2018-04-04 01:16:55 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
2008-06-26 04:01:30 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
|
|
*/
|
|
|
|
|
2018-04-04 01:16:55 +08:00
|
|
|
#ifndef BTRFS_LOCKING_H
|
|
|
|
#define BTRFS_LOCKING_H
|
2008-06-26 04:01:30 +08:00
|
|
|
|
2020-01-30 20:59:44 +08:00
|
|
|
#include <linux/atomic.h>
|
|
|
|
#include <linux/wait.h>
|
|
|
|
#include <linux/percpu_counter.h>
|
2019-09-25 00:44:24 +08:00
|
|
|
#include "extent_io.h"
|
|
|
|
|
2011-07-17 03:23:14 +08:00
|
|
|
#define BTRFS_WRITE_LOCK 1
|
|
|
|
#define BTRFS_READ_LOCK 2
|
|
|
|
|
2020-08-20 23:46:02 +08:00
|
|
|
/*
|
|
|
|
* We are limited in number of subclasses by MAX_LOCKDEP_SUBCLASSES, which at
|
|
|
|
* the time of this patch is 8, which is how many we use. Keep this in mind if
|
|
|
|
* you decide you want to add another subclass.
|
|
|
|
*/
|
|
|
|
enum btrfs_lock_nesting {
|
|
|
|
BTRFS_NESTING_NORMAL,
|
|
|
|
|
2020-08-20 23:46:03 +08:00
|
|
|
/*
|
|
|
|
* When we COW a block we are holding the lock on the original block,
|
|
|
|
* and since our lockdep maps are rootid+level, this confuses lockdep
|
|
|
|
* when we lock the newly allocated COW'd block. Handle this by having
|
|
|
|
* a subclass for COW'ed blocks so that lockdep doesn't complain.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_COW,
|
|
|
|
|
2020-08-20 23:46:04 +08:00
|
|
|
/*
|
|
|
|
* Oftentimes we need to lock adjacent nodes on the same level while
|
|
|
|
* still holding the lock on the original node we searched to, such as
|
|
|
|
* for searching forward or for split/balance.
|
|
|
|
*
|
|
|
|
* Because of this we need to indicate to lockdep that this is
|
|
|
|
* acceptable by having a different subclass for each of these
|
|
|
|
* operations.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_LEFT,
|
|
|
|
BTRFS_NESTING_RIGHT,
|
|
|
|
|
2020-08-20 23:46:05 +08:00
|
|
|
/*
|
|
|
|
* When splitting we will be holding a lock on the left/right node when
|
|
|
|
* we need to cow that node, thus we need a new set of subclasses for
|
|
|
|
* these two operations.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_LEFT_COW,
|
|
|
|
BTRFS_NESTING_RIGHT_COW,
|
|
|
|
|
2020-08-20 23:46:06 +08:00
|
|
|
/*
|
|
|
|
* When splitting we may push nodes to the left or right, but still use
|
|
|
|
* the subsequent nodes in our path, keeping our locks on those adjacent
|
|
|
|
* blocks. Thus when we go to allocate a new split block we've already
|
|
|
|
* used up all of our available subclasses, so this subclass exists to
|
|
|
|
* handle this case where we need to allocate a new split block.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_SPLIT,
|
|
|
|
|
2020-08-20 23:46:07 +08:00
|
|
|
/*
|
|
|
|
* When promoting a new block to a root we need to have a special
|
|
|
|
* subclass so we don't confuse lockdep, as it will appear that we are
|
|
|
|
* locking a higher level node before a lower level one. Copying also
|
|
|
|
* has this problem as it appears we're locking the same block again
|
|
|
|
* when we make a snapshot of an existing root.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_NEW_ROOT,
|
|
|
|
|
2020-08-20 23:46:02 +08:00
|
|
|
/*
|
|
|
|
* We are limited to MAX_LOCKDEP_SUBLCLASSES number of subclasses, so
|
|
|
|
* add this in here and add a static_assert to keep us from going over
|
|
|
|
* the limit. As of this writing we're limited to 8, and we're
|
|
|
|
* definitely using 8, hence this check to keep us from messing up in
|
|
|
|
* the future.
|
|
|
|
*/
|
|
|
|
BTRFS_NESTING_MAX,
|
|
|
|
};
|
|
|
|
|
2022-10-25 02:46:53 +08:00
|
|
|
enum btrfs_lockdep_trans_states {
|
|
|
|
BTRFS_LOCKDEP_TRANS_COMMIT_START,
|
|
|
|
BTRFS_LOCKDEP_TRANS_UNBLOCKED,
|
|
|
|
BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED,
|
|
|
|
BTRFS_LOCKDEP_TRANS_COMPLETED,
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Lockdep annotation for wait events.
|
|
|
|
*
|
|
|
|
* @owner: The struct where the lockdep map is defined
|
|
|
|
* @lock: The lockdep map corresponding to a wait event
|
|
|
|
*
|
|
|
|
* This macro is used to annotate a wait event. In this case a thread acquires
|
|
|
|
* the lockdep map as writer (exclusive lock) because it has to block until all
|
|
|
|
* the threads that hold the lock as readers signal the condition for the wait
|
|
|
|
* event and release their locks.
|
|
|
|
*/
|
|
|
|
#define btrfs_might_wait_for_event(owner, lock) \
|
|
|
|
do { \
|
|
|
|
rwsem_acquire(&owner->lock##_map, 0, 0, _THIS_IP_); \
|
|
|
|
rwsem_release(&owner->lock##_map, _THIS_IP_); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Protection for the resource/condition of a wait event.
|
|
|
|
*
|
|
|
|
* @owner: The struct where the lockdep map is defined
|
|
|
|
* @lock: The lockdep map corresponding to a wait event
|
|
|
|
*
|
|
|
|
* Many threads can modify the condition for the wait event at the same time
|
|
|
|
* and signal the threads that block on the wait event. The threads that modify
|
|
|
|
* the condition and do the signaling acquire the lock as readers (shared
|
|
|
|
* lock).
|
|
|
|
*/
|
|
|
|
#define btrfs_lockdep_acquire(owner, lock) \
|
|
|
|
rwsem_acquire_read(&owner->lock##_map, 0, 0, _THIS_IP_)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Used after signaling the condition for a wait event to release the lockdep
|
|
|
|
* map held by a reader thread.
|
|
|
|
*/
|
|
|
|
#define btrfs_lockdep_release(owner, lock) \
|
|
|
|
rwsem_release(&owner->lock##_map, _THIS_IP_)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Macros for the transaction states wait events, similar to the generic wait
|
|
|
|
* event macros.
|
|
|
|
*/
|
|
|
|
#define btrfs_might_wait_for_state(owner, i) \
|
|
|
|
do { \
|
|
|
|
rwsem_acquire(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_); \
|
|
|
|
rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define btrfs_trans_state_lockdep_acquire(owner, i) \
|
|
|
|
rwsem_acquire_read(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_)
|
|
|
|
|
|
|
|
#define btrfs_trans_state_lockdep_release(owner, i) \
|
|
|
|
rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_)
|
|
|
|
|
|
|
|
/* Initialization of the lockdep map */
|
|
|
|
#define btrfs_lockdep_init_map(owner, lock) \
|
|
|
|
do { \
|
|
|
|
static struct lock_class_key lock##_key; \
|
|
|
|
lockdep_init_map(&owner->lock##_map, #lock, &lock##_key, 0); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
/* Initialization of the transaction states lockdep maps. */
|
|
|
|
#define btrfs_state_lockdep_init_map(owner, lock, state) \
|
|
|
|
do { \
|
|
|
|
static struct lock_class_key lock##_key; \
|
|
|
|
lockdep_init_map(&owner->btrfs_state_change_map[state], #lock, \
|
|
|
|
&lock##_key, 0); \
|
|
|
|
} while (0)
|
|
|
|
|
2020-08-20 23:46:02 +08:00
|
|
|
static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
|
|
|
|
"too many lock subclasses defined");
|
|
|
|
|
2020-01-30 20:59:44 +08:00
|
|
|
struct btrfs_path;
|
|
|
|
|
2020-08-20 23:46:02 +08:00
|
|
|
void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
|
2012-03-01 21:56:26 +08:00
|
|
|
void btrfs_tree_lock(struct extent_buffer *eb);
|
|
|
|
void btrfs_tree_unlock(struct extent_buffer *eb);
|
Btrfs: Change btree locking to use explicit blocking points
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
|
|
|
|
2020-11-07 05:27:35 +08:00
|
|
|
void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
|
2011-07-17 03:23:14 +08:00
|
|
|
void btrfs_tree_read_lock(struct extent_buffer *eb);
|
|
|
|
void btrfs_tree_read_unlock(struct extent_buffer *eb);
|
|
|
|
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
|
|
|
|
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
|
2020-08-20 23:46:01 +08:00
|
|
|
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
|
2020-11-07 05:27:33 +08:00
|
|
|
struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
|
2022-09-13 03:27:42 +08:00
|
|
|
struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root);
|
2014-11-20 02:25:09 +08:00
|
|
|
|
2019-09-25 00:44:24 +08:00
|
|
|
#ifdef CONFIG_BTRFS_DEBUG
|
2021-09-22 17:36:45 +08:00
|
|
|
static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
lockdep_assert_held_write(&eb->lock);
|
2019-09-25 00:44:24 +08:00
|
|
|
}
|
|
|
|
#else
|
2021-09-22 17:36:45 +08:00
|
|
|
static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { }
|
2019-09-25 00:44:24 +08:00
|
|
|
#endif
|
2011-07-17 03:23:14 +08:00
|
|
|
|
2019-09-25 01:17:17 +08:00
|
|
|
void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
|
2019-09-25 01:17:17 +08:00
|
|
|
|
2011-07-17 03:23:14 +08:00
|
|
|
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
|
|
|
|
{
|
2020-08-20 23:46:10 +08:00
|
|
|
if (rw == BTRFS_WRITE_LOCK)
|
2011-07-17 03:23:14 +08:00
|
|
|
btrfs_tree_unlock(eb);
|
|
|
|
else if (rw == BTRFS_READ_LOCK)
|
|
|
|
btrfs_tree_read_unlock(eb);
|
|
|
|
else
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
2020-01-30 20:59:44 +08:00
|
|
|
struct btrfs_drew_lock {
|
|
|
|
atomic_t readers;
|
2023-03-02 04:47:08 +08:00
|
|
|
atomic_t writers;
|
2020-01-30 20:59:44 +08:00
|
|
|
wait_queue_head_t pending_writers;
|
|
|
|
wait_queue_head_t pending_readers;
|
|
|
|
};
|
|
|
|
|
2023-03-02 04:47:08 +08:00
|
|
|
void btrfs_drew_lock_init(struct btrfs_drew_lock *lock);
|
2020-01-30 20:59:44 +08:00
|
|
|
void btrfs_drew_write_lock(struct btrfs_drew_lock *lock);
|
|
|
|
bool btrfs_drew_try_write_lock(struct btrfs_drew_lock *lock);
|
|
|
|
void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
|
|
|
|
void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
|
|
|
|
void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
|
|
|
|
|
2022-07-27 04:24:03 +08:00
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
|
|
void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level);
|
btrfs: fix lockdep splat with reloc root extent buffers
We have been hitting the following lockdep splat with btrfs/187 recently
WARNING: possible circular locking dependency detected
5.19.0-rc8+ #775 Not tainted
------------------------------------------------------
btrfs/752500 is trying to acquire lock:
ffff97e1875a97b8 (btrfs-treloc-02#2){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
but task is already holding lock:
ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-tree-01/1){+.+.}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_init_new_buffer+0x7d/0x2c0
btrfs_alloc_tree_block+0x120/0x3b0
__btrfs_cow_block+0x136/0x600
btrfs_cow_block+0x10b/0x230
btrfs_search_slot+0x53b/0xb70
btrfs_lookup_inode+0x2a/0xa0
__btrfs_update_delayed_inode+0x5f/0x280
btrfs_async_run_delayed_root+0x24c/0x290
btrfs_work_helper+0xf2/0x3e0
process_one_work+0x271/0x590
worker_thread+0x52/0x3b0
kthread+0xf0/0x120
ret_from_fork+0x1f/0x30
-> #1 (btrfs-tree-01){++++}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_search_slot+0x3c3/0xb70
do_relocation+0x10c/0x6b0
relocate_tree_blocks+0x317/0x6d0
relocate_block_group+0x1f1/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
-> #0 (btrfs-treloc-02#2){+.+.}-{3:3}:
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
other info that might help us debug this:
Chain exists of:
btrfs-treloc-02#2 --> btrfs-tree-01 --> btrfs-tree-01/1
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-tree-01/1);
lock(btrfs-tree-01);
lock(btrfs-tree-01/1);
lock(btrfs-treloc-02#2);
*** DEADLOCK ***
7 locks held by btrfs/752500:
#0: ffff97e292fdf460 (sb_writers#12){.+.+}-{0:0}, at: btrfs_ioctl+0x208/0x2c90
#1: ffff97e284c02050 (&fs_info->reclaim_bgs_lock){+.+.}-{3:3}, at: btrfs_balance+0x55f/0xe40
#2: ffff97e284c00878 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: btrfs_relocate_block_group+0x236/0x400
#3: ffff97e292fdf650 (sb_internal#2){.+.+}-{0:0}, at: merge_reloc_root+0xef/0x610
#4: ffff97e284c02378 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#5: ffff97e284c023a0 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#6: ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
stack backtrace:
CPU: 1 PID: 752500 Comm: btrfs Not tainted 5.19.0-rc8+ #775
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack_lvl+0x56/0x73
check_noncircular+0xd6/0x100
? lock_is_held_type+0xe2/0x140
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
? __btrfs_tree_lock+0x24/0x110
down_write_nested+0x41/0x80
? __btrfs_tree_lock+0x24/0x110
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
? lock_release+0x137/0x2d0
? _raw_spin_unlock+0x29/0x50
? release_extent_buffer+0x128/0x180
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
? lock_is_held_type+0xe2/0x140
? lock_is_held_type+0xe2/0x140
? __x64_sys_ioctl+0x88/0xc0
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
This isn't necessarily new, it's just tricky to hit in practice. There
are two competing things going on here. With relocation we create a
snapshot of every fs tree with a reloc tree. Any extent buffers that
get initialized here are initialized with the reloc root lockdep key.
However since it is a snapshot, any blocks that are currently in cache
that originally belonged to the fs tree will have the normal tree
lockdep key set. This creates the lock dependency of
reloc tree -> normal tree
for the extent buffer locking during the first phase of the relocation
as we walk down the reloc root to relocate blocks.
However this is problematic because the final phase of the relocation is
merging the reloc root into the original fs root. This involves
searching down to any keys that exist in the original fs root and then
swapping the relocated block and the original fs root block. We have to
search down to the fs root first, and then go search the reloc root for
the block we need to replace. This creates the dependency of
normal tree -> reloc tree
which is why lockdep complains.
Additionally even if we were to fix this particular mismatch with a
different nesting for the merge case, we're still slotting in a block
that has a owner of the reloc root objectid into a normal tree, so that
block will have its lockdep key set to the tree reloc root, and create a
lockdep splat later on when we wander into that block from the fs root.
Unfortunately the only solution here is to make sure we do not set the
lockdep key to the reloc tree lockdep key normally, and then reset any
blocks we wander into from the reloc root when we're doing the merged.
This solves the problem of having mixed tree reloc keys intermixed with
normal tree keys, and then allows us to make sure in the merge case we
maintain the lock order of
normal tree -> reloc tree
We handle this by setting a bit on the reloc root when we do the search
for the block we want to relocate, and any block we search into or COW
at that point gets set to the reloc tree key. This works correctly
because we only ever COW down to the parent node, so we aren't resetting
the key for the block we're linking into the fs root.
With this patch we no longer have the lockdep splat in btrfs/187.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-27 04:24:04 +08:00
|
|
|
void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb);
|
2022-07-27 04:24:03 +08:00
|
|
|
#else
|
|
|
|
static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
|
|
|
|
struct extent_buffer *eb, int level)
|
|
|
|
{
|
|
|
|
}
|
btrfs: fix lockdep splat with reloc root extent buffers
We have been hitting the following lockdep splat with btrfs/187 recently
WARNING: possible circular locking dependency detected
5.19.0-rc8+ #775 Not tainted
------------------------------------------------------
btrfs/752500 is trying to acquire lock:
ffff97e1875a97b8 (btrfs-treloc-02#2){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
but task is already holding lock:
ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-tree-01/1){+.+.}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_init_new_buffer+0x7d/0x2c0
btrfs_alloc_tree_block+0x120/0x3b0
__btrfs_cow_block+0x136/0x600
btrfs_cow_block+0x10b/0x230
btrfs_search_slot+0x53b/0xb70
btrfs_lookup_inode+0x2a/0xa0
__btrfs_update_delayed_inode+0x5f/0x280
btrfs_async_run_delayed_root+0x24c/0x290
btrfs_work_helper+0xf2/0x3e0
process_one_work+0x271/0x590
worker_thread+0x52/0x3b0
kthread+0xf0/0x120
ret_from_fork+0x1f/0x30
-> #1 (btrfs-tree-01){++++}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_search_slot+0x3c3/0xb70
do_relocation+0x10c/0x6b0
relocate_tree_blocks+0x317/0x6d0
relocate_block_group+0x1f1/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
-> #0 (btrfs-treloc-02#2){+.+.}-{3:3}:
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
other info that might help us debug this:
Chain exists of:
btrfs-treloc-02#2 --> btrfs-tree-01 --> btrfs-tree-01/1
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-tree-01/1);
lock(btrfs-tree-01);
lock(btrfs-tree-01/1);
lock(btrfs-treloc-02#2);
*** DEADLOCK ***
7 locks held by btrfs/752500:
#0: ffff97e292fdf460 (sb_writers#12){.+.+}-{0:0}, at: btrfs_ioctl+0x208/0x2c90
#1: ffff97e284c02050 (&fs_info->reclaim_bgs_lock){+.+.}-{3:3}, at: btrfs_balance+0x55f/0xe40
#2: ffff97e284c00878 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: btrfs_relocate_block_group+0x236/0x400
#3: ffff97e292fdf650 (sb_internal#2){.+.+}-{0:0}, at: merge_reloc_root+0xef/0x610
#4: ffff97e284c02378 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#5: ffff97e284c023a0 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#6: ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
stack backtrace:
CPU: 1 PID: 752500 Comm: btrfs Not tainted 5.19.0-rc8+ #775
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack_lvl+0x56/0x73
check_noncircular+0xd6/0x100
? lock_is_held_type+0xe2/0x140
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
? __btrfs_tree_lock+0x24/0x110
down_write_nested+0x41/0x80
? __btrfs_tree_lock+0x24/0x110
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
? lock_release+0x137/0x2d0
? _raw_spin_unlock+0x29/0x50
? release_extent_buffer+0x128/0x180
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
? lock_is_held_type+0xe2/0x140
? lock_is_held_type+0xe2/0x140
? __x64_sys_ioctl+0x88/0xc0
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
This isn't necessarily new, it's just tricky to hit in practice. There
are two competing things going on here. With relocation we create a
snapshot of every fs tree with a reloc tree. Any extent buffers that
get initialized here are initialized with the reloc root lockdep key.
However since it is a snapshot, any blocks that are currently in cache
that originally belonged to the fs tree will have the normal tree
lockdep key set. This creates the lock dependency of
reloc tree -> normal tree
for the extent buffer locking during the first phase of the relocation
as we walk down the reloc root to relocate blocks.
However this is problematic because the final phase of the relocation is
merging the reloc root into the original fs root. This involves
searching down to any keys that exist in the original fs root and then
swapping the relocated block and the original fs root block. We have to
search down to the fs root first, and then go search the reloc root for
the block we need to replace. This creates the dependency of
normal tree -> reloc tree
which is why lockdep complains.
Additionally even if we were to fix this particular mismatch with a
different nesting for the merge case, we're still slotting in a block
that has a owner of the reloc root objectid into a normal tree, so that
block will have its lockdep key set to the tree reloc root, and create a
lockdep splat later on when we wander into that block from the fs root.
Unfortunately the only solution here is to make sure we do not set the
lockdep key to the reloc tree lockdep key normally, and then reset any
blocks we wander into from the reloc root when we're doing the merged.
This solves the problem of having mixed tree reloc keys intermixed with
normal tree keys, and then allows us to make sure in the merge case we
maintain the lock order of
normal tree -> reloc tree
We handle this by setting a bit on the reloc root when we do the search
for the block we want to relocate, and any block we search into or COW
at that point gets set to the reloc tree key. This works correctly
because we only ever COW down to the parent node, so we aren't resetting
the key for the block we're linking into the fs root.
With this patch we no longer have the lockdep splat in btrfs/187.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-27 04:24:04 +08:00
|
|
|
static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
|
|
|
|
struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
}
|
2022-07-27 04:24:03 +08:00
|
|
|
#endif
|
|
|
|
|
2008-06-26 04:01:30 +08:00
|
|
|
#endif
|