mm: memcg/slab: uncharge during kmem_cache_free_bulk()

Object cgroup charging is done for all the objects during allocation, but
during freeing, uncharging ends up happening for only one object in the
case of bulk allocation/freeing.

Fix this by having a separate call to uncharge all the objects from
kmem_cache_free_bulk() and by modifying memcg_slab_free_hook() to take
care of bulk uncharging.

Fixes: 964d4bd370 ("mm: memcg/slab: save obj_cgroup for non-root slab objects"
Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201009060423.390479-1-bharata@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/slab.c

@@ -3438,7 +3438,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp,
 		memset(objp, 0, cachep->object_size);
 	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, caller);
-	memcg_slab_free_hook(cachep, virt_to_head_page(objp), objp);
+	memcg_slab_free_hook(cachep, &objp, 1);
 
 	/*
 	 * Skip calling cache_free_alien() when the platform is not numa.

mm/slab.h

@@ -345,30 +345,42 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 	obj_cgroup_put(objcg);
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
-					void *p)
+static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
+					void **p, int objects)
 {
+	struct kmem_cache *s;
 	struct obj_cgroup *objcg;
+	struct page *page;
 	unsigned int off;
+	int i;
 
 	if (!memcg_kmem_enabled())
 		return;
 
-	if (!page_has_obj_cgroups(page))
-		return;
+	for (i = 0; i < objects; i++) {
+		if (unlikely(!p[i]))
+			continue;
 
-	off = obj_to_index(s, page, p);
-	objcg = page_obj_cgroups(page)[off];
-	page_obj_cgroups(page)[off] = NULL;
+		page = virt_to_head_page(p[i]);
+		if (!page_has_obj_cgroups(page))
+			continue;
 
-	if (!objcg)
-		return;
+		if (!s_orig)
+			s = page->slab_cache;
+		else
+			s = s_orig;
 
-	obj_cgroup_uncharge(objcg, obj_full_size(s));
-	mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
-			-obj_full_size(s));
+		off = obj_to_index(s, page, p[i]);
+		objcg = page_obj_cgroups(page)[off];
+		if (!objcg)
+			continue;
 
-	obj_cgroup_put(objcg);
+		page_obj_cgroups(page)[off] = NULL;
+		obj_cgroup_uncharge(objcg, obj_full_size(s));
+		mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
+				-obj_full_size(s));
+		obj_cgroup_put(objcg);
+	}
 }
 
 #else /* CONFIG_MEMCG_KMEM */
@@ -406,8 +418,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 {
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
-					void *p)
+static inline void memcg_slab_free_hook(struct kmem_cache *s,
+					void **p, int objects)
 {
 }
 #endif /* CONFIG_MEMCG_KMEM */

mm/slub.c

@@ -3095,7 +3095,7 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
 
-	memcg_slab_free_hook(s, page, head);
+	memcg_slab_free_hook(s, &head, 1);
 redo:
 	/*
 	 * Determine the currently cpus per cpu slab.
@@ -3257,6 +3257,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 	if (WARN_ON(!size))
 		return;
 
+	memcg_slab_free_hook(s, p, size);
 	do {
 		struct detached_freelist df;