slub: clean up code for kmem cgroup support to kmem_cache_free_bulk

This change is primarily an attempt to make it easier to realize the
optimizations the compiler performs in-case CONFIG_MEMCG_KMEM is not
enabled.

Performance wise, even when CONFIG_MEMCG_KMEM is compiled in, the
overhead is zero.  This is because, as long as no process have enabled
kmem cgroups accounting, the assignment is replaced by asm-NOP
operations.  This is possible because memcg_kmem_enabled() uses a
static_key_false() construct.

It also helps readability as it avoid accessing the p[] array like:
p[size - 1] which "expose" that the array is processed backwards inside
helper function build_detached_freelist().

Lastly this also makes the code more robust, in error case like passing
NULL pointers in the array.  Which were previously handled before commit
03374518 ("slub: add missing kmem cgroup support to
kmem_cache_free_bulk").

Fixes: 03374518 ("slub: add missing kmem cgroup support to kmem_cache_free_bulk")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/slub.c

@@ -2815,6 +2815,7 @@ struct detached_freelist {
 	void *tail;
 	void *freelist;
 	int cnt;
+	struct kmem_cache *s;
 };
 
 /*
@@ -2829,7 +2830,8 @@ struct detached_freelist {
  * synchronization primitive.  Look ahead in the array is limited due
  * to performance reasons.
  */
-static int build_detached_freelist(struct kmem_cache *s, size_t size,
+static inline
+int build_detached_freelist(struct kmem_cache *s, size_t size,
 			    void **p, struct detached_freelist *df)
 {
 	size_t first_skipped_index = 0;
@@ -2846,8 +2848,11 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	if (!object)
 		return 0;
 
+	/* Support for memcg, compiler can optimize this out */
+	df->s = cache_from_obj(s, object);
+
 	/* Start new detached freelist */
-	set_freepointer(s, object, NULL);
+	set_freepointer(df->s, object, NULL);
 	df->page = virt_to_head_page(object);
 	df->tail = object;
 	df->freelist = object;
@@ -2862,7 +2867,7 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 		/* df->page is always set at this point */
 		if (df->page == virt_to_head_page(object)) {
 			/* Opportunity build freelist */
-			set_freepointer(s, object, df->freelist);
+			set_freepointer(df->s, object, df->freelist);
 			df->freelist = object;
 			df->cnt++;
 			p[size] = NULL; /* mark object processed */
@@ -2881,25 +2886,20 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	return first_skipped_index;
 }
 
-
 /* Note that interrupts must be enabled when calling this function. */
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
 	if (WARN_ON(!size))
 		return;
 
 	do {
 		struct detached_freelist df;
-		struct kmem_cache *s;
-
-		/* Support for memcg */
-		s = cache_from_obj(orig_s, p[size - 1]);
 
 		size = build_detached_freelist(s, size, p, &df);
 		if (unlikely(!df.page))
 			continue;
 
-		slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);