block: move the io_stat flag setting to queue_limits

Move the io_stat flag into the queue_limits feature field so that it can
be set atomically with the queue frozen.

Simplify md and dm to set the flag unconditionally instead of avoiding
setting a simple flag for cases where it already is set by other means,
which is a bit pointless.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240617060532.127975-17-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

4 files changed, 15 insertions, 17 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 0a3838e45aff..5d5431e531ae 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -579,6 +579,12 @@ int dm_split_args(int *argc, char ***argvp, char *input)
 	return 0;
 }
 
+static void dm_set_stacking_limits(struct queue_limits *limits)
+{
+	blk_set_stacking_limits(limits);
+	limits->features |= BLK_FEAT_IO_STAT;
+}
+
 /*
  * Impose necessary and sufficient conditions on a devices's table such
  * that any incoming bio which respects its logical_block_size can be
@@ -617,7 +623,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t,
 	for (i = 0; i < t->num_targets; i++) {
 		ti = dm_table_get_target(t, i);
 
-		blk_set_stacking_limits(&ti_limits);
+		dm_set_stacking_limits(&ti_limits);
 
 		/* combine all target devices' limits */
 		if (ti->type->iterate_devices)
@@ -1591,7 +1597,7 @@ int dm_calculate_queue_limits(struct dm_table *t,
 	unsigned int zone_sectors = 0;
 	bool zoned = false;
 
-	blk_set_stacking_limits(limits);
+	dm_set_stacking_limits(limits);
 
 	t->integrity_supported = true;
 	for (unsigned int i = 0; i < t->num_targets; i++) {
@@ -1604,7 +1610,7 @@ int dm_calculate_queue_limits(struct dm_table *t,
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
-		blk_set_stacking_limits(&ti_limits);
+		dm_set_stacking_limits(&ti_limits);
 
 		if (!ti->type->iterate_devices) {
 			/* Set I/O hints portion of queue limits */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 13037d6a6f62..8a976cee448b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2386,22 +2386,15 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 	struct table_device *td;
 	int r;
 
-	switch (type) {
-	case DM_TYPE_REQUEST_BASED:
+	WARN_ON_ONCE(type == DM_TYPE_NONE);
+
+	if (type == DM_TYPE_REQUEST_BASED) {
 		md->disk->fops = &dm_rq_blk_dops;
 		r = dm_mq_init_request_queue(md, t);
 		if (r) {
 			DMERR("Cannot initialize queue for request-based dm mapped device");
 			return r;
 		}
-		break;
-	case DM_TYPE_BIO_BASED:
-	case DM_TYPE_DAX_BIO_BASED:
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, md->queue);
-		break;
-	case DM_TYPE_NONE:
-		WARN_ON_ONCE(true);
-		break;
 	}
 
 	r = dm_calculate_queue_limits(t, &limits);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c23423c51fb7..8db0db8d5a27 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5787,7 +5787,8 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	int unit;
 	int error;
 	struct queue_limits lim = {
-		.features		= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA,
+		.features		= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
+					  BLK_FEAT_IO_STAT,
 	};
 
 	/*
@@ -6152,8 +6153,6 @@ int md_run(struct mddev *mddev)
 	if (!mddev_is_dm(mddev)) {
 		struct request_queue *q = mddev->gendisk->queue;
 
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
-
 		/* Set the NOWAIT flags if all underlying devices support it */
 		if (nowait)
 			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 58c13304e558..eea727cfa9e6 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -538,6 +538,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	blk_set_stacking_limits(&lim);
 	lim.dma_alignment = 3;
+	lim.features |= BLK_FEAT_IO_STAT;
 	if (head->ids.csi != NVME_CSI_ZNS)
 		lim.max_zone_append_sectors = 0;
 
@@ -550,7 +551,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 			ctrl->subsys->instance, head->instance);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
 	/*
 	 * This assumes all controllers that refer to a namespace either
 	 * support poll queues or not.  That is not a strict guarantee,