[PATCH] vmscan: don't use return value trick when oom_killer_disabled

[Minchan Kim]

M. Vefa Bicakci reported 2.6.35 kernel hang up when hibernation on his
32bit 3GB mem machine. (https://bugzilla.kernel.org/show_bug.cgi?id=16771)
Also he was bisected first bad commit is below

  commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c
  Author: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
  Date:   Fri Jun 4 14:15:05 2010 -0700

     vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure

At first impression, this seemed very strange because the above commit only
chenged function return value and hibernate_preallocate_memory() ignore
return value of shrink_all_memory(). But it's related.

Now, page allocation from hibernation code may enter infinite loop if
the system has highmem.

The reasons are two. 1) hibernate_preallocate_memory() call
alloc_pages() wrong order 2) vmscan don't care enough OOM case when
oom_killer_disabled.

This patch only fix (2). Why is oom_killer_disabled so special?
because when hibernation case, zone->all_unreclaimable never be turned on.
hibernation freeze all tasks at first, then kswapd can't works in this
case, and zone->all_unreclaimable is only turned from kswapd.

Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rjw@xxxxxxx>
Cc: M. Vefa Bicakci <bicave@xxxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxx
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: Minchan Kim <minchan.kim@xxxxxxxxx>
---
 mm/vmscan.c |   33 +++++++++++++++++++++++++++------
 1 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f620ab3..53b23a7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1893,12 +1893,11 @@ static void shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static bool shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, 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) {
@@ -1916,8 +1915,31 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 		}
 
 		shrink_zone(priority, zone, sc);
-		all_unreclaimable = false;
 	}
+}
+
+static inline bool all_unreclaimable(struct zonelist *zonelist,
+		struct scan_control *sc)
+{
+	struct zoneref *z;
+	struct zone *zone;
+	bool all_unreclaimable = true;
+
+	if (!scanning_global_lru(sc))
+		return false;
+
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+			gfp_zone(sc->gfp_mask), sc->nodemask) {
+		if (!populated_zone(zone))
+			continue;
+		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			continue;
+		if (zone->pages_scanned < (zone_reclaimable_pages(zone) * 6)) {
+			all_unreclaimable = false;
+			break;
+		}
+	}
+
 	return all_unreclaimable;
 }
 
@@ -1941,7 +1963,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	int priority;
-	bool all_unreclaimable;
 	unsigned long total_scanned = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct zoneref *z;
@@ -1958,7 +1979,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		all_unreclaimable = shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2020,7 +2041,7 @@ out:
 		return sc->nr_reclaimed;
 
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (scanning_global_lru(sc) && !all_unreclaimable)
+	if (!all_unreclaimable(zonelist, sc))
 		return 1;
 
 	return 0;
-- 
1.7.0.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/