summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2014-12-10 15:43:46 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-10 17:41:06 -0800
commit7d5e324573b0ffd7098ab880c82096ca29a11f7f (patch)
tree9847999e2b1efcab0a72425adff3d5b85d2947ad /mm
parentdfe0e773d0258a4d7dfd763e1fda04aa27680b90 (diff)
downloadlinux-7d5e324573b0ffd7098ab880c82096ca29a11f7f.tar.bz2
mm: memcontrol: clarify migration where old page is uncharged
Better explain re-entrant migration when compaction races with reclaim, and also mention swapcache readahead pages as possible uncharged migration sources. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c7
1 files changed, 6 insertions, 1 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b495f29d4746..a0ae64ca55bf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6157,7 +6157,12 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
if (PageCgroupUsed(pc))
return;
- /* Re-entrant migration: old page already uncharged? */
+ /*
+ * Swapcache readahead pages can get migrated before being
+ * charged, and migration from compaction can happen to an
+ * uncharged page when the PFN walker finds a page that
+ * reclaim just put back on the LRU but has not released yet.
+ */
pc = lookup_page_cgroup(oldpage);
if (!PageCgroupUsed(pc))
return;