1 files changed, 108 insertions, 52 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ff834e19c24..febbc044e792 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -250,49 +250,90 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 		unsigned long long delta;
 		unsigned long total_scan;
 		unsigned long max_pass;
+		int shrink_ret = 0;
+		long nr;
+		long new_nr;
+		long batch_size = shrinker->batch ? shrinker->batch
+						  : SHRINK_BATCH;
 
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
+		 * We need to avoid excessive windup on filesystem shrinkers
+		 * due to large numbers of GFP_NOFS allocations causing the
+		 * shrinkers to return -1 all the time. This results in a large
+		 * nr being built up so when a shrink that can do some work
+		 * comes along it empties the entire cache due to nr >>>
+		 * max_pass.  This is bad for sustaining a working set in
+		 * memory.
+		 *
+		 * Hence only allow the shrinker to scan the entire cache when
+		 * a large delta change is calculated directly.
+		 */
+		if (delta < max_pass / 4)
+			total_scan = min(total_scan, max_pass / 2);
+
+		/*
 		 * Avoid risking looping forever due to too large nr value:
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
+					nr_pages_scanned, lru_pages,
+					max_pass, delta, total_scan);
 
-		while (total_scan >= SHRINK_BATCH) {
-			long this_scan = SHRINK_BATCH;
-			int shrink_ret;
+		while (total_scan >= batch_size) {
 			int nr_before;
 
 			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
 			shrink_ret = do_shrinker_shrink(shrinker, shrink,
-							this_scan);
+							batch_size);
 			if (shrink_ret == -1)
 				break;
 			if (shrink_ret < nr_before)
 				ret += nr_before - shrink_ret;
-			count_vm_events(SLABS_SCANNED, this_scan);
-			total_scan -= this_scan;
+			count_vm_events(SLABS_SCANNED, batch_size);
+			total_scan -= batch_size;
 
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out:
@@ -1995,14 +2036,13 @@ restart:
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long 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;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
-	unsigned long total_scanned = 0;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2017,19 +2057,23 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
+			/* need some check for avoid more shrink_zone() */
 		}
 
-		nr_soft_scanned = 0;
-		nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-							sc->order, sc->gfp_mask,
-							&nr_soft_scanned);
-		sc->nr_reclaimed += nr_soft_reclaimed;
-		total_scanned += nr_soft_scanned;
-
 		shrink_zone(priority, zone, sc);
 	}
-
-	return total_scanned;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2094,7 +2138,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token(sc->mem_cgroup);
-		total_scanned += shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2307,7 +2351,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
 	for (i = 0; i <= classzone_idx; i++)
 		present_pages += pgdat->node_zones[i].present_pages;
 
-	return balanced_pages > (present_pages >> 2);
+	/* A special case here: if zone has no page, we think it's balanced */
+	return balanced_pages >= (present_pages >> 2);
 }
 
 /* is kswapd sleeping prematurely? */
@@ -2323,7 +2368,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 		return true;
 
 	/* Check the watermark levels */
-	for (i = 0; i < pgdat->nr_zones; i++) {
+	for (i = 0; i <= classzone_idx; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
 		if (!populated_zone(zone))
@@ -2341,7 +2386,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 		}
 
 		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
-							classzone_idx, 0))
+							i, 0))
 			all_zones_ok = false;
 		else
 			balanced += zone->present_pages;
@@ -2448,7 +2493,6 @@ loop_again:
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
-				*classzone_idx = i;
 				break;
 			}
 		}
@@ -2507,18 +2551,18 @@ loop_again:
 				KSWAPD_ZONE_BALANCE_GAP_RATIO);
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone) + balance_gap,
-					end_zone, 0))
+					end_zone, 0)) {
 				shrink_zone(priority, zone, &sc);
-			reclaim_state->reclaimed_slab = 0;
-			nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-			total_scanned += sc.nr_scanned;
 
-			if (zone->all_unreclaimable)
-				continue;
-			if (nr_slab == 0 &&
-			    !zone_reclaimable(zone))
-				zone->all_unreclaimable = 1;
+				reclaim_state->reclaimed_slab = 0;
+				nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
+				sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+				total_scanned += sc.nr_scanned;
+
+				if (nr_slab == 0 && !zone_reclaimable(zone))
+					zone->all_unreclaimable = 1;
+			}
+
 			/*
 			 * If we've done a decent amount of scanning and
 			 * the reclaim ratio is low, start doing writepage
@@ -2528,6 +2572,12 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
+			if (zone->all_unreclaimable) {
+				if (end_zone && end_zone == i)
+					end_zone--;
+				continue;
+			}
+
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
@@ -2706,8 +2756,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
  */
 static int kswapd(void *p)
 {
-	unsigned long order;
-	int classzone_idx;
+	unsigned long order, new_order;
+	int classzone_idx, new_classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2737,17 +2787,23 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	order = 0;
-	classzone_idx = MAX_NR_ZONES - 1;
+	order = new_order = 0;
+	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
 	for ( ; ; ) {
-		unsigned long new_order;
-		int new_classzone_idx;
 		int ret;
 
-		new_order = pgdat->kswapd_max_order;
-		new_classzone_idx = pgdat->classzone_idx;
-		pgdat->kswapd_max_order = 0;
-		pgdat->classzone_idx = MAX_NR_ZONES - 1;
+		/*
+		 * If the last balance_pgdat was unsuccessful it's unlikely a
+		 * new request of a similar or harder type will succeed soon
+		 * so consider going to sleep on the basis we reclaimed at
+		 */
+		if (classzone_idx >= new_classzone_idx && order == new_order) {
+			new_order = pgdat->kswapd_max_order;
+			new_classzone_idx = pgdat->classzone_idx;
+			pgdat->kswapd_max_order =  0;
+			pgdat->classzone_idx = pgdat->nr_zones - 1;
+		}
+
 		if (order < new_order || classzone_idx > new_classzone_idx) {
 			/*
 			 * Don't sleep if someone wants a larger 'order'
@@ -2760,7 +2816,7 @@ static int kswapd(void *p)
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
 			pgdat->kswapd_max_order = 0;
-			pgdat->classzone_idx = MAX_NR_ZONES - 1;
+			pgdat->classzone_idx = pgdat->nr_zones - 1;
 		}
 
 		ret = try_to_freeze();