redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity
alistair23-linux/fs/btrfs
History
Filipe Manana a6676b0fa0 btrfs: fix lockdep splat when reading qgroup config on mount 
commit 3d05cad3c3 upstream.

Lockdep reported the following splat when running test btrfs/190 from
fstests:

  [ 9482.126098] ======================================================
  [ 9482.126184] WARNING: possible circular locking dependency detected
  [ 9482.126281] 5.10.0-rc4-btrfs-next-73 #1 Not tainted
  [ 9482.126365] ------------------------------------------------------
  [ 9482.126456] mount/24187 is trying to acquire lock:
  [ 9482.126534] ffffa0c869a7dac0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}, at: qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.126647]
		 but task is already holding lock:
  [ 9482.126777] ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs]
  [ 9482.126886]
		 which lock already depends on the new lock.

  [ 9482.127078]
		 the existing dependency chain (in reverse order) is:
  [ 9482.127213]
		 -> #1 (btrfs-quota-00){++++}-{3:3}:
  [ 9482.127366]        lock_acquire+0xd8/0x490
  [ 9482.127436]        down_read_nested+0x45/0x220
  [ 9482.127528]        __btrfs_tree_read_lock+0x27/0x120 [btrfs]
  [ 9482.127613]        btrfs_read_lock_root_node+0x41/0x130 [btrfs]
  [ 9482.127702]        btrfs_search_slot+0x514/0xc30 [btrfs]
  [ 9482.127788]        update_qgroup_status_item+0x72/0x140 [btrfs]
  [ 9482.127877]        btrfs_qgroup_rescan_worker+0xde/0x680 [btrfs]
  [ 9482.127964]        btrfs_work_helper+0xf1/0x600 [btrfs]
  [ 9482.128039]        process_one_work+0x24e/0x5e0
  [ 9482.128110]        worker_thread+0x50/0x3b0
  [ 9482.128181]        kthread+0x153/0x170
  [ 9482.128256]        ret_from_fork+0x22/0x30
  [ 9482.128327]
		 -> #0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}:
  [ 9482.128464]        check_prev_add+0x91/0xc60
  [ 9482.128551]        __lock_acquire+0x1740/0x3110
  [ 9482.128623]        lock_acquire+0xd8/0x490
  [ 9482.130029]        __mutex_lock+0xa3/0xb30
  [ 9482.130590]        qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.131577]        btrfs_read_qgroup_config+0x43a/0x550 [btrfs]
  [ 9482.132175]        open_ctree+0x1228/0x18a0 [btrfs]
  [ 9482.132756]        btrfs_mount_root.cold+0x13/0xed [btrfs]
  [ 9482.133325]        legacy_get_tree+0x30/0x60
  [ 9482.133866]        vfs_get_tree+0x28/0xe0
  [ 9482.134392]        fc_mount+0xe/0x40
  [ 9482.134908]        vfs_kern_mount.part.0+0x71/0x90
  [ 9482.135428]        btrfs_mount+0x13b/0x3e0 [btrfs]
  [ 9482.135942]        legacy_get_tree+0x30/0x60
  [ 9482.136444]        vfs_get_tree+0x28/0xe0
  [ 9482.136949]        path_mount+0x2d7/0xa70
  [ 9482.137438]        do_mount+0x75/0x90
  [ 9482.137923]        __x64_sys_mount+0x8e/0xd0
  [ 9482.138400]        do_syscall_64+0x33/0x80
  [ 9482.138873]        entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [ 9482.139346]
		 other info that might help us debug this:

  [ 9482.140735]  Possible unsafe locking scenario:

  [ 9482.141594]        CPU0                    CPU1
  [ 9482.142011]        ----                    ----
  [ 9482.142411]   lock(btrfs-quota-00);
  [ 9482.142806]                                lock(&fs_info->qgroup_rescan_lock);
  [ 9482.143216]                                lock(btrfs-quota-00);
  [ 9482.143629]   lock(&fs_info->qgroup_rescan_lock);
  [ 9482.144056]
		  *** DEADLOCK ***

  [ 9482.145242] 2 locks held by mount/24187:
  [ 9482.145637]  #0: ffffa0c8411c40e8 (&type->s_umount_key#44/1){+.+.}-{3:3}, at: alloc_super+0xb9/0x400
  [ 9482.146061]  #1: ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs]
  [ 9482.146509]
		 stack backtrace:
  [ 9482.147350] CPU: 1 PID: 24187 Comm: mount Not tainted 5.10.0-rc4-btrfs-next-73 #1
  [ 9482.147788] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
  [ 9482.148709] Call Trace:
  [ 9482.149169]  dump_stack+0x8d/0xb5
  [ 9482.149628]  check_noncircular+0xff/0x110
  [ 9482.150090]  check_prev_add+0x91/0xc60
  [ 9482.150561]  ? kvm_clock_read+0x14/0x30
  [ 9482.151017]  ? kvm_sched_clock_read+0x5/0x10
  [ 9482.151470]  __lock_acquire+0x1740/0x3110
  [ 9482.151941]  ? __btrfs_tree_read_lock+0x27/0x120 [btrfs]
  [ 9482.152402]  lock_acquire+0xd8/0x490
  [ 9482.152887]  ? qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.153354]  __mutex_lock+0xa3/0xb30
  [ 9482.153826]  ? qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.154301]  ? qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.154768]  ? qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.155226]  qgroup_rescan_init+0x43/0xf0 [btrfs]
  [ 9482.155690]  btrfs_read_qgroup_config+0x43a/0x550 [btrfs]
  [ 9482.156160]  open_ctree+0x1228/0x18a0 [btrfs]
  [ 9482.156643]  btrfs_mount_root.cold+0x13/0xed [btrfs]
  [ 9482.157108]  ? rcu_read_lock_sched_held+0x5d/0x90
  [ 9482.157567]  ? kfree+0x31f/0x3e0
  [ 9482.158030]  legacy_get_tree+0x30/0x60
  [ 9482.158489]  vfs_get_tree+0x28/0xe0
  [ 9482.158947]  fc_mount+0xe/0x40
  [ 9482.159403]  vfs_kern_mount.part.0+0x71/0x90
  [ 9482.159875]  btrfs_mount+0x13b/0x3e0 [btrfs]
  [ 9482.160335]  ? rcu_read_lock_sched_held+0x5d/0x90
  [ 9482.160805]  ? kfree+0x31f/0x3e0
  [ 9482.161260]  ? legacy_get_tree+0x30/0x60
  [ 9482.161714]  legacy_get_tree+0x30/0x60
  [ 9482.162166]  vfs_get_tree+0x28/0xe0
  [ 9482.162616]  path_mount+0x2d7/0xa70
  [ 9482.163070]  do_mount+0x75/0x90
  [ 9482.163525]  __x64_sys_mount+0x8e/0xd0
  [ 9482.163986]  do_syscall_64+0x33/0x80
  [ 9482.164437]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [ 9482.164902] RIP: 0033:0x7f51e907caaa

This happens because at btrfs_read_qgroup_config() we can call
qgroup_rescan_init() while holding a read lock on a quota btree leaf,
acquired by the previous call to btrfs_search_slot_for_read(), and
qgroup_rescan_init() acquires the mutex qgroup_rescan_lock.

A qgroup rescan worker does the opposite: it acquires the mutex
qgroup_rescan_lock, at btrfs_qgroup_rescan_worker(), and then tries to
update the qgroup status item in the quota btree through the call to
update_qgroup_status_item(). This inversion of locking order
between the qgroup_rescan_lock mutex and quota btree locks causes the
splat.

Fix this simply by releasing and freeing the path before calling
qgroup_rescan_init() at btrfs_read_qgroup_config().

CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 		2020-12-02 08:49:45 +01:00
..
tests btrfs: Correctly handle empty trees in find_first_clear_extent_bit 2020-02-11 04:35:34 -08:00
Kconfig btrfs: Fix build error while LIBCRC32C is module 2019-07-17 17:03:30 +02:00
Makefile btrfs: migrate the block group lookup code 2019-09-09 14:59:04 +02:00
acl.c btrfs: cleanup btrfs_setxattr_trans and drop transaction parameter 2019-04-29 19:02:44 +02:00
async-thread.c Btrfs: fix crash during unmount due to race with delayed inode workers 2020-04-17 10:50:15 +02:00
async-thread.h Btrfs: fix crash during unmount due to race with delayed inode workers 2020-04-17 10:50:15 +02:00
backref.c btrfs: fix double free on ulist after backref resolution failure 2020-07-29 10:18:30 +02:00
backref.h btrfs: fiemap: preallocate ulists for btrfs_check_shared 2019-07-01 13:34:53 +02:00
block-group.c btrfs: take overcommit into account in inc_block_group_ro 2020-10-17 10:11:21 +02:00
block-group.h btrfs: move struct io_ctl to free-space-cache.h 2019-09-09 14:59:15 +02:00
block-rsv.c btrfs: force chunk allocation if our global rsv is larger than metadata 2020-06-22 09:31:13 +02:00
block-rsv.h btrfs: migrate the global_block_rsv helpers to block-rsv.c 2019-07-02 12:30:55 +02:00
btrfs_inode.h btrfs: remove assumption about csum type form btrfs_print_data_csum_error() 2019-07-01 13:35:02 +02:00
check-integrity.c btrfs: fix possible NULL-pointer dereference in integrity checks 2020-02-24 08:36:53 +01:00
check-integrity.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
compression.c btrfs: move cond_wake_up functions out of ctree 2019-09-09 14:59:15 +02:00
compression.h btrfs: compression: replace set_level callbacks by a common helper 2019-09-09 14:59:11 +02:00
ctree.c btrfs: cleanup cow block on error 2020-11-05 11:43:27 +01:00
ctree.h btrfs: fix readahead hang and use-after-free after removing a device 2020-11-05 11:43:27 +01:00
delalloc-space.c Btrfs: fix qgroup double free after failure to reserve metadata for delalloc 2019-10-17 20:13:44 +02:00
delalloc-space.h btrfs: migrate the delalloc space stuff to it's own home 2019-07-04 17:26:17 +02:00
delayed-inode.c btrfs: qgroup: fix wrong qgroup metadata reserve for delayed inode 2020-11-05 11:43:26 +01:00
delayed-inode.h Btrfs: delayed-inode: use rb_first_cached for ins_root and del_root 2018-10-15 17:23:33 +02:00
delayed-ref.c Btrfs: fix race between adding and putting tree mod seq elements and nodes 2020-02-11 04:35:34 -08:00
delayed-ref.h btrfs: migrate the delayed refs rsv code 2019-07-04 17:26:17 +02:00
dev-replace.c btrfs: dev-replace: fail mount if we don't have replace item with target device 2020-11-18 19:20:29 +01:00
dev-replace.h btrfs: get fs_info from trans in btrfs_run_dev_replace 2019-04-29 19:02:43 +02:00
dir-item.c btrfs: remove unused parameter fs_info from btrfs_extend_item 2019-04-29 19:02:50 +02:00
disk-io.c btrfs: fix overflow when copying corrupt csums for a message 2020-10-01 13:18:24 +02:00
disk-io.h btrfs: Make reada_tree_block_flagged private 2019-09-09 14:59:11 +02:00
export.c btrfs: export helpers for subvolume name/id resolution 2020-08-26 10:40:49 +02:00
export.h btrfs: export helpers for subvolume name/id resolution 2020-08-26 10:40:49 +02:00
extent-tree.c btrfs: tracepoints: output proper root owner for trace_find_free_extent() 2020-11-18 19:20:16 +01:00
extent_io.c btrfs: fix potential deadlock in the search ioctl 2020-09-09 19:12:31 +02:00
extent_io.h btrfs: fix potential deadlock in the search ioctl 2020-09-09 19:12:31 +02:00
extent_map.c Btrfs: fix race between using extent maps and merging them 2020-02-19 19:53:00 +01:00
extent_map.h btrfs: Remove impossible condition from mergable_maps 2019-02-25 14:13:21 +01:00
file-item.c btrfs: do not ignore error from btrfs_next_leaf() when inserting checksums 2020-06-22 09:30:55 +02:00
file.c btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation 2020-10-14 10:33:00 +02:00
free-space-cache.c btrfs: fix space cache memory leak after transaction abort 2020-09-03 11:27:02 +02:00
free-space-cache.h btrfs: move struct io_ctl to free-space-cache.h 2019-09-09 14:59:15 +02:00
free-space-tree.c btrfs: move basic block_group definitions to their own header 2019-09-09 14:59:03 +02:00
free-space-tree.h btrfs: move basic block_group definitions to their own header 2019-09-09 14:59:03 +02:00
inode-item.c btrfs: Make btrfs_find_name_in_ext_backref return struct btrfs_inode_extref 2019-09-09 14:59:16 +02:00
inode-map.c btrfs: qgroup: Always free PREALLOC META reserve in btrfs_delalloc_release_extents() 2019-10-15 18:50:07 +02:00
inode-map.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
inode.c btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation 2020-10-14 10:33:00 +02:00
ioctl.c btrfs: fix potential overflow in cluster_pages_for_defrag on 32bit arch 2020-11-18 19:20:30 +01:00
locking.c btrfs: move cond_wake_up functions out of ctree 2019-09-09 14:59:15 +02:00
locking.h btrfs: Remove unused locking functions 2019-09-09 14:58:59 +02:00
lzo.c btrfs: compression: replace set_level callbacks by a common helper 2019-09-09 14:59:11 +02:00
misc.h btrfs: move math functions to misc.h 2019-09-09 14:59:15 +02:00
ordered-data.c Btrfs: fix btrfs_wait_ordered_range() so that it waits for all ordered extents 2020-02-28 17:22:24 +01:00
ordered-data.h btrfs: don't assume ordered sums to be 4 bytes 2019-07-01 13:35:00 +02:00
orphan.c btrfs: replace GPL boilerplate by SPDX -- sources 2018-04-12 16:29:51 +02:00
print-tree.c btrfs: require only sector size alignment for parent eb bytenr 2020-09-17 13:47:51 +02:00
print-tree.h btrfs: print-tree: debugging output enhancement 2018-04-20 19:18:16 +02:00
props.c btrfs: rename the btrfs_calc_*_metadata_size helpers 2019-09-09 14:59:13 +02:00
props.h btrfs: delete unused function btrfs_set_prop_trans 2019-04-29 19:02:54 +02:00
qgroup.c btrfs: fix lockdep splat when reading qgroup config on mount 2020-12-02 08:49:45 +01:00
qgroup.h btrfs: make btrfs_qgroup_check_reserved_leak take btrfs_inode 2020-09-03 11:26:47 +02:00
raid56.c btrfs: get rid of unique workqueue helper functions 2020-01-09 10:20:06 +01:00
raid56.h btrfs: constify map parameter for nr_parity_stripes and nr_data_stripes 2019-07-01 13:34:58 +02:00
rcu-string.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
reada.c btrfs: fix readahead hang and use-after-free after removing a device 2020-11-05 11:43:27 +01:00
ref-verify.c btrfs: ref-verify: fix memory leak in btrfs_ref_tree_mod 2020-11-18 19:20:28 +01:00
ref-verify.h btrfs: ref-verify: Use btrfs_ref to refactor btrfs_ref_tree_mod() 2019-04-29 19:02:49 +02:00
relocation.c btrfs: fix min reserved size calculation in merge_reloc_root 2020-11-18 19:20:28 +01:00
root-tree.c btrfs: do not delete mismatched root refs 2020-01-23 08:22:40 +01:00
scrub.c btrfs: allocate scrub workqueues outside of locks 2020-09-09 19:12:31 +02:00
send.c btrfs: use kvzalloc() to allocate clone_roots in btrfs_ioctl_send() 2020-11-05 11:43:26 +01:00
send.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
space-info.c btrfs: take overcommit into account in inc_block_group_ro 2020-10-17 10:11:21 +02:00
space-info.h btrfs: take overcommit into account in inc_block_group_ro 2020-10-17 10:11:21 +02:00
struct-funcs.c btrfs: tie extent buffer and it's token together 2019-09-09 14:59:16 +02:00
super.c btrfs: reset compression level for lzo on remount 2020-09-03 11:27:02 +02:00
sysfs.c btrfs: sysfs: use NOFS for device creation 2020-08-21 13:05:22 +02:00
sysfs.h btrfs: sysfs: move helper macros to sysfs.c 2019-09-09 14:59:08 +02:00
transaction.c btrfs: add wrapper for transaction abort predicate 2020-08-26 10:40:49 +02:00
transaction.h btrfs: add wrapper for transaction abort predicate 2020-08-26 10:40:49 +02:00
tree-checker.c btrfs: tree-checker: add missing returns after data_ref alignment checks 2020-12-02 08:49:45 +01:00
tree-checker.h btrfs: get fs_info from eb in btrfs_check_chunk_valid 2019-04-29 19:02:39 +02:00
tree-defrag.c btrfs: open code now trivial btrfs_set_lock_blocking 2019-02-25 14:13:27 +01:00
tree-log.c btrfs: reschedule if necessary when logging directory items 2020-11-05 11:43:26 +01:00
tree-log.h btrfs: get fs_info from trans in btrfs_set_log_full_commit 2019-04-29 19:02:41 +02:00
ulist.c btrfs: replace GPL boilerplate by SPDX -- sources 2018-04-12 16:29:51 +02:00
ulist.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
uuid-tree.c btrfs: handle ENOENT in btrfs_uuid_tree_iterate 2019-12-31 16:42:05 +01:00
volumes.c btrfs: don't access possibly stale fs_info data for printing duplicate device 2020-12-02 08:49:45 +01:00
volumes.h btrfs: fix readahead hang and use-after-free after removing a device 2020-11-05 11:43:27 +01:00
xattr.c Btrfs: fix failure to persist compression property xattr deletion on fsync 2019-06-17 16:37:17 +02:00
xattr.h btrfs: cleanup btrfs_setxattr_trans and drop transaction parameter 2019-04-29 19:02:44 +02:00
zlib.c btrfs: compression: replace set_level callbacks by a common helper 2019-09-09 14:59:11 +02:00
zstd.c btrfs: move cond_wake_up functions out of ctree 2019-09-09 14:59:15 +02:00