Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

1 files changed, 31 insertions, 19 deletions

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9bfa3ea4ed63..b82736c781c5 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -941,14 +941,14 @@ int blk_register_queue(struct gendisk *disk)
 	int ret;
 	struct device *dev = disk_to_dev(disk);
 	struct request_queue *q = disk->queue;
+	bool has_elevator = false;
 
 	if (WARN_ON(!q))
 		return -ENXIO;
 
-	WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+	WARN_ONCE(blk_queue_registered(q),
 		  "%s is registering an already registered queue\n",
 		  kobject_name(&dev->kobj));
-	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
@@ -968,8 +968,7 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
-	/* Prevent changes through sysfs until registration is completed. */
-	mutex_lock(&q->sysfs_lock);
+	mutex_lock(&q->sysfs_dir_lock);
 
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0) {
@@ -990,26 +989,36 @@ int blk_register_queue(struct gendisk *disk)
 		blk_mq_debugfs_register(q);
 	}
 
-	kobject_uevent(&q->kobj, KOBJ_ADD);
-
-	wbt_enable_default(q);
-
-	blk_throtl_register_queue(q);
-
+	/*
+	 * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
+	 * switch won't happen at all.
+	 */
 	if (q->elevator) {
-		ret = elv_register_queue(q);
+		ret = elv_register_queue(q, false);
 		if (ret) {
-			mutex_unlock(&q->sysfs_lock);
-			kobject_uevent(&q->kobj, KOBJ_REMOVE);
+			mutex_unlock(&q->sysfs_dir_lock);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
 			kobject_put(&dev->kobj);
 			return ret;
 		}
+		has_elevator = true;
 	}
+
+	mutex_lock(&q->sysfs_lock);
+	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
+	wbt_enable_default(q);
+	blk_throtl_register_queue(q);
+
+	/* Now everything is ready and send out KOBJ_ADD uevent */
+	kobject_uevent(&q->kobj, KOBJ_ADD);
+	if (has_elevator)
+		kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
+	mutex_unlock(&q->sysfs_lock);
+
 	ret = 0;
 unlock:
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_register_queue);
@@ -1029,7 +1038,7 @@ void blk_unregister_queue(struct gendisk *disk)
 		return;
 
 	/* Return early if disk->queue was never registered. */
-	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+	if (!blk_queue_registered(q))
 		return;
 
 	/*
@@ -1038,25 +1047,28 @@ void blk_unregister_queue(struct gendisk *disk)
 	 * concurrent elv_iosched_store() calls.
 	 */
 	mutex_lock(&q->sysfs_lock);
-
 	blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+	mutex_unlock(&q->sysfs_lock);
 
+	mutex_lock(&q->sysfs_dir_lock);
 	/*
 	 * Remove the sysfs attributes before unregistering the queue data
 	 * structures that can be modified through sysfs.
 	 */
 	if (queue_is_mq(q))
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
-	mutex_unlock(&q->sysfs_lock);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	mutex_lock(&q->sysfs_lock);
+	/*
+	 * q->kobj has been removed, so it is safe to check if elevator
+	 * exists without holding q->sysfs_lock.
+	 */
 	if (q->elevator)
 		elv_unregister_queue(q);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
 }