block: allocate request memory local to request queue

blk_init_rl() allocates a mempool using mempool_create_node() with node
local memory.  This only allocates the mempool and element list locally
to the requeue queue node.

What we really want to do is allocate the request itself local to the
queue.  To do this, we need our own alloc and free functions that will
allocate from request_cachep and pass the request queue node in to prefer
node local memory.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index 794c3e7..fd154b9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -557,6 +557,18 @@
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
 
+/* Allocate memory local to the request queue */
+static void *alloc_request_struct(gfp_t gfp_mask, void *data)
+{
+	int nid = (int)(long)data;
+	return kmem_cache_alloc_node(request_cachep, gfp_mask, nid);
+}
+
+static void free_request_struct(void *element, void *unused)
+{
+	kmem_cache_free(request_cachep, element);
+}
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
@@ -569,9 +581,10 @@
 	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
 	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
-	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
-					  mempool_free_slab, request_cachep,
-					  gfp_mask, q->node);
+	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct,
+					  free_request_struct,
+					  (void *)(long)q->node, gfp_mask,
+					  q->node);
 	if (!rl->rq_pool)
 		return -ENOMEM;