Commit af241a08 authored by Jin Dongming's avatar Jin Dongming Committed by Linus Torvalds

thp: fix unsuitable behavior for hwpoisoned tail page

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: default avatarJin Dongming <jin.dongming@np.css.fujitsu.com>
Reviewed-by: default avatarHidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent a6d30ddd
...@@ -233,8 +233,8 @@ void shake_page(struct page *p, int access) ...@@ -233,8 +233,8 @@ void shake_page(struct page *p, int access)
} }
/* /*
* Only all shrink_slab here (which would also * Only call shrink_slab here (which would also shrink other caches) if
* shrink other caches) if access is not potentially fatal. * access is not potentially fatal.
*/ */
if (access) { if (access) {
int nr; int nr;
...@@ -1065,20 +1065,23 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) ...@@ -1065,20 +1065,23 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
* The check (unnecessarily) ignores LRU pages being isolated and * The check (unnecessarily) ignores LRU pages being isolated and
* walked by the page reclaim code, however that's not a big loss. * walked by the page reclaim code, however that's not a big loss.
*/ */
if (!PageLRU(p) && !PageHuge(p)) if (!PageHuge(p) && !PageTransCompound(p)) {
if (!PageLRU(p))
shake_page(p, 0); shake_page(p, 0);
if (!PageLRU(p) && !PageHuge(p)) { if (!PageLRU(p)) {
/* /*
* shake_page could have turned it free. * shake_page could have turned it free.
*/ */
if (is_free_buddy_page(p)) { if (is_free_buddy_page(p)) {
action_result(pfn, "free buddy, 2nd try", DELAYED); action_result(pfn, "free buddy, 2nd try",
DELAYED);
return 0; return 0;
} }
action_result(pfn, "non LRU", IGNORED); action_result(pfn, "non LRU", IGNORED);
put_page(p); put_page(p);
return -EBUSY; return -EBUSY;
} }
}
/* /*
* Lock the page and wait for writeback to finish. * Lock the page and wait for writeback to finish.
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment