| From 8e8836abf74a0b227c651cf76466b8d711470a76 Mon Sep 17 00:00:00 2001 |
| From: Vlastimil Babka <vbabka@suse.cz> |
| Date: Mon, 7 Apr 2014 15:37:50 -0700 |
| Subject: mm: try_to_unmap_cluster() should lock_page() before mlocking |
| |
| From: Vlastimil Babka <vbabka@suse.cz> |
| |
| commit 57e68e9cd65b4b8eb4045a1e0d0746458502554c upstream. |
| |
| 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> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| [bwh: Backported to 3.2: adjust context] |
| Signed-off-by: Ben Hutchings <ben@decadent.org.uk> |
| Cc: Yijing Wang <wangyijing@huawei.com> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| mm/mlock.c | 2 ++ |
| mm/rmap.c | 14 ++++++++++++-- |
| 2 files changed, 14 insertions(+), 2 deletions(-) |
| |
| --- a/mm/mlock.c |
| +++ b/mm/mlock.c |
| @@ -78,6 +78,7 @@ void __clear_page_mlock(struct page *pag |
| */ |
| void mlock_vma_page(struct page *page) |
| { |
| + /* Serialize with page migration */ |
| BUG_ON(!PageLocked(page)); |
| |
| if (!TestSetPageMlocked(page)) { |
| @@ -105,6 +106,7 @@ void mlock_vma_page(struct page *page) |
| */ |
| void munlock_vma_page(struct page *page) |
| { |
| + /* For try_to_munlock() and to serialize with page migration */ |
| BUG_ON(!PageLocked(page)); |
| |
| if (TestClearPageMlocked(page)) { |
| --- a/mm/rmap.c |
| +++ b/mm/rmap.c |
| @@ -1449,9 +1449,19 @@ static int try_to_unmap_cluster(unsigned |
| 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 */ |
| } |
| |