summaryrefslogtreecommitdiff
path: root/mm/khugepaged.c
diff options
context:
space:
mode:
authorJann Horn <jannh@google.com>2022-11-25 22:37:14 +0100
committerAndrew Morton <akpm@linux-foundation.org>2022-11-30 14:49:42 -0800
commitf268f6cf875f3220afc77bdd0bf1bb136eb54db9 (patch)
treef834a079ef989491ff51dac481179e5e199b8495 /mm/khugepaged.c
parent2ba99c5e08812494bc57f319fb562f527d9bacd8 (diff)
mm/khugepaged: invoke MMU notifiers in shmem/file collapse paths
Any codepath that zaps page table entries must invoke MMU notifiers to ensure that secondary MMUs (like KVM) don't keep accessing pages which aren't mapped anymore. Secondary MMUs don't hold their own references to pages that are mirrored over, so failing to notify them can lead to page use-after-free. I'm marking this as addressing an issue introduced in commit f3f0e1d2150b ("khugepaged: add support of collapse for tmpfs/shmem pages"), but most of the security impact of this only came in commit 27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP"), which actually omitted flushes for the removal of present PTEs, not just for the removal of empty page tables. Link: https://lkml.kernel.org/r/20221129154730.2274278-3-jannh@google.com Link: https://lkml.kernel.org/r/20221128180252.1684965-3-jannh@google.com Link: https://lkml.kernel.org/r/20221125213714.4115729-3-jannh@google.com Fixes: f3f0e1d2150b ("khugepaged: add support of collapse for tmpfs/shmem pages") Signed-off-by: Jann Horn <jannh@google.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Peter Xu <peterx@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/khugepaged.c')
-rw-r--r--mm/khugepaged.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 294cb75d9c22..3703a56571c1 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1399,6 +1399,7 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v
unsigned long addr, pmd_t *pmdp)
{
pmd_t pmd;
+ struct mmu_notifier_range range;
mmap_assert_write_locked(mm);
if (vma->vm_file)
@@ -1410,8 +1411,12 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v
if (vma->anon_vma)
lockdep_assert_held_write(&vma->anon_vma->root->rwsem);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr,
+ addr + HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
pmd = pmdp_collapse_flush(vma, addr, pmdp);
tlb_remove_table_sync_one();
+ mmu_notifier_invalidate_range_end(&range);
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, addr, pmd);
pte_free(mm, pmd_pgtable(pmd));