ while (nbCompares-- && (matchIndex > windowLow)) {
+ U32 *nextPtr = bt + 2 * (matchIndex & btMask);
+ size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
+ const BYTE *match;
+
+ if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
+ match = base + matchIndex;
+ if (match[matchLength] == ip[matchLength]) {
+ matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iLimit) + 1;
+ }
+ } else {
+ match = dictBase + matchIndex;
+ matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iLimit, dictEnd, prefixStart);
+ if (matchIndex + matchLength >= dictLimit)
+ match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
+ }
+
+ if (matchLength > bestLength) {
+ if (matchLength > matchEndIdx - matchIndex)
+ matchEndIdx = matchIndex + (U32)matchLength;
+ bestLength = matchLength;
+ matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex;
+ matches[mnum].len = (U32)matchLength;
+ mnum++;
+ if (matchLength > ZSTD_OPT_NUM)
+ break;
+ if (ip + matchLength == iLimit) /* equal : no way to know if inf or sup */
+ break; /* drop, to guarantee consistency (miss a little bit of compression) */
+ }
+
+ if (match[matchLength] < ip[matchLength]) {
+ /* match is smaller than curr */
+ *smallerPtr = matchIndex; /* update smaller idx */
+ commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
+ if (matchIndex <= btLow) {
+ smallerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
+ matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */
+ } else {
+ /* match is larger than curr */
+ *largerPtr = matchIndex;
+ commonLengthLarger = matchLength;
+ if (matchIndex <= btLow) {
+ largerPtr = &dummy32;
+ break;
+ } /* beyond tree size, stop the search */
+ largerPtr = nextPtr;
+ matchIndex = nextPtr[0];
+ }
+ }
+
+ *smallerPtr = *largerPtr = 0;
+
+update:
+ zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1;
+ return mnum;
+}
+
+/** Tree updater, providing best match */
+static U32 ZSTD_BtGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls, ZSTD_match_t *matches,
+ const U32 minMatchLen)
+{
+ if (ip < zc->base + zc->nextToUpdate)
+ return 0; /* skipped area */
+ ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls);
+ return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 0, matches, minMatchLen);
+}
+
+static U32 ZSTD_BtGetAllMatches_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */
+ const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch,
+ ZSTD_match_t *matches, const U32 minMatchLen)
+{
+ switch (matchLengthSearch) {
+ case 3: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen);
+ default:
+ case 4: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen);
+ case 5: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen);
+ case 7:
+ case 6: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen);
+ }
+}
+
+/** Tree updater, providing best match */
+static U32 ZSTD_BtGetAllMatches_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls,
+ ZSTD_match_t *matches, const U32 minMatchLen)
+{
+ if (ip < zc->base + zc->nextToUpdate)
+ return 0; /* skipped area */
+ ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls);
+ return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 1, matches, minMatchLen);
+}
+
+static U32 ZSTD_BtGetAllMatches_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */
+ const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch,
+ ZSTD_match_t *matches, const U32 minMatchLen)
+{
+ switch (matchLengthSearch) {
+ case 3: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen);
+ default:
+ case 4: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen);
+ case 5: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen);
+ case 7:
+ case 6: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen);
+ }
+}
+
+/*-*******************************
+* Optimal parser
+*********************************/
+FORCE_INLINE
+void ZSTD_compressBlock_opt_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra)
+{
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ const BYTE *const base = ctx->base;
+ const BYTE *const prefixStart = base + ctx->dictLimit;
+
+ const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
+ const U32 sufficient_len = ctx->params.cParams.targetLength;
+ const U32 mls = ctx->params.cParams.searchLength;
+ const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+
+ ZSTD_optimal_t *opt = seqStorePtr->priceTable;
+ ZSTD_match_t *matches = seqStorePtr->matchTable;
+ const BYTE *inr;
+ U32 offset, rep[ZSTD_REP_NUM];
+
+ /* init */
+ ctx->nextToUpdate3 = ctx->nextToUpdate;
+ ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize);
+ ip += (ip == prefixStart);
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ rep[i] = ctx->rep[i];
+ }
+
+ /* Match Loop */
+ while (ip < ilimit) {
+ U32 cur, match_num, last_pos, litlen, price;
+ U32 u, mlen, best_mlen, best_off, litLength;
+ memset(opt, 0, sizeof(ZSTD_optimal_t));
+ last_pos = 0;
+ litlen = (U32)(ip - anchor);
+
+ /* check repCode */
+ {
+ U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor);
+ for (i = (ip == anchor); i < last_i; i++) {
+ const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
+ if ((repCur > 0) && (repCur < (S32)(ip - prefixStart)) &&
+ (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) {
+ mlen = (U32)ZSTD_count(ip + minMatch, ip + minMatch - repCur, iend) + minMatch;
+ if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
+ best_mlen = mlen;
+ best_off = i;
+ cur = 0;
+ last_pos = 1;
+ goto _storeSequence;
+ }
+ best_off = i - (ip == anchor);
+ do {
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
+ if (mlen > last_pos || price < opt[mlen].price)
+ SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */
+ mlen--;
+ } while (mlen >= minMatch);
+ }
+ }
+ }
+
+ match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, ip, iend, maxSearches, mls, matches, minMatch);
+
+ if (!last_pos && !match_num) {
+ ip++;
+ continue;
+ }
+
+ if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
+ best_mlen = matches[match_num - 1].len;
+ best_off = matches[match_num - 1].off;
+ cur = 0;
+ last_pos = 1;
+ goto _storeSequence;
+ }
+
+ /* set prices using matches at position = 0 */
+ best_mlen = (last_pos) ? last_pos : minMatch;
+ for (u = 0; u < match_num; u++) {
+ mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
+ best_mlen = matches[u].len;
+ while (mlen <= best_mlen) {
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
+ if (mlen > last_pos || price < opt[mlen].price)
+ SET_PRICE(mlen, mlen, matches[u].off, litlen, price); /* note : macro modifies last_pos */
+ mlen++;
+ }
+ }
+
+ if (last_pos < minMatch) {
+ ip++;
+ continue;
+ }
+
+ /* initialize opt[0] */
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ opt[0].rep[i] = rep[i];
+ }
+ opt[0].mlen = 1;
+ opt[0].litlen = litlen;
+
+ /* check further positions */
+ for (cur = 1; cur <= last_pos; cur++) {
+ inr = ip + cur;
+
+ if (opt[cur - 1].mlen == 1) {
+ litlen = opt[cur - 1].litlen + 1;
+ if (cur > litlen) {
+ price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen);
+ } else
+ price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor);
+ } else {
+ litlen = 1;
+ price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1);
+ }
+
+ if (cur > last_pos || price <= opt[cur].price)
+ SET_PRICE(cur, 1, 0, litlen, price);
+
+ if (cur == last_pos)
+ break;
+
+ if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */
+ continue;
+
+ mlen = opt[cur].mlen;
+ if (opt[cur].off > ZSTD_REP_MOVE_OPT) {
+ opt[cur].rep[2] = opt[cur - mlen].rep[1];
+ opt[cur].rep[1] = opt[cur - mlen].rep[0];
+ opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT;
+ } else {
+ opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2];
+ opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1];
+ opt[cur].rep[0] =
+ ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]);
+ }
+
+ best_mlen = minMatch;
+ {
+ U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1);
+ for (i = (opt[cur].mlen != 1); i < last_i; i++) { /* check rep */
+ const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
+ if ((repCur > 0) && (repCur < (S32)(inr - prefixStart)) &&
+ (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) {
+ mlen = (U32)ZSTD_count(inr + minMatch, inr + minMatch - repCur, iend) + minMatch;
+
+ if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
+ best_mlen = mlen;
+ best_off = i;
+ last_pos = cur + 1;
+ goto _storeSequence;
+ }
+
+ best_off = i - (opt[cur].mlen != 1);
+ if (mlen > best_mlen)
+ best_mlen = mlen;
+
+ do {
+ if (opt[cur].mlen == 1) {
+ litlen = opt[cur].litlen;
+ if (cur > litlen) {
+ price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen,
+ best_off, mlen - MINMATCH, ultra);
+ } else
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
+ } else {
+ litlen = 0;
+ price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra);
+ }
+
+ if (cur + mlen > last_pos || price <= opt[cur + mlen].price)
+ SET_PRICE(cur + mlen, mlen, i, litlen, price);
+ mlen--;
+ } while (mlen >= minMatch);
+ }
+ }
+ }
+
+ match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, inr, iend, maxSearches, mls, matches, best_mlen);
+
+ if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
+ best_mlen = matches[match_num - 1].len;
+ best_off = matches[match_num - 1].off;
+ last_pos = cur + 1;
+ goto _storeSequence;
+ }
+
+ /* set prices using matches at position = cur */
+ for (u = 0; u < match_num; u++) {
+ mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
+ best_mlen = matches[u].len;
+
+ while (mlen <= best_mlen) {
+ if (opt[cur].mlen == 1) {
+ litlen = opt[cur].litlen;
+ if (cur > litlen)
+ price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen,
+ matches[u].off - 1, mlen - MINMATCH, ultra);
+ else
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
+ } else {
+ litlen = 0;
+ price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra);
+ }
+
+ if (cur + mlen > last_pos || (price < opt[cur + mlen].price))
+ SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price);
+
+ mlen++;
+ }
+ }
+ }
+
+ best_mlen = opt[last_pos].mlen;
+ best_off = opt[last_pos].off;
+ cur = last_pos - best_mlen;
+
+ /* store sequence */
+_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */
+ opt[0].mlen = 1;
+
+ while (1) {
+ mlen = opt[cur].mlen;
+ offset = opt[cur].off;
+ opt[cur].mlen = best_mlen;
+ opt[cur].off = best_off;
+ best_mlen = mlen;
+ best_off = offset;
+ if (mlen > cur)
+ break;
+ cur -= mlen;
+ }
+
+ for (u = 0; u <= last_pos;) {
+ u += opt[u].mlen;
+ }
+
+ for (cur = 0; cur < last_pos;) {
+ mlen = opt[cur].mlen;
+ if (mlen == 1) {
+ ip++;
+ cur++;
+ continue;
+ }
+ offset = opt[cur].off;
+ cur += mlen;
+ litLength = (U32)(ip - anchor);
+
+ if (offset > ZSTD_REP_MOVE_OPT) {
+ rep[2] = rep[1];
+ rep[1] = rep[0];
+ rep[0] = offset - ZSTD_REP_MOVE_OPT;
+ offset--;
+ } else {
+ if (offset != 0) {
+ best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]);
+ if (offset != 1)
+ rep[2] = rep[1];
+ rep[1] = rep[0];
+ rep[0] = best_off;
+ }
+ if (litLength == 0)
+ offset--;
+ }
+
+ ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
+ ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
+ anchor = ip = ip + mlen;
+ }
+ } /* for (cur=0; cur < last_pos; ) */
+
+ /* Save reps for next block */
+ {
+ int i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ ctx->repToConfirm[i] = rep[i];
+ }
+
+ /* Last Literals */
+ {
+ size_t const lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+FORCE_INLINE
+void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra)
+{
+ seqStore_t *seqStorePtr = &(ctx->seqStore);
+ const BYTE *const istart = (const BYTE *)src;
+ const BYTE *ip = istart;
+ const BYTE *anchor = istart;
+ const BYTE *const iend = istart + srcSize;
+ const BYTE *const ilimit = iend - 8;
+ const BYTE *const base = ctx->base;
+ const U32 lowestIndex = ctx->lowLimit;
+ const U32 dictLimit = ctx->dictLimit;
+ const BYTE *const prefixStart = base + dictLimit;
+ const BYTE *const dictBase = ctx->dictBase;
+ const BYTE *const dictEnd = dictBase + dictLimit;
+
+ const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
+ const U32 sufficient_len = ctx->params.cParams.targetLength;
+ const U32 mls = ctx->params.cParams.searchLength;
+ const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+
+ ZSTD_optimal_t *opt = seqStorePtr->priceTable;
+ ZSTD_match_t *matches = seqStorePtr->matchTable;
+ const BYTE *inr;
+
+ /* init */
+ U32 offset, rep[ZSTD_REP_NUM];
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ rep[i] = ctx->rep[i];
+ }
+
+ ctx->nextToUpdate3 = ctx->nextToUpdate;
+ ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize);
+ ip += (ip == prefixStart);
+
+ /* Match Loop */
+ while (ip < ilimit) {
+ U32 cur, match_num, last_pos, litlen, price;
+ U32 u, mlen, best_mlen, best_off, litLength;
+ U32 curr = (U32)(ip - base);
+ memset(opt, 0, sizeof(ZSTD_optimal_t));
+ last_pos = 0;
+ opt[0].litlen = (U32)(ip - anchor);
+
+ /* check repCode */
+ {
+ U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor);
+ for (i = (ip == anchor); i < last_i; i++) {
+ const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
+ const U32 repIndex = (U32)(curr - repCur);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if ((repCur > 0 && repCur <= (S32)curr) &&
+ (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) {
+ /* repcode detected we should take it */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ mlen = (U32)ZSTD_count_2segments(ip + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch;
+
+ if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
+ best_mlen = mlen;
+ best_off = i;
+ cur = 0;
+ last_pos = 1;
+ goto _storeSequence;
+ }
+
+ best_off = i - (ip == anchor);
+ litlen = opt[0].litlen;
+ do {
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
+ if (mlen > last_pos || price < opt[mlen].price)
+ SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */
+ mlen--;
+ } while (mlen >= minMatch);
+ }
+ }
+ }
+
+ match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, ip, iend, maxSearches, mls, matches, minMatch); /* first search (depth 0) */
+
+ if (!last_pos && !match_num) {
+ ip++;
+ continue;
+ }
+
+ {
+ U32 i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ opt[0].rep[i] = rep[i];
+ }
+ opt[0].mlen = 1;
+
+ if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
+ best_mlen = matches[match_num - 1].len;
+ best_off = matches[match_num - 1].off;
+ cur = 0;
+ last_pos = 1;
+ goto _storeSequence;
+ }
+
+ best_mlen = (last_pos) ? last_pos : minMatch;
+
+ /* set prices using matches at position = 0 */
+ for (u = 0; u < match_num; u++) {
+ mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
+ best_mlen = matches[u].len;
+ litlen = opt[0].litlen;
+ while (mlen <= best_mlen) {
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
+ if (mlen > last_pos || price < opt[mlen].price)
+ SET_PRICE(mlen, mlen, matches[u].off, litlen, price);
+ mlen++;
+ }
+ }
+
+ if (last_pos < minMatch) {
+ ip++;
+ continue;
+ }
+
+ /* check further positions */
+ for (cur = 1; cur <= last_pos; cur++) {
+ inr = ip + cur;
+
+ if (opt[cur - 1].mlen == 1) {
+ litlen = opt[cur - 1].litlen + 1;
+ if (cur > litlen) {
+ price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen);
+ } else
+ price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor);
+ } else {
+ litlen = 1;
+ price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1);
+ }
+
+ if (cur > last_pos || price <= opt[cur].price)
+ SET_PRICE(cur, 1, 0, litlen, price);
+
+ if (cur == last_pos)
+ break;
+
+ if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */
+ continue;
+
+ mlen = opt[cur].mlen;
+ if (opt[cur].off > ZSTD_REP_MOVE_OPT) {
+ opt[cur].rep[2] = opt[cur - mlen].rep[1];
+ opt[cur].rep[1] = opt[cur - mlen].rep[0];
+ opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT;
+ } else {
+ opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2];
+ opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1];
+ opt[cur].rep[0] =
+ ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]);
+ }
+
+ best_mlen = minMatch;
+ {
+ U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1);
+ for (i = (mlen != 1); i < last_i; i++) {
+ const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
+ const U32 repIndex = (U32)(curr + cur - repCur);
+ const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
+ const BYTE *const repMatch = repBase + repIndex;
+ if ((repCur > 0 && repCur <= (S32)(curr + cur)) &&
+ (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
+ && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) {
+ /* repcode detected */
+ const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
+ mlen = (U32)ZSTD_count_2segments(inr + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch;
+
+ if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
+ best_mlen = mlen;
+ best_off = i;
+ last_pos = cur + 1;
+ goto _storeSequence;
+ }
+
+ best_off = i - (opt[cur].mlen != 1);
+ if (mlen > best_mlen)
+ best_mlen = mlen;
+
+ do {
+ if (opt[cur].mlen == 1) {
+ litlen = opt[cur].litlen;
+ if (cur > litlen) {
+ price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen,
+ best_off, mlen - MINMATCH, ultra);
+ } else
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
+ } else {
+ litlen = 0;
+ price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra);
+ }
+
+ if (cur + mlen > last_pos || price <= opt[cur + mlen].price)
+ SET_PRICE(cur + mlen, mlen, i, litlen, price);
+ mlen--;
+ } while (mlen >= minMatch);
+ }
+ }
+ }
+
+ match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, inr, iend, maxSearches, mls, matches, minMatch);
+
+ if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
+ best_mlen = matches[match_num - 1].len;
+ best_off = matches[match_num - 1].off;
+ last_pos = cur + 1;
+ goto _storeSequence;
+ }
+
+ /* set prices using matches at position = cur */
+ for (u = 0; u < match_num; u++) {
+ mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
+ best_mlen = matches[u].len;
+
+ while (mlen <= best_mlen) {
+ if (opt[cur].mlen == 1) {
+ litlen = opt[cur].litlen;
+ if (cur > litlen)
+ price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen,
+ matches[u].off - 1, mlen - MINMATCH, ultra);
+ else
+ price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
+ } else {
+ litlen = 0;
+ price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra);
+ }
+
+ if (cur + mlen > last_pos || (price < opt[cur + mlen].price))
+ SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price);
+
+ mlen++;
+ }
+ }
+ } /* for (cur = 1; cur <= last_pos; cur++) */
+
+ best_mlen = opt[last_pos].mlen;
+ best_off = opt[last_pos].off;
+ cur = last_pos - best_mlen;
+
+ /* store sequence */
+_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */
+ opt[0].mlen = 1;
+
+ while (1) {
+ mlen = opt[cur].mlen;
+ offset = opt[cur].off;
+ opt[cur].mlen = best_mlen;
+ opt[cur].off = best_off;
+ best_mlen = mlen;
+ best_off = offset;
+ if (mlen > cur)
+ break;
+ cur -= mlen;
+ }
+
+ for (u = 0; u <= last_pos;) {
+ u += opt[u].mlen;
+ }
+
+ for (cur = 0; cur < last_pos;) {
+ mlen = opt[cur].mlen;
+ if (mlen == 1) {
+ ip++;
+ cur++;
+ continue;
+ }
+ offset = opt[cur].off;
+ cur += mlen;
+ litLength = (U32)(ip - anchor);
+
+ if (offset > ZSTD_REP_MOVE_OPT) {
+ rep[2] = rep[1];
+ rep[1] = rep[0];
+ rep[0] = offset - ZSTD_REP_MOVE_OPT;
+ offset--;
+ } else {
+ if (offset != 0) {
+ best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]);
+ if (offset != 1)
+ rep[2] = rep[1];
+ rep[1] = rep[0];
+ rep[0] = best_off;
+ }
+
+ if (litLength == 0)
+ offset--;
+ }
+
+ ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
+ ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
+ anchor = ip = ip + mlen;
+ }
+ } /* for (cur=0; cur < last_pos; ) */
+
+ /* Save reps for next block */
+ {
+ int i;
+ for (i = 0; i < ZSTD_REP_NUM; i++)
+ ctx->repToConfirm[i] = rep[i];
+ }
+
+ /* Last Literals */
+ {
+ size_t lastLLSize = iend - anchor;
+ memcpy(seqStorePtr->lit, anchor, lastLLSize);
+ seqStorePtr->lit += lastLLSize;
+ }
+}
+
+#endif /* ZSTD_OPT_H_91842398743 */
diff --git a/mm/compaction.c b/mm/compaction.c
index 70e6bec..d06ac2f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -20,6 +20,7 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/page_owner.h>
+#include <linux/psi.h>
#include "internal.h"
#ifdef CONFIG_COMPACTION
@@ -1973,11 +1974,15 @@ static int kcompactd(void *p)
pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
while (!kthread_should_stop()) {
+ unsigned long pflags;
+
trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
wait_event_freezable(pgdat->kcompactd_wait,
kcompactd_work_requested(pgdat));
+ psi_memstall_enter(&pflags);
kcompactd_do_work(pgdat);
+ psi_memstall_leave(&pflags);
}
return 0;
diff --git a/mm/debug.c b/mm/debug.c
index bebe48a..dc7ad1f 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -49,7 +49,7 @@ void __dump_page(struct page *page, const char *reason)
*/
int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
- pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
+ pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
page->mapping, page_to_pgoff(page));
if (PageCompound(page))
@@ -64,7 +64,7 @@ void __dump_page(struct page *page, const char *reason)
#ifdef CONFIG_MEMCG
if (page->mem_cgroup)
- pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+ pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
@@ -79,10 +79,10 @@ EXPORT_SYMBOL(dump_page);
void dump_vma(const struct vm_area_struct *vma)
{
- pr_emerg("vma %p start %p end %p\n"
- "next %p prev %p mm %p\n"
- "prot %lx anon_vma %p vm_ops %p\n"
- "pgoff %lx file %p private_data %p\n"
+ pr_emerg("vma %px start %px end %px\n"
+ "next %px prev %px mm %px\n"
+ "prot %lx anon_vma %px vm_ops %px\n"
+ "pgoff %lx file %px private_data %px\n"
"flags: %#lx(%pGv)\n",
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
vma->vm_prev, vma->vm_mm,
@@ -95,27 +95,27 @@ EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
- pr_emerg("mm %p mmap %p seqnum %llu task_size %lu\n"
+ pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
#ifdef CONFIG_MMU
- "get_unmapped_area %p\n"
+ "get_unmapped_area %px\n"
#endif
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
- "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
+ "pgd %px mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
"start_brk %lx brk %lx start_stack %lx\n"
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
- "binfmt %p flags %lx core_state %p\n"
+ "binfmt %px flags %lx core_state %px\n"
#ifdef CONFIG_AIO
- "ioctx_table %p\n"
+ "ioctx_table %px\n"
#endif
#ifdef CONFIG_MEMCG
- "owner %p "
+ "owner %px "
#endif
- "exe_file %p\n"
+ "exe_file %px\n"
#ifdef CONFIG_MMU_NOTIFIER
- "mmu_notifier_mm %p\n"
+ "mmu_notifier_mm %px\n"
#endif
#ifdef CONFIG_NUMA_BALANCING
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
diff --git a/mm/filemap.c b/mm/filemap.c
index 05af91f..dfeb7fc 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -35,6 +35,8 @@
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/rmap.h>
+#include <linux/delayacct.h>
+#include <linux/psi.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
@@ -438,19 +440,17 @@ static int __filemap_fdatawait_range(struct address_space *mapping,
goto out;
pagevec_init(&pvec, 0);
- while ((index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_WRITEBACK,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
+ while (index <= end) {
unsigned i;
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
+ end, PAGECACHE_TAG_WRITEBACK);
+ if (!nr_pages)
+ break;
+
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- /* until radix tree lookup accepts end_index */
- if (page->index > end)
- continue;
-
wait_on_page_writeback(page);
if (TestClearPageError(page))
ret = -EIO;
@@ -746,12 +746,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
- if (!(gfp_mask & __GFP_WRITE) &&
- shadow && workingset_refault(shadow)) {
- SetPageActive(page);
- workingset_activation(page);
- } else
- ClearPageActive(page);
+ WARN_ON_ONCE(PageActive(page));
+ if (!(gfp_mask & __GFP_WRITE) && shadow)
+ workingset_refault(page, shadow);
lru_cache_add(page);
}
return ret;
@@ -789,46 +786,177 @@ EXPORT_SYMBOL(__page_cache_alloc);
* at a cost of "thundering herd" phenomena during rare hash
* collisions.
*/
-wait_queue_head_t *page_waitqueue(struct page *page)
+#define PAGE_WAIT_TABLE_BITS 8
+#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
+static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
{
- return bit_waitqueue(page, 0);
+ return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
}
-EXPORT_SYMBOL(page_waitqueue);
+
+void __init pagecache_init(void)
+{
+ int i;
+
+ for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
+ init_waitqueue_head(&page_wait_table[i]);
+
+ page_writeback_init();
+}
+
+struct wait_page_key {
+ struct page *page;
+ int bit_nr;
+ int page_match;
+};
+
+struct wait_page_queue {
+ struct page *page;
+ int bit_nr;
+ wait_queue_t wait;
+};
+
+static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+{
+ struct wait_page_key *key = arg;
+ struct wait_page_queue *wait_page
+ = container_of(wait, struct wait_page_queue, wait);
+
+ if (wait_page->page != key->page)
+ return 0;
+ key->page_match = 1;
+
+ if (wait_page->bit_nr != key->bit_nr)
+ return 0;
+ if (test_bit(key->bit_nr, &key->page->flags))
+ return 0;
+
+ return autoremove_wake_function(wait, mode, sync, key);
+}
+
+void wake_up_page_bit(struct page *page, int bit_nr)
+{
+ wait_queue_head_t *q = page_waitqueue(page);
+ struct wait_page_key key;
+ unsigned long flags;
+
+ key.page = page;
+ key.bit_nr = bit_nr;
+ key.page_match = 0;
+
+ spin_lock_irqsave(&q->lock, flags);
+ __wake_up_locked_key(q, TASK_NORMAL, &key);
+ /*
+ * It is possible for other pages to have collided on the waitqueue
+ * hash, so in that case check for a page match. That prevents a long-
+ * term waiter
+ *
+ * It is still possible to miss a case here, when we woke page waiters
+ * and removed them from the waitqueue, but there are still other
+ * page waiters.
+ */
+ if (!waitqueue_active(q) || !key.page_match) {
+ ClearPageWaiters(page);
+ /*
+ * It's possible to miss clearing Waiters here, when we woke
+ * our page waiters, but the hashed waitqueue has waiters for
+ * other pages on it.
+ *
+ * That's okay, it's a rare case. The next waker will clear it.
+ */
+ }
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(wake_up_page_bit);
+
+static inline int wait_on_page_bit_common(wait_queue_head_t *q,
+ struct page *page, int bit_nr, int state, bool lock)
+{
+ struct wait_page_queue wait_page;
+ wait_queue_t *wait = &wait_page.wait;
+ bool thrashing = false;
+ unsigned long pflags;
+ int ret = 0;
+
+ if (bit_nr == PG_locked &&
+ !PageUptodate(page) && PageWorkingset(page)) {
+ if (!PageSwapBacked(page))
+ delayacct_thrashing_start();
+ psi_memstall_enter(&pflags);
+ thrashing = true;
+ }
+
+ init_wait(wait);
+ wait->func = wake_page_function;
+ wait_page.page = page;
+ wait_page.bit_nr = bit_nr;
+
+ for (;;) {
+ spin_lock_irq(&q->lock);
+
+ if (likely(list_empty(&wait->task_list))) {
+ if (lock)
+ __add_wait_queue_tail_exclusive(q, wait);
+ else
+ __add_wait_queue(q, wait);
+ SetPageWaiters(page);
+ }
+
+ set_current_state(state);
+
+ spin_unlock_irq(&q->lock);
+
+ if (likely(test_bit(bit_nr, &page->flags))) {
+ io_schedule();
+ }
+
+ if (lock) {
+ if (!test_and_set_bit_lock(bit_nr, &page->flags))
+ break;
+ } else {
+ if (!test_bit(bit_nr, &page->flags))
+ break;
+ }
+
+ if (unlikely(signal_pending_state(state, current))) {
+ ret = -EINTR;
+ break;
+ }
+ }
+
+ finish_wait(q, wait);
+
+ if (thrashing) {
+ if (!PageSwapBacked(page))
+ delayacct_thrashing_end();
+ psi_memstall_leave(&pflags);
+ }
+
+ /*
+ * A signal could leave PageWaiters set. Clearing it here if
+ * !waitqueue_active would be possible (by open-coding finish_wait),
+ * but still fail to catch it in the case of wait hash collision. We
+ * already can fail to clear wait hash collision cases, so don't
+ * bother with signals either.
+ */
+
+ return ret;
+}
void wait_on_page_bit(struct page *page, int bit_nr)
{
- DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
- if (test_bit(bit_nr, &page->flags))
- __wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
- TASK_UNINTERRUPTIBLE);
+ wait_queue_head_t *q = page_waitqueue(page);
+ wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
}
EXPORT_SYMBOL(wait_on_page_bit);
int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
- DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
- if (!test_bit(bit_nr, &page->flags))
- return 0;
-
- return __wait_on_bit(page_waitqueue(page), &wait,
- bit_wait_io, TASK_KILLABLE);
+ wait_queue_head_t *q = page_waitqueue(page);
+ return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
}
-int wait_on_page_bit_killable_timeout(struct page *page,
- int bit_nr, unsigned long timeout)
-{
- DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
- wait.key.timeout = jiffies + timeout;
- if (!test_bit(bit_nr, &page->flags))
- return 0;
- return __wait_on_bit(page_waitqueue(page), &wait,
- bit_wait_io_timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
-
/**
* add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
* @page: Page defining the wait queue of interest
@@ -843,6 +971,7 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue(q, waiter);
+ SetPageWaiters(page);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(add_page_wait_queue);
@@ -927,23 +1056,19 @@ EXPORT_SYMBOL_GPL(page_endio);
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
*/
-void __lock_page(struct page *page)
+void __lock_page(struct page *__page)
{
- struct page *page_head = compound_head(page);
- DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
- __wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
- TASK_UNINTERRUPTIBLE);
+ struct page *page = compound_head(__page);
+ wait_queue_head_t *q = page_waitqueue(page);
+ wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
}
EXPORT_SYMBOL(__lock_page);
-int __lock_page_killable(struct page *page)
+int __lock_page_killable(struct page *__page)
{
- struct page *page_head = compound_head(page);
- DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
- return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
- bit_wait_io, TASK_KILLABLE);
+ struct page *page = compound_head(__page);
+ wait_queue_head_t *q = page_waitqueue(page);
+ return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
@@ -1189,6 +1314,9 @@ EXPORT_SYMBOL(find_lock_entry);
* @gfp_mask and added to the page cache and the VM's LRU
* list. The page is returned locked and with an increased
* refcount. Otherwise, %NULL is returned.
+ * FGP_FOR_MMAP: Similar to FGP_CREAT, only we want to allow the caller to do
+ * its own locking dance if the page is already in cache, or unlock the page
+ * before returning if we had to add the page to pagecache.
*
* If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
* if the GFP flags specified for FGP_CREAT are atomic.
@@ -1241,7 +1369,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
if (!page)
return NULL;
- if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+ if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
fgp_flags |= FGP_LOCK;
/* Init accessed so avoid atomic mark_page_accessed later */
@@ -1255,6 +1383,14 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
if (err == -EEXIST)
goto repeat;
}
+
+ /*
+ * add_to_page_cache_lru lock's the page, and for mmap we expect
+ * a unlocked page.
+ */
+ if (page && (fgp_flags & FGP_FOR_MMAP))
+ unlock_page(page);
+
}
return page;
@@ -1492,9 +1628,10 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
EXPORT_SYMBOL(find_get_pages_contig);
/**
- * find_get_pages_tag - find and return pages that match @tag
+ * find_get_pages_range_tag - find and return pages in given range matching @tag
* @mapping: the address_space to search
* @index: the starting page index
+ * @end: The final page index (inclusive)
* @tag: the tag index
* @nr_pages: the maximum number of pages
* @pages: where the resulting pages are placed
@@ -1502,8 +1639,9 @@ EXPORT_SYMBOL(find_get_pages_contig);
* Like find_get_pages, except we only return pages which are tagged with
* @tag. We update @index to index the next page for the traversal.
*/
-unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
- int tag, unsigned int nr_pages, struct page **pages)
+unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
+ pgoff_t end, int tag, unsigned int nr_pages,
+ struct page **pages)
{
struct radix_tree_iter iter;
void **slot;
@@ -1516,6 +1654,9 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
radix_tree_for_each_tagged(slot, &mapping->page_tree,
&iter, *index, tag) {
struct page *head, *page;
+
+ if (iter.index > end)
+ break;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
@@ -1557,18 +1698,28 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
}
pages[ret] = page;
- if (++ret == nr_pages)
- break;
+ if (++ret == nr_pages) {
+ *index = pages[ret - 1]->index + 1;
+ goto out;
+ }
}
+ /*
+ * We come here when we got at @end. We take care to not overflow the
+ * index @index as it confuses some of the callers. This breaks the
+ * iteration when there is page at index -1 but that is already broken
+ * anyway.
+ */
+ if (end == (pgoff_t)-1)
+ *index = (pgoff_t)-1;
+ else
+ *index = end + 1;
+out:
rcu_read_unlock();
- if (ret)
- *index = pages[ret - 1]->index + 1;
-
return ret;
}
-EXPORT_SYMBOL(find_get_pages_tag);
+EXPORT_SYMBOL(find_get_pages_range_tag);
/**
* find_get_entries_tag - find and return entries that match @tag
@@ -1976,62 +2127,96 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
EXPORT_SYMBOL(generic_file_read_iter);
#ifdef CONFIG_MMU
-/**
- * page_cache_read - adds requested page to the page cache if not already there
- * @file: file to read
- * @offset: page index
- * @gfp_mask: memory allocation flags
- *
- * This adds the requested page to the page cache if it isn't already there,
- * and schedules an I/O to read in its contents from disk.
- */
-static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
-{
- struct address_space *mapping = file->f_mapping;
- struct page *page;
- int ret;
-
- do {
- page = __page_cache_alloc(gfp_mask|__GFP_COLD);
- if (!page)
- return -ENOMEM;
-
- ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
- if (ret == 0)
- ret = mapping->a_ops->readpage(file, page);
- else if (ret == -EEXIST)
- ret = 0; /* losing race to add is OK */
-
- put_page(page);
-
- } while (ret == AOP_TRUNCATED_PAGE);
-
- return ret;
-}
-
#define MMAP_LOTSAMISS (100)
+static struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma,
+ unsigned long flags, struct file *fpin)
+{
+ if (fpin)
+ return fpin;
+
+ /*
+ * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+ * anything, so we only pin the file and drop the mmap_sem if only
+ * FAULT_FLAG_ALLOW_RETRY is set.
+ */
+ if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
+ FAULT_FLAG_ALLOW_RETRY) {
+ fpin = get_file(vma->vm_file);
+ up_read(&vma->vm_mm->mmap_sem);
+ }
+ return fpin;
+}
+
/*
- * Synchronous readahead happens when we don't even find
- * a page in the page cache at all.
+ * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
+ * @vmf - the vm_fault for this fault.
+ * @page - the page to lock.
+ * @fpin - the pointer to the file we may pin (or is already pinned).
+ *
+ * This works similar to lock_page_or_retry in that it can drop the mmap_sem.
+ * It differs in that it actually returns the page locked if it returns 1 and 0
+ * if it couldn't lock the page. If we did have to drop the mmap_sem then fpin
+ * will point to the pinned file and needs to be fput()'ed at a later point.
*/
-static void do_sync_mmap_readahead(struct vm_area_struct *vma,
+static int lock_page_maybe_drop_mmap(struct vm_area_struct *vma,
+ unsigned long flags, struct page *page, struct file **fpin)
+{
+ if (trylock_page(page))
+ return 1;
+
+ /*
+ * NOTE! This will make us return with VM_FAULT_RETRY, but with
+ * the mmap_sem still held. That's how FAULT_FLAG_RETRY_NOWAIT
+ * is supposed to work. We have way too many special cases..
+ */
+ if (flags & FAULT_FLAG_RETRY_NOWAIT)
+ return 0;
+ *fpin = maybe_unlock_mmap_for_io(vma, flags, *fpin);
+ if (flags & FAULT_FLAG_KILLABLE) {
+ if (__lock_page_killable(page)) {
+ /*
+ * We didn't have the right flags to drop the mmap_sem,
+ * but all fault_handlers only check for fatal signals
+ * if we return VM_FAULT_RETRY, so we need to drop the
+ * mmap_sem here and return 0 if we don't have a fpin.
+ */
+ if (*fpin == NULL)
+ up_read(&vma->vm_mm->mmap_sem);
+ return 0;
+ }
+ } else
+ __lock_page(page);
+ return 1;
+}
+
+/*
+ * Synchronous readahead happens when we don't even find a page in the page
+ * cache at all. We don't want to perform IO under the mmap sem, so if we have
+ * to drop the mmap sem we return the file that was pinned in order for us to do
+ * that. If we didn't pin a file then we return NULL. The file that is
+ * returned needs to be fput()'ed when we're done with it.
+ */
+static struct file *do_sync_mmap_readahead(struct vm_area_struct *vma,
+ unsigned long flags,
struct file_ra_state *ra,
struct file *file,
pgoff_t offset)
{
+ struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
/* If we don't want any read-ahead, don't bother */
if (vma->vm_flags & VM_RAND_READ)
- return;
+ return fpin;
if (!ra->ra_pages)
- return;
+ return fpin;
if (vma->vm_flags & VM_SEQ_READ) {
+ fpin = maybe_unlock_mmap_for_io(vma, flags, fpin);
page_cache_sync_readahead(mapping, ra, file, offset,
ra->ra_pages);
- return;
+ return fpin;
}
/* Avoid banging the cache line if not needed */
@@ -2043,37 +2228,45 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
* stop bothering with read-ahead. It will only hurt.
*/
if (ra->mmap_miss > MMAP_LOTSAMISS)
- return;
+ return fpin;
/*
* mmap read-around
*/
+ fpin = maybe_unlock_mmap_for_io(vma, flags, fpin);
ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
ra_submit(ra, mapping, file);
+ return fpin;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
- * so we want to possibly extend the readahead further..
+ * so we want to possibly extend the readahead further. We return the file that
+ * was pinned if we have to drop the mmap_sem in order to do IO.
*/
-static void do_async_mmap_readahead(struct vm_area_struct *vma,
+static struct file *do_async_mmap_readahead(struct vm_area_struct *vma,
+ unsigned long flags,
struct file_ra_state *ra,
struct file *file,
struct page *page,
pgoff_t offset)
{
struct address_space *mapping = file->f_mapping;
+ struct file *fpin = NULL;
/* If we don't want any read-ahead, don't bother */
if (vma->vm_flags & VM_RAND_READ)
- return;
+ return fpin;
if (ra->mmap_miss > 0)
ra->mmap_miss--;
- if (PageReadahead(page))
+ if (PageReadahead(page)) {
+ fpin = maybe_unlock_mmap_for_io(vma, flags, fpin);
page_cache_async_readahead(mapping, ra, file,
page, offset, ra->ra_pages);
+ }
+ return fpin;
}
/**
@@ -2104,6 +2297,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int error;
struct file *file = vma->vm_file;
+ struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
@@ -2125,23 +2319,27 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
* We found the page, so try async readahead before
* waiting for the lock.
*/
- do_async_mmap_readahead(vma, ra, file, page, offset);
+ fpin = do_async_mmap_readahead(vma, vmf->flags, ra,
+ file, page, offset);
} else if (!page) {
/* No page in the page cache at all */
- do_sync_mmap_readahead(vma, ra, file, offset);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
+ fpin = do_sync_mmap_readahead(vma, vmf->flags, ra,
+ file, offset);
retry_find:
- page = find_get_page(mapping, offset);
- if (!page)
- goto no_cached_page;
+ page = pagecache_get_page(mapping, offset,
+ FGP_CREAT|FGP_FOR_MMAP,
+ vmf->gfp_mask);
+ if (!page) {
+ if (fpin)
+ goto out_retry;
+ return VM_FAULT_OOM;
+ }
}
-
- if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
- put_page(page);
- return ret | VM_FAULT_RETRY;
- }
+ if (!lock_page_maybe_drop_mmap(vma, vmf->flags, page, &fpin))
+ goto out_retry;
/* Did it get truncated? */
if (unlikely(page->mapping != mapping)) {
@@ -2159,6 +2357,16 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
goto page_not_uptodate;
/*
+ * We've made it this far and we had to drop our mmap_sem, now is the
+ * time to return to the upper layer and have it re-find the vma and
+ * redo the fault.
+ */
+ if (fpin) {
+ unlock_page(page);
+ goto out_retry;
+ }
+
+ /*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
@@ -2172,30 +2380,6 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
vmf->page = page;
return ret | VM_FAULT_LOCKED;
-no_cached_page:
- /*
- * We're only likely to ever get here if MADV_RANDOM is in
- * effect.
- */
- error = page_cache_read(file, offset, vmf->gfp_mask);
-
- /*
- * The page we want has now been added to the page cache.
- * In the unlikely event that someone removed it in the
- * meantime, we'll just come back here and read it again.
- */
- if (error >= 0)
- goto retry_find;
-
- /*
- * An error return from page_cache_read can result if the
- * system is low on memory, or a problem occurs while trying
- * to schedule I/O.
- */
- if (error == -ENOMEM)
- return VM_FAULT_OOM;
- return VM_FAULT_SIGBUS;
-
page_not_uptodate:
/*
* Umm, take care of errors if the page isn't up-to-date.
@@ -2204,12 +2388,15 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
* and we need to check for errors.
*/
ClearPageError(page);
+ fpin = maybe_unlock_mmap_for_io(vma, vmf->flags, fpin);
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (!PageUptodate(page))
error = -EIO;
}
+ if (fpin)
+ goto out_retry;
put_page(page);
if (!error || error == AOP_TRUNCATED_PAGE)
@@ -2218,6 +2405,18 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
/* Things didn't work out. Return zero to tell the mm layer so. */
shrink_readahead_size_eio(file, ra);
return VM_FAULT_SIGBUS;
+
+out_retry:
+ /*
+ * We dropped the mmap_sem, we need to return to the fault handler to
+ * re-find the vma and come back and find our hopefully still populated
+ * page.
+ */
+ if (page)
+ put_page(page);
+ if (fpin)
+ fput(fpin);
+ return ret | VM_FAULT_RETRY;
}
EXPORT_SYMBOL(filemap_fault);
@@ -2388,7 +2587,7 @@ static struct page *wait_on_page_read(struct page *page)
static struct page *do_read_cache_page(struct address_space *mapping,
pgoff_t index,
- int (*filler)(void *, struct page *),
+ int (*filler)(struct file *, struct page *),
void *data,
gfp_t gfp)
{
@@ -2503,7 +2702,7 @@ static struct page *do_read_cache_page(struct address_space *mapping,
*/
struct page *read_cache_page(struct address_space *mapping,
pgoff_t index,
- int (*filler)(void *, struct page *),
+ int (*filler)(struct file *, struct page *),
void *data)
{
return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
@@ -2525,7 +2724,7 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
pgoff_t index,
gfp_t gfp)
{
- filler_t *filler = (filler_t *)mapping->a_ops->readpage;
+ filler_t *filler = mapping->a_ops->readpage;
return do_read_cache_page(mapping, index, filler, NULL, gfp);
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0385c57..24b74f3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1914,6 +1914,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
+ (1L << PG_workingset) |
(1L << PG_locked) |
(1L << PG_unevictable) |
(1L << PG_dirty)));
diff --git a/mm/internal.h b/mm/internal.h
index f6df7cb..1bbe099 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -36,6 +36,8 @@
/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
+void page_writeback_init(void);
+
int do_swap_page(struct fault_env *fe, pte_t orig_pte);
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 1169c1f..3c57210 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -39,6 +39,16 @@
#include "kasan.h"
#include "../slab.h"
+void kasan_enable_current(void)
+{
+ current->kasan_depth++;
+}
+
+void kasan_disable_current(void)
+{
+ current->kasan_depth--;
+}
+
/*
* Poisons the shadow memory for 'size' bytes starting from 'addr'.
* Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
@@ -435,7 +445,7 @@ void kasan_cache_shrink(struct kmem_cache *cache)
quarantine_remove_cache(cache);
}
-void kasan_cache_destroy(struct kmem_cache *cache)
+void kasan_cache_shutdown(struct kmem_cache *cache)
{
quarantine_remove_cache(cache);
}
@@ -566,7 +576,8 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object)
shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) {
- kasan_report_double_free(cache, object, shadow_byte);
+ kasan_report_double_free(cache, object,
+ __builtin_return_address(1));
return true;
}
@@ -791,6 +802,55 @@ void __asan_unpoison_stack_memory(const void *addr, size_t size)
}
EXPORT_SYMBOL(__asan_unpoison_stack_memory);
+/* Emitted by compiler to poison alloca()ed objects. */
+void __asan_alloca_poison(unsigned long addr, size_t size)
+{
+ size_t rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
+ size_t padding_size = round_up(size, KASAN_ALLOCA_REDZONE_SIZE) -
+ rounded_up_size;
+ size_t rounded_down_size = round_down(size, KASAN_SHADOW_SCALE_SIZE);
+
+ const void *left_redzone = (const void *)(addr -
+ KASAN_ALLOCA_REDZONE_SIZE);
+ const void *right_redzone = (const void *)(addr + rounded_up_size);
+
+ WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE));
+
+ kasan_unpoison_shadow((const void *)(addr + rounded_down_size),
+ size - rounded_down_size);
+ kasan_poison_shadow(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
+ KASAN_ALLOCA_LEFT);
+ kasan_poison_shadow(right_redzone,
+ padding_size + KASAN_ALLOCA_REDZONE_SIZE,
+ KASAN_ALLOCA_RIGHT);
+}
+EXPORT_SYMBOL(__asan_alloca_poison);
+
+/* Emitted by compiler to unpoison alloca()ed areas when the stack unwinds. */
+void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom)
+{
+ if (unlikely(!stack_top || stack_top > stack_bottom))
+ return;
+
+ kasan_unpoison_shadow(stack_top, stack_bottom - stack_top);
+}
+EXPORT_SYMBOL(__asan_allocas_unpoison);
+
+/* Emitted by the compiler to [un]poison local variables. */
+#define DEFINE_ASAN_SET_SHADOW(byte) \
+ void __asan_set_shadow_##byte(const void *addr, size_t size) \
+ { \
+ __memset((void *)addr, 0x##byte, size); \
+ } \
+ EXPORT_SYMBOL(__asan_set_shadow_##byte)
+
+DEFINE_ASAN_SET_SHADOW(00);
+DEFINE_ASAN_SET_SHADOW(f1);
+DEFINE_ASAN_SET_SHADOW(f2);
+DEFINE_ASAN_SET_SHADOW(f3);
+DEFINE_ASAN_SET_SHADOW(f5);
+DEFINE_ASAN_SET_SHADOW(f8);
+
#ifdef CONFIG_MEMORY_HOTPLUG
static int kasan_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 1c260e6..d9cf9e2 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -23,6 +23,14 @@
#define KASAN_STACK_PARTIAL 0xF4
#define KASAN_USE_AFTER_SCOPE 0xF8
+/*
+ * alloca redzone shadow values
+ */
+#define KASAN_ALLOCA_LEFT 0xCA
+#define KASAN_ALLOCA_RIGHT 0xCB
+
+#define KASAN_ALLOCA_REDZONE_SIZE 32
+
/* Don't break randconfig/all*config builds */
#ifndef KASAN_ABI_VERSION
#define KASAN_ABI_VERSION 1
@@ -96,15 +104,10 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
<< KASAN_SHADOW_SCALE_SHIFT);
}
-static inline bool kasan_report_enabled(void)
-{
- return !current->kasan_depth;
-}
-
void kasan_report(unsigned long addr, size_t size,
bool is_write, unsigned long ip);
void kasan_report_double_free(struct kmem_cache *cache, void *object,
- s8 shadow);
+ void *ip);
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
@@ -117,4 +120,48 @@ static inline void quarantine_reduce(void) { }
static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
#endif
+/*
+ * Exported functions for interfaces called from assembly or from generated
+ * code. Declarations here to avoid warning about missing declarations.
+ */
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark);
+void __asan_register_globals(struct kasan_global *globals, size_t size);
+void __asan_unregister_globals(struct kasan_global *globals, size_t size);
+void __asan_loadN(unsigned long addr, size_t size);
+void __asan_storeN(unsigned long addr, size_t size);
+void __asan_handle_no_return(void);
+void __asan_poison_stack_memory(const void *addr, size_t size);
+void __asan_unpoison_stack_memory(const void *addr, size_t size);
+void __asan_alloca_poison(unsigned long addr, size_t size);
+void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom);
+
+void __asan_load1(unsigned long addr);
+void __asan_store1(unsigned long addr);
+void __asan_load2(unsigned long addr);
+void __asan_store2(unsigned long addr);
+void __asan_load4(unsigned long addr);
+void __asan_store4(unsigned long addr);
+void __asan_load8(unsigned long addr);
+void __asan_store8(unsigned long addr);
+void __asan_load16(unsigned long addr);
+void __asan_store16(unsigned long addr);
+
+void __asan_load1_noabort(unsigned long addr);
+void __asan_store1_noabort(unsigned long addr);
+void __asan_load2_noabort(unsigned long addr);
+void __asan_store2_noabort(unsigned long addr);
+void __asan_load4_noabort(unsigned long addr);
+void __asan_store4_noabort(unsigned long addr);
+void __asan_load8_noabort(unsigned long addr);
+void __asan_store8_noabort(unsigned long addr);
+void __asan_load16_noabort(unsigned long addr);
+void __asan_store16_noabort(unsigned long addr);
+
+void __asan_set_shadow_00(const void *addr, size_t size);
+void __asan_set_shadow_f1(const void *addr, size_t size);
+void __asan_set_shadow_f2(const void *addr, size_t size);
+void __asan_set_shadow_f3(const void *addr, size_t size);
+void __asan_set_shadow_f5(const void *addr, size_t size);
+void __asan_set_shadow_f8(const void *addr, size_t size);
+
#endif
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index baabaad..3a8ddf8 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -25,6 +25,7 @@
#include <linux/printk.h>
#include <linux/shrinker.h>
#include <linux/slab.h>
+#include <linux/srcu.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -86,24 +87,9 @@ static void qlist_move_all(struct qlist_head *from, struct qlist_head *to)
qlist_init(from);
}
-static void qlist_move(struct qlist_head *from, struct qlist_node *last,
- struct qlist_head *to, size_t size)
-{
- if (unlikely(last == from->tail)) {
- qlist_move_all(from, to);
- return;
- }
- if (qlist_empty(to))
- to->head = from->head;
- else
- to->tail->next = from->head;
- to->tail = last;
- from->head = last->next;
- last->next = NULL;
- from->bytes -= size;
- to->bytes += size;
-}
-
+#define QUARANTINE_PERCPU_SIZE (1 << 20)
+#define QUARANTINE_BATCHES \
+ (1024 > 4 * CONFIG_NR_CPUS ? 1024 : 4 * CONFIG_NR_CPUS)
/*
* The object quarantine consists of per-cpu queues and a global queue,
@@ -111,11 +97,23 @@ static void qlist_move(struct qlist_head *from, struct qlist_node *last,
*/
static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine);
-static struct qlist_head global_quarantine;
+/* Round-robin FIFO array of batches. */
+static struct qlist_head global_quarantine[QUARANTINE_BATCHES];
+static int quarantine_head;
+static int quarantine_tail;
+/* Total size of all objects in global_quarantine across all batches. */
+static unsigned long quarantine_size;
static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
/* Maximum size of the global queue. */
-static unsigned long quarantine_size;
+static unsigned long quarantine_max_size;
+
+/*
+ * Target size of a batch in global_quarantine.
+ * Usually equal to QUARANTINE_PERCPU_SIZE unless we have too much RAM.
+ */
+static unsigned long quarantine_batch_size;
/*
* The fraction of physical memory the quarantine is allowed to occupy.
@@ -124,9 +122,6 @@ static unsigned long quarantine_size;
*/
#define QUARANTINE_FRACTION 32
-#define QUARANTINE_LOW_SIZE (READ_ONCE(quarantine_size) * 3 / 4)
-#define QUARANTINE_PERCPU_SIZE (1 << 20)
-
static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink)
{
return virt_to_head_page(qlink)->slab_cache;
@@ -180,62 +175,89 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
struct qlist_head *q;
struct qlist_head temp = QLIST_INIT;
+ /*
+ * Note: irq must be disabled until after we move the batch to the
+ * global quarantine. Otherwise quarantine_remove_cache() can miss
+ * some objects belonging to the cache if they are in our local temp
+ * list. quarantine_remove_cache() executes on_each_cpu() at the
+ * beginning which ensures that it either sees the objects in per-cpu
+ * lists or in the global quarantine.
+ */
local_irq_save(flags);
q = this_cpu_ptr(&cpu_quarantine);
qlist_put(q, &info->quarantine_link, cache->size);
- if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+ if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
qlist_move_all(q, &temp);
- local_irq_restore(flags);
+ spin_lock(&quarantine_lock);
+ WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
+ qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
+ if (global_quarantine[quarantine_tail].bytes >=
+ READ_ONCE(quarantine_batch_size)) {
+ int new_tail;
- if (unlikely(!qlist_empty(&temp))) {
- spin_lock_irqsave(&quarantine_lock, flags);
- qlist_move_all(&temp, &global_quarantine);
- spin_unlock_irqrestore(&quarantine_lock, flags);
+ new_tail = quarantine_tail + 1;
+ if (new_tail == QUARANTINE_BATCHES)
+ new_tail = 0;
+ if (new_tail != quarantine_head)
+ quarantine_tail = new_tail;
+ }
+ spin_unlock(&quarantine_lock);
}
+
+ local_irq_restore(flags);
}
void quarantine_reduce(void)
{
- size_t new_quarantine_size, percpu_quarantines;
+ size_t total_size, new_quarantine_size, percpu_quarantines;
unsigned long flags;
+ int srcu_idx;
struct qlist_head to_free = QLIST_INIT;
- size_t size_to_free = 0;
- struct qlist_node *last;
- if (likely(READ_ONCE(global_quarantine.bytes) <=
- READ_ONCE(quarantine_size)))
+ if (likely(READ_ONCE(quarantine_size) <=
+ READ_ONCE(quarantine_max_size)))
return;
+ /*
+ * srcu critical section ensures that quarantine_remove_cache()
+ * will not miss objects belonging to the cache while they are in our
+ * local to_free list. srcu is chosen because (1) it gives us private
+ * grace period domain that does not interfere with anything else,
+ * and (2) it allows synchronize_srcu() to return without waiting
+ * if there are no pending read critical sections (which is the
+ * expected case).
+ */
+ srcu_idx = srcu_read_lock(&remove_cache_srcu);
spin_lock_irqsave(&quarantine_lock, flags);
/*
* Update quarantine size in case of hotplug. Allocate a fraction of
* the installed memory to quarantine minus per-cpu queue limits.
*/
- new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
+ total_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
QUARANTINE_FRACTION;
percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
- new_quarantine_size = (new_quarantine_size < percpu_quarantines) ?
- 0 : new_quarantine_size - percpu_quarantines;
- WRITE_ONCE(quarantine_size, new_quarantine_size);
+ new_quarantine_size = (total_size < percpu_quarantines) ?
+ 0 : total_size - percpu_quarantines;
+ WRITE_ONCE(quarantine_max_size, new_quarantine_size);
+ /* Aim at consuming at most 1/2 of slots in quarantine. */
+ WRITE_ONCE(quarantine_batch_size, max((size_t)QUARANTINE_PERCPU_SIZE,
+ 2 * total_size / QUARANTINE_BATCHES));
- last = global_quarantine.head;
- while (last) {
- struct kmem_cache *cache = qlink_to_cache(last);
-
- size_to_free += cache->size;
- if (!last->next || size_to_free >
- global_quarantine.bytes - QUARANTINE_LOW_SIZE)
- break;
- last = last->next;
+ if (likely(quarantine_size > quarantine_max_size)) {
+ qlist_move_all(&global_quarantine[quarantine_head], &to_free);
+ WRITE_ONCE(quarantine_size, quarantine_size - to_free.bytes);
+ quarantine_head++;
+ if (quarantine_head == QUARANTINE_BATCHES)
+ quarantine_head = 0;
}
- qlist_move(&global_quarantine, last, &to_free, size_to_free);
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, NULL);
+ srcu_read_unlock(&remove_cache_srcu, srcu_idx);
}
static void qlist_move_cache(struct qlist_head *from,
@@ -273,16 +295,34 @@ static void per_cpu_remove_cache(void *arg)
qlist_free_all(&to_free, cache);
}
+/* Free all quarantined objects belonging to cache. */
void quarantine_remove_cache(struct kmem_cache *cache)
{
- unsigned long flags;
+ unsigned long flags, i;
struct qlist_head to_free = QLIST_INIT;
+ /*
+ * Must be careful to not miss any objects that are being moved from
+ * per-cpu list to the global quarantine in quarantine_put(),
+ * nor objects being freed in quarantine_reduce(). on_each_cpu()
+ * achieves the first goal, while synchronize_srcu() achieves the
+ * second.
+ */
on_each_cpu(per_cpu_remove_cache, cache, 1);
spin_lock_irqsave(&quarantine_lock, flags);
- qlist_move_cache(&global_quarantine, &to_free, cache);
+ for (i = 0; i < QUARANTINE_BATCHES; i++) {
+ if (qlist_empty(&global_quarantine[i]))
+ continue;
+ qlist_move_cache(&global_quarantine[i], &to_free, cache);
+ /* Scanning whole quarantine can take a while. */
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+ cond_resched();
+ spin_lock_irqsave(&quarantine_lock, flags);
+ }
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, cache);
+
+ synchronize_srcu(&remove_cache_srcu);
}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index c505ac5..eff12e0 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,7 +13,9 @@
*
*/
+#include <linux/bitops.h>
#include <linux/ftrace.h>
+#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -49,7 +51,13 @@ static const void *find_first_bad_addr(const void *addr, size_t size)
return first_bad_addr;
}
-static void print_error_description(struct kasan_access_info *info)
+static bool addr_has_shadow(struct kasan_access_info *info)
+{
+ return (info->access_addr >=
+ kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
+}
+
+static const char *get_shadow_bug_type(struct kasan_access_info *info)
{
const char *bug_type = "unknown-crash";
u8 *shadow_addr;
@@ -94,14 +102,45 @@ static void print_error_description(struct kasan_access_info *info)
case KASAN_USE_AFTER_SCOPE:
bug_type = "use-after-scope";
break;
+ case KASAN_ALLOCA_LEFT:
+ case KASAN_ALLOCA_RIGHT:
+ bug_type = "alloca-out-of-bounds";
+ break;
}
- pr_err("BUG: KASAN: %s in %pS at addr %p\n",
- bug_type, (void *)info->ip,
- info->access_addr);
- pr_err("%s of size %zu by task %s/%d\n",
- info->is_write ? "Write" : "Read",
- info->access_size, current->comm, task_pid_nr(current));
+ return bug_type;
+}
+
+static const char *get_wild_bug_type(struct kasan_access_info *info)
+{
+ const char *bug_type = "unknown-crash";
+
+ if ((unsigned long)info->access_addr < PAGE_SIZE)
+ bug_type = "null-ptr-deref";
+ else if ((unsigned long)info->access_addr < TASK_SIZE)
+ bug_type = "user-memory-access";
+ else
+ bug_type = "wild-memory-access";
+
+ return bug_type;
+}
+
+static const char *get_bug_type(struct kasan_access_info *info)
+{
+ if (addr_has_shadow(info))
+ return get_shadow_bug_type(info);
+ return get_wild_bug_type(info);
+}
+
+static void print_error_description(struct kasan_access_info *info)
+{
+ const char *bug_type = get_bug_type(info);
+
+ pr_err("BUG: KASAN: %s in %pS\n",
+ bug_type, (void *)info->ip);
+ pr_err("%s of size %zu at addr %px by task %s/%d\n",
+ info->is_write ? "Write" : "Read", info->access_size,
+ info->access_addr, current->comm, task_pid_nr(current));
}
static inline bool kernel_or_module_addr(const void *addr)
@@ -137,12 +176,14 @@ static void kasan_end_report(unsigned long *flags)
pr_err("==================================================================\n");
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
spin_unlock_irqrestore(&report_lock, *flags);
+ if (panic_on_warn)
+ panic("panic_on_warn set ...\n");
kasan_enable_current();
}
-static void print_track(struct kasan_track *track)
+static void print_track(struct kasan_track *track, const char *prefix)
{
- pr_err("PID = %u\n", track->pid);
+ pr_err("%s by task %u:\n", prefix, track->pid);
if (track->stack) {
struct stack_trace trace;
@@ -153,59 +194,84 @@ static void print_track(struct kasan_track *track)
}
}
-static void kasan_object_err(struct kmem_cache *cache, void *object)
+static struct page *addr_to_page(const void *addr)
+{
+ if ((addr >= (void *)PAGE_OFFSET) &&
+ (addr < high_memory))
+ return virt_to_head_page(addr);
+ return NULL;
+}
+
+static void describe_object_addr(struct kmem_cache *cache, void *object,
+ const void *addr)
+{
+ unsigned long access_addr = (unsigned long)addr;
+ unsigned long object_addr = (unsigned long)object;
+ const char *rel_type;
+ int rel_bytes;
+
+ pr_err("The buggy address belongs to the object at %px\n"
+ " which belongs to the cache %s of size %d\n",
+ object, cache->name, cache->object_size);
+
+ if (!addr)
+ return;
+
+ if (access_addr < object_addr) {
+ rel_type = "to the left";
+ rel_bytes = object_addr - access_addr;
+ } else if (access_addr >= object_addr + cache->object_size) {
+ rel_type = "to the right";
+ rel_bytes = access_addr - (object_addr + cache->object_size);
+ } else {
+ rel_type = "inside";
+ rel_bytes = access_addr - object_addr;
+ }
+
+ pr_err("The buggy address is located %d bytes %s of\n"
+ " %d-byte region [%px, %px)\n",
+ rel_bytes, rel_type, cache->object_size, (void *)object_addr,
+ (void *)(object_addr + cache->object_size));
+}
+
+static void describe_object(struct kmem_cache *cache, void *object,
+ const void *addr)
{
struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
+ if (cache->flags & SLAB_KASAN) {
+ print_track(&alloc_info->alloc_track, "Allocated");
+ pr_err("\n");
+ print_track(&alloc_info->free_track, "Freed");
+ pr_err("\n");
+ }
+
+ describe_object_addr(cache, object, addr);
+}
+
+static void print_address_description(void *addr)
+{
+ struct page *page = addr_to_page(addr);
+
dump_stack();
- pr_err("Object at %p, in cache %s size: %d\n", object, cache->name,
- cache->object_size);
+ pr_err("\n");
- if (!(cache->flags & SLAB_KASAN))
- return;
+ if (page && PageSlab(page)) {
+ struct kmem_cache *cache = page->slab_cache;
+ void *object = nearest_obj(cache, page, addr);
- pr_err("Allocated:\n");
- print_track(&alloc_info->alloc_track);
- pr_err("Freed:\n");
- print_track(&alloc_info->free_track);
-}
+ describe_object(cache, object, addr);
+ }
-void kasan_report_double_free(struct kmem_cache *cache, void *object,
- s8 shadow)
-{
- unsigned long flags;
+ if (kernel_or_module_addr(addr) && !init_task_stack_addr(addr)) {
+ pr_err("The buggy address belongs to the variable:\n");
+ pr_err(" %pS\n", addr);
+ }
- kasan_start_report(&flags);
- pr_err("BUG: Double free or freeing an invalid pointer\n");
- pr_err("Unexpected shadow byte: 0x%hhX\n", shadow);
- kasan_object_err(cache, object);
- kasan_end_report(&flags);
-}
-
-static void print_address_description(struct kasan_access_info *info)
-{
- const void *addr = info->access_addr;
-
- if ((addr >= (void *)PAGE_OFFSET) &&
- (addr < high_memory)) {
- struct page *page = virt_to_head_page(addr);
-
- if (PageSlab(page)) {
- void *object;
- struct kmem_cache *cache = page->slab_cache;
- object = nearest_obj(cache, page,
- (void *)info->access_addr);
- kasan_object_err(cache, object);
- return;
- }
+ if (page) {
+ pr_err("The buggy address belongs to the page:\n");
dump_page(page, "kasan: bad access detected");
}
-
- if (kernel_or_module_addr(addr)) {
- if (!init_task_stack_addr(addr))
- pr_err("Address belongs to variable %pS\n", addr);
- }
- dump_stack();
}
static bool row_is_guilty(const void *row, const void *guilty)
@@ -240,7 +306,7 @@ static void print_shadow_for_address(const void *addr)
char shadow_buf[SHADOW_BYTES_PER_ROW];
snprintf(buffer, sizeof(buffer),
- (i == 0) ? ">%p: " : " %p: ", kaddr);
+ (i == 0) ? ">%px: " : " %px: ", kaddr);
/*
* We should not pass a shadow pointer to generic
* function, because generic functions may try to
@@ -260,37 +326,74 @@ static void print_shadow_for_address(const void *addr)
}
}
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+ void *ip)
+{
+ unsigned long flags;
+
+ kasan_start_report(&flags);
+ pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", ip);
+ pr_err("\n");
+ print_address_description(object);
+ pr_err("\n");
+ print_shadow_for_address(object);
+ kasan_end_report(&flags);
+}
+
static void kasan_report_error(struct kasan_access_info *info)
{
unsigned long flags;
- const char *bug_type;
kasan_start_report(&flags);
- if (info->access_addr <
- kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) {
- if ((unsigned long)info->access_addr < PAGE_SIZE)
- bug_type = "null-ptr-deref";
- else if ((unsigned long)info->access_addr < TASK_SIZE)
- bug_type = "user-memory-access";
- else
- bug_type = "wild-memory-access";
- pr_err("BUG: KASAN: %s on address %p\n",
- bug_type, info->access_addr);
- pr_err("%s of size %zu by task %s/%d\n",
- info->is_write ? "Write" : "Read",
- info->access_size, current->comm,
- task_pid_nr(current));
+ print_error_description(info);
+ pr_err("\n");
+
+ if (!addr_has_shadow(info)) {
dump_stack();
} else {
- print_error_description(info);
- print_address_description(info);
+ print_address_description((void *)info->access_addr);
+ pr_err("\n");
print_shadow_for_address(info->first_bad_addr);
}
kasan_end_report(&flags);
}
+static unsigned long kasan_flags;
+
+#define KASAN_BIT_REPORTED 0
+#define KASAN_BIT_MULTI_SHOT 1
+
+bool kasan_save_enable_multi_shot(void)
+{
+ return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot);
+
+void kasan_restore_multi_shot(bool enabled)
+{
+ if (!enabled)
+ clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
+
+static int __init kasan_set_multi_shot(char *str)
+{
+ set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+ return 1;
+}
+__setup("kasan_multi_shot", kasan_set_multi_shot);
+
+static inline bool kasan_report_enabled(void)
+{
+ if (current->kasan_depth)
+ return false;
+ if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
+ return true;
+ return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
+}
+
void kasan_report(unsigned long addr, size_t size,
bool is_write, unsigned long ip)
{
diff --git a/mm/madvise.c b/mm/madvise.c
index 4a01c4b..6849e4e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -109,7 +109,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2f44376..ae248cc 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -762,7 +762,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff,
- new_pol, vma->vm_userfaultfd_ctx);
+ new_pol, vma->vm_userfaultfd_ctx,
+ vma_get_anon_name(vma));
if (prev) {
vma = prev;
next = vma->vm_next;
diff --git a/mm/migrate.c b/mm/migrate.c
index b810ac1..751ca12 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -637,6 +637,8 @@ void migrate_page_copy(struct page *newpage, struct page *page)
SetPageActive(newpage);
} else if (TestClearPageUnevictable(page))
SetPageUnevictable(newpage);
+ if (PageWorkingset(page))
+ SetPageWorkingset(newpage);
if (PageChecked(page))
SetPageChecked(newpage);
if (PageMappedToDisk(page))
diff --git a/mm/mlock.c b/mm/mlock.c
index 3e7fe40..cdb1234 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -529,7 +529,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mmap.c b/mm/mmap.c
index 7c88156..ef91ea9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -964,7 +964,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
*/
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
/*
* VM_SOFTDIRTY should not prevent from VMA merging, if we
@@ -982,6 +983,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
return 0;
if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
return 0;
+ if (vma_get_anon_name(vma) != anon_name)
+ return 0;
return 1;
}
@@ -1014,9 +1017,10 @@ static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
+ if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
if (vma->vm_pgoff == vm_pgoff)
return 1;
@@ -1035,9 +1039,10 @@ static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
+ if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
pgoff_t vm_pglen;
vm_pglen = vma_pages(vma);
@@ -1048,9 +1053,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
}
/*
- * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
- * whether that can be merged with its predecessor or its successor.
- * Or both (it neatly fills a hole).
+ * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
+ * figure out whether that can be merged with its predecessor or its
+ * successor. Or both (it neatly fills a hole).
*
* In most cases - when called for mmap, brk or mremap - [addr,end) is
* certain not to be mapped by the time vma_merge is called; but when
@@ -1092,7 +1097,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
unsigned long end, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t pgoff, struct mempolicy *policy,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ const char __user *anon_name)
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
@@ -1125,7 +1131,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(vma_policy(prev), policy) &&
can_vma_merge_after(prev, vm_flags,
anon_vma, file, pgoff,
- vm_userfaultfd_ctx)) {
+ vm_userfaultfd_ctx,
+ anon_name)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
@@ -1134,7 +1141,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
can_vma_merge_before(next, vm_flags,
anon_vma, file,
pgoff+pglen,
- vm_userfaultfd_ctx) &&
+ vm_userfaultfd_ctx,
+ anon_name) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma, NULL)) {
/* cases 1, 6 */
@@ -1157,7 +1165,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(policy, vma_policy(next)) &&
can_vma_merge_before(next, vm_flags,
anon_vma, file, pgoff+pglen,
- vm_userfaultfd_ctx)) {
+ vm_userfaultfd_ctx,
+ anon_name)) {
if (prev && addr < prev->vm_end) /* case 4 */
err = __vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL, next);
@@ -1667,7 +1676,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
* Can we just expand an old mapping?
*/
vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
- NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
+ NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@@ -2732,6 +2741,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
return 0;
}
+EXPORT_SYMBOL(do_munmap);
int vm_munmap(unsigned long start, size_t len)
{
@@ -2921,7 +2931,7 @@ static int do_brk(unsigned long addr, unsigned long len)
/* Can we just expand an old private anonymous mapping? */
vma = vma_merge(mm, prev, addr, addr + len, flags,
- NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
+ NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@@ -3090,7 +3100,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
return NULL; /* should never get here */
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (new_vma) {
/*
* Source vma may have been merged into new_vma
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6896f77..5471f35 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -352,7 +352,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx);
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 462c778..02a727f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2186,30 +2186,14 @@ int write_cache_pages(struct address_space *mapping,
while (!done && (index <= end)) {
int i;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- /*
- * At this point, the page may be truncated or
- * invalidated (changing page->mapping to NULL), or
- * even swizzled back from swapper_space to tmpfs file
- * mapping. However, page->index will not change
- * because we have a reference on the page.
- */
- if (page->index > end) {
- /*
- * can't be range_cyclic (1st pass) because
- * end == -1 in that case.
- */
- done = 1;
- break;
- }
-
done_index = page->index;
lock_page(page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b0c451e..d30ba08 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -65,6 +65,7 @@
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/khugepaged.h>
+#include <linux/psi.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -254,10 +255,22 @@ compound_page_dtor * const compound_page_dtors[] = {
#endif
};
+/*
+ * Try to keep at least this much lowmem free. Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
int watermark_scale_factor = 10;
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
+
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
@@ -2348,8 +2361,9 @@ static void drain_pages(unsigned int cpu)
* The CPU has to be pinned. When zone parameter is non-NULL, spill just
* the single zone's pages.
*/
-void drain_local_pages(struct zone *zone)
+void drain_local_pages(void *z)
{
+ struct zone *zone = (struct zone *)z;
int cpu = smp_processor_id();
if (zone)
@@ -2409,8 +2423,7 @@ void drain_all_pages(struct zone *zone)
else
cpumask_clear_cpu(cpu, &cpus_with_pcps);
}
- on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
- zone, 1);
+ on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, zone, 1);
}
#ifdef CONFIG_HIBERNATION
@@ -3161,15 +3174,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
enum compact_priority prio, enum compact_result *compact_result)
{
struct page *page;
+ unsigned long pflags;
unsigned int noreclaim_flag = current->flags & PF_MEMALLOC;
if (!order)
return NULL;
+ psi_memstall_enter(&pflags);
current->flags |= PF_MEMALLOC;
+
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
prio);
+
current->flags = (current->flags & ~PF_MEMALLOC) | noreclaim_flag;
+ psi_memstall_leave(&pflags);
if (*compact_result <= COMPACT_INACTIVE)
return NULL;
@@ -3306,11 +3324,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
{
struct reclaim_state reclaim_state;
int progress;
+ unsigned long pflags;
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
+ psi_memstall_enter(&pflags);
current->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
@@ -3322,6 +3342,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
current->reclaim_state = NULL;
lockdep_clear_current_reclaim_state();
current->flags &= ~PF_MEMALLOC;
+ psi_memstall_leave(&pflags);
cond_resched();
@@ -6663,6 +6684,7 @@ static void setup_per_zone_lowmem_reserve(void)
static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
@@ -6674,11 +6696,14 @@ static void __setup_per_zone_wmarks(void)
}
for_each_zone(zone) {
- u64 tmp;
+ u64 min, low;
spin_lock_irqsave(&zone->lock, flags);
- tmp = (u64)pages_min * zone->managed_pages;
- do_div(tmp, lowmem_pages);
+ min = (u64)pages_min * zone->managed_pages;
+ do_div(min, lowmem_pages);
+ low = (u64)pages_low * zone->managed_pages;
+ do_div(low, vm_total_pages);
+
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -6699,7 +6724,7 @@ static void __setup_per_zone_wmarks(void)
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = tmp;
+ zone->watermark[WMARK_MIN] = min;
}
/*
@@ -6707,12 +6732,14 @@ static void __setup_per_zone_wmarks(void)
* scale factor in proportion to available memory, but
* ensure a minimum size on small systems.
*/
- tmp = max_t(u64, tmp >> 2,
+ min = max_t(u64, min >> 2,
mult_frac(zone->managed_pages,
watermark_scale_factor, 10000));
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) +
+ low + min;
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+ low + min * 2;
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -6795,7 +6822,7 @@ postcore_initcall(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
- * changes.
+ * or extra_free_kbytes changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
diff --git a/mm/page_io.c b/mm/page_io.c
index a2651f5..69735eb 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -21,6 +21,7 @@
#include <linux/writeback.h>
#include <linux/frontswap.h>
#include <linux/blkdev.h>
+#include <linux/psi.h>
#include <linux/uio.h>
#include <asm/pgtable.h>
@@ -337,10 +338,19 @@ int swap_readpage(struct page *page)
struct bio *bio;
int ret = 0;
struct swap_info_struct *sis = page_swap_info(page);
+ unsigned long pflags;
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageUptodate(page), page);
+
+ /*
+ * Count submission time as memory stall. When the device is congested,
+ * or the submitting cgroup IO-throttled, submission can be a
+ * significant part of overall IO time.
+ */
+ psi_memstall_enter(&pflags);
+
if (frontswap_load(page) == 0) {
SetPageUptodate(page);
unlock_page(page);
@@ -354,7 +364,7 @@ int swap_readpage(struct page *page)
ret = mapping->a_ops->readpage(swap_file, page);
if (!ret)
count_vm_event(PSWPIN);
- return ret;
+ goto out;
}
ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
@@ -365,7 +375,7 @@ int swap_readpage(struct page *page)
}
count_vm_event(PSWPIN);
- return 0;
+ goto out;
}
ret = 0;
@@ -379,6 +389,7 @@ int swap_readpage(struct page *page)
count_vm_event(PSWPIN);
submit_bio(bio);
out:
+ psi_memstall_leave(&pflags);
return ret;
}
diff --git a/mm/readahead.c b/mm/readahead.c
index c8a955b..bf9db0f 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -81,7 +81,7 @@ static void read_cache_pages_invalidate_pages(struct address_space *mapping,
* Hides the details of the LRU cache etc from the filesystems.
*/
int read_cache_pages(struct address_space *mapping, struct list_head *pages,
- int (*filler)(void *, struct page *), void *data)
+ int (*filler)(struct file *, struct page *), void *data)
{
struct page *page;
int ret = 0;
@@ -207,12 +207,21 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
* memory at once.
*/
int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t offset, unsigned long nr_to_read)
+ pgoff_t offset, unsigned long nr_to_read)
{
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+ struct file_ra_state *ra = &filp->f_ra;
+ unsigned long max_pages;
+
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
return -EINVAL;
- nr_to_read = min(nr_to_read, inode_to_bdi(mapping->host)->ra_pages);
+ /*
+ * If the request exceeds the readahead window, allow the read to
+ * be up to the optimal hardware IO size
+ */
+ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
+ nr_to_read = min(nr_to_read, max_pages);
while (nr_to_read) {
int err;
@@ -369,10 +378,19 @@ ondemand_readahead(struct address_space *mapping,
bool hit_readahead_marker, pgoff_t offset,
unsigned long req_size)
{
- unsigned long max = ra->ra_pages;
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+ unsigned long max_pages = ra->ra_pages;
+ unsigned long add_pages;
pgoff_t prev_offset;
/*
+ * If the request exceeds the readahead window, allow the read to
+ * be up to the optimal hardware IO size
+ */
+ if (req_size > max_pages && bdi->io_pages > max_pages)
+ max_pages = min(req_size, bdi->io_pages);
+
+ /*
* start of file
*/
if (!offset)
@@ -385,7 +403,7 @@ ondemand_readahead(struct address_space *mapping,
if ((offset == (ra->start + ra->size - ra->async_size) ||
offset == (ra->start + ra->size))) {
ra->start += ra->size;
- ra->size = get_next_ra_size(ra, max);
+ ra->size = get_next_ra_size(ra, max_pages);
ra->async_size = ra->size;
goto readit;
}
@@ -400,16 +418,16 @@ ondemand_readahead(struct address_space *mapping,
pgoff_t start;
rcu_read_lock();
- start = page_cache_next_hole(mapping, offset + 1, max);
+ start = page_cache_next_hole(mapping, offset + 1, max_pages);
rcu_read_unlock();
- if (!start || start - offset > max)
+ if (!start || start - offset > max_pages)
return 0;
ra->start = start;
ra->size = start - offset; /* old async_size */
ra->size += req_size;
- ra->size = get_next_ra_size(ra, max);
+ ra->size = get_next_ra_size(ra, max_pages);
ra->async_size = ra->size;
goto readit;
}
@@ -417,7 +435,7 @@ ondemand_readahead(struct address_space *mapping,
/*
* oversize read
*/
- if (req_size > max)
+ if (req_size > max_pages)
goto initial_readahead;
/*
@@ -433,7 +451,7 @@ ondemand_readahead(struct address_space *mapping,
* Query the page cache and look for the traces(cached history pages)
* that a sequential stream would leave behind.
*/
- if (try_context_readahead(mapping, ra, offset, req_size, max))
+ if (try_context_readahead(mapping, ra, offset, req_size, max_pages))
goto readit;
/*
@@ -444,7 +462,7 @@ ondemand_readahead(struct address_space *mapping,
initial_readahead:
ra->start = offset;
- ra->size = get_init_ra_size(req_size, max);
+ ra->size = get_init_ra_size(req_size, max_pages);
ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
readit:
@@ -452,10 +470,17 @@ ondemand_readahead(struct address_space *mapping,
* Will this read hit the readahead marker made by itself?
* If so, trigger the readahead marker hit now, and merge
* the resulted next readahead window into the current one.
+ * Take care of maximum IO pages as above.
*/
if (offset == ra->start && ra->size == ra->async_size) {
- ra->async_size = get_next_ra_size(ra, max);
- ra->size += ra->async_size;
+ add_pages = get_next_ra_size(ra, max_pages);
+ if (ra->size + add_pages <= max_pages) {
+ ra->async_size = add_pages;
+ ra->size += add_pages;
+ } else {
+ ra->size = max_pages;
+ ra->async_size = max_pages >> 1;
+ }
}
return ra_submit(ra, mapping, filp);
diff --git a/mm/shmem.c b/mm/shmem.c
index 31b0c09..ed9047d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4092,6 +4092,14 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
@@ -4111,10 +4119,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
if (IS_ERR(file))
return PTR_ERR(file);
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
+ shmem_set_file(vma, file);
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
diff --git a/mm/slab.c b/mm/slab.c
index 9547f02..a671328 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1621,11 +1621,8 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
*dbg_redzone2(cachep, objp));
}
- if (cachep->flags & SLAB_STORE_USER) {
- pr_err("Last user: [<%p>](%pSR)\n",
- *dbg_userword(cachep, objp),
- *dbg_userword(cachep, objp));
- }
+ if (cachep->flags & SLAB_STORE_USER)
+ pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp));
realobj = (char *)objp + obj_offset(cachep);
size = cachep->object_size;
for (i = 0; i < size && lines; i += 16, lines--) {
@@ -1658,7 +1655,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
/* Mismatch ! */
/* Print header */
if (lines == 0) {
- pr_err("Slab corruption (%s): %s start=%p, len=%d\n",
+ pr_err("Slab corruption (%s): %s start=%px, len=%d\n",
print_tainted(), cachep->name,
realobj, size);
print_objinfo(cachep, objp, 0);
@@ -1687,13 +1684,13 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
if (objnr) {
objp = index_to_obj(cachep, page, objnr - 1);
realobj = (char *)objp + obj_offset(cachep);
- pr_err("Prev obj: start=%p, len=%d\n", realobj, size);
+ pr_err("Prev obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
}
if (objnr + 1 < cachep->num) {
objp = index_to_obj(cachep, page, objnr + 1);
realobj = (char *)objp + obj_offset(cachep);
- pr_err("Next obj: start=%p, len=%d\n", realobj, size);
+ pr_err("Next obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
}
}
@@ -2640,7 +2637,7 @@ static void slab_put_obj(struct kmem_cache *cachep,
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
if (get_free_obj(page, i) == objnr) {
- pr_err("slab: double free detected in cache '%s', objp %p\n",
+ pr_err("slab: double free detected in cache '%s', objp %px\n",
cachep->name, objp);
BUG();
}
@@ -2803,7 +2800,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
else
slab_error(cache, "memory outside object was overwritten");
- pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
+ pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
obj, redzone1, redzone2);
}
@@ -3103,7 +3100,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
slab_error(cachep, "double free, or memory outside object was overwritten");
- pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
+ pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
@@ -3116,7 +3113,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
cachep->ctor(objp);
if (ARCH_SLAB_MINALIGN &&
((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
- pr_err("0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
+ pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n",
objp, (int)ARCH_SLAB_MINALIGN);
}
return objp;
@@ -4340,7 +4337,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
return;
}
#endif
- seq_printf(m, "%p", (void *)address);
+ seq_printf(m, "%px", (void *)address);
}
static int leaks_show(struct seq_file *m, void *p)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 26c4d47..0e6e78b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -458,6 +458,9 @@ EXPORT_SYMBOL(kmem_cache_create);
static int shutdown_cache(struct kmem_cache *s,
struct list_head *release, bool *need_rcu_barrier)
{
+ /* free asan quarantined objects */
+ kasan_cache_shutdown(s);
+
if (__kmem_cache_shutdown(s) != 0)
return -EBUSY;
@@ -741,7 +744,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
get_online_cpus();
get_online_mems();
- kasan_cache_destroy(s);
mutex_lock(&slab_mutex);
s->refcount--;
diff --git a/mm/slob.c b/mm/slob.c
index eac04d4..e6e7137 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -472,6 +472,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
{
return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
}
+EXPORT_SYMBOL(__kmalloc_track_caller);
#ifdef CONFIG_NUMA
void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
@@ -479,6 +480,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
{
return __do_kmalloc_node(size, gfp, node, caller);
}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif
void kfree(const void *block)
diff --git a/mm/slub.c b/mm/slub.c
index 5c48a8a..4fba5b5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4282,6 +4282,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
return ret;
}
+EXPORT_SYMBOL(__kmalloc_track_caller);
#ifdef CONFIG_NUMA
void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
@@ -4312,6 +4313,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
return ret;
}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif
#ifdef CONFIG_SYSFS
@@ -4713,6 +4715,22 @@ enum slab_stat_type {
#define SO_OBJECTS (1 << SL_OBJECTS)
#define SO_TOTAL (1 << SL_TOTAL)
+#ifdef CONFIG_MEMCG
+static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON);
+
+static int __init setup_slub_memcg_sysfs(char *str)
+{
+ int v;
+
+ if (get_option(&str, &v) > 0)
+ memcg_sysfs_enabled = v;
+
+ return 1;
+}
+
+__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs);
+#endif
+
static ssize_t show_slab_objects(struct kmem_cache *s,
char *buf, unsigned long flags)
{
@@ -5628,8 +5646,14 @@ static int sysfs_slab_add(struct kmem_cache *s)
{
int err;
const char *name;
+ struct kset *kset = cache_kset(s);
int unmergeable = slab_unmergeable(s);
+ if (!kset) {
+ kobject_init(&s->kobj, &slab_ktype);
+ return 0;
+ }
+
if (unmergeable) {
/*
* Slabcache can never be merged so we can use the name proper.
@@ -5646,7 +5670,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
name = create_unique_id(s);
}
- s->kobj.kset = cache_kset(s);
+ s->kobj.kset = kset;
err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
if (err)
goto out;
@@ -5656,7 +5680,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
goto out_del_kobj;
#ifdef CONFIG_MEMCG
- if (is_root_cache(s)) {
+ if (is_root_cache(s) && memcg_sysfs_enabled) {
s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
if (!s->memcg_kset) {
err = -ENOMEM;
diff --git a/mm/swap.c b/mm/swap.c
index 4dcf852..9f201d2 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -69,6 +69,7 @@ static void __page_cache_release(struct page *page)
del_page_from_lru_list(page, lruvec, page_off_lru(page));
spin_unlock_irqrestore(zone_lru_lock(zone), flags);
}
+ __ClearPageWaiters(page);
mem_cgroup_uncharge(page);
}
@@ -784,6 +785,7 @@ void release_pages(struct page **pages, int nr, bool cold)
/* Clear Active bit in case of parallel mark_page_accessed */
__ClearPageActive(page);
+ __ClearPageWaiters(page);
list_add(&page->lru, &pages_to_free);
}
@@ -954,15 +956,25 @@ unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
}
EXPORT_SYMBOL(pagevec_lookup);
-unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
- pgoff_t *index, int tag, unsigned nr_pages)
+unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
+ struct address_space *mapping, pgoff_t *index, pgoff_t end,
+ int tag)
{
- pvec->nr = find_get_pages_tag(mapping, index, tag,
- nr_pages, pvec->pages);
+ pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
+ PAGEVEC_SIZE, pvec->pages);
return pagevec_count(pvec);
}
-EXPORT_SYMBOL(pagevec_lookup_tag);
+EXPORT_SYMBOL(pagevec_lookup_range_tag);
+unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
+ struct address_space *mapping, pgoff_t *index, pgoff_t end,
+ int tag, unsigned max_pages)
+{
+ pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
+ min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages);
+ return pagevec_count(pvec);
+}
+EXPORT_SYMBOL(pagevec_lookup_range_nr_tag);
/*
* Perform any setup for the swap system
*/
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f5cb6b2..fa8e3ff 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -369,6 +369,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
/*
* Initiate read into locked page and return.
*/
+ SetPageWorkingset(new_page);
lru_cache_add_anon(new_page);
*new_page_allocated = true;
return new_page;
diff --git a/mm/usercopy.c b/mm/usercopy.c
index c2de343..9bc43f8 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -62,12 +62,11 @@ static noinline int check_stack_object(const void *obj, unsigned long len)
return GOOD_STACK;
}
-static void report_usercopy(const void *ptr, unsigned long len,
- bool to_user, const char *type)
+static void report_usercopy(unsigned long len, bool to_user, const char *type)
{
- pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n",
+ pr_emerg("kernel memory %s attempt detected %s '%s' (%lu bytes)\n",
to_user ? "exposure" : "overwrite",
- to_user ? "from" : "to", ptr, type ? : "unknown", len);
+ to_user ? "from" : "to", type ? : "unknown", len);
/*
* For greater effect, it would be nice to do do_group_exit(),
* but BUG() actually hooks all the lock-breaking and per-arch
@@ -281,6 +280,6 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user)
return;
report:
- report_usercopy(ptr, n, to_user, err);
+ report_usercopy(n, to_user, err);
}
EXPORT_SYMBOL(__check_object_size);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index af817e5..a176847 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -182,13 +182,9 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
goto out_unlock;
/*
- * Be strict and only allow __mcopy_atomic on userfaultfd
- * registered ranges to prevent userland errors going
- * unnoticed. As far as the VM consistency is concerned, it
- * would be perfectly safe to remove this check, but there's
- * no useful usage for __mcopy_atomic ouside of userfaultfd
- * registered ranges. This is after all why these are ioctls
- * belonging to the userfaultfd and not syscalls.
+ * Check the vma is registered in uffd, this is required to
+ * enforce the VM_MAYWRITE check done at uffd registration
+ * time.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
goto out_unlock;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4e5846b..aa9c382 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -47,6 +47,7 @@
#include <linux/prefetch.h>
#include <linux/printk.h>
#include <linux/dax.h>
+#include <linux/psi.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -2004,6 +2005,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
}
ClearPageActive(page); /* we are de-activating */
+ SetPageWorkingset(page);
list_add(&page->lru, &l_inactive);
}
@@ -3053,6 +3055,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
{
struct zonelist *zonelist;
unsigned long nr_reclaimed;
+ unsigned long pflags;
int nid;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
@@ -3080,9 +3083,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
sc.gfp_mask,
sc.reclaim_idx);
+ psi_memstall_enter(&pflags);
current->flags |= PF_MEMALLOC;
+
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
current->flags &= ~PF_MEMALLOC;
+ psi_memstall_leave(&pflags);
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
@@ -3232,6 +3239,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
int i;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
+ unsigned long pflags;
struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
@@ -3241,6 +3249,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
.may_unmap = 1,
.may_swap = 1,
};
+
+ psi_memstall_enter(&pflags);
count_vm_event(PAGEOUTRUN);
do {
@@ -3345,6 +3355,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
pgdat->kswapd_failures++;
out:
+ psi_memstall_leave(&pflags);
/*
* Return the order kswapd stopped reclaiming at as
* prepare_kswapd_sleep() takes it into account. If another caller
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e60435d..3932462 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -958,6 +958,7 @@ const char * const vmstat_text[] = {
"nr_pages_scanned",
"workingset_refault",
"workingset_activate",
+ "workingset_restore",
"workingset_nodereclaim",
"nr_anon_pages",
"nr_mapped",
diff --git a/mm/workingset.c b/mm/workingset.c
index 4c4f056..a697611 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -118,7 +118,7 @@
* the only thing eating into inactive list space is active pages.
*
*
- * Activating refaulting pages
+ * Refaulting inactive pages
*
* All that is known about the active list is that the pages have been
* accessed more than once in the past. This means that at any given
@@ -131,6 +131,10 @@
* used less frequently than the refaulting page - or even not used at
* all anymore.
*
+ * That means if inactive cache is refaulting with a suitable refault
+ * distance, we assume the cache workingset is transitioning and put
+ * pressure on the current active list.
+ *
* If this is wrong and demotion kicks in, the pages which are truly
* used more frequently will be reactivated while the less frequently
* used once will be evicted from memory.
@@ -138,6 +142,14 @@
* But if this is right, the stale pages will be pushed out of memory
* and the used pages get to stay in cache.
*
+ * Refaulting active pages
+ *
+ * If on the other hand the refaulting pages have recently been
+ * deactivated, it means that the active list is no longer protecting
+ * actively used cache from reclaim. The cache is NOT transitioning to
+ * a different workingset; the existing workingset is thrashing in the
+ * space allocated to the page cache.
+ *
*
* Implementation
*
@@ -153,8 +165,7 @@
*/
#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \
- NODES_SHIFT + \
- MEM_CGROUP_ID_SHIFT)
+ 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
/*
@@ -167,23 +178,28 @@
*/
static unsigned int bucket_order __read_mostly;
-static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
+static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
+ bool workingset)
{
eviction >>= bucket_order;
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
+ eviction = (eviction << 1) | workingset;
eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
}
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
- unsigned long *evictionp)
+ unsigned long *evictionp, bool *workingsetp)
{
unsigned long entry = (unsigned long)shadow;
int memcgid, nid;
+ bool workingset;
entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
+ workingset = entry & 1;
+ entry >>= 1;
nid = entry & ((1UL << NODES_SHIFT) - 1);
entry >>= NODES_SHIFT;
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
@@ -192,6 +208,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
*memcgidp = memcgid;
*pgdat = NODE_DATA(nid);
*evictionp = entry << bucket_order;
+ *workingsetp = workingset;
}
/**
@@ -204,8 +221,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
*/
void *workingset_eviction(struct address_space *mapping, struct page *page)
{
- struct mem_cgroup *memcg = page_memcg(page);
struct pglist_data *pgdat = page_pgdat(page);
+ struct mem_cgroup *memcg = page_memcg(page);
int memcgid = mem_cgroup_id(memcg);
unsigned long eviction;
struct lruvec *lruvec;
@@ -217,30 +234,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
lruvec = mem_cgroup_lruvec(pgdat, memcg);
eviction = atomic_long_inc_return(&lruvec->inactive_age);
- return pack_shadow(memcgid, pgdat, eviction);
+ return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
}
/**
* workingset_refault - evaluate the refault of a previously evicted page
+ * @page: the freshly allocated replacement page
* @shadow: shadow entry of the evicted page
*
* Calculates and evaluates the refault distance of the previously
* evicted page in the context of the node it was allocated in.
- *
- * Returns %true if the page should be activated, %false otherwise.
*/
-bool workingset_refault(void *shadow)
+void workingset_refault(struct page *page, void *shadow)
{
unsigned long refault_distance;
+ struct pglist_data *pgdat;
unsigned long active_file;
struct mem_cgroup *memcg;
unsigned long eviction;
struct lruvec *lruvec;
unsigned long refault;
- struct pglist_data *pgdat;
+ bool workingset;
int memcgid;
- unpack_shadow(shadow, &memcgid, &pgdat, &eviction);
+ unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
rcu_read_lock();
/*
@@ -260,40 +277,51 @@ bool workingset_refault(void *shadow)
* configurations instead.
*/
memcg = mem_cgroup_from_id(memcgid);
- if (!mem_cgroup_disabled() && !memcg) {
- rcu_read_unlock();
- return false;
- }
+ if (!mem_cgroup_disabled() && !memcg)
+ goto out;
lruvec = mem_cgroup_lruvec(pgdat, memcg);
refault = atomic_long_read(&lruvec->inactive_age);
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
- rcu_read_unlock();
/*
- * The unsigned subtraction here gives an accurate distance
- * across inactive_age overflows in most cases.
+ * Calculate the refault distance
*
- * There is a special case: usually, shadow entries have a
- * short lifetime and are either refaulted or reclaimed along
- * with the inode before they get too old. But it is not
- * impossible for the inactive_age to lap a shadow entry in
- * the field, which can then can result in a false small
- * refault distance, leading to a false activation should this
- * old entry actually refault again. However, earlier kernels
- * used to deactivate unconditionally with *every* reclaim
- * invocation for the longest time, so the occasional
- * inappropriate activation leading to pressure on the active
- * list is not a problem.
+ * The unsigned subtraction here gives an accurate distance
+ * across inactive_age overflows in most cases. There is a
+ * special case: usually, shadow entries have a short lifetime
+ * and are either refaulted or reclaimed along with the inode
+ * before they get too old. But it is not impossible for the
+ * inactive_age to lap a shadow entry in the field, which can
+ * then result in a false small refault distance, leading to a
+ * false activation should this old entry actually refault
+ * again. However, earlier kernels used to deactivate
+ * unconditionally with *every* reclaim invocation for the
+ * longest time, so the occasional inappropriate activation
+ * leading to pressure on the active list is not a problem.
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
inc_node_state(pgdat, WORKINGSET_REFAULT);
- if (refault_distance <= active_file) {
- inc_node_state(pgdat, WORKINGSET_ACTIVATE);
- return true;
+ /*
+ * Compare the distance to the existing workingset size. We
+ * don't act on pages that couldn't stay resident even if all
+ * the memory was available to the page cache.
+ */
+ if (refault_distance > active_file)
+ goto out;
+
+ SetPageActive(page);
+ atomic_long_inc(&lruvec->inactive_age);
+ inc_node_state(pgdat, WORKINGSET_ACTIVATE);
+
+ /* Page was active prior to eviction */
+ if (workingset) {
+ SetPageWorkingset(page);
+ inc_node_state(pgdat, WORKINGSET_RESTORE);
}
- return false;
+out:
+ rcu_read_unlock();
}
/**
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index e4cca3f..465e5a3 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -189,6 +189,7 @@ static int zs_size_classes;
* (see: fix_fullness_group())
*/
static const int fullness_threshold_frac = 4;
+static size_t huge_class_size;
struct size_class {
spinlock_t lock;
@@ -1492,6 +1493,25 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
+/**
+ * zs_huge_class_size() - Returns the size (in bytes) of the first huge
+ * zsmalloc &size_class.
+ * @pool: zsmalloc pool to use
+ *
+ * The function returns the size of the first huge class - any object of equal
+ * or bigger size will be stored in zspage consisting of a single physical
+ * page.
+ *
+ * Context: Any context.
+ *
+ * Return: the size (in bytes) of the first huge zsmalloc &size_class.
+ */
+size_t zs_huge_class_size(struct zs_pool *pool)
+{
+ return huge_class_size;
+}
+EXPORT_SYMBOL_GPL(zs_huge_class_size);
+
static unsigned long obj_malloc(struct size_class *class,
struct zspage *zspage, unsigned long handle)
{
@@ -2518,6 +2538,27 @@ struct zs_pool *zs_create_pool(const char *name)
objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
/*
+ * We iterate from biggest down to smallest classes,
+ * so huge_class_size holds the size of the first huge
+ * class. Any object bigger than or equal to that will
+ * endup in the huge class.
+ */
+ if (pages_per_zspage != 1 && objs_per_zspage != 1 &&
+ !huge_class_size) {
+ huge_class_size = size;
+ /*
+ * The object uses ZS_HANDLE_SIZE bytes to store the
+ * handle. We need to subtract it, because zs_malloc()
+ * unconditionally adds handle size before it performs
+ * size class search - so object may be smaller than
+ * huge class size, yet it still can end up in the huge
+ * class because it grows by ZS_HANDLE_SIZE extra bytes
+ * right before class lookup.
+ */
+ huge_class_size -= (ZS_HANDLE_SIZE - 1);
+ }
+
+ /*
* size_class is used for normal zsmalloc operation such
* as alloc/free for that size. Although it is natural that we
* have one size_class for each size, there is a chance that we
diff --git a/net/Kconfig b/net/Kconfig
index 7b6cd34..3775760 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -89,6 +89,12 @@
endif # if INET
+config ANDROID_PARANOID_NETWORK
+ bool "Only allow certain groups to create sockets"
+ default y
+ help
+ none
+
config NETWORK_SECMARK
bool "Security Marking"
help
@@ -258,10 +264,6 @@
config HWBM
bool
-config SOCK_CGROUP_DATA
- bool
- default n
-
config CGROUP_NET_PRIO
bool "Network priority cgroup"
depends on CGROUPS
@@ -292,6 +294,7 @@
bool "enable BPF Just In Time compiler"
depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
depends on MODULES
+ depends on !CFI
---help---
Berkeley Packet Filter filtering capabilities are normally handled
by an interpreter. This option allows kernel to generate a native
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 5d369817..ec313c9 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -106,11 +106,40 @@ void bt_sock_unregister(int proto)
}
EXPORT_SYMBOL(bt_sock_unregister);
+#ifdef CONFIG_PARANOID_NETWORK
+static inline int current_has_bt_admin(void)
+{
+ return !current_euid();
+}
+
+static inline int current_has_bt(void)
+{
+ return current_has_bt_admin();
+}
+# else
+static inline int current_has_bt_admin(void)
+{
+ return 1;
+}
+
+static inline int current_has_bt(void)
+{
+ return 1;
+}
+#endif
+
static int bt_sock_create(struct net *net, struct socket *sock, int proto,
int kern)
{
int err;
+ if (proto == BTPROTO_RFCOMM || proto == BTPROTO_SCO ||
+ proto == BTPROTO_L2CAP) {
+ if (!current_has_bt())
+ return -EPERM;
+ } else if (!current_has_bt_admin())
+ return -EPERM;
+
if (net != &init_net)
return -EAFNOSUPPORT;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 495655b..be4f5e9 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -48,11 +48,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
- u64_stats_update_begin(&brstats->syncp);
- brstats->tx_packets++;
- brstats->tx_bytes += skb->len;
- u64_stats_update_end(&brstats->syncp);
-
#ifdef CONFIG_NET_SWITCHDEV
skb->offload_fwd_mark = 0;
#endif
@@ -61,6 +56,12 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
+ u64_stats_update_begin(&brstats->syncp);
+ brstats->tx_packets++;
+ /* Exclude ETH_HLEN from byte stats for consistency with Rx chain */
+ brstats->tx_bytes += skb->len;
+ u64_stats_update_end(&brstats->syncp);
+
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c
index 517e78b..61a9f1b 100644
--- a/net/bridge/netfilter/ebt_limit.c
+++ b/net/bridge/netfilter/ebt_limit.c
@@ -105,6 +105,7 @@ static struct xt_match ebt_limit_mt_reg __read_mostly = {
.match = ebt_limit_mt,
.checkentry = ebt_limit_mt_check,
.matchsize = sizeof(struct ebt_limit_info),
+ .usersize = offsetof(struct ebt_limit_info, prev),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct ebt_compat_limit_info),
#endif
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9f17290..955fc01 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -18,6 +18,11 @@
#include <net/fib_rules.h>
#include <net/ip_tunnels.h>
+static const struct fib_kuid_range fib_kuid_range_unset = {
+ KUIDT_INIT(0),
+ KUIDT_INIT(~0),
+};
+
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
{
@@ -33,6 +38,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
r->table = table;
r->flags = flags;
r->fr_net = ops->fro_net;
+ r->uid_range = fib_kuid_range_unset;
r->suppress_prefixlen = -1;
r->suppress_ifgroup = -1;
@@ -172,6 +178,34 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
+static int uid_range_set(struct fib_kuid_range *range)
+{
+ return uid_valid(range->start) && uid_valid(range->end);
+}
+
+static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb)
+{
+ struct fib_rule_uid_range *in;
+ struct fib_kuid_range out;
+
+ in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
+
+ out.start = make_kuid(current_user_ns(), in->start);
+ out.end = make_kuid(current_user_ns(), in->end);
+
+ return out;
+}
+
+static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
+{
+ struct fib_rule_uid_range out = {
+ from_kuid_munged(current_user_ns(), range->start),
+ from_kuid_munged(current_user_ns(), range->end)
+ };
+
+ return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -193,6 +227,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
goto out;
+ if (uid_lt(fl->flowi_uid, rule->uid_range.start) ||
+ uid_gt(fl->flowi_uid, rule->uid_range.end))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -305,6 +343,10 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
if (r->l3mdev != rule->l3mdev)
continue;
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
if (!ops->compare(r, frh, tb))
continue;
return 1;
@@ -383,6 +425,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (tb[FRA_TUN_ID])
rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
+ err = -EINVAL;
if (tb[FRA_L3MDEV]) {
#ifdef CONFIG_NET_L3_MASTER_DEV
rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
@@ -404,7 +447,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
else
rule->suppress_ifgroup = -1;
- err = -EINVAL;
if (tb[FRA_GOTO]) {
if (rule->action != FR_ACT_GOTO)
goto errout_free;
@@ -429,6 +471,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (rule->l3mdev && rule->table)
goto errout_free;
+ if (tb[FRA_UID_RANGE]) {
+ if (current_user_ns() != net->user_ns) {
+ err = -EPERM;
+ goto errout_free;
+ }
+
+ rule->uid_range = nla_get_kuid_range(tb);
+
+ if (!uid_range_set(&rule->uid_range) ||
+ !uid_lte(rule->uid_range.start, rule->uid_range.end))
+ goto errout_free;
+ } else {
+ rule->uid_range = fib_kuid_range_unset;
+ }
+
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
@@ -497,6 +554,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule, *tmp;
struct nlattr *tb[FRA_MAX+1];
+ struct fib_kuid_range range;
int err = -EINVAL;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
@@ -516,6 +574,16 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err < 0)
goto errout;
+ if (tb[FRA_UID_RANGE]) {
+ range = nla_get_kuid_range(tb);
+ if (!uid_range_set(&range)) {
+ err = -EINVAL;
+ goto errout;
+ }
+ } else {
+ range = fib_kuid_range_unset;
+ }
+
list_for_each_entry(rule, &ops->rules_list, list) {
if (frh->action && (frh->action != rule->action))
continue;
@@ -552,6 +620,11 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
(rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
continue;
+ if (uid_range_set(&range) &&
+ (!uid_eq(rule->uid_range.start, range.start) ||
+ !uid_eq(rule->uid_range.end, range.end)))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -619,7 +692,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
+ nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+ nla_total_size(4) /* FRA_FWMARK */
+ nla_total_size(4) /* FRA_FWMASK */
- + nla_total_size_64bit(8); /* FRA_TUN_ID */
+ + nla_total_size_64bit(8) /* FRA_TUN_ID */
+ + nla_total_size(sizeof(struct fib_kuid_range));
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -679,7 +753,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
(rule->tun_id &&
nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
(rule->l3mdev &&
- nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
+ nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
+ (uid_range_set(&rule->uid_range) &&
+ nla_put_uid_range(skb, &rule->uid_range)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/filter.c b/net/core/filter.c
index e8c89d2..768688b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -26,6 +26,7 @@
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
+#include <linux/sock_diag.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
@@ -78,6 +79,10 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
return -ENOMEM;
+ err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb);
+ if (err)
+ return err;
+
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
@@ -85,7 +90,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+ struct sock *save_sk = skb->sk;
+ unsigned int pkt_len;
+
+ skb->sk = sk;
+ pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+ skb->sk = save_sk;
err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
}
rcu_read_unlock();
@@ -1701,6 +1711,9 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
case ARPHRD_IPGRE:
case ARPHRD_VOID:
case ARPHRD_NONE:
+#ifdef ARPHRD_RAWIP
+ case ARPHRD_RAWIP:
+#endif
return __bpf_redirect_no_mac(skb, dev, flags);
default:
return __bpf_redirect_common(skb, dev, flags);
@@ -2533,6 +2546,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
.arg5_type = ARG_CONST_STACK_SIZE,
};
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+ return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+ .func = bpf_get_socket_cookie,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+ struct sock *sk = sk_to_full_sk(skb->sk);
+ kuid_t kuid;
+
+ if (!sk || !sk_fullsock(sk))
+ return overflowuid;
+ kuid = sock_net_uid(sock_net(sk), sk);
+ return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+ .func = bpf_get_socket_uid,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static const struct bpf_func_proto *
sk_filter_func_proto(enum bpf_func_id func_id)
{
@@ -2554,6 +2597,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();
+ case BPF_FUNC_get_socket_cookie:
+ return &bpf_get_socket_cookie_proto;
+ case BPF_FUNC_get_socket_uid:
+ return &bpf_get_socket_uid_proto;
default:
return NULL;
}
@@ -2631,6 +2678,17 @@ xdp_func_proto(enum bpf_func_id func_id)
}
}
+static const struct bpf_func_proto *
+cg_skb_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_skb_load_bytes:
+ return &bpf_skb_load_bytes_proto;
+ default:
+ return sk_filter_func_proto(func_id);
+ }
+}
+
static bool __is_valid_access(int off, int size, enum bpf_access_type type)
{
if (off < 0 || off >= sizeof(struct __sk_buff))
@@ -2993,6 +3051,12 @@ static const struct bpf_verifier_ops xdp_ops = {
.convert_ctx_access = xdp_convert_ctx_access,
};
+static const struct bpf_verifier_ops cg_skb_ops = {
+ .get_func_proto = cg_skb_func_proto,
+ .is_valid_access = sk_filter_is_valid_access,
+ .convert_ctx_access = sk_filter_convert_ctx_access,
+};
+
static struct bpf_prog_type_list sk_filter_type __read_mostly = {
.ops = &sk_filter_ops,
.type = BPF_PROG_TYPE_SOCKET_FILTER,
@@ -3013,12 +3077,18 @@ static struct bpf_prog_type_list xdp_type __read_mostly = {
.type = BPF_PROG_TYPE_XDP,
};
+static struct bpf_prog_type_list cg_skb_type __read_mostly = {
+ .ops = &cg_skb_ops,
+ .type = BPF_PROG_TYPE_CGROUP_SKB,
+};
+
static int __init register_sk_filter_ops(void)
{
bpf_register_prog_type(&sk_filter_type);
bpf_register_prog_type(&sched_cls_type);
bpf_register_prog_type(&sched_act_type);
bpf_register_prog_type(&xdp_type);
+ bpf_register_prog_type(&cg_skb_type);
return 0;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 433b26f..3708301 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2345,7 +2345,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET);
} else {
/* slow path: we dont already have xfrm_state */
- x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
+ x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0,
(xfrm_address_t *)&pkt_dev->cur_daddr,
(xfrm_address_t *)&pkt_dev->cur_saddr,
AF_INET,
diff --git a/net/core/sock.c b/net/core/sock.c
index d468ffb..123f3d7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1032,6 +1032,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
union {
int val;
+ u64 val64;
struct linger ling;
struct timeval tm;
} v;
@@ -1262,6 +1263,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_incoming_cpu;
break;
+
+ case SO_COOKIE:
+ lv = sizeof(u64);
+ if (len < lv)
+ return -EINVAL;
+ v.val64 = sock_gen_cookie(sk);
+ break;
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -2470,8 +2478,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_type = sock->type;
sk->sk_wq = sock->wq;
sock->sk = sk;
- } else
+ sk->sk_uid = SOCK_INODE(sock)->i_uid;
+ } else {
sk->sk_wq = NULL;
+ sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
+ }
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index d1d9faf..fb467db 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
static struct workqueue_struct *broadcast_wq;
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
{
while (1) {
u64 res = atomic64_read(&sk->sk_cookie);
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index ecc28cf..d502c94 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -70,7 +70,7 @@ int dns_query(const char *type, const char *name, size_t namelen,
const char *options, char **_result, time64_t *_expiry)
{
struct key *rkey;
- const struct user_key_payload *upayload;
+ struct user_key_payload *upayload;
const struct cred *saved_cred;
size_t typelen, desclen;
char *desc, *cp;
@@ -141,7 +141,7 @@ int dns_query(const char *type, const char *name, size_t namelen,
if (ret)
goto put;
- upayload = user_key_payload(rkey);
+ upayload = user_key_payload_locked(rkey);
len = upayload->datalen;
ret = -ENOMEM;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 689246d..dce4f5d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -121,6 +121,19 @@
#endif
#include <net/l3mdev.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
@@ -255,6 +268,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
if (protocol < 0 || protocol >= IPPROTO_MAX)
return -EINVAL;
+ if (!current_has_network())
+ return -EACCES;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
@@ -303,8 +319,7 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
@@ -566,13 +581,24 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int err;
long timeo;
- if (addr_len < sizeof(uaddr->sa_family))
- return -EINVAL;
+ /*
+ * uaddr can be NULL and addr_len can be 0 if:
+ * sk is a TCP fastopen active socket and
+ * TCP_FASTOPEN_CONNECT sockopt is set and
+ * we already have a valid cookie for this socket.
+ * In this case, user can call write() after connect().
+ * write() will invoke tcp_sendmsg_fastopen() which calls
+ * __inet_stream_connect().
+ */
+ if (uaddr) {
+ if (addr_len < sizeof(uaddr->sa_family))
+ return -EINVAL;
- if (uaddr->sa_family == AF_UNSPEC) {
- err = sk->sk_prot->disconnect(sk, flags);
- sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
- goto out;
+ if (uaddr->sa_family == AF_UNSPEC) {
+ err = sk->sk_prot->disconnect(sk, flags);
+ sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
+ goto out;
+ }
}
switch (sock->state) {
@@ -583,7 +609,10 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
err = -EISCONN;
goto out;
case SS_CONNECTING:
- err = -EALREADY;
+ if (inet_sk(sk)->defer_connect)
+ err = -EINPROGRESS;
+ else
+ err = -EALREADY;
/* Fall out of switch with err, set for this state */
break;
case SS_UNCONNECTED:
@@ -597,6 +626,9 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
sock->state = SS_CONNECTING;
+ if (!err && inet_sk(sk)->defer_connect)
+ goto out;
+
/* Just entered SS_CONNECTING state; the only
* difference is that return value in non-blocking
* case is EINPROGRESS, rather than EALREADY.
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index aa4c045..d612d40 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -320,7 +320,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
- struct net *net;
+ struct net *net = dev_net(dev);
bool dev_match;
fl4.flowi4_oif = 0;
@@ -333,6 +333,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_tun_key.tun_id = 0;
fl4.flowi4_flags = 0;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
no_addr = idev->ifa_list == NULL;
@@ -340,13 +341,12 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
trace_fib_validate_source(dev, &fl4);
- net = dev_net(dev);
if (fib_lookup(net, &fl4, &res, 0))
goto last_resort;
if (res.type != RTN_UNICAST &&
(res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
goto e_inval;
- if (!rpf && !fib_num_tclassid_users(dev_net(dev)) &&
+ if (!rpf && !fib_num_tclassid_users(net) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
goto last_resort;
fib_combine_itag(itag, &res);
@@ -622,6 +622,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 9a21080..6b66f05 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -429,6 +429,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
@@ -477,6 +478,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
fl4->flowi4_mark = mark;
+ fl4->flowi4_uid = sock_net_uid(net, NULL);
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5a0352c..e25596f1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -431,7 +431,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -469,7 +469,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3164bae..e812bac 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -75,6 +75,7 @@
#include <net/inetpeer.h>
#include <net/inet_ecn.h>
#include <net/lwtunnel.h>
+#include <linux/bpf-cgroup.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
@@ -288,6 +289,13 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned int mtu;
+ int ret;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ if (ret) {
+ kfree_skb(skb);
+ return ret;
+ }
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
@@ -306,6 +314,20 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
return ip_finish_output2(net, sk, skb);
}
+static int ip_mc_finish_output(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int ret;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ if (ret) {
+ kfree_skb(skb);
+ return ret;
+ }
+
+ return dev_loopback_xmit(net, sk, skb);
+}
+
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
@@ -343,7 +365,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, newskb, NULL, newskb->dev,
- dev_loopback_xmit);
+ ip_mc_finish_output);
}
/* Multicasts with ttl 0 must not go beyond the host */
@@ -359,7 +381,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, newskb, NULL, newskb->dev,
- dev_loopback_xmit);
+ ip_mc_finish_output);
}
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
@@ -1606,7 +1628,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
daddr, saddr,
- tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+ arg->uid);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4822459..7b8ae1f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -836,10 +836,6 @@ copy_entries_to_user(unsigned int total_size,
return PTR_ERR(counters);
loc_cpu_entry = private->entries;
- if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
- ret = -EFAULT;
- goto free_counters;
- }
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
@@ -849,6 +845,10 @@ copy_entries_to_user(unsigned int total_size,
const struct xt_entry_target *t;
e = (struct ipt_entry *)(loc_cpu_entry + off);
+ if (copy_to_user(userptr + off, e, sizeof(*e))) {
+ ret = -EFAULT;
+ goto free_counters;
+ }
if (copy_to_user(userptr + off
+ offsetof(struct ipt_entry, counters),
&counters[num],
@@ -862,23 +862,14 @@ copy_entries_to_user(unsigned int total_size,
i += m->u.match_size) {
m = (void *)e + i;
- if (copy_to_user(userptr + off + i
- + offsetof(struct xt_entry_match,
- u.user.name),
- m->u.kernel.match->name,
- strlen(m->u.kernel.match->name)+1)
- != 0) {
+ if (xt_match_to_user(m, userptr + off + i)) {
ret = -EFAULT;
goto free_counters;
}
}
t = ipt_get_target_c(e);
- if (copy_to_user(userptr + off + e->target_offset
- + offsetof(struct xt_entry_target,
- u.user.name),
- t->u.kernel.target->name,
- strlen(t->u.kernel.target->name)+1) != 0) {
+ if (xt_target_to_user(t, userptr + off + e->target_offset)) {
ret = -EFAULT;
goto free_counters;
}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 16599ba..28bcde0 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -478,6 +478,7 @@ static struct xt_target clusterip_tg_reg __read_mostly = {
.checkentry = clusterip_tg_check,
.destroy = clusterip_tg_destroy,
.targetsize = sizeof(struct ipt_clusterip_tgt_info),
+ .usersize = offsetof(struct ipt_clusterip_tgt_info, config),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct compat_ipt_clusterip_tgt_info),
#endif /* CONFIG_COMPAT */
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 4fda9ab..65662922 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -798,7 +798,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+ inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+ sk->sk_uid);
fl4.fl4_icmp_type = user_icmph.type;
fl4.fl4_icmp_code = user_icmph.code;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index af75c0a..5f94da0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -614,7 +614,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
- daddr, saddr, 0, 0);
+ daddr, saddr, 0, 0, sk->sk_uid);
if (!hdrincl) {
rfv.msg = msg;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e9aae46..ec3d675 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -509,7 +509,8 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
+ const struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
@@ -525,19 +526,21 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0,
+ sock_net_uid(net, sk));
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
const struct sock *sk)
{
+ const struct net *net = dev_net(skb->dev);
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
u32 mark = skb->mark;
- __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
}
static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
@@ -554,7 +557,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
@@ -806,6 +809,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
struct rtable *rt;
struct flowi4 fl4;
const struct iphdr *iph = (const struct iphdr *) skb->data;
+ struct net *net = dev_net(skb->dev);
int oif = skb->dev->ifindex;
u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
@@ -813,7 +817,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
rt = (struct rtable *) dst;
- __build_flow_key(&fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
@@ -1037,7 +1041,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
if (!mark)
mark = IP4_REPLY_MARK(net, skb->mark);
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1053,7 +1057,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
if (!fl4.flowi4_mark)
fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
@@ -1072,6 +1076,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct rtable *rt;
struct dst_entry *odst = NULL;
bool new = false;
+ struct net *net = sock_net(sk);
bh_lock_sock(sk);
@@ -1085,7 +1090,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
goto out;
}
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = (struct rtable *)odst;
if (odst->obsolete && !odst->ops->check(odst, 0)) {
@@ -1125,7 +1130,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1140,9 +1145,10 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
+ struct net *net = sock_net(sk);
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- rt = __ip_route_output_key(sock_net(sk), &fl4);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
@@ -1904,6 +1910,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
fl4.flowi4_flags = 0;
fl4.daddr = daddr;
fl4.saddr = saddr;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
err = fib_lookup(net, &fl4, &res, 0);
if (err != 0) {
if (!IN_DEV_FORWARD(in_dev))
@@ -2561,6 +2568,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
@@ -2613,6 +2625,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
int mark;
struct sk_buff *skb;
u32 table_id = RT_TABLE_MAIN;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2640,6 +2653,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
@@ -2647,6 +2664,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (iif) {
struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index bcf7434..70dd013b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -378,7 +378,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
- ireq->ir_loc_addr, th->source, th->dest);
+ ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
@@ -394,7 +394,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
(req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
req->rsk_window_clamp = full_space;
- tcp_select_initial_window(full_space, req->mss,
+ tcp_select_initial_window(sock_net(sk), full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e202bab..c536180 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -27,7 +27,9 @@
static int zero;
static int one = 1;
+static int three = 3;
static int four = 4;
+static int hundred = 100;
static int thousand = 1000;
static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
@@ -994,6 +996,15 @@ static struct ctl_table ipv4_net_table[] = {
.extra2 = &one,
},
#endif
+ {
+ .procname = "tcp_default_init_rwnd",
+ .data = &init_net.ipv4.sysctl_tcp_default_init_rwnd,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &three,
+ .extra2 = &hundred,
+ },
{ }
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index aeda018..5d8a7f2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -538,6 +538,12 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (tp->urg_data & TCP_URG_VALID)
mask |= POLLPRI;
+ } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+ /* Active TCP fastopen socket with defer_connect
+ * Return POLLOUT so application can call write()
+ * in order for kernel to generate SYN+data
+ */
+ mask |= POLLOUT | POLLWRNORM;
}
/* This barrier is coupled with smp_wmb() in tcp_reset() */
smp_rmb();
@@ -1079,6 +1085,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
int *copied, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
@@ -1096,11 +1103,26 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
tp->fastopen_req->data = msg;
tp->fastopen_req->size = size;
+ if (inet->defer_connect) {
+ err = tcp_connect(sk);
+ /* Same failure procedure as in tcp_v4/6_connect */
+ if (err) {
+ tcp_set_state(sk, TCP_CLOSE);
+ inet->inet_dport = 0;
+ sk->sk_route_caps = 0;
+ }
+ }
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, uaddr,
msg->msg_namelen, flags);
- *copied = tp->fastopen_req->copied;
- tcp_free_fastopen_req(tp);
+ /* fastopen_req could already be freed in __inet_stream_connect
+ * if the connection times out or gets rst
+ */
+ if (tp->fastopen_req) {
+ *copied = tp->fastopen_req->copied;
+ tcp_free_fastopen_req(tp);
+ inet->defer_connect = 0;
+ }
return err;
}
@@ -1118,7 +1140,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
lock_sock(sk);
flags = msg->msg_flags;
- if ((flags & MSG_FASTOPEN) && !tp->repair) {
+ if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+ !tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
@@ -2324,6 +2347,10 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->data_segs_in = 0;
tp->data_segs_out = 0;
+ /* Clean up fastopen related fields */
+ tcp_free_fastopen_req(tp);
+ inet->defer_connect = 0;
+
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
if (sk->sk_frag.page) {
@@ -2695,6 +2722,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = -EINVAL;
}
break;
+ case TCP_FASTOPEN_CONNECT:
+ if (val > 1 || val < 0) {
+ err = -EINVAL;
+ } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+ if (sk->sk_state == TCP_CLOSE)
+ tp->fastopen_connect = val;
+ else
+ err = -EINVAL;
+ } else {
+ err = -EOPNOTSUPP;
+ }
+ break;
case TCP_TIMESTAMP:
if (!tp->repair)
err = -EPERM;
@@ -3008,6 +3047,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = icsk->icsk_accept_queue.fastopenq.max_qlen;
break;
+ case TCP_FASTOPEN_CONNECT:
+ val = tp->fastopen_connect;
+ break;
+
case TCP_TIMESTAMP:
val = tcp_time_stamp + tp->tsoffset;
break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index dd2560c..8ea4e97 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -326,3 +326,57 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
*foc = valid_foc;
return NULL;
}
+
+bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
+ struct tcp_fastopen_cookie *cookie)
+{
+ unsigned long last_syn_loss = 0;
+ int syn_loss = 0;
+
+ tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);
+
+ /* Recurring FO SYN losses: no cookie or data in SYN */
+ if (syn_loss > 1 &&
+ time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) {
+ cookie->len = -1;
+ return false;
+ }
+ if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+ cookie->len = -1;
+ return true;
+ }
+ return cookie->len > 0;
+}
+
+/* This function checks if we want to defer sending SYN until the first
+ * write(). We defer under the following conditions:
+ * 1. fastopen_connect sockopt is set
+ * 2. we have a valid cookie
+ * Return value: return true if we want to defer until application writes data
+ * return false if we want to send out SYN immediately
+ */
+bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
+{
+ struct tcp_fastopen_cookie cookie = { .len = 0 };
+ struct tcp_sock *tp = tcp_sk(sk);
+ u16 mss;
+
+ if (tp->fastopen_connect && !tp->fastopen_req) {
+ if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) {
+ inet_sk(sk)->defer_connect = 1;
+ return true;
+ }
+
+ /* Alloc fastopen_req in order for FO option to be included
+ * in SYN
+ */
+ tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req),
+ sk->sk_allocation);
+ if (tp->fastopen_req)
+ tp->fastopen_req->cookie = cookie;
+ else
+ *err = -ENOBUFS;
+ }
+ return false;
+}
+EXPORT_SYMBOL(tcp_fastopen_defer_connect);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d05135e..e647007 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -424,7 +424,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
int rcvmem;
rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
- tcp_default_init_rwnd(mss);
+ tcp_default_init_rwnd(sock_net(sk), mss);
/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
* Allow enough cushion so that sender is not limited by our window
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 10c4a5f..fb27e36 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -232,6 +232,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
/* OK, now commit destination to socket. */
sk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(sk, &rt->dst);
+ rt = NULL;
if (!tp->write_seq && likely(!tp->repair))
tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
@@ -241,9 +242,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
inet->inet_id = prandom_u32();
+ if (tcp_fastopen_defer_connect(sk, &err))
+ return err;
+ if (err)
+ goto failure;
+
err = tcp_connect(sk);
- rt = NULL;
if (err)
goto failure;
@@ -696,6 +701,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
offsetof(struct inet_timewait_sock, tw_bound_dev_if));
arg.tos = ip_hdr(skb)->tos;
+ arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -716,7 +722,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct net *net,
+static void tcp_v4_send_ack(const struct sock *sk,
struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
@@ -731,6 +737,7 @@ static void tcp_v4_send_ack(struct net *net,
#endif
];
} rep;
+ struct net *net = sock_net(sk);
struct ip_reply_arg arg;
memset(&rep.th, 0, sizeof(struct tcphdr));
@@ -780,6 +787,7 @@ static void tcp_v4_send_ack(struct net *net,
if (oif)
arg.bound_dev_if = oif;
arg.tos = tos;
+ arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -795,7 +803,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(sock_net(sk), skb,
+ tcp_v4_send_ack(sk, skb,
tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
@@ -823,7 +831,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
* exception of <SYN> segments, MUST be right-shifted by
* Rcv.Wind.Shift bits:
*/
- tcp_v4_send_ack(sock_net(sk), skb, seq,
+ tcp_v4_send_ack(sk, skb, seq,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp,
@@ -1686,7 +1694,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
*/
sock_hold(sk);
refcounted = true;
- nsk = tcp_check_req(sk, skb, req, false);
+ nsk = NULL;
+ if (!tcp_filter(sk, skb))
+ nsk = tcp_check_req(sk, skb, req, false);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
@@ -2483,6 +2493,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_orphan_retries = 0;
net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+ net->ipv4.sysctl_tcp_default_init_rwnd = TCP_INIT_CWND * 2;
return 0;
fail:
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a501b45..25d028a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -390,7 +390,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
req->rsk_window_clamp = full_space;
/* tcp_full_space because it is guaranteed to be the first packet */
- tcp_select_initial_window(full_space,
+ tcp_select_initial_window(sock_net(sk_listener), full_space,
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rsk_rcv_wnd,
&req->rsk_window_clamp,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b790916..c9c2024 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -186,14 +186,14 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
}
-u32 tcp_default_init_rwnd(u32 mss)
+u32 tcp_default_init_rwnd(struct net *net, u32 mss)
{
/* Initial receive window should be twice of TCP_INIT_CWND to
* enable proper sending of new unsent data during fast recovery
* (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
* limit when mss is larger than 1460.
*/
- u32 init_rwnd = TCP_INIT_CWND * 2;
+ u32 init_rwnd = net->ipv4.sysctl_tcp_default_init_rwnd;
if (mss > 1460)
init_rwnd = max((1460 * init_rwnd) / mss, 2U);
@@ -207,7 +207,7 @@ u32 tcp_default_init_rwnd(u32 mss)
* be a multiple of mss if possible. We assume here that mss >= 1.
* This MUST be enforced by all callers.
*/
-void tcp_select_initial_window(int __space, __u32 mss,
+void tcp_select_initial_window(struct net *net, int __space, __u32 mss,
__u32 *rcv_wnd, __u32 *window_clamp,
int wscale_ok, __u8 *rcv_wscale,
__u32 init_rcv_wnd)
@@ -252,7 +252,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
if (mss > (1 << *rcv_wscale)) {
if (!init_rcv_wnd) /* Use default unless specified otherwise */
- init_rcv_wnd = tcp_default_init_rwnd(mss);
+ init_rcv_wnd = tcp_default_init_rwnd(net, mss);
*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
}
@@ -3270,7 +3270,7 @@ static void tcp_connect_init(struct sock *sk)
(tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
tp->window_clamp = tcp_full_space(sk);
- tcp_select_initial_window(tcp_full_space(sk),
+ tcp_select_initial_window(sock_net(sk), tcp_full_space(sk),
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
@@ -3328,23 +3328,11 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- int syn_loss = 0, space, err = 0;
- unsigned long last_syn_loss = 0;
+ int space, err = 0;
struct sk_buff *syn_data;
tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
- tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
- &syn_loss, &last_syn_loss);
- /* Recurring FO SYN losses: revert to regular handshake temporarily */
- if (syn_loss > 1 &&
- time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) {
- fo->cookie.len = -1;
- goto fallback;
- }
-
- if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE)
- fo->cookie.len = -1;
- else if (fo->cookie.len <= 0)
+ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie))
goto fallback;
/* MSS for SYN-data is based on cached MSS and bounded by PMTU and
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 18a1a48..d7d8870 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1022,7 +1022,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 1805413..16f03d8 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -22,7 +22,8 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct rtable *rt;
@@ -30,6 +31,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
fl4->daddr = daddr->a4;
fl4->flowi4_tos = tos;
fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
+ fl4->flowi4_mark = mark;
if (saddr)
fl4->saddr = saddr->a4;
@@ -44,20 +46,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct flowi4 fl4;
- return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr);
+ return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark);
}
static int xfrm4_get_saddr(struct net *net, int oif,
- xfrm_address_t *saddr, xfrm_address_t *daddr)
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ u32 mark)
{
struct dst_entry *dst;
struct flowi4 fl4;
- dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr);
+ dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6119ab3..bf7d5ae 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -223,9 +223,11 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -238,6 +240,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -269,9 +272,11 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -284,6 +289,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64,
};
/* Check if link is ready: is it up and is a valid qdisc available */
@@ -376,9 +382,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
if (ndev->cnf.stable_secret.initialized)
- ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
- else
- ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64;
+ ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
ndev->cnf.mtu6 = dev->mtu;
ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
@@ -2204,6 +2208,31 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad
ipv6_regen_rndid(idev);
}
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+ /* Determines into what table to put autoconf PIO/RIO/default routes
+ * learned on this device.
+ *
+ * - If 0, use the same table for every device. This puts routes into
+ * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+ * (but note that these three are currently all equal to
+ * RT6_TABLE_MAIN).
+ * - If > 0, use the specified table.
+ * - If < 0, put routes into table dev->ifindex + (-rt_table).
+ */
+ struct inet6_dev *idev = in6_dev_get(dev);
+ u32 table;
+ int sysctl = idev->cnf.accept_ra_rt_table;
+ if (sysctl == 0) {
+ table = default_table;
+ } else if (sysctl > 0) {
+ table = (u32) sysctl;
+ } else {
+ table = (unsigned) dev->ifindex + (-sysctl);
+ }
+ in6_dev_put(idev);
+ return table;
+}
+
/*
* Add prefix route.
*/
@@ -2213,7 +2242,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
+ .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX),
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
@@ -2246,7 +2275,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
+ u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX);
table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
@@ -2382,8 +2411,8 @@ static void manage_tempaddrs(struct inet6_dev *idev,
static bool is_addr_mode_generate_stable(struct inet6_dev *idev)
{
- return idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY ||
- idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
+ return idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY ||
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
}
int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
@@ -3145,9 +3174,13 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
if (netif_is_l3_master(idev->dev))
return;
+ /* no link local addresses on devices flagged as slaves */
+ if (idev->dev->flags & IFF_SLAVE)
+ return;
+
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
- switch (idev->addr_gen_mode) {
+ switch (idev->cnf.addr_gen_mode) {
case IN6_ADDR_GEN_MODE_RANDOM:
ipv6_gen_mode_random_init(idev);
/* fallthrough */
@@ -3203,8 +3236,8 @@ static void addrconf_dev_config(struct net_device *dev)
/* this device type has no EUI support */
if (dev->type == ARPHRD_NONE &&
- idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)
- idev->addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM;
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)
+ idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM;
addrconf_addr_gen(idev, false);
}
@@ -4963,9 +4996,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_PROBE_INTERVAL] =
jiffies_to_msecs(cnf->rtr_probe_interval);
#ifdef CONFIG_IPV6_ROUTE_INFO
+ array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -4988,6 +5023,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast;
array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na;
array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down;
+ array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode;
}
static inline size_t inet6_ifla6_size(void)
@@ -5099,7 +5135,7 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
if (!nla)
goto nla_put_failure;
- if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode))
+ if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode))
goto nla_put_failure;
read_lock_bh(&idev->lock);
@@ -5217,6 +5253,26 @@ static int inet6_validate_link_af(const struct net_device *dev,
return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
}
+static int check_addr_gen_mode(int mode)
+{
+ if (mode != IN6_ADDR_GEN_MODE_EUI64 &&
+ mode != IN6_ADDR_GEN_MODE_NONE &&
+ mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+ mode != IN6_ADDR_GEN_MODE_RANDOM)
+ return -EINVAL;
+ return 1;
+}
+
+static int check_stable_privacy(struct inet6_dev *idev, struct net *net,
+ int mode)
+{
+ if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+ !idev->cnf.stable_secret.initialized &&
+ !net->ipv6.devconf_dflt->stable_secret.initialized)
+ return -EINVAL;
+ return 1;
+}
+
static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
{
int err = -EINVAL;
@@ -5238,18 +5294,11 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
if (tb[IFLA_INET6_ADDR_GEN_MODE]) {
u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]);
- if (mode != IN6_ADDR_GEN_MODE_EUI64 &&
- mode != IN6_ADDR_GEN_MODE_NONE &&
- mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
- mode != IN6_ADDR_GEN_MODE_RANDOM)
+ if (check_addr_gen_mode(mode) < 0 ||
+ check_stable_privacy(idev, dev_net(dev), mode) < 0)
return -EINVAL;
- if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
- !idev->cnf.stable_secret.initialized &&
- !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized)
- return -EINVAL;
-
- idev->addr_gen_mode = mode;
+ idev->cnf.addr_gen_mode = mode;
err = 0;
}
@@ -5663,6 +5712,47 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
return ret;
}
+static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = 0;
+ int new_val;
+ struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
+ struct net *net = (struct net *)ctl->extra2;
+
+ ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+
+ if (write) {
+ new_val = *((int *)ctl->data);
+
+ if (check_addr_gen_mode(new_val) < 0)
+ return -EINVAL;
+
+ /* request for default */
+ if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
+ ipv6_devconf_dflt.addr_gen_mode = new_val;
+
+ /* request for individual net device */
+ } else {
+ if (!idev)
+ return ret;
+
+ if (check_stable_privacy(idev, net, new_val) < 0)
+ return -EINVAL;
+
+ if (idev->cnf.addr_gen_mode != new_val) {
+ idev->cnf.addr_gen_mode = new_val;
+ rtnl_lock();
+ addrconf_dev_config(idev->dev);
+ rtnl_unlock();
+ }
+ }
+ }
+
+ return ret;
+}
+
static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -5713,14 +5803,14 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
struct inet6_dev *idev = __in6_dev_get(dev);
if (idev) {
- idev->addr_gen_mode =
+ idev->cnf.addr_gen_mode =
IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
}
}
} else {
struct inet6_dev *idev = ctl->extra1;
- idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+ idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
}
out:
@@ -5945,6 +6035,13 @@ static const struct ctl_table addrconf_sysctl[] = {
},
#ifdef CONFIG_IPV6_ROUTE_INFO
{
+ .procname = "accept_ra_rt_info_min_plen",
+ .data = &ipv6_devconf.accept_ra_rt_info_min_plen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_rt_info_max_plen",
.data = &ipv6_devconf.accept_ra_rt_info_max_plen,
.maxlen = sizeof(int),
@@ -5954,6 +6051,13 @@ static const struct ctl_table addrconf_sysctl[] = {
#endif
#endif
{
+ .procname = "accept_ra_rt_table",
+ .data = &ipv6_devconf.accept_ra_rt_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "proxy_ndp",
.data = &ipv6_devconf.proxy_ndp,
.maxlen = sizeof(int),
@@ -6082,7 +6186,13 @@ static const struct ctl_table addrconf_sysctl[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
-
+ },
+ {
+ .procname = "addr_gen_mode",
+ .data = &ipv6_devconf.addr_gen_mode,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_addr_gen_mode,
},
{
/* sentinel */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c6746aa..dd19cdc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -65,6 +65,20 @@
#include <asm/uaccess.h>
#include <linux/mroute6.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
+
#include "ip6_offload.h"
MODULE_AUTHOR("Cast of dozens");
@@ -121,6 +135,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
if (protocol < 0 || protocol >= IPPROTO_MAX)
return -EINVAL;
+ if (!current_has_network())
+ return -EACCES;
+
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
@@ -167,8 +184,7 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
@@ -695,6 +711,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
rcu_read_lock();
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 519e073..98d253d 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -667,9 +667,10 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fa49878..c1d66f8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -54,6 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
fl6->flowlabel = np->flow_label;
+ fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index da158a3..37268a37 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -480,9 +480,10 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 305e2ed..477692f 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -166,15 +166,15 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv);
* to explore inner IPv6 header, eg. ICMPv6 error messages.
*
* If target header is found, its offset is set in *offset and return protocol
- * number. Otherwise, return -1.
+ * number. Otherwise, return -ENOENT or -EBADMSG.
*
* If the first fragment doesn't contain the final protocol header or
* NEXTHDR_NONE it is considered invalid.
*
* Note that non-1st fragment is special case that "the protocol number
* of last header" is "next header" field in Fragment header. In this case,
- * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
- * isn't NULL.
+ * *offset is meaningless. If fragoff is not NULL, the fragment offset is
+ * stored in *fragoff; if it is NULL, return -EINVAL.
*
* if flags is not NULL and it's a fragment, then the frag flag
* IP6_FH_F_FRAG will be set. If it's an AH header, the
@@ -253,9 +253,12 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
if (target < 0 &&
((!ipv6_ext_hdr(hp->nexthdr)) ||
hp->nexthdr == NEXTHDR_NONE)) {
- if (fragoff)
+ if (fragoff) {
*fragoff = _frag_off;
- return hp->nexthdr;
+ return hp->nexthdr;
+ } else {
+ return -EINVAL;
+ }
}
if (!found)
return -ENOENT;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 2772004..17fa28f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,9 +92,10 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
@@ -486,6 +487,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
@@ -660,6 +662,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index b760cce..d0ccf07 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -88,6 +88,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
+ fl6->flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
@@ -136,6 +137,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
rcu_read_lock();
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 85c7e25..f03855d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -915,6 +915,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
fn->fn_flags |= RTN_RTINFO;
}
nsiblings = iter->rt6i_nsiblings;
+ iter->rt6i_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
if (fn->rr_ptr == iter)
fn->rr_ptr = NULL;
@@ -929,6 +930,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
break;
if (rt6_qualify_for_ecmp(iter)) {
*ins = iter->dst.rt6_next;
+ iter->rt6i_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
if (fn->rr_ptr == iter)
fn->rr_ptr = NULL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e0a2a3d..1c10aa6 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -565,6 +565,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
return -1;
@@ -624,6 +626,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
return -1;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d93a98d..5fe493f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -39,6 +39,7 @@
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/bpf-cgroup.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -66,9 +67,6 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
struct in6_addr *nexthop;
int ret;
- skb->protocol = htons(ETH_P_IPV6);
- skb->dev = dev;
-
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
@@ -131,6 +129,14 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ int ret;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ if (ret) {
+ kfree_skb(skb);
+ return ret;
+ }
+
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
@@ -144,6 +150,9 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
struct net_device *dev = skb_dst(skb)->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->dev = dev;
+
if (unlikely(idev->cnf.disable_ipv6)) {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
@@ -868,7 +877,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
if (skb->sk && dst_allfrag(skb_dst(skb)))
sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
- skb->dev = skb_dst(skb)->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
err = -EMSGSIZE;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d9e60aa..1d29e53 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1283,6 +1283,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
@@ -1370,6 +1371,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index b9f5155..365f445 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -645,9 +645,10 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e..54d165b 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -74,9 +74,10 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 505d048f..300fb16 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -196,6 +196,8 @@ static inline int ndisc_is_useropt(const struct net_device *dev,
{
return opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
+ opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
+ opt->nd_opt_type == ND_OPT_PREF64 ||
ndisc_ops_is_useropt(dev, opt->nd_opt_type);
}
@@ -1395,6 +1397,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (ri->prefix_len == 0 &&
!in6_dev->cnf.accept_ra_defrtr)
continue;
+ if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+ continue;
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d11c468..39970e2 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -26,6 +26,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
+ .flowi6_uid = sock_net_uid(net, skb->sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 21cad30..bd27d8e 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -864,10 +864,6 @@ copy_entries_to_user(unsigned int total_size,
return PTR_ERR(counters);
loc_cpu_entry = private->entries;
- if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
- ret = -EFAULT;
- goto free_counters;
- }
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
@@ -877,6 +873,10 @@ copy_entries_to_user(unsigned int total_size,
const struct xt_entry_target *t;
e = (struct ip6t_entry *)(loc_cpu_entry + off);
+ if (copy_to_user(userptr + off, e, sizeof(*e))) {
+ ret = -EFAULT;
+ goto free_counters;
+ }
if (copy_to_user(userptr + off
+ offsetof(struct ip6t_entry, counters),
&counters[num],
@@ -890,23 +890,14 @@ copy_entries_to_user(unsigned int total_size,
i += m->u.match_size) {
m = (void *)e + i;
- if (copy_to_user(userptr + off + i
- + offsetof(struct xt_entry_match,
- u.user.name),
- m->u.kernel.match->name,
- strlen(m->u.kernel.match->name)+1)
- != 0) {
+ if (xt_match_to_user(m, userptr + off + i)) {
ret = -EFAULT;
goto free_counters;
}
}
t = ip6t_get_target_c(e);
- if (copy_to_user(userptr + off + e->target_offset
- + offsetof(struct xt_entry_target,
- u.user.name),
- t->u.kernel.target->name,
- strlen(t->u.kernel.target->name)+1) != 0) {
+ if (xt_target_to_user(t, userptr + off + e->target_offset)) {
ret = -EFAULT;
goto free_counters;
}
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 590f767..a379d2f 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -112,6 +112,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
.table = "mangle",
.target = ip6t_snpt_tg,
.targetsize = sizeof(struct ip6t_npt_tginfo),
+ .usersize = offsetof(struct ip6t_npt_tginfo, adjustment),
.checkentry = ip6t_npt_checkentry,
.family = NFPROTO_IPV6,
.hooks = (1 << NF_INET_LOCAL_IN) |
@@ -123,6 +124,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
.table = "mangle",
.target = ip6t_dnpt_tg,
.targetsize = sizeof(struct ip6t_npt_tginfo),
+ .usersize = offsetof(struct ip6t_npt_tginfo, adjustment),
.checkentry = ip6t_npt_checkentry,
.family = NFPROTO_IPV6,
.hooks = (1 << NF_INET_PRE_ROUTING) |
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index e209ae1..45c1a5b 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -113,6 +113,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.daddr = *daddr;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 47acd20..f3caf95 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -801,6 +801,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 03d1a61..abe18b5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1419,7 +1419,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1431,6 +1431,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1447,7 +1448,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
if (!oif && skb->dev)
oif = l3mdev_master_ifindex(skb->dev);
- ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark);
+ ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -1539,7 +1540,8 @@ static struct dst_entry *ip6_route_redirect(struct net *net,
flags, __ip6_route_redirect);
}
-void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+ kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1552,6 +1554,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1573,6 +1576,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
fl6.flowi6_mark = mark;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
dst = ip6_route_redirect(net, &fl6, &iph->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1581,7 +1585,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
- ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark);
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark,
+ sk->sk_uid);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
@@ -2356,8 +2361,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *gwaddr,
struct net_device *dev)
{
- u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
- int ifindex = dev->ifindex;
+ u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO);
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
@@ -2372,7 +2376,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->dst.dev->ifindex != ifindex)
+ if (rt->dst.dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
@@ -2403,7 +2407,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_nlinfo.nl_net = net,
};
- cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
+ cfg.fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO),
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
@@ -2419,7 +2423,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
{
- u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
+ u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_MAIN);
struct rt6_info *rt;
struct fib6_table *table;
@@ -2445,7 +2449,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
+ .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_DFLT),
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2468,43 +2472,16 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
return rt6_get_dflt_router(gwaddr, dev);
}
-static void __rt6_purge_dflt_routers(struct fib6_table *table)
-{
- struct rt6_info *rt;
-
-restart:
- read_lock_bh(&table->tb6_lock);
- for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- ip6_del_rt(rt);
- goto restart;
- }
- }
- read_unlock_bh(&table->tb6_lock);
-
- table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
+int rt6_addrconf_purge(struct rt6_info *rt, void *arg) {
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+ (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2))
+ return -1;
+ return 0;
}
void rt6_purge_dflt_routers(struct net *net)
{
- struct fib6_table *table;
- struct hlist_head *head;
- unsigned int h;
-
- rcu_read_lock();
-
- for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
- head = &net->ipv6.fib_table_hash[h];
- hlist_for_each_entry_rcu(table, head, tb6_hlist) {
- if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
- __rt6_purge_dflt_routers(table);
- }
- }
-
- rcu_read_unlock();
+ fib6_clean_all(net, rt6_addrconf_purge, NULL);
}
static void rtmsg_to_fib6_config(struct net *net,
@@ -2823,6 +2800,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_EXPIRES] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
[RTA_TABLE] = { .type = NLA_U32 },
};
@@ -3404,6 +3382,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (tb[RTA_MARK])
fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 0e368c1..2e8f7d0 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -228,6 +228,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
@@ -242,7 +243,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
(req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
req->rsk_window_clamp = full_space;
- tcp_select_initial_window(full_space, req->mss,
+ tcp_select_initial_window(sock_net(sk), full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7b336b7..6c594ce 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -238,6 +238,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
@@ -289,6 +290,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
inet->inet_sport,
inet->inet_dport);
+ if (tcp_fastopen_defer_connect(sk, &err))
+ return err;
+ if (err)
+ goto late_failure;
+
err = tcp_connect(sk);
if (err)
goto late_failure;
@@ -297,7 +303,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
late_failure:
tcp_set_state(sk, TCP_CLOSE);
- __sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
@@ -835,6 +840,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
+ fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
@@ -1240,9 +1246,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
- if (tcp_filter(sk, skb))
- goto discard;
-
/*
* socket locking is here for SMP purposes as backlog rcv
* is currently called with bh processing disabled.
@@ -1443,7 +1446,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
}
sock_hold(sk);
refcounted = true;
- nsk = tcp_check_req(sk, skb, req, false);
+ nsk = NULL;
+ if (!tcp_filter(sk, skb))
+ nsk = tcp_check_req(sk, skb, req, false);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1ad84e1..c2e53a9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1162,6 +1162,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
if (msg->msg_controllen) {
opt = &opt_space;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 0c7f27a..d82f427 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -29,7 +29,8 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct flowi6 fl6;
struct dst_entry *dst;
@@ -38,6 +39,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+ fl6.flowi6_mark = mark;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
@@ -54,12 +56,13 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
}
static int xfrm6_get_saddr(struct net *net, int oif,
- xfrm_address_t *saddr, xfrm_address_t *daddr)
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ u32 mark)
{
struct dst_entry *dst;
struct net_device *dev;
- dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr);
+ dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 76a008b..d9736b8 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1390,7 +1390,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
}
if (!x)
- x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family);
+ x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family);
if (x == NULL)
return -ENOENT;
@@ -2434,7 +2434,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
return err;
}
- xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN,
+ xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
pol->sadb_x_policy_dir - 1, &sel, pol_ctx,
1, &err);
security_xfrm_policy_free(pol_ctx);
@@ -2687,7 +2687,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_
return -EINVAL;
delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2);
- xp = xfrm_policy_byid(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN,
+ xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
dir, pol->sadb_x_policy_id, delete, &err);
if (xp == NULL)
return -ENOENT;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 15f8bd0..f94c814 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -711,7 +711,7 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
*/
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
- int length, int (*payload_hook)(struct sk_buff *skb))
+ int length)
{
struct l2tp_tunnel *tunnel = session->tunnel;
int offset;
@@ -832,13 +832,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
__skb_pull(skb, offset);
- /* If caller wants to process the payload before we queue the
- * packet, do so now.
- */
- if (payload_hook)
- if ((*payload_hook)(skb))
- goto discard;
-
/* Prepare skb for adding to the session's reorder_q. Hold
* packets for max reorder_timeout or 1 second if not
* reordering.
@@ -898,8 +891,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_queue_purge);
* Returns 1 if the packet was not a good data packet and could not be
* forwarded. All such packets are passed up to userspace to deal with.
*/
-static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
- int (*payload_hook)(struct sk_buff *skb))
+static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
{
struct l2tp_session *session = NULL;
unsigned char *ptr, *optr;
@@ -997,7 +989,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
goto error;
- l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+ l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
l2tp_session_dec_refcount(session);
return 0;
@@ -1026,7 +1018,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n",
tunnel->name, skb->len);
- if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook))
+ if (l2tp_udp_recv_core(tunnel, skb))
goto pass_up_put;
sock_put(sk);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 57c1810..891f79a 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -186,7 +186,6 @@ struct l2tp_tunnel {
#ifdef CONFIG_DEBUG_FS
void (*show)(struct seq_file *m, void *arg);
#endif
- int (*recv_payload_hook)(struct sk_buff *skb);
void (*old_sk_destruct)(struct sock *);
struct sock *sock; /* Parent socket */
int fd; /* Parent fd, if tunnel socket
@@ -264,7 +263,7 @@ int l2tp_session_delete(struct l2tp_session *session);
void l2tp_session_free(struct l2tp_session *session);
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
- int length, int (*payload_hook)(struct sk_buff *skb));
+ int length);
int l2tp_session_queue_purge(struct l2tp_session *session);
int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
void l2tp_session_set_header_len(struct l2tp_session *session, int version);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 3817c35..aa85e13 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -160,7 +160,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
goto discard_sess;
- l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+ l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
return 0;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 76ef758..bdd9c97 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -171,8 +171,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
goto discard_sess;
- l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
- tunnel->recv_payload_hook);
+ l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
return 0;
@@ -537,6 +536,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 979fa86..d684ae0 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -185,25 +185,6 @@ static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
* Receive data handling
*****************************************************************************/
-static int pppol2tp_recv_payload_hook(struct sk_buff *skb)
-{
- /* Skip PPP header, if present. In testing, Microsoft L2TP clients
- * don't send the PPP header (PPP header compression enabled), but
- * other clients can include the header. So we cope with both cases
- * here. The PPP header is always FF03 when using L2TP.
- *
- * Note that skb->data[] isn't dereferenced from a u16 ptr here since
- * the field may be unaligned.
- */
- if (!pskb_may_pull(skb, 2))
- return 1;
-
- if ((skb->data[0] == PPP_ALLSTATIONS) && (skb->data[1] == PPP_UI))
- skb_pull(skb, 2);
-
- return 0;
-}
-
/* Receive message. This is the recvmsg for the PPPoL2TP socket.
*/
static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg,
@@ -250,6 +231,17 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
if (sk == NULL)
goto no_sock;
+ /* If the first two bytes are 0xFF03, consider that it is the PPP's
+ * Address and Control fields and skip them. The L2TP module has always
+ * worked this way, although, in theory, the use of these fields should
+ * be negociated and handled at the PPP layer. These fields are
+ * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered
+ * Information command with Poll/Final bit set to zero (RFC 1662).
+ */
+ if (pskb_may_pull(skb, 2) && skb->data[0] == PPP_ALLSTATIONS &&
+ skb->data[1] == PPP_UI)
+ skb_pull(skb, 2);
+
if (sk->sk_state & PPPOX_BOUND) {
struct pppox_sock *po;
@@ -743,9 +735,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
goto end;
}
- if (tunnel->recv_payload_hook == NULL)
- tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
-
if (tunnel->peer_tunnel_id == 0)
tunnel->peer_tunnel_id = peer_tunnel_id;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e8d56d9..9875358 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1316,6 +1316,8 @@
based on who created the socket: the user or group. It is also
possible to check whether a socket actually exists.
+ Conflicts with '"quota, tag, uid" match'
+
config NETFILTER_XT_MATCH_POLICY
tristate 'IPsec "policy" match support'
depends on XFRM
@@ -1359,6 +1361,29 @@
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+config NETFILTER_XT_MATCH_QUOTA2
+ tristate '"quota2" match support'
+ depends on NETFILTER_ADVANCED
+ help
+ This option adds a `quota2' match, which allows to match on a
+ byte counter correctly and not per CPU.
+ It allows naming the quotas.
+ This is based on http://xtables-addons.git.sourceforge.net
+
+ If you want to compile it as a module, say M here and read
+ <file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+
+config NETFILTER_XT_MATCH_QUOTA2_LOG
+ bool '"quota2" Netfilter LOG support'
+ depends on NETFILTER_XT_MATCH_QUOTA2
+ default n
+ help
+ This option allows `quota2' to log ONCE when a quota limit
+ is passed. It logs via NETLINK using the NETLINK_NFLOG family.
+ It logs similarly to how ipt_ULOG would without data.
+
+ If unsure, say `N'.
+
config NETFILTER_XT_MATCH_RATEEST
tristate '"rateest" match support'
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index c23c3c8..f65df6d 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -168,6 +168,7 @@
obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA2) += xt_quota2.o
obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o
obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o
obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d507d0f..1f21aa3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1077,7 +1077,7 @@ static void gc_worker(struct work_struct *work)
next_run = gc_work->next_gc_run;
gc_work->last_bucket = i;
- queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
+ queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
}
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
@@ -1867,7 +1867,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
return 0;
}
-int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
+int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
{
unsigned int hashsize;
int rc;
@@ -1995,7 +1995,7 @@ int nf_conntrack_init_start(void)
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
conntrack_gc_work_init(&conntrack_gc_work);
- queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
+ queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ);
return 0;
diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c
index e84a578..d76afaf 100644
--- a/net/netfilter/nf_nat_ftp.c
+++ b/net/netfilter/nf_nat_ftp.c
@@ -134,7 +134,7 @@ static int __init nf_nat_ftp_init(void)
}
/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */
-static int warn_set(const char *val, struct kernel_param *kp)
+static int warn_set(const char *val, const struct kernel_param *kp)
{
printk(KERN_INFO KBUILD_MODNAME
": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n");
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index 1fb2258..8039bcd 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -107,7 +107,7 @@ static int __init nf_nat_irc_init(void)
}
/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */
-static int warn_set(const char *val, struct kernel_param *kp)
+static int warn_set(const char *val, const struct kernel_param *kp)
{
printk(KERN_INFO KBUILD_MODNAME
": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n");
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e065140..1db6988 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -267,6 +267,60 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
}
EXPORT_SYMBOL_GPL(xt_request_find_target);
+
+static int xt_obj_to_user(u16 __user *psize, u16 size,
+ void __user *pname, const char *name,
+ u8 __user *prev, u8 rev)
+{
+ if (put_user(size, psize))
+ return -EFAULT;
+ if (copy_to_user(pname, name, strlen(name) + 1))
+ return -EFAULT;
+ if (put_user(rev, prev))
+ return -EFAULT;
+
+ return 0;
+}
+
+#define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \
+ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \
+ U->u.user.name, K->u.kernel.TYPE->name, \
+ &U->u.user.revision, K->u.kernel.TYPE->revision)
+
+int xt_data_to_user(void __user *dst, const void *src,
+ int usersize, int size)
+{
+ usersize = usersize ? : size;
+ if (copy_to_user(dst, src, usersize))
+ return -EFAULT;
+ if (usersize != size && clear_user(dst + usersize, size - usersize))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xt_data_to_user);
+
+#define XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \
+ xt_data_to_user(U->data, K->data, \
+ K->u.kernel.TYPE->usersize, \
+ C_SIZE ? : K->u.kernel.TYPE->TYPE##size)
+
+int xt_match_to_user(const struct xt_entry_match *m,
+ struct xt_entry_match __user *u)
+{
+ return XT_OBJ_TO_USER(u, m, match, 0) ||
+ XT_DATA_TO_USER(u, m, match, 0);
+}
+EXPORT_SYMBOL_GPL(xt_match_to_user);
+
+int xt_target_to_user(const struct xt_entry_target *t,
+ struct xt_entry_target __user *u)
+{
+ return XT_OBJ_TO_USER(u, t, target, 0) ||
+ XT_DATA_TO_USER(u, t, target, 0);
+}
+EXPORT_SYMBOL_GPL(xt_target_to_user);
+
static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
{
const struct xt_match *m;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 00ef824..1390f34 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -380,6 +380,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.name = "CT",
.family = NFPROTO_UNSPEC,
.targetsize = sizeof(struct xt_ct_target_info),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v0,
.destroy = xt_ct_tg_destroy_v0,
.target = xt_ct_target_v0,
@@ -391,6 +392,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision = 1,
.targetsize = sizeof(struct xt_ct_target_info_v1),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v1,
.destroy = xt_ct_tg_destroy_v1,
.target = xt_ct_target_v1,
@@ -402,6 +404,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision = 2,
.targetsize = sizeof(struct xt_ct_target_info_v1),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v2,
.destroy = xt_ct_tg_destroy_v1,
.target = xt_ct_target_v1,
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 921c9bd..44c42a7 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -5,6 +5,7 @@
* After timer expires a kevent will be sent.
*
* Copyright (C) 2004, 2010 Nokia Corporation
+ *
* Written by Timo Teras <ext-timo.teras@nokia.com>
*
* Converted to x_tables and reworked for upstream inclusion
@@ -38,8 +39,17 @@
#include <linux/netfilter/xt_IDLETIMER.h>
#include <linux/kdev_t.h>
#include <linux/kobject.h>
+#include <linux/skbuff.h>
#include <linux/workqueue.h>
#include <linux/sysfs.h>
+#include <linux/rtc.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/suspend.h>
+#include <linux/notifier.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
struct idletimer_tg_attr {
struct attribute attr;
@@ -55,14 +65,110 @@ struct idletimer_tg {
struct kobject *kobj;
struct idletimer_tg_attr attr;
+ struct timespec delayed_timer_trigger;
+ struct timespec last_modified_timer;
+ struct timespec last_suspend_time;
+ struct notifier_block pm_nb;
+
+ int timeout;
unsigned int refcnt;
+ bool work_pending;
+ bool send_nl_msg;
+ bool active;
+ uid_t uid;
};
static LIST_HEAD(idletimer_tg_list);
static DEFINE_MUTEX(list_mutex);
+static DEFINE_SPINLOCK(timestamp_lock);
static struct kobject *idletimer_tg_kobj;
+static bool check_for_delayed_trigger(struct idletimer_tg *timer,
+ struct timespec *ts)
+{
+ bool state;
+ struct timespec temp;
+ spin_lock_bh(×tamp_lock);
+ timer->work_pending = false;
+ if ((ts->tv_sec - timer->last_modified_timer.tv_sec) > timer->timeout ||
+ timer->delayed_timer_trigger.tv_sec != 0) {
+ state = false;
+ temp.tv_sec = timer->timeout;
+ temp.tv_nsec = 0;
+ if (timer->delayed_timer_trigger.tv_sec != 0) {
+ temp = timespec_add(timer->delayed_timer_trigger, temp);
+ ts->tv_sec = temp.tv_sec;
+ ts->tv_nsec = temp.tv_nsec;
+ timer->delayed_timer_trigger.tv_sec = 0;
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ } else {
+ temp = timespec_add(timer->last_modified_timer, temp);
+ ts->tv_sec = temp.tv_sec;
+ ts->tv_nsec = temp.tv_nsec;
+ }
+ } else {
+ state = timer->active;
+ }
+ spin_unlock_bh(×tamp_lock);
+ return state;
+}
+
+static void notify_netlink_uevent(const char *iface, struct idletimer_tg *timer)
+{
+ char iface_msg[NLMSG_MAX_SIZE];
+ char state_msg[NLMSG_MAX_SIZE];
+ char timestamp_msg[NLMSG_MAX_SIZE];
+ char uid_msg[NLMSG_MAX_SIZE];
+ char *envp[] = { iface_msg, state_msg, timestamp_msg, uid_msg, NULL };
+ int res;
+ struct timespec ts;
+ uint64_t time_ns;
+ bool state;
+
+ res = snprintf(iface_msg, NLMSG_MAX_SIZE, "INTERFACE=%s",
+ iface);
+ if (NLMSG_MAX_SIZE <= res) {
+ pr_err("message too long (%d)", res);
+ return;
+ }
+
+ get_monotonic_boottime(&ts);
+ state = check_for_delayed_trigger(timer, &ts);
+ res = snprintf(state_msg, NLMSG_MAX_SIZE, "STATE=%s",
+ state ? "active" : "inactive");
+
+ if (NLMSG_MAX_SIZE <= res) {
+ pr_err("message too long (%d)", res);
+ return;
+ }
+
+ if (state) {
+ res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=%u", timer->uid);
+ if (NLMSG_MAX_SIZE <= res)
+ pr_err("message too long (%d)", res);
+ } else {
+ res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=");
+ if (NLMSG_MAX_SIZE <= res)
+ pr_err("message too long (%d)", res);
+ }
+
+ time_ns = timespec_to_ns(&ts);
+ res = snprintf(timestamp_msg, NLMSG_MAX_SIZE, "TIME_NS=%llu", time_ns);
+ if (NLMSG_MAX_SIZE <= res) {
+ timestamp_msg[0] = '\0';
+ pr_err("message too long (%d)", res);
+ }
+
+ pr_debug("putting nlmsg: <%s> <%s> <%s> <%s>\n", iface_msg, state_msg,
+ timestamp_msg, uid_msg);
+ kobject_uevent_env(idletimer_tg_kobj, KOBJ_CHANGE, envp);
+ return;
+
+
+}
+
static
struct idletimer_tg *__idletimer_tg_find_by_label(const char *label)
{
@@ -83,6 +189,7 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
{
struct idletimer_tg *timer;
unsigned long expires = 0;
+ unsigned long now = jiffies;
mutex_lock(&list_mutex);
@@ -92,11 +199,15 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
mutex_unlock(&list_mutex);
- if (time_after(expires, jiffies))
+ if (time_after(expires, now))
return sprintf(buf, "%u\n",
- jiffies_to_msecs(expires - jiffies) / 1000);
+ jiffies_to_msecs(expires - now) / 1000);
- return sprintf(buf, "0\n");
+ if (timer->send_nl_msg)
+ return sprintf(buf, "0 %d\n",
+ jiffies_to_msecs(now - expires) / 1000);
+ else
+ return sprintf(buf, "0\n");
}
static void idletimer_tg_work(struct work_struct *work)
@@ -105,6 +216,9 @@ static void idletimer_tg_work(struct work_struct *work)
work);
sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name);
+
+ if (timer->send_nl_msg)
+ notify_netlink_uevent(timer->attr.attr.name, timer);
}
static void idletimer_tg_expired(unsigned long data)
@@ -112,8 +226,55 @@ static void idletimer_tg_expired(unsigned long data)
struct idletimer_tg *timer = (struct idletimer_tg *) data;
pr_debug("timer %s expired\n", timer->attr.attr.name);
-
+ spin_lock_bh(×tamp_lock);
+ timer->active = false;
+ timer->work_pending = true;
schedule_work(&timer->work);
+ spin_unlock_bh(×tamp_lock);
+}
+
+static int idletimer_resume(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ struct timespec ts;
+ unsigned long time_diff, now = jiffies;
+ struct idletimer_tg *timer = container_of(notifier,
+ struct idletimer_tg, pm_nb);
+ if (!timer)
+ return NOTIFY_DONE;
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ get_monotonic_boottime(&timer->last_suspend_time);
+ break;
+ case PM_POST_SUSPEND:
+ spin_lock_bh(×tamp_lock);
+ if (!timer->active) {
+ spin_unlock_bh(×tamp_lock);
+ break;
+ }
+ /* since jiffies are not updated when suspended now represents
+ * the time it would have suspended */
+ if (time_after(timer->timer.expires, now)) {
+ get_monotonic_boottime(&ts);
+ ts = timespec_sub(ts, timer->last_suspend_time);
+ time_diff = timespec_to_jiffies(&ts);
+ if (timer->timer.expires > (time_diff + now)) {
+ mod_timer_pending(&timer->timer,
+ (timer->timer.expires - time_diff));
+ } else {
+ del_timer(&timer->timer);
+ timer->timer.expires = 0;
+ timer->active = false;
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ }
+ }
+ spin_unlock_bh(×tamp_lock);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
}
static int idletimer_check_sysfs_name(const char *name, unsigned int size)
@@ -166,6 +327,21 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
setup_timer(&info->timer->timer, idletimer_tg_expired,
(unsigned long) info->timer);
info->timer->refcnt = 1;
+ info->timer->send_nl_msg = (info->send_nl_msg == 0) ? false : true;
+ info->timer->active = true;
+ info->timer->timeout = info->timeout;
+
+ info->timer->delayed_timer_trigger.tv_sec = 0;
+ info->timer->delayed_timer_trigger.tv_nsec = 0;
+ info->timer->work_pending = false;
+ info->timer->uid = 0;
+ get_monotonic_boottime(&info->timer->last_modified_timer);
+
+ info->timer->pm_nb.notifier_call = idletimer_resume;
+ ret = register_pm_notifier(&info->timer->pm_nb);
+ if (ret)
+ printk(KERN_WARNING "[%s] Failed to register pm notifier %d\n",
+ __func__, ret);
INIT_WORK(&info->timer->work, idletimer_tg_work);
@@ -182,6 +358,42 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
return ret;
}
+static void reset_timer(const struct idletimer_tg_info *info,
+ struct sk_buff *skb)
+{
+ unsigned long now = jiffies;
+ struct idletimer_tg *timer = info->timer;
+ bool timer_prev;
+
+ spin_lock_bh(×tamp_lock);
+ timer_prev = timer->active;
+ timer->active = true;
+ /* timer_prev is used to guard overflow problem in time_before*/
+ if (!timer_prev || time_before(timer->timer.expires, now)) {
+ pr_debug("Starting Checkentry timer (Expired, Jiffies): %lu, %lu\n",
+ timer->timer.expires, now);
+
+ /* Stores the uid resposible for waking up the radio */
+ if (skb && (skb->sk)) {
+ timer->uid = from_kuid_munged(current_user_ns(),
+ sock_i_uid(skb_to_full_sk(skb)));
+ }
+
+ /* checks if there is a pending inactive notification*/
+ if (timer->work_pending)
+ timer->delayed_timer_trigger = timer->last_modified_timer;
+ else {
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ }
+ }
+
+ get_monotonic_boottime(&timer->last_modified_timer);
+ mod_timer(&timer->timer,
+ msecs_to_jiffies(info->timeout * 1000) + now);
+ spin_unlock_bh(×tamp_lock);
+}
+
/*
* The actual xt_tables plugin.
*/
@@ -189,15 +401,23 @@ static unsigned int idletimer_tg_target(struct sk_buff *skb,
const struct xt_action_param *par)
{
const struct idletimer_tg_info *info = par->targinfo;
+ unsigned long now = jiffies;
pr_debug("resetting timer %s, timeout period %u\n",
info->label, info->timeout);
BUG_ON(!info->timer);
- mod_timer(&info->timer->timer,
- msecs_to_jiffies(info->timeout * 1000) + jiffies);
+ info->timer->active = true;
+ if (time_before(info->timer->timer.expires, now)) {
+ schedule_work(&info->timer->work);
+ pr_debug("Starting timer %s (Expired, Jiffies): %lu, %lu\n",
+ info->label, info->timer->timer.expires, now);
+ }
+
+ /* TODO: Avoid modifying timers on each packet */
+ reset_timer(info, skb);
return XT_CONTINUE;
}
@@ -206,7 +426,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
struct idletimer_tg_info *info = par->targinfo;
int ret;
- pr_debug("checkentry targinfo%s\n", info->label);
+ pr_debug("checkentry targinfo %s\n", info->label);
if (info->timeout == 0) {
pr_debug("timeout value is zero\n");
@@ -228,9 +448,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
info->timer = __idletimer_tg_find_by_label(info->label);
if (info->timer) {
info->timer->refcnt++;
- mod_timer(&info->timer->timer,
- msecs_to_jiffies(info->timeout * 1000) + jiffies);
-
+ reset_timer(info, NULL);
pr_debug("increased refcnt of timer %s to %u\n",
info->label, info->timer->refcnt);
} else {
@@ -243,6 +461,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
}
mutex_unlock(&list_mutex);
+
return 0;
}
@@ -259,13 +478,14 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par)
list_del(&info->timer->entry);
del_timer_sync(&info->timer->timer);
- cancel_work_sync(&info->timer->work);
sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr);
+ unregister_pm_notifier(&info->timer->pm_nb);
+ cancel_work_sync(&info->timer->work);
kfree(info->timer->attr.attr.name);
kfree(info->timer);
} else {
pr_debug("decreased refcnt of timer %s to %u\n",
- info->label, info->timer->refcnt);
+ info->label, info->timer->refcnt);
}
mutex_unlock(&list_mutex);
@@ -273,6 +493,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par)
static struct xt_target idletimer_tg __read_mostly = {
.name = "IDLETIMER",
+ .revision = 1,
.family = NFPROTO_UNSPEC,
.target = idletimer_tg_target,
.targetsize = sizeof(struct idletimer_tg_info),
@@ -338,3 +559,4 @@ MODULE_DESCRIPTION("Xtables: idle time monitor");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("ipt_IDLETIMER");
MODULE_ALIAS("ip6t_IDLETIMER");
+MODULE_ALIAS("arpt_IDLETIMER");
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 1076b8a..2306e6e 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -177,6 +177,7 @@ static struct xt_target xt_rateest_tg_reg __read_mostly = {
.checkentry = xt_rateest_tg_checkentry,
.destroy = xt_rateest_tg_destroy,
.targetsize = sizeof(struct xt_rateest_target_info),
+ .usersize = offsetof(struct xt_rateest_target_info, est),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 0471db4..23b2438 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -133,6 +133,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.target = tee_tg4,
.targetsize = sizeof(struct xt_tee_tginfo),
+ .usersize = offsetof(struct xt_tee_tginfo, priv),
.checkentry = tee_tg_check,
.destroy = tee_tg_destroy,
.me = THIS_MODULE,
@@ -144,6 +145,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.target = tee_tg6,
.targetsize = sizeof(struct xt_tee_tginfo),
+ .usersize = offsetof(struct xt_tee_tginfo, priv),
.checkentry = tee_tg_check,
.destroy = tee_tg_destroy,
.me = THIS_MODULE,
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 7b993f2..7e7746c 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -8,8 +8,10 @@
*/
#include <linux/module.h>
+#include <linux/syscalls.h>
#include <linux/skbuff.h>
#include <linux/filter.h>
+#include <linux/bpf.h>
#include <linux/netfilter/xt_bpf.h>
#include <linux/netfilter/x_tables.h>
@@ -20,18 +22,18 @@ MODULE_LICENSE("GPL");
MODULE_ALIAS("ipt_bpf");
MODULE_ALIAS("ip6t_bpf");
-static int bpf_mt_check(const struct xt_mtchk_param *par)
+static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len,
+ struct bpf_prog **ret)
{
- struct xt_bpf_info *info = par->matchinfo;
struct sock_fprog_kern program;
- if (info->bpf_program_num_elem > XT_BPF_MAX_NUM_INSTR)
+ if (len > XT_BPF_MAX_NUM_INSTR)
return -EINVAL;
- program.len = info->bpf_program_num_elem;
- program.filter = info->bpf_program;
+ program.len = len;
+ program.filter = insns;
- if (bpf_prog_create(&info->filter, &program)) {
+ if (bpf_prog_create(ret, &program)) {
pr_info("bpf: check failed: parse error\n");
return -EINVAL;
}
@@ -39,6 +41,53 @@ static int bpf_mt_check(const struct xt_mtchk_param *par)
return 0;
}
+static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret)
+{
+ struct bpf_prog *prog;
+
+ prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ *ret = prog;
+ return 0;
+}
+
+static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
+{
+ if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX)
+ return -EINVAL;
+
+ *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER);
+ return PTR_ERR_OR_ZERO(*ret);
+
+}
+
+static int bpf_mt_check(const struct xt_mtchk_param *par)
+{
+ struct xt_bpf_info *info = par->matchinfo;
+
+ return __bpf_mt_check_bytecode(info->bpf_program,
+ info->bpf_program_num_elem,
+ &info->filter);
+}
+
+static int bpf_mt_check_v1(const struct xt_mtchk_param *par)
+{
+ struct xt_bpf_info_v1 *info = par->matchinfo;
+
+ if (info->mode == XT_BPF_MODE_BYTECODE)
+ return __bpf_mt_check_bytecode(info->bpf_program,
+ info->bpf_program_num_elem,
+ &info->filter);
+ else if (info->mode == XT_BPF_MODE_FD_ELF)
+ return __bpf_mt_check_fd(info->fd, &info->filter);
+ else if (info->mode == XT_BPF_MODE_PATH_PINNED)
+ return __bpf_mt_check_path(info->path, &info->filter);
+ else
+ return -EINVAL;
+}
+
static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_bpf_info *info = par->matchinfo;
@@ -46,31 +95,60 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par)
return BPF_PROG_RUN(info->filter, skb);
}
+static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_bpf_info_v1 *info = par->matchinfo;
+
+ return !!bpf_prog_run_save_cb(info->filter, (struct sk_buff *) skb);
+}
+
static void bpf_mt_destroy(const struct xt_mtdtor_param *par)
{
const struct xt_bpf_info *info = par->matchinfo;
+
bpf_prog_destroy(info->filter);
}
-static struct xt_match bpf_mt_reg __read_mostly = {
- .name = "bpf",
- .revision = 0,
- .family = NFPROTO_UNSPEC,
- .checkentry = bpf_mt_check,
- .match = bpf_mt,
- .destroy = bpf_mt_destroy,
- .matchsize = sizeof(struct xt_bpf_info),
- .me = THIS_MODULE,
+static void bpf_mt_destroy_v1(const struct xt_mtdtor_param *par)
+{
+ const struct xt_bpf_info_v1 *info = par->matchinfo;
+
+ bpf_prog_destroy(info->filter);
+}
+
+static struct xt_match bpf_mt_reg[] __read_mostly = {
+ {
+ .name = "bpf",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .checkentry = bpf_mt_check,
+ .match = bpf_mt,
+ .destroy = bpf_mt_destroy,
+ .matchsize = sizeof(struct xt_bpf_info),
+ .usersize = offsetof(struct xt_bpf_info, filter),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "bpf",
+ .revision = 1,
+ .family = NFPROTO_UNSPEC,
+ .checkentry = bpf_mt_check_v1,
+ .match = bpf_mt_v1,
+ .destroy = bpf_mt_destroy_v1,
+ .matchsize = sizeof(struct xt_bpf_info_v1),
+ .usersize = offsetof(struct xt_bpf_info_v1, filter),
+ .me = THIS_MODULE,
+ },
};
static int __init bpf_mt_init(void)
{
- return xt_register_match(&bpf_mt_reg);
+ return xt_register_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg));
}
static void __exit bpf_mt_exit(void)
{
- xt_unregister_match(&bpf_mt_reg);
+ xt_unregister_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg));
}
module_init(bpf_mt_init);
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 0eddbd5..891f4e7 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -123,6 +123,7 @@ static struct xt_match cgroup_mt_reg[] __read_mostly = {
.checkentry = cgroup_mt_check_v1,
.match = cgroup_mt_v1,
.matchsize = sizeof(struct xt_cgroup_info_v1),
+ .usersize = offsetof(struct xt_cgroup_info_v1, priv),
.destroy = cgroup_mt_destroy_v1,
.me = THIS_MODULE,
.hooks = (1 << NF_INET_LOCAL_OUT) |
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index b6dc322..6b36598 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -431,6 +431,7 @@ static struct xt_match connlimit_mt_reg __read_mostly = {
.checkentry = connlimit_mt_check,
.match = connlimit_mt,
.matchsize = sizeof(struct xt_connlimit_info),
+ .usersize = offsetof(struct xt_connlimit_info, data),
.destroy = connlimit_mt_destroy,
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 140a9ae2..97df6f9 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -851,6 +851,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.match = hashlimit_mt_v1,
.matchsize = sizeof(struct xt_hashlimit_mtinfo1),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo),
.checkentry = hashlimit_mt_check_v1,
.destroy = hashlimit_mt_destroy_v1,
.me = THIS_MODULE,
@@ -861,6 +862,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.match = hashlimit_mt,
.matchsize = sizeof(struct xt_hashlimit_mtinfo2),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo),
.checkentry = hashlimit_mt_check,
.destroy = hashlimit_mt_destroy,
.me = THIS_MODULE,
@@ -872,6 +874,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.match = hashlimit_mt_v1,
.matchsize = sizeof(struct xt_hashlimit_mtinfo1),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo),
.checkentry = hashlimit_mt_check_v1,
.destroy = hashlimit_mt_destroy_v1,
.me = THIS_MODULE,
@@ -882,6 +885,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.match = hashlimit_mt,
.matchsize = sizeof(struct xt_hashlimit_mtinfo2),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo),
.checkentry = hashlimit_mt_check,
.destroy = hashlimit_mt_destroy,
.me = THIS_MODULE,
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index bef8505..dab962d 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -192,6 +192,8 @@ static struct xt_match limit_mt_reg __read_mostly = {
.compatsize = sizeof(struct compat_xt_rateinfo),
.compat_from_user = limit_mt_compat_from_user,
.compat_to_user = limit_mt_compat_to_user,
+#else
+ .usersize = offsetof(struct xt_rateinfo, prev),
#endif
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index 44c8eb4..10d61a6 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -73,6 +73,7 @@ static struct xt_match quota_mt_reg __read_mostly = {
.checkentry = quota_mt_check,
.destroy = quota_mt_destroy,
.matchsize = sizeof(struct xt_quota_info),
+ .usersize = offsetof(struct xt_quota_info, master),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c
new file mode 100644
index 0000000..5c1c160
--- /dev/null
+++ b/net/netfilter/xt_quota2.c
@@ -0,0 +1,400 @@
+/*
+ * xt_quota2 - enhanced xt_quota that can count upwards and in packets
+ * as a minimal accounting match.
+ * by Jan Engelhardt <jengelh@medozas.de>, 2008
+ *
+ * Originally based on xt_quota.c:
+ * netfilter module to enforce network quotas
+ * Sam Johnston <samj@samj.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License; either
+ * version 2 of the License, as published by the Free Software Foundation.
+ */
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_quota2.h>
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+/* For compatibility, these definitions are copied from the
+ * deprecated header file <linux/netfilter_ipv4/ipt_ULOG.h> */
+#define ULOG_MAC_LEN 80
+#define ULOG_PREFIX_LEN 32
+
+/* Format of the ULOG packets passed through netlink */
+typedef struct ulog_packet_msg {
+ unsigned long mark;
+ long timestamp_sec;
+ long timestamp_usec;
+ unsigned int hook;
+ char indev_name[IFNAMSIZ];
+ char outdev_name[IFNAMSIZ];
+ size_t data_len;
+ char prefix[ULOG_PREFIX_LEN];
+ unsigned char mac_len;
+ unsigned char mac[ULOG_MAC_LEN];
+ unsigned char payload[0];
+} ulog_packet_msg_t;
+#endif
+
+/**
+ * @lock: lock to protect quota writers from each other
+ */
+struct xt_quota_counter {
+ u_int64_t quota;
+ spinlock_t lock;
+ struct list_head list;
+ atomic_t ref;
+ char name[sizeof(((struct xt_quota_mtinfo2 *)NULL)->name)];
+ struct proc_dir_entry *procfs_entry;
+};
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+/* Harald's favorite number +1 :D From ipt_ULOG.C */
+static int qlog_nl_event = 112;
+module_param_named(event_num, qlog_nl_event, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(event_num,
+ "Event number for NETLINK_NFLOG message. 0 disables log."
+ "111 is what ipt_ULOG uses.");
+static struct sock *nflognl;
+#endif
+
+static LIST_HEAD(counter_list);
+static DEFINE_SPINLOCK(counter_list_lock);
+
+static struct proc_dir_entry *proc_xt_quota;
+static unsigned int quota_list_perms = S_IRUGO | S_IWUSR;
+static kuid_t quota_list_uid = KUIDT_INIT(0);
+static kgid_t quota_list_gid = KGIDT_INIT(0);
+module_param_named(perms, quota_list_perms, uint, S_IRUGO | S_IWUSR);
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+static void quota2_log(unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const char *prefix)
+{
+ ulog_packet_msg_t *pm;
+ struct sk_buff *log_skb;
+ size_t size;
+ struct nlmsghdr *nlh;
+
+ if (!qlog_nl_event)
+ return;
+
+ size = NLMSG_SPACE(sizeof(*pm));
+ size = max(size, (size_t)NLMSG_GOODSIZE);
+ log_skb = alloc_skb(size, GFP_ATOMIC);
+ if (!log_skb) {
+ pr_err("xt_quota2: cannot alloc skb for logging\n");
+ return;
+ }
+
+ nlh = nlmsg_put(log_skb, /*pid*/0, /*seq*/0, qlog_nl_event,
+ sizeof(*pm), 0);
+ if (!nlh) {
+ pr_err("xt_quota2: nlmsg_put failed\n");
+ kfree_skb(log_skb);
+ return;
+ }
+ pm = nlmsg_data(nlh);
+ if (skb->tstamp.tv64 == 0)
+ __net_timestamp((struct sk_buff *)skb);
+ pm->data_len = 0;
+ pm->hook = hooknum;
+ if (prefix != NULL)
+ strlcpy(pm->prefix, prefix, sizeof(pm->prefix));
+ else
+ *(pm->prefix) = '\0';
+ if (in)
+ strlcpy(pm->indev_name, in->name, sizeof(pm->indev_name));
+ else
+ pm->indev_name[0] = '\0';
+
+ if (out)
+ strlcpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
+ else
+ pm->outdev_name[0] = '\0';
+
+ NETLINK_CB(log_skb).dst_group = 1;
+ pr_debug("throwing 1 packets to netlink group 1\n");
+ netlink_broadcast(nflognl, log_skb, 0, 1, GFP_ATOMIC);
+}
+#else
+static void quota2_log(unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const char *prefix)
+{
+}
+#endif /* if+else CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG */
+
+static ssize_t quota_proc_read(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ spin_lock_bh(&e->lock);
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", e->quota);
+ spin_unlock_bh(&e->lock);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t quota_proc_write(struct file *file, const char __user *input,
+ size_t size, loff_t *ppos)
+{
+ struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+ char buf[sizeof("18446744073709551616")];
+
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+ if (copy_from_user(buf, input, size) != 0)
+ return -EFAULT;
+ buf[sizeof(buf)-1] = '\0';
+
+ spin_lock_bh(&e->lock);
+ e->quota = simple_strtoull(buf, NULL, 0);
+ spin_unlock_bh(&e->lock);
+ return size;
+}
+
+static const struct file_operations q2_counter_fops = {
+ .read = quota_proc_read,
+ .write = quota_proc_write,
+ .llseek = default_llseek,
+};
+
+static struct xt_quota_counter *
+q2_new_counter(const struct xt_quota_mtinfo2 *q, bool anon)
+{
+ struct xt_quota_counter *e;
+ unsigned int size;
+
+ /* Do not need all the procfs things for anonymous counters. */
+ size = anon ? offsetof(typeof(*e), list) : sizeof(*e);
+ e = kmalloc(size, GFP_KERNEL);
+ if (e == NULL)
+ return NULL;
+
+ e->quota = q->quota;
+ spin_lock_init(&e->lock);
+ if (!anon) {
+ INIT_LIST_HEAD(&e->list);
+ atomic_set(&e->ref, 1);
+ strlcpy(e->name, q->name, sizeof(e->name));
+ }
+ return e;
+}
+
+/**
+ * q2_get_counter - get ref to counter or create new
+ * @name: name of counter
+ */
+static struct xt_quota_counter *
+q2_get_counter(const struct xt_quota_mtinfo2 *q)
+{
+ struct proc_dir_entry *p;
+ struct xt_quota_counter *e = NULL;
+ struct xt_quota_counter *new_e;
+
+ if (*q->name == '\0')
+ return q2_new_counter(q, true);
+
+ /* No need to hold a lock while getting a new counter */
+ new_e = q2_new_counter(q, false);
+ if (new_e == NULL)
+ goto out;
+
+ spin_lock_bh(&counter_list_lock);
+ list_for_each_entry(e, &counter_list, list)
+ if (strcmp(e->name, q->name) == 0) {
+ atomic_inc(&e->ref);
+ spin_unlock_bh(&counter_list_lock);
+ kfree(new_e);
+ pr_debug("xt_quota2: old counter name=%s", e->name);
+ return e;
+ }
+ e = new_e;
+ pr_debug("xt_quota2: new_counter name=%s", e->name);
+ list_add_tail(&e->list, &counter_list);
+ /* The entry having a refcount of 1 is not directly destructible.
+ * This func has not yet returned the new entry, thus iptables
+ * has not references for destroying this entry.
+ * For another rule to try to destroy it, it would 1st need for this
+ * func* to be re-invoked, acquire a new ref for the same named quota.
+ * Nobody will access the e->procfs_entry either.
+ * So release the lock. */
+ spin_unlock_bh(&counter_list_lock);
+
+ /* create_proc_entry() is not spin_lock happy */
+ p = e->procfs_entry = proc_create_data(e->name, quota_list_perms,
+ proc_xt_quota, &q2_counter_fops, e);
+
+ if (IS_ERR_OR_NULL(p)) {
+ spin_lock_bh(&counter_list_lock);
+ list_del(&e->list);
+ spin_unlock_bh(&counter_list_lock);
+ goto out;
+ }
+ proc_set_user(p, quota_list_uid, quota_list_gid);
+ return e;
+
+ out:
+ kfree(e);
+ return NULL;
+}
+
+static int quota_mt2_check(const struct xt_mtchk_param *par)
+{
+ struct xt_quota_mtinfo2 *q = par->matchinfo;
+
+ pr_debug("xt_quota2: check() flags=0x%04x", q->flags);
+
+ if (q->flags & ~XT_QUOTA_MASK)
+ return -EINVAL;
+
+ q->name[sizeof(q->name)-1] = '\0';
+ if (*q->name == '.' || strchr(q->name, '/') != NULL) {
+ printk(KERN_ERR "xt_quota.3: illegal name\n");
+ return -EINVAL;
+ }
+
+ q->master = q2_get_counter(q);
+ if (q->master == NULL) {
+ printk(KERN_ERR "xt_quota.3: memory alloc failure\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void quota_mt2_destroy(const struct xt_mtdtor_param *par)
+{
+ struct xt_quota_mtinfo2 *q = par->matchinfo;
+ struct xt_quota_counter *e = q->master;
+
+ if (*q->name == '\0') {
+ kfree(e);
+ return;
+ }
+
+ spin_lock_bh(&counter_list_lock);
+ if (!atomic_dec_and_test(&e->ref)) {
+ spin_unlock_bh(&counter_list_lock);
+ return;
+ }
+
+ list_del(&e->list);
+ spin_unlock_bh(&counter_list_lock);
+ remove_proc_entry(e->name, proc_xt_quota);
+ kfree(e);
+}
+
+static bool
+quota_mt2(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ struct xt_quota_mtinfo2 *q = (void *)par->matchinfo;
+ struct xt_quota_counter *e = q->master;
+ int charge = (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+ bool no_change = q->flags & XT_QUOTA_NO_CHANGE;
+ bool ret = q->flags & XT_QUOTA_INVERT;
+
+ spin_lock_bh(&e->lock);
+ if (q->flags & XT_QUOTA_GROW) {
+ /*
+ * While no_change is pointless in "grow" mode, we will
+ * implement it here simply to have a consistent behavior.
+ */
+ if (!no_change)
+ e->quota += charge;
+ ret = true; /* note: does not respect inversion (bug??) */
+ } else {
+ if (e->quota > charge) {
+ if (!no_change)
+ e->quota -= charge;
+ ret = !ret;
+ } else if (e->quota) {
+ /* We are transitioning, log that fact. */
+ quota2_log(par->hooknum,
+ skb,
+ par->in,
+ par->out,
+ q->name);
+ /* we do not allow even small packets from now on */
+ e->quota = 0;
+ }
+ }
+ spin_unlock_bh(&e->lock);
+ return ret;
+}
+
+static struct xt_match quota_mt2_reg[] __read_mostly = {
+ {
+ .name = "quota2",
+ .revision = 3,
+ .family = NFPROTO_IPV4,
+ .checkentry = quota_mt2_check,
+ .match = quota_mt2,
+ .destroy = quota_mt2_destroy,
+ .matchsize = sizeof(struct xt_quota_mtinfo2),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "quota2",
+ .revision = 3,
+ .family = NFPROTO_IPV6,
+ .checkentry = quota_mt2_check,
+ .match = quota_mt2,
+ .destroy = quota_mt2_destroy,
+ .matchsize = sizeof(struct xt_quota_mtinfo2),
+ .me = THIS_MODULE,
+ },
+};
+
+static int __init quota_mt2_init(void)
+{
+ int ret;
+ pr_debug("xt_quota2: init()");
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+ nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, NULL);
+ if (!nflognl)
+ return -ENOMEM;
+#endif
+
+ proc_xt_quota = proc_mkdir("xt_quota", init_net.proc_net);
+ if (proc_xt_quota == NULL)
+ return -EACCES;
+
+ ret = xt_register_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+ if (ret < 0)
+ remove_proc_entry("xt_quota", init_net.proc_net);
+ pr_debug("xt_quota2: init() %d", ret);
+ return ret;
+}
+
+static void __exit quota_mt2_exit(void)
+{
+ xt_unregister_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+ remove_proc_entry("xt_quota", init_net.proc_net);
+}
+
+module_init(quota_mt2_init);
+module_exit(quota_mt2_exit);
+MODULE_DESCRIPTION("Xtables: countdown quota match; up counter");
+MODULE_AUTHOR("Sam Johnston <samj@samj.net>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_quota2");
+MODULE_ALIAS("ip6t_quota2");
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 7720b03..d46dc9f 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -135,6 +135,7 @@ static struct xt_match xt_rateest_mt_reg __read_mostly = {
.checkentry = xt_rateest_mt_checkentry,
.destroy = xt_rateest_mt_destroy,
.matchsize = sizeof(struct xt_rateest_match_info),
+ .usersize = offsetof(struct xt_rateest_match_info, est1),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index b10ade2..a52fbaf 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -144,13 +144,14 @@ static bool xt_socket_sk_is_transparent(struct sock *sk)
}
}
-static struct sock *xt_socket_lookup_slow_v4(struct net *net,
+struct sock *xt_socket_lookup_slow_v4(struct net *net,
const struct sk_buff *skb,
const struct net_device *indev)
{
const struct iphdr *iph = ip_hdr(skb);
struct sk_buff *data_skb = NULL;
int doff = 0;
+ struct sock *sk = skb->sk;
__be32 uninitialized_var(daddr), uninitialized_var(saddr);
__be16 uninitialized_var(dport), uninitialized_var(sport);
u8 uninitialized_var(protocol);
@@ -205,9 +206,16 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net,
}
#endif
- return xt_socket_get_sock_v4(net, data_skb, doff, protocol, saddr,
- daddr, sport, dport, indev);
+ if (sk)
+ atomic_inc(&sk->sk_refcnt);
+ else
+ sk = xt_socket_get_sock_v4(dev_net(skb->dev), data_skb, doff,
+ protocol, saddr, daddr, sport,
+ dport, indev);
+
+ return sk;
}
+EXPORT_SYMBOL(xt_socket_lookup_slow_v4);
static bool
socket_match(const struct sk_buff *skb, struct xt_action_param *par,
@@ -239,8 +247,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
transparent)
pskb->mark = sk->sk_mark;
- if (sk != skb->sk)
- sock_gen_put(sk);
+ sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
@@ -344,10 +351,11 @@ xt_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
return NULL;
}
-static struct sock *xt_socket_lookup_slow_v6(struct net *net,
+struct sock *xt_socket_lookup_slow_v6(struct net *net,
const struct sk_buff *skb,
const struct net_device *indev)
{
+ struct sock *sk = skb->sk;
__be16 uninitialized_var(dport), uninitialized_var(sport);
const struct in6_addr *daddr = NULL, *saddr = NULL;
struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -387,9 +395,16 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net,
return NULL;
}
- return xt_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
- sport, dport, indev);
+ if (sk)
+ atomic_inc(&sk->sk_refcnt);
+ else
+ sk = xt_socket_get_sock_v6(dev_net(skb->dev), data_skb, doff,
+ tproto, saddr, daddr, sport, dport,
+ indev);
+
+ return sk;
}
+EXPORT_SYMBOL(xt_socket_lookup_slow_v6);
static bool
socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c
index 0bc3460..423293e 100644
--- a/net/netfilter/xt_string.c
+++ b/net/netfilter/xt_string.c
@@ -77,6 +77,7 @@ static struct xt_match xt_string_mt_reg __read_mostly = {
.match = string_mt,
.destroy = string_mt_destroy,
.matchsize = sizeof(struct xt_string_info),
+ .usersize = offsetof(struct xt_string_info, config),
.me = THIS_MODULE,
};
diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig
index 868f1ad..8463a6d 100644
--- a/net/rfkill/Kconfig
+++ b/net/rfkill/Kconfig
@@ -10,6 +10,11 @@
To compile this driver as a module, choose M here: the
module will be called rfkill.
+config RFKILL_PM
+ bool "Power off on suspend"
+ depends on RFKILL && PM
+ default y
+
# LED trigger support
config RFKILL_LEDS
bool
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 87c3584..fd25a94 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -796,8 +796,7 @@ void rfkill_resume_polling(struct rfkill *rfkill)
}
EXPORT_SYMBOL(rfkill_resume_polling);
-#ifdef CONFIG_PM_SLEEP
-static int rfkill_suspend(struct device *dev)
+static __maybe_unused int rfkill_suspend(struct device *dev)
{
struct rfkill *rfkill = to_rfkill(dev);
@@ -807,7 +806,7 @@ static int rfkill_suspend(struct device *dev)
return 0;
}
-static int rfkill_resume(struct device *dev)
+static __maybe_unused int rfkill_resume(struct device *dev)
{
struct rfkill *rfkill = to_rfkill(dev);
bool cur;
@@ -827,17 +826,13 @@ static int rfkill_resume(struct device *dev)
}
static SIMPLE_DEV_PM_OPS(rfkill_pm_ops, rfkill_suspend, rfkill_resume);
-#define RFKILL_PM_OPS (&rfkill_pm_ops)
-#else
-#define RFKILL_PM_OPS NULL
-#endif
static struct class rfkill_class = {
.name = "rfkill",
.dev_release = rfkill_release,
.dev_groups = rfkill_dev_groups,
.dev_uevent = rfkill_dev_uevent,
- .pm = RFKILL_PM_OPS,
+ .pm = IS_ENABLED(CONFIG_RFKILL_PM) ? &rfkill_pm_ops : NULL,
};
bool rfkill_blocked(struct rfkill *rfkill)
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index a309a07..909848f 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -63,6 +63,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/random.h>
diff --git a/net/socket.c b/net/socket.c
index ab64ae8..5362e4e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -534,8 +534,25 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
return used;
}
+static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+ int err = simple_setattr(dentry, iattr);
+
+ if (!err && (iattr->ia_valid & ATTR_UID)) {
+ struct socket *sock = SOCKET_I(d_inode(dentry));
+
+ if (sock->sk)
+ sock->sk->sk_uid = iattr->ia_uid;
+ else
+ err = -ENOENT;
+ }
+
+ return err;
+}
+
static const struct inode_operations sockfs_inode_ops = {
.listxattr = sockfs_listxattr,
+ .setattr = sockfs_setattr,
};
/**
@@ -578,12 +595,17 @@ EXPORT_SYMBOL(sock_alloc);
* an inode not a file.
*/
-void sock_release(struct socket *sock)
+static void __sock_release(struct socket *sock, struct inode *inode)
{
if (sock->ops) {
struct module *owner = sock->ops->owner;
+ if (inode)
+ inode_lock(inode);
sock->ops->release(sock);
+ sock->sk = NULL;
+ if (inode)
+ inode_unlock(inode);
sock->ops = NULL;
module_put(owner);
}
@@ -598,6 +620,11 @@ void sock_release(struct socket *sock)
}
sock->file = NULL;
}
+
+void sock_release(struct socket *sock)
+{
+ __sock_release(sock, NULL);
+}
EXPORT_SYMBOL(sock_release);
void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
@@ -1030,7 +1057,7 @@ static int sock_mmap(struct file *file, struct vm_area_struct *vma)
static int sock_close(struct inode *inode, struct file *filp)
{
- sock_release(SOCKET_I(inode));
+ __sock_release(SOCKET_I(inode), inode);
return 0;
}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index eea18a1..f984ff2 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -50,7 +50,7 @@ EXPORT_SYMBOL_GPL(svc_pool_map);
static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
static int
-param_set_pool_mode(const char *val, struct kernel_param *kp)
+param_set_pool_mode(const char *val, const struct kernel_param *kp)
{
int *ip = (int *)kp->arg;
struct svc_pool_map *m = &svc_pool_map;
@@ -80,7 +80,7 @@ param_set_pool_mode(const char *val, struct kernel_param *kp)
}
static int
-param_get_pool_mode(char *buf, struct kernel_param *kp)
+param_get_pool_mode(char *buf, const struct kernel_param *kp)
{
int *ip = (int *)kp->arg;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index c60be11b..46eff10 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -70,7 +70,7 @@ module_param(bss_entries_limit, int, 0644);
MODULE_PARM_DESC(bss_entries_limit,
"limit to number of scan BSS entries (per wiphy, default 1000)");
-#define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ)
+#define IEEE80211_SCAN_RESULT_EXPIRE (7 * HZ)
static void bss_free(struct cfg80211_internal_bss *bss)
{
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index c09336b..668fdfa 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -22,6 +22,25 @@
If unsure, say Y.
+config XFRM_USER_COMPAT
+ tristate "Compatible ABI support"
+ depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \
+ HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select WANT_COMPAT_NETLINK_MESSAGES
+ help
+ Transformation(XFRM) user configuration interface like IPsec
+ used by compatible Linux applications.
+
+ If unsure, say N.
+
+config XFRM_INTERFACE
+ tristate "Transformation virtual interface"
+ depends on XFRM && IPV6
+ ---help---
+ This provides a virtual interface to route IPsec traffic.
+
+ If unsure, say N.
+
config XFRM_SUB_POLICY
bool "Transformation sub policy support"
depends on XFRM
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index c0e9619..cd4393c7 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -8,4 +8,6 @@
obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
+obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 44ac85f..d0ca0db 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -241,7 +241,7 @@ static struct xfrm_algo_desc aalg_list[] = {
.uinfo = {
.auth = {
- .icv_truncbits = 96,
+ .icv_truncbits = 128,
.icv_fullbits = 256,
}
},
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
new file mode 100644
index 0000000..27e1551
--- /dev/null
+++ b/net/xfrm/xfrm_compat.c
@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM compat layer
+ * Author: Dmitry Safonov <dima@arista.com>
+ * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
+ */
+#include <linux/compat.h>
+#include <linux/vmalloc.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+
+struct compat_xfrm_lifetime_cfg {
+ compat_u64 soft_byte_limit, hard_byte_limit;
+ compat_u64 soft_packet_limit, hard_packet_limit;
+ compat_u64 soft_add_expires_seconds, hard_add_expires_seconds;
+ compat_u64 soft_use_expires_seconds, hard_use_expires_seconds;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_lifetime_cur {
+ compat_u64 bytes, packets, add_time, use_time;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_userpolicy_info {
+ struct xfrm_selector sel;
+ struct compat_xfrm_lifetime_cfg lft;
+ struct compat_xfrm_lifetime_cur curlft;
+ __u32 priority, index;
+ u8 dir, action, flags, share;
+ /* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_usersa_info {
+ struct xfrm_selector sel;
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct compat_xfrm_lifetime_cfg lft;
+ struct compat_xfrm_lifetime_cur curlft;
+ struct xfrm_stats stats;
+ __u32 seq, reqid;
+ u16 family;
+ u8 mode, replay_window, flags;
+ /* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_user_acquire {
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct xfrm_selector sel;
+ struct compat_xfrm_userpolicy_info policy;
+ /* 4 bytes additional padding on 64bit */
+ __u32 aalgos, ealgos, calgos, seq;
+};
+
+struct compat_xfrm_userspi_info {
+ struct compat_xfrm_usersa_info info;
+ /* 4 bytes additional padding on 64bit */
+ __u32 min, max;
+};
+
+struct compat_xfrm_user_expire {
+ struct compat_xfrm_usersa_info state;
+ /* 8 bytes additional padding on 64bit */
+ u8 hard;
+};
+
+struct compat_xfrm_user_polexpire {
+ struct compat_xfrm_userpolicy_info pol;
+ /* 8 bytes additional padding on 64bit */
+ u8 hard;
+};
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
+ [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+ [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+ [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+ [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+ [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+ [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+ [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info),
+ [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire),
+ [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire),
+ [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+ [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+ [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire),
+ [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+ [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+ [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+ [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+ [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+ [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+ [XFRM_MSG_NEWSADINFO - XFRM_MSG_BASE] = sizeof(u32),
+ [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32),
+ [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
+ [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
+ [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
+};
+
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+ [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)},
+ [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)},
+ [XFRMA_LASTUSED] = { .type = NLA_U64},
+ [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)},
+ [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) },
+ [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) },
+ [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) },
+ [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) },
+ [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) },
+ [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) },
+ [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) },
+ [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) },
+ [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) },
+ [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 },
+ [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 },
+ [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) },
+ [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) },
+ [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)},
+ [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) },
+ [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) },
+ [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) },
+ [XFRMA_TFCPAD] = { .type = NLA_U32 },
+ [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) },
+ [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 },
+ [XFRMA_PROTO] = { .type = NLA_U8 },
+ [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) },
+ [XFRMA_SET_MARK] = { .type = NLA_U32 },
+ [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 },
+ [XFRMA_IF_ID] = { .type = NLA_U32 },
+};
+
+static inline void *kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
+ const struct nlmsghdr *nlh_src, u16 type)
+{
+ int payload = compat_msg_min[type];
+ int src_len = xfrm_msg_min[type];
+ struct nlmsghdr *nlh_dst;
+
+ /* Compat messages are shorter or equal to native (+padding) */
+ if (WARN_ON_ONCE(src_len < payload))
+ return ERR_PTR(-EMSGSIZE);
+
+ nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq,
+ nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags);
+ if (!nlh_dst)
+ return ERR_PTR(-EMSGSIZE);
+
+ memset(nlmsg_data(nlh_dst), 0, payload);
+
+ switch (nlh_src->nlmsg_type) {
+ /* Compat message has the same layout as native */
+ case XFRM_MSG_DELSA:
+ case XFRM_MSG_DELPOLICY:
+ case XFRM_MSG_FLUSHSA:
+ case XFRM_MSG_FLUSHPOLICY:
+ case XFRM_MSG_NEWAE:
+ case XFRM_MSG_REPORT:
+ case XFRM_MSG_MIGRATE:
+ case XFRM_MSG_NEWSADINFO:
+ case XFRM_MSG_NEWSPDINFO:
+ case XFRM_MSG_MAPPING:
+ WARN_ON_ONCE(src_len != payload);
+ memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len);
+ break;
+ /* 4 byte alignment for trailing u64 on native, but not on compat */
+ case XFRM_MSG_NEWSA:
+ case XFRM_MSG_NEWPOLICY:
+ case XFRM_MSG_UPDSA:
+ case XFRM_MSG_UPDPOLICY:
+ WARN_ON_ONCE(src_len != payload + 4);
+ memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload);
+ break;
+ case XFRM_MSG_EXPIRE: {
+ const struct xfrm_user_expire *src_ue = nlmsg_data(nlh_src);
+ struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst);
+
+ /* compat_xfrm_user_expire has 4-byte smaller state */
+ memcpy(dst_ue, src_ue, sizeof(dst_ue->state));
+ dst_ue->hard = src_ue->hard;
+ break;
+ }
+ case XFRM_MSG_ACQUIRE: {
+ const struct xfrm_user_acquire *src_ua = nlmsg_data(nlh_src);
+ struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst);
+
+ memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+ dst_ua->aalgos = src_ua->aalgos;
+ dst_ua->ealgos = src_ua->ealgos;
+ dst_ua->calgos = src_ua->calgos;
+ dst_ua->seq = src_ua->seq;
+ break;
+ }
+ case XFRM_MSG_POLEXPIRE: {
+ const struct xfrm_user_polexpire *src_upe = nlmsg_data(nlh_src);
+ struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst);
+
+ /* compat_xfrm_user_polexpire has 4-byte smaller state */
+ memcpy(dst_upe, src_upe, sizeof(dst_upe->pol));
+ dst_upe->hard = src_upe->hard;
+ break;
+ }
+ case XFRM_MSG_ALLOCSPI: {
+ const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src);
+ struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst);
+
+ /* compat_xfrm_user_polexpire has 4-byte smaller state */
+ memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+ dst_usi->min = src_usi->min;
+ dst_usi->max = src_usi->max;
+ break;
+ }
+ /* Not being sent by kernel */
+ case XFRM_MSG_GETSA:
+ case XFRM_MSG_GETPOLICY:
+ case XFRM_MSG_GETAE:
+ case XFRM_MSG_GETSADINFO:
+ case XFRM_MSG_GETSPDINFO:
+ default:
+ WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
+ return nlh_dst;
+}
+
+static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len)
+{
+ return nla_put(dst, src->nla_type, len, nla_data(src));
+}
+
+static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
+{
+ switch (src->nla_type) {
+ case XFRMA_PAD:
+ case XFRMA_OFFLOAD_DEV:
+ /* Ignore */
+ return 0;
+ case XFRMA_ALG_AUTH:
+ case XFRMA_ALG_CRYPT:
+ case XFRMA_ALG_COMP:
+ case XFRMA_ENCAP:
+ case XFRMA_TMPL:
+ return xfrm_nla_cpy(dst, src, nla_len(src));
+ case XFRMA_SA:
+ return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info));
+ case XFRMA_POLICY:
+ return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info));
+ case XFRMA_SEC_CTX:
+ return xfrm_nla_cpy(dst, src, nla_len(src));
+ case XFRMA_LTIME_VAL:
+ return nla_put_64bit(dst, src->nla_type, nla_len(src),
+ nla_data(src), XFRMA_PAD);
+ case XFRMA_REPLAY_VAL:
+ case XFRMA_REPLAY_THRESH:
+ case XFRMA_ETIMER_THRESH:
+ case XFRMA_SRCADDR:
+ case XFRMA_COADDR:
+ return xfrm_nla_cpy(dst, src, nla_len(src));
+ case XFRMA_LASTUSED:
+ return nla_put_64bit(dst, src->nla_type, nla_len(src),
+ nla_data(src), XFRMA_PAD);
+ case XFRMA_POLICY_TYPE:
+ case XFRMA_MIGRATE:
+ case XFRMA_ALG_AEAD:
+ case XFRMA_KMADDRESS:
+ case XFRMA_ALG_AUTH_TRUNC:
+ case XFRMA_MARK:
+ case XFRMA_TFCPAD:
+ case XFRMA_REPLAY_ESN_VAL:
+ case XFRMA_SA_EXTRA_FLAGS:
+ case XFRMA_PROTO:
+ case XFRMA_ADDRESS_FILTER:
+ case XFRMA_SET_MARK:
+ case XFRMA_SET_MARK_MASK:
+ case XFRMA_IF_ID:
+ return xfrm_nla_cpy(dst, src, nla_len(src));
+ default:
+ BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+ WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+ return -EOPNOTSUPP;
+ }
+}
+
+/* Take kernel-built (64bit layout) and create 32bit layout for userspace */
+static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
+{
+ u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+ const struct nlattr *nla, *attrs;
+ struct nlmsghdr *nlh_dst;
+ int len, remaining;
+
+ nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type);
+ if (IS_ERR(nlh_dst))
+ return PTR_ERR(nlh_dst);
+
+ attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]);
+ len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
+
+ nla_for_each_attr(nla, attrs, len, remaining) {
+ int err = xfrm_xlate64_attr(dst, nla);
+
+ if (err)
+ return err;
+ }
+
+ nlmsg_end(dst, nlh_dst);
+
+ return 0;
+}
+
+static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src)
+{
+ u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+ struct sk_buff *new = NULL;
+ int err;
+
+ if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+ return -EOPNOTSUPP;
+
+ if (skb_shinfo(skb)->frag_list == NULL) {
+ new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
+ if (!new)
+ return -ENOMEM;
+ skb_shinfo(skb)->frag_list = new;
+ }
+
+ err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src);
+ if (err) {
+ if (new) {
+ kfree_skb(new);
+ skb_shinfo(skb)->frag_list = NULL;
+ }
+ return err;
+ }
+
+ return 0;
+}
+
+/* Calculates len of translated 64-bit message. */
+static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
+ struct nlattr *attrs[XFRMA_MAX+1])
+{
+ size_t len = nlmsg_len(src);
+
+ switch (src->nlmsg_type) {
+ case XFRM_MSG_NEWSA:
+ case XFRM_MSG_NEWPOLICY:
+ case XFRM_MSG_ALLOCSPI:
+ case XFRM_MSG_ACQUIRE:
+ case XFRM_MSG_UPDPOLICY:
+ case XFRM_MSG_UPDSA:
+ len += 4;
+ break;
+ case XFRM_MSG_EXPIRE:
+ case XFRM_MSG_POLEXPIRE:
+ len += 8;
+ break;
+ default:
+ break;
+ }
+
+ if (attrs[XFRMA_SA])
+ len += 4;
+ if (attrs[XFRMA_POLICY])
+ len += 4;
+
+ /* XXX: some attrs may need to be realigned
+ * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ */
+
+ return len;
+}
+
+static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
+ size_t size, int copy_len, int payload)
+{
+ struct nlmsghdr *nlmsg = dst;
+ struct nlattr *nla;
+
+ if (WARN_ON_ONCE(copy_len > payload))
+ copy_len = payload;
+
+ if (size - *pos < nla_attr_size(payload))
+ return -ENOBUFS;
+
+ nla = dst + *pos;
+
+ memcpy(nla, src, nla_attr_size(copy_len));
+ nla->nla_len = nla_attr_size(payload);
+ *pos += nla_attr_size(payload);
+ nlmsg->nlmsg_len += nla->nla_len;
+
+ memset(dst + *pos, 0, payload - copy_len);
+ *pos += payload - copy_len;
+
+ return 0;
+}
+
+static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
+ size_t *pos, size_t size)
+{
+ int type = nla_type(nla);
+ u16 pol_len32, pol_len64;
+ int err;
+
+ if (type > XFRMA_MAX) {
+ BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+ return -EOPNOTSUPP;
+ }
+ if (nla_len(nla) < compat_policy[type].len) {
+ return -EOPNOTSUPP;
+ }
+
+ pol_len32 = compat_policy[type].len;
+ pol_len64 = xfrma_policy[type].len;
+
+ /* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */
+ if (pol_len32 != pol_len64) {
+ if (nla_len(nla) != compat_policy[type].len) {
+ return -EOPNOTSUPP;
+ }
+ err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64);
+ if (err)
+ return err;
+ }
+
+ return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla));
+}
+
+static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
+ struct nlattr *attrs[XFRMA_MAX+1],
+ size_t size, u8 type)
+{
+ size_t pos;
+ int i;
+
+ memcpy(dst, src, NLMSG_HDRLEN);
+ dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type];
+ memset(nlmsg_data(dst), 0, xfrm_msg_min[type]);
+
+ switch (src->nlmsg_type) {
+ /* Compat message has the same layout as native */
+ case XFRM_MSG_DELSA:
+ case XFRM_MSG_GETSA:
+ case XFRM_MSG_DELPOLICY:
+ case XFRM_MSG_GETPOLICY:
+ case XFRM_MSG_FLUSHSA:
+ case XFRM_MSG_FLUSHPOLICY:
+ case XFRM_MSG_NEWAE:
+ case XFRM_MSG_GETAE:
+ case XFRM_MSG_REPORT:
+ case XFRM_MSG_MIGRATE:
+ case XFRM_MSG_NEWSADINFO:
+ case XFRM_MSG_GETSADINFO:
+ case XFRM_MSG_NEWSPDINFO:
+ case XFRM_MSG_GETSPDINFO:
+ case XFRM_MSG_MAPPING:
+ memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+ break;
+ /* 4 byte alignment for trailing u64 on native, but not on compat */
+ case XFRM_MSG_NEWSA:
+ case XFRM_MSG_NEWPOLICY:
+ case XFRM_MSG_UPDSA:
+ case XFRM_MSG_UPDPOLICY:
+ memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+ break;
+ case XFRM_MSG_EXPIRE: {
+ const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src);
+ struct xfrm_user_expire *dst_ue = nlmsg_data(dst);
+
+ /* compat_xfrm_user_expire has 4-byte smaller state */
+ memcpy(dst_ue, src_ue, sizeof(src_ue->state));
+ dst_ue->hard = src_ue->hard;
+ break;
+ }
+ case XFRM_MSG_ACQUIRE: {
+ const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src);
+ struct xfrm_user_acquire *dst_ua = nlmsg_data(dst);
+
+ memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+ dst_ua->aalgos = src_ua->aalgos;
+ dst_ua->ealgos = src_ua->ealgos;
+ dst_ua->calgos = src_ua->calgos;
+ dst_ua->seq = src_ua->seq;
+ break;
+ }
+ case XFRM_MSG_POLEXPIRE: {
+ const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src);
+ struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst);
+
+ /* compat_xfrm_user_polexpire has 4-byte smaller state */
+ memcpy(dst_upe, src_upe, sizeof(src_upe->pol));
+ dst_upe->hard = src_upe->hard;
+ break;
+ }
+ case XFRM_MSG_ALLOCSPI: {
+ const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src);
+ struct xfrm_userspi_info *dst_usi = nlmsg_data(dst);
+
+ /* compat_xfrm_user_polexpire has 4-byte smaller state */
+ memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+ dst_usi->min = src_usi->min;
+ dst_usi->max = src_usi->max;
+ break;
+ }
+ default:
+ return -EOPNOTSUPP;
+ }
+ pos = dst->nlmsg_len;
+
+ for (i = 1; i < XFRMA_MAX + 1; i++) {
+ int err;
+
+ if (i == XFRMA_PAD || i == XFRMA_OFFLOAD_DEV)
+ continue;
+
+ if (!attrs[i])
+ continue;
+
+ err = xfrm_xlate32_attr(dst, attrs[i], &pos, size);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
+ int maxtype, const struct nla_policy *policy)
+{
+ /* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */
+ u16 type = h32->nlmsg_type - XFRM_MSG_BASE;
+ struct nlattr *attrs[XFRMA_MAX+1];
+ struct nlmsghdr *h64;
+ size_t len;
+ int err;
+
+ BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min));
+
+ if (type >= ARRAY_SIZE(xfrm_msg_min))
+ return ERR_PTR(-EINVAL);
+
+ /* Don't call parse: the message might have only nlmsg header */
+ if ((h32->nlmsg_type == XFRM_MSG_GETSA ||
+ h32->nlmsg_type == XFRM_MSG_GETPOLICY) &&
+ (h32->nlmsg_flags & NLM_F_DUMP))
+ return NULL;
+
+ err = nlmsg_parse(h32, compat_msg_min[type], attrs,
+ maxtype ? : XFRMA_MAX, policy ? : compat_policy);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ len = xfrm_user_rcv_calculate_len64(h32, attrs);
+ /* The message doesn't need translation */
+ if (len == nlmsg_len(h32))
+ return NULL;
+
+ len += NLMSG_HDRLEN;
+ h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO);
+ if (!h64)
+ return ERR_PTR(-ENOMEM);
+
+ err = xfrm_xlate32(h64, h32, attrs, len, type);
+ if (err < 0) {
+ kvfree(h64);
+ return ERR_PTR(err);
+ }
+
+ return h64;
+}
+
+static int xfrm_user_policy_compat(u8 **pdata32, int optlen)
+{
+ struct compat_xfrm_userpolicy_info *p = (void *)*pdata32;
+ u8 *src_templates, *dst_templates;
+ u8 *data64;
+
+ if (optlen < sizeof(*p))
+ return -EINVAL;
+
+ data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN);
+ if (!data64)
+ return -ENOMEM;
+
+ memcpy(data64, *pdata32, sizeof(*p));
+ memset(data64 + sizeof(*p), 0, 4);
+
+ src_templates = *pdata32 + sizeof(*p);
+ dst_templates = data64 + sizeof(*p) + 4;
+ memcpy(dst_templates, src_templates, optlen - sizeof(*p));
+
+ kfree(*pdata32);
+ *pdata32 = data64;
+ return 0;
+}
+
+static struct xfrm_translator xfrm_translator = {
+ .owner = THIS_MODULE,
+ .alloc_compat = xfrm_alloc_compat,
+ .rcv_msg_compat = xfrm_user_rcv_msg_compat,
+ .xlate_user_policy_sockptr = xfrm_user_policy_compat,
+};
+
+static int __init xfrm_compat_init(void)
+{
+ return xfrm_register_translator(&xfrm_translator);
+}
+
+static void __exit xfrm_compat_exit(void)
+{
+ xfrm_unregister_translator(&xfrm_translator);
+}
+
+module_init(xfrm_compat_init);
+module_exit(xfrm_compat_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Safonov");
+MODULE_DESCRIPTION("XFRM 32-bit compatibility layer");
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index d613bf7..3264a7c 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -234,23 +234,28 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
seq = 0;
if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
+ secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
do {
if (skb->sp->len == XFRM_MAX_DEPTH) {
+ secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
goto drop;
}
x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
if (x == NULL) {
+ secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
goto drop;
}
+ skb->mark = xfrm_smark_get(skb->mark, x);
+
skb->sp->xvec[skb->sp->len++] = x;
spin_lock(&x->lock);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
new file mode 100644
index 0000000..0b6818d
--- /dev/null
+++ b/net/xfrm/xfrm_interface.c
@@ -0,0 +1,974 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM virtual interface
+ *
+ * Copyright (C) 2018 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ */
+
+#include <linux/module.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/sockios.h>
+#include <linux/icmp.h>
+#include <linux/if.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_link.h>
+#include <linux/if_arp.h>
+#include <linux/icmpv6.h>
+#include <linux/init.h>
+#include <linux/route.h>
+#include <linux/rtnetlink.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/slab.h>
+#include <linux/hash.h>
+
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/etherdevice.h>
+
+static int xfrmi_dev_init(struct net_device *dev);
+static void xfrmi_dev_setup(struct net_device *dev);
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly;
+static unsigned int xfrmi_net_id __read_mostly;
+
+struct xfrmi_net {
+ /* lists for storing interfaces in use */
+ struct xfrm_if __rcu *xfrmi[1];
+};
+
+#define for_each_xfrmi_rcu(start, xi) \
+ for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next))
+
+static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
+{
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+ struct xfrm_if *xi;
+
+ for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
+ if (x->if_id == xi->p.if_id &&
+ (xi->dev->flags & IFF_UP))
+ return xi;
+ }
+
+ return NULL;
+}
+
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+{
+ struct xfrmi_net *xfrmn;
+ int ifindex;
+ struct xfrm_if *xi;
+
+ if (!skb->dev)
+ return NULL;
+
+ xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id);
+ ifindex = skb->dev->ifindex;
+
+ for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
+ if (ifindex == xi->dev->ifindex &&
+ (xi->dev->flags & IFF_UP))
+ return xi;
+ }
+
+ return NULL;
+}
+
+static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+ struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0];
+
+ rcu_assign_pointer(xi->next , rtnl_dereference(*xip));
+ rcu_assign_pointer(*xip, xi);
+}
+
+static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+ struct xfrm_if __rcu **xip;
+ struct xfrm_if *iter;
+
+ for (xip = &xfrmn->xfrmi[0];
+ (iter = rtnl_dereference(*xip)) != NULL;
+ xip = &iter->next) {
+ if (xi == iter) {
+ rcu_assign_pointer(*xip, xi->next);
+ break;
+ }
+ }
+}
+
+static void xfrmi_dev_free(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+}
+
+static int xfrmi_create2(struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+ int err;
+
+ dev->rtnl_link_ops = &xfrmi_link_ops;
+ err = register_netdevice(dev);
+ if (err < 0)
+ goto out;
+
+ strcpy(xi->p.name, dev->name);
+
+ dev_hold(dev);
+ xfrmi_link(xfrmn, xi);
+
+ return 0;
+
+out:
+ return err;
+}
+
+static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p)
+{
+ struct net_device *dev;
+ struct xfrm_if *xi;
+ char name[IFNAMSIZ];
+ int err;
+
+ if (p->name[0]) {
+ strlcpy(name, p->name, IFNAMSIZ);
+ } else {
+ err = -EINVAL;
+ goto failed;
+ }
+
+ dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup);
+ if (!dev) {
+ err = -EAGAIN;
+ goto failed;
+ }
+
+ dev_net_set(dev, net);
+
+ xi = netdev_priv(dev);
+ xi->p = *p;
+ xi->net = net;
+ xi->dev = dev;
+ xi->phydev = dev_get_by_index(net, p->link);
+ if (!xi->phydev) {
+ err = -ENODEV;
+ goto failed_free;
+ }
+
+ err = xfrmi_create2(dev);
+ if (err < 0)
+ goto failed_dev_put;
+
+ return xi;
+
+failed_dev_put:
+ dev_put(xi->phydev);
+failed_free:
+ free_netdev(dev);
+failed:
+ return ERR_PTR(err);
+}
+
+static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
+ int create)
+{
+ struct xfrm_if __rcu **xip;
+ struct xfrm_if *xi;
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+ for (xip = &xfrmn->xfrmi[0];
+ (xi = rtnl_dereference(*xip)) != NULL;
+ xip = &xi->next) {
+ if (xi->p.if_id == p->if_id) {
+ if (create)
+ return ERR_PTR(-EEXIST);
+
+ return xi;
+ }
+ }
+ if (!create)
+ return ERR_PTR(-ENODEV);
+ return xfrmi_create(net, p);
+}
+
+static void xfrmi_dev_uninit(struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id);
+
+ xfrmi_unlink(xfrmn, xi);
+ dev_put(xi->phydev);
+ dev_put(dev);
+}
+
+static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
+{
+ skb->tstamp.tv64 = 0;
+ skb->pkt_type = PACKET_HOST;
+ skb->skb_iif = 0;
+ skb->ignore_df = 0;
+ skb_dst_drop(skb);
+ nf_reset(skb);
+ nf_reset_trace(skb);
+
+ if (!xnet)
+ return;
+
+ ipvs_reset(skb);
+ secpath_reset(skb);
+ skb_orphan(skb);
+ skb->mark = 0;
+}
+
+static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
+{
+ struct pcpu_sw_netstats *tstats;
+ struct xfrm_mode *inner_mode;
+ struct net_device *dev;
+ struct xfrm_state *x;
+ struct xfrm_if *xi;
+ bool xnet;
+
+ if (err && !skb->sp)
+ return 0;
+
+ x = xfrm_input_state(skb);
+
+ xi = xfrmi_lookup(xs_net(x), x);
+ if (!xi)
+ return 1;
+
+ dev = xi->dev;
+ skb->dev = dev;
+
+ if (err) {
+ dev->stats.rx_errors++;
+ dev->stats.rx_dropped++;
+
+ return 0;
+ }
+
+ xnet = !net_eq(xi->net, dev_net(skb->dev));
+
+ if (xnet) {
+ inner_mode = x->inner_mode;
+
+ if (x->sel.family == AF_UNSPEC) {
+ inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+ if (inner_mode == NULL) {
+ XFRM_INC_STATS(dev_net(skb->dev),
+ LINUX_MIB_XFRMINSTATEMODEERROR);
+ return -EINVAL;
+ }
+ }
+
+ if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb,
+ inner_mode->afinfo->family))
+ return -EPERM;
+ }
+
+ xfrmi_scrub_packet(skb, xnet);
+
+ tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
+
+ return 0;
+}
+
+static int
+xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct net_device_stats *stats = &xi->dev->stats;
+ struct dst_entry *dst = skb_dst(skb);
+ unsigned int length = skb->len;
+ struct net_device *tdev;
+ struct xfrm_state *x;
+ int err = -1;
+ int mtu;
+
+ if (!dst)
+ goto tx_err_link_failure;
+
+ fl->flowi_xfrm.if_id = xi->p.if_id;
+
+ dst_hold(dst);
+ dst = xfrm_lookup(xi->net, dst, fl, NULL, 0);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
+ dst = NULL;
+ goto tx_err_link_failure;
+ }
+
+ x = dst->xfrm;
+ if (!x)
+ goto tx_err_link_failure;
+
+ if (x->if_id != xi->p.if_id)
+ goto tx_err_link_failure;
+
+ tdev = dst->dev;
+
+ if (tdev == dev) {
+ stats->collisions++;
+ net_warn_ratelimited("%s: Local routing loop detected!\n",
+ xi->p.name);
+ goto tx_err_dst_release;
+ }
+
+ mtu = dst_mtu(dst);
+ if (!skb->ignore_df && skb->len > mtu) {
+ if (dst && dst->ops->update_pmtu)
+ dst->ops->update_pmtu(dst, NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ } else {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+ }
+
+ dst_release(dst);
+ return -EMSGSIZE;
+ }
+
+ xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev)));
+ skb_dst_set(skb, dst);
+ skb->dev = tdev;
+
+ err = dst_output(xi->net, skb->sk, skb);
+ if (net_xmit_eval(err) == 0) {
+ struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += length;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ stats->tx_errors++;
+ stats->tx_aborted_errors++;
+ }
+
+ return 0;
+tx_err_link_failure:
+ stats->tx_carrier_errors++;
+ dst_link_failure(skb);
+tx_err_dst_release:
+ dst_release(dst);
+ return err;
+}
+
+static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct net_device_stats *stats = &xi->dev->stats;
+ struct flowi fl;
+ int ret;
+
+ memset(&fl, 0, sizeof(fl));
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IPV6):
+ xfrm_decode_session(skb, &fl, AF_INET6);
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ break;
+ case htons(ETH_P_IP):
+ xfrm_decode_session(skb, &fl, AF_INET);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ break;
+ default:
+ goto tx_err;
+ }
+
+ fl.flowi_oif = xi->phydev->ifindex;
+
+ ret = xfrmi_xmit2(skb, dev, &fl);
+ if (ret < 0)
+ goto tx_err;
+
+ return NETDEV_TX_OK;
+
+tx_err:
+ stats->tx_errors++;
+ stats->tx_dropped++;
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static int xfrmi4_err(struct sk_buff *skb, u32 info)
+{
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ struct net *net = dev_net(skb->dev);
+ int protocol = iph->protocol;
+ struct ip_comp_hdr *ipch;
+ struct ip_esp_hdr *esph;
+ struct ip_auth_hdr *ah ;
+ struct xfrm_state *x;
+ struct xfrm_if *xi;
+ __be32 spi;
+
+ switch (protocol) {
+ case IPPROTO_ESP:
+ esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
+ spi = esph->spi;
+ break;
+ case IPPROTO_AH:
+ ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+ spi = ah->spi;
+ break;
+ case IPPROTO_COMP:
+ ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+ spi = htonl(ntohs(ipch->cpi));
+ break;
+ default:
+ return 0;
+ }
+
+ switch (icmp_hdr(skb)->type) {
+ case ICMP_DEST_UNREACH:
+ if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+ return 0;
+ case ICMP_REDIRECT:
+ break;
+ default:
+ return 0;
+ }
+
+ x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ spi, protocol, AF_INET);
+ if (!x)
+ return 0;
+
+ xi = xfrmi_lookup(net, x);
+ if (!xi) {
+ xfrm_state_put(x);
+ return -1;
+ }
+
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+ ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ else
+ ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ xfrm_state_put(x);
+
+ return 0;
+}
+
+static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
+ struct net *net = dev_net(skb->dev);
+ int protocol = iph->nexthdr;
+ struct ip_comp_hdr *ipch;
+ struct ip_esp_hdr *esph;
+ struct ip_auth_hdr *ah;
+ struct xfrm_state *x;
+ struct xfrm_if *xi;
+ __be32 spi;
+
+ switch (protocol) {
+ case IPPROTO_ESP:
+ esph = (struct ip_esp_hdr *)(skb->data + offset);
+ spi = esph->spi;
+ break;
+ case IPPROTO_AH:
+ ah = (struct ip_auth_hdr *)(skb->data + offset);
+ spi = ah->spi;
+ break;
+ case IPPROTO_COMP:
+ ipch = (struct ip_comp_hdr *)(skb->data + offset);
+ spi = htonl(ntohs(ipch->cpi));
+ break;
+ default:
+ return 0;
+ }
+
+ if (type != ICMPV6_PKT_TOOBIG &&
+ type != NDISC_REDIRECT)
+ return 0;
+
+ x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ spi, protocol, AF_INET6);
+ if (!x)
+ return 0;
+
+ xi = xfrmi_lookup(net, x);
+ if (!xi) {
+ xfrm_state_put(x);
+ return -1;
+ }
+
+ if (type == NDISC_REDIRECT)
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
+ else
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
+ xfrm_state_put(x);
+
+ return 0;
+}
+
+static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p)
+{
+ if (xi->p.link != p->link)
+ return -EINVAL;
+
+ xi->p.if_id = p->if_id;
+
+ return 0;
+}
+
+static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p)
+{
+ struct net *net = dev_net(xi->dev);
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+ int err;
+
+ xfrmi_unlink(xfrmn, xi);
+ synchronize_net();
+ err = xfrmi_change(xi, p);
+ xfrmi_link(xfrmn, xi);
+ netdev_state_change(xi->dev);
+ return err;
+}
+
+static struct rtnl_link_stats64 *xfrmi_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *s)
+{
+ int cpu;
+
+ if (!dev->tstats)
+ return s;
+
+ for_each_possible_cpu(cpu) {
+ struct pcpu_sw_netstats *stats;
+ struct pcpu_sw_netstats tmp;
+ int start;
+
+ stats = per_cpu_ptr(dev->tstats, cpu);
+ do {
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
+ tmp.rx_packets = stats->rx_packets;
+ tmp.rx_bytes = stats->rx_bytes;
+ tmp.tx_packets = stats->tx_packets;
+ tmp.tx_bytes = stats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+ s->rx_packets += tmp.rx_packets;
+ s->rx_bytes += tmp.rx_bytes;
+ s->tx_packets += tmp.tx_packets;
+ s->tx_bytes += tmp.tx_bytes;
+ }
+
+ s->rx_dropped = dev->stats.rx_dropped;
+ s->tx_dropped = dev->stats.tx_dropped;
+
+ return s;
+}
+
+static int xfrmi_get_iflink(const struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+
+ return xi->phydev->ifindex;
+}
+
+
+static const struct net_device_ops xfrmi_netdev_ops = {
+ .ndo_init = xfrmi_dev_init,
+ .ndo_uninit = xfrmi_dev_uninit,
+ .ndo_start_xmit = xfrmi_xmit,
+ .ndo_get_stats64 = xfrmi_get_stats64,
+ .ndo_get_iflink = xfrmi_get_iflink,
+};
+
+static void xfrmi_dev_setup(struct net_device *dev)
+{
+ dev->netdev_ops = &xfrmi_netdev_ops;
+ dev->type = ARPHRD_NONE;
+ dev->hard_header_len = ETH_HLEN;
+ dev->min_header_len = ETH_HLEN;
+ dev->mtu = ETH_DATA_LEN;
+ dev->addr_len = ETH_ALEN;
+ dev->flags = IFF_NOARP;
+ dev->destructor = xfrmi_dev_free;
+ netif_keep_dst(dev);
+}
+
+static int xfrmi_dev_init(struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct net_device *phydev = xi->phydev;
+ int err;
+
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ err = gro_cells_init(&xi->gro_cells, dev);
+ if (err) {
+ free_percpu(dev->tstats);
+ return err;
+ }
+
+ dev->features |= NETIF_F_LLTX;
+
+ dev->needed_headroom = phydev->needed_headroom;
+ dev->needed_tailroom = phydev->needed_tailroom;
+
+ if (is_zero_ether_addr(dev->dev_addr))
+ eth_hw_addr_inherit(dev, phydev);
+ if (is_zero_ether_addr(dev->broadcast))
+ memcpy(dev->broadcast, phydev->broadcast, dev->addr_len);
+
+ return 0;
+}
+
+static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ return 0;
+}
+
+static void xfrmi_netlink_parms(struct nlattr *data[],
+ struct xfrm_if_parms *parms)
+{
+ memset(parms, 0, sizeof(*parms));
+
+ if (!data)
+ return;
+
+ if (data[IFLA_XFRM_LINK])
+ parms->link = nla_get_u32(data[IFLA_XFRM_LINK]);
+
+ if (data[IFLA_XFRM_IF_ID])
+ parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]);
+}
+
+static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net *net = dev_net(dev);
+ struct xfrm_if_parms *p;
+ struct xfrm_if *xi;
+
+ xi = netdev_priv(dev);
+ p = &xi->p;
+
+ xfrmi_netlink_parms(data, p);
+
+ if (!tb[IFLA_IFNAME])
+ return -EINVAL;
+
+ nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ);
+
+ xi = xfrmi_locate(net, p, 1);
+ return PTR_ERR_OR_ZERO(xi);
+}
+
+static void xfrmi_dellink(struct net_device *dev, struct list_head *head)
+{
+ unregister_netdevice_queue(dev, head);
+}
+
+static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[])
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+
+ xfrmi_netlink_parms(data, &xi->p);
+
+ xi = xfrmi_locate(net, &xi->p, 0);
+
+ if (IS_ERR_OR_NULL(xi)) {
+ xi = netdev_priv(dev);
+ } else {
+ if (xi->dev != dev)
+ return -EEXIST;
+ }
+
+ return xfrmi_update(xi, &xi->p);
+}
+
+static size_t xfrmi_get_size(const struct net_device *dev)
+{
+ return
+ /* IFLA_XFRM_LINK */
+ nla_total_size(4) +
+ /* IFLA_XFRM_IF_ID */
+ nla_total_size(4) +
+ 0;
+}
+
+static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+ struct xfrm_if_parms *parm = &xi->p;
+
+ if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) ||
+ nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+struct net *xfrmi_get_link_net(const struct net_device *dev)
+{
+ struct xfrm_if *xi = netdev_priv(dev);
+
+ return dev_net(xi->phydev);
+}
+
+static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = {
+ [IFLA_XFRM_LINK] = { .type = NLA_U32 },
+ [IFLA_XFRM_IF_ID] = { .type = NLA_U32 },
+};
+
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
+ .kind = "xfrm",
+ .maxtype = IFLA_XFRM_MAX,
+ .policy = xfrmi_policy,
+ .priv_size = sizeof(struct xfrm_if),
+ .setup = xfrmi_dev_setup,
+ .validate = xfrmi_validate,
+ .newlink = xfrmi_newlink,
+ .dellink = xfrmi_dellink,
+ .changelink = xfrmi_changelink,
+ .get_size = xfrmi_get_size,
+ .fill_info = xfrmi_fill_info,
+ .get_link_net = xfrmi_get_link_net,
+};
+
+static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn)
+{
+ struct xfrm_if *xi;
+ LIST_HEAD(list);
+
+ xi = rtnl_dereference(xfrmn->xfrmi[0]);
+ if (!xi)
+ return;
+
+ unregister_netdevice_queue(xi->dev, &list);
+ unregister_netdevice_many(&list);
+}
+
+static int __net_init xfrmi_init_net(struct net *net)
+{
+ return 0;
+}
+
+static void __net_exit xfrmi_exit_net(struct net *net)
+{
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+ rtnl_lock();
+ xfrmi_destroy_interfaces(xfrmn);
+ rtnl_unlock();
+}
+
+static struct pernet_operations xfrmi_net_ops = {
+ .init = xfrmi_init_net,
+ .exit = xfrmi_exit_net,
+ .id = &xfrmi_net_id,
+ .size = sizeof(struct xfrmi_net),
+};
+
+static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
+ .handler = xfrm6_rcv,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi6_err,
+ .priority = 10,
+};
+
+static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = {
+ .handler = xfrm6_rcv,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi6_err,
+ .priority = 10,
+};
+
+static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = {
+ .handler = xfrm6_rcv,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi6_err,
+ .priority = 10,
+};
+
+static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
+ .handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi4_err,
+ .priority = 10,
+};
+
+static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = {
+ .handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi4_err,
+ .priority = 10,
+};
+
+static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = {
+ .handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = xfrmi_rcv_cb,
+ .err_handler = xfrmi4_err,
+ .priority = 10,
+};
+
+static int __init xfrmi4_init(void)
+{
+ int err;
+
+ err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP);
+ if (err < 0)
+ goto xfrm_proto_esp_failed;
+ err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH);
+ if (err < 0)
+ goto xfrm_proto_ah_failed;
+ err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+ if (err < 0)
+ goto xfrm_proto_comp_failed;
+
+ return 0;
+
+xfrm_proto_comp_failed:
+ xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+ xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+ return err;
+}
+
+static void xfrmi4_fini(void)
+{
+ xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+ xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+ xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+}
+
+static int __init xfrmi6_init(void)
+{
+ int err;
+
+ err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP);
+ if (err < 0)
+ goto xfrm_proto_esp_failed;
+ err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH);
+ if (err < 0)
+ goto xfrm_proto_ah_failed;
+ err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+ if (err < 0)
+ goto xfrm_proto_comp_failed;
+
+ return 0;
+
+xfrm_proto_comp_failed:
+ xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+ xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+ return err;
+}
+
+static void xfrmi6_fini(void)
+{
+ xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+ xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+ xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+}
+
+static const struct xfrm_if_cb xfrm_if_cb = {
+ .decode_session = xfrmi_decode_session,
+};
+
+static int __init xfrmi_init(void)
+{
+ const char *msg;
+ int err;
+
+ pr_info("IPsec XFRM device driver\n");
+
+ msg = "tunnel device";
+ err = register_pernet_device(&xfrmi_net_ops);
+ if (err < 0)
+ goto pernet_dev_failed;
+
+ msg = "xfrm4 protocols";
+ err = xfrmi4_init();
+ if (err < 0)
+ goto xfrmi4_failed;
+
+ msg = "xfrm6 protocols";
+ err = xfrmi6_init();
+ if (err < 0)
+ goto xfrmi6_failed;
+
+
+ msg = "netlink interface";
+ err = rtnl_link_register(&xfrmi_link_ops);
+ if (err < 0)
+ goto rtnl_link_failed;
+
+ xfrm_if_register_cb(&xfrm_if_cb);
+
+ return err;
+
+rtnl_link_failed:
+ xfrmi6_fini();
+xfrmi6_failed:
+ xfrmi4_fini();
+xfrmi4_failed:
+ unregister_pernet_device(&xfrmi_net_ops);
+pernet_dev_failed:
+ pr_err("xfrmi init: failed to register %s\n", msg);
+ return err;
+}
+
+static void __exit xfrmi_fini(void)
+{
+ xfrm_if_unregister_cb();
+ rtnl_link_unregister(&xfrmi_link_ops);
+ xfrmi4_fini();
+ xfrmi6_fini();
+ unregister_pernet_device(&xfrmi_net_ops);
+}
+
+module_init(xfrmi_init);
+module_exit(xfrmi_fini);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("xfrm");
+MODULE_ALIAS_NETDEV("xfrm0");
+MODULE_AUTHOR("Steffen Klassert");
+MODULE_DESCRIPTION("XFRM virtual interface");
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 2c4aa7b..26c15f8 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,6 +66,8 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
goto error_nolock;
}
+ skb->mark = xfrm_smark_get(skb->mark, x);
+
err = x->outer_mode->output(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b00ed36..e090ff4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -44,6 +44,9 @@ struct xfrm_flo {
u8 flags;
};
+static DEFINE_SPINLOCK(xfrm_if_cb_lock);
+static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
+
static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
__read_mostly;
@@ -116,7 +119,13 @@ static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family)
return afinfo;
}
-static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo)
+/* Called with rcu_read_lock(). */
+static const struct xfrm_if_cb *xfrm_if_get_cb(void)
+{
+ return rcu_dereference(xfrm_if_cb);
+}
+
+static void xfrm_policy_put_afinfo(const struct xfrm_policy_afinfo *afinfo)
{
rcu_read_unlock();
}
@@ -125,7 +134,7 @@ static inline struct dst_entry *__xfrm_dst_lookup(struct net *net,
int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr,
- int family)
+ int family, u32 mark)
{
struct xfrm_policy_afinfo *afinfo;
struct dst_entry *dst;
@@ -134,7 +143,7 @@ static inline struct dst_entry *__xfrm_dst_lookup(struct net *net,
if (unlikely(afinfo == NULL))
return ERR_PTR(-EAFNOSUPPORT);
- dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr);
+ dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark);
xfrm_policy_put_afinfo(afinfo);
@@ -145,7 +154,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
int tos, int oif,
xfrm_address_t *prev_saddr,
xfrm_address_t *prev_daddr,
- int family)
+ int family, u32 mark)
{
struct net *net = xs_net(x);
xfrm_address_t *saddr = &x->props.saddr;
@@ -161,7 +170,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
daddr = x->coaddr;
}
- dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family);
+ dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark);
if (!IS_ERR(dst)) {
if (prev_saddr != saddr)
@@ -778,6 +787,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
newpos = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == policy->type &&
+ pol->if_id == policy->if_id &&
!selector_cmp(&pol->selector, &policy->selector) &&
xfrm_policy_mark_match(policy, pol) &&
xfrm_sec_ctx_match(pol->security, policy->security) &&
@@ -830,8 +840,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
}
EXPORT_SYMBOL(xfrm_policy_insert);
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
- int dir, struct xfrm_selector *sel,
+struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
+ u8 type, int dir,
+ struct xfrm_selector *sel,
struct xfrm_sec_ctx *ctx, int delete,
int *err)
{
@@ -844,6 +855,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == type &&
+ pol->if_id == if_id &&
(mark & pol->mark.m) == pol->mark.v &&
!selector_cmp(sel, &pol->selector) &&
xfrm_sec_ctx_match(ctx, pol->security)) {
@@ -869,8 +881,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
}
EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
- int dir, u32 id, int delete, int *err)
+struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
+ u8 type, int dir, u32 id, int delete,
+ int *err)
{
struct xfrm_policy *pol, *ret;
struct hlist_head *chain;
@@ -885,6 +898,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
ret = NULL;
hlist_for_each_entry(pol, chain, byidx) {
if (pol->type == type && pol->index == id &&
+ pol->if_id == if_id &&
(mark & pol->mark.m) == pol->mark.v) {
xfrm_pol_hold(pol);
if (delete) {
@@ -1095,6 +1109,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
bool match;
if (pol->family != family ||
+ pol->if_id != fl->flowi_xfrm.if_id ||
(fl->flowi_mark & pol->mark.m) != pol->mark.v ||
pol->type != type)
return ret;
@@ -1264,7 +1279,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
match = xfrm_selector_match(&pol->selector, fl, family);
if (match) {
- if ((sk->sk_mark & pol->mark.m) != pol->mark.v) {
+ if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
+ pol->if_id != fl->flowi_xfrm.if_id) {
pol = NULL;
goto out;
}
@@ -1392,6 +1408,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
newp->lft = old->lft;
newp->curlft = old->curlft;
newp->mark = old->mark;
+ newp->if_id = old->if_id;
newp->action = old->action;
newp->flags = old->flags;
newp->xfrm_nr = old->xfrm_nr;
@@ -1432,14 +1449,14 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
static int
xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
- xfrm_address_t *remote, unsigned short family)
+ xfrm_address_t *remote, unsigned short family, u32 mark)
{
int err;
struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
if (unlikely(afinfo == NULL))
return -EINVAL;
- err = afinfo->get_saddr(net, oif, local, remote);
+ err = afinfo->get_saddr(net, oif, local, remote, mark);
xfrm_policy_put_afinfo(afinfo);
return err;
}
@@ -1470,7 +1487,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
if (xfrm_addr_any(local, tmpl->encap_family)) {
error = xfrm_get_saddr(net, fl->flowi_oif,
&tmp, remote,
- tmpl->encap_family);
+ tmpl->encap_family, 0);
if (error)
goto fail;
local = &tmp;
@@ -1747,9 +1764,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
dst_copy_metrics(dst1, dst);
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
+ __u32 mark = 0;
+
+ if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
+ mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
- &saddr, &daddr, family);
+ &saddr, &daddr, family, mark);
err = PTR_ERR(dst);
if (IS_ERR(dst))
goto put_states;
@@ -2119,6 +2141,10 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
xflo->dst_orig);
if (IS_ERR(new_xdst)) {
err = PTR_ERR(new_xdst);
+ if (err == -EREMOTE) {
+ xfrm_pols_put(pols, num_pols);
+ return NULL;
+ }
if (err != -EAGAIN)
goto error;
if (oldflo == NULL)
@@ -2231,6 +2257,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
if (IS_ERR(xdst)) {
xfrm_pols_put(pols, num_pols);
err = PTR_ERR(xdst);
+ if (err == -EREMOTE)
+ goto nopol;
+
goto dropdst;
} else if (xdst == NULL) {
num_xfrms = 0;
@@ -2429,13 +2458,21 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
unsigned int family, int reverse)
{
- struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+ const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+ const struct xfrm_if_cb *ifcb = xfrm_if_get_cb();
+ struct xfrm_if *xi;
int err;
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
afinfo->decode_session(skb, fl, reverse);
+ if (ifcb) {
+ xi = ifcb->decode_session(skb);
+ if (xi)
+ fl->flowi_xfrm.if_id = xi->p.if_id;
+ }
+
err = security_xfrm_decode_session(skb, &fl->flowi_secid);
xfrm_policy_put_afinfo(afinfo);
return err;
@@ -2900,6 +2937,20 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
static struct notifier_block xfrm_dev_notifier = {
.notifier_call = xfrm_dev_event,
};
+void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb)
+{
+ spin_lock(&xfrm_if_cb_lock);
+ rcu_assign_pointer(xfrm_if_cb, ifcb);
+ spin_unlock(&xfrm_if_cb_lock);
+}
+EXPORT_SYMBOL(xfrm_if_register_cb);
+
+void xfrm_if_unregister_cb(void)
+{
+ RCU_INIT_POINTER(xfrm_if_cb, NULL);
+ synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_if_unregister_cb);
#ifdef CONFIG_XFRM_STATISTICS
static int __net_init xfrm_statistics_init(struct net *net)
@@ -3079,6 +3130,9 @@ void __init xfrm_init(void)
register_pernet_subsys(&xfrm_net_ops);
seqcount_init(&xfrm_policy_hash_generation);
xfrm_input_init();
+
+ RCU_INIT_POINTER(xfrm_if_cb, NULL);
+ synchronize_rcu();
}
#ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 4d19f2f..1af6ba7 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -797,6 +797,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
int error = 0;
struct xfrm_state *best = NULL;
u32 mark = pol->mark.v & pol->mark.m;
+ u32 if_id = fl->flowi_xfrm.if_id;
unsigned short encap_family = tmpl->encap_family;
unsigned int sequence;
struct km_event c;
@@ -811,6 +812,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
+ x->if_id == if_id &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
tmpl->mode == x->props.mode &&
@@ -827,6 +829,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
+ x->if_id == if_id &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
tmpl->mode == x->props.mode &&
@@ -866,6 +869,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
* to current session. */
xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
memcpy(&x->mark, &pol->mark, sizeof(x->mark));
+ x->if_id = if_id;
error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
if (error) {
@@ -923,7 +927,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
}
struct xfrm_state *
-xfrm_stateonly_find(struct net *net, u32 mark,
+xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
xfrm_address_t *daddr, xfrm_address_t *saddr,
unsigned short family, u8 mode, u8 proto, u32 reqid)
{
@@ -936,6 +940,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
if (x->props.family == family &&
x->props.reqid == reqid &&
(mark & x->mark.m) == x->mark.v &&
+ x->if_id == if_id &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, family) &&
mode == x->props.mode &&
@@ -1016,11 +1021,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
struct xfrm_state *x;
unsigned int h;
u32 mark = xnew->mark.v & xnew->mark.m;
+ u32 if_id = xnew->if_id;
h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
+ x->if_id == if_id &&
(mark & x->mark.m) == x->mark.v &&
xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
@@ -1043,7 +1050,7 @@ EXPORT_SYMBOL(xfrm_state_insert);
static struct xfrm_state *__find_acq_core(struct net *net,
const struct xfrm_mark *m,
unsigned short family, u8 mode,
- u32 reqid, u8 proto,
+ u32 reqid, u32 if_id, u8 proto,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
int create)
@@ -1098,6 +1105,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
x->props.family = family;
x->props.mode = mode;
x->props.reqid = reqid;
+ x->if_id = if_id;
x->mark.v = m->v;
x->mark.m = m->m;
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
@@ -1152,7 +1160,7 @@ int xfrm_state_add(struct xfrm_state *x)
if (use_spi && !x1)
x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
- x->props.reqid, x->id.proto,
+ x->props.reqid, x->if_id, x->id.proto,
&x->id.daddr, &x->props.saddr, 0);
__xfrm_state_bump_genids(x);
@@ -1244,6 +1252,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig)
x->props.flags = orig->props.flags;
x->props.extra_flags = orig->props.extra_flags;
+ x->if_id = orig->if_id;
x->tfcpad = orig->tfcpad;
x->replay_maxdiff = orig->replay_maxdiff;
x->replay_maxage = orig->replay_maxage;
@@ -1398,6 +1407,19 @@ int xfrm_state_update(struct xfrm_state *x)
if (x1->curlft.use_time)
xfrm_state_check_expire(x1);
+ if (x->props.smark.m || x->props.smark.v || x->if_id) {
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+
+ if (x->props.smark.m || x->props.smark.v)
+ x1->props.smark = x->props.smark;
+
+ if (x->if_id)
+ x1->if_id = x->if_id;
+
+ __xfrm_state_bump_genids(x1);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ }
+
err = 0;
x->km.state = XFRM_STATE_DEAD;
__xfrm_state_put(x);
@@ -1461,13 +1483,13 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
struct xfrm_state *
xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
- u8 proto, const xfrm_address_t *daddr,
+ u32 if_id, u8 proto, const xfrm_address_t *daddr,
const xfrm_address_t *saddr, int create, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
+ x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
@@ -1884,6 +1906,66 @@ bool km_is_alive(const struct km_event *c)
}
EXPORT_SYMBOL(km_is_alive);
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+ struct xfrm_translator *xtr;
+
+ rcu_read_lock();
+ xtr = rcu_dereference(xfrm_translator);
+ if (unlikely(!xtr))
+ goto out;
+ if (!try_module_get(xtr->owner))
+ xtr = NULL;
+out:
+ rcu_read_unlock();
+ return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+ module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+ int err = 0;
+
+ spin_lock_bh(&xfrm_translator_lock);
+ if (unlikely(xfrm_translator != NULL))
+ err = -EEXIST;
+ else
+ rcu_assign_pointer(xfrm_translator, xtr);
+ spin_unlock_bh(&xfrm_translator_lock);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+ int err = 0;
+
+ spin_lock_bh(&xfrm_translator_lock);
+ if (likely(xfrm_translator != NULL)) {
+ if (rcu_access_pointer(xfrm_translator) != xtr)
+ err = -EINVAL;
+ else
+ RCU_INIT_POINTER(xfrm_translator, NULL);
+ }
+ spin_unlock_bh(&xfrm_translator_lock);
+ synchronize_rcu();
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
{
int err;
@@ -1891,11 +1973,6 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
struct xfrm_mgr *km;
struct xfrm_policy *pol = NULL;
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- return -EOPNOTSUPP;
-#endif
-
if (!optval && !optlen) {
xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
@@ -1914,6 +1991,23 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
if (copy_from_user(data, optval, optlen))
goto out;
+ /* Use the 64-bit / untranslated format on Android, even for compat */
+ if (!IS_ENABLED(CONFIG_ANDROID) || IS_ENABLED(CONFIG_XFRM_USER_COMPAT)) {
+ if (in_compat_syscall()) {
+ struct xfrm_translator *xtr = xfrm_get_translator();
+
+ if (!xtr)
+ return -EOPNOTSUPP;
+
+ err = xtr->xlate_user_policy_sockptr(&data, optlen);
+ xfrm_put_translator(xtr);
+ if (err) {
+ kfree(data);
+ return err;
+ }
+ }
+ }
+
err = -EINVAL;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
@@ -1927,6 +2021,7 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
if (err >= 0) {
xfrm_sk_policy_insert(sk, err, pol);
xfrm_pol_put(pol);
+ __sk_dst_reset(sk);
err = 0;
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index feb24ca..05d1060 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -553,6 +553,19 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
x->replay_maxdiff = nla_get_u32(rt);
}
+static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m)
+{
+ if (attrs[XFRMA_SET_MARK]) {
+ m->v = nla_get_u32(attrs[XFRMA_SET_MARK]);
+ if (attrs[XFRMA_SET_MARK_MASK])
+ m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]);
+ else
+ m->m = 0xffffffff;
+ } else {
+ m->v = m->m = 0;
+ }
+}
+
static struct xfrm_state *xfrm_state_construct(struct net *net,
struct xfrm_usersa_info *p,
struct nlattr **attrs,
@@ -605,6 +618,11 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
xfrm_mark_get(attrs, &x->mark);
+ xfrm_smark_init(attrs, &x->props.smark);
+
+ if (attrs[XFRMA_IF_ID])
+ x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
err = __xfrm_init_state(x, false);
if (err)
goto error;
@@ -818,6 +836,18 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
return 0;
}
+static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m)
+{
+ int ret = 0;
+
+ if (m->v | m->m) {
+ ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v);
+ if (!ret)
+ ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m);
+ }
+ return ret;
+}
+
/* Don't change this without updating xfrm_sa_len! */
static int copy_to_user_state_extra(struct xfrm_state *x,
struct xfrm_usersa_info *p,
@@ -881,6 +911,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
ret = xfrm_mark_put(skb, &x->mark);
if (ret)
goto out;
+
+ ret = xfrm_smark_put(skb, &x->props.smark);
+ if (ret)
+ goto out;
+
if (x->replay_esn)
ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
xfrm_replay_state_esn_len(x->replay_esn),
@@ -890,6 +925,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
&x->replay);
if (ret)
goto out;
+
+ if (x->if_id) {
+ ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id);
+ if (ret)
+ goto out;
+ }
+
if (x->security)
ret = copy_sec_ctx(x->security, skb);
out:
@@ -901,6 +943,7 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
struct xfrm_dump_info *sp = ptr;
struct sk_buff *in_skb = sp->in_skb;
struct sk_buff *skb = sp->out_skb;
+ struct xfrm_translator *xtr;
struct xfrm_usersa_info *p;
struct nlmsghdr *nlh;
int err;
@@ -918,6 +961,18 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
return err;
}
nlmsg_end(skb, nlh);
+
+ xtr = xfrm_get_translator();
+ if (xtr) {
+ err = xtr->alloc_compat(skb, nlh);
+
+ xfrm_put_translator(xtr);
+ if (err) {
+ nlmsg_cancel(skb, nlh);
+ return err;
+ }
+ }
+
return 0;
}
@@ -932,7 +987,6 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb)
return 0;
}
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -1009,12 +1063,24 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
u32 pid, unsigned int group)
{
struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+ struct xfrm_translator *xtr;
if (!nlsk) {
kfree_skb(skb);
return -EPIPE;
}
+ xtr = xfrm_get_translator();
+ if (xtr) {
+ int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+ xfrm_put_translator(xtr);
+ if (err) {
+ kfree_skb(skb);
+ return err;
+ }
+ }
+
return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
}
@@ -1232,12 +1298,14 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
struct xfrm_userspi_info *p;
+ struct xfrm_translator *xtr;
struct sk_buff *resp_skb;
xfrm_address_t *daddr;
int family;
int err;
u32 mark;
struct xfrm_mark m;
+ u32 if_id = 0;
p = nlmsg_data(nlh);
err = verify_spi_info(p->info.id.proto, p->min, p->max);
@@ -1250,6 +1318,10 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
x = NULL;
mark = xfrm_mark_get(attrs, &m);
+
+ if (attrs[XFRMA_IF_ID])
+ if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
if (p->info.seq) {
x = xfrm_find_acq_byseq(net, mark, p->info.seq);
if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) {
@@ -1260,7 +1332,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!x)
x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid,
- p->info.id.proto, daddr,
+ if_id, p->info.id.proto, daddr,
&p->info.saddr, 1,
family);
err = -ENOENT;
@@ -1277,6 +1349,17 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
}
+ xtr = xfrm_get_translator();
+ if (xtr) {
+ err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+ xfrm_put_translator(xtr);
+ if (err) {
+ kfree_skb(resp_skb);
+ goto out;
+ }
+ }
+
err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
out:
@@ -1550,6 +1633,9 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us
xfrm_mark_get(attrs, &xp->mark);
+ if (attrs[XFRMA_IF_ID])
+ xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
return xp;
error:
*errp = err;
@@ -1680,6 +1766,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
struct xfrm_userpolicy_info *p;
struct sk_buff *in_skb = sp->in_skb;
struct sk_buff *skb = sp->out_skb;
+ struct xfrm_translator *xtr;
struct nlmsghdr *nlh;
int err;
@@ -1697,11 +1784,25 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
+ if (!err)
+ err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
nlmsg_end(skb, nlh);
+
+ xtr = xfrm_get_translator();
+ if (xtr) {
+ err = xtr->alloc_compat(skb, nlh);
+
+ xfrm_put_translator(xtr);
+ if (err) {
+ nlmsg_cancel(skb, nlh);
+ return err;
+ }
+ }
+
return 0;
}
@@ -1778,6 +1879,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
int delete;
struct xfrm_mark m;
u32 mark = xfrm_mark_get(attrs, &m);
+ u32 if_id = 0;
p = nlmsg_data(nlh);
delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY;
@@ -1790,8 +1892,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err)
return err;
+ if (attrs[XFRMA_IF_ID])
+ if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
if (p->index)
- xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, delete, &err);
+ xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err);
else {
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
struct xfrm_sec_ctx *ctx;
@@ -1808,7 +1913,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err)
return err;
}
- xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, &p->sel,
+ xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel,
ctx, delete, &err);
security_xfrm_policy_free(ctx);
}
@@ -1932,6 +2037,10 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
if (err)
goto out_cancel;
+ err = xfrm_if_id_put(skb, x->if_id);
+ if (err)
+ goto out_cancel;
+
nlmsg_end(skb, nlh);
return 0;
@@ -2073,6 +2182,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
int err = -ENOENT;
struct xfrm_mark m;
u32 mark = xfrm_mark_get(attrs, &m);
+ u32 if_id = 0;
err = copy_from_user_policy_type(&type, attrs);
if (err)
@@ -2082,8 +2192,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err)
return err;
+ if (attrs[XFRMA_IF_ID])
+ if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
if (p->index)
- xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, 0, &err);
+ xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err);
else {
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
struct xfrm_sec_ctx *ctx;
@@ -2100,7 +2213,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err)
return err;
}
- xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir,
+ xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir,
&p->sel, ctx, 0, &err);
security_xfrm_policy_free(ctx);
}
@@ -2409,7 +2522,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
#define XMSGSIZE(type) sizeof(struct type)
-static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
+const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
[XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
[XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
[XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
@@ -2432,10 +2545,11 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
[XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
[XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
};
+EXPORT_SYMBOL_GPL(xfrm_msg_min);
#undef XMSGSIZE
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
+const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
[XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)},
[XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)},
[XFRMA_LASTUSED] = { .type = NLA_U64},
@@ -2462,7 +2576,11 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
[XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 },
[XFRMA_PROTO] = { .type = NLA_U8 },
[XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) },
+ [XFRMA_SET_MARK] = { .type = NLA_U32 },
+ [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 },
+ [XFRMA_IF_ID] = { .type = NLA_U32 },
};
+EXPORT_SYMBOL_GPL(xfrma_policy);
static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
@@ -2511,13 +2629,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
struct nlattr *attrs[XFRMA_MAX+1];
const struct xfrm_link *link;
+ struct nlmsghdr *nlh64 = NULL;
int type, err;
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- return -EOPNOTSUPP;
-#endif
-
type = nlh->nlmsg_type;
if (type > XFRM_MSG_MAX)
return -EINVAL;
@@ -2529,32 +2643,58 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (!netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
+ /* Use the 64-bit / untranslated format on Android, even for compat */
+ if (!IS_ENABLED(CONFIG_ANDROID) || IS_ENABLED(CONFIG_XFRM_USER_COMPAT)) {
+ if (in_compat_syscall()) {
+ struct xfrm_translator *xtr = xfrm_get_translator();
+
+ if (!xtr)
+ return -EOPNOTSUPP;
+
+ nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
+ link->nla_pol);
+ xfrm_put_translator(xtr);
+ if (IS_ERR(nlh64))
+ return PTR_ERR(nlh64);
+ if (nlh64)
+ nlh = nlh64;
+ }
+ }
+
if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
(nlh->nlmsg_flags & NLM_F_DUMP)) {
- if (link->dump == NULL)
- return -EINVAL;
+ struct netlink_dump_control c = {
+ .start = link->start,
+ .dump = link->dump,
+ .done = link->done,
+ };
- {
- struct netlink_dump_control c = {
- .start = link->start,
- .dump = link->dump,
- .done = link->done,
- };
- return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+ if (link->dump == NULL) {
+ err = -EINVAL;
+ goto err;
}
+
+ err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+ goto err;
}
err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs,
link->nla_max ? : XFRMA_MAX,
link->nla_pol ? : xfrma_policy);
if (err < 0)
- return err;
+ goto err;
- if (link->doit == NULL)
- return -EINVAL;
+ if (link->doit == NULL) {
+ err = -EINVAL;
+ goto err;
+ }
- return link->doit(skb, nlh, attrs);
+ err = link->doit(skb, nlh, attrs);
+
+err:
+ kvfree(nlh64);
+ return err;
}
static void xfrm_netlink_rcv(struct sk_buff *skb)
@@ -2590,6 +2730,10 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct
if (err)
return err;
+ err = xfrm_if_id_put(skb, x->if_id);
+ if (err)
+ return err;
+
nlmsg_end(skb, nlh);
return 0;
}
@@ -2681,6 +2825,12 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
l += nla_total_size(sizeof(*x->coaddr));
if (x->props.extra_flags)
l += nla_total_size(sizeof(x->props.extra_flags));
+ if (x->props.smark.v | x->props.smark.m) {
+ l += nla_total_size(sizeof(x->props.smark.v));
+ l += nla_total_size(sizeof(x->props.smark.m));
+ }
+ if (x->if_id)
+ l += nla_total_size(sizeof(x->if_id));
/* Must count x->lastused as it may become non-zero behind our back. */
l += nla_total_size_64bit(sizeof(u64));
@@ -2808,6 +2958,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
+ if (!err)
+ err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
@@ -2923,6 +3075,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
+ if (!err)
+ err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
@@ -3002,6 +3156,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
+ if (!err)
+ err = xfrm_if_id_put(skb, xp->if_id);
if (err)
goto out_free_skb;
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 72c5867..b2cdced 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -22,6 +22,7 @@
hostprogs-y += map_perf_test
hostprogs-y += test_overhead
hostprogs-y += test_cgrp2_array_pin
+hostprogs-y += test_cgrp2_attach
hostprogs-y += xdp1
hostprogs-y += xdp2
hostprogs-y += test_current_task_under_cgroup
@@ -50,6 +51,7 @@
map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
+test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o
xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
# reuse xdp1 source intentionally
xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
index 9969e35..9cbc786 100644
--- a/samples/bpf/libbpf.c
+++ b/samples/bpf/libbpf.c
@@ -104,6 +104,29 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
}
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+ unsigned int flags)
+{
+ union bpf_attr attr = {
+ .target_fd = target_fd,
+ .attach_bpf_fd = prog_fd,
+ .attach_type = type,
+ .attach_flags = flags;
+ };
+
+ return syscall(__NR_bpf, BPF_PROG_ATTACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+{
+ union bpf_attr attr = {
+ .target_fd = target_fd,
+ .attach_type = type,
+ };
+
+ return syscall(__NR_bpf, BPF_PROG_DETACH, &attr, sizeof(attr));
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr = {
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index ac6edb6..b06cf5a 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -15,6 +15,10 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, int insn_len,
const char *license, int kern_version);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+ unsigned int flags);
+int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+
int bpf_obj_pin(int fd, const char *pathname);
int bpf_obj_get(const char *pathname);
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
new file mode 100644
index 0000000..9de4896
--- /dev/null
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -0,0 +1,147 @@
+/* eBPF example program:
+ *
+ * - Creates arraymap in kernel with 4 bytes keys and 8 byte values
+ *
+ * - Loads eBPF program
+ *
+ * The eBPF program accesses the map passed in to store two pieces of
+ * information. The number of invocations of the program, which maps
+ * to the number of packets received, is stored to key 0. Key 1 is
+ * incremented on each iteration by the number of bytes stored in
+ * the skb.
+ *
+ * - Detaches any eBPF program previously attached to the cgroup
+ *
+ * - Attaches the new program to a cgroup using BPF_PROG_ATTACH
+ *
+ * - Every second, reads map[0] and map[1] to see how many bytes and
+ * packets were seen on any socket of tasks in the given cgroup.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+#include <unistd.h>
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+
+#include <linux/bpf.h>
+
+#include "libbpf.h"
+
+enum {
+ MAP_KEY_PACKETS,
+ MAP_KEY_BYTES,
+};
+
+static int prog_load(int map_fd, int verdict)
+{
+ struct bpf_insn prog[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), /* save r6 so it's not clobbered by BPF_CALL */
+
+ /* Count packets */
+ BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_PACKETS), /* r0 = 0 */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+ BPF_LD_MAP_FD(BPF_REG_1, map_fd), /* load map fd to r1 */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+
+ /* Count bytes */
+ BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+ BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+
+ BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+ BPF_EXIT_INSN(),
+ };
+
+ return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB,
+ prog, sizeof(prog), "GPL", 0);
+}
+
+static int usage(const char *argv0)
+{
+ printf("Usage: %s <cg-path> <egress|ingress> [drop]\n", argv0);
+ return EXIT_FAILURE;
+}
+
+int main(int argc, char **argv)
+{
+ int cg_fd, map_fd, prog_fd, key, ret;
+ long long pkt_cnt, byte_cnt;
+ enum bpf_attach_type type;
+ int verdict = 1;
+
+ if (argc < 3)
+ return usage(argv[0]);
+
+ if (strcmp(argv[2], "ingress") == 0)
+ type = BPF_CGROUP_INET_INGRESS;
+ else if (strcmp(argv[2], "egress") == 0)
+ type = BPF_CGROUP_INET_EGRESS;
+ else
+ return usage(argv[0]);
+
+ if (argc > 3 && strcmp(argv[3], "drop") == 0)
+ verdict = 0;
+
+ cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY);
+ if (cg_fd < 0) {
+ printf("Failed to open cgroup path: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY,
+ sizeof(key), sizeof(byte_cnt),
+ 256, 0);
+ if (map_fd < 0) {
+ printf("Failed to create map: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ prog_fd = prog_load(map_fd, verdict);
+ printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf);
+
+ if (prog_fd < 0) {
+ printf("Failed to load prog: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ ret = bpf_prog_detach(cg_fd, type);
+ printf("bpf_prog_detach() returned '%s' (%d)\n", strerror(errno), errno);
+
+ ret = bpf_prog_attach(prog_fd, cg_fd, type, 0);
+ if (ret < 0) {
+ printf("Failed to attach prog to cgroup: '%s'\n",
+ strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ while (1) {
+ key = MAP_KEY_PACKETS;
+ assert(bpf_lookup_elem(map_fd, &key, &pkt_cnt) == 0);
+
+ key = MAP_KEY_BYTES;
+ assert(bpf_lookup_elem(map_fd, &key, &byte_cnt) == 0);
+
+ printf("cgroup received %lld packets, %lld bytes\n",
+ pkt_cnt, byte_cnt);
+ sleep(1);
+ }
+
+ return EXIT_SUCCESS;
+}
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 1920b9e..a45ea93 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -149,6 +149,37 @@
# Expands to either gcc or clang
cc-name = $(shell $(CC) -v 2>&1 | grep -q "clang version" && echo clang || echo gcc)
+# __cc-version
+# Returns compiler version
+__cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/$(cc-name)-version.sh $(CC))
+
+# __cc-fullversion
+# Returns full compiler version
+__cc-fullversion = $(shell $(CONFIG_SHELL) \
+ $(srctree)/scripts/$(cc-name)-version.sh -p $(CC))
+
+# __cc-ifversion
+# Matches compiler name and version
+# Usage: EXTRA_CFLAGS += $(call cc-if-name-version, gcc, -lt, 0402, -O1)
+__cc-ifversion = $(shell [ $(cc-name) = $(1) ] && [ $(__cc-version) $(2) $(3) ] && echo $(4) || echo $(5))
+
+# __cc-if-fullversion
+# Matches compiler name and full version
+# Usage: EXTRA_CFLAGS += $(call cc-if-name-fullversion, gcc, -lt, 040502, -O1)
+__cc-if-fullversion = $(shell [ $(cc-name) = $(1) ] && [ $(__cc-fullversion) $(2) $(3) ] && echo $(4) || echo $(5))
+
+# gcc-ifversion
+gcc-ifversion = $(call __cc-ifversion, gcc, $(1), $(2), $(3), $(4))
+
+# gcc-if-fullversion
+gcc-if-fullversion = (call __cc-if-fullversion, gcc, $(1), $(2), $(3), $(4))
+
+# clang-ifversion
+clang-ifversion = $(call __cc-ifversion, clang, $(1), $(2), $(3), $(4))
+
+# clang-if-fullversion
+clang-if-fullversion = (call __cc-if-fullversion, clang, $(1), $(2), $(3), $(4))
+
# cc-version
cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC))
@@ -156,9 +187,9 @@
cc-fullversion = $(shell $(CONFIG_SHELL) \
$(srctree)/scripts/gcc-version.sh -p $(CC))
-# cc-ifversion
-# Usage: EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1)
-cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4))
+# backward compatibility
+cc-ifversion = $(gcc-ifversion)
+cc-if-fullversion = $(gcc-if-fullversion)
# cc-ldoption
# Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both)
@@ -174,6 +205,10 @@
# Important: no spaces around options
ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2))
+# ld-name
+# Expands to either bfd or gold
+ld-name = $(shell $(LD) -v 2>&1 | grep -q "GNU gold" && echo gold || echo bfd)
+
# ld-version
# Note this is mainly for HJ Lu's 3 number binutil versions
ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh)
@@ -182,6 +217,18 @@
# Usage: $(call ld-ifversion, -ge, 22252, y)
ld-ifversion = $(shell [ $(ld-version) $(1) $(2) ] && echo $(3) || echo $(4))
+# __ld-ifversion
+# Usage: $(call __ld-ifversion, gold, -ge, 112000000, y)
+__ld-ifversion = $(shell [ $(ld-name) = $(1) ] && [ $(ld-version) $(2) $(3) ] && echo $(4) || echo $(5))
+
+# bfd-ifversion
+# Usage: $(call bfd-ifversion, -ge, 227000000, y)
+bfd-ifversion = $(call __ld-ifversion, bfd, $(1), $(2), $(3), $(4))
+
+# gold-ifversion
+# Usage: $(call gold-ifversion, -ge, 112000000, y)
+gold-ifversion = $(call __ld-ifversion, gold, $(1), $(2), $(3), $(4))
+
######
###
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 6228a83..d41c72a 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -208,6 +208,23 @@
cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $<
+ifdef CONFIG_LTO_CLANG
+# Generate .o.symversions files for each .o with exported symbols, and link these
+# to the kernel and/or modules at the end.
+cmd_modversions_c = \
+ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) >/dev/null 2>/dev/null; then \
+ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \
+ $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
+ > $(@D)/$(@F).symversions; \
+ fi; \
+ else \
+ if $(LLVM_DIS) -o=- $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \
+ $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
+ > $(@D)/$(@F).symversions; \
+ fi; \
+ fi; \
+ mv -f $(@D)/.tmp_$(@F) $@;
+else
cmd_modversions_c = \
if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \
$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
@@ -220,12 +237,19 @@
mv -f $(@D)/.tmp_$(@F) $@; \
fi;
endif
+endif
ifdef CONFIG_FTRACE_MCOUNT_RECORD
ifdef BUILD_C_RECORDMCOUNT
ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
RECORDMCOUNT_FLAGS = -w
endif
+
+ifdef CONFIG_LTO_CLANG
+# With LTO, we postpone running recordmcount until after the LTO link step, so
+# let's export the parameters for the link script.
+export RECORDMCOUNT_FLAGS
+else
# Due to recursion, we must skip empty.o.
# The empty.o file is created in the make process in order to determine
# the target endianness and word size. It is made before all other C
@@ -234,23 +258,29 @@
if [ $(@) != "scripts/mod/empty.o" ]; then \
$(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)"; \
fi;
+endif
+
recordmcount_source := $(srctree)/scripts/recordmcount.c \
$(srctree)/scripts/recordmcount.h
-else
+else # !BUILD_C_RECORDMCOUNT
sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
"$(if $(CONFIG_64BIT),64,32)" \
"$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
"$(LD)" "$(NM)" "$(RM)" "$(MV)" \
"$(if $(part-of-module),1,0)" "$(@)";
+
recordmcount_source := $(srctree)/scripts/recordmcount.pl
-endif
+endif # BUILD_C_RECORDMCOUNT
+
+ifndef CONFIG_LTO_CLANG
cmd_record_mcount = \
if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \
"$(CC_FLAGS_FTRACE)" ]; then \
$(sub_cmd_record_mcount) \
fi;
endif
+endif # CONFIG_FTRACE_MCOUNT_RECORD
ifdef CONFIG_STACK_VALIDATION
ifneq ($(SKIP_STACK_VALIDATION),1)
@@ -437,9 +467,30 @@
#
ifdef builtin-target
+ifdef CONFIG_LTO_CLANG
+ ifdef CONFIG_MODVERSIONS
+ # combine symversions for later processing
+ update_lto_symversions = \
+ rm -f $@.symversions; \
+ for i in $(filter-out FORCE,$^); do \
+ if [ -f $$i.symversions ]; then \
+ cat $$i.symversions \
+ >> $@.symversions; \
+ fi; \
+ done;
+ endif
+ # rebuild the symbol table with llvm-ar to include IR files
+ update_lto_symtable = ; \
+ mv -f $@ $@.tmp; \
+ $(LLVM_AR) rcsT$(KBUILD_ARFLAGS) $@ \
+ $$($(AR) t $@.tmp); \
+ rm -f $@.tmp
+endif
+
ifdef CONFIG_THIN_ARCHIVES
- cmd_make_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS)
- cmd_make_empty_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS)
+ cmd_make_builtin = $(update_lto_symversions) \
+ rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS)
+ cmd_make_empty_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS)
quiet_cmd_link_o_target = AR $@
else
cmd_make_builtin = $(LD) $(ld_flags) -r -o
@@ -479,7 +530,11 @@
quiet_cmd_link_l_target = AR $@
ifdef CONFIG_THIN_ARCHIVES
- cmd_link_l_target = rm -f $@; $(AR) rcsT$(KBUILD_ARFLAGS) $@ $(lib-y)
+ cmd_link_l_target = \
+ $(update_lto_symversions) \
+ rm -f $@; \
+ $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(lib-y) \
+ $(update_lto_symtable)
else
cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y)
endif
@@ -497,14 +552,36 @@
ref_prefix = EXTERN(
endif
-quiet_cmd_export_list = EXPORTS $@
-cmd_export_list = $(OBJDUMP) -h $< | \
- sed -ne '/___ksymtab/{s/.*+/$(ref_prefix)/;s/ .*/)/;p}' >$(ksyms-lds);\
- rm -f $(dummy-object);\
- $(AR) rcs$(KBUILD_ARFLAGS) $(dummy-object);\
+filter_export_list = sed -ne '/___ksymtab/s/.*+\([^ "]*\).*/$(ref_prefix)\1)/p'
+link_export_list = rm -f $(dummy-object);\
+ echo | $(CC) $(a_flags) -c -o $(dummy-object) -x assembler -;\
$(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\
rm $(dummy-object) $(ksyms-lds)
+quiet_cmd_export_list = EXPORTS $@
+
+ifdef CONFIG_LTO_CLANG
+# objdump doesn't understand IR files and llvm-dis doesn't support archives,
+# so we'll walk through each file in the archive separately
+cmd_export_list = \
+ rm -f $(ksyms-lds); \
+ for o in $$($(AR) t $<); do \
+ if $(OBJDUMP) -h $$o >/dev/null 2>/dev/null; then \
+ $(OBJDUMP) -h $$o | \
+ $(filter_export_list) \
+ >>$(ksyms-lds); \
+ else \
+ $(LLVM_DIS) -o=- $$o | \
+ $(filter_export_list) \
+ >>$(ksyms-lds); \
+ fi; \
+ done; \
+ $(link_export_list)
+else
+cmd_export_list = $(OBJDUMP) -h $< | $(filter_export_list) >$(ksyms-lds); \
+ $(link_export_list)
+endif
+
$(obj)/lib-ksyms.o: $(lib-target) FORCE
$(call if_changed,export_list)
@@ -528,20 +605,36 @@
$($(subst $(obj)/,,$(@:.o=-y))) \
$($(subst $(obj)/,,$(@:.o=-m)))), $^)
-quiet_cmd_link_multi-y = LD $@
-cmd_link_multi-y = $(LD) $(ld_flags) -r -o $@ $(link_multi_deps) $(cmd_secanalysis)
+cmd_link_multi-link = $(LD) $(ld_flags) -r -o $@ $(link_multi_deps) $(cmd_secanalysis)
+
+ifdef CONFIG_THIN_ARCHIVES
+ quiet_cmd_link_multi-y = AR $@
+ cmd_link_multi-y = $(update_lto_symversions) \
+ rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(link_multi_deps) \
+ $(update_lto_symtable)
+else
+ quiet_cmd_link_multi-y = LD $@
+ cmd_link_multi-y = $(cmd_link_multi-link)
+endif
quiet_cmd_link_multi-m = LD [M] $@
-cmd_link_multi-m = $(cmd_link_multi-y)
+
+ifdef CONFIG_LTO_CLANG
+ # don't compile IR until needed
+ cmd_link_multi-m = $(cmd_link_multi-y)
+else
+ cmd_link_multi-m = $(cmd_link_multi-link)
+endif
$(multi-used-y): FORCE
$(call if_changed,link_multi-y)
-$(call multi_depend, $(multi-used-y), .o, -objs -y)
$(multi-used-m): FORCE
$(call if_changed,link_multi-m)
@{ echo $(@:.o=.ko); echo $(link_multi_deps); \
$(cmd_undef_syms); } > $(MODVERDIR)/$(@F:.o=.mod)
+
+$(call multi_depend, $(multi-used-y), .o, -objs -y)
$(call multi_depend, $(multi-used-m), .o, -objs -y -m)
targets += $(multi-used-y) $(multi-used-m)
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 50616ea..2e70c6f 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -11,7 +11,7 @@
# The filename Kbuild has precedence over Makefile
kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src))
-include $(if $(wildcard $(kbuild-dir)/Kbuild), $(kbuild-dir)/Kbuild, $(kbuild-dir)/Makefile)
+-include $(if $(wildcard $(kbuild-dir)/Kbuild), $(kbuild-dir)/Kbuild, $(kbuild-dir)/Makefile)
# Figure out what we need to build from the various variables
# ==========================================================================
diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 2624d4bf..d809e00 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -9,10 +9,7 @@
CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address
-CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \
- -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET) \
- --param asan-stack=1 --param asan-globals=1 \
- --param asan-instrumentation-with-call-threshold=$(call_threshold))
+cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
ifeq ($(call cc-option, $(CFLAGS_KASAN_MINIMAL) -Werror),)
ifneq ($(CONFIG_COMPILE_TEST),y)
@@ -20,13 +17,24 @@
-fsanitize=kernel-address is not supported by compiler)
endif
else
- ifeq ($(CFLAGS_KASAN),)
- ifneq ($(CONFIG_COMPILE_TEST),y)
- $(warning CONFIG_KASAN: compiler does not support all options.\
- Trying minimal configuration)
- endif
- CFLAGS_KASAN := $(CFLAGS_KASAN_MINIMAL)
- endif
+ # -fasan-shadow-offset fails without -fsanitize
+ CFLAGS_KASAN_SHADOW := $(call cc-option, -fsanitize=kernel-address \
+ -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET), \
+ $(call cc-option, -fsanitize=kernel-address \
+ -mllvm -asan-mapping-offset=$(KASAN_SHADOW_OFFSET)))
+
+ ifeq ($(strip $(CFLAGS_KASAN_SHADOW)),)
+ CFLAGS_KASAN := $(CFLAGS_KASAN_MINIMAL)
+ else
+ # Now add all the compiler specific options that are valid standalone
+ CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \
+ $(call cc-param,asan-globals=1) \
+ $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \
+ $(call cc-param,asan-stack=1) \
+ $(call cc-param,asan-use-after-scope=1) \
+ $(call cc-param,asan-instrument-allocas=1)
+ endif
+
endif
CFLAGS_KASAN_NOSANITIZE := -fno-builtin
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 4e02d51..45b5f55 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -314,6 +314,12 @@
dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
+# cat
+# ---------------------------------------------------------------------------
+# Concatentate multiple files together
+quiet_cmd_cat = CAT $@
+cmd_cat = (cat $(filter-out FORCE,$^) > $@) || (rm -f $@; false)
+
# Bzip2
# ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index 07650ee..6f4c3f5 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -29,7 +29,7 @@
INSTALL_MOD_DIR ?= extra
ext-mod-dir = $(INSTALL_MOD_DIR)$(subst $(patsubst %/,%,$(KBUILD_EXTMOD)),,$(@D))
-modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
+modinst_dir ?= $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
$(modules):
$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 8cb7971..c960480 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -82,12 +82,28 @@
MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS)))
+# If CONFIG_LTO_CLANG is enabled, .o files are either LLVM IR, or empty, so we
+# need to link them into actual objects before passing them to modpost
+modpost-ext = $(if $(CONFIG_LTO_CLANG),.lto,)
+
+ifdef CONFIG_LTO_CLANG
+quiet_cmd_cc_lto_link_modules = LD [M] $@
+cmd_cc_lto_link_modules = \
+ $(LD) $(ld_flags) -r -o $(@) \
+ $(shell [ -s $(@:$(modpost-ext).o=.o.symversions) ] && \
+ echo -T $(@:$(modpost-ext).o=.o.symversions)) \
+ --whole-archive $(filter-out FORCE,$^)
+
+$(modules:.ko=$(modpost-ext).o): %$(modpost-ext).o: %.o FORCE
+ $(call if_changed,cc_lto_link_modules)
+endif
+
# We can go over command line length here, so be careful.
quiet_cmd_modpost = MODPOST $(words $(filter-out vmlinux FORCE, $^)) modules
- cmd_modpost = $(MODLISTCMD) | sed 's/\.ko$$/.o/' | $(modpost) $(MODPOST_OPT) -s -T -
+ cmd_modpost = $(MODLISTCMD) | sed 's/\.ko$$/$(modpost-ext)\.o/' | $(modpost) $(MODPOST_OPT) -s -T -
PHONY += __modpost
-__modpost: $(modules:.ko=.o) FORCE
+__modpost: $(modules:.ko=$(modpost-ext).o) FORCE
$(call cmd,modpost) $(wildcard vmlinux)
quiet_cmd_kernel-mod = MODPOST $@
@@ -98,8 +114,7 @@
# Declare generated files as targets for modpost
$(symverfile): __modpost ;
-$(modules:.ko=.mod.c): __modpost ;
-
+$(modules:.ko=$(modpost-ext).mod.c): __modpost ;
# Step 5), compile all *.mod.c files
@@ -110,22 +125,37 @@
cmd_cc_o_c = $(CC) $(c_flags) $(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE) \
-c -o $@ $<
-$(modules:.ko=.mod.o): %.mod.o: %.mod.c FORCE
+$(modules:.ko=.mod.o): %.mod.o: %$(modpost-ext).mod.c FORCE
$(call if_changed_dep,cc_o_c)
-targets += $(modules:.ko=.mod.o)
+targets += $(modules:.ko=$(modpost-ext).mod.o)
ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
# Step 6), final link of the modules with optional arch pass after final link
quiet_cmd_ld_ko_o = LD [M] $@
+
+ifdef CONFIG_LTO_CLANG
+ cmd_ld_ko_o = \
+ $(LD) -r $(LDFLAGS) \
+ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
+ $(shell [ -s $(@:.ko=.o.symversions) ] && \
+ echo -T $(@:.ko=.o.symversions)) \
+ -o $@ --whole-archive \
+ $(filter-out FORCE,$(^:$(modpost-ext).o=.o))
+
+ ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ cmd_ld_ko_o += ; $(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) $@
+ endif
+else
cmd_ld_ko_o = \
$(LD) -r $(LDFLAGS) \
$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
-o $@ $(filter-out FORCE,$^) ; \
$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
+endif
-$(modules): %.ko :%.o %.mod.o FORCE
+$(modules): %.ko: %$(modpost-ext).o %.mod.o FORCE
+$(call if_changed,ld_ko_o)
targets += $(modules)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index c3b2324..ce03fe2 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2529,6 +2529,7 @@
# Check for git id commit length and improperly formed commit descriptions
if ($in_commit_log && !$commit_log_possible_stack_dump &&
$line !~ /^\s*(?:Link|Patchwork|http|https|BugLink):/i &&
+ $line !~ /^This reverts commit [0-9a-f]{7,40}/ &&
($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i &&
$line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
@@ -5620,6 +5621,32 @@
}
}
+ # check for vsprintf extension %p<foo> misuses
+ if ($^V && $^V ge 5.10.0 &&
+ defined $stat &&
+ $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s &&
+ $1 !~ /^_*volatile_*$/) {
+ my $bad_extension = "";
+ my $lc = $stat =~ tr@\n@@;
+ $lc = $lc + $linenr;
+ for (my $count = $linenr; $count <= $lc; $count++) {
+ my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
+ $fmt =~ s/%%//g;
+ if ($fmt =~ /(\%[\*\d\.]*p(?![\WFfSsBKRraEhMmIiUDdgVCbGNOx]).)/) {
+ $bad_extension = $1;
+ last;
+ }
+ }
+ if ($bad_extension ne "") {
+ my $stat_real = raw_line($linenr, 0);
+ for (my $count = $linenr + 1; $count <= $lc; $count++) {
+ $stat_real = $stat_real . "\n" . raw_line($count, 0);
+ }
+ WARN("VSPRINTF_POINTER_EXTENSION",
+ "Invalid vsprintf pointer extension '$bad_extension'\n" . "$here\n$stat_real\n");
+ }
+ }
+
# Check for misused memsets
if ($^V && $^V ge 5.10.0 &&
defined $stat &&
diff --git a/scripts/clang-android.sh b/scripts/clang-android.sh
new file mode 100755
index 0000000..9186c4f
--- /dev/null
+++ b/scripts/clang-android.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+$* -dM -E - </dev/null 2>&1 | grep -q __ANDROID__ && echo "y"
diff --git a/scripts/clang-version.sh b/scripts/clang-version.sh
new file mode 100755
index 0000000..9780efa
--- /dev/null
+++ b/scripts/clang-version.sh
@@ -0,0 +1,33 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# clang-version [-p] clang-command
+#
+# Prints the compiler version of `clang-command' in a canonical 4-digit form
+# such as `0500' for clang-5.0 etc.
+#
+# With the -p option, prints the patchlevel as well, for example `050001' for
+# clang-5.0.1 etc.
+#
+
+if [ "$1" = "-p" ] ; then
+ with_patchlevel=1;
+ shift;
+fi
+
+compiler="$*"
+
+if [ ${#compiler} -eq 0 ]; then
+ echo "Error: No compiler specified."
+ printf "Usage:\n\t$0 <clang-command>\n"
+ exit 1
+fi
+
+MAJOR=$(echo __clang_major__ | $compiler -E -x c - | tail -n 1)
+MINOR=$(echo __clang_minor__ | $compiler -E -x c - | tail -n 1)
+if [ "x$with_patchlevel" != "x" ] ; then
+ PATCHLEVEL=$(echo __clang_patchlevel__ | $compiler -E -x c - | tail -n 1)
+ printf "%02d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL
+else
+ printf "%02d%02d\\n" $MAJOR $MINOR
+fi
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index f742c65..8b4329c 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -53,9 +53,40 @@
${AR} rcsT${KBUILD_ARFLAGS} built-in.o \
${KBUILD_VMLINUX_INIT} \
${KBUILD_VMLINUX_MAIN}
+
+ if [ -n "${CONFIG_LTO_CLANG}" ]; then
+ mv -f built-in.o built-in.o.tmp
+ ${LLVM_AR} rcsT${KBUILD_ARFLAGS} built-in.o $(${AR} t built-in.o.tmp)
+ rm -f built-in.o.tmp
+ fi
fi
}
+# If CONFIG_LTO_CLANG is selected, collect generated symbol versions into
+# .tmp_symversions
+modversions()
+{
+ if [ -z "${CONFIG_LTO_CLANG}" ]; then
+ return
+ fi
+
+ if [ -z "${CONFIG_MODVERSIONS}" ]; then
+ return
+ fi
+
+ rm -f .tmp_symversions
+
+ for a in built-in.o ${KBUILD_VMLINUX_LIBS}; do
+ for o in $(${AR} t $a); do
+ if [ -f ${o}.symversions ]; then
+ cat ${o}.symversions >> .tmp_symversions
+ fi
+ done
+ done
+
+ echo "-T .tmp_symversions"
+}
+
# Link of vmlinux.o used for section mismatch analysis
# ${1} output file
modpost_link()
@@ -70,7 +101,29 @@
${KBUILD_VMLINUX_MAIN} \
--end-group"
fi
- ${LD} ${LDFLAGS} -r -o ${1} ${objects}
+
+ if [ -n "${CONFIG_LTO_CLANG}" ]; then
+ # This might take a while, so indicate that we're doing
+ # an LTO link
+ info LTO vmlinux.o
+ else
+ info LD vmlinux.o
+ fi
+
+ ${LD} ${LDFLAGS} -r -o ${1} $(modversions) ${objects}
+}
+
+# If CONFIG_LTO_CLANG is selected, we postpone running recordmcount until
+# we have compiled LLVM IR to an object file.
+recordmcount()
+{
+ if [ -z "${CONFIG_LTO_CLANG}" ]; then
+ return
+ fi
+
+ if [ -n "${CONFIG_FTRACE_MCOUNT_RECORD}" ]; then
+ scripts/recordmcount ${RECORDMCOUNT_FLAGS} $*
+ fi
}
# Link of vmlinux
@@ -82,7 +135,15 @@
local objects
if [ "${SRCARCH}" != "um" ]; then
- if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
+ local ld=${LD}
+ local ldflags="${LDFLAGS} ${LDFLAGS_vmlinux}"
+
+ if [ -n "${LDFINAL_vmlinux}" ]; then
+ ld=${LDFINAL_vmlinux}
+ ldflags="${LDFLAGS_FINAL_vmlinux} ${LDFLAGS_vmlinux}"
+ fi
+
+ if [[ -n "${CONFIG_THIN_ARCHIVES}" && -z "${CONFIG_LTO_CLANG}" ]]; then
objects="--whole-archive built-in.o ${1}"
else
objects="${KBUILD_VMLINUX_INIT} \
@@ -92,8 +153,7 @@
${1}"
fi
- ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \
- -T ${lds} ${objects}
+ ${ld} ${ldflags} -o ${2} -T ${lds} ${objects}
else
if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
objects="-Wl,--whole-archive built-in.o ${1}"
@@ -113,7 +173,6 @@
fi
}
-
# Create ${2} .o file with all symbols from the ${1} object file
kallsyms()
{
@@ -164,6 +223,7 @@
rm -f .tmp_System.map
rm -f .tmp_kallsyms*
rm -f .tmp_version
+ rm -f .tmp_symversions
rm -f .tmp_vmlinux*
rm -f built-in.o
rm -f System.map
@@ -209,15 +269,6 @@
. "./${KCONFIG_CONFIG}"
esac
-archive_builtin
-
-#link vmlinux.o
-info LD vmlinux.o
-modpost_link vmlinux.o
-
-# modpost vmlinux.o to check for section mismatches
-${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o
-
# Update version
info GEN .version
if [ ! -r .version ]; then
@@ -228,9 +279,27 @@
expr 0$(cat .old_version) + 1 >.version;
fi;
+archive_builtin
+
+#link vmlinux.o
+modpost_link vmlinux.o
+
+# modpost vmlinux.o to check for section mismatches
+${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o
+
# final build of init/
${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init GCC_PLUGINS_CFLAGS="${GCC_PLUGINS_CFLAGS}"
+if [ -n "${CONFIG_LTO_CLANG}" ]; then
+ # Re-use vmlinux.o, so we can avoid the slow LTO link step in
+ # vmlinux_link
+ KBUILD_VMLINUX_INIT=
+ KBUILD_VMLINUX_MAIN=vmlinux.o
+
+ # Call recordmcount if needed
+ recordmcount vmlinux.o
+fi
+
kallsymso=""
kallsyms_vmlinux=""
if [ -n "${CONFIG_KALLSYMS}" ]; then
diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index b497d97..247cf1f 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -1,4 +1,5 @@
OBJECT_FILES_NON_STANDARD := y
+CFLAGS_empty.o += $(DISABLE_LTO)
hostprogs-y := modpost mk_elfconfig
always := $(hostprogs-y) empty.o
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 9abcdf2..3dda774 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -936,6 +936,7 @@ static const char *const head_sections[] = { ".head.text*", NULL };
static const char *const linker_symbols[] =
{ "__init_begin", "_sinittext", "_einittext", NULL };
static const char *const optim_symbols[] = { "*.constprop.*", NULL };
+static const char *const cfi_symbols[] = { "*.cfi", NULL };
enum mismatch {
TEXT_TO_ANY_INIT,
@@ -1165,6 +1166,17 @@ static const struct sectioncheck *section_mismatch(
* whitelisting, which relies on pattern-matching against symbol
* names to work. (One situation where gcc can autogenerate ELF
* local symbols is when "-fsection-anchors" is used.)
+ *
+ * Pattern 7:
+ * With CONFIG_CFI_CLANG, clang appends .cfi to all indirectly called
+ * functions and creates a function stub with the original name. This
+ * stub is always placed in .text, even if the actual function with the
+ * .cfi postfix is in .init.text or .exit.text.
+ * This pattern is identified by
+ * tosec = init or exit section
+ * fromsec = text section
+ * tosym = *.cfi
+ *
**/
static int secref_whitelist(const struct sectioncheck *mismatch,
const char *fromsec, const char *fromsym,
@@ -1207,6 +1219,12 @@ static int secref_whitelist(const struct sectioncheck *mismatch,
if (strstarts(fromsym, ".L"))
return 0;
+ /* Check for pattern 7 */
+ if (match(fromsec, text_sections) &&
+ match(tosec, init_exit_sections) &&
+ match(tosym, cfi_symbols))
+ return 0;
+
return 1;
}
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 9972141..347f706 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -370,7 +370,8 @@ is_mcounted_section_name(char const *const txtname)
strcmp(".softirqentry.text", txtname) == 0 ||
strcmp(".kprobes.text", txtname) == 0 ||
strcmp(".cpuidle.text", txtname) == 0 ||
- strcmp(".text.unlikely", txtname) == 0;
+ (strncmp(".text.", txtname, 6) == 0 &&
+ strcmp(".text..ftrace", txtname) != 0);
}
/* 32 bit and 64 bit are very similar */
diff --git a/security/Kconfig b/security/Kconfig
index 32f36b4..80a2934 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -18,6 +18,15 @@
If you are unsure how to answer this question, answer N.
+config SECURITY_PERF_EVENTS_RESTRICT
+ bool "Restrict unprivileged use of performance events"
+ depends on PERF_EVENTS
+ help
+ If you say Y here, the kernel.perf_event_paranoid sysctl
+ will be set to 3 by default, and no unprivileged use of the
+ perf_event_open syscall will be permitted unless it is
+ changed.
+
config SECURITY
bool "Enable different security models"
depends on SYSFS
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 02cc952..1d3b8ab 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -656,11 +656,11 @@ static const struct kernel_param_ops param_ops_aalockpolicy = {
.get = param_get_aalockpolicy
};
-static int param_set_audit(const char *val, struct kernel_param *kp);
-static int param_get_audit(char *buffer, struct kernel_param *kp);
+static int param_set_audit(const char *val, const struct kernel_param *kp);
+static int param_get_audit(char *buffer, const struct kernel_param *kp);
-static int param_set_mode(const char *val, struct kernel_param *kp);
-static int param_get_mode(char *buffer, struct kernel_param *kp);
+static int param_set_mode(const char *val, const struct kernel_param *kp);
+static int param_get_mode(char *buffer, const struct kernel_param *kp);
/* Flag values, also controllable via /sys/module/apparmor/parameters
* We define special types as we want to do additional mediation.
@@ -774,7 +774,7 @@ static int param_get_aauint(char *buffer, const struct kernel_param *kp)
return param_get_uint(buffer, kp);
}
-static int param_get_audit(char *buffer, struct kernel_param *kp)
+static int param_get_audit(char *buffer, const struct kernel_param *kp)
{
if (!policy_view_capable())
return -EPERM;
@@ -785,7 +785,7 @@ static int param_get_audit(char *buffer, struct kernel_param *kp)
return sprintf(buffer, "%s", audit_mode_names[aa_g_audit]);
}
-static int param_set_audit(const char *val, struct kernel_param *kp)
+static int param_set_audit(const char *val, const struct kernel_param *kp)
{
int i;
if (!policy_admin_capable())
@@ -807,7 +807,7 @@ static int param_set_audit(const char *val, struct kernel_param *kp)
return -EINVAL;
}
-static int param_get_mode(char *buffer, struct kernel_param *kp)
+static int param_get_mode(char *buffer, const struct kernel_param *kp)
{
if (!policy_admin_capable())
return -EPERM;
@@ -818,7 +818,7 @@ static int param_get_mode(char *buffer, struct kernel_param *kp)
return sprintf(buffer, "%s", aa_profile_mode_names[aa_g_profile_mode]);
}
-static int param_set_mode(const char *val, struct kernel_param *kp)
+static int param_set_mode(const char *val, const struct kernel_param *kp)
{
int i;
if (!policy_admin_capable())
diff --git a/security/commoncap.c b/security/commoncap.c
index b86aca8..7a30e4a 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -31,6 +31,10 @@
#include <linux/binfmts.h>
#include <linux/personality.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+#endif
+
/*
* If a non-root user executes a setuid-root binary in
* !secure(SECURE_NOROOT) mode, then we raise capabilities.
@@ -54,7 +58,7 @@ static void warn_setuid_and_fcaps_mixed(const char *fname)
}
/**
- * cap_capable - Determine whether a task has a particular effective capability
+ * __cap_capable - Determine whether a task has a particular effective capability
* @cred: The credentials to use
* @ns: The user namespace in which we need the capability
* @cap: The capability to check for
@@ -68,7 +72,7 @@ static void warn_setuid_and_fcaps_mixed(const char *fname)
* cap_has_capability() returns 0 when a task has a capability, but the
* kernel's capable() and has_capability() returns 1 for this case.
*/
-int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
+int __cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
int cap, int audit)
{
struct user_namespace *ns = targ_ns;
@@ -103,6 +107,27 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
/* We never get here */
}
+int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
+ int cap, int audit)
+{
+ int ret = __cap_capable(cred, targ_ns, cap, audit);
+
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+ if (ret != 0 && cap == CAP_NET_RAW && in_egroup_p(AID_NET_RAW)) {
+ printk("Process %s granted CAP_NET_RAW from Android group net_raw.\n", current->comm);
+ printk(" Please update the .rc file to explictly set 'capabilities NET_RAW'\n");
+ printk(" Implicit grants are deprecated and will be removed in the future.\n");
+ return 0;
+ }
+ if (ret != 0 && cap == CAP_NET_ADMIN && in_egroup_p(AID_NET_ADMIN)) {
+ printk("Process %s granted CAP_NET_ADMIN from Android group net_admin.\n", current->comm);
+ printk(" Please update the .rc file to explictly set 'capabilities NET_ADMIN'\n");
+ printk(" Implicit grants are deprecated and will be removed in the future.\n");
+ return 0;
+ }
+#endif
+ return ret;
+}
/**
* cap_settime - Determine whether the current process may set the system clock
* @ts: The time to set
diff --git a/security/inode.c b/security/inode.c
index c83db05..b4531f2 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -100,7 +100,7 @@ struct dentry *securityfs_create_file(const char *name, umode_t mode,
dir = d_inode(parent);
inode_lock(dir);
- dentry = lookup_one_len(name, parent, strlen(name));
+ dentry = lookup_one_len2(name, mount, parent, strlen(name));
if (IS_ERR(dentry))
goto out;
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 531ed2e..893af4c 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -55,7 +55,7 @@ static ssize_t mpi_from_key(key_serial_t keyid, size_t maxlen, MPI *mpi)
if (status == 0) {
const struct user_key_payload *payload;
- payload = user_key_payload(key);
+ payload = user_key_payload_locked(key);
if (maxlen == 0) {
*mpi = NULL;
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index ead2fd6..1f3d600 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -313,7 +313,7 @@ static struct key *request_user_key(const char *master_desc, const u8 **master_k
goto error;
down_read(&ukey->sem);
- upayload = user_key_payload(ukey);
+ upayload = user_key_payload_locked(ukey);
if (!upayload) {
/* key was revoked before we acquired its semaphore */
up_read(&ukey->sem);
@@ -933,7 +933,7 @@ static long encrypted_read(const struct key *key, char __user *buffer,
size_t asciiblob_len;
int ret;
- epayload = rcu_dereference_key(key);
+ epayload = dereference_key_locked(key);
/* returns the hex encoded iv, encrypted-data, and hmac as ascii */
asciiblob_len = epayload->datablob_len + ivsize + 1
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 4ba2f6b..e0fcb17 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1139,12 +1139,12 @@ static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
static long trusted_read(const struct key *key, char __user *buffer,
size_t buflen)
{
- struct trusted_key_payload *p;
+ const struct trusted_key_payload *p;
char *ascii_buf;
char *bufp;
int i;
- p = rcu_dereference_key(key);
+ p = dereference_key_locked(key);
if (!p)
return -EINVAL;
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 3dc2607..b4c170a 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -107,7 +107,7 @@ int user_update(struct key *key, struct key_preparsed_payload *prep)
/* attach the new data, displacing the old */
key->expiry = prep->expiry;
if (key_is_positive(key))
- zap = rcu_dereference_key(key);
+ zap = dereference_key_locked(key);
rcu_assign_keypointer(key, prep->payload.data[0]);
prep->payload.data[0] = NULL;
@@ -123,7 +123,7 @@ EXPORT_SYMBOL_GPL(user_update);
*/
void user_revoke(struct key *key)
{
- struct user_key_payload *upayload = key->payload.data[0];
+ struct user_key_payload *upayload = user_key_payload_locked(key);
/* clear the quota */
key_payload_reserve(key, 0);
@@ -169,7 +169,7 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen)
const struct user_key_payload *upayload;
long ret;
- upayload = user_key_payload(key);
+ upayload = user_key_payload_locked(key);
ret = upayload->datalen;
/* we can return the data as is */
diff --git a/security/security.c b/security/security.c
index 112df16..de6ebf8 100644
--- a/security/security.c
+++ b/security/security.c
@@ -11,6 +11,7 @@
* (at your option) any later version.
*/
+#include <linux/bpf.h>
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/module.h>
@@ -508,6 +509,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
return 0;
return call_int_hook(path_chown, 0, path, uid, gid);
}
+EXPORT_SYMBOL(security_path_chown);
int security_path_chroot(const struct path *path)
{
@@ -1596,6 +1598,37 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule,
}
#endif /* CONFIG_AUDIT */
+#ifdef CONFIG_BPF_SYSCALL
+int security_bpf(int cmd, union bpf_attr *attr, unsigned int size)
+{
+ return call_int_hook(bpf, 0, cmd, attr, size);
+}
+int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+ return call_int_hook(bpf_map, 0, map, fmode);
+}
+int security_bpf_prog(struct bpf_prog *prog)
+{
+ return call_int_hook(bpf_prog, 0, prog);
+}
+int security_bpf_map_alloc(struct bpf_map *map)
+{
+ return call_int_hook(bpf_map_alloc_security, 0, map);
+}
+int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+ return call_int_hook(bpf_prog_alloc_security, 0, aux);
+}
+void security_bpf_map_free(struct bpf_map *map)
+{
+ call_void_hook(bpf_map_free_security, map);
+}
+void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+ call_void_hook(bpf_prog_free_security, aux);
+}
+#endif /* CONFIG_BPF_SYSCALL */
+
struct security_hook_heads security_hook_heads = {
.binder_set_context_mgr =
LIST_HEAD_INIT(security_hook_heads.binder_set_context_mgr),
@@ -1947,4 +1980,20 @@ struct security_hook_heads security_hook_heads = {
.audit_rule_free =
LIST_HEAD_INIT(security_hook_heads.audit_rule_free),
#endif /* CONFIG_AUDIT */
+#ifdef CONFIG_BPF_SYSCALL
+ .bpf =
+ LIST_HEAD_INIT(security_hook_heads.bpf),
+ .bpf_map =
+ LIST_HEAD_INIT(security_hook_heads.bpf_map),
+ .bpf_prog =
+ LIST_HEAD_INIT(security_hook_heads.bpf_prog),
+ .bpf_map_alloc_security =
+ LIST_HEAD_INIT(security_hook_heads.bpf_map_alloc_security),
+ .bpf_map_free_security =
+ LIST_HEAD_INIT(security_hook_heads.bpf_map_free_security),
+ .bpf_prog_alloc_security =
+ LIST_HEAD_INIT(security_hook_heads.bpf_prog_alloc_security),
+ .bpf_prog_free_security =
+ LIST_HEAD_INIT(security_hook_heads.bpf_prog_free_security),
+#endif /* CONFIG_BPF_SYSCALL */
};
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a2b63a6..e231b9f 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -83,6 +83,7 @@
#include <linux/export.h>
#include <linux/msg.h>
#include <linux/shm.h>
+#include <linux/bpf.h>
#include "avc.h"
#include "objsec.h"
@@ -473,6 +474,7 @@ static int selinux_is_genfs_special_handling(struct super_block *sb)
return !strcmp(sb->s_type->name, "sysfs") ||
!strcmp(sb->s_type->name, "pstore") ||
!strcmp(sb->s_type->name, "debugfs") ||
+ !strcmp(sb->s_type->name, "tracefs") ||
!strcmp(sb->s_type->name, "rootfs");
}
@@ -819,6 +821,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
sbsec->flags |= SE_SBPROC | SE_SBGENFS;
if (!strcmp(sb->s_type->name, "debugfs") ||
+ !strcmp(sb->s_type->name, "tracefs") ||
!strcmp(sb->s_type->name, "sysfs") ||
!strcmp(sb->s_type->name, "pstore"))
sbsec->flags |= SE_SBGENFS;
@@ -1767,6 +1770,10 @@ static inline int file_path_has_perm(const struct cred *cred,
return inode_has_perm(cred, file_inode(file), av, &ad);
}
+#ifdef CONFIG_BPF_SYSCALL
+static int bpf_fd_pass(struct file *file, u32 sid);
+#endif
+
/* Check whether a task can use an open file descriptor to
access an inode in a given way. Check access to the
descriptor itself, and then use dentry_has_perm to
@@ -1797,6 +1804,12 @@ static int file_has_perm(const struct cred *cred,
goto out;
}
+#ifdef CONFIG_BPF_SYSCALL
+ rc = bpf_fd_pass(file, cred_sid(cred));
+ if (rc)
+ return rc;
+#endif
+
/* av is zero if only checking access to the descriptor. */
rc = 0;
if (av)
@@ -2126,6 +2139,12 @@ static int selinux_binder_transfer_file(struct task_struct *from,
return rc;
}
+#ifdef CONFIG_BPF_SYSCALL
+ rc = bpf_fd_pass(file, sid);
+ if (rc)
+ return rc;
+#endif
+
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
@@ -6122,6 +6141,139 @@ static int selinux_key_getsecurity(struct key *key, char **_buffer)
#endif
+#ifdef CONFIG_BPF_SYSCALL
+static int selinux_bpf(int cmd, union bpf_attr *attr,
+ unsigned int size)
+{
+ u32 sid = current_sid();
+ int ret;
+
+ switch (cmd) {
+ case BPF_MAP_CREATE:
+ ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE,
+ NULL);
+ break;
+ case BPF_PROG_LOAD:
+ ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD,
+ NULL);
+ break;
+ default:
+ ret = 0;
+ break;
+ }
+
+ return ret;
+}
+
+static u32 bpf_map_fmode_to_av(fmode_t fmode)
+{
+ u32 av = 0;
+
+ if (fmode & FMODE_READ)
+ av |= BPF__MAP_READ;
+ if (fmode & FMODE_WRITE)
+ av |= BPF__MAP_WRITE;
+ return av;
+}
+
+/* This function will check the file pass through unix socket or binder to see
+ * if it is a bpf related object. And apply correspinding checks on the bpf
+ * object based on the type. The bpf maps and programs, not like other files and
+ * socket, are using a shared anonymous inode inside the kernel as their inode.
+ * So checking that inode cannot identify if the process have privilege to
+ * access the bpf object and that's why we have to add this additional check in
+ * selinux_file_receive and selinux_binder_transfer_files.
+ */
+static int bpf_fd_pass(struct file *file, u32 sid)
+{
+ struct bpf_security_struct *bpfsec;
+ struct bpf_prog *prog;
+ struct bpf_map *map;
+ int ret;
+
+ if (file->f_op == &bpf_map_fops) {
+ map = file->private_data;
+ bpfsec = map->security;
+ ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+ bpf_map_fmode_to_av(file->f_mode), NULL);
+ if (ret)
+ return ret;
+ } else if (file->f_op == &bpf_prog_fops) {
+ prog = file->private_data;
+ bpfsec = prog->aux->security;
+ ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+ BPF__PROG_RUN, NULL);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+ u32 sid = current_sid();
+ struct bpf_security_struct *bpfsec;
+
+ bpfsec = map->security;
+ return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+ bpf_map_fmode_to_av(fmode), NULL);
+}
+
+static int selinux_bpf_prog(struct bpf_prog *prog)
+{
+ u32 sid = current_sid();
+ struct bpf_security_struct *bpfsec;
+
+ bpfsec = prog->aux->security;
+ return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+ BPF__PROG_RUN, NULL);
+}
+
+static int selinux_bpf_map_alloc(struct bpf_map *map)
+{
+ struct bpf_security_struct *bpfsec;
+
+ bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+ if (!bpfsec)
+ return -ENOMEM;
+
+ bpfsec->sid = current_sid();
+ map->security = bpfsec;
+
+ return 0;
+}
+
+static void selinux_bpf_map_free(struct bpf_map *map)
+{
+ struct bpf_security_struct *bpfsec = map->security;
+
+ map->security = NULL;
+ kfree(bpfsec);
+}
+
+static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+ struct bpf_security_struct *bpfsec;
+
+ bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+ if (!bpfsec)
+ return -ENOMEM;
+
+ bpfsec->sid = current_sid();
+ aux->security = bpfsec;
+
+ return 0;
+}
+
+static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+ struct bpf_security_struct *bpfsec = aux->security;
+
+ aux->security = NULL;
+ kfree(bpfsec);
+}
+#endif
+
static struct security_hook_list selinux_hooks[] = {
LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr),
LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction),
@@ -6336,6 +6488,16 @@ static struct security_hook_list selinux_hooks[] = {
LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match),
LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free),
#endif
+
+#ifdef CONFIG_BPF_SYSCALL
+ LSM_HOOK_INIT(bpf, selinux_bpf),
+ LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
+ LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
+ LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
+ LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
+ LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
+ LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
+#endif
};
static __init int selinux_init(void)
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 1f1f4b2..1764b22 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -105,7 +105,7 @@ struct security_class_mapping secclass_map[] = {
{ COMMON_IPC_PERMS, NULL } },
{ "netlink_route_socket",
{ COMMON_SOCK_PERMS,
- "nlmsg_read", "nlmsg_write", NULL } },
+ "nlmsg_read", "nlmsg_write", "nlmsg_readpriv", NULL } },
{ "netlink_tcpdiag_socket",
{ COMMON_SOCK_PERMS,
"nlmsg_read", "nlmsg_write", NULL } },
@@ -165,5 +165,7 @@ struct security_class_mapping secclass_map[] = {
{ COMMON_CAP_PERMS, NULL } },
{ "cap2_userns",
{ COMMON_CAP2_PERMS, NULL } },
+ { "bpf",
+ {"map_create", "map_read", "map_write", "prog_load", "prog_run"} },
{ NULL }
};
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index c21e135..43535cd 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -128,6 +128,10 @@ struct key_security_struct {
u32 sid; /* SID of key */
};
+struct bpf_security_struct {
+ u32 sid; /*SID of bpf obj creater*/
+};
+
extern unsigned int selinux_checkreqprot;
#endif /* _SELINUX_OBJSEC_H_ */
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 308a286..2775170 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -75,6 +75,7 @@ enum {
};
#define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1)
+extern int selinux_android_netlink_route;
extern int selinux_policycap_netpeer;
extern int selinux_policycap_openperm;
extern int selinux_policycap_alwaysnetwork;
@@ -263,6 +264,7 @@ extern struct vfsmount *selinuxfs_mount;
extern void selnl_notify_setenforce(int val);
extern void selnl_notify_policyload(u32 seqno);
extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm);
+extern void selinux_nlmsg_init(void);
#endif /* _SELINUX_SECURITY_H_ */
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2ca9cde..697785c 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -193,3 +193,27 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
return err;
}
+
+static void nlmsg_set_getlink_perm(u32 perm)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nlmsg_route_perms); i++) {
+ if (nlmsg_route_perms[i].nlmsg_type == RTM_GETLINK) {
+ nlmsg_route_perms[i].perm = perm;
+ break;
+ }
+ }
+}
+
+/**
+ * Use nlmsg_readpriv as the permission for RTM_GETLINK messages if the
+ * netlink_route_getlink policy capability is set. Otherwise use nlmsg_read.
+ */
+void selinux_nlmsg_init(void)
+{
+ if (selinux_android_netlink_route)
+ nlmsg_set_getlink_perm(NETLINK_ROUTE_SOCKET__NLMSG_READPRIV);
+ else
+ nlmsg_set_getlink_perm(NETLINK_ROUTE_SOCKET__NLMSG_READ);
+}
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index af9cc83..62518b0 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -2332,6 +2332,10 @@ int policydb_read(struct policydb *p, void *fp)
p->reject_unknown = !!(le32_to_cpu(buf[1]) & REJECT_UNKNOWN);
p->allow_unknown = !!(le32_to_cpu(buf[1]) & ALLOW_UNKNOWN);
+ if ((le32_to_cpu(buf[1]) & POLICYDB_CONFIG_ANDROID_NETLINK_ROUTE)) {
+ p->android_netlink_route = 1;
+ }
+
if (p->policyvers >= POLICYDB_VERSION_POLCAP) {
rc = ebitmap_read(&p->policycaps, fp);
if (rc)
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
index 725d594..0d511cf 100644
--- a/security/selinux/ss/policydb.h
+++ b/security/selinux/ss/policydb.h
@@ -227,6 +227,7 @@ struct genfs {
/* The policy database */
struct policydb {
int mls_enabled;
+ int android_netlink_route;
/* symbol tables */
struct symtab symtab[SYM_NUM];
@@ -313,6 +314,7 @@ extern int policydb_write(struct policydb *p, void *fp);
#define PERM_SYMTAB_SIZE 32
#define POLICYDB_CONFIG_MLS 1
+#define POLICYDB_CONFIG_ANDROID_NETLINK_ROUTE (1 << 31)
/* the config flags related to unknown classes/perms are bits 2 and 3 */
#define REJECT_UNKNOWN 0x00000002
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 6ca2978..14bbea8 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -70,6 +70,7 @@
#include "ebitmap.h"
#include "audit.h"
+int selinux_android_netlink_route;
int selinux_policycap_netpeer;
int selinux_policycap_openperm;
int selinux_policycap_alwaysnetwork;
@@ -1991,6 +1992,9 @@ static void security_load_policycaps(void)
POLICYDB_CAPABILITY_OPENPERM);
selinux_policycap_alwaysnetwork = ebitmap_get_bit(&policydb.policycaps,
POLICYDB_CAPABILITY_ALWAYSNETWORK);
+
+ selinux_android_netlink_route = policydb.android_netlink_route;
+ selinux_nlmsg_init();
}
static int security_preserve_bools(struct policydb *p);
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 34df10a..ba94989 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -202,6 +202,8 @@ static void print_delayacct(struct taskstats *t)
"SWAP %15s%15s%15s\n"
" %15llu%15llu%15llums\n"
"RECLAIM %12s%15s%15s\n"
+ " %15llu%15llu%15llums\n"
+ "THRASHING%12s%15s%15s\n"
" %15llu%15llu%15llums\n",
"count", "real total", "virtual total",
"delay total", "delay average",
@@ -221,7 +223,11 @@ static void print_delayacct(struct taskstats *t)
"count", "delay total", "delay average",
(unsigned long long)t->freepages_count,
(unsigned long long)t->freepages_delay_total,
- average_ms(t->freepages_delay_total, t->freepages_count));
+ average_ms(t->freepages_delay_total, t->freepages_count),
+ "count", "delay total", "delay average",
+ (unsigned long long)t->thrashing_count,
+ (unsigned long long)t->thrashing_delay_total,
+ average_ms(t->thrashing_delay_total, t->thrashing_count));
}
static void task_context_switch_counts(struct taskstats *t)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f09c70b..a339bea 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,6 +73,8 @@ enum bpf_cmd {
BPF_PROG_LOAD,
BPF_OBJ_PIN,
BPF_OBJ_GET,
+ BPF_PROG_ATTACH,
+ BPF_PROG_DETACH,
};
enum bpf_map_type {
@@ -96,8 +98,23 @@ enum bpf_prog_type {
BPF_PROG_TYPE_TRACEPOINT,
BPF_PROG_TYPE_XDP,
BPF_PROG_TYPE_PERF_EVENT,
+ BPF_PROG_TYPE_CGROUP_SKB,
};
+enum bpf_attach_type {
+ BPF_CGROUP_INET_INGRESS,
+ BPF_CGROUP_INET_EGRESS,
+ __MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -107,6 +124,10 @@ enum bpf_prog_type {
#define BPF_F_NO_PREALLOC (1U << 0)
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY (1U << 3)
+#define BPF_F_WRONLY (1U << 4)
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
@@ -140,6 +161,14 @@ union bpf_attr {
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
+ __u32 file_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ __u32 target_fd; /* container object to attach to */
+ __u32 attach_bpf_fd; /* eBPF program to attach */
+ __u32 attach_type;
+ __u32 attach_flags;
};
} __attribute__((aligned(8)));
@@ -426,6 +455,67 @@ enum bpf_func_id {
*/
BPF_FUNC_set_hash_invalid,
+ /**
+ * int bpf_get_numa_node_id()
+ * Return: Id of current NUMA node.
+ */
+ BPF_FUNC_get_numa_node_id,
+
+ /**
+ * int bpf_skb_change_head()
+ * Grows headroom of skb and adjusts MAC header offset accordingly.
+ * Will extends/reallocae as required automatically.
+ * May change skb data pointer and will thus invalidate any check
+ * performed for direct packet access.
+ * @skb: pointer to skb
+ * @len: length of header to be pushed in front
+ * @flags: Flags (unused for now)
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_head,
+
+ /**
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ * Adjust the xdp_md.data by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data
+ * Return: 0 on success or negative on error
+ */
+ BPF_FUNC_xdp_adjust_head,
+
+ /**
+ * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * Copy a NUL terminated string from unsafe address. In case the string
+ * length is smaller than size, the target is not padded with further NUL
+ * bytes. In case the string length is larger than size, just count-1
+ * bytes are copied and the last byte is set to NUL.
+ * @dst: destination address
+ * @size: maximum number of bytes to copy, including the trailing NUL
+ * @unsafe_ptr: unsafe address
+ * Return:
+ * > 0 length of the string including the trailing NUL on success
+ * < 0 error
+ */
+ BPF_FUNC_probe_read_str,
+
+ /**
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ * Get the cookie for the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ * field is missing inside sk_buff
+ */
+ BPF_FUNC_get_socket_cookie,
+
+ /**
+ * u32 bpf_get_socket_uid(skb)
+ * Get the owner uid of the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: uid of the socket owner on success or 0 if the socket pointer
+ * inside sk_buff is NULL
+ */
+ BPF_FUNC_get_socket_uid,
+
__BPF_FUNC_MAX_ID,
};
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index b04000a..2b65efd 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -4,7 +4,11 @@
enum {
HW_BREAKPOINT_LEN_1 = 1,
HW_BREAKPOINT_LEN_2 = 2,
+ HW_BREAKPOINT_LEN_3 = 3,
HW_BREAKPOINT_LEN_4 = 4,
+ HW_BREAKPOINT_LEN_5 = 5,
+ HW_BREAKPOINT_LEN_6 = 6,
+ HW_BREAKPOINT_LEN_7 = 7,
HW_BREAKPOINT_LEN_8 = 8,
};
diff --git a/verity_dev_keys.x509 b/verity_dev_keys.x509
new file mode 100644
index 0000000..86399c3
--- /dev/null
+++ b/verity_dev_keys.x509
@@ -0,0 +1,24 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----