linux-stable/fs/btrfs/locking.h

239 lines
7.6 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
#ifndef BTRFS_LOCKING_H
#define BTRFS_LOCKING_H
#include <linux/atomic.h>
#include <linux/wait.h>
#include <linux/lockdep.h>
#include <linux/percpu_counter.h>
#include "extent_io.h"
#include "locking.h"
struct extent_buffer;
struct btrfs_path;
struct btrfs_root;
#define BTRFS_WRITE_LOCK 1
#define BTRFS_READ_LOCK 2
/*
* 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,
/*
* 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,
/*
* 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,
/*
* 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,
/*
* 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,
/*
* 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,
/*
* 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,
};
enum btrfs_lockdep_trans_states {
btrfs: do not block starts waiting on previous transaction commit Internally I got a report of very long stalls on normal operations like creating a new file when auto relocation was running. The reporter used the 'bpf offcputime' tracer to show that we would get stuck in start_transaction for 5 to 30 seconds, and were always being woken up by the transaction commit. Using my timing-everything script, which times how long a function takes and what percentage of that total time is taken up by its children, I saw several traces like this 1083 took 32812902424 ns 29929002926 ns 91.2110% wait_for_commit_duration 25568 ns 7.7920e-05% commit_fs_roots_duration 1007751 ns 0.00307% commit_cowonly_roots_duration 446855602 ns 1.36182% btrfs_run_delayed_refs_duration 271980 ns 0.00082% btrfs_run_delayed_items_duration 2008 ns 6.1195e-06% btrfs_apply_pending_changes_duration 9656 ns 2.9427e-05% switch_commit_roots_duration 1598 ns 4.8700e-06% btrfs_commit_device_sizes_duration 4314 ns 1.3147e-05% btrfs_free_log_root_tree_duration Here I was only tracing functions that happen where we are between START_COMMIT and UNBLOCKED in order to see what would be keeping us blocked for so long. The wait_for_commit() we do is where we wait for a previous transaction that hasn't completed it's commit. This can include all of the unpin work and other cleanups, which tends to be the longest part of our transaction commit. There is no reason we should be blocking new things from entering the transaction at this point, it just adds to random latency spikes for no reason. Fix this by adding a PREP stage. This allows us to properly deal with multiple committers coming in at the same time, we retain the behavior that the winner waits on the previous transaction and the losers all wait for this transaction commit to occur. Nothing else is blocked during the PREP stage, and then once the wait is complete we switch to COMMIT_START and all of the same behavior as before is maintained. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2023-08-24 20:59:22 +00:00
BTRFS_LOCKDEP_TRANS_COMMIT_PREP,
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)
static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
"too many lock subclasses defined");
void btrfs_tree_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
btrfs: locking: inline btrfs_tree_lock() and btrfs_tree_read_lock() The functions btrfs_tree_lock() and btrfs_tree_read_lock() are very trivial so that can be made inline and avoid call overhead, as they are very often called inside critical sections (when searching a btree for example, attempting to lock a child node/leaf while holding a lock on the parent). So make them static inline, which even reduces the size of the btrfs module a little bit. Before this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718786 156276 16920 1891982 1cde8e fs/btrfs/btrfs.ko After this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718650 156260 16920 1891830 1cddf6 fs/btrfs/btrfs.ko Running fs_mark also showed a tiny improvement with this script: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 FILES=100000 THREADS=$(nproc --all) echo "performance" | \ tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor umount $DEV &> /dev/null mkfs.btrfs -f $DEV mount $DEV $MNT OPTS="-S 0 -L 5 -n $FILES -s 0 -t $THREADS -k" for ((i = 1; i <= $THREADS; i++)); do OPTS="$OPTS -d $MNT/d$i" done fs_mark $OPTS umount $MNT Before this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 180894.0 10705410 16 2400000 0 228211.4 10765738 23 3600000 0 215969.6 11011072 30 4800000 0 199077.1 11145587 46 6000000 0 176624.1 11658470 After this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 185312.3 10708377 16 2400000 0 229320.4 10858013 23 3600000 0 217958.7 11006167 30 4800000 0 205122.9 11112899 46 6000000 0 178039.1 11438852 Reviewed-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-03-15 12:15:53 +00:00
static inline void btrfs_tree_lock(struct extent_buffer *eb)
{
btrfs_tree_lock_nested(eb, BTRFS_NESTING_NORMAL);
btrfs: locking: inline btrfs_tree_lock() and btrfs_tree_read_lock() The functions btrfs_tree_lock() and btrfs_tree_read_lock() are very trivial so that can be made inline and avoid call overhead, as they are very often called inside critical sections (when searching a btree for example, attempting to lock a child node/leaf while holding a lock on the parent). So make them static inline, which even reduces the size of the btrfs module a little bit. Before this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718786 156276 16920 1891982 1cde8e fs/btrfs/btrfs.ko After this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718650 156260 16920 1891830 1cddf6 fs/btrfs/btrfs.ko Running fs_mark also showed a tiny improvement with this script: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 FILES=100000 THREADS=$(nproc --all) echo "performance" | \ tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor umount $DEV &> /dev/null mkfs.btrfs -f $DEV mount $DEV $MNT OPTS="-S 0 -L 5 -n $FILES -s 0 -t $THREADS -k" for ((i = 1; i <= $THREADS; i++)); do OPTS="$OPTS -d $MNT/d$i" done fs_mark $OPTS umount $MNT Before this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 180894.0 10705410 16 2400000 0 228211.4 10765738 23 3600000 0 215969.6 11011072 30 4800000 0 199077.1 11145587 46 6000000 0 176624.1 11658470 After this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 185312.3 10708377 16 2400000 0 229320.4 10858013 23 3600000 0 217958.7 11006167 30 4800000 0 205122.9 11112899 46 6000000 0 178039.1 11438852 Reviewed-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-03-15 12:15:53 +00:00
}
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 14:25:08 +00:00
void btrfs_tree_read_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
btrfs: locking: inline btrfs_tree_lock() and btrfs_tree_read_lock() The functions btrfs_tree_lock() and btrfs_tree_read_lock() are very trivial so that can be made inline and avoid call overhead, as they are very often called inside critical sections (when searching a btree for example, attempting to lock a child node/leaf while holding a lock on the parent). So make them static inline, which even reduces the size of the btrfs module a little bit. Before this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718786 156276 16920 1891982 1cde8e fs/btrfs/btrfs.ko After this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718650 156260 16920 1891830 1cddf6 fs/btrfs/btrfs.ko Running fs_mark also showed a tiny improvement with this script: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 FILES=100000 THREADS=$(nproc --all) echo "performance" | \ tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor umount $DEV &> /dev/null mkfs.btrfs -f $DEV mount $DEV $MNT OPTS="-S 0 -L 5 -n $FILES -s 0 -t $THREADS -k" for ((i = 1; i <= $THREADS; i++)); do OPTS="$OPTS -d $MNT/d$i" done fs_mark $OPTS umount $MNT Before this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 180894.0 10705410 16 2400000 0 228211.4 10765738 23 3600000 0 215969.6 11011072 30 4800000 0 199077.1 11145587 46 6000000 0 176624.1 11658470 After this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 185312.3 10708377 16 2400000 0 229320.4 10858013 23 3600000 0 217958.7 11006167 30 4800000 0 205122.9 11112899 46 6000000 0 178039.1 11438852 Reviewed-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-03-15 12:15:53 +00:00
static inline void btrfs_tree_read_lock(struct extent_buffer *eb)
{
btrfs_tree_read_lock_nested(eb, BTRFS_NESTING_NORMAL);
btrfs: locking: inline btrfs_tree_lock() and btrfs_tree_read_lock() The functions btrfs_tree_lock() and btrfs_tree_read_lock() are very trivial so that can be made inline and avoid call overhead, as they are very often called inside critical sections (when searching a btree for example, attempting to lock a child node/leaf while holding a lock on the parent). So make them static inline, which even reduces the size of the btrfs module a little bit. Before this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718786 156276 16920 1891982 1cde8e fs/btrfs/btrfs.ko After this change: $ size fs/btrfs/btrfs.ko text data bss dec hex filename 1718650 156260 16920 1891830 1cddf6 fs/btrfs/btrfs.ko Running fs_mark also showed a tiny improvement with this script: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 FILES=100000 THREADS=$(nproc --all) echo "performance" | \ tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor umount $DEV &> /dev/null mkfs.btrfs -f $DEV mount $DEV $MNT OPTS="-S 0 -L 5 -n $FILES -s 0 -t $THREADS -k" for ((i = 1; i <= $THREADS; i++)); do OPTS="$OPTS -d $MNT/d$i" done fs_mark $OPTS umount $MNT Before this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 180894.0 10705410 16 2400000 0 228211.4 10765738 23 3600000 0 215969.6 11011072 30 4800000 0 199077.1 11145587 46 6000000 0 176624.1 11658470 After this change: FSUse% Count Size Files/sec App Overhead 10 1200000 0 185312.3 10708377 16 2400000 0 229320.4 10858013 23 3600000 0 217958.7 11006167 30 4800000 0 205122.9 11112899 46 6000000 0 178039.1 11438852 Reviewed-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-03-15 12:15:53 +00:00
}
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);
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root);
#ifdef CONFIG_BTRFS_DEBUG
static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb)
{
lockdep_assert_held_write(&eb->lock);
}
#else
static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { }
#endif
void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
if (rw == BTRFS_WRITE_LOCK)
btrfs_tree_unlock(eb);
else if (rw == BTRFS_READ_LOCK)
btrfs_tree_read_unlock(eb);
else
BUG();
}
struct btrfs_drew_lock {
atomic_t readers;
atomic_t writers;
wait_queue_head_t pending_writers;
wait_queue_head_t pending_readers;
};
void btrfs_drew_lock_init(struct btrfs_drew_lock *lock);
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);
#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>
2022-07-26 20:24:04 +00:00
void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb);
#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>
2022-07-26 20:24:04 +00:00
static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
struct extent_buffer *eb)
{
}
#endif
#endif