summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2020-08-06 23:26:22 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-07 11:33:29 -0700
commit18e77600f7a1ed69f8ce46c9e11cad0985712dfa (patch)
tree5f81e6fc1ee60c9986cc1e3c45ce056ff23cc255 /mm
parent119a5fc16105b2b9383a6e2a7800b2ef861b2975 (diff)
downloadlinux-18e77600f7a1ed69f8ce46c9e11cad0985712dfa.tar.bz2
khugepaged: retract_page_tables() remember to test exit
Only once have I seen this scenario (and forgot even to notice what forced the eventual crash): a sequence of "BUG: Bad page map" alerts from vm_normal_page(), from zap_pte_range() servicing exit_mmap(); pmd:00000000, pte values corresponding to data in physical page 0. The pte mappings being zapped in this case were supposed to be from a huge page of ext4 text (but could as well have been shmem): my belief is that it was racing with collapse_file()'s retract_page_tables(), found *pmd pointing to a page table, locked it, but *pmd had become 0 by the time start_pte was decided. In most cases, that possibility is excluded by holding mmap lock; but exit_mmap() proceeds without mmap lock. Most of what's run by khugepaged checks khugepaged_test_exit() after acquiring mmap lock: khugepaged_collapse_pte_mapped_thps() and hugepage_vma_revalidate() do so, for example. But retract_page_tables() did not: fix that. The fix is for retract_page_tables() to check khugepaged_test_exit(), after acquiring mmap lock, before doing anything to the page table. Getting the mmap lock serializes with __mmput(), which briefly takes and drops it in __khugepaged_exit(); then the khugepaged_test_exit() check on mm_users makes sure we don't touch the page table once exit_mmap() might reach it, since exit_mmap() will be proceeding without mmap lock, not expecting anyone to be racing with it. Fixes: f3f0e1d2150b ("khugepaged: add support of collapse for tmpfs/shmem pages") Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Song Liu <songliubraving@fb.com> Cc: <stable@vger.kernel.org> [4.8+] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008021215400.27773@eggly.anvils Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/khugepaged.c24
1 files changed, 14 insertions, 10 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a9aca9b71d6f..ac04b332a373 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1532,6 +1532,7 @@ out:
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
struct vm_area_struct *vma;
+ struct mm_struct *mm;
unsigned long addr;
pmd_t *pmd, _pmd;
@@ -1560,7 +1561,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
continue;
if (vma->vm_end < addr + HPAGE_PMD_SIZE)
continue;
- pmd = mm_find_pmd(vma->vm_mm, addr);
+ mm = vma->vm_mm;
+ pmd = mm_find_pmd(mm, addr);
if (!pmd)
continue;
/*
@@ -1570,17 +1572,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
* mmap_lock while holding page lock. Fault path does it in
* reverse order. Trylock is a way to avoid deadlock.
*/
- if (mmap_write_trylock(vma->vm_mm)) {
- spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
- /* assume page table is clear */
- _pmd = pmdp_collapse_flush(vma, addr, pmd);
- spin_unlock(ptl);
- mmap_write_unlock(vma->vm_mm);
- mm_dec_nr_ptes(vma->vm_mm);
- pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+ if (mmap_write_trylock(mm)) {
+ if (!khugepaged_test_exit(mm)) {
+ spinlock_t *ptl = pmd_lock(mm, pmd);
+ /* assume page table is clear */
+ _pmd = pmdp_collapse_flush(vma, addr, pmd);
+ spin_unlock(ptl);
+ mm_dec_nr_ptes(mm);
+ pte_free(mm, pmd_pgtable(_pmd));
+ }
+ mmap_write_unlock(mm);
} else {
/* Try again later */
- khugepaged_add_pte_mapped_thp(vma->vm_mm, addr);
+ khugepaged_add_pte_mapped_thp(mm, addr);
}
}
i_mmap_unlock_write(mapping);