drgn_dump_damon_status.py is a script for dumping DAMON internal status in
json format. It is being used for seeing if DAMON parameters that are set
using _damon_sysfs.py are actually passed to DAMON in the kernel space.
It is, however, not dumping full DAMON internal status, and it makes
increasing test coverage difficult. Add damos filters dumping for more
tests.
Link: https://lkml.kernel.org/r/20250720171652.92309-12-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
drgn_dump_damon_status.py is a script for dumping DAMON internal status in
json format. It is being used for seeing if DAMON parameters that are set
using _damon_sysfs.py are actually passed to DAMON in the kernel space.
It is, however, not dumping full DAMON internal status, and it makes
increasing test coverage difficult. Add ctx->ops.id dumping for more
tests.
Link: https://lkml.kernel.org/r/20250720171652.92309-11-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
drgn_dump_damon_status.py is a script for dumping DAMON internal status in
json format. It is being used for seeing if DAMON parameters that are set
using _damon_sysfs.py are actually passed to DAMON in the kernel space.
It is, however, not dumping full DAMON internal status, and it makes
increasing test coverage difficult. Add damos->migrate_dests dumping for
more tests.
Link: https://lkml.kernel.org/r/20250720171652.92309-10-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "selftests/damon/sysfs.py: test all parameters".
sysfs.py tests if DAMON sysfs interface is passing the user-requested
parameters to DAMON as expected. But only the default (minimum)
parameters are being tested. This is partially because _damon_sysfs.py,
which is the library for making the parameter requests, is not supporting
the entire parameters. The internal DAMON status dump script
(drgn_dump_damon_status.py) is also not dumping entire parameters. Extend
the test coverage by updating parameters input and status dumping scripts
to support all parameters, and writing additional tests using those.
This increased test coverage actually found one real bug
(https://lore.kernel.org/20250719181932.72944-1-sj@kernel.org).
First seven patches (1-7) extend _damon_sysfs.py for all parameters setup.
The eight patch (8) fixes _damon_sysfs.py to use correct max nr_acceses
and age values for their type. Following three patches (9-11) extend
drgn_dump_damon_status.py to dump full DAMON parameters. Following nine
patches (12-20) refactor sysfs.py for general testing code reuse, and
extend it for full parameters check. Finally, two patches (21 and 22) add
test cases in sysfs.py for full parameters testing.
This patch (of 22):
_damon_sysfs.py contains code for test-purpose DAMON sysfs interface
control. Add support of DAMOS watermarks setup for more tests.
Link: https://lkml.kernel.org/r/20250720171652.92309-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20250720171652.92309-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "tools/testing: expand mremap testing".
Expand our mremap() testing to further assert that behaviour is as
expected.
There is a poorly documented mremap() feature whereby it is possible to
mremap() multiple VMAs (even with gaps) when shrinking, as long as the
resultant shrunk range spans only a single VMA.
So we start by asserting this behaviour functions correctly both with an
in-place shrink and a shrink/move.
Next, we further test the newly introduced ability to mremap() multiple
VMAs when performing a MAP_FIXED move (that is without the size being
changed), firstly by asserting that MREMAP_DONTUNMAP has no bearing on
this behaviour.
Finally, we explicitly test that such moves, when splitting source VMAs,
function correctly.
This patch (of 3):
There is an apparently little-known feature of mremap() whereby, in stark
contrast to other modes (other than the recently introduced capacity to
move multiple VMAs), the input source range span multiple VMAs with gaps
between.
This is, when shrinking a VMA, whether moving it or not, and the shrink
would reduce the range to a single VMA - this is permitted, as the shrink
is actioned by an unmap.
This patch adds tests to assert that this behaves as expected.
Link: https://lkml.kernel.org/r/cover.1753119043.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/f08122893a26092a2bec6e69443e87f468ffdbed.1753119043.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Use folio_pte_batch to batch process a large folio. Note that, PTE
batching here will save a few function calls, and this strategy in certain
cases (not this one) batches atomic operations in general, so we have a
performance win for all arches. This patch paves the way for patch 7
which will help us elide the TLBI per contig block on arm64.
The correctness of this patch lies on the correctness of setting the new
ptes based upon information only from the first pte of the batch (which
may also have accumulated a/d bits via modify_prot_start_ptes()).
Observe that the flag combination we pass to mprotect_folio_pte_batch()
guarantees that the batch is uniform w.r.t the soft-dirty bit and the
writable bit. Therefore, the only bits which may differ are the a/d bits.
So we only need to worry about code which is concerned about the a/d bits
of the PTEs.
Setting extra a/d bits on the new ptes where previously they were not set,
is fine - setting access bit when it was not set is not an incorrectness
problem but will only possibly delay the reclaim of the page mapped by the
pte (which is in fact intended because the kernel just operated on this
region via mprotect()!). Setting dirty bit when it was not set is again
not an incorrectness problem but will only possibly force an unnecessary
writeback.
So now we need to reason whether something can go wrong via
can_change_pte_writable(). The pte_protnone, pte_needs_soft_dirty_wp, and
userfaultfd_pte_wp cases are solved due to uniformity in the corresponding
bits guaranteed by the flag combination. The ptes all belong to the same
VMA (since callers guarantee that [start, end) will lie within the VMA)
therefore the conditional based on the VMA is also safe to batch around.
Since the dirty bit on the PTE really is just an indication that the folio
got written to - even if the PTE is not actually dirty but one of the PTEs
in the batch is, the wp-fault optimization can be made. Therefore, it is
safe to batch around pte_dirty() in can_change_shared_pte_writable() (in
fact this is better since without batching, it may happen that some ptes
aren't changed to writable just because they are not dirty, even though
the other ptes mapping the same large folio are dirty).
To batch around the PageAnonExclusive case, we must check the
corresponding condition for every single page. Therefore, from the large
folio batch, we process sub batches of ptes mapping pages with the same
PageAnonExclusive condition, and process that sub batch, then determine
and process the next sub batch, and so on. Note that this does not cause
any extra overhead; if suppose the size of the folio batch is 512, then
the sub batch processing in total will take 512 iterations, which is the
same as what we would have done before.
For pte_needs_flush():
ppc does not care about the a/d bits.
For x86, PAGE_SAVED_DIRTY is ignored. We will flush only when a/d bits
get cleared; since we can only have extra a/d bits due to batching, we
will only have an extra flush, not a case where we elide a flush due to
batching when we shouldn't have.
Link: https://lkml.kernel.org/r/20250718090244.21092-7-dev.jain@arm.com
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joey Gouly <joey.gouly@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "Optimize mprotect() for large folios", v5.
Use folio_pte_batch() to optimize change_pte_range(). On arm64, if the
ptes are painted with the contig bit, then ptep_get() will iterate through
all 16 entries to collect a/d bits. Hence this optimization will result
in a 16x reduction in the number of ptep_get() calls. Next,
ptep_modify_prot_start() will eventually call contpte_try_unfold() on
every contig block, thus flushing the TLB for the complete large folio
range. Instead, use get_and_clear_full_ptes() so as to elide TLBIs on
each contig block, and only do them on the starting and ending contig
block.
For split folios, there will be no pte batching; the batch size returned
by folio_pte_batch() will be 1. For pagetable split folios, the ptes will
still point to the same large folio; for arm64, this results in the
optimization described above, and for other arches, a minor improvement is
expected due to a reduction in the number of function calls.
mm-selftests pass on arm64. I have some failing tests on my x86 VM
already; no new tests fail as a result of this patchset.
We use the following test cases to measure performance, mprotect()'ing the
mapped memory to read-only then read-write 40 times:
Test case 1: Mapping 1G of memory, touching it to get PMD-THPs, then
pte-mapping those THPs
Test case 2: Mapping 1G of memory with 64K mTHPs
Test case 3: Mapping 1G of memory with 4K pages
Average execution time on arm64, Apple M3:
Before the patchset:
T1: 2.1 seconds T2: 2 seconds T3: 1 second
After the patchset:
T1: 0.65 seconds T2: 0.7 seconds T3: 1.1 seconds
Observing T1/T2 and T3 before the patchset, we also remove the regression
introduced by ptep_get() on a contpte block. And, for large folios we get
an almost 74% performance improvement, albeit the trade-off being a slight
degradation in the small folio case.
For x86:
Before the patchset:
T1: 3.75 seconds T2: 3.7 seconds T3: 3.85 seconds
After the patchset:
T1: 3.7 seconds T2: 3.7 seconds T3: 3.9 seconds
So there is a minor improvement due to reduction in number of function
calls, and a slight degradation in the small folio case due to the
overhead of vm_normal_folio() + folio_test_large().
Here is the test program:
#define _GNU_SOURCE
#include <sys/mman.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#define SIZE (1024*1024*1024)
unsigned long pmdsize = (1UL << 21);
unsigned long pagesize = (1UL << 12);
static void pte_map_thps(char *mem, size_t size)
{
size_t offs;
int ret = 0;
/* PTE-map each THP by temporarily splitting the VMAs. */
for (offs = 0; offs < size; offs += pmdsize) {
ret |= madvise(mem + offs, pagesize, MADV_DONTFORK);
ret |= madvise(mem + offs, pagesize, MADV_DOFORK);
}
if (ret) {
fprintf(stderr, "ERROR: mprotect() failed\n");
exit(1);
}
}
int main(int argc, char *argv[])
{
char *p;
int ret = 0;
p = mmap((1UL << 30), SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (p != (1UL << 30)) {
perror("mmap");
return 1;
}
memset(p, 0, SIZE);
if (madvise(p, SIZE, MADV_NOHUGEPAGE))
perror("madvise");
explicit_bzero(p, SIZE);
pte_map_thps(p, SIZE);
for (int loops = 0; loops < 40; loops++) {
if (mprotect(p, SIZE, PROT_READ))
perror("mprotect"), exit(1);
if (mprotect(p, SIZE, PROT_READ|PROT_WRITE))
perror("mprotect"), exit(1);
explicit_bzero(p, SIZE);
}
}
This patch (of 7):
Reduce indentation by refactoring the prot_numa case into a new function.
No functional change intended.
Link: https://lkml.kernel.org/r/20250718090244.21092-1-dev.jain@arm.com
Link: https://lkml.kernel.org/r/20250718090244.21092-2-dev.jain@arm.com
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joey Gouly <joey.gouly@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "__folio_split() clean up", v5.
This patchset refactors __folio_split() and __split_unmapped_folio() to:
1. make __split_unmapped_folio() reusable for splitting unmapped
folios. It avoids the need for a new boolean unmapped parameter to
guard mapping-related code when __split_unmapped_folio() is reused to
split unmapped folios.
2. improve code readability and prevent smatch/coverity checkers from
complaining about NULL mapping referencing.
An additional benefit for __split_unmapped_folio() refactoring is that
__split_unmapped_folio() could be called on after-split folios by
__folio_split(). It can enable new split methods. For example, at
deferred split time, unmapped subpages can scatter arbitrarily within a
large folio, neither uniform nor non-uniform split can maximize
after-split folio orders for mapped subpages. The hope is that by calling
__split_unmapped_folio() multiple times, a better split result can be
achieved.
This patch (of 6):
remap(), folio_ref_unfreeze(), lru_add_split_folio() are not relevant to
splitting unmapped folio operations. Move them out to __folio_split() so
that __split_unmapped_folio() only handles unmapped folio splits. This
makes __split_unmapped_folio() reusable.
Remove the swapcache folio split check code before
__split_unmapped_folio() call, since it is already checked at the
beginning of __folio_split() in uniform_split_supported() and
non_uniform_split_supported().
Along with the code move, there are some variable renames:
1. release is renamed to new_folio,
2. origin_folio is now folio, since __folio_split() has folio pointing to
the original folio already.
Link: https://lkml.kernel.org/r/20250718023000.4044406-1-ziy@nvidia.com
Link: https://lkml.kernel.org/r/20250718023000.4044406-2-ziy@nvidia.com
Link: https://lkml.kernel.org/r/20250718183720.4054515-1-ziy@nvidia.com
Link: https://lkml.kernel.org/r/20250718183720.4054515-2-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Antonio Quartulli <antonio@mandelbit.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <k.shutemov@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The mempool wake-up path has a edge case bug that affects pools created
with min_nr=0. When a thread blocks waiting for memory from an empty pool
(curr_nr == 0), subsequent mempool_free() calls fail to wake the waiting
thread because the condition "curr_nr < min_nr" evaluates to "0 < 0" which
is false, this can cause threads to sleep indefinitely according to the
code logic.
There is at least 2 places where the mempool created with min_nr=0:
1. lib/btree.c:191: mempool_create(0, btree_alloc, btree_free, NULL)
2. drivers/md/dm-verity-fec.c:791:
mempool_init_slab_pool(&f->extra_pool, 0, f->cache)
Add an explicit check in mempool_free() to handle the min_nr=0 case: when
the pool has zero minimum reserves, is currently empty, and has active
waiters, allocate the element then wake up the sleeper.
Link: https://lkml.kernel.org/r/f28a81ba-615c-481e-86fb-c0bf4115ec89@suse.com
Signed-off-by: Yadan Fan <ydfan@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With maple_tree supporting vma tree traversal under RCU and per-vma locks,
/proc/pid/maps can be read while holding individual vma locks instead of
locking the entire address space.
A completely lockless approach (walking vma tree under RCU) would be quite
complex with the main issue being get_vma_name() using callbacks which
might not work correctly with a stable vma copy, requiring original
(unstable) vma - see special_mapping_name() for example.
When per-vma lock acquisition fails, we take the mmap_lock for reading,
lock the vma, release the mmap_lock and continue. This fallback to mmap
read lock guarantees the reader to make forward progress even during lock
contention. This will interfere with the writer but for a very short time
while we are acquiring the per-vma lock and only when there was contention
on the vma reader is interested in.
We shouldn't see a repeated fallback to mmap read locks in practice, as
this require a very unlikely series of lock contentions (for instance due
to repeated vma split operations). However even if this did somehow
happen, we would still progress.
One case requiring special handling is when a vma changes between the time
it was found and the time it got locked. A problematic case would be if a
vma got shrunk so that its vm_start moved higher in the address space and
a new vma was installed at the beginning:
reader found: |--------VMA A--------|
VMA is modified: |-VMA B-|----VMA A----|
reader locks modified VMA A
reader reports VMA A: | gap |----VMA A----|
This would result in reporting a gap in the address space that does not
exist. To prevent this we retry the lookup after locking the vma, however
we do that only when we identify a gap and detect that the address space
was changed after we found the vma.
This change is designed to reduce mmap_lock contention and prevent a
process reading /proc/pid/maps files (often a low priority task, such as
monitoring/data collection services) from blocking address space updates.
Note that this change has a userspace visible disadvantage: it allows for
sub-page data tearing as opposed to the previous mechanism where data
tearing could happen only between pages of generated output data. Since
current userspace considers data tearing between pages to be acceptable,
we assume is will be able to handle sub-page data tearing as well.
Link: https://lkml.kernel.org/r/20250719182854.3166724-7-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeongjun Park <aha310510@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Ye Bin <yebin10@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "use per-vma locks for /proc/pid/maps reads", v8.
Reading /proc/pid/maps requires read-locking mmap_lock which prevents any
other task from concurrently modifying the address space. This guarantees
coherent reporting of virtual address ranges, however it can block
important updates from happening. Oftentimes /proc/pid/maps readers are
low priority monitoring tasks and them blocking high priority tasks
results in priority inversion.
Locking the entire address space is required to present fully coherent
picture of the address space, however even current implementation does not
strictly guarantee that by outputting vmas in page-size chunks and
dropping mmap_lock in between each chunk. Address space modifications are
possible while mmap_lock is dropped and userspace reading the content is
expected to deal with possible concurrent address space modifications.
Considering these relaxed rules, holding mmap_lock is not strictly needed
as long as we can guarantee that a concurrently modified vma is reported
either in its original form or after it was modified.
This patchset switches from holding mmap_lock while reading /proc/pid/maps
to taking per-vma locks as we walk the vma tree. This reduces the
contention with tasks modifying the address space because they would have
to contend for the same vma as opposed to the entire address space.
Previous version of this patchset [1] tried to perform /proc/pid/maps
reading under RCU, however its implementation is quite complex and the
results are worse than the new version because it still relied on
mmap_lock speculation which retries if any part of the address space gets
modified. New implementaion is both simpler and results in less
contention. Note that similar approach would not work for /proc/pid/smaps
reading as it also walks the page table and that's not RCU-safe.
Paul McKenney's designed a test [2] to measure mmap/munmap latencies while
concurrently reading /proc/pid/maps. The test has a pair of processes
scanning /proc/PID/maps, and another process unmapping and remapping 4K
pages from a 128MB range of anonymous memory. At the end of each 10
second run, the latency of each mmap() or munmap() operation is measured,
and for each run the maximum and mean latency is printed. The map/unmap
process is started first, its PID is passed to the scanners, and then the
map/unmap process waits until both scanners are running before starting
its timed test. The scanners keep scanning until the specified
/proc/PID/maps file disappears.
The latest results from Paul:
Stock mm-unstable, all of the runs had maximum latencies in excess of 0.5
milliseconds, and with 80% of the runs' latencies exceeding a full
millisecond, and ranging up beyond 4 full milliseconds. In contrast, 99%
of the runs with this patch series applied had maximum latencies of less
than 0.5 milliseconds, with the single outlier at only 0.608 milliseconds.
From a median-performance (as opposed to maximum-latency) viewpoint, this
patch series also looks good, with stock mm weighing in at 11 microseconds
and patch series at 6 microseconds, better than a 2x improvement.
Before the change:
./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2
0.011 0.008 0.521
0.011 0.008 0.552
0.011 0.008 0.590
0.011 0.008 0.660
...
0.011 0.015 2.987
0.011 0.015 3.038
0.011 0.016 3.431
0.011 0.016 4.707
After the change:
./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2
0.006 0.005 0.026
0.006 0.005 0.029
0.006 0.005 0.034
0.006 0.005 0.035
...
0.006 0.006 0.421
0.006 0.006 0.423
0.006 0.006 0.439
0.006 0.006 0.608
The patchset also adds a number of tests to check for /proc/pid/maps data
coherency. They are designed to detect any unexpected data tearing while
performing some common address space modifications (vma split, resize and
remap). Even before these changes, reading /proc/pid/maps might have
inconsistent data because the file is read page-by-page with mmap_lock
being dropped between the pages. An example of user-visible inconsistency
can be that the same vma is printed twice: once before it was modified and
then after the modifications. For example if vma was extended, it might
be found and reported twice. What is not expected is to see a gap where
there should have been a vma both before and after modification. This
patchset increases the chances of such tearing, therefore it's even more
important now to test for unexpected inconsistencies.
In [3] Lorenzo identified the following possible vma merging/splitting
scenarios:
Merges with changes to existing vmas:
1 Merge both - mapping a vma over another one and between two vmas which
can be merged after this replacement;
2. Merge left full - mapping a vma at the end of an existing one and
completely over its right neighbor;
3. Merge left partial - mapping a vma at the end of an existing one and
partially over its right neighbor;
4. Merge right full - mapping a vma before the start of an existing one
and completely over its left neighbor;
5. Merge right partial - mapping a vma before the start of an existing one
and partially over its left neighbor;
Merges without changes to existing vmas:
6. Merge both - mapping a vma into a gap between two vmas which can be
merged after the insertion;
7. Merge left - mapping a vma at the end of an existing one;
8. Merge right - mapping a vma before the start end of an existing one;
Splits
9. Split with new vma at the lower address;
10. Split with new vma at the higher address;
If such merges or splits happen concurrently with the /proc/maps reading
we might report a vma twice, once before the modification and once after
it is modified:
Case 1 might report overwritten and previous vma along with the final
merged vma;
Case 2 might report previous and the final merged vma;
Case 3 might cause us to retry once we detect the temporary gap caused by
shrinking of the right neighbor;
Case 4 might report overritten and the final merged vma;
Case 5 might cause us to retry once we detect the temporary gap caused by
shrinking of the left neighbor;
Case 6 might report previous vma and the gap along with the final marged
vma;
Case 7 might report previous and the final merged vma;
Case 8 might report the original gap and the final merged vma covering the
gap;
Case 9 might cause us to retry once we detect the temporary gap caused by
shrinking of the original vma at the vma start;
Case 10 might cause us to retry once we detect the temporary gap caused by
shrinking of the original vma at the vma end;
In all these cases the retry mechanism prevents us from reporting possible
temporary gaps.
[1] https://lore.kernel.org/all/20250418174959.1431962-1-surenb@google.com/
[2] https://github.com/paulmckrcu/proc-mmap_sem-test
[3] https://lore.kernel.org/all/e1863f40-39ab-4e5b-984a-c48765ffde1c@lucifer.local/
The /proc/pid/maps file is generated page by page, with the mmap_lock
released between pages. This can lead to inconsistent reads if the
underlying vmas are concurrently modified. For instance, if a vma split
or merge occurs at a page boundary while /proc/pid/maps is being read, the
same vma might be seen twice: once before and once after the change. This
duplication is considered acceptable for userspace handling. However,
observing a "hole" where a vma should be (e.g., due to a vma being
replaced and the space temporarily being empty) is unacceptable.
Implement a test that:
1. Forks a child process which continuously modifies its address
space, specifically targeting a vma at the boundary between two pages.
2. The parent process repeatedly reads the child's /proc/pid/maps.
3. The parent process checks the last vma of the first page and the
first vma of the second page for consistency, looking for the effects
of vma splits or merges.
The test duration is configurable via DURATION environment variable
expressed in seconds. The default test duration is 5 seconds.
Example Command: DURATION=10 ./proc-maps-race
Link: https://lore.kernel.org/all/20250418174959.1431962-1-surenb@google.com/ [1]
Link: https://github.com/paulmckrcu/proc-mmap_sem-test [2]
Link: https://lore.kernel.org/all/e1863f40-39ab-4e5b-984a-c48765ffde1c@lucifer.local/ [3]
Link: https://lkml.kernel.org/r/20250719182854.3166724-1-surenb@google.com
Link: https://lkml.kernel.org/r/20250719182854.3166724-2-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeongjun Park <aha310510@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Ye Bin <yebin10@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
A race condition is possible in stable_page_flags() where user-space is
reading /proc/kpageflags concurrently to a folio split. This may lead to
oopses or BUG_ON()s being triggered.
To fix this, this commit uses snapshot_page() in stable_page_flags() so
that stable_page_flags() works with a stable page and folio snapshots
instead.
Note that stable_page_flags() makes use of some functions that require the
original page or folio pointer to work properly (eg. is_free_budy_page()
and folio_test_idle()). Since those functions can't be used on the page
snapshot, we replace their usage with flags that were set by
snapshot_page() for this purpose.
Link: https://lkml.kernel.org/r/52c16c0f00995a812a55980c2f26848a999a34ab.1752499009.git.luizcap@redhat.com
Signed-off-by: Luiz Capitulino <luizcap@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit refactors __dump_page() into snapshot_page().
snapshot_page() tries to take a faithful snapshot of a page and its folio
representation. The snapshot is returned in the struct page_snapshot
parameter along with additional flags that are best retrieved at snapshot
creation time to reduce race windows.
This function is intended to be used by callers that need a stable
representation of a struct page and struct folio so that pointers or page
information doesn't change while working on a page.
The idea and original implementation of snapshot_page() comes from Matthew
Wilcox with suggestions for improvements from David Hildenbrand. All bugs
and misconceptions are mine.
[luizcap@redhat.com: fix set_ps_flags() commentary]
Link: https://lkml.kernel.org/r/d5c75701-b353-4536-a306-187fab0655b3@redhat.com
Link: https://lkml.kernel.org/r/637a03a05cb2e3df88f84ff9e9f9642374ef813a.1752499009.git.luizcap@redhat.com
Signed-off-by: Luiz Capitulino <luizcap@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "mm: introduce snapshot_page()", v3.
This series introduces snapshot_page(), a helper function that can be used
to create a snapshot of a struct page and its associated struct folio.
This function is intended to help callers with a consistent view of a a
folio while reducing the chance of encountering partially updated or
inconsistent state, such as during folio splitting which could lead to
crashes and BUG_ON()s being triggered.
This patch (of 4):
Let's avoid working with the PMD when not required. If
vm_normal_page_pmd() would be called on something that is not a present
pmd, it would already be a bug (pfn possibly garbage).
While at it, let's support passing in any pfn covered by the huge zero
folio by masking off PFN bits -- which should be rather cheap.
Link: https://lkml.kernel.org/r/cover.1752499009.git.luizcap@redhat.com
Link: https://lkml.kernel.org/r/4940826e99f0c709a7cf7beb94f53288320aea5a.1752499009.git.luizcap@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Luiz Capitulino <luizcap@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
We use maxpages from read_swap_header() to initialize swap_info_struct,
however the maxpages might be reduced in setup_swap_extents() and the
si->max is assigned with the reduced maxpages from the
setup_swap_extents().
Obviously, this could lead to memory waste as we allocated memory based on
larger maxpages, besides, this could lead to a potential deadloop as
following:
1) When calling setup_clusters() with larger maxpages, unavailable
pages within range [si->max, larger maxpages) are not accounted with
inc_cluster_info_page(). As a result, these pages are assumed
available but can not be allocated. The cluster contains these pages
can be moved to frag_clusters list after it's all available pages were
allocated.
2) When the cluster mentioned in 1) is the only cluster in
frag_clusters list, cluster_alloc_swap_entry() assume order 0
allocation will never failed and will enter a deadloop by keep trying
to allocate page from the only cluster in frag_clusters which contains
no actually available page.
Call setup_swap_extents() to get the final maxpages before
swap_info_struct initialization to fix the issue.
After this change, span will include badblocks and will become large
value which I think is correct value:
In summary, there are two kinds of swapfile_activate operations.
1. Filesystem style: Treat all blocks logical continuity and find
usable physical extents in logical range. In this way, si->pages will
be actual usable physical blocks and span will be "1 + highest_block -
lowest_block".
2. Block device style: Treat all blocks physically continue and only
one single extent is added. In this way, si->pages will be si->max and
span will be "si->pages - 1". Actually, si->pages and si->max is only
used in block device style and span value is set with si->pages. As a
result, span value in block device style will become a larger value as
you mentioned.
I think larger value is correct based on:
1. Span value in filesystem style is "1 + highest_block -
lowest_block" which is the range cover all possible phisical blocks
including the badblocks.
2. For block device style, si->pages is the actual usable block number
and is already in pr_info. The original span value before this patch
is also refer to usable block number which is redundant in pr_info.
[shikemeng@huaweicloud.com: ensure si->pages == si->max - 1 after setup_swap_extents()]
Link: https://lkml.kernel.org/r/20250522122554.12209-3-shikemeng@huaweicloud.com
Link: https://lkml.kernel.org/r/20250718065139.61989-1-shikemeng@huaweicloud.com
Link: https://lkml.kernel.org/r/20250522122554.12209-3-shikemeng@huaweicloud.com
Fixes: 661383c611 ("mm: swap: relaim the cached parts that got scanned")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kairui Song <kasong@tencent.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
