diff options
| author | Kirill A. Shutemov <kirill.shutemov@linux.intel.com> | 2017-04-13 14:56:26 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-04-13 18:24:21 -0700 |
| commit | 58ceeb6bec86d9140f9d91d71a710e963523d063 (patch) | |
| tree | c9b4a990429893f3cdb70771701e2565de4b532f /mm/huge_memory.c | |
| parent | c0c379e2931b05facef538e53bf3b21f283d9a0b (diff) | |
| download | linux-58ceeb6bec86d9140f9d91d71a710e963523d063.tar.bz2 | |
thp: fix MADV_DONTNEED vs. MADV_FREE race
Both MADV_DONTNEED and MADV_FREE handled with down_read(mmap_sem).
It's critical to not clear pmd intermittently while handling MADV_FREE
to avoid race with MADV_DONTNEED:
CPU0: CPU1:
madvise_free_huge_pmd()
pmdp_huge_get_and_clear_full()
madvise_dontneed()
zap_pmd_range()
pmd_trans_huge(*pmd) == 0 (without ptl)
// skip the pmd
set_pmd_at();
// pmd is re-established
It results in MADV_DONTNEED skipping the pmd, leaving it not cleared.
It violates MADV_DONTNEED interface and can result is userspace
misbehaviour.
Basically it's the same race as with numa balancing in
change_huge_pmd(), but a bit simpler to mitigate: we don't need to
preserve dirty/young flags here due to MADV_FREE functionality.
[kirill.shutemov@linux.intel.com: Urgh... Power is special again]
Link: http://lkml.kernel.org/r/20170303102636.bhd2zhtpds4mt62a@black.fi.intel.com
Link: http://lkml.kernel.org/r/20170302151034.27829-4-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/huge_memory.c')
| -rw-r--r-- | mm/huge_memory.c | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 26769465af63..f3c4f9d22821 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1568,8 +1568,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, deactivate_page(page); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { - orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, - tlb->fullmm); + pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); |