mm: make unreserve highatomic functions reliable

Currently, unreserve_highatomic_pageblock bails out if it found
highatomic pageblock regardless of really moving free pages from the one
so that it could mitigate unreserve logic's goal which saves OOM of a
process.

This patch makes unreserve functions bail out only if it moves some
pages out of !highatomic free list to avoid such false positive.

Another potential problem is that by race between page freeing and
reserve highatomic function, pages could be in highatomic free list even
though the pageblock is !high atomic migratetype.  In that case,
unreserve_highatomic_pageblock can be void if count of highatomic
reserve is less than pageblock_nr_pages.  We could solve it simply via
draining all of reserved pages before the OOM.  It would have a
safeguard role to exhuast reserved pages before converging to OOM.

Link: http://lkml.kernel.org/r/1476259429-18279-5-git-send-email-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Sangseok Lee <sangseok.lee@lge.com>
Cc: Michal Hocko <mhocko@suse.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 085de0442dd44b297206414bccfb57876c608b0e..2b69e28706b18642036fcb173d855f9e6764c865 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2058,8 +2058,12 @@ out_unlock:
  * potentially hurts the reliability of high-order allocations when under
  * intense memory pressure but failed atomic allocations should be easier
  * to recover from than an OOM.
+ *
+ * If @force is true, try to unreserve a pageblock even though highatomic
+ * pageblock is exhausted.
  */
-static bool unreserve_highatomic_pageblock(const struct alloc_context *ac)
+static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
+                                               bool force)
 {
        struct zonelist *zonelist = ac->zonelist;
        unsigned long flags;
@@ -2071,8 +2075,12 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac)
 
        for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
                                                                ac->nodemask) {
-               /* Preserve at least one pageblock */
-               if (zone->nr_reserved_highatomic <= pageblock_nr_pages)
+               /*
+                * Preserve at least one pageblock unless memory pressure
+                * is really high.
+                */
+               if (!force && zone->nr_reserved_highatomic <=
+                                       pageblock_nr_pages)
                        continue;
 
                spin_lock_irqsave(&zone->lock, flags);
@@ -2117,8 +2125,10 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac)
                         */
                        set_pageblock_migratetype(page, ac->migratetype);
                        ret = move_freepages_block(zone, page, ac->migratetype);
-                       spin_unlock_irqrestore(&zone->lock, flags);
-                       return ret;
+                       if (ret) {
+                               spin_unlock_irqrestore(&zone->lock, flags);
+                               return ret;
+                       }
                }
                spin_unlock_irqrestore(&zone->lock, flags);
        }
@@ -3322,7 +3332,7 @@ retry:
         * Shrink them them and try again
         */
        if (!page && !drained) {
-               unreserve_highatomic_pageblock(ac);
+               unreserve_highatomic_pageblock(ac, false);
                drain_all_pages(NULL);
                drained = true;
                goto retry;
@@ -3441,7 +3451,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
         */
        if (*no_progress_loops > MAX_RECLAIM_RETRIES) {
                /* Before OOM, exhaust highatomic_reserve */
-               return unreserve_highatomic_pageblock(ac);
+               return unreserve_highatomic_pageblock(ac, true);
        }
 
        /*