diff --git a/mm/vmscan.c b/mm/vmscan.c
index fe0d5c4..799ebce 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -155,14 +155,31 @@
 }
 
 /*
- * Add a shrinker callback to be called from the vm
+ * Add a shrinker callback to be called from the vm.
  */
-void register_shrinker(struct shrinker *shrinker)
+int register_shrinker(struct shrinker *shrinker)
 {
-	atomic_long_set(&shrinker->nr_in_batch, 0);
+	size_t size = sizeof(*shrinker->nr_deferred);
+
+	/*
+	 * If we only have one possible node in the system anyway, save
+	 * ourselves the trouble and disable NUMA aware behavior. This way we
+	 * will save memory and some small loop time later.
+	 */
+	if (nr_node_ids == 1)
+		shrinker->flags &= ~SHRINKER_NUMA_AWARE;
+
+	if (shrinker->flags & SHRINKER_NUMA_AWARE)
+		size *= nr_node_ids;
+
+	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
+	if (!shrinker->nr_deferred)
+		return -ENOMEM;
+
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
 	up_write(&shrinker_rwsem);
+	return 0;
 }
 EXPORT_SYMBOL(register_shrinker);
 
@@ -186,6 +203,118 @@
 }
 
 #define SHRINK_BATCH 128
+
+static unsigned long
+shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
+		 unsigned long nr_pages_scanned, unsigned long lru_pages)
+{
+	unsigned long freed = 0;
+	unsigned long long delta;
+	long total_scan;
+	long max_pass;
+	long nr;
+	long new_nr;
+	int nid = shrinkctl->nid;
+	long batch_size = shrinker->batch ? shrinker->batch
+					  : SHRINK_BATCH;
+
+	if (shrinker->count_objects)
+		max_pass = shrinker->count_objects(shrinker, shrinkctl);
+	else
+		max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0);
+	if (max_pass == 0)
+		return 0;
+
+	/*
+	 * 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.
+	 */
+	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+
+	total_scan = nr;
+	delta = (4 * nr_pages_scanned) / shrinker->seeks;
+	delta *= max_pass;
+	do_div(delta, lru_pages + 1);
+	total_scan += delta;
+	if (total_scan < 0) {
+		printk(KERN_ERR
+		"shrink_slab: %pF negative objects to delete nr=%ld\n",
+		       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 (total_scan > max_pass * 2)
+		total_scan = max_pass * 2;
+
+	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
+				nr_pages_scanned, lru_pages,
+				max_pass, delta, total_scan);
+
+	while (total_scan >= batch_size) {
+
+		if (shrinker->scan_objects) {
+			unsigned long ret;
+			shrinkctl->nr_to_scan = batch_size;
+			ret = shrinker->scan_objects(shrinker, shrinkctl);
+
+			if (ret == SHRINK_STOP)
+				break;
+			freed += ret;
+		} else {
+			int nr_before;
+			long ret;
+
+			nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0);
+			ret = do_shrinker_shrink(shrinker, shrinkctl,
+							batch_size);
+			if (ret == -1)
+				break;
+			if (ret < nr_before)
+				freed += nr_before - ret;
+		}
+
+		count_vm_events(SLABS_SCANNED, batch_size);
+		total_scan -= batch_size;
+
+		cond_resched();
+	}
+
+	/*
+	 * 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.
+	 */
+	if (total_scan > 0)
+		new_nr = atomic_long_add_return(total_scan,
+						&shrinker->nr_deferred[nid]);
+	else
+		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
+
+	trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+	return freed;
+}
+
 /*
  * Call the shrink functions to age shrinkable caches
  *
@@ -227,108 +356,18 @@
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		unsigned long long delta;
-		long total_scan;
-		long max_pass;
-		long nr;
-		long new_nr;
-		long batch_size = shrinker->batch ? shrinker->batch
-						  : SHRINK_BATCH;
+		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+			if (!node_online(shrinkctl->nid))
+				continue;
 
-		if (shrinker->count_objects)
-			max_pass = shrinker->count_objects(shrinker, shrinkctl);
-		else
-			max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0);
-		if (max_pass == 0)
-			continue;
+			if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
+			    (shrinkctl->nid != 0))
+				break;
 
-		/*
-		 * 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.
-		 */
-		nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
+			freed += shrink_slab_node(shrinkctl, shrinker,
+				 nr_pages_scanned, lru_pages);
 
-		total_scan = nr;
-		delta = (4 * nr_pages_scanned) / shrinker->seeks;
-		delta *= max_pass;
-		do_div(delta, lru_pages + 1);
-		total_scan += delta;
-		if (total_scan < 0) {
-			printk(KERN_ERR
-			"shrink_slab: %pF negative objects to delete nr=%ld\n",
-			       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 (total_scan > max_pass * 2)
-			total_scan = max_pass * 2;
-
-		trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
-					nr_pages_scanned, lru_pages,
-					max_pass, delta, total_scan);
-
-		while (total_scan >= batch_size) {
-
-			if (shrinker->scan_objects) {
-				unsigned long ret;
-				shrinkctl->nr_to_scan = batch_size;
-				ret = shrinker->scan_objects(shrinker, shrinkctl);
-
-				if (ret == SHRINK_STOP)
-					break;
-				freed += ret;
-			} else {
-				int nr_before;
-				long ret;
-
-				nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0);
-				ret = do_shrinker_shrink(shrinker, shrinkctl,
-								batch_size);
-				if (ret == -1)
-					break;
-				if (ret < nr_before)
-					freed += nr_before - ret;
-			}
-
-			count_vm_events(SLABS_SCANNED, batch_size);
-			total_scan -= batch_size;
-
-			cond_resched();
-		}
-
-		/*
-		 * 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.
-		 */
-		if (total_scan > 0)
-			new_nr = atomic_long_add_return(total_scan,
-					&shrinker->nr_in_batch);
-		else
-			new_nr = atomic_long_read(&shrinker->nr_in_batch);
-
-		trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out: