btrfs: zoned: use dedicated lock for data relocation

Currently, we use btrfs_inode_{lock,unlock}() to grant an exclusive
writeback of the relocation data inode in
btrfs_zoned_data_reloc_{lock,unlock}(). However, that can cause a deadlock
in the following path.

Thread A takes btrfs_inode_lock() and waits for metadata reservation by
e.g, waiting for writeback:

prealloc_file_extent_cluster()
  - btrfs_inode_lock(&inode->vfs_inode, 0);
  - btrfs_prealloc_file_range()
  ...
    - btrfs_replace_file_extents()
      - btrfs_start_transaction
      ...
        - btrfs_reserve_metadata_bytes()

Thread B (e.g, doing a writeback work) needs to wait for the inode lock to
continue writeback process:

do_writepages
  - btrfs_writepages
    - extent_writpages
      - btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
        - btrfs_inode_lock()

The deadlock is caused by relying on the vfs_inode's lock. By using it, we
introduced unnecessary exclusion of writeback and
btrfs_prealloc_file_range(). Also, the lock at this point is useless as we
don't have any dirty pages in the inode yet.

Introduce fs_info->zoned_data_reloc_io_lock and use it for the exclusive
writeback.

Fixes: 5ec7c05c9358 ("btrfs: zoned: only allow one process to add pages to a relocation inode")
CC: stable@vger.kernel.org # 5.16.x: fbe485f95555: btrfs: zoned: encapsulate inode locking for zoned relocation
CC: stable@vger.kernel.org # 5.16.x
CC: stable@vger.kernel.org # 5.17
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4db17bd05a21508258f7c053fb3b925e0ceb5876..604a4d54cf0d4a3bfad1b9285641b20ea65becf5 100644 (file)
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1060,6 +1060,7 @@ struct btrfs_fs_info {
         */
        spinlock_t relocation_bg_lock;
        u64 data_reloc_bg;
+       struct mutex zoned_data_reloc_io_lock;
 
        u64 nr_global_roots;
 

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index cebd7a78c964fcc76ecd3aa8c65af997a23ca91d..20e70eb88465c63bffbd244012740eb4e8426ae6 100644 (file)
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3156,6 +3156,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
        mutex_init(&fs_info->reloc_mutex);
        mutex_init(&fs_info->delalloc_root_mutex);
        mutex_init(&fs_info->zoned_meta_io_lock);
+       mutex_init(&fs_info->zoned_data_reloc_io_lock);
        seqlock_init(&fs_info->profiles_lock);
 
        INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);

diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index cbf016a7bb5dd393873d555a3d347b9e0fc46d18..6dee76248cb4da37c8a1efe01045e6f9ffeda8fb 100644 (file)
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
        struct btrfs_root *root = inode->root;
 
        if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
-               btrfs_inode_lock(&inode->vfs_inode, 0);
+               mutex_lock(&root->fs_info->zoned_data_reloc_io_lock);
 }
 
 static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
@@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
        struct btrfs_root *root = inode->root;
 
        if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
-               btrfs_inode_unlock(&inode->vfs_inode, 0);
+               mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock);
 }
 
 #endif