summaryrefslogtreecommitdiffstats
path: root/mm/mlock.c
diff options
context:
space:
mode:
authorVlastimil Babka <vbabka@suse.cz>2014-01-02 12:58:44 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-01-02 14:40:30 -0800
commit3b25df93c6e37e323b86a2a8c1e00c0a2821c6c9 (patch)
tree69737469efd0313ffa2b3fcbb93daf04c72a5dc6 /mm/mlock.c
parentc424be1cbbf852e46acc84d73162af3066cd2c86 (diff)
mm: munlock: fix deadlock in __munlock_pagevec()
Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec" introduced __munlock_pagevec() to speed up munlock by holding lru_lock over multiple isolated pages. Pages that fail to be isolated are put_page()d immediately, also within the lock. This can lead to deadlock when __munlock_pagevec() becomes the holder of the last page pin and put_page() leads to __page_cache_release() which also locks lru_lock. The deadlock has been observed by Sasha Levin using trinity. This patch avoids the deadlock by deferring put_page() operations until lru_lock is released. Another pagevec (which is also used by later phases of the function is reused to gather the pages for put_page() operation. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.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/mlock.c')
-rw-r--r--mm/mlock.c15
1 files changed, 10 insertions, 5 deletions
diff --git a/mm/mlock.c b/mm/mlock.c
index c59c420fd6e..192e6eebe4f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -298,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
int i;
int nr = pagevec_count(pvec);
- int delta_munlocked = -nr;
+ int delta_munlocked;
struct pagevec pvec_putback;
int pgrescued = 0;
+ pagevec_init(&pvec_putback, 0);
+
/* Phase 1: page isolation */
spin_lock_irq(&zone->lru_lock);
for (i = 0; i < nr; i++) {
@@ -330,18 +332,21 @@ skip_munlock:
/*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
- * pin.
+ * pin. We cannot do it under lru_lock however. If it's
+ * the last pin, __page_cache_release would deadlock.
*/
+ pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
- put_page(page);
- delta_munlocked++;
}
}
+ delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
spin_unlock_irq(&zone->lru_lock);
+ /* Now we can release pins of pages that we are not munlocking */
+ pagevec_release(&pvec_putback);
+
/* Phase 2: page munlock */
- pagevec_init(&pvec_putback, 0);
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];