Commit 5f0addf7 authored by Naohiro Aota's avatar Naohiro Aota Committed by David Sterba

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: 35156d85 ("btrfs: zoned: only allow one process to add pages to a relocation inode")
CC: stable@vger.kernel.org # 5.16.x: 869f4cdc: 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: default avatarJohannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: default avatarNaohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent a692e13d
...@@ -1060,6 +1060,7 @@ struct btrfs_fs_info { ...@@ -1060,6 +1060,7 @@ struct btrfs_fs_info {
*/ */
spinlock_t relocation_bg_lock; spinlock_t relocation_bg_lock;
u64 data_reloc_bg; u64 data_reloc_bg;
struct mutex zoned_data_reloc_io_lock;
u64 nr_global_roots; u64 nr_global_roots;
......
...@@ -3156,6 +3156,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) ...@@ -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->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->delalloc_root_mutex);
mutex_init(&fs_info->zoned_meta_io_lock); mutex_init(&fs_info->zoned_meta_io_lock);
mutex_init(&fs_info->zoned_data_reloc_io_lock);
seqlock_init(&fs_info->profiles_lock); seqlock_init(&fs_info->profiles_lock);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
......
...@@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode) ...@@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
struct btrfs_root *root = inode->root; struct btrfs_root *root = inode->root;
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) 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) 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) ...@@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
struct btrfs_root *root = inode->root; struct btrfs_root *root = inode->root;
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) 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 #endif
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment