Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

1 files changed, 81 insertions, 57 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 95a1ee3d314e..e1ea3a7bd9d9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -732,28 +732,48 @@ static char *_dm_claim_ptr = "I belong to device-mapper";
 /*
  * Open a table device so we can use it as a map destination.
  */
-static int open_table_device(struct table_device *td, dev_t dev,
-			     struct mapped_device *md)
+static struct table_device *open_table_device(struct mapped_device *md,
+		dev_t dev, fmode_t mode)
 {
+	struct table_device *td;
 	struct block_device *bdev;
 	u64 part_off;
 	int r;
 
-	BUG_ON(td->dm_dev.bdev);
+	td = kmalloc_node(sizeof(*td), GFP_KERNEL, md->numa_node_id);
+	if (!td)
+		return ERR_PTR(-ENOMEM);
+	refcount_set(&td->count, 1);
 
-	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+	bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr);
+	if (IS_ERR(bdev)) {
+		r = PTR_ERR(bdev);
+		goto out_free_td;
+	}
 
-	r = bd_link_disk_holder(bdev, dm_disk(md));
-	if (r) {
-		blkdev_put(bdev, td->dm_dev.mode | FMODE_EXCL);
-		return r;
+	/*
+	 * We can be called before the dm disk is added.  In that case we can't
+	 * register the holder relation here.  It will be done once add_disk was
+	 * called.
+	 */
+	if (md->disk->slave_dir) {
+		r = bd_link_disk_holder(bdev, md->disk);
+		if (r)
+			goto out_blkdev_put;
 	}
 
+	td->dm_dev.mode = mode;
 	td->dm_dev.bdev = bdev;
 	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off, NULL, NULL);
-	return 0;
+	format_dev_t(td->dm_dev.name, dev);
+	list_add(&td->list, &md->table_devices);
+	return td;
+
+out_blkdev_put:
+	blkdev_put(bdev, mode | FMODE_EXCL);
+out_free_td:
+	kfree(td);
+	return ERR_PTR(r);
 }
 
 /*
@@ -761,14 +781,12 @@ static int open_table_device(struct table_device *td, dev_t dev,
  */
 static void close_table_device(struct table_device *td, struct mapped_device *md)
 {
-	if (!td->dm_dev.bdev)
-		return;
-
-	bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md));
+	if (md->disk->slave_dir)
+		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
 	blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
 	put_dax(td->dm_dev.dax_dev);
-	td->dm_dev.bdev = NULL;
-	td->dm_dev.dax_dev = NULL;
+	list_del(&td->list);
+	kfree(td);
 }
 
 static struct table_device *find_table_device(struct list_head *l, dev_t dev,
@@ -786,31 +804,16 @@ static struct table_device *find_table_device(struct list_head *l, dev_t dev,
 int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
 			struct dm_dev **result)
 {
-	int r;
 	struct table_device *td;
 
 	mutex_lock(&md->table_devices_lock);
 	td = find_table_device(&md->table_devices, dev, mode);
 	if (!td) {
-		td = kmalloc_node(sizeof(*td), GFP_KERNEL, md->numa_node_id);
-		if (!td) {
+		td = open_table_device(md, dev, mode);
+		if (IS_ERR(td)) {
 			mutex_unlock(&md->table_devices_lock);
-			return -ENOMEM;
+			return PTR_ERR(td);
 		}
-
-		td->dm_dev.mode = mode;
-		td->dm_dev.bdev = NULL;
-
-		if ((r = open_table_device(td, dev, md))) {
-			mutex_unlock(&md->table_devices_lock);
-			kfree(td);
-			return r;
-		}
-
-		format_dev_t(td->dm_dev.name, dev);
-
-		refcount_set(&td->count, 1);
-		list_add(&td->list, &md->table_devices);
 	} else {
 		refcount_inc(&td->count);
 	}
@@ -825,27 +828,11 @@ void dm_put_table_device(struct mapped_device *md, struct dm_dev *d)
 	struct table_device *td = container_of(d, struct table_device, dm_dev);
 
 	mutex_lock(&md->table_devices_lock);
-	if (refcount_dec_and_test(&td->count)) {
+	if (refcount_dec_and_test(&td->count))
 		close_table_device(td, md);
-		list_del(&td->list);
-		kfree(td);
-	}
 	mutex_unlock(&md->table_devices_lock);
 }
 
-static void free_table_devices(struct list_head *devices)
-{
-	struct list_head *tmp, *next;
-
-	list_for_each_safe(tmp, next, devices) {
-		struct table_device *td = list_entry(tmp, struct table_device, list);
-
-		DMWARN("dm_destroy: %s still exists with %d references",
-		       td->dm_dev.name, refcount_read(&td->count));
-		kfree(td);
-	}
-}
-
 /*
  * Get the geometry associated with a dm device
  */
@@ -1972,8 +1959,21 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		md->disk->private_data = NULL;
 		spin_unlock(&_minor_lock);
 		if (dm_get_md_type(md) != DM_TYPE_NONE) {
+			struct table_device *td;
+
 			dm_sysfs_exit(md);
+			list_for_each_entry(td, &md->table_devices, list) {
+				bd_unlink_disk_holder(td->dm_dev.bdev,
+						      md->disk);
+			}
+
+			/*
+			 * Hold lock to make sure del_gendisk() won't concurrent
+			 * with open/close_table_device().
+			 */
+			mutex_lock(&md->table_devices_lock);
 			del_gendisk(md->disk);
+			mutex_unlock(&md->table_devices_lock);
 		}
 		dm_queue_destroy_crypto_profile(md->queue);
 		put_disk(md->disk);
@@ -2122,7 +2122,7 @@ static void free_dev(struct mapped_device *md)
 
 	cleanup_mapped_device(md);
 
-	free_table_devices(&md->table_devices);
+	WARN_ON_ONCE(!list_empty(&md->table_devices));
 	dm_stats_cleanup(&md->stats);
 	free_minor(minor);
 
@@ -2305,6 +2305,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 {
 	enum dm_queue_mode type = dm_table_get_type(t);
 	struct queue_limits limits;
+	struct table_device *td;
 	int r;
 
 	switch (type) {
@@ -2333,17 +2334,40 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 	if (r)
 		return r;
 
+	/*
+	 * Hold lock to make sure add_disk() and del_gendisk() won't concurrent
+	 * with open_table_device() and close_table_device().
+	 */
+	mutex_lock(&md->table_devices_lock);
 	r = add_disk(md->disk);
+	mutex_unlock(&md->table_devices_lock);
 	if (r)
 		return r;
 
-	r = dm_sysfs_init(md);
-	if (r) {
-		del_gendisk(md->disk);
-		return r;
+	/*
+	 * Register the holder relationship for devices added before the disk
+	 * was live.
+	 */
+	list_for_each_entry(td, &md->table_devices, list) {
+		r = bd_link_disk_holder(td->dm_dev.bdev, md->disk);
+		if (r)
+			goto out_undo_holders;
 	}
+
+	r = dm_sysfs_init(md);
+	if (r)
+		goto out_undo_holders;
+
 	md->type = type;
 	return 0;
+
+out_undo_holders:
+	list_for_each_entry_continue_reverse(td, &md->table_devices, list)
+		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
+	mutex_lock(&md->table_devices_lock);
+	del_gendisk(md->disk);
+	mutex_unlock(&md->table_devices_lock);
+	return r;
 }
 
 struct mapped_device *dm_get_md(dev_t dev)