Merge tag 'vfs-6.7.super' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs superblock updates from Christian Brauner:
 "This contains the work to make block device opening functions return a
  struct bdev_handle instead of just a struct block_device. The same
  struct bdev_handle is then also passed to block device closing
  functions.

  This allows us to propagate context from opening to closing a block
  device without having to modify all users everytime.

  Sidenote, in the future we might even want to try and have block
  device opening functions return a struct file directly but that's a
  series on top of this.

  These are further preparatory changes to be able to count writable
  opens and blocking writes to mounted block devices. That's a separate
  piece of work for next cycle and for that we absolutely need the
  changes to btrfs that have been quietly dropped somehow.

  Originally the series contained a patch that removed the old
  blkdev_*() helpers. But since this would've caused needles churn in
  -next for bcachefs we ended up delaying it.

  The second piece of work addresses one of the major annoyances about
  the work last cycle, namely that we required dropping s_umount
  whenever we used the superblock and fs_holder_ops for a block device.

  The reason for that requirement had been that in some codepaths
  s_umount could've been taken under disk->open_mutex (that's always
  been the case, at least theoretically). For example, on surprise block
  device removal or media change. And opening and closing block devices
  required grabbing disk->open_mutex as well.

  So we did the work and went through the block layer and fixed all
  those places so that s_umount is never taken under disk->open_mutex.
  This means no more brittle games where we yield and reacquire s_umount
  during block device opening and closing and no more requirements where
  block devices need to be closed. Filesystems don't need to care about
  this.

  There's a bunch of other follow-up work such as moving block device
  freezing and thawing to holder operations which makes it work for all
  block devices and not just the main block device just as we did for
  surprise removal. But that is for next cycle.

  Tested with fstests for all major fses, blktests, LTP"

* tag 'vfs-6.7.super' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs: (37 commits)
  porting: update locking requirements
  fs: assert that open_mutex isn't held over holder ops
  block: assert that we're not holding open_mutex over blk_report_disk_dead
  block: move bdev_mark_dead out of disk_check_media_change
  block: WARN_ON_ONCE() when we remove active partitions
  block: simplify bdev_del_partition()
  fs: Avoid grabbing sb->s_umount under bdev->bd_holder_lock
  jfs: fix log->bdev_handle null ptr deref in lbmStartIO
  bcache: Fixup error handling in register_cache()
  xfs: Convert to bdev_open_by_path()
  reiserfs: Convert to bdev_open_by_dev/path()
  ocfs2: Convert to use bdev_open_by_dev()
  nfs/blocklayout: Convert to use bdev_open_by_dev/path()
  jfs: Convert to bdev_open_by_dev()
  f2fs: Convert to bdev_open_by_dev/path()
  ext4: Convert to bdev_open_by_dev()
  erofs: Convert to use bdev_open_by_path()
  btrfs: Convert to bdev_open_by_path()
  fs: Convert to bdev_open_by_dev()
  mm/swap: Convert to use bdev_open_by_dev()
  ...

4 files changed, 73 insertions, 72 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index fff22ed55c42..6b5b6cec13c4 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -247,6 +247,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
+	struct bdev_handle *bdev_handle;
 	struct block_device *bdev;
 	u64 devid = BTRFS_DEV_REPLACE_DEVID;
 	int ret = 0;
@@ -257,12 +258,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
-				  fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev)) {
+	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+					fs_info->bdev_holder, NULL);
+	if (IS_ERR(bdev_handle)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
-		return PTR_ERR(bdev);
+		return PTR_ERR(bdev_handle);
 	}
+	bdev = bdev_handle->bdev;
 
 	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
 		btrfs_err(fs_info,
@@ -313,9 +315,9 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	device->commit_bytes_used = device->bytes_used;
 	device->fs_info = fs_info;
 	device->bdev = bdev;
+	device->bdev_handle = bdev_handle;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
-	device->holder = fs_info->bdev_holder;
 	device->dev_stats_valid = 1;
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_devices;
@@ -334,7 +336,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	blkdev_put(bdev, fs_info->bdev_holder);
+	bdev_release(bdev_handle);
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8e7d03bc1b56..108edf8ffedf 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2676,8 +2676,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
-	struct block_device *bdev = NULL;
-	void *holder;
+	struct bdev_handle *bdev_handle = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2714,7 +2713,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto err_drop;
 
 	/* Exclusive operation is now claimed */
-	ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
+	ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -2728,8 +2727,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	}
 err_drop:
 	mnt_drop_write_file(file);
-	if (bdev)
-		blkdev_put(bdev, holder);
+	if (bdev_handle)
+		bdev_release(bdev_handle);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2742,8 +2741,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args *vol_args;
-	struct block_device *bdev = NULL;
-	void *holder;
+	struct bdev_handle *bdev_handle = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2770,15 +2768,15 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
+		ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
 	}
 
 	mnt_drop_write_file(file);
-	if (bdev)
-		blkdev_put(bdev, holder);
+	if (bdev_handle)
+		bdev_release(bdev_handle);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b9ef6f54635c..1f38affa4d9c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -511,37 +511,39 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid(
 
 static int
 btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
-		      int flush, struct block_device **bdev,
+		      int flush, struct bdev_handle **bdev_handle,
 		      struct btrfs_super_block **disk_super)
 {
+	struct block_device *bdev;
 	int ret;
 
-	*bdev = blkdev_get_by_path(device_path, flags, holder, NULL);
+	*bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL);
 
-	if (IS_ERR(*bdev)) {
-		ret = PTR_ERR(*bdev);
+	if (IS_ERR(*bdev_handle)) {
+		ret = PTR_ERR(*bdev_handle);
 		goto error;
 	}
+	bdev = (*bdev_handle)->bdev;
 
 	if (flush)
-		sync_blockdev(*bdev);
-	ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE);
+		sync_blockdev(bdev);
+	ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
-		blkdev_put(*bdev, holder);
+		bdev_release(*bdev_handle);
 		goto error;
 	}
-	invalidate_bdev(*bdev);
-	*disk_super = btrfs_read_dev_super(*bdev);
+	invalidate_bdev(bdev);
+	*disk_super = btrfs_read_dev_super(bdev);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		blkdev_put(*bdev, holder);
+		bdev_release(*bdev_handle);
 		goto error;
 	}
 
 	return 0;
 
 error:
-	*bdev = NULL;
+	*bdev_handle = NULL;
 	return ret;
 }
 
@@ -613,7 +615,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, blk_mode_t flags,
 			void *holder)
 {
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	struct btrfs_super_block *disk_super;
 	u64 devid;
 	int ret;
@@ -624,7 +626,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		return -EINVAL;
 
 	ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
-				    &bdev, &disk_super);
+				    &bdev_handle, &disk_super);
 	if (ret)
 		return ret;
 
@@ -648,21 +650,21 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		fs_devices->seeding = true;
 	} else {
-		if (bdev_read_only(bdev))
+		if (bdev_read_only(bdev_handle->bdev))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		else
 			set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	}
 
-	if (!bdev_nonrot(bdev))
+	if (!bdev_nonrot(bdev_handle->bdev))
 		fs_devices->rotating = true;
 
-	if (bdev_max_discard_sectors(bdev))
+	if (bdev_max_discard_sectors(bdev_handle->bdev))
 		fs_devices->discardable = true;
 
-	device->bdev = bdev;
+	device->bdev_handle = bdev_handle;
+	device->bdev = bdev_handle->bdev;
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
-	device->holder = holder;
 
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
@@ -676,7 +678,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	blkdev_put(bdev, holder);
+	bdev_release(bdev_handle);
 
 	return -EINVAL;
 }
@@ -1068,9 +1070,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 		if (device->devid == BTRFS_DEV_REPLACE_DEVID)
 			continue;
 
-		if (device->bdev) {
-			blkdev_put(device->bdev, device->holder);
+		if (device->bdev_handle) {
+			bdev_release(device->bdev_handle);
 			device->bdev = NULL;
+			device->bdev_handle = NULL;
 			fs_devices->open_devices--;
 		}
 		if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
@@ -1115,7 +1118,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	blkdev_put(device->bdev, device->holder);
+	bdev_release(device->bdev_handle);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1363,7 +1366,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags)
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	u64 bytenr, bytenr_orig;
 	int ret;
 
@@ -1386,18 +1389,19 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags)
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev = blkdev_get_by_path(path, flags, NULL, NULL);
-	if (IS_ERR(bdev))
-		return ERR_CAST(bdev);
+	bdev_handle = bdev_open_by_path(path, flags, NULL, NULL);
+	if (IS_ERR(bdev_handle))
+		return ERR_CAST(bdev_handle);
 
 	bytenr_orig = btrfs_sb_offset(0);
-	ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr);
+	ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr);
 	if (ret) {
 		device = ERR_PTR(ret);
 		goto error_bdev_put;
 	}
 
-	disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig);
+	disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr,
+					   bytenr_orig);
 	if (IS_ERR(disk_super)) {
 		device = ERR_CAST(disk_super);
 		goto error_bdev_put;
@@ -1410,7 +1414,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags)
 	btrfs_release_disk_super(disk_super);
 
 error_bdev_put:
-	blkdev_put(bdev, NULL);
+	bdev_release(bdev_handle);
 
 	return device;
 }
@@ -2087,7 +2091,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct block_device **bdev, void **holder)
+		    struct bdev_handle **bdev_handle)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
@@ -2196,7 +2200,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 
 	btrfs_assign_next_active_device(device, NULL);
 
-	if (device->bdev) {
+	if (device->bdev_handle) {
 		cur_devices->open_devices--;
 		/* remove sysfs entry */
 		btrfs_sysfs_remove_device(device);
@@ -2212,9 +2216,9 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	 * free the device.
 	 *
 	 * We cannot call btrfs_close_bdev() here because we're holding the sb
-	 * write lock, and blkdev_put() will pull in the ->open_mutex on the
-	 * block device and it's dependencies.  Instead just flush the device
-	 * and let the caller do the final blkdev_put.
+	 * write lock, and bdev_release() will pull in the ->open_mutex on
+	 * the block device and it's dependencies.  Instead just flush the
+	 * device and let the caller do the final bdev_release.
 	 */
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		btrfs_scratch_superblocks(fs_info, device->bdev,
@@ -2225,8 +2229,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	*bdev = device->bdev;
-	*holder = device->holder;
+	*bdev_handle = device->bdev_handle;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2363,7 +2366,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 				 const char *path)
 {
 	struct btrfs_super_block *disk_super;
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	int ret;
 
 	if (!path || !path[0])
@@ -2381,7 +2384,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
-				    &bdev, &disk_super);
+				    &bdev_handle, &disk_super);
 	if (ret) {
 		btrfs_put_dev_args_from_path(args);
 		return ret;
@@ -2394,7 +2397,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	else
 		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	blkdev_put(bdev, NULL);
+	bdev_release(bdev_handle);
 	return 0;
 }
 
@@ -2614,7 +2617,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	struct super_block *sb = fs_info->sb;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_fs_devices *seed_devices = NULL;
@@ -2627,12 +2630,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
-				  fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+					fs_info->bdev_holder, NULL);
+	if (IS_ERR(bdev_handle))
+		return PTR_ERR(bdev_handle);
 
-	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
+	if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -2644,11 +2647,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		locked = true;
 	}
 
-	sync_blockdev(bdev);
+	sync_blockdev(bdev_handle->bdev);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
-		if (device->bdev == bdev) {
+		if (device->bdev == bdev_handle->bdev) {
 			ret = -EEXIST;
 			rcu_read_unlock();
 			goto error;
@@ -2664,7 +2667,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 
 	device->fs_info = fs_info;
-	device->bdev = bdev;
+	device->bdev_handle = bdev_handle;
+	device->bdev = bdev_handle->bdev;
 	ret = lookup_bdev(device_path, &device->devt);
 	if (ret)
 		goto error_free_device;
@@ -2685,12 +2689,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	device->io_align = fs_info->sectorsize;
 	device->sector_size = fs_info->sectorsize;
 	device->total_bytes =
-		round_down(bdev_nr_bytes(bdev), fs_info->sectorsize);
+		round_down(bdev_nr_bytes(device->bdev), fs_info->sectorsize);
 	device->disk_total_bytes = device->total_bytes;
 	device->commit_total_bytes = device->total_bytes;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
-	device->holder = fs_info->bdev_holder;
 	device->dev_stats_valid = 1;
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 
@@ -2726,7 +2729,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
-	if (!bdev_nonrot(bdev))
+	if (!bdev_nonrot(device->bdev))
 		fs_devices->rotating = true;
 
 	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
@@ -2848,7 +2851,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	blkdev_put(bdev, fs_info->bdev_holder);
+	bdev_release(bdev_handle);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2128a032c3b7..1702cb7cac00 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -90,13 +90,11 @@ struct btrfs_device {
 
 	u64 generation;
 
+	struct bdev_handle *bdev_handle;
 	struct block_device *bdev;
 
 	struct btrfs_zoned_device_info *zone_info;
 
-	/* block device holder for blkdev_get/put */
-	void *holder;
-
 	/*
 	 * Device's major-minor number. Must be set even if the device is not
 	 * opened (bdev == NULL), unless the device is missing.
@@ -629,7 +627,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct block_device **bdev, void **holder);
+		    struct bdev_handle **bdev_handle);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,