2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 06:34:11 +08:00
linux-next/fs/btrfs/disk-io.h
Qu Wenruo 2dfb1e43f5 btrfs: preallocate anon block device at first phase of snapshot creation
[BUG]
When the anonymous block device pool is exhausted, subvolume/snapshot
creation fails with EMFILE (Too many files open). This has been reported
by a user. The allocation happens in the second phase during transaction
commit where it's only way out is to abort the transaction

  BTRFS: Transaction aborted (error -24)
  WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs]
  RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs]
  Call Trace:
   create_pending_snapshots+0x82/0xa0 [btrfs]
   btrfs_commit_transaction+0x275/0x8c0 [btrfs]
   btrfs_mksubvol+0x4b9/0x500 [btrfs]
   btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs]
   btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs]
   btrfs_ioctl+0x11a4/0x2da0 [btrfs]
   do_vfs_ioctl+0xa9/0x640
   ksys_ioctl+0x67/0x90
   __x64_sys_ioctl+0x1a/0x20
   do_syscall_64+0x5a/0x110
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ---[ end trace 33f2f83f3d5250e9 ]---
  BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown
  BTRFS info (device sda1): forced readonly
  BTRFS warning (device sda1): Skipping commit of aborted transaction.
  BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown

[CAUSE]
When the global anonymous block device pool is exhausted, the following
call chain will fail, and lead to transaction abort:

 btrfs_ioctl_snap_create_v2()
 |- btrfs_ioctl_snap_create_transid()
    |- btrfs_mksubvol()
       |- btrfs_commit_transaction()
          |- create_pending_snapshot()
             |- btrfs_get_fs_root()
                |- btrfs_init_fs_root()
                   |- get_anon_bdev()

[FIX]
Although we can't enlarge the anonymous block device pool, at least we
can preallocate anon_dev for subvolume/snapshot in the first phase,
outside of transaction context and exactly at the moment the user calls
the creation ioctl.

Reported-by: Greed Rong <greedrong@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+=tHJX7nb9DPw@mail.gmail.com/
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-27 12:55:38 +02:00

147 lines
5.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#ifndef BTRFS_DISK_IO_H
#define BTRFS_DISK_IO_H
#define BTRFS_SUPER_INFO_OFFSET SZ_64K
#define BTRFS_SUPER_INFO_SIZE 4096
#define BTRFS_SUPER_MIRROR_MAX 3
#define BTRFS_SUPER_MIRROR_SHIFT 12
/*
* Fixed blocksize for all devices, applies to specific ways of reading
* metadata like superblock. Must meet the set_blocksize requirements.
*
* Do not change.
*/
#define BTRFS_BDEV_BLOCKSIZE (4096)
enum btrfs_wq_endio_type {
BTRFS_WQ_ENDIO_DATA,
BTRFS_WQ_ENDIO_METADATA,
BTRFS_WQ_ENDIO_FREE_SPACE,
BTRFS_WQ_ENDIO_RAID56,
};
static inline u64 btrfs_sb_offset(int mirror)
{
u64 start = SZ_16K;
if (mirror)
return start << (BTRFS_SUPER_MIRROR_SHIFT * mirror);
return BTRFS_SUPER_INFO_OFFSET;
}
struct btrfs_device;
struct btrfs_fs_devices;
void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_verify_level_key(struct extent_buffer *eb, int level,
struct btrfs_key *first_key, u64 parent_transid);
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 parent_transid, int level,
struct btrfs_key *first_key);
void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr);
struct extent_buffer *btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info,
u64 bytenr);
void btrfs_clean_tree_block(struct extent_buffer *buf);
int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options);
void __cold close_ctree(struct btrfs_fs_info *fs_info);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
int copy_num);
int btrfs_commit_super(struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
struct btrfs_key *key);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, bool check_ref);
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, dev_t anon_dev);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info);
void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
#endif
/*
* This function is used to grab the root, and avoid it is freed when we
* access it. But it doesn't ensure that the tree is not dropped.
*
* If you want to ensure the whole tree is safe, you should use
* fs_info->subvol_srcu
*/
static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root)
{
if (!root)
return NULL;
if (refcount_inc_not_zero(&root->refs))
return root;
return NULL;
}
void btrfs_put_root(struct btrfs_root *root);
void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
int atomic);
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
struct btrfs_key *first_key);
blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
enum btrfs_wq_endio_type metadata);
blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset, void *private_data,
extent_submit_bio_start_t *submit_bio_start);
blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
int mirror_num);
int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
u64 objectid);
int btree_lock_page_hook(struct page *page, void *data,
void (*flush_fn)(void *));
struct extent_map *btree_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 len);
int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
int __init btrfs_end_io_wq_init(void);
void __cold btrfs_end_io_wq_exit(void);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void btrfs_init_lockdep(void);
void btrfs_set_buffer_lockdep_class(u64 objectid,
struct extent_buffer *eb, int level);
#else
static inline void btrfs_init_lockdep(void)
{ }
static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
struct extent_buffer *eb, int level)
{
}
#endif
#endif