3 files changed, 97 insertions, 29 deletions

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ad220359f1b0..0af2bb2028fd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -316,6 +316,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 						struct vm_area_struct *vma);
 
 /* linux/mm/vmscan.c */
+extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
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:
 	/*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a386454c015a..c4a2f4512fca 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -191,7 +191,7 @@ static bool sane_reclaim(struct scan_control *sc)
 }
 #endif
 
-static unsigned long zone_reclaimable_pages(struct zone *zone)
+unsigned long zone_reclaimable_pages(struct zone *zone)
 {
 	unsigned long nr;
 
@@ -2507,10 +2507,8 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
- *
- * Returns true if a zone was reclaimable.
  */
-static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
+static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
@@ -2518,7 +2516,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	unsigned long nr_soft_scanned;
 	gfp_t orig_mask;
 	enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
-	bool reclaimable = false;
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
@@ -2583,17 +2580,10 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 						&nr_soft_scanned);
 			sc->nr_reclaimed += nr_soft_reclaimed;
 			sc->nr_scanned += nr_soft_scanned;
-			if (nr_soft_reclaimed)
-				reclaimable = true;
 			/* need some check for avoid more shrink_zone() */
 		}
 
-		if (shrink_zone(zone, sc, zone_idx(zone) == classzone_idx))
-			reclaimable = true;
-
-		if (global_reclaim(sc) &&
-		    !reclaimable && zone_reclaimable(zone))
-			reclaimable = true;
+		shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
 	}
 
 	/*
@@ -2601,8 +2591,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	 * promoted it to __GFP_HIGHMEM.
 	 */
 	sc->gfp_mask = orig_mask;
-
-	return reclaimable;
 }
 
 /*
@@ -2627,7 +2615,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	int initial_priority = sc->priority;
 	unsigned long total_scanned = 0;
 	unsigned long writeback_threshold;
-	bool zones_reclaimable;
 retry:
 	delayacct_freepages_start();
 
@@ -2638,7 +2625,7 @@ retry:
 		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
 				sc->priority);
 		sc->nr_scanned = 0;
-		zones_reclaimable = shrink_zones(zonelist, sc);
+		shrink_zones(zonelist, sc);
 
 		total_scanned += sc->nr_scanned;
 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
@@ -2685,10 +2672,6 @@ retry:
 		goto retry;
 	}
 
-	/* Any of the zones still reclaimable?  Don't OOM. */
-	if (zones_reclaimable)
-		return 1;
-
 	return 0;
 }