vmscan: check all_unreclaimable in direct reclaim path

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 bisected
the regression to

  commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c
  Author: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
  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 that vmscan don't care enough OOM
case when oom_killer_disabled.

The problem sequence is following as.

1. hibernation
2. oom_disable
3. alloc_pages
4. do_try_to_free_pages
       if (scanning_global_lru(sc) && !all_unreclaimable)
               return 1;

If kswapd is not freozen, it would set zone->all_unreclaimable to 1 and
then shrink_zones maybe return true(ie, all_unreclaimable is true).  So at
last, alloc_pages could go to _nopage_.  If it is, it should have no
problem.

This patch adds all_unreclaimable check to protect in direct reclaim path,
too.  It can care of hibernation OOM case and help bailout
all_unreclaimable case slightly.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Reported-by: M. Vefa Bicakci <bicave@superonline.com>
Reported-by: <caiqian@redhat.com>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: <caiqian@redhat.com>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c391c32..c5dfabf 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1804,12 +1804,11 @@ 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) {
@@ -1827,8 +1826,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
                }
 
                shrink_zone(priority, zone, sc);
-               all_unreclaimable = false;
        }
+}
+
+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.
+ */
+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) {
+               if (!populated_zone(zone))
+                       continue;
+               if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+                       continue;
+               if (zone_reclaimable(zone)) {
+                       all_unreclaimable = false;
+                       break;
+               }
+       }
+
        return all_unreclaimable;
 }
 
@@ -1852,7 +1881,6 @@ 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;
@@ -1869,7 +1897,7 @@ 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
@@ -1931,7 +1959,7 @@ 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 (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
                return 1;
 
        return 0;
@@ -2197,8 +2225,7 @@ loop_again:
                        total_scanned += sc.nr_scanned;
                        if (zone->all_unreclaimable)
                                continue;
-                       if (nr_slab == 0 &&
-                           zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+                       if (nr_slab == 0 && !zone_reclaimable(zone))
                                zone->all_unreclaimable = 1;
                        /*
                         * If we've done a decent amount of scanning and