Add parameter to add_partial to avoid having two functions

Add a parameter to add_partial instead of having separate functions. The
parameter allows a more detailed control of where the slab pages is placed in
the partial queues.

If we put slabs back to the front then they are likely immediately used for
allocations. If they are put at the end then we can maximize the time that
the partial slabs spent without being subject to allocations.

When deactivating slab we can put the slabs that had remote objects freed (we
can see that because objects were put on the freelist that requires locks) to
them at the end of the list so that the cachelines of remote processors can
cool down. Slabs that had objects from the local cpu freed to them (objects
exist in the lockless freelist) are put in the front of the list to be reused
ASAP in order to exploit the cache hot state of the local cpu.

Patch seems to slightly improve tbench speed (1-2%).

Signed-off-by: Christoph Lameter <[e-mail]>
Reviewed-by: Pekka Enberg <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

mm/slub.c

···
 /*
  * Management of partially allocated slabs
  */
-static void add_partial_tail(struct kmem_cache_node *n, struct page *page)
+static void add_partial(struct kmem_cache_node *n,
+				struct page *page, int tail)
 {
 	spin_lock(&n->list_lock);
 	n->nr_partial++;
-	list_add_tail(&page->lru, &n->partial);
-	spin_unlock(&n->list_lock);
-}
-
-static void add_partial(struct kmem_cache_node *n, struct page *page)
-{
-	spin_lock(&n->list_lock);
-	n->nr_partial++;
-	list_add(&page->lru, &n->partial);
+	if (tail)
+		list_add_tail(&page->lru, &n->partial);
+	else
+		list_add(&page->lru, &n->partial);
 	spin_unlock(&n->list_lock);
 }
 
···
  *
  * On exit the slab lock will have been dropped.
  */
-static void unfreeze_slab(struct kmem_cache *s, struct page *page)
+static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
···
 	if (page->inuse) {
 
 		if (page->freelist)
-			add_partial(n, page);
+			add_partial(n, page, tail);
 		else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
 			add_full(n, page);
 		slab_unlock(page);
···
 			 * partial list stays small. kmem_cache_shrink can
 			 * reclaim empty slabs from the partial list.
 			 */
-			add_partial_tail(n, page);
+			add_partial(n, page, 1);
 			slab_unlock(page);
 		} else {
 			slab_unlock(page);
···
 static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	struct page *page = c->page;
+	int tail = 1;
 	/*
 	 * Merge cpu freelist into freelist. Typically we get here
 	 * because both freelists are empty. So this is unlikely
···
 	 */
 	while (unlikely(c->freelist)) {
 		void **object;
+
+		tail = 0;	/* Hot objects. Put the slab first */
 
 		/* Retrieve object from cpu_freelist */
 		object = c->freelist;
···
 		page->inuse--;
 	}
 	c->page = NULL;
-	unfreeze_slab(s, page);
+	unfreeze_slab(s, page, tail);
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
···
 	 * then add it.
 	 */
 	if (unlikely(!prior))
-		add_partial_tail(get_node(s, page_to_nid(page)), page);
+		add_partial(get_node(s, page_to_nid(page)), page, 1);
 
 out_unlock:
 	slab_unlock(page);
···
 #endif
 	init_kmem_cache_node(n);
 	atomic_long_inc(&n->nr_slabs);
-	add_partial(n, page);
+	add_partial(n, page, 0);
 	return n;
 }