mm/slub: optimize free fast path code layout

Inspection of kmem_cache_free() disassembly showed we could make the
fast path smaller by providing few more hints to the compiler, and
splitting the memcg_slab_free_hook() into an inline part that only
checks if there's work to do, and an out of line part doing the actual
uncharge.

bloat-o-meter results:
add/remove: 2/0 grow/shrink: 0/3 up/down: 286/-554 (-268)
Function                                     old     new   delta
__memcg_slab_free_hook                         -     270    +270
__pfx___memcg_slab_free_hook                   -      16     +16
kfree                                        828     665    -163
kmem_cache_free                             1116     948    -168
kmem_cache_free_bulk.part                   1701    1478    -223

Checking kmem_cache_free() disassembly now shows the non-fastpath
cases are handled out of line, which should reduce instruction cache
usage.
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

mm/slub.c

@@ -1959,20 +1959,11 @@ void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg,
 	return __memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
-					void **p, int objects)
+static void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
+				   void **p, int objects,
+				   struct obj_cgroup **objcgs)
 {
-	struct obj_cgroup **objcgs;
-	int i;
-
-	if (!memcg_kmem_online())
-		return;
-
-	objcgs = slab_objcgs(slab);
-	if (!objcgs)
-		return;
-
-	for (i = 0; i < objects; i++) {
+	for (int i = 0; i < objects; i++) {
 		struct obj_cgroup *objcg;
 		unsigned int off;
 
@@ -1988,6 +1979,22 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 		obj_cgroup_put(objcg);
 	}
 }
+
+static __fastpath_inline
+void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
+			  int objects)
+{
+	struct obj_cgroup **objcgs;
+
+	if (!memcg_kmem_online())
+		return;
+
+	objcgs = slab_objcgs(slab);
+	if (likely(!objcgs))
+		return;
+
+	__memcg_slab_free_hook(s, slab, p, objects, objcgs);
+}
 #else /* CONFIG_MEMCG_KMEM */
 static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 {
@@ -2047,7 +2054,7 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
 	 * The initialization memset's clear the object and the metadata,
 	 * but don't touch the SLAB redzone.
 	 */
-	if (init) {
+	if (unlikely(init)) {
 		int rsize;
 
 		if (!kasan_has_integrated_init())
@@ -2083,7 +2090,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 		next = get_freepointer(s, object);
 
 		/* If object's reuse doesn't have to be delayed */
-		if (!slab_free_hook(s, object, slab_want_init_on_free(s))) {
+		if (likely(!slab_free_hook(s, object,
+					   slab_want_init_on_free(s)))) {
 			/* Move object to the new freelist */
 			set_freepointer(s, object, *head);
 			*head = object;
@@ -4282,7 +4290,7 @@ static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
 	 * With KASAN enabled slab_free_freelist_hook modifies the freelist
 	 * to remove objects, whose reuse must be delayed.
 	 */
-	if (slab_free_freelist_hook(s, &head, &tail, &cnt))
+	if (likely(slab_free_freelist_hook(s, &head, &tail, &cnt)))
 		do_slab_free(s, slab, head, tail, cnt, addr);
 }