summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>2011-04-14 15:22:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-04-14 16:06:56 -0700
commit929bea7c714220fc76ce3f75bef9056477c28e74 (patch)
treed41b4592b658173e00c7b8bad2bce048f02e0ead /mm
parentfe936dfc23fed3475b11067e8d9b70553eafcd9e (diff)
downloadlinux-929bea7c714220fc76ce3f75bef9056477c28e74.tar.gz
linux-929bea7c714220fc76ce3f75bef9056477c28e74.tar.bz2
linux-929bea7c714220fc76ce3f75bef9056477c28e74.zip
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name
all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> 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/vmscan.c24
1 files changed, 13 insertions, 11 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c7f5a6d4b75b..f6b435c80079 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -41,6 +41,7 @@
#include <linux/memcontrol.h>
#include <linux/delayacct.h>
#include <linux/sysctl.h>
+#include <linux/oom.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -1988,17 +1989,12 @@ static bool zone_reclaimable(struct zone *zone)
return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
}
-/*
- * As hibernation is going on, kswapd is freezed so that it can't mark
- * the zone into all_unreclaimable. It can't handle OOM during hibernation.
- * So let's check zone's unreclaimable in direct reclaim as well as kswapd.
- */
+/* All zones in zonelist are unreclaimable? */
static bool all_unreclaimable(struct zonelist *zonelist,
struct scan_control *sc)
{
struct zoneref *z;
struct zone *zone;
- bool all_unreclaimable = true;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2006,13 +2002,11 @@ static bool all_unreclaimable(struct zonelist *zonelist,
continue;
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- if (zone_reclaimable(zone)) {
- all_unreclaimable = false;
- break;
- }
+ if (!zone->all_unreclaimable)
+ return false;
}
- return all_unreclaimable;
+ return true;
}
/*
@@ -2108,6 +2102,14 @@ out:
if (sc->nr_reclaimed)
return sc->nr_reclaimed;
+ /*
+ * As hibernation is going on, kswapd is freezed so that it can't mark
+ * the zone into all_unreclaimable. Thus bypassing all_unreclaimable
+ * check.
+ */
+ if (oom_killer_disabled)
+ return 0;
+
/* top priority shrink_zones still had more to do? don't OOM, then */
if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
return 1;