summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorVlastimil Babka <vbabka@suse.cz>2014-04-07 15:37:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-04-07 16:35:57 -0700
commit57e68e9cd65b4b8eb4045a1e0d0746458502554c (patch)
tree2c375533eed1c0f0d1e4c45a9ba99fcabfdfdc23
parent3a025760fc158b3726eac89ee95d7f29599e9dfa (diff)
downloadlinux-57e68e9cd65b4b8eb4045a1e0d0746458502554c.tar.bz2
mm: try_to_unmap_cluster() should lock_page() before mlocking
A BUG_ON(!PageLocked) was triggered in mlock_vma_page() by Sasha Levin fuzzing with trinity. The call site try_to_unmap_cluster() does not lock the pages other than its check_page parameter (which is already locked). The BUG_ON in mlock_vma_page() is not documented and its purpose is somewhat unclear, but apparently it serializes against page migration, which could otherwise fail to transfer the PG_mlocked flag. This would not be fatal, as the page would be eventually encountered again, but NR_MLOCK accounting would become distorted nevertheless. This patch adds a comment to the BUG_ON in mlock_vma_page() and munlock_vma_page() to that effect. The call site try_to_unmap_cluster() is fixed so that for page != check_page, trylock_page() is attempted (to avoid possible deadlocks as we already have check_page locked) and mlock_vma_page() is performed only upon success. If the page lock cannot be obtained, the page is left without PG_mlocked, which is again not a problem in the whole unevictable memory design. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Bob Liu <bob.liu@oracle.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Michel Lespinasse <walken@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/mlock.c2
-rw-r--r--mm/rmap.c14
2 files changed, 14 insertions, 2 deletions
diff --git a/mm/mlock.c b/mm/mlock.c
index 4e1a68162285..b1eb53634005 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page)
*/
void mlock_vma_page(struct page *page)
{
+ /* Serialize with page migration */
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page)) {
@@ -174,6 +175,7 @@ unsigned int munlock_vma_page(struct page *page)
unsigned int nr_pages;
struct zone *zone = page_zone(page);
+ /* For try_to_munlock() and to serialize with page migration */
BUG_ON(!PageLocked(page));
/*
diff --git a/mm/rmap.c b/mm/rmap.c
index 11cf322f8133..9c3e77396d1a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1332,9 +1332,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
BUG_ON(!page || PageAnon(page));
if (locked_vma) {
- mlock_vma_page(page); /* no-op if already mlocked */
- if (page == check_page)
+ if (page == check_page) {
+ /* we know we have check_page locked */
+ mlock_vma_page(page);
ret = SWAP_MLOCK;
+ } else if (trylock_page(page)) {
+ /*
+ * If we can lock the page, perform mlock.
+ * Otherwise leave the page alone, it will be
+ * eventually encountered again later.
+ */
+ mlock_vma_page(page);
+ unlock_page(page);
+ }
continue; /* don't unmap */
}