[PATCH 4/6] blk-mq: Update queue map when changing queue count

Keith Busch keith.busch at intel.com
Wed Jan 4 14:41:09 PST 2017


The queue map needs to match how many hardware queues exist, otherwise
it may indicate a less than optimal mapping, contain a hctx_id that
was freed, or attempt to initialize a request map for invalid context.

Signed-off-by: Keith Busch <keith.busch at intel.com>
---
 block/blk-mq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a8e67a1..9b7ed03 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2223,7 +2223,6 @@ static void blk_mq_queue_reinit(struct request_queue *q,
 	 * we should change hctx numa_node according to new topology (this
 	 * involves free and re-allocate memory, worthy doing?)
 	 */
-
 	blk_mq_map_swqueue(q, online_mask);
 
 	blk_mq_sysfs_register(q);
@@ -2481,6 +2480,11 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 		blk_mq_freeze_queue(q);
 
 	set->nr_hw_queues = nr_hw_queues;
+	if (set->ops->map_queues)
+		set->ops->map_queues(set);
+	else
+		blk_mq_map_queues(set);
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 
-- 
2.5.5




More information about the Linux-nvme mailing list