[PATCH 3.2 43/62] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED
From: Ben Hutchings
Date: Tue Mar 29 2016 - 16:06:05 EST
3.2.79-rc1 review patch. If anyone has any objections, please let me know.
From: Andrea Arcangeli <aarcange@xxxxxxxxxx>
commit ad33bb04b2a6cee6c1f99fabb15cddbf93ff0433 upstream.
introduced to locklessy (but atomically) detect when a pmd is a regular
(stable) pmd or when the pmd is unstable and can infinitely transition
from pmd_none() and pmd_trans_huge() from under us, while only holding
the mmap_sem for reading (for writing not).
While holding the mmap_sem only for reading, MADV_DONTNEED can run from
under us and so before we can assume the pmd to be a regular stable pmd
we need to compare it against pmd_none() and pmd_trans_huge() in an
atomic way, with pmd_trans_unstable(). The old pmd_trans_huge() left a
tiny window for a race.
Useful applications are unlikely to notice the difference as doing
MADV_DONTNEED concurrently with a page fault would lead to undefined
[akpm@xxxxxxxxxxxxxxxxxxxx: tidy up comment grammar/layout]
Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Reported-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
mm/memory.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
@@ -3583,8 +3583,18 @@ retry:
if (unlikely(pmd_none(*pmd)) && __pte_alloc(mm, vma, pmd, address))
- /* if an huge pmd materialized from under us just retry later */
- if (unlikely(pmd_trans_huge(*pmd)))
+ * If a huge pmd materialized under us just retry later. Use
+ * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+ * didn't become pmd_trans_huge under us and then back to pmd_none, as
+ * a result of MADV_DONTNEED running immediately after a huge pmd fault
+ * in a different thread of this mm, in turn leading to a misleading
+ * pmd_trans_huge() retval. All we have to ensure is that it is a
+ * regular pmd that we can walk with pte_offset_map() and we can do that
+ * through an atomic read in C, which is what pmd_trans_unstable()
+ * provides.
+ if (unlikely(pmd_trans_unstable(pmd)))
* A regular pmd is established and it can't morph into a huge pmd