Vlastimil Babka [Tue, 24 Jun 2025 13:03:46 +0000 (15:03 +0200)]
mm, madvise: extract mm code from prctl_set_vma() to mm/madvise.c
Setting anon_name is done via madvise_set_anon_name() and behaves a lot of
like other madvise operations. However, apparently because madvise() has
lacked the 4th argument and prctl() not, the userspace entry point has
been implemented via prctl(PR_SET_VMA, ...) and handled first by
prctl_set_vma().
Currently prctl_set_vma() lives in kernel/sys.c but setting the
vma->anon_name is mm-specific code so extract it to a new
set_anon_vma_name() function under mm. mm/madvise.c seems to be the most
straightforward place as that's where madvise_set_anon_name() lives. Stop
declaring the latter in mm.h and instead declare set_anon_vma_name().
Link: https://lkml.kernel.org/r/20250624-anon_name_cleanup-v2-2-600075462a11@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: David Hildenbrand <david@redhat.com> Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Colin Cross <ccross@google.com> Cc: Jann Horn <jannh@google.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: SeongJae Park <sj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Vlastimil Babka [Tue, 24 Jun 2025 13:03:45 +0000 (15:03 +0200)]
mm, madvise: simplify anon_name handling
Patch series "madvise anon_name cleanups", v2.
While reviewing Lorenzo's madvise cleanups I've noticed that we can handle
anon_name in madvise code much better, so sending that as patch 1.
Initially I wanted to do first move the existing logic from
madvise_vma_behavior() to madvise_update_vma() as a separate patch before
the actual simplification but that would require adding
anon_vma_name_put() in error handling paths only to be removed again, so
it's a single patch to avoid churn.
It's also an opportunity to move some mm code from prctl under mm, hence
patch 2. After code moving preparation in patch 3, also unify madvise
lock handling for madvise_set_anon_name() in patch 4.
This patch (of 4):
Since the introduction in 9a10064f5625 ("mm: add a field to store names
for private anonymous memory") the code to set anon_name on a vma has been
using madvise_update_vma() to call replace_anon_vma_name(). Since the
former is called also by a number of other madvise behaviours that do not
set a new anon_name, they have been passing the existing anon_name of the
vma to make replace_anon_vma_name() a no-op.
This is rather wasteful as it needs anon_vma_name_eq() to determine the
no-op situations, and checks for when replace_anon_vma_name() is allowed
(the vma is anon/shmem) duplicate the checks already done earlier in
madvise_vma_behavior(). It has also lead to commit 942341dcc574 ("mm: fix
use-after-free when anon vma name is used after vma is freed") adding
anon_name refcount get/put operations exactly to the cases that actually
do not change anon_name - just so the replace_anon_vma_name() can keep
safely determining it has nothing to do.
The recent madvise cleanups made this suboptimal handling very obvious,
but happily also allow for an easy fix. madvise_update_vma() now has the
complete information whether it's been called to set a new anon_name, so
stop passing it the existing vma's name and doing the refcount get/put in
its only caller madvise_vma_behavior().
In madvise_update_vma() itself, limit calling of replace_anon_vma_name()
only to cases where we are setting a new name, otherwise we know it's a
no-op. We can rely solely on the __MADV_SET_ANON_VMA_NAME behaviour and
can remove the duplicate checks for vma being anon/shmem that were done
already in madvise_vma_behavior().
Additionally, by using vma_modify_flags() when not modifying the
anon_name, avoid explicitly passing the existing vma's anon_name and
storing a pointer to it in struct madv_behavior or a local variable. This
prevents the danger of accessing a freed anon_name after vma merging,
previously fixed by commit 942341dcc574.
Link: https://lkml.kernel.org/r/20250624-anon_name_cleanup-v2-0-600075462a11@suse.cz Link: https://lkml.kernel.org/r/20250624-anon_name_cleanup-v2-1-600075462a11@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Colin Cross <ccross@google.com> Cc: Jann Horn <jannh@google.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: SeongJae Park <sj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Fri, 20 Jun 2025 15:33:05 +0000 (16:33 +0100)]
mm/madvise: eliminate very confusing manipulation of prev VMA
The madvise code has for the longest time had very confusing code around
the 'prev' VMA pointer passed around various functions which, in all cases
except madvise_update_vma(), is unused and instead simply updated as soon
as the function is invoked.
To compound the confusion, the prev pointer is also used to indicate to
the caller that the mmap lock has been dropped and that we can therefore
not safely access the end of the current VMA (which might have been
updated by madvise_update_vma()).
Clear up this confusion by not setting prev = vma anywhere except in
madvise_walk_vmas(), update all references to prev which will always be
equal to vma after madvise_vma_behavior() is invoked, and adding a flag to
indicate that the lock has been dropped to make this explicit.
Additionally, drop a redundant BUG_ON() from madvise_collapse(), which is
simply reiterating the BUG_ON(mmap_locked) above it (note that BUG_ON() is
not appropriate here, but we leave existing code as-is).
We finally adjust the madvise_walk_vmas() logic to be a little clearer -
delaying the assignment of the end of the range to the start of the new
range until the last moment and handling the lock being dropped scenario
immediately.
Additionally add some explanatory comments.
[lorenzo.stoakes@oracle.com: fix very subtle bug] Link: https://lkml.kernel.org/r/dca94cde-8afb-4eab-8e57-3f508624d670@lucifer.local Link: https://lkml.kernel.org/r/63d281c5df2e64225ab5b4bda398b45e22818701.1750433500.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: SeongJae Park <sj@kernel.org> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Barry Song <baohua@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Fri, 20 Jun 2025 15:33:04 +0000 (16:33 +0100)]
mm/madvise: thread all madvise state through madv_behavior
Doing so means we can get rid of all the weird struct vm_area_struct
**prev stuff, everything becomes consistent and in future if we want to
make change to behaviour there's a single place where all relevant state
is stored.
This also allows us to update try_vma_read_lock() to be a little more
succinct and set up state for us, as well as cleaning up
madvise_update_vma().
We also update the debug assertion prior to madvise_update_vma() to assert
that this is a write operation as correctly pointed out by Barry in the
relevant thread.
We can't reasonably update the madvise functions that live outside of
mm/madvise.c so we leave those as-is.
Link: https://lkml.kernel.org/r/7b345ab82ef51e551f8bc0c4f7be25712871629d.1750433500.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: SeongJae Park <sj@kernel.org> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Barry Song <baohua@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Fri, 20 Jun 2025 15:33:03 +0000 (16:33 +0100)]
mm/madvise: thread VMA range state through madvise_behavior
Rather than updating start and a confusing local parameter 'tmp' in
madvise_walk_vmas(), instead store the current range being operated upon
in the struct madvise_behavior helper object in a range pair and use this
consistently in all operations.
This makes it clearer what is going on and opens the door to further
cleanup now we store state regarding what is currently being operated upon
here.
Link: https://lkml.kernel.org/r/518480ceb48553d3c280bc2b0b5e77bbad840147.1750433500.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: SeongJae Park <sj@kernel.org> Reviewed-by: Barry Song <baohua@kernel.org> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Fri, 20 Jun 2025 15:33:02 +0000 (16:33 +0100)]
mm/madvise: thread mm_struct through madvise_behavior
There's no need to thread a pointer to the mm_struct nor have different
functions signatures for each behaviour, instead store state in the struct
madvise_behavior object consistently and use it for all madvise() actions.
Link: https://lkml.kernel.org/r/a47d850b0111735e026d438c3300c0e3b7f439f4.1750433500.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: SeongJae Park <sj@kernel.org> Reviewed-by: Barry Song <baohua@kernel.org> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Fri, 20 Jun 2025 15:33:01 +0000 (16:33 +0100)]
mm/madvise: remove the visitor pattern and thread anon_vma state
Patch series "madvise cleanup", v2.
This is a series of patches that helps address a number of historic
problems in the madvise() implementation:
* Eliminate the visitor pattern and having the code which is implemented
for both the anon_vma_name implementation and ordinary madvise()
operations use the same madvise_vma_behavior() implementation.
* Thread state through the madvise_behavior state object - this object,
very usefully introduced by SJ, is already used to transmit state
through operations. This series extends this by having all madvise()
operations use this, including anon_vma_name.
* Thread range, VMA state through madvise_behavior - This helps avoid a
lot of the confusing code around range and VMA state and again keeps
things consistent and with a single 'source of truth'.
* Addressing the very strange behaviour around the passed around struct
vm_area_struct **prev pointer - all read-only users do absolutely
nothing with the prev pointer. The only function that uses it is
madvise_update_vma(), and in all cases prev is always reset to VMA.
Fix this by no longer having aything but madvise_update_vma()
reference prev, and having madvise_walk_vmas() update prev in each
instance. Additionally make it clear that the meaningful change in vma
state is when madvise_update_vma() potentially merges a VMA, so
explicitly retrieve the VMA in this case.
* Update and clarify the madvise_walk_vmas() function - this is a source
of a great deal of confusion, so simplify, stop using prev = NULL to
signify that the mmap lock has been dropped (!) and make that explicit,
and add some comments to explain what's going on.
This patch (of 5):
Now we have the madvise_behavior helper struct we no longer need to mess
around with void* pointers in order to propagate anon_vma_name, and this
means we can get rid of the confusing and inconsistent visitor pattern
implementation in madvise_vma_anon_name().
This means we now have a single state object that threads through most of
madvise()'s logic and a single code path which executes the majority of
madvise() behaviour (we maintain separate logic for failure injection and
memory population for the time being).
We are able to remove the visitor pattern by handling the anon_vma_name
setting logic via an internal madvise flag - __MADV_SET_ANON_VMA_NAME.
This uses a negative value so it isn't reasonable that we will ever add
this as a UAPI flag.
Additionally, the madvise_behavior_valid() check ensures that
user-specified behaviours are strictly only those we permit which, of
course, this flag will be excluded from.
We are able to propagate the anon_vma_name object through use of the
madvise_behavior helper struct.
Doing this results in a can_modify_vma_madv() check for anonymous VMA name
changes, however this will cause no issues as this operation is not
prohibited.
We can also then reuse more code and drop the redundant
madvise_vma_anon_name() function altogether.
Additionally separate out behaviours that update VMAs from those that do
not.
Link: https://lkml.kernel.org/r/cover.1750433500.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/c5094bfccb41ecd19d4e9bcaa1c4a11e00158bba.1750433500.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: SeongJae Park <sj@kernel.org> Reviewed-by: Barry Song <baohua@kernel.org> Acked-by: David Hildenbrand <david@redhat.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Li Wang [Tue, 24 Jun 2025 03:27:48 +0000 (11:27 +0800)]
ksm_tests: skip hugepage test when Transparent Hugepages are disabled
Some systems (e.g. minimal or real-time kernels) may not enable
Transparent Hugepages (THP), causing MADV_HUGEPAGE to return EINVAL. This
patch introduces a runtime check using the existing THP sysfs interface
and skips the hugepage merging test (`-H`) when THP is not available.
# --------------------
# running ./khugepaged
# --------------------
# Reading PMD pagesize failed# [FAIL]
not ok 1 khugepaged # exit=1
# --------------------
# running ./soft-dirty
# --------------------
# TAP version 13
# 1..15
# ok 1 Test test_simple
# ok 2 Test test_vma_reuse dirty bit of allocated page
# ok 3 Test test_vma_reuse dirty bit of reused address page
# Bail out! Reading PMD pagesize failed# Planned tests != run tests (15 != 3)
# # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0
# [FAIL]
not ok 1 soft-dirty # exit=1
# SUMMARY: PASS=0 SKIP=0 FAIL=1
# -------------------
# running ./migration
# -------------------
# TAP version 13
# 1..3
# # Starting 3 tests from 1 test cases.
# # RUN migration.private_anon ...
# # OK migration.private_anon
# ok 1 migration.private_anon
# # RUN migration.shared_anon ...
# # OK migration.shared_anon
# ok 2 migration.shared_anon
# # RUN migration.private_anon_thp ...
# # migration.c:196:private_anon_thp:Expected madvise(ptr, TWOMEG, MADV_HUGEPAGE) (-1) == 0 (0)
# # private_anon_thp: Test terminated by assertion
# # FAIL migration.private_anon_thp
# not ok 3 migration.private_anon_thp
# # FAILED: 2 / 3 tests passed.
# # Totals: pass:2 fail:1 xfail:0 xpass:0 skip:0 error:0
# [FAIL]
not ok 1 migration # exit=1
It's true that CONFIG_TRANSPARENT_HUGEPAGE=y is explicitly enabled in
tools/testing/selftests/mm/config, so ideally the runtime environment
should also support THP.
However, in practice, we've found that on some systems:
- THP is disabled at boot time (transparent_hugepage=never)
- Or manually disabled via sysfs
- Or unavailable in RT kernels, containers, or minimal CI environments
In these cases, the test will fail with EINVAL on madvise(MADV_HUGEPAGE),
even though the kernel config is correct.
To make the test suite more robust and avoid false negatives, this patch
adds a runtime check for /sys/kernel/mm/transparent_hugepage/enabled.
If THP is not available, the hugepage test (-H) is skipped with a clear
message.
Link: https://lkml.kernel.org/r/20250624032748.393836-1-liwang@redhat.com Signed-off-by: Li Wang <liwang@redhat.com> Cc: Aruna Ramakrishna <aruna.ramakrishna@oracle.com> Cc: Bagas Sanjaya <bagasdotme@gmail.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Keith Lucas <keith.lucas@oracle.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Li Wang [Tue, 24 Jun 2025 04:24:11 +0000 (12:24 +0800)]
selftests/mm: fix UFFDIO_API usage with proper two-step feature negotiation
The current implementation of test_unmerge_uffd_wp() explicitly sets
`uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP` before calling
UFFDIO_API. This can cause the ioctl() call to fail with EINVAL on
kernels that do not support UFFD-WP, leading the test to fail
unnecessarily:
# ------------------------------
# running ./ksm_functional_tests
# ------------------------------
# TAP version 13
# 1..9
# # [RUN] test_unmerge
# ok 1 Pages were unmerged
# # [RUN] test_unmerge_zero_pages
# ok 2 KSM zero pages were unmerged
# # [RUN] test_unmerge_discarded
# ok 3 Pages were unmerged
# # [RUN] test_unmerge_uffd_wp
# not ok 4 UFFDIO_API failed <-----
# # [RUN] test_prot_none
# ok 5 Pages were unmerged
# # [RUN] test_prctl
# ok 6 Setting/clearing PR_SET_MEMORY_MERGE works
# # [RUN] test_prctl_fork
# # No pages got merged
# # [RUN] test_prctl_fork_exec
# ok 7 PR_SET_MEMORY_MERGE value is inherited
# # [RUN] test_prctl_unmerge
# ok 8 Pages were unmerged
# Bail out! 1 out of 8 tests failed
# # Planned tests != run tests (9 != 8)
# # Totals: pass:7 fail:1 xfail:0 xpass:0 skip:0 error:0
# [FAIL]
This patch improves compatibility and robustness of the UFFD-WP test
(test_unmerge_uffd_wp) by correctly implementing the UFFDIO_API two-step
handshake as recommended by the userfaultfd(2) man page.
Key changes:
1. Use features=0 in the initial UFFDIO_API call to query supported
feature bits, rather than immediately requesting WP support.
2. Skip the test gracefully if:
- UFFDIO_API fails with EINVAL (e.g. unsupported API version), or
- UFFD_FEATURE_PAGEFAULT_FLAG_WP is not advertised by the kernel.
3. Close the initial userfaultfd and create a new one before enabling
the required feature, since UFFDIO_API can only be called once per fd.
4. Improve diagnostics by distinguishing between expected and unexpected
failures, using strerror() to report errors.
This ensures the test behaves correctly across a wider range of kernel
versions and configurations, while preserving the intended behavior on
kernels that support UFFD-WP.
[liwang@redhat.com: fail the test if sys_userfaultfd() fails, per David] Link: https://lkml.kernel.org/r/20250625004645.400520-1-liwang@redhat.com Link: https://lkml.kernel.org/r/20250624042411.395285-1-liwang@redhat.com Signed-off-by: Li Wang <liwang@redhat.com> Suggested-by: David Hildenbrand <david@redhat.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Aruna Ramakrishna <aruna.ramakrishna@oracle.com> Cc: Bagas Sanjaya <bagasdotme@gmail.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Keith Lucas <keith.lucas@oracle.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Li Wang <liwang@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liam R. Howlett [Tue, 24 Jun 2025 15:48:23 +0000 (11:48 -0400)]
maple_tree: add testing for restoring maple state to active
Restoring maple status to ma_active on overflow/underflow when mas->node
was NULL could have happened in the past, but was masked by a bug in
mas_walk(). Add test cases that triggered the bug when the node was
mas->node prior to fixing the maple state setup.
Add a few extra tests around restoring the active maple status.
Liam R. Howlett [Tue, 24 Jun 2025 15:48:22 +0000 (11:48 -0400)]
maple_tree: fix status setup on restore to active
During the initial call with a maple state, an error status may be set
before a valid node is populated into the maple state node. Subsequent
calls with the maple state may restore the state into an active state with
no node set. This was masked by the mas_walk() always resetting the
status to ma_start and result in an extra walk in this rare scenario.
Don't restore the state to active unless there is a value in the structs
node. This also allows mas_walk() to be fixed to use the active state
without exposing an issue.
User visible results are marginal performance improvements when an active
state can be restored and used instead of rewalking the tree.
Stable is not Cc'ed because the existing code is stable and the
performance gains are not worth the risk.
copy_to_kernel_nofault() is an internal helper which should not be visible
to loadable modules – exporting it would give exploit code a cheap
oracle to probe kernel addresses. Instead, keep the helper un-exported
and compile the kunit case that exercises it only when
mm/kasan/kasan_test.o is linked into vmlinux.
[snovitoll@gmail.com: add a brief comment to `#ifndef MODULE`] Link: https://lkml.kernel.org/r/20250622141142.79332-1-snovitoll@gmail.com Link: https://lkml.kernel.org/r/20250622051906.67374-1-snovitoll@gmail.com Fixes: ca79a00bb9a8 ("kasan: migrate copy_user_test to kunit") Signed-off-by: Sabyrzhan Tasbolatov <snovitoll@gmail.com> Suggested-by: Christoph Hellwig <hch@infradead.org> Suggested-by: Marco Elver <elver@google.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
lib/test_vmalloc.c: restrict default test mask to avoid test warnings
When the vmalloc test is built into the kernel, it runs automatically
during the boot. The current-default "run_test_mask" includes all test
cases, including those which are designed to fail and which trigger kernel
warnings.
These kernel splats can be misinterpreted as actual kernel bugs, leading
to false alarms and unnecessary reports.
To address this, limit the default test mask to only the first few tests
which are expected to pass cleanly. These tests are safe and should not
generate any warnings unless there is a real bug.
Users who wish to explicitly run specific test cases have to pass the
run_test_mask as a boot parameter or at module load time.
Link: https://lkml.kernel.org/r/20250623184035.581229-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Baoquan He <bhe@redhat.com> Cc: Harry Yoo <harry.yoo@oracle.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: David Wang <00107082@163.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
lib/test_vmalloc.c: use late_initcall() if built-in for init ordering
When the vmalloc test code is compiled as a built-in, use late_initcall()
instead of module_init() to defer a vmalloc test execution until most
subsystems are up and running.
It avoids interfering with components that may not yet be initialized at
module_init() time. For example, there was a recent report of memory
profiling infrastructure not being ready early enough leading to kernel
crash.
By using late_initcall() in the built-in case, we ensure the tests are run
at a safer point during a boot sequence.
Link: https://lkml.kernel.org/r/20250623184035.581229-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Baoquan He <bhe@redhat.com> Cc: Harry Yoo <harry.yoo@oracle.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: David Wang <00107082@163.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Sun, 22 Jun 2025 21:37:59 +0000 (14:37 -0700)]
mm/damon/sysfs: decouple from damon_ops_id
Decouple DAMON sysfs interface from damon_ops_id. For this, define and
use new mm/damon/sysfs.c internal data structure that maps the user-space
keywords and damon_ops_id, instead of having the implicit and unflexible
array index rule.
SeongJae Park [Sun, 22 Jun 2025 21:37:58 +0000 (14:37 -0700)]
mm/damon/sysfs-schemes: decouple from damos_filter_type
Decouple DAMOS sysfs interface from damos_filter_type. For this, define
and use new sysfs-schemes internal data structure that maps the user-space
keywords and damos_filter_type, instead of having the implicit and
unflexible array index rule.
SeongJae Park [Sun, 22 Jun 2025 21:37:57 +0000 (14:37 -0700)]
mm/damon/sysfs-schemes: decouple from damos_wmark_metric
Decouple DAMOS sysfs interface from damos_wmark_metric. For this, define
and use new sysfs-schemes internal data structure that maps the user-space
keywords and damos_wmark_metric, instead of having the implicit and
unflexible array index rule.
SeongJae Park [Sun, 22 Jun 2025 21:37:56 +0000 (14:37 -0700)]
mm/damon/sysfs-schemes: decouple from damos_action
Decouple DAMOS sysfs interface from damos_action. For this, define and
use new sysfs-schemes internal data structure that maps the user-space
keywords and damos_action, instead of having the implicit and unflexible
array index rule.
[akpm@linux-foundation.org: make damos_sysfs_action_names static] Closes: https://lore.kernel.org/oe-kbuild-all/202506271655.b8yfEZIT-lkp@intel.com/ Link: https://lkml.kernel.org/r/20250622213759.50930-3-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Sun, 22 Jun 2025 21:37:55 +0000 (14:37 -0700)]
mm/damon/sysfs-schemes: decouple from damos_quota_goal_metric
Patch series "mm/damon: decouple sysfs from core".
DAMON sysfs interface is coupled with core layer. It maintains some of
its keywords arrays be synchronized with matching DAMON core API enums.
It is unnecessary coupling that makes separated changes for different
layers difficult. Decouple the layers by introducing new data structure
for the mappings on DAMON sysfs interface.
This patch (of 5):
Decouple DAMOS sysfs interface from damos_quota_goal_metric. For this,
define and use new sysfs-schemes internal data structure that maps the
user-space keywords and damos_quota_goal_metric, instead of having the
implicit and unflexible array index rule.
mm/ptdump: take the memory hotplug lock inside ptdump_walk_pgd()
Memory hot remove unmaps and tears down various kernel page table regions
as required. The ptdump code can race with concurrent modifications of
the kernel page tables. When leaf entries are modified concurrently, the
dump code may log stale or inconsistent information for a VA range, but
this is otherwise not harmful.
But when intermediate levels of kernel page table are freed, the dump code
will continue to use memory that has been freed and potentially
reallocated for another purpose. In such cases, the ptdump code may
dereference bogus addresses, leading to a number of potential problems.
To avoid the above mentioned race condition, platforms such as arm64,
riscv and s390 take memory hotplug lock, while dumping kernel page table
via the sysfs interface /sys/kernel/debug/kernel_page_tables.
Similar race condition exists while checking for pages that might have
been marked W+X via /sys/kernel/debug/kernel_page_tables/check_wx_pages
which in turn calls ptdump_check_wx(). Instead of solving this race
condition again, let's just move the memory hotplug lock inside generic
ptdump_check_wx() which will benefit both the scenarios.
Drop get_online_mems() and put_online_mems() combination from all existing
platform ptdump code paths.
Link: https://lkml.kernel.org/r/20250620052427.2092093-1-anshuman.khandual@arm.com Fixes: bbd6ec605c0f ("arm64/mm: Enable memory hot remove") Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Dev Jain <dev.jain@arm.com> Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> [s390] Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Peter Xu [Fri, 20 Jun 2025 15:00:58 +0000 (11:00 -0400)]
selftests/mm: reduce uffd-unit-test poison test to minimum
The test will still generate quite some unwanted MCE error messages to
syslog. There was old proposal ratelimiting the MCE messages from kernel,
but that has risk of hiding real useful information on production systems.
We can at least reduce the test to minimum to not over-pollute dmesg,
however trying to not lose its coverage too much.
Dev Jain [Tue, 24 Jun 2025 08:07:48 +0000 (13:37 +0530)]
maple tree: use goto label to simplify code
Use the underflow goto label to set the status to ma_underflow and return
NULL, as is being done elsewhere.
[akpm@linux-foundation.org: add newline, per Liam (and remove one, per akpm)] Link: https://lkml.kernel.org/r/20250624080748.4855-1-dev.jain@arm.com Signed-off-by: Dev Jain <dev.jain@arm.com> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reviewed-by: Wei Yang <richard.weiyang@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:58:04 +0000 (18:58 +1000)]
mm: remove PFN_DEV, PFN_MAP, PFN_SPECIAL, PFN_SG_CHAIN and PFN_SG_LAST
The PFN_MAP flag is no longer used for anything, so remove it. The
PFN_SG_CHAIN and PFN_SG_LAST flags never appear to have been used so also
remove them. The last user of PFN_SPECIAL was removed by 653d7825c149
("dcssblk: mark DAX broken, remove FS_DAX_LIMITED support").
Users of PFN_DEV were removed earlier in this series by "mm: Remove
remaining uses of PFN_DEV".
Link: https://lkml.kernel.org/r/670b3950d70b4d97b905bb597dadfd3633de4314.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:58:03 +0000 (18:58 +1000)]
mm: remove devmap related functions and page table bits
Now that DAX and all other reference counts to ZONE_DEVICE pages are
managed normally there is no need for the special devmap PTE/PMD/PUD page
table bits. So drop all references to these, freeing up a software
defined page table bit on architectures supporting it.
Link: https://lkml.kernel.org/r/6389398c32cc9daa3dfcaa9f79c7972525d310ce.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: Will Deacon <will@kernel.org> # arm64 Acked-by: David Hildenbrand <david@redhat.com> Suggested-by: Chunyan Zhang <zhang.lyra@gmail.com> Reviewed-by: Björn Töpel <bjorn@rivosinc.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:58:02 +0000 (18:58 +1000)]
fs/dax: remove FS_DAX_LIMITED config option
The dcssblk driver was the last user of FS_DAX_LIMITED. That was marked
broken by 653d7825c149 ("dcssblk: mark DAX broken, remove FS_DAX_LIMITED
support") to allow removal of PFN_SPECIAL. However the FS_DAX_LIMITED
config option itself was not removed, so do that now.
Link: https://lkml.kernel.org/r/b47bf164b4a1013d736fa1a3d501bc8b8e71311f.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:58:01 +0000 (18:58 +1000)]
powerpc: remove checks for devmap pages and PMDs/PUDs
PFN_DEV no longer exists. This means no devmap PMDs or PUDs will be
created, so checking for them is redundant. Instead mappings of pages
that would have previously returned true for pXd_devmap() will return true
for pXd_trans_huge()
Link: https://lkml.kernel.org/r/31f63cc8dd518f9e2ec300681fe302eb4adf49b4.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The pmd_devmap() check in check_pmd_state() is redundant because the only
user of pmd_devmap were device dax and fs dax. However all callers of
check_pmd_state() first call thp_vma_allowable_order() to check if the vma
should be scanned. Except when called from a page fault this always
returns 0 for dax vma's, hence we would never expect to see a pmd_devmap
entry.
Link: https://lkml.kernel.org/r/a68175fd3a37e9b72cc82c1d63fd8b69691a85b5.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:59 +0000 (18:57 +1000)]
mm: remove redundant pXd_devmap calls
DAX was the only thing that created pmd_devmap and pud_devmap entries
however it no longer does as DAX pages are now refcounted normally and
pXd_trans_huge() returns true for those. Therefore checking both
pXd_devmap and pXd_trans_huge() is redundant and the former can be removed
without changing behaviour as it will always be false.
Link: https://lkml.kernel.org/r/d58f089dc16b7feb7c6728164f37dea65d64a0d3.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:58 +0000 (18:57 +1000)]
mm/huge_memory: remove pXd_devmap usage from insert_pXd_pfn()
Nothing uses PFN_DEV anymore so no need to create devmap pXd's when
mapping a PFN. Instead special mappings will be created which ensures
vm_normal_page_pXd() will not return pages which don't have an associated
page. This could change behaviour slightly on architectures where
pXd_devmap() does not imply pXd_special() as the normal page checks would
have fallen through to checking VM_PFNMAP/MIXEDMAP instead, which in
theory at least could have returned a page.
However vm_normal_page_pXd() should never have been returning pages for
pXd_devmap() entries anyway, so anything relying on that would have been a
bug.
Link: https://lkml.kernel.org/r/cd8658f9ff10afcfffd8b145a39d98bf1c595ffa.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:57 +0000 (18:57 +1000)]
mm/gup: remove pXX_devmap usage from get_user_pages()
GUP uses pXX_devmap() calls to see if it needs to a get a reference on the
associated pgmap data structure to ensure the pages won't go away.
However it's a driver responsibility to ensure that if pages are mapped
(ie. discoverable by GUP) that they are not offlined or removed from the
memmap so there is no need to hold a reference on the pgmap data structure
to ensure this.
Furthermore mappings with PFN_DEV are no longer created, hence this
effectively dead code anyway so can be removed.
Link: https://lkml.kernel.org/r/708b2be76876659ec5261fe5d059b07268b98b36.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:56 +0000 (18:57 +1000)]
mm: convert vmf_insert_mixed() from using pte_devmap to pte_special
DAX no longer requires device PTEs as it always has a ZONE_DEVICE page
associated with the PTE that can be reference counted normally. Other
users of pte_devmap are drivers that set PFN_DEV when calling
vmf_insert_mixed() which ensures vm_normal_page() returns NULL for these
entries.
There is no reason to distinguish these pte_devmap users so in order to
free up a PTE bit use pte_special instead for entries created with
vmf_insert_mixed(). This will ensure vm_normal_page() will continue to
return NULL for these pages.
Architectures that don't support pte_special also don't support pte_devmap
so those will continue to rely on pfn_valid() to determine if the page can
be mapped.
Link: https://lkml.kernel.org/r/93086bd446e7bf8e4c85345613ac18f706b01f60.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:55 +0000 (18:57 +1000)]
mm: remove remaining uses of PFN_DEV
PFN_DEV was used by callers of dax_direct_access() to figure out if the
returned PFN is associated with a page using pfn_t_has_page() or not.
However all DAX PFNs now require an assoicated ZONE_DEVICE page so can
assume a page exists.
Other users of PFN_DEV were setting it before calling vmf_insert_mixed().
This is unnecessary as it is no longer checked, instead relying on
pfn_valid() to determine if there is an associated page or not.
Link: https://lkml.kernel.org/r/74b293aebc21b941090bc3e7aeafa91b57c821a5.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:54 +0000 (18:57 +1000)]
mm: filter zone device pages returned from folio_walk_start()
Previously dax pages were skipped by the pagewalk code as pud_special() or
vm_normal_page{_pmd}() would be false for DAX pages. Now that dax pages
are refcounted normally that is no longer the case, so the pagewalk code
will start returning them.
Most callers already explicitly filter for DAX or zone device pages so
don't need updating. However some don't, so add checks to those callers.
Link: https://lkml.kernel.org/r/4ecb7b357fc5b435588024770b88bbb695c30090.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Alistair Popple [Thu, 19 Jun 2025 08:57:53 +0000 (18:57 +1000)]
mm: convert pXd_devmap checks to vma_is_dax
Patch series "mm: Remove pXX_devmap page table bit and pfn_t type", v3.
All users of dax now require a ZONE_DEVICE page which is properly
refcounted. This means there is no longer any need for the PFN_DEV,
PFN_MAP and PFN_SPECIAL flags. Furthermore the PFN_SG_CHAIN and
PFN_SG_LAST flags never appear to have been used. It is therefore
possible to remove the pfn_t type and replace any usage with raw pfns.
The remaining users of PFN_DEV have simply passed this to
vmf_insert_mixed() to create pte_devmap() mappings. It is unclear why
this was the case but presumably to ensure vm_normal_page() does not
return these pages. These users can be trivially converted to raw pfns
and creating a pXX_special() mapping to ensure vm_normal_page() still
doesn't return these pages.
Now that there are no users of PFN_DEV we can remove the devmap page table
bit and all associated functions and macros, freeing up a software page
table bit.
This patch (of 14):
Currently dax is the only user of pmd and pud mapped ZONE_DEVICE pages.
Therefore page walkers that want to exclude DAX pages can check pmd_devmap
or pud_devmap. However soon dax will no longer set PFN_DEV, meaning dax
pages are mapped as normal pages.
Ensure page walkers that currently use pXd_devmap to skip DAX pages
continue to do so by adding explicit checks of the VMA instead.
Remove vma_is_dax() check from mm/userfaultfd.c as validate_move_areas()
will already skip DAX VMA's on account of them not being anonymous.
The check in userfaultfd_must_wait() is also redundant as
vma_can_userfault() should have already filtered out dax vma's.
For HMM the pud_devmap check seems unnecessary as there is no reason we
shouldn't be able to handle any leaf PUD here so remove it also.
Link: https://lkml.kernel.org/r/cover.176965585864cb8d2cf41464b44dcc0471e643a0.1750323463.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/f0611f6f475f48fcdf34c65084a359aefef4cccc.1750323463.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Balbir Singh <balbirs@nvidia.com> Cc: Björn Töpel <bjorn@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Chunyan Zhang <zhang.lyra@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Inki Dae <m.szyprowski@samsung.com> Cc: John Groves <john@groves.net> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Björn Töpel <bjorn@rivosinc.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Hao Ge [Wed, 18 Jun 2025 01:58:09 +0000 (09:58 +0800)]
mm/percpu: conditionally define _shared_alloc_tag via CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
Recently discovered this entry while checking kallsyms on ARM64: ffff800083e509c0 D _shared_alloc_tag
If ARCH_NEEDS_WEAK_PER_CPU is not defined(it is only defined for s390 and
alpha architectures), there's no need to statically define the percpu
variable _shared_alloc_tag.
Therefore, we need to implement isolation for this purpose.
When building the core kernel code for s390 or alpha architectures,
ARCH_NEEDS_WEAK_PER_CPU remains undefined (as it is gated by #if
defined(MODULE)). However, when building modules for these architectures,
the macro is explicitly defined.
Therefore, we remove all instances of ARCH_NEEDS_WEAK_PER_CPU from the
code and introduced CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU to replace the
relevant logic. We can now conditionally define the perpcu variable
_shared_alloc_tag based on CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU. This
allows architectures (such as s390/alpha) that require weak definitions
for percpu variables in modules to include the definition, while others
can omit it via compile-time exclusion.
Link: https://lkml.kernel.org/r/20250618015809.1235761-1-hao.ge@linux.dev Signed-off-by: Hao Ge <gehao@kylinos.cn> Suggested-by: Suren Baghdasaryan <surenb@google.com> Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> [s390] Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Cc: Chistoph Lameter <cl@linux.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Richard Henderson <richard.henderson@linaro.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Vivek Kasireddy [Wed, 18 Jun 2025 05:30:55 +0000 (22:30 -0700)]
selftests/udmabuf: add a test to pin first before writing to memfd
Unlike the existing tests, this new test will create a memfd (backed by
hugetlb) and pin the folios in it (a small subset) before writing/
populating it with data. This is a valid use-case that invokes the
memfd_alloc_folio() kernel API and is expected to work unless there aren't
enough hugetlb folios to satisfy the allocation needs.
Link: https://lkml.kernel.org/r/20250618053415.1036185-4-vivek.kasireddy@intel.com Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com> Cc: Gerd Hoffmann <kraxel@redhat.com> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: David Hildenbrand <david@redhat.com> Cc: Oscar Salvador <osalvador@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Vivek Kasireddy [Wed, 18 Jun 2025 05:30:54 +0000 (22:30 -0700)]
mm/memfd: reserve hugetlb folios before allocation
When we try to allocate a folio via alloc_hugetlb_folio_reserve(), we need
to ensure that there is an active reservation associated with the
allocation. Otherwise, our allocation request would fail if there are no
active reservations made at that moment against any other allocations.
This is because alloc_hugetlb_folio_reserve() checks h->resv_huge_pages
before proceeding with the allocation.
Therefore, to address this issue, we just need to make a reservation (by
calling hugetlb_reserve_pages()) before we try to allocate the folio.
This will also ensure that proper region/subpool accounting is done
associated with our allocation.
Link: https://lkml.kernel.org/r/20250618053415.1036185-3-vivek.kasireddy@intel.com Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: David Hildenbrand <david@redhat.com> Cc: Gerd Hoffmann <kraxel@redhat.com> Cc: Oscar Salvador <osalvador@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Vivek Kasireddy [Wed, 18 Jun 2025 05:30:53 +0000 (22:30 -0700)]
mm/hugetlb: make hugetlb_reserve_pages() return nr of entries updated
Patch series "mm/memfd: Reserve hugetlb folios before allocation", v4.
There are cases when we try to pin a folio but discover that it has not
been faulted-in. So, we try to allocate it in memfd_alloc_folio() but the
allocation request may not succeed if there are no active reservations in
the system at that instant.
Therefore, making a reservation (by calling hugetlb_reserve_pages())
associated with the allocation will ensure that our request would not fail
due to lack of reservations. This will also ensure that proper
region/subpool accounting is done with our allocation.
This patch (of 3):
Currently, hugetlb_reserve_pages() returns a bool to indicate whether the
reservation map update for the range [from, to] was successful or not.
This is not sufficient for the case where the caller needs to determine
how many entries were updated for the range.
Therefore, have hugetlb_reserve_pages() return the number of entries
updated in the reservation map associated with the range [from, to].
Also, update the callers of hugetlb_reserve_pages() to handle the new
return value.
Petr Pavlu [Wed, 18 Jun 2025 12:50:35 +0000 (14:50 +0200)]
codetag: avoid unused alloc_tags sections/symbols
With CONFIG_MEM_ALLOC_PROFILING=n, vmlinux and all modules unnecessarily
contain the symbols __start_alloc_tags and __stop_alloc_tags, which define
an empty range. In the case of modules, the presence of these symbols
also forces the linker to create an empty .codetag.alloc_tags section.
Update codetag.lds.h to make the data conditional on
CONFIG_MEM_ALLOC_PROFILING.
Link: https://lkml.kernel.org/r/20250618125037.53182-1-petr.pavlu@suse.com Signed-off-by: Petr Pavlu <petr.pavlu@suse.com> Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Casey Chen <cachen@purestorage.com> Cc: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Wed, 18 Jun 2025 19:42:54 +0000 (20:42 +0100)]
mm: update architecture and driver code to use vm_flags_t
In future we intend to change the vm_flags_t type, so it isn't correct for
architecture and driver code to assume it is unsigned long. Correct this
assumption across the board.
Overall, this patch does not introduce any functional change.
Link: https://lkml.kernel.org/r/b6eb1894abc5555ece80bb08af5c022ef780c8bc.1750274467.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Acked-by: Christian Brauner <brauner@kernel.org> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Pedro Falcato <pfalcato@suse.de> Acked-by: Catalin Marinas <catalin.marinas@arm.com> [arm64] Acked-by: Zi Yan <ziy@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <kees@kernel.org> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Wed, 18 Jun 2025 19:42:53 +0000 (20:42 +0100)]
mm: update core kernel code to use vm_flags_t consistently
The core kernel code is currently very inconsistent in its use of
vm_flags_t vs. unsigned long. This prevents us from changing the type of
vm_flags_t in the future and is simply not correct, so correct this.
While this results in rather a lot of churn, it is a critical
pre-requisite for a future planned change to VMA flag type.
Additionally, update VMA userland tests to account for the changes.
To make review easier and to break things into smaller parts, driver and
architecture-specific changes is left for a subsequent commit.
The code has been adjusted to cascade the changes across all calling code
as far as is needed.
We will adjust architecture-specific and driver code in a subsequent patch.
Overall, this patch does not introduce any functional change.
Link: https://lkml.kernel.org/r/d1588e7bb96d1ea3fe7b9df2c699d5b4592d901d.1750274467.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Kees Cook <kees@kernel.org> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Acked-by: Jan Kara <jack@suse.cz> Acked-by: Christian Brauner <brauner@kernel.org> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Pedro Falcato <pfalcato@suse.de> Acked-by: Zi Yan <ziy@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Jann Horn <jannh@google.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lorenzo Stoakes [Wed, 18 Jun 2025 19:42:52 +0000 (20:42 +0100)]
mm: change vm_get_page_prot() to accept vm_flags_t argument
Patch series "use vm_flags_t consistently".
The VMA flags field vma->vm_flags is of type vm_flags_t. Right now this
is exactly equivalent to unsigned long, but it should not be assumed to
be.
Much code that references vma->vm_flags already correctly uses vm_flags_t,
but a fairly large chunk of code simply uses unsigned long and assumes
that the two are equivalent.
This series corrects that and has us use vm_flags_t consistently.
This series is motivated by the desire to, in a future series, adjust
vm_flags_t to be a u64 regardless of whether the kernel is 32-bit or
64-bit in order to deal with the VMA flag exhaustion issue and avoid all
the various problems that arise from it (being unable to use certain
features in 32-bit, being unable to add new flags except for 64-bit, etc.)
This is therefore a critical first step towards that goal. At any rate,
using the correct type is of value regardless.
We additionally take the opportunity to refer to VMA flags as vm_flags
where possible to make clear what we're referring to.
Overall, this series does not introduce any functional change.
This patch (of 3):
We abstract the type of the VMA flags to vm_flags_t, however in may places
it is simply assumed this is unsigned long, which is simply incorrect.
At the moment this is simply an incongruity, however in future we plan to
change this type and therefore this change is a critical requirement for
doing so.
Overall, this patch does not introduce any functional change.
[lorenzo.stoakes@oracle.com: add missing vm_get_page_prot() instance, remove include] Link: https://lkml.kernel.org/r/552f88e1-2df8-4e95-92b8-812f7c8db829@lucifer.local Link: https://lkml.kernel.org/r/cover.1750274467.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/a12769720a2743f235643b158c4f4f0a9911daf0.1750274467.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Acked-by: Christian Brauner <brauner@kernel.org> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Pedro Falcato <pfalcato@suse.de> Acked-by: Catalin Marinas <catalin.marinas@arm.com> [arm64] Acked-by: Zi Yan <ziy@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <kees@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Commit a00ce85af2a1 ("mm: make alloc_demote_folio externally invokable for
migration") was made to let DAMOS_MIGRATE_{HOT,COLD} call the function.
But a previous commit made DAMOS_MIGRATE_{HOT,COLD} call
alloc_migration_target() instead. Hence there are no more callers of the
function outside of vmscan.c. Revert the commit to make the function
static again.
Link: https://lkml.kernel.org/r/20250616172346.67659-4-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Honggyu Kim <honggyu.kim@sk.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Commit 8f75267d22bd ("mm: rename alloc_demote_folio to
alloc_migrate_folio") was to reflect the fact the function is called for
not only demotion, but also general migrations from
DAMOS_MIGRATE_{HOT,COLD}. The previous commit made the DAMOS actions to
not use alloc_migrate_folio(), though. So, demote_folio_list() is the
only caller of alloc_migrate_folio(), and the name could now be rather
confusing. Revert the renaming commit.
Link: https://lkml.kernel.org/r/20250616172346.67659-3-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Honggyu Kim <honggyu.kim@sk.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Mon, 16 Jun 2025 17:23:44 +0000 (10:23 -0700)]
mm/damon/paddr: use alloc_migartion_target() with no migration fallback nodemask
Patch series "mm/damon: use alloc_migrate_target() for
DAMOS_MIGRATE_{HOT,COLD}".
DAMOS_MIGRATE_{HOT,COLD} implementation resembles that for demotion, and
hence the behavior is also similar to that. But, since those are not only
for demotion but general migrations, it would be better to match with that
for move_pages() system call. Make the implementation and the behavior
more similar to move_pages() by not setting migration fallback nodes, and
using alloc_migration_target() instead of alloc_migrate_folio().
alloc_migrate_folio() was renamed from alloc_demote_folio() and been
non-static function, to let DAMOS_MIGRATE_{HOT,COLD} call it. As
alloc_migration_target() is called instead, the renaming and de-static
changes are no more required but could only make future code readers be
confused. Revert the changes, too.
This patch (of 3):
DAMOS_MIGRATE_{HOT,COLD} implementation resembles that for
demote_folio_list(). Because those are not only for demotion but general
folio migrations, it makes more sense to behave similarly to move_pages()
system call. Make the behavior more similar to move_pages(), by using
alloc_migration_target() instead of alloc_migrate_folio(), without
fallback nodemask.
Link: https://lkml.kernel.org/r/20250616172346.67659-2-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Honggyu Kim <honggyu.kim@sk.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liam R. Howlett [Mon, 16 Jun 2025 18:45:21 +0000 (14:45 -0400)]
tools/testing/radix-tree: test maple tree chaining mas_preallocate() calls
Testing calling multiple mas_preallocate() calls in a row after adjusting
the maple state. Ensures new calls to mas_preallocate() will change the
number of allocated nodes.
Link: https://lkml.kernel.org/r/20250616184521.3382795-4-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com> Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Hailong Liu <hailong.liu@oppo.com> Cc: "Liam R. Howlett" <howlett@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Peng Zhang <zhangpeng.00@bytedance.com> Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liam R. Howlett [Mon, 16 Jun 2025 18:45:19 +0000 (14:45 -0400)]
testing/radix-tree/maple: increase readers and reduce delay for faster machines
Faster machines may not see the initial or updated value in the race
condition. Reduce the delay so that faster machines are less likely to
fail testing of the race conditions.
Link: https://lkml.kernel.org/r/20250616184521.3382795-2-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <howlett@gmail.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Hailong Liu <hailong.liu@oppo.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Peng Zhang <zhangpeng.00@bytedance.com> Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Baolin Wang [Fri, 13 Jun 2025 09:12:19 +0000 (17:12 +0800)]
mm: huge_memory: fix the check for allowed huge orders in shmem
Shmem already supports mTHP, and shmem_allowable_huge_orders() will return
the huge orders allowed by shmem. However, there is no check against the
'orders' parameter passed by __thp_vma_allowable_orders(), which can lead
to incorrect check results for __thp_vma_allowable_orders().
For example, when a user wants to check if shmem supports PMD-sized THP by
thp_vma_allowable_order(), if shmem only enables 64K mTHP, the current
logic would cause thp_vma_allowable_order() to return true, implying that
shmem allows PMD-sized THP allocation, which it actually does not.
I don't think this will cause a significant impact on users, and this will
only have some impact on the shmem THP collapse. That is to say, even
though the shmem sysfs setting does not enable the PMD-sized THP, the
thp_vma_allowable_order() still indicates that shmem allows PMD-sized
collapse, meaning it might successfully collapse into THP, or it might not
(for example, thp_vma_suitable_order() check failed in the collapse
process). However, this still does not align with the shmem sysfs
configuration, fix it.
Link: https://lkml.kernel.org/r/529affb3220153d0d5a542960b535cdfc33f51d7.1749804835.git.baolin.wang@linux.alibaba.com Fixes: 26c7d8413aaf ("mm: thp: support "THPeligible" semantics for mTHP with anonymous shmem") Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Zi Yan <ziy@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <baohua@kernel.org> Cc: Dev Jain <dev.jain@arm.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Mark Brown [Fri, 13 Jun 2025 11:44:07 +0000 (12:44 +0100)]
selftest/mm: skip if fallocate() is unsupported in gup_longterm
Currently gup_longterm assumes that filesystems support fallocate() and
uses that to allocate space in files, however this is an optional feature
and is in particular not implemented by NFSv3 which is commonly used in CI
systems leading to spurious failures. Check for lack of support and
report a skip instead for that case.
Lorenzo Stoakes [Fri, 13 Jun 2025 18:48:07 +0000 (19:48 +0100)]
mm/vma: use vmg->target to specify target VMA for new VMA merge
In commit 3a75ccba047b ("mm: simplify vma merge structure and expand
comments") we introduced the vmg->target field to make the merging of
existing VMAs simpler - clarifying precisely which VMA would eventually
become the merged VMA once the merge operation was complete.
New VMA merging did not get quite the same treatment, retaining the rather
confusing convention of storing the target VMA in vmg->middle.
This patch corrects this state of affairs, utilising vmg->target for this
purpose for both vma_merge_new_range() and also for vma_expand().
We retain the WARN_ON for vmg->middle being specified in
vma_merge_new_range() as doing so would make no sense, but add an
additional debug assert for setting vmg->target.
This patch additionally updates VMA userland testing to account for this
change.
mm/huge_memory: don't mark refcounted folios special in vmf_insert_folio_pud()
Marking PUDs that map a "normal" refcounted folios as special is against
our rules documented for vm_normal_page(). normal (refcounted) folios
shall never have the page table mapping marked as special.
Fortunately, there are not that many pud_special() check that can be
mislead and are right now rather harmless: e.g., none so far bases
decisions whether to grab a folio reference on that decision.
Well, and GUP-fast will fallback to GUP-slow. All in all, so far no big
implications as it seems.
Getting this right will get more important as we introduce
folio_normal_page_pud() and start using it in more place where we
currently special-case based on other VMA flags.
Fix it just like we fixed vmf_insert_folio_pmd().
Add folio_mk_pud() to mimic what we do with folio_mk_pmd().
Link: https://lkml.kernel.org/r/20250613092702.1943533-4-david@redhat.com Fixes: dbe54153296d ("mm/huge_memory: add vmf_insert_folio_pud()") Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Alistair Popple <apopple@nvidia.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/huge_memory: don't mark refcounted folios special in vmf_insert_folio_pmd()
Marking PMDs that map a "normal" refcounted folios as special is against
our rules documented for vm_normal_page(): normal (refcounted) folios
shall never have the page table mapping marked as special.
Fortunately, there are not that many pmd_special() check that can be
mislead, and most vm_normal_page_pmd()/vm_normal_folio_pmd() users that
would get this wrong right now are rather harmless: e.g., none so far
bases decisions whether to grab a folio reference on that decision.
Well, and GUP-fast will fallback to GUP-slow. All in all, so far no big
implications as it seems.
Getting this right will get more important as we use
folio_normal_page_pmd() in more places.
Fix it by teaching insert_pfn_pmd() to properly handle folios and pfns --
moving refcount/mapcount/etc handling in there, renaming it to
insert_pmd(), and distinguishing between both cases using a new simple
"struct folio_or_pfn" structure.
Use folio_mk_pmd() to create a pmd for a folio cleanly.
Link: https://lkml.kernel.org/r/20250613092702.1943533-3-david@redhat.com Fixes: 6c88f72691f8 ("mm/huge_memory: add vmf_insert_folio_pmd()") Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Alistair Popple <apopple@nvidia.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/huge_memory: don't ignore queried cachemode in vmf_insert_pfn_pud()
Patch series "mm/huge_memory: vmf_insert_folio_*() and
vmf_insert_pfn_pud() fixes", v3.
While working on improving vm_normal_page() and friends, I stumbled over
this issues: refcounted "normal" folios must not be marked using
pmd_special() / pud_special(). Otherwise, we're effectively telling the
system that these folios are no "normal", violating the rules we
documented for vm_normal_page().
Fortunately, there are not many pmd_special()/pud_special() users yet. So
far there doesn't seem to be serious damage.
Tested using the ndctl tests ("ndctl:dax" suite).
This patch (of 3):
We set up the cache mode but ... don't forward the updated pgprot to
insert_pfn_pud().
Only a problem on x86-64 PAT when mapping PFNs using PUDs that require a
special cachemode.
Fix it by using the proper pgprot where the cachemode was setup.
It is unclear in which configurations we would get the cachemode wrong:
through vfio seems possible. Getting cachemodes wrong is usually ...
bad. As the fix is easy, let's backport it to stable.
Identified by code inspection.
Link: https://lkml.kernel.org/r/20250613092702.1943533-1-david@redhat.com Link: https://lkml.kernel.org/r/20250613092702.1943533-2-david@redhat.com Fixes: 7b806d229ef1 ("mm: remove vmf_insert_pfn_xxx_prot() for huge page-table entries") Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Tested-by: Dan Williams <dan.j.williams@intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Dev Jain <dev.jain@arm.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Baolin Wang [Fri, 13 Jun 2025 01:49:20 +0000 (09:49 +0800)]
selftests: mm: add shmem collapse as a default test item
Currently, we only test anonymous memory collapse by default. We should
also add shmem collapse as a default test item to catch issues that could
break the test cases.
Link: https://lkml.kernel.org/r/a30b1529b399f2e649b5a05c3d352f41a68faeae.1749779183.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Dev Jain <dev.jain@arm.com> Tested-by: Dev Jain <dev.jain@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Zi Yan <ziy@nvidia.com> Cc: Barry Song <baohua@kernel.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Baolin Wang [Fri, 13 Jun 2025 01:49:19 +0000 (09:49 +0800)]
selftests: khugepaged: fix the shmem collapse failure
When running the khugepaged selftest for shmem (./khugepaged all:shmem), I
encountered the following test failures:
: Run test: collapse_full (khugepaged:shmem)
: Collapse multiple fully populated PTE table.... Fail
: ...
: Run test: collapse_single_pte_entry (khugepaged:shmem)
: Collapse PTE table with single PTE entry present.... Fail
: ...
: Run test: collapse_full_of_compound (khugepaged:shmem)
: Allocate huge page... OK
: Split huge page leaving single PTE page table full of compound pages... OK
: Collapse PTE table full of compound pages.... Fail
The reason for the failure is that it will set MADV_NOHUGEPAGE to prevent
khugepaged from continuing to scan shmem VMA after khugepaged finishes
scanning in the wait_for_scan() function. Moreover, shmem requires a
refault to establish PMD mappings.
However, after commit 2b0f922323cc ("mm: don't install PMD mappings when
THPs are disabled by the hw/process/vma"), PMD mappings are prevented if
the VMA is set with MADV_NOHUGEPAGE flag, so shmem cannot establish PMD
mappings during refault.
One way to fix this issue is to move the MADV_NOHUGEPAGE setting after the
shmem refault. After shmem refault and check huge, the test case will
unmap the shmem immediately. So it seems unnecessary to set the
MADV_NOHUGEPAGE.
Then we can simply drop the MADV_NOHUGEPAGE setting, and all khugepaged
test cases passed.
Link: https://lkml.kernel.org/r/d8502fc50d0304c2afd27ced062b1d636b7a872e.1749779183.git.baolin.wang@linux.alibaba.com Fixes: 2b0f922323cc ("mm: don't install PMD mappings when THPs are disabled by the hw/process/vma") Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Dev Jain <dev.jain@arm.com> Tested-by: Dev Jain <dev.jain@arm.com> Tested-by: Mario Casquero <mcasquer@redhat.com> Cc: Barry Song <baohua@kernel.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Mariano Pache <npache@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
ceph: convert ceph_zero_partial_page() to use a folio
Retrieve a folio from the pagecache instead of a page and operate on it.
Removes several hidden calls to compound_head() along with calls to
deprecated functions like wait_on_page_writeback() and find_lock_page().
[dan.carpenter@linaro.org: fix NULL vs IS_ERR() bug in ceph_zero_partial_page()] Link: https://lkml.kernel.org/r/685c1424.050a0220.baa8.d6a1@mx.google.com Link: https://lkml.kernel.org/r/20250612143443.2848197-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Xiubo Li <xiubli@redhat.com> Cc: Dan Carpenter <dan.carpenter@linaro.org> Cc: Alex Markuze <amarkuze@redhat.com> Cc: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Barry Song [Wed, 11 Jun 2025 10:47:45 +0000 (22:47 +1200)]
mm: madvise: use per_vma lock for MADV_FREE
MADV_FREE is another option, besides MADV_DONTNEED, for dynamic memory
freeing in user-space native or Java heap memory management. For example,
jemalloc can be configured to use MADV_FREE, and recent versions of the
Android Java heap have also increasingly adopted MADV_FREE. Supporting
per-VMA locking for MADV_FREE thus appears increasingly necessary.
We have replaced walk_page_range() with walk_page_range_vma(). Along with
the proposed madvise_lock_mode by Lorenzo, the necessary infrastructure is
now in place to begin exploring per-VMA locking support for MADV_FREE and
potentially other madvise using walk_page_range_vma().
This patch adds support for the PGWALK_VMA_RDLOCK walk_lock mode in
walk_page_range_vma(), and leverages madvise_lock_mode from madv_behavior
to select the appropriate walk_lock—either mmap_lock or per-VMA
lock—based on the context.
Because we now dynamically update the walk_ops->walk_lock field, we must
ensure this is thread-safe. The madvise_free_walk_ops is now defined as a
stack variable instead of a global constant.
Link: https://lkml.kernel.org/r/20250611104745.57405-1-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: SeongJae Park <sj@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Tangquan Zheng <zhengtangquan@oppo.com> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Dev Jain [Tue, 10 Jun 2025 03:50:43 +0000 (09:20 +0530)]
mm: optimize mremap() by PTE batching
Use folio_pte_batch() to optimize move_ptes(). 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_get_and_clear()
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; nr_ptes will be 1. For
pagetable splitting, the ptes will still point to the same large folio;
for arm64, this results in the optimization described above, and for other
arches (including the general case), a minor improvement is expected due
to a reduction in the number of function calls.
Link: https://lkml.kernel.org/r/20250610035043.75448-3-dev.jain@arm.com Signed-off-by: Dev Jain <dev.jain@arm.com> Reviewed-by: Barry Song <baohua@kernel.org> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Pedro Falcato <pfalcato@suse.de> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Bang Li <libang.li@antgroup.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: bibo mao <maobibo@loongson.cn> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jann Horn <jannh@google.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: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <yang@os.amperecomputing.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Dev Jain [Tue, 10 Jun 2025 03:50:42 +0000 (09:20 +0530)]
mm: call pointers to ptes as ptep
Patch series "Optimize mremap() for large folios", v4.
Currently move_ptes() iterates through ptes one by one. If the underlying
folio mapped by the ptes is large, we can process those ptes in a batch
using folio_pte_batch(), thus clearing and setting the PTEs in one go.
For arm64 specifically, this results in a 16x reduction in the number of
ptep_get() calls (since on a contig block, ptep_get() on arm64 will
iterate through all 16 entries to collect a/d bits), and we also elide
extra TLBIs through get_and_clear_full_ptes, replacing ptep_get_and_clear.
Mapping 1M of memory with 64K folios, memsetting it, remapping it to src +
1M, and munmapping it 10,000 times, the average execution time reduces
from 1.9 to 1.2 seconds, giving a 37% performance optimization, on Apple
M3 (arm64). No regression is observed for small folios.
Avoid confusion between pte_t* and pte_t data types by suffixing pointer
type variables with p. No functional change.
Link: https://lkml.kernel.org/r/20250610035043.75448-1-dev.jain@arm.com Link: https://lkml.kernel.org/r/20250610035043.75448-2-dev.jain@arm.com Signed-off-by: Dev Jain <dev.jain@arm.com> Reviewed-by: Barry Song <baohua@kernel.org> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pedro Falcato <pfalcato@suse.de> Cc: Bang Li <libang.li@antgroup.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: bibo mao <maobibo@loongson.cn> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jann Horn <jannh@google.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: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <yang@os.amperecomputing.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Since these values can be large, the multiplication may exceed the
maximum value of an int (INT_MAX) and overflow (Our platform did),
leading to an incorrect adist.
User-visible impact:
The memory tiering subsystem will misinterpret slow memory (like CXL)
as faster than DRAM, causing inappropriate demotion of pages from
CXL (slow memory) to DRAM (fast memory).
For example, we will see the following demotion chains from the dmesg, where
Node0,1 are DRAM, and Node2,3 are CXL node:
Demotion targets for Node 0: null
Demotion targets for Node 1: null
Demotion targets for Node 2: preferred: 0-1, fallback: 0-1
Demotion targets for Node 3: preferred: 0-1, fallback: 0-1
Change MEMTIER_ADISTANCE_DRAM to be a long constant by writing it with
the 'L' suffix. This prevents the overflow because the multiplication
will then be done in the long type which has a larger range.
David Wang [Mon, 9 Jun 2025 06:44:08 +0000 (14:44 +0800)]
alloc_tag: keep codetag iterator active between read()
When reading /proc/allocinfo, for each read syscall, seq_file would invoke
start/stop callbacks. In start callback, a memory is alloced to store
iterator and the iterator would start from beginning to walk linearly to
current read position.
seq_file read() takes at most 4096 bytes, even if read with a larger user
space buffer, meaning read out all of /proc/allocinfo, tens of read
syscalls are needed. For example, a 306036 bytes allocinfo files need 76
reads:
$ sudo cat /proc/allocinfo | wc
3964 16678 306036
$ sudo strace -T -e read cat /proc/allocinfo
...
read(3, " 4096 1 arch/x86/k"..., 131072) = 4063 <0.000062>
...
read(3, " 0 0 sound/core"..., 131072) = 4021 <0.000150>
...
For those n=3964 lines, each read takes about m=3964/76=52 lines,
since iterator restart from beginning for each read(),
it would move forward
m steps on 1st read
2*m steps on 2nd read
3*m steps on 3rd read
...
n steps on last read
As read() along, those linear seek steps make read() calls slower and
slower. Adding those up, codetag iterator moves about O(n*n/m) steps,
making data structure traversal take significant part of the whole
reading. Profiling when stress reading /proc/allocinfo confirms it:
A private data alloced at open() time can be used to carry iterator alive
across read() calls, and avoid the memory allocation and iterator reset
for each read(). This way, only O(1) memory allocation and O(n) steps
iterating, and `time` shows performance improvement from ~7ms to ~4ms.
Profiling with the change:
Link: https://lkml.kernel.org/r/20250609064408.112783-1-00107082@163.com Signed-off-by: David Wang <00107082@163.com> Acked-by: Suren Baghdasaryan <surenb@google.com> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Wang [Mon, 9 Jun 2025 06:42:00 +0000 (14:42 +0800)]
alloc_tag: add sequence number for module and iterator
Codetag iterator use <id,address> pair to guarantee the validness. But
both id and address can be reused, there is theoretical possibility when
module inserted right after another module removed, kmalloc returns an
address same as the address kfree by previous module and IDR key reuses
the key recently removed.
Add a sequence number to codetag_module and code_iterator, the sequence
number is strickly incremented whenever a module is loaded. An iterator
is valid if and only if its sequence number match codetag_module's.
Link: https://lkml.kernel.org/r/20250609064200.112639-1-00107082@163.com Signed-off-by: David Wang <00107082@163.com> Acked-by: Suren Baghdasaryan <surenb@google.com> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Li Zhe [Fri, 6 Jun 2025 02:37:42 +0000 (10:37 +0800)]
gup: optimize longterm pin_user_pages() for large folio
In the current implementation of longterm pin_user_pages(), we invoke
collect_longterm_unpinnable_folios(). This function iterates through the
list to check whether each folio belongs to the "longterm_unpinnabled"
category. The folios in this list essentially correspond to a contiguous
region of userspace addresses, with each folio representing a physical
address in increments of PAGESIZE.
If this userspace address range is mapped with large folio, we can
optimize the performance of function collect_longterm_unpinnable_folios()
by reducing the using of READ_ONCE() invoked in
pofs_get_folio()->page_folio()->_compound_head().
Also, we can simplify the logic of collect_longterm_unpinnable_folios().
Instead of comparing with prev_folio after calling pofs_get_folio(), we
can check whether the next page is within the same folio.
The performance test results, based on v6.15, obtained through the
gup_test tool from the kernel source tree are as follows. We achieve an
improvement of over 66% for large folio with pagesize=2M. For small
folio, we have only observed a very slight degradation in performance.
Without this patch:
[root@localhost ~] ./gup_test -HL -m 8192 -n 512
TAP version 13
1..1
# PIN_LONGTERM_BENCHMARK: Time: get:14391 put:10858 us#
ok 1 ioctl status 0
# Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
[root@localhost ~]# ./gup_test -LT -m 8192 -n 512
TAP version 13
1..1
# PIN_LONGTERM_BENCHMARK: Time: get:130538 put:31676 us#
ok 1 ioctl status 0
# Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
With this patch:
[root@localhost ~] ./gup_test -HL -m 8192 -n 512
TAP version 13
1..1
# PIN_LONGTERM_BENCHMARK: Time: get:4867 put:10516 us#
ok 1 ioctl status 0
# Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
[root@localhost ~]# ./gup_test -LT -m 8192 -n 512
TAP version 13
1..1
# PIN_LONGTERM_BENCHMARK: Time: get:131798 put:31328 us#
ok 1 ioctl status 0
# Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
Lorenzo Stoakes [Thu, 5 Jun 2025 13:51:04 +0000 (14:51 +0100)]
mm/pagewalk: split walk_page_range_novma() into kernel/user parts
walk_page_range_novma() is rather confusing - it supports two modes, one
used often, the other used only for debugging.
The first mode is the common case of traversal of kernel page tables,
which is what nearly all callers use this for.
Secondly it provides an unusual debugging interface that allows for the
traversal of page tables in a userland range of memory even for that
memory which is not described by a VMA.
It is far from certain that such page tables should even exist, but
perhaps this is precisely why it is useful as a debugging mechanism.
As a result, this is utilised by ptdump only. Historically, things were
reversed - ptdump was the only user, and other parts of the kernel evolved
to use the kernel page table walking here.
Since we have some complicated and confusing locking rules for the novma
case, it makes sense to separate the two usages into their own functions.
Doing this also provide self-documentation as to the intent of the caller
- are they doing something rather unusual or are they simply doing a
standard kernel page table walk?
We therefore establish two separate functions - walk_page_range_debug()
for this single usage, and walk_kernel_page_table_range() for general
kernel page table walking.
The walk_page_range_debug() function is currently used to traverse both
userland and kernel mappings, so we maintain this and in the case of
kernel mappings being traversed, we have walk_page_range_debug() invoke
walk_kernel_page_table_range() internally.
We additionally make walk_page_range_debug() internal to mm.
Link: https://lkml.kernel.org/r/20250605135104.90720-1-lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> Acked-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: David Hildenbrand <david@redhat.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Barry Song <baohua@kernel.org> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Jann Horn <jannh@google.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: WANG Xuerui <kernel@xen0n.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Arnd Bergmann [Tue, 10 Jun 2025 09:21:50 +0000 (11:21 +0200)]
lib/test_hmm: reduce stack usage
The various test ioctl handlers use arrays of 64 integers that add up to
1KiB of stack data, which in turn leads to exceeding the warning limit in
some configurations:
Use half the size for these arrays, in order to stay under the warning
limits. The code can already deal with arbitrary lengths, but this may be
a little less efficient.
Link: https://lkml.kernel.org/r/20250610092159.2639515-1-arnd@kernel.org Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Alistair Popple <apopple@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jeff Johnson <jeff.johnson@oss.qualcomm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Thorsten Blum <thorsten.blum@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Mark Brown [Tue, 10 Jun 2025 14:07:44 +0000 (15:07 +0100)]
selftests/mm: check for YAMA ptrace_scope configuraiton before modifying it
When running the memfd_secret test run_vmtests.sh unconditionally tries
to confgiure the YAMA LSM's ptrace_scope configuration, leading to an error
if YAMA is not in the running kernel:
# ./run_vmtests.sh: line 432: /proc/sys/kernel/yama/ptrace_scope: No such file or directory
# # ----------------------
# # running ./memfd_secret
# # ----------------------
Check that this file is present before trying to write to it.
The indentation here is a bit odd, and it doesn't seem great that we
configure but don't restore ptrace_scope.
Casey Chen [Tue, 10 Jun 2025 16:22:58 +0000 (10:22 -0600)]
alloc_tag: remove empty module tag section
The empty MOD_CODETAG_SECTIONS() macro added an incomplete .data section
in module linker script, which caused symbol lookup tools like gdb to
misinterpret symbol addresses e.g., __ib_process_cq incorrectly mapping to
unrelated functions like below.
(gdb) disas __ib_process_cq
Dump of assembler code for function trace_event_fields_cq_schedule:
Removing the empty section restores proper symbol resolution and layout,
ensuring .data placement behaves as expected.
Link: https://lkml.kernel.org/r/20250610162258.324645-1-cachen@purestorage.com Fixes: 0db6f8d7820a ("alloc_tag: load module tags into separate contiguous memory") 22d407b164ff ("lib: add allocation tagging support for memory allocation profiling") Signed-off-by: Casey Chen <cachen@purestorage.com> Reviewed-by: Yuanyuan Zhong <yzhong@purestorage.com> Acked-by: Suren Baghdasaryan <surenb@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Luis Chamberalin <mcgrof@kernel.org> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Ryan Roberts [Mon, 9 Jun 2025 09:27:27 +0000 (10:27 +0100)]
mm/filemap: allow arch to request folio size for exec memory
Change the readahead config so that if it is being requested for an
executable mapping, do a synchronous read into a set of folios with an
arch-specified order and in a naturally aligned manner. We no longer
center the read on the faulting page but simply align it down to the
previous natural boundary. Additionally, we don't bother with an
asynchronous part.
On arm64 if memory is physically contiguous and naturally aligned to the
"contpte" size, we can use contpte mappings, which improves utilization of
the TLB. When paired with the "multi-size THP" feature, this works well
to reduce dTLB pressure. However iTLB pressure is still high due to
executable mappings having a low likelihood of being in the required folio
size and mapping alignment, even when the filesystem supports readahead
into large folios (e.g. XFS).
The reason for the low likelihood is that the current readahead algorithm
starts with an order-0 folio and increases the folio order by 2 every time
the readahead mark is hit. But most executable memory tends to be
accessed randomly and so the readahead mark is rarely hit and most
executable folios remain order-0.
So let's special-case the read(ahead) logic for executable mappings. The
trade-off is performance improvement (due to more efficient storage of the
translations in iTLB) vs potential for making reclaim more difficult (due
to the folios being larger so if a part of the folio is hot the whole
thing is considered hot). But executable memory is a small portion of the
overall system memory so I doubt this will even register from a reclaim
perspective.
I've chosen 64K folio size for arm64 which benefits both the 4K and 16K
base page size configs. Crucially the same amount of data is still read
(usually 128K) so I'm not expecting any read amplification issues. I
don't anticipate any write amplification because text is always RO.
Note that the text region of an ELF file could be populated into the page
cache for other reasons than taking a fault in a mmapped area. The most
common case is due to the loader read()ing the header which can be shared
with the beginning of text. So some text will still remain in small
folios, but this simple, best effort change provides good performance
improvements as is.
Confine this special-case approach to the bounds of the VMA. This
prevents wasting memory for any padding that might exist in the file
between sections. Previously the padding would have been contained in
order-0 folios and would be easy to reclaim. But now it would be part of
a larger folio so more difficult to reclaim. Solve this by simply not
reading it into memory in the first place.
Benchmarking
============
The below shows pgbench and redis benchmarks on Graviton3 arm64 system.
First, confirmation that this patch causes more text to be contained in
64K folios:
The above shows that for both workloads (each isolated with cgroups) as
well as the general system state after boot, the amount of text backed by
4K and 16K folios reduces and the amount backed by 64K folios increases
significantly. And the amount of text that is contpte-mapped
significantly increases (see last row).
And this is reflected in performance improvement. "(I)" indicates a
statistically significant improvement. Note TPS and Reqs/sec are rates so
bigger is better, ms is time so smaller is better:
Ryan Roberts [Mon, 9 Jun 2025 09:27:26 +0000 (10:27 +0100)]
mm/readahead: store folio order in struct file_ra_state
Previously the folio order of the previous readahead request was inferred
from the folio who's readahead marker was hit. But due to the way we have
to round to non-natural boundaries sometimes, this first folio in the
readahead block is often smaller than the preferred order for that
request. This means that for cases where the initial sync readahead is
poorly aligned, the folio order will ramp up much more slowly.
So instead, let's store the order in struct file_ra_state so we are not
affected by any required alignment. We previously made enough room in the
struct for a 16 order field. This should be plenty big enough since we
are limited to MAX_PAGECACHE_ORDER anyway, which is certainly never larger
than ~20.
Since we now pass order in struct file_ra_state, page_cache_ra_order() no
longer needs it's new_order parameter, so let's remove that.
Worked example:
Here we are touching pages 17-256 sequentially just as we did in the
previous commit, but now that we are remembering the preferred order
explicitly, we no longer have the slow ramp up problem. Note specifically
that we no longer have 2 rounds (2x ~128K) of order-2 folios:
Link: https://lkml.kernel.org/r/20250609092729.274960-5-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Ryan Roberts [Mon, 9 Jun 2025 09:27:25 +0000 (10:27 +0100)]
mm/readahead: make space in struct file_ra_state
We need to be able to store the preferred folio order associated with a
readahead request in the struct file_ra_state so that we can more
accurately increase the order across subsequent readahead requests. But
struct file_ra_state is per-struct file, so we don't really want to
increase it's size.
mmap_miss is currently 32 bits but it is only counted up to 10 *
MMAP_LOTSAMISS, which is currently defined as 1000. So 16 bits should be
plenty. Redefine it to unsigned short, making room for order as unsigned
short in follow up commit.
Link: https://lkml.kernel.org/r/20250609092729.274960-4-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Ryan Roberts [Mon, 9 Jun 2025 09:27:24 +0000 (10:27 +0100)]
mm/readahead: terminate async readahead on natural boundary
Previously asynchonous readahead would read ra_pages (usually 128K)
directly after the end of the synchonous readahead and given the
synchronous readahead portion had no alignment guarantees (beyond page
boundaries) it is possible (and likely) that the end of the initial 128K
region would not fall on a natural boundary for the folio size being used.
Therefore smaller folios were used to align down to the required
boundary, both at the end of the previous readahead block and at the start
of the new one.
In the worst cases, this can result in never properly ramping up the folio
size, and instead getting stuck oscillating between order-0, -1 and -2
folios. The next readahead will try to use folios whose order is +2
bigger than the folio that had the readahead marker. But because of the
alignment requirements, that folio (the first one in the readahead block)
can end up being order-0 in some cases.
There will be 2 modifications to solve this issue:
1) Calculate the readahead size so the end is aligned to a folio
boundary. This prevents needing to allocate small folios to align
down at the end of the window and fixes the oscillation problem.
2) Remember the "preferred folio order" in the ra state instead of
inferring it from the folio with the readahead marker. This solves
the slow ramp up problem (discussed in a subsequent patch).
This patch addresses (1) only. A subsequent patch will address (2).
Worked example:
The following shows the previous pathalogical behaviour when the initial
synchronous readahead is unaligned. We start reading at page 17 in the
file and read sequentially from there. I'm showing a dump of the pages in
the page cache just after we read the first page of the folio with the
readahead marker.
Initially there are no pages in the page cache:
TYPE STARTOFFS ENDOFFS SIZE STARTPG ENDPG NRPG ORDER RA
----- ---------- ---------- ---------- ------- ------- ----- ----- --
HOLE 0x00000000 0x00800000 8388608 0 2048 2048
Then we access page 17, causing synchonous read-around of 128K with a
readahead marker set up at page 25. So far, all as expected:
Now access pages 18-25 inclusive. This causes an asynchronous 128K
readahead starting at page 33. But since we are unaligned, even though
the preferred folio order is 2, the first folio in this batch (the one
with the new readahead marker) is order-0:
This ramp up from order-0 with smaller orders at the edges for alignment
cycle continues all the way to the end of the file (not shown).
After the change, we round down the end boundary to the order boundary so
we no longer get stuck in the cycle and can ramp up the order over time.
Note that the rate of the ramp up is still not as we would expect it. We
will fix that next. Here we are touching pages 17-256 sequentially:
Link: https://lkml.kernel.org/r/20250609092729.274960-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Ryan Roberts [Mon, 9 Jun 2025 09:27:23 +0000 (10:27 +0100)]
mm/readahead: honour new_order in page_cache_ra_order()
Patch series "Readahead tweaks for larger folios", v5.
This series adds some tweaks to readahead so that it does a better job of
ramping up folio sizes as readahead extends further into the file. And it
additionally special-cases executable mappings to allow the arch to
request a preferred folio size for text.
This patch (of 5):
page_cache_ra_order() takes a parameter called new_order, which is
intended to express the preferred order of the folios that will be
allocated for the readahead operation. Most callers indeed call this with
their preferred new order. But page_cache_async_ra() calls it with the
preferred order of the previous readahead request (actually the order of
the folio that had the readahead marker, which may be smaller when
alignment comes into play).
And despite the parameter name, page_cache_ra_order() always treats it at
the old order, adding 2 to it on entry. As a result, a cold readahead
always starts with order-2 folios.
Let's fix this behaviour by always passing in the *new* order.
Worked example:
Prior to the change, mmaping an 8MB file and touching each page
sequentially, resulted in the following, where we start with order-2
folios for the first 128K then ramp up to order-4 for the next 128K, then
get clamped to order-5 for the rest of the file because pa_pages is
limited to 128K:
After the change, the same operation results in the first 128K being
order-0, then we start ramping up to order-2, -4, and finally get clamped
at order-5:
Dev Jain [Wed, 4 Jun 2025 04:15:33 +0000 (09:45 +0530)]
xarray: add a BUG_ON() to ensure caller is not sibling
Suppose xas is pointing somewhere near the end of the multi-entry batch.
Then it may happen that the computed slot already falls beyond the batch,
thus breaking the loop due to !xa_is_sibling(), and computing the wrong
order.
For example, suppose we have a shift-6 node having an order-9 entry => 8 -
1 = 7 siblings, so assume the slots are at offset 0 till 7 in this node.
If xas->xa_offset is 6, then the code will compute order as 1 +
xas->xa_node->shift = 7. Therefore, the order computation must start from
the beginning of the multi-slot entries, that is, the non-sibling entry.
Thus ensure that the caller is aware of this by triggering a BUG when the
entry is a sibling entry. Note that this BUG_ON() is only active while
running selftests, so there is no overhead in a running kernel.
Link: https://lkml.kernel.org/r/20250604041533.91198-1-dev.jain@arm.com Signed-off-by: Dev Jain <dev.jain@arm.com> Acked-by: Zi Yan <ziy@nvidia.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@kernel.org> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
wangzijie [Sat, 7 Jun 2025 02:13:53 +0000 (10:13 +0800)]
proc: use the same treatment to check proc_lseek as ones for proc_read_iter et.al
Check pde->proc_ops->proc_lseek directly may cause UAF in rmmod scenario.
It's a gap in proc_reg_open() after commit 654b33ada4ab("proc: fix UAF in
proc_get_inode()"). Followed by AI Viro's suggestion, fix it in same
manner.
Link: https://lkml.kernel.org/r/20250607021353.1127963-1-wangzijie1@honor.com Fixes: 3f61631d47f1 ("take care to handle NULL ->proc_lseek()") Signed-off-by: wangzijie <wangzijie1@honor.com> Reviewed-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com> Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Barry Song [Sat, 7 Jun 2025 22:01:50 +0000 (10:01 +1200)]
mm: use per_vma lock for MADV_DONTNEED
Certain madvise operations, especially MADV_DONTNEED, occur far more
frequently than other madvise options, particularly in native and Java
heaps for dynamic memory management.
Currently, the mmap_lock is always held during these operations, even when
unnecessary. This causes lock contention and can lead to severe priority
inversion, where low-priority threads—such as Android's
HeapTaskDaemon— hold the lock and block higher-priority threads.
This patch enables the use of per-VMA locks when the advised range lies
entirely within a single VMA, avoiding the need for full VMA traversal.
In practice, userspace heaps rarely issue MADV_DONTNEED across multiple
VMAs.
Tangquan's testing shows that over 99.5% of memory reclaimed by Android
benefits from this per-VMA lock optimization. After extended runtime,
217,735 madvise calls from HeapTaskDaemon used the per-VMA path, while
only 1,231 fell back to mmap_lock.
To simplify handling, the implementation falls back to the standard
mmap_lock if userfaultfd is enabled on the VMA, avoiding the complexity of
userfaultfd_remove().
Many thanks to Lorenzo's work[1] on "mm/madvise: support VMA read locks
for MADV_DONTNEED[_LOCKED]"
Then use this mechanism to permit VMA locking to be done later in the
madvise() logic and also to allow altering of the locking mode to permit
falling back to an mmap read lock if required."
One important point, as pointed out by Jann[2], is that
untagged_addr_remote() requires holding mmap_lock. This is because
address tagging on x86 and RISC-V is quite complex.
Until untagged_addr_remote() becomes atomic—which seems unlikely in the
near future—we cannot support per-VMA locks for remote processes. So
for now, only local processes are supported.
Lance said:
: Just to put some numbers on it, I ran a micro-benchmark with 100
: parallel threads, where each thread calls madvise() on its own 1GiB
: chunk of 64KiB mTHP-backed memory. The performance gain is huge:
:
: 1) MADV_DONTNEED saw its average time drop from 0.0508s to 0.0270s
: (~47% faster)
:
: 2) MADV_FREE saw its average time drop from 0.3078s to 0.1095s (~64%
: faster)
Tal Zussman [Fri, 20 Jun 2025 01:24:26 +0000 (21:24 -0400)]
userfaultfd: remove UFFD_CLOEXEC, UFFD_NONBLOCK, and UFFD_FLAGS_SET
UFFD_CLOEXEC, UFFD_NONBLOCK, and UFFD_FLAGS_SET have been unused since
they were added in commit 932b18e0aec6 ("userfaultfd:
linux/userfaultfd_k.h"). Remove them and the associated BUILD_BUG_ON()
checks.
Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-4-a7274d3bd5e4@columbia.edu Signed-off-by: Tal Zussman <tz2294@columbia.edu> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tal Zussman [Fri, 20 Jun 2025 01:24:25 +0000 (21:24 -0400)]
userfaultfd: remove (VM_)BUG_ON()s
BUG_ON() is deprecated [1]. Convert all the BUG_ON()s and VM_BUG_ON()s to
use VM_WARN_ON_ONCE().
There are a few additional cases that are converted or modified:
- Convert the printk(KERN_WARNING ...) in handle_userfault() to use
pr_warn().
- Convert the WARN_ON_ONCE()s in move_pages() to use VM_WARN_ON_ONCE(),
as the relevant conditions are already checked in validate_range() in
move_pages()'s caller.
- Convert the VM_WARN_ON()'s in move_pages() to VM_WARN_ON_ONCE(). These
cases should never happen and are similar to those in mfill_atomic()
and mfill_atomic_hugetlb(), which were previously BUG_ON()s.
move_pages() was added later than those functions and makes use of
VM_WARN_ON() as a replacement for the deprecated BUG_ON(), but.
VM_WARN_ON_ONCE() is likely a better direct replacement.
- Convert the WARN_ON() for !VM_MAYWRITE in userfaultfd_unregister() and
userfaultfd_register_range() to VM_WARN_ON_ONCE(). This condition is
enforced in userfaultfd_register() so it should never happen, and can
be converted to a debug check.
Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-3-a7274d3bd5e4@columbia.edu Signed-off-by: Tal Zussman <tz2294@columbia.edu> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Brauner <brauner@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason A. Donenfeld <Jason@zx2c4.com> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tal Zussman [Fri, 20 Jun 2025 01:24:24 +0000 (21:24 -0400)]
userfaultfd: prevent unregistering VMAs through a different userfaultfd
Currently, a VMA registered with a uffd can be unregistered through a
different uffd associated with the same mm_struct.
The existing behavior is slightly broken and may incorrectly reject
unregistering some VMAs due to the following check:
if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
goto out_unlock;
where wp_async is derived from ctx, not from cur. For example, a
file-backed VMA registered with wp_async enabled and UFFD_WP mode cannot
be unregistered through a uffd that does not have wp_async enabled.
Rather than fix this and maintain this odd behavior, make unregistration
stricter by requiring VMAs to be unregistered through the same uffd they
were registered with. Additionally, reorder the BUG() checks to avoid the
aforementioned wp_async issue in them. Convert the existing check to
VM_WARN_ON_ONCE() as BUG_ON() is deprecated.
This change slightly modifies the ABI. It should not be backported to
-stable. It is expected that no one depends on this behavior, and no such
cases are known.
While at it, correct the comment for the no userfaultfd case. This seems
to be a copy-paste artifact from the analogous userfaultfd_register()
check.
Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-2-a7274d3bd5e4@columbia.edu Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Tal Zussman <tz2294@columbia.edu> Acked-by: David Hildenbrand <david@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jason A. Donenfeld <Jason@zx2c4.com> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tal Zussman [Fri, 20 Jun 2025 01:24:23 +0000 (21:24 -0400)]
userfaultfd: correctly prevent registering VM_DROPPABLE regions
Patch series "mm: userfaultfd: assorted fixes and cleanups", v3.
Two fixes and two cleanups for userfaultfd.
Note that the third patch yields a small change in the ABI, but we seem to
have concluded that it is acceptable in this case.
This patch (of 4):
vma_can_userfault() masks off non-userfaultfd VM flags from vm_flags. The
vm_flags & VM_DROPPABLE test will then always be false, incorrectly
allowing VM_DROPPABLE regions to be registered with userfaultfd.
Additionally, vm_flags is not guaranteed to correspond to the actual VMA's
flags. Fix this test by checking the VMA's flags directly.
projects / thirdparty / kernel / linux.git / log
