alistair23-linux/fs/btrfs/transaction.h
Filipe Manana a6d155d2e3 Btrfs: fix deadlock between fiemap and transaction commits
The fiemap handler locks a file range that can have unflushed delalloc,
and after locking the range, it tries to attach to a running transaction.
If the running transaction started its commit, that is, it is in state
TRANS_STATE_COMMIT_START, and either the filesystem was mounted with the
flushoncommit option or the transaction is creating a snapshot for the
subvolume that contains the file that fiemap is operating on, we end up
deadlocking. This happens because fiemap is blocked on the transaction,
waiting for it to complete, and the transaction is waiting for the flushed
dealloc to complete, which requires locking the file range that the fiemap
task already locked. The following stack traces serve as an example of
when this deadlock happens:

  (...)
  [404571.515510] Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs]
  [404571.515956] Call Trace:
  [404571.516360]  ? __schedule+0x3ae/0x7b0
  [404571.516730]  schedule+0x3a/0xb0
  [404571.517104]  lock_extent_bits+0x1ec/0x2a0 [btrfs]
  [404571.517465]  ? remove_wait_queue+0x60/0x60
  [404571.517832]  btrfs_finish_ordered_io+0x292/0x800 [btrfs]
  [404571.518202]  normal_work_helper+0xea/0x530 [btrfs]
  [404571.518566]  process_one_work+0x21e/0x5c0
  [404571.518990]  worker_thread+0x4f/0x3b0
  [404571.519413]  ? process_one_work+0x5c0/0x5c0
  [404571.519829]  kthread+0x103/0x140
  [404571.520191]  ? kthread_create_worker_on_cpu+0x70/0x70
  [404571.520565]  ret_from_fork+0x3a/0x50
  [404571.520915] kworker/u8:6    D    0 31651      2 0x80004000
  [404571.521290] Workqueue: btrfs-flush_delalloc btrfs_flush_delalloc_helper [btrfs]
  (...)
  [404571.537000] fsstress        D    0 13117  13115 0x00004000
  [404571.537263] Call Trace:
  [404571.537524]  ? __schedule+0x3ae/0x7b0
  [404571.537788]  schedule+0x3a/0xb0
  [404571.538066]  wait_current_trans+0xc8/0x100 [btrfs]
  [404571.538349]  ? remove_wait_queue+0x60/0x60
  [404571.538680]  start_transaction+0x33c/0x500 [btrfs]
  [404571.539076]  btrfs_check_shared+0xa3/0x1f0 [btrfs]
  [404571.539513]  ? extent_fiemap+0x2ce/0x650 [btrfs]
  [404571.539866]  extent_fiemap+0x2ce/0x650 [btrfs]
  [404571.540170]  do_vfs_ioctl+0x526/0x6f0
  [404571.540436]  ksys_ioctl+0x70/0x80
  [404571.540734]  __x64_sys_ioctl+0x16/0x20
  [404571.540997]  do_syscall_64+0x60/0x1d0
  [404571.541279]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
  (...)
  [404571.543729] btrfs           D    0 14210  14208 0x00004000
  [404571.544023] Call Trace:
  [404571.544275]  ? __schedule+0x3ae/0x7b0
  [404571.544526]  ? wait_for_completion+0x112/0x1a0
  [404571.544795]  schedule+0x3a/0xb0
  [404571.545064]  schedule_timeout+0x1ff/0x390
  [404571.545351]  ? lock_acquire+0xa6/0x190
  [404571.545638]  ? wait_for_completion+0x49/0x1a0
  [404571.545890]  ? wait_for_completion+0x112/0x1a0
  [404571.546228]  wait_for_completion+0x131/0x1a0
  [404571.546503]  ? wake_up_q+0x70/0x70
  [404571.546775]  btrfs_wait_ordered_extents+0x27c/0x400 [btrfs]
  [404571.547159]  btrfs_commit_transaction+0x3b0/0xae0 [btrfs]
  [404571.547449]  ? btrfs_mksubvol+0x4a4/0x640 [btrfs]
  [404571.547703]  ? remove_wait_queue+0x60/0x60
  [404571.547969]  btrfs_mksubvol+0x605/0x640 [btrfs]
  [404571.548226]  ? __sb_start_write+0xd4/0x1c0
  [404571.548512]  ? mnt_want_write_file+0x24/0x50
  [404571.548789]  btrfs_ioctl_snap_create_transid+0x169/0x1a0 [btrfs]
  [404571.549048]  btrfs_ioctl_snap_create_v2+0x11d/0x170 [btrfs]
  [404571.549307]  btrfs_ioctl+0x133f/0x3150 [btrfs]
  [404571.549549]  ? mem_cgroup_charge_statistics+0x4c/0xd0
  [404571.549792]  ? mem_cgroup_commit_charge+0x84/0x4b0
  [404571.550064]  ? __handle_mm_fault+0xe3e/0x11f0
  [404571.550306]  ? do_raw_spin_unlock+0x49/0xc0
  [404571.550608]  ? _raw_spin_unlock+0x24/0x30
  [404571.550976]  ? __handle_mm_fault+0xedf/0x11f0
  [404571.551319]  ? do_vfs_ioctl+0xa2/0x6f0
  [404571.551659]  ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs]
  [404571.552087]  do_vfs_ioctl+0xa2/0x6f0
  [404571.552355]  ksys_ioctl+0x70/0x80
  [404571.552621]  __x64_sys_ioctl+0x16/0x20
  [404571.552864]  do_syscall_64+0x60/0x1d0
  [404571.553104]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
  (...)

If we were joining the transaction instead of attaching to it, we would
not risk a deadlock because a join only blocks if the transaction is in a
state greater then or equals to TRANS_STATE_COMMIT_DOING, and the delalloc
flush performed by a transaction is done before it reaches that state,
when it is in the state TRANS_STATE_COMMIT_START. However a transaction
join is intended for use cases where we do modify the filesystem, and
fiemap only needs to peek at delayed references from the current
transaction in order to determine if extents are shared, and, besides
that, when there is no current transaction or when it blocks to wait for
a current committing transaction to complete, it creates a new transaction
without reserving any space. Such unnecessary transactions, besides doing
unnecessary IO, can cause transaction aborts (-ENOSPC) and unnecessary
rotation of the precious backup roots.

So fix this by adding a new transaction join variant, named join_nostart,
which behaves like the regular join, but it does not create a transaction
when none currently exists or after waiting for a committing transaction
to complete.

Fixes: 03628cdbc6 ("Btrfs: do not start a transaction during fiemap")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-07-30 18:25:12 +02:00

233 lines
7.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#ifndef BTRFS_TRANSACTION_H
#define BTRFS_TRANSACTION_H
#include <linux/refcount.h>
#include "btrfs_inode.h"
#include "delayed-ref.h"
#include "ctree.h"
enum btrfs_trans_state {
TRANS_STATE_RUNNING,
TRANS_STATE_BLOCKED,
TRANS_STATE_COMMIT_START,
TRANS_STATE_COMMIT_DOING,
TRANS_STATE_UNBLOCKED,
TRANS_STATE_COMPLETED,
TRANS_STATE_MAX,
};
#define BTRFS_TRANS_HAVE_FREE_BGS 0
#define BTRFS_TRANS_DIRTY_BG_RUN 1
#define BTRFS_TRANS_CACHE_ENOSPC 2
struct btrfs_transaction {
u64 transid;
/*
* total external writers(USERSPACE/START/ATTACH) in this
* transaction, it must be zero before the transaction is
* being committed
*/
atomic_t num_extwriters;
/*
* total writers in this transaction, it must be zero before the
* transaction can end
*/
atomic_t num_writers;
refcount_t use_count;
unsigned long flags;
/* Be protected by fs_info->trans_lock when we want to change it. */
enum btrfs_trans_state state;
int aborted;
struct list_head list;
struct extent_io_tree dirty_pages;
time64_t start_time;
wait_queue_head_t writer_wait;
wait_queue_head_t commit_wait;
struct list_head pending_snapshots;
struct list_head dev_update_list;
struct list_head switch_commits;
struct list_head dirty_bgs;
/*
* There is no explicit lock which protects io_bgs, rather its
* consistency is implied by the fact that all the sites which modify
* it do so under some form of transaction critical section, namely:
*
* - btrfs_start_dirty_block_groups - This function can only ever be
* run by one of the transaction committers. Refer to
* BTRFS_TRANS_DIRTY_BG_RUN usage in btrfs_commit_transaction
*
* - btrfs_write_dirty_blockgroups - this is called by
* commit_cowonly_roots from transaction critical section
* (TRANS_STATE_COMMIT_DOING)
*
* - btrfs_cleanup_dirty_bgs - called on transaction abort
*/
struct list_head io_bgs;
struct list_head dropped_roots;
/*
* we need to make sure block group deletion doesn't race with
* free space cache writeout. This mutex keeps them from stomping
* on each other
*/
struct mutex cache_write_mutex;
spinlock_t dirty_bgs_lock;
/* Protected by spin lock fs_info->unused_bgs_lock. */
struct list_head deleted_bgs;
spinlock_t dropped_roots_lock;
struct btrfs_delayed_ref_root delayed_refs;
struct btrfs_fs_info *fs_info;
};
#define __TRANS_FREEZABLE (1U << 0)
#define __TRANS_START (1U << 9)
#define __TRANS_ATTACH (1U << 10)
#define __TRANS_JOIN (1U << 11)
#define __TRANS_JOIN_NOLOCK (1U << 12)
#define __TRANS_DUMMY (1U << 13)
#define __TRANS_JOIN_NOSTART (1U << 14)
#define TRANS_START (__TRANS_START | __TRANS_FREEZABLE)
#define TRANS_ATTACH (__TRANS_ATTACH)
#define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE)
#define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK)
#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART)
#define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH)
#define BTRFS_SEND_TRANS_STUB ((void *)1)
struct btrfs_trans_handle {
u64 transid;
u64 bytes_reserved;
u64 chunk_bytes_reserved;
unsigned long delayed_ref_updates;
struct btrfs_transaction *transaction;
struct btrfs_block_rsv *block_rsv;
struct btrfs_block_rsv *orig_rsv;
refcount_t use_count;
unsigned int type;
short aborted;
bool adding_csums;
bool allocating_chunk;
bool can_flush_pending_bgs;
bool reloc_reserved;
bool dirty;
struct btrfs_root *root;
struct btrfs_fs_info *fs_info;
struct list_head new_bgs;
};
struct btrfs_pending_snapshot {
struct dentry *dentry;
struct inode *dir;
struct btrfs_root *root;
struct btrfs_root_item *root_item;
struct btrfs_root *snap;
struct btrfs_qgroup_inherit *inherit;
struct btrfs_path *path;
/* block reservation for the operation */
struct btrfs_block_rsv block_rsv;
/* extra metadata reservation for relocation */
int error;
bool readonly;
struct list_head list;
};
static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
struct inode *inode)
{
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->last_trans = trans->transaction->transid;
BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
spin_unlock(&BTRFS_I(inode)->lock);
}
/*
* Make qgroup codes to skip given qgroupid, means the old/new_roots for
* qgroup won't contain the qgroupid in it.
*/
static inline void btrfs_set_skip_qgroup(struct btrfs_trans_handle *trans,
u64 qgroupid)
{
struct btrfs_delayed_ref_root *delayed_refs;
delayed_refs = &trans->transaction->delayed_refs;
WARN_ON(delayed_refs->qgroup_to_skip);
delayed_refs->qgroup_to_skip = qgroupid;
}
static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans)
{
struct btrfs_delayed_ref_root *delayed_refs;
delayed_refs = &trans->transaction->delayed_refs;
WARN_ON(!delayed_refs->qgroup_to_skip);
delayed_refs->qgroup_to_skip = 0;
}
int btrfs_end_transaction(struct btrfs_trans_handle *trans);
struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
unsigned int num_items);
struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
struct btrfs_root *root,
unsigned int num_items,
int min_factor);
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
struct btrfs_root *root);
int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid);
void btrfs_add_dead_root(struct btrfs_root *root);
int btrfs_defrag_root(struct btrfs_root *root);
int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
int wait_for_unblock);
/*
* Try to commit transaction asynchronously, so this is safe to call
* even holding a spinlock.
*
* It's done by informing transaction_kthread to commit transaction without
* waiting for commit interval.
*/
static inline void btrfs_commit_transaction_locksafe(
struct btrfs_fs_info *fs_info)
{
set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
wake_up_process(fs_info->transaction_kthread);
}
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
void btrfs_throttle(struct btrfs_fs_info *fs_info);
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages, int mark);
int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages);
int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark);
int btrfs_transaction_blocked(struct btrfs_fs_info *info);
int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
void btrfs_put_transaction(struct btrfs_transaction *transaction);
void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
#endif