blk-mq: allow the driver to pass in a queue mapping

This allows drivers specify their own queue mapping by overriding the
setup-time function that builds the mq_map.  This can be used for
example to build the map based on the MSI-X vector mapping provided
by the core interrupt layer for PCI devices.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-mq-cpumap.c

@@ -31,14 +31,16 @@ static int get_first_sibling(unsigned int cpu)
 	return cpu;
 }
 
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-			    const struct cpumask *online_mask)
+int blk_mq_map_queues(struct blk_mq_tag_set *set)
 {
+	unsigned int *map = set->mq_map;
+	unsigned int nr_queues = set->nr_hw_queues;
+	const struct cpumask *online_mask = cpu_online_mask;
 	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
 	cpumask_var_t cpus;
 
 	if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
-		return 1;
+		return -ENOMEM;
 
 	cpumask_clear(cpus);
 	nr_cpus = nr_uniq_cpus = 0;
@@ -86,23 +88,6 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
 	return 0;
 }
 
-unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
-{
-	unsigned int *map;
-
-	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
-				set->numa_node);
-	if (!map)
-		return NULL;
-
-	if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
-		return map;
-
-	kfree(map);
-	return NULL;
-}
-
 /*
  * We have no quick way of doing reverse lookups. This is only used at
  * queue init time, so runtime isn't important.

block/blk-mq.c

@@ -2286,6 +2286,8 @@ EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
+	int ret;
+
 	BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
 
 	if (!set->nr_hw_queues)
@@ -2324,11 +2326,21 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->tags)
 		return -ENOMEM;
 
-	set->mq_map = blk_mq_make_queue_map(set);
+	ret = -ENOMEM;
+	set->mq_map = kzalloc_node(sizeof(*set->mq_map) * nr_cpu_ids,
+			GFP_KERNEL, set->numa_node);
 	if (!set->mq_map)
 		goto out_free_tags;
 
-	if (blk_mq_alloc_rq_maps(set))
+	if (set->ops->map_queues)
+		ret = set->ops->map_queues(set);
+	else
+		ret = blk_mq_map_queues(set);
+	if (ret)
+		goto out_free_mq_map;
+
+	ret = blk_mq_alloc_rq_maps(set);
+	if (ret)
 		goto out_free_mq_map;
 
 	mutex_init(&set->tag_list_lock);
@@ -2342,7 +2354,7 @@ out_free_mq_map:
 out_free_tags:
 	kfree(set->tags);
 	set->tags = NULL;
-	return -ENOMEM;
+	return ret;
 }
 EXPORT_SYMBOL(blk_mq_alloc_tag_set);
 

block/blk-mq.h

@@ -47,9 +47,7 @@ void blk_mq_disable_hotplug(void);
 /*
  * CPU -> queue mappings
  */
-extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
-extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-				   const struct cpumask *online_mask);
+int blk_mq_map_queues(struct blk_mq_tag_set *set);
 extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
 
 static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,

include/linux/blk-mq.h

@@ -104,6 +104,7 @@ typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
 typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
 typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int);
+typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
 
 
 struct blk_mq_ops {
@@ -144,6 +145,8 @@ struct blk_mq_ops {
 	init_request_fn		*init_request;
 	exit_request_fn		*exit_request;
 	reinit_request_fn	*reinit_request;
+
+	map_queues_fn		*map_queues;
 };
 
 enum {