Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma fixes from Jason Gunthorpe:
"A few more merge window regressions that didn't make rc1:
- New validation in the DMA layer triggers wrong use of the DMA layer
in rxe, siw and rdmavt
- Accidental change of a hypervisor facing ABI when widening the port
speed u8 to u16 in vmw_pvrdma
- Memory leak on error unwind in SRP target"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
RDMA/srpt: Fix typo in srpt_unregister_mad_agent docstring
RDMA/vmw_pvrdma: Fix the active_speed and phys_state value
IB/srpt: Fix memory leak in srpt_add_one
RDMA: Fix software RDMA drivers for dma mapping error
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 6a59a13..61a7310 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -26,6 +26,10 @@
PDFLATEX = xelatex
LATEXOPTS = -interaction=batchmode
+ifeq ($(KBUILD_VERBOSE),0)
+SPHINXOPTS += "-q"
+endif
+
# User-friendly check for sphinx-build
HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
diff --git a/Documentation/admin-guide/LSM/SafeSetID.rst b/Documentation/admin-guide/LSM/SafeSetID.rst
index 17996c9..0ec3486 100644
--- a/Documentation/admin-guide/LSM/SafeSetID.rst
+++ b/Documentation/admin-guide/LSM/SafeSetID.rst
@@ -107,7 +107,7 @@
privileges, such as allowing a user to set up user namespace UID/GID mappings.
Note on GID policies and setgroups()
-==================
+====================================
In v5.9 we are adding support for limiting CAP_SETGID privileges as was done
previously for CAP_SETUID. However, for compatibility with common sandboxing
related code conventions in userspace, we currently allow arbitrary
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index 37940a0..10fde58 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -478,7 +478,7 @@
statistics of the given idle state. That information is exposed by the kernel
via ``sysfs``.
-For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/`
+For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/`
directory in ``sysfs``, where the number ``<N>`` is assigned to the given
CPU at the initialization time. That directory contains a set of subdirectories
called :file:`state0`, :file:`state1` and so on, up to the number of idle state
@@ -494,7 +494,7 @@
residency.
``below``
- Total number of times this idle state had been asked for, but cerainly
+ Total number of times this idle state had been asked for, but certainly
a deeper idle state would have been a better match for the observed idle
duration.
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 57fd6ce..f2ab8a5 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -300,6 +300,7 @@
0: 0 1 2 3 4 5 6 7
RSS hash key:
84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
netdev_tstamp_prequeue
----------------------
diff --git a/Documentation/arm/sunxi.rst b/Documentation/arm/sunxi.rst
index 62b533d..0c536ae 100644
--- a/Documentation/arm/sunxi.rst
+++ b/Documentation/arm/sunxi.rst
@@ -148,3 +148,13 @@
* User Manual
http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf
+
+ - Allwinner H6
+
+ * Datasheet
+
+ https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf
+
+ * User Manual
+
+ https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 1e44983..ed2b43e 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -51,7 +51,7 @@
support for Sphinx v3.0 and above is brand new. Be prepared for
possible issues in the generated output.
''')
- if minor > 0 or patch >= 2:
+ if (major > 3) or (minor > 0 or patch >= 2):
# Sphinx c function parser is more pedantic with regards to type
# checking. Due to that, having macros at c:function cause problems.
# Those needed to be scaped by using c_id_attributes[] array
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index c09c9ca..2b68add 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -295,11 +295,13 @@
pass::
ok 28 - kmalloc_double_kzfree
+
or, if kmalloc failed::
# kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
Expected ptr is not null, but is
not ok 4 - kmalloc_large_oob_right
+
or, if a KASAN report was expected, but not found::
# kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
diff --git a/Documentation/devicetree/bindings/clock/hi6220-clock.txt b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
index ef3deb7..17ac4a3 100644
--- a/Documentation/devicetree/bindings/clock/hi6220-clock.txt
+++ b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
@@ -4,7 +4,7 @@
please refer the following document to know more about the binding rules
for these system controllers:
-Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
Required Properties:
diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst
index bbb0c1c..a94f17d 100644
--- a/Documentation/filesystems/api-summary.rst
+++ b/Documentation/filesystems/api-summary.rst
@@ -86,9 +86,6 @@
.. kernel-doc:: fs/dax.c
:export:
-.. kernel-doc:: fs/direct-io.c
- :export:
-
.. kernel-doc:: fs/libfs.c
:export:
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 1f9ea82..2062a60 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -83,10 +83,6 @@
===================
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :doc: AMDGPU XGMI Support
-
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :internal:
AMDGPU RAS Support
==================
@@ -124,9 +120,6 @@
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
:doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
- :internal:
-
Sample Code
-----------
Sample code for testing error injection can be found here:
diff --git a/Documentation/hwmon/adm1266.rst b/Documentation/hwmon/adm1266.rst
index 9257f8a..2b87701 100644
--- a/Documentation/hwmon/adm1266.rst
+++ b/Documentation/hwmon/adm1266.rst
@@ -20,7 +20,7 @@
integrated 12 bit SAR ADC, accessed using a PMBus interface.
The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
Sysfs entries
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index e6b91ab..b797db7 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -132,6 +132,7 @@
mcp3021
menf21bmc
mlxreg-fan
+ mp2975
nct6683
nct6775
nct7802
diff --git a/Documentation/hwmon/mp2975.rst b/Documentation/hwmon/mp2975.rst
index 5b0609c..81d816b 100644
--- a/Documentation/hwmon/mp2975.rst
+++ b/Documentation/hwmon/mp2975.rst
@@ -20,6 +20,7 @@
vendor dual-loop, digital, multi-phase controller MP2975.
This device:
+
- Supports up to two power rail.
- Provides 8 pulse-width modulations (PWMs), and can be configured up
to 8-phase operation for rail 1 and up to 4-phase operation for rail
@@ -32,10 +33,12 @@
10-mV DAC, IMVP9 mode with 5-mV DAC.
Device supports:
+
- SVID interface.
- AVSBus interface.
Device complaint with:
+
- PMBus rev 1.3 interface.
Device supports direct format for reading output current, output voltage,
@@ -45,11 +48,14 @@
The below VID modes are supported: VR12, VR13, IMVP9.
The driver provides the next attributes for the current:
+
- for current in: input, maximum alarm;
- for current out input, maximum alarm and highest values;
- for phase current: input and label.
-attributes.
+ attributes.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- 'k' is number of configured phases (from 1 to 8);
- indexes 1, 1*n for "iin";
@@ -65,11 +71,14 @@
**curr[1-{2n+k}]_label**
The driver provides the next attributes for the voltage:
+
- for voltage in: input, high critical threshold, high critical alarm, all only
from page 0;
- for voltage out: input, low and high critical thresholds, low and high
critical alarms, from pages 0 and 1;
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "iin";
- indexes n+1, n+2 for "vout";
@@ -87,9 +96,12 @@
**in[2-{n+1}1_lcrit_alarm**
The driver provides the next attributes for the power:
+
- for power in alarm and input.
- for power out: highest and input.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "pin";
- indexes n+1, n+2 for "pout";
diff --git a/Documentation/locking/lockdep-design.rst b/Documentation/locking/lockdep-design.rst
index cec03bd1..9f3cfca 100644
--- a/Documentation/locking/lockdep-design.rst
+++ b/Documentation/locking/lockdep-design.rst
@@ -42,6 +42,7 @@
(4 usages * n STATEs + 1) categories:
where the 4 usages can be:
+
- 'ever held in STATE context'
- 'ever held as readlock in STATE context'
- 'ever held with STATE enabled'
@@ -49,10 +50,12 @@
where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
now they include:
+
- hardirq
- softirq
where the last 1 category is:
+
- 'ever used' [ == !unused ]
When locking rules are violated, these usage bits are presented in the
@@ -96,9 +99,9 @@
+--------------+-------------+--------------+
| | irq enabled | irq disabled |
+--------------+-------------+--------------+
- | ever in irq | ? | - |
+ | ever in irq | '?' | '-' |
+--------------+-------------+--------------+
- | never in irq | + | . |
+ | never in irq | '+' | '.' |
+--------------+-------------+--------------+
The character '-' suggests irq is disabled because if otherwise the
@@ -216,7 +219,7 @@
BD_MUTEX_PARTITION
};
-mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+ mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
In this case the locking is done on a bdev object that is known to be a
partition.
@@ -334,7 +337,7 @@
----------------
The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
+Exceeding this number will trigger the following lockdep warning::
(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
@@ -420,7 +423,8 @@
The difference between recursive readers and non-recursive readers is because:
recursive readers get blocked only by a write lock *holder*, while non-recursive
-readers could get blocked by a write lock *waiter*. Considering the follow example:
+readers could get blocked by a write lock *waiter*. Considering the follow
+example::
TASK A: TASK B:
@@ -448,20 +452,22 @@
Block condition matrix, Y means the row blocks the column, and N means otherwise.
- | E | r | R |
+---+---+---+---+
- E | Y | Y | Y |
+ | | E | r | R |
+---+---+---+---+
- r | Y | Y | N |
+ | E | Y | Y | Y |
+---+---+---+---+
- R | Y | Y | N |
+ | r | Y | Y | N |
+ +---+---+---+---+
+ | R | Y | Y | N |
+ +---+---+---+---+
(W: writers, r: non-recursive readers, R: recursive readers)
acquired recursively. Unlike non-recursive read locks, recursive read locks
only get blocked by current write lock *holders* other than write lock
-*waiters*, for example:
+*waiters*, for example::
TASK A: TASK B:
@@ -491,7 +497,7 @@
even true for two non-recursive read locks). A non-recursive lock can block the
corresponding recursive lock, and vice versa.
-A deadlock case with recursive locks involved is as follow:
+A deadlock case with recursive locks involved is as follow::
TASK A: TASK B:
@@ -510,7 +516,7 @@
dependencies, but we can show that 4 types of lock dependencies are enough for
deadlock detection.
-For each lock dependency:
+For each lock dependency::
L1 -> L2
@@ -525,20 +531,25 @@
With the above combination for simplification, there are 4 types of dependency edges
in the lockdep graph:
-1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
+1) -(ER)->:
+ exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
X -> Y and X is a writer and Y is a recursive reader.
-2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
+2) -(EN)->:
+ exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
X -> Y and X is a writer and Y is either a writer or non-recursive reader.
-3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means
+3) -(SR)->:
+ shared reader to recursive reader dependency, "X -(SR)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is a recursive reader.
-4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
+4) -(SN)->:
+ shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is either a writer or
non-recursive reader.
-Note that given two locks, they may have multiple dependencies between them, for example:
+Note that given two locks, they may have multiple dependencies between them,
+for example::
TASK A:
@@ -592,11 +603,11 @@
Proof for sufficiency (Lemma 1):
-Let's say we have a strong circle:
+Let's say we have a strong circle::
L1 -> L2 ... -> Ln -> L1
-, which means we have dependencies:
+, which means we have dependencies::
L1 -> L2
L2 -> L3
@@ -633,7 +644,7 @@
for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting
for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly,
we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we
-have a circle:
+have a circle::
Ln -> L1 -> L2 -> ... -> Ln
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index b165181..a432dc4 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -70,6 +70,7 @@
that both the name (as reported by ``fw.app.name``) and version are
required to uniquely identify the package.
* - ``fw.app.bundle_id``
+ - running
- 0xc0000001
- Unique identifier for the DDP package loaded in the device. Also
referred to as the DDP Track ID. Can be used to uniquely identify
diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst
index 8e15bc9..234abed 100644
--- a/Documentation/networking/statistics.rst
+++ b/Documentation/networking/statistics.rst
@@ -175,5 +175,4 @@
translated to netlink attributes when dumped. Drivers must not overwrite
the statistics they don't report with 0.
-.. kernel-doc:: include/linux/ethtool.h
- :identifiers: ethtool_pause_stats
+- ethtool_pause_stats()
diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py
index 409dbc4..3e81eba 100644
--- a/Documentation/sphinx/automarkup.py
+++ b/Documentation/sphinx/automarkup.py
@@ -16,28 +16,36 @@
from itertools import chain
#
+# Python 2 lacks re.ASCII...
+#
+try:
+ ascii_p3 = re.ASCII
+except AttributeError:
+ ascii_p3 = 0
+
+#
# Regex nastiness. Of course.
# Try to identify "function()" that's not already marked up some
# other way. Sphinx doesn't like a lot of stuff right after a
# :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
# bit tries to restrict matches to things that won't create trouble.
#
-RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII)
+RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
#
# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
#
RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
- flags=re.ASCII)
+ flags=ascii_p3)
#
# Sphinx 3 uses a different C role for each one of struct, union, enum and
# typedef
#
-RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
#
# Detects a reference to a documentation page of the form Documentation/... with
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 69fc516..acd2cc2 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -22,6 +22,7 @@
spec_ctrl
accelerators/ocxl
ioctl/index
+ iommu
media/index
.. only:: subproject and html
diff --git a/MAINTAINERS b/MAINTAINERS
index b516bb3..78e908e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -978,7 +978,7 @@
L: linux-iio@vger.kernel.org
S: Supported
W: http://ez.analog.com/community/linux-device-drivers
-F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt
+F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
F: drivers/iio/adc/ad7768-1.c
ANALOG DEVICES INC AD7780 DRIVER
@@ -3857,7 +3857,7 @@
L: linux-usb@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
-F: Documentation/devicetree/bindings/usb/cdns-usb3.txt
+F: Documentation/devicetree/bindings/usb/cdns,usb3.yaml
F: drivers/usb/cdns3/
CADET FM/AM RADIO RECEIVER DRIVER
@@ -7916,7 +7916,7 @@
M: john.garry@huawei.com
S: Maintained
W: http://www.hisilicon.com
-F: Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt
+F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
F: drivers/bus/hisi_lpc.c
HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
@@ -14527,6 +14527,14 @@
F: drivers/mailbox/qcom-ipcc.c
F: include/dt-bindings/mailbox/qcom-ipcc.h
+QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER
+M: Robert Marko <robert.marko@sartura.hr>
+M: Luka Perkov <luka.perkov@sartura.hr>
+L: linux-arm-msm@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml
+F: drivers/regulator/vqmmc-ipq4019-regulator.c
+
QUALCOMM RMNET DRIVER
M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
M: Sean Tranchetti <stranche@codeaurora.org>
@@ -14882,7 +14890,6 @@
R: Sergei Shtylyov <sergei.shtylyov@gmail.com>
L: netdev@vger.kernel.org
L: linux-renesas-soc@vger.kernel.org
-F: Documentation/devicetree/bindings/net/renesas,*.txt
F: Documentation/devicetree/bindings/net/renesas,*.yaml
F: drivers/net/ethernet/renesas/
F: include/linux/sh_eth.h
@@ -18083,7 +18090,7 @@
M: Binghui Wang <wangbinghui@hisilicon.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt
+F: Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml
F: drivers/phy/hisilicon/phy-hi3660-usb3.c
USB ISP116X DRIVER
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index d57112a..c23dbf8 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -354,8 +354,8 @@ static void __init free_highpages(void)
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index a5e5db6..39b2ede 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode)
add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
/* Load the new page-table. */
+ sev_verify_cbit(top_level_pgt);
write_cr3(top_level_pgt);
}
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index dd07e7b..aa56179 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -68,6 +68,9 @@
SYM_FUNC_END(get_sev_encryption_bit)
.code64
+
+#include "../../kernel/sev_verify_cbit.S"
+
SYM_FUNC_START(set_sev_encryption_mask)
#ifdef CONFIG_AMD_MEM_ENCRYPT
push %rbp
@@ -81,6 +84,19 @@
bts %rax, sme_me_mask(%rip) /* Create the encryption mask */
+ /*
+ * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
+ * get_sev_encryption_bit() because this function is 32-bit code and
+ * shared between 64-bit and 32-bit boot path.
+ */
+ movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */
+ rdmsr
+
+ /* Store MSR value in sev_status */
+ shlq $32, %rdx
+ orq %rdx, %rax
+ movq %rax, sev_status(%rip)
+
.Lno_sev_mask:
movq %rbp, %rsp /* Restore original stack pointer */
@@ -96,5 +112,7 @@
#ifdef CONFIG_AMD_MEM_ENCRYPT
.balign 8
-SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sev_status, .quad 0)
+SYM_DATA(sev_check_data, .quad 0)
#endif
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 6d31f1b..d9a631c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -159,4 +159,6 @@ void boot_page_fault(void);
void boot_stage1_vc(void);
void boot_stage2_vc(void);
+unsigned long sev_verify_cbit(unsigned long cr3);
+
#endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7eb2a1c..3c41773 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -161,6 +161,21 @@
/* Setup early boot stage 4-/5-level pagetables. */
addq phys_base(%rip), %rax
+
+ /*
+ * For SEV guests: Verify that the C-bit is correct. A malicious
+ * hypervisor could lie about the C-bit position to perform a ROP
+ * attack on the guest by writing to the unencrypted stack and wait for
+ * the next RET instruction.
+ * %rsi carries pointer to realmode data and is callee-clobbered. Save
+ * and restore it.
+ */
+ pushq %rsi
+ movq %rax, %rdi
+ call sev_verify_cbit
+ popq %rsi
+
+ /* Switch to new page-table */
movq %rax, %cr3
/* Ensure I am executing from virtual addresses */
@@ -279,6 +294,7 @@
SYM_CODE_END(secondary_startup_64)
#include "verify_cpu.S"
+#include "sev_verify_cbit.S"
#ifdef CONFIG_HOTPLUG_CPU
/*
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 5f83cca..7d04b35 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
goto fail;
regs->dx = val >> 32;
+ /*
+ * This is a VC handler and the #VC is only raised when SEV-ES is
+ * active, which means SEV must be active too. Do sanity checks on the
+ * CPUID results to make sure the hypervisor does not trick the kernel
+ * into the no-sev path. This could map sensitive data unencrypted and
+ * make it accessible to the hypervisor.
+ *
+ * In particular, check for:
+ * - Hypervisor CPUID bit
+ * - Availability of CPUID leaf 0x8000001f
+ * - SEV CPUID bit.
+ *
+ * The hypervisor might still report the wrong C-bit position, but this
+ * can't be checked here.
+ */
+
+ if ((fn == 1 && !(regs->cx & BIT(31))))
+ /* Hypervisor bit */
+ goto fail;
+ else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+ /* SEV leaf check */
+ goto fail;
+ else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
+ /* SEV bit */
+ goto fail;
+
/* Skip over the CPUID two-byte opcode */
regs->ip += 2;
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 4a96726..0bd1a0f 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -374,8 +374,8 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
return ES_EXCEPTION;
}
-static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
- unsigned long vaddr, phys_addr_t *paddr)
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ unsigned long vaddr, phys_addr_t *paddr)
{
unsigned long va = (unsigned long)vaddr;
unsigned int level;
@@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
if (user_mode(ctxt->regs))
ctxt->fi.error_code |= X86_PF_USER;
- return false;
+ return ES_EXCEPTION;
}
+ if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+ /* Emulated MMIO to/from encrypted memory not supported */
+ return ES_UNSUPPORTED;
+
pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
pa |= va & ~page_level_mask(level);
*paddr = pa;
- return true;
+ return ES_OK;
}
/* Include code shared with pre-decompression boot stage */
@@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
{
u64 exit_code, exit_info_1, exit_info_2;
unsigned long ghcb_pa = __pa(ghcb);
+ enum es_result res;
phys_addr_t paddr;
void __user *ref;
@@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
- if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
- if (!read)
+ res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+ if (res != ES_OK) {
+ if (res == ES_EXCEPTION && !read)
ctxt->fi.error_code |= X86_PF_WRITE;
- return ES_EXCEPTION;
+ return res;
}
exit_info_1 = paddr;
diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S
new file mode 100644
index 0000000..ee04941
--- /dev/null
+++ b/arch/x86/kernel/sev_verify_cbit.S
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sev_verify_cbit.S - Code for verification of the C-bit position reported
+ * by the Hypervisor when running with SEV enabled.
+ *
+ * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de)
+ *
+ * sev_verify_cbit() is called before switching to a new long-mode page-table
+ * at boot.
+ *
+ * Verify that the C-bit position is correct by writing a random value to
+ * an encrypted memory location while on the current page-table. Then it
+ * switches to the new page-table to verify the memory content is still the
+ * same. After that it switches back to the current page-table and when the
+ * check succeeded it returns. If the check failed the code invalidates the
+ * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to
+ * make sure no interrupt or exception can get the CPU out of the hlt loop.
+ *
+ * New page-table pointer is expected in %rdi (first parameter)
+ *
+ */
+SYM_FUNC_START(sev_verify_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /* First check if a C-bit was detected */
+ movq sme_me_mask(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */
+ movq sev_status(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* Save CR4 in %rsi */
+ movq %cr4, %rsi
+
+ /* Disable Global Pages */
+ movq %rsi, %rdx
+ andq $(~X86_CR4_PGE), %rdx
+ movq %rdx, %cr4
+
+ /*
+ * Verified that running under SEV - now get a random value using
+ * RDRAND. This instruction is mandatory when running as an SEV guest.
+ *
+ * Don't bail out of the loop if RDRAND returns errors. It is better to
+ * prevent forward progress than to work with a non-random value here.
+ */
+1: rdrand %rdx
+ jnc 1b
+
+ /* Store value to memory and keep it in %rdx */
+ movq %rdx, sev_check_data(%rip)
+
+ /* Backup current %cr3 value to restore it later */
+ movq %cr3, %rcx
+
+ /* Switch to new %cr3 - This might unmap the stack */
+ movq %rdi, %cr3
+
+ /*
+ * Compare value in %rdx with memory location. If C-bit is incorrect
+ * this would read the encrypted data and make the check fail.
+ */
+ cmpq %rdx, sev_check_data(%rip)
+
+ /* Restore old %cr3 */
+ movq %rcx, %cr3
+
+ /* Restore previous CR4 */
+ movq %rsi, %cr4
+
+ /* Check CMPQ result */
+ je 3f
+
+ /*
+ * The check failed, prevent any forward progress to prevent ROP
+ * attacks, invalidate the stack and go into a hlt loop.
+ */
+ xorq %rsp, %rsp
+ subq $0x1000, %rsp
+2: hlt
+ jmp 2b
+3:
+#endif
+ /* Return page-table pointer */
+ movq %rdi, %rax
+ ret
+SYM_FUNC_END(sev_verify_cbit)
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index efbb3de..bc08337 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -39,6 +39,7 @@
*/
u64 sme_me_mask __section(".data") = 0;
u64 sev_status __section(".data") = 0;
+u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index c6fc83e..8731b7a 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -89,8 +89,8 @@ static void __init free_highpages(void)
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 78114dd..d661ada 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -773,8 +773,7 @@ static void __device_link_del(struct kref *kref)
dev_dbg(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del_rcu(&link->s_node);
list_del_rcu(&link->c_node);
@@ -788,8 +787,7 @@ static void __device_link_del(struct kref *kref)
dev_info(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del(&link->s_node);
list_del(&link->c_node);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b42229b..148e819 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1117,6 +1117,8 @@ static void __device_release_driver(struct device *dev, struct device *parent)
drv = dev->driver;
if (drv) {
+ pm_runtime_get_sync(dev);
+
while (device_links_busy(dev)) {
__device_driver_unlock(dev, parent);
@@ -1128,13 +1130,12 @@ static void __device_release_driver(struct device *dev, struct device *parent)
* have released the driver successfully while this one
* was waiting, so check for that.
*/
- if (dev->driver != drv)
+ if (dev->driver != drv) {
+ pm_runtime_put(dev);
return;
+ }
}
- pm_runtime_get_sync(dev);
- pm_runtime_clean_up_links(dev);
-
driver_sysfs_remove(dev);
if (dev->bus)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6f605f7..bfda153 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1643,42 +1643,6 @@ void pm_runtime_remove(struct device *dev)
}
/**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
- struct device_link *link;
- int idx;
-
- idx = device_links_read_lock();
-
- list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
- device_links_read_lock_held()) {
- if (!(link->flags & DL_FLAG_MANAGED))
- continue;
-
- while (refcount_dec_not_one(&link->rpm_active))
- pm_runtime_put_noidle(dev);
- }
-
- device_links_read_unlock(idx);
-}
-
-/**
* pm_runtime_get_suppliers - Resume and reference-count supplier devices.
* @dev: Consumer device.
*/
@@ -1729,7 +1693,7 @@ void pm_runtime_new_link(struct device *dev)
spin_unlock_irq(&dev->power.lock);
}
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
{
spin_lock_irq(&dev->power.lock);
WARN_ON(dev->power.links_count == 0);
@@ -1737,6 +1701,25 @@ void pm_runtime_drop_link(struct device *dev)
spin_unlock_irq(&dev->power.lock);
}
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+ if (!(link->flags & DL_FLAG_PM_RUNTIME))
+ return;
+
+ pm_runtime_drop_link_count(link->consumer);
+
+ while (refcount_dec_not_one(&link->rpm_active))
+ pm_runtime_put(link->supplier);
+}
+
static bool pm_runtime_need_not_resume(struct device *dev)
{
return atomic_read(&dev->power.usage_count) <= 1 &&
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index fa2f1b4..a94bf28 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -7,7 +7,7 @@
*
* This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512.
*
- * You could find the datasheet in Documentation/arm/sunxi/README
+ * You could find the datasheet in Documentation/arm/sunxi.rst
*/
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
index 78503006..cfde9ee 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
@@ -7,7 +7,7 @@
*
* This file handle the PRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
index 6543281..5b7af44 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
@@ -7,7 +7,7 @@
*
* This file handle the TRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 37da353..5dbe93f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -239,9 +239,11 @@ bool amdgpu_device_supports_baco(struct drm_device *dev)
return amdgpu_asic_supports_baco(adev);
}
+/*
+ * VRAM access helper functions
+ */
+
/**
- * VRAM access helper functions.
- *
* amdgpu_device_vram_access - read/write a buffer in vram
*
* @adev: amdgpu_device pointer
@@ -705,7 +707,7 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
/**
* amdgpu_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
@@ -722,7 +724,7 @@ static uint32_t amdgpu_invalid_rreg(struct amdgpu_device *adev, uint32_t reg)
/**
* amdgpu_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
@@ -739,7 +741,7 @@ static void amdgpu_invalid_wreg(struct amdgpu_device *adev, uint32_t reg, uint32
/**
* amdgpu_invalid_rreg64 - dummy 64 bit reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
@@ -756,7 +758,7 @@ static uint64_t amdgpu_invalid_rreg64(struct amdgpu_device *adev, uint32_t reg)
/**
* amdgpu_invalid_wreg64 - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
@@ -773,7 +775,7 @@ static void amdgpu_invalid_wreg64(struct amdgpu_device *adev, uint32_t reg, uint
/**
* amdgpu_block_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
*
@@ -793,7 +795,7 @@ static uint32_t amdgpu_block_invalid_rreg(struct amdgpu_device *adev,
/**
* amdgpu_block_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
* @v: value to write to the register
@@ -813,7 +815,7 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
/**
* amdgpu_device_asic_init - Wrapper for atom asic_init
*
- * @dev: drm_device pointer
+ * @adev: amdgpu_device pointer
*
* Does any asic specific work and then calls atom asic init.
*/
@@ -827,7 +829,7 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev)
/**
* amdgpu_device_vram_scratch_init - allocate the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Allocates a scratch page of VRAM for use by various things in the
* driver.
@@ -844,7 +846,7 @@ static int amdgpu_device_vram_scratch_init(struct amdgpu_device *adev)
/**
* amdgpu_device_vram_scratch_fini - Free the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Frees the VRAM scratch page.
*/
@@ -3011,7 +3013,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
/**
* amdgpu_device_has_dc_support - check if dc is supported
*
- * @adev: amdgpu_device_pointer
+ * @adev: amdgpu_device pointer
*
* Returns true for supported, false for not supported
*/
@@ -4045,7 +4047,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
/**
* amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @from_hypervisor: request from hypervisor
*
* do VF FLR and reinitialize Asic
@@ -4100,7 +4102,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
/**
* amdgpu_device_has_job_running - check if there is any job in mirror list
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* check if there is any job in mirror list
*/
@@ -4128,7 +4130,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
/**
* amdgpu_device_should_recover_gpu - check if we should try GPU recovery
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover
* a hung GPU.
@@ -4477,7 +4479,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
/**
* amdgpu_device_gpu_recover - reset the asic and recover scheduler
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @job: which job trigger hang
*
* Attempt to reset the GPU if it has hung (all asics).
@@ -4497,7 +4499,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
bool need_emergency_restart = false;
bool audio_suspended = false;
- /**
+ /*
* Special case: RAS triggered and full reset isn't supported
*/
need_emergency_restart = amdgpu_ras_need_emergency_restart(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index f203e4a..731f3aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -81,8 +81,8 @@ static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func;
/**
* amdgpu_gtt_mgr_init - init GTT manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of GTT
+ * @adev: amdgpu_device pointer
+ * @gtt_size: maximum size of GTT
*
* Allocate and initialize the GTT manager.
*/
@@ -123,7 +123,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
/**
* amdgpu_gtt_mgr_fini - free and destroy GTT manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the GTT manager, returns -EBUSY if ranges are still
* allocated inside it.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 01c1171..0c6b7c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -168,8 +168,7 @@ static const struct ttm_resource_manager_func amdgpu_vram_mgr_func;
/**
* amdgpu_vram_mgr_init - init VRAM manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of VRAM
+ * @adev: amdgpu_device pointer
*
* Allocate and initialize the VRAM manager.
*/
@@ -199,7 +198,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
/**
* amdgpu_vram_mgr_fini - free and destroy VRAM manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the VRAM manager, returns -EBUSY if ranges are still
* allocated inside it.
@@ -229,7 +228,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
/**
* amdgpu_vram_mgr_vis_size - Calculate visible node size
*
- * @adev: amdgpu device structure
+ * @adev: amdgpu_device pointer
* @node: MM node structure
*
* Calculate how many bytes of the MM node are inside visible VRAM
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e2b23486..373b848 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -583,7 +583,7 @@ static void amdgpu_dm_fbc_init(struct drm_connector *connector)
{
struct drm_device *dev = connector->dev;
struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_comressor_info *compressor = &adev->dm.compressor;
+ struct dm_compressor_info *compressor = &adev->dm.compressor;
struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector);
struct drm_display_mode *mode;
unsigned long max_size = 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 34f6369..a8a0e8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -86,7 +86,7 @@ struct irq_list_head {
* @bo_ptr: Pointer to the buffer object
* @gpu_addr: MMIO gpu addr
*/
-struct dm_comressor_info {
+struct dm_compressor_info {
void *cpu_addr;
struct amdgpu_bo *bo_ptr;
uint64_t gpu_addr;
@@ -148,7 +148,7 @@ struct amdgpu_dm_backlight_caps {
* @soc_bounding_box: SOC bounding box values provided by gpu_info FW
* @cached_state: Caches device atomic state for suspend/resume
* @cached_dc_state: Cached state of content streams
- * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info
* @force_timing_sync: set via debugfs. When set, indicates that all connected
* displays will be forced to synchronize.
*/
@@ -324,7 +324,7 @@ struct amdgpu_display_manager {
struct drm_atomic_state *cached_state;
struct dc_state *cached_dc_state;
- struct dm_comressor_info compressor;
+ struct dm_compressor_info compressor;
const struct firmware *fw_dmcu;
uint32_t dmcu_fw_version;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 41435a6..bdeb010 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -256,6 +256,7 @@ enum rdma_ch_state {
* @rdma_cm: See below.
* @rdma_cm.cm_id: RDMA CM ID associated with the channel.
* @cq: IB completion queue for this channel.
+ * @cq_size: Number of CQEs in @cq.
* @zw_cqe: Zero-length write CQE.
* @rcu: RCU head.
* @kref: kref for this channel.
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 3a469c7..aedfaaa 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -112,7 +112,7 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
u64 dma_end = 0;
/* Determine the overall bounds of all DMA regions */
- for (dma_start = ~0ULL; r->size; r++) {
+ for (dma_start = ~0; r->size; r++) {
/* Take lower and upper limits */
if (r->dma_start < dma_start)
dma_start = r->dma_start;
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 2483e76..0e0a526 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1181,6 +1181,10 @@ static void _opp_table_kref_release(struct kref *kref)
struct opp_device *opp_dev, *temp;
int i;
+ /* Drop the lock as soon as we can */
+ list_del(&opp_table->node);
+ mutex_unlock(&opp_table_lock);
+
_of_clear_opp_table(opp_table);
/* Release clk */
@@ -1208,10 +1212,7 @@ static void _opp_table_kref_release(struct kref *kref)
mutex_destroy(&opp_table->genpd_virt_dev_lock);
mutex_destroy(&opp_table->lock);
- list_del(&opp_table->node);
kfree(opp_table);
-
- mutex_unlock(&opp_table_lock);
}
void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
@@ -1930,7 +1931,7 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
return ERR_PTR(-EINVAL);
opp_table = dev_pm_opp_get_opp_table(dev);
- if (!IS_ERR(opp_table))
+ if (IS_ERR(opp_table))
return opp_table;
/* This should be called before OPPs are initialized */
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 874b587..9faeb83 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -944,6 +944,8 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table)
nr -= 2;
}
+ return 0;
+
remove_static_opp:
_opp_remove_all_static(opp_table);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 674f32d..44c2a65 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -586,8 +586,12 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
* ATU, so we should not program the ATU here.
*/
if (pp->bridge->child_ops == &dw_child_pcie_ops) {
- struct resource_entry *entry =
- resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
+ struct resource_entry *tmp, *entry = NULL;
+
+ /* Get last memory resource entry */
+ resource_list_for_each_entry(tmp, &pp->bridge->windows)
+ if (resource_type(tmp->res) == IORESOURCE_MEM)
+ entry = tmp;
dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0,
PCIE_ATU_TYPE_MEM, entry->res->start,
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index eee8283..ed13e81 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -958,25 +958,16 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port)
}
/*
- * We can't use devm_of_pci_get_host_bridge_resources() because we
- * need to parse our special DT properties encoding the MEM and IO
- * apertures.
+ * devm_of_pci_get_host_bridge_resources() only sets up translateable resources,
+ * so we need extra resource setup parsing our special DT properties encoding
+ * the MEM and IO apertures.
*/
static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
{
struct device *dev = &pcie->pdev->dev;
- struct device_node *np = dev->of_node;
struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
int ret;
- /* Get the bus range */
- ret = of_pci_parse_bus_range(np, &pcie->busn);
- if (ret) {
- dev_err(dev, "failed to parse bus-range property: %d\n", ret);
- return ret;
- }
- pci_add_resource(&bridge->windows, &pcie->busn);
-
/* Get the PCIe memory aperture */
mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
if (resource_size(&pcie->mem) == 0) {
@@ -986,6 +977,9 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
pcie->mem.name = "PCI MEM";
pci_add_resource(&bridge->windows, &pcie->mem);
+ ret = devm_request_resource(dev, &iomem_resource, &pcie->mem);
+ if (ret)
+ return ret;
/* Get the PCIe IO aperture */
mvebu_mbus_get_pcie_io_aperture(&pcie->io);
@@ -999,9 +993,12 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
pcie->realio.name = "PCI I/O";
pci_add_resource(&bridge->windows, &pcie->realio);
+ ret = devm_request_resource(dev, &ioport_resource, &pcie->realio);
+ if (ret)
+ return ret;
}
- return devm_request_pci_bus_resources(dev, &bridge->windows);
+ return 0;
}
/*
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6d4d5a2..e578d34 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3516,8 +3516,13 @@ void pci_acs_init(struct pci_dev *dev)
{
dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
- if (dev->acs_cap)
- pci_enable_acs(dev);
+ /*
+ * Attempt to enable ACS regardless of capability because some Root
+ * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have
+ * the standard ACS capability but still support ACS via those
+ * quirks.
+ */
+ pci_enable_acs(dev);
}
/**
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 0b2830e..70d6d52 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -620,7 +620,7 @@ static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type,
case ARBITRARY_UNIT:
default:
return value;
- };
+ }
if (to_raw)
return div64_u64(value, units) * scale;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a4ffd71..a5ad553 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -4165,6 +4165,8 @@ int regulator_get_voltage_rdev(struct regulator_dev *rdev)
ret = rdev->desc->fixed_uV;
} else if (rdev->supply) {
ret = regulator_get_voltage_rdev(rdev->supply->rdev);
+ } else if (rdev->supply_name) {
+ return -EPROBE_DEFER;
} else {
return -EINVAL;
}
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index b87116e..9b6ba94 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -1259,18 +1259,6 @@ static int bcm2835_spi_setup(struct spi_device *spi)
if (!chip)
return 0;
- /*
- * Retrieve the corresponding GPIO line used for CS.
- * The inversion semantics will be handled by the GPIO core
- * code, so we pass GPIOD_OUT_LOW for "unasserted" and
- * the correct flag for inversion semantics. The SPI_CS_HIGH
- * on spi->mode cannot be checked for polarity in this case
- * as the flag use_gpio_descriptors enforces SPI_CS_HIGH.
- */
- if (of_property_read_bool(spi->dev.of_node, "spi-cs-high"))
- lflags = GPIO_ACTIVE_HIGH;
- else
- lflags = GPIO_ACTIVE_LOW;
spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select,
DRV_NAME,
lflags,
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3967afa..1a08c1d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1080,12 +1080,11 @@ MODULE_DEVICE_TABLE(of, fsl_dspi_dt_ids);
#ifdef CONFIG_PM_SLEEP
static int dspi_suspend(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
if (dspi->irq)
disable_irq(dspi->irq);
- spi_controller_suspend(ctlr);
+ spi_controller_suspend(dspi->ctlr);
clk_disable_unprepare(dspi->clk);
pinctrl_pm_select_sleep_state(dev);
@@ -1095,8 +1094,7 @@ static int dspi_suspend(struct device *dev)
static int dspi_resume(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
int ret;
pinctrl_pm_select_default_state(dev);
@@ -1104,7 +1102,7 @@ static int dspi_resume(struct device *dev)
ret = clk_prepare_enable(dspi->clk);
if (ret)
return ret;
- spi_controller_resume(ctlr);
+ spi_controller_resume(dspi->ctlr);
if (dspi->irq)
enable_irq(dspi->irq);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 060b1f5..4b80e27 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1676,15 +1676,18 @@ static int spi_imx_probe(struct platform_device *pdev)
goto out_master_put;
}
- pm_runtime_enable(spi_imx->dev);
+ ret = clk_prepare_enable(spi_imx->clk_per);
+ if (ret)
+ goto out_master_put;
+
+ ret = clk_prepare_enable(spi_imx->clk_ipg);
+ if (ret)
+ goto out_put_per;
+
pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT);
pm_runtime_use_autosuspend(spi_imx->dev);
-
- ret = pm_runtime_get_sync(spi_imx->dev);
- if (ret < 0) {
- dev_err(spi_imx->dev, "failed to enable clock\n");
- goto out_runtime_pm_put;
- }
+ pm_runtime_set_active(spi_imx->dev);
+ pm_runtime_enable(spi_imx->dev);
spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
/*
@@ -1722,8 +1725,12 @@ static int spi_imx_probe(struct platform_device *pdev)
spi_imx_sdma_exit(spi_imx);
out_runtime_pm_put:
pm_runtime_dont_use_autosuspend(spi_imx->dev);
- pm_runtime_put_sync(spi_imx->dev);
+ pm_runtime_set_suspended(&pdev->dev);
pm_runtime_disable(spi_imx->dev);
+
+ clk_disable_unprepare(spi_imx->clk_ipg);
+out_put_per:
+ clk_disable_unprepare(spi_imx->clk_per);
out_master_put:
spi_master_put(master);
diff --git a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
index 43b5630..510edd1 100644
--- a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
+++ b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
@@ -24,7 +24,7 @@
In addition, it is recommended to declare a mmc-pwrseq on SDIO host above
WFx. Without it, you may encounter issues with warm boot. The mmc-pwrseq
should be compatible with mmc-pwrseq-simple. Please consult
- Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt for more
+ Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml for more
information.
For SPI':'
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 2321775..5f61b25a9 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -484,7 +484,7 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd,
return 0;
}
-static inline int do_fontx_ioctl(int cmd,
+static inline int do_fontx_ioctl(struct vc_data *vc, int cmd,
struct consolefontdesc __user *user_cfd,
struct console_font_op *op)
{
@@ -502,15 +502,16 @@ static inline int do_fontx_ioctl(int cmd,
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- return con_font_op(vc_cons[fg_console].d, op);
- case GIO_FONTX: {
+ return con_font_op(vc, op);
+
+ case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
op->width = 8;
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
@@ -518,12 +519,11 @@ static inline int do_fontx_ioctl(int cmd,
if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc)))
return -EFAULT;
return 0;
- }
}
return -EINVAL;
}
-static int vt_io_fontreset(struct console_font_op *op)
+static int vt_io_fontreset(struct vc_data *vc, struct console_font_op *op)
{
int ret;
@@ -537,12 +537,12 @@ static int vt_io_fontreset(struct console_font_op *op)
op->op = KD_FONT_OP_SET_DEFAULT;
op->data = NULL;
- ret = con_font_op(vc_cons[fg_console].d, op);
+ ret = con_font_op(vc, op);
if (ret)
return ret;
console_lock();
- con_set_default_unimap(vc_cons[fg_console].d);
+ con_set_default_unimap(vc);
console_unlock();
return 0;
@@ -584,7 +584,7 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up,
op.height = 0;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case GIO_FONT:
op.op = KD_FONT_OP_GET;
@@ -593,7 +593,7 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up,
op.height = 32;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case PIO_CMAP:
if (!perm)
@@ -609,13 +609,13 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up,
fallthrough;
case GIO_FONTX:
- return do_fontx_ioctl(cmd, up, &op);
+ return do_fontx_ioctl(vc, cmd, up, &op);
case PIO_FONTRESET:
if (!perm)
return -EPERM;
- return vt_io_fontreset(&op);
+ return vt_io_fontreset(vc, &op);
case PIO_SCRNMAP:
if (!perm)
@@ -1066,8 +1066,9 @@ struct compat_consolefontdesc {
};
static inline int
-compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
- int perm, struct console_font_op *op)
+compat_fontx_ioctl(struct vc_data *vc, int cmd,
+ struct compat_consolefontdesc __user *user_cfd,
+ int perm, struct console_font_op *op)
{
struct compat_consolefontdesc cfdarg;
int i;
@@ -1085,7 +1086,8 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- return con_font_op(vc_cons[fg_console].d, op);
+ return con_font_op(vc, op);
+
case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
@@ -1093,7 +1095,7 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
@@ -1183,7 +1185,7 @@ long vt_compat_ioctl(struct tty_struct *tty,
*/
case PIO_FONTX:
case GIO_FONTX:
- return compat_fontx_ioctl(cmd, up, perm, &op);
+ return compat_fontx_ioctl(vc, cmd, up, perm, &op);
case KDFONTOP:
return compat_kdfontop_ioctl(up, perm, &op, vc);
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 38884d6..95c573d 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -148,11 +148,6 @@ static const struct xattr_handler afs_xattr_afs_acl_handler = {
.set = afs_xattr_set_acl,
};
-static void yfs_acl_put(struct afs_operation *op)
-{
- yfs_free_opaque_acl(op->yacl);
-}
-
static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = {
.issue_yfs_rpc = yfs_fs_fetch_opaque_acl,
.success = afs_acl_success,
@@ -246,7 +241,7 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler,
static const struct afs_operation_ops yfs_store_opaque_acl2_operation = {
.issue_yfs_rpc = yfs_fs_store_opaque_acl2,
.success = afs_acl_success,
- .put = yfs_acl_put,
+ .put = afs_acl_put,
};
/*
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3b1239b..bd787e7 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -1990,6 +1990,7 @@ void yfs_fs_store_opaque_acl2(struct afs_operation *op)
memcpy(bp, acl->data, acl->size);
if (acl->size != size)
memset((void *)bp + acl->size, 0, size - acl->size);
+ bp += size / sizeof(__be32);
yfs_check_req(call, bp);
trace_afs_make_fs_call(call, &vp->fid);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 5441c17..d98a2e5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1078,7 +1078,8 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
out_free:
kfree(gl->gl_lksb.sb_lvbptr);
kmem_cache_free(cachep, gl);
- atomic_dec(&sdp->sd_glock_disposal);
+ if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+ wake_up(&sdp->sd_glock_wait);
out:
return ret;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index aa3f523..6c1432d 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -165,6 +165,31 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
}
/**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct address_space *metamapping = &sdp->sd_aspace;
+ struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ const unsigned bsize = sdp->sd_sb.sb_bsize;
+ loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+ int error;
+
+ filemap_fdatawrite_range(metamapping, start, end);
+ error = filemap_fdatawait_range(metamapping, start, end);
+ WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+ mapping_set_error(metamapping, error);
+ if (error)
+ gfs2_io_error(sdp);
+ return error;
+}
+
+/**
* rgrp_go_sync - sync out the metadata for this glock
* @gl: the glock
*
@@ -176,11 +201,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
static int rgrp_go_sync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = &sdp->sd_aspace;
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
- const unsigned bsize = sdp->sd_sb.sb_bsize;
- loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
- loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
int error;
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -189,10 +210,7 @@ static int rgrp_go_sync(struct gfs2_glock *gl)
gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_RGRP_GO_SYNC);
- filemap_fdatawrite_range(mapping, start, end);
- error = filemap_fdatawait_range(mapping, start, end);
- WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
- mapping_set_error(mapping, error);
+ error = gfs2_rgrp_metasync(gl);
if (!error)
error = gfs2_ail_empty_gl(gl);
gfs2_free_clones(rgd);
@@ -266,7 +284,24 @@ static void gfs2_clear_glop_pending(struct gfs2_inode *ip)
}
/**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+int gfs2_inode_metasync(struct gfs2_glock *gl)
+{
+ struct address_space *metamapping = gfs2_glock2aspace(gl);
+ int error;
+
+ filemap_fdatawrite(metamapping);
+ error = filemap_fdatawait(metamapping);
+ if (error)
+ gfs2_io_error(gl->gl_name.ln_sbd);
+ return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
* @gl: the glock protecting the inode
*
*/
@@ -297,8 +332,7 @@ static int inode_go_sync(struct gfs2_glock *gl)
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
- ret = filemap_fdatawait(metamapping);
- mapping_set_error(metamapping, ret);
+ ret = gfs2_inode_metasync(gl);
if (!error)
error = ret;
gfs2_ail_empty_gl(gl);
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index 2dd192e..695898a 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -22,6 +22,7 @@ extern const struct gfs2_glock_operations gfs2_quota_glops;
extern const struct gfs2_glock_operations gfs2_journal_glops;
extern const struct gfs2_glock_operations *gfs2_glops_list[];
+extern int gfs2_inode_metasync(struct gfs2_glock *gl);
extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
#endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6774865..077ccb1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -180,7 +180,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail;
- gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
+ if (blktype != GFS2_BLKST_UNLINKED)
+ gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
io_gl = NULL;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index ed69298..3922b26 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -22,6 +22,7 @@
#include "incore.h"
#include "inode.h"
#include "glock.h"
+#include "glops.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
@@ -817,41 +818,19 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
return error;
}
-/**
- * gfs2_meta_sync - Sync all buffers associated with a glock
- * @gl: The glock
- *
- */
-
-void gfs2_meta_sync(struct gfs2_glock *gl)
-{
- struct address_space *mapping = gfs2_glock2aspace(gl);
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- int error;
-
- if (mapping == NULL)
- mapping = &sdp->sd_aspace;
-
- filemap_fdatawrite(mapping);
- error = filemap_fdatawait(mapping);
-
- if (error)
- gfs2_io_error(gl->gl_name.ln_sbd);
-}
-
static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
@@ -1060,14 +1039,14 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
/* data sync? */
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 4a3d8ae..fbdbb08 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -27,8 +27,6 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf);
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, bool keep_cache);
-extern void gfs2_meta_sync(struct gfs2_glock *gl);
-
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
unsigned int limit;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 7a7e3c1..61fce59 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -633,8 +633,10 @@ static int init_statfs(struct gfs2_sbd *sdp)
if (IS_ERR(sdp->sd_statfs_inode)) {
error = PTR_ERR(sdp->sd_statfs_inode);
fs_err(sdp, "can't read in statfs inode: %d\n", error);
- goto fail;
+ goto out;
}
+ if (sdp->sd_args.ar_spectator)
+ goto out;
pn = gfs2_lookup_simple(master, "per_node");
if (IS_ERR(pn)) {
@@ -682,15 +684,17 @@ static int init_statfs(struct gfs2_sbd *sdp)
iput(pn);
put_statfs:
iput(sdp->sd_statfs_inode);
-fail:
+out:
return error;
}
/* Uninitialize and free up memory used by the list of statfs inodes */
static void uninit_statfs(struct gfs2_sbd *sdp)
{
- gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
- free_local_statfs_inodes(sdp);
+ if (!sdp->sd_args.ar_spectator) {
+ gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+ free_local_statfs_inodes(sdp);
+ }
iput(sdp->sd_statfs_inode);
}
@@ -704,7 +708,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
if (undo) {
jindex = 0;
- goto fail_jinode_gh;
+ goto fail_statfs;
}
sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index b5cbe21..c26c68e 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -349,7 +349,7 @@ static int update_statfs_inode(struct gfs2_jdesc *jd,
mark_buffer_dirty(bh);
brelse(bh);
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
out:
return error;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ee491bb..92d799a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -719,9 +719,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
}
gfs2_free_clones(rgd);
+ return_all_reservations(rgd);
kfree(rgd->rd_bits);
rgd->rd_bits = NULL;
- return_all_reservations(rgd);
kmem_cache_free(gfs2_rgrpd_cachep, rgd);
}
}
@@ -1370,6 +1370,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+ return -EROFS;
+
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b285192b..b3d951a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -738,6 +738,7 @@ static void gfs2_put_super(struct super_block *sb)
gfs2_jindex_free(sdp);
/* Take apart glock structures and buffer lists */
gfs2_gl_hash_clear(sdp);
+ truncate_inode_pages_final(&sdp->sd_aspace);
gfs2_delete_debugfs_file(sdp);
/* Unmount the locking protocol */
gfs2_lm_unmount(sdp);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0f70700..b362523 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1049,6 +1049,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
OOM_SCORE_ADJ_MAX;
put_task_struct(task);
+ if (oom_adj > OOM_ADJUST_MAX)
+ oom_adj = OOM_ADJUST_MAX;
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b23eeca..794b2a3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -235,6 +235,8 @@ enum hctx_type {
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
+ * @active_queues_shared_sbitmap:
+ * number of active request queues per tag set.
* @__bitmap_tags: A shared tags sbitmap, used over all hctx's
* @__breserved_tags:
* A shared reserved tags sbitmap, used over all hctx's
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe..db6ae4d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2759,6 +2759,15 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
return VM_FAULT_NOPAGE;
}
+#ifndef io_remap_pfn_range
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+}
+#endif
+
static inline vm_fault_t vmf_error(int err)
{
if (err == -ENOMEM)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c77b7c31..e1e19c1 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -344,9 +344,9 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
- * @offset: the page index
+ * @index: the page index
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
@@ -363,9 +363,9 @@ static inline struct page *find_lock_page(struct address_space *mapping,
/**
* find_lock_head - Locate, pin and lock a pagecache page.
* @mapping: The address_space to search.
- * @offset: The page index.
+ * @index: The page index.
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, its head page is returned locked and with an increased
* refcount.
*
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 38c33ea..71125a4 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,10 +1427,6 @@ typedef unsigned int pgtbl_mod_mask;
#endif /* !__ASSEMBLY__ */
-#ifndef io_remap_pfn_range
-#define io_remap_pfn_range remap_pfn_range
-#endif
-
#ifndef has_transparent_hugepage
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define has_transparent_hugepage() 1
diff --git a/include/linux/phy.h b/include/linux/phy.h
index eb3cb1a..56563e5e0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -147,16 +147,8 @@ typedef enum {
PHY_INTERFACE_MODE_MAX,
} phy_interface_t;
-/**
+/*
* phy_supported_speeds - return all speeds currently supported by a PHY device
- * @phy: The PHY device to return supported speeds of.
- * @speeds: buffer to store supported speeds in.
- * @size: size of speeds buffer.
- *
- * Description: Returns the number of supported speeds, and fills
- * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain all currently supported speeds, will return as
- * many speeds as can fit.
*/
unsigned int phy_supported_speeds(struct phy_device *phy,
unsigned int *speeds,
@@ -1022,14 +1014,9 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum,
regnum, mask, set);
}
-/**
+/*
* phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for phy_read();
*/
int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
@@ -1064,38 +1051,21 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
__ret; \
})
-/**
+/*
* __phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for __phy_read();
*/
int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
-/**
+/*
* phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for phy_write();
*/
int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
-/**
+/*
* __phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for __phy_write();
*/
int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 18b02dc..4b708f4 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -54,11 +54,10 @@ extern u64 pm_runtime_autosuspend_expiration(struct device *dev);
extern void pm_runtime_update_max_time_suspended(struct device *dev,
s64 delta_ns);
extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
-extern void pm_runtime_clean_up_links(struct device *dev);
extern void pm_runtime_get_suppliers(struct device *dev);
extern void pm_runtime_put_suppliers(struct device *dev);
extern void pm_runtime_new_link(struct device *dev);
-extern void pm_runtime_drop_link(struct device *dev);
+extern void pm_runtime_drop_link(struct device_link *link);
/**
* pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
@@ -276,11 +275,10 @@ static inline u64 pm_runtime_autosuspend_expiration(
struct device *dev) { return 0; }
static inline void pm_runtime_set_memalloc_noio(struct device *dev,
bool enable){}
-static inline void pm_runtime_clean_up_links(struct device *dev) {}
static inline void pm_runtime_get_suppliers(struct device *dev) {}
static inline void pm_runtime_put_suppliers(struct device *dev) {}
static inline void pm_runtime_new_link(struct device *dev) {}
-static inline void pm_runtime_drop_link(struct device *dev) {}
+static inline void pm_runtime_drop_link(struct device_link *link) {}
#endif /* !CONFIG_PM */
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 7fabb1a..497990c 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -147,24 +147,6 @@ static inline unsigned int refcount_read(const refcount_t *r)
return atomic_read(&r->refs);
}
-/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at REFCOUNT_SATURATED and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time. In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
{
int old = refcount_read(r);
@@ -183,11 +165,42 @@ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, in
return old;
}
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
{
return __refcount_add_not_zero(i, r, NULL);
}
+static inline void __refcount_add(int i, refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_add_relaxed(i, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (unlikely(!old))
+ refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
+ else if (unlikely(old < 0 || old + i < 0))
+ refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
+}
+
/**
* refcount_add - add a value to a refcount
* @i: the value to add to the refcount
@@ -204,24 +217,16 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
*/
-static inline void __refcount_add(int i, refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_add_relaxed(i, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (unlikely(!old))
- refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
- else if (unlikely(old < 0 || old + i < 0))
- refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
-}
-
static inline void refcount_add(int i, refcount_t *r)
{
__refcount_add(i, r, NULL);
}
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+ return __refcount_add_not_zero(1, r, oldp);
+}
+
/**
* refcount_inc_not_zero - increment a refcount unless it is 0
* @r: the refcount to increment
@@ -235,16 +240,16 @@ static inline void refcount_add(int i, refcount_t *r)
*
* Return: true if the increment was successful, false otherwise
*/
-static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
-{
- return __refcount_add_not_zero(1, r, oldp);
-}
-
static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
{
return __refcount_inc_not_zero(r, NULL);
}
+static inline void __refcount_inc(refcount_t *r, int *oldp)
+{
+ __refcount_add(1, r, oldp);
+}
+
/**
* refcount_inc - increment a refcount
* @r: the refcount to increment
@@ -257,16 +262,29 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
* Will WARN if the refcount is 0, as this represents a possible use-after-free
* condition.
*/
-static inline void __refcount_inc(refcount_t *r, int *oldp)
-{
- __refcount_add(1, r, oldp);
-}
-
static inline void refcount_inc(refcount_t *r)
{
__refcount_inc(r, NULL);
}
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_sub_release(i, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (old == i) {
+ smp_acquire__after_ctrl_dep();
+ return true;
+ }
+
+ if (unlikely(old < 0 || old - i < 0))
+ refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+ return false;
+}
+
/**
* refcount_sub_and_test - subtract from a refcount and test if it is 0
* @i: amount to subtract from the refcount
@@ -287,29 +305,16 @@ static inline void refcount_inc(refcount_t *r)
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_sub_release(i, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (old == i) {
- smp_acquire__after_ctrl_dep();
- return true;
- }
-
- if (unlikely(old < 0 || old - i < 0))
- refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
-
- return false;
-}
-
static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
{
return __refcount_sub_and_test(i, r, NULL);
}
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
+{
+ return __refcount_sub_and_test(1, r, oldp);
+}
+
/**
* refcount_dec_and_test - decrement a refcount and test if it is 0
* @r: the refcount
@@ -323,16 +328,22 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
-{
- return __refcount_sub_and_test(1, r, oldp);
-}
-
static inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
return __refcount_dec_and_test(r, NULL);
}
+static inline void __refcount_dec(refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_sub_release(1, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (unlikely(old <= 1))
+ refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
+}
+
/**
* refcount_dec - decrement a refcount
* @r: the refcount
@@ -343,17 +354,6 @@ static inline __must_check bool refcount_dec_and_test(refcount_t *r)
* Provides release memory ordering, such that prior loads and stores are done
* before.
*/
-static inline void __refcount_dec(refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_sub_release(1, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (unlikely(old <= 1))
- refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
-}
-
static inline void refcount_dec(refcount_t *r)
{
__refcount_dec(r, NULL);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index ce76f49..396ebae 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -225,8 +225,7 @@ static long hung_timeout_jiffies(unsigned long last_checked,
* Process updating of timeout sysctl
*/
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index e29773c..933a625 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -897,7 +897,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t)
/* Move the work from worker->delayed_work_list. */
WARN_ON_ONCE(list_empty(&work->node));
list_del_init(&work->node);
- kthread_insert_work(worker, work, &worker->work_list);
+ if (!work->canceling)
+ kthread_insert_work(worker, work, &worker->work_list);
raw_spin_unlock_irqrestore(&worker->lock, flags);
}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c03a5775..d73bccd 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,9 +102,12 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
unsigned int next_freq)
{
- if (sg_policy->next_freq == next_freq &&
- !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
- return false;
+ if (!sg_policy->need_freq_update) {
+ if (sg_policy->next_freq == next_freq)
+ return false;
+ } else {
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+ }
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
@@ -162,11 +165,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
freq = map_util_freq(util, freq, max);
- if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update &&
- !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+ if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
@@ -442,7 +443,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
unsigned long util, max;
unsigned int next_f;
- bool busy;
unsigned int cached_freq = sg_policy->cached_raw_freq;
sugov_iowait_boost(sg_cpu, time, flags);
@@ -453,9 +453,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
- /* Limits may have changed, don't skip frequency update */
- busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
util = sugov_iowait_apply(sg_cpu, time, util, max);
@@ -464,7 +461,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
* 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) {
+ if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
next_f = sg_policy->next_freq;
/* Restore cached freq as next_freq has changed */
@@ -829,9 +826,10 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
sg_policy->limits_changed = false;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
diff --git a/kernel/signal.c b/kernel/signal.c
index a38b3ed..ef8f2a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -391,16 +391,17 @@ static bool task_participate_group_stop(struct task_struct *task)
void task_join_group_stop(struct task_struct *task)
{
+ unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
+ struct signal_struct *sig = current->signal;
+
+ if (sig->group_stop_count) {
+ sig->group_stop_count++;
+ mask |= JOBCTL_STOP_CONSUME;
+ } else if (!(sig->flags & SIGNAL_STOP_STOPPED))
+ return;
+
/* Have the new thread join an on-going signal group stop */
- unsigned long jobctl = current->jobctl;
- if (jobctl & JOBCTL_STOP_PENDING) {
- struct signal_struct *sig = current->signal;
- unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
- unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
- if (task_set_jobctl_pending(task, signr | gstop)) {
- sig->group_stop_count++;
- }
- }
+ task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
}
/*
diff --git a/lib/crc32test.c b/lib/crc32test.c
index 97d6a57..61ddce2 100644
--- a/lib/crc32test.c
+++ b/lib/crc32test.c
@@ -683,7 +683,6 @@ static int __init crc32c_test(void)
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
@@ -694,7 +693,6 @@ static int __init crc32c_test(void)
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
@@ -768,7 +766,6 @@ static int __init crc32_test(void)
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
@@ -783,7 +780,6 @@ static int __init crc32_test(void)
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
CRC_LE_BITS, CRC_BE_BITS);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 63c2617..662f862 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -216,6 +216,12 @@ static void kmalloc_oob_16(struct kunit *test)
u64 words[2];
} *ptr1, *ptr2;
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
@@ -227,6 +233,23 @@ static void kmalloc_oob_16(struct kunit *test)
kfree(ptr2);
}
+static void kmalloc_uaf_16(struct kunit *test)
+{
+ struct {
+ u64 words[2];
+ } *ptr1, *ptr2;
+
+ ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
+
+ ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
+ kfree(ptr2);
+
+ KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2);
+ kfree(ptr1);
+}
+
static void kmalloc_oob_memset_2(struct kunit *test)
{
char *ptr;
@@ -429,6 +452,12 @@ static void kasan_global_oob(struct kunit *test)
volatile int i = 3;
char *p = &global_array[ARRAY_SIZE(global_array) + i];
+ /* Only generic mode instruments globals. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
}
@@ -467,6 +496,12 @@ static void kasan_alloca_oob_left(struct kunit *test)
char alloca_array[i];
char *p = alloca_array - 1;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
@@ -481,6 +516,12 @@ static void kasan_alloca_oob_right(struct kunit *test)
char alloca_array[i];
char *p = alloca_array + i;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
@@ -551,6 +592,9 @@ static void kasan_memchr(struct kunit *test)
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
@@ -573,6 +617,9 @@ static void kasan_memcmp(struct kunit *test)
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
memset(arr, 0, sizeof(arr));
@@ -619,13 +666,50 @@ static void kasan_strings(struct kunit *test)
KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1));
}
-static void kasan_bitops(struct kunit *test)
+static void kasan_bitops_modify(struct kunit *test, int nr, void *addr)
{
+ KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr));
+}
+
+static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr)
+{
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr));
+
+#if defined(clear_bit_unlock_is_negative_byte)
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
+ clear_bit_unlock_is_negative_byte(nr, addr));
+#endif
+}
+
+static void kasan_bitops_generic(struct kunit *test)
+{
+ long *bits;
+
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
/*
* Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
* this way we do not actually corrupt other memory.
*/
- long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
+ bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
/*
@@ -633,55 +717,34 @@ static void kasan_bitops(struct kunit *test)
* below accesses are still out-of-bounds, since bitops are defined to
* operate on the whole long the bit is in.
*/
- KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits));
+ kasan_bitops_modify(test, BITS_PER_LONG, bits);
/*
* Below calls try to access bit beyond allocated memory.
*/
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kfree(bits);
+}
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits));
+static void kasan_bitops_tags(struct kunit *test)
+{
+ long *bits;
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* This test is specifically crafted for the tag-based mode. */
+ if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n");
+ return;
+ }
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Allocation size will be rounded to up granule size, which is 16. */
+ bits = kzalloc(sizeof(*bits), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Do the accesses past the 16 allocated bytes. */
+ kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]);
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]);
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result =
- test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
-#if defined(clear_bit_unlock_is_negative_byte)
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result = clear_bit_unlock_is_negative_byte(
- BITS_PER_LONG + BITS_PER_BYTE, bits));
-#endif
kfree(bits);
}
@@ -728,6 +791,7 @@ static struct kunit_case kasan_kunit_test_cases[] = {
KUNIT_CASE(kmalloc_oob_krealloc_more),
KUNIT_CASE(kmalloc_oob_krealloc_less),
KUNIT_CASE(kmalloc_oob_16),
+ KUNIT_CASE(kmalloc_uaf_16),
KUNIT_CASE(kmalloc_oob_in_memset),
KUNIT_CASE(kmalloc_oob_memset_2),
KUNIT_CASE(kmalloc_oob_memset_4),
@@ -751,7 +815,8 @@ static struct kunit_case kasan_kunit_test_cases[] = {
KUNIT_CASE(kasan_memchr),
KUNIT_CASE(kasan_memcmp),
KUNIT_CASE(kasan_strings),
- KUNIT_CASE(kasan_bitops),
+ KUNIT_CASE(kasan_bitops_generic),
+ KUNIT_CASE(kasan_bitops_tags),
KUNIT_CASE(kmalloc_double_kzfree),
KUNIT_CASE(vmalloc_oob),
{}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8f..5a620f6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@ static long region_del(struct resv_map *resv, long f, long t)
}
del += t - f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, t - f);
/* New entry for end of split region */
nrg->from = t;
@@ -660,9 +662,6 @@ static long region_del(struct resv_map *resv, long f, long t)
/* Original entry is trimmed */
rg->to = f;
- hugetlb_cgroup_uncharge_file_region(
- resv, rg, nrg->to - nrg->from);
-
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -678,17 +677,17 @@ static long region_del(struct resv_map *resv, long f, long t)
}
if (f <= rg->from) { /* Trim beginning of region */
- del += t - rg->from;
- rg->from = t;
-
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from);
- } else { /* Trim end of region */
- del += rg->to - f;
- rg->to = f;
+ del += t - rg->from;
+ rg->from = t;
+ } else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f);
+
+ del += rg->to - f;
+ rg->to = f;
}
}
@@ -2443,6 +2442,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
+ if (deferred_reserve)
+ hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+ pages_per_huge_page(h), page);
}
return page;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3a24e3b..3dcbf24 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4110,11 +4110,17 @@ static int memcg_stat_show(struct seq_file *m, void *v)
(u64)memsw * PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+ unsigned long nr;
+
if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
continue;
+ nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (memcg1_stats[i] == NR_ANON_THPS)
+ nr *= HPAGE_PMD_NR;
+#endif
seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
- (u64)memcg_page_state(memcg, memcg1_stats[i]) *
- PAGE_SIZE);
+ (u64)nr * PAGE_SIZE);
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -5339,17 +5345,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
memcg->swappiness = mem_cgroup_swappiness(parent);
memcg->oom_kill_disable = parent->oom_kill_disable;
}
- if (parent && parent->use_hierarchy) {
+ if (!parent) {
+ page_counter_init(&memcg->memory, NULL);
+ page_counter_init(&memcg->swap, NULL);
+ page_counter_init(&memcg->kmem, NULL);
+ page_counter_init(&memcg->tcpmem, NULL);
+ } else if (parent->use_hierarchy) {
memcg->use_hierarchy = true;
page_counter_init(&memcg->memory, &parent->memory);
page_counter_init(&memcg->swap, &parent->swap);
page_counter_init(&memcg->kmem, &parent->kmem);
page_counter_init(&memcg->tcpmem, &parent->tcpmem);
} else {
- page_counter_init(&memcg->memory, NULL);
- page_counter_init(&memcg->swap, NULL);
- page_counter_init(&memcg->kmem, NULL);
- page_counter_init(&memcg->tcpmem, NULL);
+ page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
+ page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
+ page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+ page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
/*
* Deeper hierachy with use_hierarchy == false doesn't make
* much sense so let cgroup subsystem know about this
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3fde772..3ca4898 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,7 +525,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long flags = qp->flags;
int ret;
bool has_unmovable = false;
- pte_t *pte;
+ pte_t *pte, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
@@ -539,7 +539,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
if (pmd_trans_unstable(pmd))
return 0;
- pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
@@ -571,7 +571,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
} else
break;
}
- pte_unmap_unlock(pte - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
if (has_unmovable)
diff --git a/mm/memremap.c b/mm/memremap.c
index 73a206d..16b2fb4 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -41,28 +41,24 @@ EXPORT_SYMBOL_GPL(memremap_compat_align);
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
- static_branch_dec(&devmap_managed_key);
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_dec(&devmap_managed_key);
}
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
- (!pgmap->ops || !pgmap->ops->page_free)) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- static_branch_inc(&devmap_managed_key);
- return 0;
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_inc(&devmap_managed_key);
}
#else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- return -EINVAL;
}
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
@@ -169,7 +165,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
pageunmap_range(pgmap, i);
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
- devmap_managed_enable_put();
+ devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
@@ -307,7 +303,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
.pgprot = PAGE_KERNEL,
};
const int nr_range = pgmap->nr_range;
- bool need_devmap_managed = true;
int error, i;
if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
@@ -323,6 +318,10 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
@@ -336,11 +335,9 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
}
break;
case MEMORY_DEVICE_GENERIC:
- need_devmap_managed = false;
break;
case MEMORY_DEVICE_PCI_P2PDMA:
params.pgprot = pgprot_noncached(params.pgprot);
- need_devmap_managed = false;
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@@ -364,11 +361,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
}
}
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(pgmap);
- if (error)
- return ERR_PTR(error);
- }
+ devmap_managed_enable_get(pgmap);
/*
* Clear the pgmap nr_range as it will be incremented for each
diff --git a/mm/truncate.c b/mm/truncate.c
index 18cec39..960edf5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,7 +528,7 @@ void truncate_inode_pages_final(struct address_space *mapping)
}
EXPORT_SYMBOL(truncate_inode_pages_final);
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
pgoff_t indices[PAGEVEC_SIZE];
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index c8f6b11..f699cf0 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1092,7 +1092,11 @@
print "\n\n.. c:type:: " . $name . "\n\n";
} else {
my $name = $args{'struct'};
- print "\n\n.. c:struct:: " . $name . "\n\n";
+ if ($args{'type'} eq 'union') {
+ print "\n\n.. c:union:: " . $name . "\n\n";
+ } else {
+ print "\n\n.. c:struct:: " . $name . "\n\n";
+ }
}
print_lineno($declaration_start_line);
$lineprefix = " ";
@@ -1427,20 +1431,25 @@
}
}
+my $typedef_type = qr { ((?:\s+[\w\*]+){1,8})\s* }x;
+my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x;
+my $typedef_args = qr { \s*\((.*)\); }x;
+
+my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x;
+my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x;
+
sub dump_typedef($$) {
my $x = shift;
my $file = shift;
$x =~ s@/\*.*?\*/@@gos; # strip comments.
- # Parse function prototypes
- if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ ||
- $x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) {
-
- # Function typedefs
+ # Parse function typedef prototypes
+ if ($x =~ $typedef1 || $x =~ $typedef2) {
$return_type = $1;
$declaration_name = $2;
my $args = $3;
+ $return_type =~ s/^\s+//;
create_parameterlist($args, ',', $file, $declaration_name);
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index ba85bb2..1c17c3a 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -159,6 +159,21 @@ struct kvm_sync_regs {
struct kvm_arch_memory_slot {
};
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+ __u16 base_event;
+ __u16 nevents;
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+ __u8 action;
+ __u8 pad[3];
+};
+
/* for KVM_GET/SET_VCPU_EVENTS */
struct kvm_vcpu_events {
struct {
@@ -242,6 +257,15 @@ struct kvm_vcpu_events {
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
@@ -329,6 +353,7 @@ struct kvm_vcpu_events {
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
#define KVM_ARM_VCPU_PMU_V3_IRQ 0
#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_PMU_V3_FILTER 2
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 6ca1e68..ede3186 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -29,7 +29,7 @@
{ 0x13, "SIGP conditional emergency signal" }, \
{ 0x15, "SIGP sense running" }, \
{ 0x16, "SIGP set multithreading"}, \
- { 0x17, "SIGP store additional status ait address"}
+ { 0x17, "SIGP store additional status at address"}
#define icpt_prog_codes \
{ 0x0001, "Prog Operation" }, \
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 2901d5d..dad350d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -96,7 +96,7 @@
#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-/* free ( 3*32+17) */
+#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */
#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -236,6 +236,7 @@
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -288,6 +289,7 @@
#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -353,6 +355,7 @@
#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
@@ -368,6 +371,7 @@
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 4ea8584..5861d34 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,12 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD 0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -75,7 +81,8 @@
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+ DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 2859ee4..972a34d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -257,6 +257,9 @@
#define MSR_IA32_LASTINTFROMIP 0x000001dd
#define MSR_IA32_LASTINTTOIP 0x000001de
+#define MSR_IA32_PASID 0x00000d93
+#define MSR_IA32_PASID_VALID BIT_ULL(31)
+
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
#define DEBUGCTLMSR_BTF_SHIFT 1
@@ -464,11 +467,15 @@
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
@@ -857,11 +864,14 @@
#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c
#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
+#define MSR_PERF_METRICS 0x00000329
+
/* PERF_GLOBAL_OVF_CTL bits */
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 6847d85..3ff0d48 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -54,7 +54,7 @@
#endif
#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
/* Paravirtualized systems may not have PSE or PGE available */
#define NEED_PSE 0
#define NEED_PGE 0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 0780f97..89e5f3d 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -192,6 +192,26 @@ struct kvm_msr_list {
__u32 indices[0];
};
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+ __u32 flags;
+ __u32 nmsrs; /* number of msrs in bitmap */
+ __u32 base; /* MSR index the bitmap starts at */
+ __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+ __u32 flags;
+ struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
struct kvm_cpuid_entry {
__u32 function;
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 2e8a30f..f1d8307 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -29,6 +29,7 @@
#define SVM_EXIT_WRITE_DR6 0x036
#define SVM_EXIT_WRITE_DR7 0x037
#define SVM_EXIT_EXCP_BASE 0x040
+#define SVM_EXIT_LAST_EXCP 0x05f
#define SVM_EXIT_INTR 0x060
#define SVM_EXIT_NMI 0x061
#define SVM_EXIT_SMI 0x062
@@ -76,10 +77,21 @@
#define SVM_EXIT_MWAIT_COND 0x08c
#define SVM_EXIT_XSETBV 0x08d
#define SVM_EXIT_RDPRU 0x08e
+#define SVM_EXIT_INVPCID 0x0a2
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402
+/* SEV-ES software-defined VMGEXIT events */
+#define SVM_VMGEXIT_MMIO_READ 0x80000001
+#define SVM_VMGEXIT_MMIO_WRITE 0x80000002
+#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003
+#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004
+#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005
+#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0
+#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1
+#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
+
#define SVM_EXIT_ERR -1
#define SVM_EXIT_REASONS \
@@ -171,6 +183,7 @@
{ SVM_EXIT_MONITOR, "monitor" }, \
{ SVM_EXIT_MWAIT, "mwait" }, \
{ SVM_EXIT_XSETBV, "xsetbv" }, \
+ { SVM_EXIT_INVPCID, "invpcid" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index a04e813..4648738 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -185,7 +185,6 @@ int main(int argc, char *argv[])
main_test_libperl();
main_test_hello();
main_test_libelf();
- main_test_libelf_mmap();
main_test_get_current_dir_name();
main_test_gettid();
main_test_glibc();
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index b9d4322..95c072b 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -27,18 +27,6 @@
#define __pure __attribute__((pure))
#endif
#define noinline __attribute__((noinline))
-#ifdef __has_attribute
-#if __has_attribute(disable_tail_calls)
-#define __no_tail_call __attribute__((disable_tail_calls))
-#endif
-#endif
-#ifndef __no_tail_call
-#if GCC_VERSION > 40201
-#define __no_tail_call __attribute__((optimize("no-optimize-sibling-calls")))
-#else
-#define __no_tail_call
-#endif
-#endif
#ifndef __packed
#define __packed __attribute__((packed))
#endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 2b3f735..d22a974 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -47,9 +47,6 @@
#ifndef noinline
#define noinline
#endif
-#ifndef __no_tail_call
-#define __no_tail_call
-#endif
/* Are two types/vars the same type (ignoring qualifiers)? */
#ifndef __same_type
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f2b5d72..2056318 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
#undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 0054606..fa1f3d6 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait {
*/
#define I915_PARAM_PERF_REVISION 54
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
/* Must be kept compact -- no holes and well documented */
typedef struct drm_i915_getparam {
@@ -1046,6 +1052,38 @@ struct drm_i915_gem_exec_fence {
__u32 flags;
};
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+ struct i915_user_extension base;
+
+ /**
+ * Number of element in the handles_ptr & value_ptr arrays.
+ */
+ __u64 fence_count;
+
+ /**
+ * Pointer to an array of struct drm_i915_gem_exec_fence of length
+ * fence_count.
+ */
+ __u64 handles_ptr;
+
+ /**
+ * Pointer to an array of u64 values of length fence_count. Values
+ * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+ * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+ */
+ __u64 values_ptr;
+};
+
struct drm_i915_gem_execbuffer2 {
/**
* List of gem_exec_object2 structs
@@ -1062,8 +1100,14 @@ struct drm_i915_gem_execbuffer2 {
__u32 num_cliprects;
/**
* This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
- * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a
- * struct drm_i915_gem_exec_fence *fences.
+ * & I915_EXEC_USE_EXTENSIONS are not set.
+ *
+ * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+ * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+ * of the array.
+ *
+ * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+ * single struct i915_user_extension and num_cliprects is 0.
*/
__u64 cliprects_ptr;
#define I915_EXEC_RING_MASK (0x3f)
@@ -1181,7 +1225,16 @@ struct drm_i915_gem_execbuffer2 {
*/
#define I915_EXEC_FENCE_SUBMIT (1 << 20)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS (1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 7875709..e5de603 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -45,7 +45,6 @@ struct fscrypt_policy_v1 {
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
-#define fscrypt_policy fscrypt_policy_v1
/*
* Process-subscribed "logon" key description prefix and payload format.
@@ -156,9 +155,9 @@ struct fscrypt_get_key_status_arg {
__u32 __out_reserved[13];
};
-#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +169,7 @@ struct fscrypt_get_key_status_arg {
/* old names; don't add anything new here! */
#ifndef __KERNEL__
+#define fscrypt_policy fscrypt_policy_v1
#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7d8eced..ca41220 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -248,6 +248,8 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_IOAPIC_EOI 26
#define KVM_EXIT_HYPERV 27
#define KVM_EXIT_ARM_NISV 28
+#define KVM_EXIT_X86_RDMSR 29
+#define KVM_EXIT_X86_WRMSR 30
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -413,6 +415,17 @@ struct kvm_run {
__u64 esr_iss;
__u64 fault_ipa;
} arm_nisv;
+ /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+ struct {
+ __u8 error; /* user -> kernel */
+ __u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+ __u32 reason; /* kernel -> user */
+ __u32 index; /* kernel -> user */
+ __u64 data; /* kernel <-> user */
+ } msr;
/* Fix the size of the union. */
char padding[256];
};
@@ -1037,6 +1050,9 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_SMALLER_MAXPHYADDR 185
#define KVM_CAP_S390_DIAG318 186
#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1538,6 +1554,9 @@ struct kvm_pv_cmd {
/* Available with KVM_CAP_S390_PROTECTED */
#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 923cc16..f55bc68 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -27,6 +27,7 @@
#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB
#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 96a0240..dd8306e 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -16,6 +16,7 @@
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */
#define MS_NOATIME 1024 /* Do not update access times. */
#define MS_NODIRATIME 2048 /* Do not update directory access times */
#define MS_BIND 4096
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 3e5dcdd..b95d3c4 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@ union perf_mem_data_src {
#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */
/* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT 38
+#define PERF_MEM_SNOOPX_SHIFT 38
/* locked instruction */
#define PERF_MEM_LOCK_NA 0x01 /* not available */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 07b4f81..7f08277 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -233,6 +233,15 @@ struct prctl_mm_map {
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT 1
+# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT 3
+# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 7523218..c998860 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -146,4 +146,8 @@
/* Set event fd for config interrupt*/
#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
#endif
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6890fc4b..ce8516e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -749,6 +749,7 @@
PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 3478096..3798192 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,12 +361,13 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
+# Do not add new syscalls to this range. Numbers 548 and above are available
+# for non-x32 use.
#
512 x32 rt_sigaction compat_sys_rt_sigaction
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
@@ -404,3 +405,5 @@
545 x32 execveat compat_sys_execveat
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
+# This is the end of the legacy x32 range. Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 44a75f2..de80534 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4639,9 +4639,9 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
err = 0;
if (lists[0]) {
- struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
- "event selector. use 'perf list' to list available events",
- parse_events_option);
+ struct option o = {
+ .value = &trace->evlist,
+ };
err = parse_events_option(&o, lists[0], 0);
}
out:
@@ -4655,9 +4655,12 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u
{
struct trace *trace = opt->value;
- if (!list_empty(&trace->evlist->core.entries))
- return parse_cgroups(opt, str, unset);
-
+ if (!list_empty(&trace->evlist->core.entries)) {
+ struct option o = {
+ .value = &trace->evlist,
+ };
+ return parse_cgroups(&o, str, unset);
+ }
trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
return 0;
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index de31935..00f4fcf 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -329,7 +329,7 @@
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index f31794d..0dd8b13 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -323,7 +323,7 @@
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2491d16..8363809 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -95,7 +95,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
return strcmp((const char *) symbol, funcs[idx]);
}
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
{
struct perf_sample sample;
unsigned long cnt = 0;
@@ -126,7 +126,7 @@ __no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
static int global_unwind_retval = -INT_MAX;
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
{
/* Any possible value should be 'thread' */
struct thread *thread = *(struct thread **)p1;
@@ -145,7 +145,7 @@ __no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
return p1 - p2;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
{
struct thread *array[2] = {thread, thread};
void *fp = &bsearch;
@@ -164,12 +164,12 @@ __no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
return global_unwind_retval;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
{
return test_dwarf_unwind__krava_3(thread);
}
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
{
return test_dwarf_unwind__krava_2(thread);
}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a07626f..b0e1880 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2963,7 +2963,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
struct popup_action actions[MAX_OPTIONS];
int nr_options = 0;
int key = -1;
- char buf[64];
+ char buf[128];
int delay_secs = hbt ? hbt->refresh : 0;
#define HIST_BROWSER_HELP_COMMON \
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8763772..6b410c3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -102,6 +102,8 @@ int build_id__sprintf(const struct build_id *build_id, char *bf)
const u8 *raw = build_id->data;
size_t i;
+ bf[0] = 0x0;
+
for (i = 0; i < build_id->size; ++i) {
sprintf(bid, "%02x", *raw);
++raw;
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index a405dad..3c20b12 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -15,6 +15,9 @@
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index e0af36b..d9b385f 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -25,6 +25,18 @@ static inline size_t hash_bits(size_t h, int bits)
#endif
}
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7d4194f..15385ea 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
union perf_event *event,
struct perf_sample *sample __maybe_unused)
{
+ struct symbol *sym;
struct map *map;
map = maps__find(&machine->kmaps, event->ksymbol.addr);
- if (map)
+ if (!map)
+ return 0;
+
+ if (map != machine->vmlinux_map)
maps__remove(&machine->kmaps, map);
+ else {
+ sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+ if (sym)
+ dso__delete_symbol(map->dso, sym);
+ }
return 0;
}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7cbd024..c83c2c6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num)
static int python_start_script(const char *script, int argc, const char **argv)
{
struct tables *tables = &tables_global;
- PyMODINIT_FUNC (*initfunc)(void);
#if PY_MAJOR_VERSION < 3
const char **command_line;
#else
@@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv)
FILE *fp;
#if PY_MAJOR_VERSION < 3
- initfunc = initperf_trace_context;
command_line = malloc((argc + 1) * sizeof(const char *));
command_line[0] = script;
for (i = 1; i < argc + 1; i++)
command_line[i] = argv[i - 1];
+ PyImport_AppendInittab(name, initperf_trace_context);
#else
- initfunc = PyInit_perf_trace_context;
command_line = malloc((argc + 1) * sizeof(wchar_t *));
command_line[0] = Py_DecodeLocale(script, NULL);
for (i = 1; i < argc + 1; i++)
command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+ PyImport_AppendInittab(name, PyInit_perf_trace_context);
#endif
-
- PyImport_AppendInittab(name, initfunc);
Py_Initialize();
#if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7a5f037..0980802 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -595,6 +595,7 @@ static void perf_event__mmap2_swap(union perf_event *event,
event->mmap2.maj = bswap_32(event->mmap2.maj);
event->mmap2.min = bswap_32(event->mmap2.min);
event->mmap2.ino = bswap_64(event->mmap2.ino);
+ event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
if (sample_id_all) {
void *data = &event->mmap2.filename;
@@ -710,6 +711,18 @@ static void perf_event__namespaces_swap(union perf_event *event,
swap_sample_id_all(event, &event->namespaces.link_info[i]);
}
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+ event->cgroup.id = bswap_64(event->cgroup.id);
+
+ if (sample_id_all) {
+ void *data = &event->cgroup.path;
+
+ data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
+}
+
static u8 revbyte(u8 b)
{
int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +965,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_SWITCH] = perf_event__switch_swap,
[PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap,
[PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap,
+ [PERF_RECORD_CGROUP] = perf_event__cgroup_swap,
[PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6138866..0d14abd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym)
}
}
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+ rb_erase_cached(&sym->rb_node, &dso->symbols);
+ symbol__delete(sym);
+ dso__reset_find_symbol_cache(dso);
+}
+
struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
{
if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f4801c4..954d6a0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -131,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
void dso__insert_symbol(struct dso *dso,
struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+ struct symbol *sym);
struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
index d979ff1..8f82f99 100644
--- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
+++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
@@ -3282,4 +3282,99 @@ TEST(epoll60)
close(ctx.epfd);
}
+struct epoll61_ctx {
+ int epfd;
+ int evfd;
+};
+
+static void *epoll61_write_eventfd(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ int64_t l = 1;
+
+ usleep(10950);
+ write(ctx->evfd, &l, sizeof(l));
+ return NULL;
+}
+
+static void *epoll61_epoll_with_timeout(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+ int n;
+
+ n = epoll_wait(ctx->epfd, events, 1, 11);
+ /*
+ * If epoll returned the eventfd, write on the eventfd to wake up the
+ * blocking poller.
+ */
+ if (n == 1) {
+ int64_t l = 1;
+
+ write(ctx->evfd, &l, sizeof(l));
+ }
+ return NULL;
+}
+
+static void *epoll61_blocking_epoll(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+
+ epoll_wait(ctx->epfd, events, 1, -1);
+ return NULL;
+}
+
+TEST(epoll61)
+{
+ struct epoll61_ctx ctx;
+ struct epoll_event ev;
+ int i, r;
+
+ ctx.epfd = epoll_create1(0);
+ ASSERT_GE(ctx.epfd, 0);
+ ctx.evfd = eventfd(0, EFD_NONBLOCK);
+ ASSERT_GE(ctx.evfd, 0);
+
+ ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP;
+ ev.data.ptr = NULL;
+ r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev);
+ ASSERT_EQ(r, 0);
+
+ /*
+ * We are testing a race. Repeat the test case 1000 times to make it
+ * more likely to fail in case of a bug.
+ */
+ for (i = 0; i < 1000; i++) {
+ pthread_t threads[3];
+ int n;
+
+ /*
+ * Start 3 threads:
+ * Thread 1 sleeps for 10.9ms and writes to the evenfd.
+ * Thread 2 calls epoll with a timeout of 11ms.
+ * Thread 3 calls epoll with a timeout of -1.
+ *
+ * The eventfd write by Thread 1 should either wakeup Thread 2
+ * or Thread 3. If it wakes up Thread 2, Thread 2 writes on the
+ * eventfd to wake up Thread 3.
+ *
+ * If no events are missed, all three threads should eventually
+ * be joinable.
+ */
+ ASSERT_EQ(pthread_create(&threads[0], NULL,
+ epoll61_write_eventfd, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[1], NULL,
+ epoll61_epoll_with_timeout, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[2], NULL,
+ epoll61_blocking_epoll, &ctx), 0);
+
+ for (n = 0; n < ARRAY_SIZE(threads); ++n)
+ ASSERT_EQ(pthread_join(threads[n], NULL), 0);
+ }
+
+ close(ctx.epfd);
+ close(ctx.evfd);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index f19804d..d747d6b 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -432,7 +432,7 @@
*/
/**
- * ASSERT_EQ(expected, seen)
+ * ASSERT_EQ()
*
* @expected: expected value
* @seen: measured value
@@ -443,7 +443,7 @@
__EXPECT(expected, #expected, seen, #seen, ==, 1)
/**
- * ASSERT_NE(expected, seen)
+ * ASSERT_NE()
*
* @expected: expected value
* @seen: measured value
@@ -454,7 +454,7 @@
__EXPECT(expected, #expected, seen, #seen, !=, 1)
/**
- * ASSERT_LT(expected, seen)
+ * ASSERT_LT()
*
* @expected: expected value
* @seen: measured value
@@ -465,7 +465,7 @@
__EXPECT(expected, #expected, seen, #seen, <, 1)
/**
- * ASSERT_LE(expected, seen)
+ * ASSERT_LE()
*
* @expected: expected value
* @seen: measured value
@@ -476,7 +476,7 @@
__EXPECT(expected, #expected, seen, #seen, <=, 1)
/**
- * ASSERT_GT(expected, seen)
+ * ASSERT_GT()
*
* @expected: expected value
* @seen: measured value
@@ -487,7 +487,7 @@
__EXPECT(expected, #expected, seen, #seen, >, 1)
/**
- * ASSERT_GE(expected, seen)
+ * ASSERT_GE()
*
* @expected: expected value
* @seen: measured value
@@ -498,7 +498,7 @@
__EXPECT(expected, #expected, seen, #seen, >=, 1)
/**
- * ASSERT_NULL(seen)
+ * ASSERT_NULL()
*
* @seen: measured value
*
@@ -508,7 +508,7 @@
__EXPECT(NULL, "NULL", seen, #seen, ==, 1)
/**
- * ASSERT_TRUE(seen)
+ * ASSERT_TRUE()
*
* @seen: measured value
*
@@ -518,7 +518,7 @@
__EXPECT(0, "0", seen, #seen, !=, 1)
/**
- * ASSERT_FALSE(seen)
+ * ASSERT_FALSE()
*
* @seen: measured value
*
@@ -528,7 +528,7 @@
__EXPECT(0, "0", seen, #seen, ==, 1)
/**
- * ASSERT_STREQ(expected, seen)
+ * ASSERT_STREQ()
*
* @expected: expected value
* @seen: measured value
@@ -539,7 +539,7 @@
__EXPECT_STR(expected, seen, ==, 1)
/**
- * ASSERT_STRNE(expected, seen)
+ * ASSERT_STRNE()
*
* @expected: expected value
* @seen: measured value
@@ -550,7 +550,7 @@
__EXPECT_STR(expected, seen, !=, 1)
/**
- * EXPECT_EQ(expected, seen)
+ * EXPECT_EQ()
*
* @expected: expected value
* @seen: measured value
@@ -561,7 +561,7 @@
__EXPECT(expected, #expected, seen, #seen, ==, 0)
/**
- * EXPECT_NE(expected, seen)
+ * EXPECT_NE()
*
* @expected: expected value
* @seen: measured value
@@ -572,7 +572,7 @@
__EXPECT(expected, #expected, seen, #seen, !=, 0)
/**
- * EXPECT_LT(expected, seen)
+ * EXPECT_LT()
*
* @expected: expected value
* @seen: measured value
@@ -583,7 +583,7 @@
__EXPECT(expected, #expected, seen, #seen, <, 0)
/**
- * EXPECT_LE(expected, seen)
+ * EXPECT_LE()
*
* @expected: expected value
* @seen: measured value
@@ -594,7 +594,7 @@
__EXPECT(expected, #expected, seen, #seen, <=, 0)
/**
- * EXPECT_GT(expected, seen)
+ * EXPECT_GT()
*
* @expected: expected value
* @seen: measured value
@@ -605,7 +605,7 @@
__EXPECT(expected, #expected, seen, #seen, >, 0)
/**
- * EXPECT_GE(expected, seen)
+ * EXPECT_GE()
*
* @expected: expected value
* @seen: measured value
@@ -616,7 +616,7 @@
__EXPECT(expected, #expected, seen, #seen, >=, 0)
/**
- * EXPECT_NULL(seen)
+ * EXPECT_NULL()
*
* @seen: measured value
*
@@ -626,7 +626,7 @@
__EXPECT(NULL, "NULL", seen, #seen, ==, 0)
/**
- * EXPECT_TRUE(seen)
+ * EXPECT_TRUE()
*
* @seen: measured value
*
@@ -636,7 +636,7 @@
__EXPECT(0, "0", seen, #seen, !=, 0)
/**
- * EXPECT_FALSE(seen)
+ * EXPECT_FALSE()
*
* @seen: measured value
*
@@ -646,7 +646,7 @@
__EXPECT(0, "0", seen, #seen, ==, 0)
/**
- * EXPECT_STREQ(expected, seen)
+ * EXPECT_STREQ()
*
* @expected: expected value
* @seen: measured value
@@ -657,7 +657,7 @@
__EXPECT_STR(expected, seen, ==, 0)
/**
- * EXPECT_STRNE(expected, seen)
+ * EXPECT_STRNE()
*
* @expected: expected value
* @seen: measured value