linux/fs/btrfs/locking.h
Josef Bacik b40130b23c 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>
2022-08-17 16:19:12 +02:00

149 lines
4.8 KiB
C

/* 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/percpu_counter.h>
#include "extent_io.h"
#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,
};
static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
"too many lock subclasses defined");
struct btrfs_path;
void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
void btrfs_tree_lock(struct extent_buffer *eb);
void btrfs_tree_unlock(struct extent_buffer *eb);
void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
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);
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_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;
struct percpu_counter writers;
wait_queue_head_t pending_writers;
wait_queue_head_t pending_readers;
};
int btrfs_drew_lock_init(struct btrfs_drew_lock *lock);
void btrfs_drew_lock_destroy(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);
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)
{
}
static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
struct extent_buffer *eb)
{
}
#endif
#endif