mm/slab: make cache_grow() handle the page allocated on arbitrary node

Currently, cache_grow() assumes that allocated page's nodeid would be
same with parameter nodeid which is used for allocation request.  If we
discard this assumption, we can handle fallback_alloc() case gracefully.
So, this patch makes cache_grow() handle the page allocated on arbitrary
node and clean-up relevant code.

Signed-off-by: Joonsoo Kim <[email protected]>
Cc: Jesper Dangaard Brouer <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Pekka Enberg <[email protected]>
Cc: David Rientjes <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/slab.c

@@ -2556,13 +2556,14 @@ static void slab_map_pages(struct kmem_cache *cache, struct page *page,
  * Grow (by 1) the number of slabs within a cache.  This is called by
  * kmem_cache_alloc() when there are no active objs left in a cache.
  */
-static int cache_grow(struct kmem_cache *cachep,
-		gfp_t flags, int nodeid, struct page *page)
+static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	void *freelist;
 	size_t offset;
 	gfp_t local_flags;
+	int page_node;
 	struct kmem_cache_node *n;
+	struct page *page;
 
 	/*
 	 * Be lazy and only check for valid flags here,  keeping it out of the
@@ -2590,12 +2591,12 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * Get mem for the objs.  Attempt to allocate a physical page from
 	 * 'nodeid'.
 	 */
-	if (!page)
-		page = kmem_getpages(cachep, local_flags, nodeid);
+	page = kmem_getpages(cachep, local_flags, nodeid);
 	if (!page)
 		goto failed;
 
-	n = get_node(cachep, nodeid);
+	page_node = page_to_nid(page);
+	n = get_node(cachep, page_node);
 
 	/* Get colour for the slab, and cal the next value. */
 	n->colour_next++;
@@ -2610,7 +2611,7 @@ static int cache_grow(struct kmem_cache *cachep,
 
 	/* Get slab management. */
 	freelist = alloc_slabmgmt(cachep, page, offset,
-			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
+			local_flags & ~GFP_CONSTRAINT_MASK, page_node);
 	if (OFF_SLAB(cachep) && !freelist)
 		goto opps1;
 
@@ -2629,13 +2630,13 @@ static int cache_grow(struct kmem_cache *cachep,
 	STATS_INC_GROWN(cachep);
 	n->free_objects += cachep->num;
 	spin_unlock(&n->list_lock);
-	return 1;
+	return page_node;
 opps1:
 	kmem_freepages(cachep, page);
 failed:
 	if (gfpflags_allow_blocking(local_flags))
 		local_irq_disable();
-	return 0;
+	return -1;
 }
 
 #if DEBUG
@@ -2916,14 +2917,14 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 				return obj;
 		}
 
-		x = cache_grow(cachep, gfp_exact_node(flags), node, NULL);
+		x = cache_grow(cachep, gfp_exact_node(flags), node);
 
 		/* cache_grow can reenable interrupts, then ac could change. */
 		ac = cpu_cache_get(cachep);
 		node = numa_mem_id();
 
 		/* no objects in sight? abort */
-		if (!x && ac->avail == 0)
+		if (x < 0 && ac->avail == 0)
 			return NULL;
 
 		if (!ac->avail)		/* objects refilled by interrupt? */
@@ -3052,7 +3053,6 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 {
 	struct zonelist *zonelist;
-	gfp_t local_flags;
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
@@ -3063,8 +3063,6 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
-
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = node_zonelist(mempolicy_slab_node(), flags);
@@ -3094,33 +3092,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 		 * We may trigger various forms of reclaim on the allowed
 		 * set and go into memory reserves if necessary.
 		 */
-		struct page *page;
+		nid = cache_grow(cache, flags, numa_mem_id());
+		if (nid >= 0) {
+			obj = ____cache_alloc_node(cache,
+				gfp_exact_node(flags), nid);
 
-		if (gfpflags_allow_blocking(local_flags))
-			local_irq_enable();
-		kmem_flagcheck(cache, flags);
-		page = kmem_getpages(cache, local_flags, numa_mem_id());
-		if (gfpflags_allow_blocking(local_flags))
-			local_irq_disable();
-		if (page) {
 			/*
-			 * Insert into the appropriate per node queues
+			 * Another processor may allocate the objects in
+			 * the slab since we are not holding any locks.
 			 */
-			nid = page_to_nid(page);
-			if (cache_grow(cache, flags, nid, page)) {
-				obj = ____cache_alloc_node(cache,
-					gfp_exact_node(flags), nid);
-				if (!obj)
-					/*
-					 * Another processor may allocate the
-					 * objects in the slab since we are
-					 * not holding any locks.
-					 */
-					goto retry;
-			} else {
-				/* cache_grow already freed obj */
-				obj = NULL;
-			}
+			if (!obj)
+				goto retry;
 		}
 	}
 
@@ -3171,8 +3153,8 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 
 must_grow:
 	spin_unlock(&n->list_lock);
-	x = cache_grow(cachep, gfp_exact_node(flags), nodeid, NULL);
-	if (x)
+	x = cache_grow(cachep, gfp_exact_node(flags), nodeid);
+	if (x >= 0)
 		goto retry;
 
 	return fallback_alloc(cachep, flags);