mm: slab: optimize memcg_slab_free_hook()

Most callers of memcg_slab_free_hook() already know the slab,  which could
be passed to memcg_slab_free_hook() directly to reduce the overhead of an
another call of virt_to_slab().  For bulk freeing of objects, the call of
slab_objcgs() in the loop in memcg_slab_free_hook() is redundant as well.
Rework memcg_slab_free_hook() and build_detached_freelist() to reduce
those unnecessary overhead and make memcg_slab_free_hook() can handle bulk
freeing in slab_free().

Move the calling site of memcg_slab_free_hook() from do_slab_free() to
slab_free() for slub to make the code clearer since the logic is weird
(e.g. the caller need to judge whether it needs to call
memcg_slab_free_hook()). It is easy to make mistakes like missing calling
of memcg_slab_free_hook() like fixes of:

  commit d1b2cf6cb84a ("mm: memcg/slab: uncharge during kmem_cache_free_bulk()")
  commit ae085d7f9365 ("mm: kfence: fix missing objcg housekeeping for SLAB")

This optimization is mainly for bulk objects freeing.  The following numbers
is shown for 16-object freeing.

                           before      after
  kmem_cache_free_bulk:   ~430 ns     ~400 ns

The overhead is reduced by about 7% for 16-object freeing.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Link: https://lore.kernel.org/r/20220429123044.37885-1-songmuchun@bytedance.com
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

1 files changed, 8 insertions, 22 deletions

diff --git a/mm/slab.h b/mm/slab.h
index db9fb5c8dae7..a8d5eb1c323f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -547,36 +547,22 @@ 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_orig,
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 					void **p, int objects)
 {
-	struct kmem_cache *s;
 	struct obj_cgroup **objcgs;
-	struct obj_cgroup *objcg;
-	struct slab *slab;
-	unsigned int off;
 	int i;
 
 	if (!memcg_kmem_enabled())
 		return;
 
-	for (i = 0; i < objects; i++) {
-		if (unlikely(!p[i]))
-			continue;
-
-		slab = virt_to_slab(p[i]);
-		/* we could be given a kmalloc_large() object, skip those */
-		if (!slab)
-			continue;
-
-		objcgs = slab_objcgs(slab);
-		if (!objcgs)
-			continue;
+	objcgs = slab_objcgs(slab);
+	if (!objcgs)
+		return;
 
-		if (!s_orig)
-			s = slab->slab_cache;
-		else
-			s = s_orig;
+	for (i = 0; i < objects; i++) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
 
 		off = obj_to_index(s, slab, p[i]);
 		objcg = objcgs[off];
@@ -628,7 +614,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 {
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s,
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 					void **p, int objects)
 {
 }