| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
When fp-stress gets a termination signal it sets a flag telling itself to
exit and sends a termination signal to all the children. If the flag is set
then don't bother repeating this process, it isn't going to accomplish
anything other than consume CPU time which can be an issue when running in
emulation.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently we set -march=armv8.5+memtag when building the MTE selftests,
allowing the compiler to emit v8.5 and MTE instructions for anything it
generates. This means that we may get code that will generate SIGILLs when
run on older systems rather than skipping on non-MTE systems as should be
the case. Most toolchains don't select any incompatible instructions but
I have seen some reports which suggest that some may be appearing which do
so. This is also potentially problematic in that if the compiler chooses to
emit any MTE instructions for the C code it may interfere with the MTE
usage we are trying to test.
Since the only reason we are specifying this option is to allow us to
assemble MTE instructions in mte_helper.S we can avoid these issues by
moving to using a .arch directive there and adding the -march explicitly to
the toolchain support check instead of the generic CFLAGS.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
We use a local variable hwcap to refer to the element of the hwcaps array
which we are currently checking. When checking for the relevant hwcap bit
being set in testing we were dereferencing hwcaps rather than hwcap in
fetching the AT_HWCAP to use, which is perfectly valid C but means we were
always checking the bit was set in the hwcap for whichever feature is first
in the array. Remove the stray s.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Validate the RNG hwcap and make sure we don't generate a SIGILL reading
RNDR when it is reported.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Include SVE 2 and the various subfeatures it adds in the set of
hwcaps we check for.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Clean up the output of the test by adding a missing newline, the fix had
been done locally but didn't make it into the applied version.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
There are a couple of spelling mistakes of signame names. Fix them.
Signed-off-by: Colin Ian King <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently syscall-abi permits the bits in Z registers not shared with the
V registers as well as all of the predicate registers to be preserved on
syscall but the actual implementation has always cleared them and our
documentation has now been updated to make that the documented ABI so
update the syscall-abi test to match.
Signed-off-by: Mark Brown <[email protected]>
Acked-by: Catalin Marinas <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
The buffer used for verifying SVE Z registers allocated enough space for
16 maximally sized registers rather than 32 due to using the macro for the
number of P registers. In practice this didn't matter since for historical
reasons the maximum VQ defined in the ABI is greater the architectural
maximum so we will always allocate more space than is needed even with
emulated platforms implementing the architectural maximum. Still, we should
use the right define.
Signed-off-by: Mark Brown <[email protected]>
Acked-by: Catalin Marinas <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Now that the core utilities for signal testing support handling data in
EXTRA_CONTEXT blocks we can test larger SVE and SME VLs which spill over
the limits in the base signal context. This is done by defining storage
for the context as a union with a ucontext_t and a buffer together with
some helpers for getting relevant sizes and offsets like we do for
fake_sigframe, this isn't the most lovely code ever but is fairly
straightforward to implement and much less invasive to the somewhat
unclear and indistinct layers of abstraction in the signal handling test
code.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
In order to allow testing of signal contexts that overflow the base signal
frame allow callers to pass the buffer size for the user context into
get_signal_context(). No functional change.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
When preserving the signal context for later verification by testcases
check for and include any EXTRA_CONTEXT block if enough space has been
provided.
Since the EXTRA_CONTEXT block includes a pointer to the start of the
additional data block we need to do at least some fixup on the copied
data. For simplicity in users we do this by extending the length of
the EXTRA_CONTEXT to include the following termination record, this
will cause users to see the extra data as part of the linked list of
contexts without needing any special handling. Care will be needed if
any specific tests for EXTRA_CONTEXT are added beyond the validation
done in ASSERT_GOOD_CONTEXT.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently in validate_reserved() we check the basic form and contents of
an EXTRA_CONTEXT block but do not actually validate anything inside the
data block it provides. Extend the validation to do so, when we get to the
terminator for the main data block reset and start walking the extra data
block instead.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently for the more complex signal context types we validate the context
specific details the end of the parsing loop validate_reserved() if we've
ever seen a context of that type. This is currently merely a bit inefficient
but will get a bit awkward when we start parsing extra_context, at which
point we will need to reset the head to advance into the extra space that
extra_context provides. Instead only do the more detailed checks on each
context type the first time we see that context type.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Nothing outside testcases.c should need to use validate_extra_context(),
remove the prototype to ensure nothing does.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently in validate_extra_context() we assert both that the extra data
pointed to by the EXTRA_CONTEXT is 16 byte aligned and that it immediately
follows the struct _aarch64_ctx providing the terminator for the linked
list of contexts in the signal frame. Since struct _aarch64_ctx is an 8
byte structure which must be 16 byte aligned these cannot both be true. As
documented in sigcontext.h and implemented by the kernel the extra data
should be at the next 16 byte aligned address after the terminator so fix
the validation to match.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
When arm64 signal context data overflows the base struct sigcontext it gets
placed in an extra buffer pointed to by a record of type EXTRA_CONTEXT in
the base struct sigcontext which is required to be the last record in the
base struct sigframe. The current validation code attempts to check this
by using GET_RESV_NEXT_HEAD() to step forward from the current record to
the next but that is a macro which assumes it is being provided with a
struct _aarch64_ctx and uses the size there to skip forward to the next
record. Instead validate_extra_context() passes it a struct extra_context
which has a separate size field. This compiles but results in us trying
to validate a termination record in completely the wrong place, at best
failing validation and at worst just segfaulting. Fix this by passing
the struct _aarch64_ctx we meant to into the macro.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
In handle_input_signal_copyctx() we use ASSERT_GOOD_CONTEXT() to validate
that the context we are saving meets expectations however we do this on
the saved copy rather than on the actual signal context passed in. This
breaks validation of EXTRA_CONTEXT since we attempt to validate the ABI
requirement that the additional space supplied is immediately after the
termination record in the standard context which will not be the case
after it has been copied to another location.
Fix this by doing the validation before we copy. Note that nothing actually
looks inside the EXTRA_CONTEXT at present.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
The za_regs signal test was enumerating the SVE vector lengths rather than
the SME vector lengths through cut'n'paste error when determining what to
test. Enumerate the SME vector lengths instead.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
When ZA is disabled there should be no register data in the ZA signal
frame, add a test case which confirms that this is the case.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently we accept any size for the ZA signal context that the shared
code will accept which means we don't verify that any data is present.
Since we have enabled ZA we know that there must be data so strengthen
the check to only accept a signal frame with data, and while we're at it
since we enabled ZA but did not set any data we know that ZA must contain
zeros, confirm that.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently the stress test programs for floating point context switching are
run by hand, there are extremely simplistic harnesses which run some copies
of each test individually but they are not integrated into kselftest and
with SVE and SME they only run with whatever vector length the process has
by default. This is hassle when running the tests and means that they're
not being run at all by CI systems picking up kselftest.
In order to improve our coverage and provide a more convenient interface
provide a harness program which starts enough stress test programs up to
cause context switching and runs them for a set period. If only FPSIMD is
available in the system we start two copies of the FPSIMD stress test per
CPU, otherwise we start one copy of the FPSIMD and then start the SVE,
streaming SVE and ZA tests once per CPU for each available VL they have
to run on. We then run for a set period monitoring for any errors
reported by the test programs before cleanly terminating them.
In order to provide additional coverage of signal handling and some extra
noise in the scheduling we send a SIGUSR2 to the stress tests once a
second, the tests will count the number of signals they get.
Since kselftest is generally expected to run quickly we by default only run
for ten seconds. This is enough to show if there is anything cripplingly
wrong but not exactly a thorough soak test, for interactive and more
focused use a command line option -t N is provided which overrides the
length of time to run for (specified in seconds) and if 0 is specified then
there is no timeout and the test must be manually terminated. The timeout
is counted in seconds with no output, this is done to account for the
potentially slow startup time for the test programs on virtual platforms
which tend to struggle during startup as they are both slow and tend to
support a wide range of vector lengths.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
To interface more robustly with other processes install the signal handers
in the floating point stress tests before we produce any output, this
means that a parent process can know that if it has seen any output from
the test then the test is ready to handle incoming signals.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Currently the floating point stress tests mostly support testing that the
data they are checking can be disrupted from a signal handler triggered by
SIGUSR1. This is not properly implemented for all the tests and in testing
is frequently modified to just handle the signal without corrupting data in
order to ensure that signal handling does not corrupt data. Directly support
this usage by installing a SIGUSR2 handler which simply counts the signal
delivery.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Since we now have an explicit test for the syscall ABI there is no need for
za-test to cover getpid() so just unconditionally do sched_yield() like we
do in fpsimd-test.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
Add some trivial hwcap validation which checks that /proc/cpuinfo and
AT_HWCAP agree with each other and can verify that for extensions that can
generate a SIGILL due to adding new instructions one appears or doesn't
appear as expected. I've added SVE and SME, other capabilities can be
added later if this gets merged.
This isn't super exciting but on the other hand took very little time to
write and should be handy when verifying that you wired up AT_HWCAP
properly.
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
|
|
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull more hotfixes from Andrew Morton:
"Seventeen hotfixes. Mostly memory management things.
Ten patches are cc:stable, addressing pre-6.0 issues"
* tag 'mm-hotfixes-stable-2022-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
.mailmap: update Luca Ceresoli's e-mail address
mm/mprotect: only reference swap pfn page if type match
squashfs: don't call kmalloc in decompressors
mm/damon/dbgfs: avoid duplicate context directory creation
mailmap: update email address for Colin King
asm-generic: sections: refactor memory_intersects
bootmem: remove the vmemmap pages from kmemleak in put_page_bootmem
ocfs2: fix freeing uninitialized resource on ocfs2_dlm_shutdown
Revert "memcg: cleanup racy sum avoidance code"
mm/zsmalloc: do not attempt to free IS_ERR handle
binder_alloc: add missing mmap_lock calls when using the VMA
mm: re-allow pinning of zero pfns (again)
vmcoreinfo: add kallsyms_num_syms symbol
mailmap: update Guilherme G. Piccoli's email addresses
writeback: avoid use-after-free after removing device
shmem: update folio if shmem_replace_page() updates the page
mm/hugetlb: avoid corrupting page->mapping in hugetlb_mcopy_atomic_pte
|
|
Pull bitmap fixes from Yury Norov:
"Fix the reported issues, and implements the suggested improvements,
for the version of the cpumask tests [1] that was merged with commit
c41e8866c28c ("lib/test: introduce cpumask KUnit test suite").
These changes include fixes for the tests, and better alignment with
the KUnit style guidelines"
* tag 'bitmap-6.0-rc3' of github.com:/norov/linux:
lib/cpumask_kunit: add tests file to MAINTAINERS
lib/cpumask_kunit: log mask contents
lib/test_cpumask: follow KUnit style guidelines
lib/test_cpumask: fix cpu_possible_mask last test
lib/test_cpumask: drop cpu_possible_mask full test
|
|
My Bootlin address is preferred from now on.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Luca Ceresoli <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Atish Patra <[email protected]>
Cc: Hans Verkuil <[email protected]>
Cc: Thomas Petazzoni <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Yu Zhao reported a bug after the commit "mm/swap: Add swp_offset_pfn() to
fetch PFN from swap entry" added a check in swp_offset_pfn() for swap type [1]:
kernel BUG at include/linux/swapops.h:117!
CPU: 46 PID: 5245 Comm: EventManager_De Tainted: G S O L 6.0.0-dbg-DEV #2
RIP: 0010:pfn_swap_entry_to_page+0x72/0xf0
Code: c6 48 8b 36 48 83 fe ff 74 53 48 01 d1 48 83 c1 08 48 8b 09 f6
c1 01 75 7b 66 90 48 89 c1 48 8b 09 f6 c1 01 74 74 5d c3 eb 9e <0f> 0b
48 ba ff ff ff ff 03 00 00 00 eb ae a9 ff 0f 00 00 75 13 48
RSP: 0018:ffffa59e73fabb80 EFLAGS: 00010282
RAX: 00000000ffffffe8 RBX: 0c00000000000000 RCX: ffffcd5440000000
RDX: 1ffffffffff7a80a RSI: 0000000000000000 RDI: 0c0000000000042b
RBP: ffffa59e73fabb80 R08: ffff9965ca6e8bb8 R09: 0000000000000000
R10: ffffffffa5a2f62d R11: 0000030b372e9fff R12: ffff997b79db5738
R13: 000000000000042b R14: 0c0000000000042b R15: 1ffffffffff7a80a
FS: 00007f549d1bb700(0000) GS:ffff99d3cf680000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000440d035b3180 CR3: 0000002243176004 CR4: 00000000003706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
change_pte_range+0x36e/0x880
change_p4d_range+0x2e8/0x670
change_protection_range+0x14e/0x2c0
mprotect_fixup+0x1ee/0x330
do_mprotect_pkey+0x34c/0x440
__x64_sys_mprotect+0x1d/0x30
It triggers because pfn_swap_entry_to_page() could be called upon e.g. a
genuine swap entry.
Fix it by only calling it when it's a write migration entry where the page*
is used.
[1] https://lore.kernel.org/lkml/CAOUHufaVC2Za-p8m0aiHw6YkheDcrO-C3wRGixwDS32VTS+k1w@mail.gmail.com/
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive")
Signed-off-by: Peter Xu <[email protected]>
Reported-by: Yu Zhao <[email protected]>
Tested-by: Yu Zhao <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Cc: "Huang, Ying" <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The decompressors may be called while in an atomic section. So move the
kmalloc() out of this path, and into the "page actor" init function.
This fixes a regression introduced by commit
f268eedddf35 ("squashfs: extend "page actor" to handle missing pages")
Link: https://lkml.kernel.org/r/[email protected]
Fixes: f268eedddf35 ("squashfs: extend "page actor" to handle missing pages")
Reported-by: Chris Murphy <[email protected]>
Signed-off-by: Phillip Lougher <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
When user tries to create a DAMON context via the DAMON debugfs interface
with a name of an already existing context, the context directory creation
fails but a new context is created and added in the internal data
structure, due to absence of the directory creation success check. As a
result, memory could leak and DAMON cannot be turned on. An example test
case is as below:
# cd /sys/kernel/debug/damon/
# echo "off" > monitor_on
# echo paddr > target_ids
# echo "abc" > mk_context
# echo "abc" > mk_context
# echo $$ > abc/target_ids
# echo "on" > monitor_on <<< fails
Return value of 'debugfs_create_dir()' is expected to be ignored in
general, but this is an exceptional case as DAMON feature is depending
on the debugfs functionality and it has the potential duplicate name
issue. This commit therefore fixes the issue by checking the directory
creation failure and immediately return the error in the case.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 75c1c2b53c78 ("mm/damon/dbgfs: support multiple contexts")
Signed-off-by: Badari Pulavarty <[email protected]>
Signed-off-by: SeongJae Park <[email protected]>
Cc: <[email protected]> [ 5.15.x]
Signed-off-by: Andrew Morton <[email protected]>
|
|
Colin King is working on kernel janitorial fixes in his spare time and
using his Intel email is confusing. Use his gmail account as the default
email address.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Colin Ian King <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
There are two problems with the current code of memory_intersects:
First, it doesn't check whether the region (begin, end) falls inside the
region (virt, vend), that is (virt < begin && vend > end).
The second problem is if vend is equal to begin, it will return true but
this is wrong since vend (virt + size) is not the last address of the
memory region but (virt + size -1) is. The wrong determination will
trigger the misreporting when the function check_for_illegal_area calls
memory_intersects to check if the dma region intersects with stext region.
The misreporting is as below (stext is at 0x80100000):
WARNING: CPU: 0 PID: 77 at kernel/dma/debug.c:1073 check_for_illegal_area+0x130/0x168
DMA-API: chipidea-usb2 e0002000.usb: device driver maps memory from kernel text or rodata [addr=800f0000] [len=65536]
Modules linked in:
CPU: 1 PID: 77 Comm: usb-storage Not tainted 5.19.0-yocto-standard #5
Hardware name: Xilinx Zynq Platform
unwind_backtrace from show_stack+0x18/0x1c
show_stack from dump_stack_lvl+0x58/0x70
dump_stack_lvl from __warn+0xb0/0x198
__warn from warn_slowpath_fmt+0x80/0xb4
warn_slowpath_fmt from check_for_illegal_area+0x130/0x168
check_for_illegal_area from debug_dma_map_sg+0x94/0x368
debug_dma_map_sg from __dma_map_sg_attrs+0x114/0x128
__dma_map_sg_attrs from dma_map_sg_attrs+0x18/0x24
dma_map_sg_attrs from usb_hcd_map_urb_for_dma+0x250/0x3b4
usb_hcd_map_urb_for_dma from usb_hcd_submit_urb+0x194/0x214
usb_hcd_submit_urb from usb_sg_wait+0xa4/0x118
usb_sg_wait from usb_stor_bulk_transfer_sglist+0xa0/0xec
usb_stor_bulk_transfer_sglist from usb_stor_bulk_srb+0x38/0x70
usb_stor_bulk_srb from usb_stor_Bulk_transport+0x150/0x360
usb_stor_Bulk_transport from usb_stor_invoke_transport+0x38/0x440
usb_stor_invoke_transport from usb_stor_control_thread+0x1e0/0x238
usb_stor_control_thread from kthread+0xf8/0x104
kthread from ret_from_fork+0x14/0x2c
Refactor memory_intersects to fix the two problems above.
Before the 1d7db834a027e ("dma-debug: use memory_intersects()
directly"), memory_intersects is called only by printk_late_init:
printk_late_init -> init_section_intersects ->memory_intersects.
There were few places where memory_intersects was called.
When commit 1d7db834a027e ("dma-debug: use memory_intersects()
directly") was merged and CONFIG_DMA_API_DEBUG is enabled, the DMA
subsystem uses it to check for an illegal area and the calltrace above
is triggered.
[[email protected]: fix nearby comment typo]
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 979559362516 ("asm/sections: add helpers to check for section data")
Signed-off-by: Quanyang Wang <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Thierry Reding <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The vmemmap pages is marked by kmemleak when allocated from memblock.
Remove it from kmemleak when freeing the page. Otherwise, when we reuse
the page, kmemleak may report such an error and then stop working.
kmemleak: Cannot insert 0xffff98fb6eab3d40 into the object search tree (overlaps existing)
kmemleak: Kernel memory leak detector disabled
kmemleak: Object 0xffff98fb6be00000 (size 335544320):
kmemleak: comm "swapper", pid 0, jiffies 4294892296
kmemleak: min_count = 0
kmemleak: count = 0
kmemleak: flags = 0x1
kmemleak: checksum = 0
kmemleak: backtrace:
Link: https://lkml.kernel.org/r/[email protected]
Fixes: f41f2ed43ca5 (mm: hugetlb: free the vmemmap pages associated with each HugeTLB page)
Signed-off-by: Liu Shixin <[email protected]>
Reviewed-by: Muchun Song <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
After commit 0737e01de9c4 ("ocfs2: ocfs2_mount_volume does cleanup job
before return error"), any procedure after ocfs2_dlm_init() fails will
trigger crash when calling ocfs2_dlm_shutdown().
ie: On local mount mode, no dlm resource is initialized. If
ocfs2_mount_volume() fails in ocfs2_find_slot(), error handling will call
ocfs2_dlm_shutdown(), then does dlm resource cleanup job, which will
trigger kernel crash.
This solution should bypass uninitialized resources in
ocfs2_dlm_shutdown().
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 0737e01de9c4 ("ocfs2: ocfs2_mount_volume does cleanup job before return error")
Signed-off-by: Heming Zhao <[email protected]>
Reviewed-by: Joseph Qi <[email protected]>
Cc: Mark Fasheh <[email protected]>
Cc: Joel Becker <[email protected]>
Cc: Junxiao Bi <[email protected]>
Cc: Changwei Ge <[email protected]>
Cc: Gang He <[email protected]>
Cc: Jun Piao <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
This reverts commit 96e51ccf1af33e82f429a0d6baebba29c6448d0f.
Recently we started running the kernel with rstat infrastructure on
production traffic and begin to see negative memcg stats values.
Particularly the 'sock' stat is the one which we observed having negative
value.
$ grep "sock " /mnt/memory/job/memory.stat
sock 253952
total_sock 18446744073708724224
Re-run after couple of seconds
$ grep "sock " /mnt/memory/job/memory.stat
sock 253952
total_sock 53248
For now we are only seeing this issue on large machines (256 CPUs) and
only with 'sock' stat. I think the networking stack increase the stat on
one cpu and decrease it on another cpu much more often. So, this negative
sock is due to rstat flusher flushing the stats on the CPU that has seen
the decrement of sock but missed the CPU that has increments. A typical
race condition.
For easy stable backport, revert is the most simple solution. For long
term solution, I am thinking of two directions. First is just reduce the
race window by optimizing the rstat flusher. Second is if the reader sees
a negative stat value, force flush and restart the stat collection.
Basically retry but limited.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 96e51ccf1af33e8 ("memcg: cleanup racy sum avoidance code")
Signed-off-by: Shakeel Butt <[email protected]>
Cc: "Michal Koutný" <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Roman Gushchin <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Yosry Ahmed <[email protected]>
Cc: Greg Thelen <[email protected]>
Cc: <[email protected]> [5.15]
Signed-off-by: Andrew Morton <[email protected]>
|
|
zsmalloc() now returns ERR_PTR values as handles, which zram accidentally
can pass to zs_free(). Another bad scenario is when zcomp_compress()
fails - handle has default -ENOMEM value, and zs_free() will try to free
that "pointer value".
Add the missing check and make sure that zs_free() bails out when
ERR_PTR() is passed to it.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: c7e6f17b52e9 ("zsmalloc: zs_malloc: return ERR_PTR on failure")
Signed-off-by: Sergey Senozhatsky <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Nitin Gupta <[email protected]>,
Signed-off-by: Andrew Morton <[email protected]>
|
|
Take the mmap_read_lock() when using the VMA in binder_alloc_print_pages()
and when checking for a VMA in binder_alloc_new_buf_locked().
It is worth noting binder_alloc_new_buf_locked() drops the VMA read lock
after it verifies a VMA exists, but may be taken again deeper in the call
stack, if necessary.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: a43cfc87caaf (android: binder: stop saving a pointer to the VMA)
Signed-off-by: Liam R. Howlett <[email protected]>
Reported-by: Ondrej Mosnacek <[email protected]>
Reported-by: <[email protected]>
Acked-by: Carlos Llamas <[email protected]>
Tested-by: Ondrej Mosnacek <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Christian Brauner (Microsoft) <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Hridya Valsaraju <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: Martijn Coenen <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Todd Kjos <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: "Arve Hjønnevåg" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The below referenced commit makes the same error as 1c563432588d ("mm: fix
is_pinnable_page against a cma page"), re-interpreting the logic to
exclude pinning of the zero page, which breaks device assignment with
vfio.
To avoid further subtle mistakes, split the logic into discrete tests.
[[email protected]: simplify comment, per John]
Link: https://lkml.kernel.org/r/166015037385.760108.16881097713975517242.stgit@omen
Link: https://lore.kernel.org/all/165490039431.944052.12458624139225785964.stgit@omen
Fixes: f25cbb7a95a2 ("mm: add zone device coherent type memory support")
Signed-off-by: Alex Williamson <[email protected]>
Suggested-by: Matthew Wilcox <[email protected]>
Suggested-by: Felix Kuehling <[email protected]>
Tested-by: Slawomir Laba <[email protected]>
Reviewed-by: John Hubbard <[email protected]>
Cc: Alex Sierra <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Alistair Popple <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The rest of the kallsyms symbols are useless without knowing the number of
symbols in the table. In an earlier patch, I somehow dropped the
kallsyms_num_syms symbol, so add it back in.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 5fd8fea935a1 ("vmcoreinfo: include kallsyms symbols")
Signed-off-by: Stephen Brennan <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Dave Young <[email protected]>
Cc: Vivek Goyal <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Both @canonical and @ibm email addresses are invalid now; use my personal
address instead.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Guilherme G. Piccoli <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
When a disk is removed, bdi_unregister gets called to stop further
writeback and wait for associated delayed work to complete. However,
wb_inode_writeback_end() may schedule bandwidth estimation dwork after
this has completed, which can result in the timer attempting to access the
just freed bdi_writeback.
Fix this by checking if the bdi_writeback is alive, similar to when
scheduling writeback work.
Since this requires wb->work_lock, and wb_inode_writeback_end() may get
called from interrupt, switch wb->work_lock to an irqsafe lock.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 45a2966fd641 ("writeback: fix bandwidth estimate for spiky workload")
Signed-off-by: Khazhismel Kumykov <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Cc: Michael Stapelberg <[email protected]>
Cc: Wu Fengguang <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
If we allocate a new page, we need to make sure that our folio matches
that new page.
If we do end up in this code path, we store the wrong page in the shmem
inode's page cache, and I would rather imagine that data corruption
ensues.
This will be solved by changing shmem_replace_page() to
shmem_replace_folio(), but this is the minimal fix.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: da08e9b79323 ("mm/shmem: convert shmem_swapin_page() to shmem_swapin_folio()")
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Reviewed-by: William Kucharski <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
In MCOPY_ATOMIC_CONTINUE case with a non-shared VMA, pages in the page
cache are installed in the ptes. But hugepage_add_new_anon_rmap is called
for them mistakenly because they're not vm_shared. This will corrupt the
page->mapping used by page cache code.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl")
Signed-off-by: Miaohe Lin <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Fixes:
- check that subvolume is writable when changing xattrs from security
namespace
- fix memory leak in device lookup helper
- update generation of hole file extent item when merging holes
- fix space cache corruption and potential double allocations; this
is a rare bug but can be serious once it happens, stable backports
and analysis tool will be provided
- fix error handling when deleting root references
- fix crash due to assert when attempting to cancel suspended device
replace, add message what to do if mount fails due to missing
replace item
Regressions:
- don't merge pages into bio if their page offset is not contiguous
- don't allow large NOWAIT direct reads, this could lead to short
reads eg. in io_uring"
* tag 'for-6.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: add info when mount fails due to stale replace target
btrfs: replace: drop assert for suspended replace
btrfs: fix silent failure when deleting root reference
btrfs: fix space cache corruption and potential double allocations
btrfs: don't allow large NOWAIT direct reads
btrfs: don't merge pages into bio if their page offset is not contiguous
btrfs: update generation of hole file extent item when merging holes
btrfs: fix possible memory leak in btrfs_get_dev_args_from_path()
btrfs: check if root is readonly while setting security xattr
|
|
Pull cfis fixes from Steve French:
- two locking fixes (zero range, punch hole)
- DFS 9 fix (padding), affecting some servers
- three minor cleanup changes
* tag '6.0-rc2-smb3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6:
cifs: Add helper function to check smb1+ server
cifs: Use help macro to get the mid header size
cifs: Use help macro to get the header preamble size
cifs: skip extra NULL byte in filenames
smb3: missing inode locks in punch hole
smb3: missing inode locks in zero range
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull misc x86 fixes from Ingo Molnar:
- Fix PAT on Xen, which caused i915 driver failures
- Fix compat INT 80 entry crash on Xen PV guests
- Fix 'MMIO Stale Data' mitigation status reporting on older Intel CPUs
- Fix RSB stuffing regressions
- Fix ORC unwinding on ftrace trampolines
- Add Intel Raptor Lake CPU model number
- Fix (work around) a SEV-SNP bootloader bug providing bogus values in
boot_params->cc_blob_address, by ignoring the value on !SEV-SNP
bootups.
- Fix SEV-SNP early boot failure
- Fix the objtool list of noreturn functions and annotate snp_abort(),
which bug confused objtool on gcc-12.
- Fix the documentation for retbleed
* tag 'x86-urgent-2022-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
Documentation/ABI: Mention retbleed vulnerability info file for sysfs
x86/sev: Mark snp_abort() noreturn
x86/sev: Don't use cc_platform_has() for early SEV-SNP calls
x86/boot: Don't propagate uninitialized boot_params->cc_blob_address
x86/cpu: Add new Raptor Lake CPU model number
x86/unwind/orc: Unwind ftrace trampolines with correct ORC entry
x86/nospec: Fix i386 RSB stuffing
x86/nospec: Unwreck the RSB stuffing
x86/bugs: Add "unknown" reporting for MMIO Stale Data
x86/entry: Fix entry_INT80_compat for Xen PV guests
x86/PAT: Have pat_enabled() properly reflect state when running on Xen
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 perf fixes from Ingo Molnar:
"Misc fixes: an Arch-LBR fix, a PEBS enumeration fix, an Intel DS fix,
PEBS constraints fix on Alder Lake CPUs and an Intel uncore PMU fix"
* tag 'perf-urgent-2022-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU
perf/x86/intel: Fix pebs event constraints for ADL
perf/x86/intel/ds: Fix precise store latency handling
perf/x86/core: Set pebs_capable and PMU_FL_PEBS_ALL for the Baseline
perf/x86/lbr: Enable the branch type for the Arch LBR by default
|