block: don't update BLK_FEAT_POLL in __blk_mq_update_nr_hw_queues

When __blk_mq_update_nr_hw_queues changes the number of tag sets, it
might have to disable poll queues.  Currently it does so by adjusting
the BLK_FEAT_POLL, which is a bit against the intent of features that
describe hardware / driver capabilities, but more importantly causes
nasty lock order problems with the broadly held freeze when updating the
number of hardware queues and the limits lock.  Fix this by leaving
BLK_FEAT_POLL alone, and instead check for the number of poll queues in
the bio submission and poll handlers.  While this adds extra work to the
fast path, the variables are in cache lines used by these operations
anyway, so it should be cheap enough.

Fixes: 8023e14 ("block: move the poll flag to queue_limits")
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Ming Lei <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Reviewed-by: Johannes Thumshirn <[email protected]>
Reviewed-by: Nilay Shroff <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: Christoph Hellwig

block/blk-core.c

@@ -951,14 +951,13 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	 */
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return 0;
-	if (!(q->limits.features & BLK_FEAT_POLL)) {
-		ret = 0;
-	} else if (queue_is_mq(q)) {
+	if (queue_is_mq(q)) {
 		ret = blk_mq_poll(q, cookie, iob, flags);
 	} else {
 		struct gendisk *disk = q->disk;
 
-		if (disk && disk->fops->poll_bio)
+		if ((q->limits.features & BLK_FEAT_POLL) && disk &&
+		    disk->fops->poll_bio)
 			ret = disk->fops->poll_bio(bio, iob, flags);
 	}
 	blk_queue_exit(q);

block/blk-mq.c

@@ -3105,8 +3105,7 @@ void blk_mq_submit_bio(struct bio *bio)
 		goto queue_exit;
 	}
 
-	if ((bio->bi_opf & REQ_POLLED) &&
-	    !(q->limits.features & BLK_FEAT_POLL)) {
+	if ((bio->bi_opf & REQ_POLLED) && !blk_mq_can_poll(q)) {
 		bio->bi_status = BLK_STS_NOTSUPP;
 		bio_endio(bio);
 		goto queue_exit;
@@ -4328,12 +4327,6 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-static bool blk_mq_can_poll(struct blk_mq_tag_set *set)
-{
-	return set->nr_maps > HCTX_TYPE_POLL &&
-		set->map[HCTX_TYPE_POLL].nr_queues;
-}
-
 struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 		struct queue_limits *lim, void *queuedata)
 {
@@ -4344,7 +4337,7 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 	if (!lim)
 		lim = &default_lim;
 	lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
-	if (blk_mq_can_poll(set))
+	if (set->nr_maps > HCTX_TYPE_POLL)
 		lim->features |= BLK_FEAT_POLL;
 
 	q = blk_alloc_queue(lim, set->numa_node);
@@ -5032,8 +5025,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 fallback:
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
-		struct queue_limits lim;
-
 		blk_mq_realloc_hw_ctxs(set, q);
 
 		if (q->nr_hw_queues != set->nr_hw_queues) {
@@ -5047,13 +5038,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 			set->nr_hw_queues = prev_nr_hw_queues;
 			goto fallback;
 		}
-		lim = queue_limits_start_update(q);
-		if (blk_mq_can_poll(set))
-			lim.features |= BLK_FEAT_POLL;
-		else
-			lim.features &= ~BLK_FEAT_POLL;
-		if (queue_limits_commit_update(q, &lim) < 0)
-			pr_warn("updating the poll flag failed\n");
 		blk_mq_map_swqueue(q);
 	}
 
@@ -5113,9 +5097,9 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 int blk_mq_poll(struct request_queue *q, blk_qc_t cookie,
 		struct io_comp_batch *iob, unsigned int flags)
 {
-	struct blk_mq_hw_ctx *hctx = xa_load(&q->hctx_table, cookie);
-
-	return blk_hctx_poll(q, hctx, iob, flags);
+	if (!blk_mq_can_poll(q))
+		return 0;
+	return blk_hctx_poll(q, xa_load(&q->hctx_table, cookie), iob, flags);
 }
 
 int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,

block/blk-mq.h

@@ -448,4 +448,10 @@ do {								\
 #define blk_mq_run_dispatch_ops(q, dispatch_ops)		\
 	__blk_mq_run_dispatch_ops(q, true, dispatch_ops)	\
 
+static inline bool blk_mq_can_poll(struct request_queue *q)
+{
+	return (q->limits.features & BLK_FEAT_POLL) &&
+		q->tag_set->map[HCTX_TYPE_POLL].nr_queues;
+}
+
 #endif

block/blk-sysfs.c

@@ -245,10 +245,17 @@ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
 		!!(disk->queue->limits.features & _feature));		\
 }
 
-QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL);
 QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA);
 QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX);
 
+static ssize_t queue_poll_show(struct gendisk *disk, char *page)
+{
+	if (queue_is_mq(disk->queue))
+		return sysfs_emit(page, "%u\n", blk_mq_can_poll(disk->queue));
+	return sysfs_emit(page, "%u\n",
+		!!(disk->queue->limits.features & BLK_FEAT_POLL));
+}
+
 static ssize_t queue_zoned_show(struct gendisk *disk, char *page)
 {
 	if (blk_queue_is_zoned(disk->queue))