mm: page allocator: reconsider zones for allocation after direct reclaim

With zone_reclaim_mode enabled, it's possible for zones to be considered
full in the zonelist_cache so they are skipped in the future.  If the
process enters direct reclaim, the ZLC may still consider zones to be full
even after reclaiming pages.  Reconsider all zones for allocation if
direct reclaim returns successfully.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 830a465..0944723 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1616,6 +1616,21 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
        set_bit(i, zlc->fullzones);
 }
 
+/*
+ * clear all zones full, called after direct reclaim makes progress so that
+ * a zone that was recently full is not skipped over for up to a second
+ */
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+       struct zonelist_cache *zlc;     /* cached zonelist speedup info */
+
+       zlc = zonelist->zlcache_ptr;
+       if (!zlc)
+               return;
+
+       bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+}
+
 #else  /* CONFIG_NUMA */
 
 static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
@@ -1632,6 +1647,10 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
 static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 {
 }
+
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+}
 #endif /* CONFIG_NUMA */
 
 /*
@@ -1963,6 +1982,10 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
        if (unlikely(!(*did_some_progress)))
                return NULL;
 
+       /* After successful reclaim, reconsider all zones for allocation */
+       if (NUMA_BUILD)
+               zlc_clear_zones_full(zonelist);
+
 retry:
        page = get_page_from_freelist(gfp_mask, nodemask, order,
                                        zonelist, high_zoneidx,