summaryrefslogtreecommitdiff
path: root/mm/mmap.c
diff options
context:
space:
mode:
authorSuren Baghdasaryan <surenb@google.com>2022-01-14 14:06:14 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-15 16:30:27 +0200
commit64591e8605d6e2fba2ff38e3227645f039b8893f (patch)
tree0052f7aa5f716cd1569f7c5e2a340861dcbbbed1 /mm/mmap.c
parent36090def7bad06a6346f86a7cfdbfda2d138cb64 (diff)
mm: protect free_pgtables with mmap_lock write lock in exit_mmap
oom-reaper and process_mrelease system call should protect against races with exit_mmap which can destroy page tables while they walk the VMA tree. oom-reaper protects from that race by setting MMF_OOM_VICTIM and by relying on exit_mmap to set MMF_OOM_SKIP before taking and releasing mmap_write_lock. process_mrelease has to elevate mm->mm_users to prevent such race. Both oom-reaper and process_mrelease hold mmap_read_lock when walking the VMA tree. The locking rules and mechanisms could be simpler if exit_mmap takes mmap_write_lock while executing destructive operations such as free_pgtables. Change exit_mmap to hold the mmap_write_lock when calling unlock_range, free_pgtables and remove_vma. Note also that because oom-reaper checks VM_LOCKED flag, unlock_range() should not be allowed to race with it. Before this patch, remove_vma used to be called with no locks held, however with fput being executed asynchronously and vm_ops->close not being allowed to hold mmap_lock (it is called from __split_vma with mmap_sem held for write), changing that should be fine. In most cases this lock should be uncontended. Previously, Kirill reported ~4% regression caused by a similar change [1]. We reran the same test and although the individual results are quite noisy, the percentiles show lower regression with 1.6% being the worst case [2]. The change allows oom-reaper and process_mrelease to execute safely under mmap_read_lock without worries that exit_mmap might destroy page tables from under them. [1] https://lore.kernel.org/all/20170725141723.ivukwhddk2voyhuc@node.shutemov.name/ [2] https://lore.kernel.org/all/CAJuCfpGC9-c9P40x7oy=jy5SphMcd0o0G_6U1-+JAziGKG6dGA@mail.gmail.com/ Link: https://lkml.kernel.org/r/20211209191325.3069345-1-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: David Rientjes <rientjes@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Rik van Riel <riel@surriel.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Brauner <christian@brauner.io> Cc: Christoph Hellwig <hch@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Christian Brauner <christian.brauner@ubuntu.com> Cc: Florian Weimer <fweimer@redhat.com> Cc: Jan Engelhardt <jengelh@inai.de> Cc: Tim Murray <timmurray@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mmap.c')
-rw-r--r--mm/mmap.c16
1 files changed, 8 insertions, 8 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index 77733b113c40..3f48d0928e6b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3149,25 +3149,27 @@ void exit_mmap(struct mm_struct *mm)
* to mmu_notifier_release(mm) ensures mmu notifier callbacks in
* __oom_reap_task_mm() will not block.
*
- * This needs to be done before calling munlock_vma_pages_all(),
+ * This needs to be done before calling unlock_range(),
* which clears VM_LOCKED, otherwise the oom reaper cannot
* reliably test it.
*/
(void)__oom_reap_task_mm(mm);
set_bit(MMF_OOM_SKIP, &mm->flags);
- mmap_write_lock(mm);
- mmap_write_unlock(mm);
}
+ mmap_write_lock(mm);
if (mm->locked_vm)
unlock_range(mm->mmap, ULONG_MAX);
arch_exit_mmap(mm);
vma = mm->mmap;
- if (!vma) /* Can happen if dup_mmap() received an OOM */
+ if (!vma) {
+ /* Can happen if dup_mmap() received an OOM */
+ mmap_write_unlock(mm);
return;
+ }
lru_add_drain();
flush_cache_mm(mm);
@@ -3178,16 +3180,14 @@ void exit_mmap(struct mm_struct *mm)
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb);
- /*
- * Walk the list again, actually closing and freeing it,
- * with preemption enabled, without holding any MM locks.
- */
+ /* Walk the list again, actually closing and freeing it. */
while (vma) {
if (vma->vm_flags & VM_ACCOUNT)
nr_accounted += vma_pages(vma);
vma = remove_vma(vma);
cond_resched();
}
+ mmap_write_unlock(mm);
vm_unacct_memory(nr_accounted);
}