Skip to content

Commit

Permalink
thp: fix unsuitable behavior for hwpoisoned tail page
Browse files Browse the repository at this point in the history
When a tail page of THP is poisoned, memory-failure will do nothing except
setting PG_hwpoison, while the expected behavior is that the process, who
is using the poisoned tail page, should be killed.

The above problem is caused by lru check of the poisoned tail page of THP.
Because PG_lru flag is only set on the head page of THP, the check always
consider the poisoned tail page as NON lru page.

So the lru check for the tail page of THP should be avoided, as like as
hugetlb.

This patch adds !PageTransCompound() before lru check for THP, because of
the check (!PageHuge() && !PageTransCompound()) the whole branch could be
optimized away at build time when both hugetlbfs and THP are set with "N"
(or in archs not supporting either of those).

[akpm@linux-foundation.org: fix unrelated typo in shake_page() comment]
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
  • Loading branch information
Jin Dongming authored and Linus Torvalds committed Feb 3, 2011
1 parent a6d30dd commit af241a0
Showing 1 changed file with 17 additions and 14 deletions.
31 changes: 17 additions & 14 deletions mm/memory-failure.c
Original file line number Diff line number Diff line change
Expand Up @@ -233,8 +233,8 @@ void shake_page(struct page *p, int access)
}

/*
* Only all shrink_slab here (which would also
* shrink other caches) if access is not potentially fatal.
* Only call shrink_slab here (which would also shrink other caches) if
* access is not potentially fatal.
*/
if (access) {
int nr;
Expand Down Expand Up @@ -1065,19 +1065,22 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
* The check (unnecessarily) ignores LRU pages being isolated and
* walked by the page reclaim code, however that's not a big loss.
*/
if (!PageLRU(p) && !PageHuge(p))
shake_page(p, 0);
if (!PageLRU(p) && !PageHuge(p)) {
/*
* shake_page could have turned it free.
*/
if (is_free_buddy_page(p)) {
action_result(pfn, "free buddy, 2nd try", DELAYED);
return 0;
if (!PageHuge(p) && !PageTransCompound(p)) {
if (!PageLRU(p))
shake_page(p, 0);
if (!PageLRU(p)) {
/*
* shake_page could have turned it free.
*/
if (is_free_buddy_page(p)) {
action_result(pfn, "free buddy, 2nd try",
DELAYED);
return 0;
}
action_result(pfn, "non LRU", IGNORED);
put_page(p);
return -EBUSY;
}
action_result(pfn, "non LRU", IGNORED);
put_page(p);
return -EBUSY;
}

/*
Expand Down

0 comments on commit af241a0

Please sign in to comment.