slub: correct to calculate num of acquired objects in get_partial_node()

There is a subtle bug when calculating a number of acquired objects.

Currently, we calculate "available = page->objects - page->inuse",
after acquire_slab() is called in get_partial_node().

In acquire_slab() with mode = 1, we always set new.inuse = page->objects.
So,

	acquire_slab(s, n, page, object == NULL);

	if (!object) {
		c->page = page;
		stat(s, ALLOC_FROM_PARTIAL);
		object = t;
		available = page->objects - page->inuse;

		!!! availabe is always 0 !!!
	...

Therfore, "available > s->cpu_partial / 2" is always false and
we always go to second iteration.
This patch correct this problem.

After that, we don't need return value of put_cpu_partial().
So remove it.

Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/mm/slub.c b/mm/slub.c
index aa0728d..8f73593 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1493,7 +1493,7 @@
  */
 static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
-		int mode)
+		int mode, int *objects)
 {
 	void *freelist;
 	unsigned long counters;
@@ -1507,6 +1507,7 @@
 	freelist = page->freelist;
 	counters = page->counters;
 	new.counters = counters;
+	*objects = new.objects - new.inuse;
 	if (mode) {
 		new.inuse = page->objects;
 		new.freelist = NULL;
@@ -1528,7 +1529,7 @@
 	return freelist;
 }
 
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
 static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
 
 /*
@@ -1539,6 +1540,8 @@
 {
 	struct page *page, *page2;
 	void *object = NULL;
+	int available = 0;
+	int objects;
 
 	/*
 	 * Racy check. If we mistakenly see no partial slabs then we
@@ -1552,22 +1555,21 @@
 	spin_lock(&n->list_lock);
 	list_for_each_entry_safe(page, page2, &n->partial, lru) {
 		void *t;
-		int available;
 
 		if (!pfmemalloc_match(page, flags))
 			continue;
 
-		t = acquire_slab(s, n, page, object == NULL);
+		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
 			break;
 
+		available += objects;
 		if (!object) {
 			c->page = page;
 			stat(s, ALLOC_FROM_PARTIAL);
 			object = t;
-			available =  page->objects - page->inuse;
 		} else {
-			available = put_cpu_partial(s, page, 0);
+			put_cpu_partial(s, page, 0);
 			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
@@ -1946,7 +1948,7 @@
  * If we did not find a slot then simply move all the partials to the
  * per node partial list.
  */
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 {
 	struct page *oldpage;
 	int pages;
@@ -1984,7 +1986,6 @@
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	return pobjects;
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)