1 files changed, 51 insertions, 10 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8b920ce3ae02..03822f86f288 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -303,7 +303,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
 /*
  * Add a shrinker callback to be called from the vm.
  */
-int register_shrinker(struct shrinker *shrinker)
+int prealloc_shrinker(struct shrinker *shrinker)
 {
 	size_t size = sizeof(*shrinker->nr_deferred);
 
@@ -313,10 +313,29 @@ int register_shrinker(struct shrinker *shrinker)
 	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
+	return 0;
+}
+
+void free_prealloced_shrinker(struct shrinker *shrinker)
+{
+	kfree(shrinker->nr_deferred);
+	shrinker->nr_deferred = NULL;
+}
 
+void register_shrinker_prepared(struct shrinker *shrinker)
+{
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
 	up_write(&shrinker_rwsem);
+}
+
+int register_shrinker(struct shrinker *shrinker)
+{
+	int err = prealloc_shrinker(shrinker);
+
+	if (err)
+		return err;
+	register_shrinker_prepared(shrinker);
 	return 0;
 }
 EXPORT_SYMBOL(register_shrinker);
@@ -1399,7 +1418,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 				return ret;
 
 			mapping = page_mapping(page);
-			migrate_dirty = mapping && mapping->a_ops->migratepage;
+			migrate_dirty = !mapping || mapping->a_ops->migratepage;
 			unlock_page(page);
 			if (!migrate_dirty)
 				return ret;
@@ -2525,12 +2544,28 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			unsigned long reclaimed;
 			unsigned long scanned;
 
-			if (mem_cgroup_low(root, memcg)) {
+			switch (mem_cgroup_protected(root, memcg)) {
+			case MEMCG_PROT_MIN:
+				/*
+				 * Hard protection.
+				 * If there is no reclaimable memory, OOM.
+				 */
+				continue;
+			case MEMCG_PROT_LOW:
+				/*
+				 * Soft protection.
+				 * Respect the protection only as long as
+				 * there is an unprotected supply
+				 * of reclaimable memory from other cgroups.
+				 */
 				if (!sc->memcg_low_reclaim) {
 					sc->memcg_low_skipped = 1;
 					continue;
 				}
 				memcg_memory_event(memcg, MEMCG_LOW);
+				break;
+			case MEMCG_PROT_NONE:
+				break;
 			}
 
 			reclaimed = sc->nr_reclaimed;
@@ -3299,11 +3334,15 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		.may_unmap = 1,
 		.may_swap = 1,
 	};
+
+	__fs_reclaim_acquire();
+
 	count_vm_event(PAGEOUTRUN);
 
 	do {
 		unsigned long nr_reclaimed = sc.nr_reclaimed;
 		bool raise_priority = true;
+		bool ret;
 
 		sc.reclaim_idx = classzone_idx;
 
@@ -3376,7 +3415,10 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 			wake_up_all(&pgdat->pfmemalloc_wait);
 
 		/* Check if kswapd should be suspending */
-		if (try_to_freeze() || kthread_should_stop())
+		__fs_reclaim_release();
+		ret = try_to_freeze();
+		__fs_reclaim_acquire();
+		if (ret || kthread_should_stop())
 			break;
 
 		/*
@@ -3393,6 +3435,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 
 out:
 	snapshot_refaults(NULL, pgdat);
+	__fs_reclaim_release();
 	/*
 	 * Return the order kswapd stopped reclaiming at as
 	 * prepare_kswapd_sleep() takes it into account. If another caller
@@ -3581,9 +3624,7 @@ kswapd_try_sleep:
 		 */
 		trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
 						alloc_order);
-		fs_reclaim_acquire(GFP_KERNEL);
 		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
-		fs_reclaim_release(GFP_KERNEL);
 		if (reclaim_order < alloc_order)
 			goto kswapd_try_sleep;
 	}
@@ -3665,16 +3706,16 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
 
-	noreclaim_flag = memalloc_noreclaim_save();
 	fs_reclaim_acquire(sc.gfp_mask);
+	noreclaim_flag = memalloc_noreclaim_save();
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	p->reclaim_state = NULL;
-	fs_reclaim_release(sc.gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
+	fs_reclaim_release(sc.gfp_mask);
 
 	return nr_reclaimed;
 }
@@ -3851,6 +3892,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	};
 
 	cond_resched();
+	fs_reclaim_acquire(sc.gfp_mask);
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
 	 * and we also need to be able to write out pages for RECLAIM_WRITE
@@ -3858,7 +3900,6 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 */
 	noreclaim_flag = memalloc_noreclaim_save();
 	p->flags |= PF_SWAPWRITE;
-	fs_reclaim_acquire(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
@@ -3873,9 +3914,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	}
 
 	p->reclaim_state = NULL;
-	fs_reclaim_release(gfp_mask);
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
+	fs_reclaim_release(sc.gfp_mask);
 	return sc.nr_reclaimed >= nr_pages;
 }