slab: implement bulk alloc in SLAB allocator

This patch implements the alloc side of bulk API for the SLAB allocator.

Further optimization are still possible by changing the call to
__do_cache_alloc() into something that can return multiple objects.
This optimization is left for later, given end results already show in
the area of 80% speedup.
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/slab.c

@@ -3394,7 +3394,40 @@ EXPORT_SYMBOL(kmem_cache_free_bulk);
 int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			  void **p)
 {
-	return __kmem_cache_alloc_bulk(s, flags, size, p);
+	size_t i;
+
+	s = slab_pre_alloc_hook(s, flags);
+	if (!s)
+		return 0;
+
+	cache_alloc_debugcheck_before(s, flags);
+
+	local_irq_disable();
+	for (i = 0; i < size; i++) {
+		void *objp = __do_cache_alloc(s, flags);
+
+		/* this call could be done outside IRQ disabled section */
+		objp = cache_alloc_debugcheck_after(s, flags, objp, _RET_IP_);
+
+		if (unlikely(!objp))
+			goto error;
+		p[i] = objp;
+	}
+	local_irq_enable();
+
+	/* Clear memory outside IRQ disabled section */
+	if (unlikely(flags & __GFP_ZERO))
+		for (i = 0; i < size; i++)
+			memset(p[i], 0, s->object_size);
+
+	slab_post_alloc_hook(s, flags, size, p);
+	/* FIXME: Trace call missing. Christoph would like a bulk variant */
+	return size;
+error:
+	local_irq_enable();
+	slab_post_alloc_hook(s, flags, i, p);
+	__kmem_cache_free_bulk(s, i, p);
+	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);