1 files changed, 92 insertions, 8 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8bcc10616fab..fa39efc3a692 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3386,6 +3386,77 @@ static inline bool is_thp_gfp_mask(gfp_t gfp_mask)
 	return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
 }
 
+/*
+ * Maximum number of reclaim retries without any progress before OOM killer
+ * is consider as the only way to move forward.
+ */
+#define MAX_RECLAIM_RETRIES 16
+
+/*
+ * Checks whether it makes sense to retry the reclaim to make a forward progress
+ * for the given allocation request.
+ * The reclaim feedback represented by did_some_progress (any progress during
+ * the last reclaim round), pages_reclaimed (cumulative number of reclaimed
+ * pages) and no_progress_loops (number of reclaim rounds without any progress
+ * in a row) is considered as well as the reclaimable pages on the applicable
+ * zone list (with a backoff mechanism which is a function of no_progress_loops).
+ *
+ * Returns true if a retry is viable or false to enter the oom path.
+ */
+static inline bool
+should_reclaim_retry(gfp_t gfp_mask, unsigned order,
+		     struct alloc_context *ac, int alloc_flags,
+		     bool did_some_progress, unsigned long pages_reclaimed,
+		     int no_progress_loops)
+{
+	struct zone *zone;
+	struct zoneref *z;
+
+	/*
+	 * Make sure we converge to OOM if we cannot make any progress
+	 * several times in the row.
+	 */
+	if (no_progress_loops > MAX_RECLAIM_RETRIES)
+		return false;
+
+	if (order > PAGE_ALLOC_COSTLY_ORDER) {
+		if (pages_reclaimed >= (1<<order))
+			return false;
+
+		if (did_some_progress)
+			return true;
+	}
+
+	/*
+	 * Keep reclaiming pages while there is a chance this will lead somewhere.
+	 * If none of the target zones can satisfy our allocation request even
+	 * if all reclaimable pages are considered then we are screwed and have
+	 * to go OOM.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
+					ac->nodemask) {
+		unsigned long available;
+
+		available = zone_reclaimable_pages(zone);
+		available -= DIV_ROUND_UP(no_progress_loops * available,
+					  MAX_RECLAIM_RETRIES);
+		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
+		/*
+		 * Would the allocation succeed if we reclaimed the whole
+		 * available?
+		 */
+		if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
+				ac->high_zoneidx, alloc_flags, available)) {
+			/* Wait for some write requests to complete then retry */
+			wait_iff_congested(zone, BLK_RW_ASYNC, HZ/50);
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
@@ -3397,6 +3468,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	enum compact_result compact_result;
+	int no_progress_loops = 0;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3525,23 +3597,35 @@ retry:
 	if (gfp_mask & __GFP_NORETRY)
 		goto noretry;
 
-	/* Keep reclaiming pages as long as there is reasonable progress */
-	pages_reclaimed += did_some_progress;
-	if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) ||
-	    ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) {
-		/* Wait for some write requests to complete then retry */
-		wait_iff_congested(ac->preferred_zoneref->zone, BLK_RW_ASYNC, HZ/50);
-		goto retry;
+	/*
+	 * Do not retry costly high order allocations unless they are
+	 * __GFP_REPEAT
+	 */
+	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
+		goto noretry;
+
+	if (did_some_progress) {
+		no_progress_loops = 0;
+		pages_reclaimed += did_some_progress;
+	} else {
+		no_progress_loops++;
 	}
 
+	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
+				 did_some_progress > 0, pages_reclaimed,
+				 no_progress_loops))
+		goto retry;
+
 	/* Reclaim has failed us, start killing things */
 	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
 	if (page)
 		goto got_pg;
 
 	/* Retry as long as the OOM killer is making progress */
-	if (did_some_progress)
+	if (did_some_progress) {
+		no_progress_loops = 0;
 		goto retry;
+	}
 
 noretry:
 	/*