Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Another series of killing more code than what is being added, again
  thanks to Christoph's relentless cleanups and tech debt tackling.

  This contains:

   - blk-iocost improvements (Baolin Wang)

   - part0 iostat fix (Jeffle Xu)

   - Disable iopoll for split bios (Jeffle Xu)

   - block tracepoint cleanups (Christoph Hellwig)

   - Merging of struct block_device and hd_struct (Christoph Hellwig)

   - Rework/cleanup of how block device sizes are updated (Christoph
     Hellwig)

   - Simplification of gendisk lookup and removal of block device
     aliasing (Christoph Hellwig)

   - Block device ioctl cleanups (Christoph Hellwig)

   - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig)

   - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig)

   - sbitmap improvements (Pavel Begunkov)

   - Hybrid polling fix (Pavel Begunkov)

   - bvec iteration improvements (Pavel Begunkov)

   - Zone revalidation fixes (Damien Le Moal)

   - blk-throttle limit fix (Yu Kuai)

   - Various little fixes"

* tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits)
  blk-mq: fix msec comment from micro to milli seconds
  blk-mq: update arg in comment of blk_mq_map_queue
  blk-mq: add helper allocating tagset->tags
  Revert "block: Fix a lockdep complaint triggered by request queue flushing"
  nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class
  blk-mq: add new API of blk_mq_hctx_set_fq_lock_class
  block: disable iopoll for split bio
  block: Improve blk_revalidate_disk_zones() checks
  sbitmap: simplify wrap check
  sbitmap: replace CAS with atomic and
  sbitmap: remove swap_lock
  sbitmap: optimise sbitmap_deferred_clear()
  blk-mq: skip hybrid polling if iopoll doesn't spin
  blk-iocost: Factor out the base vrate change into a separate function
  blk-iocost: Factor out the active iocgs' state check into a separate function
  blk-iocost: Move the usage ratio calculation to the correct place
  blk-iocost: Remove unnecessary advance declaration
  blk-iocost: Fix some typos in comments
  blktrace: fix up a kerneldoc comment
  block: remove the request_queue to argument request based tracepoints
  ...

4 files changed, 23 insertions, 28 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9a270e49df17..9b6ebeb29cca 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -93,16 +93,6 @@ static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
 
-static void nvme_update_bdev_size(struct gendisk *disk)
-{
-	struct block_device *bdev = bdget_disk(disk, 0);
-
-	if (bdev) {
-		bd_set_nr_sectors(bdev, get_capacity(disk));
-		bdput(bdev);
-	}
-}
-
 /*
  * Prepare a queue for teardown.
  *
@@ -119,8 +109,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	blk_set_queue_dying(ns->queue);
 	blk_mq_unquiesce_queue(ns->queue);
 
-	set_capacity(ns->disk, 0);
-	nvme_update_bdev_size(ns->disk);
+	set_capacity_and_notify(ns->disk, 0);
 }
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -2053,7 +2042,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 			capacity = 0;
 	}
 
-	set_capacity_revalidate_and_notify(disk, capacity, false);
+	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
 	nvme_config_write_zeroes(disk, ns);
@@ -2134,7 +2123,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
 		blk_queue_update_readahead(ns->head->disk->queue);
-		nvme_update_bdev_size(ns->head->disk);
 		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
 #endif
@@ -3962,8 +3950,6 @@ out:
 	 */
 	if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
 		nvme_ns_remove(ns);
-	else
-		revalidate_disk_size(ns->disk, true);
 }
 
 static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 74896be40c17..106cf5c44ee7 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -312,8 +312,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 	if (likely(ns)) {
 		bio->bi_disk = ns->disk;
 		bio->bi_opf |= REQ_NVME_MPATH;
-		trace_block_bio_remap(bio->bi_disk->queue, bio,
-				      disk_devt(ns->head->disk),
+		trace_block_bio_remap(bio, disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
 		ret = submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index dca34489a1dc..8d90235e4fcc 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -89,12 +89,12 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	if (!ns->bdev)
 		goto out;
 
-	host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
-	data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
-		sectors[READ]), 1000);
-	host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
-	data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
-		sectors[WRITE]), 1000);
+	host_reads = part_stat_read(ns->bdev, ios[READ]);
+	data_units_read =
+		DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000);
+	host_writes = part_stat_read(ns->bdev, ios[WRITE]);
+	data_units_written =
+		DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000);
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
 	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
@@ -120,12 +120,12 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 		/* we don't have the right data for file backed ns */
 		if (!ns->bdev)
 			continue;
-		host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
+		host_reads += part_stat_read(ns->bdev, ios[READ]);
 		data_units_read += DIV_ROUND_UP(
-			part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000);
-		host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+			part_stat_read(ns->bdev, sectors[READ]), 1000);
+		host_writes += part_stat_read(ns->bdev, ios[WRITE]);
 		data_units_written += DIV_ROUND_UP(
-			part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000);
+			part_stat_read(ns->bdev, sectors[WRITE]), 1000);
 	}
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index f6d81239be21..07806016c09d 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -211,6 +211,8 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
 
+static struct lock_class_key loop_hctx_fq_lock_key;
+
 static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 		unsigned int hctx_idx)
 {
@@ -219,6 +221,14 @@ static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 
 	BUG_ON(hctx_idx >= ctrl->ctrl.queue_count);
 
+	/*
+	 * flush_end_io() can be called recursively for us, so use our own
+	 * lock class key for avoiding lockdep possible recursive locking,
+	 * then we can remove the dynamically allocated lock class for each
+	 * flush queue, that way may cause horrible boot delay.
+	 */
+	blk_mq_hctx_set_fq_lock_class(hctx, &loop_hctx_fq_lock_key);
+
 	hctx->driver_data = queue;
 	return 0;
 }