Pull slab fixes from Vlastimil Babka:

 - Two fixes for race conditions in obj_exts allocation (Hao Ge)

 - Fix for slab accounting imbalance due to deferred slab decativation
   (Vlastimil Babka)

* tag 'slab-for-6.18-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
  slab: Fix obj_ext mistakenly considered NULL due to race condition
  slab: fix slab accounting imbalance due to defer_deactivate_slab()
  slab: Avoid race on slab->obj_exts in alloc_slab_obj_exts

If two competing threads enter alloc_slab_obj_exts(), and the one that
allocates the vector wins the cmpxchg(), the other thread that failed
allocation mistakenly assumes that slab->obj_exts is still empty due to
its own allocation failure. This will then trigger warnings with
CONFIG_MEM_ALLOC_PROFILING_DEBUG checks in the subsequent free path.

Therefore, let's check the result of cmpxchg() to see if marking the
allocation as failed was successful. If it wasn't, check whether the
winning side has succeeded its allocation (it might have been also
marking it as failed) and if yes, return success.

Suggested-by: Harry Yoo <harry.yoo@oracle.com>
Fixes: f7381b911640 ("slab: mark slab->obj_exts allocation failures unconditionally")
Cc: <stable@vger.kernel.org>
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Link: https://patch.msgid.link/20251023143313.1327968-1-hao.ge@linux.dev
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

Since commit af92793e52c3 ("slab: Introduce kmalloc_nolock() and
kfree_nolock().") there's a possibility in alloc_single_from_new_slab()
that we discard the newly allocated slab if we can't spin and we fail to
trylock. As a result we don't perform inc_slabs_node() later in the
function. Instead we perform a deferred deactivate_slab() which can
either put the unacounted slab on partial list, or discard it
immediately while performing dec_slabs_node(). Either way will cause an
accounting imbalance.

Fix this by not marking the slab as frozen, and using free_slab()
instead of deactivate_slab() for non-frozen slabs in
free_deferred_objects(). For CONFIG_SLUB_TINY, that's the only possible
case. By not using discard_slab() we avoid dec_slabs_node().

Fixes: af92793e52c3 ("slab: Introduce kmalloc_nolock() and kfree_nolock().")
Link: https://patch.msgid.link/20251023-fix-slab-accounting-v2-1-0e62d50986ea@suse.cz
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

Pull hotfixes from Andrew Morton:
 "17 hotfixes. 12 are cc:stable and 14 are for MM.

  There's a two-patch DAMON series from SeongJae Park which addresses a
  missed check and possible memory leak. Apart from that it's all
  singletons - please see the changelogs for details"

* tag 'mm-hotfixes-stable-2025-10-22-12-43' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  csky: abiv2: adapt to new folio flags field
  mm/damon/core: use damos_commit_quota_goal() for new goal commit
  mm/damon/core: fix potential memory leak by cleaning ops_filter in damon_destroy_scheme
  hugetlbfs: move lock assertions after early returns in huge_pmd_unshare()
  vmw_balloon: indicate success when effectively deflating during migration
  mm/damon/core: fix list_add_tail() call on damon_call()
  mm/mremap: correctly account old mapping after MREMAP_DONTUNMAP remap
  mm: prevent poison consumption when splitting THP
  ocfs2: clear extent cache after moving/defragmenting extents
  mm: don't spin in add_stack_record when gfp flags don't allow
  dma-debug: don't report false positives with DMA_BOUNCE_UNALIGNED_KMALLOC
  mm/damon/sysfs: dealloc commit test ctx always
  mm/damon/sysfs: catch commit test ctx alloc failure
  hung_task: fix warnings caused by unaligned lock pointers

When damos_commit_quota_goals() is called for adding new DAMOS quota goals
of DAMOS_QUOTA_USER_INPUT metric, current_value fields of the new goals
should be also set as requested.

However, damos_commit_quota_goals() is not updating the field for the
case, since it is setting only metrics and target values using
damos_new_quota_goal(), and metric-optional union fields using
damos_commit_quota_goal_union().  As a result, users could see the first
current_value parameter that committed online with a new quota goal is
ignored.  Users are assumed to commit the current_value for
DAMOS_QUOTA_USER_INPUT quota goals, since it is being used as a feedback. 
Hence the real impact would be subtle.  That said, this is obviously not
intended behavior.

Fix the issue by using damos_commit_quota_goal() which sets all quota goal
parameters, instead of damos_commit_quota_goal_union(), which sets only
the union fields.

Link: https://lkml.kernel.org/r/20251014001846.279282-1-sj@kernel.org
Fixes: 1aef9df0ee90 ("mm/damon/core: commit damos_quota_goal->nid")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.16+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Currently, damon_destroy_scheme() only cleans up the filter list but
leaves ops_filter untouched, which could lead to memory leaks when a
scheme is destroyed.

This patch ensures both filter and ops_filter are properly freed in
damon_destroy_scheme(), preventing potential memory leaks.

Link: https://lkml.kernel.org/r/20251014084225.313313-1-lienze@kylinos.cn
Fixes: ab82e57981d0 ("mm/damon/core: introduce damos->ops_filters")
Signed-off-by: Enze Li <lienze@kylinos.cn>
Reviewed-by: SeongJae Park <sj@kernel.org>
Tested-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

When hugetlb_vmdelete_list() processes VMAs during truncate operations, it
may encounter VMAs where huge_pmd_unshare() is called without the required
shareable lock.  This triggers an assertion failure in
hugetlb_vma_assert_locked().

The previous fix in commit dd83609b8898 ("hugetlbfs: skip VMAs without
shareable locks in hugetlb_vmdelete_list") skipped entire VMAs without
shareable locks to avoid the assertion.  However, this prevented pages
from being unmapped and freed, causing a regression in
fallocate(PUNCH_HOLE) operations where pages were not freed immediately,
as reported by Mark Brown.

Instead of checking locks in the caller or skipping VMAs, move the lock
assertions in huge_pmd_unshare() to after the early return checks.  The
assertions are only needed when actual PMD unsharing work will be
performed.  If the function returns early because sz != PMD_SIZE or the
PMD is not shared, no locks are required and assertions should not fire.

This approach reverts the VMA skipping logic from commit dd83609b8898
("hugetlbfs: skip VMAs without shareable locks in hugetlb_vmdelete_list")
while moving the assertions to avoid the assertion failure, keeping all
the logic within huge_pmd_unshare() itself and allowing page unmapping and
freeing to proceed for all VMAs.

Link: https://lkml.kernel.org/r/20251014113344.21194-1-kartikey406@gmail.com
Fixes: dd83609b8898 ("hugetlbfs: skip VMAs without shareable locks in hugetlb_vmdelete_list")
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Reported-by: <syzbot+f26d7c75c26ec19790e7@syzkaller.appspotmail.com>
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://syzkaller.appspot.com/bug?extid=f26d7c75c26ec19790e7
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Oscar Salvador <osalvador@suse.de>
Tested-by: <syzbot+f26d7c75c26ec19790e7@syzkaller.appspotmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Each damon_ctx maintains callback requests using a linked list
(damon_ctx->call_controls).  When a new callback request is received via
damon_call(), the new request should be added to the list.  However, the
function is making a mistake at list_add_tail() invocation: putting the
new item to add and the list head to add it before, in the opposite order.
Because of the linked list manipulation implementation, the new request
can still be reached from the context's list head.  But the list items
that were added before the new request are dropped from the list.

As a result, the callbacks are unexpectedly not invocated.  Worse yet, if
the dropped callback requests were dynamically allocated, the memory is
leaked.  Actually DAMON sysfs interface is using a dynamically allocated
repeat-mode callback request for automatic essential stats update.  And
because the online DAMON parameters commit is using a non-repeat-mode
callback request, the issue can easily be reproduced, like below.

    # damo start --damos_action stat --refresh_stat 1s
    # damo tune --damos_action stat --refresh_stat 1s

The first command dynamically allocates the repeat-mode callback request
for automatic essential stat update.  Users can see the essential stats
are automatically updated for every second, using the sysfs interface.

The second command calls damon_commit() with a new callback request that
was made for the commit.  As a result, the previously added repeat-mode
callback request is dropped from the list.  The automatic stats refresh
stops working, and the memory for the repeat-mode callback request is
leaked.  It can be confirmed using kmemleak.

Fix the mistake on the list_add_tail() call.

Link: https://lkml.kernel.org/r/20251014205939.1206-1-sj@kernel.org
Fixes: 004ded6bee11 ("mm/damon: accept parallel damon_call() requests")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.17+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Commit b714ccb02a76 ("mm/mremap: complete refactor of move_vma()")
mistakenly introduced a new behaviour - clearing the VM_ACCOUNT flag of
the old mapping when a mapping is mremap()'d with the MREMAP_DONTUNMAP
flag set.

While we always clear the VM_LOCKED and VM_LOCKONFAULT flags for the old
mapping (the page tables have been moved, so there is no data that could
possibly be locked in memory), there is no reason to touch any other VMA
flags.

This is because after the move the old mapping is in a state as if it were
freshly mapped.  This implies that the attributes of the mapping ought to
remain the same, including whether or not the mapping is accounted.

Link: https://lkml.kernel.org/r/20251013165836.273113-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Fixes: b714ccb02a76 ("mm/mremap: complete refactor of move_vma()")
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

If two competing threads enter alloc_slab_obj_exts() and one of them
fails to allocate the object extension vector, it might override the
valid slab->obj_exts allocated by the other thread with
OBJEXTS_ALLOC_FAIL. This will cause the thread that lost this race and
expects a valid pointer to dereference a NULL pointer later on.

Update slab->obj_exts atomically using cmpxchg() to avoid
slab->obj_exts overrides by racing threads.

Thanks for Vlastimil and Suren's help with debugging.

Fixes: f7381b911640 ("slab: mark slab->obj_exts allocation failures unconditionally")
Cc: <stable@vger.kernel.org>
Suggested-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Link: https://patch.msgid.link/20251021010353.1187193-1-hao.ge@linux.dev
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>