Merge tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:

 - disk events cleanup (Christoph)

 - gendisk and request queue allocation simplifications (Christoph)

 - bdev_disk_changed cleanups (Christoph)

 - IO priority improvements (Bart)

 - Chained bio completion trace fix (Edward)

 - blk-wbt fixes (Jan)

 - blk-wbt enable/disable fix (Zhang)

 - Scheduler dispatch improvements (Jan, Ming)

 - Shared tagset scheduler improvements (John)

 - BFQ updates (Paolo, Luca, Pietro)

 - BFQ lock inversion fix (Jan)

 - Documentation improvements (Kir)

 - CLONE_IO block cgroup fix (Tejun)

 - Remove of ancient and deprecated block dump feature (zhangyi)

 - Discard merge fix (Ming)

 - Misc fixes or followup fixes (Colin, Damien, Dan, Long, Max, Thomas,
   Yang)

* tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block: (129 commits)
  block: fix discard request merge
  block/mq-deadline: Remove a WARN_ON_ONCE() call
  blk-mq: update hctx->dispatch_busy in case of real scheduler
  blk: Fix lock inversion between ioc lock and bfqd lock
  bfq: Remove merged request already in bfq_requests_merged()
  block: pass a gendisk to bdev_disk_changed
  block: move bdev_disk_changed
  block: add the events* attributes to disk_attrs
  block: move the disk events code to a separate file
  block: fix trace completion for chained bio
  block/partitions/msdos: Fix typo inidicator -> indicator
  block, bfq: reset waker pointer with shared queues
  block, bfq: check waker only for queues with no in-flight I/O
  block, bfq: avoid delayed merge of async queues
  block, bfq: boost throughput by extending queue-merging times
  block, bfq: consider also creation time in delayed stable merge
  block, bfq: fix delayed stable merge check
  block, bfq: let also stably merged queues enjoy weight raising
  blk-wbt: make sure throttle is enabled properly
  blk-wbt: introduce a new disable state to prevent false positive by rwb_enabled()
  ...

4 files changed, 97 insertions, 182 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index eb34f5c357cf..ca8bf1869ca8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -895,7 +895,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	mapping_set_gfp_mask(&inode->i_data, GFP_USER);
 
 	bdev = I_BDEV(inode);
-	mutex_init(&bdev->bd_mutex);
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
 	bdev->bd_disk = disk;
@@ -1154,7 +1153,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	struct bd_holder_disk *holder;
 	int ret = 0;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&bdev->bd_disk->open_mutex);
 
 	WARN_ON_ONCE(!bdev->bd_holder);
 
@@ -1199,7 +1198,7 @@ out_del:
 out_free:
 	kfree(holder);
 out_unlock:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&bdev->bd_disk->open_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(bd_link_disk_holder);
@@ -1218,7 +1217,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 {
 	struct bd_holder_disk *holder;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&bdev->bd_disk->open_mutex);
 
 	holder = bd_find_holder_disk(bdev, disk);
 
@@ -1230,138 +1229,97 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		kfree(holder);
 	}
 
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&bdev->bd_disk->open_mutex);
 }
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 #endif
 
-static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
+static void blkdev_flush_mapping(struct block_device *bdev)
+{
+	WARN_ON_ONCE(bdev->bd_holders);
+	sync_blockdev(bdev);
+	kill_bdev(bdev);
+	bdev_write_inode(bdev);
+}
 
-int bdev_disk_changed(struct block_device *bdev, bool invalidate)
+static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	int ret = 0;
 
-	lockdep_assert_held(&bdev->bd_mutex);
-
-	if (!(disk->flags & GENHD_FL_UP))
-		return -ENXIO;
-
-rescan:
-	if (bdev->bd_part_count)
-		return -EBUSY;
-	sync_blockdev(bdev);
-	invalidate_bdev(bdev);
-	blk_drop_partitions(disk);
-
-	clear_bit(GD_NEED_PART_SCAN, &disk->state);
-
-	/*
-	 * Historically we only set the capacity to zero for devices that
-	 * support partitions (independ of actually having partitions created).
-	 * Doing that is rather inconsistent, but changing it broke legacy
-	 * udisks polling for legacy ide-cdrom devices.  Use the crude check
-	 * below to get the sane behavior for most device while not breaking
-	 * userspace for this particular setup.
-	 */
-	if (invalidate) {
-		if (disk_part_scan_enabled(disk) ||
-		    !(disk->flags & GENHD_FL_REMOVABLE))
-			set_capacity(disk, 0);
+	if (disk->fops->open) {
+		ret = disk->fops->open(bdev, mode);
+		if (ret) {
+			/* avoid ghost partitions on a removed medium */
+			if (ret == -ENOMEDIUM &&
+			     test_bit(GD_NEED_PART_SCAN, &disk->state))
+				bdev_disk_changed(disk, true);
+			return ret;
+		}
 	}
 
-	if (get_capacity(disk)) {
-		ret = blk_add_partitions(disk, bdev);
-		if (ret == -EAGAIN)
-			goto rescan;
-	} else if (invalidate) {
-		/*
-		 * Tell userspace that the media / partition table may have
-		 * changed.
-		 */
-		kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+	if (!bdev->bd_openers) {
+		set_init_blocksize(bdev);
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	}
+	if (test_bit(GD_NEED_PART_SCAN, &disk->state))
+		bdev_disk_changed(disk, false);
+	bdev->bd_openers++;
+	return 0;;
+}
 
-	return ret;
+static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
+{
+	if (!--bdev->bd_openers)
+		blkdev_flush_mapping(bdev);
+	if (bdev->bd_disk->fops->release)
+		bdev->bd_disk->fops->release(bdev->bd_disk, mode);
 }
-/*
- * Only exported for loop and dasd for historic reasons.  Don't use in new
- * code!
- */
-EXPORT_SYMBOL_GPL(bdev_disk_changed);
 
-/*
- * bd_mutex locking:
- *
- *  mutex_lock(part->bd_mutex)
- *    mutex_lock_nested(whole->bd_mutex, 1)
- */
-static int __blkdev_get(struct block_device *bdev, fmode_t mode)
+static int blkdev_get_part(struct block_device *part, fmode_t mode)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	int ret = 0;
+	struct gendisk *disk = part->bd_disk;
+	struct block_device *whole;
+	int ret;
 
-	if (!(disk->flags & GENHD_FL_UP))
-		return -ENXIO;
+	if (part->bd_openers)
+		goto done;
 
-	if (!bdev->bd_openers) {
-		if (!bdev_is_partition(bdev)) {
-			ret = 0;
-			if (disk->fops->open)
-				ret = disk->fops->open(bdev, mode);
+	whole = bdgrab(disk->part0);
+	ret = blkdev_get_whole(whole, mode);
+	if (ret)
+		goto out_put_whole;
 
-			if (!ret)
-				set_init_blocksize(bdev);
+	ret = -ENXIO;
+	if (!bdev_nr_sectors(part))
+		goto out_blkdev_put;
 
-			/*
-			 * If the device is invalidated, rescan partition
-			 * if open succeeded or failed with -ENOMEDIUM.
-			 * The latter is necessary to prevent ghost
-			 * partitions on a removed medium.
-			 */
-			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
-			    (!ret || ret == -ENOMEDIUM))
-				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
+	disk->open_partitions++;
+	set_init_blocksize(part);
+	if (part->bd_bdi == &noop_backing_dev_info)
+		part->bd_bdi = bdi_get(disk->queue->backing_dev_info);
+done:
+	part->bd_openers++;
+	return 0;
 
-			if (ret)
-				return ret;
-		} else {
-			struct block_device *whole = bdgrab(disk->part0);
-
-			mutex_lock_nested(&whole->bd_mutex, 1);
-			ret = __blkdev_get(whole, mode);
-			if (ret) {
-				mutex_unlock(&whole->bd_mutex);
-				bdput(whole);
-				return ret;
-			}
-			whole->bd_part_count++;
-			mutex_unlock(&whole->bd_mutex);
+out_blkdev_put:
+	blkdev_put_whole(whole, mode);
+out_put_whole:
+	bdput(whole);
+	return ret;
+}
 
-			if (!bdev_nr_sectors(bdev)) {
-				__blkdev_put(whole, mode, 1);
-				bdput(whole);
-				return -ENXIO;
-			}
-			set_init_blocksize(bdev);
-		}
+static void blkdev_put_part(struct block_device *part, fmode_t mode)
+{
+	struct block_device *whole = bdev_whole(part);
 
-		if (bdev->bd_bdi == &noop_backing_dev_info)
-			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
-	} else {
-		if (!bdev_is_partition(bdev)) {
-			if (bdev->bd_disk->fops->open)
-				ret = bdev->bd_disk->fops->open(bdev, mode);
-			/* the same as first opener case, read comment there */
-			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
-			    (!ret || ret == -ENOMEDIUM))
-				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
-			if (ret)
-				return ret;
-		}
-	}
-	bdev->bd_openers++;
-	return 0;
+	if (--part->bd_openers)
+		return;
+	blkdev_flush_mapping(part);
+	whole->bd_disk->open_partitions--;
+	blkdev_put_whole(whole, mode);
+	bdput(whole);
 }
 
 struct block_device *blkdev_get_no_open(dev_t dev)
@@ -1447,8 +1405,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 
 	disk_block_events(disk);
 
-	mutex_lock(&bdev->bd_mutex);
-	ret =__blkdev_get(bdev, mode);
+	mutex_lock(&disk->open_mutex);
+	ret = -ENXIO;
+	if (!(disk->flags & GENHD_FL_UP))
+		goto abort_claiming;
+	if (bdev_is_partition(bdev))
+		ret = blkdev_get_part(bdev, mode);
+	else
+		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
 		goto abort_claiming;
 	if (mode & FMODE_EXCL) {
@@ -1467,7 +1431,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 			unblock_events = false;
 		}
 	}
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&disk->open_mutex);
 
 	if (unblock_events)
 		disk_unblock_events(disk);
@@ -1476,7 +1440,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 abort_claiming:
 	if (mode & FMODE_EXCL)
 		bd_abort_claiming(bdev, holder);
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
 put_blkdev:
 	blkdev_put_no_open(bdev);
@@ -1551,10 +1515,9 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return 0;
 }
 
-static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
+void blkdev_put(struct block_device *bdev, fmode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct block_device *victim = NULL;
 
 	/*
 	 * Sync early if it looks like we're the last one.  If someone else
@@ -1566,41 +1529,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	if (bdev->bd_openers == 1)
 		sync_blockdev(bdev);
 
-	mutex_lock_nested(&bdev->bd_mutex, for_part);
-	if (for_part)
-		bdev->bd_part_count--;
-
-	if (!--bdev->bd_openers) {
-		WARN_ON_ONCE(bdev->bd_holders);
-		sync_blockdev(bdev);
-		kill_bdev(bdev);
-		bdev_write_inode(bdev);
-		if (bdev_is_partition(bdev))
-			victim = bdev_whole(bdev);
-	}
-
-	if (!bdev_is_partition(bdev) && disk->fops->release)
-		disk->fops->release(disk, mode);
-	mutex_unlock(&bdev->bd_mutex);
-	if (victim) {
-		__blkdev_put(victim, mode, 1);
-		bdput(victim);
-	}
-}
-
-void blkdev_put(struct block_device *bdev, fmode_t mode)
-{
-	struct gendisk *disk = bdev->bd_disk;
-
-	mutex_lock(&bdev->bd_mutex);
-
+	mutex_lock(&disk->open_mutex);
 	if (mode & FMODE_EXCL) {
 		struct block_device *whole = bdev_whole(bdev);
 		bool bdev_free;
 
 		/*
 		 * Release a claim on the device.  The holder fields
-		 * are protected with bdev_lock.  bd_mutex is to
+		 * are protected with bdev_lock.  open_mutex is to
 		 * synchronize disk_holder unlinking.
 		 */
 		spin_lock(&bdev_lock);
@@ -1631,9 +1567,13 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	 * from userland - e.g. eject(1).
 	 */
 	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
-	mutex_unlock(&bdev->bd_mutex);
 
-	__blkdev_put(bdev, mode, 0);
+	if (bdev_is_partition(bdev))
+		blkdev_put_part(bdev, mode);
+	else
+		blkdev_put_whole(bdev, mode);
+	mutex_unlock(&disk->open_mutex);
+
 	blkdev_put_no_open(bdev);
 }
 EXPORT_SYMBOL(blkdev_put);
@@ -1941,10 +1881,10 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 		old_inode = inode;
 		bdev = I_BDEV(inode);
 
-		mutex_lock(&bdev->bd_mutex);
+		mutex_lock(&bdev->bd_disk->open_mutex);
 		if (bdev->bd_openers)
 			func(bdev, arg);
-		mutex_unlock(&bdev->bd_mutex);
+		mutex_unlock(&bdev->bd_disk->open_mutex);
 
 		spin_lock(&blockdev_superblock->s_inode_list_lock);
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 782e16795bc4..807502cd6510 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1247,7 +1247,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	lockdep_assert_held(&uuid_mutex);
 	/*
 	 * The device_list_mutex cannot be taken here in case opening the
-	 * underlying device takes further locks like bd_mutex.
+	 * underlying device takes further locks like open_mutex.
 	 *
 	 * We also don't need the lock here as this is called during mount and
 	 * exclusion is provided by uuid_mutex
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 62193106683d..8c7e9e51a398 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2343,28 +2343,6 @@ int dirtytime_interval_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static noinline void block_dump___mark_inode_dirty(struct inode *inode)
-{
-	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
-		struct dentry *dentry;
-		const char *name = "?";
-
-		dentry = d_find_alias(inode);
-		if (dentry) {
-			spin_lock(&dentry->d_lock);
-			name = (const char *) dentry->d_name.name;
-		}
-		printk(KERN_DEBUG
-		       "%s(%d): dirtied inode %lu (%s) on %s\n",
-		       current->comm, task_pid_nr(current), inode->i_ino,
-		       name, inode->i_sb->s_id);
-		if (dentry) {
-			spin_unlock(&dentry->d_lock);
-			dput(dentry);
-		}
-	}
-}
-
 /**
  * __mark_inode_dirty -	internal function to mark an inode dirty
  *
@@ -2434,9 +2412,6 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	    (dirtytime && (inode->i_state & I_DIRTY_INODE)))
 		return;
 
-	if (unlikely(block_dump))
-		block_dump___mark_inode_dirty(inode);
-
 	spin_lock(&inode->i_lock);
 	if (dirtytime && (inode->i_state & I_DIRTY_INODE))
 		goto out_unlock_inode;
diff --git a/fs/super.c b/fs/super.c
index 11b7e7213fd1..91b7f156735b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1277,9 +1277,9 @@ int get_tree_bdev(struct fs_context *fc,
 		}
 
 		/*
-		 * s_umount nests inside bd_mutex during
+		 * s_umount nests inside open_mutex during
 		 * __invalidate_device().  blkdev_put() acquires
-		 * bd_mutex and can't be called under s_umount.  Drop
+		 * open_mutex and can't be called under s_umount.  Drop
 		 * s_umount temporarily.  This is safe as we're
 		 * holding an active reference.
 		 */
@@ -1352,9 +1352,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 		}
 
 		/*
-		 * s_umount nests inside bd_mutex during
+		 * s_umount nests inside open_mutex during
 		 * __invalidate_device().  blkdev_put() acquires
-		 * bd_mutex and can't be called under s_umount.  Drop
+		 * open_mutex and can't be called under s_umount.  Drop
 		 * s_umount temporarily.  This is safe as we're
 		 * holding an active reference.
 		 */