sl[au]b: charge slabs to kmemcg explicitly

We have only a few places where we actually want to charge kmem so
instead of intruding into the general page allocation path with
__GFP_KMEMCG it's better to explictly charge kmem there.  All kmem
charges will be easier to follow that way.

This is a step towards removing __GFP_KMEMCG.  It removes __GFP_KMEMCG
from memcg caches' allocflags.  Instead it makes slab allocation path
call memcg_charge_kmem directly getting memcg to charge from the cache's
memcg params.

This also eliminates any possibility of misaccounting an allocation
going from one memcg's cache to another memcg, because now we always
charge slabs against the memcg the cache belongs to.  That's why this
patch removes the big comment to memcg_kmem_get_cache.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 59 insertions, 26 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b569b8be5c5..96e5d2573eb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -506,6 +506,9 @@ void memcg_update_array_size(int num_groups);
 struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
+int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size);
+void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size);
+
 void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
 int __kmem_cache_destroy_memcg_children(struct kmem_cache *s);
 
@@ -583,17 +586,7 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
  * @cachep: the original global kmem cache
  * @gfp: allocation flags.
  *
- * This function assumes that the task allocating, which determines the memcg
- * in the page allocator, belongs to the same cgroup throughout the whole
- * process.  Misacounting can happen if the task calls memcg_kmem_get_cache()
- * while belonging to a cgroup, and later on changes. This is considered
- * acceptable, and should only happen upon task migration.
- *
- * Before the cache is created by the memcg core, there is also a possible
- * imbalance: the task belongs to a memcg, but the cache being allocated from
- * is the global cache, since the child cache is not yet guaranteed to be
- * ready. This case is also fine, since in this case the GFP_KMEMCG will not be
- * passed and the page allocator will not attempt any cgroup accounting.
+ * All memory allocated from a per-memcg cache is charged to the owner memcg.
  */
 static __always_inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5177c6d4a2d..56a768b3d5a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2953,7 +2953,7 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
 }
 #endif
 
-static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 {
 	struct res_counter *fail_res;
 	int ret = 0;
@@ -2991,7 +2991,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	return ret;
 }
 
-static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
 {
 	res_counter_uncharge(&memcg->res, size);
 	if (do_swap_account)
diff --git a/mm/slab.c b/mm/slab.c
index 5c846d25c17..944ac58cfcf 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1688,8 +1688,12 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		flags |= __GFP_RECLAIMABLE;
 
+	if (memcg_charge_slab(cachep, flags, cachep->gfporder))
+		return NULL;
+
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
 	if (!page) {
+		memcg_uncharge_slab(cachep, cachep->gfporder);
 		slab_out_of_memory(cachep, flags, nodeid);
 		return NULL;
 	}
@@ -1747,7 +1751,8 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
-	__free_memcg_kmem_pages(page, cachep->gfporder);
+	__free_pages(page, cachep->gfporder);
+	memcg_uncharge_slab(cachep, cachep->gfporder);
 }
 
 static void kmem_rcu_free(struct rcu_head *head)
diff --git a/mm/slab.h b/mm/slab.h
index 6bd4c353704..863e67b8c8c 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -192,6 +192,26 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 		return s;
 	return s->memcg_params->root_cache;
 }
+
+static __always_inline int memcg_charge_slab(struct kmem_cache *s,
+					     gfp_t gfp, int order)
+{
+	if (!memcg_kmem_enabled())
+		return 0;
+	if (is_root_cache(s))
+		return 0;
+	return memcg_charge_kmem(s->memcg_params->memcg, gfp,
+				 PAGE_SIZE << order);
+}
+
+static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
+{
+	if (!memcg_kmem_enabled())
+		return;
+	if (is_root_cache(s))
+		return;
+	memcg_uncharge_kmem(s->memcg_params->memcg, PAGE_SIZE << order);
+}
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
 {
@@ -227,6 +247,15 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 {
 	return s;
 }
+
+static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
+{
+	return 0;
+}
+
+static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
+{
+}
 #endif
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 102cc6fca3d..06f0c612563 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -290,12 +290,8 @@ void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_c
 				 root_cache->size, root_cache->align,
 				 root_cache->flags, root_cache->ctor,
 				 memcg, root_cache);
-	if (IS_ERR(s)) {
+	if (IS_ERR(s))
 		kfree(cache_name);
-		goto out_unlock;
-	}
-
-	s->allocflags |= __GFP_KMEMCG;
 
 out_unlock:
 	mutex_unlock(&slab_mutex);
diff --git a/mm/slub.c b/mm/slub.c
index d05a5483106..fc9831851be 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1312,17 +1312,26 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 /*
  * Slab allocation and freeing
  */
-static inline struct page *alloc_slab_page(gfp_t flags, int node,
-					struct kmem_cache_order_objects oo)
+static inline struct page *alloc_slab_page(struct kmem_cache *s,
+		gfp_t flags, int node, struct kmem_cache_order_objects oo)
 {
+	struct page *page;
 	int order = oo_order(oo);
 
 	flags |= __GFP_NOTRACK;
 
+	if (memcg_charge_slab(s, flags, order))
+		return NULL;
+
 	if (node == NUMA_NO_NODE)
-		return alloc_pages(flags, order);
+		page = alloc_pages(flags, order);
 	else
-		return alloc_pages_exact_node(node, flags, order);
+		page = alloc_pages_exact_node(node, flags, order);
+
+	if (!page)
+		memcg_uncharge_slab(s, order);
+
+	return page;
 }
 
 static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
@@ -1344,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	 */
 	alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
 
-	page = alloc_slab_page(alloc_gfp, node, oo);
+	page = alloc_slab_page(s, alloc_gfp, node, oo);
 	if (unlikely(!page)) {
 		oo = s->min;
 		alloc_gfp = flags;
@@ -1352,7 +1361,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 		 * Allocation may have failed due to fragmentation.
 		 * Try a lower order alloc if possible
 		 */
-		page = alloc_slab_page(alloc_gfp, node, oo);
+		page = alloc_slab_page(s, alloc_gfp, node, oo);
 
 		if (page)
 			stat(s, ORDER_FALLBACK);
@@ -1468,7 +1477,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 	page_mapcount_reset(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;
-	__free_memcg_kmem_pages(page, order);
+	__free_pages(page, order);
+	memcg_uncharge_slab(s, order);
 }
 
 #define need_reserve_slab_rcu						\