Merge 4.9.83 into android-4.9
Changes in 4.9.83
scsi: smartpqi: allow static build ("built-in")
drm/radeon: Add dpm quirk for Jet PRO (v2)
drm/radeon: adjust tested variable
rtc-opal: Fix handling of firmware error codes, prevent busy loops
mbcache: initialize entry->e_referenced in mb_cache_entry_create()
jbd2: fix sphinx kernel-doc build warnings
ext4: fix a race in the ext4 shutdown path
ext4: save error to disk in __ext4_grp_locked_error()
ext4: correct documentation for grpid mount option
mm: hide a #warning for COMPILE_TEST
mm: Fix memory size alignment in devm_memremap_pages_release()
MIPS: Fix typo BIG_ENDIAN to CPU_BIG_ENDIAN
PCI: keystone: Fix interrupt-controller-node lookup
video: fbdev: atmel_lcdfb: fix display-timings lookup
console/dummy: leave .con_font_get set to NULL
rtlwifi: rtl8821ae: Fix connection lost problem correctly
target/iscsi: avoid NULL dereference in CHAP auth error path
Btrfs: fix deadlock in run_delalloc_nocow
Btrfs: fix crash due to not cleaning up tree log block's dirty bits
Btrfs: fix extent state leak from tree log
Btrfs: fix btrfs_evict_inode to handle abnormal inodes correctly
Btrfs: fix unexpected -EEXIST when creating new inode
9p/trans_virtio: discard zero-length reply
mtd: nand: vf610: set correct ooblayout
ALSA: hda - Fix headset mic detection problem for two Dell machines
ALSA: usb-audio: Fix UAC2 get_ctl request with a RANGE attribute
ALSA: hda/realtek - Enable Thinkpad Dock device for ALC298 platform
ALSA: hda/realtek: PCI quirk for Fujitsu U7x7
ALSA: usb-audio: add implicit fb quirk for Behringer UFX1204
ALSA: seq: Fix racy pool initializations
mvpp2: fix multicast address filter
usb: Move USB_UHCI_BIG_ENDIAN_* out of USB_SUPPORT
dm: correctly handle chained bios in dec_pending()
powerpc: fix build errors in stable tree
IB/qib: Fix comparison error with qperf compare/swap test
IB/mlx4: Fix incorrectly releasing steerable UD QPs when have only ETH ports
kselftest: fix OOM in memory compaction test
RDMA/rxe: Fix a race condition related to the QP error state
cpufreq: powernv: Dont assume distinct pstate values for nominal and pmin
PM / devfreq: Propagate error from devfreq_add_device()
ocfs2: try a blocking lock before return AOP_TRUNCATED_PAGE
s390: fix handling of -1 in set{,fs}[gu]id16 syscalls
arm64: dts: msm8916: Correct ipc references for smsm
ARM: lpc3250: fix uda1380 gpio numbers
ARM: dts: STi: Add gpio polarity for "hdmi,hpd-gpio" property
ARM: dts: nomadik: add interrupt-parent for clcd
arm: spear600: Add missing interrupt-parent of rtc
arm: spear13xx: Fix dmas cells
arm: spear13xx: Fix spics gpio controller's warning
x86/entry/64/compat: Clear registers for compat syscalls, to reduce speculation attack surface
compiler-gcc.h: Introduce __optimize function attribute
x86/speculation: Update Speculation Control microcode blacklist
x86/speculation: Correct Speculation Control microcode blacklist again
KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by always inlining iterator helper methods
X86/nVMX: Properly set spec_ctrl and pred_cmd before merging MSRs
x86/speculation: Clean up various Spectre related details
selftests/x86/pkeys: Remove unused functions
selftests/x86: Do not rely on "int $0x80" in test_mremap_vdso.c
selftests/x86: Do not rely on "int $0x80" in single_step_syscall.c
x86/speculation: Fix up array_index_nospec_mask() asm constraint
nospec: Move array_index_nospec() parameter checking into separate macro
x86/speculation: Add <asm/msr-index.h> dependency
selftests/x86/mpx: Fix incorrect bounds with old _sigfault
x86/cpu: Rename cpu_data.x86_mask to cpu_data.x86_stepping
x86/spectre: Fix an error message
x86/cpu: Change type of x86_cache_size variable to unsigned int
x86: fix build warnign with 32-bit PAE
vfs: don't do RCU lookup of empty pathnames
ARM: dts: exynos: fix RTC interrupt for exynos5410
ARM: pxa/tosa-bt: add MODULE_LICENSE tag
arm64: dts: msm8916: Add missing #phy-cells
ARM: dts: s5pv210: add interrupt-parent for ohci
arm: dts: mt2701: Add reset-cells
ARM: dts: Delete bogus reference to the charlcd
media: r820t: fix r820t_write_reg for KASAN
Linux 4.9.83
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
diff --git a/.gitignore b/.gitignore
index c2ed4ec..4105cfb 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,6 +33,7 @@
*.lzo
*.patch
*.gcno
+*.ll
modules.builtin
Module.symvers
*.dwo
@@ -114,3 +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/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..2baed11 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -51,12 +51,33 @@
Controls the dirty page count condition for the in-place-update
policies.
+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>/max_victim_search
Date: January 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
@@ -93,6 +114,12 @@
Description:
Controls the idle timing.
+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
Contact: "Chao Yu" <chao2.yu@samsung.com>
@@ -112,3 +139,50 @@
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
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/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/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/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..e7fb61e 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -157,6 +157,20 @@
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.
================================================================================
DEBUGFS ENTRIES
@@ -202,6 +216,15 @@
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/proc.txt b/Documentation/filesystems/proc.txt
index 74329fd..6e027ae 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
@@ -486,6 +489,9 @@
be present in all further kernel releases. Things get changed, the flags may
be vanished or the reverse -- new added.
+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/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 466c039..29a998d 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
@@ -1035,6 +1036,11 @@
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.
@@ -1903,6 +1909,12 @@
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]
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3db8c67..f9154c5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -603,6 +603,16 @@
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
@@ -1442,11 +1452,20 @@
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.
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/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/Kbuild b/Kbuild
index 3d0ae15..94c7527 100644
--- a/Kbuild
+++ b/Kbuild
@@ -7,31 +7,6 @@
# 4) Check for missing system calls
# 5) Generate constants.py (may need bounds.h)
-# Default sed regexp - multiline due to syntax constraints
-define sed-y
- "/^->/{s:->#\(.*\):/* \1 */:; \
- s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:->::; p;}"
-endef
-
-# Use filechk to avoid rebuilds when a header changes, but the resulting file
-# does not
-define filechk_offsets
- (set -e; \
- echo "#ifndef $2"; \
- echo "#define $2"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y); \
- echo ""; \
- echo "#endif" )
-endef
-
#####
# 1) Generate bounds.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 63cefa6..a419303 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9010,6 +9010,11 @@
F: drivers/oprofile/
F: include/linux/oprofile.h
+OP-TEE DRIVER
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: drivers/tee/optee/
+
ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
M: Mark Fasheh <mfasheh@versity.com>
M: Joel Becker <jlbec@evilplan.org>
@@ -10655,6 +10660,14 @@
F: include/linux/stm.h
F: include/uapi/linux/stm.h
+TEE SUBSYSTEM
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: include/linux/tee_drv.h
+F: include/uapi/linux/tee.h
+F: drivers/tee/
+F: Documentation/tee.txt
+
THUNDERBOLT DRIVER
M: Andreas Noever <andreas.noever@gmail.com>
S: Maintained
diff --git a/Makefile b/Makefile
index cfae9b8..8eed54f 100644
--- a/Makefile
+++ b/Makefile
@@ -301,7 +301,7 @@
HOSTCC = gcc
HOSTCXX = g++
-HOSTCFLAGS = -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89
+HOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89
HOSTCXXFLAGS = -O2
ifeq ($(shell $(HOSTCC) -v 2>&1 | grep -c "clang version"), 1)
@@ -640,7 +640,8 @@
endif
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,)
+KBUILD_CFLAGS += $(call cc-option,-Oz,-Os)
+KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,)
else
ifdef CONFIG_PROFILE_ALL_BRANCHES
KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,)
@@ -700,11 +701,22 @@
KBUILD_CFLAGS += $(stackp-flag)
ifeq ($(cc-name),clang)
+ifneq ($(CROSS_COMPILE),)
+CLANG_TRIPLE ?= $(CROSS_COMPILE)
+CLANG_TARGET := --target=$(notdir $(CLANG_TRIPLE:%-=%))
+GCC_TOOLCHAIN := $(realpath $(dir $(shell which $(LD)))/..)
+endif
+ifneq ($(GCC_TOOLCHAIN),)
+CLANG_GCC_TC := --gcc-toolchain=$(GCC_TOOLCHAIN)
+endif
+KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
+KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+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
@@ -712,6 +724,8 @@
# See modpost pattern 2
KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
else
# These warnings generated too much noise in a regular build.
@@ -1366,6 +1380,8 @@
@echo ' (default: $$(INSTALL_MOD_PATH)/lib/firmware)'
@echo ' dir/ - Build all files in dir and below'
@echo ' dir/file.[ois] - Build specified target only'
+ @echo ' dir/file.ll - Build the LLVM assembly file'
+ @echo ' (requires compiler support for LLVM assembly generation)'
@echo ' dir/file.lst - Build specified mixed source/assembly target only'
@echo ' (requires a recent binutils and recent build (System.map))'
@echo ' dir/file.ko - Build module including final link'
@@ -1550,6 +1566,7 @@
-o -name '*.symtypes' -o -name 'modules.order' \
-o -name modules.builtin -o -name '.tmp_*.o.*' \
-o -name '*.c.[012]*.*' \
+ -o -name '*.ll' \
-o -name '*.gcno' \) -type f -print | xargs rm -f
# Generate tags for editors
@@ -1653,6 +1670,8 @@
$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
%.symtypes: %.c prepare scripts FORCE
$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
+%.ll: %.c prepare scripts FORCE
+ $(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
# Modules
/: prepare scripts FORCE
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 b5d529f..00be82f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1836,6 +1836,15 @@
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"
@@ -1864,6 +1873,21 @@
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 d83f7c3..17dcd94 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1723,6 +1723,14 @@
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 6be9ee1..b53a7b4 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 fc6d541..51fc9fb 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -781,6 +781,8 @@
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 := $(DTB_LIST)
clean-files := *.dtb
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 9353184..ce01364 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -17,3 +17,7 @@
config SHARP_SCOOP
bool
+
+config FIQ_GLUE
+ bool
+ select FIQ
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 27f23b1..04aca89 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -4,6 +4,7 @@
obj-y += firmware.o
+obj-$(CONFIG_FIQ_GLUE) += fiq_glue.o fiq_glue_setup.o
obj-$(CONFIG_ICST) += icst.o
obj-$(CONFIG_SA1111) += sa1111.o
obj-$(CONFIG_DMABOUNCE) += dmabounce.o
diff --git a/arch/arm/common/fiq_glue.S b/arch/arm/common/fiq_glue.S
new file mode 100644
index 0000000..24b42ce
--- /dev/null
+++ b/arch/arm/common/fiq_glue.S
@@ -0,0 +1,118 @@
+/*
+ * 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.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+
+ .global fiq_glue_end
+
+ /* fiq stack: r0-r15,cpsr,spsr of interrupted mode */
+
+ENTRY(fiq_glue)
+ /* store pc, cpsr from previous mode, reserve space for spsr */
+ mrs r12, spsr
+ sub lr, lr, #4
+ subs r10, #1
+ bne nested_fiq
+
+ str r12, [sp, #-8]!
+ str lr, [sp, #-4]!
+
+ /* store r8-r14 from previous mode */
+ sub sp, sp, #(7 * 4)
+ stmia sp, {r8-r14}^
+ nop
+
+ /* store r0-r7 from previous mode */
+ stmfd sp!, {r0-r7}
+
+ /* setup func(data,regs) arguments */
+ mov r0, r9
+ mov r1, sp
+ mov r3, r8
+
+ mov r7, sp
+
+ /* Get sp and lr from non-user modes */
+ and r4, r12, #MODE_MASK
+ cmp r4, #USR_MODE
+ beq fiq_from_usr_mode
+
+ mov r7, sp
+ orr r4, r4, #(PSR_I_BIT | PSR_F_BIT)
+ msr cpsr_c, r4
+ str sp, [r7, #(4 * 13)]
+ str lr, [r7, #(4 * 14)]
+ mrs r5, spsr
+ str r5, [r7, #(4 * 17)]
+
+ cmp r4, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+ /* use fiq stack if we reenter this mode */
+ subne sp, r7, #(4 * 3)
+
+fiq_from_usr_mode:
+ msr cpsr_c, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+ mov r2, sp
+ sub sp, r7, #12
+ stmfd sp!, {r2, ip, lr}
+ /* call func(data,regs) */
+ blx r3
+ ldmfd sp, {r2, ip, lr}
+ mov sp, r2
+
+ /* restore/discard saved state */
+ cmp r4, #USR_MODE
+ beq fiq_from_usr_mode_exit
+
+ msr cpsr_c, r4
+ ldr sp, [r7, #(4 * 13)]
+ ldr lr, [r7, #(4 * 14)]
+ msr spsr_cxsf, r5
+
+fiq_from_usr_mode_exit:
+ msr cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+
+ ldmfd sp!, {r0-r7}
+ ldr lr, [sp, #(4 * 7)]
+ ldr r12, [sp, #(4 * 8)]
+ add sp, sp, #(10 * 4)
+exit_fiq:
+ msr spsr_cxsf, r12
+ add r10, #1
+ cmp r11, #0
+ moveqs pc, lr
+ bx r11 /* jump to custom fiq return function */
+
+nested_fiq:
+ orr r12, r12, #(PSR_F_BIT)
+ b exit_fiq
+
+fiq_glue_end:
+
+ENTRY(fiq_glue_setup) /* func, data, sp, smc call number */
+ stmfd sp!, {r4}
+ mrs r4, cpsr
+ msr cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+ movs r8, r0
+ mov r9, r1
+ mov sp, r2
+ mov r11, r3
+ moveq r10, #0
+ movne r10, #1
+ msr cpsr_c, r4
+ ldmfd sp!, {r4}
+ bx lr
+
diff --git a/arch/arm/common/fiq_glue_setup.c b/arch/arm/common/fiq_glue_setup.c
new file mode 100644
index 0000000..8cb1b61
--- /dev/null
+++ b/arch/arm/common/fiq_glue_setup.c
@@ -0,0 +1,147 @@
+/*
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/fiq.h>
+#include <asm/fiq_glue.h>
+
+extern unsigned char fiq_glue, fiq_glue_end;
+extern void fiq_glue_setup(void *func, void *data, void *sp,
+ fiq_return_handler_t fiq_return_handler);
+
+static struct fiq_handler fiq_debbuger_fiq_handler = {
+ .name = "fiq_glue",
+};
+DEFINE_PER_CPU(void *, fiq_stack);
+static struct fiq_glue_handler *current_handler;
+static fiq_return_handler_t fiq_return_handler;
+static DEFINE_MUTEX(fiq_glue_lock);
+
+static void fiq_glue_setup_helper(void *info)
+{
+ struct fiq_glue_handler *handler = info;
+ fiq_glue_setup(handler->fiq, handler,
+ __get_cpu_var(fiq_stack) + THREAD_START_SP,
+ fiq_return_handler);
+}
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler)
+{
+ int ret;
+ int cpu;
+
+ if (!handler || !handler->fiq)
+ return -EINVAL;
+
+ mutex_lock(&fiq_glue_lock);
+ if (fiq_stack) {
+ ret = -EBUSY;
+ goto err_busy;
+ }
+
+ for_each_possible_cpu(cpu) {
+ void *stack;
+ stack = (void *)__get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+ if (WARN_ON(!stack)) {
+ ret = -ENOMEM;
+ goto err_alloc_fiq_stack;
+ }
+ per_cpu(fiq_stack, cpu) = stack;
+ }
+
+ ret = claim_fiq(&fiq_debbuger_fiq_handler);
+ if (WARN_ON(ret))
+ goto err_claim_fiq;
+
+ current_handler = handler;
+ on_each_cpu(fiq_glue_setup_helper, handler, true);
+ set_fiq_handler(&fiq_glue, &fiq_glue_end - &fiq_glue);
+
+ mutex_unlock(&fiq_glue_lock);
+ return 0;
+
+err_claim_fiq:
+err_alloc_fiq_stack:
+ for_each_possible_cpu(cpu) {
+ __free_pages(per_cpu(fiq_stack, cpu), THREAD_SIZE_ORDER);
+ per_cpu(fiq_stack, cpu) = NULL;
+ }
+err_busy:
+ mutex_unlock(&fiq_glue_lock);
+ return ret;
+}
+
+static void fiq_glue_update_return_handler(void (*fiq_return)(void))
+{
+ fiq_return_handler = fiq_return;
+ if (current_handler)
+ on_each_cpu(fiq_glue_setup_helper, current_handler, true);
+}
+
+int fiq_glue_set_return_handler(void (*fiq_return)(void))
+{
+ int ret;
+
+ mutex_lock(&fiq_glue_lock);
+ if (fiq_return_handler) {
+ ret = -EBUSY;
+ goto err_busy;
+ }
+ fiq_glue_update_return_handler(fiq_return);
+ ret = 0;
+err_busy:
+ mutex_unlock(&fiq_glue_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(fiq_glue_set_return_handler);
+
+int fiq_glue_clear_return_handler(void (*fiq_return)(void))
+{
+ int ret;
+
+ mutex_lock(&fiq_glue_lock);
+ if (WARN_ON(fiq_return_handler != fiq_return)) {
+ ret = -EINVAL;
+ goto err_inval;
+ }
+ fiq_glue_update_return_handler(NULL);
+ ret = 0;
+err_inval:
+ mutex_unlock(&fiq_glue_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(fiq_glue_clear_return_handler);
+
+/**
+ * fiq_glue_resume - Restore fiqs after suspend or low power idle states
+ *
+ * This must be called before calling local_fiq_enable after returning from a
+ * power state where the fiq mode registers were lost. If a driver provided
+ * a resume hook when it registered the handler it will be called.
+ */
+
+void fiq_glue_resume(void)
+{
+ if (!current_handler)
+ return;
+ fiq_glue_setup(current_handler->fiq, current_handler,
+ __get_cpu_var(fiq_stack) + THREAD_START_SP,
+ fiq_return_handler);
+ if (current_handler->resume)
+ current_handler->resume(current_handler);
+}
+
diff --git a/arch/arm/configs/ranchu_defconfig b/arch/arm/configs/ranchu_defconfig
new file mode 100644
index 0000000..49e7bbd
--- /dev/null
+++ b/arch/arm/configs/ranchu_defconfig
@@ -0,0 +1,316 @@
+# 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_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=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_KEYCHORD=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/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..d060641 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 +25,12 @@ 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
+#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/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..c6324b5 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 +90,78 @@ void arch_cpu_idle_enter(void)
void arch_cpu_idle_exit(void)
{
ledtrig_cpu(CPU_LED_IDLE_END);
+ idle_notifier_call_chain(IDLE_END);
+}
+
+/*
+ * 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)) {
+ printk(" ********");
+ } else {
+ printk(" %08x", data);
+ }
+ ++p;
+ }
+ printk("\n");
+ }
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+ mm_segment_t fs;
+
+ fs = get_fs();
+ set_fs(KERNEL_DS);
+ show_data(regs->ARM_pc - nbytes, nbytes * 2, "PC");
+ show_data(regs->ARM_lr - nbytes, nbytes * 2, "LR");
+ show_data(regs->ARM_sp - nbytes, nbytes * 2, "SP");
+ show_data(regs->ARM_ip - nbytes, nbytes * 2, "IP");
+ show_data(regs->ARM_fp - nbytes, nbytes * 2, "FP");
+ show_data(regs->ARM_r0 - nbytes, nbytes * 2, "R0");
+ show_data(regs->ARM_r1 - nbytes, nbytes * 2, "R1");
+ show_data(regs->ARM_r2 - nbytes, nbytes * 2, "R2");
+ show_data(regs->ARM_r3 - nbytes, nbytes * 2, "R3");
+ show_data(regs->ARM_r4 - nbytes, nbytes * 2, "R4");
+ show_data(regs->ARM_r5 - nbytes, nbytes * 2, "R5");
+ show_data(regs->ARM_r6 - nbytes, nbytes * 2, "R6");
+ show_data(regs->ARM_r7 - nbytes, nbytes * 2, "R7");
+ show_data(regs->ARM_r8 - nbytes, nbytes * 2, "R8");
+ show_data(regs->ARM_r9 - nbytes, nbytes * 2, "R9");
+ show_data(regs->ARM_r10 - nbytes, nbytes * 2, "R10");
+ set_fs(fs);
}
void __show_regs(struct pt_regs *regs)
@@ -182,6 +255,8 @@ void __show_regs(struct pt_regs *regs)
printk("Control: %08x%s\n", ctrl, buf);
}
#endif
+
+ show_extra_register_data(regs, 128);
}
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/topology.c b/arch/arm/kernel/topology.c
index ec279d1..df30200 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -42,9 +42,15 @@
*/
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)
{
+#ifdef CONFIG_CPU_FREQ
+ unsigned long max_freq_scale = cpufreq_scale_max_freq_capacity(cpu);
+
+ return per_cpu(cpu_scale, cpu) * max_freq_scale >> SCHED_CAPACITY_SHIFT;
+#else
return per_cpu(cpu_scale, cpu);
+#endif
}
static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
@@ -153,6 +159,8 @@ 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 +168,14 @@ 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 +287,138 @@ 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/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 f7861dc..a9ef54d 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -273,10 +273,10 @@ 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 cf57a77..5702e7d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -733,6 +733,18 @@
However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
4M allocations matching the default size used by generic code.
+config UNMAP_KERNEL_AT_EL0
+ bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
+ default y
+ help
+ Speculation attacks against some high-performance processors can
+ be used to bypass MMU permission checks and leak kernel data to
+ userspace. This can be defended against by unmapping the kernel
+ when running in userspace, mapping it back in on exception entry
+ via a trampoline page in the vector table.
+
+ If unsure, say Y.
+
menuconfig ARMV8_DEPRECATED
bool "Emulate deprecated/obsolete ARMv8 instructions"
depends on COMPAT
@@ -800,6 +812,14 @@
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
@@ -959,6 +979,23 @@
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
@@ -966,6 +1003,7 @@
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
@@ -998,6 +1036,41 @@
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 92110c2..c76311c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -41,9 +41,17 @@
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)
@@ -80,6 +88,10 @@
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 +110,12 @@
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 +142,9 @@
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 1f012c5..2c8cb86 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.gz
+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/ranchu64_defconfig b/arch/arm64/configs/ranchu64_defconfig
new file mode 100644
index 0000000..fc55008
--- /dev/null
+++ b/arch/arm64/configs/ranchu64_defconfig
@@ -0,0 +1,312 @@
+# 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_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=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_KEYCHORD=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/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index c98e7e8..8550408 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -82,7 +82,8 @@
ldr dgb, [x0, #16]
/* load sha1_ce_state::finalize */
- ldr w4, [x0, #:lo12:sha1_ce_offsetof_finalize]
+ ldr_l w4, sha1_ce_offsetof_finalize, x4
+ ldr w4, [x0, x4]
/* load input */
0: ld1 {v8.4s-v11.4s}, [x1], #64
@@ -132,7 +133,8 @@
* the padding is handled by the C code in that case.
*/
cbz x4, 3f
- ldr x4, [x0, #:lo12:sha1_ce_offsetof_count]
+ ldr_l w4, sha1_ce_offsetof_count, x4
+ ldr x4, [x0, x4]
movi v9.2d, #0
mov x8, #0x80000000
movi v10.2d, #0
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index aefda98..ea319c0 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -17,9 +17,6 @@
#include <linux/crypto.h>
#include <linux/module.h>
-#define ASM_EXPORT(sym, val) \
- asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
@@ -32,6 +29,9 @@ struct sha1_ce_state {
asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
int blocks);
+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);
+
static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
@@ -52,11 +52,6 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
- ASM_EXPORT(sha1_ce_offsetof_count,
- offsetof(struct sha1_ce_state, sst.count));
- ASM_EXPORT(sha1_ce_offsetof_finalize,
- offsetof(struct sha1_ce_state, finalize));
-
/*
* Allow the asm code to perform the finalization if there is no
* partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 01cfee0..679c6c0 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -88,7 +88,8 @@
ld1 {dgav.4s, dgbv.4s}, [x0]
/* load sha256_ce_state::finalize */
- ldr w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
+ ldr_l w4, sha256_ce_offsetof_finalize, x4
+ ldr w4, [x0, x4]
/* load input */
0: ld1 {v16.4s-v19.4s}, [x1], #64
@@ -136,7 +137,8 @@
* the padding is handled by the C code in that case.
*/
cbz x4, 3f
- ldr x4, [x0, #:lo12:sha256_ce_offsetof_count]
+ ldr_l w4, sha256_ce_offsetof_count, x4
+ ldr x4, [x0, x4]
movi v17.2d, #0
mov x8, #0x80000000
movi v18.2d, #0
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 7cd5875..0ed9486 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -17,9 +17,6 @@
#include <linux/crypto.h>
#include <linux/module.h>
-#define ASM_EXPORT(sym, val) \
- asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
@@ -32,6 +29,11 @@ struct sha256_ce_state {
asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
int blocks);
+const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
+ sst.count);
+const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
+ finalize);
+
static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
@@ -52,11 +54,6 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
struct sha256_ce_state *sctx = shash_desc_ctx(desc);
bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
- ASM_EXPORT(sha256_ce_offsetof_count,
- offsetof(struct sha256_ce_state, sst.count));
- ASM_EXPORT(sha256_ce_offsetof_finalize,
- offsetof(struct sha256_ce_state, finalize));
-
/*
* Allow the asm code to perform the finalization if there is no
* partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 851290d..e008b76 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -41,6 +41,15 @@
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.
*/
@@ -413,4 +422,11 @@ alternative_endif
movk \reg, :abs_g0_nc:\val
.endm
+/*
+ * Return the current thread_info.
+ */
+ .macro get_thread_info, rd
+ mrs \rd, sp_el0
+ .endm
+
#endif /* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 87b4465..4a4a98a 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -35,6 +35,8 @@
#define ARM64_HYP_OFFSET_LOW 14
#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
-#define ARM64_NCAPS 16
+#define ARM64_UNMAP_KERNEL_AT_EL0 23
+
+#define ARM64_NCAPS 24
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 0bc0b1de..51afac1 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -208,6 +208,12 @@ 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);
+}
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index a9e54aa..6c4f9e8 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>
@@ -54,6 +55,9 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
#define alloc_screen_info(x...) &screen_info
#define free_screen_info(x...)
+/* redeclare as 'hidden' so the compiler will generate relative references */
+extern struct screen_info screen_info __attribute__((__visibility__("hidden")));
+
static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
{
}
@@ -75,7 +79,32 @@ 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
+ * (if different from init_mm).
+ */
+ uaccess_ttbr0_disable();
+ if (current->active_mm != &init_mm)
+ 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/fixmap.h b/arch/arm64/include/asm/fixmap.h
index caf86be..d8e5805 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -51,6 +51,12 @@ enum fixed_addresses {
FIX_EARLYCON_MEM_BASE,
FIX_TEXT_POKE0,
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ FIX_ENTRY_TRAMP_DATA,
+ FIX_ENTRY_TRAMP_TEXT,
+#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
__end_of_permanent_fixed_addresses,
/*
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index f2585cd..85c4a89 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
futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -118,8 +115,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
+ 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"
@@ -134,10 +131,10 @@ 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..77a27af 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
@@ -71,8 +78,16 @@
/*
* Initial memory map attributes.
*/
-#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define SWAPPER_PTE_FLAGS (_SWAPPER_PTE_FLAGS | PTE_NG)
+#define SWAPPER_PMD_FLAGS (_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
+#else
+#define SWAPPER_PTE_FLAGS _SWAPPER_PTE_FLAGS
+#define SWAPPER_PMD_FLAGS _SWAPPER_PMD_FLAGS
+#endif
#if ARM64_SWAPPER_USES_SECTION_MAPS
#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6d22017..ef305f8 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
@@ -270,7 +270,7 @@ 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/memory.h b/arch/arm64/include/asm/memory.h
index 53211a0..30cd697 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -165,6 +165,11 @@ 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.
*/
@@ -205,6 +210,7 @@ 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 8d9fce0..d7750fc 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -16,6 +16,12 @@
#ifndef __ASM_MMU_H
#define __ASM_MMU_H
+
+#define USER_ASID_FLAG (UL(1) << 48)
+#define TTBR_ASID_MASK (UL(0xffff) << 48)
+
+#ifndef __ASSEMBLY__
+
typedef struct {
atomic64_t id;
void *vdso;
@@ -28,6 +34,12 @@ typedef struct {
*/
#define ASID(mm) ((mm)->context.id.counter & 0xffff)
+static inline bool arm64_kernel_unmapped_at_el0(void)
+{
+ return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
+ cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+}
+
extern void paging_init(void);
extern void bootmem_init(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
@@ -37,4 +49,5 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
pgprot_t prot, bool allow_block_mappings);
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
+#endif /* !__ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a501853..6ad61e7 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>
@@ -44,12 +45,19 @@ 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();
}
+static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+ BUG_ON(pgd == swapper_pg_dir);
+ cpu_set_reserved_ttbr0();
+ cpu_do_switch_mm(virt_to_phys(pgd),mm);
+}
+
/*
* TCR.T0SZ value to use when the ID map is active. Usually equals
* TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
@@ -103,7 +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);
}
@@ -113,7 +121,7 @@ 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);
}
/*
@@ -128,7 +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);
@@ -163,21 +171,28 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
}
-/*
- * 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)
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+ struct mm_struct *mm)
+{
+ if (system_uses_ttbr0_pan()) {
+ u64 ttbr;
+ BUG_ON(mm->pgd == swapper_pg_dir);
+ 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 __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.
@@ -190,9 +205,28 @@ 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). Avoid setting the reserved
+ * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+ */
+ if (next != &init_mm)
+ 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/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index eb0c2bd..8df4cb6 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -272,6 +272,7 @@
#define TCR_TG1_4K (UL(2) << TCR_TG1_SHIFT)
#define TCR_TG1_64K (UL(3) << TCR_TG1_SHIFT)
+#define TCR_A1 (UL(1) << 22)
#define TCR_ASID16 (UL(1) << 36)
#define TCR_TBI0 (UL(1) << 37)
#define TCR_HA (UL(1) << 39)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2142c77..84b5283 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -34,8 +34,16 @@
#include <asm/pgtable-types.h>
-#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define PROT_DEFAULT (_PROT_DEFAULT | PTE_NG)
+#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_SECT_NG)
+#else
+#define PROT_DEFAULT _PROT_DEFAULT
+#define PROT_SECT_DEFAULT _PROT_SECT_DEFAULT
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -48,6 +56,7 @@
#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT (_PAGE_DEFAULT & ~PTE_NG)
#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
@@ -55,15 +64,15 @@
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
-#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
+#define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
+#define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
+#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
-#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7acd3c5..7bcd8b9 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))
@@ -692,6 +692,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
/*
* Encode and decode a swap entry:
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 14ad6e4..16cef2e 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -35,12 +35,6 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
#include <asm/memory.h>
-#define cpu_switch_mm(pgd,mm) \
-do { \
- BUG_ON(pgd == swapper_pg_dir); \
- cpu_do_switch_mm(virt_to_phys(pgd),mm); \
-} while (0)
-
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* __ASM_PROCFNS_H */
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/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e9ea5a6..3e34cc6 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -48,6 +48,9 @@ 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 */
};
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index deab523..ad6bd8b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -23,6 +23,7 @@
#include <linux/sched.h>
#include <asm/cputype.h>
+#include <asm/mmu.h>
/*
* Raw TLBI operations.
@@ -42,6 +43,11 @@
#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0)
+#define __tlbi_user(op, arg) do { \
+ if (arm64_kernel_unmapped_at_el0()) \
+ __tlbi(op, (arg) | USER_ASID_FLAG); \
+} while (0)
+
/*
* TLB Management
* ==============
@@ -103,6 +109,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
dsb(ishst);
__tlbi(aside1is, asid);
+ __tlbi_user(aside1is, asid);
dsb(ish);
}
@@ -113,6 +120,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
dsb(ishst);
__tlbi(vale1is, addr);
+ __tlbi_user(vale1is, addr);
dsb(ish);
}
@@ -139,10 +147,13 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
- if (last_level)
+ if (last_level) {
__tlbi(vale1is, addr);
- else
+ __tlbi_user(vale1is, addr);
+ } else {
__tlbi(vae1is, addr);
+ __tlbi_user(vae1is, addr);
+ }
}
dsb(ish);
}
@@ -182,6 +193,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
__tlbi(vae1is, addr);
+ __tlbi_user(vae1is, addr);
dsb(ish);
}
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 8b57339..7ec84d0 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -31,6 +31,14 @@ 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);
+extern unsigned long cpufreq_scale_max_freq_capacity(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 811cf16..95cbade 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
*/
@@ -26,10 +33,8 @@
#include <linux/string.h>
#include <linux/thread_info.h>
-#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/ptrace.h>
-#include <asm/sysreg.h>
#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/compiler.h>
@@ -121,6 +126,115 @@ static inline void set_fs(mm_segment_t fs)
" .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);
+}
+
+/*
* The "__xxx" versions of the user access functions do not verify the address
* space - it must have been done previously with a separate "access_ok()"
* call.
@@ -147,8 +261,7 @@ static inline void set_fs(mm_segment_t fs)
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), \
@@ -169,9 +282,8 @@ 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(x, ptr) \
@@ -216,8 +328,7 @@ 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), \
@@ -238,8 +349,7 @@ 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(x, ptr) \
@@ -332,4 +442,77 @@ 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/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 c0ede23..29d2ad8 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 c58ddf8..b6c9389 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -24,6 +24,7 @@
#include <linux/kvm_host.h>
#include <linux/suspend.h>
#include <asm/cpufeature.h>
+#include <asm/fixmap.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
@@ -41,6 +42,9 @@ int main(void)
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));
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ DEFINE(TSK_TI_TTBR0, offsetof(struct thread_info, ttbr0));
+#endif
BLANK();
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
BLANK();
@@ -144,11 +148,14 @@ int main(void)
DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2));
DEFINE(ARM_SMCCC_QUIRK_ID_OFFS, offsetof(struct arm_smccc_quirk, id));
DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS, offsetof(struct arm_smccc_quirk, state));
-
BLANK();
DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address));
DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address));
DEFINE(HIBERN_PBE_NEXT, offsetof(struct pbe, next));
DEFINE(ARM64_FTR_SYSVAL, offsetof(struct arm64_ftr_reg, sys_val));
+ BLANK();
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ DEFINE(TRAMP_VALIAS, TRAMP_VALIAS);
+#endif
return 0;
}
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 3a129d4..bfbd9e9 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>
@@ -47,6 +48,7 @@ unsigned int compat_elf_hwcap2 __read_mostly;
#endif
DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcaps);
DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
EXPORT_SYMBOL(cpu_hwcap_keys);
@@ -736,7 +738,7 @@ 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:
@@ -746,6 +748,40 @@ static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode();
}
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
+
+static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
+ int __unused)
+{
+ /* Forced on command line? */
+ if (__kpti_forced) {
+ pr_info_once("kernel page table isolation forced %s by command line option\n",
+ __kpti_forced > 0 ? "ON" : "OFF");
+ return __kpti_forced > 0;
+ }
+
+ /* Useful for KASLR robustness */
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+ return true;
+
+ return false;
+}
+
+static int __init parse_kpti(char *str)
+{
+ bool enabled;
+ int ret = strtobool(str, &enabled);
+
+ if (ret)
+ return ret;
+
+ __kpti_forced = enabled ? 1 : -1;
+ return 0;
+}
+__setup("kpti=", parse_kpti);
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -829,6 +865,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.def_scope = SCOPE_SYSTEM,
.matches = hyp_offset_low,
},
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ {
+ .capability = ARM64_UNMAP_KERNEL_AT_EL0,
+ .def_scope = SCOPE_SYSTEM,
+ .matches = unmap_kernel_at_el0,
+ },
+#endif
{},
};
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b4c7db4..32de484 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -29,7 +29,10 @@
#include <asm/esr.h>
#include <asm/irq.h>
#include <asm/memory.h>
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
#include <asm/thread_info.h>
+#include <asm/uaccess.h>
#include <asm/asm-uaccess.h>
#include <asm/unistd.h>
@@ -68,8 +71,31 @@
#define BAD_FIQ 2
#define BAD_ERROR 3
- .macro kernel_entry, el, regsize = 64
+ .macro kernel_ventry, el, label, regsize = 64
+ .align 7
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+ .if \el == 0
+ .if \regsize == 64
+ mrs x30, tpidrro_el0
+ msr tpidrro_el0, xzr
+ .else
+ mov x30, xzr
+ .endif
+ .endif
+alternative_else_nop_endif
+#endif
+
sub sp, sp, #S_FRAME_SIZE
+ b el\()\el\()_\label
+ .endm
+
+ .macro tramp_alias, dst, sym
+ mov_q \dst, TRAMP_VALIAS
+ add \dst, \dst, #(\sym - .entry.tramp.text)
+ .endm
+
+ .macro kernel_entry, el, regsize = 64
.if \regsize == 32
mov w0, w0 // zero upper 32 bits of x0
.endif
@@ -110,6 +136,32 @@
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]
/*
@@ -148,21 +200,58 @@
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?
+ b.eq 3f
+
#ifdef CONFIG_ARM64_ERRATUM_845719
alternative_if ARM64_WORKAROUND_845719
- tbz x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrs x29, contextidr_el1
msr contextidr_el1, x29
#else
msr contextidr_el1, xzr
#endif
-1:
alternative_else_nop_endif
#endif
+3:
.endif
+
msr elr_el1, x21 // set up the return data
msr spsr_el1, x22
ldp x0, x1, [sp, #16 * 0]
@@ -182,11 +271,21 @@
ldp x28, x29, [sp, #16 * 14]
ldr lr, [sp, #S_LR]
add sp, sp, #S_FRAME_SIZE // restore sp
- eret // return to kernel
- .endm
- .macro get_thread_info, rd
- mrs \rd, sp_el0
+ .if \el == 0
+alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ bne 4f
+ msr far_el1, x30
+ tramp_alias x30, tramp_exit_native
+ br x30
+4:
+ tramp_alias x30, tramp_exit_compat
+ br x30
+#endif
+ .else
+ eret
+ .endif
.endm
.macro irq_stack_entry
@@ -257,31 +356,31 @@
.align 11
ENTRY(vectors)
- ventry el1_sync_invalid // Synchronous EL1t
- ventry el1_irq_invalid // IRQ EL1t
- ventry el1_fiq_invalid // FIQ EL1t
- ventry el1_error_invalid // Error EL1t
+ kernel_ventry 1, sync_invalid // Synchronous EL1t
+ kernel_ventry 1, irq_invalid // IRQ EL1t
+ kernel_ventry 1, fiq_invalid // FIQ EL1t
+ kernel_ventry 1, error_invalid // Error EL1t
- ventry el1_sync // Synchronous EL1h
- ventry el1_irq // IRQ EL1h
- ventry el1_fiq_invalid // FIQ EL1h
- ventry el1_error_invalid // Error EL1h
+ kernel_ventry 1, sync // Synchronous EL1h
+ kernel_ventry 1, irq // IRQ EL1h
+ kernel_ventry 1, fiq_invalid // FIQ EL1h
+ kernel_ventry 1, error_invalid // Error EL1h
- ventry el0_sync // Synchronous 64-bit EL0
- ventry el0_irq // IRQ 64-bit EL0
- ventry el0_fiq_invalid // FIQ 64-bit EL0
- ventry el0_error_invalid // Error 64-bit EL0
+ kernel_ventry 0, sync // Synchronous 64-bit EL0
+ kernel_ventry 0, irq // IRQ 64-bit EL0
+ kernel_ventry 0, fiq_invalid // FIQ 64-bit EL0
+ kernel_ventry 0, error_invalid // Error 64-bit EL0
#ifdef CONFIG_COMPAT
- ventry el0_sync_compat // Synchronous 32-bit EL0
- ventry el0_irq_compat // IRQ 32-bit EL0
- ventry el0_fiq_invalid_compat // FIQ 32-bit EL0
- ventry el0_error_invalid_compat // Error 32-bit EL0
+ kernel_ventry 0, sync_compat, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_compat, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid_compat, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_invalid_compat, 32 // Error 32-bit EL0
#else
- ventry el0_sync_invalid // Synchronous 32-bit EL0
- ventry el0_irq_invalid // IRQ 32-bit EL0
- ventry el0_fiq_invalid // FIQ 32-bit EL0
- ventry el0_error_invalid // Error 32-bit EL0
+ kernel_ventry 0, sync_invalid, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_invalid, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0
#endif
END(vectors)
@@ -801,6 +900,119 @@
.popsection // .entry.text
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ */
+ .pushsection ".entry.tramp.text", "ax"
+
+ .macro tramp_map_kernel, tmp
+ mrs \tmp, ttbr1_el1
+ 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 + RESERVED_TTBR0_SIZE)
+ orr \tmp, \tmp, #USER_ASID_FLAG
+ msr ttbr1_el1, \tmp
+ /*
+ * We avoid running the post_ttbr_update_workaround here because the
+ * user and kernel ASIDs don't have conflicting mappings, so any
+ * "blessing" as described in:
+ *
+ * http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com
+ *
+ * will not hurt correctness. Whilst this may partially defeat the
+ * point of using split ASIDs in the first place, it avoids
+ * the hit of invalidating the entire I-cache on every return to
+ * userspace.
+ */
+ .endm
+
+ .macro tramp_ventry, regsize = 64
+ .align 7
+1:
+ .if \regsize == 64
+ msr tpidrro_el0, x30 // Restored in kernel_ventry
+ .endif
+ bl 2f
+ b .
+2:
+ 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
+#endif
+ prfm plil1strm, [x30, #(1b - tramp_vectors)]
+ msr vbar_el1, x30
+ add x30, x30, #(1b - tramp_vectors)
+ isb
+ ret
+ .endm
+
+ .macro tramp_exit, regsize = 64
+ adr x30, tramp_vectors
+ msr vbar_el1, x30
+ tramp_unmap_kernel x30
+ .if \regsize == 64
+ mrs x30, far_el1
+ .endif
+ eret
+ .endm
+
+ .align 11
+ENTRY(tramp_vectors)
+ .space 0x400
+
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+END(tramp_vectors)
+
+ENTRY(tramp_exit_native)
+ tramp_exit
+END(tramp_exit_native)
+
+ENTRY(tramp_exit_compat)
+ tramp_exit 32
+END(tramp_exit_compat)
+
+ .ltorg
+ .popsection // .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+ .pushsection ".rodata", "a"
+ .align PAGE_SHIFT
+ .globl __entry_tramp_data_start
+__entry_tramp_data_start:
+ .quad vectors
+ .popsection // .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
/*
* Special system call wrappers.
*/
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 539bebc..1177adf 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
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index d55a7b0..8bed26a 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;
@@ -460,7 +457,6 @@ 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);
@@ -481,12 +477,6 @@ 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.
*/
@@ -537,7 +527,7 @@ 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 0b9e5f6..fb0082a 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;
@@ -518,18 +558,17 @@ 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.
@@ -662,12 +701,47 @@ 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;
@@ -676,35 +750,15 @@ 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.
@@ -713,18 +767,41 @@ 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/process.c b/arch/arm64/kernel/process.c
index 0e73949..7e365ff 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -166,6 +166,70 @@ 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)) {
+ printk(" ********");
+ } else {
+ printk(" %08x", data);
+ }
+ ++p;
+ }
+ printk("\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 +265,8 @@ void __show_regs(struct pt_regs *regs)
pr_cont("\n");
}
+ if (!user_mode(regs))
+ show_extra_register_data(regs, 128);
printk("\n");
}
@@ -306,17 +372,17 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
static void tls_thread_switch(struct task_struct *next)
{
- unsigned long tpidr, tpidrro;
+ unsigned long tpidr;
tpidr = read_sysreg(tpidr_el0);
*task_user_tls(current) = tpidr;
- tpidr = *task_user_tls(next);
- tpidrro = is_compat_thread(task_thread_info(next)) ?
- next->thread.tp_value : 0;
+ if (is_compat_thread(task_thread_info(next)))
+ write_sysreg(next->thread.tp_value, tpidrro_el0);
+ else if (!arm64_kernel_unmapped_at_el0())
+ write_sysreg(0, tpidrro_el0);
- write_sysreg(tpidr, tpidr_el0);
- write_sysreg(tpidrro, tpidrro_el0);
+ write_sysreg(*task_user_tls(next), tpidr_el0);
}
/* Restore the UAO state depending on next's addr_limit */
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 42816be..e8edbf1 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 8eedeef..a22161c 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/setup.c b/arch/arm64/kernel/setup.c
index f534f492..6a9dc51 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_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/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/topology.c b/arch/arm64/kernel/topology.c
index 694f6de..7758f7f 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -19,10 +19,30 @@
#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)
+{
+#ifdef CONFIG_CPU_FREQ
+ unsigned long max_freq_scale = cpufreq_scale_max_freq_capacity(cpu);
+
+ return per_cpu(cpu_scale, cpu) * max_freq_scale >> SCHED_CAPACITY_SHIFT;
+#else
+ return per_cpu(cpu_scale, cpu);
+#endif
+}
+
+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 +226,72 @@ 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 +353,7 @@ 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 +384,8 @@ 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 c743d1f..5fd787a 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -33,6 +33,7 @@
#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>
@@ -435,9 +436,10 @@ 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" \
@@ -449,7 +451,9 @@ 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)
{
@@ -492,6 +496,25 @@ 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;
@@ -510,6 +533,18 @@ 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 4bcfe01..7492d90 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];
@@ -216,10 +220,8 @@ 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/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index 76320e9..c39872a 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -309,7 +309,7 @@
b.ne 4f
ldr x2, 6f
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 1105aab..34d3ed6 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -56,6 +56,17 @@
#define HIBERNATE_TEXT
#endif
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_TEXT \
+ . = ALIGN(PAGE_SIZE); \
+ VMLINUX_SYMBOL(__entry_tramp_text_start) = .; \
+ *(.entry.tramp.text) \
+ . = ALIGN(PAGE_SIZE); \
+ VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
+#else
+#define TRAMP_TEXT
+#endif
+
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -128,6 +139,7 @@
HYPERVISOR_TEXT
IDMAP_TEXT
HIBERNATE_TEXT
+ TRAMP_TEXT
*(.fixup)
*(.gnu.warning)
. = ALIGN(16);
@@ -216,6 +228,16 @@
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;
+#endif
+
_end = .;
STABS_DEBUG
@@ -235,7 +257,10 @@
ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
<= SZ_4K, "Hibernate exit text too big or misaligned")
#endif
-
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+ "Entry trampoline text too big")
+#endif
/*
* If padding is applied before .head.text, virt<->phys conversions will fail.
*/
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 5d1cad3..07c7ad9 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(__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(__clear_user)
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 4fd67ea..c7a7d96 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 f7292dd0..e8bfaf1 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(__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(__copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 7a7efe2..f6cfcc0 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 efcf1f7..d45dea9 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -39,7 +39,16 @@ static cpumask_t tlb_flush_pending;
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION (1UL << asid_bits)
-#define NUM_USER_ASIDS ASID_FIRST_VERSION
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid) (((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx) (((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION)
+#define asid2idx(asid) ((asid) & ~ASID_MASK)
+#define idx2asid(idx) asid2idx(idx)
+#endif
/* Get the ASIDBits supported by the current CPU */
static u32 get_cpu_asid_bits(void)
@@ -104,7 +113,7 @@ static void flush_context(unsigned int cpu)
*/
if (asid == 0)
asid = per_cpu(reserved_asids, i);
- __set_bit(asid & ~ASID_MASK, asid_map);
+ __set_bit(asid2idx(asid), asid_map);
per_cpu(reserved_asids, i) = asid;
}
@@ -159,16 +168,16 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
* We had a valid ASID in a previous life, so try to re-use
* it if possible.
*/
- asid &= ~ASID_MASK;
- if (!__test_and_set_bit(asid, asid_map))
+ if (!__test_and_set_bit(asid2idx(asid), asid_map))
return newasid;
}
/*
* Allocate a free ASID. If we can't find one, take a note of the
- * currently active ASIDs and mark the TLBs as requiring flushes.
- * We always count from ASID #1, as we use ASID #0 when setting a
- * reserved TTBR0 for the init_mm.
+ * currently active ASIDs and mark the TLBs as requiring flushes. We
+ * always count from ASID #2 (index 1), as we use ASID #0 when setting
+ * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+ * pairs.
*/
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
if (asid != NUM_USER_ASIDS)
@@ -185,7 +194,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
set_asid:
__set_bit(asid, asid_map);
cur_idx = asid;
- return asid | generation;
+ return idx2asid(asid) | generation;
}
void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
@@ -221,7 +230,21 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
switch_mm_fastpath:
- 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. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+ asm(ALTERNATIVE("nop; nop; nop",
+ "ic iallu; dsb nsh; isb",
+ ARM64_WORKAROUND_CAVIUM_27456,
+ CONFIG_CAVIUM_ERRATUM_27456));
}
static int asids_init(void)
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 403fe9e..bc463b5 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -286,13 +286,19 @@ 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)
@@ -332,7 +338,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
mm_flags |= FAULT_FLAG_WRITE;
}
- if (is_permission_fault(esr) && (addr < USER_DS)) {
+ if (addr < USER_DS && 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 9b8b477..2b35b67 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>
@@ -145,9 +146,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
#endif /* CONFIG_NUMA */
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+#define PFN_MASK ((1UL << (64 - PAGE_SHIFT)) - 1)
+
int pfn_valid(unsigned long pfn)
{
- return memblock_is_map_memory(pfn << PAGE_SHIFT);
+ return (pfn & PFN_MASK) == pfn && memblock_is_map_memory(pfn << PAGE_SHIFT);
}
EXPORT_SYMBOL(pfn_valid);
#endif
@@ -209,8 +212,8 @@ 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,
@@ -225,7 +228,7 @@ 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) {
@@ -278,7 +281,7 @@ 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);
@@ -486,7 +489,8 @@ 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 757009d..201d918 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 05615a3f..31d16d8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -30,6 +30,7 @@
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/stop_machine.h>
+#include <linux/mm.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
@@ -319,8 +320,8 @@ 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
@@ -387,21 +388,21 @@ 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);
}
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));
@@ -419,6 +420,37 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
vm_area_add_early(vma);
}
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+ extern char __entry_tramp_text_start[];
+
+ pgprot_t prot = PAGE_KERNEL_EXEC;
+ phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+ /* The trampoline is always mapped and can therefore be global */
+ pgprot_val(prot) &= ~PTE_NG;
+
+ /* Map only the text into the trampoline page table */
+ memset(tramp_pg_dir, 0, PGD_SIZE);
+ __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
+ prot, pgd_pgtable_alloc, 0);
+
+ /* Map both the text and data into the kernel page table */
+ __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ extern char __entry_tramp_data_start[];
+
+ __set_fixmap(FIX_ENTRY_TRAMP_DATA,
+ __pa_symbol(__entry_tramp_data_start),
+ PAGE_KERNEL_RO);
+ }
+
+ return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
/*
* Create fine-grained mappings for the kernel.
*/
@@ -449,7 +481,7 @@ static void __init map_kernel(pgd_t *pgd)
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START),
- __pud(__pa(bm_pmd) | PUD_TYPE_TABLE));
+ __pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE));
pud_clear_fixmap();
} else {
BUG();
@@ -480,7 +512,7 @@ void __init paging_init(void)
*/
cpu_replace_ttbr1(__va(pgd_phys));
memcpy(swapper_pg_dir, pgd, PAGE_SIZE);
- cpu_replace_ttbr1(swapper_pg_dir);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
pgd_clear_fixmap();
memblock_free(pgd_phys, PAGE_SIZE);
@@ -489,7 +521,7 @@ 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);
}
@@ -600,6 +632,12 @@ 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;
@@ -609,7 +647,7 @@ 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
@@ -618,12 +656,14 @@ 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 352c73b..89e3d95 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -132,16 +132,17 @@
* - pgd_phys - physical address of new TTB
*/
ENTRY(cpu_do_switch_mm)
+ mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
- bfi x0, x1, #48, #16 // set the ASID
- msr ttbr0_el1, x0 // set TTBR0
+#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
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
- ic iallu
- dsb nsh
+ msr ttbr0_el1, x0 // now update TTBR0
isb
-alternative_else_nop_endif
- ret
+ b post_ttbr_update_workaround // Back to C code...
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
@@ -222,7 +223,7 @@
* both user and kernel.
*/
ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
- TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0
+ TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0 | TCR_A1
tcr_set_idmap_t0sz x10, x9
/*
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/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 3686d6a..9edda54 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -50,32 +50,10 @@
# The gate DSO image is built using a special linker script.
include $(src)/Makefile.gate
-# Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
-define sed-y
- "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
-endef
-quiet_cmd_nr_irqs = GEN $@
-define cmd_nr_irqs
- (set -e; \
- echo "#ifndef __ASM_NR_IRQS_H__"; \
- echo "#define __ASM_NR_IRQS_H__"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " *"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y) $<; \
- echo ""; \
- echo "#endif" ) > $@
-endef
-
# We use internal kbuild rules to avoid the "is up to date" message from make
arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
$(Q)mkdir -p $(dir $@)
$(call if_changed_dep,cc_s_c)
-include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
- $(Q)mkdir -p $(dir $@)
- $(call cmd,nr_irqs)
+include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s FORCE
+ $(call filechk,offsets,__ASM_NR_IRQS_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/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/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/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/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/x86/Makefile b/arch/x86/Makefile
index cd22cb8..ea24114 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -11,6 +11,16 @@
KBUILD_DEFCONFIG := $(ARCH)_defconfig
endif
+# For gcc stack alignment is specified with -mpreferred-stack-boundary,
+# clang has the option -mstack-alignment for that purpose.
+ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
+ cc_stack_align4 := -mpreferred-stack-boundary=2
+ cc_stack_align8 := -mpreferred-stack-boundary=3
+else ifneq ($(call cc-option, -mstack-alignment=16),)
+ cc_stack_align4 := -mstack-alignment=4
+ cc_stack_align8 := -mstack-alignment=8
+endif
+
# How to compile the 16-bit code. Note we always compile for -march=i386;
# that way we can complain to the user if the CPU is insufficient.
#
@@ -24,10 +34,11 @@
-DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
- -mno-mmx -mno-sse \
- $(call cc-option, -ffreestanding) \
- $(call cc-option, -fno-stack-protector) \
- $(call cc-option, -mpreferred-stack-boundary=2)
+ -mno-mmx -mno-sse
+
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
export REALMODE_CFLAGS
# BITS is used as extension for files which are available in a 32 bit
@@ -64,8 +75,10 @@
# with nonstandard options
KBUILD_CFLAGS += -fno-pic
- # prevent gcc from keeping the stack 16 byte aligned
- KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
+ # Align the stack to the register width instead of using the default
+ # alignment of 16 bytes. This reduces stack usage and the number of
+ # alignment instructions.
+ KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
# a lot more stack due to the lack of sharing of stacklots:
@@ -88,17 +101,25 @@
KBUILD_CFLAGS += -m64
# Align jump targets to 1 byte, not the default 16 bytes:
- KBUILD_CFLAGS += -falign-jumps=1
+ KBUILD_CFLAGS += $(call cc-option,-falign-jumps=1)
# Pack loops tightly as well:
- KBUILD_CFLAGS += -falign-loops=1
+ KBUILD_CFLAGS += $(call cc-option,-falign-loops=1)
# Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
- # Use -mpreferred-stack-boundary=3 if supported.
- KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+ 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
+ # alignment it will generate extra alignment instructions for the
+ # default alignment which keep the stack *mis*aligned.
+ # Furthermore an alignment to the register width reduces stack usage
+ # and the number of alignment instructions.
+ KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8))
# Use -mskip-rax-setup if supported.
KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 9e240fc..08dfce0 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -16,6 +16,15 @@
#include "ctype.h"
#include "string.h"
+/*
+ * Undef these macros so that the functions that we provide
+ * here will have the correct names regardless of how string.h
+ * may have chosen to #define them.
+ */
+#undef memcpy
+#undef memset
+#undef memcmp
+
int memcmp(const void *s1, const void *s2, size_t len)
{
bool diff;
diff --git a/arch/x86/configs/i386_ranchu_defconfig b/arch/x86/configs/i386_ranchu_defconfig
new file mode 100644
index 0000000..a1c83c4
--- /dev/null
+++ b/arch/x86/configs/i386_ranchu_defconfig
@@ -0,0 +1,424 @@
+# 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_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=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_KEYCHORD=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_ranchu_defconfig b/arch/x86/configs/x86_64_ranchu_defconfig
new file mode 100644
index 0000000..d50434f
--- /dev/null
+++ b/arch/x86/configs/x86_64_ranchu_defconfig
@@ -0,0 +1,419 @@
+# 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_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=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_KEYCHORD=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/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index a916c4a..5f6a5af 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -65,7 +65,6 @@
#include <linux/linkage.h>
#include <asm/inst.h>
-#define CONCAT(a,b) a##b
#define VMOVDQ vmovdqu
#define xdata0 %xmm0
@@ -92,8 +91,6 @@
#define num_bytes %r8
#define tmp %r10
-#define DDQ(i) CONCAT(ddq_add_,i)
-#define XMM(i) CONCAT(%xmm, i)
#define DDQ_DATA 0
#define XDATA 1
#define KEY_128 1
@@ -131,12 +128,12 @@
/* generate a unique variable for ddq_add_x */
.macro setddq n
- var_ddq_add = DDQ(\n)
+ var_ddq_add = ddq_add_\n
.endm
/* generate a unique variable for xmm register */
.macro setxdata n
- var_xdata = XMM(\n)
+ var_xdata = %xmm\n
.endm
/* club the numeric 'id' to the symbol 'name' */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index db5009c..8be2aaa 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -614,13 +614,8 @@
#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/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/asm.h b/arch/x86/include/asm/asm.h
index 7bb29a4..08684b3 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -34,6 +34,7 @@
#define _ASM_ADD __ASM_SIZE(add)
#define _ASM_SUB __ASM_SIZE(sub)
#define _ASM_XADD __ASM_SIZE(xadd)
+#define _ASM_MUL __ASM_SIZE(mul)
#define _ASM_AX __ASM_REG(ax)
#define _ASM_BX __ASM_REG(bx)
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 0f400c0..bc5902c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -459,8 +459,8 @@ 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))
@@ -480,8 +480,8 @@ 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))
@@ -520,7 +520,7 @@ 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__ \
@@ -530,7 +530,7 @@ 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__ \
@@ -557,7 +557,7 @@ 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/uaccess.h b/arch/x86/include/asm/uaccess.h
index a8d85a6..0c87840 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -171,11 +171,11 @@ __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 ccdc23d..1fdcb8c 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/process.c b/arch/x86/kernel/process.c
index a55b320..54b2711 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -67,19 +67,6 @@ 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
/*
@@ -255,14 +242,14 @@ 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/vmx.c b/arch/x86/kvm/vmx.c
index 1e16821..dc34038 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8625,7 +8625,6 @@ 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
@@ -8659,7 +8658,7 @@ 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/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 121f59c..0c7fe44 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -5,6 +5,7 @@
* kernel starts. This file is included in the compressed kernel and
* normally linked in the regular.
*/
+#include <asm/asm.h>
#include <asm/kaslr.h>
#include <asm/msr.h>
#include <asm/archrandom.h>
@@ -79,7 +80,7 @@ unsigned long kaslr_get_random_long(const char *purpose)
}
/* Circular multiply for better bit diffusion */
- asm("mul %3"
+ asm(_ASM_MUL "%3"
: "=a" (random), "=d" (raw)
: "a" (random), "rm" (mix_const));
random += raw;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 74dea7f..3d7f60f 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -759,7 +759,6 @@ 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
@@ -774,7 +773,7 @@ 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));
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/blk-core.c b/block/blk-core.c
index 23daf40b..b2e5764 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -40,6 +40,8 @@
#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);
@@ -3572,3 +3574,52 @@ 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/build.config.goldfish.arm b/build.config.goldfish.arm
new file mode 100644
index 0000000..866da93
--- /dev/null
+++ b/build.config.goldfish.arm
@@ -0,0 +1,12 @@
+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
+"
diff --git a/build.config.goldfish.arm64 b/build.config.goldfish.arm64
new file mode 100644
index 0000000..9c963cf
--- /dev/null
+++ b/build.config.goldfish.arm64
@@ -0,0 +1,12 @@
+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
+"
diff --git a/build.config.goldfish.mips b/build.config.goldfish.mips
new file mode 100644
index 0000000..8af53d2
--- /dev/null
+++ b/build.config.goldfish.mips
@@ -0,0 +1,11 @@
+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
+"
diff --git a/build.config.goldfish.mips64 b/build.config.goldfish.mips64
new file mode 100644
index 0000000..2a33d36
--- /dev/null
+++ b/build.config.goldfish.mips64
@@ -0,0 +1,11 @@
+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
+"
diff --git a/build.config.goldfish.x86 b/build.config.goldfish.x86
new file mode 100644
index 0000000..f86253f
--- /dev/null
+++ b/build.config.goldfish.x86
@@ -0,0 +1,12 @@
+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
+"
diff --git a/build.config.goldfish.x86_64 b/build.config.goldfish.x86_64
new file mode 100644
index 0000000..e173886
--- /dev/null
+++ b/build.config.goldfish.x86_64
@@ -0,0 +1,12 @@
+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
+"
diff --git a/crypto/api.c b/crypto/api.c
index bbc147c..e5c1abf 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);
@@ -611,5 +612,17 @@ 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/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 733bf0b..9a90575 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -174,3 +174,4 @@
obj-$(CONFIG_ANDROID) += android/
obj-$(CONFIG_NVMEM) += nvmem/
obj-$(CONFIG_FPGA) += fpga/
+obj-$(CONFIG_TEE) += tee/
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
index bdfc6c6..01de42c 100644
--- a/drivers/android/Kconfig
+++ b/drivers/android/Kconfig
@@ -19,6 +19,18 @@
Android process, using Binder to identify, invoke and pass arguments
between said processes.
+config ANDROID_BINDER_DEVICES
+ string "Android Binder devices"
+ depends on ANDROID_BINDER_IPC
+ default "binder,hwbinder,vndbinder"
+ ---help---
+ Default value for the binder.devices parameter.
+
+ The binder.devices parameter is a comma-separated list of strings
+ that specifies the names of the binder device nodes that will be
+ created. Each binder device has its own context manager, and is
+ therefore logically separated from the other devices.
+
config ANDROID_BINDER_IPC_32BIT
bool
depends on !64BIT && ANDROID_BINDER_IPC
@@ -32,6 +44,16 @@
Note that enabling this will break newer Android user-space.
+config ANDROID_BINDER_IPC_SELFTEST
+ bool "Android Binder IPC Driver Selftest"
+ depends on ANDROID_BINDER_IPC
+ ---help---
+ This feature allows binder selftest to run.
+
+ Binder selftest checks the allocation and free of binder buffers
+ exhaustively with combinations of various buffer sizes and
+ alignments.
+
endif # if ANDROID
endmenu
diff --git a/drivers/android/Makefile b/drivers/android/Makefile
index 3b7e4b0..a01254c 100644
--- a/drivers/android/Makefile
+++ b/drivers/android/Makefile
@@ -1,3 +1,4 @@
ccflags-y += -I$(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 15009b2b..bb48a7b 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 +67,31 @@
#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>
+#include <linux/spinlock.h>
#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
#define BINDER_IPC_32BIT 1
#endif
#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) \
@@ -104,16 +137,15 @@ 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);
-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;
@@ -145,6 +177,17 @@ 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 +200,27 @@ 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 +230,14 @@ 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 +247,50 @@ 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];
- memset(e, 0, sizeof(*e));
- log->next++;
- if (log->next == ARRAY_SIZE(log->entry)) {
- log->next = 0;
+ if (cur >= ARRAY_SIZE(log->entry))
log->full = 1;
- }
+ 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));
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 {
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 +298,76 @@ 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
+ * (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;
@@ -234,97 +378,192 @@ 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 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,
+ BINDER_DEFERRED_FLUSH = 0x01,
+ BINDER_DEFERRED_RELEASE = 0x02,
};
+/**
+ * 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)
+ * @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
+ * (protected by @inner_lock)
+ * @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 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;
+ int 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 {
@@ -333,22 +572,63 @@ 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 = 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 {
@@ -365,30 +645,330 @@ 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;
+ /**
+ * @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;
};
+/**
+ * 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;
+}
+
+/**
+ * binder_dequeue_work_head() - Dequeues the item at head of list
+ * @proc: binder_proc associated with list
+ * @list: list to dequeue head
+ *
+ * Removes the head of the list if there are items on the list
+ *
+ * Return: pointer dequeued binder_work, NULL if list was empty
+ */
+static struct binder_work *binder_dequeue_work_head(
+ struct binder_proc *proc,
+ struct list_head *list)
+{
+ struct binder_work *w;
+
+ binder_inner_proc_lock(proc);
+ w = binder_dequeue_work_head_ilocked(list);
+ binder_inner_proc_unlock(proc);
+ 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);
+
+struct files_struct *binder_get_files_struct(struct binder_proc *proc)
+{
+ return get_files_struct(proc->tsk);
+}
static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
{
- struct files_struct *files = proc->files;
+ struct files_struct *files;
unsigned long rlim_cur;
unsigned long irqs;
+ int ret;
+ files = binder_get_files_struct(proc);
if (files == NULL)
return -ESRCH;
- if (!lock_task_sighand(proc->tsk, &irqs))
- return -EMFILE;
+ if (!lock_task_sighand(proc->tsk, &irqs)) {
+ ret = -EMFILE;
+ goto err;
+ }
rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
unlock_task_sighand(proc->tsk, &irqs);
- return __alloc_fd(files, 0, rlim_cur, flags);
+ ret = __alloc_fd(files, 0, rlim_cur, flags);
+err:
+ put_files_struct(files);
+ return ret;
}
/*
@@ -397,8 +977,12 @@ static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
static void task_fd_install(
struct binder_proc *proc, unsigned int fd, struct file *file)
{
- if (proc->files)
- __fd_install(proc->files, fd, file);
+ struct files_struct *files = binder_get_files_struct(proc);
+
+ if (files) {
+ __fd_install(files, fd, file);
+ put_files_struct(files);
+ }
}
/*
@@ -406,469 +990,300 @@ static void task_fd_install(
*/
static long task_close_fd(struct binder_proc *proc, unsigned int fd)
{
+ struct files_struct *files = binder_get_files_struct(proc);
int retval;
- if (proc->files == NULL)
+ if (files == NULL)
return -ESRCH;
- retval = __close_fd(proc->files, fd);
+ retval = __close_fd(files, fd);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
+ put_files_struct(files);
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 %p\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 %p-%p\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);
- 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 %p\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 %p 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 %p 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 %p\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 %p share page with %p\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 %p share page with %p\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 %p do not share page%s%s with %p or %p\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 %p 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);
@@ -876,21 +1291,47 @@ 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);
@@ -898,39 +1339,86 @@ 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);
+ 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;
@@ -939,8 +1427,19 @@ 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)
@@ -951,58 +1450,172 @@ 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;
@@ -1010,11 +1623,11 @@ 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 {
@@ -1024,13 +1637,34 @@ 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;
@@ -1043,22 +1677,22 @@ 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;
@@ -1066,121 +1700,423 @@ 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 (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);
+ proc->tmp_ref--;
+ if (proc->is_dead && RB_EMPTY_ROOT(&proc->threads) &&
+ !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)
+{
if (t->buffer)
t->buffer->transaction = NULL;
kfree(t);
@@ -1195,30 +2131,28 @@ 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);
+ WARN(1, "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;
@@ -1227,7 +2161,7 @@ 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");
@@ -1240,11 +2174,178 @@ 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_validate_object() - checks for a valid metadata object in a buffer.
+ * @buffer: binder_buffer that we're parsing.
+ * @offset: offset in the buffer at which to validate an object.
+ *
+ * Return: If there's a valid metadata object at @offset in @buffer, the
+ * size of that object. Otherwise, it returns zero.
+ */
+static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset)
+{
+ /* Check if we can read a header first */
+ struct binder_object_header *hdr;
+ size_t object_size = 0;
+
+ if (offset > buffer->data_size - sizeof(*hdr) ||
+ buffer->data_size < sizeof(*hdr) ||
+ !IS_ALIGNED(offset, sizeof(u32)))
+ return 0;
+
+ /* Ok, now see if we can read a complete object. */
+ hdr = (struct binder_object_header *)(buffer->data + offset);
+ 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.
+ * @b: binder_buffer containing the object
+ * @index: index in offset array at which the binder_buffer_object is
+ * located
+ * @start: points to the start of the offset array
+ * @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.
+ */
+static struct binder_buffer_object *binder_validate_ptr(struct binder_buffer *b,
+ binder_size_t index,
+ binder_size_t *start,
+ binder_size_t num_valid)
+{
+ struct binder_buffer_object *buffer_obj;
+ binder_size_t *offp;
+
+ if (index >= num_valid)
+ return NULL;
+
+ offp = start + index;
+ buffer_obj = (struct binder_buffer_object *)(b->data + *offp);
+ if (buffer_obj->hdr.type != BINDER_TYPE_PTR)
+ return NULL;
+
+ return buffer_obj;
+}
+
+/**
+ * binder_validate_fixup() - validates pointer/fd fixups happen in order.
+ * @b: transaction buffer
+ * @objects_start start of objects buffer
+ * @buffer: binder_buffer_object in which to fix up
+ * @offset: start offset in @buffer to fix up
+ * @last_obj: last binder_buffer_object that we fixed up in
+ * @last_min_offset: minimum fixup offset in @last_obj
+ *
+ * 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_buffer *b,
+ binder_size_t *objects_start,
+ struct binder_buffer_object *buffer,
+ binder_size_t fixup_offset,
+ struct binder_buffer_object *last_obj,
+ binder_size_t last_min_offset)
+{
+ if (!last_obj) {
+ /* Nothing to fix up in */
+ return false;
+ }
+
+ while (last_obj != buffer) {
+ /*
+ * Safe to retrieve the parent of last_obj, since it
+ * was already previously verified by the driver.
+ */
+ if ((last_obj->flags & BINDER_BUFFER_FLAG_HAS_PARENT) == 0)
+ return false;
+ last_min_offset = last_obj->parent_offset + sizeof(uintptr_t);
+ last_obj = (struct binder_buffer_object *)
+ (b->data + *(objects_start + last_obj->parent));
+ }
+ 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 *offp, *off_end;
+ binder_size_t *offp, *off_start, *off_end;
int debug_id = buffer->debug_id;
binder_debug(BINDER_DEBUG_TRANSACTION,
@@ -1255,28 +2356,30 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
if (buffer->target_node)
binder_dec_node(buffer->target_node, 1, 0);
- offp = (binder_size_t *)(buffer->data +
- ALIGN(buffer->data_size, sizeof(void *)));
+ off_start = (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_end = (void *)off_start + buffer->offsets_size;
+ for (offp = off_start; offp < off_end; offp++) {
+ struct binder_object_header *hdr;
+ size_t object_size = binder_validate_object(buffer, *offp);
- 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",
+ if (object_size == 0) {
+ pr_err("transaction release %d bad object at offset %lld, size %zd\n",
debug_id, (u64)*offp, buffer->data_size);
continue;
}
- fp = (struct flat_binder_object *)(buffer->data + *offp);
- switch (fp->type) {
+ hdr = (struct binder_object_header *)(buffer->data + *offp);
+ 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);
@@ -1285,90 +2388,560 @@ 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;
+ uintptr_t parent_buffer;
+ u32 *fd_array;
+ size_t fd_index;
+ binder_size_t fd_buf_size;
+
+ fda = to_binder_fd_array_object(hdr);
+ parent = binder_validate_ptr(buffer, fda->parent,
+ off_start,
+ offp - off_start);
+ if (!parent) {
+ pr_err("transaction release %d bad parent offset",
+ debug_id);
+ continue;
+ }
+ /*
+ * Since the parent was already fixed up, convert it
+ * back to kernel address space to access it
+ */
+ parent_buffer = parent->buffer -
+ binder_alloc_get_user_buffer_offset(
+ &proc->alloc);
+
+ 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;
+ }
+ fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
+ for (fd_index = 0; fd_index < fda->num_fds; fd_index++)
+ task_close_fd(proc, fd_array[fd_index]);
+ } 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;
+ int target_fd;
+ uintptr_t parent_buffer;
+ u32 *fd_array;
+ 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;
+ }
+ /*
+ * Since the parent was already fixed up, convert it
+ * back to the kernel address space to access it
+ */
+ parent_buffer = parent->buffer -
+ binder_alloc_get_user_buffer_offset(&target_proc->alloc);
+ fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset);
+ if (!IS_ALIGNED((unsigned long)fd_array, 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++) {
+ target_fd = binder_translate_fd(fd_array[fdi], t, thread,
+ in_reply_to);
+ if (target_fd < 0)
+ goto err_translate_fd_failed;
+ fd_array[fdi] = target_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++)
+ task_close_fd(target_proc, fd_array[fdi]);
+ 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,
+ binder_size_t num_valid,
+ struct binder_buffer_object *last_fixup_obj,
+ binder_size_t last_fixup_min_off)
+{
+ struct binder_buffer_object *parent;
+ u8 *parent_buffer;
+ struct binder_buffer *b = t->buffer;
+ struct binder_proc *proc = thread->proc;
+ struct binder_proc *target_proc = t->to_proc;
+
+ if (!(bp->flags & BINDER_BUFFER_FLAG_HAS_PARENT))
+ return 0;
+
+ parent = binder_validate_ptr(b, bp->parent, off_start, 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(b, off_start,
+ parent, bp->parent_offset,
+ last_fixup_obj,
+ 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;
+ }
+ parent_buffer = (u8 *)((uintptr_t)parent->buffer -
+ binder_alloc_get_user_buffer_offset(
+ &target_proc->alloc));
+ *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = 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 = 1;
+ }
+ }
+
+ 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);
+ 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 *offp, *off_end, *off_start;
binder_size_t off_min;
- struct binder_proc *target_proc;
+ u8 *sg_bufp, *sg_buf_end;
+ 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;
+ struct binder_buffer_object *last_fixup_obj = NULL;
+ binder_size_t last_fixup_min_off = 0;
+ struct binder_context *context = proc->context;
+ int t_debug_id = atomic_inc_return(&binder_last_id);
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) {
@@ -1377,106 +2950,148 @@ 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;
+ 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;
- goto err_invalid_target_handle;
}
- target_node = ref->node;
+ binder_proc_unlock(proc);
} else {
- target_node = binder_context_mgr_node;
- if (target_node == NULL) {
+ 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;
- goto err_no_context_mgr_node;
- }
+ mutex_unlock(&context->context_mgr_node_lock);
}
- 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 (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;
@@ -1487,14 +3102,30 @@ 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;
+ }
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;
@@ -1502,17 +3133,17 @@ static void binder_transaction(struct binder_proc *proc,
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 *)));
+ off_start = (binder_size_t *)(t->buffer->data +
+ ALIGN(tr->data_size, sizeof(void *)));
+ offp = off_start;
if (copy_from_user(t->buffer->data, (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)
@@ -1520,231 +3151,253 @@ static void binder_transaction(struct binder_proc *proc,
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_end = (void *)off_start + tr->offsets_size;
+ sg_bufp = (u8 *)(PTR_ALIGN(off_end, sizeof(void *)));
+ sg_buf_end = sg_bufp + extra_buffers_size;
off_min = 0;
for (; offp < off_end; offp++) {
- struct flat_binder_object *fp;
+ struct binder_object_header *hdr;
+ size_t object_size = binder_validate_object(t->buffer, *offp);
- 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",
+ if (object_size == 0 || *offp < 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)*offp,
(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 = (struct binder_object_header *)(t->buffer->data + *offp);
+ off_min = *offp + 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);
} 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;
- }
- 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);
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
}
} 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;
} break;
+ case BINDER_TYPE_FDA: {
+ struct binder_fd_array_object *fda =
+ to_binder_fd_array_object(hdr);
+ struct binder_buffer_object *parent =
+ binder_validate_ptr(t->buffer, fda->parent,
+ off_start,
+ offp - off_start);
+ 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(t->buffer, off_start,
+ parent, fda->parent_offset,
+ last_fixup_obj,
+ 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 = parent;
+ 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 - sg_bufp;
+ 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 (copy_from_user(sg_bufp,
+ (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)sg_bufp +
+ binder_alloc_get_user_buffer_offset(
+ &target_proc->alloc);
+ sg_bufp += ALIGN(bp->length, sizeof(u64));
+
+ ret = binder_fixup_parent(t, thread, bp, off_start,
+ offp - off_start,
+ last_fixup_obj,
+ last_fixup_min_off);
+ if (ret < 0) {
+ return_error = BR_FAILED_REPLY;
+ return_error_param = ret;
+ return_error_line = __LINE__;
+ goto err_translate_failed;
+ }
+ last_fixup_obj = bp;
+ 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);
+ 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:
kfree(tcomplete);
binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
@@ -1756,25 +3409,48 @@ 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,
@@ -1783,19 +3459,22 @@ 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:
@@ -1803,53 +3482,61 @@ 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)) {
- 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;
+ 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)
+ ret = binder_inc_ref_for_node(
+ proc, ctx_mgr_node,
+ strong, NULL, &rdata);
+ 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:
@@ -1857,6 +3544,7 @@ 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;
@@ -1881,13 +3569,17 @@ 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;
@@ -1896,16 +3588,23 @@ 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:
@@ -1923,7 +3622,8 @@ static int binder_thread_write(struct binder_proc *proc,
return -EFAULT;
ptr += sizeof(binder_uintptr_t);
- buffer = binder_buffer_lookup(proc, data_ptr);
+ buffer = binder_alloc_prepare_to_free(&proc->alloc,
+ 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);
@@ -1945,18 +3645,41 @@ static int binder_thread_write(struct binder_proc *proc,
buffer->transaction = NULL;
}
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 = 0;
+ } 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_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;
@@ -1964,7 +3687,8 @@ 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;
}
@@ -1972,6 +3696,7 @@ 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",
@@ -1985,6 +3710,7 @@ 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,
@@ -2009,7 +3735,7 @@ 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;
@@ -2017,7 +3743,28 @@ 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,
@@ -2025,6 +3772,8 @@ 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;
}
@@ -2034,21 +3783,18 @@ 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);
@@ -2057,17 +3803,19 @@ 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;
@@ -2076,22 +3824,35 @@ 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;
@@ -2102,8 +3863,13 @@ 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;
@@ -2117,19 +3883,25 @@ 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:
@@ -2147,23 +3919,73 @@ 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,
@@ -2185,37 +4007,15 @@ 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))) {
@@ -2224,24 +4024,16 @@ 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)
@@ -2250,31 +4042,54 @@ 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_work *w = NULL;
+ struct list_head *list = NULL;
struct binder_transaction *t = NULL;
+ struct binder_thread *t_from;
- 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;
+ e->cmd = BR_OK;
+ ptr += sizeof(uint32_t);
+
+ binder_stat_br(proc, thread, 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;
@@ -2284,113 +4099,134 @@ 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;
@@ -2402,16 +4238,14 @@ 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);
+ 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;
@@ -2422,8 +4256,9 @@ static int binder_thread_read(struct binder_proc *proc,
tr.flags = t->flags;
tr.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));
@@ -2433,18 +4268,32 @@ static int binder_thread_read(struct binder_proc *proc,
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.buffer = (binder_uintptr_t)
+ ((uintptr_t)t->buffer->data +
+ binder_alloc_get_user_buffer_offset(&proc->alloc));
tr.data.ptr.offsets = tr.data.ptr.buffer +
ALIGN(t->buffer->data_size,
sizeof(void *));
- if (put_user(cmd, (uint32_t __user *)ptr))
+ 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, sizeof(tr))) {
+ 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);
trace_binder_transaction_received(t);
@@ -2454,21 +4303,22 @@ static int binder_thread_read(struct binder_proc *proc,
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,
+ 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);
- 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)) {
+ 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;
}
@@ -2476,45 +4326,52 @@ 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;
- while (!list_empty(list)) {
- w = list_first_entry(list, struct binder_work, entry);
- list_del_init(&w->entry);
+ while (1) {
+ w = binder_dequeue_work_head(proc, list);
+ if (!w)
+ return;
+
switch (w->type) {
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,
@@ -2542,7 +4399,8 @@ static void binder_release_work(struct list_head *list)
}
-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;
@@ -2557,38 +4415,102 @@ 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()
+ */
+ 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",
@@ -2609,12 +4531,28 @@ 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 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);
+
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;
}
@@ -2623,30 +4561,21 @@ 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);
- wait_for_proc_work = thread->transaction_stack == NULL &&
- list_empty(&thread->todo) && thread->return_error == BR_OK;
+ binder_inner_proc_lock(thread->proc);
+ thread->looper |= BINDER_LOOPER_STATE_POLL;
+ wait_for_proc_work = binder_available_for_proc_work_ilocked(thread);
- binder_unlock(__func__);
+ binder_inner_proc_unlock(thread->proc);
- 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;
- }
+ poll_wait(filp, &thread->wait, wait);
+
+ if (binder_has_work(thread, wait_for_proc_work))
+ return POLLIN;
+
return 0;
}
@@ -2693,8 +4622,10 @@ 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;
@@ -2718,9 +4649,12 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp)
{
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;
@@ -2728,31 +4662,60 @@ 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, NULL);
+ 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_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;
@@ -2764,13 +4727,14 @@ 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;
@@ -2783,12 +4747,19 @@ 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:
ret = binder_ioctl_set_ctx_mgr(filp);
if (ret)
@@ -2797,7 +4768,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
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: {
@@ -2814,6 +4785,24 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
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;
@@ -2821,8 +4810,7 @@ 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);
@@ -2851,9 +4839,7 @@ 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_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
+ binder_alloc_vma_close(&proc->alloc);
}
static int binder_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -2870,10 +4856,8 @@ 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;
@@ -2882,8 +4866,8 @@ 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));
@@ -2893,73 +4877,13 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
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 %p 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_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();
- proc->files = get_files_struct(current);
- proc->vma = vma;
- proc->vma_vm_mm = vma->vm_mm;
+ ret = binder_alloc_mmap_handler(&proc->alloc, vma);
- /*pr_info("binder_mmap: %d %lx-%lx maps %p\n",
- proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
- return 0;
+ return ret;
-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",
proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
@@ -2969,6 +4893,7 @@ 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",
current->group_leader->pid, current->pid);
@@ -2976,28 +4901,49 @@ static int binder_open(struct inode *nodp, struct file *filp)
proc = kzalloc(sizeof(*proc), GFP_KERNEL);
if (proc == NULL)
return -ENOMEM;
+ spin_lock_init(&proc->inner_lock);
+ spin_lock_init(&proc->outer_lock);
get_task_struct(current->group_leader);
proc->tsk = current->group_leader;
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 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, S_IRUGO,
- binder_debugfs_dir_entry_proc, proc, &binder_proc_fops);
+ binder_debugfs_dir_entry_proc,
+ (void *)(unsigned long)proc->pid,
+ &binder_proc_fops);
}
return 0;
@@ -3017,16 +4963,17 @@ 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,
@@ -3047,13 +4994,21 @@ 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;
}
@@ -3061,59 +5016,82 @@ 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
+ */
+ 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;
@@ -3123,84 +5101,50 @@ 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 %p 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)
{
struct binder_proc *proc;
- struct files_struct *files;
-
int defer;
do {
- binder_lock(__func__);
mutex_lock(&binder_deferred_lock);
if (!hlist_empty(&binder_deferred_list)) {
proc = hlist_entry(binder_deferred_list.first,
@@ -3214,22 +5158,11 @@ static void binder_deferred_func(struct work_struct *work)
}
mutex_unlock(&binder_deferred_lock);
- files = NULL;
- if (defer & BINDER_DEFERRED_PUT_FILES) {
- files = proc->files;
- if (files)
- proc->files = NULL;
- }
-
if (defer & BINDER_DEFERRED_FLUSH)
binder_deferred_flush(proc);
if (defer & BINDER_DEFERRED_RELEASE)
binder_deferred_release(proc); /* frees proc */
-
- binder_unlock(__func__);
- if (files)
- put_files_struct(files);
} while (proc);
}
static DECLARE_WORK(binder_deferred_work, binder_deferred_func);
@@ -3247,41 +5180,52 @@ 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: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d",
+ "%s %d: %p 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 %p\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: %p size %zd:%zd %s\n",
- prefix, buffer->debug_id, buffer->data,
buffer->data_size, buffer->offsets_size,
- buffer->transaction ? "active" : "delivered");
+ buffer->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;
@@ -3289,8 +5233,16 @@ 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;
@@ -3315,40 +5267,46 @@ 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;
@@ -3358,27 +5316,35 @@ 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)
{
- seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %p\n",
- ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ",
- ref->node->debug_id, ref->strong, ref->weak, ref->death);
+ binder_node_lock(ref->node);
+ seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %pK\n",
+ 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,
@@ -3388,35 +5354,60 @@ 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);
+ /*
+ * 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;
}
@@ -3459,7 +5450,9 @@ 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[] = {
@@ -3480,17 +5473,21 @@ 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) !=
@@ -3498,11 +5495,15 @@ 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);
}
}
@@ -3510,50 +5511,61 @@ 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);
@@ -3564,107 +5576,131 @@ 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;
}
@@ -3679,26 +5715,56 @@ 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;
+ struct binder_device *device;
+ struct hlist_node *tmp;
+
+ binder_alloc_shrinker_init();
+
+ 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,
@@ -3726,6 +5792,35 @@ static int __init binder_init(void)
&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);
+
+ while ((device_name = strsep(&device_names, ","))) {
+ 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);
+ }
+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..1c76daa
--- /dev/null
+++ b/drivers/android/binder_alloc.c
@@ -0,0 +1,1015 @@
+/* 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 "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 (u8 *)alloc->buffer +
+ alloc->buffer_size - (u8 *)buffer->data;
+ return (u8 *)binder_buffer_next(buffer)->data - (u8 *)buffer->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->data < buffer->data)
+ p = &parent->rb_left;
+ else if (new_buffer->data > buffer->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 *kern_ptr;
+
+ kern_ptr = (void *)(user_ptr - alloc->user_buffer_offset);
+
+ while (n) {
+ buffer = rb_entry(n, struct binder_buffer, rb_node);
+ BUG_ON(buffer->free);
+
+ if (kern_ptr < buffer->data)
+ n = n->rb_left;
+ else if (kern_ptr > buffer->data)
+ n = n->rb_right;
+ else {
+ /*
+ * Guard against user threads attempting to
+ * free the buffer twice
+ */
+ if (buffer->free_in_progress) {
+ pr_err("%d:%d FREE_BUFFER u%016llx user freed buffer twice\n",
+ alloc->pid, current->pid, (u64)user_ptr);
+ return NULL;
+ }
+ buffer->free_in_progress = 1;
+ 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 *start, void *end)
+{
+ void *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_write(&mm->mmap_sem);
+ 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);
+
+ ret = map_kernel_range_noflush((unsigned long)page_addr,
+ PAGE_SIZE, PAGE_KERNEL,
+ &page->page_ptr);
+ 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",
+ alloc->pid, page_addr);
+ goto err_map_kernel_failed;
+ }
+ user_page_addr =
+ (uintptr_t)page_addr + alloc->user_buffer_offset;
+ 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_write(&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:
+ unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
+err_map_kernel_failed:
+ __free_page(page->page_ptr);
+ page->page_ptr = NULL;
+err_alloc_page_failed:
+err_page_ptr_cleared:
+ ;
+ }
+err_no_vma:
+ if (mm) {
+ up_write(&mm->mmap_sem);
+ mmput(mm);
+ }
+ return vma ? -ENOMEM : -ESRCH;
+}
+
+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 *has_page_addr;
+ void *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 *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
+ WARN_ON(n && buffer_size != size);
+ end_page_addr =
+ (void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
+ if (end_page_addr > has_page_addr)
+ end_page_addr = has_page_addr;
+ ret = binder_update_page_range(alloc, 1,
+ (void *)PAGE_ALIGN((uintptr_t)buffer->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->data = (u8 *)buffer->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->free_in_progress = 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 *)PAGE_ALIGN((uintptr_t)buffer->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 *buffer_start_page(struct binder_buffer *buffer)
+{
+ return (void *)((uintptr_t)buffer->data & PAGE_MASK);
+}
+
+static void *prev_buffer_end_page(struct binder_buffer *buffer)
+{
+ return (void *)(((uintptr_t)(buffer->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->data, prev->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->data,
+ next->data);
+ }
+ }
+
+ if (PAGE_ALIGNED(buffer->data)) {
+ binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+ "%d: merge free, buffer start %pK is page aligned\n",
+ alloc->pid, buffer->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->data,
+ prev->data, next ? next->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->data < alloc->buffer);
+ BUG_ON(buffer->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 *)PAGE_ALIGN((uintptr_t)buffer->data),
+ (void *)(((uintptr_t)buffer->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;
+ struct vm_struct *area;
+ 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;
+ }
+
+ 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;
+ }
+ alloc->buffer = area->addr;
+ alloc->user_buffer_offset =
+ vma->vm_start - (uintptr_t)alloc->buffer;
+ mutex_unlock(&binder_alloc_mmap_lock);
+
+#ifdef CONFIG_CPU_CACHE_VIPT
+ if (cache_is_vipt_aliasing()) {
+ while (CACHE_COLOUR(
+ (vma->vm_start ^ (uint32_t)alloc->buffer))) {
+ pr_info("%s: %d %lx-%lx maps %pK bad alignment\n",
+ __func__, alloc->pid, vma->vm_start,
+ vma->vm_end, alloc->buffer);
+ vma->vm_start += PAGE_SIZE;
+ }
+ }
+#endif
+ 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->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);
+ vfree(alloc->buffer);
+ alloc->buffer = NULL;
+err_get_vm_area_failed:
+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 *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");
+ unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
+ __free_page(alloc->pages[i].page_ptr);
+ page_count++;
+ }
+ kfree(alloc->pages);
+ vfree(alloc->buffer);
+ }
+ 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->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;
+ vma = alloc->vma;
+ if (vma) {
+ if (!mmget_not_zero(alloc->vma_vm_mm))
+ goto err_mmget;
+ mm = alloc->vma_vm_mm;
+ if (!down_write_trylock(&mm->mmap_sem))
+ goto err_down_write_mmap_sem_failed;
+ }
+
+ list_lru_isolate(lru, item);
+ spin_unlock(lock);
+
+ if (vma) {
+ trace_binder_unmap_user_start(alloc, index);
+
+ zap_page_range(vma,
+ page_addr +
+ alloc->user_buffer_offset,
+ PAGE_SIZE, NULL);
+
+ trace_binder_unmap_user_end(alloc, index);
+
+ up_write(&mm->mmap_sem);
+ mmput(mm);
+ }
+
+ trace_binder_unmap_kernel_start(alloc, index);
+
+ unmap_kernel_range(page_addr, PAGE_SIZE);
+ __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);
+}
+
+void binder_alloc_shrinker_init(void)
+{
+ list_lru_init(&binder_alloc_lru);
+ register_shrinker(&binder_shrinker);
+}
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
new file mode 100644
index 0000000..0b14530
--- /dev/null
+++ b/drivers/android/binder_alloc.h
@@ -0,0 +1,188 @@
+/*
+ * 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>
+
+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: describe the second member of struct blah,
+ * @async_transaction: describe the second member of struct blah,
+ * @debug_id: describe the second member of struct blah,
+ * @transaction: describe the second member of struct blah,
+ * @target_node: describe the second member of struct blah,
+ * @data_size: describe the second member of struct blah,
+ * @offsets_size: describe the second member of struct blah,
+ * @extra_buffers_size: describe the second member of struct blah,
+ * @data:i describe the second member of struct blah,
+ *
+ * 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 free_in_progress:1;
+ unsigned debug_id:28;
+
+ struct binder_transaction *transaction;
+
+ struct binder_node *target_node;
+ size_t data_size;
+ size_t offsets_size;
+ size_t extra_buffers_size;
+ void *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
+ * @user_buffer_offset: offset between user and kernel VAs for buffer
+ * @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 *buffer;
+ ptrdiff_t user_buffer_offset;
+ 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);
+void 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;
+}
+
+/**
+ * binder_alloc_get_user_buffer_offset() - get offset between kernel/user addrs
+ * @alloc: binder_alloc for this proc
+ *
+ * Return: the offset between kernel and user-space addresses to use for
+ * virtual address conversion
+ */
+static inline ptrdiff_t
+binder_alloc_get_user_buffer_offset(struct binder_alloc *alloc)
+{
+ /*
+ * user_buffer_offset is constant if vma is set and
+ * undefined if vma is not set. It is possible to
+ * get here with !alloc->vma if the target process
+ * is dying while a transaction is being initiated.
+ * Returning the old value is ok in this case and
+ * the transaction will fail.
+ */
+ return alloc->user_buffer_offset;
+}
+
+#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..8bd7bce
--- /dev/null
+++ b/drivers/android/binder_alloc_selftest.c
@@ -0,0 +1,310 @@
+/* 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 *page_addr, *end;
+ int page_index;
+
+ end = (void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
+ page_addr = buffer->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..b11dffc 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,
+ TP_PROTO(struct binder_alloc *alloc, bool allocate,
void *start, void *end),
- TP_ARGS(proc, allocate, start, 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/power/main.c b/drivers/base/power/main.c
index dfffba3..dc259d2 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);
@@ -1373,6 +1375,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
pm_wakeup_event(dev, 0);
if (pm_wakeup_pending()) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
async_error = -EBUSY;
goto Complete;
}
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index f98121f..90c16d8 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"
@@ -804,6 +805,37 @@ 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;
@@ -1011,7 +1043,7 @@ 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),
@@ -1032,7 +1064,7 @@ 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/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 a2503db..e3bc592 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -449,7 +449,10 @@ 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..1170bfe 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -102,6 +102,16 @@
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 +203,26 @@
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..f0c9905 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -10,6 +10,7 @@
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 4d3ec92..e4cbfe5 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -280,6 +280,13 @@ 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 35e34c0..f0475d4 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -29,6 +29,9 @@
#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 +120,12 @@ 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 +310,50 @@ 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_scale) = SCHED_CAPACITY_SCALE;
+
+static void
+scale_freq_capacity(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs)
+{
+ unsigned long cur = freqs ? freqs->new : policy->cur;
+ unsigned long scale = (cur << SCHED_CAPACITY_SHIFT) / policy->max;
+ struct cpufreq_cpuinfo *cpuinfo = &policy->cpuinfo;
+ int cpu;
+
+ pr_debug("cpus %*pbl cur/cur max freq %lu/%u kHz freq scale %lu\n",
+ cpumask_pr_args(policy->cpus), cur, policy->max, scale);
+
+ for_each_cpu(cpu, policy->cpus)
+ per_cpu(freq_scale, cpu) = scale;
+
+ if (freqs)
+ return;
+
+ scale = (policy->max << SCHED_CAPACITY_SHIFT) / cpuinfo->max_freq;
+
+ pr_debug("cpus %*pbl cur max/max freq %u/%u kHz max freq scale %lu\n",
+ cpumask_pr_args(policy->cpus), policy->max, cpuinfo->max_freq,
+ scale);
+
+ for_each_cpu(cpu, policy->cpus)
+ per_cpu(max_freq_scale, cpu) = scale;
+}
+
+unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(freq_scale, cpu);
+}
+
+unsigned long cpufreq_scale_max_freq_capacity(int cpu)
+{
+ return per_cpu(max_freq_scale, cpu);
+}
+
static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
struct cpufreq_freqs *freqs, unsigned int state)
{
@@ -378,6 +431,9 @@ 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 +461,12 @@ void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
spin_unlock(&policy->transition_lock);
+ scale_freq_capacity(policy, freqs);
+#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);
@@ -2199,8 +2261,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_NOTIFY, new_policy);
+ scale_freq_capacity(new_policy, NULL);
+
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_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/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..65bb6fd 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -178,7 +178,12 @@ 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/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 f0c374d..c835f62 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -299,10 +299,9 @@ 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 (!test_and_set_bit(POLL_ENABLED, &sync_file->fence->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/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 5e23e2d..b12bc38 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -10,7 +10,7 @@
-fPIC -fno-strict-aliasing -mno-red-zone \
-mno-mmx -mno-sse
-cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS))
+cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
-fno-builtin -fpic -mno-single-pic-base
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 993aa56..7ec09ea 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -18,8 +18,6 @@
#include "efistub.h"
-bool __nokaslr;
-
static int efi_get_secureboot(efi_system_table_t *sys_table_arg)
{
static efi_char16_t const sb_var_name[] = {
@@ -268,18 +266,6 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
goto fail;
}
- /* check whether 'nokaslr' was passed on the command line */
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
- static const u8 default_cmdline[] = CONFIG_CMDLINE;
- const u8 *str, *cmdline = cmdline_ptr;
-
- if (IS_ENABLED(CONFIG_CMDLINE_FORCE))
- cmdline = default_cmdline;
- str = strstr(cmdline, "nokaslr");
- if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
- __nokaslr = true;
- }
-
si = setup_graphics(sys_table);
status = handle_kernel_image(sys_table, image_addr, &image_size,
@@ -291,9 +277,13 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
goto fail_free_cmdline;
}
- status = efi_parse_options(cmdline_ptr);
- if (status != EFI_SUCCESS)
- pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
+ if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
+ IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
+ cmdline_size == 0)
+ efi_parse_options(CONFIG_CMDLINE);
+
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0)
+ efi_parse_options(cmdline_ptr);
secure_boot = efi_get_secureboot(sys_table);
if (secure_boot > 0)
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index eae693e..f7a6970 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -9,15 +9,21 @@
* published by the Free Software Foundation.
*
*/
+
+/*
+ * To prevent the compiler from emitting GOT-indirected (and thus absolute)
+ * references to the section markers, override their visibility as 'hidden'
+ */
+#pragma GCC visibility push(hidden)
+#include <asm/sections.h>
+#pragma GCC visibility pop
+
#include <linux/efi.h>
#include <asm/efi.h>
-#include <asm/sections.h>
#include <asm/sysreg.h>
#include "efistub.h"
-extern bool __nokaslr;
-
efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
{
u64 tg;
@@ -52,7 +58,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
u64 phys_seed = 0;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
- if (!__nokaslr) {
+ if (!nokaslr()) {
status = efi_get_random_bytes(sys_table_arg,
sizeof(phys_seed),
(u8 *)&phys_seed);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index aded106..2db141c 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -41,6 +41,13 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
#define EFI_ALLOC_ALIGN EFI_PAGE_SIZE
#endif
+static int __section(.data) __nokaslr;
+
+int __pure nokaslr(void)
+{
+ return __nokaslr;
+}
+
#define EFI_MMAP_NR_SLACK_SLOTS 8
struct file_info {
@@ -351,10 +358,14 @@ void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
* environments, first in the early boot environment of the EFI boot
* stub, and subsequently during the kernel boot.
*/
-efi_status_t efi_parse_options(char *cmdline)
+efi_status_t efi_parse_options(char const *cmdline)
{
char *str;
+ str = strstr(cmdline, "nokaslr");
+ if (str == cmdline || (str && str > cmdline && *(str - 1) == ' '))
+ __nokaslr = 1;
+
/*
* If no EFI parameters were specified on the cmdline we've got
* nothing to do.
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index fac6799..d0e5aca 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -15,6 +15,8 @@
*/
#undef __init
+extern int __pure nokaslr(void);
+
void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
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 34adde1..33778bf 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) {
@@ -1152,6 +1195,36 @@ 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
@@ -1470,11 +1543,9 @@ 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)
@@ -1484,17 +1555,6 @@ 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;
}
@@ -1599,6 +1659,206 @@ 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)
{
@@ -1611,11 +1871,10 @@ 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))
@@ -1656,6 +1915,8 @@ 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;
@@ -1730,20 +1991,10 @@ 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) {
/*
@@ -1760,20 +2011,7 @@ 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 f5815e1..fe00bea 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -663,6 +663,10 @@ 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 d09276e..94983e8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1604,7 +1604,14 @@ 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/uhid.c b/drivers/hid/uhid.c
index 7f8ff39..e46f656 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -28,6 +28,8 @@
#define UHID_NAME "uhid"
#define UHID_BUFSIZE 32
+static DEFINE_MUTEX(uhid_open_mutex);
+
struct uhid_device {
struct mutex devlock;
bool running;
@@ -142,15 +144,26 @@ 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 4db8d6a..83358eb 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -1026,7 +1026,8 @@ 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);
@@ -1045,20 +1046,25 @@ 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 d6941ea..1549436 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");
@@ -383,7 +373,7 @@ 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);
@@ -504,7 +494,6 @@ 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;
@@ -528,9 +517,8 @@ 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;
}
@@ -542,7 +530,7 @@ 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;
@@ -573,7 +561,7 @@ 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-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index 0673baf..ff579a7 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -46,8 +46,11 @@
#define TPIU_ITATBCTR0 0xef8
/** register definition **/
+/* FFSR - 0x300 */
+#define FFSR_FT_STOPPED BIT(1)
/* FFCR - 0x304 */
#define FFCR_FON_MAN BIT(6)
+#define FFCR_STOP_FI BIT(12)
/**
* @base: memory mapped base address for this component.
@@ -85,10 +88,14 @@ static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
{
CS_UNLOCK(drvdata->base);
- /* Clear formatter controle reg. */
- writel_relaxed(0x0, drvdata->base + TPIU_FFCR);
+ /* Clear formatter and stop on flush */
+ writel_relaxed(FFCR_STOP_FI, drvdata->base + TPIU_FFCR);
/* Generate manual flush */
- writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+ writel_relaxed(FFCR_STOP_FI | FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+ /* Wait for flush to complete */
+ coresight_timeout(drvdata->base, TPIU_FFCR, FFCR_FON_MAN, 0);
+ /* Wait for formatter to stop */
+ coresight_timeout(drvdata->base, TPIU_FFSR, FFSR_FT_STOPPED, 1);
CS_LOCK(drvdata->base);
}
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 7bf00a0..0c37356 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -368,6 +368,52 @@ 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.
@@ -380,6 +426,7 @@ 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;
@@ -387,15 +434,15 @@ 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;
}
@@ -422,18 +469,22 @@ 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);
@@ -497,6 +548,7 @@ 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;
mutex_lock(&coresight_mutex);
@@ -508,7 +560,17 @@ int coresight_enable(struct coresight_device *csdev)
if (csdev->enable)
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/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..94360fe 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -367,6 +367,17 @@
To compile this driver as a module, choose M here: the module will be
called ati_remote2.
+config INPUT_KEYCHORD
+ tristate "Key chord input driver support"
+ help
+ Say Y here if you want to enable the key chord driver
+ accessible at /dev/keychord. This driver can be used
+ for receiving notifications when client specified key
+ combinations are pressed.
+
+ To compile this driver as a module, choose M here: the
+ module will be called keychord.
+
config INPUT_KEYSPAN_REMOTE
tristate "Keyspan DMR USB remote control"
depends on USB_ARCH_HAS_HCD
@@ -535,6 +546,11 @@
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..64bf231 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -36,10 +36,12 @@
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
obj-$(CONFIG_INPUT_IXP4XX_BEEPER) += ixp4xx-beeper.o
+obj-$(CONFIG_INPUT_KEYCHORD) += keychord.o
obj-$(CONFIG_INPUT_KEYSPAN_REMOTE) += keyspan_remote.o
obj-$(CONFIG_INPUT_KXTJ9) += kxtj9.o
obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.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/input/misc/keychord.c b/drivers/input/misc/keychord.c
new file mode 100644
index 0000000..fdcc146
--- /dev/null
+++ b/drivers/input/misc/keychord.c
@@ -0,0 +1,467 @@
+/*
+ * drivers/input/misc/keychord.c
+ *
+ * Copyright (C) 2008 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.
+ *
+*/
+
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/keychord.h>
+#include <linux/sched.h>
+
+#define KEYCHORD_NAME "keychord"
+#define BUFFER_SIZE 16
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("Key chord input driver");
+MODULE_SUPPORTED_DEVICE("keychord");
+MODULE_LICENSE("GPL");
+
+#define NEXT_KEYCHORD(kc) ((struct input_keychord *) \
+ ((char *)kc + sizeof(struct input_keychord) + \
+ kc->count * sizeof(kc->keycodes[0])))
+
+struct keychord_device {
+ struct input_handler input_handler;
+ int registered;
+
+ /* list of keychords to monitor */
+ struct input_keychord *keychords;
+ int keychord_count;
+
+ /* bitmask of keys contained in our keychords */
+ unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+ /* current state of the keys */
+ unsigned long keystate[BITS_TO_LONGS(KEY_CNT)];
+ /* number of keys that are currently pressed */
+ int key_down;
+
+ /* second input_device_id is needed for null termination */
+ struct input_device_id device_ids[2];
+
+ spinlock_t lock;
+ wait_queue_head_t waitq;
+ unsigned char head;
+ unsigned char tail;
+ __u16 buff[BUFFER_SIZE];
+ /* Bit to serialize writes to this device */
+#define KEYCHORD_BUSY 0x01
+ unsigned long flags;
+ wait_queue_head_t write_waitq;
+};
+
+static int check_keychord(struct keychord_device *kdev,
+ struct input_keychord *keychord)
+{
+ int i;
+
+ if (keychord->count != kdev->key_down)
+ return 0;
+
+ for (i = 0; i < keychord->count; i++) {
+ if (!test_bit(keychord->keycodes[i], kdev->keystate))
+ return 0;
+ }
+
+ /* we have a match */
+ return 1;
+}
+
+static void keychord_event(struct input_handle *handle, unsigned int type,
+ unsigned int code, int value)
+{
+ struct keychord_device *kdev = handle->private;
+ struct input_keychord *keychord;
+ unsigned long flags;
+ int i, got_chord = 0;
+
+ if (type != EV_KEY || code >= KEY_MAX)
+ return;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* do nothing if key state did not change */
+ if (!test_bit(code, kdev->keystate) == !value)
+ goto done;
+ __change_bit(code, kdev->keystate);
+ if (value)
+ kdev->key_down++;
+ else
+ kdev->key_down--;
+
+ /* don't notify on key up */
+ if (!value)
+ goto done;
+ /* ignore this event if it is not one of the keys we are monitoring */
+ if (!test_bit(code, kdev->keybit))
+ goto done;
+
+ keychord = kdev->keychords;
+ if (!keychord)
+ goto done;
+
+ /* check to see if the keyboard state matches any keychords */
+ for (i = 0; i < kdev->keychord_count; i++) {
+ if (check_keychord(kdev, keychord)) {
+ kdev->buff[kdev->head] = keychord->id;
+ kdev->head = (kdev->head + 1) % BUFFER_SIZE;
+ got_chord = 1;
+ break;
+ }
+ /* skip to next keychord */
+ keychord = NEXT_KEYCHORD(keychord);
+ }
+
+done:
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ if (got_chord) {
+ pr_info("keychord: got keychord id %d. Any tasks: %d\n",
+ keychord->id,
+ !list_empty_careful(&kdev->waitq.task_list));
+ wake_up_interruptible(&kdev->waitq);
+ }
+}
+
+static int keychord_connect(struct input_handler *handler,
+ struct input_dev *dev,
+ const struct input_device_id *id)
+{
+ int i, ret;
+ struct input_handle *handle;
+ struct keychord_device *kdev =
+ container_of(handler, struct keychord_device, input_handler);
+
+ /*
+ * ignore this input device if it does not contain any keycodes
+ * that we are monitoring
+ */
+ for (i = 0; i < KEY_MAX; i++) {
+ if (test_bit(i, kdev->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 = KEYCHORD_NAME;
+ handle->private = kdev;
+
+ ret = input_register_handle(handle);
+ if (ret)
+ goto err_input_register_handle;
+
+ ret = input_open_device(handle);
+ if (ret)
+ goto err_input_open_device;
+
+ pr_info("keychord: using input dev %s for fevent\n", dev->name);
+ return 0;
+
+err_input_open_device:
+ input_unregister_handle(handle);
+err_input_register_handle:
+ kfree(handle);
+ return ret;
+}
+
+static void keychord_disconnect(struct input_handle *handle)
+{
+ input_close_device(handle);
+ input_unregister_handle(handle);
+ kfree(handle);
+}
+
+/*
+ * keychord_read is used to read keychord events from the driver
+ */
+static ssize_t keychord_read(struct file *file, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct keychord_device *kdev = file->private_data;
+ __u16 id;
+ int retval;
+ unsigned long flags;
+
+ if (count < sizeof(id))
+ return -EINVAL;
+ count = sizeof(id);
+
+ if (kdev->head == kdev->tail && (file->f_flags & O_NONBLOCK))
+ return -EAGAIN;
+
+ retval = wait_event_interruptible(kdev->waitq,
+ kdev->head != kdev->tail);
+ if (retval)
+ return retval;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* pop a keychord ID off the queue */
+ id = kdev->buff[kdev->tail];
+ kdev->tail = (kdev->tail + 1) % BUFFER_SIZE;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ if (copy_to_user(buffer, &id, count))
+ return -EFAULT;
+
+ return count;
+}
+
+/*
+ * serializes writes on a device. can use mutex_lock_interruptible()
+ * for this particular use case as well - a matter of preference.
+ */
+static int
+keychord_write_lock(struct keychord_device *kdev)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ while (kdev->flags & KEYCHORD_BUSY) {
+ spin_unlock_irqrestore(&kdev->lock, flags);
+ ret = wait_event_interruptible(kdev->write_waitq,
+ ((kdev->flags & KEYCHORD_BUSY) == 0));
+ if (ret)
+ return ret;
+ spin_lock_irqsave(&kdev->lock, flags);
+ }
+ kdev->flags |= KEYCHORD_BUSY;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+ return 0;
+}
+
+static void
+keychord_write_unlock(struct keychord_device *kdev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ kdev->flags &= ~KEYCHORD_BUSY;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+ wake_up_interruptible(&kdev->write_waitq);
+}
+
+/*
+ * keychord_write is used to configure the driver
+ */
+static ssize_t keychord_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct keychord_device *kdev = file->private_data;
+ struct input_keychord *keychords = 0;
+ struct input_keychord *keychord;
+ int ret, i, key;
+ unsigned long flags;
+ size_t resid = count;
+ size_t key_bytes;
+
+ if (count < sizeof(struct input_keychord))
+ return -EINVAL;
+ keychords = kzalloc(count, GFP_KERNEL);
+ if (!keychords)
+ return -ENOMEM;
+
+ /* read list of keychords from userspace */
+ if (copy_from_user(keychords, buffer, count)) {
+ kfree(keychords);
+ return -EFAULT;
+ }
+
+ /*
+ * Serialize writes to this device to prevent various races.
+ * 1) writers racing here could do duplicate input_unregister_handler()
+ * calls, resulting in attempting to unlink a node from a list that
+ * does not exist.
+ * 2) writers racing here could do duplicate input_register_handler() calls
+ * below, resulting in a duplicate insertion of a node into the list.
+ * 3) a double kfree of keychords can occur (in the event that
+ * input_register_handler() fails below.
+ */
+ ret = keychord_write_lock(kdev);
+ if (ret) {
+ kfree(keychords);
+ return ret;
+ }
+
+ /* unregister handler before changing configuration */
+ if (kdev->registered) {
+ input_unregister_handler(&kdev->input_handler);
+ kdev->registered = 0;
+ }
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* clear any existing configuration */
+ kfree(kdev->keychords);
+ kdev->keychords = 0;
+ kdev->keychord_count = 0;
+ kdev->key_down = 0;
+ memset(kdev->keybit, 0, sizeof(kdev->keybit));
+ memset(kdev->keystate, 0, sizeof(kdev->keystate));
+ kdev->head = kdev->tail = 0;
+
+ keychord = keychords;
+
+ while (resid > 0) {
+ /* Is the entire keychord entry header present ? */
+ if (resid < sizeof(struct input_keychord)) {
+ pr_err("keychord: Insufficient bytes present for header %zu\n",
+ resid);
+ goto err_unlock_return;
+ }
+ resid -= sizeof(struct input_keychord);
+ if (keychord->count <= 0) {
+ pr_err("keychord: invalid keycode count %d\n",
+ keychord->count);
+ goto err_unlock_return;
+ }
+ key_bytes = keychord->count * sizeof(keychord->keycodes[0]);
+ /* Do we have all the expected keycodes ? */
+ if (resid < key_bytes) {
+ pr_err("keychord: Insufficient bytes present for keycount %zu\n",
+ resid);
+ goto err_unlock_return;
+ }
+ resid -= key_bytes;
+
+ if (keychord->version != KEYCHORD_VERSION) {
+ pr_err("keychord: unsupported version %d\n",
+ keychord->version);
+ goto err_unlock_return;
+ }
+
+ /* keep track of the keys we are monitoring in keybit */
+ for (i = 0; i < keychord->count; i++) {
+ key = keychord->keycodes[i];
+ if (key < 0 || key >= KEY_CNT) {
+ pr_err("keychord: keycode %d out of range\n",
+ key);
+ goto err_unlock_return;
+ }
+ __set_bit(key, kdev->keybit);
+ }
+
+ kdev->keychord_count++;
+ keychord = NEXT_KEYCHORD(keychord);
+ }
+
+ kdev->keychords = keychords;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ ret = input_register_handler(&kdev->input_handler);
+ if (ret) {
+ kfree(keychords);
+ kdev->keychords = 0;
+ keychord_write_unlock(kdev);
+ return ret;
+ }
+ kdev->registered = 1;
+
+ keychord_write_unlock(kdev);
+
+ return count;
+
+err_unlock_return:
+ spin_unlock_irqrestore(&kdev->lock, flags);
+ kfree(keychords);
+ keychord_write_unlock(kdev);
+ return -EINVAL;
+}
+
+static unsigned int keychord_poll(struct file *file, poll_table *wait)
+{
+ struct keychord_device *kdev = file->private_data;
+
+ poll_wait(file, &kdev->waitq, wait);
+
+ if (kdev->head != kdev->tail)
+ return POLLIN | POLLRDNORM;
+
+ return 0;
+}
+
+static int keychord_open(struct inode *inode, struct file *file)
+{
+ struct keychord_device *kdev;
+
+ kdev = kzalloc(sizeof(struct keychord_device), GFP_KERNEL);
+ if (!kdev)
+ return -ENOMEM;
+
+ spin_lock_init(&kdev->lock);
+ init_waitqueue_head(&kdev->waitq);
+ init_waitqueue_head(&kdev->write_waitq);
+
+ kdev->input_handler.event = keychord_event;
+ kdev->input_handler.connect = keychord_connect;
+ kdev->input_handler.disconnect = keychord_disconnect;
+ kdev->input_handler.name = KEYCHORD_NAME;
+ kdev->input_handler.id_table = kdev->device_ids;
+
+ kdev->device_ids[0].flags = INPUT_DEVICE_ID_MATCH_EVBIT;
+ __set_bit(EV_KEY, kdev->device_ids[0].evbit);
+
+ file->private_data = kdev;
+
+ return 0;
+}
+
+static int keychord_release(struct inode *inode, struct file *file)
+{
+ struct keychord_device *kdev = file->private_data;
+
+ if (kdev->registered)
+ input_unregister_handler(&kdev->input_handler);
+ kfree(kdev->keychords);
+ kfree(kdev);
+
+ return 0;
+}
+
+static const struct file_operations keychord_fops = {
+ .owner = THIS_MODULE,
+ .open = keychord_open,
+ .release = keychord_release,
+ .read = keychord_read,
+ .write = keychord_write,
+ .poll = keychord_poll,
+};
+
+static struct miscdevice keychord_misc = {
+ .fops = &keychord_fops,
+ .name = KEYCHORD_NAME,
+ .minor = MISC_DYNAMIC_MINOR,
+};
+
+static int __init keychord_init(void)
+{
+ return misc_register(&keychord_misc);
+}
+
+static void __exit keychord_exit(void)
+{
+ misc_deregister(&keychord_misc);
+}
+
+module_init(keychord_init);
+module_exit(keychord_exit);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 197e29d..e7b8f49 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -459,6 +459,21 @@
If unsure, say N.
+config DM_VERITY_HASH_PREFETCH_MIN_SIZE_128
+ bool "Prefetch size 128"
+
+config DM_VERITY_HASH_PREFETCH_MIN_SIZE
+ int "Verity hash prefetch minimum size"
+ depends on DM_VERITY
+ range 1 4096
+ default 128 if DM_VERITY_HASH_PREFETCH_MIN_SIZE_128
+ default 1
+ ---help---
+ This sets minimum number of hash blocks to prefetch for dm-verity.
+ For devices like eMMC, having larger prefetch size like 128 can improve
+ performance with increased memory consumption for keeping more hashes
+ in RAM.
+
config DM_VERITY_FEC
bool "Verity forward error correction support"
depends on DM_VERITY
@@ -501,4 +516,22 @@
If unsure, say N.
+config DM_ANDROID_VERITY
+ bool "Android verity target support"
+ depends on DM_VERITY=y
+ depends on X509_CERTIFICATE_PARSER
+ depends on SYSTEM_TRUSTED_KEYRING
+ depends on PUBLIC_KEY_ALGO_RSA
+ depends on KEYS
+ depends on ASYMMETRIC_KEY_TYPE
+ depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+ depends on MD_LINEAR=y
+ select DM_VERITY_HASH_PREFETCH_MIN_SIZE_128
+ ---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.
endif # MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 3cbda1a..f26ce41 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -59,6 +59,7 @@
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-$(CONFIG_DM_ANDROID_VERITY) += dm-android-verity.o
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c
new file mode 100644
index 0000000..eb4bdf6
--- /dev/null
+++ b/drivers/md/dm-android-verity.c
@@ -0,0 +1,947 @@
+/*
+ * 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/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 table_extract_mpi_array(struct public_key_signature *pks,
+ const void *data, size_t len)
+{
+ MPI mpi = mpi_read_raw_data(data, len);
+
+ if (!mpi) {
+ DMERR("Error while allocating mpi array");
+ return -ENOMEM;
+ }
+
+ pks->mpi[0] = mpi;
+ pks->nr_mpi = 1;
+ return 0;
+}
+
+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_hash_algo = 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 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;
+
+ 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(READ, 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 int verify_verity_signature(char *key_id,
+ struct android_metadata *metadata)
+{
+ key_ref_t key_ref;
+ struct key *key;
+ struct public_key_signature *pks = NULL;
+ int retval = -EINVAL;
+
+ key_ref = keyring_search(make_key_ref(system_trusted_keyring, 1),
+ &key_type_asymmetric, key_id);
+
+ if (IS_ERR(key_ref)) {
+ DMERR("keyring: key not found");
+ return -ENOKEY;
+ }
+
+ key = key_ref_to_ptr(key_ref);
+
+ 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;
+ }
+
+ retval = table_extract_mpi_array(pks, &metadata->header->signature[0],
+ RSANUMBYTES);
+ if (retval < 0) {
+ DMERR("Error extracting mpi %d", retval);
+ goto error;
+ }
+
+ retval = verify_signature(key, pks);
+ mpi_free(pks->rsa.s);
+error:
+ kfree(pks);
+ key_put(key);
+
+ return retval;
+}
+
+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 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, *table_ptr, dummy, *target_device,
+ *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;
+ }
+ } else if (argc == 2)
+ key_id = argv[1];
+ else {
+ DMERR("Incorrect number of arguments");
+ handle_error();
+ return -EINVAL;
+ }
+
+ target_device = argv[0];
+
+ 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 mount as verity target");
+ else {
+ target_added = true;
+ DMINFO("android-verity mounted 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-crypt.c b/drivers/md/dm-crypt.c
index 0aedd0e..7a5b75f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1866,16 +1866,24 @@ 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";
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a68c650..be13ebf 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1927,6 +1927,45 @@ 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 5ac239d..d837a28 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-fec.c b/drivers/md/dm-verity-fec.c
index 78f3601..3b62315 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;
@@ -572,6 +576,12 @@ 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;
@@ -660,6 +670,28 @@ 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.
*/
@@ -683,8 +715,10 @@ 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)) {
@@ -692,6 +726,16 @@ 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 0aba34a..5d0a996 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -501,6 +501,7 @@ static void verity_prefetch_io(struct work_struct *work)
container_of(work, struct dm_verity_prefetch_work, work);
struct dm_verity *v = pw->v;
int i;
+ sector_t prefetch_size;
for (i = v->levels - 2; i >= 0; i--) {
sector_t hash_block_start;
@@ -523,8 +524,14 @@ static void verity_prefetch_io(struct work_struct *work)
hash_block_end = v->hash_blocks - 1;
}
no_prefetch_cluster:
+ // for emmc, it is more efficient to send bigger read
+ prefetch_size = max((sector_t)CONFIG_DM_VERITY_HASH_PREFETCH_MIN_SIZE,
+ hash_block_end - hash_block_start + 1);
+ if ((hash_block_start + prefetch_size) >= (v->hash_start + v->hash_blocks)) {
+ prefetch_size = hash_block_end - hash_block_start + 1;
+ }
dm_bufio_prefetch(v->bufio, hash_block_start,
- hash_block_end - hash_block_start + 1);
+ prefetch_size);
}
kfree(pw);
@@ -551,7 +558,7 @@ 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 +599,12 @@ 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;
@@ -655,8 +663,9 @@ static void verity_status(struct dm_target *ti, status_type_t type,
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 +677,18 @@ 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 +700,9 @@ 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;
@@ -719,6 +731,7 @@ static void verity_dtr(struct dm_target *ti)
kfree(v);
}
+EXPORT_SYMBOL_GPL(verity_dtr);
static int verity_alloc_zero_digest(struct dm_verity *v)
{
@@ -817,7 +830,7 @@ 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;
@@ -1053,6 +1066,7 @@ 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",
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index fb419f4..75effca 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -126,4 +126,14 @@ 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);
#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/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 3198336..4a25950 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
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..42a513c
--- /dev/null
+++ b/drivers/misc/uid_sys_stats.c
@@ -0,0 +1,701 @@
+/* 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/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);
+ 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;
+ }
+
+ read_lock(&tasklist_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) {
+ read_unlock(&tasklist_lock);
+ 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);
+ read_unlock(&tasklist_lock);
+
+ 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;
+ }
+ 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 2553d90..00b9d7e 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;
@@ -3026,6 +3048,22 @@ 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;
@@ -3058,6 +3096,63 @@ 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 0c6de9f..3e5954f 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 f09148a..ad70934 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -847,6 +847,9 @@ 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) {
/*
@@ -873,7 +876,26 @@ 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;
}
@@ -1071,7 +1093,10 @@ 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);
@@ -1081,7 +1106,23 @@ 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);
@@ -1143,6 +1184,9 @@ 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);
@@ -1153,7 +1197,23 @@ 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:
@@ -1228,6 +1288,9 @@ 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);
@@ -1264,9 +1327,27 @@ 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/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/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/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/tun.c b/drivers/net/tun.c
index eb6dc28..5f51668 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2019,6 +2019,12 @@ 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/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/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 712936f..fbd26ec 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 798a32b..2062852 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -217,7 +217,8 @@ 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 3a98563..6e84e12 100644
--- a/drivers/nfc/st21nfca/se.c
+++ b/drivers/nfc/st21nfca/se.c
@@ -320,23 +320,33 @@ 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);
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 502f554..c0914fb 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1060,42 +1060,66 @@ 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/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/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index bcde8d1..fdb824f 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -107,7 +107,10 @@ 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,
@@ -198,6 +201,12 @@ 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/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 2e93412..fb4dafb 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"
@@ -1482,6 +1483,17 @@ 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];
@@ -3588,6 +3600,7 @@ 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];
@@ -3599,6 +3612,22 @@ 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);
@@ -6330,6 +6359,61 @@ 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
@@ -6345,6 +6429,7 @@ void ufshcd_remove(struct ufs_hba *hba)
scsi_host_put(hba->host);
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);
@@ -6658,6 +6743,8 @@ 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.
@@ -6674,6 +6761,7 @@ 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;
scsi_host_put(host);
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index f2170d5..b35a5b9 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -563,6 +563,9 @@ struct ufs_hba {
enum bkops_status urgent_bkops_lvl;
bool is_urgent_bkops_lvl_checked;
+ 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..7bd27a4 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -24,8 +24,19 @@
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.
+
source "drivers/staging/android/ion/Kconfig"
+source "drivers/staging/android/fiq_debugger/Kconfig"
+
endif # if ANDROID
endmenu
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index 7ed1be7..21b0ff4 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -1,6 +1,7 @@
ccflags-y += -I$(src) # needed for trace events
obj-y += ion/
+obj-$(CONFIG_FIQ_DEBUGGER) += fiq_debugger/
obj-$(CONFIG_ASHMEM) += ashmem.o
obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER) += lowmemorykiller.o
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 558a66b..eb41e84 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -410,22 +410,14 @@ 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;
@@ -462,9 +454,9 @@ 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/fiq_debugger/Kconfig b/drivers/staging/android/fiq_debugger/Kconfig
new file mode 100644
index 0000000..60fc224
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Kconfig
@@ -0,0 +1,58 @@
+config FIQ_DEBUGGER
+ bool "FIQ Mode Serial Debugger"
+ default n
+ depends on ARM || ARM64
+ help
+ The FIQ serial debugger can accept commands even when the
+ kernel is unresponsive due to being stuck with interrupts
+ disabled.
+
+config FIQ_DEBUGGER_NO_SLEEP
+ bool "Keep serial debugger active"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Enables the serial debugger at boot. Passing
+ fiq_debugger.no_sleep on the kernel commandline will
+ override this config option.
+
+config FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+ bool "Don't disable wakeup IRQ when debugger is active"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Don't disable the wakeup irq when enabling the uart clock. This will
+ cause extra interrupts, but it makes the serial debugger usable with
+ on some MSM radio builds that ignore the uart clock request in power
+ collapse.
+
+config FIQ_DEBUGGER_CONSOLE
+ bool "Console on FIQ Serial Debugger port"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Enables a console so that printk messages are displayed on
+ the debugger serial port as the occur.
+
+config FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+ bool "Put the FIQ debugger into console mode by default"
+ depends on FIQ_DEBUGGER_CONSOLE
+ default n
+ help
+ If enabled, this puts the fiq debugger into console mode by default.
+ Otherwise, the fiq debugger will start out in debug mode.
+
+config FIQ_DEBUGGER_UART_OVERLAY
+ bool "Install uart DT overlay"
+ depends on FIQ_DEBUGGER
+ select OF_OVERLAY
+ default n
+ help
+ If enabled, fiq debugger is calling fiq_debugger_uart_overlay()
+ that will apply overlay uart_overlay@0 to disable proper uart.
+
+config FIQ_WATCHDOG
+ bool
+ select FIQ_DEBUGGER
+ select PSTORE_RAM
+ default n
diff --git a/drivers/staging/android/fiq_debugger/Makefile b/drivers/staging/android/fiq_debugger/Makefile
new file mode 100644
index 0000000..a7ca487
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Makefile
@@ -0,0 +1,4 @@
+obj-y += fiq_debugger.o
+obj-$(CONFIG_ARM) += fiq_debugger_arm.o
+obj-$(CONFIG_ARM64) += fiq_debugger_arm64.o
+obj-$(CONFIG_FIQ_WATCHDOG) += fiq_watchdog.o
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.c b/drivers/staging/android/fiq_debugger/fiq_debugger.c
new file mode 100644
index 0000000..d9bc1253
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.c
@@ -0,0 +1,1246 @@
+/*
+ * drivers/staging/android/fiq_debugger.c
+ *
+ * Serial Debugger Interface accessed through an FIQ interrupt.
+ *
+ * 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.
+ */
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/console.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/kernel_stat.h>
+#include <linux/kmsg_dump.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/timer.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+
+#ifdef CONFIG_FIQ_GLUE
+#include <asm/fiq_glue.h>
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_UART_OVERLAY
+#include <linux/of.h>
+#endif
+
+#include <linux/uaccess.h>
+
+#include "fiq_debugger.h"
+#include "fiq_debugger_priv.h"
+#include "fiq_debugger_ringbuf.h"
+
+#define DEBUG_MAX 64
+#define MAX_UNHANDLED_FIQ_COUNT 1000000
+
+#define MAX_FIQ_DEBUGGER_PORTS 4
+
+struct fiq_debugger_state {
+#ifdef CONFIG_FIQ_GLUE
+ struct fiq_glue_handler handler;
+#endif
+ struct fiq_debugger_output output;
+
+ int fiq;
+ int uart_irq;
+ int signal_irq;
+ int wakeup_irq;
+ bool wakeup_irq_no_set_wake;
+ struct clk *clk;
+ struct fiq_debugger_pdata *pdata;
+ struct platform_device *pdev;
+
+ char debug_cmd[DEBUG_MAX];
+ int debug_busy;
+ int debug_abort;
+
+ char debug_buf[DEBUG_MAX];
+ int debug_count;
+
+ bool no_sleep;
+ bool debug_enable;
+ bool ignore_next_wakeup_irq;
+ struct timer_list sleep_timer;
+ spinlock_t sleep_timer_lock;
+ bool uart_enabled;
+ struct wakeup_source debugger_wake_src;
+ bool console_enable;
+ int current_cpu;
+ atomic_t unhandled_fiq_count;
+ bool in_fiq;
+
+ struct work_struct work;
+ spinlock_t work_lock;
+ char work_cmd[DEBUG_MAX];
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+ spinlock_t console_lock;
+ struct console console;
+ struct tty_port tty_port;
+ struct fiq_debugger_ringbuf *tty_rbuf;
+ bool syslog_dumping;
+#endif
+
+ unsigned int last_irqs[NR_IRQS];
+ unsigned int last_local_timer_irqs[NR_CPUS];
+};
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+struct tty_driver *fiq_tty_driver;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_NO_SLEEP
+static bool initial_no_sleep = true;
+#else
+static bool initial_no_sleep;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+static bool initial_debug_enable = true;
+static bool initial_console_enable = true;
+#else
+static bool initial_debug_enable;
+static bool initial_console_enable;
+#endif
+
+static bool fiq_kgdb_enable;
+static bool fiq_debugger_disable;
+
+module_param_named(no_sleep, initial_no_sleep, bool, 0644);
+module_param_named(debug_enable, initial_debug_enable, bool, 0644);
+module_param_named(console_enable, initial_console_enable, bool, 0644);
+module_param_named(kgdb_enable, fiq_kgdb_enable, bool, 0644);
+module_param_named(disable, fiq_debugger_disable, bool, 0644);
+
+#ifdef CONFIG_FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state) {}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state) {}
+#else
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state)
+{
+ if (state->wakeup_irq < 0)
+ return;
+ enable_irq(state->wakeup_irq);
+ if (!state->wakeup_irq_no_set_wake)
+ enable_irq_wake(state->wakeup_irq);
+}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state)
+{
+ if (state->wakeup_irq < 0)
+ return;
+ disable_irq_nosync(state->wakeup_irq);
+ if (!state->wakeup_irq_no_set_wake)
+ disable_irq_wake(state->wakeup_irq);
+}
+#endif
+
+static inline bool fiq_debugger_have_fiq(struct fiq_debugger_state *state)
+{
+ return (state->fiq >= 0);
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_force_irq(struct fiq_debugger_state *state)
+{
+ unsigned int irq = state->signal_irq;
+
+ if (WARN_ON(!fiq_debugger_have_fiq(state)))
+ return;
+ if (state->pdata->force_irq) {
+ state->pdata->force_irq(state->pdev, irq);
+ } else {
+ struct irq_chip *chip = irq_get_chip(irq);
+ if (chip && chip->irq_retrigger)
+ chip->irq_retrigger(irq_get_irq_data(irq));
+ }
+}
+#endif
+
+static void fiq_debugger_uart_enable(struct fiq_debugger_state *state)
+{
+ if (state->clk)
+ clk_enable(state->clk);
+ if (state->pdata->uart_enable)
+ state->pdata->uart_enable(state->pdev);
+}
+
+static void fiq_debugger_uart_disable(struct fiq_debugger_state *state)
+{
+ if (state->pdata->uart_disable)
+ state->pdata->uart_disable(state->pdev);
+ if (state->clk)
+ clk_disable(state->clk);
+}
+
+static void fiq_debugger_uart_flush(struct fiq_debugger_state *state)
+{
+ if (state->pdata->uart_flush)
+ state->pdata->uart_flush(state->pdev);
+}
+
+static void fiq_debugger_putc(struct fiq_debugger_state *state, char c)
+{
+ state->pdata->uart_putc(state->pdev, c);
+}
+
+static void fiq_debugger_puts(struct fiq_debugger_state *state, char *s)
+{
+ unsigned c;
+ while ((c = *s++)) {
+ if (c == '\n')
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, c);
+ }
+}
+
+static void fiq_debugger_prompt(struct fiq_debugger_state *state)
+{
+ fiq_debugger_puts(state, "debug> ");
+}
+
+static void fiq_debugger_dump_kernel_log(struct fiq_debugger_state *state)
+{
+ char buf[512];
+ size_t len;
+ struct kmsg_dumper dumper = { .active = true };
+
+
+ kmsg_dump_rewind_nolock(&dumper);
+ while (kmsg_dump_get_line_nolock(&dumper, true, buf,
+ sizeof(buf) - 1, &len)) {
+ buf[len] = 0;
+ fiq_debugger_puts(state, buf);
+ }
+}
+
+static void fiq_debugger_printf(struct fiq_debugger_output *output,
+ const char *fmt, ...)
+{
+ struct fiq_debugger_state *state;
+ char buf[256];
+ va_list ap;
+
+ state = container_of(output, struct fiq_debugger_state, output);
+ va_start(ap, fmt);
+ vsnprintf(buf, sizeof(buf), fmt, ap);
+ va_end(ap);
+
+ fiq_debugger_puts(state, buf);
+}
+
+/* Safe outside fiq context */
+static int fiq_debugger_printf_nfiq(void *cookie, const char *fmt, ...)
+{
+ struct fiq_debugger_state *state = cookie;
+ char buf[256];
+ va_list ap;
+ unsigned long irq_flags;
+
+ va_start(ap, fmt);
+ vsnprintf(buf, 128, fmt, ap);
+ va_end(ap);
+
+ local_irq_save(irq_flags);
+ fiq_debugger_puts(state, buf);
+ fiq_debugger_uart_flush(state);
+ local_irq_restore(irq_flags);
+ return state->debug_abort;
+}
+
+static void fiq_debugger_dump_irqs(struct fiq_debugger_state *state)
+{
+ int n;
+ struct irq_desc *desc;
+
+ fiq_debugger_printf(&state->output,
+ "irqnr total since-last status name\n");
+ for_each_irq_desc(n, desc) {
+ struct irqaction *act = desc->action;
+ if (!act && !kstat_irqs(n))
+ continue;
+ fiq_debugger_printf(&state->output, "%5d: %10u %11u %8x %s\n", n,
+ kstat_irqs(n),
+ kstat_irqs(n) - state->last_irqs[n],
+ desc->status_use_accessors,
+ (act && act->name) ? act->name : "???");
+ state->last_irqs[n] = kstat_irqs(n);
+ }
+}
+
+static void fiq_debugger_do_ps(struct fiq_debugger_state *state)
+{
+ struct task_struct *g;
+ struct task_struct *p;
+ unsigned task_state;
+ static const char stat_nam[] = "RSDTtZX";
+
+ fiq_debugger_printf(&state->output, "pid ppid prio task pc\n");
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ task_state = p->state ? __ffs(p->state) + 1 : 0;
+ fiq_debugger_printf(&state->output,
+ "%5d %5d %4d ", p->pid, p->parent->pid, p->prio);
+ fiq_debugger_printf(&state->output, "%-13.13s %c", p->comm,
+ task_state >= sizeof(stat_nam) ? '?' : stat_nam[task_state]);
+ if (task_state == TASK_RUNNING)
+ fiq_debugger_printf(&state->output, " running\n");
+ else
+ fiq_debugger_printf(&state->output, " %08lx\n",
+ thread_saved_pc(p));
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
+}
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+ state->syslog_dumping = true;
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+ state->syslog_dumping = false;
+}
+#else
+extern int do_syslog(int type, char __user *bug, int count);
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+ do_syslog(5 /* clear */, NULL, 0);
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+ fiq_debugger_dump_kernel_log(state);
+}
+#endif
+
+static void fiq_debugger_do_sysrq(struct fiq_debugger_state *state, char rq)
+{
+ if ((rq == 'g' || rq == 'G') && !fiq_kgdb_enable) {
+ fiq_debugger_printf(&state->output, "sysrq-g blocked\n");
+ return;
+ }
+ fiq_debugger_begin_syslog_dump(state);
+ handle_sysrq(rq);
+ fiq_debugger_end_syslog_dump(state);
+}
+
+#ifdef CONFIG_KGDB
+static void fiq_debugger_do_kgdb(struct fiq_debugger_state *state)
+{
+ if (!fiq_kgdb_enable) {
+ fiq_debugger_printf(&state->output, "kgdb through fiq debugger not enabled\n");
+ return;
+ }
+
+ fiq_debugger_printf(&state->output, "enabling console and triggering kgdb\n");
+ state->console_enable = true;
+ handle_sysrq('g');
+}
+#endif
+
+static void fiq_debugger_schedule_work(struct fiq_debugger_state *state,
+ char *cmd)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->work_lock, flags);
+ if (state->work_cmd[0] != '\0') {
+ fiq_debugger_printf(&state->output, "work command processor busy\n");
+ spin_unlock_irqrestore(&state->work_lock, flags);
+ return;
+ }
+
+ strlcpy(state->work_cmd, cmd, sizeof(state->work_cmd));
+ spin_unlock_irqrestore(&state->work_lock, flags);
+
+ schedule_work(&state->work);
+}
+
+static void fiq_debugger_work(struct work_struct *work)
+{
+ struct fiq_debugger_state *state;
+ char work_cmd[DEBUG_MAX];
+ char *cmd;
+ unsigned long flags;
+
+ state = container_of(work, struct fiq_debugger_state, work);
+
+ spin_lock_irqsave(&state->work_lock, flags);
+
+ strlcpy(work_cmd, state->work_cmd, sizeof(work_cmd));
+ state->work_cmd[0] = '\0';
+
+ spin_unlock_irqrestore(&state->work_lock, flags);
+
+ cmd = work_cmd;
+ if (!strncmp(cmd, "reboot", 6)) {
+ cmd += 6;
+ while (*cmd == ' ')
+ cmd++;
+ if (*cmd != '\0')
+ kernel_restart(cmd);
+ else
+ kernel_restart(NULL);
+ } else {
+ fiq_debugger_printf(&state->output, "unknown work command '%s'\n",
+ work_cmd);
+ }
+}
+
+/* This function CANNOT be called in FIQ context */
+static void fiq_debugger_irq_exec(struct fiq_debugger_state *state, char *cmd)
+{
+ if (!strcmp(cmd, "ps"))
+ fiq_debugger_do_ps(state);
+ if (!strcmp(cmd, "sysrq"))
+ fiq_debugger_do_sysrq(state, 'h');
+ if (!strncmp(cmd, "sysrq ", 6))
+ fiq_debugger_do_sysrq(state, cmd[6]);
+#ifdef CONFIG_KGDB
+ if (!strcmp(cmd, "kgdb"))
+ fiq_debugger_do_kgdb(state);
+#endif
+ if (!strncmp(cmd, "reboot", 6))
+ fiq_debugger_schedule_work(state, cmd);
+}
+
+static void fiq_debugger_help(struct fiq_debugger_state *state)
+{
+ fiq_debugger_printf(&state->output,
+ "FIQ Debugger commands:\n"
+ " pc PC status\n"
+ " regs Register dump\n"
+ " allregs Extended Register dump\n"
+ " bt Stack trace\n"
+ " reboot [<c>] Reboot with command <c>\n"
+ " reset [<c>] Hard reset with command <c>\n"
+ " irqs Interupt status\n"
+ " kmsg Kernel log\n"
+ " version Kernel version\n");
+ fiq_debugger_printf(&state->output,
+ " sleep Allow sleep while in FIQ\n"
+ " nosleep Disable sleep while in FIQ\n"
+ " console Switch terminal to console\n"
+ " cpu Current CPU\n"
+ " cpu <number> Switch to CPU<number>\n");
+ fiq_debugger_printf(&state->output,
+ " ps Process list\n"
+ " sysrq sysrq options\n"
+ " sysrq <param> Execute sysrq with <param>\n");
+#ifdef CONFIG_KGDB
+ fiq_debugger_printf(&state->output,
+ " kgdb Enter kernel debugger\n");
+#endif
+}
+
+static void fiq_debugger_take_affinity(void *info)
+{
+ struct fiq_debugger_state *state = info;
+ struct cpumask cpumask;
+
+ cpumask_clear(&cpumask);
+ cpumask_set_cpu(get_cpu(), &cpumask);
+
+ irq_set_affinity(state->uart_irq, &cpumask);
+}
+
+static void fiq_debugger_switch_cpu(struct fiq_debugger_state *state, int cpu)
+{
+ if (!fiq_debugger_have_fiq(state))
+ smp_call_function_single(cpu, fiq_debugger_take_affinity, state,
+ false);
+ state->current_cpu = cpu;
+}
+
+static bool fiq_debugger_fiq_exec(struct fiq_debugger_state *state,
+ const char *cmd, const struct pt_regs *regs,
+ void *svc_sp)
+{
+ bool signal_helper = false;
+
+ if (!strcmp(cmd, "help") || !strcmp(cmd, "?")) {
+ fiq_debugger_help(state);
+ } else if (!strcmp(cmd, "pc")) {
+ fiq_debugger_dump_pc(&state->output, regs);
+ } else if (!strcmp(cmd, "regs")) {
+ fiq_debugger_dump_regs(&state->output, regs);
+ } else if (!strcmp(cmd, "allregs")) {
+ fiq_debugger_dump_allregs(&state->output, regs);
+ } else if (!strcmp(cmd, "bt")) {
+ fiq_debugger_dump_stacktrace(&state->output, regs, 100, svc_sp);
+ } else if (!strncmp(cmd, "reset", 5)) {
+ cmd += 5;
+ while (*cmd == ' ')
+ cmd++;
+ if (*cmd) {
+ char tmp_cmd[32];
+ strlcpy(tmp_cmd, cmd, sizeof(tmp_cmd));
+ machine_restart(tmp_cmd);
+ } else {
+ machine_restart(NULL);
+ }
+ } else if (!strcmp(cmd, "irqs")) {
+ fiq_debugger_dump_irqs(state);
+ } else if (!strcmp(cmd, "kmsg")) {
+ fiq_debugger_dump_kernel_log(state);
+ } else if (!strcmp(cmd, "version")) {
+ fiq_debugger_printf(&state->output, "%s\n", linux_banner);
+ } else if (!strcmp(cmd, "sleep")) {
+ state->no_sleep = false;
+ fiq_debugger_printf(&state->output, "enabling sleep\n");
+ } else if (!strcmp(cmd, "nosleep")) {
+ state->no_sleep = true;
+ fiq_debugger_printf(&state->output, "disabling sleep\n");
+ } else if (!strcmp(cmd, "console")) {
+ fiq_debugger_printf(&state->output, "console mode\n");
+ fiq_debugger_uart_flush(state);
+ state->console_enable = true;
+ } else if (!strcmp(cmd, "cpu")) {
+ fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+ } else if (!strncmp(cmd, "cpu ", 4)) {
+ unsigned long cpu = 0;
+ if (kstrtoul(cmd + 4, 10, &cpu) == 0)
+ fiq_debugger_switch_cpu(state, cpu);
+ else
+ fiq_debugger_printf(&state->output, "invalid cpu\n");
+ fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+ } else {
+ if (state->debug_busy) {
+ fiq_debugger_printf(&state->output,
+ "command processor busy. trying to abort.\n");
+ state->debug_abort = -1;
+ } else {
+ strcpy(state->debug_cmd, cmd);
+ state->debug_busy = 1;
+ }
+
+ return true;
+ }
+ if (!state->console_enable)
+ fiq_debugger_prompt(state);
+
+ return signal_helper;
+}
+
+static void fiq_debugger_sleep_timer_expired(unsigned long data)
+{
+ struct fiq_debugger_state *state = (struct fiq_debugger_state *)data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ if (state->uart_enabled && !state->no_sleep) {
+ if (state->debug_enable && !state->console_enable) {
+ state->debug_enable = false;
+ fiq_debugger_printf_nfiq(state,
+ "suspending fiq debugger\n");
+ }
+ state->ignore_next_wakeup_irq = true;
+ fiq_debugger_uart_disable(state);
+ state->uart_enabled = false;
+ fiq_debugger_enable_wakeup_irq(state);
+ }
+ __pm_relax(&state->debugger_wake_src);
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static void fiq_debugger_handle_wakeup(struct fiq_debugger_state *state)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ if (state->wakeup_irq >= 0 && state->ignore_next_wakeup_irq) {
+ state->ignore_next_wakeup_irq = false;
+ } else if (!state->uart_enabled) {
+ __pm_stay_awake(&state->debugger_wake_src);
+ fiq_debugger_uart_enable(state);
+ state->uart_enabled = true;
+ fiq_debugger_disable_wakeup_irq(state);
+ mod_timer(&state->sleep_timer, jiffies + HZ / 2);
+ }
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static irqreturn_t fiq_debugger_wakeup_irq_handler(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+
+ if (!state->no_sleep)
+ fiq_debugger_puts(state, "WAKEUP\n");
+ fiq_debugger_handle_wakeup(state);
+
+ return IRQ_HANDLED;
+}
+
+static
+void fiq_debugger_handle_console_irq_context(struct fiq_debugger_state *state)
+{
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ if (state->tty_port.ops) {
+ int i;
+ int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+ for (i = 0; i < count; i++) {
+ int c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+ tty_insert_flip_char(&state->tty_port, c, TTY_NORMAL);
+ if (!fiq_debugger_ringbuf_consume(state->tty_rbuf, 1))
+ pr_warn("fiq tty failed to consume byte\n");
+ }
+ tty_flip_buffer_push(&state->tty_port);
+ }
+#endif
+}
+
+static void fiq_debugger_handle_irq_context(struct fiq_debugger_state *state)
+{
+ if (!state->no_sleep) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ __pm_stay_awake(&state->debugger_wake_src);
+ mod_timer(&state->sleep_timer, jiffies + HZ * 5);
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+ }
+ fiq_debugger_handle_console_irq_context(state);
+ if (state->debug_busy) {
+ fiq_debugger_irq_exec(state, state->debug_cmd);
+ if (!state->console_enable)
+ fiq_debugger_prompt(state);
+ state->debug_busy = 0;
+ }
+}
+
+static int fiq_debugger_getc(struct fiq_debugger_state *state)
+{
+ return state->pdata->uart_getc(state->pdev);
+}
+
+static bool fiq_debugger_handle_uart_interrupt(struct fiq_debugger_state *state,
+ int this_cpu, const struct pt_regs *regs, void *svc_sp)
+{
+ int c;
+ static int last_c;
+ int count = 0;
+ bool signal_helper = false;
+
+ if (this_cpu != state->current_cpu) {
+ if (state->in_fiq)
+ return false;
+
+ if (atomic_inc_return(&state->unhandled_fiq_count) !=
+ MAX_UNHANDLED_FIQ_COUNT)
+ return false;
+
+ fiq_debugger_printf(&state->output,
+ "fiq_debugger: cpu %d not responding, "
+ "reverting to cpu %d\n", state->current_cpu,
+ this_cpu);
+
+ atomic_set(&state->unhandled_fiq_count, 0);
+ fiq_debugger_switch_cpu(state, this_cpu);
+ return false;
+ }
+
+ state->in_fiq = true;
+
+ while ((c = fiq_debugger_getc(state)) != FIQ_DEBUGGER_NO_CHAR) {
+ count++;
+ if (!state->debug_enable) {
+ if ((c == 13) || (c == 10)) {
+ state->debug_enable = true;
+ state->debug_count = 0;
+ fiq_debugger_prompt(state);
+ }
+ } else if (c == FIQ_DEBUGGER_BREAK) {
+ state->console_enable = false;
+ fiq_debugger_puts(state, "fiq debugger mode\n");
+ state->debug_count = 0;
+ fiq_debugger_prompt(state);
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+ } else if (state->console_enable && state->tty_rbuf) {
+ fiq_debugger_ringbuf_push(state->tty_rbuf, c);
+ signal_helper = true;
+#endif
+ } else if ((c >= ' ') && (c < 127)) {
+ if (state->debug_count < (DEBUG_MAX - 1)) {
+ state->debug_buf[state->debug_count++] = c;
+ fiq_debugger_putc(state, c);
+ }
+ } else if ((c == 8) || (c == 127)) {
+ if (state->debug_count > 0) {
+ state->debug_count--;
+ fiq_debugger_putc(state, 8);
+ fiq_debugger_putc(state, ' ');
+ fiq_debugger_putc(state, 8);
+ }
+ } else if ((c == 13) || (c == 10)) {
+ if (c == '\r' || (c == '\n' && last_c != '\r')) {
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, '\n');
+ }
+ if (state->debug_count) {
+ state->debug_buf[state->debug_count] = 0;
+ state->debug_count = 0;
+ signal_helper |=
+ fiq_debugger_fiq_exec(state,
+ state->debug_buf,
+ regs, svc_sp);
+ } else {
+ fiq_debugger_prompt(state);
+ }
+ }
+ last_c = c;
+ }
+ if (!state->console_enable)
+ fiq_debugger_uart_flush(state);
+ if (state->pdata->fiq_ack)
+ state->pdata->fiq_ack(state->pdev, state->fiq);
+
+ /* poke sleep timer if necessary */
+ if (state->debug_enable && !state->no_sleep)
+ signal_helper = true;
+
+ atomic_set(&state->unhandled_fiq_count, 0);
+ state->in_fiq = false;
+
+ return signal_helper;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_fiq(struct fiq_glue_handler *h,
+ const struct pt_regs *regs, void *svc_sp)
+{
+ struct fiq_debugger_state *state =
+ container_of(h, struct fiq_debugger_state, handler);
+ unsigned int this_cpu = THREAD_INFO(svc_sp)->cpu;
+ bool need_irq;
+
+ need_irq = fiq_debugger_handle_uart_interrupt(state, this_cpu, regs,
+ svc_sp);
+ if (need_irq)
+ fiq_debugger_force_irq(state);
+}
+#endif
+
+/*
+ * When not using FIQs, we only use this single interrupt as an entry point.
+ * This just effectively takes over the UART interrupt and does all the work
+ * in this context.
+ */
+static irqreturn_t fiq_debugger_uart_irq(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+ bool not_done;
+
+ fiq_debugger_handle_wakeup(state);
+
+ /* handle the debugger irq in regular context */
+ not_done = fiq_debugger_handle_uart_interrupt(state, smp_processor_id(),
+ get_irq_regs(),
+ current_thread_info());
+ if (not_done)
+ fiq_debugger_handle_irq_context(state);
+
+ return IRQ_HANDLED;
+}
+
+/*
+ * If FIQs are used, not everything can happen in fiq context.
+ * FIQ handler does what it can and then signals this interrupt to finish the
+ * job in irq context.
+ */
+static irqreturn_t fiq_debugger_signal_irq(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+
+ if (state->pdata->force_irq_ack)
+ state->pdata->force_irq_ack(state->pdev, state->signal_irq);
+
+ fiq_debugger_handle_irq_context(state);
+
+ return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_resume(struct fiq_glue_handler *h)
+{
+ struct fiq_debugger_state *state =
+ container_of(h, struct fiq_debugger_state, handler);
+ if (state->pdata->uart_resume)
+ state->pdata->uart_resume(state->pdev);
+}
+#endif
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+struct tty_driver *fiq_debugger_console_device(struct console *co, int *index)
+{
+ *index = co->index;
+ return fiq_tty_driver;
+}
+
+static void fiq_debugger_console_write(struct console *co,
+ const char *s, unsigned int count)
+{
+ struct fiq_debugger_state *state;
+ unsigned long flags;
+
+ state = container_of(co, struct fiq_debugger_state, console);
+
+ if (!state->console_enable && !state->syslog_dumping)
+ return;
+
+ fiq_debugger_uart_enable(state);
+ spin_lock_irqsave(&state->console_lock, flags);
+ while (count--) {
+ if (*s == '\n')
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, *s++);
+ }
+ fiq_debugger_uart_flush(state);
+ spin_unlock_irqrestore(&state->console_lock, flags);
+ fiq_debugger_uart_disable(state);
+}
+
+static struct console fiq_debugger_console = {
+ .name = "ttyFIQ",
+ .device = fiq_debugger_console_device,
+ .write = fiq_debugger_console_write,
+ .flags = CON_PRINTBUFFER | CON_ANYTIME | CON_ENABLED,
+};
+
+int fiq_tty_open(struct tty_struct *tty, struct file *filp)
+{
+ int line = tty->index;
+ struct fiq_debugger_state **states = tty->driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+
+ return tty_port_open(&state->tty_port, tty, filp);
+}
+
+void fiq_tty_close(struct tty_struct *tty, struct file *filp)
+{
+ tty_port_close(tty->port, tty, filp);
+}
+
+int fiq_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+{
+ int i;
+ int line = tty->index;
+ struct fiq_debugger_state **states = tty->driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+
+ if (!state->console_enable)
+ return count;
+
+ fiq_debugger_uart_enable(state);
+ spin_lock_irq(&state->console_lock);
+ for (i = 0; i < count; i++)
+ fiq_debugger_putc(state, *buf++);
+ spin_unlock_irq(&state->console_lock);
+ fiq_debugger_uart_disable(state);
+
+ return count;
+}
+
+int fiq_tty_write_room(struct tty_struct *tty)
+{
+ return 16;
+}
+
+#ifdef CONFIG_CONSOLE_POLL
+static int fiq_tty_poll_init(struct tty_driver *driver, int line, char *options)
+{
+ return 0;
+}
+
+static int fiq_tty_poll_get_char(struct tty_driver *driver, int line)
+{
+ struct fiq_debugger_state **states = driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+ int c = NO_POLL_CHAR;
+
+ fiq_debugger_uart_enable(state);
+ if (fiq_debugger_have_fiq(state)) {
+ int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+ if (count > 0) {
+ c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+ fiq_debugger_ringbuf_consume(state->tty_rbuf, 1);
+ }
+ } else {
+ c = fiq_debugger_getc(state);
+ if (c == FIQ_DEBUGGER_NO_CHAR)
+ c = NO_POLL_CHAR;
+ }
+ fiq_debugger_uart_disable(state);
+
+ return c;
+}
+
+static void fiq_tty_poll_put_char(struct tty_driver *driver, int line, char ch)
+{
+ struct fiq_debugger_state **states = driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+ fiq_debugger_uart_enable(state);
+ fiq_debugger_putc(state, ch);
+ fiq_debugger_uart_disable(state);
+}
+#endif
+
+static const struct tty_port_operations fiq_tty_port_ops;
+
+static const struct tty_operations fiq_tty_driver_ops = {
+ .write = fiq_tty_write,
+ .write_room = fiq_tty_write_room,
+ .open = fiq_tty_open,
+ .close = fiq_tty_close,
+#ifdef CONFIG_CONSOLE_POLL
+ .poll_init = fiq_tty_poll_init,
+ .poll_get_char = fiq_tty_poll_get_char,
+ .poll_put_char = fiq_tty_poll_put_char,
+#endif
+};
+
+static int fiq_debugger_tty_init(void)
+{
+ int ret;
+ struct fiq_debugger_state **states = NULL;
+
+ states = kzalloc(sizeof(*states) * MAX_FIQ_DEBUGGER_PORTS, GFP_KERNEL);
+ if (!states) {
+ pr_err("Failed to allocate fiq debugger state structres\n");
+ return -ENOMEM;
+ }
+
+ fiq_tty_driver = alloc_tty_driver(MAX_FIQ_DEBUGGER_PORTS);
+ if (!fiq_tty_driver) {
+ pr_err("Failed to allocate fiq debugger tty\n");
+ ret = -ENOMEM;
+ goto err_free_state;
+ }
+
+ fiq_tty_driver->owner = THIS_MODULE;
+ fiq_tty_driver->driver_name = "fiq-debugger";
+ fiq_tty_driver->name = "ttyFIQ";
+ fiq_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
+ fiq_tty_driver->subtype = SERIAL_TYPE_NORMAL;
+ fiq_tty_driver->init_termios = tty_std_termios;
+ fiq_tty_driver->flags = TTY_DRIVER_REAL_RAW |
+ TTY_DRIVER_DYNAMIC_DEV;
+ fiq_tty_driver->driver_state = states;
+
+ fiq_tty_driver->init_termios.c_cflag =
+ B115200 | CS8 | CREAD | HUPCL | CLOCAL;
+ fiq_tty_driver->init_termios.c_ispeed = 115200;
+ fiq_tty_driver->init_termios.c_ospeed = 115200;
+
+ tty_set_operations(fiq_tty_driver, &fiq_tty_driver_ops);
+
+ ret = tty_register_driver(fiq_tty_driver);
+ if (ret) {
+ pr_err("Failed to register fiq tty: %d\n", ret);
+ goto err_free_tty;
+ }
+
+ pr_info("Registered FIQ tty driver\n");
+ return 0;
+
+err_free_tty:
+ put_tty_driver(fiq_tty_driver);
+ fiq_tty_driver = NULL;
+err_free_state:
+ kfree(states);
+ return ret;
+}
+
+static int fiq_debugger_tty_init_one(struct fiq_debugger_state *state)
+{
+ int ret;
+ struct device *tty_dev;
+ struct fiq_debugger_state **states = fiq_tty_driver->driver_state;
+
+ states[state->pdev->id] = state;
+
+ state->tty_rbuf = fiq_debugger_ringbuf_alloc(1024);
+ if (!state->tty_rbuf) {
+ pr_err("Failed to allocate fiq debugger ringbuf\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ tty_port_init(&state->tty_port);
+ state->tty_port.ops = &fiq_tty_port_ops;
+
+ tty_dev = tty_port_register_device(&state->tty_port, fiq_tty_driver,
+ state->pdev->id, &state->pdev->dev);
+ if (IS_ERR(tty_dev)) {
+ pr_err("Failed to register fiq debugger tty device\n");
+ ret = PTR_ERR(tty_dev);
+ goto err;
+ }
+
+ device_set_wakeup_capable(tty_dev, 1);
+
+ pr_info("Registered fiq debugger ttyFIQ%d\n", state->pdev->id);
+
+ return 0;
+
+err:
+ fiq_debugger_ringbuf_free(state->tty_rbuf);
+ state->tty_rbuf = NULL;
+ return ret;
+}
+#endif
+
+static int fiq_debugger_dev_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+ if (state->pdata->uart_dev_suspend)
+ return state->pdata->uart_dev_suspend(pdev);
+ return 0;
+}
+
+static int fiq_debugger_dev_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+ if (state->pdata->uart_dev_resume)
+ return state->pdata->uart_dev_resume(pdev);
+ return 0;
+}
+
+static int fiq_debugger_probe(struct platform_device *pdev)
+{
+ int ret;
+ struct fiq_debugger_pdata *pdata = dev_get_platdata(&pdev->dev);
+ struct fiq_debugger_state *state;
+ int fiq;
+ int uart_irq;
+
+ if (pdev->id >= MAX_FIQ_DEBUGGER_PORTS)
+ return -EINVAL;
+
+ if (!pdata->uart_getc || !pdata->uart_putc)
+ return -EINVAL;
+ if ((pdata->uart_enable && !pdata->uart_disable) ||
+ (!pdata->uart_enable && pdata->uart_disable))
+ return -EINVAL;
+
+ fiq = platform_get_irq_byname(pdev, "fiq");
+ uart_irq = platform_get_irq_byname(pdev, "uart_irq");
+
+ /* uart_irq mode and fiq mode are mutually exclusive, but one of them
+ * is required */
+ if ((uart_irq < 0 && fiq < 0) || (uart_irq >= 0 && fiq >= 0))
+ return -EINVAL;
+ if (fiq >= 0 && !pdata->fiq_enable)
+ return -EINVAL;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ state->output.printf = fiq_debugger_printf;
+ setup_timer(&state->sleep_timer, fiq_debugger_sleep_timer_expired,
+ (unsigned long)state);
+ state->pdata = pdata;
+ state->pdev = pdev;
+ state->no_sleep = initial_no_sleep;
+ state->debug_enable = initial_debug_enable;
+ state->console_enable = initial_console_enable;
+
+ state->fiq = fiq;
+ state->uart_irq = uart_irq;
+ state->signal_irq = platform_get_irq_byname(pdev, "signal");
+ state->wakeup_irq = platform_get_irq_byname(pdev, "wakeup");
+
+ INIT_WORK(&state->work, fiq_debugger_work);
+ spin_lock_init(&state->work_lock);
+
+ platform_set_drvdata(pdev, state);
+
+ spin_lock_init(&state->sleep_timer_lock);
+
+ if (state->wakeup_irq < 0 && fiq_debugger_have_fiq(state))
+ state->no_sleep = true;
+ state->ignore_next_wakeup_irq = !state->no_sleep;
+
+ wakeup_source_init(&state->debugger_wake_src, "serial-debug");
+
+ state->clk = clk_get(&pdev->dev, NULL);
+ if (IS_ERR(state->clk))
+ state->clk = NULL;
+
+ /* do not call pdata->uart_enable here since uart_init may still
+ * need to do some initialization before uart_enable can work.
+ * So, only try to manage the clock during init.
+ */
+ if (state->clk)
+ clk_enable(state->clk);
+
+ if (pdata->uart_init) {
+ ret = pdata->uart_init(pdev);
+ if (ret)
+ goto err_uart_init;
+ }
+
+ fiq_debugger_printf_nfiq(state,
+ "<hit enter %sto activate fiq debugger>\n",
+ state->no_sleep ? "" : "twice ");
+
+#ifdef CONFIG_FIQ_GLUE
+ if (fiq_debugger_have_fiq(state)) {
+ state->handler.fiq = fiq_debugger_fiq;
+ state->handler.resume = fiq_debugger_resume;
+ ret = fiq_glue_register_handler(&state->handler);
+ if (ret) {
+ pr_err("%s: could not install fiq handler\n", __func__);
+ goto err_register_irq;
+ }
+
+ pdata->fiq_enable(pdev, state->fiq, 1);
+ } else
+#endif
+ {
+ ret = request_irq(state->uart_irq, fiq_debugger_uart_irq,
+ IRQF_NO_SUSPEND, "debug", state);
+ if (ret) {
+ pr_err("%s: could not install irq handler\n", __func__);
+ goto err_register_irq;
+ }
+
+ /* for irq-only mode, we want this irq to wake us up, if it
+ * can.
+ */
+ enable_irq_wake(state->uart_irq);
+ }
+
+ if (state->clk)
+ clk_disable(state->clk);
+
+ if (state->signal_irq >= 0) {
+ ret = request_irq(state->signal_irq, fiq_debugger_signal_irq,
+ IRQF_TRIGGER_RISING, "debug-signal", state);
+ if (ret)
+ pr_err("serial_debugger: could not install signal_irq");
+ }
+
+ if (state->wakeup_irq >= 0) {
+ ret = request_irq(state->wakeup_irq,
+ fiq_debugger_wakeup_irq_handler,
+ IRQF_TRIGGER_FALLING,
+ "debug-wakeup", state);
+ if (ret) {
+ pr_err("serial_debugger: "
+ "could not install wakeup irq\n");
+ state->wakeup_irq = -1;
+ } else {
+ ret = enable_irq_wake(state->wakeup_irq);
+ if (ret) {
+ pr_err("serial_debugger: "
+ "could not enable wakeup\n");
+ state->wakeup_irq_no_set_wake = true;
+ }
+ }
+ }
+ if (state->no_sleep)
+ fiq_debugger_handle_wakeup(state);
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ spin_lock_init(&state->console_lock);
+ state->console = fiq_debugger_console;
+ state->console.index = pdev->id;
+ if (!console_set_on_cmdline)
+ add_preferred_console(state->console.name,
+ state->console.index, NULL);
+ register_console(&state->console);
+ fiq_debugger_tty_init_one(state);
+#endif
+ return 0;
+
+err_register_irq:
+ if (pdata->uart_free)
+ pdata->uart_free(pdev);
+err_uart_init:
+ if (state->clk)
+ clk_disable(state->clk);
+ if (state->clk)
+ clk_put(state->clk);
+ wakeup_source_trash(&state->debugger_wake_src);
+ platform_set_drvdata(pdev, NULL);
+ kfree(state);
+ return ret;
+}
+
+static const struct dev_pm_ops fiq_debugger_dev_pm_ops = {
+ .suspend = fiq_debugger_dev_suspend,
+ .resume = fiq_debugger_dev_resume,
+};
+
+static struct platform_driver fiq_debugger_driver = {
+ .probe = fiq_debugger_probe,
+ .driver = {
+ .name = "fiq_debugger",
+ .pm = &fiq_debugger_dev_pm_ops,
+ },
+};
+
+#if defined(CONFIG_FIQ_DEBUGGER_UART_OVERLAY)
+int fiq_debugger_uart_overlay(void)
+{
+ struct device_node *onp = of_find_node_by_path("/uart_overlay@0");
+ int ret;
+
+ if (!onp) {
+ pr_err("serial_debugger: uart overlay not found\n");
+ return -ENODEV;
+ }
+
+ ret = of_overlay_create(onp);
+ if (ret < 0) {
+ pr_err("serial_debugger: fail to create overlay: %d\n", ret);
+ of_node_put(onp);
+ return ret;
+ }
+
+ pr_info("serial_debugger: uart overlay applied\n");
+ return 0;
+}
+#endif
+
+static int __init fiq_debugger_init(void)
+{
+ if (fiq_debugger_disable) {
+ pr_err("serial_debugger: disabled\n");
+ return -ENODEV;
+ }
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ fiq_debugger_tty_init();
+#endif
+#if defined(CONFIG_FIQ_DEBUGGER_UART_OVERLAY)
+ fiq_debugger_uart_overlay();
+#endif
+ return platform_driver_register(&fiq_debugger_driver);
+}
+
+postcore_initcall(fiq_debugger_init);
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.h b/drivers/staging/android/fiq_debugger/fiq_debugger.h
new file mode 100644
index 0000000..c9ec4f8
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.h
@@ -0,0 +1,64 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Colin Cross <ccross@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 _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+#define _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+
+#include <linux/serial_core.h>
+
+#define FIQ_DEBUGGER_NO_CHAR NO_POLL_CHAR
+#define FIQ_DEBUGGER_BREAK 0x00ff0100
+
+#define FIQ_DEBUGGER_FIQ_IRQ_NAME "fiq"
+#define FIQ_DEBUGGER_SIGNAL_IRQ_NAME "signal"
+#define FIQ_DEBUGGER_WAKEUP_IRQ_NAME "wakeup"
+
+/**
+ * struct fiq_debugger_pdata - fiq debugger platform data
+ * @uart_resume: used to restore uart state right before enabling
+ * the fiq.
+ * @uart_enable: Do the work necessary to communicate with the uart
+ * hw (enable clocks, etc.). This must be ref-counted.
+ * @uart_disable: Do the work necessary to disable the uart hw
+ * (disable clocks, etc.). This must be ref-counted.
+ * @uart_dev_suspend: called during PM suspend, generally not needed
+ * for real fiq mode debugger.
+ * @uart_dev_resume: called during PM resume, generally not needed
+ * for real fiq mode debugger.
+ */
+struct fiq_debugger_pdata {
+ int (*uart_init)(struct platform_device *pdev);
+ void (*uart_free)(struct platform_device *pdev);
+ int (*uart_resume)(struct platform_device *pdev);
+ int (*uart_getc)(struct platform_device *pdev);
+ void (*uart_putc)(struct platform_device *pdev, unsigned int c);
+ void (*uart_flush)(struct platform_device *pdev);
+ void (*uart_enable)(struct platform_device *pdev);
+ void (*uart_disable)(struct platform_device *pdev);
+
+ int (*uart_dev_suspend)(struct platform_device *pdev);
+ int (*uart_dev_resume)(struct platform_device *pdev);
+
+ void (*fiq_enable)(struct platform_device *pdev, unsigned int fiq,
+ bool enable);
+ void (*fiq_ack)(struct platform_device *pdev, unsigned int fiq);
+
+ void (*force_irq)(struct platform_device *pdev, unsigned int irq);
+ void (*force_irq_ack)(struct platform_device *pdev, unsigned int irq);
+};
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
new file mode 100644
index 0000000..8b3e013
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@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/ptrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(unsigned cpsr)
+{
+ switch (cpsr & MODE_MASK) {
+ case USR_MODE: return "USR";
+ case FIQ_MODE: return "FIQ";
+ case IRQ_MODE: return "IRQ";
+ case SVC_MODE: return "SVC";
+ case ABT_MODE: return "ABT";
+ case UND_MODE: return "UND";
+ case SYSTEM_MODE: return "SYS";
+ default: return "???";
+ }
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " pc %08x cpsr %08x mode %s\n",
+ regs->ARM_pc, regs->ARM_cpsr, mode_name(regs->ARM_cpsr));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output,
+ " r0 %08x r1 %08x r2 %08x r3 %08x\n",
+ regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
+ output->printf(output,
+ " r4 %08x r5 %08x r6 %08x r7 %08x\n",
+ regs->ARM_r4, regs->ARM_r5, regs->ARM_r6, regs->ARM_r7);
+ output->printf(output,
+ " r8 %08x r9 %08x r10 %08x r11 %08x mode %s\n",
+ regs->ARM_r8, regs->ARM_r9, regs->ARM_r10, regs->ARM_fp,
+ mode_name(regs->ARM_cpsr));
+ output->printf(output,
+ " ip %08x sp %08x lr %08x pc %08x cpsr %08x\n",
+ regs->ARM_ip, regs->ARM_sp, regs->ARM_lr, regs->ARM_pc,
+ regs->ARM_cpsr);
+}
+
+struct mode_regs {
+ unsigned long sp_svc;
+ unsigned long lr_svc;
+ unsigned long spsr_svc;
+
+ unsigned long sp_abt;
+ unsigned long lr_abt;
+ unsigned long spsr_abt;
+
+ unsigned long sp_und;
+ unsigned long lr_und;
+ unsigned long spsr_und;
+
+ unsigned long sp_irq;
+ unsigned long lr_irq;
+ unsigned long spsr_irq;
+
+ unsigned long r8_fiq;
+ unsigned long r9_fiq;
+ unsigned long r10_fiq;
+ unsigned long r11_fiq;
+ unsigned long r12_fiq;
+ unsigned long sp_fiq;
+ unsigned long lr_fiq;
+ unsigned long spsr_fiq;
+};
+
+static void __naked get_mode_regs(struct mode_regs *regs)
+{
+ asm volatile (
+ "mrs r1, cpsr\n"
+ "msr cpsr_c, #0xd3 @(SVC_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd7 @(ABT_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xdb @(UND_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd2 @(IRQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd1 @(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r8 - r14}\n"
+ "mrs r2, spsr\n"
+ "stmia r0!, {r2}\n"
+ "msr cpsr_c, r1\n"
+ "bx lr\n");
+}
+
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ struct mode_regs mode_regs;
+ unsigned long mode = regs->ARM_cpsr & MODE_MASK;
+
+ fiq_debugger_dump_regs(output, regs);
+ get_mode_regs(&mode_regs);
+
+ output->printf(output,
+ "%csvc: sp %08x lr %08x spsr %08x\n",
+ mode == SVC_MODE ? '*' : ' ',
+ mode_regs.sp_svc, mode_regs.lr_svc, mode_regs.spsr_svc);
+ output->printf(output,
+ "%cabt: sp %08x lr %08x spsr %08x\n",
+ mode == ABT_MODE ? '*' : ' ',
+ mode_regs.sp_abt, mode_regs.lr_abt, mode_regs.spsr_abt);
+ output->printf(output,
+ "%cund: sp %08x lr %08x spsr %08x\n",
+ mode == UND_MODE ? '*' : ' ',
+ mode_regs.sp_und, mode_regs.lr_und, mode_regs.spsr_und);
+ output->printf(output,
+ "%cirq: sp %08x lr %08x spsr %08x\n",
+ mode == IRQ_MODE ? '*' : ' ',
+ mode_regs.sp_irq, mode_regs.lr_irq, mode_regs.spsr_irq);
+ output->printf(output,
+ "%cfiq: r8 %08x r9 %08x r10 %08x r11 %08x r12 %08x\n",
+ mode == FIQ_MODE ? '*' : ' ',
+ mode_regs.r8_fiq, mode_regs.r9_fiq, mode_regs.r10_fiq,
+ mode_regs.r11_fiq, mode_regs.r12_fiq);
+ output->printf(output,
+ " fiq: sp %08x lr %08x spsr %08x\n",
+ mode_regs.sp_fiq, mode_regs.lr_fiq, mode_regs.spsr_fiq);
+}
+
+struct stacktrace_state {
+ struct fiq_debugger_output *output;
+ unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+ struct stacktrace_state *sts = d;
+
+ if (sts->depth) {
+ sts->output->printf(sts->output,
+ " pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+ frame->pc, frame->pc, frame->lr, frame->lr,
+ frame->sp, frame->fp);
+ sts->depth--;
+ return 0;
+ }
+ sts->output->printf(sts->output, " ...\n");
+
+ return sts->depth == 0;
+}
+
+struct frame_tail {
+ struct frame_tail *fp;
+ unsigned long sp;
+ unsigned long lr;
+} __attribute__((packed));
+
+static struct frame_tail *user_backtrace(struct fiq_debugger_output *output,
+ struct frame_tail *tail)
+{
+ struct frame_tail buftail[2];
+
+ /* Also check accessibility of one struct frame_tail beyond */
+ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) {
+ output->printf(output, " invalid frame pointer %p\n",
+ tail);
+ return NULL;
+ }
+ if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) {
+ output->printf(output,
+ " failed to copy frame pointer %p\n", tail);
+ return NULL;
+ }
+
+ output->printf(output, " %p\n", buftail[0].lr);
+
+ /* frame pointers should strictly progress back up the stack
+ * (towards higher addresses) */
+ if (tail >= buftail[0].fp)
+ return NULL;
+
+ return buftail[0].fp-1;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+ struct frame_tail *tail;
+ struct thread_info *real_thread_info = THREAD_INFO(ssp);
+ struct stacktrace_state sts;
+
+ sts.depth = depth;
+ sts.output = output;
+ *current_thread_info() = *real_thread_info;
+
+ if (!current)
+ output->printf(output, "current NULL\n");
+ else
+ output->printf(output, "pid: %d comm: %s\n",
+ current->pid, current->comm);
+ fiq_debugger_dump_regs(output, regs);
+
+ if (!user_mode(regs)) {
+ struct stackframe frame;
+ frame.fp = regs->ARM_fp;
+ frame.sp = regs->ARM_sp;
+ frame.lr = regs->ARM_lr;
+ frame.pc = regs->ARM_pc;
+ output->printf(output,
+ " pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+ regs->ARM_pc, regs->ARM_pc, regs->ARM_lr, regs->ARM_lr,
+ regs->ARM_sp, regs->ARM_fp);
+ walk_stackframe(&frame, report_trace, &sts);
+ return;
+ }
+
+ tail = ((struct frame_tail *) regs->ARM_fp) - 1;
+ while (depth-- && tail && !((unsigned long) tail & 3))
+ tail = user_backtrace(output, tail);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
new file mode 100644
index 0000000..97246bc
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@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/ptrace.h>
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(const struct pt_regs *regs)
+{
+ if (compat_user_mode(regs)) {
+ return "USR";
+ } else {
+ switch (processor_mode(regs)) {
+ case PSR_MODE_EL0t: return "EL0t";
+ case PSR_MODE_EL1t: return "EL1t";
+ case PSR_MODE_EL1h: return "EL1h";
+ case PSR_MODE_EL2t: return "EL2t";
+ case PSR_MODE_EL2h: return "EL2h";
+ default: return "???";
+ }
+ }
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " pc %016lx cpsr %08lx mode %s\n",
+ regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch32(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " r0 %08x r1 %08x r2 %08x r3 %08x\n",
+ regs->compat_usr(0), regs->compat_usr(1),
+ regs->compat_usr(2), regs->compat_usr(3));
+ output->printf(output, " r4 %08x r5 %08x r6 %08x r7 %08x\n",
+ regs->compat_usr(4), regs->compat_usr(5),
+ regs->compat_usr(6), regs->compat_usr(7));
+ output->printf(output, " r8 %08x r9 %08x r10 %08x r11 %08x\n",
+ regs->compat_usr(8), regs->compat_usr(9),
+ regs->compat_usr(10), regs->compat_usr(11));
+ output->printf(output, " ip %08x sp %08x lr %08x pc %08x\n",
+ regs->compat_usr(12), regs->compat_sp,
+ regs->compat_lr, regs->pc);
+ output->printf(output, " cpsr %08x (%s)\n",
+ regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch64(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+
+ output->printf(output, " x0 %016lx x1 %016lx\n",
+ regs->regs[0], regs->regs[1]);
+ output->printf(output, " x2 %016lx x3 %016lx\n",
+ regs->regs[2], regs->regs[3]);
+ output->printf(output, " x4 %016lx x5 %016lx\n",
+ regs->regs[4], regs->regs[5]);
+ output->printf(output, " x6 %016lx x7 %016lx\n",
+ regs->regs[6], regs->regs[7]);
+ output->printf(output, " x8 %016lx x9 %016lx\n",
+ regs->regs[8], regs->regs[9]);
+ output->printf(output, " x10 %016lx x11 %016lx\n",
+ regs->regs[10], regs->regs[11]);
+ output->printf(output, " x12 %016lx x13 %016lx\n",
+ regs->regs[12], regs->regs[13]);
+ output->printf(output, " x14 %016lx x15 %016lx\n",
+ regs->regs[14], regs->regs[15]);
+ output->printf(output, " x16 %016lx x17 %016lx\n",
+ regs->regs[16], regs->regs[17]);
+ output->printf(output, " x18 %016lx x19 %016lx\n",
+ regs->regs[18], regs->regs[19]);
+ output->printf(output, " x20 %016lx x21 %016lx\n",
+ regs->regs[20], regs->regs[21]);
+ output->printf(output, " x22 %016lx x23 %016lx\n",
+ regs->regs[22], regs->regs[23]);
+ output->printf(output, " x24 %016lx x25 %016lx\n",
+ regs->regs[24], regs->regs[25]);
+ output->printf(output, " x26 %016lx x27 %016lx\n",
+ regs->regs[26], regs->regs[27]);
+ output->printf(output, " x28 %016lx x29 %016lx\n",
+ regs->regs[28], regs->regs[29]);
+ output->printf(output, " x30 %016lx sp %016lx\n",
+ regs->regs[30], regs->sp);
+ output->printf(output, " pc %016lx cpsr %08x (%s)\n",
+ regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ if (compat_user_mode(regs))
+ fiq_debugger_dump_regs_aarch32(output, regs);
+ else
+ fiq_debugger_dump_regs_aarch64(output, regs);
+}
+
+#define READ_SPECIAL_REG(x) ({ \
+ u64 val; \
+ asm volatile ("mrs %0, " # x : "=r"(val)); \
+ val; \
+})
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ u32 pstate = READ_SPECIAL_REG(CurrentEl);
+ bool in_el2 = (pstate & PSR_MODE_MASK) >= PSR_MODE_EL2t;
+
+ fiq_debugger_dump_regs(output, regs);
+
+ output->printf(output, " sp_el0 %016lx\n",
+ READ_SPECIAL_REG(sp_el0));
+
+ if (in_el2)
+ output->printf(output, " sp_el1 %016lx\n",
+ READ_SPECIAL_REG(sp_el1));
+
+ output->printf(output, " elr_el1 %016lx\n",
+ READ_SPECIAL_REG(elr_el1));
+
+ output->printf(output, " spsr_el1 %08lx\n",
+ READ_SPECIAL_REG(spsr_el1));
+
+ if (in_el2) {
+ output->printf(output, " spsr_irq %08lx\n",
+ READ_SPECIAL_REG(spsr_irq));
+ output->printf(output, " spsr_abt %08lx\n",
+ READ_SPECIAL_REG(spsr_abt));
+ output->printf(output, " spsr_und %08lx\n",
+ READ_SPECIAL_REG(spsr_und));
+ output->printf(output, " spsr_fiq %08lx\n",
+ READ_SPECIAL_REG(spsr_fiq));
+ output->printf(output, " spsr_el2 %08lx\n",
+ READ_SPECIAL_REG(elr_el2));
+ output->printf(output, " spsr_el2 %08lx\n",
+ READ_SPECIAL_REG(spsr_el2));
+ }
+}
+
+struct stacktrace_state {
+ struct fiq_debugger_output *output;
+ unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+ struct stacktrace_state *sts = d;
+
+ if (sts->depth) {
+ sts->output->printf(sts->output, "%pF:\n", frame->pc);
+ sts->output->printf(sts->output,
+ " pc %016lx sp %016lx fp %016lx\n",
+ frame->pc, frame->sp, frame->fp);
+ sts->depth--;
+ return 0;
+ }
+ sts->output->printf(sts->output, " ...\n");
+
+ return sts->depth == 0;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+ struct thread_info *real_thread_info = THREAD_INFO(ssp);
+ struct stacktrace_state sts;
+
+ sts.depth = depth;
+ sts.output = output;
+ *current_thread_info() = *real_thread_info;
+
+ if (!current)
+ output->printf(output, "current NULL\n");
+ else
+ output->printf(output, "pid: %d comm: %s\n",
+ current->pid, current->comm);
+ fiq_debugger_dump_regs(output, regs);
+
+ if (!user_mode(regs)) {
+ struct stackframe frame;
+ frame.fp = regs->regs[29];
+ frame.sp = regs->sp;
+ frame.pc = regs->pc;
+ output->printf(output, "\n");
+ walk_stackframe(current, &frame, report_trace, &sts);
+ }
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
new file mode 100644
index 0000000..d5d051f
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@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 _FIQ_DEBUGGER_PRIV_H_
+#define _FIQ_DEBUGGER_PRIV_H_
+
+#define THREAD_INFO(sp) ((struct thread_info *) \
+ ((unsigned long)(sp) & ~(THREAD_SIZE - 1)))
+
+struct fiq_debugger_output {
+ void (*printf)(struct fiq_debugger_output *output, const char *fmt, ...);
+};
+
+struct pt_regs;
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp);
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
new file mode 100644
index 0000000..10c3c5d
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
@@ -0,0 +1,94 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
+ *
+ * simple lockless ringbuffer
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+struct fiq_debugger_ringbuf {
+ int len;
+ int head;
+ int tail;
+ u8 buf[];
+};
+
+
+static inline struct fiq_debugger_ringbuf *fiq_debugger_ringbuf_alloc(int len)
+{
+ struct fiq_debugger_ringbuf *rbuf;
+
+ rbuf = kzalloc(sizeof(*rbuf) + len, GFP_KERNEL);
+ if (rbuf == NULL)
+ return NULL;
+
+ rbuf->len = len;
+ rbuf->head = 0;
+ rbuf->tail = 0;
+ smp_mb();
+
+ return rbuf;
+}
+
+static inline void fiq_debugger_ringbuf_free(struct fiq_debugger_ringbuf *rbuf)
+{
+ kfree(rbuf);
+}
+
+static inline int fiq_debugger_ringbuf_level(struct fiq_debugger_ringbuf *rbuf)
+{
+ int level = rbuf->head - rbuf->tail;
+
+ if (level < 0)
+ level = rbuf->len + level;
+
+ return level;
+}
+
+static inline int fiq_debugger_ringbuf_room(struct fiq_debugger_ringbuf *rbuf)
+{
+ return rbuf->len - fiq_debugger_ringbuf_level(rbuf) - 1;
+}
+
+static inline u8
+fiq_debugger_ringbuf_peek(struct fiq_debugger_ringbuf *rbuf, int i)
+{
+ return rbuf->buf[(rbuf->tail + i) % rbuf->len];
+}
+
+static inline int
+fiq_debugger_ringbuf_consume(struct fiq_debugger_ringbuf *rbuf, int count)
+{
+ count = min(count, fiq_debugger_ringbuf_level(rbuf));
+
+ rbuf->tail = (rbuf->tail + count) % rbuf->len;
+ smp_mb();
+
+ return count;
+}
+
+static inline int
+fiq_debugger_ringbuf_push(struct fiq_debugger_ringbuf *rbuf, u8 datum)
+{
+ if (fiq_debugger_ringbuf_room(rbuf) == 0)
+ return 0;
+
+ rbuf->buf[rbuf->head] = datum;
+ smp_mb();
+ rbuf->head = (rbuf->head + 1) % rbuf->len;
+ smp_mb();
+
+ return 1;
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.c b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
new file mode 100644
index 0000000..194b541
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
@@ -0,0 +1,56 @@
+/*
+ * 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/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/pstore_ram.h>
+
+#include "fiq_watchdog.h"
+#include "fiq_debugger_priv.h"
+
+static DEFINE_RAW_SPINLOCK(fiq_watchdog_lock);
+
+static void fiq_watchdog_printf(struct fiq_debugger_output *output,
+ const char *fmt, ...)
+{
+ char buf[256];
+ va_list ap;
+ int len;
+
+ va_start(ap, fmt);
+ len = vscnprintf(buf, sizeof(buf), fmt, ap);
+ va_end(ap);
+
+ ramoops_console_write_buf(buf, len);
+}
+
+struct fiq_debugger_output fiq_watchdog_output = {
+ .printf = fiq_watchdog_printf,
+};
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp)
+{
+ char msg[24];
+ int len;
+
+ raw_spin_lock(&fiq_watchdog_lock);
+
+ len = scnprintf(msg, sizeof(msg), "watchdog fiq cpu %d\n",
+ THREAD_INFO(svc_sp)->cpu);
+ ramoops_console_write_buf(msg, len);
+
+ fiq_debugger_dump_stacktrace(&fiq_watchdog_output, regs, 100, svc_sp);
+
+ raw_spin_unlock(&fiq_watchdog_lock);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.h b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
new file mode 100644
index 0000000..c6b507f
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
@@ -0,0 +1,20 @@
+/*
+ * 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 _FIQ_WATCHDOG_H_
+#define _FIQ_WATCHDOG_H_
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp);
+
+#endif
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index ec3b665..687be36 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -43,6 +43,9 @@
#include <linux/profile.h>
#include <linux/notifier.h>
+#define CREATE_TRACE_POINTS
+#include "trace/lowmemorykiller.h"
+
static u32 lowmem_debug_level = 1;
static short lowmem_adj[6] = {
0,
@@ -93,6 +96,7 @@ 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)
@@ -160,23 +164,27 @@ 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;
}
@@ -200,12 +208,96 @@ static int __init lowmem_init(void)
}
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/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/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..ed2d71c
--- /dev/null
+++ b/drivers/tee/tee_shm.c
@@ -0,0 +1,510 @@
+/*
+ * 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;
+
+ fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
+ if (fd >= 0)
+ get_dma_buf(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..2d855a9 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 const (*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/serial_core.c b/drivers/tty/serial/serial_core.c
index 23973a8..dce39de 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 f3ee80e..f6cce5a 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
@@ -362,6 +374,44 @@
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
+ 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 406758e..b47ef9e 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1995,6 +1995,12 @@ 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 a5ca409..b1d22d8 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)
{
@@ -60,6 +85,12 @@ struct gadget_info {
bool use_os_desc;
char b_vendor_code;
char qw_sign[OS_STRING_QW_SIGN_LEN];
+#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)
@@ -265,7 +296,7 @@ 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;
@@ -1369,6 +1400,60 @@ 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;
@@ -1388,14 +1473,91 @@ static void configfs_composite_unbind(struct usb_gadget *gadget)
set_gadget_data(gadget, NULL);
}
+#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 = composite_setup,
.reset = composite_disconnect,
.disconnect = composite_disconnect,
-
+#endif
.suspend = composite_suspend,
.resume = composite_resume,
@@ -1407,6 +1569,89 @@ 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)
@@ -1458,7 +1703,11 @@ 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);
@@ -1467,6 +1716,7 @@ 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 = {
@@ -1506,6 +1756,13 @@ 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);
@@ -1513,5 +1770,10 @@ 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..7aa2656
--- /dev/null
+++ b/drivers/usb/gadget/function/f_accessory.c
@@ -0,0 +1,1352 @@
+/*
+ * 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/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 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:1;
+
+ /* disconnected indicates state of open & release
+ * Set to 1 when we disconnect.
+ * Not cleared until our file is closed.
+ */
+ int disconnected:1;
+
+ /* 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,
+};
+
+/* temporary variable used between acc_open() and acc_gadget_bind() */
+static struct acc_dev *_acc_dev;
+
+struct acc_instance {
+ struct usb_function_instance func_inst;
+ const char *name;
+};
+
+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 = _acc_dev;
+
+ 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);
+}
+
+static void acc_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = _acc_dev;
+
+ dev->rx_done = 1;
+ if (req->status == -ESHUTDOWN) {
+ pr_debug("acc_complete_out set disconnected");
+ acc_set_disconnected(dev);
+ }
+
+ wake_up(&dev->read_wq);
+}
+
+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;
+ 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;
+ }
+
+ 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 = count;
+ 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)
+{
+ printk(KERN_INFO "acc_open\n");
+ if (atomic_xchg(&_acc_dev->open_excl, 1))
+ return -EBUSY;
+
+ _acc_dev->disconnected = 0;
+ fp->private_data = _acc_dev;
+ return 0;
+}
+
+static int acc_release(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "acc_release\n");
+
+ WARN_ON(!atomic_xchg(&_acc_dev->open_excl, 0));
+ /* indicate that we are disconnected
+ * still could be online so don't touch online flag
+ */
+ _acc_dev->disconnected = 1;
+ 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 = _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;
+
+/*
+ printk(KERN_INFO "acc_ctrlrequest "
+ "%02x.%02x v%04x i%04x l%u\n",
+ b_requestType, b_request,
+ w_value, w_index, w_length);
+*/
+
+ 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);
+ 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;
+
+ /* do nothing if usb accessory device doesn't exist */
+ if (!dev)
+ return;
+
+ 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 = _acc_dev;
+ struct list_head *entry, *temp;
+ struct acc_hid_dev *hid;
+ struct list_head new_list, dead_list;
+ unsigned long flags;
+
+ 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);
+ }
+}
+
+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 *dev;
+ int ret;
+
+ 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);
+
+ /* _acc_dev must be set before calling usb_gadget_register_driver */
+ _acc_dev = dev;
+
+ ret = misc_register(&acc_device);
+ if (ret)
+ goto err;
+
+ return 0;
+
+err:
+ kfree(dev);
+ pr_err("USB accessory gadget driver failed to initialize\n");
+ return ret;
+}
+
+void acc_disconnect(void)
+{
+ /* unregister all HID devices if USB is disconnected */
+ kill_all_hid_devices(_acc_dev);
+}
+EXPORT_SYMBOL_GPL(acc_disconnect);
+
+static void acc_cleanup(void)
+{
+ misc_deregister(&acc_device);
+ kfree(_acc_dev);
+ _acc_dev = NULL;
+}
+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;
+ struct acc_dev *dev;
+ 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);
+ pr_err("Error setting ACCESSORY\n");
+ return ERR_PTR(err);
+ }
+
+ config_group_init_type_name(&fi_acc->func_inst.group,
+ "", &acc_func_type);
+ dev = _acc_dev;
+ return &fi_acc->func_inst;
+}
+
+static void acc_free(struct usb_function *f)
+{
+/*NO-OP: no function specific resource allocation in mtp_alloc*/
+}
+
+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 = _acc_dev;
+
+ pr_info("acc_alloc\n");
+
+ 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 a5719f2..a832d27 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -1167,6 +1167,65 @@ 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;
@@ -1184,6 +1243,11 @@ 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);
@@ -1201,6 +1265,7 @@ 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);
}
@@ -1280,6 +1345,7 @@ 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;
setup_fail:
diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c
new file mode 100644
index 0000000..54f7ebb
--- /dev/null
+++ b/drivers/usb/gadget/function/f_mtp.c
@@ -0,0 +1,1554 @@
+/*
+ * 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;
+
+ 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;
+
+ 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 b9c409a..6801de9 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
#
@@ -208,4 +216,13 @@
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/video/fbdev/goldfishfb.c b/drivers/video/fbdev/goldfishfb.c
index 7f6c9e6..1e56b50 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,
@@ -234,7 +235,7 @@ static int goldfish_fb_probe(struct platform_device *pdev)
fb->fb.var.activate = FB_ACTIVATE_NOW;
fb->fb.var.height = readl(fb->reg_base + FB_GET_PHYS_HEIGHT);
fb->fb.var.width = readl(fb->reg_base + FB_GET_PHYS_WIDTH);
- fb->fb.var.pixclock = 10000;
+ fb->fb.var.pixclock = 0;
fb->fb.var.red.offset = 11;
fb->fb.var.red.length = 5;
@@ -304,12 +305,25 @@ 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/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..f207d43 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 \
@@ -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/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/cifs/connect.c b/fs/cifs/connect.c
index 441d434..c4a27f6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2439,7 +2439,7 @@ 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..2596c9a
--- /dev/null
+++ b/fs/crypto/bio.c
@@ -0,0 +1,145 @@
+/*
+ * 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"
+
+/*
+ * 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->mapping->host, page,
+ PAGE_SIZE, 0, page->index);
+
+ 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);
+
+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 73de144..732a786 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -24,10 +24,10 @@
#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 "fscrypt_private.h"
static unsigned int num_prealloc_crypto_pages = 32;
static unsigned int num_prealloc_crypto_ctxs = 128;
@@ -44,7 +44,7 @@ static mempool_t *fscrypt_bounce_page_pool = NULL;
static LIST_HEAD(fscrypt_free_ctxs);
static DEFINE_SPINLOCK(fscrypt_ctx_lock);
-static struct workqueue_struct *fscrypt_read_workqueue;
+struct workqueue_struct *fscrypt_read_workqueue;
static DEFINE_MUTEX(fscrypt_init_mutex);
static struct kmem_cache *fscrypt_ctx_cachep;
@@ -63,7 +63,7 @@ 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 +88,7 @@ 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;
@@ -121,47 +121,39 @@ 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)
-{
- struct fscrypt_completion_result *ecr = req->data;
-
- if (res == -EINPROGRESS)
- return;
- ecr->res = res;
- complete(&ecr->completion);
-}
-
-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;
+ u8 padding[FS_IV_SIZE - sizeof(__le64)];
+ } 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);
+
+ BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE);
+ BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE);
+ iv.index = cpu_to_le64(lblk_num);
+ memset(iv.padding, 0, sizeof(iv.padding));
+
+ if (ci->ci_essiv_tfm != NULL) {
+ crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv,
+ (u8 *)&iv);
+ }
+
req = skcipher_request_alloc(tfm, gfp_flags);
if (!req) {
printk_ratelimited(KERN_ERR
@@ -172,26 +164,17 @@ static int do_page_crypto(struct inode *inode,
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
@@ -202,53 +185,86 @@ static int do_page_crypto(struct inode *inode,
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 +281,13 @@ 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 +295,17 @@ 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
@@ -358,7 +320,7 @@ 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;
}
@@ -392,63 +354,6 @@ const struct dentry_operations fscrypt_d_ops = {
};
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)
{
struct fscrypt_ctx *ctx;
@@ -474,16 +379,21 @@ 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 +420,6 @@ int fscrypt_initialize(void)
mutex_unlock(&fscrypt_init_mutex);
return res;
}
-EXPORT_SYMBOL(fscrypt_initialize);
/**
* fscrypt_init() - Set up for fs encryption.
@@ -552,6 +461,8 @@ 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..6eb4343 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -12,22 +12,7 @@
#include <linux/scatterlist.h>
#include <linux/ratelimit.h>
-#include <linux/fscrypto.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)
-{
- struct fscrypt_completion_result *ecr = req->data;
-
- if (res == -EINPROGRESS)
- return;
- ecr->res = res;
- complete(&ecr->completion);
-}
+#include "fscrypt_private.h"
/**
* fname_encrypt() - encrypt a filename
@@ -40,7 +25,7 @@ static int fname_encrypt(struct inode *inode,
const struct qstr *iname, struct fscrypt_str *oname)
{
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;
@@ -76,17 +61,12 @@ static int fname_encrypt(struct inode *inode,
}
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- fname_crypt_complete, &ecr);
+ crypto_req_done, &wait);
sg_init_one(&sg, oname->name, cryptlen);
skcipher_request_set_crypt(req, &sg, &sg, cryptlen, 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
@@ -110,7 +90,7 @@ 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;
@@ -131,7 +111,7 @@ static int fname_decrypt(struct inode *inode,
}
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);
@@ -140,11 +120,7 @@ static int fname_decrypt(struct inode *inode,
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;
- }
+ res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
printk_ratelimited(KERN_ERR
@@ -159,6 +135,8 @@ 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() -
*
@@ -209,7 +187,7 @@ static int digest_decode(const char *src, int len, char *dst)
return cp - dst;
}
-u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
+u32 fscrypt_fname_encrypted_size(const struct inode *inode, u32 ilen)
{
int padding = 32;
struct fscrypt_info *ci = inode->i_crypt_info;
@@ -227,14 +205,17 @@ EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
* Allocates an output buffer that is sufficient for the crypto operation
* specified by the context and the direction.
*/
-int fscrypt_fname_alloc_buffer(struct inode *inode,
+int fscrypt_fname_alloc_buffer(const struct inode *inode,
u32 ilen, struct fscrypt_str *crypto_str)
{
- unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
+ u32 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)));
crypto_str->len = olen;
- if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
- olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+ olen = max(olen, max_encoded_len);
+
/*
* Allocated buffer can hold one more character to null-terminate the
* string
@@ -266,6 +247,10 @@ 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 +259,7 @@ 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] = '.';
@@ -289,20 +274,24 @@ 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);
@@ -336,16 +325,40 @@ int fscrypt_fname_usr_to_disk(struct inode *inode,
}
EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
+/**
+ * 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
+ *
+ * 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_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;
@@ -373,25 +386,37 @@ 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;
@@ -403,12 +428,3 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
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..4688a64
--- /dev/null
+++ b/fs/crypto/fscrypt_private.h
@@ -0,0 +1,88 @@
+/*
+ * 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_IV_SIZE 16
+#define FS_AES_128_ECB_KEY_SIZE 16
+#define FS_AES_128_CBC_KEY_SIZE 16
+#define FS_AES_128_CTS_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_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
+
+/*
+ * A pointer to this structure is stored in the file system's in-core
+ * representation of an inode.
+ */
+struct fscrypt_info {
+ u8 ci_data_mode;
+ u8 ci_filename_mode;
+ u8 ci_flags;
+ struct crypto_skcipher *ci_ctfm;
+ struct crypto_cipher *ci_essiv_tfm;
+ u8 ci_master_key[FS_KEY_DESCRIPTOR_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
+
+/* crypto.c */
+extern int fscrypt_initialize(unsigned int cop_flags);
+extern struct workqueue_struct *fscrypt_read_workqueue;
+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);
+
+/* keyinfo.c */
+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..9f5fb2e
--- /dev/null
+++ b/fs/crypto/hooks.c
@@ -0,0 +1,112 @@
+/*
+ * 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)) {
+ pr_warn_ratelimited("fscrypt: 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);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index a755fa1..c891d2e 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -10,34 +10,28 @@
#include <keys/user-type.h>
#include <linux/scatterlist.h>
-#include <linux/fscrypto.h>
+#include <linux/ratelimit.h>
+#include <crypto/aes.h>
+#include <crypto/sha.h>
+#include "fscrypt_private.h"
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
- struct fscrypt_completion_result *ecr = req->data;
-
- if (rc == -EINPROGRESS)
- return;
-
- ecr->res = rc;
- complete(&ecr->completion);
-}
+static struct crypto_shash *essiv_hash_tfm;
/**
* 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.
+ * @derived_raw_key: Derived raw key.
*
* Return: Zero on success; non-zero otherwise.
*/
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])
+ const struct fscrypt_key *source_key,
+ u8 derived_raw_key[FS_MAX_KEY_SIZE])
{
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);
@@ -54,21 +48,17 @@ 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);
+ crypto_req_done, &wait);
res = crypto_skcipher_setkey(tfm, deriving_key,
FS_AES_128_ECB_KEY_SIZE);
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, source_key->raw, source_key->size);
+ sg_init_one(&dst_sg, derived_raw_key, source_key->size);
+ skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size,
+ NULL);
+ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
out:
skcipher_request_free(req);
crypto_free_skcipher(tfm);
@@ -77,26 +67,22 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
static int validate_user_key(struct fscrypt_info *crypt_info,
struct fscrypt_context *ctx, u8 *raw_key,
- u8 *prefix, int prefix_size)
+ const char *prefix, int min_keysize)
{
- u8 *full_key_descriptor;
+ char *description;
struct key *keyring_key;
struct fscrypt_key *master_key;
const struct user_key_payload *ukp;
- int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
int res;
- full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
- if (!full_key_descriptor)
+ description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
+ FS_KEY_DESCRIPTOR_SIZE,
+ ctx->master_key_descriptor);
+ if (!description)
return -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);
+ keyring_key = request_key(&key_type_logon, description, NULL);
+ kfree(description);
if (IS_ERR(keyring_key))
return PTR_ERR(keyring_key);
down_read(&keyring_key->sem);
@@ -107,7 +93,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
res = -ENOKEY;
goto out;
}
- ukp = user_key_payload(keyring_key);
+ ukp = user_key_payload_locked(keyring_key);
if (!ukp) {
/* key was revoked before we acquired its semaphore */
res = -EKEYREVOKED;
@@ -120,50 +106,60 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
master_key = (struct fscrypt_key *)ukp->data;
BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
- if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+ if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE
+ || master_key->size % AES_BLOCK_SIZE != 0) {
printk_once(KERN_WARNING
"%s: key size incorrect: %d\n",
__func__, master_key->size);
res = -ENOKEY;
goto out;
}
- res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
+ res = derive_key_aes(ctx->nonce, master_key, raw_key);
out:
up_read(&keyring_key->sem);
key_put(keyring_key);
return res;
}
+static const struct {
+ const char *cipher_str;
+ int keysize;
+} available_modes[] = {
+ [FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)",
+ FS_AES_256_XTS_KEY_SIZE },
+ [FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))",
+ FS_AES_256_CTS_KEY_SIZE },
+ [FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)",
+ FS_AES_128_CBC_KEY_SIZE },
+ [FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))",
+ FS_AES_128_CTS_KEY_SIZE },
+};
+
static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
const char **cipher_str_ret, int *keysize_ret)
{
+ u32 mode;
+
+ if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
+ pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n",
+ inode->i_ino,
+ ci->ci_data_mode, ci->ci_filename_mode);
+ return -EINVAL;
+ }
+
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;
+ mode = ci->ci_data_mode;
+ } else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
+ mode = ci->ci_filename_mode;
+ } else {
+ 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 -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;
- }
- pr_warn_once("fscrypto: unsupported filenames encryption mode "
- "%d for inode %lu\n",
- ci->ci_filename_mode, inode->i_ino);
- return -ENOKEY;
- }
-
- pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n",
- (inode->i_mode & S_IFMT), inode->i_ino);
- return -ENOKEY;
+ *cipher_str_ret = available_modes[mode].cipher_str;
+ *keysize_ret = available_modes[mode].keysize;
+ return 0;
}
static void put_crypt_info(struct fscrypt_info *ci)
@@ -172,9 +168,76 @@ static void put_crypt_info(struct fscrypt_info *ci)
return;
crypto_free_skcipher(ci->ci_ctfm);
+ crypto_free_cipher(ci->ci_essiv_tfm);
kmem_cache_free(fscrypt_info_cachep, ci);
}
+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)) {
+ pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n",
+ 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;
+ }
+ }
+
+ {
+ 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);
+}
+
int fscrypt_get_encryption_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
@@ -188,21 +251,21 @@ int fscrypt_get_encryption_info(struct inode *inode)
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;
}
@@ -221,6 +284,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
crypt_info->ci_data_mode = ctx.contents_encryption_mode;
crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
crypt_info->ci_ctfm = NULL;
+ crypt_info->ci_essiv_tfm = NULL;
memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
sizeof(crypt_info->ci_master_key));
@@ -237,20 +301,12 @@ int fscrypt_get_encryption_info(struct inode *inode)
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);
+ res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX,
+ keysize);
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);
+ int res2 = validate_user_key(crypt_info, &ctx, raw_key,
+ inode->i_sb->s_cop->key_prefix,
+ keysize);
if (res2) {
if (res2 == -ENOKEY)
res = -ENOKEY;
@@ -259,22 +315,33 @@ int fscrypt_get_encryption_info(struct inode *inode)
} else 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);
+ pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n",
+ __func__, res, 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);
+ /*
+ * if the provided key is longer than keysize, we use the first
+ * keysize bytes of the derived key only
+ */
res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
if (res)
goto out;
+ if (S_ISREG(inode->i_mode) &&
+ crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) {
+ res = init_essiv_generator(crypt_info, raw_key, keysize);
+ if (res) {
+ pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n",
+ __func__, res, inode->i_ino);
+ goto out;
+ }
+ }
if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
crypt_info = NULL;
out:
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index c160d2d..2f2c53f 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;
@@ -93,16 +54,20 @@ static int create_encryption_context_from_policy(struct inode *inode,
return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
}
-int fscrypt_process_policy(struct file *filp,
- const struct fscrypt_policy *policy)
+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;
if (!inode_owner_or_capable(inode))
return -EACCES;
- if (policy->version != 0)
+ if (policy.version != 0)
return -EINVAL;
ret = mnt_want_write_file(filp);
@@ -111,22 +76,23 @@ int fscrypt_process_policy(struct file *filp,
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 (!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__);
- ret = -EINVAL;
+ &policy);
+ } 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;
}
inode_unlock(inode);
@@ -134,32 +100,38 @@ int fscrypt_process_policy(struct file *filp,
mnt_drop_write_file(filp);
return ret;
}
-EXPORT_SYMBOL(fscrypt_process_policy);
+EXPORT_SYMBOL(fscrypt_ioctl_set_policy);
-int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
{
+ struct inode *inode = file_inode(filp);
struct fscrypt_context ctx;
+ 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;
- policy->version = 0;
- policy->contents_encryption_mode = ctx.contents_encryption_mode;
- policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
- policy->flags = ctx.flags;
- memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+ policy.version = 0;
+ policy.contents_encryption_mode = ctx.contents_encryption_mode;
+ policy.filenames_encryption_mode = ctx.filenames_encryption_mode;
+ policy.flags = ctx.flags;
+ memcpy(policy.master_key_descriptor, ctx.master_key_descriptor,
FS_KEY_DESCRIPTOR_SIZE);
+
+ if (copy_to_user(arg, &policy, sizeof(policy)))
+ return -EFAULT;
return 0;
}
-EXPORT_SYMBOL(fscrypt_get_policy);
+EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
/**
* fscrypt_has_permitted_context() - is a file's encryption policy permitted
@@ -194,11 +166,11 @@ 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;
/*
@@ -258,9 +230,9 @@ 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)
@@ -269,9 +241,6 @@ 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;
@@ -281,19 +250,11 @@ 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,
+ 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 67957f5..227a4f9 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3215,6 +3215,7 @@ 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 3cbc304..5b96ba7 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>
@@ -1673,7 +1674,8 @@ 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 b8c43be..3e2de29 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1304,7 +1304,7 @@ 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/ext4/ext4.h b/fs/ext4/ext4.h
index a8a750f..c175391 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
*/
@@ -1516,12 +1513,6 @@ struct ext4_sb_info {
/* Barrier between changing inodes' journal flags and writepages ops. */
struct percpu_rw_semaphore s_journal_flag_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)
@@ -2277,11 +2268,6 @@ 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);
@@ -2330,28 +2316,6 @@ 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_process_policy fscrypt_notsupp_process_policy
-#define fscrypt_get_policy fscrypt_notsupp_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 */
@@ -2373,17 +2337,16 @@ 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))
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
};
@@ -2450,7 +2413,8 @@ 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);
@@ -3070,7 +3034,7 @@ 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 2d94e85..2cec605 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1093,6 +1093,17 @@ 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;
@@ -1114,13 +1125,6 @@ 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 73cbc01..4d78b93 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))
@@ -501,6 +502,17 @@ 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.
@@ -512,6 +524,8 @@ 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);
@@ -1021,7 +1035,7 @@ 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 5cccec6..eb06f9a 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
@@ -1165,7 +1166,8 @@ 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
@@ -1182,6 +1184,16 @@ 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
@@ -1319,6 +1331,7 @@ static int ext4_write_end(struct file *file,
int ret = 0, ret2;
int i_size_changed = 0;
+ trace_android_fs_datawrite_end(inode, pos, len);
trace_ext4_write_end(inode, pos, len, copied);
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
@@ -1423,6 +1436,7 @@ static int ext4_journalled_write_end(struct file *file,
unsigned from, to;
int size_changed = 0;
+ 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;
@@ -2923,6 +2937,16 @@ 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)) {
@@ -3041,6 +3065,7 @@ 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;
@@ -3605,6 +3630,7 @@ 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))
@@ -3621,12 +3647,42 @@ 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;
}
@@ -3777,7 +3833,8 @@ 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)) {
@@ -4394,8 +4451,11 @@ 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 bf5ae8e..15ca15c 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)
@@ -735,11 +737,13 @@ 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;
@@ -747,13 +751,16 @@ 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;
+
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
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;
@@ -765,28 +772,19 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
- case EXT4_IOC_SET_ENCRYPTION_POLICY: {
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- struct fscrypt_policy policy;
+ case EXT4_IOC_SET_ENCRYPTION_POLICY:
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
+ return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
- if (copy_from_user(&policy,
- (struct fscrypt_policy __user *)arg,
- sizeof(policy)))
- return -EFAULT;
- return fscrypt_process_policy(filp, &policy);
-#else
- return -EOPNOTSUPP;
-#endif
- }
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);
@@ -816,30 +814,18 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
- }
- case EXT4_IOC_GET_ENCRYPTION_POLICY: {
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- struct fscrypt_policy policy;
- int err = 0;
-
- if (!ext4_encrypted_inode(inode))
- return -ENOENT;
- err = fscrypt_get_policy(inode, &policy);
- if (err)
- return err;
- if (copy_to_user((void __user *)arg, &policy, sizeof(policy)))
- return -EFAULT;
- return 0;
#else
return -EOPNOTSUPP;
#endif
}
+ case EXT4_IOC_GET_ENCRYPTION_POLICY:
+ return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
+
case EXT4_IOC_FSGETXATTR:
{
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 64056c6..e5e99a7 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2772,7 +2772,8 @@ 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;
@@ -2781,7 +2782,7 @@ 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);
}
/*
@@ -2803,7 +2804,7 @@ 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"
@@ -4856,7 +4857,8 @@ 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"
@@ -5052,13 +5054,15 @@ 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)
{
@@ -5079,7 +5083,7 @@ __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;
@@ -5092,6 +5096,7 @@ __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
@@ -5106,7 +5111,7 @@ __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;
@@ -5139,7 +5144,8 @@ 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;
@@ -5181,6 +5187,7 @@ 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
@@ -5189,7 +5196,8 @@ 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;
@@ -5245,7 +5253,7 @@ 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 b1766a6..8338cd4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1237,37 +1237,24 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
}
/*
- * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure.
+ * Test whether a directory entry matches the filename being searched for.
*
- * `len <= EXT4_NAME_LEN' is guaranteed by caller.
- * `de != NULL' is guaranteed by caller.
+ * Return: %true if the directory entry matches, otherwise %false.
*/
-static inline int ext4_match(struct ext4_filename *fname,
- struct ext4_dir_entry_2 *de)
+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 0;
+ 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);
}
/*
@@ -1281,48 +1268,31 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
struct ext4_dir_entry_2 * de;
char * dlimit;
int de_len;
- int res;
de = (struct ext4_dir_entry_2 *)search_buf;
dlimit = search_buf + buf_size;
while ((char *) de < dlimit) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
- if ((char *) de + de->name_len <= dlimit) {
- res = ext4_match(fname, de);
- if (res < 0) {
- res = -1;
- goto return_result;
- }
- if (res > 0) {
- /* found a match - just to be sure, do
- * a full check */
- if (ext4_check_dir_entry(dir, NULL, de, bh,
- bh->b_data,
- bh->b_size, offset)) {
- res = -1;
- goto return_result;
- }
- *res_dir = de;
- res = 1;
- goto return_result;
- }
-
+ if ((char *) de + de->name_len <= dlimit &&
+ ext4_match(fname, de)) {
+ /* found a match - just to be sure, do
+ * a full check */
+ if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
+ bh->b_size, offset))
+ return -1;
+ *res_dir = de;
+ return 1;
}
/* prevent looping on a bad block */
de_len = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
- if (de_len <= 0) {
- res = -1;
- goto return_result;
- }
+ if (de_len <= 0)
+ return -1;
offset += de_len;
de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
}
-
- res = 0;
-return_result:
- return res;
+ return 0;
}
static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block,
@@ -1620,16 +1590,9 @@ 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);
}
@@ -1837,24 +1800,15 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
int nlen, rlen;
unsigned int offset = 0;
char *top;
- int res;
de = (struct ext4_dir_entry_2 *)buf;
top = buf + buf_size - reclen;
while ((char *) de <= top) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
- buf, buf_size, offset)) {
- res = -EFSCORRUPTED;
- goto return_result;
- }
- /* Provide crypto context and crypto buffer to ext4 match */
- res = ext4_match(fname, de);
- if (res < 0)
- goto return_result;
- if (res > 0) {
- res = -EEXIST;
- goto return_result;
- }
+ buf, buf_size, offset))
+ return -EFSCORRUPTED;
+ if (ext4_match(fname, de))
+ return -EEXIST;
nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
if ((de->inode ? rlen - nlen : rlen) >= reclen)
@@ -1862,22 +1816,17 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
offset += rlen;
}
-
if ((char *) de > top)
- res = -ENOSPC;
- else {
- *dest_de = de;
- res = 0;
- }
-return_result:
- return res;
+ return -ENOSPC;
+
+ *dest_de = de;
+ 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;
@@ -1896,7 +1845,6 @@ 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;
}
/*
@@ -1932,11 +1880,8 @@ 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
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 0094923..0718a86 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"
@@ -470,7 +469,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
gfp_t gfp_flags = GFP_NOFS;
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 && wbc->sync_mode == WB_SYNC_ALL) {
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index a81b829..2531cc1 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.
*
@@ -72,6 +84,9 @@ 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);
@@ -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 1ec4b6e..43ce5fc 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1103,57 +1103,75 @@ 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));
}
@@ -1164,20 +1182,14 @@ static unsigned ext4_max_namelen(struct inode *inode)
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,
-};
#endif
#ifdef CONFIG_QUOTA
@@ -3907,7 +3919,9 @@ 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))
@@ -4221,11 +4235,6 @@ 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/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 55aa29c..2bb7c9f 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -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;
@@ -233,7 +234,7 @@ 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);
}
}
@@ -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);
}
@@ -384,7 +388,7 @@ 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,
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b4dbc2f..a30024f 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -29,9 +29,8 @@ struct kmem_cache *inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
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);
}
/*
@@ -65,7 +64,7 @@ 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,
@@ -160,8 +159,9 @@ 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,
};
struct blk_plug plug;
@@ -207,12 +207,10 @@ 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;
}
@@ -228,11 +226,12 @@ 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);
+ 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);
@@ -245,16 +244,17 @@ static int f2fs_write_meta_page(struct page *page,
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
- write_meta_page(sbi, page);
+ 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, page->mapping->host,
+ 0, page->index, 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;
@@ -263,23 +263,33 @@ 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))
goto skip_write;
- trace_f2fs_writepages(mapping->host, wbc, META);
+ /* if locked failed, cp will flush dirty pages instead */
+ if (!mutex_trylock(&sbi->cp_mutex))
+ goto skip_write;
- /* if mounting is failed, skip writing node pages */
- mutex_lock(&sbi->cp_mutex);
+ trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
- written = sync_meta_pages(sbi, META, wbc->nr_to_write);
+ written = 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;
@@ -291,7 +301,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
}
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
- long nr_to_write)
+ 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;
@@ -342,7 +352,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
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;
}
@@ -356,7 +366,7 @@ 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);
@@ -390,24 +400,23 @@ 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;
@@ -415,6 +424,10 @@ 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();
@@ -443,7 +456,7 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
void 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)
@@ -469,7 +482,7 @@ void 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);
@@ -483,6 +496,27 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
}
}
+void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type)
+{
+ __add_ino_entry(sbi, ino, devidx, type);
+}
+
+bool 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 acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
@@ -493,6 +527,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
#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
@@ -518,7 +553,7 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
void 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);
+ __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
update_inode_page(inode);
}
@@ -542,7 +577,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
return err;
}
- __add_ino_entry(sbi, ino, ORPHAN_INO);
+ __add_ino_entry(sbi, ino, 0, ORPHAN_INO);
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode)) {
@@ -565,7 +600,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
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.",
+ "%s: orphan failed (ino=%x) by kernel, retry mount.",
__func__, ino);
return -EIO;
}
@@ -576,11 +611,28 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
int 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 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);
@@ -596,14 +648,22 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
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:
+#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)
@@ -675,14 +735,13 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
*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_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_msg(sbi->sb, KERN_WARNING, "invalid crc value");
return -EINVAL;
@@ -770,7 +829,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
/* Sanity checking of checkpoint */
if (sanity_check_ckpt(sbi))
- goto fail_no_cp;
+ goto free_fail_no_cp;
if (cur_page == cp1)
sbi->cur_cp_pack = 1;
@@ -798,6 +857,9 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
f2fs_put_page(cp2, 1);
return 0;
+free_fail_no_cp:
+ f2fs_put_page(cp1, 1);
+ f2fs_put_page(cp2, 1);
fail_no_cp:
kfree(sbi->ckpt);
return -EINVAL;
@@ -812,7 +874,9 @@ 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);
}
@@ -870,6 +934,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
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 ?
@@ -888,18 +953,34 @@ 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) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ 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;
@@ -921,18 +1002,35 @@ 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))
+ 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);
+}
+
/*
* Freeze all the FS-operations for checkpoint.
*/
@@ -956,33 +1054,47 @@ static int block_operations(struct f2fs_sb_info *sbi)
err = 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;
+ cond_resched();
goto retry_flush_dents;
}
/*
* 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 (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_dents;
+ }
+
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);
+ err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
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;
@@ -991,8 +1103,6 @@ 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);
}
@@ -1003,7 +1113,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
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;
io_schedule_timeout(5*HZ);
@@ -1015,15 +1125,24 @@ 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);
+
+ 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);
@@ -1039,15 +1158,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* set this flag to activate crc|cp_ver for recovery */
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
- spin_unlock(&sbi->cp_lock);
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
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;
@@ -1056,22 +1174,20 @@ 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);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
- next_free_nid(sbi, &last_nid);
-
/*
* 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->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
@@ -1090,18 +1206,14 @@ 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);
+ 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 +
@@ -1130,11 +1242,37 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk = __start_cp_next_addr(sbi);
+ /* 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++)
+ update_meta_page(sbi, nm_i->nat_bits +
+ (i << F2FS_BLKSIZE_BITS), blk + i);
+
+ /* Flush all the NAT BITS pages */
+ while (get_pages(sbi, F2FS_DIRTY_META)) {
+ sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ }
+ }
+
/* need to wait for end_io results */
wait_on_all_pages_writeback(sbi);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ /* flush all device cache */
+ err = f2fs_flush_device_cache(sbi);
+ if (err)
+ return err;
+
/* write out checkpoint buffer at block 0 */
update_meta_page(sbi, ckpt, start_blk++);
@@ -1179,7 +1317,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
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);
+ sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO);
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
@@ -1189,7 +1327,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
- clear_prefree_segments(sbi, cpc);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
__set_cp_next_pack(sbi);
@@ -1219,8 +1356,8 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
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;
@@ -1239,18 +1376,23 @@ 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 (!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) {
+ flush_sit_entries(sbi, cpc);
+ clear_prefree_segments(sbi, cpc);
+ unblock_operations(sbi);
+ goto out;
+ }
}
/*
@@ -1262,18 +1404,20 @@ 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_nat_entries(sbi, cpc);
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)
+ release_discard_addrs(sbi);
+ else
+ clear_prefree_segments(sbi, cpc);
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);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 99432b5..36090d0 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -28,6 +28,27 @@
#include "segment.h"
#include "trace.h"
#include <trace/events/f2fs.h>
+#include <trace/events/android_fs.h>
+
+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) ||
+ is_cold_data(page))
+ return true;
+ return false;
+}
static void f2fs_read_end_io(struct bio *bio)
{
@@ -35,8 +56,10 @@ static void f2fs_read_end_io(struct bio *bio)
int i;
#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_IO)) {
+ f2fs_show_injection_info(FAULT_IO);
bio->bi_error = -EIO;
+ }
#endif
if (f2fs_bio_encrypted(bio)) {
@@ -71,6 +94,18 @@ static void f2fs_write_end_io(struct bio *bio)
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);
@@ -78,9 +113,11 @@ static void f2fs_write_end_io(struct bio *bio)
mapping_set_error(page->mapping, -EIO);
f2fs_stop_checkpoint(sbi, true);
}
+ dec_page_count(sbi, type);
+ 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);
@@ -88,6 +125,46 @@ 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,
@@ -95,10 +172,9 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
{
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);
+ f2fs_target_device(sbi, blk_addr, bio);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
bio->bi_private = is_read ? NULL : sbi;
@@ -109,11 +185,46 @@ 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) &&
+ unsigned int start;
+
+ if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
current->plug && (type == DATA || type == NODE))
blk_finish_plug(current->plug);
+
+ if (type != DATA && type != NODE)
+ goto submit_io;
+
+ 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_ZERO | __GFP_NOFAIL);
+ f2fs_bug_on(sbi, !page);
+
+ 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);
}
@@ -124,19 +235,19 @@ 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;
}
-static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
- struct page *page, nid_t ino)
+static bool __has_merged_page(struct f2fs_bio_info *io,
+ struct inode *inode, nid_t ino, pgoff_t idx)
{
struct bio_vec *bvec;
struct page *target;
@@ -145,7 +256,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
if (!io->bio)
return false;
- if (!inode && !page && !ino)
+ if (!inode && !ino)
return true;
bio_for_each_segment_all(bvec, io->bio, i) {
@@ -155,10 +266,11 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
else
target = fscrypt_control_page(bvec->bv_page);
+ if (idx != target->index)
+ continue;
+
if (inode && inode == target->mapping->host)
return true;
- if (page && page == target)
- return true;
if (ino && ino == ino_of_node(target))
return true;
}
@@ -167,72 +279,88 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
}
static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
- struct page *page, nid_t ino,
- enum page_type type)
+ nid_t ino, pgoff_t idx, enum page_type type)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
- struct f2fs_bio_info *io = &sbi->write_io[btype];
- bool ret;
+ enum temp_type temp;
+ struct f2fs_bio_info *io;
+ bool ret = false;
- down_read(&io->io_rwsem);
- ret = __has_merged_page(io, inode, page, ino);
- up_read(&io->io_rwsem);
+ for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+ io = sbi->write_io[btype] + temp;
+
+ down_read(&io->io_rwsem);
+ ret = __has_merged_page(io, inode, ino, idx);
+ up_read(&io->io_rwsem);
+
+ /* TODO: use HOT temp only for meta pages now. */
+ if (ret || btype == META)
+ break;
+ }
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)
+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;
-
- 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)
+static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, nid_t ino, pgoff_t idx,
+ enum page_type type, bool force)
{
- __f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+ enum temp_type temp;
+
+ if (!force && !has_merged_page(sbi, inode, ino, idx, type))
+ return;
+
+ for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+
+ __f2fs_submit_merged_write(sbi, type, temp);
+
+ /* TODO: use HOT temp only for meta pages now. */
+ if (type >= META)
+ break;
+ }
}
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
- struct inode *inode, struct page *page,
- nid_t ino, enum page_type type, int rw)
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
- if (has_merged_page(sbi, inode, page, ino, type))
- __f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+ __submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
}
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, nid_t ino, pgoff_t idx,
+ 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, inode, ino, idx, 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)
{
@@ -253,41 +381,65 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
bio_set_op_attrs(bio, fio->op, fio->op_flags);
__submit_bio(fio->sbi, bio, fio->type);
+
+ if (!is_read_io(fio->op))
+ inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
return 0;
}
-void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+int 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;
+ int err = 0;
- 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_fail;
+ }
+ fio = list_first_entry(&io->io_list,
+ struct f2fs_io_info, list);
+ list_del(&fio->list);
+ spin_unlock(&io->io_lock);
+ }
if (fio->old_blkaddr != NEW_ADDR)
verify_block_addr(sbi, fio->old_blkaddr);
verify_block_addr(sbi, 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);
-
+ if ((fio->type == DATA || fio->type == NODE) &&
+ fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
+ err = -EAGAIN;
+ dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+ goto out_fail;
+ }
io->bio = __bio_alloc(sbi, fio->new_blkaddr,
- bio_blocks, is_read);
+ BIO_MAX_PAGES, false);
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;
}
@@ -295,18 +447,74 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
io->last_block_in_bio = fio->new_blkaddr;
f2fs_trace_ios(fio, 0);
+ trace_f2fs_submit_page_write(fio->page, fio);
+
+ if (fio->in_list)
+ goto next;
+out_fail:
up_write(&io->io_rwsem);
- trace_f2fs_submit_page_mbio(fio->page, fio);
+ return err;
+}
+
+static struct bio *f2fs_grab_read_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 bio *bio;
+
+ if (f2fs_encrypted_file(inode)) {
+ 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_block_writeback(sbi, blkaddr);
+ }
+
+ bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
+ if (!bio) {
+ if (ctx)
+ fscrypt_release_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ f2fs_target_device(sbi, blkaddr, bio);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ 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);
+
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ bio_put(bio);
+ return -EFAULT;
+ }
+ __submit_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);
}
/*
@@ -334,14 +542,15 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
int 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);
@@ -349,8 +558,8 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
f2fs_wait_on_page_writeback(dn->node_page, NODE, 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);
@@ -392,7 +601,7 @@ 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)) {
@@ -409,18 +618,8 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
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)
@@ -461,9 +660,7 @@ 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;
@@ -483,7 +680,7 @@ 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 = get_read_data_page(inode, index, 0, false);
if (IS_ERR(page))
return page;
@@ -509,7 +706,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
- page = get_read_data_page(inode, index, READ_SYNC, for_write);
+ page = get_read_data_page(inode, index, 0, for_write);
if (IS_ERR(page))
return page;
@@ -590,29 +787,27 @@ static int __allocate_data_block(struct dnode_of_data *dn)
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;
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);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr == NEW_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);
- 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);
+ &sum, CURSEG_WARM_DATA, NULL, false);
set_data_blkaddr(dn);
/* update i_size */
@@ -624,11 +819,28 @@ static int __allocate_data_block(struct dnode_of_data *dn)
return 0;
}
-ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
+static inline bool __force_buffered_io(struct inode *inode, int rw)
+{
+ return (f2fs_encrypted_file(inode) ||
+ (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
+ F2FS_I_SB(inode)->s_ndevs);
+}
+
+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 err = 0;
+
+ /* convert inline data for Direct I/O*/
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+
+ 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));
@@ -639,20 +851,34 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
map.m_next_pgofs = NULL;
- 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 (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
- ret = f2fs_convert_inline_inode(inode);
- if (ret)
- return ret;
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return f2fs_map_blocks(inode, &map, 1,
+ __force_buffered_io(inode, WRITE) ?
+ F2FS_GET_BLOCK_PRE_AIO :
+ F2FS_GET_BLOCK_PRE_DIO);
+ 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;
+ return err;
+}
+
+static inline 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);
+ }
}
/*
@@ -675,8 +901,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
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;
if (!maxblocks)
@@ -698,7 +923,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
next_dnode:
if (create)
- f2fs_lock_op(sbi);
+ __do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -720,7 +945,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
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 (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
if (create) {
@@ -735,14 +960,12 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
}
} else {
err = __allocate_data_block(&dn);
- if (!err) {
+ 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) {
@@ -793,7 +1016,6 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
err = 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) {
@@ -811,18 +1033,17 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
f2fs_put_dnode(&dn);
if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
}
- allocated = false;
goto next_dnode;
sync_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, err);
@@ -834,19 +1055,19 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
pgoff_t *next_pgofs)
{
struct f2fs_map_blocks map;
- int ret;
+ int err;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
map.m_next_pgofs = next_pgofs;
- 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 = map.m_len << inode->i_blkbits;
+ 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,
@@ -861,7 +1082,7 @@ 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_DEFAULT, NULL);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -891,7 +1112,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
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;
@@ -908,13 +1128,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
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);
@@ -933,13 +1146,11 @@ 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;
}
@@ -977,37 +1188,6 @@ 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_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.
@@ -1036,9 +1216,10 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
- prefetchw(&page->flags);
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,
@@ -1072,7 +1253,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
map.m_len = last_block - block_in_file;
if (f2fs_map_blocks(inode, &map, 0,
- F2FS_GET_BLOCK_READ))
+ F2FS_GET_BLOCK_DEFAULT))
goto set_error_page;
}
got_it:
@@ -1096,18 +1277,18 @@ 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);
bio = NULL;
}
if (bio == NULL) {
- bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ bio = f2fs_grab_read_bio(inode, block_nr, nr_pages);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
}
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1155,8 +1336,8 @@ 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);
@@ -1167,17 +1348,84 @@ static int f2fs_read_data_pages(struct file *file,
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
}
+static int encrypt_one_page(struct f2fs_io_info *fio)
+{
+ struct inode *inode = fio->page->mapping->host;
+ gfp_t gfp_flags = GFP_NOFS;
+
+ if (!f2fs_encrypted_file(inode))
+ return 0;
+
+ /* wait for GCed encrypted page writeback */
+ f2fs_wait_on_block_writeback(fio->sbi, 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))
+ return 0;
+
+ /* 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);
+}
+
+static inline bool need_inplace_update(struct f2fs_io_info *fio)
+{
+ struct inode *inode = fio->page->mapping->host;
+
+ if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
+ return false;
+ if (is_cold_data(fio->page))
+ return false;
+ if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+ return false;
+
+ return need_inplace_update_policy(inode, fio);
+}
+
+static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
+{
+ if (fio->old_blkaddr == NEW_ADDR)
+ return false;
+ if (fio->old_blkaddr == NULL_ADDR)
+ return false;
+ return true;
+}
+
int 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};
+ bool ipu_force = false;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
+ if (need_inplace_update(fio) &&
+ f2fs_lookup_extent_cache(inode, page->index, &ei)) {
+ fio->old_blkaddr = ei.blk + page->index - ei.fofs;
+
+ if (valid_ipu_blkaddr(fio)) {
+ 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 = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
- return err;
+ goto out;
fio->old_blkaddr = dn.data_blkaddr;
@@ -1186,57 +1434,57 @@ int do_write_data_page(struct f2fs_io_info *fio)
ClearPageUptodate(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 current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(fio->old_blkaddr != NEW_ADDR &&
- !is_cold_data(page) &&
- !IS_ATOMIC_WRITTEN_PAGE(page) &&
- need_inplace_update(inode))) {
- rewrite_data_page(fio);
+ if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) {
+ err = encrypt_one_page(fio);
+ if (err)
+ goto out_writepage;
+
+ set_page_writeback(page);
+ f2fs_put_dnode(&dn);
+ if (fio->need_lock == LOCK_REQ)
+ f2fs_unlock_op(fio->sbi);
+ err = rewrite_data_page(fio);
+ 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 = encrypt_one_page(fio);
+ if (err)
+ goto out_writepage;
+
+ set_page_writeback(page);
+
+ /* LFS mode write path */
+ 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);
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);
@@ -1249,15 +1497,23 @@ 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,
};
trace_f2fs_writepage(page, DATA);
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto redirty_out;
+
if (page->index < end_index)
goto write;
@@ -1271,8 +1527,6 @@ 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 */
@@ -1289,6 +1543,7 @@ static int f2fs_write_data_page(struct page *page,
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
+ fio.need_lock = LOCK_DONE;
err = do_write_data_page(&fio);
goto done;
}
@@ -1297,52 +1552,81 @@ 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)
+ if (!err)
+ goto out;
+ }
+
+ if (err == -EAGAIN) {
err = do_write_data_page(&fio);
+ if (err == -EAGAIN) {
+ fio.need_lock = LOCK_REQ;
+ err = do_write_data_page(&fio);
+ }
+ }
+
+ down_write(&F2FS_I(inode)->i_sem);
if (F2FS_I(inode)->last_disk_size < psize)
F2FS_I(inode)->last_disk_size = psize;
- f2fs_unlock_op(sbi);
+ 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)
ClearPageUptodate(page);
if (wbc->for_reclaim) {
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+ f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
+ clear_inode_flag(inode, FI_HOT_DATA);
remove_dirty_inode(inode);
+ submitted = NULL;
}
unlock_page(page);
- f2fs_balance_fs(sbi, need_balance_fs);
+ if (!S_ISDIR(inode->i_mode))
+ 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);
+ if (!err)
+ 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;
@@ -1352,13 +1636,19 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
+ pgoff_t last_idx = ULONG_MAX;
int cycled;
int range_whole = 0;
int tag;
- int nwritten = 0;
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;
@@ -1392,6 +1682,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ bool submitted = false;
if (page->index > end) {
done = 1;
@@ -1399,7 +1690,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
}
done_index = page->index;
-
+retry_write:
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -1425,17 +1716,37 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
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 {
- nwritten++;
+ } else if (submitted) {
+ last_idx = page->index;
}
- if (--wbc->nr_to_write <= 0 &&
- wbc->sync_mode == WB_SYNC_NONE) {
+ /* give a priority to WB_SYNC threads */
+ if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) ||
+ --wbc->nr_to_write <= 0) &&
+ wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
@@ -1453,15 +1764,16 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
- if (nwritten)
- f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
- NULL, 0, DATA, WRITE);
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+ 0, last_idx, DATA);
return ret;
}
-static int f2fs_write_data_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+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);
@@ -1476,6 +1788,10 @@ static int f2fs_write_data_pages(struct address_space *mapping,
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
+ /* 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) && wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
@@ -1485,15 +1801,20 @@ static int f2fs_write_data_pages(struct address_space *mapping,
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);
+ else if (atomic_read(&sbi->wb_sync_req))
+ goto skip_write;
+
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 (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_dec(&sbi->wb_sync_req);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
@@ -1508,14 +1829,26 @@ 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_mmap_sem);
truncate_pagecache(inode, i_size);
truncate_blocks(inode, i_size, true);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
}
}
@@ -1528,19 +1861,20 @@ 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;
/*
* 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;
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_MASK) >= i_size_read(inode)) {
- f2fs_lock_op(sbi);
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
locked = true;
}
restart:
@@ -1554,7 +1888,7 @@ 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) {
+ if (pos + len <= MAX_INLINE_DATA(inode)) {
read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
@@ -1576,7 +1910,8 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
err = 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);
locked = true;
goto restart;
}
@@ -1590,7 +1925,7 @@ 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, F2FS_GET_BLOCK_PRE_AIO, false);
return err;
}
@@ -1606,8 +1941,24 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
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);
+ if (f2fs_is_atomic_file(inode) &&
+ !available_free_memory(sbi, INMEM_PAGES)) {
+ err = -ENOMEM;
+ 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:
@@ -1623,7 +1974,7 @@ 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;
@@ -1651,31 +2002,24 @@ 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);
+ if (f2fs_encrypted_file(inode))
+ f2fs_wait_on_block_writeback(sbi, blkaddr);
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)) {
@@ -1692,6 +2036,8 @@ 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 (f2fs_is_atomic_file(inode))
+ drop_inmem_pages_all(sbi);
return err;
}
@@ -1702,6 +2048,7 @@ 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);
/*
@@ -1710,7 +2057,7 @@ 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);
@@ -1719,7 +2066,6 @@ 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);
@@ -1756,24 +2102,55 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (err)
return err;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- return 0;
- if (test_opt(F2FS_I_SB(inode), LFS))
+ if (__force_buffered_io(inode, rw))
return 0;
trace_f2fs_direct_IO_enter(inode, offset, count, 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);
+ }
+
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 (rw == WRITE) {
- if (err > 0)
+ if (err > 0) {
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
+ err);
set_inode_flag(inode, FI_UPDATE_WRITE);
- else if (err < 0)
+ } else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
+ }
}
+ 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);
return err;
@@ -1790,17 +2167,19 @@ 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);
+ remove_dirty_inode(inode);
+ }
}
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
- return;
+ return drop_inmem_page(inode, page);
set_page_private(page, 0);
ClearPagePrivate(page);
@@ -1860,7 +2239,7 @@ 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);
return 1;
@@ -1907,8 +2286,12 @@ 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,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 687998e..ecada84 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -45,12 +45,43 @@ 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 = 0;
+ if (f2fs_sb_has_quota_ino(sbi->sb)) {
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (f2fs_qf_ino(sbi->sb, i))
+ si->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_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
+ si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+ 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->issing_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->issing_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 +92,8 @@ 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);
@@ -74,7 +107,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
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->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
@@ -87,8 +122,8 @@ 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 = 0; i < 2; i++) {
@@ -112,10 +147,10 @@ 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;
@@ -144,7 +179,11 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
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;
@@ -181,6 +220,10 @@ 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 * NAT_ENTRY_BITMAP_SIZE;
+ 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 +233,23 @@ 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);
@@ -223,9 +273,10 @@ 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",
+ 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 +301,8 @@ 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);
@@ -310,22 +361,33 @@ 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, " - IO (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, " [");
@@ -410,6 +472,11 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
atomic_set(&sbi->inline_dir, 0);
atomic_set(&sbi->inplace_count, 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);
mutex_unlock(&f2fs_stat_mutex);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 8add4e8..f68df7d 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -10,10 +10,12 @@
*/
#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)
{
@@ -94,7 +96,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
de = find_target_dentry(fname, namehash, max_slots, &d);
if (de)
*res_page = dentry_page;
@@ -111,8 +113,6 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
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 +130,11 @@ 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;
@@ -212,13 +194,9 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
f2fs_put_page(dentry_page, 0);
}
- /* This is to increase the speed of f2fs_create */
- if (!de && room) {
- F2FS_I(dir)->task = current;
- if (F2FS_I(dir)->chash != namehash) {
- F2FS_I(dir)->chash = namehash;
- F2FS_I(dir)->clevel = level;
- }
+ if (!de && room && F2FS_I(dir)->chash != namehash) {
+ F2FS_I(dir)->chash = namehash;
+ F2FS_I(dir)->clevel = level;
}
return de;
@@ -259,6 +237,9 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
break;
}
out:
+ /* This is to increase the speed of f2fs_create */
+ if (!de)
+ F2FS_I(dir)->task = current;
return de;
}
@@ -325,7 +306,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
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);
}
@@ -342,24 +323,6 @@ 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,
struct f2fs_dentry_ptr *d)
{
@@ -389,7 +352,7 @@ static int make_empty_dir(struct inode *inode,
dentry_blk = kmap_atomic(dentry_page);
- make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
do_make_empty_dir(inode, parent, &d);
kunmap_atomic(dentry_blk);
@@ -443,15 +406,19 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
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.
@@ -478,7 +445,7 @@ 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);
@@ -557,8 +524,10 @@ 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;
@@ -602,11 +571,9 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
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);
@@ -740,6 +707,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+ struct address_space *mapping = page_mapping(page);
+ unsigned long flags;
int i;
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
@@ -753,7 +722,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
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,
@@ -763,17 +732,23 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
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)) {
+ 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);
+
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
ClearPageUptodate(page);
inode_dec_dirty_pages(dir);
+ remove_dirty_inode(dir);
}
f2fs_put_page(page, 1);
}
@@ -816,7 +791,7 @@ 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;
@@ -851,7 +826,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
(u32)de->hash_code, 0,
&de_name, fstr);
if (err)
- return true;
+ return err;
de_name = *fstr;
fstr->len = save_len;
@@ -859,12 +834,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
if (!dir_emit(ctx, de_name.name, de_name.len,
le32_to_cpu(de->ino), d_type))
- return true;
+ return 1;
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
ctx->pos = start_pos + bit_pos;
}
- return false;
+ return 0;
}
static int f2fs_readdir(struct file *file, struct dir_context *ctx)
@@ -874,6 +849,7 @@ 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);
@@ -882,51 +858,63 @@ 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);
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);
- 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)) {
+ err = f2fs_fill_dentries(ctx, &d,
+ n * NR_DENTRY_IN_BLOCK, &fstr);
+ if (err) {
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
break;
}
- ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
- 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 7b32ce9..ff2352a 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -18,6 +18,179 @@
#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 *__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 **__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 *__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 __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 +250,7 @@ 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 +267,7 @@ 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 +275,6 @@ 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)
{
@@ -172,12 +315,12 @@ static void __drop_largest_extent(struct inode *inode,
if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
largest->len = 0;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}
/* return true, if inode page is changed */
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et;
@@ -215,6 +358,16 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
return false;
}
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+{
+ bool ret = __f2fs_init_extent_tree(inode, i_ext);
+
+ if (!F2FS_I(inode)->extent_tree)
+ set_inode_flag(inode, FI_NO_EXTENT);
+
+ return ret;
+}
+
static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
struct extent_info *ei)
{
@@ -237,17 +390,24 @@ 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 *)__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);
@@ -256,87 +416,6 @@ 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,
struct extent_tree *et, struct extent_info *ei,
struct extent_node *prev_ex,
@@ -391,17 +470,7 @@ 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 = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
do_insert:
en = __attach_extent_node(sbi, et, ei, parent, p);
if (!en)
@@ -417,7 +486,7 @@ 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);
@@ -430,7 +499,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
unsigned int pos = (unsigned int)fofs;
if (!et)
- return false;
+ return;
trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
@@ -438,7 +507,7 @@ 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;
@@ -451,8 +520,11 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
__drop_largest_extent(inode, 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 *)__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;
@@ -493,9 +565,8 @@ 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)
@@ -536,8 +607,6 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
__free_extent_tree(sbi, et);
write_unlock(&et->lock);
-
- return !__is_extent_same(&prev, &et->largest);
}
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -553,7 +622,7 @@ 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 */
@@ -575,11 +644,11 @@ 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);
@@ -609,7 +678,7 @@ 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);
@@ -656,10 +725,10 @@ 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;
}
@@ -667,12 +736,12 @@ 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;
@@ -719,7 +788,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
void 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);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 88e111a..d156dee 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -19,12 +19,16 @@
#include <linux/magic.h>
#include <linux/kobject.h>
#include <linux/sched.h>
+#include <linux/writeback.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>
+#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)
#else
@@ -41,11 +45,14 @@
enum {
FAULT_KMALLOC,
FAULT_PAGE_ALLOC,
+ FAULT_PAGE_GET,
+ FAULT_ALLOC_BIO,
FAULT_ALLOC_NID,
FAULT_ORPHAN,
FAULT_BLOCK,
FAULT_DIR_DEPTH,
FAULT_EVICT_INODE,
+ FAULT_TRUNCATE,
FAULT_IO,
FAULT_CHECKPOINT,
FAULT_MAX,
@@ -58,7 +65,7 @@ struct f2fs_fault_info {
};
extern char *fault_name[FAULT_MAX];
-#define IS_FAULT_SET(fi, type) (fi->inject_type & (1 << (type)))
+#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
#endif
/*
@@ -83,10 +90,15 @@ 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 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 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 ver_after(a, b) (typecheck(unsigned long long, a) && \
typecheck(unsigned long long, b) && \
@@ -102,15 +114,21 @@ struct f2fs_mount_info {
unsigned int opt;
};
-#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_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)
+ (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)
+ (F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
/*
* For checkpoint manager
@@ -120,19 +138,22 @@ 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 DEF_BATCHED_TRIM_SECTIONS 2
+#define DEF_BATCHED_TRIM_SECTIONS 2048
#define BATCHED_TRIM_SEGMENTS(sbi) \
- (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+ (GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections))
#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_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */
#define DEF_CP_INTERVAL 60 /* 60 secs */
#define DEF_IDLE_INTERVAL 5 /* 5 secs */
@@ -141,7 +162,6 @@ struct cp_control {
__u64 trim_start;
__u64 trim_end;
__u64 trim_minlen;
- __u64 trimmed;
};
/*
@@ -160,12 +180,14 @@ enum {
ORPHAN_INO, /* for orphan ino list */
APPEND_INO, /* for append ino list */
UPDATE_INO, /* for update 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 */
@@ -174,18 +196,89 @@ struct inode_entry {
struct inode *inode; /* vfs inode pointer */
};
-/* for the list of blockaddresses to be discarded */
+/* for the bitmap indicate blocks to be discarded */
struct discard_entry {
struct list_head list; /* list head */
- block_t blkaddr; /* block address to be discarded */
- int len; /* # of consecutive blocks of the discard */
+ block_t start_blkaddr; /* start blockaddr of current segment */
+ unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */
};
-struct bio_entry {
- struct list_head list;
- struct bio *bio;
- struct completion event;
- int error;
+/* 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,
+ D_SUBMIT,
+ D_DONE,
+};
+
+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 */
+ int error; /* bio error */
+};
+
+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 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 */
+ unsigned int granularity; /* discard granularity */
+};
+
+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 */
+ unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for 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 */
+ atomic_t issued_discard; /* # of issued discard */
+ atomic_t issing_discard; /* # of issing discard */
+ atomic_t discard_cmd_cnt; /* # of cached cmd count */
+ struct rb_root root; /* root of discard rb-tree */
};
/* for the list of fsync inodes, used only during recovery */
@@ -196,13 +289,13 @@ 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))
@@ -210,6 +303,7 @@ 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;
}
@@ -217,6 +311,7 @@ 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;
}
@@ -242,11 +337,17 @@ 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_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
@@ -271,6 +372,12 @@ 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;
@@ -283,36 +390,71 @@ 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
+#define DEF_MIN_INLINE_SIZE 1
+static inline int get_extra_isize(struct inode *inode);
+static inline int get_inline_xattr_addrs(struct inode *inode);
+#define F2FS_INLINE_XATTR_ADDRS(inode) get_inline_xattr_addrs(inode)
+#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \
+ (CUR_ADDRS_PER_INODE(inode) - \
+ F2FS_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;
}
/*
@@ -344,16 +486,30 @@ enum {
/* 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 rb_node rb_node;
+ union {
+ struct {
+ unsigned int fofs;
+ unsigned int len;
+ u32 blk;
+ };
+ struct extent_info ei; /* extent info */
+
+ };
struct list_head list; /* node in global extent list of sbi */
- struct extent_info ei; /* extent info */
struct extent_tree *et; /* extent tree pointer */
};
@@ -387,12 +543,13 @@ struct f2fs_map_blocks {
};
/* 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_PRE_DIO,
+ F2FS_GET_BLOCK_PRE_AIO,
+};
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -401,6 +558,7 @@ 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 file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
@@ -413,6 +571,8 @@ 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 DEF_DIR_LEVEL 0
@@ -432,16 +592,30 @@ 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 */
+ 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 */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -468,11 +642,22 @@ 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)
{
- return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk &&
- ei1->len == ei2->len);
+ return back->lstart + back->len == front->lstart;
+}
+
+static inline bool __is_discard_back_mergeable(struct discard_info *cur,
+ struct discard_info *back)
+{
+ return __is_discard_mergeable(back, cur);
+}
+
+static inline bool __is_discard_front_mergeable(struct discard_info *cur,
+ struct discard_info *front)
+{
+ return __is_discard_mergeable(cur, front);
}
static inline bool __is_extent_mergeable(struct extent_info *back,
@@ -494,20 +679,29 @@ 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 *);
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
static inline void __try_update_largest_extent(struct inode *inode,
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);
+ f2fs_mark_inode_dirty_sync(inode, 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 */
@@ -520,16 +714,28 @@ struct f2fs_nm_info {
struct list_head nat_entries; /* cached nat entry list (clean) */
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)[NAT_ENTRY_BITMAP_SIZE];
+ 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 */
};
@@ -586,19 +792,20 @@ 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 issing_flush; /* # of issing flushes */
struct llist_head issue_list; /* list for command issue */
struct llist_node *dispatch_list; /* list for command dispatch */
};
@@ -609,6 +816,8 @@ 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 */
@@ -621,12 +830,6 @@ 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 */
@@ -635,10 +838,14 @@ 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_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;
};
/*
@@ -650,13 +857,17 @@ 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,
NR_COUNT_TYPE,
};
@@ -680,35 +891,102 @@ 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,
+};
+
+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 */
+ enum iostat_type io_type; /* io type */
};
-#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,
};
@@ -736,10 +1014,6 @@ enum {
MAX_TIME,
};
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-#endif
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
@@ -747,10 +1021,11 @@ struct f2fs_sb_info {
int valid_super_block; /* valid super block no */
unsigned long s_flag; /* flags for sbi */
-#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 */
@@ -759,9 +1034,11 @@ 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 */
+ struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
+ /* bio ordering for NODE/DATA */
+ int write_io_size_bits; /* Write IO size bits */
+ mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
@@ -771,6 +1048,7 @@ 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 */
@@ -786,7 +1064,7 @@ 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 */
@@ -811,19 +1089,26 @@ struct f2fs_sb_info {
loff_t max_file_blocks; /* max block index of file */
int active_logs; /* # of active logs */
int dir_level; /* directory level */
+ int inline_xattr_size; /* inline xattr size */
+ unsigned int trigger_ssr_threshold; /* threshold to trigger ssr */
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 */
+ block_t reserved_blocks; /* configurable reserved blocks */
+ block_t current_reserved_blocks; /* current reserved blocks */
+
u32 s_next_generation; /* for NFS support */
- atomic_t nr_wb_bios; /* # of writeback bios */
/* # 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; /* count # of WB_SYNC threads */
+
/* valid inode count */
struct percpu_counter total_valid_inode_count;
@@ -856,18 +1141,30 @@ 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 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;
@@ -878,13 +1175,26 @@ struct f2fs_sb_info {
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
+ /* Precomputed FS UUID checksum for seeding other checksums */
+ __u32 s_chksum_seed;
+
/* For fault injection */
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct f2fs_fault_info fault_info;
#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
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
+#define f2fs_show_injection_info(type) \
+ printk("%sF2FS-fs : inject %s in %s of %pF\n", \
+ KERN_INFO, 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;
@@ -898,10 +1208,6 @@ 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;
@@ -912,8 +1218,8 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
* 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)
{
@@ -922,8 +1228,7 @@ static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
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);
}
@@ -969,6 +1274,27 @@ 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)
+{
+ 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 struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -1069,6 +1395,19 @@ 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);
@@ -1092,9 +1431,11 @@ 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)
@@ -1108,16 +1449,34 @@ 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);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ if (lock)
+ spin_lock_irqsave(&sbi->cp_lock, flags);
+ __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+ kfree(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)
@@ -1125,6 +1484,11 @@ 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);
@@ -1153,7 +1517,7 @@ 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)
@@ -1174,17 +1538,14 @@ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
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)
@@ -1192,15 +1553,24 @@ 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 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;
+
+ ret = dquot_reserve_block(inode, *count);
+ if (ret)
+ return ret;
#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(sbi, FAULT_BLOCK))
- return false;
+ if (time_to_inject(sbi, FAULT_BLOCK)) {
+ f2fs_show_injection_info(FAULT_BLOCK);
+ release = *count;
+ goto enospc;
+ }
#endif
/*
* let's increase this in prior to actual block count change in order
@@ -1210,39 +1580,55 @@ 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 (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
+ diff = sbi->total_valid_block_count - avail_user_block_count;
*count -= diff;
- sbi->total_valid_block_count = sbi->user_block_count;
+ release = diff;
+ sbi->total_valid_block_count = avail_user_block_count;
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 (release)
+ dquot_release_reservation_block(inode, release);
+ f2fs_i_blocks_write(inode, *count, true, true);
+ return 0;
+
+enospc:
+ 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)
+ if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES ||
+ count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA)
return;
set_sbi_flag(sbi, SBI_IS_DIRTY);
@@ -1253,6 +1639,8 @@ 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)
@@ -1269,6 +1657,8 @@ 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)
@@ -1363,51 +1753,80 @@ 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;
+ bool quota = inode && !is_inode;
+
+ if (quota) {
+ int ret = dquot_reserve_block(inode, 1);
+ if (ret)
+ return ret;
+ }
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_BLOCK)) {
+ f2fs_show_injection_info(FAULT_BLOCK);
+ goto enospc;
+ }
+#endif
spin_lock(&sbi->stat_lock);
valid_block_count = sbi->total_valid_block_count + 1;
- if (unlikely(valid_block_count > sbi->user_block_count)) {
+ if (unlikely(valid_block_count + sbi->current_reserved_blocks >
+ 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 (quota)
+ 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)
+ f2fs_i_blocks_write(inode, 1, false, true);
}
static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1435,17 +1854,33 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
{
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct page *page = find_lock_page(mapping, index);
+
if (page)
return page;
- if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
+ if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
+ f2fs_show_injection_info(FAULT_PAGE_ALLOC);
return NULL;
+ }
#endif
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)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
+ f2fs_show_injection_info(FAULT_PAGE_GET);
+ return NULL;
+ }
+#endif
+ 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);
@@ -1495,15 +1930,25 @@ 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;
+ }
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
+ f2fs_show_injection_info(FAULT_ALLOC_BIO);
+ return NULL;
+ }
+#endif
+ return bio_alloc(GFP_KERNEL, npages);
}
static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
@@ -1518,22 +1963,42 @@ 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 (!inode) {
+ if (is_inode)
+ base = offset_in_addr(&raw_node->i);
+ } else if (f2fs_has_extra_attr(inode) && is_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)
@@ -1596,6 +2061,20 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
*addr ^= mask;
}
+#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
+#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
+#define F2FS_FL_INHERITED (FS_PROJINHERIT_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 */
@@ -1614,6 +2093,7 @@ 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 */
@@ -1621,6 +2101,10 @@ 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 */
};
static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -1634,7 +2118,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
return;
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}
@@ -1661,7 +2145,7 @@ 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)
@@ -1670,18 +2154,26 @@ 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);
}
@@ -1695,34 +2187,27 @@ 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_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)
@@ -1739,6 +2224,8 @@ 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);
}
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
@@ -1755,6 +2242,13 @@ 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;
+}
+
+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)
@@ -1764,24 +2258,20 @@ 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) - F2FS_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]);
+ F2FS_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)
@@ -1789,12 +2279,6 @@ 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);
@@ -1810,6 +2294,11 @@ 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);
@@ -1825,10 +2314,12 @@ 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)
@@ -1850,15 +2341,40 @@ 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 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;
+
+ 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;
+}
+
+#define sb_rdonly f2fs_readonly
static inline int f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
@@ -1893,13 +2409,15 @@ 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))
+ if (time_to_inject(sbi, FAULT_KMALLOC)) {
+ f2fs_show_injection_info(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;
@@ -1909,7 +2427,7 @@ 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 *kvzalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -1919,42 +2437,95 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
return ret;
}
+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 int get_extra_isize(struct inode *inode)
+{
+ return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
+}
+
+static inline int f2fs_sb_has_flexible_inline_xattr(struct super_block *sb);
+static inline int get_inline_xattr_addrs(struct inode *inode)
+{
+ return F2FS_I(inode)->i_inline_xattr_size;
+}
+
#define 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 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);
+}
/*
* 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 truncate_data_blocks(struct dnode_of_data *dn);
+int 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 truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+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);
/*
* 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 try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
+int update_inode(struct inode *inode, struct page *node_page);
+int 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 handle_failed_inode(struct inode *inode);
/*
* namei.c
@@ -1964,40 +2535,45 @@ 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 *);
+void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
+unsigned char get_de_type(struct f2fs_dir_entry *de);
+struct f2fs_dir_entry *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 do_make_empty_dir(struct inode *inode, struct inode *parent,
+ struct f2fs_dentry_ptr *d);
+struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+ const struct qstr *new_name,
+ const struct qstr *orig_name, struct page *dpage);
+void update_parent_metadata(struct inode *dir, struct inode *inode,
+ unsigned int current_depth);
+int 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_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+ struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_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)
{
@@ -2008,12 +2584,14 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
/*
* 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);
+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 *, ...);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
int sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
@@ -2028,160 +2606,197 @@ 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 *);
+bool available_free_memory(struct f2fs_sb_info *sbi, int type);
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
+void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
+int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
+int truncate_inode_blocks(struct inode *inode, pgoff_t from);
+int truncate_xattr_node(struct inode *inode);
+int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
+int remove_inode_page(struct inode *inode);
+struct page *new_inode_page(struct inode *inode);
+struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs);
+void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
+struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct page *get_node_page_ra(struct page *parent, int start);
+void move_node_page(struct page *node_page, int gc_type);
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic);
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type);
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
+bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
+void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
+void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
+void recover_inline_xattr(struct inode *inode, struct page *page);
+int recover_xattr_data(struct inode *inode, struct page *page,
+ block_t blkaddr);
+int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
+int restore_node_summary(struct f2fs_sb_info *sbi,
+ unsigned int segno, struct f2fs_summary_block *sum);
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_node_manager(struct f2fs_sb_info *sbi);
+void destroy_node_manager(struct f2fs_sb_info *sbi);
int __init create_node_manager_caches(void);
void 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 *);
+bool need_SSR(struct f2fs_sb_info *sbi);
+void register_inmem_page(struct inode *inode, struct page *page);
+void drop_inmem_pages_all(struct f2fs_sb_info *sbi);
+void drop_inmem_pages(struct inode *inode);
+void drop_inmem_page(struct inode *inode, struct page *page);
+int 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 create_flush_cmd_control(struct f2fs_sb_info *sbi);
+int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
+void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+void init_discard_policy(struct discard_policy *dpolicy, int discard_type,
+ unsigned int granularity);
+void stop_discard_thread(struct f2fs_sb_info *sbi);
+bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void release_discard_addrs(struct f2fs_sb_info *sbi);
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+ enum iostat_type io_type);
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
+int rewrite_data_page(struct f2fs_io_info *fio);
+void __f2fs_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 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);
+void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr);
+void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+ unsigned int val, int alloc);
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_segment_manager(struct f2fs_sb_info *sbi);
+void destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init create_segment_manager_caches(void);
void destroy_segment_manager_caches(void);
/*
* 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);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
-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 *);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
+bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+ int type, bool sync);
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+ long nr_to_write, enum iostat_type io_type);
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
+bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+ unsigned int devidx, int type);
+bool 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 acquire_orphan_inode(struct f2fs_sb_info *sbi);
+void release_orphan_inode(struct f2fs_sb_info *sbi);
+void add_orphan_inode(struct inode *inode);
+void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
+int recover_orphan_inodes(struct f2fs_sb_info *sbi);
+int get_valid_checkpoint(struct f2fs_sb_info *sbi);
+void update_dirty_page(struct inode *inode, struct page *page);
+void remove_dirty_inode(struct inode *inode);
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init create_checkpoint_caches(void);
void 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);
+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, nid_t ino, pgoff_t idx,
+ enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
+int f2fs_submit_page_bio(struct f2fs_io_info *fio);
+int 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 set_data_blkaddr(struct dnode_of_data *dn);
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
+int 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 *get_read_data_page(struct inode *inode, pgoff_t index,
+ int op_flags, bool for_write);
+struct page *find_data_page(struct inode *inode, pgoff_t index);
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+ bool for_write);
+struct page *get_new_data_page(struct inode *inode,
+ struct page *ipage, pgoff_t index, bool new_i_size);
+int do_write_data_page(struct f2fs_io_info *fio);
+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);
+void f2fs_set_page_dirty_nobuffers(struct page *page);
+int __f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ enum iostat_type io_type);
+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
/*
* 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 start_gc_thread(struct f2fs_sb_info *sbi);
+void stop_gc_thread(struct f2fs_sb_info *sbi);
+block_t 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 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 recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
+bool space_for_roll_forward(struct f2fs_sb_info *sbi);
/*
* debug.c
@@ -2195,13 +2810,20 @@ 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_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;
@@ -2273,11 +2895,33 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
((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 { \
@@ -2287,14 +2931,14 @@ 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) \
@@ -2302,37 +2946,43 @@ 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 f2fs_build_stats(struct f2fs_sb_info *sbi);
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
int __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_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_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) { }
@@ -2355,53 +3005,79 @@ extern struct kmem_cache *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 read_inline_data(struct page *page, struct page *ipage);
+void 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 recover_inline_data(struct inode *inode, struct page *npage);
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page);
+int 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 *__lookup_rb_tree(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs);
+struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+ struct rb_root *root, struct rb_node **parent,
+ unsigned int ofs);
+struct rb_entry *__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 __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 *);
+ pgoff_t fofs, block_t blkaddr, unsigned int len);
+void init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init create_extent_cache(void);
void 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
*/
static inline bool f2fs_encrypted_inode(struct inode *inode)
@@ -2409,10 +3085,16 @@ 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);
+ inode->i_flags |= S_ENCRYPTED;
#endif
}
@@ -2426,9 +3108,55 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb)
return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
}
-static inline int f2fs_sb_mounted_hmsmr(struct super_block *sb)
+static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb)
{
- return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_HMSMR);
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED);
+}
+
+static inline int f2fs_sb_has_extra_attr(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_EXTRA_ATTR);
+}
+
+static inline int f2fs_sb_has_project_quota(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_PRJQUOTA);
+}
+
+static inline int f2fs_sb_has_inode_chksum(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM);
+}
+
+static inline int f2fs_sb_has_flexible_inline_xattr(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_FLEXIBLE_INLINE_XATTR);
+}
+
+static inline int f2fs_sb_has_quota_ino(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_QUOTA_INO);
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline int get_blkz_type(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkaddr)
+{
+ 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_discard_en(struct f2fs_sb_info *sbi)
+{
+ struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
+
+ return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb);
}
static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
@@ -2457,28 +3185,4 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
#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_process_policy fscrypt_notsupp_process_policy
-#define fscrypt_get_policy fscrypt_notsupp_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
#endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 801111e..020cfaa 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -20,6 +20,7 @@
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
+#include <linux/uio.h>
#include <linux/uuid.h>
#include <linux/file.h>
@@ -32,6 +33,19 @@
#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)
{
@@ -41,6 +55,11 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct dnode_of_data dn;
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));
@@ -59,13 +78,14 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
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;
}
/*
@@ -85,25 +105,28 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
if (!PageUptodate(page))
SetPageUptodate(page);
+ f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
+
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 (f2fs_encrypted_file(inode))
+ f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr);
- /* if gced page is attached, don't write to cold segment */
- clear_cold_data(page);
+out_sem:
+ up_read(&F2FS_I(inode)->i_mmap_sem);
out:
sb_end_pagefault(inode->i_sb);
f2fs_update_time(sbi, REQ_TIME);
+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 +141,34 @@ 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;
+ cp_reason = CP_WRONG_PINO;
else if (!space_for_roll_forward(sbi))
- need_cp = true;
+ cp_reason = CP_NO_SPC_ROLL;
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_NODE_NEED_CP;
else if (test_opt(sbi, FASTBOOT))
- need_cp = true;
+ cp_reason = CP_FASTBOOT_MODE;
else if (sbi->active_logs == 2)
- need_cp = true;
+ cp_reason = CP_SPEC_LOG_NUM;
- return need_cp;
+ return cp_reason;
}
static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
@@ -170,7 +188,6 @@ 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);
@@ -186,7 +203,7 @@ 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,
@@ -205,12 +222,12 @@ 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;
}
@@ -236,10 +253,10 @@ 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);
@@ -264,31 +281,47 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
}
if (need_inode_block_update(sbi, ino)) {
- f2fs_mark_inode_dirty_sync(inode);
+ 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 = wait_on_node_pages_writeback(sbi, ino);
+ if (ret)
+ goto out;
+ }
/* once recovery info is written, don't need to tack this */
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)
+ ret = f2fs_issue_flush(sbi, inode->i_ino);
+ if (!ret) {
+ remove_ino_entry(sbi, ino, UPDATE_INO);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
+ 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);
}
@@ -376,7 +409,8 @@ 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 (__found_offset(blkaddr, dirty, pgofs, whence)) {
f2fs_put_dnode(&dn);
@@ -424,13 +458,8 @@ 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);
@@ -444,11 +473,10 @@ 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;
- if (!ret && f2fs_encrypted_inode(inode)) {
- ret = fscrypt_get_encryption_info(inode);
+ if (f2fs_encrypted_inode(inode)) {
+ int ret = fscrypt_get_encryption_info(inode);
if (ret)
return -EACCES;
if (!fscrypt_has_encryption_key(inode))
@@ -461,7 +489,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
return -EPERM;
}
dput(dir);
- return ret;
+ return dquot_file_open(inode, filp);
}
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -470,9 +498,13 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
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);
@@ -532,12 +564,14 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
page = 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);
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;
@@ -570,8 +604,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
}
if (f2fs_has_inline_data(inode)) {
- if (truncate_inline_inode(ipage, from))
- set_page_dirty(ipage);
+ truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
@@ -614,12 +647,21 @@ 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);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
+ f2fs_show_injection_info(FAULT_TRUNCATE);
+ return -EIO;
+ }
+#endif
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
@@ -632,16 +674,21 @@ int f2fs_truncate(struct inode *inode)
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);
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;
}
@@ -679,28 +726,53 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int err;
+ bool size_changed = false;
+
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
err = setattr_prepare(dentry, attr);
if (err)
return err;
- if (attr->ia_valid & ATTR_SIZE) {
- if (f2fs_encrypted_inode(inode) &&
- fscrypt_get_encryption_info(inode))
- return -EACCES;
+ 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))) {
+ err = dquot_transfer(inode, attr);
+ if (err)
+ return err;
+ }
- if (attr->ia_size <= i_size_read(inode)) {
- truncate_setsize(inode, attr->ia_size);
- err = f2fs_truncate(inode);
+ if (attr->ia_valid & ATTR_SIZE) {
+ if (f2fs_encrypted_inode(inode)) {
+ err = fscrypt_get_encryption_info(inode);
if (err)
return err;
- f2fs_balance_fs(F2FS_I_SB(inode), true);
+ if (!fscrypt_has_encryption_key(inode))
+ return -ENOKEY;
+ }
+
+ if (attr->ia_size <= i_size_read(inode)) {
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+ truncate_setsize(inode, attr->ia_size);
+ err = f2fs_truncate(inode);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ if (err)
+ return err;
} else {
/*
* do not trim all blocks after i_size if target size is
* larger than i_size.
*/
+ down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_setsize(inode, attr->ia_size);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
/* should convert inline inode here */
if (!f2fs_may_inline_data(inode)) {
@@ -710,6 +782,12 @@ 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);
+
+ size_changed = true;
}
__setattr_copy(inode, attr);
@@ -722,7 +800,12 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
}
}
- f2fs_mark_inode_dirty_sync(inode);
+ /* file size may changed here */
+ f2fs_mark_inode_dirty_sync(inode, size_changed);
+
+ /* inode change will produce dirty node pages flushed by checkpoint */
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
return err;
}
@@ -774,7 +857,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
- pg_start++;
+ pg_start = get_next_page_offset(&dn, pg_start);
continue;
}
return err;
@@ -836,12 +919,14 @@ 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_mmap_sem);
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
f2fs_lock_op(sbi);
ret = truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
}
}
@@ -872,7 +957,8 @@ 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);
+ *blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (!is_checkpointed_data(sbi, *blkaddr)) {
if (test_opt(sbi, LFS)) {
@@ -948,15 +1034,15 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
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);
+ dn.data_blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
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);
@@ -1008,11 +1094,11 @@ 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 = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
if (!src_blkaddr)
return -ENOMEM;
- do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+ do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
@@ -1080,16 +1166,20 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
pg_start = offset >> PAGE_SHIFT;
pg_end = (offset + len) >> PAGE_SHIFT;
+ down_write(&F2FS_I(inode)->i_mmap_sem);
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
- return ret;
+ goto out;
+
+ /* avoid gc operation during block exchange */
+ down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
truncate_pagecache(inode, offset);
ret = f2fs_do_collapse(inode, pg_start, pg_end);
if (ret)
- return ret;
+ goto out_unlock;
/* write out all moved pages, if possible */
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -1101,7 +1191,10 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ret = truncate_blocks(inode, new_size, true);
if (!ret)
f2fs_i_size_write(inode, new_size);
-
+out_unlock:
+ up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1115,7 +1208,8 @@ 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++;
}
@@ -1126,8 +1220,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
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
* allocation.
@@ -1166,9 +1260,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
+ down_write(&F2FS_I(inode)->i_mmap_sem);
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
- return ret;
+ goto out_sem;
truncate_pagecache_range(inode, offset, offset + len - 1);
@@ -1182,17 +1277,15 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
- return ret;
+ goto out_sem;
- if (offset + len > new_size)
- new_size = offset + len;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
- return ret;
+ goto out_sem;
new_size = max_t(loff_t, new_size,
(loff_t)pg_start << PAGE_SHIFT);
@@ -1218,6 +1311,9 @@ 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);
+
+ f2fs_balance_fs(sbi, dn.node_changed);
+
if (ret)
goto out;
@@ -1238,6 +1334,8 @@ 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);
+out_sem:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1250,8 +1348,9 @@ 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;
@@ -1266,14 +1365,18 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
ret = truncate_blocks(inode, i_size_read(inode), true);
if (ret)
- return ret;
+ goto out;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
- return ret;
+ goto out;
+
+ /* avoid gc operation during block exchange */
+ down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
truncate_pagecache(inode, offset);
@@ -1302,6 +1405,10 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
if (!ret)
f2fs_i_size_write(inode, new_size);
+
+ up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1313,15 +1420,15 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
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);
@@ -1333,12 +1440,12 @@ 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;
@@ -1349,10 +1456,14 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
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,
@@ -1361,6 +1472,9 @@ 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;
@@ -1393,7 +1507,7 @@ 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);
}
@@ -1419,6 +1533,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(inode, FI_DROP_CACHE);
@@ -1426,17 +1541,20 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
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)
+ drop_inmem_pages(inode);
+ return 0;
}
static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
@@ -1465,28 +1583,34 @@ 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 (!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;
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;
}
@@ -1506,6 +1630,9 @@ 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;
@@ -1520,17 +1647,26 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
goto out;
set_inode_flag(inode, FI_ATOMIC_FILE);
+ set_inode_flag(inode, FI_HOT_DATA);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (!get_dirty_pages(inode))
- goto out;
+ goto inc_stat;
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)
+ if (ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ goto out;
+ }
+
+inc_stat:
+ F2FS_I(inode)->inmem_task = current;
+ stat_inc_atomic_write(inode);
+ stat_update_max_atomic_write(inode);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -1555,15 +1691,19 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
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);
+ if (ret)
goto err_out;
- }
- }
- ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ if (!ret) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ stat_dec_atomic_write(inode);
+ }
+ } else {
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
+ }
err_out:
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -1578,6 +1718,9 @@ 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;
@@ -1591,6 +1734,9 @@ 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:
@@ -1646,6 +1792,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
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);
}
@@ -1691,7 +1838,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
- sync_meta_pages(sbi, META, LONG_MAX);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
break;
default:
@@ -1752,31 +1899,21 @@ static bool uuid_is_nonzero(__u8 u[16])
static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
- struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
- if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
- sizeof(policy)))
- return -EFAULT;
+ if (!f2fs_sb_has_crypto(inode->i_sb))
+ return -EOPNOTSUPP;
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return fscrypt_process_policy(filp, &policy);
+ return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
{
- struct fscrypt_policy policy;
- struct inode *inode = file_inode(filp);
- int err;
-
- err = fscrypt_get_policy(inode, &policy);
- if (err)
- return err;
-
- if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
- return -EFAULT;
- return 0;
+ if (!f2fs_sb_has_crypto(file_inode(filp)->i_sb))
+ return -EOPNOTSUPP;
+ return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
@@ -1842,7 +1979,51 @@ 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;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ end = range.start + range.len;
+ if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi))
+ return -EINVAL;
+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 += sbi->blocks_per_seg;
+ if (range.start <= end)
+ goto do_more;
out:
mnt_drop_write_file(filp);
return ret;
@@ -1876,17 +2057,16 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
{
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
- struct extent_info ei;
+ struct extent_info ei = {0,0,0};
pgoff_t pg_start, pg_end;
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 (need_inplace_update_policy(inode, NULL))
return -EINVAL;
pg_start = range->start >> PAGE_SHIFT;
@@ -1920,7 +2100,7 @@ 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;
@@ -1944,7 +2124,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
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 = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi);
/*
* make sure there are enough free section for LFS allocation, this can
@@ -1962,7 +2142,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
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;
@@ -2021,42 +2201,40 @@ 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,
@@ -2090,9 +2268,13 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
}
inode_lock(src);
+ down_write(&F2FS_I(src)->dio_rwsem[WRITE]);
if (src != dst) {
- if (!inode_trylock(dst)) {
- ret = -EBUSY;
+ ret = -EBUSY;
+ if (!inode_trylock(dst))
+ goto out;
+ if (!down_write_trylock(&F2FS_I(dst)->dio_rwsem[WRITE])) {
+ inode_unlock(dst);
goto out;
}
}
@@ -2152,9 +2334,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
}
f2fs_unlock_op(sbi);
out_unlock:
- if (src != dst)
+ if (src != dst) {
+ up_write(&F2FS_I(dst)->dio_rwsem[WRITE]);
inode_unlock(dst);
+ }
out:
+ up_write(&F2FS_I(src)->dio_rwsem[WRITE]);
inode_unlock(src);
return ret;
}
@@ -2190,6 +2375,8 @@ 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)))
@@ -2199,8 +2386,84 @@ 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 (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 ||
+ sbi->segs_per_sec != 1) {
+ 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);
+}
+
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);
@@ -2230,12 +2493,18 @@ 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);
default:
return -ENOTTY;
}
@@ -2248,20 +2517,30 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
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);
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);
+ int err;
+
+ if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+ set_inode_flag(inode, FI_NO_PREALLOC);
+
+ err = f2fs_preallocate_blocks(iocb, from);
+ if (err) {
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+ inode_unlock(inode);
+ return err;
}
+ blk_start_plug(&plug);
+ ret = __generic_file_write_iter(iocb, from);
+ blk_finish_plug(&plug);
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
}
inode_unlock(inode);
@@ -2293,10 +2572,12 @@ 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:
break;
default:
return -ENOIOCTLCMD;
@@ -2312,6 +2593,7 @@ 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 34a69e7..5d5bba4 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -28,17 +28,23 @@ 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 {
+ 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())
continue;
- else
- wait_event_interruptible_timeout(*wq,
- kthread_should_stop(),
- msecs_to_jiffies(wait_ms));
if (kthread_should_stop())
break;
@@ -48,10 +54,15 @@ static int gc_thread_func(void *data)
}
#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))
+ continue;
+
/*
* [GC triggering condition]
* 0. GC is not conducted currently.
@@ -66,23 +77,28 @@ static int gc_thread_func(void *data)
* So, I'd like to wait some time to collect dirty segments.
*/
if (!mutex_trylock(&sbi->gc_mutex))
- continue;
+ goto next;
+
+ if (gc_th->gc_urgent) {
+ wait_ms = gc_th->urgent_sleep_time;
+ goto do_gc;
+ }
if (!is_idle(sbi)) {
increase_sleep_time(gc_th, &wait_ms);
mutex_unlock(&sbi->gc_mutex);
- continue;
+ 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,
@@ -90,6 +106,8 @@ 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;
@@ -107,11 +125,14 @@ 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_urgent = 0;
+ gc_th->gc_wake= 0;
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
@@ -170,7 +191,11 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
if (gc_type != FG_GC && 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 */
+ if (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 +205,7 @@ 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 */
@@ -205,7 +230,7 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
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 +238,8 @@ 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 +248,7 @@ 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 +275,7 @@ 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 +304,7 @@ 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 +318,18 @@ 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 (IS_DATASEG(get_seg_entry(sbi, *result)->type) &&
+ 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];
+ 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 +342,10 @@ 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;
}
@@ -327,7 +362,7 @@ 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;
@@ -345,17 +380,18 @@ 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:
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
@@ -420,10 +456,10 @@ 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;
}
@@ -538,12 +574,14 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
get_node_info(sbi, nid, dni);
if (sum->version != dni->version) {
- f2fs_put_page(node_page, 1);
- return false;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: valid data with mismatched node version.",
+ __func__);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
}
*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)
@@ -551,14 +589,22 @@ 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)
+/*
+ * Move data block via META_MAPPING while keeping locked data page.
+ * This can be used to move blocks, aka LBAs, directly on disk.
+ */
+static void move_data_block(struct inode *inode, block_t bidx,
+ 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,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
@@ -572,6 +618,12 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
if (!page)
return;
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+ goto out;
+
+ if (f2fs_is_atomic_file(inode))
+ goto out;
+
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
if (err)
@@ -596,10 +648,10 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
- &sum, CURSEG_COLD_DATA);
+ &sum, CURSEG_COLD_DATA, NULL, false);
- fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
- FGP_LOCK | FGP_CREAT, GFP_NOFS);
+ 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;
@@ -632,9 +684,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
f2fs_wait_on_page_writeback(dn.node_page, NODE, 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);
+
+ f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);
f2fs_update_data_blkaddr(&dn, newaddr);
set_inode_flag(inode, FI_APPEND_WRITE);
@@ -652,7 +706,8 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
f2fs_put_page(page, 1);
}
-static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
+static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
+ unsigned int segno, int off)
{
struct page *page;
@@ -660,6 +715,12 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
if (IS_ERR(page))
return;
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+ goto out;
+
+ if (f2fs_is_atomic_file(inode))
+ goto out;
+
if (gc_type == BG_GC) {
if (PageWriteback(page))
goto out;
@@ -668,11 +729,16 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
} 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;
@@ -680,8 +746,10 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
retry:
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);
+ remove_dirty_inode(inode);
+ }
set_cold_data(page);
@@ -690,8 +758,6 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
-
- clear_cold_data(page);
}
out:
f2fs_put_page(page, 1);
@@ -761,16 +827,22 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
continue;
/* if encrypted inode, let's go phase 3 */
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
+ if (f2fs_encrypted_file(inode)) {
add_gc_inode(gc_list, inode);
continue;
}
+ if (!down_write_trylock(
+ &F2FS_I(inode)->dio_rwsem[WRITE])) {
+ iput(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);
+ up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
if (IS_ERR(data_page)) {
iput(inode);
continue;
@@ -796,14 +868,18 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
continue;
}
locked = true;
+
+ /* wait for all inflight aio data */
+ inode_dio_wait(inode);
}
start_bidx = 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_encrypted_file(inode))
+ move_data_block(inode, start_bidx, segno, off);
else
- move_data_page(inode, start_bidx, gc_type);
+ move_data_page(inode, start_bidx, gc_type,
+ segno, off);
if (locked) {
up_write(&fi->dio_rwsem[WRITE]);
@@ -824,10 +900,10 @@ 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;
}
@@ -840,7 +916,7 @@ 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;
unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
SUM_TYPE_DATA : SUM_TYPE_NODE;
@@ -864,7 +940,7 @@ 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 ||
+ if (get_valid_blocks(sbi, segno, false) == 0 ||
!PageUptodate(sum_page) ||
unlikely(f2fs_cp_error(sbi)))
goto next;
@@ -875,11 +951,10 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
/*
* 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
@@ -887,87 +962,113 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
gc_type);
stat_inc_seg_count(sbi, type, gc_type);
+
+ if (gc_type == FG_GC &&
+ get_valid_blocks(sbi, segno, false) == 0)
+ seg_freed++;
next:
f2fs_put_page(sum_page, 0);
}
if (gc_type == FG_GC)
- f2fs_submit_merged_bio(sbi,
- (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+ 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),
};
+ 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);
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)) {
+ if (prefree_segments(sbi)) {
ret = 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)
sbi->cur_victim_sec = NULL_SEGNO;
if (!sync) {
- if (has_not_enough_free_secs(sbi, sec_freed, 0))
+ if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
+ segno = NULL_SEGNO;
goto gc_more;
+ }
if (gc_type == FG_GC)
ret = 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);
@@ -979,7 +1080,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
void build_gc_manager(struct f2fs_sb_info *sbi)
{
- u64 main_count, resv_count, ovp_count, blocks_per_sec;
+ u64 main_count, resv_count, ovp_count;
DIRTY_I(sbi)->v_ops = &default_v_ops;
@@ -987,8 +1088,12 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
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->fggc_threshold = div_u64((main_count - ovp_count) * blocks_per_sec,
- (main_count - resv_count));
+ sbi->fggc_threshold = div64_u64((main_count - ovp_count) *
+ BLKS_PER_SEC(sbi), (main_count - resv_count));
+
+ /* give warm/cold data area from slower device */
+ if (sbi->s_ndevs && sbi->segs_per_sec == 1)
+ 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..9325191 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -13,6 +13,7 @@
* 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 */
@@ -27,12 +28,15 @@ 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_urgent;
+ unsigned int gc_wake;
};
struct gc_inode_list {
@@ -65,25 +69,32 @@ 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/inline.c b/fs/f2fs/inline.c
index a21faa1..364114a 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -13,6 +13,7 @@
#include "f2fs.h"
#include "node.h"
+#include <trace/events/android_fs.h>
bool f2fs_may_inline_data(struct inode *inode)
{
@@ -22,10 +23,10 @@ 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_encrypted_file(inode))
return false;
return true;
@@ -44,6 +45,7 @@ bool f2fs_may_inline_dentry(struct inode *inode)
void read_inline_data(struct page *page, struct page *ipage)
{
+ struct inode *inode = page->mapping->host;
void *src_addr, *dst_addr;
if (PageUptodate(page))
@@ -51,45 +53,62 @@ 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 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);
+ 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;
+ 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 = 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;
}
@@ -101,6 +120,8 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
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;
}
@@ -109,11 +130,13 @@ 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,
};
int dirty, err;
@@ -135,20 +158,23 @@ 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);
fio.old_blkaddr = dn->data_blkaddr;
+ set_inode_flag(dn->inode, FI_HOT_DATA);
write_data_page(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
- if (dirty)
+ if (dirty) {
inode_dec_dirty_pages(dn->inode);
+ 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);
+ 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;
}
@@ -195,6 +221,8 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
+ struct address_space *mapping = page_mapping(page);
+ unsigned long flags;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -211,11 +239,16 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
f2fs_wait_on_page_writeback(dn.inode_page, NODE, 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);
+ 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);
+
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
@@ -250,9 +283,9 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
f2fs_wait_on_page_writeback(ipage, NODE, 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);
@@ -265,9 +298,8 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
if (f2fs_has_inline_data(inode)) {
ipage = 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);
+ 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))
@@ -281,11 +313,11 @@ struct f2fs_dir_entry *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);
@@ -296,9 +328,9 @@ 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);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
de = find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
@@ -312,19 +344,19 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
int 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);
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
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;
}
@@ -333,11 +365,12 @@ 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);
@@ -352,25 +385,24 @@ 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);
+ zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE);
dentry_blk = kmap_atomic(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))
@@ -378,7 +410,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
- truncate_inline_inode(ipage, 0);
+ truncate_inline_inode(dir, ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
@@ -391,14 +423,13 @@ 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;
@@ -419,7 +450,7 @@ 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;
@@ -440,20 +471,20 @@ static int f2fs_add_inline_entries(struct inode *dir,
}
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));
+ truncate_inline_inode(dir, ipage, 0);
unlock_page(ipage);
@@ -469,9 +500,9 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
return 0;
recover:
lock_page(ipage);
- memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ 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);
@@ -480,7 +511,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
}
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);
@@ -496,7 +527,7 @@ 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;
@@ -506,11 +537,12 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
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 = 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;
@@ -525,14 +557,11 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
err = PTR_ERR(page);
goto fail;
}
- if (f2fs_encrypted_inode(dir))
- file_set_enc_name(inode);
}
f2fs_wait_on_page_writeback(ipage, NODE, 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);
@@ -555,7 +584,8 @@ 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;
@@ -563,17 +593,18 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
lock_page(page);
f2fs_wait_on_page_writeback(page, NODE, 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);
@@ -584,20 +615,21 @@ 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);
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;
@@ -607,26 +639,30 @@ 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);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
- inline_dentry = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(inode, ipage);
- make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
- if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
- ctx->pos = NR_INLINE_DENTRY;
+ err = f2fs_fill_dentries(ctx, &d, 0, fstr);
+ if (!err)
+ ctx->pos = d.max;
f2fs_put_page(ipage, 1);
- return 0;
+ return err < 0 ? err : 0;
}
int f2fs_inline_data_fiemap(struct inode *inode,
@@ -648,7 +684,7 @@ 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)
@@ -657,7 +693,8 @@ int f2fs_inline_data_fiemap(struct inode *inode,
get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
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 d736989..b4c4f2b 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -16,13 +16,15 @@
#include "f2fs.h"
#include "node.h"
+#include "segment.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 (f2fs_inode_dirtied(inode, sync))
return;
+
mark_inode_dirty_sync(inode);
}
@@ -41,27 +43,31 @@ void f2fs_set_inode_flags(struct inode *inode)
new_fl |= S_NOATIME;
if (flags & FS_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 bool __written_first_block(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 (addr != NEW_ADDR && addr != NULL_ADDR)
return true;
@@ -70,25 +76,27 @@ static bool __written_first_block(struct f2fs_inode *ri)
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++) {
@@ -103,12 +111,84 @@ 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;
+ int extra_isize = le32_to_cpu(ri->i_extra_isize);
+
+ if (!f2fs_sb_has_inode_chksum(sbi->sb))
+ return false;
+
+ if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
+ return false;
+
+ if (!F2FS_FITS_IN_INODE(ri, 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 (!f2fs_enable_inode_chksum(sbi, page) ||
+ PageDirty(page) || PageWriteback(page))
+ 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 int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
+ projid_t i_projid;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
@@ -129,7 +209,7 @@ 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);
@@ -152,6 +232,26 @@ 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->sb)) {
+ f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+ 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;
+ }
+
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
@@ -165,6 +265,16 @@ static int do_read_inode(struct inode *inode)
if (!need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
+ if (fi->i_flags & FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) &&
+ 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);
+
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -225,6 +335,7 @@ 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;
@@ -252,6 +363,7 @@ struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
int update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
f2fs_inode_synced(inode);
@@ -265,13 +377,15 @@ 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);
@@ -287,6 +401,24 @@ int update_inode(struct inode *inode, struct page *node_page)
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)->sb))
+ 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)->sb) &&
+ 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);
+ }
+ }
+
__set_inode_rdev(inode, ri);
set_cold_node(inode, node_page);
@@ -312,7 +444,6 @@ int update_inode_page(struct inode *inode)
} else if (err != -ENOENT) {
f2fs_stop_checkpoint(sbi, false);
}
- f2fs_inode_synced(inode);
return 0;
}
ret = update_inode(inode, node_page);
@@ -335,7 +466,8 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
* 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))
+ update_inode_page(inode);
+ if (wbc && wbc->nr_to_write)
f2fs_balance_fs(sbi, true);
return 0;
}
@@ -368,10 +500,11 @@ void f2fs_evict_inode(struct inode *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
+ dquot_initialize(inode);
+
+ remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
+ remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+ remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
@@ -380,10 +513,18 @@ void f2fs_evict_inode(struct inode *inode)
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+ f2fs_show_injection_info(FAULT_EVICT_INODE);
+ err = -EIO;
+ }
+#endif
if (!err) {
f2fs_lock_op(sbi);
err = remove_inode_page(inode);
f2fs_unlock_op(sbi);
+ if (err == -ENOENT)
+ err = 0;
}
/* give more chances, if ENOMEM case */
@@ -394,25 +535,39 @@ void f2fs_evict_inode(struct inode *inode)
if (err)
update_inode_page(inode);
+ dquot_free_inode(inode);
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)))
+ 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 (inode->i_nlink) {
+ 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);
+ } else {
+ f2fs_bug_on(sbi, err &&
+ !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
}
- f2fs_bug_on(sbi, err &&
- !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
out_clear:
fscrypt_put_encryption_info(inode, NULL);
clear_inode(inode);
@@ -424,6 +579,19 @@ void handle_failed_inode(struct inode *inode)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct node_info ni;
+ /*
+ * 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.
+ */
+ update_inode_page(inode);
+ f2fs_inode_synced(inode);
+
/* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 8556fe1..5deadc9 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -15,6 +15,7 @@
#include <linux/ctype.h>
#include <linux/dcache.h>
#include <linux/namei.h>
+#include <linux/quotaops.h>
#include "f2fs.h"
#include "node.h"
@@ -28,6 +29,7 @@ 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);
@@ -42,6 +44,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
}
f2fs_unlock_op(sbi);
+ nid_free = true;
+
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
@@ -52,29 +56,69 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
- nid_free = true;
goto fail;
}
+ if (f2fs_sb_has_project_quota(sbi->sb) &&
+ (F2FS_I(dir)->i_flags & FS_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;
+
+ err = dquot_alloc_inode(inode);
+ if (err)
+ goto fail_drop;
+
/* If the directory encrypted, then we should encrypt the inode. */
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
f2fs_set_encrypted_inode(inode);
set_inode_flag(inode, FI_NEW_INODE);
+ if (f2fs_sb_has_extra_attr(sbi->sb)) {
+ 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->sb)) {
+ f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+ if (f2fs_has_inline_xattr(inode))
+ xattr_size = 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 |= FS_INDEX_FL;
+
+ if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
trace_f2fs_new_inode(inode, 0);
return inode;
@@ -85,6 +129,16 @@ 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)
@@ -136,6 +190,13 @@ 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 = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -148,8 +209,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
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)
@@ -163,6 +222,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
@@ -176,10 +237,22 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
if (f2fs_encrypted_inode(dir) &&
!fscrypt_has_permitted_context(dir, inode))
return -EPERM;
+ 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);
@@ -233,6 +306,10 @@ 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);
@@ -273,12 +350,15 @@ 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));
+ trace_f2fs_lookup_start(dir, dentry, flags);
+
if (f2fs_encrypted_inode(dir)) {
- int res = fscrypt_get_encryption_info(dir);
+ err = fscrypt_get_encryption_info(dir);
/*
* DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
@@ -288,18 +368,22 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
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 (err && err != -ENOKEY)
+ goto out;
}
- if (dentry->d_name.len > F2FS_NAME_LEN)
- return ERR_PTR(-ENAMETOOLONG);
+ if (dentry->d_name.len > F2FS_NAME_LEN) {
+ err = -ENAMETOOLONG;
+ goto out;
+ }
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);
@@ -307,32 +391,41 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
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);
}
@@ -346,6 +439,16 @@ 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))
@@ -397,6 +500,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
struct fscrypt_symlink_data *sd = NULL;
int err;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
if (f2fs_encrypted_inode(dir)) {
err = fscrypt_get_encryption_info(dir);
if (err)
@@ -412,6 +518,10 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
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);
@@ -423,8 +533,6 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
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)
@@ -487,6 +595,8 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
}
kfree(sd);
+
+ f2fs_balance_fs(sbi, true);
return err;
out:
handle_failed_inode(inode);
@@ -499,6 +609,13 @@ 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);
@@ -508,8 +625,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
- f2fs_balance_fs(sbi, true);
-
set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
@@ -524,6 +639,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out_fail:
@@ -547,6 +664,13 @@ 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 = dquot_initialize(dir);
+ if (err)
+ return err;
+
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -554,8 +678,6 @@ 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)
@@ -569,6 +691,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
@@ -582,6 +706,10 @@ 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);
@@ -595,8 +723,6 @@ 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);
if (err)
@@ -622,6 +748,8 @@ 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:
@@ -633,6 +761,9 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(dir))))
+ return -EIO;
+
if (f2fs_encrypted_inode(dir)) {
int err = fscrypt_get_encryption_info(dir);
if (err)
@@ -644,6 +775,9 @@ 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);
}
@@ -663,6 +797,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
bool is_old_inline = f2fs_has_inline_dentry(old_dir);
int err = -ENOENT;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
if ((f2fs_encrypted_inode(old_dir) &&
!fscrypt_has_encryption_key(old_dir)) ||
(f2fs_encrypted_inode(new_dir) &&
@@ -675,6 +812,25 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out;
}
+ 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;
+ }
+
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
@@ -720,13 +876,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
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);
@@ -778,13 +927,14 @@ 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);
@@ -849,6 +999,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
int old_nlink = 0, new_nlink = 0;
int err = -ENOENT;
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
if ((f2fs_encrypted_inode(old_dir) &&
!fscrypt_has_encryption_key(old_dir)) ||
(f2fs_encrypted_inode(new_dir) &&
@@ -861,6 +1014,22 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
!fscrypt_has_permitted_context(old_dir, new_inode)))
return -EPERM;
+ 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;
+
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
@@ -908,8 +1077,8 @@ 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;
}
@@ -917,18 +1086,6 @@ 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);
@@ -950,7 +1107,7 @@ 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);
@@ -965,21 +1122,13 @@ 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);
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
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);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 01177ec..fe1fc66 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,10 +19,11 @@
#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_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;
@@ -45,8 +46,8 @@ 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 +63,10 @@ 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 +74,10 @@ 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;
@@ -132,6 +138,44 @@ 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_NOFS | __GFP_ZERO);
+ else
+ new = kmem_cache_alloc(nat_entry_slab,
+ GFP_NOFS | __GFP_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);
+ list_add_tail(&ne->list, &nm_i->nat_entries);
+ 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);
@@ -148,7 +192,7 @@ 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,
@@ -157,9 +201,6 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
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 +211,27 @@ 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);
+
+ 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:
+ if (nat_get_blkaddr(ne) == NEW_ADDR)
+ list_del_init(&ne->list);
+ else
+ list_move_tail(&ne->list, &head->entry_list);
}
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;
-
- 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--;
- }
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ 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,
@@ -245,35 +288,29 @@ 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 +318,12 @@ 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 +335,9 @@ 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);
@@ -312,10 +353,6 @@ 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 */
@@ -367,6 +404,7 @@ 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;
@@ -392,21 +430,23 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
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 = get_meta_page(sbi, index);
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);
}
/*
@@ -535,7 +575,7 @@ static int get_node_path(struct inode *inode, long block,
level = 3;
goto got;
} else {
- BUG();
+ return -E2BIG;
}
got:
return level;
@@ -559,6 +599,8 @@ 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;
@@ -594,7 +636,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
}
dn->nid = nids[i];
- npage[i] = new_node_page(dn, noffset[i], NULL);
+ npage[i] = new_node_page(dn, noffset[i]);
if (IS_ERR(npage[i])) {
alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
@@ -635,7 +677,8 @@ 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:
@@ -659,15 +702,11 @@ static void truncate_node(struct dnode_of_data *dn)
struct node_info ni;
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);
/* Deallocate node address */
invalidate_blocks(sbi, ni.blk_addr);
- dec_valid_node_count(sbi, dn->inode);
+ 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) {
@@ -675,7 +714,7 @@ static void truncate_node(struct dnode_of_data *dn)
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);
@@ -861,6 +900,8 @@ 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);
if (IS_ERR(page)) {
@@ -941,7 +982,8 @@ 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 truncate_xattr_node(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t nid = F2FS_I(inode)->i_xattr_nid;
@@ -957,13 +999,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
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;
+ set_new_dnode(&dn, inode, NULL, npage, nid);
truncate_node(&dn);
return 0;
}
@@ -982,7 +1018,7 @@ int remove_inode_page(struct inode *inode)
if (err)
return err;
- err = truncate_xattr_node(inode, dn.inode_page);
+ err = truncate_xattr_node(inode);
if (err) {
f2fs_put_dnode(&dn);
return err;
@@ -995,7 +1031,7 @@ int remove_inode_page(struct inode *inode)
/* 0 is possible, after f2fs_new_inode() has failed */
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);
@@ -1010,14 +1046,13 @@ 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 new_node_page(&dn, 0);
}
-struct page *new_node_page(struct dnode_of_data *dn,
- unsigned int ofs, struct page *ipage)
+struct page *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;
@@ -1028,17 +1063,18 @@ 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;
- }
- 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;
+#ifdef CONFIG_F2FS_CHECK_FS
+ get_node_info(sbi, dn->nid, &new_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);
@@ -1134,11 +1170,12 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
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;
}
@@ -1152,15 +1189,27 @@ 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;
}
@@ -1189,7 +1238,8 @@ 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;
@@ -1204,6 +1254,7 @@ 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);
+ remove_dirty_inode(inode);
if (ret)
set_page_dirty(page);
page_out:
@@ -1212,37 +1263,6 @@ 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;
@@ -1303,16 +1323,135 @@ static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
return last_page;
}
+static int __write_node_page(struct page *page, bool atomic, bool *submitted,
+ struct writeback_control *wbc, bool do_balance,
+ enum iostat_type io_type)
+{
+ 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,
+ };
+
+ 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 (atomic && !test_opt(sbi, NOBARRIER))
+ fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
+
+ 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_write_cond(sbi, page->mapping->host, 0,
+ page->index, 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;
+}
+
+void move_node_page(struct page *node_page, int gc_type)
+{
+ if (gc_type == FG_GC) {
+ 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(F2FS_P_SB(node_page), PageWriteback(node_page));
+ if (!clear_page_dirty_for_io(node_page))
+ goto out_page;
+
+ if (__write_node_page(node_page, false, NULL,
+ &wbc, false, FS_GC_NODE_IO))
+ 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 int f2fs_write_node_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO);
+}
+
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic)
{
pgoff_t index, end;
+ pgoff_t last_idx = ULONG_MAX;
struct pagevec pvec;
int ret = 0;
struct page *last_page = NULL;
bool marked = false;
nid_t ino = inode->i_ino;
- int nwritten = 0;
if (atomic) {
last_page = last_fsync_dnode(sbi, ino);
@@ -1334,11 +1473,13 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
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))
@@ -1364,6 +1505,9 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
f2fs_wait_on_page_writeback(page, NODE, true);
BUG_ON(PageWriteback(page));
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
+
if (!atomic || page == last_page) {
set_fsync_mark(page, 1);
if (IS_INODE(page)) {
@@ -1381,13 +1525,16 @@ 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);
if (ret) {
unlock_page(page);
f2fs_put_page(last_page, 0);
break;
- } else {
- nwritten++;
+ } else if (submitted) {
+ last_idx = page->index;
}
if (page == last_page) {
@@ -1407,17 +1554,19 @@ 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);
set_page_dirty(last_page);
unlock_page(last_page);
goto retry;
}
-
- if (nwritten)
- f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
+out:
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE);
return ret ? -EIO: 0;
}
-int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type)
{
pgoff_t index, end;
struct pagevec pvec;
@@ -1441,6 +1590,7 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
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);
@@ -1494,9 +1644,11 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
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);
+ if (ret)
unlock_page(page);
- else
+ else if (submitted)
nwritten++;
if (--wbc->nr_to_write == 0)
@@ -1517,7 +1669,7 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
}
out:
if (nwritten)
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ f2fs_submit_merged_write(sbi, NODE);
return ret;
}
@@ -1560,72 +1712,6 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
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;
- }
-
- 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)
{
@@ -1633,6 +1719,9 @@ 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);
@@ -1645,7 +1734,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
blk_start_plug(&plug);
- sync_node_pages(sbi, wbc);
+ 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);
return 0;
@@ -1692,111 +1781,274 @@ 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);
- struct free_nid *i;
- struct nat_entry *ne;
- if (!available_free_memory(sbi, FREE_NIDS))
- return -1;
+ 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);
+ }
+}
+
+/* return if the nid is recognized as free */
+static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct free_nid *i, *e;
+ struct nat_entry *ne;
+ int err = -EINVAL;
+ bool ret = false;
/* 0 nid should not be used */
if (unlikely(nid == 0))
- return 0;
-
- if (build) {
- /* do not add allocated nids */
- ne = __lookup_nat_cache(nm_i, nid);
- if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
- nat_get_blkaddr(ne) != NULL_ADDR))
- 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)) {
- kmem_cache_free(free_nid_slab, i);
- return 0;
- }
+ if (radix_tree_preload(GFP_NOFS))
+ goto err;
- spin_lock(&nm_i->free_nid_list_lock);
- if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
- spin_unlock(&nm_i->free_nid_list_lock);
- radix_tree_preload_end();
- kmem_cache_free(free_nid_slab, i);
- return 0;
+ spin_lock(&nm_i->nid_list_lock);
+
+ if (build) {
+ /*
+ * Thread A Thread B
+ * - f2fs_create
+ * - f2fs_new_inode
+ * - alloc_nid
+ * - __insert_nid_to_list(PREALLOC_NID)
+ * - f2fs_balance_fs_bg
+ * - build_free_nids
+ * - __build_free_nids
+ * - scan_nat_page
+ * - add_free_nid
+ * - __lookup_nat_cache
+ * - f2fs_add_link
+ * - init_inode_metadata
+ * - new_inode_page
+ * - new_node_page
+ * - set_node_addr
+ * - 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) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
+ goto err_out;
+
+ e = __lookup_free_nid_list(nm_i, nid);
+ if (e) {
+ if (e->state == FREE_NID)
+ ret = true;
+ goto err_out;
+ }
}
- list_add_tail(&i->list, &nm_i->free_nid_list);
- nm_i->fcnt++;
- spin_unlock(&nm_i->free_nid_list_lock);
+ ret = true;
+ err = __insert_free_nid(sbi, i, FREE_NID);
+err_out:
+ spin_unlock(&nm_i->nid_list_lock);
radix_tree_preload_end();
- return 1;
+err:
+ if (err)
+ kmem_cache_free(free_nid_slab, i);
+ 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 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]--;
+ }
+}
+
static void 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;
+ if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+ return;
+
+ __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++) {
+ bool freed = false;
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 == NULL_ADDR) {
- if (add_free_nid(sbi, start_nid, true) < 0)
- break;
- }
+ if (blk_addr == NULL_ADDR)
+ freed = add_free_nid(sbi, start_nid, true);
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ update_free_nid_bitmap(sbi, start_nid, freed, true);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
}
}
-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;
+
+ 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);
+ 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);
+
+ 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 void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
int i = 0;
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)
+ if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
return;
+ if (!sync && !available_free_memory(sbi, FREE_NIDS))
+ return;
+
+ 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;
+ }
+
/* readahead nat pages to be scanned */
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
@@ -1821,24 +2073,21 @@ 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),
nm_i->ra_nid_pages, META_NAT, false);
}
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+{
+ mutex_lock(&NM_I(sbi)->build_lock);
+ __build_free_nids(sbi, sync, mount);
+ mutex_unlock(&NM_I(sbi)->build_lock);
+}
+
/*
* If this function returns success, caller can obtain a new nid
* from second parameter of this function.
@@ -1850,34 +2099,37 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
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))
- return false;
+ spin_lock(&nm_i->nid_list_lock);
- spin_lock(&nm_i->free_nid_list_lock);
+ if (unlikely(nm_i->available_nids == 0)) {
+ spin_unlock(&nm_i->nid_list_lock);
+ return false;
+ }
/* We should not use stale free nids created by build_free_nids */
- if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
+ if (nm_i->nid_cnt[FREE_NID] && !on_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);
+ build_free_nids(sbi, true, false);
goto retry;
}
@@ -1889,11 +2141,11 @@ void 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);
}
@@ -1910,17 +2162,22 @@ 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);
+ f2fs_bug_on(sbi, !i);
+
if (!available_free_memory(sbi, FREE_NIDS)) {
- __del_from_free_nid_list(nm_i, i);
+ __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);
@@ -1932,24 +2189,23 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
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;
@@ -1971,8 +2227,8 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
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);
@@ -1982,38 +2238,47 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
f2fs_put_page(ipage, 1);
}
-void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
+int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
{
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;
- /* 1: invalidate the previous xattr nid */
if (!prev_xnid)
goto recover_xnid;
- /* Deallocate node address */
+ /* 1: invalidate the previous xattr nid */
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);
+ 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 (!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 = new_node_page(&dn, XATTR_NODE_OFFSET);
+ if (IS_ERR(xpage)) {
+ 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);
+ alloc_nid_done(sbi, new_xnid);
+ 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)
@@ -2035,7 +2300,7 @@ 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);
@@ -2049,12 +2314,25 @@ 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->sb) &&
+ 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->sb) &&
+ F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+ i_projid))
+ dst->i_projid = src->i_projid;
+ }
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);
@@ -2069,7 +2347,6 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
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 */
@@ -2078,7 +2355,7 @@ 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);
@@ -2117,9 +2394,22 @@ 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);
@@ -2144,8 +2434,41 @@ static void __adjust_nat_entry_set(struct nat_entry_set *nes,
list_add_tail(&nes->set_list, head);
}
+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 void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
- struct nat_entry_set *set)
+ 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;
@@ -2160,7 +2483,8 @@ 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) {
@@ -2177,8 +2501,7 @@ 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,
@@ -2191,26 +2514,38 @@ 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)
+ __clear_nat_cache_dirty(NM_I(sbi), set, ne);
+ if (nat_get_blkaddr(ne) == NULL_ADDR) {
add_free_nid(sbi, nid, false);
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ NM_I(sbi)->available_nids++;
+ update_free_nid_bitmap(sbi, nid, true, false);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ } 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);
+ }
}
/*
* This function is called during the checkpointing process.
*/
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+void 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);
@@ -2231,7 +2566,8 @@ 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,
@@ -2245,11 +2581,86 @@ 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);
+ __flush_nat_entry_set(sbi, set, cpc);
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);
+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_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 +
+ F2FS_BLKSIZE - 1);
+ nm_i->nat_bits = kzalloc(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 = get_meta_page(sbi, nat_bits_addr++);
+
+ 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)
@@ -2257,19 +2668,21 @@ 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 -
+ 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;
@@ -2282,7 +2695,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&nm_i->nat_entries);
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);
@@ -2295,6 +2708,39 @@ 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;
+}
+
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ nm_i->free_nid_bitmap = kvzalloc(nm_i->nat_blocks *
+ NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL);
+ if (!nm_i->free_nid_bitmap)
+ return -ENOMEM;
+
+ nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8,
+ GFP_KERNEL);
+ if (!nm_i->nat_block_bitmap)
+ return -ENOMEM;
+
+ nm_i->free_nid_count = kvzalloc(nm_i->nat_blocks *
+ sizeof(unsigned short), GFP_KERNEL);
+ if (!nm_i->free_nid_count)
+ return -ENOMEM;
return 0;
}
@@ -2310,7 +2756,14 @@ int build_node_manager(struct f2fs_sb_info *sbi)
if (err)
return err;
- build_free_nids(sbi);
+ err = init_free_nid_cache(sbi);
+ if (err)
+ return err;
+
+ /* load free nid status from nat_bits table */
+ load_free_nid_bitmap(sbi);
+
+ build_free_nids(sbi, true, true);
return 0;
}
@@ -2327,17 +2780,17 @@ 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);
@@ -2367,7 +2820,15 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
}
up_write(&nm_i->nat_tree_lock);
+ kvfree(nm_i->nat_block_bitmap);
+ kvfree(nm_i->free_nid_bitmap);
+ kvfree(nm_i->free_nid_count);
+
kfree(nm_i->nat_bitmap);
+ kfree(nm_i->nat_bits);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(nm_i->nat_bitmap_mir);
+#endif
sbi->nm_info = NULL;
kfree(nm_i);
}
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 868bec6..0ee3e5f 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -9,10 +9,10 @@
* 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
@@ -62,16 +62,16 @@ 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)
@@ -140,6 +140,7 @@ enum mem_type {
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 +151,10 @@ 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 +162,14 @@ 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 +178,12 @@ 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 +192,16 @@ 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 +216,7 @@ 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 +225,9 @@ 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 +291,11 @@ 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 +303,12 @@ 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);
+ 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 +337,7 @@ 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)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 98c1a63..92c57ac 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -69,20 +69,34 @@ 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)
@@ -107,7 +121,8 @@ 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);
@@ -140,6 +155,13 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
err = -EEXIST;
goto out_unmap_put;
}
+
+ err = dquot_initialize(einode);
+ if (err) {
+ iput(einode);
+ goto out_unmap_put;
+ }
+
err = acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
@@ -180,13 +202,15 @@ static void recover_inode(struct inode *inode, struct page *page)
inode->i_mode = le16_to_cpu(raw->i_mode);
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;
+
if (file_enc_name(inode))
name = "<encrypted>";
else
@@ -196,33 +220,8 @@ static void recover_inode(struct inode *inode, struct page *page)
ino_of_node(page), name);
}
-static bool is_same_inode(struct inode *inode, struct page *ipage)
-{
- struct f2fs_inode *ri = F2FS_INODE(ipage);
- struct timespec disk;
-
- if (!IS_INODE(ipage))
- return true;
-
- disk.tv_sec = le64_to_cpu(ri->i_ctime);
- disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
- if (timespec_compare(&inode->i_ctime, &disk) > 0)
- return false;
-
- disk.tv_sec = le64_to_cpu(ri->i_atime);
- disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
- if (timespec_compare(&inode->i_atime, &disk) > 0)
- return false;
-
- disk.tv_sec = le64_to_cpu(ri->i_mtime);
- disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
- if (timespec_compare(&inode->i_mtime, &disk) > 0)
- return false;
-
- return true;
-}
-
-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;
@@ -248,21 +247,23 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
- if (entry) {
- if (!is_same_inode(entry->inode, page))
- goto next;
- } else {
- if (IS_INODE(page) && is_dent_dnode(page)) {
+ if (!entry) {
+ bool quota_inode = false;
+
+ if (!check_only &&
+ IS_INODE(page) && is_dent_dnode(page)) {
err = 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) {
@@ -353,10 +354,18 @@ 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;
}
@@ -386,7 +395,8 @@ 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)
+ if (datablock_addr(tdn.inode, tdn.node_page,
+ tdn.ofs_in_node) == blkaddr)
truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
@@ -405,11 +415,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (IS_INODE(page)) {
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 = recover_xattr_data(inode, page, blkaddr);
+ if (!err)
+ recovered++;
goto out;
}
@@ -441,8 +449,8 @@ 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)
@@ -454,8 +462,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
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
@@ -507,8 +517,10 @@ 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;
}
@@ -576,18 +588,34 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
int 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 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, "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 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(&dir_list);
@@ -595,16 +623,14 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
/* 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;
@@ -613,7 +639,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
-out:
+skip:
destroy_fsync_dnodes(&inode_list);
/* truncate meta pages to be used by the recovery */
@@ -639,5 +665,13 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
}
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 e10f616..0abe694 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -16,17 +16,20 @@
#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;
@@ -166,8 +169,24 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
return result - size + __reverse_ffz(tmp);
}
+bool 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_thread && sbi->gc_thread->gc_urgent)
+ return true;
+
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
+ SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
+}
+
void 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;
@@ -186,6 +205,10 @@ 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);
@@ -212,9 +235,15 @@ static int __revoke_inmem_pages(struct inode *inode,
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 = 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;
}
@@ -238,15 +267,76 @@ static int __revoke_inmem_pages(struct inode *inode,
return err;
}
+void drop_inmem_pages_all(struct f2fs_sb_info *sbi)
+{
+ 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]);
+
+ if (inode) {
+ drop_inmem_pages(inode);
+ iput(inode);
+ }
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto next;
+}
+
void drop_inmem_pages(struct inode *inode)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
- clear_inode_flag(inode, FI_ATOMIC_FILE);
-
mutex_lock(&fi->inmem_lock);
__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+ 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);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ stat_dec_atomic_write(inode);
+}
+
+void 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, !cur || 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);
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ f2fs_put_page(page, 0);
+
+ trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
}
static int __commit_inmem_pages(struct inode *inode,
@@ -257,12 +347,13 @@ static int __commit_inmem_pages(struct inode *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,
};
- bool submit_bio = false;
+ pgoff_t last_idx = ULONG_MAX;
int err = 0;
list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
@@ -274,28 +365,35 @@ static int __commit_inmem_pages(struct inode *inode,
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);
-
+ remove_dirty_inode(inode);
+ }
+retry:
fio.page = page;
+ fio.old_blkaddr = NULL_ADDR;
+ fio.encrypted_page = NULL;
+ fio.need_lock = LOCK_DONE;
err = 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;
+ last_idx = page->index;
}
unlock_page(page);
list_move_tail(&cur->list, revoke_list);
}
- if (submit_bio)
- f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
if (!err)
__revoke_inmem_pages(inode, revoke_list, false, false);
@@ -314,6 +412,8 @@ int commit_inmem_pages(struct inode *inode)
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
+ set_inode_flag(inode, FI_ATOMIC_COMMIT);
+
mutex_lock(&fi->inmem_lock);
err = __commit_inmem_pages(inode, &revoke_list);
if (err) {
@@ -333,8 +433,14 @@ int commit_inmem_pages(struct inode *inode)
/* drop all uncommitted pages */
__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
}
+ 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);
return err;
}
@@ -346,15 +452,14 @@ 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);
/*
@@ -363,7 +468,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
*/
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);
}
}
@@ -380,14 +485,17 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
if (!available_free_memory(sbi, FREE_NIDS))
try_to_free_nids(sbi, MAX_FREE_NIDS);
else
- build_free_nids(sbi);
+ build_free_nids(sbi, false, false);
+
+ if (!is_idle(sbi) && !excess_dirty_nats(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) ||
excess_prefree_segs(sbi) ||
excess_dirty_nats(sbi) ||
- (is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+ f2fs_time_over(sbi, CP_TIME)) {
if (test_opt(sbi, DATA_FLUSH)) {
struct blk_plug plug;
@@ -400,77 +508,138 @@ 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 = f2fs_bio_alloc(sbi, 0, true);
+ int ret;
+
+ 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 (!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)) {
+ ret = submit_flush_wait(sbi, ino);
+ atomic_inc(&fcc->issued_flush);
return ret;
}
+ if (atomic_inc_return(&fcc->issing_flush) == 1 || sbi->s_ndevs > 1) {
+ ret = submit_flush_wait(sbi, ino);
+ atomic_dec(&fcc->issing_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->issing_flush);
+ } else {
+ struct llist_node *list;
+
+ list = llist_del_all(&fcc->issue_list);
+ if (!list) {
+ wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->issing_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->issing_flush);
+ continue;
+ }
+ tmp->ret = ret;
+ complete(&tmp->wait);
+ }
+ }
+ }
return cmd.ret;
}
@@ -481,33 +650,73 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
struct flush_cmd_control *fcc;
int err = 0;
+ if (SM_I(sbi)->fcc_info) {
+ fcc = SM_I(sbi)->fcc_info;
+ if (fcc->f2fs_issue_flush)
+ return err;
+ goto init_thread;
+ }
+
fcc = kzalloc(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->issing_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;
+ SM_I(sbi)->fcc_info = NULL;
return err;
}
return err;
}
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void 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) {
+ kfree(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,
@@ -550,8 +759,8 @@ 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);
}
}
@@ -571,7 +780,7 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
mutex_lock(&dirty_i->seglist_lock);
- valid_blocks = get_valid_blocks(sbi, segno, 0);
+ valid_blocks = get_valid_blocks(sbi, segno, false);
if (valid_blocks == 0) {
__locate_dirty_segment(sbi, segno, PRE);
@@ -586,120 +795,731 @@ 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)
+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 list_head *wait_list = &(SM_I(sbi)->wait_list);
- struct bio_entry *be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc;
- INIT_LIST_HEAD(&be->list);
- be->bio = bio;
- init_completion(&be->event);
- list_add_tail(&be->list, wait_list);
+ f2fs_bug_on(sbi, !len);
- return be;
+ 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->error = 0;
+ init_completion(&dc->wait);
+ list_add_tail(&dc->list, pend_list);
+ atomic_inc(&dcc->discard_cmd_cnt);
+ dcc->undiscard_blks += len;
+
+ return dc;
}
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *sbi)
+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 list_head *wait_list = &(SM_I(sbi)->wait_list);
- struct bio_entry *be, *tmp;
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *dc;
- list_for_each_entry_safe(be, tmp, wait_list, list) {
- struct bio *bio = be->bio;
- int err;
+ dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
- wait_for_completion_io(&be->event);
- err = be->error;
- if (err == -EOPNOTSUPP)
- err = 0;
+ rb_link_node(&dc->rb_node, parent, p);
+ rb_insert_color(&dc->rb_node, &dcc->root);
- if (err)
- f2fs_msg(sbi->sb, KERN_INFO,
- "Issue discard failed, ret: %d", err);
+ return dc;
+}
- bio_put(bio);
- list_del(&be->list);
- kmem_cache_free(bio_entry_slab, be);
+static void __detach_discard_cmd(struct discard_cmd_control *dcc,
+ struct discard_cmd *dc)
+{
+ if (dc->state == D_DONE)
+ atomic_dec(&dcc->issing_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;
+
+ trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
+
+ f2fs_bug_on(sbi, dc->ref);
+
+ if (dc->error == -EOPNOTSUPP)
+ dc->error = 0;
+
+ if (dc->error)
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Issue discard(%u, %u, %u) failed, ret: %d",
+ 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;
+
+ dc->error = bio->bi_error;
+ dc->state = D_DONE;
+ complete_all(&dc->wait);
+ bio_put(bio);
+}
+
+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);
}
-}
-
-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);
+#endif
}
/* 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 void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy,
+ struct discard_cmd *dc)
{
- struct block_device *bdev = sbi->sb->s_bdev;
+ 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 bio *bio = NULL;
- int err;
+ int flag = dpolicy->sync ? REQ_SYNC : 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;
- bio->bi_private = be;
- bio->bi_end_io = f2fs_submit_bio_wait_endio;
- bio->bi_opf |= REQ_SYNC;
- submit_bio(bio);
+ trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
+
+ dc->error = __blkdev_issue_discard(dc->bdev,
+ SECTOR_FROM_BLOCK(dc->start),
+ SECTOR_FROM_BLOCK(dc->len),
+ GFP_NOFS, 0, &bio);
+ if (!dc->error) {
+ /* should keep before submission to avoid D_DONE right away */
+ dc->state = D_SUBMIT;
+ atomic_inc(&dcc->issued_discard);
+ atomic_inc(&dcc->issing_discard);
+ if (bio) {
+ bio->bi_private = dc;
+ bio->bi_end_io = f2fs_submit_discard_endio;
+ bio->bi_opf |= flag;
+ submit_bio(bio);
+ list_move_tail(&dc->list, wait_list);
+ __check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
+
+ f2fs_update_iostat(sbi, FS_DISCARD, 1);
+ }
+ } else {
+ __remove_discard_cmd(sbi, dc);
+ }
+}
+
+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;
}
- return err;
+ p = __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;
+ block_t end = lstart + len;
+
+ mutex_lock(&dcc->cmd_lock);
+
+ dc = (struct discard_cmd *)__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)) {
+ 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)) {
+ 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);
+ }
+
+ mutex_unlock(&dcc->cmd_lock);
+}
+
+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;
+ }
+ __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
+ return 0;
+}
+
+static void __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;
+
+next:
+ issued = 0;
+
+ mutex_lock(&dcc->cmd_lock);
+ f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+
+ dc = (struct discard_cmd *)__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;
+
+ if (dc->len < dpolicy->granularity)
+ goto skip;
+
+ if (dc->state != D_PREP) {
+ list_move_tail(&dc->list, &dcc->fstrim_list);
+ goto skip;
+ }
+
+ __submit_discard_cmd(sbi, dpolicy, dc);
+
+ if (++issued >= dpolicy->max_requests) {
+ start = dc->lstart + dc->len;
+
+ blk_finish_plug(&plug);
+ mutex_unlock(&dcc->cmd_lock);
+
+ schedule();
+
+ goto next;
+ }
+skip:
+ node = rb_next(&dc->rb_node);
+ 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);
+}
+
+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, iter = 0, issued = 0;
+ bool io_interrupted = false;
+
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ if (i + 1 < dpolicy->granularity)
+ break;
+ pend_list = &dcc->pend_list[i];
+
+ mutex_lock(&dcc->cmd_lock);
+ f2fs_bug_on(sbi, !__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)) {
+ io_interrupted = true;
+ goto skip;
+ }
+
+ __submit_discard_cmd(sbi, dpolicy, dc);
+ issued++;
+skip:
+ if (++iter >= dpolicy->max_requests)
+ break;
+ }
+ blk_finish_plug(&plug);
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (iter >= dpolicy->max_requests)
+ 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;
+}
+
+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 void __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy)
+{
+ __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
+}
+
+/* This should be covered by global mutex, &sit_i->sentry_lock */
+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 *)__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 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_wait_discard_bios(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_policy dpolicy;
+ bool dropped;
+
+ init_discard_policy(&dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity);
+ __issue_discard_cmd(sbi, &dpolicy);
+ dropped = __drop_discard_cmd(sbi);
+ __wait_all_discard_cmd(sbi, &dpolicy);
+
+ 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(&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 (try_to_freeze())
+ continue;
+ if (kthread_should_stop())
+ return 0;
+
+ if (dcc->discard_wake) {
+ dcc->discard_wake = 0;
+ if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
+ init_discard_policy(&dpolicy,
+ DPOLICY_FORCE, 1);
+ }
+
+ sb_start_intwrite(sbi->sb);
+
+ issued = __issue_discard_cmd(sbi, &dpolicy);
+ if (issued) {
+ __wait_all_discard_cmd(sbi, &dpolicy);
+ wait_ms = dpolicy.min_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_mounted_blkzoned(sbi->sb) &&
+ 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;
@@ -709,16 +1529,19 @@ 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;
+ return false;
if (!force) {
if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
- SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
- return;
+ 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) */
@@ -726,7 +1549,8 @@ 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;
@@ -736,13 +1560,27 @@ 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)
{
- struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
/* drop caches */
@@ -768,16 +1606,14 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
void 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);
mutex_lock(&dirty_i->seglist_lock);
@@ -794,19 +1630,23 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
dirty_i->nr_dirty[PRE] -= end - start;
- if (force || !test_opt(sbi, DISCARD))
+ if (!test_opt(sbi, DISCARD))
continue;
+ if (force && start >= cpc->trim_start &&
+ (end - 1) <= cpc->trim_end)
+ continue;
+
if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
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);
@@ -820,17 +1660,128 @@ 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_mounted_blkzoned(sbi->sb) ||
+ (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:
+ cur_pos = next_pos;
+ is_valid = !is_valid;
+
+ if (cur_pos < sbi->blocks_per_seg)
+ goto find_next;
+
list_del(&entry->list);
- SM_I(sbi)->nr_discards -= entry->len;
+ dcc->nr_discards -= total_len;
kmem_cache_free(discard_entry_slab, entry);
}
- blk_finish_plug(&plug);
+ wake_up_discard_thread(sbi, false);
+}
+
+void init_discard_policy(struct discard_policy *dpolicy,
+ int discard_type, unsigned int granularity)
+{
+ /* common policy */
+ dpolicy->type = discard_type;
+ dpolicy->sync = true;
+ dpolicy->granularity = granularity;
+
+ if (discard_type == DPOLICY_BG) {
+ dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+ dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+ dpolicy->io_aware = true;
+ } else if (discard_type == DPOLICY_FORCE) {
+ dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+ dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+ dpolicy->io_aware = true;
+ } else if (discard_type == DPOLICY_FSTRIM) {
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+ dpolicy->io_aware = false;
+ } else if (discard_type == DPOLICY_UMOUNT) {
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+ dpolicy->io_aware = 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 = kzalloc(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->issing_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->root = RB_ROOT;
+
+ 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);
+ kfree(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;
+
+ stop_discard_thread(sbi);
+
+ kfree(dcc);
+ SM_I(sbi)->dcc_info = NULL;
}
static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
@@ -859,6 +1810,10 @@ 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);
@@ -875,14 +1830,54 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
/* 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);
+ }
+#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_discard_en(sbi) &&
!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
+
+ /* don't overwrite by SSR to keep node chain */
+ if (se->type == CURSEG_WARM_NODE) {
+ 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);
+ }
+#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;
+ }
+
if (f2fs_discard_en(sbi) &&
f2fs_test_and_clear_bit(offset, se->discard_map))
sbi->discard_blks++;
@@ -899,16 +1894,6 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
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)
{
unsigned int segno = GET_SEGNO(sbi, addr);
@@ -919,14 +1904,14 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
return;
/* 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)
@@ -939,7 +1924,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
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);
@@ -948,7 +1933,7 @@ 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;
}
@@ -1006,12 +1991,8 @@ struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
void 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);
- 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);
}
@@ -1068,8 +2049,8 @@ 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;
@@ -1079,8 +2060,8 @@ 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:
@@ -1110,9 +2091,8 @@ 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)
@@ -1156,7 +2136,7 @@ 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;
@@ -1169,6 +2149,20 @@ 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 (sbi->segs_per_sec != 1)
+ return CURSEG_I(sbi, type)->segno;
+
+ if (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];
+ return CURSEG_I(sbi, type)->segno;
+}
+
/*
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
@@ -1187,6 +2181,7 @@ 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);
@@ -1229,7 +2224,7 @@ 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);
@@ -1250,28 +2245,53 @@ 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 = 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);
}
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);
+ /* 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;
+ }
+ }
return 0;
}
@@ -1286,55 +2306,73 @@ 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))
new_curseg(sbi, type, false);
else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
- change_curseg(sbi, type, true);
+ 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)
-{
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- 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)
{
+ struct curseg_info *curseg;
+ unsigned int old_segno;
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 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;
+}
+
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;
+ unsigned int start_segno, end_segno, cur_segno;
+ block_t start_block, end_block;
struct cp_control cpc;
+ struct discard_policy dpolicy;
+ unsigned long long trimmed = 0;
int err = 0;
if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
return -EINVAL;
- cpc.trimmed = 0;
if (end <= MAIN_BLKADDR(sbi))
goto out;
@@ -1348,12 +2386,14 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
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);
+
cpc.reason = CP_DISCARD;
cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
/* do checkpoint to issue discard commands safely */
- for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
- cpc.trim_start = start_segno;
+ for (cur_segno = start_segno; cur_segno <= end_segno;
+ cur_segno = cpc.trim_end + 1) {
+ cpc.trim_start = cur_segno;
if (sbi->discard_blks == 0)
break;
@@ -1361,7 +2401,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
cpc.trim_end = end_segno;
else
cpc.trim_end = min_t(unsigned int,
- rounddown(start_segno +
+ rounddown(cur_segno +
BATCHED_TRIM_SEGMENTS(sbi),
sbi->segs_per_sec) - 1, end_segno);
@@ -1373,8 +2413,16 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
schedule();
}
+
+ start_block = START_BLOCK(sbi, start_segno);
+ end_block = START_BLOCK(sbi, min(cur_segno, end_segno) + 1);
+
+ init_discard_policy(&dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
+ __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);
+ range->len = F2FS_BLK_TO_BYTES(trimmed);
return err;
}
@@ -1386,87 +2434,108 @@ 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)
+#if 0
+int 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;
+ }
+}
+#endif
+
+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 (is_inode_flag_set(inode, FI_HOT_DATA))
+ return CURSEG_HOT_DATA;
+ /* 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 (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,
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
@@ -1478,57 +2547,111 @@ 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;
+ 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 */
+ 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);
+ int err;
- if (fio->type == NODE || fio->type == DATA)
- mutex_lock(&fio->sbi->wio_mutex[fio->type]);
-
+reallocate:
allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type);
+ &fio->new_blkaddr, sum, type, fio, true);
/* writeout dirty page into bdev */
- f2fs_submit_page_mbio(fio);
-
- if (fio->type == NODE || fio->type == DATA)
- mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
+ err = f2fs_submit_page_write(fio);
+ if (err == -EAGAIN) {
+ fio->old_blkaddr = fio->new_blkaddr;
+ goto reallocate;
+ } else if (!err) {
+ update_device_state(fio);
+ }
}
-void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
+void 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,
.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);
+ f2fs_submit_page_write(&fio);
+
+ f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
}
void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -1537,6 +2660,8 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
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)
@@ -1550,13 +2675,36 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.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 rewrite_data_page(struct f2fs_io_info *fio)
{
+ int err;
+
fio->new_blkaddr = fio->old_blkaddr;
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;
+}
+
+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_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -1574,6 +2722,8 @@ 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)) {
@@ -1583,14 +2733,19 @@ 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;
+ }
}
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;
@@ -1598,7 +2753,7 @@ 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);
@@ -1617,13 +2772,14 @@ 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,
@@ -1647,7 +2803,8 @@ void f2fs_wait_on_page_writeback(struct page *page,
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+ f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+ 0, page->index, type);
if (ordered)
wait_on_page_writeback(page);
else
@@ -1655,8 +2812,7 @@ void f2fs_wait_on_page_writeback(struct page *page,
}
}
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct page *cpage;
@@ -2077,7 +3233,7 @@ 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;
@@ -2127,9 +3283,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
se = get_seg_entry(sbi, segno);
/* 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) {
@@ -2163,11 +3319,15 @@ 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);
}
@@ -2175,10 +3335,9 @@ 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 */
@@ -2188,13 +3347,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+ sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) *
sizeof(struct seg_entry), 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 = kvzalloc(bitmap_size, GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
@@ -2207,6 +3366,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
!sit_i->sentries[start].ckpt_valid_map)
return -ENOMEM;
+#ifdef CONFIG_F2FS_CHECK_FS
+ sit_i->sentries[start].cur_valid_map_mir
+ = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->sentries[start].cur_valid_map_mir)
+ return -ENOMEM;
+#endif
+
if (f2fs_discard_en(sbi)) {
sit_i->sentries[start].discard_map
= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
@@ -2220,7 +3386,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
return -ENOMEM;
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
+ sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) *
sizeof(struct sec_entry), GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
@@ -2233,23 +3399,28 @@ 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;
}
@@ -2266,12 +3437,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
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 = kvmalloc(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 = kvmalloc(sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -2324,10 +3495,10 @@ static void 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;
do {
- readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
+ readed = 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;
@@ -2347,10 +3518,17 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
/* 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)
@@ -2374,10 +3552,15 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
seg_info_from_raw_sit(se, &sit);
if (f2fs_discard_en(sbi)) {
- memcpy(se->discard_map, se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks += old_valid_blocks -
- 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 += old_valid_blocks -
+ se->valid_blocks;
+ }
}
if (sbi->segs_per_sec > 1)
@@ -2396,6 +3579,9 @@ 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 */
@@ -2418,7 +3604,7 @@ 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) {
@@ -2436,7 +3622,7 @@ 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 = kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
return 0;
@@ -2458,7 +3644,7 @@ 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] = kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->dirty_segmap[i])
return -ENOMEM;
}
@@ -2475,7 +3661,7 @@ 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;
@@ -2492,7 +3678,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
sit_i->min_mtime = mtime;
}
sit_i->max_mtime = get_mtime(sbi);
- mutex_unlock(&sit_i->sentry_lock);
+ up_write(&sit_i->sentry_lock);
}
int build_segment_manager(struct f2fs_sb_info *sbi)
@@ -2524,22 +3710,25 @@ 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->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
+ sm_info->min_ssr_sections = reserved_sections(sbi);
sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
INIT_LIST_HEAD(&sm_info->sit_entry_set);
- if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+ init_rwsem(&sm_info->curseg_lock);
+
+ if (!f2fs_readonly(sbi->sb)) {
err = 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;
@@ -2633,6 +3822,9 @@ 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);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(sit_i->sentries[start].cur_valid_map_mir);
+#endif
kfree(sit_i->sentries[start].ckpt_valid_map);
kfree(sit_i->sentries[start].discard_map);
}
@@ -2645,6 +3837,9 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
SM_I(sbi)->sit_info = NULL;
kfree(sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(sit_i->sit_bitmap_mir);
+#endif
kfree(sit_i);
}
@@ -2654,7 +3849,8 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
if (!sm_info)
return;
- destroy_flush_cmd_control(sbi);
+ destroy_flush_cmd_control(sbi, true);
+ destroy_discard_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
destroy_free_segmap(sbi);
@@ -2670,15 +3866,15 @@ int __init create_segment_manager_caches(void)
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));
@@ -2688,8 +3884,8 @@ 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:
@@ -2699,7 +3895,7 @@ int __init create_segment_manager_caches(void)
void 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 b164f83..d1d394c 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -18,79 +18,91 @@
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */
-/* 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 F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
-#define IS_DATASEG(t) (t <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t) (t >= CURSEG_HOT_NODE)
+/* 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 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)->main_blkaddr)
#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_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)->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) \
- (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \
+ ((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_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) \
@@ -101,9 +113,7 @@
#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.
@@ -132,7 +142,10 @@ enum {
*/
enum {
GC_CB = 0,
- GC_GREEDY
+ GC_GREEDY,
+ ALLOC_NEXT,
+ FLUSH_DEVICE,
+ MAX_GC_POLICY,
};
/*
@@ -164,6 +177,9 @@ 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.
@@ -186,9 +202,12 @@ 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)
struct inmem_pages {
struct list_head list;
@@ -203,13 +222,16 @@ 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 */
@@ -218,6 +240,8 @@ 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 {
@@ -294,17 +318,17 @@ 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 && sbi->segs_per_sec > 1)
return get_sec_entry(sbi, segno)->valid_blocks;
else
return get_seg_entry(sbi, segno)->valid_blocks;
@@ -317,6 +341,9 @@ 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);
}
@@ -346,8 +373,8 @@ 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);
@@ -367,7 +394,8 @@ 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))
@@ -378,8 +406,8 @@ 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);
@@ -400,7 +428,8 @@ 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--;
@@ -414,6 +443,12 @@ 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);
}
@@ -457,26 +492,36 @@ 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,
@@ -484,14 +529,17 @@ 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 bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -521,6 +569,7 @@ 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
enum {
F2FS_IPU_FORCE,
@@ -528,20 +577,22 @@ enum {
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
F2FS_IPU_FSYNC,
+ F2FS_IPU_ASYNC,
};
-static inline bool need_inplace_update(struct inode *inode)
+static inline bool need_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;
- /* 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 this is cold file, we should overwrite to avoid fragmentation */
+ if (file_is_cold(inode))
+ return true;
+
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
@@ -553,6 +604,15 @@ static inline bool need_inplace_update(struct inode *inode)
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))
@@ -633,6 +693,12 @@ 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;
@@ -658,13 +724,17 @@ 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)
{
struct sit_info *sit_i = SIT_I(sbi);
- return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
- sit_i->mounted_time;
+ time64_t now = ktime_get_real_seconds();
+
+ return sit_i->elapsed_time + now - sit_i->mounted_time;
}
static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
@@ -691,7 +761,7 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int 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) >=
+ if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >
sbi->fggc_threshold)
return true;
return false;
@@ -704,19 +774,12 @@ 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)
{
@@ -728,7 +791,7 @@ 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;
}
@@ -745,12 +808,36 @@ 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)
+ 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 46c9154..0b5664a 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -21,14 +21,16 @@ 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)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index eb20b87..8f364c5 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -22,8 +22,10 @@
#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"
@@ -35,20 +37,21 @@
#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] = {
[FAULT_KMALLOC] = "kmalloc",
[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_TRUNCATE] = "truncate fail",
[FAULT_IO] = "IO error",
[FAULT_CHECKPOINT] = "checkpoint error",
};
@@ -82,6 +85,7 @@ enum {
Opt_discard,
Opt_nodiscard,
Opt_noheap,
+ Opt_heap,
Opt_user_xattr,
Opt_nouser_xattr,
Opt_acl,
@@ -89,6 +93,8 @@ 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,
@@ -101,9 +107,24 @@ enum {
Opt_noinline_data,
Opt_data_flush,
Opt_mode,
+ Opt_io_size_bits,
Opt_fault_injection,
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_err,
};
@@ -114,6 +135,7 @@ 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 +143,8 @@ 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"},
@@ -133,210 +157,27 @@ static match_table_t f2fs_tokens = {
{Opt_noinline_data, "noinline_data"},
{Opt_data_flush, "data_flush"},
{Opt_mode, "mode=%s"},
+ {Opt_io_size_bits, "io_bits=%u"},
{Opt_fault_injection, "fault_injection=%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_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;
@@ -345,7 +186,7 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+ printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
va_end(args);
}
@@ -356,6 +197,122 @@ 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) && !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(sb)) {
+ 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 -EINVAL;
+ }
+ if (sbi->s_qf_names[qtype]) {
+ if (strcmp(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;
+ }
+ sbi->s_qf_names[qtype] = qname;
+ set_opt(sbi, QUOTA);
+ return 0;
+errout:
+ kfree(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) && sbi->s_qf_names[qtype]) {
+ f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+ " when quota turned on");
+ return -EINVAL;
+ }
+ kfree(sbi->s_qf_names[qtype]);
+ 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->sb)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. "
+ "Cannot enable project quota enforcement.");
+ return -1;
+ }
+ if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA] ||
+ sbi->s_qf_names[PRJQUOTA]) {
+ if (test_opt(sbi, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
+ clear_opt(sbi, USRQUOTA);
+
+ if (test_opt(sbi, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
+ clear_opt(sbi, GRPQUOTA);
+
+ if (test_opt(sbi, PRJQUOTA) && 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 (!sbi->s_jquota_fmt) {
+ f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format "
+ "not specified");
+ return -1;
+ }
+ }
+
+ if (f2fs_sb_has_quota_ino(sbi->sb) && sbi->s_jquota_fmt) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "QUOTA feature is enabled, so ignore jquota_fmt");
+ sbi->s_jquota_fmt = 0;
+ }
+ if (f2fs_sb_has_quota_ino(sbi->sb) && sb_rdonly(sbi->sb)) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Filesystem with quota feature cannot be mounted RDWR "
+ "without CONFIG_QUOTA");
+ return -1;
+ }
+ return 0;
+}
+#endif
+
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -363,6 +320,9 @@ static int parse_options(struct super_block *sb, char *options)
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
+#ifdef CONFIG_QUOTA
+ int ret;
+#endif
if (!options)
return 0;
@@ -412,17 +372,26 @@ static int parse_options(struct super_block *sb, char *options)
q = bdev_get_queue(sb->s_bdev);
if (blk_queue_discard(q)) {
set_opt(sbi, DISCARD);
- } else {
+ } else if (!f2fs_sb_mounted_blkzoned(sb)) {
f2fs_msg(sb, KERN_WARNING,
"mounting with \"discard\" option, but "
"the device does not support discard");
}
break;
case Opt_nodiscard:
+ if (f2fs_sb_mounted_blkzoned(sb)) {
+ 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 +402,15 @@ 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);
+ sbi->inline_xattr_size = arg;
+ break;
#else
case Opt_user_xattr:
f2fs_msg(sb, KERN_INFO,
@@ -446,6 +424,10 @@ 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:
@@ -512,6 +494,13 @@ static int parse_options(struct super_block *sb, char *options)
return -ENOMEM;
if (strlen(name) == 8 &&
!strncmp(name, "adaptive", 8)) {
+ if (f2fs_sb_mounted_blkzoned(sb)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "adaptive mode is not allowed with "
+ "zoned block device feature");
+ kfree(name);
+ return -EINVAL;
+ }
set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
} else if (strlen(name) == 3 &&
!strncmp(name, "lfs", 3)) {
@@ -522,11 +511,23 @@ static int parse_options(struct super_block *sb, char *options)
}
kfree(name);
break;
+ case Opt_io_size_bits:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (arg > __ilog2_u32(BIO_MAX_PAGES)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "Not support %d, larger than %d",
+ 1 << arg, BIO_MAX_PAGES);
+ return -EINVAL;
+ }
+ sbi->write_io_size_bits = arg;
+ break;
case Opt_fault_injection:
if (args->from && match_int(args, &arg))
return -EINVAL;
#ifdef CONFIG_F2FS_FAULT_INJECTION
f2fs_build_fault_attr(sbi, arg);
+ set_opt(sbi, FAULT_INJECTION);
#else
f2fs_msg(sb, KERN_INFO,
"FAULT_INJECTION was not selected");
@@ -538,6 +539,81 @@ static int parse_options(struct super_block *sb, char *options)
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:
+ sbi->s_jquota_fmt = QFMT_VFS_OLD;
+ break;
+ case Opt_jqfmt_vfsv0:
+ sbi->s_jquota_fmt = QFMT_VFS_V0;
+ break;
+ case Opt_jqfmt_vfsv1:
+ 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
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -545,6 +621,35 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
}
}
+#ifdef CONFIG_QUOTA
+ if (f2fs_check_quota_options(sbi))
+ 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)) {
+ if (!test_opt(sbi, INLINE_XATTR)) {
+ f2fs_msg(sb, KERN_ERR,
+ "inline_xattr_size option should be "
+ "set with inline_xattr option");
+ return -EINVAL;
+ }
+ if (!sbi->inline_xattr_size ||
+ sbi->inline_xattr_size >= DEF_ADDRS_PER_INODE -
+ F2FS_TOTAL_EXTRA_ATTR_SIZE -
+ DEF_INLINE_RESERVED_SIZE -
+ DEF_MIN_INLINE_SIZE) {
+ f2fs_msg(sb, KERN_ERR,
+ "inline xattr size is out of range");
+ return -EINVAL;
+ }
+ }
return 0;
}
@@ -559,25 +664,33 @@ 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_mmap_sem);
+ init_rwsem(&fi->i_xattr_sem);
+#ifdef CONFIG_QUOTA
+ memset(&fi->i_dquot, 0, sizeof(fi->i_dquot));
+ fi->i_reserved_quota = 0;
+#endif
/* 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)
@@ -606,34 +719,36 @@ static int f2fs_drop_inode(struct inode *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 +760,12 @@ 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 +789,7 @@ 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 +809,26 @@ 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
+ kfree(FDEV(i).blkz_type);
+#endif
+ }
+ kfree(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);
@@ -721,6 +846,16 @@ static void f2fs_put_super(struct super_block *sb)
write_checkpoint(sbi, &cpc);
}
+ /* be sure to wait for any on-going discard commands */
+ dropped = f2fs_wait_discard_bios(sbi);
+
+ if (f2fs_discard_en(sbi) && !sbi->discard_blks && !dropped) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT | CP_TRIMMED,
+ };
+ write_checkpoint(sbi, &cpc);
+ }
+
/* write_checkpoint can update stat informaion */
f2fs_destroy_stats(sbi);
@@ -729,13 +864,12 @@ static void f2fs_put_super(struct super_block *sb)
* In addition, EIO will skip do checkpoint, we need this as well.
*/
release_ino_entry(sbi, true);
- release_discard_addrs(sbi);
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);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -745,15 +879,23 @@ static void f2fs_put_super(struct super_block *sb)
destroy_segment_manager(sbi);
kfree(sbi->ckpt);
- kobject_put(&sbi->s_kobj);
- wait_for_completion(&sbi->s_kobj_unregister);
+
+ 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);
+ destroy_device_list(sbi);
+ mempool_destroy(sbi->write_io_dummy);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
destroy_percpu_info(sbi);
+ for (i = 0; i < NR_PAGE_TYPE; i++)
+ kfree(sbi->write_io[i]);
kfree(sbi);
}
@@ -762,8 +904,14 @@ 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;
+
trace_f2fs_sync_fs(sb, sync);
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ return -EAGAIN;
+
if (sync) {
struct cp_control cpc;
@@ -780,13 +928,17 @@ 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)
@@ -794,12 +946,55 @@ 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;
+ u64 avail_node_count;
total_count = le64_to_cpu(sbi->raw_super->block_count);
user_block_count = sbi->user_block_count;
@@ -810,18 +1005,67 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
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_bavail = user_block_count - valid_user_blocks(sbi) -
+ sbi->current_reserved_blocks;
- buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
- buf->f_ffree = buf->f_files - valid_inode_count(sbi);
+ avail_node_count = sbi->total_node_count - 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 (sbi->s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (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 (sbi->s_qf_names[USRQUOTA])
+ seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]);
+
+ if (sbi->s_qf_names[GRPQUOTA])
+ seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]);
+
+ if (sbi->s_qf_names[PRJQUOTA])
+ seq_show_option(seq, "prjjquota", 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 +1083,9 @@ 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 +1093,11 @@ 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",
+ sbi->inline_xattr_size);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
@@ -883,89 +1134,43 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
else if (test_opt(sbi, LFS))
seq_puts(seq, "lfs");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
+ if (F2FS_IO_SIZE_BITS(sbi))
+ seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (test_opt(sbi, FAULT_INJECTION))
+ seq_printf(seq, ",fault_injection=%u",
+ sbi->fault_info.inject_rate);
+#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);
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, ' ');
- }
-
- 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;
+ sbi->inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
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;
set_opt(sbi, FLUSH_MERGE);
- if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+ if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
set_opt_mode(sbi, F2FS_MOUNT_LFS);
set_opt(sbi, DISCARD);
} else {
@@ -984,10 +1189,14 @@ static void default_options(struct f2fs_sb_info *sbi)
#endif
}
+#ifdef CONFIG_QUOTA
+static int f2fs_enable_quotas(struct super_block *sb);
+#endif
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;
+ unsigned long old_sb_flags;
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
@@ -995,14 +1204,37 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct f2fs_fault_info ffi = sbi->fault_info;
#endif
+#ifdef CONFIG_QUOTA
+ int s_jquota_fmt;
+ char *s_qf_names[MAXQUOTAS];
+ int i, j;
+#endif
/*
* Save the old mount options in case we
* need to restore them.
*/
org_mount_opt = sbi->mount_opt;
+ old_sb_flags = sb->s_flags;
active_logs = sbi->active_logs;
+#ifdef CONFIG_QUOTA
+ s_jquota_fmt = sbi->s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (sbi->s_qf_names[i]) {
+ s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
+ GFP_KERNEL);
+ if (!s_qf_names[i]) {
+ for (j = 0; j < i; j++)
+ kfree(s_qf_names[j]);
+ return -ENOMEM;
+ }
+ } else {
+ 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)) {
err = f2fs_commit_super(sbi, false);
@@ -1012,7 +1244,6 @@ 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 */
@@ -1027,6 +1258,23 @@ 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 {
+ /* 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(sb)) {
+ 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;
@@ -1067,13 +1315,19 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
* 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) {
+ clear_opt(sbi, FLUSH_MERGE);
+ destroy_flush_cmd_control(sbi, false);
+ } else {
err = 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++)
+ kfree(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);
@@ -1088,21 +1342,367 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
stop_gc_thread(sbi);
}
restore_opts:
+#ifdef CONFIG_QUOTA
+ sbi->s_jquota_fmt = s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ kfree(sbi->s_qf_names[i]);
+ sbi->s_qf_names[i] = s_qf_names[i];
+ }
+#endif
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
+ sb->s_flags = old_sb_flags;
#ifdef CONFIG_F2FS_FAULT_INJECTION
sbi->fault_info = ffi;
#endif
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_mapping_page(mapping, blkidx, NULL);
+ if (IS_ERR(page)) {
+ if (PTR_ERR(page) == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto repeat;
+ }
+ 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);
+ 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;
+ }
+ 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)
+{
+ return dquot_quota_on_mount(sbi->sb, sbi->s_qf_names[type],
+ 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->sb) && 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 (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(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),
+ };
+
+ 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);
+ return err;
+ }
+ }
+ }
+ return 0;
+}
+
+static int f2fs_quota_sync(struct super_block *sb, int type)
+{
+ struct quota_info *dqopt = sb_dqopt(sb);
+ int cnt;
+ int ret;
+
+ ret = dquot_writeback_dquots(sb, type);
+ if (ret)
+ return ret;
+
+ /*
+ * Now when everything is written we can discard the pagecache so
+ * that userspace sees the changes.
+ */
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+ if (type != -1 && cnt != type)
+ continue;
+ if (!sb_has_quota_active(sb, cnt))
+ continue;
+
+ ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping);
+ if (ret)
+ return ret;
+
+ inode_lock(dqopt->files[cnt]);
+ truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+ inode_unlock(dqopt->files[cnt]);
+ }
+ return 0;
+}
+
+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 |= FS_NOATIME_FL | FS_IMMUTABLE_FL;
+ inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+ S_NOATIME | S_IMMUTABLE);
+ 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);
+
+ f2fs_quota_sync(sb, type);
+
+ err = dquot_quota_off(sb, type);
+ if (err || f2fs_sb_has_quota_ino(sb))
+ goto out_put;
+
+ inode_lock(inode);
+ F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL);
+ inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+ 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;
+
+ for (type = 0; type < MAXQUOTAS; type++)
+ f2fs_quota_off(sb, type);
+}
+
+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 = dquot_commit,
+ .acquire_dquot = dquot_acquire,
+ .release_dquot = dquot_release,
+ .mark_dirty = dquot_mark_dquot_dirty,
+ .write_info = 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
+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,
@@ -1120,12 +1720,6 @@ 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)
{
@@ -1140,18 +1734,13 @@ static unsigned f2fs_max_namelen(struct inode *inode)
inode->i_sb->s_blocksize : F2FS_NAME_LEN;
}
-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,
.empty_dir = f2fs_empty_dir,
.max_namelen = f2fs_max_namelen,
};
-#else
-static struct fscrypt_operations f2fs_cryptops = {
- .is_encrypted = f2fs_encrypted_inode,
-};
#endif
static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
@@ -1201,9 +1790,16 @@ 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);
@@ -1229,7 +1825,7 @@ static int __f2fs_commit_super(struct buffer_head *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,
@@ -1424,6 +2020,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ unsigned int ovp_segments, reserved_segments;
unsigned int main_segs, blocks_per_seg;
int i;
@@ -1437,6 +2034,16 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
if (unlikely(fsmeta >= total))
return 1;
+ ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+ reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+ if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+ ovp_segments == 0 || reserved_segments == 0)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong layout: check mkfs.f2fs version");
+ return 1;
+ }
+
main_segs = le32_to_cpu(raw_super->segment_count_main);
blocks_per_seg = sbi->blocks_per_seg;
@@ -1461,7 +2068,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
static void init_sb_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = sbi->raw_super;
- int i;
+ int i, j;
sbi->log_sectors_per_block =
le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1489,17 +2096,17 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_COUNT_TYPE; i++)
atomic_set(&sbi->nr_pages[i], 0);
+ atomic_set(&sbi->wb_sync_req, 0);
+
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
- mutex_init(&sbi->wio_mutex[NODE]);
- mutex_init(&sbi->wio_mutex[DATA]);
+ for (i = 0; i < NR_PAGE_TYPE - 1; i++)
+ for (j = HOT; j < NR_TEMP_TYPE; j++)
+ mutex_init(&sbi->wio_mutex[i][j]);
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);
}
static int init_percpu_info(struct f2fs_sb_info *sbi)
@@ -1514,6 +2121,71 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
GFP_KERNEL);
}
+#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_mounted_blkzoned(sbi->sb))
+ 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 = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
+ if (!FDEV(devi).blkz_type)
+ return -ENOMEM;
+
+#define F2FS_REPORT_NR_ZONES 4096
+
+ zones = kcalloc(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++;
+ }
+ }
+
+ kfree(zones);
+
+ return err;
+}
+#endif
+
/*
* Read f2fs raw super block.
* Because we have two copies of super block, so read both of them
@@ -1606,6 +2278,104 @@ 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 = kcalloc(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_mounted_blkzoned(sbi->sb)) {
+ 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 int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
@@ -1653,6 +2423,24 @@ 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(sb))
+ 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_mounted_blkzoned(sb)) {
+ 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);
@@ -1671,33 +2459,60 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
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(sb))
+ 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;
+#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));
/* init f2fs-specific super block info */
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
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] = kmalloc(n * sizeof(struct f2fs_bio_info),
+ GFP_KERNEL);
+ if (!sbi->write_io[i]) {
+ err = -ENOMEM;
+ goto free_options;
+ }
+
+ 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);
@@ -1708,12 +2523,21 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto free_options;
+ 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_options;
+ }
+ }
+
/* 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);
@@ -1722,6 +2546,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
goto free_meta_inode;
}
+ /* 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,
@@ -1730,6 +2561,8 @@ 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;
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -1777,10 +2610,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
f2fs_join_shrinker(sbi);
- /* if there are nt orphan nodes free them */
- err = recover_orphan_inodes(sbi);
+ err = f2fs_build_stats(sbi);
if (err)
- goto free_node_inode;
+ goto free_nm;
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
@@ -1801,26 +2633,28 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
goto free_root_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
+ /*
+ * Turn on quotas which were not enabled for read-only mounts if
+ * filesystem has quota feature, so that they are updated correctly.
+ */
+ if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb)) {
+ err = f2fs_enable_quotas(sb);
+ if (err) {
+ f2fs_msg(sb, KERN_ERR,
+ "Cannot turn on quotas: error %d", err);
+ goto free_sysfs;
+ }
}
-
- 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 = recover_orphan_inodes(sbi);
if (err)
- goto free_proc;
+ goto free_meta;
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
@@ -1831,7 +2665,7 @@ 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)
@@ -1845,7 +2679,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
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);
@@ -1854,7 +2688,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
err = -EINVAL;
f2fs_msg(sb, KERN_ERR,
"Need to recover fsync data");
- goto free_kobj;
+ goto free_meta;
}
}
skip_recovery:
@@ -1869,7 +2703,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
- goto free_kobj;
+ goto free_meta;
}
kfree(options);
@@ -1881,22 +2715,29 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sbi->valid_super_block ? 1 : 2, err);
}
+ 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);
return 0;
-free_kobj:
+free_meta:
+#ifdef CONFIG_QUOTA
+ if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb))
+ f2fs_quota_off_umount(sbi->sb);
+#endif
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);
+ /*
+ * Some dirty meta pages can be produced by recover_orphan_inodes()
+ * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+ * followed by write_checkpoint() through f2fs_write_node_pages(), which
+ * falls into an infinite loop in sync_meta_pages().
+ */
+ truncate_inode_pages_final(META_MAPPING(sbi));
+#ifdef CONFIG_QUOTA
+free_sysfs:
+#endif
+ f2fs_unregister_sysfs(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
@@ -1907,16 +2748,27 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
f2fs_leave_shrinker(sbi);
iput(sbi->node_inode);
mutex_unlock(&sbi->umount_mutex);
+ f2fs_destroy_stats(sbi);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
+free_devices:
+ destroy_device_list(sbi);
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
+free_io_dummy:
+ mempool_destroy(sbi->write_io_dummy);
free_options:
+ for (i = 0; i < NR_PAGE_TYPE; i++)
+ kfree(sbi->write_io[i]);
destroy_percpu_info(sbi);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
kfree(options);
free_sb_buf:
kfree(raw_super);
@@ -1942,8 +2794,11 @@ 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)
+ if (sb->s_root) {
set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+ stop_gc_thread(F2FS_SB(sb));
+ stop_discard_thread(F2FS_SB(sb));
+ }
kill_block_super(sb);
}
@@ -1997,30 +2852,26 @@ static int __init init_f2fs_fs(void)
err = 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();
if (err)
goto free_filesystem;
- f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
return 0;
free_filesystem:
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();
free_checkpoint_caches:
@@ -2037,11 +2888,10 @@ static int __init init_f2fs_fs(void)
static void __exit exit_f2fs_fs(void)
{
- remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
unregister_shrinker(&f2fs_shrinker_info);
- kset_unregister(f2fs_kset);
+ f2fs_exit_sysfs();
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
@@ -2056,3 +2906,4 @@ 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..9835348
--- /dev/null
+++ b/fs/f2fs/sysfs.c
@@ -0,0 +1,577 @@
+/*
+ * f2fs sysfs interface
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com/
+ * Copyright (c) 2017 Chao Yu <chao@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/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 *)&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_crypto(sb))
+ len += snprintf(buf, PAGE_SIZE - len, "%s",
+ "encryption");
+ if (f2fs_sb_mounted_blkzoned(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "blkzoned");
+ if (f2fs_sb_has_extra_attr(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "extra_attr");
+ if (f2fs_sb_has_project_quota(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "projquota");
+ if (f2fs_sb_has_inode_chksum(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "inode_checksum");
+ if (f2fs_sb_has_flexible_inline_xattr(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "flexible_inline_xattr");
+ if (f2fs_sb_has_quota_ino(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "quota_ino");
+ 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;
+
+ 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
+ if (a->struct_type == RESERVED_BLOCKS) {
+ spin_lock(&sbi->stat_lock);
+ if (t > (unsigned long)sbi->user_block_count) {
+ 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;
+ }
+
+ *ui = t;
+
+ if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
+ f2fs_reset_iostat(sbi);
+ if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && 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);
+ }
+
+ 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);
+}
+
+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,
+};
+
+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:
+ 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(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent);
+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_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, 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, iostat_enable, iostat_enable);
+#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);
+
+#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_hot_blocks),
+ ATTR_LIST(min_ssr_sections),
+ 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),
+ ATTR_LIST(iostat_enable),
+#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),
+ 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 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 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 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;
+}
+
+#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);
+
+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);
+ }
+ 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(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 73b4e1d..bccbbf2 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -59,7 +59,7 @@ 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);
if (radix_tree_preload(GFP_NOFS))
return;
@@ -138,7 +138,7 @@ 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/xattr.c b/fs/f2fs/xattr.c
index 3e1c028..ec8961e 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -106,7 +106,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
@@ -217,55 +217,157 @@ 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);
+
+ list_for_each_xattr(entry, base_addr) {
+ if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
+ (void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
+ base_addr + inline_size) {
+ *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;
+ }
+ 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 = 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 = 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)
+{
+ 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;
+
+ txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+ GFP_F2FS_ZERO);
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);
- }
- memcpy(txattr_addr, inline_addr, inline_size);
- f2fs_put_page(page, 1);
+ *xe = __find_inline_xattr(inode, txattr_addr, &last_addr,
+ index, len, name);
+ if (*xe)
+ goto check;
}
/* 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:
+ kzfree(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 = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+ GFP_F2FS_ZERO);
+ 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);
@@ -286,13 +388,13 @@ 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))
@@ -300,30 +402,30 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
/* 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)) {
+ in_page = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(in_page)) {
alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(page);
+ 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);
/* no need to use xattr node block */
if (hsize <= inline_size) {
- err = truncate_xattr_node(inode, ipage);
+ err = truncate_xattr_node(inode);
alloc_nid_failed(sbi, new_nid);
- return err;
+ 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;
}
}
@@ -332,39 +434,43 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(xpage);
+ goto in_page_out;
}
f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE, 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 = new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_nid);
- return PTR_ERR(xpage);
+ goto in_page_out;
}
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;
if (name == NULL)
return -EINVAL;
@@ -373,21 +479,18 @@ 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);
+ 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) {
@@ -395,8 +498,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
memcpy(buffer, pval, size);
}
error = size;
-
-cleanup:
+out:
kzfree(base_addr);
return error;
}
@@ -409,7 +511,9 @@ 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;
@@ -445,6 +549,15 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
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 +592,17 @@ 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 (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;
@@ -554,7 +672,7 @@ 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:
@@ -569,6 +687,10 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
/* this case is only from init_inode_metadata */
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
@@ -578,7 +700,9 @@ 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..dbcd1d1 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -58,10 +58,10 @@ 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)))
@@ -72,9 +72,10 @@ 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) - \
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0703a11..ad2e55d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2111,7 +2111,7 @@ 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 f117926..83511cb 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");
@@ -453,7 +455,9 @@ 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)
@@ -1880,6 +1884,10 @@ 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) {
+ req->out.h.error = kern_path((char *)req->out.args[0].value, 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 4bbad74..c9889fd 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -262,6 +262,50 @@ 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;
@@ -284,11 +328,13 @@ 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/fuse_i.h b/fs/fuse/fuse_i.h
index 9130794..6b30a12 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -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/inode.c b/fs/inode.c
index 920aa0b..3844c31 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1781,7 +1781,7 @@ 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;
@@ -1790,7 +1790,7 @@ 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);
}
/*
@@ -1812,7 +1812,7 @@ 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/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 6cfb45f..339f7c7 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -375,9 +375,11 @@ 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);
@@ -401,7 +403,7 @@ 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;
@@ -421,7 +423,7 @@ 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;
@@ -429,7 +431,14 @@ 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);
@@ -465,14 +474,20 @@ 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);
@@ -1666,13 +1681,13 @@ 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)
@@ -2146,11 +2161,12 @@ 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);
}
@@ -2415,6 +2431,7 @@ 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
*
@@ -2423,7 +2440,7 @@ 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;
@@ -2457,12 +2474,18 @@ 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);
/**
@@ -2765,7 +2788,7 @@ 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;
@@ -2777,7 +2800,7 @@ 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))
@@ -2809,7 +2832,7 @@ 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);
@@ -2821,7 +2844,7 @@ 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);
}
/*
@@ -2868,10 +2891,10 @@ 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;
@@ -2887,6 +2910,13 @@ 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)
@@ -2898,6 +2928,7 @@ 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;
@@ -2922,7 +2953,7 @@ 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;
@@ -2957,7 +2988,7 @@ 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);
}
@@ -2984,7 +3015,7 @@ 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;
@@ -3415,7 +3446,7 @@ 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) {
@@ -3668,9 +3699,9 @@ 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;
@@ -3694,6 +3725,12 @@ 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)
@@ -3736,12 +3773,12 @@ 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:
@@ -3762,9 +3799,9 @@ 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)
@@ -3786,6 +3823,12 @@ 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)
@@ -3804,7 +3847,7 @@ 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;
@@ -3818,9 +3861,9 @@ 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;
@@ -3855,6 +3898,12 @@ 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)
@@ -3900,7 +3949,7 @@ 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:
@@ -3939,10 +3988,10 @@ 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;
@@ -3977,6 +4026,12 @@ 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);
/*
@@ -4024,7 +4079,7 @@ 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);
}
@@ -4074,9 +4129,9 @@ 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;
@@ -4093,6 +4148,12 @@ 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,
@@ -4115,7 +4176,7 @@ 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;
@@ -4150,7 +4211,7 @@ 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;
@@ -4159,7 +4220,7 @@ 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;
@@ -4209,6 +4270,12 @@ 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);
/*
@@ -4264,7 +4331,7 @@ 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) {
@@ -4339,7 +4406,8 @@ 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)
{
@@ -4358,19 +4426,19 @@ 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;
@@ -4384,12 +4452,12 @@ 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;
}
@@ -4466,6 +4534,14 @@ 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,
@@ -4579,7 +4655,7 @@ 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:
@@ -4624,7 +4700,7 @@ 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 d7360f9..2160bb9 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);
@@ -975,10 +977,18 @@ 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);
@@ -1022,6 +1032,14 @@ 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
@@ -2305,8 +2323,14 @@ 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 f1160cd..eaac878 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/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/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/open.c b/fs/open.c
index a6c6244..73b7d19 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;
@@ -387,6 +397,7 @@ 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)) {
/*
@@ -398,7 +409,7 @@ 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;
@@ -442,7 +453,7 @@ 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;
@@ -462,6 +473,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
struct fd f = fdget_raw(fd);
struct inode *inode;
+ struct vfsmount *mnt;
int error = -EBADF;
error = -EBADF;
@@ -469,12 +481,13 @@ 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:
@@ -493,7 +506,7 @@ 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;
@@ -533,7 +546,7 @@ 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) {
@@ -613,7 +626,7 @@ 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/pnode.c b/fs/pnode.c
index d15c63e..ddb846f 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -609,3 +609,37 @@ int propagate_umount(struct list_head *list)
return 0;
}
+
+/*
+ * Iterates over all slaves, and slaves of slaves.
+ */
+static struct mount *next_descendent(struct mount *root, struct mount *cur)
+{
+ if (!IS_MNT_NEW(cur) && !list_empty(&cur->mnt_slave_list))
+ return first_slave(cur);
+ do {
+ struct mount *master = cur->mnt_master;
+
+ if (!master || cur->mnt_slave.next != &master->mnt_slave_list) {
+ struct mount *next = next_slave(cur);
+
+ return (next == root) ? NULL : next;
+ }
+ cur = master;
+ } while (cur != root);
+ return NULL;
+}
+
+void propagate_remount(struct mount *mnt)
+{
+ struct mount *m = mnt;
+ struct super_block *sb = mnt->mnt.mnt_sb;
+
+ if (sb->s_op->copy_mnt_data) {
+ m = next_descendent(mnt, m);
+ while (m) {
+ sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data);
+ m = next_descendent(mnt, m);
+ }
+ }
+}
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/base.c b/fs/proc/base.c
index e67fec3..27c4e8f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2912,8 +2912,8 @@ static const struct pid_entry tgid_base_stuff[] = {
ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
- REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+ REG("oom_adj", S_IRUSR, proc_oom_adj_operations),
+ REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
@@ -3303,8 +3303,8 @@ static const struct pid_entry tid_base_stuff[] = {
ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
- REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+ REG("oom_adj", S_IRUSR, proc_oom_adj_operations),
+ REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5138e78..9182f84 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;
@@ -341,8 +391,15 @@ 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:
@@ -756,6 +813,12 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
show_map_vma(m, vma, is_pid);
+ if (vma_get_anon_name(vma)) {
+ seq_puts(m, "Name: ");
+ seq_print_vma_name(m, vma);
+ seq_putc(m, '\n');
+ }
+
seq_printf(m,
"Size: %8lu kB\n"
"Rss: %8lu kB\n"
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 8b09271..8e151fb 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -550,6 +550,12 @@ 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/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..e9426a6
--- /dev/null
+++ b/fs/sdcardfs/dentry.c
@@ -0,0 +1,193 @@
+/*
+ * 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)) {
+ d_drop(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) {
+ d_drop(dentry);
+ goto out;
+ }
+ }
+
+ spin_lock(&lower_dentry->d_lock);
+ if (d_unhashed(lower_dentry)) {
+ spin_unlock(&lower_dentry->d_lock);
+ d_drop(dentry);
+ err = 0;
+ goto out;
+ }
+ spin_unlock(&lower_dentry->d_lock);
+
+ if (parent_lower_dentry != lower_cur_parent_dentry) {
+ d_drop(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)) {
+ __d_drop(dentry);
+ 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) {
+ d_drop(dentry);
+ 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;
+}
+
+static void sdcardfs_d_release(struct dentry *dentry)
+{
+ /* 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_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..0b3b223
--- /dev/null
+++ b/fs/sdcardfs/derived_perm.c
@@ -0,0 +1,472 @@
+/*
+ * 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_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_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 (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..5ac0b0b
--- /dev/null
+++ b/fs/sdcardfs/file.c
@@ -0,0 +1,449 @@
+/*
+ * 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;
+
+ /* 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) {
+ fsstack_copy_inode_size(d_inode(dentry),
+ file_inode(lower_file));
+ fsstack_copy_attr_times(d_inode(dentry),
+ file_inode(lower_file));
+ }
+
+ 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 */
+ OVERRIDE_CRED(sbi, saved_cred, SDCARDFS_I(file_inode(file)));
+
+ 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_CRED(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 */
+ OVERRIDE_CRED(sbi, saved_cred, SDCARDFS_I(file_inode(file)));
+
+ if (lower_file->f_op->compat_ioctl)
+ err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
+
+ REVERT_CRED(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 */
+ OVERRIDE_CRED(sbi, saved_cred, SDCARDFS_I(inode));
+
+ 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_CRED(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;
+
+ 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) {
+ fsstack_copy_inode_size(file->f_path.dentry->d_inode,
+ file_inode(lower_file));
+ fsstack_copy_attr_times(file->f_path.dentry->d_inode,
+ file_inode(lower_file));
+ }
+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..9cdb396
--- /dev/null
+++ b/fs/sdcardfs/inode.c
@@ -0,0 +1,919 @@
+/*
+ * 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>
+
+/* 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)
+{
+ 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;
+}
+
+/* Do not directly use this function, use REVERT_CRED() instead. */
+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 */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir));
+
+ 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;
+ }
+ current->fs = copied_fs;
+ current->fs->umask = 0;
+ 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:
+ current->fs = saved_fs;
+ free_fs_struct(copied_fs);
+out_unlock:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *new_dentry)
+{
+ struct dentry *lower_old_dentry;
+ struct dentry *lower_new_dentry;
+ struct dentry *lower_dir_dentry;
+ u64 file_size_save;
+ int err;
+ struct path lower_old_path, lower_new_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ file_size_save = i_size_read(d_inode(old_dentry));
+ sdcardfs_get_lower_path(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_dir_dentry = lock_parent(lower_new_dentry);
+
+ err = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry),
+ lower_new_dentry, NULL);
+ if (err || !d_inode(lower_new_dentry))
+ goto out;
+
+ err = sdcardfs_interpose(new_dentry, dir->i_sb, &lower_new_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, d_inode(lower_new_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_new_dentry));
+ set_nlink(d_inode(old_dentry),
+ sdcardfs_lower_inode(d_inode(old_dentry))->i_nlink);
+ i_size_write(d_inode(new_dentry), file_size_save);
+out:
+ unlock_dir(lower_dir_dentry);
+ sdcardfs_put_lower_path(old_dentry, &lower_old_path);
+ sdcardfs_put_lower_path(new_dentry, &lower_new_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+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 */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir));
+
+ 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_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_symlink(struct inode *dir, struct dentry *dentry,
+ const char *symname)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ err = vfs_symlink(d_inode(lower_parent_dentry), lower_dentry, symname);
+ if (err)
+ goto out;
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry));
+
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+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 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 */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir));
+
+ /* check disk space */
+ if (!check_min_free_space(dentry, 0, 1)) {
+ pr_err("sdcardfs: No minimum free space.\n");
+ err = -ENOSPC;
+ goto out_revert;
+ }
+
+ /* 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;
+ }
+ current->fs = copied_fs;
+ current->fs->umask = 0;
+ 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_CRED(saved_cred);
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(d_inode(dentry)));
+ 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:
+ current->fs = saved_fs;
+ free_fs_struct(copied_fs);
+out_unlock:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out_revert:
+ REVERT_CRED(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 */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir));
+
+ /* 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_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+ dev_t dev)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ err = vfs_mknod(d_inode(lower_parent_dentry), lower_dentry, mode, dev);
+ if (err)
+ goto out;
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry));
+
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+/*
+ * 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 */
+ OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred, SDCARDFS_I(new_dir));
+
+ 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_CRED(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);
+ /* XXX
+ * Original sdcardfs code calls inode_permission(lower_inode,.. )
+ * for checking inode permission. But doing such things here seems
+ * duplicated work, because the functions called after this func,
+ * such as vfs_create, vfs_unlink, vfs_rename, and etc,
+ * does exactly same thing, i.e., they calls inode_permission().
+ * So we just let they do the things.
+ * If there are any security hole, just uncomment following if block.
+ */
+#if 0
+ if (!err) {
+ /*
+ * Permission check on lower_inode(=EXT4).
+ * we check it with AID_MEDIA_RW permission
+ */
+ struct inode *lower_inode;
+
+ OVERRIDE_CRED(SDCARDFS_SB(inode->sb));
+
+ lower_inode = sdcardfs_lower_inode(inode);
+ err = inode_permission(lower_inode, mask);
+
+ REVERT_CRED();
+ }
+#endif
+ 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 */
+ OVERRIDE_CRED(SDCARDFS_SB(dentry->d_sb), saved_cred, SDCARDFS_I(inode));
+
+ 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_CRED(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,
+ /* XXX Following operations are implemented,
+ * but FUSE(sdcard) or FAT does not support them
+ * These methods are *NOT* perfectly tested.
+ .symlink = sdcardfs_symlink,
+ .link = sdcardfs_link,
+ .mknod = sdcardfs_mknod,
+ */
+};
+
+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..843fcd2
--- /dev/null
+++ b/fs/sdcardfs/lookup.c
@@ -0,0 +1,466 @@
+/*
+ * 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)
+{
+ if (!dentry || !dentry->d_fsdata)
+ return;
+ 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 */
+ OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir));
+
+ 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_CRED(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..e4fd3fb
--- /dev/null
+++ b/fs/sdcardfs/main.c
@@ -0,0 +1,491 @@
+/*
+ * 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_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_reserved_mb, "reserved_mb=%u"},
+ {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;
+
+ *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;
+ /* 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_default_normal:
+ case Opt_multiuser:
+ case Opt_userid:
+ case Opt_fsuid:
+ case Opt_fsgid:
+ case Opt_reserved_mb:
+ 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);
+
+ /* 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_iput;
+ }
+ 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);
+out_iput:
+ iput(inode);
+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) {
+ 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..6da0c21
--- /dev/null
+++ b/fs/sdcardfs/packagelist.c
@@ -0,0 +1,881 @@
+/*
+ * 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);
+ 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..610466a
--- /dev/null
+++ b/fs/sdcardfs/sdcardfs.h
@@ -0,0 +1,677 @@
+/*
+ * 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)
+
+/* OVERRIDE_CRED() and REVERT_CRED()
+ * OVERRIDE_CRED()
+ * backup original task->cred
+ * and modifies task->cred->fsuid/fsgid to specified value.
+ * REVERT_CRED()
+ * restore original task->cred->fsuid/fsgid.
+ * These two macro should be used in pair, and OVERRIDE_CRED() should be
+ * placed at the beginning of a function, right after variable declaration.
+ */
+#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred, info) \
+ do { \
+ saved_cred = override_fsids(sdcardfs_sbi, info->data); \
+ if (!saved_cred) \
+ return -ENOMEM; \
+ } while (0)
+
+#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred, info) \
+ do { \
+ saved_cred = override_fsids(sdcardfs_sbi, info->data); \
+ if (!saved_cred) \
+ return ERR_PTR(-ENOMEM); \
+ } while (0)
+
+#define REVERT_CRED(saved_cred) revert_fsids(saved_cred)
+
+/* 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;
+ unsigned int reserved_mb;
+};
+
+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_case_eq(q1->name, q2->name);
+}
+
+#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..cffcdb1
--- /dev/null
+++ b/fs/sdcardfs/super.c
@@ -0,0 +1,331 @@
+/*
+ * 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);
+
+ 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/squashfs/Kconfig b/fs/squashfs/Kconfig
index ffb093e..6dd158a 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -26,34 +26,6 @@
If unsure, say N.
choice
- prompt "File decompression options"
- depends on SQUASHFS
- help
- Squashfs now supports two options for decompressing file
- data. Traditionally Squashfs has decompressed into an
- intermediate buffer and then memcopied it into the page cache.
- Squashfs now supports the ability to decompress directly into
- the page cache.
-
- If unsure, select "Decompress file data into an intermediate buffer"
-
-config SQUASHFS_FILE_CACHE
- bool "Decompress file data into an intermediate buffer"
- help
- Decompress file data into an intermediate buffer and then
- memcopy it into the page cache.
-
-config SQUASHFS_FILE_DIRECT
- bool "Decompress files directly into the page cache"
- help
- Directly decompress file data into the page cache.
- Doing so can significantly improve performance because
- it eliminates a memcpy and it also removes the lock contention
- on the single buffer.
-
-endchoice
-
-choice
prompt "Decompressor parallelisation options"
depends on SQUASHFS
help
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 246a6f3..fe51f15 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -5,8 +5,7 @@
obj-$(CONFIG_SQUASHFS) += squashfs.o
squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
squashfs-y += namei.o super.o symlink.o decompressor.o
-squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
-squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
+squashfs-y += file_direct.o page_actor.o
squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index ce62a38..7077476 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -28,9 +28,12 @@
#include <linux/fs.h>
#include <linux/vfs.h>
+#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/string.h>
+#include <linux/pagemap.h>
#include <linux/buffer_head.h>
+#include <linux/workqueue.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -38,45 +41,382 @@
#include "decompressor.h"
#include "page_actor.h"
-/*
- * Read the metadata block length, this is stored in the first two
- * bytes of the metadata block.
- */
-static struct buffer_head *get_block_length(struct super_block *sb,
- u64 *cur_index, int *offset, int *length)
+static struct workqueue_struct *squashfs_read_wq;
+
+struct squashfs_read_request {
+ struct super_block *sb;
+ u64 index;
+ int length;
+ int compressed;
+ int offset;
+ u64 read_end;
+ struct squashfs_page_actor *output;
+ enum {
+ SQUASHFS_COPY,
+ SQUASHFS_DECOMPRESS,
+ SQUASHFS_METADATA,
+ } data_processing;
+ bool synchronous;
+
+ /*
+ * If the read is synchronous, it is possible to retrieve information
+ * about the request by setting these pointers.
+ */
+ int *res;
+ int *bytes_read;
+ int *bytes_uncompressed;
+
+ int nr_buffers;
+ struct buffer_head **bh;
+ struct work_struct offload;
+};
+
+struct squashfs_bio_request {
+ struct buffer_head **bh;
+ int nr_buffers;
+};
+
+static int squashfs_bio_submit(struct squashfs_read_request *req);
+
+int squashfs_init_read_wq(void)
{
- struct squashfs_sb_info *msblk = sb->s_fs_info;
- struct buffer_head *bh;
+ squashfs_read_wq = create_workqueue("SquashFS read wq");
+ return !!squashfs_read_wq;
+}
- bh = sb_bread(sb, *cur_index);
- if (bh == NULL)
- return NULL;
+void squashfs_destroy_read_wq(void)
+{
+ flush_workqueue(squashfs_read_wq);
+ destroy_workqueue(squashfs_read_wq);
+}
- if (msblk->devblksize - *offset == 1) {
- *length = (unsigned char) bh->b_data[*offset];
- put_bh(bh);
- bh = sb_bread(sb, ++(*cur_index));
- if (bh == NULL)
- return NULL;
- *length |= (unsigned char) bh->b_data[0] << 8;
- *offset = 1;
- } else {
- *length = (unsigned char) bh->b_data[*offset] |
- (unsigned char) bh->b_data[*offset + 1] << 8;
- *offset += 2;
+static void free_read_request(struct squashfs_read_request *req, int error)
+{
+ if (!req->synchronous)
+ squashfs_page_actor_free(req->output, error);
+ if (req->res)
+ *(req->res) = error;
+ kfree(req->bh);
+ kfree(req);
+}
- if (*offset == msblk->devblksize) {
- put_bh(bh);
- bh = sb_bread(sb, ++(*cur_index));
- if (bh == NULL)
- return NULL;
- *offset = 0;
+static void squashfs_process_blocks(struct squashfs_read_request *req)
+{
+ int error = 0;
+ int bytes, i, length;
+ struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+ struct squashfs_page_actor *actor = req->output;
+ struct buffer_head **bh = req->bh;
+ int nr_buffers = req->nr_buffers;
+
+ for (i = 0; i < nr_buffers; ++i) {
+ if (!bh[i])
+ continue;
+ wait_on_buffer(bh[i]);
+ if (!buffer_uptodate(bh[i]))
+ error = -EIO;
+ }
+ if (error)
+ goto cleanup;
+
+ if (req->data_processing == SQUASHFS_METADATA) {
+ /* Extract the length of the metadata block */
+ if (req->offset != msblk->devblksize - 1) {
+ length = le16_to_cpup((__le16 *)
+ (bh[0]->b_data + req->offset));
+ } else {
+ length = (unsigned char)bh[0]->b_data[req->offset];
+ length |= (unsigned char)bh[1]->b_data[0] << 8;
+ }
+ req->compressed = SQUASHFS_COMPRESSED(length);
+ req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
+ : SQUASHFS_COPY;
+ length = SQUASHFS_COMPRESSED_SIZE(length);
+ if (req->index + length + 2 > req->read_end) {
+ for (i = 0; i < nr_buffers; ++i)
+ put_bh(bh[i]);
+ kfree(bh);
+ req->length = length;
+ req->index += 2;
+ squashfs_bio_submit(req);
+ return;
+ }
+ req->length = length;
+ req->offset = (req->offset + 2) % PAGE_SIZE;
+ if (req->offset < 2) {
+ put_bh(bh[0]);
+ ++bh;
+ --nr_buffers;
+ }
+ }
+ if (req->bytes_read)
+ *(req->bytes_read) = req->length;
+
+ if (req->data_processing == SQUASHFS_COPY) {
+ squashfs_bh_to_actor(bh, nr_buffers, req->output, req->offset,
+ req->length, msblk->devblksize);
+ } else if (req->data_processing == SQUASHFS_DECOMPRESS) {
+ req->length = squashfs_decompress(msblk, bh, nr_buffers,
+ req->offset, req->length, actor);
+ if (req->length < 0) {
+ error = -EIO;
+ goto cleanup;
}
}
- return bh;
+ /* Last page may have trailing bytes not filled */
+ bytes = req->length % PAGE_SIZE;
+ if (bytes && actor->page[actor->pages - 1])
+ zero_user_segment(actor->page[actor->pages - 1], bytes,
+ PAGE_SIZE);
+
+cleanup:
+ if (req->bytes_uncompressed)
+ *(req->bytes_uncompressed) = req->length;
+ if (error) {
+ for (i = 0; i < nr_buffers; ++i)
+ if (bh[i])
+ put_bh(bh[i]);
+ }
+ free_read_request(req, error);
}
+static void read_wq_handler(struct work_struct *work)
+{
+ squashfs_process_blocks(container_of(work,
+ struct squashfs_read_request, offload));
+}
+
+static void squashfs_bio_end_io(struct bio *bio)
+{
+ int i;
+ int error = bio->bi_error;
+ struct squashfs_bio_request *bio_req = bio->bi_private;
+
+ bio_put(bio);
+
+ for (i = 0; i < bio_req->nr_buffers; ++i) {
+ if (!bio_req->bh[i])
+ continue;
+ if (!error)
+ set_buffer_uptodate(bio_req->bh[i]);
+ else
+ clear_buffer_uptodate(bio_req->bh[i]);
+ unlock_buffer(bio_req->bh[i]);
+ }
+ kfree(bio_req);
+}
+
+static int bh_is_optional(struct squashfs_read_request *req, int idx)
+{
+ int start_idx, end_idx;
+ struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+
+ start_idx = (idx * msblk->devblksize - req->offset) >> PAGE_SHIFT;
+ end_idx = ((idx + 1) * msblk->devblksize - req->offset + 1) >> PAGE_SHIFT;
+ if (start_idx >= req->output->pages)
+ return 1;
+ if (start_idx < 0)
+ start_idx = end_idx;
+ if (end_idx >= req->output->pages)
+ end_idx = start_idx;
+ return !req->output->page[start_idx] && !req->output->page[end_idx];
+}
+
+static int actor_getblks(struct squashfs_read_request *req, u64 block)
+{
+ int i;
+
+ req->bh = kmalloc_array(req->nr_buffers, sizeof(*(req->bh)), GFP_NOIO);
+ if (!req->bh)
+ return -ENOMEM;
+
+ for (i = 0; i < req->nr_buffers; ++i) {
+ /*
+ * When dealing with an uncompressed block, the actor may
+ * contains NULL pages. There's no need to read the buffers
+ * associated with these pages.
+ */
+ if (!req->compressed && bh_is_optional(req, i)) {
+ req->bh[i] = NULL;
+ continue;
+ }
+ req->bh[i] = sb_getblk(req->sb, block + i);
+ if (!req->bh[i]) {
+ while (--i) {
+ if (req->bh[i])
+ put_bh(req->bh[i]);
+ }
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static int squashfs_bio_submit(struct squashfs_read_request *req)
+{
+ struct bio *bio = NULL;
+ struct buffer_head *bh;
+ struct squashfs_bio_request *bio_req = NULL;
+ int b = 0, prev_block = 0;
+ struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+
+ u64 read_start = round_down(req->index, msblk->devblksize);
+ u64 read_end = round_up(req->index + req->length, msblk->devblksize);
+ sector_t block = read_start >> msblk->devblksize_log2;
+ sector_t block_end = read_end >> msblk->devblksize_log2;
+ int offset = read_start - round_down(req->index, PAGE_SIZE);
+ int nr_buffers = block_end - block;
+ int blksz = msblk->devblksize;
+ int bio_max_pages = nr_buffers > BIO_MAX_PAGES ? BIO_MAX_PAGES
+ : nr_buffers;
+
+ /* Setup the request */
+ req->read_end = read_end;
+ req->offset = req->index - read_start;
+ req->nr_buffers = nr_buffers;
+ if (actor_getblks(req, block) < 0)
+ goto getblk_failed;
+
+ /* Create and submit the BIOs */
+ for (b = 0; b < nr_buffers; ++b, offset += blksz) {
+ bh = req->bh[b];
+ if (!bh || !trylock_buffer(bh))
+ continue;
+ if (buffer_uptodate(bh)) {
+ unlock_buffer(bh);
+ continue;
+ }
+ offset %= PAGE_SIZE;
+
+ /* Append the buffer to the current BIO if it is contiguous */
+ if (bio && bio_req && prev_block + 1 == b) {
+ if (bio_add_page(bio, bh->b_page, blksz, offset)) {
+ bio_req->nr_buffers += 1;
+ prev_block = b;
+ continue;
+ }
+ }
+
+ /* Otherwise, submit the current BIO and create a new one */
+ if (bio)
+ submit_bio(bio);
+ bio_req = kcalloc(1, sizeof(struct squashfs_bio_request),
+ GFP_NOIO);
+ if (!bio_req)
+ goto req_alloc_failed;
+ bio_req->bh = &req->bh[b];
+ bio = bio_alloc(GFP_NOIO, bio_max_pages);
+ if (!bio)
+ goto bio_alloc_failed;
+ bio->bi_bdev = req->sb->s_bdev;
+ bio->bi_iter.bi_sector = (block + b)
+ << (msblk->devblksize_log2 - 9);
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ bio->bi_private = bio_req;
+ bio->bi_end_io = squashfs_bio_end_io;
+
+ bio_add_page(bio, bh->b_page, blksz, offset);
+ bio_req->nr_buffers += 1;
+ prev_block = b;
+ }
+ if (bio)
+ submit_bio(bio);
+
+ if (req->synchronous)
+ squashfs_process_blocks(req);
+ else {
+ INIT_WORK(&req->offload, read_wq_handler);
+ schedule_work(&req->offload);
+ }
+ return 0;
+
+bio_alloc_failed:
+ kfree(bio_req);
+req_alloc_failed:
+ unlock_buffer(bh);
+ while (--nr_buffers >= b)
+ if (req->bh[nr_buffers])
+ put_bh(req->bh[nr_buffers]);
+ while (--b >= 0)
+ if (req->bh[b])
+ wait_on_buffer(req->bh[b]);
+getblk_failed:
+ free_read_request(req, -ENOMEM);
+ return -ENOMEM;
+}
+
+static int read_metadata_block(struct squashfs_read_request *req,
+ u64 *next_index)
+{
+ int ret, error, bytes_read = 0, bytes_uncompressed = 0;
+ struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+
+ if (req->index + 2 > msblk->bytes_used) {
+ free_read_request(req, -EINVAL);
+ return -EINVAL;
+ }
+ req->length = 2;
+
+ /* Do not read beyond the end of the device */
+ if (req->index + req->length > msblk->bytes_used)
+ req->length = msblk->bytes_used - req->index;
+ req->data_processing = SQUASHFS_METADATA;
+
+ /*
+ * Reading metadata is always synchronous because we don't know the
+ * length in advance and the function is expected to update
+ * 'next_index' and return the length.
+ */
+ req->synchronous = true;
+ req->res = &error;
+ req->bytes_read = &bytes_read;
+ req->bytes_uncompressed = &bytes_uncompressed;
+
+ TRACE("Metadata block @ 0x%llx, %scompressed size %d, src size %d\n",
+ req->index, req->compressed ? "" : "un", bytes_read,
+ req->output->length);
+
+ ret = squashfs_bio_submit(req);
+ if (ret)
+ return ret;
+ if (error)
+ return error;
+ if (next_index)
+ *next_index += 2 + bytes_read;
+ return bytes_uncompressed;
+}
+
+static int read_data_block(struct squashfs_read_request *req, int length,
+ u64 *next_index, bool synchronous)
+{
+ int ret, error = 0, bytes_uncompressed = 0, bytes_read = 0;
+
+ req->compressed = SQUASHFS_COMPRESSED_BLOCK(length);
+ req->length = length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
+ req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
+ : SQUASHFS_COPY;
+
+ req->synchronous = synchronous;
+ if (synchronous) {
+ req->res = &error;
+ req->bytes_read = &bytes_read;
+ req->bytes_uncompressed = &bytes_uncompressed;
+ }
+
+ TRACE("Data block @ 0x%llx, %scompressed size %d, src size %d\n",
+ req->index, req->compressed ? "" : "un", req->length,
+ req->output->length);
+
+ ret = squashfs_bio_submit(req);
+ if (ret)
+ return ret;
+ if (synchronous)
+ ret = error ? error : bytes_uncompressed;
+ if (next_index)
+ *next_index += length;
+ return ret;
+}
/*
* Read and decompress a metadata block or datablock. Length is non-zero
@@ -87,128 +427,50 @@ static struct buffer_head *get_block_length(struct super_block *sb,
* generated a larger block - this does occasionally happen with compression
* algorithms).
*/
-int squashfs_read_data(struct super_block *sb, u64 index, int length,
- u64 *next_index, struct squashfs_page_actor *output)
+static int __squashfs_read_data(struct super_block *sb, u64 index, int length,
+ u64 *next_index, struct squashfs_page_actor *output, bool sync)
{
- struct squashfs_sb_info *msblk = sb->s_fs_info;
- struct buffer_head **bh;
- int offset = index & ((1 << msblk->devblksize_log2) - 1);
- u64 cur_index = index >> msblk->devblksize_log2;
- int bytes, compressed, b = 0, k = 0, avail, i;
+ struct squashfs_read_request *req;
- bh = kcalloc(((output->length + msblk->devblksize - 1)
- >> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
- if (bh == NULL)
+ req = kcalloc(1, sizeof(struct squashfs_read_request), GFP_KERNEL);
+ if (!req) {
+ if (!sync)
+ squashfs_page_actor_free(output, -ENOMEM);
return -ENOMEM;
-
- if (length) {
- /*
- * Datablock.
- */
- bytes = -offset;
- compressed = SQUASHFS_COMPRESSED_BLOCK(length);
- length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
- if (next_index)
- *next_index = index + length;
-
- TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
- index, compressed ? "" : "un", length, output->length);
-
- if (length < 0 || length > output->length ||
- (index + length) > msblk->bytes_used)
- goto read_failure;
-
- for (b = 0; bytes < length; b++, cur_index++) {
- bh[b] = sb_getblk(sb, cur_index);
- if (bh[b] == NULL)
- goto block_release;
- bytes += msblk->devblksize;
- }
- ll_rw_block(REQ_OP_READ, 0, b, bh);
- } else {
- /*
- * Metadata block.
- */
- if ((index + 2) > msblk->bytes_used)
- goto read_failure;
-
- bh[0] = get_block_length(sb, &cur_index, &offset, &length);
- if (bh[0] == NULL)
- goto read_failure;
- b = 1;
-
- bytes = msblk->devblksize - offset;
- compressed = SQUASHFS_COMPRESSED(length);
- length = SQUASHFS_COMPRESSED_SIZE(length);
- if (next_index)
- *next_index = index + length + 2;
-
- TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
- compressed ? "" : "un", length);
-
- if (length < 0 || length > output->length ||
- (index + length) > msblk->bytes_used)
- goto block_release;
-
- for (; bytes < length; b++) {
- bh[b] = sb_getblk(sb, ++cur_index);
- if (bh[b] == NULL)
- goto block_release;
- bytes += msblk->devblksize;
- }
- ll_rw_block(REQ_OP_READ, 0, b - 1, bh + 1);
}
- for (i = 0; i < b; i++) {
- wait_on_buffer(bh[i]);
- if (!buffer_uptodate(bh[i]))
- goto block_release;
+ req->sb = sb;
+ req->index = index;
+ req->output = output;
+
+ if (next_index)
+ *next_index = index;
+
+ if (length)
+ length = read_data_block(req, length, next_index, sync);
+ else
+ length = read_metadata_block(req, next_index);
+
+ if (length < 0) {
+ ERROR("squashfs_read_data failed to read block 0x%llx\n",
+ (unsigned long long)index);
+ return -EIO;
}
- if (compressed) {
- length = squashfs_decompress(msblk, bh, b, offset, length,
- output);
- if (length < 0)
- goto read_failure;
- } else {
- /*
- * Block is uncompressed.
- */
- int in, pg_offset = 0;
- void *data = squashfs_first_page(output);
-
- for (bytes = length; k < b; k++) {
- in = min(bytes, msblk->devblksize - offset);
- bytes -= in;
- while (in) {
- if (pg_offset == PAGE_SIZE) {
- data = squashfs_next_page(output);
- pg_offset = 0;
- }
- avail = min_t(int, in, PAGE_SIZE -
- pg_offset);
- memcpy(data + pg_offset, bh[k]->b_data + offset,
- avail);
- in -= avail;
- pg_offset += avail;
- offset += avail;
- }
- offset = 0;
- put_bh(bh[k]);
- }
- squashfs_finish_page(output);
- }
-
- kfree(bh);
return length;
+}
-block_release:
- for (; k < b; k++)
- put_bh(bh[k]);
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+ u64 *next_index, struct squashfs_page_actor *output)
+{
+ return __squashfs_read_data(sb, index, length, next_index, output,
+ true);
+}
-read_failure:
- ERROR("squashfs_read_data failed to read block 0x%llx\n",
- (unsigned long long) index);
- kfree(bh);
- return -EIO;
+int squashfs_read_data_async(struct super_block *sb, u64 index, int length,
+ u64 *next_index, struct squashfs_page_actor *output)
+{
+
+ return __squashfs_read_data(sb, index, length, next_index, output,
+ false);
}
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 23813c0..05e4244 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -209,17 +209,14 @@ void squashfs_cache_put(struct squashfs_cache_entry *entry)
*/
void squashfs_cache_delete(struct squashfs_cache *cache)
{
- int i, j;
+ int i;
if (cache == NULL)
return;
for (i = 0; i < cache->entries; i++) {
- if (cache->entry[i].data) {
- for (j = 0; j < cache->pages; j++)
- kfree(cache->entry[i].data[j]);
- kfree(cache->entry[i].data);
- }
+ if (cache->entry[i].page)
+ free_page_array(cache->entry[i].page, cache->pages);
kfree(cache->entry[i].actor);
}
@@ -236,7 +233,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
struct squashfs_cache *squashfs_cache_init(char *name, int entries,
int block_size)
{
- int i, j;
+ int i;
struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL);
if (cache == NULL) {
@@ -268,22 +265,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
init_waitqueue_head(&cache->entry[i].wait_queue);
entry->cache = cache;
entry->block = SQUASHFS_INVALID_BLK;
- entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL);
- if (entry->data == NULL) {
+ entry->page = alloc_page_array(cache->pages, GFP_KERNEL);
+ if (!entry->page) {
ERROR("Failed to allocate %s cache entry\n", name);
goto cleanup;
}
-
- for (j = 0; j < cache->pages; j++) {
- entry->data[j] = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (entry->data[j] == NULL) {
- ERROR("Failed to allocate %s buffer\n", name);
- goto cleanup;
- }
- }
-
- entry->actor = squashfs_page_actor_init(entry->data,
- cache->pages, 0);
+ entry->actor = squashfs_page_actor_init(entry->page,
+ cache->pages, 0, NULL);
if (entry->actor == NULL) {
ERROR("Failed to allocate %s cache entry\n", name);
goto cleanup;
@@ -314,18 +302,20 @@ int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry,
return min(length, entry->length - offset);
while (offset < entry->length) {
- void *buff = entry->data[offset / PAGE_SIZE]
- + (offset % PAGE_SIZE);
+ void *buff = kmap_atomic(entry->page[offset / PAGE_SIZE])
+ + (offset % PAGE_SIZE);
int bytes = min_t(int, entry->length - offset,
PAGE_SIZE - (offset % PAGE_SIZE));
if (bytes >= remaining) {
memcpy(buffer, buff, remaining);
+ kunmap_atomic(buff);
remaining = 0;
break;
}
memcpy(buffer, buff, bytes);
+ kunmap_atomic(buff);
buffer += bytes;
remaining -= bytes;
offset += bytes;
@@ -416,43 +406,38 @@ struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb,
void *squashfs_read_table(struct super_block *sb, u64 block, int length)
{
int pages = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
- int i, res;
- void *table, *buffer, **data;
+ struct page **page;
+ void *buff;
+ int res;
struct squashfs_page_actor *actor;
- table = buffer = kmalloc(length, GFP_KERNEL);
- if (table == NULL)
+ page = alloc_page_array(pages, GFP_KERNEL);
+ if (!page)
return ERR_PTR(-ENOMEM);
- data = kcalloc(pages, sizeof(void *), GFP_KERNEL);
- if (data == NULL) {
+ actor = squashfs_page_actor_init(page, pages, length, NULL);
+ if (actor == NULL) {
res = -ENOMEM;
goto failed;
}
- actor = squashfs_page_actor_init(data, pages, length);
- if (actor == NULL) {
- res = -ENOMEM;
- goto failed2;
- }
-
- for (i = 0; i < pages; i++, buffer += PAGE_SIZE)
- data[i] = buffer;
-
res = squashfs_read_data(sb, block, length |
SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor);
- kfree(data);
- kfree(actor);
-
if (res < 0)
- goto failed;
+ goto failed2;
- return table;
+ buff = kmalloc(length, GFP_KERNEL);
+ if (!buff)
+ goto failed2;
+ squashfs_actor_to_buf(actor, buff, length);
+ squashfs_page_actor_free(actor, 0);
+ free_page_array(page, pages);
+ return buff;
failed2:
- kfree(data);
+ squashfs_page_actor_free(actor, 0);
failed:
- kfree(table);
+ free_page_array(page, pages);
return ERR_PTR(res);
}
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index d2bc136..7de35bf 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -24,7 +24,8 @@
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/slab.h>
-#include <linux/buffer_head.h>
+#include <linux/highmem.h>
+#include <linux/fs.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -94,40 +95,44 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
static void *get_comp_opts(struct super_block *sb, unsigned short flags)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- void *buffer = NULL, *comp_opts;
+ void *comp_opts, *buffer = NULL;
+ struct page *page;
struct squashfs_page_actor *actor = NULL;
int length = 0;
+ if (!SQUASHFS_COMP_OPTS(flags))
+ return squashfs_comp_opts(msblk, buffer, length);
+
/*
* Read decompressor specific options from file system if present
*/
- if (SQUASHFS_COMP_OPTS(flags)) {
- buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (buffer == NULL) {
- comp_opts = ERR_PTR(-ENOMEM);
- goto out;
- }
- actor = squashfs_page_actor_init(&buffer, 1, 0);
- if (actor == NULL) {
- comp_opts = ERR_PTR(-ENOMEM);
- goto out;
- }
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return ERR_PTR(-ENOMEM);
- length = squashfs_read_data(sb,
- sizeof(struct squashfs_super_block), 0, NULL, actor);
-
- if (length < 0) {
- comp_opts = ERR_PTR(length);
- goto out;
- }
+ actor = squashfs_page_actor_init(&page, 1, 0, NULL);
+ if (actor == NULL) {
+ comp_opts = ERR_PTR(-ENOMEM);
+ goto actor_error;
}
- comp_opts = squashfs_comp_opts(msblk, buffer, length);
+ length = squashfs_read_data(sb,
+ sizeof(struct squashfs_super_block), 0, NULL, actor);
-out:
- kfree(actor);
- kfree(buffer);
+ if (length < 0) {
+ comp_opts = ERR_PTR(length);
+ goto read_error;
+ }
+
+ buffer = kmap_atomic(page);
+ comp_opts = squashfs_comp_opts(msblk, buffer, length);
+ kunmap_atomic(buffer);
+
+read_error:
+ squashfs_page_actor_free(actor, 0);
+actor_error:
+ __free_page(page);
return comp_opts;
}
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 13d8094..bb2e77e 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -47,6 +47,7 @@
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/mutex.h>
+#include <linux/mm_inline.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -438,6 +439,21 @@ static int squashfs_readpage_fragment(struct page *page)
return res;
}
+static int squashfs_readpages_fragment(struct page *page,
+ struct list_head *readahead_pages, struct address_space *mapping)
+{
+ if (!page) {
+ page = lru_to_page(readahead_pages);
+ list_del(&page->lru);
+ if (add_to_page_cache_lru(page, mapping, page->index,
+ mapping_gfp_constraint(mapping, GFP_KERNEL))) {
+ put_page(page);
+ return 0;
+ }
+ }
+ return squashfs_readpage_fragment(page);
+}
+
static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
{
struct inode *inode = page->mapping->host;
@@ -450,54 +466,105 @@ static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
return 0;
}
-static int squashfs_readpage(struct file *file, struct page *page)
+static int squashfs_readpages_sparse(struct page *page,
+ struct list_head *readahead_pages, int index, int file_end,
+ struct address_space *mapping)
{
- struct inode *inode = page->mapping->host;
+ if (!page) {
+ page = lru_to_page(readahead_pages);
+ list_del(&page->lru);
+ if (add_to_page_cache_lru(page, mapping, page->index,
+ mapping_gfp_constraint(mapping, GFP_KERNEL))) {
+ put_page(page);
+ return 0;
+ }
+ }
+ return squashfs_readpage_sparse(page, index, file_end);
+}
+
+static int __squashfs_readpages(struct file *file, struct page *page,
+ struct list_head *readahead_pages, unsigned int nr_pages,
+ struct address_space *mapping)
+{
+ struct inode *inode = mapping->host;
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
- int index = page->index >> (msblk->block_log - PAGE_SHIFT);
int file_end = i_size_read(inode) >> msblk->block_log;
int res;
- void *pageaddr;
+
+ do {
+ struct page *cur_page = page ? page
+ : lru_to_page(readahead_pages);
+ int page_index = cur_page->index;
+ int index = page_index >> (msblk->block_log - PAGE_SHIFT);
+
+ if (page_index >= ((i_size_read(inode) + PAGE_SIZE - 1) >>
+ PAGE_SHIFT))
+ return 1;
+
+ if (index < file_end || squashfs_i(inode)->fragment_block ==
+ SQUASHFS_INVALID_BLK) {
+ u64 block = 0;
+ int bsize = read_blocklist(inode, index, &block);
+
+ if (bsize < 0)
+ return -1;
+
+ if (bsize == 0) {
+ res = squashfs_readpages_sparse(page,
+ readahead_pages, index, file_end,
+ mapping);
+ } else {
+ res = squashfs_readpages_block(page,
+ readahead_pages, &nr_pages, mapping,
+ page_index, block, bsize);
+ }
+ } else {
+ res = squashfs_readpages_fragment(page,
+ readahead_pages, mapping);
+ }
+ if (res)
+ return 0;
+ page = NULL;
+ } while (readahead_pages && !list_empty(readahead_pages));
+
+ return 0;
+}
+
+static int squashfs_readpage(struct file *file, struct page *page)
+{
+ int ret;
TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
- page->index, squashfs_i(inode)->start);
+ page->index, squashfs_i(page->mapping->host)->start);
- if (page->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >>
- PAGE_SHIFT))
- goto out;
+ get_page(page);
- if (index < file_end || squashfs_i(inode)->fragment_block ==
- SQUASHFS_INVALID_BLK) {
- u64 block = 0;
- int bsize = read_blocklist(inode, index, &block);
- if (bsize < 0)
- goto error_out;
-
- if (bsize == 0)
- res = squashfs_readpage_sparse(page, index, file_end);
+ ret = __squashfs_readpages(file, page, NULL, 1, page->mapping);
+ if (ret) {
+ flush_dcache_page(page);
+ if (ret < 0)
+ SetPageError(page);
else
- res = squashfs_readpage_block(page, block, bsize);
- } else
- res = squashfs_readpage_fragment(page);
+ SetPageUptodate(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ unlock_page(page);
+ put_page(page);
+ }
- if (!res)
- return 0;
+ return 0;
+}
-error_out:
- SetPageError(page);
-out:
- pageaddr = kmap_atomic(page);
- memset(pageaddr, 0, PAGE_SIZE);
- kunmap_atomic(pageaddr);
- flush_dcache_page(page);
- if (!PageError(page))
- SetPageUptodate(page);
- unlock_page(page);
-
+static int squashfs_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned int nr_pages)
+{
+ TRACE("Entered squashfs_readpages, %u pages, first page index %lx\n",
+ nr_pages, lru_to_page(pages)->index);
+ __squashfs_readpages(file, NULL, pages, nr_pages, mapping);
return 0;
}
const struct address_space_operations squashfs_aops = {
- .readpage = squashfs_readpage
+ .readpage = squashfs_readpage,
+ .readpages = squashfs_readpages,
};
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
deleted file mode 100644
index f2310d2..0000000
--- a/fs/squashfs/file_cache.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright (c) 2013
- * Phillip Lougher <phillip@squashfs.org.uk>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- */
-
-#include <linux/fs.h>
-#include <linux/vfs.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/pagemap.h>
-#include <linux/mutex.h>
-
-#include "squashfs_fs.h"
-#include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
-#include "squashfs.h"
-
-/* Read separately compressed datablock and memcopy into page cache */
-int squashfs_readpage_block(struct page *page, u64 block, int bsize)
-{
- struct inode *i = page->mapping->host;
- struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
- block, bsize);
- int res = buffer->error;
-
- if (res)
- ERROR("Unable to read page, block %llx, size %x\n", block,
- bsize);
- else
- squashfs_copy_cache(page, buffer, buffer->length, 0);
-
- squashfs_cache_put(buffer);
- return res;
-}
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index cb485d8..dc87f77 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -13,6 +13,7 @@
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/mutex.h>
+#include <linux/mm_inline.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -20,157 +21,136 @@
#include "squashfs.h"
#include "page_actor.h"
-static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
- int pages, struct page **page);
-
-/* Read separately compressed datablock directly into page cache */
-int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
-
+static void release_actor_pages(struct page **page, int pages, int error)
{
- struct inode *inode = target_page->mapping->host;
- struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+ int i;
- int file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
- int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
- int start_index = target_page->index & ~mask;
- int end_index = start_index | mask;
- int i, n, pages, missing_pages, bytes, res = -ENOMEM;
+ for (i = 0; i < pages; i++) {
+ if (!page[i])
+ continue;
+ flush_dcache_page(page[i]);
+ if (!error)
+ SetPageUptodate(page[i]);
+ else {
+ SetPageError(page[i]);
+ zero_user_segment(page[i], 0, PAGE_SIZE);
+ }
+ unlock_page(page[i]);
+ put_page(page[i]);
+ }
+ kfree(page);
+}
+
+/*
+ * Create a "page actor" which will kmap and kunmap the
+ * page cache pages appropriately within the decompressor
+ */
+static struct squashfs_page_actor *actor_from_page_cache(
+ unsigned int actor_pages, struct page *target_page,
+ struct list_head *rpages, unsigned int *nr_pages, int start_index,
+ struct address_space *mapping)
+{
struct page **page;
struct squashfs_page_actor *actor;
- void *pageaddr;
+ int i, n;
+ gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
- if (end_index > file_end)
- end_index = file_end;
+ page = kmalloc_array(actor_pages, sizeof(void *), GFP_KERNEL);
+ if (!page)
+ return NULL;
- pages = end_index - start_index + 1;
+ for (i = 0, n = start_index; i < actor_pages; i++, n++) {
+ if (target_page == NULL && rpages && !list_empty(rpages)) {
+ struct page *cur_page = lru_to_page(rpages);
- page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL);
- if (page == NULL)
- return res;
+ if (cur_page->index < start_index + actor_pages) {
+ list_del(&cur_page->lru);
+ --(*nr_pages);
+ if (add_to_page_cache_lru(cur_page, mapping,
+ cur_page->index, gfp))
+ put_page(cur_page);
+ else
+ target_page = cur_page;
+ } else
+ rpages = NULL;
+ }
- /*
- * Create a "page actor" which will kmap and kunmap the
- * page cache pages appropriately within the decompressor
- */
- actor = squashfs_page_actor_init_special(page, pages, 0);
- if (actor == NULL)
- goto out;
-
- /* Try to grab all the pages covered by the Squashfs block */
- for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) {
- page[i] = (n == target_page->index) ? target_page :
- grab_cache_page_nowait(target_page->mapping, n);
-
- if (page[i] == NULL) {
- missing_pages++;
- continue;
+ if (target_page && target_page->index == n) {
+ page[i] = target_page;
+ target_page = NULL;
+ } else {
+ page[i] = grab_cache_page_nowait(mapping, n);
+ if (page[i] == NULL)
+ continue;
}
if (PageUptodate(page[i])) {
unlock_page(page[i]);
put_page(page[i]);
page[i] = NULL;
- missing_pages++;
}
}
- if (missing_pages) {
- /*
- * Couldn't get one or more pages, this page has either
- * been VM reclaimed, but others are still in the page cache
- * and uptodate, or we're racing with another thread in
- * squashfs_readpage also trying to grab them. Fall back to
- * using an intermediate buffer.
- */
- res = squashfs_read_cache(target_page, block, bsize, pages,
- page);
- if (res < 0)
- goto mark_errored;
-
- goto out;
+ actor = squashfs_page_actor_init(page, actor_pages, 0,
+ release_actor_pages);
+ if (!actor) {
+ release_actor_pages(page, actor_pages, -ENOMEM);
+ kfree(page);
+ return NULL;
}
-
- /* Decompress directly into the page cache buffers */
- res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
- if (res < 0)
- goto mark_errored;
-
- /* Last page may have trailing bytes not filled */
- bytes = res % PAGE_SIZE;
- if (bytes) {
- pageaddr = kmap_atomic(page[pages - 1]);
- memset(pageaddr + bytes, 0, PAGE_SIZE - bytes);
- kunmap_atomic(pageaddr);
- }
-
- /* Mark pages as uptodate, unlock and release */
- for (i = 0; i < pages; i++) {
- flush_dcache_page(page[i]);
- SetPageUptodate(page[i]);
- unlock_page(page[i]);
- if (page[i] != target_page)
- put_page(page[i]);
- }
-
- kfree(actor);
- kfree(page);
-
- return 0;
-
-mark_errored:
- /* Decompression failed, mark pages as errored. Target_page is
- * dealt with by the caller
- */
- for (i = 0; i < pages; i++) {
- if (page[i] == NULL || page[i] == target_page)
- continue;
- flush_dcache_page(page[i]);
- SetPageError(page[i]);
- unlock_page(page[i]);
- put_page(page[i]);
- }
-
-out:
- kfree(actor);
- kfree(page);
- return res;
+ return actor;
}
+int squashfs_readpages_block(struct page *target_page,
+ struct list_head *readahead_pages,
+ unsigned int *nr_pages,
+ struct address_space *mapping,
+ int page_index, u64 block, int bsize)
-static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
- int pages, struct page **page)
{
- struct inode *i = target_page->mapping->host;
- struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
- block, bsize);
- int bytes = buffer->length, res = buffer->error, n, offset = 0;
- void *pageaddr;
+ struct squashfs_page_actor *actor;
+ struct inode *inode = mapping->host;
+ struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+ int start_index, end_index, file_end, actor_pages, res;
+ int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
- if (res) {
- ERROR("Unable to read page, block %llx, size %x\n", block,
- bsize);
- goto out;
+ /*
+ * If readpage() is called on an uncompressed datablock, we can just
+ * read the pages instead of fetching the whole block.
+ * This greatly improves the performance when a process keep doing
+ * random reads because we only fetch the necessary data.
+ * The readahead algorithm will take care of doing speculative reads
+ * if necessary.
+ * We can't read more than 1 block even if readahead provides use more
+ * pages because we don't know yet if the next block is compressed or
+ * not.
+ */
+ if (bsize && !SQUASHFS_COMPRESSED_BLOCK(bsize)) {
+ u64 block_end = block + msblk->block_size;
+
+ block += (page_index & mask) * PAGE_SIZE;
+ actor_pages = (block_end - block) / PAGE_SIZE;
+ if (*nr_pages < actor_pages)
+ actor_pages = *nr_pages;
+ start_index = page_index;
+ bsize = min_t(int, bsize, (PAGE_SIZE * actor_pages)
+ | SQUASHFS_COMPRESSED_BIT_BLOCK);
+ } else {
+ file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+ start_index = page_index & ~mask;
+ end_index = start_index | mask;
+ if (end_index > file_end)
+ end_index = file_end;
+ actor_pages = end_index - start_index + 1;
}
- for (n = 0; n < pages && bytes > 0; n++,
- bytes -= PAGE_SIZE, offset += PAGE_SIZE) {
- int avail = min_t(int, bytes, PAGE_SIZE);
+ actor = actor_from_page_cache(actor_pages, target_page,
+ readahead_pages, nr_pages, start_index,
+ mapping);
+ if (!actor)
+ return -ENOMEM;
- if (page[n] == NULL)
- continue;
-
- pageaddr = kmap_atomic(page[n]);
- squashfs_copy_data(pageaddr, buffer, offset, avail);
- memset(pageaddr + avail, 0, PAGE_SIZE - avail);
- kunmap_atomic(pageaddr);
- flush_dcache_page(page[n]);
- SetPageUptodate(page[n]);
- unlock_page(page[n]);
- if (page[n] != target_page)
- put_page(page[n]);
- }
-
-out:
- squashfs_cache_put(buffer);
- return res;
+ res = squashfs_read_data_async(inode->i_sb, block, bsize, NULL,
+ actor);
+ return res < 0 ? res : 0;
}
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index ff4468b..df4fa3c 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -94,39 +94,17 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct buffer_head **bh, int b, int offset, int length,
struct squashfs_page_actor *output)
{
- struct squashfs_lz4 *stream = strm;
- void *buff = stream->input, *data;
- int avail, i, bytes = length, res;
+ int res;
size_t dest_len = output->length;
+ struct squashfs_lz4 *stream = strm;
- for (i = 0; i < b; i++) {
- avail = min(bytes, msblk->devblksize - offset);
- memcpy(buff, bh[i]->b_data + offset, avail);
- buff += avail;
- bytes -= avail;
- offset = 0;
- put_bh(bh[i]);
- }
-
+ squashfs_bh_to_buf(bh, b, stream->input, offset, length,
+ msblk->devblksize);
res = lz4_decompress_unknownoutputsize(stream->input, length,
stream->output, &dest_len);
if (res)
return -EIO;
-
- bytes = dest_len;
- data = squashfs_first_page(output);
- buff = stream->output;
- while (data) {
- if (bytes <= PAGE_SIZE) {
- memcpy(data, buff, bytes);
- break;
- }
- memcpy(data, buff, PAGE_SIZE);
- buff += PAGE_SIZE;
- bytes -= PAGE_SIZE;
- data = squashfs_next_page(output);
- }
- squashfs_finish_page(output);
+ squashfs_buf_to_actor(stream->output, output, dest_len);
return dest_len;
}
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 934c17e..2c844d5 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -79,45 +79,19 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct buffer_head **bh, int b, int offset, int length,
struct squashfs_page_actor *output)
{
- struct squashfs_lzo *stream = strm;
- void *buff = stream->input, *data;
- int avail, i, bytes = length, res;
+ int res;
size_t out_len = output->length;
+ struct squashfs_lzo *stream = strm;
- for (i = 0; i < b; i++) {
- avail = min(bytes, msblk->devblksize - offset);
- memcpy(buff, bh[i]->b_data + offset, avail);
- buff += avail;
- bytes -= avail;
- offset = 0;
- put_bh(bh[i]);
- }
-
+ squashfs_bh_to_buf(bh, b, stream->input, offset, length,
+ msblk->devblksize);
res = lzo1x_decompress_safe(stream->input, (size_t)length,
stream->output, &out_len);
if (res != LZO_E_OK)
- goto failed;
+ return -EIO;
+ squashfs_buf_to_actor(stream->output, output, out_len);
- res = bytes = (int)out_len;
- data = squashfs_first_page(output);
- buff = stream->output;
- while (data) {
- if (bytes <= PAGE_SIZE) {
- memcpy(data, buff, bytes);
- break;
- } else {
- memcpy(data, buff, PAGE_SIZE);
- buff += PAGE_SIZE;
- bytes -= PAGE_SIZE;
- data = squashfs_next_page(output);
- }
- }
- squashfs_finish_page(output);
-
- return res;
-
-failed:
- return -EIO;
+ return out_len;
}
const struct squashfs_decompressor squashfs_lzo_comp_ops = {
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 9b7b1b6..e348f56 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -9,79 +9,11 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/buffer_head.h>
#include "page_actor.h"
-/*
- * This file contains implementations of page_actor for decompressing into
- * an intermediate buffer, and for decompressing directly into the
- * page cache.
- *
- * Calling code should avoid sleeping between calls to squashfs_first_page()
- * and squashfs_finish_page().
- */
-
-/* Implementation of page_actor for decompressing into intermediate buffer */
-static void *cache_first_page(struct squashfs_page_actor *actor)
-{
- actor->next_page = 1;
- return actor->buffer[0];
-}
-
-static void *cache_next_page(struct squashfs_page_actor *actor)
-{
- if (actor->next_page == actor->pages)
- return NULL;
-
- return actor->buffer[actor->next_page++];
-}
-
-static void cache_finish_page(struct squashfs_page_actor *actor)
-{
- /* empty */
-}
-
-struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
- int pages, int length)
-{
- struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
-
- if (actor == NULL)
- return NULL;
-
- actor->length = length ? : pages * PAGE_SIZE;
- actor->buffer = buffer;
- actor->pages = pages;
- actor->next_page = 0;
- actor->squashfs_first_page = cache_first_page;
- actor->squashfs_next_page = cache_next_page;
- actor->squashfs_finish_page = cache_finish_page;
- return actor;
-}
-
-/* Implementation of page_actor for decompressing directly into page cache. */
-static void *direct_first_page(struct squashfs_page_actor *actor)
-{
- actor->next_page = 1;
- return actor->pageaddr = kmap_atomic(actor->page[0]);
-}
-
-static void *direct_next_page(struct squashfs_page_actor *actor)
-{
- if (actor->pageaddr)
- kunmap_atomic(actor->pageaddr);
-
- return actor->pageaddr = actor->next_page == actor->pages ? NULL :
- kmap_atomic(actor->page[actor->next_page++]);
-}
-
-static void direct_finish_page(struct squashfs_page_actor *actor)
-{
- if (actor->pageaddr)
- kunmap_atomic(actor->pageaddr);
-}
-
-struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
- int pages, int length)
+struct squashfs_page_actor *squashfs_page_actor_init(struct page **page,
+ int pages, int length, void (*release_pages)(struct page **, int, int))
{
struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
@@ -93,8 +25,129 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
actor->pages = pages;
actor->next_page = 0;
actor->pageaddr = NULL;
- actor->squashfs_first_page = direct_first_page;
- actor->squashfs_next_page = direct_next_page;
- actor->squashfs_finish_page = direct_finish_page;
+ actor->release_pages = release_pages;
return actor;
}
+
+void squashfs_page_actor_free(struct squashfs_page_actor *actor, int error)
+{
+ if (!actor)
+ return;
+
+ if (actor->release_pages)
+ actor->release_pages(actor->page, actor->pages, error);
+ kfree(actor);
+}
+
+void squashfs_actor_to_buf(struct squashfs_page_actor *actor, void *buf,
+ int length)
+{
+ void *pageaddr;
+ int pos = 0, avail, i;
+
+ for (i = 0; i < actor->pages && pos < length; ++i) {
+ avail = min_t(int, length - pos, PAGE_SIZE);
+ if (actor->page[i]) {
+ pageaddr = kmap_atomic(actor->page[i]);
+ memcpy(buf + pos, pageaddr, avail);
+ kunmap_atomic(pageaddr);
+ }
+ pos += avail;
+ }
+}
+
+void squashfs_buf_to_actor(void *buf, struct squashfs_page_actor *actor,
+ int length)
+{
+ void *pageaddr;
+ int pos = 0, avail, i;
+
+ for (i = 0; i < actor->pages && pos < length; ++i) {
+ avail = min_t(int, length - pos, PAGE_SIZE);
+ if (actor->page[i]) {
+ pageaddr = kmap_atomic(actor->page[i]);
+ memcpy(pageaddr, buf + pos, avail);
+ kunmap_atomic(pageaddr);
+ }
+ pos += avail;
+ }
+}
+
+void squashfs_bh_to_actor(struct buffer_head **bh, int nr_buffers,
+ struct squashfs_page_actor *actor, int offset, int length, int blksz)
+{
+ void *kaddr = NULL;
+ int bytes = 0, pgoff = 0, b = 0, p = 0, avail, i;
+
+ while (bytes < length) {
+ if (actor->page[p]) {
+ kaddr = kmap_atomic(actor->page[p]);
+ while (pgoff < PAGE_SIZE && bytes < length) {
+ avail = min_t(int, blksz - offset,
+ PAGE_SIZE - pgoff);
+ memcpy(kaddr + pgoff, bh[b]->b_data + offset,
+ avail);
+ pgoff += avail;
+ bytes += avail;
+ offset = (offset + avail) % blksz;
+ if (!offset) {
+ put_bh(bh[b]);
+ ++b;
+ }
+ }
+ kunmap_atomic(kaddr);
+ pgoff = 0;
+ } else {
+ for (i = 0; i < PAGE_SIZE / blksz; ++i) {
+ if (bh[b])
+ put_bh(bh[b]);
+ ++b;
+ }
+ bytes += PAGE_SIZE;
+ }
+ ++p;
+ }
+}
+
+void squashfs_bh_to_buf(struct buffer_head **bh, int nr_buffers, void *buf,
+ int offset, int length, int blksz)
+{
+ int i, avail, bytes = 0;
+
+ for (i = 0; i < nr_buffers && bytes < length; ++i) {
+ avail = min_t(int, length - bytes, blksz - offset);
+ if (bh[i]) {
+ memcpy(buf + bytes, bh[i]->b_data + offset, avail);
+ put_bh(bh[i]);
+ }
+ bytes += avail;
+ offset = 0;
+ }
+}
+
+void free_page_array(struct page **page, int nr_pages)
+{
+ int i;
+
+ for (i = 0; i < nr_pages; ++i)
+ __free_page(page[i]);
+ kfree(page);
+}
+
+struct page **alloc_page_array(int nr_pages, int gfp_mask)
+{
+ int i;
+ struct page **page;
+
+ page = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
+ if (!page)
+ return NULL;
+ for (i = 0; i < nr_pages; ++i) {
+ page[i] = alloc_page(gfp_mask);
+ if (!page[i]) {
+ free_page_array(page, i);
+ return NULL;
+ }
+ }
+ return page;
+}
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 98537ea..aa1ed79 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -5,77 +5,61 @@
* Phillip Lougher <phillip@squashfs.org.uk>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
+ * the COPYING file in the top-level squashfsory.
*/
-#ifndef CONFIG_SQUASHFS_FILE_DIRECT
struct squashfs_page_actor {
- void **page;
+ struct page **page;
+ void *pageaddr;
int pages;
int length;
int next_page;
+ void (*release_pages)(struct page **, int, int);
};
-static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
- int pages, int length)
-{
- struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+extern struct squashfs_page_actor *squashfs_page_actor_init(struct page **,
+ int, int, void (*)(struct page **, int, int));
+extern void squashfs_page_actor_free(struct squashfs_page_actor *, int);
- if (actor == NULL)
- return NULL;
+extern void squashfs_actor_to_buf(struct squashfs_page_actor *, void *, int);
+extern void squashfs_buf_to_actor(void *, struct squashfs_page_actor *, int);
+extern void squashfs_bh_to_actor(struct buffer_head **, int,
+ struct squashfs_page_actor *, int, int, int);
+extern void squashfs_bh_to_buf(struct buffer_head **, int, void *, int, int,
+ int);
- actor->length = length ? : pages * PAGE_SIZE;
- actor->page = page;
- actor->pages = pages;
- actor->next_page = 0;
- return actor;
-}
-
+/*
+ * Calling code should avoid sleeping between calls to squashfs_first_page()
+ * and squashfs_finish_page().
+ */
static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
{
actor->next_page = 1;
- return actor->page[0];
+ return actor->pageaddr = actor->page[0] ? kmap_atomic(actor->page[0])
+ : NULL;
}
static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
{
- return actor->next_page == actor->pages ? NULL :
- actor->page[actor->next_page++];
+ if (!IS_ERR_OR_NULL(actor->pageaddr))
+ kunmap_atomic(actor->pageaddr);
+
+ if (actor->next_page == actor->pages)
+ return actor->pageaddr = ERR_PTR(-ENODATA);
+
+ actor->pageaddr = actor->page[actor->next_page] ?
+ kmap_atomic(actor->page[actor->next_page]) : NULL;
+ ++actor->next_page;
+ return actor->pageaddr;
}
static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
{
- /* empty */
+ if (!IS_ERR_OR_NULL(actor->pageaddr))
+ kunmap_atomic(actor->pageaddr);
}
-#else
-struct squashfs_page_actor {
- union {
- void **buffer;
- struct page **page;
- };
- void *pageaddr;
- void *(*squashfs_first_page)(struct squashfs_page_actor *);
- void *(*squashfs_next_page)(struct squashfs_page_actor *);
- void (*squashfs_finish_page)(struct squashfs_page_actor *);
- int pages;
- int length;
- int next_page;
-};
-extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int);
-extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page
- **, int, int);
-static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
-{
- return actor->squashfs_first_page(actor);
-}
-static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
-{
- return actor->squashfs_next_page(actor);
-}
-static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
-{
- actor->squashfs_finish_page(actor);
-}
-#endif
+extern struct page **alloc_page_array(int, int);
+extern void free_page_array(struct page **, int);
+
#endif
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 887d6d2..f4faab5 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -28,8 +28,12 @@
#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args)
/* block.c */
+extern int squashfs_init_read_wq(void);
+extern void squashfs_destroy_read_wq(void);
extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
struct squashfs_page_actor *);
+extern int squashfs_read_data_async(struct super_block *, u64, int, u64 *,
+ struct squashfs_page_actor *);
/* cache.c */
extern struct squashfs_cache *squashfs_cache_init(char *, int, int);
@@ -70,8 +74,9 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
int);
-/* file_xxx.c */
-extern int squashfs_readpage_block(struct page *, u64, int);
+/* file_direct.c */
+extern int squashfs_readpages_block(struct page *, struct list_head *,
+ unsigned int *, struct address_space *, int, u64, int);
/* id.c */
extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h
index 1da565c..8a6995d 100644
--- a/fs/squashfs/squashfs_fs_sb.h
+++ b/fs/squashfs/squashfs_fs_sb.h
@@ -49,7 +49,7 @@ struct squashfs_cache_entry {
int num_waiters;
wait_queue_head_t wait_queue;
struct squashfs_cache *cache;
- void **data;
+ struct page **page;
struct squashfs_page_actor *actor;
};
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index cf01e15..e2a0a73 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -444,9 +444,15 @@ static int __init init_squashfs_fs(void)
if (err)
return err;
+ if (!squashfs_init_read_wq()) {
+ destroy_inodecache();
+ return -ENOMEM;
+ }
+
err = register_filesystem(&squashfs_fs_type);
if (err) {
destroy_inodecache();
+ squashfs_destroy_read_wq();
return err;
}
@@ -460,6 +466,7 @@ static void __exit exit_squashfs_fs(void)
{
unregister_filesystem(&squashfs_fs_type);
destroy_inodecache();
+ squashfs_destroy_read_wq();
}
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 6bfaef7..2f7be1f 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -55,7 +55,7 @@ static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk,
struct comp_opts *opts;
int err = 0, n;
- opts = kmalloc(sizeof(*opts), GFP_KERNEL);
+ opts = kmalloc(sizeof(*opts), GFP_ATOMIC);
if (opts == NULL) {
err = -ENOMEM;
goto out2;
@@ -136,6 +136,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
enum xz_ret xz_err;
int avail, total = 0, k = 0;
struct squashfs_xz *stream = strm;
+ void *buf = NULL;
xz_dec_reset(stream->state);
stream->buf.in_pos = 0;
@@ -156,12 +157,20 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
if (stream->buf.out_pos == stream->buf.out_size) {
stream->buf.out = squashfs_next_page(output);
- if (stream->buf.out != NULL) {
+ if (!IS_ERR(stream->buf.out)) {
stream->buf.out_pos = 0;
total += PAGE_SIZE;
}
}
+ if (!stream->buf.out) {
+ if (!buf) {
+ buf = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+ if (!buf)
+ goto out;
+ }
+ stream->buf.out = buf;
+ }
xz_err = xz_dec_run(stream->state, &stream->buf);
if (stream->buf.in_pos == stream->buf.in_size && k < b)
@@ -173,11 +182,13 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
if (xz_err != XZ_STREAM_END || k < b)
goto out;
+ kfree(buf);
return total + stream->buf.out_pos;
out:
for (; k < b; k++)
put_bh(bh[k]);
+ kfree(buf);
return -EIO;
}
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 2ec24d1..d917c72 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -66,6 +66,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct buffer_head **bh, int b, int offset, int length,
struct squashfs_page_actor *output)
{
+ void *buf = NULL;
int zlib_err, zlib_init = 0, k = 0;
z_stream *stream = strm;
@@ -84,10 +85,19 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
if (stream->avail_out == 0) {
stream->next_out = squashfs_next_page(output);
- if (stream->next_out != NULL)
+ if (!IS_ERR(stream->next_out))
stream->avail_out = PAGE_SIZE;
}
+ if (!stream->next_out) {
+ if (!buf) {
+ buf = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+ if (!buf)
+ goto out;
+ }
+ stream->next_out = buf;
+ }
+
if (!zlib_init) {
zlib_err = zlib_inflateInit(stream);
if (zlib_err != Z_OK) {
@@ -115,11 +125,13 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
if (k < b)
goto out;
+ kfree(buf);
return stream->total_out;
out:
for (; k < b; k++)
put_bh(bh[k]);
+ kfree(buf);
return -EIO;
}
diff --git a/fs/super.c b/fs/super.c
index 1058bf3..2987fe3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -757,7 +757,8 @@ 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
@@ -765,7 +766,7 @@ 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;
@@ -807,7 +808,16 @@ 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)
@@ -839,12 +849,17 @@ 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++;
@@ -1164,7 +1179,7 @@ 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;
@@ -1181,7 +1196,10 @@ 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 784d667..9d9c032 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -493,7 +493,8 @@ 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
@@ -872,7 +873,8 @@ 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;
@@ -1009,7 +1011,8 @@ 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 932b906..1b00bab 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 2e6000a..3a396a9 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -499,25 +499,17 @@
*(.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)
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 c56fef4..e098cbe 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/blkdev.h b/include/linux/blkdev.h
index f6a8161..fe8dd27 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)
@@ -1700,6 +1703,62 @@ 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..ace92fc
--- /dev/null
+++ b/include/linux/bpf-cgroup.h
@@ -0,0 +1,77 @@
+#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 cgroup_bpf {
+ /*
+ * Store two sets of bpf_prog pointers, one for programs that are
+ * pinned directly to this cgroup, and one for those that are effective
+ * when this cgroup is accessed.
+ */
+ struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
+ struct bpf_prog *effective[MAX_BPF_ATTACH_TYPE];
+ bool disallow_override[MAX_BPF_ATTACH_TYPE];
+};
+
+void cgroup_bpf_put(struct cgroup *cgrp);
+void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
+
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+ struct bpf_prog *prog, enum bpf_attach_type type,
+ bool overridable);
+
+/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, bool overridable);
+
+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 void cgroup_bpf_inherit(struct cgroup *cgrp,
+ struct cgroup *parent) {}
+
+#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..193c40e 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;
@@ -241,6 +247,9 @@ 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 +267,11 @@ 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 +286,8 @@ 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
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 6fb1c34..080dd59 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -16,6 +16,7 @@
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
+#include <linux/bpf-cgroup.h>
#ifdef CONFIG_CGROUPS
@@ -301,6 +302,9 @@ struct cgroup {
/* used to schedule release agent */
struct work_struct release_agent_work;
+ /* used to store eBPF programs */
+ struct cgroup_bpf bpf;
+
/* ids of the ancestors at each level including self */
int ancestor_ids[];
};
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-gcc.h b/include/linux/compiler-gcc.h
index eb0ed31..3a8c897 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,18 +66,22 @@
/*
* Force always-inline if the user requests it so via the .config,
- * or if gcc is too old:
+ * or if gcc is too old.
+ * GCC does not warn about unused static inline functions for
+ * -Wunused-function. This turns out to avoid the need for complex #ifdef
+ * directives. Suppress the warning in clang as well by using "unused"
+ * function attribute, which is redundant but not harmful for gcc.
*/
#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
!defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline inline __attribute__((always_inline)) notrace
-#define __inline__ __inline__ __attribute__((always_inline)) notrace
-#define __inline __inline __attribute__((always_inline)) notrace
+#define inline inline __attribute__((always_inline,unused)) notrace
+#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace
+#define __inline __inline __attribute__((always_inline,unused)) notrace
#else
/* A lot of inline functions can cause havoc with function tracing */
-#define inline inline notrace
-#define __inline__ __inline__ notrace
-#define __inline __inline notrace
+#define inline inline __attribute__((unused)) notrace
+#define __inline__ __inline__ __attribute__((unused)) notrace
+#define __inline __inline __attribute__((unused)) notrace
#endif
#define __always_inline inline __attribute__((always_inline))
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 2f475ad..b86c3fb 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -253,4 +253,11 @@ void cpuhp_report_idle_dead(void);
static inline void cpuhp_report_idle_dead(void) { }
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+#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 32dc0cbd..0b98599 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);
@@ -359,6 +368,14 @@ 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);
@@ -553,6 +570,32 @@ 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 *
@@ -886,4 +929,8 @@ 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(int cpu);
#endif /* _LINUX_CPUFREQ_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 7cee555..0a72625 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
@@ -465,6 +466,45 @@ 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 ff295e1..3d4a198 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/device-mapper.h b/include/linux/device-mapper.h
index ef7962e..cf86f52 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/efi.h b/include/linux/efi.h
index cba7177..5e204a5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1427,7 +1427,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
unsigned long *load_addr,
unsigned long *load_size);
-efi_status_t efi_parse_options(char *cmdline);
+efi_status_t efi_parse_options(char const *cmdline);
efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg,
struct screen_info *si, efi_guid_t *proto,
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index e46e7d1..43e98d3 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -32,9 +32,17 @@
/* 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 << (sbi)->write_io_size_bits) /* Blocks */
+#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */
+#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */
+#define F2FS_IO_SIZE_BITS(sbi) ((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)
@@ -52,10 +60,17 @@
#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 */
@@ -94,12 +109,16 @@ struct f2fs_super_block {
__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 reserved[315]; /* valid reserved region */
} __packed;
/*
* For checkpoint
*/
+#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 +165,7 @@ 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 {
@@ -168,8 +187,11 @@ struct f2fs_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 +211,7 @@ 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 */
struct f2fs_inode {
__le16 i_mode; /* file mode */
@@ -219,8 +239,16 @@ 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 */
+ __le32 i_extra_end[0]; /* for attribute size calculation */
+ };
+ __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;
@@ -264,6 +292,7 @@ struct f2fs_node {
* For NAT entries
*/
#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8)
struct f2fs_nat_entry {
__u8 version; /* latest version of cached nat entry */
@@ -439,7 +468,7 @@ 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
@@ -448,7 +477,7 @@ typedef __le32 f2fs_hash_t;
#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
/*
- * space utilization of regular dentry and inline dentry
+ * space utilization of regular dentry and inline dentry (w/o extra reservation)
* regular dentry inline dentry
* bitmap 1 * 27 = 27 1 * 23 = 23
* reserved 1 * 3 = 3 1 * 7 = 7
@@ -484,24 +513,6 @@ 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 +528,6 @@ 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/fs.h b/include/linux/fs.h
index d705ae0..cbcdcb2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1608,13 +1608,21 @@ 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 *);
/*
@@ -1742,6 +1750,7 @@ 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);
@@ -1756,6 +1765,7 @@ 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,
@@ -1804,9 +1814,13 @@ 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 *);
@@ -1843,6 +1857,7 @@ 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
@@ -1881,6 +1896,7 @@ 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)
@@ -2040,6 +2056,9 @@ 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;
@@ -2338,6 +2357,8 @@ 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,
@@ -2580,8 +2601,11 @@ 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..8641e56
--- /dev/null
+++ b/include/linux/fscrypt.h
@@ -0,0 +1,290 @@
+/*
+ * 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/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_CRYPTO_BLOCK_SIZE 16
+
+struct fscrypt_info;
+
+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 */
+};
+
+/**
+ * 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;
+
+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)
+
+/*
+ * fscrypt superblock flags
+ */
+#define FS_CFLG_OWN_PAGES (1U << 1)
+
+/*
+ * crypto opertions 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 (*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_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;
+
+ return false;
+}
+
+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;
+}
+
+#if __FS_HAS_ENCRYPTION
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+ return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
+}
+
+static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+{
+ return (inode->i_crypt_info != NULL);
+}
+
+#include <linux/fscrypt_supp.h>
+
+#else /* !__FS_HAS_ENCRYPTION */
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+}
+
+static inline bool fscrypt_has_encryption_key(const struct inode *inode)
+{
+ return 0;
+}
+
+#include <linux/fscrypt_notsupp.h>
+#endif /* __FS_HAS_ENCRYPTION */
+
+/**
+ * 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;
+}
+
+#endif /* _LINUX_FSCRYPT_H */
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
new file mode 100644
index 0000000..c4c6bf2
--- /dev/null
+++ b/include/linux/fscrypt_notsupp.h
@@ -0,0 +1,210 @@
+/*
+ * 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
+
+/* crypto.c */
+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 void fscrypt_restore_control_page(struct page *page)
+{
+ return;
+}
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+ return;
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+ 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,
+ struct fscrypt_info *ci)
+{
+ 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 u32 fscrypt_fname_encrypted_size(const struct inode *inode,
+ u32 ilen)
+{
+ /* never happens */
+ WARN_ON(1);
+ return 0;
+}
+
+static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
+ u32 ilen,
+ 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 int fscrypt_fname_usr_to_disk(struct inode *inode,
+ const struct qstr *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_pages(struct fscrypt_ctx *ctx,
+ struct bio *bio)
+{
+ return;
+}
+
+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;
+}
+
+#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..2db5e970
--- /dev/null
+++ b/include/linux/fscrypt_supp.h
@@ -0,0 +1,156 @@
+/*
+ * 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
+
+/* crypto.c */
+extern struct kmem_cache *fscrypt_info_cachep;
+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);
+extern void fscrypt_restore_control_page(struct page *);
+
+extern const struct dentry_operations fscrypt_d_ops;
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+ d_set_d_op(dentry, &fscrypt_d_ops);
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+ spin_unlock(&dentry->d_lock);
+}
+
+/* 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 *);
+
+static inline void fscrypt_free_filename(struct fscrypt_name *fname)
+{
+ kfree(fname->crypto_buf.name);
+}
+
+extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32);
+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 *);
+extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
+ 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_pages(struct fscrypt_ctx *, struct 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);
+
+#endif /* _LINUX_FSCRYPT_SUPP_H */
diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h
deleted file mode 100644
index f6dfc29..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_process_policy(struct file *, const struct fscrypt_policy *);
-extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *);
-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_process_policy(struct file *f,
- const struct fscrypt_policy *p)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_get_policy(struct inode *i,
- struct fscrypt_policy *p)
-{
- 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..f4c0d36 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -734,7 +734,8 @@ 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/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/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 ba7a9b0..325727a 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/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..11ff751 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;
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 820c0ad..b37afd1 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -30,16 +30,10 @@ 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);
@@ -52,7 +46,7 @@ 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);
@@ -81,6 +75,9 @@ 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) {}
@@ -98,7 +95,7 @@ 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/kbuild.h b/include/linux/kbuild.h
index 22a7219..4e80f3a 100644
--- a/include/linux/kbuild.h
+++ b/include/linux/kbuild.h
@@ -2,14 +2,14 @@
#define __LINUX_KBUILD_H
#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+ asm volatile("\n.ascii \"->" #sym " %0 " #val "\"" : : "i" (val))
-#define BLANK() asm volatile("\n->" : : )
+#define BLANK() asm volatile("\n.ascii \"->\"" : : )
#define OFFSET(sym, str, mem) \
DEFINE(sym, offsetof(struct str, mem))
#define COMMENT(x) \
- asm volatile("\n->#" x)
+ asm volatile("\n.ascii \"->#" x "\"")
#endif
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/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/keychord.h b/include/linux/keychord.h
new file mode 100644
index 0000000..08cf540
--- /dev/null
+++ b/include/linux/keychord.h
@@ -0,0 +1,23 @@
+/*
+ * Key chord input driver
+ *
+ * Copyright (C) 2008 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_KEYCHORD_H_
+#define __LINUX_KEYCHORD_H_
+
+#include <uapi/linux/keychord.h>
+
+#endif /* __LINUX_KEYCHORD_H_ */
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/llist.h b/include/linux/llist.h
index fd4ca0b..ac67961 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -88,6 +88,23 @@ static inline void init_llist_head(struct llist_head *list)
container_of(ptr, type, member)
/**
+ * member_address_is_nonnull - check whether the member address is not NULL
+ * @ptr: the object pointer (struct type * that contains the llist_node)
+ * @member: the name of the llist_node within the struct.
+ *
+ * This macro is conceptually the same as
+ * &ptr->member != NULL
+ * but it works around the fact that compilers can decide that taking a member
+ * address is never a NULL pointer.
+ *
+ * Real objects that start at a high address and have a member at NULL are
+ * unlikely to exist, but such pointers may be returned e.g. by the
+ * container_of() macro.
+ */
+#define member_address_is_nonnull(ptr, member) \
+ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0)
+
+/**
* llist_for_each - iterate over some deleted entries of a lock-less list
* @pos: the &struct llist_node to use as a loop cursor
* @node: the first entry of deleted list entries
@@ -121,7 +138,7 @@ static inline void init_llist_head(struct llist_head *list)
*/
#define llist_for_each_entry(pos, node, member) \
for ((pos) = llist_entry((node), typeof(*(pos)), member); \
- &(pos)->member != NULL; \
+ member_address_is_nonnull(pos, member); \
(pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
/**
@@ -143,7 +160,7 @@ static inline void init_llist_head(struct llist_head *list)
*/
#define llist_for_each_entry_safe(pos, n, node, member) \
for (pos = llist_entry((node), typeof(*pos), member); \
- &pos->member != NULL && \
+ member_address_is_nonnull(pos, member) && \
(n = llist_entry(pos->member.next, typeof(*n), member), true); \
pos = n)
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 2217e2f..67dffb8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -76,6 +76,10 @@ extern int mmap_rnd_compat_bits __read_mostly;
#define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x)))
#endif
+#ifndef lm_alias
+#define lm_alias(x) __va(__pa_symbol(x))
+#endif
+
/*
* To prevent common memory management code establishing
* a zero page mapping on a read fault.
@@ -1139,6 +1143,7 @@ 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);
@@ -1949,7 +1954,7 @@ 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 e8471c2..5942478 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -326,11 +326,18 @@ 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
@@ -620,4 +627,13 @@ 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/module.h b/include/linux/module.h
index d2224a0..fd9e121 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -127,13 +127,13 @@ extern void cleanup_module(void);
/* Each module must use one module_init(). */
#define module_init(initfn) \
- static inline initcall_t __inittest(void) \
+ static inline initcall_t __maybe_unused __inittest(void) \
{ return initfn; } \
int init_module(void) __attribute__((alias(#initfn)));
/* This is only required if you want to be unloadable. */
#define module_exit(exitfn) \
- static inline exitcall_t __exittest(void) \
+ static inline exitcall_t __maybe_unused __exittest(void) \
{ return exitfn; } \
void cleanup_module(void) __attribute__((alias(#exitfn)));
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/xt_qtaguid.h b/include/linux/netfilter/xt_qtaguid.h
new file mode 100644
index 0000000..1c67155
--- /dev/null
+++ b/include/linux/netfilter/xt_qtaguid.h
@@ -0,0 +1,14 @@
+#ifndef _XT_QTAGUID_MATCH_H
+#define _XT_QTAGUID_MATCH_H
+
+/* For now we just replace the xt_owner.
+ * FIXME: make iptables aware of qtaguid. */
+#include <linux/netfilter/xt_owner.h>
+
+#define XT_QTAGUID_UID XT_OWNER_UID
+#define XT_QTAGUID_GID XT_OWNER_GID
+#define XT_QTAGUID_SOCKET XT_OWNER_SOCKET
+#define xt_qtaguid_match_info xt_owner_match_info
+
+int qtaguid_untag(struct socket *sock, bool kernel);
+#endif /* _XT_QTAGUID_MATCH_H */
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/perf_event.h b/include/linux/perf_event.h
index 78ed810..61ab566 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1168,6 +1168,11 @@ 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/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 3965503..ecfb4cac 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/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/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/sched.h b/include/linux/sched.h
index a4d0afc..8d4ce3f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -173,6 +173,9 @@ 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);
+#ifdef CONFIG_CPU_QUIET
+extern u64 nr_running_integral(unsigned int cpu);
+#endif
extern void calc_global_load(unsigned long ticks);
@@ -315,6 +318,15 @@ 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>
/*
@@ -982,6 +994,14 @@ 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,
@@ -1045,6 +1065,7 @@ 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)
@@ -1077,8 +1098,57 @@ 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;
@@ -1147,6 +1217,8 @@ 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;
@@ -1184,6 +1256,8 @@ 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
@@ -1197,6 +1271,7 @@ 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;
@@ -1342,6 +1417,70 @@ 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
@@ -1515,6 +1654,16 @@ 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
@@ -3557,6 +3706,11 @@ 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)
{
@@ -3573,6 +3727,9 @@ 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/sysctl.h b/include/linux/sched/sysctl.h
index 22db1e6..da3a02d 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 3442014..1a94397 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 d971837..448321b 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -434,6 +434,7 @@ 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/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 f50b717c..fc11641 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -219,8 +219,9 @@ struct tcp_sock {
} rack;
u16 advmss; /* Advertised MSS */
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/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/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 4616a49..93f0253 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -581,6 +581,7 @@ 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/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/net/addrconf.h b/include/net/addrconf.h
index b8ee8a1..858f308 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -244,6 +244,8 @@ 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 456e4a6..8dbfdf7 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;
};
@@ -92,7 +98,8 @@ 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..6bbbca8 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
@@ -37,6 +38,7 @@ struct flowi_common {
#define FLOWI_FLAG_SKIP_NH_OIF 0x04
__u32 flowic_secid;
struct flowi_tunnel flowic_tun_key;
+ kuid_t flowic_uid;
};
union flowi_uli {
@@ -74,6 +76,7 @@ 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
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -93,7 +96,8 @@ 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 +108,7 @@ 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_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
@@ -131,6 +136,7 @@ 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
struct in6_addr daddr;
struct in6_addr saddr;
/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -176,6 +182,7 @@ 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
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 0464b20..a2f3a49 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -212,7 +212,11 @@ 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 0e3dcd5..573fd7f 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 2c43993..4341731 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/route.h b/include/net/route.h
index 0429d47..c0874c8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -153,7 +153,7 @@ 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);
@@ -269,7 +269,8 @@ 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 6d42ed8..badd144 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -419,6 +419,7 @@ 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;
@@ -1647,6 +1648,7 @@ 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);
}
@@ -1654,6 +1656,11 @@ 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 caf35e0..d082f11 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -271,6 +271,7 @@ extern int sysctl_tcp_autocorking;
extern int sysctl_tcp_invalid_ratelimit;
extern int sysctl_tcp_pacing_ss_ratio;
extern int sysctl_tcp_pacing_ca_ratio;
+extern int sysctl_tcp_default_init_rwnd;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -1506,6 +1507,9 @@ 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
/* Fastopen key context */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 835c30e..9b6e6a4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -155,6 +155,7 @@ struct xfrm_state {
int header_len;
int trailer_len;
u32 extra_flags;
+ u32 output_mark;
} props;
struct xfrm_lifetime_cfg lft;
@@ -284,10 +285,12 @@ 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);
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..a45a727 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, \
@@ -109,12 +120,26 @@ 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" })
struct victim_sel_policy;
struct f2fs_map_blocks;
@@ -190,14 +215,14 @@ 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 +230,15 @@ 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 +262,7 @@ 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 +332,13 @@ 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),
@@ -516,14 +548,14 @@ TRACE_EVENT(f2fs_map_blocks,
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 +567,120 @@ 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 +696,7 @@ 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 +710,114 @@ 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 +943,7 @@ 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 +963,7 @@ 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 +975,18 @@ 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 +999,7 @@ 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 +1008,15 @@ 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 +1026,55 @@ 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 +1333,16 @@ 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 +1351,85 @@ 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 +1542,7 @@ 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 +1589,7 @@ 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)
);
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/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..f5024c5
--- /dev/null
+++ b/include/trace/events/preemptirq.h
@@ -0,0 +1,70 @@
+#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>
+
+#else /* !CONFIG_PREEMPTIRQ_EVENTS */
+
+#define trace_irq_enable(...)
+#define trace_irq_disable(...)
+#define trace_preempt_enable(...)
+#define trace_preempt_disable(...)
+#define trace_irq_enable_rcuidle(...)
+#define trace_irq_disable_rcuidle(...)
+#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..f0517de 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 +586,578 @@ 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( unsigned long, 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 = (((unsigned long)((struct ravg*)_ravg)->demand) << SCHED_CAPACITY_SHIFT);
+ do_div(__entry->util_avg_walt, walt_ravg_window);
+ 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=%lu 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( unsigned long, 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 =
+ cpu_rq(cpu)->prev_runnable_sum << SCHED_CAPACITY_SHIFT;
+ do_div(__entry->util_avg_walt, walt_ravg_window);
+ 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=%lu",
+ __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 accounting sched group energy
+ */
+TRACE_EVENT(sched_energy_diff,
+
+ TP_PROTO(struct task_struct *tsk, int scpu, int dcpu, int udelta,
+ int nrgb, int nrga, int nrgd, int capb, int capa, int capd,
+ int nrgn, int nrgp),
+
+ TP_ARGS(tsk, scpu, dcpu, udelta,
+ nrgb, nrga, nrgd, capb, capa, capd,
+ nrgn, nrgp),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, scpu )
+ __field( int, dcpu )
+ __field( int, udelta )
+ __field( int, nrgb )
+ __field( int, nrga )
+ __field( int, nrgd )
+ __field( int, capb )
+ __field( int, capa )
+ __field( int, capd )
+ __field( int, nrgn )
+ __field( int, nrgp )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->scpu = scpu;
+ __entry->dcpu = dcpu;
+ __entry->udelta = udelta;
+ __entry->nrgb = nrgb;
+ __entry->nrga = nrga;
+ __entry->nrgd = nrgd;
+ __entry->capb = capb;
+ __entry->capa = capa;
+ __entry->capd = capd;
+ __entry->nrgn = nrgn;
+ __entry->nrgp = nrgp;
+ ),
+
+ TP_printk("pid=%d comm=%s "
+ "src_cpu=%d dst_cpu=%d usage_delta=%d "
+ "nrg_before=%d nrg_after=%d nrg_diff=%d "
+ "cap_before=%d cap_after=%d cap_delta=%d "
+ "nrg_delta=%d nrg_payoff=%d",
+ __entry->pid, __entry->comm,
+ __entry->scpu, __entry->dcpu, __entry->udelta,
+ __entry->nrgb, __entry->nrga, __entry->nrgd,
+ __entry->capb, __entry->capa, __entry->capd,
+ __entry->nrgn, __entry->nrgp)
+);
+
+/*
+ * 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(unsigned long, 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 %lu 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/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/linux/android/binder.h b/include/uapi/linux/android/binder.h
index 41420e3..5539933 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -33,11 +33,60 @@ 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,
};
#ifdef BINDER_IPC_32BIT
@@ -48,6 +97,14 @@ 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 +113,8 @@ 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 +126,86 @@ 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 +233,19 @@ 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;
+};
+
#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 +253,7 @@ 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)
/*
* NOTE: Two special error codes you should check for when calling
@@ -162,6 +312,11 @@ struct binder_transaction_data {
} data;
};
+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;
@@ -346,6 +501,12 @@ 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..a339bea 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 +98,23 @@ 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/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..7683188 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 +257,47 @@ 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_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
+#define FS_ENCRYPTION_MODE_AES_128_CBC 5
+#define FS_ENCRYPTION_MODE_AES_128_CTS 6
+
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 42fa977..0932378 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -375,6 +375,7 @@ 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_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/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/keychord.h b/include/uapi/linux/keychord.h
new file mode 100644
index 0000000..ea7cf4d
--- /dev/null
+++ b/include/uapi/linux/keychord.h
@@ -0,0 +1,52 @@
+/*
+ * Key chord input driver
+ *
+ * Copyright (C) 2008 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_KEYCHORD_H_
+#define _UAPI_LINUX_KEYCHORD_H_
+
+#include <linux/input.h>
+
+#define KEYCHORD_VERSION 1
+
+/*
+ * One or more input_keychord structs are written to /dev/keychord
+ * at once to specify the list of keychords to monitor.
+ * Reading /dev/keychord returns the id of a keychord when the
+ * keychord combination is pressed. A keychord is signalled when
+ * all of the keys in the keycode list are in the pressed state.
+ * The order in which the keys are pressed does not matter.
+ * The keychord will not be signalled if keys not in the keycode
+ * list are pressed.
+ * Keychords will not be signalled on key release events.
+ */
+struct input_keychord {
+ /* should be KEYCHORD_VERSION */
+ __u16 version;
+ /*
+ * client specified ID, returned from read()
+ * when this keychord is pressed.
+ */
+ __u16 id;
+
+ /* number of keycodes in this keychord */
+ __u16 count;
+
+ /* variable length array of keycodes */
+ __u16 keycodes[];
+};
+
+#endif /* _UAPI_LINUX_KEYCHORD_H_ */
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_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 a8d0759..96b269b 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -197,4 +197,7 @@ struct prctl_mm_map {
# define PR_CAP_AMBIENT_LOWER 3
# define PR_CAP_AMBIENT_CLEAR_ALL 4
+#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/sysctl.h b/include/uapi/linux/sysctl.h
index d2b1215..e13d480 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/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..7d75e56 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -303,6 +303,8 @@ 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_OUTPUT_MARK, /* __u32 */
__XFRMA_MAX
#define XFRMA_MAX (__XFRMA_MAX - 1)
diff --git a/init/Kconfig b/init/Kconfig
index b331fee..544d791 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
@@ -971,6 +980,82 @@
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
@@ -1154,6 +1239,19 @@
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
@@ -1163,6 +1261,10 @@
Say N.
+config SOCK_CGROUP_DATA
+ bool
+ default n
+
endif # CGROUPS
config CHECKPOINT_RESTORE
@@ -1248,6 +1350,43 @@
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
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/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/ipc/mqueue.c b/ipc/mqueue.c
index 28a142f..02fb438 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -745,7 +745,7 @@ 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);
@@ -761,7 +761,7 @@ 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());
}
@@ -794,7 +794,7 @@ 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;
@@ -865,7 +865,7 @@ 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);
@@ -877,7 +877,7 @@ 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/bpf/Makefile b/kernel/bpf/Makefile
index eed911d..b22256b 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,3 +5,4 @@
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 9a1e6ed..2eb9b7f 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;
@@ -53,7 +56,8 @@ 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..a44a7e4
--- /dev/null
+++ b/kernel/bpf/cgroup.c
@@ -0,0 +1,205 @@
+/*
+ * 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.prog); type++) {
+ struct bpf_prog *prog = cgrp->bpf.prog[type];
+
+ if (prog) {
+ bpf_prog_put(prog);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ }
+ }
+}
+
+/**
+ * cgroup_bpf_inherit() - inherit effective programs from parent
+ * @cgrp: the cgroup to modify
+ * @parent: the parent to inherit from
+ */
+void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
+{
+ unsigned int type;
+
+ for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) {
+ struct bpf_prog *e;
+
+ e = rcu_dereference_protected(parent->bpf.effective[type],
+ lockdep_is_held(&cgroup_mutex));
+ rcu_assign_pointer(cgrp->bpf.effective[type], e);
+ cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
+ }
+}
+
+/**
+ * __cgroup_bpf_update() - Update the pinned program of a cgroup, and
+ * propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @parent: The parent of @cgrp, or %NULL if @cgrp is the root
+ * @prog: A new program to pin
+ * @type: Type of pinning operation (ingress/egress)
+ *
+ * Each cgroup has a set of two pointers for bpf programs; one for eBPF
+ * programs it owns, and which is effective for execution.
+ *
+ * If @prog is not %NULL, this function attaches a new program to the cgroup
+ * and releases the one that is currently attached, if any. @prog is then made
+ * the effective program of type @type in that cgroup.
+ *
+ * If @prog is %NULL, the currently attached program of type @type is released,
+ * and the effective program of the parent cgroup (if any) is inherited to
+ * @cgrp.
+ *
+ * Then, the descendants of @cgrp are walked and the effective program for
+ * each of them is set to the effective program of @cgrp unless the
+ * descendant has its own program attached, in which case the subbranch is
+ * skipped. This ensures that delegated subcgroups with own programs are left
+ * untouched.
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+ struct bpf_prog *prog, enum bpf_attach_type type,
+ bool new_overridable)
+{
+ struct bpf_prog *old_prog, *effective = NULL;
+ struct cgroup_subsys_state *pos;
+ bool overridable = true;
+
+ if (parent) {
+ overridable = !parent->bpf.disallow_override[type];
+ effective = rcu_dereference_protected(parent->bpf.effective[type],
+ lockdep_is_held(&cgroup_mutex));
+ }
+
+ if (prog && effective && !overridable)
+ /* if parent has non-overridable prog attached, disallow
+ * attaching new programs to descendent cgroup
+ */
+ return -EPERM;
+
+ if (prog && effective && overridable != new_overridable)
+ /* if parent has overridable prog attached, only
+ * allow overridable programs in descendent cgroup
+ */
+ return -EPERM;
+
+ old_prog = cgrp->bpf.prog[type];
+
+ if (prog) {
+ overridable = new_overridable;
+ effective = prog;
+ if (old_prog &&
+ cgrp->bpf.disallow_override[type] == new_overridable)
+ /* disallow attaching non-overridable on top
+ * of existing overridable in this cgroup
+ * and vice versa
+ */
+ return -EPERM;
+ }
+
+ if (!prog && !old_prog)
+ /* report error when trying to detach and nothing is attached */
+ return -ENOENT;
+
+ cgrp->bpf.prog[type] = prog;
+
+ css_for_each_descendant_pre(pos, &cgrp->self) {
+ struct cgroup *desc = container_of(pos, struct cgroup, self);
+
+ /* skip the subtree if the descendant has its own program */
+ if (desc->bpf.prog[type] && desc != cgrp) {
+ pos = css_rightmost_descendant(pos);
+ } else {
+ rcu_assign_pointer(desc->bpf.effective[type],
+ effective);
+ desc->bpf.disallow_override[type] = !overridable;
+ }
+ }
+
+ if (prog)
+ static_branch_inc(&cgroup_bpf_enabled_key);
+
+ if (old_prog) {
+ bpf_prog_put(old_prog);
+ static_branch_dec(&cgroup_bpf_enabled_key);
+ }
+ return 0;
+}
+
+/**
+ * __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)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret = 0;
+
+ 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);
+
+ rcu_read_lock();
+
+ prog = rcu_dereference(cgrp->bpf.effective[type]);
+ if (prog) {
+ unsigned int offset = skb->data - skb_network_header(skb);
+ struct sock *save_sk = skb->sk;
+
+ skb->sk = sk;
+ __skb_push(skb, offset);
+ ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM;
+ __skb_pull(skb, offset);
+ skb->sk = save_sk;
+ }
+
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index ad2f0ed..27f4f2c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -14,6 +14,8 @@
#include <linux/jhash.h>
#include <linux/filter.h>
#include "percpu_freelist.h"
+#define HTAB_CREATE_FLAG_MASK \
+ (BPF_F_NO_PREALLOC | BPF_F_RDONLY | BPF_F_WRONLY)
struct bucket {
struct hlist_head head;
@@ -148,7 +150,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
int err, i;
u64 cost;
- 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..2d23c32 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;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index be85191..230aced 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 91a2d37..590ce0a 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;
+ }
+
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
@@ -607,6 +678,7 @@ 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);
}
@@ -625,12 +697,20 @@ 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);
}
@@ -722,7 +802,9 @@ 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 */
@@ -730,10 +812,14 @@ 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;
@@ -773,16 +859,18 @@ 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));
@@ -790,12 +878,93 @@ 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
+
+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_ALLOW_OVERRIDE)
+ 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_update(cgrp, prog, attr->attach_type,
+ attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+ 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)
+{
+ 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:
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
+ cgroup_put(cgrp);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_CGROUP_BPF */
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -837,6 +1006,10 @@ 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);
@@ -862,6 +1035,16 @@ 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/cgroup.c b/kernel/cgroup.c
index 4c23343..0feeaca 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2856,7 +2856,8 @@ 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)) {
@@ -5075,6 +5076,8 @@ 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);
@@ -5287,6 +5290,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
if (!cgroup_on_dfl(cgrp))
cgrp->subtree_control = cgroup_control(cgrp);
+ if (parent)
+ cgroup_bpf_inherit(cgrp, parent);
+
cgroup_propagate_control(cgrp);
return cgrp;
@@ -6502,6 +6508,20 @@ static __init int cgroup_namespaces_init(void)
}
subsys_initcall(cgroup_namespaces_init);
+#ifdef CONFIG_CGROUP_BPF
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, bool overridable)
+{
+ struct cgroup *parent = cgroup_parent(cgrp);
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
+ 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 802eb33..9c70769 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1156,6 +1156,7 @@ 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();
@@ -1173,6 +1174,12 @@ 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);
@@ -1935,3 +1942,23 @@ void __init boot_cpu_state_init(void)
{
per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
}
+
+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 77777d9..3990c1f 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;
-
+ 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/events/core.c b/kernel/events/core.c
index 13b9784..2cc5ed1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -389,8 +389,13 @@ 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 */
@@ -9634,6 +9639,9 @@ 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 3076f30..46a7c2b 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>
@@ -775,6 +777,9 @@ void __noreturn do_exit(long code)
}
exit_signals(tsk); /* sets PF_EXITING */
+
+ schedtune_exit_task(tsk);
+
/*
* Ensure that all new tsk->pi_lock acquisitions must observe
* PF_EXITING. Serializes against futex.c:attach_to_pi_owner().
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3cbb0c8..f4988f5 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);
@@ -124,6 +261,7 @@ 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);
}
@@ -142,7 +280,7 @@ 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;
@@ -171,6 +309,7 @@ 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;
@@ -206,7 +345,7 @@ 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:
/*
@@ -216,17 +355,25 @@ 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;
/* 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;
@@ -244,6 +391,7 @@ 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:
@@ -266,6 +414,7 @@ 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/power/Kconfig b/kernel/power/Kconfig
index e8517b6..f4330a2 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 9c5b231..20fc294 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 */
@@ -1870,6 +1874,10 @@ 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..c9dbe93 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,10 +18,12 @@
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
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bce3a7a..b9d5c0d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,6 +90,7 @@
#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);
@@ -156,6 +157,18 @@ int sysctl_sched_rt_runtime = 950000;
/* cpus with isolated domains */
cpumask_var_t cpu_isolated_map;
+struct rq *
+lock_rq_of(struct task_struct *p, struct rq_flags *flags)
+{
+ return task_rq_lock(p, flags);
+}
+
+void
+unlock_rq_of(struct rq *rq, struct task_struct *p, struct rq_flags *flags)
+{
+ task_rq_unlock(rq, p, flags);
+}
+
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
@@ -997,7 +1010,9 @@ 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);
@@ -1253,6 +1268,8 @@ 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);
@@ -1268,7 +1285,9 @@ 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);
@@ -2009,6 +2028,10 @@ 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
@@ -2082,14 +2105,24 @@ 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;
set_task_cpu(p, cpu);
}
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
@@ -2139,8 +2172,13 @@ 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))
+ if (!task_on_rq_queued(p)) {
+ u64 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);
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
ttwu_do_wakeup(rq, p, 0, cookie);
ttwu_stat(p, smp_processor_id(), 0);
@@ -2204,7 +2242,12 @@ 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;
@@ -2564,6 +2607,9 @@ 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
/*
@@ -2577,9 +2623,12 @@ 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);
@@ -2964,6 +3013,36 @@ 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();
@@ -3081,6 +3160,9 @@ 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);
@@ -3094,6 +3176,9 @@ 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
@@ -3337,6 +3422,7 @@ static void __sched notrace __schedule(bool preempt)
struct pin_cookie cookie;
struct rq *rq;
int cpu;
+ u64 wallclock;
cpu = smp_processor_id();
rq = cpu_rq(cpu);
@@ -3389,11 +3475,18 @@ static void __sched notrace __schedule(bool preempt)
update_rq_clock(rq);
next = pick_next_task(rq, prev, cookie);
+ 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;
@@ -3650,6 +3743,7 @@ 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
@@ -3746,6 +3840,8 @@ 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
@@ -4178,6 +4274,7 @@ 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
@@ -5663,9 +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;
}
@@ -5707,7 +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);
}
@@ -5760,8 +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 |
@@ -5771,7 +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;
}
@@ -5804,7 +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;
}
@@ -5902,6 +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:
@@ -6013,11 +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;
@@ -6038,6 +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);
}
/*
@@ -6219,6 +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
@@ -6347,6 +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()
*/
@@ -6462,6 +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:
@@ -6474,7 +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,
@@ -7032,7 +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);
@@ -7050,8 +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;
}
}
@@ -7071,10 +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);
}
@@ -7083,22 +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);
@@ -7441,6 +7629,9 @@ 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);
@@ -7617,6 +7808,7 @@ 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?
*
@@ -7656,11 +7848,17 @@ 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);
@@ -7718,6 +7916,14 @@ 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)
{
/*
@@ -7743,8 +7949,10 @@ 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;
@@ -8437,6 +8645,7 @@ 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..3edb2bb 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 +282,41 @@ 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)
{
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
@@ -248,8 +329,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
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 +342,7 @@ 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 +353,7 @@ 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 +365,18 @@ 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);
+
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 +393,21 @@ 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 +420,32 @@ 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 +454,42 @@ 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 +511,64 @@ 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 +594,30 @@ 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 +629,23 @@ 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 +656,25 @@ 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 +685,6 @@ 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 +694,10 @@ 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 +705,11 @@ 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 +721,7 @@ 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 +741,10 @@ 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 5ebee31..5e9422b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -8,7 +8,7 @@
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif
-
+#include "walt.h"
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -46,11 +46,18 @@ 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;
@@ -65,8 +72,16 @@ void irqtime_account_irq(struct task_struct *curr)
irqtime->hardirq_time += delta;
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
irqtime->softirq_time += delta;
+#ifdef CONFIG_SCHED_WALT
+ else
+ account = false;
+#endif
u64_stats_update_end(&irqtime->sync);
+#ifdef CONFIG_SCHED_WALT
+ if (account)
+ walt_account_irqtime(cpu, curr, delta, wallclock);
+#endif
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3042881..49815cc 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)
@@ -868,6 +870,7 @@ 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);
@@ -882,6 +885,7 @@ 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);
@@ -1554,7 +1558,9 @@ 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;
@@ -1642,7 +1648,9 @@ 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;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fa178b6..59e38cd 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), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[1], "idle_states", &sge->idle_states[0].power,
+ sge->nr_idle_states*sizeof(struct idle_state), 0644,
+ proc_doulongvec_minmax, false);
+ set_table_entry(&table[2], "nr_cap_states", &sge->nr_cap_states,
+ sizeof(int), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[3], "cap_states", &sge->cap_states[0].cap,
+ sge->nr_cap_states*sizeof(struct capacity_state), 0644,
+ 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 3d862f5..bae83f7 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
@@ -2645,16 +2694,20 @@ 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;
@@ -2663,8 +2716,9 @@ 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 */
@@ -2815,6 +2869,7 @@ __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;
@@ -2890,6 +2945,26 @@ __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
@@ -2969,8 +3044,168 @@ 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)
@@ -3041,6 +3276,7 @@ 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)) {
@@ -3048,6 +3284,7 @@ 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,
@@ -3061,27 +3298,51 @@ 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);
+ }
}
/**
@@ -3094,31 +3355,12 @@ 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);
}
@@ -3133,14 +3375,12 @@ 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);
}
@@ -3150,34 +3390,20 @@ 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 =
@@ -3206,13 +3432,25 @@ 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() ->
@@ -3224,9 +3462,7 @@ 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);
}
@@ -3251,7 +3487,10 @@ 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);
}
@@ -3396,9 +3635,18 @@ 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);
@@ -3470,6 +3718,16 @@ 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);
@@ -3493,7 +3751,7 @@ 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,
@@ -3557,7 +3815,7 @@ 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);
@@ -3675,8 +3933,8 @@ 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
/*
@@ -4527,6 +4785,14 @@ 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
@@ -4537,6 +4803,9 @@ 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
@@ -4561,6 +4830,7 @@ 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;
}
@@ -4568,17 +4838,49 @@ 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);
}
@@ -4608,6 +4910,7 @@ 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) {
@@ -4627,17 +4930,33 @@ 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);
}
@@ -4944,15 +5263,6 @@ 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)
{
@@ -5104,6 +5414,520 @@ 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;
+}
+
+static inline bool energy_aware(void)
+{
+ return sched_feat(ENERGY_AWARE);
+}
+
+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 trg_cpu;
+ int energy;
+ int payoff;
+ struct task_struct *task;
+ struct {
+ int before;
+ int after;
+ int delta;
+ int diff;
+ } nrg;
+ struct {
+ int before;
+ int after;
+ int delta;
+ } cap;
+};
+
+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)
+{
+ 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->task);
+
+ /*
+ * 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->trg_cpu))
+ util += eenv->util_delta;
+
+ max_util = max(max_util, util);
+ }
+
+ 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, struct sched_group *sg)
+{
+ unsigned long capacity = sg->sge->cap_states[eenv->cap_idx].cap;
+ unsigned long util, util_sum = 0;
+ int cpu;
+
+ for_each_cpu(cpu, sched_group_cpus(sg)) {
+ util = cpu_util_wake(cpu, eenv->task);
+
+ /*
+ * 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->trg_cpu))
+ 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,
+ const struct sched_group_energy * const sge)
+{
+ int idx, max_idx = sge->nr_cap_states - 1;
+ unsigned long util = group_max_util(eenv);
+
+ /* default is max_cap if we don't find a match */
+ eenv->cap_idx = max_idx;
+
+ for (idx = 0; idx < sge->nr_cap_states; idx++) {
+ if (sge->cap_states[idx].cap >= util) {
+ eenv->cap_idx = idx;
+ break;
+ }
+ }
+
+ return eenv->cap_idx;
+}
+
+static int group_idle_state(struct energy_env *eenv, struct sched_group *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++;
+
+ /*
+ * 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(i);
+
+ src_in_grp = cpumask_test_cpu(eenv->src_cpu, sched_group_cpus(sg));
+ dst_in_grp = cpumask_test_cpu(eenv->dst_cpu, 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;
+ }
+ /* add or remove util as appropriate to indicate what group util
+ * will be (worst case - no concurrent execution) after moving the task
+ */
+ grp_util += src_in_grp ? -eenv->util_delta : 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;
+}
+
+/*
+ * sched_group_energy(): Computes the absolute energy consumption of cpus
+ * belonging to the sched_group including shared resources shared only by
+ * members of the group. Iterates over all cpus in the hierarchy below the
+ * sched_group starting from the bottom working it's way up before going to
+ * the next cpu until all cpus are covered at all levels. The current
+ * implementation is likely to gather the same util statistics multiple times.
+ * This can probably be done in a faster but more complex way.
+ * Note: sched_group_energy() may fail when racing with sched_domain updates.
+ */
+static int sched_group_energy(struct energy_env *eenv)
+{
+ struct cpumask visit_cpus;
+ u64 total_energy = 0;
+ 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 {
+ unsigned long group_util;
+ int sg_busy_energy, sg_idle_energy;
+ int cap_idx, idle_idx;
+
+ if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
+ eenv->sg_cap = sg_shared_cap;
+ else
+ eenv->sg_cap = sg;
+
+ cap_idx = find_new_capacity(eenv, sg->sge);
+
+ if (sg->group_weight == 1) {
+ /* Remove capacity of src CPU (before task move) */
+ if (eenv->trg_cpu == eenv->src_cpu &&
+ cpumask_test_cpu(eenv->src_cpu, sched_group_cpus(sg))) {
+ eenv->cap.before = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta -= eenv->cap.before;
+ }
+ /* Add capacity of dst CPU (after task move) */
+ if (eenv->trg_cpu == eenv->dst_cpu &&
+ cpumask_test_cpu(eenv->dst_cpu, sched_group_cpus(sg))) {
+ eenv->cap.after = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta += eenv->cap.after;
+ }
+ }
+
+ idle_idx = group_idle_state(eenv, sg);
+ group_util = group_norm_util(eenv, sg);
+
+ sg_busy_energy = (group_util * sg->sge->cap_states[cap_idx].power);
+ sg_idle_energy = ((SCHED_CAPACITY_SCALE-group_util)
+ * sg->sge->idle_states[idle_idx].power);
+
+ total_energy += sg_busy_energy + sg_idle_energy;
+
+ 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)))
+ 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;
+ }
+
+ eenv->energy = total_energy >> SCHED_CAPACITY_SHIFT;
+ 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));
+}
+
+static inline unsigned long task_util(struct task_struct *p);
+
+/*
+ * energy_diff(): Estimate the energy impact of changing the utilization
+ * distribution. eenv specifies the change: utilisation amount, source, and
+ * destination cpu. Source or destination cpu may be -1 in which case the
+ * utilization is removed from or added to the system (e.g. task wake-up). If
+ * both are specified, the utilization is migrated.
+ */
+static inline int __energy_diff(struct energy_env *eenv)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int sd_cpu = -1, energy_before = 0, energy_after = 0;
+ int diff, margin;
+
+ struct energy_env eenv_before = {
+ .util_delta = task_util(eenv->task),
+ .src_cpu = eenv->src_cpu,
+ .dst_cpu = eenv->dst_cpu,
+ .trg_cpu = eenv->src_cpu,
+ .nrg = { 0, 0, 0, 0},
+ .cap = { 0, 0, 0 },
+ .task = eenv->task,
+ };
+
+ if (eenv->src_cpu == eenv->dst_cpu)
+ return 0;
+
+ sd_cpu = (eenv->src_cpu != -1) ? eenv->src_cpu : eenv->dst_cpu;
+ sd = rcu_dereference(per_cpu(sd_ea, sd_cpu));
+
+ if (!sd)
+ return 0; /* Error */
+
+ sg = sd->groups;
+
+ do {
+ if (cpu_in_sg(sg, eenv->src_cpu) || cpu_in_sg(sg, eenv->dst_cpu)) {
+ eenv_before.sg_top = eenv->sg_top = sg;
+
+ if (sched_group_energy(&eenv_before))
+ return 0; /* Invalid result abort */
+ energy_before += eenv_before.energy;
+
+ /* Keep track of SRC cpu (before) capacity */
+ eenv->cap.before = eenv_before.cap.before;
+ eenv->cap.delta = eenv_before.cap.delta;
+
+ if (sched_group_energy(eenv))
+ return 0; /* Invalid result abort */
+ energy_after += eenv->energy;
+ }
+ } while (sg = sg->next, sg != sd->groups);
+
+ eenv->nrg.before = energy_before;
+ eenv->nrg.after = energy_after;
+ eenv->nrg.diff = eenv->nrg.after - eenv->nrg.before;
+ eenv->payoff = 0;
+#ifndef CONFIG_SCHED_TUNE
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ eenv->nrg.delta, eenv->payoff);
+#endif
+ /*
+ * Dead-zone margin preventing too many migrations.
+ */
+
+ margin = eenv->nrg.before >> 6; /* ~1.56% */
+
+ diff = eenv->nrg.after - eenv->nrg.before;
+
+ eenv->nrg.diff = (abs(diff) < margin) ? 0 : eenv->nrg.diff;
+
+ return eenv->nrg.diff;
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+struct target_nrg schedtune_target_nrg;
+extern bool schedtune_initialized;
+/*
+ * System energy normalization
+ * Returns the normalized value, in the range [0..SCHED_CAPACITY_SCALE],
+ * corresponding to the specified energy variation.
+ */
+static inline int
+normalize_energy(int energy_diff)
+{
+ u32 normalized_nrg;
+
+ /* during early setup, we don't know the extents */
+ if (unlikely(!schedtune_initialized))
+ return energy_diff < 0 ? -1 : 1 ;
+
+#ifdef CONFIG_SCHED_DEBUG
+ {
+ int max_delta;
+
+ /* Check for boundaries */
+ max_delta = schedtune_target_nrg.max_power;
+ max_delta -= schedtune_target_nrg.min_power;
+ WARN_ON(abs(energy_diff) >= max_delta);
+ }
+#endif
+
+ /* Do scaling using positive numbers to increase the range */
+ normalized_nrg = (energy_diff < 0) ? -energy_diff : energy_diff;
+
+ /* Scale by energy magnitude */
+ normalized_nrg <<= SCHED_CAPACITY_SHIFT;
+
+ /* Normalize on max energy for target platform */
+ normalized_nrg = reciprocal_divide(
+ normalized_nrg, schedtune_target_nrg.rdiv);
+
+ return (energy_diff < 0) ? -normalized_nrg : normalized_nrg;
+}
+
+static inline int
+energy_diff(struct energy_env *eenv)
+{
+ int boost = schedtune_task_boost(eenv->task);
+ int nrg_delta;
+
+ /* Conpute "absolute" energy diff */
+ __energy_diff(eenv);
+
+ /* Return energy diff when boost margin is 0 */
+ if (boost == 0) {
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ 0, -eenv->nrg.diff);
+ return eenv->nrg.diff;
+ }
+
+ /* Compute normalized energy diff */
+ nrg_delta = normalize_energy(eenv->nrg.diff);
+ eenv->nrg.delta = nrg_delta;
+
+ eenv->payoff = schedtune_accept_deltas(
+ eenv->nrg.delta,
+ eenv->cap.delta,
+ eenv->task);
+
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ eenv->nrg.delta, eenv->payoff);
+
+ /*
+ * When SchedTune is enabled, the energy_diff() function will return
+ * the computed energy payoff value. Since the energy_diff() return
+ * value is expected to be negative by its callers, this evaluation
+ * function return a negative value each time the evaluation return a
+ * positive payoff, which is the condition for the acceptance of
+ * a scheduling decision
+ */
+ return -eenv->payoff;
+}
+#else /* CONFIG_SCHED_TUNE */
+#define energy_diff(eenv) __energy_diff(eenv)
+#endif
+
+/*
* 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
@@ -5199,24 +6023,179 @@ 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 *task);
+
+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 *task)
+{
+ int boost = schedtune_task_boost(task);
+ unsigned long util;
+ long margin;
+
+ if (boost == 0)
+ return 0;
+
+ util = task_util(task);
+ 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 *task)
+{
+ 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 *task)
+{
+ unsigned long util = task_util(task);
+ long margin = schedtune_task_margin(task);
+
+ trace_sched_boost_task(task, util, margin);
+
+ return util + margin;
+}
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+ return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+}
+
/*
* 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;
@@ -5228,8 +6207,13 @@ 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 */
@@ -5238,30 +6222,85 @@ 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;
@@ -5310,6 +6349,68 @@ 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)
@@ -5477,96 +6578,549 @@ 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;
+ 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;
+
+ 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);
+ 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;
+
+ /*
+ * 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;
+ 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 - new_util) < target_max_spare_cap)
+ continue;
+
+ target_max_spare_cap = capacity_orig - new_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)
+{
+ struct sched_domain *sd;
+ int target_cpu = prev_cpu, tmp_target, tmp_backup;
+ bool boosted, prefer_idle;
+
+ 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;
+ }
+ }
+
+ rcu_read_lock();
+#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
+
+ sync_entity_load_avg(&p->se);
+
+ sd = rcu_dereference(per_cpu(sd_ea, prev_cpu));
+ /* Find a cpu with sufficient capacity */
+ tmp_target = find_best_target(p, &tmp_backup, boosted, prefer_idle);
+
+ if (!sd)
+ goto unlock;
+ if (tmp_target >= 0) {
+ target_cpu = tmp_target;
+ if ((boosted || prefer_idle) && idle_cpu(target_cpu)) {
+ schedstat_inc(p->se.statistics.nr_wakeups_secb_idle_bt);
+ schedstat_inc(this_rq()->eas_stats.secb_idle_bt);
+ goto unlock;
+ }
+ }
+
+ if (target_cpu != prev_cpu) {
+ int delta = 0;
+ struct energy_env eenv = {
+ .util_delta = task_util(p),
+ .src_cpu = prev_cpu,
+ .dst_cpu = target_cpu,
+ .task = p,
+ .trg_cpu = target_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);
+ goto unlock;
+ }
+
+ if (energy_diff(&eenv) >= 0) {
+ /* No energy saving for target_cpu, try backup */
+ target_cpu = tmp_backup;
+ eenv.dst_cpu = target_cpu;
+ eenv.trg_cpu = target_cpu;
+ if (tmp_backup < 0 ||
+ tmp_backup == prev_cpu ||
+ energy_diff(&eenv) >= 0) {
+ 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_nrg_sav);
+ schedstat_inc(this_rq()->eas_stats.secb_nrg_sav);
+ 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,
@@ -5590,10 +7144,13 @@ 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))
@@ -5621,43 +7178,21 @@ 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();
@@ -5717,6 +7252,8 @@ 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
@@ -5963,6 +7500,8 @@ 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;
@@ -5984,9 +7523,12 @@ 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
@@ -6199,6 +7741,13 @@ 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
@@ -6217,6 +7766,7 @@ 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;
@@ -6227,6 +7777,7 @@ struct lb_env {
unsigned int loop_max;
enum fbq_type fbq_type;
+ enum group_type busiest_group_type;
struct list_head tasks;
};
@@ -6408,7 +7959,9 @@ 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);
}
/*
@@ -6592,12 +8145,19 @@ 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);
}
@@ -6669,12 +8229,6 @@ 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
*/
@@ -6690,6 +8244,7 @@ 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;
@@ -6787,13 +8342,43 @@ 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;
+ 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;
@@ -6802,13 +8387,15 @@ 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);
@@ -6821,6 +8408,8 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
}
capacity = 0;
+ max_capacity = 0;
+ min_capacity = ULONG_MAX;
if (child->flags & SD_OVERLAP) {
/*
@@ -6845,11 +8434,13 @@ 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 {
/*
@@ -6859,12 +8450,18 @@ 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;
}
/*
@@ -6959,6 +8556,17 @@ 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)
@@ -6969,9 +8577,44 @@ 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.
@@ -6980,11 +8623,12 @@ 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;
@@ -6994,6 +8638,12 @@ 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);
@@ -7018,6 +8668,12 @@ 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 */
@@ -7059,9 +8715,31 @@ 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;
@@ -7116,6 +8794,9 @@ 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.
@@ -7127,7 +8808,7 @@ 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;
@@ -7149,7 +8830,7 @@ 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;
@@ -7171,6 +8852,15 @@ 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;
@@ -7187,10 +8877,23 @@ 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);
+ }
}
}
@@ -7343,6 +9046,22 @@ 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);
}
@@ -7376,6 +9095,11 @@ 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
@@ -7411,6 +9135,10 @@ 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;
@@ -7433,11 +9161,19 @@ 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.
@@ -7461,7 +9197,8 @@ 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 {
/*
@@ -7474,6 +9211,7 @@ 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;
@@ -7532,7 +9270,8 @@ 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;
/*
@@ -7590,6 +9329,14 @@ 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);
}
@@ -7638,7 +9385,7 @@ 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;
@@ -7705,6 +9452,7 @@ 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
@@ -7802,7 +9550,8 @@ 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);
@@ -7939,8 +9688,9 @@ 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)
@@ -8031,8 +9781,18 @@ 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);
@@ -8052,6 +9812,17 @@ 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) {
@@ -8061,16 +9832,9 @@ 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) {
@@ -8084,8 +9848,18 @@ 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);
@@ -8106,12 +9880,6 @@ 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);
@@ -8445,9 +10213,14 @@ 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) {
@@ -8541,6 +10314,47 @@ 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 */
/*
@@ -8558,6 +10372,16 @@ 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
+
}
/*
@@ -8644,11 +10468,65 @@ 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)) {
/*
@@ -8659,30 +10537,15 @@ 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;
@@ -8736,6 +10599,9 @@ 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
@@ -8844,7 +10710,8 @@ 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);
}
@@ -8936,8 +10803,10 @@ 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);
}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1b3c818..2a453df 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -74,3 +74,12 @@ 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
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/rt.c b/kernel/sched/rt.c
index f6d68dd..cedc7c7 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;
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
@@ -886,6 +888,51 @@ 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);
@@ -909,8 +956,14 @@ 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,
@@ -1311,6 +1364,7 @@ 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);
@@ -1322,6 +1376,7 @@ 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);
}
@@ -1831,7 +1886,9 @@ 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;
@@ -2103,7 +2160,9 @@ 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
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f564a1d2..c016d7e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -39,8 +39,10 @@ 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
@@ -410,6 +412,7 @@ 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
@@ -444,6 +447,10 @@ struct cfs_rq {
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
+#ifdef CONFIG_SCHED_WALT
+ u64 cumulative_runnable_avg;
+#endif
+
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
u64 runtime_expires;
@@ -539,6 +546,12 @@ 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
@@ -557,6 +570,9 @@ 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).
@@ -586,7 +602,11 @@ 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;
@@ -620,6 +640,7 @@ 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;
@@ -629,6 +650,14 @@ 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;
@@ -641,6 +670,7 @@ 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 */
/*
@@ -674,6 +704,7 @@ 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;
@@ -690,6 +721,20 @@ 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
@@ -728,6 +773,9 @@ 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
@@ -737,6 +785,7 @@ struct rq {
#ifdef CONFIG_CPU_IDLE
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
+ int idle_state_idx;
#endif
};
@@ -886,6 +935,8 @@ 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;
@@ -893,7 +944,9 @@ 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 */
@@ -906,6 +959,7 @@ struct sched_group {
unsigned int group_weight;
struct sched_group_capacity *sgc;
+ const struct sched_group_energy *sge;
/*
* The CPUs this group covers.
@@ -1214,6 +1268,7 @@ extern const u32 sched_prio_to_wmult[40];
#else
#define ENQUEUE_MIGRATED 0x00
#endif
+#define ENQUEUE_WAKEUP_NEW 0x40
#define RETRY_TASK ((void *)-1UL)
@@ -1304,6 +1359,7 @@ 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);
@@ -1324,6 +1380,17 @@ 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)
@@ -1334,6 +1401,15 @@ 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);
@@ -1388,7 +1464,7 @@ 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;
@@ -1404,13 +1480,50 @@ 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
@@ -1483,10 +1596,87 @@ 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) { }
@@ -1521,6 +1711,9 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
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
@@ -1593,7 +1786,8 @@ 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_);
}
@@ -1809,6 +2003,17 @@ 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/stop_task.c b/kernel/sched/stop_task.c
index 604297a..836a389 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.
@@ -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)
diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
new file mode 100644
index 0000000..654934f
--- /dev/null
+++ b/kernel/sched/tune.c
@@ -0,0 +1,956 @@
+#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;
+extern 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.
+ */
+
+/* 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 */
+ bool idle;
+ int boost_max;
+ struct {
+ /* 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) {
+ /*
+ * 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);
+
+ /*
+ * 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 int
+schedtune_boostgroup_init(struct schedtune *st)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Keep track of allocated boost groups */
+ allocated_group[st->idx] = st;
+
+ /* Initialize the per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ bg->group[st->idx].boost = 0;
+ bg->group[st->idx].tasks = 0;
+ raw_spin_lock_init(&bg->lock);
+ }
+
+ return 0;
+}
+
+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 */
+ st->idx = idx;
+ if (schedtune_boostgroup_init(st))
+ goto release;
+
+ return &st->css;
+
+release:
+ kfree(st);
+out:
+ return ERR_PTR(-ENOMEM);
+}
+
+static void
+schedtune_boostgroup_release(struct schedtune *st)
+{
+ /* Reset this boost group */
+ schedtune_boostgroup_update(st->idx, 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);
+
+ 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));
+ 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..343c2c9
--- /dev/null
+++ b/kernel/sched/walt.c
@@ -0,0 +1,901 @@
+/*
+ * 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);
+}
+
+static void
+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);
+
+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;
+}
+
+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))
+ 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..de7edac
--- /dev/null
+++ b/kernel/sched/walt.h
@@ -0,0 +1,64 @@
+/*
+ * 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_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);
+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_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) { }
+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 */
+
+extern bool walt_disabled;
+
+#endif
diff --git a/kernel/sys.c b/kernel/sys.c
index 89d5be4..1157bf7 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>
@@ -2072,6 +2074,153 @@ 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
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2270,6 +2419,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_GET_FP_MODE:
error = GET_FP_MODE(me);
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 24d603d..3d10a47 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -308,6 +308,50 @@ 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),
@@ -449,6 +493,21 @@ 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",
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index dae1a45..6a93da8 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 d831827..427e33d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -70,6 +70,10 @@ 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)
@@ -283,12 +287,14 @@ 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;
@@ -442,6 +448,35 @@ 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;
@@ -590,9 +625,6 @@ 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
@@ -602,6 +634,9 @@ 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 */
@@ -643,7 +678,6 @@ 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);
@@ -655,10 +689,13 @@ 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);
}
/**
@@ -1382,19 +1419,18 @@ 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);
@@ -1518,8 +1554,7 @@ 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);
@@ -2037,15 +2072,12 @@ 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/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 15b0264..7590d6a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1125,6 +1125,7 @@ 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
};
@@ -1597,6 +1598,7 @@ void tracing_reset_all_online_cpus(void)
#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
+static unsigned saved_tgids[SAVED_CMDLINES_DEFAULT];
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -1835,7 +1837,7 @@ static int trace_save_cmdline(struct task_struct *tsk)
}
set_cmdline(idx, tsk->comm);
-
+ saved_tgids[idx] = tsk->tgid;
arch_spin_unlock(&trace_cmdline_lock);
return 1;
@@ -1878,6 +1880,25 @@ void trace_find_cmdline(int pid, char comm[])
preempt_enable();
}
+int trace_find_tgid(int pid)
+{
+ unsigned map;
+ int tgid;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+ map = savedcmd->map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ tgid = saved_tgids[map];
+ else
+ tgid = -1;
+
+ 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())
@@ -2926,6 +2947,13 @@ 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);
@@ -2938,6 +2966,18 @@ 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)
{
@@ -3250,9 +3290,15 @@ 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);
}
}
}
@@ -4583,6 +4629,50 @@ 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 pid;
+ int i;
+
+ file_buf = kmalloc(SAVED_CMDLINES_DEFAULT*(16+1+16), GFP_KERNEL);
+ if (!file_buf)
+ return -ENOMEM;
+
+ buf = file_buf;
+
+ for (i = 0; i < SAVED_CMDLINES_DEFAULT; i++) {
+ int tgid;
+ int r;
+
+ pid = savedcmd->map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ tgid = trace_find_tgid(pid);
+ r = sprintf(buf, "%d %d\n", pid, tgid);
+ buf += r;
+ len += r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, len);
+
+ kfree(file_buf);
+
+ 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)
{
@@ -7214,6 +7304,9 @@ 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 b0d8576..d4c6633 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -690,6 +690,7 @@ 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;
@@ -1009,7 +1010,8 @@ 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 a17cb1d..3cb38f1 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 */
};
@@ -1243,6 +1248,9 @@ 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;
@@ -1300,13 +1308,6 @@ 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 */
@@ -1375,6 +1376,11 @@ 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;
@@ -1456,19 +1462,6 @@ 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",
@@ -1545,16 +1538,6 @@ 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_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/lib/Kconfig.debug b/lib/Kconfig.debug
index f60e672..db71a20 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -923,6 +923,15 @@
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
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/test_kasan.c b/lib/test_kasan.c
index fbdf879..0e70ecc 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
@@ -441,6 +442,12 @@ static noinline void __init use_after_scope_test(void)
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();
@@ -465,6 +472,9 @@ static int __init kmalloc_tests_init(void)
ksize_unpoisons_memory();
copy_user_test();
use_after_scope_test();
+
+ kasan_restore_multi_shot(multishot);
+
return -EAGAIN;
}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 0e9505f..7a6d1a1 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.
@@ -428,7 +438,7 @@ 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);
}
@@ -559,7 +569,8 @@ 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;
}
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 1c260e6..1229298 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -96,15 +96,10 @@ 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);
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 8ca412a..04bb1d3 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;
@@ -96,12 +104,39 @@ static void print_error_description(struct kasan_access_info *info)
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 %p 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 +172,14 @@ 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 +190,84 @@ 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 %p\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 [%p, %p)\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)
@@ -260,37 +322,74 @@ 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 a49afe0..bb58a44 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 a8ab5e7..9547583 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -752,7 +752,8 @@ 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/mlock.c b/mm/mlock.c
index f050569..9cdd063 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 45ac5b9..4b412e2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -970,7 +970,8 @@ 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
@@ -988,6 +989,8 @@ 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;
}
@@ -1020,9 +1023,10 @@ 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;
@@ -1041,9 +1045,10 @@ 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);
@@ -1054,9 +1059,9 @@ 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
@@ -1098,7 +1103,8 @@ 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;
@@ -1131,7 +1137,8 @@ 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?
*/
@@ -1140,7 +1147,8 @@ 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 */
@@ -1163,7 +1171,8 @@ 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);
@@ -1641,7 +1650,7 @@ 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;
@@ -2701,6 +2710,7 @@ 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)
{
@@ -2896,7 +2906,7 @@ static int do_brk(unsigned long addr, unsigned long request)
/* 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;
@@ -3057,7 +3067,7 @@ 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 ae740c9..1f2c969 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -303,7 +303,7 @@ 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/shmem.c b/mm/shmem.c
index 004e0f87..7a74b6d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4067,6 +4067,14 @@ 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
@@ -4086,10 +4094,7 @@ 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_common.c b/mm/slab_common.c
index 622f6b6..0dc614d 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/net/Kconfig b/net/Kconfig
index 7b6cd34..28071fc 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
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 1aff2da..4b32525 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 5f5e28f..04eea2f 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/core/fib_rules.c b/net/core/fib_rules.c
index be4629c..31c4041 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..c385c55 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();
@@ -2533,6 +2543,36 @@ 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 +2594,10 @@ 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 +2675,17 @@ 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 +3048,12 @@ 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 +3074,18 @@ 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/sock.c b/net/core/sock.c
index e3b6046..1d88335 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1031,6 +1031,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
union {
int val;
+ u64 val64;
struct linger ling;
struct timeval tm;
} v;
@@ -1261,6 +1262,13 @@ 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).
@@ -2441,8 +2449,11 @@ 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/Makefile b/net/ipv4/Makefile
index bc6a6c8..a8b934a 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,6 +16,7 @@
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
+obj-$(CONFIG_SYSFS) += sysfs_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b5116ec..01cda5b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -89,6 +89,7 @@
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/slab.h>
+#include <linux/netfilter/xt_qtaguid.h>
#include <asm/uaccess.h>
@@ -121,6 +122,19 @@
#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 +269,9 @@ 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 +320,7 @@ 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;
@@ -397,6 +413,9 @@ int inet_release(struct socket *sock)
if (sk) {
long timeout;
+#ifdef CONFIG_NETFILTER_XT_MATCH_QTAGUID
+ qtaguid_untag(sock, true);
+#endif
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
@@ -566,13 +585,24 @@ 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 +613,10 @@ 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 +630,9 @@ 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 ffae472..08b7260 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -319,7 +319,7 @@ 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;
@@ -332,6 +332,7 @@ 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;
@@ -339,13 +340,12 @@ 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);
@@ -621,6 +621,7 @@ 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 31f17f0..42a19fb 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -425,6 +425,7 @@ 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);
@@ -473,6 +474,7 @@ 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 d1cab49..2621838 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -417,7 +417,7 @@ 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))
@@ -453,7 +453,7 @@ 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 2c3c1a2..e60f9fa 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -74,6 +74,7 @@
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/lwtunnel.h>
+#include <linux/bpf-cgroup.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
@@ -287,6 +288,13 @@ 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 */
@@ -305,6 +313,20 @@ 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);
@@ -342,7 +364,7 @@ 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 */
@@ -358,7 +380,7 @@ 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,
@@ -1597,7 +1619,8 @@ 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/ping.c b/net/ipv4/ping.c
index e612991..93bfadf 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -796,7 +796,8 @@ 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);
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 59d8770..a860df2 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -612,7 +612,7 @@ 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 7ac3192..1a6b2e1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -507,7 +507,8 @@ 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)
@@ -523,19 +524,21 @@ 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)
@@ -552,7 +555,7 @@ 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();
}
@@ -799,6 +802,7 @@ 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;
@@ -806,7 +810,7 @@ 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);
}
@@ -1024,7 +1028,7 @@ 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)) {
@@ -1040,7 +1044,7 @@ 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);
@@ -1059,6 +1063,7 @@ 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);
@@ -1072,7 +1077,7 @@ 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)) {
@@ -1112,7 +1117,7 @@ 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)) {
@@ -1127,9 +1132,10 @@ 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);
@@ -1858,6 +1864,7 @@ 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))
@@ -2509,6 +2516,11 @@ 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)) {
@@ -2561,6 +2573,7 @@ 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)
@@ -2588,6 +2601,10 @@ 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;
@@ -2595,6 +2612,7 @@ 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 0597ad7..4487c71 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -373,7 +373,7 @@ 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)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 566cfc5..d540bf1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -151,6 +151,21 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
return ret;
}
+/* Validate changes from /proc interface. */
+static int proc_tcp_default_init_rwnd(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int old_value = *(int *)ctl->data;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
+
+ if (write && ret == 0 && (new_value < 3 || new_value > 100))
+ *(int *)ctl->data = old_value;
+
+ return ret;
+}
+
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -624,6 +639,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_ms_jiffies,
},
{
+ .procname = "tcp_default_init_rwnd",
+ .data = &sysctl_tcp_default_init_rwnd,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_default_init_rwnd
+ },
+ {
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
diff --git a/net/ipv4/sysfs_net_ipv4.c b/net/ipv4/sysfs_net_ipv4.c
new file mode 100644
index 0000000..0cbbf10
--- /dev/null
+++ b/net/ipv4/sysfs_net_ipv4.c
@@ -0,0 +1,88 @@
+/*
+ * net/ipv4/sysfs_net_ipv4.c
+ *
+ * sysfs-based networking knobs (so we can, unlike with sysctl, control perms)
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Robert Love <rlove@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.
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <net/tcp.h>
+
+#define CREATE_IPV4_FILE(_name, _var) \
+static ssize_t _name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+{ \
+ return sprintf(buf, "%d\n", _var); \
+} \
+static ssize_t _name##_store(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ int val, ret; \
+ ret = sscanf(buf, "%d", &val); \
+ if (ret != 1) \
+ return -EINVAL; \
+ if (val < 0) \
+ return -EINVAL; \
+ _var = val; \
+ return count; \
+} \
+static struct kobj_attribute _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+CREATE_IPV4_FILE(tcp_wmem_min, sysctl_tcp_wmem[0]);
+CREATE_IPV4_FILE(tcp_wmem_def, sysctl_tcp_wmem[1]);
+CREATE_IPV4_FILE(tcp_wmem_max, sysctl_tcp_wmem[2]);
+
+CREATE_IPV4_FILE(tcp_rmem_min, sysctl_tcp_rmem[0]);
+CREATE_IPV4_FILE(tcp_rmem_def, sysctl_tcp_rmem[1]);
+CREATE_IPV4_FILE(tcp_rmem_max, sysctl_tcp_rmem[2]);
+
+static struct attribute *ipv4_attrs[] = {
+ &tcp_wmem_min_attr.attr,
+ &tcp_wmem_def_attr.attr,
+ &tcp_wmem_max_attr.attr,
+ &tcp_rmem_min_attr.attr,
+ &tcp_rmem_def_attr.attr,
+ &tcp_rmem_max_attr.attr,
+ NULL
+};
+
+static struct attribute_group ipv4_attr_group = {
+ .attrs = ipv4_attrs,
+};
+
+static __init int sysfs_ipv4_init(void)
+{
+ struct kobject *ipv4_kobject;
+ int ret;
+
+ ipv4_kobject = kobject_create_and_add("ipv4", kernel_kobj);
+ if (!ipv4_kobject)
+ return -ENOMEM;
+
+ ret = sysfs_create_group(ipv4_kobject, &ipv4_attr_group);
+ if (ret) {
+ kobject_put(ipv4_kobject);
+ return ret;
+ }
+
+ return 0;
+}
+
+subsys_initcall(sysfs_ipv4_init);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d1a767..7ea8027 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 +1140,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
lock_sock(sk);
flags = msg->msg_flags;
- if (flags & MSG_FASTOPEN) {
+ if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
@@ -2314,6 +2336,10 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_rx_dst = NULL;
tcp_saved_syn_free(tp);
+ /* 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) {
@@ -2686,6 +2712,18 @@ 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;
@@ -2999,6 +3037,10 @@ 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 2f107e4..759d83e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -100,6 +100,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b396073..710d1af 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 = tp->write_seq ^ jiffies;
+ if (tcp_fastopen_defer_connect(sk, &err))
+ return err;
+ if (err)
+ goto failure;
+
err = tcp_connect(sk);
- rt = NULL;
if (err)
goto failure;
@@ -695,6 +700,7 @@ 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,
@@ -715,7 +721,7 @@ 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,
@@ -730,6 +736,7 @@ 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));
@@ -779,6 +786,7 @@ 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,
@@ -794,7 +802,7 @@ 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,
@@ -822,7 +830,7 @@ 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,
@@ -1670,7 +1678,9 @@ 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;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3d7b59e..20634ea 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -188,7 +188,7 @@ u32 tcp_default_init_rwnd(u32 mss)
* (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 = sysctl_tcp_default_init_rwnd;
if (mss > 1460)
init_rwnd = max((1460 * init_rwnd) / mss, 2U);
@@ -3251,23 +3251,11 @@ 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 bef4a94..6a4527a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1016,7 +1016,8 @@ 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 6a7ff69..7f9a8df 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 1594d9f..b74fd8c 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,
@@ -269,9 +271,11 @@ 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,
@@ -2200,6 +2204,31 @@ 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.
*/
@@ -2209,7 +2238,7 @@ 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,
@@ -2242,7 +2271,7 @@ 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)
@@ -4954,9 +4983,11 @@ 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
@@ -5929,6 +5960,13 @@ 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),
@@ -5938,6 +5976,13 @@ 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),
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4213790..1111684 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;
@@ -680,6 +696,7 @@ 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 0630a4d5..189eb10 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -662,9 +662,10 @@ 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 38062f4..b8baa1b 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 111ba55..cbcdd5d 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -474,9 +474,10 @@ 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 798a095..10d1deb 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(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 5da8649..7ba9a6e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -914,6 +914,7 @@ 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;
@@ -928,6 +929,7 @@ 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 db2613b..21bd54f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -560,6 +560,8 @@ 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;
@@ -619,6 +621,8 @@ 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 2e3db36..55ca65c 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);
@@ -862,7 +871,6 @@ 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 131e6aa..4c52236 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1262,6 +1262,8 @@ 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);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
@@ -1345,6 +1347,8 @@ 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);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 9123335..afc30a0 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -613,9 +613,10 @@ 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 d8e6714..01858ac 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1395,6 +1395,8 @@ 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/ping.c b/net/ipv6/ping.c
index 9828681..2a965d4 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 71ffa52..ff701ce 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -780,6 +780,7 @@ 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 6e8bacb..c107569 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1417,7 +1417,7 @@ 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;
@@ -1429,6 +1429,7 @@ 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)
@@ -1442,7 +1443,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
struct dst_entry *dst;
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -1534,7 +1535,8 @@ 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;
@@ -1547,6 +1549,7 @@ 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);
@@ -1568,6 +1571,7 @@ 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);
@@ -1576,7 +1580,8 @@ 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);
@@ -2350,8 +2355,7 @@ 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;
@@ -2366,7 +2370,7 @@ 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;
@@ -2397,7 +2401,7 @@ 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;
@@ -2413,7 +2417,7 @@ 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;
@@ -2439,7 +2443,7 @@ 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 |
@@ -2462,43 +2466,16 @@ 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,
@@ -2816,6 +2793,7 @@ 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 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -3395,6 +3373,12 @@ 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 7a86433d..a67174e 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(sk, &fl6, final_p);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index eb62454..82b7a8e 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.
@@ -1439,7 +1442,9 @@ 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 4db5f54..c43ef0c 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 e0f71c0..4003b28 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/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 2470972..86ad51a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -526,6 +526,7 @@ 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/netfilter/Kconfig b/net/netfilter/Kconfig
index e8d56d9..177d3ae 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
@@ -1349,6 +1351,22 @@
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_QTAGUID
+ bool '"quota, tag, owner" match and stats support'
+ depends on NETFILTER_XT_MATCH_SOCKET
+ depends on NETFILTER_XT_MATCH_OWNER=n
+ help
+ This option replaces the `owner' match. In addition to matching
+ on uid, it keeps stats based on a tag assigned to a socket.
+ The full tag is comprised of a UID and an accounting tag.
+ The tags are assignable to sockets from user space (e.g. a download
+ manager can assign the socket to another UID for accounting).
+ Stats and control are done via /proc/net/xt_qtaguid/.
+ It replaces owner as it takes the same arguments, but should
+ really be recognized by the iptables tool.
+
+ If unsure, say `N'.
+
config NETFILTER_XT_MATCH_QUOTA
tristate '"quota" match support'
depends on NETFILTER_ADVANCED
@@ -1359,6 +1377,29 @@
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..54ba5aa 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -167,7 +167,9 @@
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QTAGUID) += xt_qtaguid_print.o xt_qtaguid.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 750b8bf..8da893c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1023,7 +1023,7 @@ 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)
@@ -1922,7 +1922,7 @@ 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/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index daf45da..f11aa28 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_tg_create(struct idletimer_tg_info *info)
@@ -146,6 +307,21 @@ 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);
mod_timer(&info->timer->timer,
msecs_to_jiffies(info->timeout * 1000) + jiffies);
@@ -162,6 +338,42 @@ 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.
*/
@@ -169,15 +381,23 @@ 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;
}
@@ -186,7 +406,7 @@ 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");
@@ -205,9 +425,7 @@ 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 {
@@ -220,6 +438,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
}
mutex_unlock(&list_mutex);
+
return 0;
}
@@ -236,13 +455,14 @@ 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);
@@ -250,6 +470,7 @@ 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),
@@ -315,3 +536,4 @@ 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_qtaguid.c b/net/netfilter/xt_qtaguid.c
new file mode 100644
index 0000000..3dfa5a0
--- /dev/null
+++ b/net/netfilter/xt_qtaguid.c
@@ -0,0 +1,3026 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, 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.
+ */
+
+/*
+ * There are run-time debug flags enabled via the debug_mask module param, or
+ * via the DEFAULT_DEBUG_MASK. See xt_qtaguid_internal.h.
+ */
+#define DEBUG
+
+#include <linux/file.h>
+#include <linux/inetdevice.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_qtaguid.h>
+#include <linux/ratelimit.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+
+#include <linux/netfilter/xt_socket.h>
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+#include "../../fs/proc/internal.h"
+
+/*
+ * We only use the xt_socket funcs within a similar context to avoid unexpected
+ * return values.
+ */
+#define XT_SOCKET_SUPPORTED_HOOKS \
+ ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN))
+
+
+static const char *module_procdirname = "xt_qtaguid";
+static struct proc_dir_entry *xt_qtaguid_procdir;
+
+static unsigned int proc_iface_perms = S_IRUGO;
+module_param_named(iface_perms, proc_iface_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_stats_file;
+static unsigned int proc_stats_perms = S_IRUGO;
+module_param_named(stats_perms, proc_stats_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_ctrl_file;
+
+/* Everybody can write. But proc_ctrl_write_limited is true by default which
+ * limits what can be controlled. See the can_*() functions.
+ */
+static unsigned int proc_ctrl_perms = S_IRUGO | S_IWUGO;
+module_param_named(ctrl_perms, proc_ctrl_perms, uint, S_IRUGO | S_IWUSR);
+
+/* Limited by default, so the gid of the ctrl and stats proc entries
+ * will limit what can be done. See the can_*() functions.
+ */
+static bool proc_stats_readall_limited = true;
+static bool proc_ctrl_write_limited = true;
+
+module_param_named(stats_readall_limited, proc_stats_readall_limited, bool,
+ S_IRUGO | S_IWUSR);
+module_param_named(ctrl_write_limited, proc_ctrl_write_limited, bool,
+ S_IRUGO | S_IWUSR);
+
+/*
+ * Limit the number of active tags (via socket tags) for a given UID.
+ * Multiple processes could share the UID.
+ */
+static int max_sock_tags = DEFAULT_MAX_SOCK_TAGS;
+module_param(max_sock_tags, int, S_IRUGO | S_IWUSR);
+
+/*
+ * After the kernel has initiallized this module, it is still possible
+ * to make it passive.
+ * Setting passive to Y:
+ * - the iface stats handling will not act on notifications.
+ * - iptables matches will never match.
+ * - ctrl commands silently succeed.
+ * - stats are always empty.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool module_passive;
+module_param_named(passive, module_passive, bool, S_IRUGO | S_IWUSR);
+
+/*
+ * Control how qtaguid data is tracked per proc/uid.
+ * Setting tag_tracking_passive to Y:
+ * - don't create proc specific structs to track tags
+ * - don't check that active tag stats exceed some limits.
+ * - don't clean up socket tags on process exits.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool qtu_proc_handling_passive;
+module_param_named(tag_tracking_passive, qtu_proc_handling_passive, bool,
+ S_IRUGO | S_IWUSR);
+
+#define QTU_DEV_NAME "xt_qtaguid"
+
+uint qtaguid_debug_mask = DEFAULT_DEBUG_MASK;
+module_param_named(debug_mask, qtaguid_debug_mask, uint, S_IRUGO | S_IWUSR);
+
+/*---------------------------------------------------------------------------*/
+static const char *iface_stat_procdirname = "iface_stat";
+static struct proc_dir_entry *iface_stat_procdir;
+/*
+ * The iface_stat_all* will go away once userspace gets use to the new fields
+ * that have a format line.
+ */
+static const char *iface_stat_all_procfilename = "iface_stat_all";
+static struct proc_dir_entry *iface_stat_all_procfile;
+static const char *iface_stat_fmt_procfilename = "iface_stat_fmt";
+static struct proc_dir_entry *iface_stat_fmt_procfile;
+
+
+static LIST_HEAD(iface_stat_list);
+static DEFINE_SPINLOCK(iface_stat_list_lock);
+
+static struct rb_root sock_tag_tree = RB_ROOT;
+static DEFINE_SPINLOCK(sock_tag_list_lock);
+
+static struct rb_root tag_counter_set_tree = RB_ROOT;
+static DEFINE_SPINLOCK(tag_counter_set_list_lock);
+
+static struct rb_root uid_tag_data_tree = RB_ROOT;
+static DEFINE_SPINLOCK(uid_tag_data_tree_lock);
+
+static struct rb_root proc_qtu_data_tree = RB_ROOT;
+/* No proc_qtu_data_tree_lock; use uid_tag_data_tree_lock */
+
+static struct qtaguid_event_counts qtu_events;
+/*----------------------------------------------*/
+static bool can_manipulate_uids(void)
+{
+ /* root pwnd */
+ return in_egroup_p(xt_qtaguid_ctrl_file->gid)
+ || unlikely(!from_kuid(&init_user_ns, current_fsuid())) || unlikely(!proc_ctrl_write_limited)
+ || unlikely(uid_eq(current_fsuid(), xt_qtaguid_ctrl_file->uid));
+}
+
+static bool can_impersonate_uid(kuid_t uid)
+{
+ return uid_eq(uid, current_fsuid()) || can_manipulate_uids();
+}
+
+static bool can_read_other_uid_stats(kuid_t uid)
+{
+ /* root pwnd */
+ return in_egroup_p(xt_qtaguid_stats_file->gid)
+ || unlikely(!from_kuid(&init_user_ns, current_fsuid())) || uid_eq(uid, current_fsuid())
+ || unlikely(!proc_stats_readall_limited)
+ || unlikely(uid_eq(current_fsuid(), xt_qtaguid_ctrl_file->uid));
+}
+
+static inline void dc_add_byte_packets(struct data_counters *counters, int set,
+ enum ifs_tx_rx direction,
+ enum ifs_proto ifs_proto,
+ int bytes,
+ int packets)
+{
+ counters->bpc[set][direction][ifs_proto].bytes += bytes;
+ counters->bpc[set][direction][ifs_proto].packets += packets;
+}
+
+static struct tag_node *tag_node_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct tag_node *data = rb_entry(node, struct tag_node, node);
+ int result;
+ RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+ " node=%p data=%p\n", tag, node, data);
+ result = tag_compare(tag, data->tag);
+ RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+ " data.tag=0x%llx (uid=%u) res=%d\n",
+ tag, data->tag, get_uid_from_tag(data->tag), result);
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void tag_node_tree_insert(struct tag_node *data, struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct tag_node *this = rb_entry(*new, struct tag_node,
+ node);
+ int result = tag_compare(data->tag, this->tag);
+ RB_DEBUG("qtaguid: %s(): tag=0x%llx"
+ " (uid=%u)\n", __func__,
+ this->tag,
+ get_uid_from_tag(this->tag));
+ parent = *new;
+ if (result < 0)
+ new = &((*new)->rb_left);
+ else if (result > 0)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void tag_stat_tree_insert(struct tag_stat *data, struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_stat *tag_stat_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_stat, tn.node);
+}
+
+static void tag_counter_set_tree_insert(struct tag_counter_set *data,
+ struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_counter_set *tag_counter_set_tree_search(struct rb_root *root,
+ tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_counter_set, tn.node);
+
+}
+
+static void tag_ref_tree_insert(struct tag_ref *data, struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_ref *tag_ref_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_ref, tn.node);
+}
+
+static struct sock_tag *sock_tag_tree_search(struct rb_root *root,
+ const struct sock *sk)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct sock_tag *data = rb_entry(node, struct sock_tag,
+ sock_node);
+ if (sk < data->sk)
+ node = node->rb_left;
+ else if (sk > data->sk)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void sock_tag_tree_insert(struct sock_tag *data, struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct sock_tag *this = rb_entry(*new, struct sock_tag,
+ sock_node);
+ parent = *new;
+ if (data->sk < this->sk)
+ new = &((*new)->rb_left);
+ else if (data->sk > this->sk)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->sock_node, parent, new);
+ rb_insert_color(&data->sock_node, root);
+}
+
+static void sock_tag_tree_erase(struct rb_root *st_to_free_tree)
+{
+ struct rb_node *node;
+ struct sock_tag *st_entry;
+
+ node = rb_first(st_to_free_tree);
+ while (node) {
+ st_entry = rb_entry(node, struct sock_tag, sock_node);
+ node = rb_next(node);
+ CT_DEBUG("qtaguid: %s(): "
+ "erase st: sk=%p tag=0x%llx (uid=%u)\n", __func__,
+ st_entry->sk,
+ st_entry->tag,
+ get_uid_from_tag(st_entry->tag));
+ rb_erase(&st_entry->sock_node, st_to_free_tree);
+ sock_put(st_entry->sk);
+ kfree(st_entry);
+ }
+}
+
+static struct proc_qtu_data *proc_qtu_data_tree_search(struct rb_root *root,
+ const pid_t pid)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct proc_qtu_data *data = rb_entry(node,
+ struct proc_qtu_data,
+ node);
+ if (pid < data->pid)
+ node = node->rb_left;
+ else if (pid > data->pid)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void proc_qtu_data_tree_insert(struct proc_qtu_data *data,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct proc_qtu_data *this = rb_entry(*new,
+ struct proc_qtu_data,
+ node);
+ parent = *new;
+ if (data->pid < this->pid)
+ new = &((*new)->rb_left);
+ else if (data->pid > this->pid)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void uid_tag_data_tree_insert(struct uid_tag_data *data,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct uid_tag_data *this = rb_entry(*new,
+ struct uid_tag_data,
+ node);
+ parent = *new;
+ if (data->uid < this->uid)
+ new = &((*new)->rb_left);
+ else if (data->uid > this->uid)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static struct uid_tag_data *uid_tag_data_tree_search(struct rb_root *root,
+ uid_t uid)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct uid_tag_data *data = rb_entry(node,
+ struct uid_tag_data,
+ node);
+ if (uid < data->uid)
+ node = node->rb_left;
+ else if (uid > data->uid)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+/*
+ * Allocates a new uid_tag_data struct if needed.
+ * Returns a pointer to the found or allocated uid_tag_data.
+ * Returns a PTR_ERR on failures, and lock is not held.
+ * If found is not NULL:
+ * sets *found to true if not allocated.
+ * sets *found to false if allocated.
+ */
+struct uid_tag_data *get_uid_data(uid_t uid, bool *found_res)
+{
+ struct uid_tag_data *utd_entry;
+
+ /* Look for top level uid_tag_data for the UID */
+ utd_entry = uid_tag_data_tree_search(&uid_tag_data_tree, uid);
+ DR_DEBUG("qtaguid: get_uid_data(%u) utd=%p\n", uid, utd_entry);
+
+ if (found_res)
+ *found_res = utd_entry;
+ if (utd_entry)
+ return utd_entry;
+
+ utd_entry = kzalloc(sizeof(*utd_entry), GFP_ATOMIC);
+ if (!utd_entry) {
+ pr_err("qtaguid: get_uid_data(%u): "
+ "tag data alloc failed\n", uid);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ utd_entry->uid = uid;
+ utd_entry->tag_ref_tree = RB_ROOT;
+ uid_tag_data_tree_insert(utd_entry, &uid_tag_data_tree);
+ DR_DEBUG("qtaguid: get_uid_data(%u) new utd=%p\n", uid, utd_entry);
+ return utd_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *new_tag_ref(tag_t new_tag,
+ struct uid_tag_data *utd_entry)
+{
+ struct tag_ref *tr_entry;
+ int res;
+
+ if (utd_entry->num_active_tags + 1 > max_sock_tags) {
+ pr_info("qtaguid: new_tag_ref(0x%llx): "
+ "tag ref alloc quota exceeded. max=%d\n",
+ new_tag, max_sock_tags);
+ res = -EMFILE;
+ goto err_res;
+
+ }
+
+ tr_entry = kzalloc(sizeof(*tr_entry), GFP_ATOMIC);
+ if (!tr_entry) {
+ pr_err("qtaguid: new_tag_ref(0x%llx): "
+ "tag ref alloc failed\n",
+ new_tag);
+ res = -ENOMEM;
+ goto err_res;
+ }
+ tr_entry->tn.tag = new_tag;
+ /* tr_entry->num_sock_tags handled by caller */
+ utd_entry->num_active_tags++;
+ tag_ref_tree_insert(tr_entry, &utd_entry->tag_ref_tree);
+ DR_DEBUG("qtaguid: new_tag_ref(0x%llx): "
+ " inserted new tag ref %p\n",
+ new_tag, tr_entry);
+ return tr_entry;
+
+err_res:
+ return ERR_PTR(res);
+}
+
+static struct tag_ref *lookup_tag_ref(tag_t full_tag,
+ struct uid_tag_data **utd_res)
+{
+ struct uid_tag_data *utd_entry;
+ struct tag_ref *tr_entry;
+ bool found_utd;
+ uid_t uid = get_uid_from_tag(full_tag);
+
+ DR_DEBUG("qtaguid: lookup_tag_ref(tag=0x%llx (uid=%u))\n",
+ full_tag, uid);
+
+ utd_entry = get_uid_data(uid, &found_utd);
+ if (IS_ERR_OR_NULL(utd_entry)) {
+ if (utd_res)
+ *utd_res = utd_entry;
+ return NULL;
+ }
+
+ tr_entry = tag_ref_tree_search(&utd_entry->tag_ref_tree, full_tag);
+ if (utd_res)
+ *utd_res = utd_entry;
+ DR_DEBUG("qtaguid: lookup_tag_ref(0x%llx) utd_entry=%p tr_entry=%p\n",
+ full_tag, utd_entry, tr_entry);
+ return tr_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *get_tag_ref(tag_t full_tag,
+ struct uid_tag_data **utd_res)
+{
+ struct uid_tag_data *utd_entry;
+ struct tag_ref *tr_entry;
+
+ DR_DEBUG("qtaguid: get_tag_ref(0x%llx)\n",
+ full_tag);
+ tr_entry = lookup_tag_ref(full_tag, &utd_entry);
+ BUG_ON(IS_ERR_OR_NULL(utd_entry));
+ if (!tr_entry)
+ tr_entry = new_tag_ref(full_tag, utd_entry);
+
+ if (utd_res)
+ *utd_res = utd_entry;
+ DR_DEBUG("qtaguid: get_tag_ref(0x%llx) utd=%p tr=%p\n",
+ full_tag, utd_entry, tr_entry);
+ return tr_entry;
+}
+
+/* Checks and maybe frees the UID Tag Data entry */
+static void put_utd_entry(struct uid_tag_data *utd_entry)
+{
+ /* Are we done with the UID tag data entry? */
+ if (RB_EMPTY_ROOT(&utd_entry->tag_ref_tree) &&
+ !utd_entry->num_pqd) {
+ DR_DEBUG("qtaguid: %s(): "
+ "erase utd_entry=%p uid=%u "
+ "by pid=%u tgid=%u uid=%u\n", __func__,
+ utd_entry, utd_entry->uid,
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+ BUG_ON(utd_entry->num_active_tags);
+ rb_erase(&utd_entry->node, &uid_tag_data_tree);
+ kfree(utd_entry);
+ } else {
+ DR_DEBUG("qtaguid: %s(): "
+ "utd_entry=%p still has %d tags %d proc_qtu_data\n",
+ __func__, utd_entry, utd_entry->num_active_tags,
+ utd_entry->num_pqd);
+ BUG_ON(!(utd_entry->num_active_tags ||
+ utd_entry->num_pqd));
+ }
+}
+
+/*
+ * If no sock_tags are using this tag_ref,
+ * decrements refcount of utd_entry, removes tr_entry
+ * from utd_entry->tag_ref_tree and frees.
+ */
+static void free_tag_ref_from_utd_entry(struct tag_ref *tr_entry,
+ struct uid_tag_data *utd_entry)
+{
+ DR_DEBUG("qtaguid: %s(): %p tag=0x%llx (uid=%u)\n", __func__,
+ tr_entry, tr_entry->tn.tag,
+ get_uid_from_tag(tr_entry->tn.tag));
+ if (!tr_entry->num_sock_tags) {
+ BUG_ON(!utd_entry->num_active_tags);
+ utd_entry->num_active_tags--;
+ rb_erase(&tr_entry->tn.node, &utd_entry->tag_ref_tree);
+ DR_DEBUG("qtaguid: %s(): erased %p\n", __func__, tr_entry);
+ kfree(tr_entry);
+ }
+}
+
+static void put_tag_ref_tree(tag_t full_tag, struct uid_tag_data *utd_entry)
+{
+ struct rb_node *node;
+ struct tag_ref *tr_entry;
+ tag_t acct_tag;
+
+ DR_DEBUG("qtaguid: %s(tag=0x%llx (uid=%u))\n", __func__,
+ full_tag, get_uid_from_tag(full_tag));
+ acct_tag = get_atag_from_tag(full_tag);
+ node = rb_first(&utd_entry->tag_ref_tree);
+ while (node) {
+ tr_entry = rb_entry(node, struct tag_ref, tn.node);
+ node = rb_next(node);
+ if (!acct_tag || tr_entry->tn.tag == full_tag)
+ free_tag_ref_from_utd_entry(tr_entry, utd_entry);
+ }
+}
+
+static ssize_t read_proc_u64(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ uint64_t *valuep = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", *valuep);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t read_proc_bool(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ bool *valuep = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%u\n", *valuep);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static int get_active_counter_set(tag_t tag)
+{
+ int active_set = 0;
+ struct tag_counter_set *tcs;
+
+ MT_DEBUG("qtaguid: get_active_counter_set(tag=0x%llx)"
+ " (uid=%u)\n",
+ tag, get_uid_from_tag(tag));
+ /* For now we only handle UID tags for active sets */
+ tag = get_utag_from_tag(tag);
+ spin_lock_bh(&tag_counter_set_list_lock);
+ tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (tcs)
+ active_set = tcs->active_set;
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ return active_set;
+}
+
+/*
+ * Find the entry for tracking the specified interface.
+ * Caller must hold iface_stat_list_lock
+ */
+static struct iface_stat *get_iface_entry(const char *ifname)
+{
+ struct iface_stat *iface_entry;
+
+ /* Find the entry for tracking the specified tag within the interface */
+ if (ifname == NULL) {
+ pr_info("qtaguid: iface_stat: get() NULL device name\n");
+ return NULL;
+ }
+
+ /* Iterate over interfaces */
+ list_for_each_entry(iface_entry, &iface_stat_list, list) {
+ if (!strcmp(ifname, iface_entry->ifname))
+ goto done;
+ }
+ iface_entry = NULL;
+done:
+ return iface_entry;
+}
+
+/* This is for fmt2 only */
+static void pp_iface_stat_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "ifname "
+ "total_skb_rx_bytes total_skb_rx_packets "
+ "total_skb_tx_bytes total_skb_tx_packets "
+ "rx_tcp_bytes rx_tcp_packets "
+ "rx_udp_bytes rx_udp_packets "
+ "rx_other_bytes rx_other_packets "
+ "tx_tcp_bytes tx_tcp_packets "
+ "tx_udp_bytes tx_udp_packets "
+ "tx_other_bytes tx_other_packets\n"
+ );
+}
+
+static void pp_iface_stat_line(struct seq_file *m,
+ struct iface_stat *iface_entry)
+{
+ struct data_counters *cnts;
+ int cnt_set = 0; /* We only use one set for the device */
+ cnts = &iface_entry->totals_via_skb;
+ seq_printf(m, "%s %llu %llu %llu %llu %llu %llu %llu %llu "
+ "%llu %llu %llu %llu %llu %llu %llu %llu\n",
+ iface_entry->ifname,
+ dc_sum_bytes(cnts, cnt_set, IFS_RX),
+ dc_sum_packets(cnts, cnt_set, IFS_RX),
+ dc_sum_bytes(cnts, cnt_set, IFS_TX),
+ dc_sum_packets(cnts, cnt_set, IFS_TX),
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+}
+
+struct proc_iface_stat_fmt_info {
+ int fmt;
+};
+
+static void *iface_stat_fmt_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_iface_stat_fmt_info *p = m->private;
+ loff_t n = *pos;
+
+ /*
+ * This lock will prevent iface_stat_update() from changing active,
+ * and in turn prevent an interface from unregistering itself.
+ */
+ spin_lock_bh(&iface_stat_list_lock);
+
+ if (unlikely(module_passive))
+ return NULL;
+
+ if (!n && p->fmt == 2)
+ pp_iface_stat_header(m);
+
+ return seq_list_start(&iface_stat_list, n);
+}
+
+static void *iface_stat_fmt_proc_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ return seq_list_next(p, &iface_stat_list, pos);
+}
+
+static void iface_stat_fmt_proc_stop(struct seq_file *m, void *p)
+{
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static int iface_stat_fmt_proc_show(struct seq_file *m, void *v)
+{
+ struct proc_iface_stat_fmt_info *p = m->private;
+ struct iface_stat *iface_entry;
+ struct rtnl_link_stats64 dev_stats, *stats;
+ struct rtnl_link_stats64 no_dev_stats = {0};
+
+
+ CT_DEBUG("qtaguid:proc iface_stat_fmt pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+ iface_entry = list_entry(v, struct iface_stat, list);
+
+ if (iface_entry->active) {
+ stats = dev_get_stats(iface_entry->net_dev,
+ &dev_stats);
+ } else {
+ stats = &no_dev_stats;
+ }
+ /*
+ * If the meaning of the data changes, then update the fmtX
+ * string.
+ */
+ if (p->fmt == 1) {
+ seq_printf(m, "%s %d %llu %llu %llu %llu %llu %llu %llu %llu\n",
+ iface_entry->ifname,
+ iface_entry->active,
+ iface_entry->totals_via_dev[IFS_RX].bytes,
+ iface_entry->totals_via_dev[IFS_RX].packets,
+ iface_entry->totals_via_dev[IFS_TX].bytes,
+ iface_entry->totals_via_dev[IFS_TX].packets,
+ stats->rx_bytes, stats->rx_packets,
+ stats->tx_bytes, stats->tx_packets
+ );
+ } else {
+ pp_iface_stat_line(m, iface_entry);
+ }
+ return 0;
+}
+
+static const struct file_operations read_u64_fops = {
+ .read = read_proc_u64,
+ .llseek = default_llseek,
+};
+
+static const struct file_operations read_bool_fops = {
+ .read = read_proc_bool,
+ .llseek = default_llseek,
+};
+
+static void iface_create_proc_worker(struct work_struct *work)
+{
+ struct proc_dir_entry *proc_entry;
+ struct iface_stat_work *isw = container_of(work, struct iface_stat_work,
+ iface_work);
+ struct iface_stat *new_iface = isw->iface_entry;
+
+ /* iface_entries are not deleted, so safe to manipulate. */
+ proc_entry = proc_mkdir(new_iface->ifname, iface_stat_procdir);
+ if (IS_ERR_OR_NULL(proc_entry)) {
+ pr_err("qtaguid: iface_stat: create_proc(): alloc failed.\n");
+ kfree(isw);
+ return;
+ }
+
+ new_iface->proc_ptr = proc_entry;
+
+ proc_create_data("tx_bytes", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_TX].bytes);
+ proc_create_data("rx_bytes", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_RX].bytes);
+ proc_create_data("tx_packets", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_TX].packets);
+ proc_create_data("rx_packets", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_RX].packets);
+ proc_create_data("active", proc_iface_perms, proc_entry,
+ &read_bool_fops, &new_iface->active);
+
+ IF_DEBUG("qtaguid: iface_stat: create_proc(): done "
+ "entry=%p dev=%s\n", new_iface, new_iface->ifname);
+ kfree(isw);
+}
+
+/*
+ * Will set the entry's active state, and
+ * update the net_dev accordingly also.
+ */
+static void _iface_stat_set_active(struct iface_stat *entry,
+ struct net_device *net_dev,
+ bool activate)
+{
+ if (activate) {
+ entry->net_dev = net_dev;
+ entry->active = true;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "enable tracking. rfcnt=%d\n", __func__,
+ entry->ifname,
+ __this_cpu_read(*net_dev->pcpu_refcnt));
+ } else {
+ entry->active = false;
+ entry->net_dev = NULL;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "disable tracking. rfcnt=%d\n", __func__,
+ entry->ifname,
+ __this_cpu_read(*net_dev->pcpu_refcnt));
+
+ }
+}
+
+/* Caller must hold iface_stat_list_lock */
+static struct iface_stat *iface_alloc(struct net_device *net_dev)
+{
+ struct iface_stat *new_iface;
+ struct iface_stat_work *isw;
+
+ new_iface = kzalloc(sizeof(*new_iface), GFP_ATOMIC);
+ if (new_iface == NULL) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "iface_stat alloc failed\n", net_dev->name);
+ return NULL;
+ }
+ new_iface->ifname = kstrdup(net_dev->name, GFP_ATOMIC);
+ if (new_iface->ifname == NULL) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "ifname alloc failed\n", net_dev->name);
+ kfree(new_iface);
+ return NULL;
+ }
+ spin_lock_init(&new_iface->tag_stat_list_lock);
+ new_iface->tag_stat_tree = RB_ROOT;
+ _iface_stat_set_active(new_iface, net_dev, true);
+
+ /*
+ * ipv6 notifier chains are atomic :(
+ * No create_proc_read_entry() for you!
+ */
+ isw = kmalloc(sizeof(*isw), GFP_ATOMIC);
+ if (!isw) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "work alloc failed\n", new_iface->ifname);
+ _iface_stat_set_active(new_iface, net_dev, false);
+ kfree(new_iface->ifname);
+ kfree(new_iface);
+ return NULL;
+ }
+ isw->iface_entry = new_iface;
+ INIT_WORK(&isw->iface_work, iface_create_proc_worker);
+ schedule_work(&isw->iface_work);
+ list_add(&new_iface->list, &iface_stat_list);
+ return new_iface;
+}
+
+static void iface_check_stats_reset_and_adjust(struct net_device *net_dev,
+ struct iface_stat *iface)
+{
+ struct rtnl_link_stats64 dev_stats, *stats;
+ bool stats_rewound;
+
+ stats = dev_get_stats(net_dev, &dev_stats);
+ /* No empty packets */
+ stats_rewound =
+ (stats->rx_bytes < iface->last_known[IFS_RX].bytes)
+ || (stats->tx_bytes < iface->last_known[IFS_TX].bytes);
+
+ IF_DEBUG("qtaguid: %s(%s): iface=%p netdev=%p "
+ "bytes rx/tx=%llu/%llu "
+ "active=%d last_known=%d "
+ "stats_rewound=%d\n", __func__,
+ net_dev ? net_dev->name : "?",
+ iface, net_dev,
+ stats->rx_bytes, stats->tx_bytes,
+ iface->active, iface->last_known_valid, stats_rewound);
+
+ if (iface->active && iface->last_known_valid && stats_rewound) {
+ pr_warn_once("qtaguid: iface_stat: %s(%s): "
+ "iface reset its stats unexpectedly\n", __func__,
+ net_dev->name);
+
+ iface->totals_via_dev[IFS_TX].bytes +=
+ iface->last_known[IFS_TX].bytes;
+ iface->totals_via_dev[IFS_TX].packets +=
+ iface->last_known[IFS_TX].packets;
+ iface->totals_via_dev[IFS_RX].bytes +=
+ iface->last_known[IFS_RX].bytes;
+ iface->totals_via_dev[IFS_RX].packets +=
+ iface->last_known[IFS_RX].packets;
+ iface->last_known_valid = false;
+ IF_DEBUG("qtaguid: %s(%s): iface=%p "
+ "used last known bytes rx/tx=%llu/%llu\n", __func__,
+ iface->ifname, iface, iface->last_known[IFS_RX].bytes,
+ iface->last_known[IFS_TX].bytes);
+ }
+}
+
+/*
+ * Create a new entry for tracking the specified interface.
+ * Do nothing if the entry already exists.
+ * Called when an interface is configured with a valid IP address.
+ */
+static void iface_stat_create(struct net_device *net_dev,
+ struct in_ifaddr *ifa)
+{
+ struct in_device *in_dev = NULL;
+ const char *ifname;
+ struct iface_stat *entry;
+ __be32 ipaddr = 0;
+ struct iface_stat *new_iface;
+
+ IF_DEBUG("qtaguid: iface_stat: create(%s): ifa=%p netdev=%p\n",
+ net_dev ? net_dev->name : "?",
+ ifa, net_dev);
+ if (!net_dev) {
+ pr_err("qtaguid: iface_stat: create(): no net dev\n");
+ return;
+ }
+
+ ifname = net_dev->name;
+ if (!ifa) {
+ in_dev = in_dev_get(net_dev);
+ if (!in_dev) {
+ pr_err("qtaguid: iface_stat: create(%s): no inet dev\n",
+ ifname);
+ return;
+ }
+ IF_DEBUG("qtaguid: iface_stat: create(%s): in_dev=%p\n",
+ ifname, in_dev);
+ for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): "
+ "ifa=%p ifa_label=%s\n",
+ ifname, ifa, ifa->ifa_label);
+ if (!strcmp(ifname, ifa->ifa_label))
+ break;
+ }
+ }
+
+ if (!ifa) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): no matching IP\n",
+ ifname);
+ goto done_put;
+ }
+ ipaddr = ifa->ifa_local;
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(ifname);
+ if (entry != NULL) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): entry=%p\n",
+ ifname, entry);
+ iface_check_stats_reset_and_adjust(net_dev, entry);
+ _iface_stat_set_active(entry, net_dev, true);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "tracking now %d on ip=%pI4\n", __func__,
+ entry->ifname, true, &ipaddr);
+ goto done_unlock_put;
+ }
+
+ new_iface = iface_alloc(net_dev);
+ IF_DEBUG("qtaguid: iface_stat: create(%s): done "
+ "entry=%p ip=%pI4\n", ifname, new_iface, &ipaddr);
+done_unlock_put:
+ spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+ if (in_dev)
+ in_dev_put(in_dev);
+}
+
+static void iface_stat_create_ipv6(struct net_device *net_dev,
+ struct inet6_ifaddr *ifa)
+{
+ struct in_device *in_dev;
+ const char *ifname;
+ struct iface_stat *entry;
+ struct iface_stat *new_iface;
+ int addr_type;
+
+ IF_DEBUG("qtaguid: iface_stat: create6(): ifa=%p netdev=%p->name=%s\n",
+ ifa, net_dev, net_dev ? net_dev->name : "");
+ if (!net_dev) {
+ pr_err("qtaguid: iface_stat: create6(): no net dev!\n");
+ return;
+ }
+ ifname = net_dev->name;
+
+ in_dev = in_dev_get(net_dev);
+ if (!in_dev) {
+ pr_err("qtaguid: iface_stat: create6(%s): no inet dev\n",
+ ifname);
+ return;
+ }
+
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): in_dev=%p\n",
+ ifname, in_dev);
+
+ if (!ifa) {
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): no matching IP\n",
+ ifname);
+ goto done_put;
+ }
+ addr_type = ipv6_addr_type(&ifa->addr);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(ifname);
+ if (entry != NULL) {
+ IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+ ifname, entry);
+ iface_check_stats_reset_and_adjust(net_dev, entry);
+ _iface_stat_set_active(entry, net_dev, true);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "tracking now %d on ip=%pI6c\n", __func__,
+ entry->ifname, true, &ifa->addr);
+ goto done_unlock_put;
+ }
+
+ new_iface = iface_alloc(net_dev);
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): done "
+ "entry=%p ip=%pI6c\n", ifname, new_iface, &ifa->addr);
+
+done_unlock_put:
+ spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+ in_dev_put(in_dev);
+}
+
+static struct sock_tag *get_sock_stat_nl(const struct sock *sk)
+{
+ MT_DEBUG("qtaguid: get_sock_stat_nl(sk=%p)\n", sk);
+ return sock_tag_tree_search(&sock_tag_tree, sk);
+}
+
+static struct sock_tag *get_sock_stat(const struct sock *sk)
+{
+ struct sock_tag *sock_tag_entry;
+ MT_DEBUG("qtaguid: get_sock_stat(sk=%p)\n", sk);
+ if (!sk)
+ return NULL;
+ spin_lock_bh(&sock_tag_list_lock);
+ sock_tag_entry = get_sock_stat_nl(sk);
+ spin_unlock_bh(&sock_tag_list_lock);
+ return sock_tag_entry;
+}
+
+static int ipx_proto(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ int thoff = 0, tproto;
+
+ switch (par->family) {
+ case NFPROTO_IPV6:
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
+ if (tproto < 0)
+ MT_DEBUG("%s(): transport header not found in ipv6"
+ " skb=%p\n", __func__, skb);
+ break;
+ case NFPROTO_IPV4:
+ tproto = ip_hdr(skb)->protocol;
+ break;
+ default:
+ tproto = IPPROTO_RAW;
+ }
+ return tproto;
+}
+
+static void
+data_counters_update(struct data_counters *dc, int set,
+ enum ifs_tx_rx direction, int proto, int bytes)
+{
+ switch (proto) {
+ case IPPROTO_TCP:
+ dc_add_byte_packets(dc, set, direction, IFS_TCP, bytes, 1);
+ break;
+ case IPPROTO_UDP:
+ dc_add_byte_packets(dc, set, direction, IFS_UDP, bytes, 1);
+ break;
+ case IPPROTO_IP:
+ default:
+ dc_add_byte_packets(dc, set, direction, IFS_PROTO_OTHER, bytes,
+ 1);
+ break;
+ }
+}
+
+/*
+ * Update stats for the specified interface. Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called when an device is being unregistered.
+ */
+static void iface_stat_update(struct net_device *net_dev, bool stash_only)
+{
+ struct rtnl_link_stats64 dev_stats, *stats;
+ struct iface_stat *entry;
+
+ stats = dev_get_stats(net_dev, &dev_stats);
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(net_dev->name);
+ if (entry == NULL) {
+ IF_DEBUG("qtaguid: iface_stat: update(%s): not tracked\n",
+ net_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+ net_dev->name, entry);
+ if (!entry->active) {
+ IF_DEBUG("qtaguid: %s(%s): already disabled\n", __func__,
+ net_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ if (stash_only) {
+ entry->last_known[IFS_TX].bytes = stats->tx_bytes;
+ entry->last_known[IFS_TX].packets = stats->tx_packets;
+ entry->last_known[IFS_RX].bytes = stats->rx_bytes;
+ entry->last_known[IFS_RX].packets = stats->rx_packets;
+ entry->last_known_valid = true;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "dev stats stashed rx/tx=%llu/%llu\n", __func__,
+ net_dev->name, stats->rx_bytes, stats->tx_bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+ entry->totals_via_dev[IFS_TX].bytes += stats->tx_bytes;
+ entry->totals_via_dev[IFS_TX].packets += stats->tx_packets;
+ entry->totals_via_dev[IFS_RX].bytes += stats->rx_bytes;
+ entry->totals_via_dev[IFS_RX].packets += stats->rx_packets;
+ /* We don't need the last_known[] anymore */
+ entry->last_known_valid = false;
+ _iface_stat_set_active(entry, net_dev, false);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "disable tracking. rx/tx=%llu/%llu\n", __func__,
+ net_dev->name, stats->rx_bytes, stats->tx_bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/* Guarantied to return a net_device that has a name */
+static void get_dev_and_dir(const struct sk_buff *skb,
+ struct xt_action_param *par,
+ enum ifs_tx_rx *direction,
+ const struct net_device **el_dev)
+{
+ BUG_ON(!direction || !el_dev);
+
+ if (par->in) {
+ *el_dev = par->in;
+ *direction = IFS_RX;
+ } else if (par->out) {
+ *el_dev = par->out;
+ *direction = IFS_TX;
+ } else {
+ pr_err("qtaguid[%d]: %s(): no par->in/out?!!\n",
+ par->hooknum, __func__);
+ BUG();
+ }
+ if (unlikely(!(*el_dev)->name)) {
+ pr_err("qtaguid[%d]: %s(): no dev->name?!!\n",
+ par->hooknum, __func__);
+ BUG();
+ }
+ if (skb->dev && *el_dev != skb->dev) {
+ MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs par->%s=%p %s\n",
+ par->hooknum, skb->dev, skb->dev->name,
+ *direction == IFS_RX ? "in" : "out", *el_dev,
+ (*el_dev)->name);
+ }
+}
+
+/*
+ * Update stats for the specified interface from the skb.
+ * Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called on each sk.
+ */
+static void iface_stat_update_from_skb(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ struct iface_stat *entry;
+ const struct net_device *el_dev;
+ enum ifs_tx_rx direction;
+ int bytes = skb->len;
+ int proto;
+
+ get_dev_and_dir(skb, par, &direction, &el_dev);
+ proto = ipx_proto(skb, par);
+ MT_DEBUG("qtaguid[%d]: iface_stat: %s(%s): "
+ "type=%d fam=%d proto=%d dir=%d\n",
+ par->hooknum, __func__, el_dev->name, el_dev->type,
+ par->family, proto, direction);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(el_dev->name);
+ if (entry == NULL) {
+ IF_DEBUG("qtaguid[%d]: iface_stat: %s(%s): not tracked\n",
+ par->hooknum, __func__, el_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ IF_DEBUG("qtaguid[%d]: %s(%s): entry=%p\n", par->hooknum, __func__,
+ el_dev->name, entry);
+
+ data_counters_update(&entry->totals_via_skb, 0, direction, proto,
+ bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static void tag_stat_update(struct tag_stat *tag_entry,
+ enum ifs_tx_rx direction, int proto, int bytes)
+{
+ int active_set;
+ active_set = get_active_counter_set(tag_entry->tn.tag);
+ MT_DEBUG("qtaguid: tag_stat_update(tag=0x%llx (uid=%u) set=%d "
+ "dir=%d proto=%d bytes=%d)\n",
+ tag_entry->tn.tag, get_uid_from_tag(tag_entry->tn.tag),
+ active_set, direction, proto, bytes);
+ data_counters_update(&tag_entry->counters, active_set, direction,
+ proto, bytes);
+ if (tag_entry->parent_counters)
+ data_counters_update(tag_entry->parent_counters, active_set,
+ direction, proto, bytes);
+}
+
+/*
+ * Create a new entry for tracking the specified {acct_tag,uid_tag} within
+ * the interface.
+ * iface_entry->tag_stat_list_lock should be held.
+ */
+static struct tag_stat *create_if_tag_stat(struct iface_stat *iface_entry,
+ tag_t tag)
+{
+ struct tag_stat *new_tag_stat_entry = NULL;
+ IF_DEBUG("qtaguid: iface_stat: %s(): ife=%p tag=0x%llx"
+ " (uid=%u)\n", __func__,
+ iface_entry, tag, get_uid_from_tag(tag));
+ new_tag_stat_entry = kzalloc(sizeof(*new_tag_stat_entry), GFP_ATOMIC);
+ if (!new_tag_stat_entry) {
+ pr_err("qtaguid: iface_stat: tag stat alloc failed\n");
+ goto done;
+ }
+ new_tag_stat_entry->tn.tag = tag;
+ tag_stat_tree_insert(new_tag_stat_entry, &iface_entry->tag_stat_tree);
+done:
+ return new_tag_stat_entry;
+}
+
+static void if_tag_stat_update(const char *ifname, uid_t uid,
+ const struct sock *sk, enum ifs_tx_rx direction,
+ int proto, int bytes)
+{
+ struct tag_stat *tag_stat_entry;
+ tag_t tag, acct_tag;
+ tag_t uid_tag;
+ struct data_counters *uid_tag_counters;
+ struct sock_tag *sock_tag_entry;
+ struct iface_stat *iface_entry;
+ struct tag_stat *new_tag_stat = NULL;
+ MT_DEBUG("qtaguid: if_tag_stat_update(ifname=%s "
+ "uid=%u sk=%p dir=%d proto=%d bytes=%d)\n",
+ ifname, uid, sk, direction, proto, bytes);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ iface_entry = get_iface_entry(ifname);
+ if (!iface_entry) {
+ pr_err_ratelimited("qtaguid: tag_stat: stat_update() "
+ "%s not found\n", ifname);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+ /* It is ok to process data when an iface_entry is inactive */
+
+ MT_DEBUG("qtaguid: tag_stat: stat_update() dev=%s entry=%p\n",
+ ifname, iface_entry);
+
+ /*
+ * Look for a tagged sock.
+ * It will have an acct_uid.
+ */
+ sock_tag_entry = get_sock_stat(sk);
+ if (sock_tag_entry) {
+ tag = sock_tag_entry->tag;
+ acct_tag = get_atag_from_tag(tag);
+ uid_tag = get_utag_from_tag(tag);
+ } else {
+ acct_tag = make_atag_from_value(0);
+ tag = combine_atag_with_uid(acct_tag, uid);
+ uid_tag = make_tag_from_uid(uid);
+ }
+ MT_DEBUG("qtaguid: tag_stat: stat_update(): "
+ " looking for tag=0x%llx (uid=%u) in ife=%p\n",
+ tag, get_uid_from_tag(tag), iface_entry);
+ /* Loop over tag list under this interface for {acct_tag,uid_tag} */
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+
+ tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+ tag);
+ if (tag_stat_entry) {
+ /*
+ * Updating the {acct_tag, uid_tag} entry handles both stats:
+ * {0, uid_tag} will also get updated.
+ */
+ tag_stat_update(tag_stat_entry, direction, proto, bytes);
+ goto unlock;
+ }
+
+ /* Loop over tag list under this interface for {0,uid_tag} */
+ tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+ uid_tag);
+ if (!tag_stat_entry) {
+ /* Here: the base uid_tag did not exist */
+ /*
+ * No parent counters. So
+ * - No {0, uid_tag} stats and no {acc_tag, uid_tag} stats.
+ */
+ new_tag_stat = create_if_tag_stat(iface_entry, uid_tag);
+ if (!new_tag_stat)
+ goto unlock;
+ uid_tag_counters = &new_tag_stat->counters;
+ } else {
+ uid_tag_counters = &tag_stat_entry->counters;
+ }
+
+ if (acct_tag) {
+ /* Create the child {acct_tag, uid_tag} and hook up parent. */
+ new_tag_stat = create_if_tag_stat(iface_entry, tag);
+ if (!new_tag_stat)
+ goto unlock;
+ new_tag_stat->parent_counters = uid_tag_counters;
+ } else {
+ /*
+ * For new_tag_stat to be still NULL here would require:
+ * {0, uid_tag} exists
+ * and {acct_tag, uid_tag} doesn't exist
+ * AND acct_tag == 0.
+ * Impossible. This reassures us that new_tag_stat
+ * below will always be assigned.
+ */
+ BUG_ON(!new_tag_stat);
+ }
+ tag_stat_update(new_tag_stat, direction, proto, bytes);
+unlock:
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static int iface_netdev_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr) {
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: netdev_event(): "
+ "ev=0x%lx/%s netdev=%p->name=%s\n",
+ event, netdev_evt_str(event), dev, dev ? dev->name : "");
+
+ switch (event) {
+ case NETDEV_UP:
+ iface_stat_create(dev, NULL);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static int iface_inet6addr_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct inet6_ifaddr *ifa = ptr;
+ struct net_device *dev;
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: inet6addr_event(): "
+ "ev=0x%lx/%s ifa=%p\n",
+ event, netdev_evt_str(event), ifa);
+
+ switch (event) {
+ case NETDEV_UP:
+ BUG_ON(!ifa || !ifa->idev);
+ dev = (struct net_device *)ifa->idev->dev;
+ iface_stat_create_ipv6(dev, ifa);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ BUG_ON(!ifa || !ifa->idev);
+ dev = (struct net_device *)ifa->idev->dev;
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static int iface_inetaddr_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = ptr;
+ struct net_device *dev;
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: inetaddr_event(): "
+ "ev=0x%lx/%s ifa=%p\n",
+ event, netdev_evt_str(event), ifa);
+
+ switch (event) {
+ case NETDEV_UP:
+ BUG_ON(!ifa || !ifa->ifa_dev);
+ dev = ifa->ifa_dev->dev;
+ iface_stat_create(dev, ifa);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ BUG_ON(!ifa || !ifa->ifa_dev);
+ dev = ifa->ifa_dev->dev;
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block iface_netdev_notifier_blk = {
+ .notifier_call = iface_netdev_event_handler,
+};
+
+static struct notifier_block iface_inetaddr_notifier_blk = {
+ .notifier_call = iface_inetaddr_event_handler,
+};
+
+static struct notifier_block iface_inet6addr_notifier_blk = {
+ .notifier_call = iface_inet6addr_event_handler,
+};
+
+static const struct seq_operations iface_stat_fmt_proc_seq_ops = {
+ .start = iface_stat_fmt_proc_start,
+ .next = iface_stat_fmt_proc_next,
+ .stop = iface_stat_fmt_proc_stop,
+ .show = iface_stat_fmt_proc_show,
+};
+
+static int proc_iface_stat_fmt_open(struct inode *inode, struct file *file)
+{
+ struct proc_iface_stat_fmt_info *s;
+
+ s = __seq_open_private(file, &iface_stat_fmt_proc_seq_ops,
+ sizeof(struct proc_iface_stat_fmt_info));
+ if (!s)
+ return -ENOMEM;
+
+ s->fmt = (uintptr_t)PDE_DATA(inode);
+ return 0;
+}
+
+static const struct file_operations proc_iface_stat_fmt_fops = {
+ .open = proc_iface_stat_fmt_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static int __init iface_stat_init(struct proc_dir_entry *parent_procdir)
+{
+ int err;
+
+ iface_stat_procdir = proc_mkdir(iface_stat_procdirname, parent_procdir);
+ if (!iface_stat_procdir) {
+ pr_err("qtaguid: iface_stat: init failed to create proc entry\n");
+ err = -1;
+ goto err;
+ }
+
+ iface_stat_all_procfile = proc_create_data(iface_stat_all_procfilename,
+ proc_iface_perms,
+ parent_procdir,
+ &proc_iface_stat_fmt_fops,
+ (void *)1 /* fmt1 */);
+ if (!iface_stat_all_procfile) {
+ pr_err("qtaguid: iface_stat: init "
+ " failed to create stat_old proc entry\n");
+ err = -1;
+ goto err_zap_entry;
+ }
+
+ iface_stat_fmt_procfile = proc_create_data(iface_stat_fmt_procfilename,
+ proc_iface_perms,
+ parent_procdir,
+ &proc_iface_stat_fmt_fops,
+ (void *)2 /* fmt2 */);
+ if (!iface_stat_fmt_procfile) {
+ pr_err("qtaguid: iface_stat: init "
+ " failed to create stat_all proc entry\n");
+ err = -1;
+ goto err_zap_all_stats_entry;
+ }
+
+
+ err = register_netdevice_notifier(&iface_netdev_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register dev event handler\n");
+ goto err_zap_all_stats_entries;
+ }
+ err = register_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register ipv4 dev event handler\n");
+ goto err_unreg_nd;
+ }
+
+ err = register_inet6addr_notifier(&iface_inet6addr_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register ipv6 dev event handler\n");
+ goto err_unreg_ip4_addr;
+ }
+ return 0;
+
+err_unreg_ip4_addr:
+ unregister_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+err_unreg_nd:
+ unregister_netdevice_notifier(&iface_netdev_notifier_blk);
+err_zap_all_stats_entries:
+ remove_proc_entry(iface_stat_fmt_procfilename, parent_procdir);
+err_zap_all_stats_entry:
+ remove_proc_entry(iface_stat_all_procfilename, parent_procdir);
+err_zap_entry:
+ remove_proc_entry(iface_stat_procdirname, parent_procdir);
+err:
+ return err;
+}
+
+static struct sock *qtaguid_find_sk(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ struct sock *sk;
+ unsigned int hook_mask = (1 << par->hooknum);
+
+ MT_DEBUG("qtaguid[%d]: find_sk(skb=%p) family=%d\n",
+ par->hooknum, skb, par->family);
+
+ /*
+ * Let's not abuse the the xt_socket_get*_sk(), or else it will
+ * return garbage SKs.
+ */
+ if (!(hook_mask & XT_SOCKET_SUPPORTED_HOOKS))
+ return NULL;
+
+ switch (par->family) {
+ case NFPROTO_IPV6:
+ sk = xt_socket_lookup_slow_v6(dev_net(skb->dev), skb, par->in);
+ break;
+ case NFPROTO_IPV4:
+ sk = xt_socket_lookup_slow_v4(dev_net(skb->dev), skb, par->in);
+ break;
+ default:
+ return NULL;
+ }
+
+ if (sk) {
+ MT_DEBUG("qtaguid[%d]: %p->sk_proto=%u->sk_state=%d\n",
+ par->hooknum, sk, sk->sk_protocol, sk->sk_state);
+ }
+ return sk;
+}
+
+static void account_for_uid(const struct sk_buff *skb,
+ const struct sock *alternate_sk, uid_t uid,
+ struct xt_action_param *par)
+{
+ const struct net_device *el_dev;
+ enum ifs_tx_rx direction;
+ int proto;
+
+ get_dev_and_dir(skb, par, &direction, &el_dev);
+ proto = ipx_proto(skb, par);
+ MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d dir=%d\n",
+ par->hooknum, el_dev->name, el_dev->type,
+ par->family, proto, direction);
+
+ if_tag_stat_update(el_dev->name, uid,
+ skb->sk ? skb->sk : alternate_sk,
+ direction,
+ proto, skb->len);
+}
+
+static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_qtaguid_match_info *info = par->matchinfo;
+ const struct file *filp;
+ bool got_sock = false;
+ struct sock *sk;
+ kuid_t sock_uid;
+ bool res;
+ bool set_sk_callback_lock = false;
+ /*
+ * TODO: unhack how to force just accounting.
+ * For now we only do tag stats when the uid-owner is not requested
+ */
+ bool do_tag_stat = !(info->match & XT_QTAGUID_UID);
+
+ if (unlikely(module_passive))
+ return (info->match ^ info->invert) == 0;
+
+ MT_DEBUG("qtaguid[%d]: entered skb=%p par->in=%p/out=%p fam=%d\n",
+ par->hooknum, skb, par->in, par->out, par->family);
+
+ atomic64_inc(&qtu_events.match_calls);
+ if (skb == NULL) {
+ res = (info->match ^ info->invert) == 0;
+ goto ret_res;
+ }
+
+ switch (par->hooknum) {
+ case NF_INET_PRE_ROUTING:
+ case NF_INET_POST_ROUTING:
+ atomic64_inc(&qtu_events.match_calls_prepost);
+ iface_stat_update_from_skb(skb, par);
+ /*
+ * We are done in pre/post. The skb will get processed
+ * further alter.
+ */
+ res = (info->match ^ info->invert);
+ goto ret_res;
+ break;
+ /* default: Fall through and do UID releated work */
+ }
+
+ sk = skb_to_full_sk(skb);
+ /*
+ * When in TCP_TIME_WAIT the sk is not a "struct sock" but
+ * "struct inet_timewait_sock" which is missing fields.
+ * So we ignore it.
+ */
+ if (sk && sk->sk_state == TCP_TIME_WAIT)
+ sk = NULL;
+ if (sk == NULL) {
+ /*
+ * A missing sk->sk_socket happens when packets are in-flight
+ * and the matching socket is already closed and gone.
+ */
+ sk = qtaguid_find_sk(skb, par);
+ /*
+ * TCP_NEW_SYN_RECV are not "struct sock" but "struct request_sock"
+ * where we can get a pointer to a full socket to retrieve uid/gid.
+ * When in TCP_TIME_WAIT, sk is a struct inet_timewait_sock
+ * which is missing fields and does not contain any reference
+ * to a full socket, so just ignore the socket.
+ */
+ if (sk && sk->sk_state == TCP_NEW_SYN_RECV) {
+ sock_gen_put(sk);
+ sk = sk_to_full_sk(sk);
+ } else if (sk && (!sk_fullsock(sk) || sk->sk_state == TCP_TIME_WAIT)) {
+ sock_gen_put(sk);
+ sk = NULL;
+ } else {
+ /*
+ * If we got the socket from the find_sk(), we will need to put
+ * it back, as nf_tproxy_get_sock_v4() got it.
+ */
+ got_sock = sk;
+ }
+ if (sk)
+ atomic64_inc(&qtu_events.match_found_sk_in_ct);
+ else
+ atomic64_inc(&qtu_events.match_found_no_sk_in_ct);
+ } else {
+ atomic64_inc(&qtu_events.match_found_sk);
+ }
+ MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d fam=%d proto=%d\n",
+ par->hooknum, sk, got_sock, par->family, ipx_proto(skb, par));
+
+ if (!sk) {
+ /*
+ * Here, the qtaguid_find_sk() using connection tracking
+ * couldn't find the owner, so for now we just count them
+ * against the system.
+ */
+ if (do_tag_stat)
+ account_for_uid(skb, sk, 0, par);
+ MT_DEBUG("qtaguid[%d]: leaving (sk=NULL)\n", par->hooknum);
+ res = (info->match ^ info->invert) == 0;
+ atomic64_inc(&qtu_events.match_no_sk);
+ goto put_sock_ret_res;
+ } else if (info->match & info->invert & XT_QTAGUID_SOCKET) {
+ res = false;
+ goto put_sock_ret_res;
+ }
+ sock_uid = sk->sk_uid;
+ if (do_tag_stat)
+ account_for_uid(skb, sk, from_kuid(&init_user_ns, sock_uid),
+ par);
+
+ /*
+ * The following two tests fail the match when:
+ * id not in range AND no inverted condition requested
+ * or id in range AND inverted condition requested
+ * Thus (!a && b) || (a && !b) == a ^ b
+ */
+ if (info->match & XT_QTAGUID_UID) {
+ kuid_t uid_min = make_kuid(&init_user_ns, info->uid_min);
+ kuid_t uid_max = make_kuid(&init_user_ns, info->uid_max);
+
+ if ((uid_gte(sock_uid, uid_min) &&
+ uid_lte(sock_uid, uid_max)) ^
+ !(info->invert & XT_QTAGUID_UID)) {
+ MT_DEBUG("qtaguid[%d]: leaving uid not matching\n",
+ par->hooknum);
+ res = false;
+ goto put_sock_ret_res;
+ }
+ }
+ if (info->match & XT_QTAGUID_GID) {
+ kgid_t gid_min = make_kgid(&init_user_ns, info->gid_min);
+ kgid_t gid_max = make_kgid(&init_user_ns, info->gid_max);
+ set_sk_callback_lock = true;
+ read_lock_bh(&sk->sk_callback_lock);
+ MT_DEBUG("qtaguid[%d]: sk=%p->sk_socket=%p->file=%p\n",
+ par->hooknum, sk, sk->sk_socket,
+ sk->sk_socket ? sk->sk_socket->file : (void *)-1LL);
+ filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+ if (!filp) {
+ res = ((info->match ^ info->invert) &
+ XT_QTAGUID_GID) == 0;
+ atomic64_inc(&qtu_events.match_no_sk_gid);
+ goto put_sock_ret_res;
+ }
+ MT_DEBUG("qtaguid[%d]: filp...uid=%u\n",
+ par->hooknum, filp ?
+ from_kuid(&init_user_ns, filp->f_cred->fsuid) : -1);
+ if ((gid_gte(filp->f_cred->fsgid, gid_min) &&
+ gid_lte(filp->f_cred->fsgid, gid_max)) ^
+ !(info->invert & XT_QTAGUID_GID)) {
+ MT_DEBUG("qtaguid[%d]: leaving gid not matching\n",
+ par->hooknum);
+ res = false;
+ goto put_sock_ret_res;
+ }
+ }
+ MT_DEBUG("qtaguid[%d]: leaving matched\n", par->hooknum);
+ res = true;
+
+put_sock_ret_res:
+ if (got_sock)
+ sock_gen_put(sk);
+ if (set_sk_callback_lock)
+ read_unlock_bh(&sk->sk_callback_lock);
+ret_res:
+ MT_DEBUG("qtaguid[%d]: left %d\n", par->hooknum, res);
+ return res;
+}
+
+#ifdef DDEBUG
+/*
+ * This function is not in xt_qtaguid_print.c because of locks visibility.
+ * The lock of sock_tag_list must be aquired before calling this function
+ */
+static void prdebug_full_state_locked(int indent_level, const char *fmt, ...)
+{
+ va_list args;
+ char *fmt_buff;
+ char *buff;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ fmt_buff = kasprintf(GFP_ATOMIC,
+ "qtaguid: %s(): %s {\n", __func__, fmt);
+ BUG_ON(!fmt_buff);
+ va_start(args, fmt);
+ buff = kvasprintf(GFP_ATOMIC,
+ fmt_buff, args);
+ BUG_ON(!buff);
+ pr_debug("%s", buff);
+ kfree(fmt_buff);
+ kfree(buff);
+ va_end(args);
+
+ prdebug_sock_tag_tree(indent_level, &sock_tag_tree);
+
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree);
+ prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ prdebug_iface_stat_list(indent_level, &iface_stat_list);
+ spin_unlock_bh(&iface_stat_list_lock);
+
+ pr_debug("qtaguid: %s(): }\n", __func__);
+}
+#else
+static void prdebug_full_state_locked(int indent_level, const char *fmt, ...) {}
+#endif
+
+struct proc_ctrl_print_info {
+ struct sock *sk; /* socket found by reading to sk_pos */
+ loff_t sk_pos;
+};
+
+static void *qtaguid_ctrl_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct proc_ctrl_print_info *pcpi = m->private;
+ struct sock_tag *sock_tag_entry = v;
+ struct rb_node *node;
+
+ (*pos)++;
+
+ if (!v || v == SEQ_START_TOKEN)
+ return NULL;
+
+ node = rb_next(&sock_tag_entry->sock_node);
+ if (!node) {
+ pcpi->sk = NULL;
+ sock_tag_entry = SEQ_START_TOKEN;
+ } else {
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ pcpi->sk = sock_tag_entry->sk;
+ }
+ pcpi->sk_pos = *pos;
+ return sock_tag_entry;
+}
+
+static void *qtaguid_ctrl_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_ctrl_print_info *pcpi = m->private;
+ struct sock_tag *sock_tag_entry;
+ struct rb_node *node;
+
+ spin_lock_bh(&sock_tag_list_lock);
+
+ if (unlikely(module_passive))
+ return NULL;
+
+ if (*pos == 0) {
+ pcpi->sk_pos = 0;
+ node = rb_first(&sock_tag_tree);
+ if (!node) {
+ pcpi->sk = NULL;
+ return SEQ_START_TOKEN;
+ }
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ pcpi->sk = sock_tag_entry->sk;
+ } else {
+ sock_tag_entry = (pcpi->sk ? get_sock_stat_nl(pcpi->sk) :
+ NULL) ?: SEQ_START_TOKEN;
+ if (*pos != pcpi->sk_pos) {
+ /* seq_read skipped a next call */
+ *pos = pcpi->sk_pos;
+ return qtaguid_ctrl_proc_next(m, sock_tag_entry, pos);
+ }
+ }
+ return sock_tag_entry;
+}
+
+static void qtaguid_ctrl_proc_stop(struct seq_file *m, void *v)
+{
+ spin_unlock_bh(&sock_tag_list_lock);
+}
+
+/*
+ * Procfs reader to get all active socket tags using style "1)" as described in
+ * fs/proc/generic.c
+ */
+static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v)
+{
+ struct sock_tag *sock_tag_entry = v;
+ uid_t uid;
+
+ CT_DEBUG("qtaguid: proc ctrl pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+ if (sock_tag_entry != SEQ_START_TOKEN) {
+ int sk_ref_count;
+ uid = get_uid_from_tag(sock_tag_entry->tag);
+ CT_DEBUG("qtaguid: proc_read(): sk=%p tag=0x%llx (uid=%u) "
+ "pid=%u\n",
+ sock_tag_entry->sk,
+ sock_tag_entry->tag,
+ uid,
+ sock_tag_entry->pid
+ );
+ sk_ref_count = atomic_read(
+ &sock_tag_entry->sk->sk_refcnt);
+ seq_printf(m, "sock=%pK tag=0x%llx (uid=%u) pid=%u "
+ "f_count=%d\n",
+ sock_tag_entry->sk,
+ sock_tag_entry->tag, uid,
+ sock_tag_entry->pid, sk_ref_count);
+ } else {
+ seq_printf(m, "events: sockets_tagged=%llu "
+ "sockets_untagged=%llu "
+ "counter_set_changes=%llu "
+ "delete_cmds=%llu "
+ "iface_events=%llu "
+ "match_calls=%llu "
+ "match_calls_prepost=%llu "
+ "match_found_sk=%llu "
+ "match_found_sk_in_ct=%llu "
+ "match_found_no_sk_in_ct=%llu "
+ "match_no_sk=%llu "
+ "match_no_sk_gid=%llu\n",
+ (u64)atomic64_read(&qtu_events.sockets_tagged),
+ (u64)atomic64_read(&qtu_events.sockets_untagged),
+ (u64)atomic64_read(&qtu_events.counter_set_changes),
+ (u64)atomic64_read(&qtu_events.delete_cmds),
+ (u64)atomic64_read(&qtu_events.iface_events),
+ (u64)atomic64_read(&qtu_events.match_calls),
+ (u64)atomic64_read(&qtu_events.match_calls_prepost),
+ (u64)atomic64_read(&qtu_events.match_found_sk),
+ (u64)atomic64_read(&qtu_events.match_found_sk_in_ct),
+ (u64)atomic64_read(&qtu_events.match_found_no_sk_in_ct),
+ (u64)atomic64_read(&qtu_events.match_no_sk),
+ (u64)atomic64_read(&qtu_events.match_no_sk_gid));
+
+ /* Count the following as part of the last item_index. No need
+ * to lock the sock_tag_list here since it is already locked when
+ * starting the seq_file operation
+ */
+ prdebug_full_state_locked(0, "proc ctrl");
+ }
+
+ return 0;
+}
+
+/*
+ * Delete socket tags, and stat tags associated with a given
+ * accouting tag and uid.
+ */
+static int ctrl_cmd_delete(const char *input)
+{
+ char cmd;
+ int uid_int;
+ kuid_t uid;
+ uid_t entry_uid;
+ tag_t acct_tag;
+ tag_t tag;
+ int res, argc;
+ struct iface_stat *iface_entry;
+ struct rb_node *node;
+ struct sock_tag *st_entry;
+ struct rb_root st_to_free_tree = RB_ROOT;
+ struct tag_stat *ts_entry;
+ struct tag_counter_set *tcs_entry;
+ struct tag_ref *tr_entry;
+ struct uid_tag_data *utd_entry;
+
+ argc = sscanf(input, "%c %llu %u", &cmd, &acct_tag, &uid_int);
+ uid = make_kuid(&init_user_ns, uid_int);
+ CT_DEBUG("qtaguid: ctrl_delete(%s): argc=%d cmd=%c "
+ "user_tag=0x%llx uid=%u\n", input, argc, cmd,
+ acct_tag, uid_int);
+ if (argc < 2) {
+ res = -EINVAL;
+ goto err;
+ }
+ if (!valid_atag(acct_tag)) {
+ pr_info("qtaguid: ctrl_delete(%s): invalid tag\n", input);
+ res = -EINVAL;
+ goto err;
+ }
+ if (argc < 3) {
+ uid = current_fsuid();
+ uid_int = from_kuid(&init_user_ns, uid);
+ } else if (!can_impersonate_uid(uid)) {
+ pr_info("qtaguid: ctrl_delete(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+ res = -EPERM;
+ goto err;
+ }
+
+ tag = combine_atag_with_uid(acct_tag, uid_int);
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "looking for tag=0x%llx (uid=%u)\n",
+ input, tag, uid_int);
+
+ /* Delete socket tags */
+ spin_lock_bh(&sock_tag_list_lock);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ node = rb_first(&sock_tag_tree);
+ while (node) {
+ st_entry = rb_entry(node, struct sock_tag, sock_node);
+ entry_uid = get_uid_from_tag(st_entry->tag);
+ node = rb_next(node);
+ if (entry_uid != uid_int)
+ continue;
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): st tag=0x%llx (uid=%u)\n",
+ input, st_entry->tag, entry_uid);
+
+ if (!acct_tag || st_entry->tag == tag) {
+ rb_erase(&st_entry->sock_node, &sock_tag_tree);
+ /* Can't sockfd_put() within spinlock, do it later. */
+ sock_tag_tree_insert(st_entry, &st_to_free_tree);
+ tr_entry = lookup_tag_ref(st_entry->tag, NULL);
+ BUG_ON(tr_entry->num_sock_tags <= 0);
+ tr_entry->num_sock_tags--;
+ /*
+ * TODO: remove if, and start failing.
+ * This is a hack to work around the fact that in some
+ * places we have "if (IS_ERR_OR_NULL(pqd_entry))"
+ * and are trying to work around apps
+ * that didn't open the /dev/xt_qtaguid.
+ */
+ if (st_entry->list.next && st_entry->list.prev)
+ list_del(&st_entry->list);
+ }
+ }
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+
+ sock_tag_tree_erase(&st_to_free_tree);
+
+ /* Delete tag counter-sets */
+ spin_lock_bh(&tag_counter_set_list_lock);
+ /* Counter sets are only on the uid tag, not full tag */
+ tcs_entry = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (tcs_entry) {
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "erase tcs: tag=0x%llx (uid=%u) set=%d\n",
+ input,
+ tcs_entry->tn.tag,
+ get_uid_from_tag(tcs_entry->tn.tag),
+ tcs_entry->active_set);
+ rb_erase(&tcs_entry->tn.node, &tag_counter_set_tree);
+ kfree(tcs_entry);
+ }
+ spin_unlock_bh(&tag_counter_set_list_lock);
+
+ /*
+ * If acct_tag is 0, then all entries belonging to uid are
+ * erased.
+ */
+ spin_lock_bh(&iface_stat_list_lock);
+ list_for_each_entry(iface_entry, &iface_stat_list, list) {
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+ node = rb_first(&iface_entry->tag_stat_tree);
+ while (node) {
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ entry_uid = get_uid_from_tag(ts_entry->tn.tag);
+ node = rb_next(node);
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "ts tag=0x%llx (uid=%u)\n",
+ input, ts_entry->tn.tag, entry_uid);
+
+ if (entry_uid != uid_int)
+ continue;
+ if (!acct_tag || ts_entry->tn.tag == tag) {
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "erase ts: %s 0x%llx %u\n",
+ input, iface_entry->ifname,
+ get_atag_from_tag(ts_entry->tn.tag),
+ entry_uid);
+ rb_erase(&ts_entry->tn.node,
+ &iface_entry->tag_stat_tree);
+ kfree(ts_entry);
+ }
+ }
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ }
+ spin_unlock_bh(&iface_stat_list_lock);
+
+ /* Cleanup the uid_tag_data */
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ node = rb_first(&uid_tag_data_tree);
+ while (node) {
+ utd_entry = rb_entry(node, struct uid_tag_data, node);
+ entry_uid = utd_entry->uid;
+ node = rb_next(node);
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "utd uid=%u\n",
+ input, entry_uid);
+
+ if (entry_uid != uid_int)
+ continue;
+ /*
+ * Go over the tag_refs, and those that don't have
+ * sock_tags using them are freed.
+ */
+ put_tag_ref_tree(tag, utd_entry);
+ put_utd_entry(utd_entry);
+ }
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+
+ atomic64_inc(&qtu_events.delete_cmds);
+ res = 0;
+
+err:
+ return res;
+}
+
+static int ctrl_cmd_counter_set(const char *input)
+{
+ char cmd;
+ uid_t uid = 0;
+ tag_t tag;
+ int res, argc;
+ struct tag_counter_set *tcs;
+ int counter_set;
+
+ argc = sscanf(input, "%c %d %u", &cmd, &counter_set, &uid);
+ CT_DEBUG("qtaguid: ctrl_counterset(%s): argc=%d cmd=%c "
+ "set=%d uid=%u\n", input, argc, cmd,
+ counter_set, uid);
+ if (argc != 3) {
+ res = -EINVAL;
+ goto err;
+ }
+ if (counter_set < 0 || counter_set >= IFS_MAX_COUNTER_SETS) {
+ pr_info("qtaguid: ctrl_counterset(%s): invalid counter_set range\n",
+ input);
+ res = -EINVAL;
+ goto err;
+ }
+ if (!can_manipulate_uids()) {
+ pr_info("qtaguid: ctrl_counterset(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+ res = -EPERM;
+ goto err;
+ }
+
+ tag = make_tag_from_uid(uid);
+ spin_lock_bh(&tag_counter_set_list_lock);
+ tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (!tcs) {
+ tcs = kzalloc(sizeof(*tcs), GFP_ATOMIC);
+ if (!tcs) {
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ pr_err("qtaguid: ctrl_counterset(%s): "
+ "failed to alloc counter set\n",
+ input);
+ res = -ENOMEM;
+ goto err;
+ }
+ tcs->tn.tag = tag;
+ tag_counter_set_tree_insert(tcs, &tag_counter_set_tree);
+ CT_DEBUG("qtaguid: ctrl_counterset(%s): added tcs tag=0x%llx "
+ "(uid=%u) set=%d\n",
+ input, tag, get_uid_from_tag(tag), counter_set);
+ }
+ tcs->active_set = counter_set;
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ atomic64_inc(&qtu_events.counter_set_changes);
+ res = 0;
+
+err:
+ return res;
+}
+
+static int ctrl_cmd_tag(const char *input)
+{
+ char cmd;
+ int sock_fd = 0;
+ kuid_t uid;
+ unsigned int uid_int = 0;
+ tag_t acct_tag = make_atag_from_value(0);
+ tag_t full_tag;
+ struct socket *el_socket;
+ int res, argc;
+ struct sock_tag *sock_tag_entry;
+ struct tag_ref *tag_ref_entry;
+ struct uid_tag_data *uid_tag_data_entry;
+ struct proc_qtu_data *pqd_entry;
+
+ /* Unassigned args will get defaulted later. */
+ argc = sscanf(input, "%c %d %llu %u", &cmd, &sock_fd, &acct_tag, &uid_int);
+ uid = make_kuid(&init_user_ns, uid_int);
+ CT_DEBUG("qtaguid: ctrl_tag(%s): argc=%d cmd=%c sock_fd=%d "
+ "acct_tag=0x%llx uid=%u\n", input, argc, cmd, sock_fd,
+ acct_tag, uid_int);
+ if (argc < 2) {
+ res = -EINVAL;
+ goto err;
+ }
+ el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */
+ if (!el_socket) {
+ pr_info("qtaguid: ctrl_tag(%s): failed to lookup"
+ " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+ input, sock_fd, res, current->pid, current->tgid,
+ from_kuid(&init_user_ns, current_fsuid()));
+ goto err;
+ }
+ CT_DEBUG("qtaguid: ctrl_tag(%s): socket->...->sk_refcnt=%d ->sk=%p\n",
+ input, atomic_read(&el_socket->sk->sk_refcnt),
+ el_socket->sk);
+ if (argc < 3) {
+ acct_tag = make_atag_from_value(0);
+ } else if (!valid_atag(acct_tag)) {
+ pr_info("qtaguid: ctrl_tag(%s): invalid tag\n", input);
+ res = -EINVAL;
+ goto err_put;
+ }
+ CT_DEBUG("qtaguid: ctrl_tag(%s): "
+ "pid=%u tgid=%u uid=%u euid=%u fsuid=%u "
+ "ctrl.gid=%u in_group()=%d in_egroup()=%d\n",
+ input, current->pid, current->tgid,
+ from_kuid(&init_user_ns, current_uid()),
+ from_kuid(&init_user_ns, current_euid()),
+ from_kuid(&init_user_ns, current_fsuid()),
+ from_kgid(&init_user_ns, xt_qtaguid_ctrl_file->gid),
+ in_group_p(xt_qtaguid_ctrl_file->gid),
+ in_egroup_p(xt_qtaguid_ctrl_file->gid));
+ if (argc < 4) {
+ uid = current_fsuid();
+ uid_int = from_kuid(&init_user_ns, uid);
+ } else if (!can_impersonate_uid(uid)) {
+ pr_info("qtaguid: ctrl_tag(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+ res = -EPERM;
+ goto err_put;
+ }
+ full_tag = combine_atag_with_uid(acct_tag, uid_int);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+ tag_ref_entry = get_tag_ref(full_tag, &uid_tag_data_entry);
+ if (IS_ERR(tag_ref_entry)) {
+ res = PTR_ERR(tag_ref_entry);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+ goto err_put;
+ }
+ tag_ref_entry->num_sock_tags++;
+ if (sock_tag_entry) {
+ struct tag_ref *prev_tag_ref_entry;
+
+ CT_DEBUG("qtaguid: ctrl_tag(%s): retag for sk=%p "
+ "st@%p ...->sk_refcnt=%d\n",
+ input, el_socket->sk, sock_tag_entry,
+ atomic_read(&el_socket->sk->sk_refcnt));
+ prev_tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag,
+ &uid_tag_data_entry);
+ BUG_ON(IS_ERR_OR_NULL(prev_tag_ref_entry));
+ BUG_ON(prev_tag_ref_entry->num_sock_tags <= 0);
+ prev_tag_ref_entry->num_sock_tags--;
+ sock_tag_entry->tag = full_tag;
+ } else {
+ CT_DEBUG("qtaguid: ctrl_tag(%s): newtag for sk=%p\n",
+ input, el_socket->sk);
+ sock_tag_entry = kzalloc(sizeof(*sock_tag_entry),
+ GFP_ATOMIC);
+ if (!sock_tag_entry) {
+ pr_err("qtaguid: ctrl_tag(%s): "
+ "socket tag alloc failed\n",
+ input);
+ BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+ tag_ref_entry->num_sock_tags--;
+ free_tag_ref_from_utd_entry(tag_ref_entry,
+ uid_tag_data_entry);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+ res = -ENOMEM;
+ goto err_put;
+ }
+ /*
+ * Hold the sk refcount here to make sure the sk pointer cannot
+ * be freed and reused
+ */
+ sock_hold(el_socket->sk);
+ sock_tag_entry->sk = el_socket->sk;
+ sock_tag_entry->pid = current->tgid;
+ sock_tag_entry->tag = combine_atag_with_uid(acct_tag, uid_int);
+ pqd_entry = proc_qtu_data_tree_search(
+ &proc_qtu_data_tree, current->tgid);
+ /*
+ * TODO: remove if, and start failing.
+ * At first, we want to catch user-space code that is not
+ * opening the /dev/xt_qtaguid.
+ */
+ if (IS_ERR_OR_NULL(pqd_entry))
+ pr_warn_once(
+ "qtaguid: %s(): "
+ "User space forgot to open /dev/xt_qtaguid? "
+ "pid=%u tgid=%u uid=%u\n", __func__,
+ current->pid, current->tgid,
+ from_kuid(&init_user_ns, current_fsuid()));
+ else
+ list_add(&sock_tag_entry->list,
+ &pqd_entry->sock_tag_list);
+
+ sock_tag_tree_insert(sock_tag_entry, &sock_tag_tree);
+ atomic64_inc(&qtu_events.sockets_tagged);
+ }
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+ /* We keep the ref to the sk until it is untagged */
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done st@%p ...->sk_refcnt=%d\n",
+ input, sock_tag_entry,
+ atomic_read(&el_socket->sk->sk_refcnt));
+ sockfd_put(el_socket);
+ return 0;
+
+err_put:
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done. ...->sk_refcnt=%d\n",
+ input, atomic_read(&el_socket->sk->sk_refcnt) - 1);
+ /* Release the sock_fd that was grabbed by sockfd_lookup(). */
+ sockfd_put(el_socket);
+ return res;
+
+err:
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done.\n", input);
+ return res;
+}
+
+static int ctrl_cmd_untag(const char *input)
+{
+ char cmd;
+ int sock_fd = 0;
+ struct socket *el_socket;
+ int res, argc;
+
+ argc = sscanf(input, "%c %d", &cmd, &sock_fd);
+ CT_DEBUG("qtaguid: ctrl_untag(%s): argc=%d cmd=%c sock_fd=%d\n",
+ input, argc, cmd, sock_fd);
+ if (argc < 2) {
+ res = -EINVAL;
+ return res;
+ }
+ el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */
+ if (!el_socket) {
+ pr_info("qtaguid: ctrl_untag(%s): failed to lookup"
+ " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+ input, sock_fd, res, current->pid, current->tgid,
+ from_kuid(&init_user_ns, current_fsuid()));
+ return res;
+ }
+ CT_DEBUG("qtaguid: ctrl_untag(%s): socket->...->f_count=%ld ->sk=%p\n",
+ input, atomic_long_read(&el_socket->file->f_count),
+ el_socket->sk);
+ res = qtaguid_untag(el_socket, false);
+ sockfd_put(el_socket);
+ return res;
+}
+
+int qtaguid_untag(struct socket *el_socket, bool kernel)
+{
+ int res;
+ pid_t pid;
+ struct sock_tag *sock_tag_entry;
+ struct tag_ref *tag_ref_entry;
+ struct uid_tag_data *utd_entry;
+ struct proc_qtu_data *pqd_entry;
+
+ spin_lock_bh(&sock_tag_list_lock);
+ sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+ if (!sock_tag_entry) {
+ spin_unlock_bh(&sock_tag_list_lock);
+ res = -EINVAL;
+ return res;
+ }
+ /*
+ * The socket already belongs to the current process
+ * so it can do whatever it wants to it.
+ */
+ rb_erase(&sock_tag_entry->sock_node, &sock_tag_tree);
+
+ tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag, &utd_entry);
+ BUG_ON(!tag_ref_entry);
+ BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ if (kernel)
+ pid = sock_tag_entry->pid;
+ else
+ pid = current->tgid;
+ pqd_entry = proc_qtu_data_tree_search(
+ &proc_qtu_data_tree, pid);
+ /*
+ * TODO: remove if, and start failing.
+ * At first, we want to catch user-space code that is not
+ * opening the /dev/xt_qtaguid.
+ */
+ if (IS_ERR_OR_NULL(pqd_entry) || !sock_tag_entry->list.next) {
+ pr_warn_once("qtaguid: %s(): "
+ "User space forgot to open /dev/xt_qtaguid? "
+ "pid=%u tgid=%u sk_pid=%u, uid=%u\n", __func__,
+ current->pid, current->tgid, sock_tag_entry->pid,
+ from_kuid(&init_user_ns, current_fsuid()));
+ } else {
+ list_del(&sock_tag_entry->list);
+ }
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ /*
+ * We don't free tag_ref from the utd_entry here,
+ * only during a cmd_delete().
+ */
+ tag_ref_entry->num_sock_tags--;
+ spin_unlock_bh(&sock_tag_list_lock);
+ /*
+ * Release the sock_fd that was grabbed at tag time.
+ */
+ sock_put(sock_tag_entry->sk);
+ CT_DEBUG("qtaguid: done. st@%p ...->sk_refcnt=%d\n",
+ sock_tag_entry,
+ atomic_read(&el_socket->sk->sk_refcnt));
+
+ kfree(sock_tag_entry);
+ atomic64_inc(&qtu_events.sockets_untagged);
+
+ return 0;
+}
+
+static ssize_t qtaguid_ctrl_parse(const char *input, size_t count)
+{
+ char cmd;
+ ssize_t res;
+
+ CT_DEBUG("qtaguid: ctrl(%s): pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+ cmd = input[0];
+ /* Collect params for commands */
+ switch (cmd) {
+ case 'd':
+ res = ctrl_cmd_delete(input);
+ break;
+
+ case 's':
+ res = ctrl_cmd_counter_set(input);
+ break;
+
+ case 't':
+ res = ctrl_cmd_tag(input);
+ break;
+
+ case 'u':
+ res = ctrl_cmd_untag(input);
+ break;
+
+ default:
+ res = -EINVAL;
+ goto err;
+ }
+ if (!res)
+ res = count;
+err:
+ CT_DEBUG("qtaguid: ctrl(%s): res=%zd\n", input, res);
+ return res;
+}
+
+#define MAX_QTAGUID_CTRL_INPUT_LEN 255
+static ssize_t qtaguid_ctrl_proc_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *offp)
+{
+ char input_buf[MAX_QTAGUID_CTRL_INPUT_LEN];
+
+ if (unlikely(module_passive))
+ return count;
+
+ if (count >= MAX_QTAGUID_CTRL_INPUT_LEN)
+ return -EINVAL;
+
+ if (copy_from_user(input_buf, buffer, count))
+ return -EFAULT;
+
+ input_buf[count] = '\0';
+ return qtaguid_ctrl_parse(input_buf, count);
+}
+
+struct proc_print_info {
+ struct iface_stat *iface_entry;
+ int item_index;
+ tag_t tag; /* tag found by reading to tag_pos */
+ off_t tag_pos;
+ int tag_item_index;
+};
+
+static void pp_stats_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "idx iface acct_tag_hex uid_tag_int cnt_set "
+ "rx_bytes rx_packets "
+ "tx_bytes tx_packets "
+ "rx_tcp_bytes rx_tcp_packets "
+ "rx_udp_bytes rx_udp_packets "
+ "rx_other_bytes rx_other_packets "
+ "tx_tcp_bytes tx_tcp_packets "
+ "tx_udp_bytes tx_udp_packets "
+ "tx_other_bytes tx_other_packets\n");
+}
+
+static int pp_stats_line(struct seq_file *m, struct tag_stat *ts_entry,
+ int cnt_set)
+{
+ struct data_counters *cnts;
+ tag_t tag = ts_entry->tn.tag;
+ uid_t stat_uid = get_uid_from_tag(tag);
+ struct proc_print_info *ppi = m->private;
+ /* Detailed tags are not available to everybody */
+ if (!can_read_other_uid_stats(make_kuid(&init_user_ns,stat_uid))) {
+ CT_DEBUG("qtaguid: stats line: "
+ "%s 0x%llx %u: insufficient priv "
+ "from pid=%u tgid=%u uid=%u stats.gid=%u\n",
+ ppi->iface_entry->ifname,
+ get_atag_from_tag(tag), stat_uid,
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()),
+ from_kgid(&init_user_ns,xt_qtaguid_stats_file->gid));
+ return 0;
+ }
+ ppi->item_index++;
+ cnts = &ts_entry->counters;
+ seq_printf(m, "%d %s 0x%llx %u %u "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu\n",
+ ppi->item_index,
+ ppi->iface_entry->ifname,
+ get_atag_from_tag(tag),
+ stat_uid,
+ cnt_set,
+ dc_sum_bytes(cnts, cnt_set, IFS_RX),
+ dc_sum_packets(cnts, cnt_set, IFS_RX),
+ dc_sum_bytes(cnts, cnt_set, IFS_TX),
+ dc_sum_packets(cnts, cnt_set, IFS_TX),
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+ return seq_has_overflowed(m) ? -ENOSPC : 1;
+}
+
+static bool pp_sets(struct seq_file *m, struct tag_stat *ts_entry)
+{
+ int ret;
+ int counter_set;
+ for (counter_set = 0; counter_set < IFS_MAX_COUNTER_SETS;
+ counter_set++) {
+ ret = pp_stats_line(m, ts_entry, counter_set);
+ if (ret < 0)
+ return false;
+ }
+ return true;
+}
+
+static int qtaguid_stats_proc_iface_stat_ptr_valid(struct iface_stat *ptr)
+{
+ struct iface_stat *iface_entry;
+
+ if (!ptr)
+ return false;
+
+ list_for_each_entry(iface_entry, &iface_stat_list, list)
+ if (iface_entry == ptr)
+ return true;
+ return false;
+}
+
+static void qtaguid_stats_proc_next_iface_entry(struct proc_print_info *ppi)
+{
+ spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ list_for_each_entry_continue(ppi->iface_entry, &iface_stat_list, list) {
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ return;
+ }
+ ppi->iface_entry = NULL;
+}
+
+static void *qtaguid_stats_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct proc_print_info *ppi = m->private;
+ struct tag_stat *ts_entry;
+ struct rb_node *node;
+
+ if (!v) {
+ pr_err("qtaguid: %s(): unexpected v: NULL\n", __func__);
+ return NULL;
+ }
+
+ (*pos)++;
+
+ if (!ppi->iface_entry || unlikely(module_passive))
+ return NULL;
+
+ if (v == SEQ_START_TOKEN)
+ node = rb_first(&ppi->iface_entry->tag_stat_tree);
+ else
+ node = rb_next(&((struct tag_stat *)v)->tn.node);
+
+ while (!node) {
+ qtaguid_stats_proc_next_iface_entry(ppi);
+ if (!ppi->iface_entry)
+ return NULL;
+ node = rb_first(&ppi->iface_entry->tag_stat_tree);
+ }
+
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ ppi->tag = ts_entry->tn.tag;
+ ppi->tag_pos = *pos;
+ ppi->tag_item_index = ppi->item_index;
+ return ts_entry;
+}
+
+static void *qtaguid_stats_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_print_info *ppi = m->private;
+ struct tag_stat *ts_entry = NULL;
+
+ spin_lock_bh(&iface_stat_list_lock);
+
+ if (*pos == 0) {
+ ppi->item_index = 1;
+ ppi->tag_pos = 0;
+ if (list_empty(&iface_stat_list)) {
+ ppi->iface_entry = NULL;
+ } else {
+ ppi->iface_entry = list_first_entry(&iface_stat_list,
+ struct iface_stat,
+ list);
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ }
+ return SEQ_START_TOKEN;
+ }
+ if (!qtaguid_stats_proc_iface_stat_ptr_valid(ppi->iface_entry)) {
+ if (ppi->iface_entry) {
+ pr_err("qtaguid: %s(): iface_entry %p not found\n",
+ __func__, ppi->iface_entry);
+ ppi->iface_entry = NULL;
+ }
+ return NULL;
+ }
+
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+
+ if (!ppi->tag_pos) {
+ /* seq_read skipped first next call */
+ ts_entry = SEQ_START_TOKEN;
+ } else {
+ ts_entry = tag_stat_tree_search(
+ &ppi->iface_entry->tag_stat_tree, ppi->tag);
+ if (!ts_entry) {
+ pr_info("qtaguid: %s(): tag_stat.tag 0x%llx not found. Abort.\n",
+ __func__, ppi->tag);
+ return NULL;
+ }
+ }
+
+ if (*pos == ppi->tag_pos) { /* normal resume */
+ ppi->item_index = ppi->tag_item_index;
+ } else {
+ /* seq_read skipped a next call */
+ *pos = ppi->tag_pos;
+ ts_entry = qtaguid_stats_proc_next(m, ts_entry, pos);
+ }
+
+ return ts_entry;
+}
+
+static void qtaguid_stats_proc_stop(struct seq_file *m, void *v)
+{
+ struct proc_print_info *ppi = m->private;
+ if (ppi->iface_entry)
+ spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/*
+ * Procfs reader to get all tag stats using style "1)" as described in
+ * fs/proc/generic.c
+ * Groups all protocols tx/rx bytes.
+ */
+static int qtaguid_stats_proc_show(struct seq_file *m, void *v)
+{
+ struct tag_stat *ts_entry = v;
+
+ if (v == SEQ_START_TOKEN)
+ pp_stats_header(m);
+ else
+ pp_sets(m, ts_entry);
+
+ return 0;
+}
+
+/*------------------------------------------*/
+static int qtudev_open(struct inode *inode, struct file *file)
+{
+ struct uid_tag_data *utd_entry;
+ struct proc_qtu_data *pqd_entry;
+ struct proc_qtu_data *new_pqd_entry;
+ int res;
+ bool utd_entry_found;
+
+ if (unlikely(qtu_proc_handling_passive))
+ return 0;
+
+ DR_DEBUG("qtaguid: qtudev_open(): pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+ spin_lock_bh(&uid_tag_data_tree_lock);
+
+ /* Look for existing uid data, or alloc one. */
+ utd_entry = get_uid_data(from_kuid(&init_user_ns, current_fsuid()), &utd_entry_found);
+ if (IS_ERR_OR_NULL(utd_entry)) {
+ res = PTR_ERR(utd_entry);
+ goto err_unlock;
+ }
+
+ /* Look for existing PID based proc_data */
+ pqd_entry = proc_qtu_data_tree_search(&proc_qtu_data_tree,
+ current->tgid);
+ if (pqd_entry) {
+ pr_err("qtaguid: qtudev_open(): %u/%u %u "
+ "%s already opened\n",
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()),
+ QTU_DEV_NAME);
+ res = -EBUSY;
+ goto err_unlock_free_utd;
+ }
+
+ new_pqd_entry = kzalloc(sizeof(*new_pqd_entry), GFP_ATOMIC);
+ if (!new_pqd_entry) {
+ pr_err("qtaguid: qtudev_open(): %u/%u %u: "
+ "proc data alloc failed\n",
+ current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+ res = -ENOMEM;
+ goto err_unlock_free_utd;
+ }
+ new_pqd_entry->pid = current->tgid;
+ INIT_LIST_HEAD(&new_pqd_entry->sock_tag_list);
+ new_pqd_entry->parent_tag_data = utd_entry;
+ utd_entry->num_pqd++;
+
+ proc_qtu_data_tree_insert(new_pqd_entry,
+ &proc_qtu_data_tree);
+
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ DR_DEBUG("qtaguid: tracking data for uid=%u in pqd=%p\n",
+ from_kuid(&init_user_ns, current_fsuid()), new_pqd_entry);
+ file->private_data = new_pqd_entry;
+ return 0;
+
+err_unlock_free_utd:
+ if (!utd_entry_found) {
+ rb_erase(&utd_entry->node, &uid_tag_data_tree);
+ kfree(utd_entry);
+ }
+err_unlock:
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ return res;
+}
+
+static int qtudev_release(struct inode *inode, struct file *file)
+{
+ struct proc_qtu_data *pqd_entry = file->private_data;
+ struct uid_tag_data *utd_entry = pqd_entry->parent_tag_data;
+ struct sock_tag *st_entry;
+ struct rb_root st_to_free_tree = RB_ROOT;
+ struct list_head *entry, *next;
+ struct tag_ref *tr;
+
+ if (unlikely(qtu_proc_handling_passive))
+ return 0;
+
+ /*
+ * Do not trust the current->pid, it might just be a kworker cleaning
+ * up after a dead proc.
+ */
+ DR_DEBUG("qtaguid: qtudev_release(): "
+ "pid=%u tgid=%u uid=%u "
+ "pqd_entry=%p->pid=%u utd_entry=%p->active_tags=%d\n",
+ current->pid, current->tgid, pqd_entry->parent_tag_data->uid,
+ pqd_entry, pqd_entry->pid, utd_entry,
+ utd_entry->num_active_tags);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+
+ list_for_each_safe(entry, next, &pqd_entry->sock_tag_list) {
+ st_entry = list_entry(entry, struct sock_tag, list);
+ DR_DEBUG("qtaguid: %s(): "
+ "erase sock_tag=%p->sk=%p pid=%u tgid=%u uid=%u\n",
+ __func__,
+ st_entry, st_entry->sk,
+ current->pid, current->tgid,
+ pqd_entry->parent_tag_data->uid);
+
+ utd_entry = uid_tag_data_tree_search(
+ &uid_tag_data_tree,
+ get_uid_from_tag(st_entry->tag));
+ BUG_ON(IS_ERR_OR_NULL(utd_entry));
+ DR_DEBUG("qtaguid: %s(): "
+ "looking for tag=0x%llx in utd_entry=%p\n", __func__,
+ st_entry->tag, utd_entry);
+ tr = tag_ref_tree_search(&utd_entry->tag_ref_tree,
+ st_entry->tag);
+ BUG_ON(!tr);
+ BUG_ON(tr->num_sock_tags <= 0);
+ tr->num_sock_tags--;
+ free_tag_ref_from_utd_entry(tr, utd_entry);
+
+ rb_erase(&st_entry->sock_node, &sock_tag_tree);
+ list_del(&st_entry->list);
+ /* Can't sockfd_put() within spinlock, do it later. */
+ sock_tag_tree_insert(st_entry, &st_to_free_tree);
+
+ /*
+ * Try to free the utd_entry if no other proc_qtu_data is
+ * using it (num_pqd is 0) and it doesn't have active tags
+ * (num_active_tags is 0).
+ */
+ put_utd_entry(utd_entry);
+ }
+
+ rb_erase(&pqd_entry->node, &proc_qtu_data_tree);
+ BUG_ON(pqd_entry->parent_tag_data->num_pqd < 1);
+ pqd_entry->parent_tag_data->num_pqd--;
+ put_utd_entry(pqd_entry->parent_tag_data);
+ kfree(pqd_entry);
+ file->private_data = NULL;
+
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+
+
+ sock_tag_tree_erase(&st_to_free_tree);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ prdebug_full_state_locked(0, "%s(): pid=%u tgid=%u", __func__,
+ current->pid, current->tgid);
+ spin_unlock_bh(&sock_tag_list_lock);
+ return 0;
+}
+
+/*------------------------------------------*/
+static const struct file_operations qtudev_fops = {
+ .owner = THIS_MODULE,
+ .open = qtudev_open,
+ .release = qtudev_release,
+};
+
+static struct miscdevice qtu_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = QTU_DEV_NAME,
+ .fops = &qtudev_fops,
+ /* How sad it doesn't allow for defaults: .mode = S_IRUGO | S_IWUSR */
+};
+
+static const struct seq_operations proc_qtaguid_ctrl_seqops = {
+ .start = qtaguid_ctrl_proc_start,
+ .next = qtaguid_ctrl_proc_next,
+ .stop = qtaguid_ctrl_proc_stop,
+ .show = qtaguid_ctrl_proc_show,
+};
+
+static int proc_qtaguid_ctrl_open(struct inode *inode, struct file *file)
+{
+ return seq_open_private(file, &proc_qtaguid_ctrl_seqops,
+ sizeof(struct proc_ctrl_print_info));
+}
+
+static const struct file_operations proc_qtaguid_ctrl_fops = {
+ .open = proc_qtaguid_ctrl_open,
+ .read = seq_read,
+ .write = qtaguid_ctrl_proc_write,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct seq_operations proc_qtaguid_stats_seqops = {
+ .start = qtaguid_stats_proc_start,
+ .next = qtaguid_stats_proc_next,
+ .stop = qtaguid_stats_proc_stop,
+ .show = qtaguid_stats_proc_show,
+};
+
+static int proc_qtaguid_stats_open(struct inode *inode, struct file *file)
+{
+ return seq_open_private(file, &proc_qtaguid_stats_seqops,
+ sizeof(struct proc_print_info));
+}
+
+static const struct file_operations proc_qtaguid_stats_fops = {
+ .open = proc_qtaguid_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+/*------------------------------------------*/
+static int __init qtaguid_proc_register(struct proc_dir_entry **res_procdir)
+{
+ int ret;
+ *res_procdir = proc_mkdir(module_procdirname, init_net.proc_net);
+ if (!*res_procdir) {
+ pr_err("qtaguid: failed to create proc/.../xt_qtaguid\n");
+ ret = -ENOMEM;
+ goto no_dir;
+ }
+
+ xt_qtaguid_ctrl_file = proc_create_data("ctrl", proc_ctrl_perms,
+ *res_procdir,
+ &proc_qtaguid_ctrl_fops,
+ NULL);
+ if (!xt_qtaguid_ctrl_file) {
+ pr_err("qtaguid: failed to create xt_qtaguid/ctrl "
+ " file\n");
+ ret = -ENOMEM;
+ goto no_ctrl_entry;
+ }
+
+ xt_qtaguid_stats_file = proc_create_data("stats", proc_stats_perms,
+ *res_procdir,
+ &proc_qtaguid_stats_fops,
+ NULL);
+ if (!xt_qtaguid_stats_file) {
+ pr_err("qtaguid: failed to create xt_qtaguid/stats "
+ "file\n");
+ ret = -ENOMEM;
+ goto no_stats_entry;
+ }
+ /*
+ * TODO: add support counter hacking
+ * xt_qtaguid_stats_file->write_proc = qtaguid_stats_proc_write;
+ */
+ return 0;
+
+no_stats_entry:
+ remove_proc_entry("ctrl", *res_procdir);
+no_ctrl_entry:
+ remove_proc_entry("xt_qtaguid", NULL);
+no_dir:
+ return ret;
+}
+
+static struct xt_match qtaguid_mt_reg __read_mostly = {
+ /*
+ * This module masquerades as the "owner" module so that iptables
+ * tools can deal with it.
+ */
+ .name = "owner",
+ .revision = 1,
+ .family = NFPROTO_UNSPEC,
+ .match = qtaguid_mt,
+ .matchsize = sizeof(struct xt_qtaguid_match_info),
+ .me = THIS_MODULE,
+};
+
+static int __init qtaguid_mt_init(void)
+{
+ if (qtaguid_proc_register(&xt_qtaguid_procdir)
+ || iface_stat_init(xt_qtaguid_procdir)
+ || xt_register_match(&qtaguid_mt_reg)
+ || misc_register(&qtu_device))
+ return -1;
+ return 0;
+}
+
+/*
+ * TODO: allow unloading of the module.
+ * For now stats are permanent.
+ * Kconfig forces'y/n' and never an 'm'.
+ */
+
+module_init(qtaguid_mt_init);
+MODULE_AUTHOR("jpa <jpa@google.com>");
+MODULE_DESCRIPTION("Xtables: socket owner+tag matching and associated stats");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_owner");
+MODULE_ALIAS("ip6t_owner");
+MODULE_ALIAS("ipt_qtaguid");
+MODULE_ALIAS("ip6t_qtaguid");
diff --git a/net/netfilter/xt_qtaguid_internal.h b/net/netfilter/xt_qtaguid_internal.h
new file mode 100644
index 0000000..c705270
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_internal.h
@@ -0,0 +1,350 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, 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.
+ */
+#ifndef __XT_QTAGUID_INTERNAL_H__
+#define __XT_QTAGUID_INTERNAL_H__
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock_types.h>
+#include <linux/workqueue.h>
+
+/* Iface handling */
+#define IDEBUG_MASK (1<<0)
+/* Iptable Matching. Per packet. */
+#define MDEBUG_MASK (1<<1)
+/* Red-black tree handling. Per packet. */
+#define RDEBUG_MASK (1<<2)
+/* procfs ctrl/stats handling */
+#define CDEBUG_MASK (1<<3)
+/* dev and resource tracking */
+#define DDEBUG_MASK (1<<4)
+
+/* E.g (IDEBUG_MASK | CDEBUG_MASK | DDEBUG_MASK) */
+#define DEFAULT_DEBUG_MASK 0
+
+/*
+ * (Un)Define these *DEBUG to compile out/in the pr_debug calls.
+ * All undef: text size ~ 0x3030; all def: ~ 0x4404.
+ */
+#define IDEBUG
+#define MDEBUG
+#define RDEBUG
+#define CDEBUG
+#define DDEBUG
+
+#define MSK_DEBUG(mask, ...) do { \
+ if (unlikely(qtaguid_debug_mask & (mask))) \
+ pr_debug(__VA_ARGS__); \
+ } while (0)
+#ifdef IDEBUG
+#define IF_DEBUG(...) MSK_DEBUG(IDEBUG_MASK, __VA_ARGS__)
+#else
+#define IF_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef MDEBUG
+#define MT_DEBUG(...) MSK_DEBUG(MDEBUG_MASK, __VA_ARGS__)
+#else
+#define MT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef RDEBUG
+#define RB_DEBUG(...) MSK_DEBUG(RDEBUG_MASK, __VA_ARGS__)
+#else
+#define RB_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef CDEBUG
+#define CT_DEBUG(...) MSK_DEBUG(CDEBUG_MASK, __VA_ARGS__)
+#else
+#define CT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef DDEBUG
+#define DR_DEBUG(...) MSK_DEBUG(DDEBUG_MASK, __VA_ARGS__)
+#else
+#define DR_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+
+extern uint qtaguid_debug_mask;
+
+/*---------------------------------------------------------------------------*/
+/*
+ * Tags:
+ *
+ * They represent what the data usage counters will be tracked against.
+ * By default a tag is just based on the UID.
+ * The UID is used as the base for policing, and can not be ignored.
+ * So a tag will always at least represent a UID (uid_tag).
+ *
+ * A tag can be augmented with an "accounting tag" which is associated
+ * with a UID.
+ * User space can set the acct_tag portion of the tag which is then used
+ * with sockets: all data belonging to that socket will be counted against the
+ * tag. The policing is then based on the tag's uid_tag portion,
+ * and stats are collected for the acct_tag portion separately.
+ *
+ * There could be
+ * a: {acct_tag=1, uid_tag=10003}
+ * b: {acct_tag=2, uid_tag=10003}
+ * c: {acct_tag=3, uid_tag=10003}
+ * d: {acct_tag=0, uid_tag=10003}
+ * a, b, and c represent tags associated with specific sockets.
+ * d is for the totals for that uid, including all untagged traffic.
+ * Typically d is used with policing/quota rules.
+ *
+ * We want tag_t big enough to distinguish uid_t and acct_tag.
+ * It might become a struct if needed.
+ * Nothing should be using it as an int.
+ */
+typedef uint64_t tag_t; /* Only used via accessors */
+
+#define TAG_UID_MASK 0xFFFFFFFFULL
+#define TAG_ACCT_MASK (~0xFFFFFFFFULL)
+
+static inline int tag_compare(tag_t t1, tag_t t2)
+{
+ return t1 < t2 ? -1 : t1 == t2 ? 0 : 1;
+}
+
+static inline tag_t combine_atag_with_uid(tag_t acct_tag, uid_t uid)
+{
+ return acct_tag | uid;
+}
+static inline tag_t make_tag_from_uid(uid_t uid)
+{
+ return uid;
+}
+static inline uid_t get_uid_from_tag(tag_t tag)
+{
+ return tag & TAG_UID_MASK;
+}
+static inline tag_t get_utag_from_tag(tag_t tag)
+{
+ return tag & TAG_UID_MASK;
+}
+static inline tag_t get_atag_from_tag(tag_t tag)
+{
+ return tag & TAG_ACCT_MASK;
+}
+
+static inline bool valid_atag(tag_t tag)
+{
+ return !(tag & TAG_UID_MASK);
+}
+static inline tag_t make_atag_from_value(uint32_t value)
+{
+ return (uint64_t)value << 32;
+}
+/*---------------------------------------------------------------------------*/
+
+/*
+ * Maximum number of socket tags that a UID is allowed to have active.
+ * Multiple processes belonging to the same UID contribute towards this limit.
+ * Special UIDs that can impersonate a UID also contribute (e.g. download
+ * manager, ...)
+ */
+#define DEFAULT_MAX_SOCK_TAGS 1024
+
+/*
+ * For now we only track 2 sets of counters.
+ * The default set is 0.
+ * Userspace can activate another set for a given uid being tracked.
+ */
+#define IFS_MAX_COUNTER_SETS 2
+
+enum ifs_tx_rx {
+ IFS_TX,
+ IFS_RX,
+ IFS_MAX_DIRECTIONS
+};
+
+/* For now, TCP, UDP, the rest */
+enum ifs_proto {
+ IFS_TCP,
+ IFS_UDP,
+ IFS_PROTO_OTHER,
+ IFS_MAX_PROTOS
+};
+
+struct byte_packet_counters {
+ uint64_t bytes;
+ uint64_t packets;
+};
+
+struct data_counters {
+ struct byte_packet_counters bpc[IFS_MAX_COUNTER_SETS][IFS_MAX_DIRECTIONS][IFS_MAX_PROTOS];
+};
+
+static inline uint64_t dc_sum_bytes(struct data_counters *counters,
+ int set,
+ enum ifs_tx_rx direction)
+{
+ return counters->bpc[set][direction][IFS_TCP].bytes
+ + counters->bpc[set][direction][IFS_UDP].bytes
+ + counters->bpc[set][direction][IFS_PROTO_OTHER].bytes;
+}
+
+static inline uint64_t dc_sum_packets(struct data_counters *counters,
+ int set,
+ enum ifs_tx_rx direction)
+{
+ return counters->bpc[set][direction][IFS_TCP].packets
+ + counters->bpc[set][direction][IFS_UDP].packets
+ + counters->bpc[set][direction][IFS_PROTO_OTHER].packets;
+}
+
+
+/* Generic X based nodes used as a base for rb_tree ops */
+struct tag_node {
+ struct rb_node node;
+ tag_t tag;
+};
+
+struct tag_stat {
+ struct tag_node tn;
+ struct data_counters counters;
+ /*
+ * If this tag is acct_tag based, we need to count against the
+ * matching parent uid_tag.
+ */
+ struct data_counters *parent_counters;
+};
+
+struct iface_stat {
+ struct list_head list; /* in iface_stat_list */
+ char *ifname;
+ bool active;
+ /* net_dev is only valid for active iface_stat */
+ struct net_device *net_dev;
+
+ struct byte_packet_counters totals_via_dev[IFS_MAX_DIRECTIONS];
+ struct data_counters totals_via_skb;
+ /*
+ * We keep the last_known, because some devices reset their counters
+ * just before NETDEV_UP, while some will reset just before
+ * NETDEV_REGISTER (which is more normal).
+ * So now, if the device didn't do a NETDEV_UNREGISTER and we see
+ * its current dev stats smaller that what was previously known, we
+ * assume an UNREGISTER and just use the last_known.
+ */
+ struct byte_packet_counters last_known[IFS_MAX_DIRECTIONS];
+ /* last_known is usable when last_known_valid is true */
+ bool last_known_valid;
+
+ struct proc_dir_entry *proc_ptr;
+
+ struct rb_root tag_stat_tree;
+ spinlock_t tag_stat_list_lock;
+};
+
+/* This is needed to create proc_dir_entries from atomic context. */
+struct iface_stat_work {
+ struct work_struct iface_work;
+ struct iface_stat *iface_entry;
+};
+
+/*
+ * Track tag that this socket is transferring data for, and not necessarily
+ * the uid that owns the socket.
+ * This is the tag against which tag_stat.counters will be billed.
+ * These structs need to be looked up by sock and pid.
+ */
+struct sock_tag {
+ struct rb_node sock_node;
+ struct sock *sk; /* Only used as a number, never dereferenced */
+ /* Used to associate with a given pid */
+ struct list_head list; /* in proc_qtu_data.sock_tag_list */
+ pid_t pid;
+
+ tag_t tag;
+};
+
+struct qtaguid_event_counts {
+ /* Various successful events */
+ atomic64_t sockets_tagged;
+ atomic64_t sockets_untagged;
+ atomic64_t counter_set_changes;
+ atomic64_t delete_cmds;
+ atomic64_t iface_events; /* Number of NETDEV_* events handled */
+
+ atomic64_t match_calls; /* Number of times iptables called mt */
+ /* Number of times iptables called mt from pre or post routing hooks */
+ atomic64_t match_calls_prepost;
+ /*
+ * match_found_sk_*: numbers related to the netfilter matching
+ * function finding a sock for the sk_buff.
+ * Total skbs processed is sum(match_found*).
+ */
+ atomic64_t match_found_sk; /* An sk was already in the sk_buff. */
+ /* The connection tracker had or didn't have the sk. */
+ atomic64_t match_found_sk_in_ct;
+ atomic64_t match_found_no_sk_in_ct;
+ /*
+ * No sk could be found. No apparent owner. Could happen with
+ * unsolicited traffic.
+ */
+ atomic64_t match_no_sk;
+ /*
+ * The file ptr in the sk_socket wasn't there and we couldn't get GID.
+ * This might happen for traffic while the socket is being closed.
+ */
+ atomic64_t match_no_sk_gid;
+};
+
+/* Track the set active_set for the given tag. */
+struct tag_counter_set {
+ struct tag_node tn;
+ int active_set;
+};
+
+/*----------------------------------------------*/
+/*
+ * The qtu uid data is used to track resources that are created directly or
+ * indirectly by processes (uid tracked).
+ * It is shared by the processes with the same uid.
+ * Some of the resource will be counted to prevent further rogue allocations,
+ * some will need freeing once the owner process (uid) exits.
+ */
+struct uid_tag_data {
+ struct rb_node node;
+ uid_t uid;
+
+ /*
+ * For the uid, how many accounting tags have been set.
+ */
+ int num_active_tags;
+ /* Track the number of proc_qtu_data that reference it */
+ int num_pqd;
+ struct rb_root tag_ref_tree;
+ /* No tag_node_tree_lock; use uid_tag_data_tree_lock */
+};
+
+struct tag_ref {
+ struct tag_node tn;
+
+ /*
+ * This tracks the number of active sockets that have a tag on them
+ * which matches this tag_ref.tn.tag.
+ * A tag ref can live on after the sockets are untagged.
+ * A tag ref can only be removed during a tag delete command.
+ */
+ int num_sock_tags;
+};
+
+struct proc_qtu_data {
+ struct rb_node node;
+ pid_t pid;
+
+ struct uid_tag_data *parent_tag_data;
+
+ /* Tracks the sock_tags that need freeing upon this proc's death */
+ struct list_head sock_tag_list;
+ /* No spinlock_t sock_tag_list_lock; use the global one. */
+};
+
+/*----------------------------------------------*/
+#endif /* ifndef __XT_QTAGUID_INTERNAL_H__ */
diff --git a/net/netfilter/xt_qtaguid_print.c b/net/netfilter/xt_qtaguid_print.c
new file mode 100644
index 0000000..2a7190d
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.c
@@ -0,0 +1,566 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, 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.
+ */
+
+/*
+ * Most of the functions in this file just waste time if DEBUG is not defined.
+ * The matching xt_qtaguid_print.h will static inline empty funcs if the needed
+ * debug flags ore not defined.
+ * Those funcs that fail to allocate memory will panic as there is no need to
+ * hobble allong just pretending to do the requested work.
+ */
+
+#define DEBUG
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/net.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+#include <net/sock.h>
+
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+
+#ifdef DDEBUG
+
+static void _bug_on_err_or_null(void *ptr)
+{
+ if (IS_ERR_OR_NULL(ptr)) {
+ pr_err("qtaguid: kmalloc failed\n");
+ BUG();
+ }
+}
+
+char *pp_tag_t(tag_t *tag)
+{
+ char *res;
+
+ if (!tag)
+ res = kasprintf(GFP_ATOMIC, "tag_t@null{}");
+ else
+ res = kasprintf(GFP_ATOMIC,
+ "tag_t@%p{tag=0x%llx, uid=%u}",
+ tag, *tag, get_uid_from_tag(*tag));
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+ char *res;
+
+ if (!dc)
+ res = kasprintf(GFP_ATOMIC, "data_counters@null{}");
+ else if (showValues)
+ res = kasprintf(
+ GFP_ATOMIC, "data_counters@%p{"
+ "set0{"
+ "rx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}, "
+ "tx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}}, "
+ "set1{"
+ "rx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}, "
+ "tx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}}}",
+ dc,
+ dc->bpc[0][IFS_RX][IFS_TCP].bytes,
+ dc->bpc[0][IFS_RX][IFS_TCP].packets,
+ dc->bpc[0][IFS_RX][IFS_UDP].bytes,
+ dc->bpc[0][IFS_RX][IFS_UDP].packets,
+ dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].packets,
+ dc->bpc[0][IFS_TX][IFS_TCP].bytes,
+ dc->bpc[0][IFS_TX][IFS_TCP].packets,
+ dc->bpc[0][IFS_TX][IFS_UDP].bytes,
+ dc->bpc[0][IFS_TX][IFS_UDP].packets,
+ dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].packets,
+ dc->bpc[1][IFS_RX][IFS_TCP].bytes,
+ dc->bpc[1][IFS_RX][IFS_TCP].packets,
+ dc->bpc[1][IFS_RX][IFS_UDP].bytes,
+ dc->bpc[1][IFS_RX][IFS_UDP].packets,
+ dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].packets,
+ dc->bpc[1][IFS_TX][IFS_TCP].bytes,
+ dc->bpc[1][IFS_TX][IFS_TCP].packets,
+ dc->bpc[1][IFS_TX][IFS_UDP].bytes,
+ dc->bpc[1][IFS_TX][IFS_UDP].packets,
+ dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].packets);
+ else
+ res = kasprintf(GFP_ATOMIC, "data_counters@%p{...}", dc);
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_tag_node(struct tag_node *tn)
+{
+ char *tag_str;
+ char *res;
+
+ if (!tn) {
+ res = kasprintf(GFP_ATOMIC, "tag_node@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tag_str = pp_tag_t(&tn->tag);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_node@%p{tag=%s}",
+ tn, tag_str);
+ _bug_on_err_or_null(res);
+ kfree(tag_str);
+ return res;
+}
+
+char *pp_tag_ref(struct tag_ref *tr)
+{
+ char *tn_str;
+ char *res;
+
+ if (!tr) {
+ res = kasprintf(GFP_ATOMIC, "tag_ref@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tn_str = pp_tag_node(&tr->tn);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_ref@%p{%s, num_sock_tags=%d}",
+ tr, tn_str, tr->num_sock_tags);
+ _bug_on_err_or_null(res);
+ kfree(tn_str);
+ return res;
+}
+
+char *pp_tag_stat(struct tag_stat *ts)
+{
+ char *tn_str;
+ char *counters_str;
+ char *parent_counters_str;
+ char *res;
+
+ if (!ts) {
+ res = kasprintf(GFP_ATOMIC, "tag_stat@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tn_str = pp_tag_node(&ts->tn);
+ counters_str = pp_data_counters(&ts->counters, true);
+ parent_counters_str = pp_data_counters(ts->parent_counters, false);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_stat@%p{%s, counters=%s, parent_counters=%s}",
+ ts, tn_str, counters_str, parent_counters_str);
+ _bug_on_err_or_null(res);
+ kfree(tn_str);
+ kfree(counters_str);
+ kfree(parent_counters_str);
+ return res;
+}
+
+char *pp_iface_stat(struct iface_stat *is)
+{
+ char *res;
+ if (!is) {
+ res = kasprintf(GFP_ATOMIC, "iface_stat@null{}");
+ } else {
+ struct data_counters *cnts = &is->totals_via_skb;
+ res = kasprintf(GFP_ATOMIC, "iface_stat@%p{"
+ "list=list_head{...}, "
+ "ifname=%s, "
+ "total_dev={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "total_skb={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "last_known_valid=%d, "
+ "last_known={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "active=%d, "
+ "net_dev=%p, "
+ "proc_ptr=%p, "
+ "tag_stat_tree=rb_root{...}}",
+ is,
+ is->ifname,
+ is->totals_via_dev[IFS_RX].bytes,
+ is->totals_via_dev[IFS_RX].packets,
+ is->totals_via_dev[IFS_TX].bytes,
+ is->totals_via_dev[IFS_TX].packets,
+ dc_sum_bytes(cnts, 0, IFS_RX),
+ dc_sum_packets(cnts, 0, IFS_RX),
+ dc_sum_bytes(cnts, 0, IFS_TX),
+ dc_sum_packets(cnts, 0, IFS_TX),
+ is->last_known_valid,
+ is->last_known[IFS_RX].bytes,
+ is->last_known[IFS_RX].packets,
+ is->last_known[IFS_TX].bytes,
+ is->last_known[IFS_TX].packets,
+ is->active,
+ is->net_dev,
+ is->proc_ptr);
+ }
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_sock_tag(struct sock_tag *st)
+{
+ char *tag_str;
+ char *res;
+
+ if (!st) {
+ res = kasprintf(GFP_ATOMIC, "sock_tag@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tag_str = pp_tag_t(&st->tag);
+ res = kasprintf(GFP_ATOMIC, "sock_tag@%p{"
+ "sock_node=rb_node{...}, "
+ "sk=%p (f_count=%d), list=list_head{...}, "
+ "pid=%u, tag=%s}",
+ st, st->sk, atomic_read(
+ &st->sk->sk_refcnt),
+ st->pid, tag_str);
+ _bug_on_err_or_null(res);
+ kfree(tag_str);
+ return res;
+}
+
+char *pp_uid_tag_data(struct uid_tag_data *utd)
+{
+ char *res;
+
+ if (!utd)
+ res = kasprintf(GFP_ATOMIC, "uid_tag_data@null{}");
+ else
+ res = kasprintf(GFP_ATOMIC, "uid_tag_data@%p{"
+ "uid=%u, num_active_acct_tags=%d, "
+ "num_pqd=%d, "
+ "tag_node_tree=rb_root{...}, "
+ "proc_qtu_data_tree=rb_root{...}}",
+ utd, utd->uid,
+ utd->num_active_tags, utd->num_pqd);
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+ char *parent_tag_data_str;
+ char *res;
+
+ if (!pqd) {
+ res = kasprintf(GFP_ATOMIC, "proc_qtu_data@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ parent_tag_data_str = pp_uid_tag_data(pqd->parent_tag_data);
+ res = kasprintf(GFP_ATOMIC, "proc_qtu_data@%p{"
+ "node=rb_node{...}, pid=%u, "
+ "parent_tag_data=%s, "
+ "sock_tag_list=list_head{...}}",
+ pqd, pqd->pid, parent_tag_data_str
+ );
+ _bug_on_err_or_null(res);
+ kfree(parent_tag_data_str);
+ return res;
+}
+
+/*------------------------------------------*/
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree)
+{
+ struct rb_node *node;
+ struct sock_tag *sock_tag_entry;
+ char *str;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(sock_tag_tree)) {
+ str = "sock_tag_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "sock_tag_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(sock_tag_tree);
+ node;
+ node = rb_next(node)) {
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ str = pp_sock_tag(sock_tag_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list)
+{
+ struct sock_tag *sock_tag_entry;
+ char *str;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (list_empty(sock_tag_list)) {
+ str = "sock_tag_list=list_head{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "sock_tag_list=list_head{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ list_for_each_entry(sock_tag_entry, sock_tag_list, list) {
+ str = pp_sock_tag(sock_tag_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct proc_qtu_data *proc_qtu_data_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(proc_qtu_data_tree)) {
+ str = "proc_qtu_data_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "proc_qtu_data_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(proc_qtu_data_tree);
+ node;
+ node = rb_next(node)) {
+ proc_qtu_data_entry = rb_entry(node,
+ struct proc_qtu_data,
+ node);
+ str = pp_proc_qtu_data(proc_qtu_data_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ indent_level++;
+ prdebug_sock_tag_list(indent_level,
+ &proc_qtu_data_entry->sock_tag_list);
+ indent_level--;
+
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct tag_ref *tag_ref_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(tag_ref_tree)) {
+ str = "tag_ref_tree{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "tag_ref_tree{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(tag_ref_tree);
+ node;
+ node = rb_next(node)) {
+ tag_ref_entry = rb_entry(node,
+ struct tag_ref,
+ tn.node);
+ str = pp_tag_ref(tag_ref_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct uid_tag_data *uid_tag_data_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(uid_tag_data_tree)) {
+ str = "uid_tag_data_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "uid_tag_data_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(uid_tag_data_tree);
+ node;
+ node = rb_next(node)) {
+ uid_tag_data_entry = rb_entry(node, struct uid_tag_data,
+ node);
+ str = pp_uid_tag_data(uid_tag_data_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ if (!RB_EMPTY_ROOT(&uid_tag_data_entry->tag_ref_tree)) {
+ indent_level++;
+ prdebug_tag_ref_tree(indent_level,
+ &uid_tag_data_entry->tag_ref_tree);
+ indent_level--;
+ }
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct tag_stat *ts_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(tag_stat_tree)) {
+ str = "tag_stat_tree{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "tag_stat_tree{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(tag_stat_tree);
+ node;
+ node = rb_next(node)) {
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ str = pp_tag_stat(ts_entry);
+ pr_debug("%*d: %s\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list)
+{
+ char *str;
+ struct iface_stat *iface_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (list_empty(iface_stat_list)) {
+ str = "iface_stat_list=list_head{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "iface_stat_list=list_head{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ list_for_each_entry(iface_entry, iface_stat_list, list) {
+ str = pp_iface_stat(iface_entry);
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ kfree(str);
+
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+ if (!RB_EMPTY_ROOT(&iface_entry->tag_stat_tree)) {
+ indent_level++;
+ prdebug_tag_stat_tree(indent_level,
+ &iface_entry->tag_stat_tree);
+ indent_level--;
+ }
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+#endif /* ifdef DDEBUG */
+/*------------------------------------------*/
+static const char * const netdev_event_strings[] = {
+ "netdev_unknown",
+ "NETDEV_UP",
+ "NETDEV_DOWN",
+ "NETDEV_REBOOT",
+ "NETDEV_CHANGE",
+ "NETDEV_REGISTER",
+ "NETDEV_UNREGISTER",
+ "NETDEV_CHANGEMTU",
+ "NETDEV_CHANGEADDR",
+ "NETDEV_GOING_DOWN",
+ "NETDEV_CHANGENAME",
+ "NETDEV_FEAT_CHANGE",
+ "NETDEV_BONDING_FAILOVER",
+ "NETDEV_PRE_UP",
+ "NETDEV_PRE_TYPE_CHANGE",
+ "NETDEV_POST_TYPE_CHANGE",
+ "NETDEV_POST_INIT",
+ "NETDEV_UNREGISTER_BATCH",
+ "NETDEV_RELEASE",
+ "NETDEV_NOTIFY_PEERS",
+ "NETDEV_JOIN",
+};
+
+const char *netdev_evt_str(int netdev_event)
+{
+ if (netdev_event < 0
+ || netdev_event >= ARRAY_SIZE(netdev_event_strings))
+ return "bad event num";
+ return netdev_event_strings[netdev_event];
+}
diff --git a/net/netfilter/xt_qtaguid_print.h b/net/netfilter/xt_qtaguid_print.h
new file mode 100644
index 0000000..b63871a
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.h
@@ -0,0 +1,120 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, 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.
+ */
+#ifndef __XT_QTAGUID_PRINT_H__
+#define __XT_QTAGUID_PRINT_H__
+
+#include "xt_qtaguid_internal.h"
+
+#ifdef DDEBUG
+
+char *pp_tag_t(tag_t *tag);
+char *pp_data_counters(struct data_counters *dc, bool showValues);
+char *pp_tag_node(struct tag_node *tn);
+char *pp_tag_ref(struct tag_ref *tr);
+char *pp_tag_stat(struct tag_stat *ts);
+char *pp_iface_stat(struct iface_stat *is);
+char *pp_sock_tag(struct sock_tag *st);
+char *pp_uid_tag_data(struct uid_tag_data *qtd);
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd);
+
+/*------------------------------------------*/
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list);
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree);
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree);
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree);
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree);
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree);
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list);
+
+#else
+
+/*------------------------------------------*/
+static inline char *pp_tag_t(tag_t *tag)
+{
+ return NULL;
+}
+static inline char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+ return NULL;
+}
+static inline char *pp_tag_node(struct tag_node *tn)
+{
+ return NULL;
+}
+static inline char *pp_tag_ref(struct tag_ref *tr)
+{
+ return NULL;
+}
+static inline char *pp_tag_stat(struct tag_stat *ts)
+{
+ return NULL;
+}
+static inline char *pp_iface_stat(struct iface_stat *is)
+{
+ return NULL;
+}
+static inline char *pp_sock_tag(struct sock_tag *st)
+{
+ return NULL;
+}
+static inline char *pp_uid_tag_data(struct uid_tag_data *qtd)
+{
+ return NULL;
+}
+static inline char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+ return NULL;
+}
+
+/*------------------------------------------*/
+static inline
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list)
+{
+}
+static inline
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree)
+{
+}
+static inline
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree)
+{
+}
+static inline
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+}
+static inline
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree)
+{
+}
+static inline
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree)
+{
+}
+static inline
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list)
+{
+}
+#endif
+/*------------------------------------------*/
+const char *netdev_evt_str(int netdev_event);
+#endif /* ifndef __XT_QTAGUID_PRINT_H__ */
diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c
new file mode 100644
index 0000000..834594a
--- /dev/null
+++ b/net/netfilter/xt_quota2.c
@@ -0,0 +1,401 @@
+/*
+ * 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);
+ remove_proc_entry(e->name, proc_xt_quota);
+ spin_unlock_bh(&counter_list_lock);
+ 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;
+ 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 (!(q->flags & XT_QUOTA_NO_CHANGE)) {
+ e->quota += (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+ }
+ ret = true;
+ } else {
+ if (e->quota >= skb->len) {
+ if (!(q->flags & XT_QUOTA_NO_CHANGE))
+ e->quota -= (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+ ret = !ret;
+ } else {
+ /* We are transitioning, log that fact. */
+ if (e->quota) {
+ 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_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/nfc/hci/core.c b/net/nfc/hci/core.c
index 2b0f0ac..5a58f9f 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -209,6 +209,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
}
create_info = (struct hci_create_pipe_resp *)skb->data;
+ if (create_info->pipe >= NFC_HCI_MAX_PIPES) {
+ status = NFC_HCI_ANY_E_NOK;
+ goto exit;
+ }
+
/* Save the new created pipe and bind with local gate,
* the description for skb->data[3] is destination gate id
* but since we received this cmd from host controller, we
@@ -232,6 +237,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
}
delete_info = (struct hci_delete_pipe_noti *)skb->data;
+ if (delete_info->pipe >= NFC_HCI_MAX_PIPES) {
+ status = NFC_HCI_ANY_E_NOK;
+ goto exit;
+ }
+
hdev->pipes[delete_info->pipe].gate = NFC_HCI_INVALID_GATE;
hdev->pipes[delete_info->pipe].dest_host = NFC_HCI_INVALID_HOST;
break;
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 884027f..a9a7128 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/socket.c b/net/socket.c
index bd3b339..34dabf4 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -533,8 +533,22 @@ 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));
+
+ sock->sk->sk_uid = iattr->ia_uid;
+ }
+
+ return err;
+}
+
static const struct inode_operations sockfs_inode_ops = {
.listxattr = sockfs_listxattr,
+ .setattr = sockfs_setattr,
};
/**
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 35ad69f..e318878 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/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_output.c b/net/xfrm/xfrm_output.c
index 637387b..d864a6d 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,6 +66,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
goto error_nolock;
}
+ if (x->props.output_mark)
+ skb->mark = x->props.output_mark;
+
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 f19e6a5..8b3fef7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -125,7 +125,7 @@ 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 +134,7 @@ 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 +145,7 @@ 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 +161,7 @@ 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)
@@ -1339,7 +1339,7 @@ EXPORT_SYMBOL(xfrm_policy_delete);
int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
{
- struct net *net = xp_net(pol);
+ struct net *net = sock_net(sk);
struct xfrm_policy *old_pol;
#ifdef CONFIG_XFRM_SUB_POLICY
@@ -1428,14 +1428,14 @@ 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;
}
@@ -1466,7 +1466,7 @@ 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;
@@ -1745,7 +1745,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
- &saddr, &daddr, family);
+ &saddr, &daddr, family,
+ xfrm[i]->props.output_mark);
err = PTR_ERR(dst);
if (IS_ERR(dst))
goto put_states;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 419bf5d..74f2e8f 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1883,6 +1883,13 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
struct xfrm_mgr *km;
struct xfrm_policy *pol = NULL;
+ if (!optval && !optlen) {
+ xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
+ xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
+ __sk_dst_reset(sk);
+ return 0;
+ }
+
if (optlen <= 0 || optlen > PAGE_SIZE)
return -EMSGSIZE;
@@ -1907,6 +1914,7 @@ 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 2293488..b09febe 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -584,6 +584,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
xfrm_mark_get(attrs, &x->mark);
+ if (attrs[XFRMA_OUTPUT_MARK])
+ x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]);
+
err = __xfrm_init_state(x, false);
if (err)
goto error;
@@ -869,6 +872,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
&x->replay);
if (ret)
goto out;
+ if (x->props.output_mark) {
+ ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark);
+ if (ret)
+ goto out;
+ }
if (x->security)
ret = copy_sec_ctx(x->security, skb);
out:
@@ -1697,6 +1705,10 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb,
struct sk_buff *skb;
int err;
+ err = verify_policy_dir(dir);
+ if (err)
+ return ERR_PTR(err);
+
skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!skb)
return ERR_PTR(-ENOMEM);
@@ -2218,6 +2230,10 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
int n = 0;
struct net *net = sock_net(skb->sk);
+ err = verify_policy_dir(pi->dir);
+ if (err)
+ return err;
+
if (attrs[XFRMA_MIGRATE] == NULL)
return -EINVAL;
@@ -2333,6 +2349,11 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
{
struct net *net = &init_net;
struct sk_buff *skb;
+ int err;
+
+ err = verify_policy_dir(dir);
+ if (err)
+ return err;
skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k), GFP_ATOMIC);
if (skb == NULL)
@@ -2408,6 +2429,7 @@ 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_OUTPUT_MARK] = { .len = NLA_U32 },
};
static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2627,6 +2649,8 @@ 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.output_mark)
+ l += nla_total_size(sizeof(x->props.output_mark));
/* Must count x->lastused as it may become non-zero behind our back. */
l += nla_total_size_64bit(sizeof(u64));
@@ -2990,6 +3014,11 @@ static int xfrm_notify_policy_flush(const struct km_event *c)
static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
{
+ int err;
+
+ err = verify_policy_dir(dir);
+ if (err)
+ return err;
switch (c->event) {
case XFRM_MSG_NEWPOLICY:
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 1792198..140a0fa2 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -108,6 +108,11 @@
as-instr = $(call try-run,\
printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+# __cc-option
+# Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586)
+__cc-option = $(call try-run,\
+ $(1) -Werror $(2) $(3) -c -x c /dev/null -o "$$TMP",$(3),$(4))
+
# Do not attempt to build with gcc plugins during cc-option tests.
# (And this uses delayed resolution so the flags will be up to date.)
CC_OPTION_CFLAGS = $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS))
@@ -115,13 +120,18 @@
# cc-option
# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
-cc-option = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+cc-option = $(call __cc-option, $(CC),\
+ $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS),$(1),$(2))
+
+# hostcc-option
+# Usage: cflags-y += $(call hostcc-option,-march=winchip-c6,-march=i586)
+hostcc-option = $(call __cc-option, $(HOSTCC),\
+ $(HOSTCFLAGS) $(HOST_EXTRACFLAGS),$(1),$(2))
# cc-option-yn
# Usage: flag := $(call cc-option-yn,-march=winchip-c6)
cc-option-yn = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
# cc-option-align
# Prefix align with either -falign or -malign
@@ -131,7 +141,7 @@
# cc-disable-warning
# Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
cc-disable-warning = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
# cc-name
# Expands to either gcc or clang
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 7675d11..3e3efd3 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -176,6 +176,14 @@
$(obj)/%.symtypes : $(src)/%.c FORCE
$(call cmd,cc_symtypes_c)
+# LLVM assembly
+# Generate .ll files from .c
+quiet_cmd_cc_ll_c = CC $(quiet_modtag) $@
+ cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -o $@ $<
+
+$(obj)/%.ll: $(src)/%.c FORCE
+ $(call if_changed_dep,cc_ll_c)
+
# C (.c) files
# The C file is compiled and updated dependency information is generated.
# (See cmd_cc_o_c + relevant part of rule_cc_o_c)
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.extrawarn b/scripts/Makefile.extrawarn
index 7c321a6..fb3522f 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -64,7 +64,6 @@
KBUILD_CFLAGS += $(call cc-disable-warning, initializer-overrides)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-value)
KBUILD_CFLAGS += $(call cc-disable-warning, format)
-KBUILD_CFLAGS += $(call cc-disable-warning, unknown-warning-option)
KBUILD_CFLAGS += $(call cc-disable-warning, sign-compare)
KBUILD_CFLAGS += $(call cc-disable-warning, format-zero-length)
KBUILD_CFLAGS += $(call cc-disable-warning, uninitialized)
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 45b5b1a..9cfd5c8 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -20,12 +20,6 @@
# Will compile qconf as a C++ program, and menu as a C program.
# They are linked as C++ code to the executable qconf
-# hostcc-option
-# Usage: cflags-y += $(call hostcc-option,-march=winchip-c6,-march=i586)
-
-hostcc-option = $(call try-run,\
- $(HOSTCC) $(HOSTCFLAGS) $(HOST_EXTRACFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
-
__hostprogs := $(sort $(hostprogs-y) $(hostprogs-m))
host-cshlib := $(sort $(hostlibs-y) $(hostlibs-m))
host-cxxshlib := $(sort $(hostcxxlibs-y) $(hostcxxlibs-m))
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 0a07f90..9e447b8 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
# ---------------------------------------------------------------------------
@@ -408,3 +414,34 @@
cmd_xzmisc = (cat $(filter-out FORCE,$^) | \
xz --check=crc32 --lzma2=dict=1MiB) > $@ || \
(rm -f $@ ; false)
+
+# ASM offsets
+# ---------------------------------------------------------------------------
+
+# Default sed regexp - multiline due to syntax constraints
+#
+# Use [:space:] because LLVM's integrated assembler inserts <tab> around
+# the .ascii directive whereas GCC keeps the <space> as-is.
+define sed-offsets
+ 's:^[[:space:]]*\.ascii[[:space:]]*"\(.*\)".*:\1:; \
+ /^->/{s:->#\(.*\):/* \1 */:; \
+ s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
+ s:->::; p;}'
+endef
+
+# Use filechk to avoid rebuilds when a header changes, but the resulting file
+# does not
+define filechk_offsets
+ (set -e; \
+ echo "#ifndef $2"; \
+ echo "#define $2"; \
+ echo "/*"; \
+ echo " * DO NOT MODIFY."; \
+ echo " *"; \
+ echo " * This file was generated by Kbuild"; \
+ echo " */"; \
+ echo ""; \
+ sed -ne $(sed-offsets); \
+ echo ""; \
+ echo "#endif" )
+endef
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)/$(modinst_dir))
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 5517164..77bc368 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2529,6 +2529,7 @@
# Check for git id commit length and improperly formed commit descriptions
if ($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 &&
diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index 19d9bca..b497d97 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -7,32 +7,8 @@
devicetable-offsets-file := devicetable-offsets.h
-define sed-y
- "/^->/{s:->#\(.*\):/* \1 */:; \
- s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:->::; p;}"
-endef
-
-quiet_cmd_offsets = GEN $@
-define cmd_offsets
- (set -e; \
- echo "#ifndef __DEVICETABLE_OFFSETS_H__"; \
- echo "#define __DEVICETABLE_OFFSETS_H__"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " *"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y) $<; \
- echo ""; \
- echo "#endif" ) > $@
-endef
-
-$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s
- $(call if_changed,offsets)
+$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s FORCE
+ $(call filechk,offsets,__DEVICETABLE_OFFSETS_H__)
targets += $(devicetable-offsets-file) devicetable-offsets.s
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/commoncap.c b/security/commoncap.c
index 8df676f..1076608 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 f825304..99890aa 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)
{
@@ -1589,6 +1591,37 @@ 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),
@@ -1940,4 +1973,20 @@ 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 c2da45a..689effa 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"
@@ -491,6 +492,7 @@ static int selinux_is_sblabel_mnt(struct super_block *sb)
!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");
}
@@ -813,6 +815,7 @@ 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;
@@ -1761,6 +1764,10 @@ 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
@@ -1791,6 +1798,12 @@ 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)
@@ -2119,6 +2132,12 @@ 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;
@@ -6077,6 +6096,139 @@ 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),
@@ -6291,6 +6443,16 @@ 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..963ff80 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -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/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9e5fc16..42dfbeb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -375,6 +375,105 @@ enum bpf_func_id {
*/
BPF_FUNC_probe_write_user,
+ /**
+ * int bpf_skb_change_tail(skb, len, flags)
+ * The helper will resize the skb to the given new size, to be used f.e.
+ * with control messages.
+ * @skb: pointer to skb
+ * @len: new skb length
+ * @flags: reserved
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_tail,
+
+ /**
+ * int bpf_skb_pull_data(skb, len)
+ * The helper will pull in non-linear data in case the skb is non-linear
+ * and not all of len are part of the linear section. Only needed for
+ * read/write with direct packet access.
+ * @skb: pointer to skb
+ * @len: len to make read/writeable
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_pull_data,
+
+ /**
+ * s64 bpf_csum_update(skb, csum)
+ * Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
+ * @skb: pointer to skb
+ * @csum: csum to add
+ * Return: csum on success or negative error
+ */
+ BPF_FUNC_csum_update,
+
+ /**
+ * void bpf_set_hash_invalid(skb)
+ * Invalidate current skb->hash.
+ * @skb: pointer to skb
+ */
+ 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_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 overflowuid if failed.
+ */
+ 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/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 55a60d3..05536d8 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -321,11 +321,10 @@
2. If you're getting any other objtool error in a compiled .c file, it
may be because the file uses an asm() statement which has a "call"
instruction. An asm() statement with a call instruction must declare
- the use of the stack pointer in its output operand. For example, on
- x86_64:
+ the use of the stack pointer in its output operand. On x86_64, this
+ means adding the ASM_CALL_CONSTRAINT as an output constraint:
- register void *__sp asm("rsp");
- asm volatile("call func" : "+r" (__sp));
+ asm volatile("call func" : ASM_CALL_CONSTRAINT);
Otherwise the stack frame may not get created before the call.