memcg: destroy memcg caches

Implement destruction of memcg caches.  Right now, only caches where our
reference counter is the last remaining are deleted.  If there are any
other reference counters around, we just leave the caches lying around
until they go away.

When that happens, a destruction function is called from the cache code.
Caches are only destroyed in process context, so we queue them up for
later processing in the general case.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 106 insertions, 2 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2298122e71ad..79fcf0cd7186 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -453,6 +453,8 @@ void memcg_update_array_size(int num_groups);
 struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c0fcf28c15b2..869efb8d2377 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -11,6 +11,8 @@
 
 #include <linux/gfp.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
+
 
 /*
  * Flags to pass to kmem_cache_create().
@@ -179,7 +181,6 @@ void kmem_cache_free(struct kmem_cache *, void *);
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
-
 /*
  * This is the main placeholder for memcg-related information in kmem caches.
  * struct kmem_cache will hold a pointer to it, so the memory cost while
@@ -197,6 +198,10 @@ void kmem_cache_free(struct kmem_cache *, void *);
  * @memcg: pointer to the memcg this cache belongs to
  * @list: list_head for the list of all caches in this memcg
  * @root_cache: pointer to the global, root cache, this cache was derived from
+ * @dead: set to true after the memcg dies; the cache may still be around.
+ * @nr_pages: number of pages that belongs to this cache.
+ * @destroy: worker to be called whenever we are ready, or believe we may be
+ *           ready, to destroy this cache.
  */
 struct memcg_cache_params {
 	bool is_root_cache;
@@ -206,6 +211,9 @@ struct memcg_cache_params {
 			struct mem_cgroup *memcg;
 			struct list_head list;
 			struct kmem_cache *root_cache;
+			bool dead;
+			atomic_t nr_pages;
+			struct work_struct destroy;
 		};
 	};
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cc13797d0fbc..270a36789859 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2779,6 +2779,19 @@ static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
 		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
 }
 
+/*
+ * This is a bit cumbersome, but it is rarely used and avoids a backpointer
+ * in the memcg_cache_params struct.
+ */
+static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
+{
+	struct kmem_cache *cachep;
+
+	VM_BUG_ON(p->is_root_cache);
+	cachep = p->root_cache;
+	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
+}
+
 static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 {
 	struct res_counter *fail_res;
@@ -3056,6 +3069,31 @@ static inline void memcg_resume_kmem_account(void)
 	current->memcg_kmem_skip_account--;
 }
 
+static void kmem_cache_destroy_work_func(struct work_struct *w)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *p;
+
+	p = container_of(w, struct memcg_cache_params, destroy);
+
+	cachep = memcg_params_to_cache(p);
+
+	if (!atomic_read(&cachep->memcg_params->nr_pages))
+		kmem_cache_destroy(cachep);
+}
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
+{
+	if (!cachep->memcg_params->dead)
+		return;
+
+	/*
+	 * We have to defer the actual destroying to a workqueue, because
+	 * we might currently be in a context that cannot sleep.
+	 */
+	schedule_work(&cachep->memcg_params->destroy);
+}
+
 static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
 {
 	char *name;
@@ -3125,6 +3163,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 
 	mem_cgroup_get(memcg);
 	new_cachep->memcg_params->root_cache = cachep;
+	atomic_set(&new_cachep->memcg_params->nr_pages , 0);
 
 	cachep->memcg_params->memcg_caches[idx] = new_cachep;
 	/*
@@ -3143,6 +3182,25 @@ struct create_work {
 	struct work_struct work;
 };
 
+static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *params;
+
+	if (!memcg_kmem_is_active(memcg))
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
+		cachep = memcg_params_to_cache(params);
+		cachep->memcg_params->dead = true;
+		INIT_WORK(&cachep->memcg_params->destroy,
+			  kmem_cache_destroy_work_func);
+		schedule_work(&cachep->memcg_params->destroy);
+	}
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
 static void memcg_create_cache_work_func(struct work_struct *w)
 {
 	struct create_work *cw;
@@ -3358,6 +3416,10 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	VM_BUG_ON(mem_cgroup_is_root(memcg));
 	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
 }
+#else
+static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -5975,6 +6037,7 @@ static void mem_cgroup_css_offline(struct cgroup *cont)
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	mem_cgroup_reparent_charges(memcg);
+	mem_cgroup_destroy_all_caches(memcg);
 }
 
 static void mem_cgroup_css_free(struct cgroup *cont)
diff --git a/mm/slab.c b/mm/slab.c
index e265865e8700..7467343f9fe7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1895,6 +1895,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		if (page->pfmemalloc)
 			SetPageSlabPfmemalloc(page + i);
 	}
+	memcg_bind_pages(cachep, cachep->gfporder);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
 		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
@@ -1931,6 +1932,8 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 		__ClearPageSlab(page);
 		page++;
 	}
+
+	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
 	free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
diff --git a/mm/slab.h b/mm/slab.h
index c95e922b166d..43d8a38b534f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -117,6 +117,21 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 				(cachep->memcg_params->memcg == memcg);
 }
 
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+	if (!is_root_cache(s))
+		atomic_add(1 << order, &s->memcg_params->nr_pages);
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+	if (is_root_cache(s))
+		return;
+
+	if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages))
+		mem_cgroup_destroy_cache(s);
+}
+
 static inline bool slab_equal_or_root(struct kmem_cache *s,
 					struct kmem_cache *p)
 {
@@ -135,6 +150,14 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 	return true;
 }
 
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+}
+
 static inline bool slab_equal_or_root(struct kmem_cache *s,
 				      struct kmem_cache *p)
 {
diff --git a/mm/slub.c b/mm/slub.c
index ef39e872b8eb..692177bebdf0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1344,6 +1344,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	void *start;
 	void *last;
 	void *p;
+	int order;
 
 	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1352,7 +1353,9 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		goto out;
 
+	order = compound_order(page);
 	inc_slabs_node(s, page_to_nid(page), page->objects);
+	memcg_bind_pages(s, order);
 	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page->pfmemalloc)
@@ -1361,7 +1364,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	start = page_address(page);
 
 	if (unlikely(s->flags & SLAB_POISON))
-		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
+		memset(start, POISON_INUSE, PAGE_SIZE << order);
 
 	last = start;
 	for_each_object(p, s, start, page->objects) {
@@ -1402,6 +1405,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	__ClearPageSlabPfmemalloc(page);
 	__ClearPageSlab(page);
+
+	memcg_release_pages(s, order);
 	reset_page_mapcount(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;