Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Improve the type checking of request flags (Bart)

 - Ensure queue mapping for a single queues always picks the right queue
   (Bart)

 - Sanitize the io priority handling (Jan)

 - rq-qos race fix (Jinke)

 - Reserved tags handling improvements (John)

 - Separate memory alignment from file/disk offset aligment for O_DIRECT
   (Keith)

 - Add new ublk driver, userspace block driver using io_uring for
   communication with the userspace backend (Ming)

 - Use try_cmpxchg() to cleanup the code in various spots (Uros)

 - Finally remove bdevname() (Christoph)

 - Clean up the zoned device handling (Christoph)

 - Clean up independent access range support (Christoph)

 - Clean up and improve block sysfs handling (Christoph)

 - Clean up and improve teardown of block devices.

   This turns the usual two step process into something that is simpler
   to implement and handle in block drivers (Christoph)

 - Clean up chunk size handling (Christoph)

 - Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
   Ming, Sebastian, Yang, Ying)

* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
  ublk_drv: fix double shift bug
  ublk_drv: make sure that correct flags(features) returned to userspace
  ublk_drv: fix error handling of ublk_add_dev
  ublk_drv: fix lockdep warning
  block: remove __blk_get_queue
  block: call blk_mq_exit_queue from disk_release for never added disks
  blk-mq: fix error handling in __blk_mq_alloc_disk
  ublk: defer disk allocation
  ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
  ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
  ublk: cleanup ublk_ctrl_uring_cmd
  ublk: simplify ublk_ch_open and ublk_ch_release
  ublk: remove the empty open and release block device operations
  ublk: remove UBLK_IO_F_PREFLUSH
  ublk: add a MAINTAINERS entry
  block: don't allow the same type rq_qos add more than once
  mmc: fix disk/queue leak in case of adding disk failure
  ublk_drv: fix an IS_ERR() vs NULL check
  ublk: remove UBLK_IO_F_INTEGRITY
  ublk_drv: remove unneeded semicolon
  ...

1 files changed, 32 insertions, 48 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 278227ba1d53..e1d5b10ac193 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -101,29 +101,6 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
 }
 EXPORT_SYMBOL_GPL(set_capacity_and_notify);
 
-/*
- * Format the device name of the indicated block device into the supplied buffer
- * and return a pointer to that same buffer for convenience.
- *
- * Note: do not use this in new code, use the %pg specifier to sprintf and
- * printk insted.
- */
-const char *bdevname(struct block_device *bdev, char *buf)
-{
-	struct gendisk *hd = bdev->bd_disk;
-	int partno = bdev->bd_partno;
-
-	if (!partno)
-		snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
-	else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
-		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
-	else
-		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
-
-	return buf;
-}
-EXPORT_SYMBOL(bdevname);
-
 static void part_stat_read_all(struct block_device *part,
 		struct disk_stats *stat)
 {
@@ -617,6 +594,8 @@ void del_gendisk(struct gendisk *disk)
 	 * Fail any new I/O.
 	 */
 	set_bit(GD_DEAD, &disk->state);
+	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+		blk_queue_flag_set(QUEUE_FLAG_DYING, q);
 	set_capacity(disk, 0);
 
 	/*
@@ -663,11 +642,16 @@ void del_gendisk(struct gendisk *disk)
 	blk_mq_unquiesce_queue(q);
 
 	/*
-	 * Allow using passthrough request again after the queue is torn down.
+	 * If the disk does not own the queue, allow using passthrough requests
+	 * again.  Else leave the queue frozen to fail all I/O.
 	 */
-	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
-	__blk_mq_unfreeze_queue(q, true);
-
+	if (!test_bit(GD_OWNS_QUEUE, &disk->state)) {
+		blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+		__blk_mq_unfreeze_queue(q, true);
+	} else {
+		if (queue_is_mq(q))
+			blk_mq_exit_queue(q);
+	}
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -1127,6 +1111,9 @@ static struct attribute_group disk_attr_group = {
 
 static const struct attribute_group *disk_attr_groups[] = {
 	&disk_attr_group,
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	&blk_trace_attr_group,
+#endif
 	NULL
 };
 
@@ -1151,10 +1138,23 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
+	/*
+	 * To undo the all initialization from blk_mq_init_allocated_queue in
+	 * case of a probe failure where add_disk is never called we have to
+	 * call blk_mq_exit_queue here. We can't do this for the more common
+	 * teardown case (yet) as the tagset can be gone by the time the disk
+	 * is released once it was added.
+	 */
+	if (queue_is_mq(disk->queue) &&
+	    test_bit(GD_OWNS_QUEUE, &disk->state) &&
+	    !test_bit(GD_ADDED, &disk->state))
+		blk_mq_exit_queue(disk->queue);
+
 	blkcg_exit_queue(disk->queue);
 
 	disk_release_events(disk);
 	kfree(disk->random);
+	disk_free_zone_bitmaps(disk);
 	xa_destroy(&disk->part_tbl);
 
 	disk->queue->disk = NULL;
@@ -1338,9 +1338,6 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 {
 	struct gendisk *disk;
 
-	if (!blk_get_queue(q))
-		return NULL;
-
 	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
 	if (!disk)
 		goto out_put_queue;
@@ -1391,7 +1388,6 @@ out_put_queue:
 	blk_put_queue(q);
 	return NULL;
 }
-EXPORT_SYMBOL(__alloc_disk_node);
 
 struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
 {
@@ -1404,9 +1400,10 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
 
 	disk = __alloc_disk_node(q, node, lkclass);
 	if (!disk) {
-		blk_cleanup_queue(q);
+		blk_put_queue(q);
 		return NULL;
 	}
+	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;
 }
 EXPORT_SYMBOL(__blk_alloc_disk);
@@ -1418,6 +1415,9 @@ EXPORT_SYMBOL(__blk_alloc_disk);
  * This decrements the refcount for the struct gendisk. When this reaches 0
  * we'll have disk_release() called.
  *
+ * Note: for blk-mq disk put_disk must be called before freeing the tag_set
+ * when handling probe errors (that is before add_disk() is called).
+ *
  * Context: Any context, but the last reference must not be dropped from
  *          atomic context.
  */
@@ -1428,22 +1428,6 @@ void put_disk(struct gendisk *disk)
 }
 EXPORT_SYMBOL(put_disk);
 
-/**
- * blk_cleanup_disk - shutdown a gendisk allocated by blk_alloc_disk
- * @disk: gendisk to shutdown
- *
- * Mark the queue hanging off @disk DYING, drain all pending requests, then mark
- * the queue DEAD, destroy and put it and the gendisk structure.
- *
- * Context: can sleep
- */
-void blk_cleanup_disk(struct gendisk *disk)
-{
-	blk_cleanup_queue(disk->queue);
-	put_disk(disk);
-}
-EXPORT_SYMBOL(blk_cleanup_disk);
-
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
 	char event[] = "DISK_RO=1";