5 files changed, 43 insertions, 11 deletions

diff --git a/mm/slab.c b/mm/slab.c
index 7894017bc16..c4b89eaf4c9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2382,7 +2382,7 @@ out:
 	return nr_freed;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *cachep)
+int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 {
 	int ret = 0;
 	int node;
@@ -2404,7 +2404,7 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep);
+	int rc = __kmem_cache_shrink(cachep, false);
 
 	if (rc)
 		return rc;
diff --git a/mm/slab.h b/mm/slab.h
index 0a56d76ac0e..4c3ac12dd64 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -138,7 +138,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
-int __kmem_cache_shrink(struct kmem_cache *);
+int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0873bcc61c7..1a1cc89acaa 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -549,10 +549,13 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 {
 	int idx;
 	struct memcg_cache_array *arr;
-	struct kmem_cache *s;
+	struct kmem_cache *s, *c;
 
 	idx = memcg_cache_id(memcg);
 
+	get_online_cpus();
+	get_online_mems();
+
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
 		if (!is_root_cache(s))
@@ -560,9 +563,17 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 
 		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
 						lockdep_is_held(&slab_mutex));
+		c = arr->entries[idx];
+		if (!c)
+			continue;
+
+		__kmem_cache_shrink(c, true);
 		arr->entries[idx] = NULL;
 	}
 	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
 }
 
 void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
@@ -649,7 +660,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 
 	get_online_cpus();
 	get_online_mems();
-	ret = __kmem_cache_shrink(cachep);
+	ret = __kmem_cache_shrink(cachep, false);
 	put_online_mems();
 	put_online_cpus();
 	return ret;
diff --git a/mm/slob.c b/mm/slob.c
index 96a86206a26..94a7fede6d4 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -618,7 +618,7 @@ int __kmem_cache_shutdown(struct kmem_cache *c)
 	return 0;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *d)
+int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 7fa27aee9b6..06cdb1829dc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2007,6 +2007,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 	int pages;
 	int pobjects;
 
+	preempt_disable();
 	do {
 		pages = 0;
 		pobjects = 0;
@@ -2040,6 +2041,14 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
 								!= oldpage);
+	if (unlikely(!s->cpu_partial)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
+		local_irq_restore(flags);
+	}
+	preempt_enable();
 #endif
 }
 
@@ -3369,7 +3378,7 @@ EXPORT_SYMBOL(kfree);
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
 {
 	int node;
 	int i;
@@ -3381,11 +3390,23 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	unsigned long flags;
 	int ret = 0;
 
+	if (deactivate) {
+		/*
+		 * Disable empty slabs caching. Used to avoid pinning offline
+		 * memory cgroups by kmem pages that can be freed.
+		 */
+		s->cpu_partial = 0;
+		s->min_partial = 0;
+
+		/*
+		 * s->cpu_partial is checked locklessly (see put_cpu_partial),
+		 * so we have to make sure the change is visible.
+		 */
+		kick_all_cpus_sync();
+	}
+
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
-		if (!n->nr_partial)
-			continue;
-
 		INIT_LIST_HEAD(&discard);
 		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
 			INIT_LIST_HEAD(promote + i);
@@ -3440,7 +3461,7 @@ static int slab_mem_going_offline_callback(void *arg)
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+		__kmem_cache_shrink(s, false);
 	mutex_unlock(&slab_mutex);
 
 	return 0;