1 files changed, 58 insertions, 16 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5ed24b94c5e..febbc044e79 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:
@@ -2310,7 +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? */