Filipe David Borba Manana 3fe81ce206 Btrfs: fix deadlock when iterating inode refs and running delayed inodes ... While running btrfs/004 from xfstests, after 503 iterations, dmesg reported a deadlock between tasks iterating inode refs and tasks running delayed inodes (during a transaction commit). It turns out that iterating inode refs implies doing one tree search and release all nodes in the path except the leaf node, and then passing that leaf node to btrfs_ref_to_path(), which in turn does another tree search without releasing the lock on the leaf node it received as parameter. This is a problem when other task wants to write to the btree as well and ends up updating the leaf that is read locked - the writer task locks the parent of the leaf and then blocks waiting for the leaf's lock to be released - at the same time, the task executing btrfs_ref_to_path() does a second tree search, without releasing the lock on the first leaf, and wants to access a leaf (the same or another one) that is a child of the same parent, resulting in a deadlock. The trace reported by lockdep follows. [84314.936373] INFO: task fsstress:11930 blocked for more than 120 seconds. [84314.936381] Tainted: G W O 3.12.0-fdm-btrfs-next-16+ #70 [84314.936383] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [84314.936386] fsstress D ffff8806e1bf8000 0 11930 11926 0x00000000 [84314.936393] ffff8804d6d89b78 0000000000000046 ffff8804d6d89b18 ffffffff810bd8bd [84314.936399] ffff8806e1bf8000 ffff8804d6d89fd8 ffff8804d6d89fd8 ffff8804d6d89fd8 [84314.936405] ffff880806308000 ffff8806e1bf8000 ffff8804d6d89c08 ffff8804deb8f190 [84314.936410] Call Trace: [84314.936421] [<ffffffff810bd8bd>] ? trace_hardirqs_on+0xd/0x10 [84314.936428] [<ffffffff81774269>] schedule+0x29/0x70 [84314.936451] [<ffffffffa0715bf5>] btrfs_tree_lock+0x75/0x270 [btrfs] [84314.936457] [<ffffffff810715c0>] ? __init_waitqueue_head+0x60/0x60 [84314.936470] [<ffffffffa06ba231>] btrfs_search_slot+0x7f1/0x930 [btrfs] [84314.936489] [<ffffffffa0731c2a>] ? __btrfs_run_delayed_items+0x13a/0x1e0 [btrfs] [84314.936504] [<ffffffffa06d2e1f>] btrfs_lookup_inode+0x2f/0xa0 [btrfs] [84314.936510] [<ffffffff810bd6ef>] ? trace_hardirqs_on_caller+0x1f/0x1e0 [84314.936528] [<ffffffffa073173c>] __btrfs_update_delayed_inode+0x4c/0x1d0 [btrfs] [84314.936543] [<ffffffffa0731c2a>] ? __btrfs_run_delayed_items+0x13a/0x1e0 [btrfs] [84314.936558] [<ffffffffa0731c2a>] ? __btrfs_run_delayed_items+0x13a/0x1e0 [btrfs] [84314.936573] [<ffffffffa0731c82>] __btrfs_run_delayed_items+0x192/0x1e0 [btrfs] [84314.936589] [<ffffffffa0731d03>] btrfs_run_delayed_items+0x13/0x20 [btrfs] [84314.936604] [<ffffffffa06dbcd4>] btrfs_flush_all_pending_stuffs+0x24/0x80 [btrfs] [84314.936620] [<ffffffffa06ddc13>] btrfs_commit_transaction+0x223/0xa20 [btrfs] [84314.936630] [<ffffffffa06ae5ae>] btrfs_sync_fs+0x6e/0x110 [btrfs] [84314.936635] [<ffffffff811d0b50>] ? __sync_filesystem+0x60/0x60 [84314.936639] [<ffffffff811d0b50>] ? __sync_filesystem+0x60/0x60 [84314.936643] [<ffffffff811d0b70>] sync_fs_one_sb+0x20/0x30 [84314.936648] [<ffffffff811a3541>] iterate_supers+0xf1/0x100 [84314.936652] [<ffffffff811d0c45>] sys_sync+0x55/0x90 [84314.936658] [<ffffffff8177ef12>] system_call_fastpath+0x16/0x1b [84314.936660] INFO: lockdep is turned off. [84314.936663] INFO: task btrfs:11955 blocked for more than 120 seconds. [84314.936666] Tainted: G W O 3.12.0-fdm-btrfs-next-16+ #70 [84314.936668] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [84314.936670] btrfs D ffff880541729a88 0 11955 11608 0x00000000 [84314.936674] ffff880541729a38 0000000000000046 ffff8805417299d8 ffffffff810bd8bd [84314.936680] ffff88075430c8a0 ffff880541729fd8 ffff880541729fd8 ffff880541729fd8 [84314.936685] ffffffff81c104e0 ffff88075430c8a0 ffff8804de8b00b8 ffff8804de8b0000 [84314.936690] Call Trace: [84314.936695] [<ffffffff810bd8bd>] ? trace_hardirqs_on+0xd/0x10 [84314.936700] [<ffffffff81774269>] schedule+0x29/0x70 [84314.936717] [<ffffffffa0715815>] btrfs_tree_read_lock+0xd5/0x140 [btrfs] [84314.936721] [<ffffffff810715c0>] ? __init_waitqueue_head+0x60/0x60 [84314.936733] [<ffffffffa06ba201>] btrfs_search_slot+0x7c1/0x930 [btrfs] [84314.936746] [<ffffffffa06bd505>] btrfs_find_item+0x55/0x160 [btrfs] [84314.936763] [<ffffffffa06ff689>] ? free_extent_buffer+0x49/0xc0 [btrfs] [84314.936780] [<ffffffffa073c9ca>] btrfs_ref_to_path+0xba/0x1e0 [btrfs] [84314.936797] [<ffffffffa06f9719>] ? release_extent_buffer+0xb9/0xe0 [btrfs] [84314.936813] [<ffffffffa06ff689>] ? free_extent_buffer+0x49/0xc0 [btrfs] [84314.936830] [<ffffffffa073cb50>] inode_to_path+0x60/0xd0 [btrfs] [84314.936846] [<ffffffffa073d365>] paths_from_inode+0x115/0x3c0 [btrfs] [84314.936851] [<ffffffff8118dd44>] ? kmem_cache_alloc_trace+0x114/0x200 [84314.936868] [<ffffffffa0714494>] btrfs_ioctl+0xf14/0x2030 [btrfs] [84314.936873] [<ffffffff817762db>] ? _raw_spin_unlock+0x2b/0x50 [84314.936877] [<ffffffff8116598f>] ? handle_mm_fault+0x34f/0xb00 [84314.936882] [<ffffffff81075563>] ? up_read+0x23/0x40 [84314.936886] [<ffffffff8177a41c>] ? __do_page_fault+0x20c/0x5a0 [84314.936892] [<ffffffff811b2946>] do_vfs_ioctl+0x96/0x570 [84314.936896] [<ffffffff81776e23>] ? error_sti+0x5/0x6 [84314.936901] [<ffffffff810b71e8>] ? trace_hardirqs_off_caller+0x28/0xd0 [84314.936906] [<ffffffff81776a09>] ? retint_swapgs+0xe/0x13 [84314.936910] [<ffffffff811b2eb1>] SyS_ioctl+0x91/0xb0 [84314.936915] [<ffffffff813eecde>] ? trace_hardirqs_on_thunk+0x3a/0x3f [84314.936920] [<ffffffff8177ef12>] system_call_fastpath+0x16/0x1b [84314.936922] INFO: lockdep is turned off. [84434.866873] INFO: task btrfs-transacti:11921 blocked for more than 120 seconds. [84434.866881] Tainted: G W O 3.12.0-fdm-btrfs-next-16+ #70 [84434.866883] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [84434.866886] btrfs-transacti D ffff880755b6a478 0 11921 2 0x00000000 [84434.866893] ffff8800735b9ce8 0000000000000046 ffff8800735b9c88 ffffffff810bd8bd [84434.866899] ffff8805a1b848a0 ffff8800735b9fd8 ffff8800735b9fd8 ffff8800735b9fd8 [84434.866904] ffffffff81c104e0 ffff8805a1b848a0 ffff880755b6a478 ffff8804cece78f0 [84434.866910] Call Trace: [84434.866920] [<ffffffff810bd8bd>] ? trace_hardirqs_on+0xd/0x10 [84434.866927] [<ffffffff81774269>] schedule+0x29/0x70 [84434.866948] [<ffffffffa06dd2ef>] wait_current_trans.isra.33+0xbf/0x120 [btrfs] [84434.866954] [<ffffffff810715c0>] ? __init_waitqueue_head+0x60/0x60 [84434.866970] [<ffffffffa06dec18>] start_transaction+0x388/0x5a0 [btrfs] [84434.866985] [<ffffffffa06db9b5>] ? transaction_kthread+0xb5/0x280 [btrfs] [84434.866999] [<ffffffffa06dee97>] btrfs_attach_transaction+0x17/0x20 [btrfs] [84434.867012] [<ffffffffa06dba9e>] transaction_kthread+0x19e/0x280 [btrfs] [84434.867026] [<ffffffffa06db900>] ? open_ctree+0x2260/0x2260 [btrfs] [84434.867030] [<ffffffff81070dad>] kthread+0xed/0x100 [84434.867035] [<ffffffff81070cc0>] ? flush_kthread_worker+0x190/0x190 [84434.867040] [<ffffffff8177ee6c>] ret_from_fork+0x7c/0xb0 [84434.867044] [<ffffffff81070cc0>] ? flush_kthread_worker+0x190/0x190 Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>		2014-01-28 13:19:59 -08:00
..
9p	consolidate simple ->d_delete() instances	2013-11-15 22:04:17 -05:00
adfs	adfs: delayed freeing of sbi	2013-10-24 23:43:27 -04:00
affs	remove obsolete references to powertweak	2013-11-27 20:34:32 -08:00
afs	Merge branch 'fscache' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs into linux-next	2013-10-28 19:36:46 -04:00
autofs4	autofs4: make freeing sbi rcu-delayed	2013-10-24 23:43:27 -04:00
befs	befs: split symlink iops in two - for short and long symlinks resp.	2013-10-24 23:34:50 -04:00
bfs	truncate: drop 'oldsize' truncate_pagecache() parameter	2013-09-12 15:38:02 -07:00
btrfs	Btrfs: fix deadlock when iterating inode refs and running delayed inodes	2014-01-28 13:19:59 -08:00
cachefiles	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs	2013-11-13 15:34:18 +09:00
ceph	ceph: Avoid data inconsistency due to d-cache aliasing in readpage()	2013-12-13 09:11:38 -08:00
cifs	cifs: set FILE_CREATED	2013-12-27 15:14:45 -06:00
coda	coda_revalidate_inode(): switch to passing inode...	2013-11-09 00:16:21 -05:00
configfs	configfs: fix race between dentry put and lookup	2013-11-21 16:42:27 -08:00
cramfs	cramfs: mark as obsolete	2013-11-13 12:09:12 +09:00
debugfs	debugfs: use list_next_entry() in debugfs_remove_recursive()	2013-11-13 12:09:24 +09:00
devpts	devpts: plug the memory leak in kill_sb	2013-11-13 12:09:36 +09:00
dlm	genetlink: only pass array to genl_register_family_with_ops()	2013-11-19 16:39:05 -05:00
ecryptfs	Quiet static checkers by removing unneeded conditionals	2013-11-22 10:58:14 -08:00
efivarfs	consolidate simple ->d_delete() instances	2013-11-15 22:04:17 -05:00
efs	efs: iget_locked() doesn't return an ERR_PTR()	2013-08-24 12:10:22 -04:00
exofs	truncate: drop 'oldsize' truncate_pagecache() parameter	2013-09-12 15:38:02 -07:00
exportfs	exportfs: fix quadratic behavior in filehandle lookup	2013-11-09 00:16:38 -05:00
ext2	ext2: Fix oops in ext2_get_block() called from ext2_quota_write()	2013-12-04 12:26:51 +01:00
ext3	Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs	2013-11-13 15:25:47 +09:00
ext4	ext4: fix bigalloc regression	2014-01-06 14:00:23 -05:00
f2fs	f2fs: issue more large discard command	2013-11-11 09:36:32 +09:00
fat	fat: rcu-delay unloading nls and freeing sbi	2013-10-24 23:43:28 -04:00
freevxfs	[readdir] convert freevxfs	2013-06-29 12:56:53 +04:00
fscache	Merge branch 'for-3.13/core' of git://git.kernel.dk/linux-block	2013-11-14 12:08:14 +09:00
fuse	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs	2013-11-13 15:34:18 +09:00
gfs2	GFS2: Fix unsafe dereference in dump_holder()	2014-01-02 12:18:04 +00:00
hfs	fs/hfs/btree.h: remove duplicate defines	2013-11-13 12:09:32 +09:00
hfsplus	block: submit_bio_wait() conversions	2013-11-24 16:33:41 -07:00
hostfs	consolidate simple ->d_delete() instances	2013-11-15 22:04:17 -05:00
hpfs	locks: break delegations on any attribute modification	2013-11-09 00:16:44 -05:00
hppfs	clean up scary strncpy(dst, src, strlen(src)) uses	2013-07-03 16:07:41 -07:00
hugetlbfs	cope with potentially long ->d_dname() output for shmem/hugetlb	2013-08-24 12:10:17 -04:00
isofs	isofs: don't pass dentry to isofs_hash{i,}_common()	2013-10-24 23:34:59 -04:00
jbd	jbd: Revert "jbd: remove dependency on __GFP_NOFAIL"	2013-10-31 20:37:15 +01:00
jbd2	jbd2: rename obsoleted msg JBD->JBD2	2013-12-08 21:14:59 -05:00
jffs2	jffs2: do not support the MLC nand	2013-10-27 16:27:07 -07:00
jfs	Just a patch to fix an oops in an error path.	2013-10-22 09:01:11 +01:00
lockd	LOCKD: Don't call utsname()->nodename from nlmclnt_setlockargs	2013-08-05 15:03:46 -04:00
logfs	block: submit_bio_wait() conversions	2013-11-24 16:33:41 -07:00
minix	fs/minix: Drop dependency on H8300	2013-09-16 18:20:25 -07:00
ncpfs	ncpfs: rcu-delay unload_nls() and freeing ncp_server	2013-10-24 23:43:28 -04:00
nfs	NFS client bugfixes	2013-12-05 13:05:48 -08:00
nfs_common
nfsd	nfsd: when reusing an existing repcache entry, unhash it first	2013-12-10 20:34:44 -05:00
nilfs2	nilfs2: fix segctor bug that causes file system corruption	2014-01-15 14:19:42 +07:00
nls
notify	fsnotify: update comments concerning locking scheme	2013-07-09 10:33:20 -07:00
ntfs	iget/iget5: don't bother with ->i_lock until we find a match	2013-11-09 00:16:31 -05:00
ocfs2	tree-wide: use reinit_completion instead of INIT_COMPLETION	2013-11-15 09:32:21 +09:00
omfs	truncate: drop 'oldsize' truncate_pagecache() parameter	2013-09-12 15:38:02 -07:00
openpromfs	[readdir] convert openpromfs	2013-06-29 12:56:32 +04:00
proc	procfs: also fix proc_reg_get_unmapped_area() for !MMU case	2013-12-12 18:19:26 -08:00
pstore	pstore: Don't allow high traffic options on fragile devices	2013-12-20 13:12:01 -08:00
qnx4	qnx4: i_sb is never NULL	2013-11-09 00:16:32 -05:00
qnx6	[readdir] convert qnx6	2013-06-29 12:56:39 +04:00
quota	genetlink: make multicast groups const, prevent abuse	2013-11-19 16:39:06 -05:00
ramfs	initmpfs: move rootfs code from fs/ramfs/ to init/	2013-09-11 15:59:37 -07:00
reiserfs	reiserfs: fix race with flush_used_journal_lists and flush_journal_list	2013-09-24 11:24:21 +02:00
romfs	[readdir] convert romfs	2013-06-29 12:56:29 +04:00
squashfs	Squashfs: fix failure to unlock pages on decompress error	2013-11-24 01:02:50 +00:00
sysfs	sysfs: give different locking key to regular and bin files	2013-12-07 21:22:00 -08:00
sysv	sysv: Add forgotten superblock lock init for v7 fs	2013-09-29 22:02:02 -04:00
ubifs	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs	2013-11-13 15:34:18 +09:00
udf	udf: fix for pathetic mount times in case of invalid file system	2013-10-18 22:39:07 +02:00
ufs	truncate: drop 'oldsize' truncate_pagecache() parameter	2013-09-12 15:38:02 -07:00
xfs	xfs: Calling destroy_work_on_stack() to pair with INIT_WORK_ONSTACK()	2014-01-10 12:39:38 -06:00
aio.c	Merge git://git.kvack.org/~bcrl/aio-next	2013-12-22 11:03:49 -08:00
anon_inodes.c	... and kill anon_inode_getfile_private()	2013-11-09 00:16:28 -05:00
attr.c	locks: break delegations on any attribute modification	2013-11-09 00:16:44 -05:00
bad_inode.c	[readdir] ->readdir() is gone	2013-06-29 12:57:04 +04:00
binfmt_aout.c	dump_skip(): dump_seek() replacement taking coredump_params	2013-11-09 00:16:26 -05:00
binfmt_elf_fdpic.c	elf{,_fdpic} coredump: get rid of pointless if (siginfo->si_signo)	2013-11-09 00:16:30 -05:00
binfmt_elf.c	elf{,_fdpic} coredump: get rid of pointless if (siginfo->si_signo)	2013-11-09 00:16:30 -05:00
binfmt_em86.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
binfmt_flat.c
binfmt_misc.c
binfmt_script.c
binfmt_som.c
bio-integrity.c	Merge branch 'for-3.12/core' of git://git.kernel.dk/linux-block	2013-09-22 15:00:11 -07:00
bio.c	bio: fix argument of __bio_add_page() for max_sectors > 0xffff	2013-11-18 12:31:27 -07:00
block_dev.c	a trivial writeback fix	2013-09-13 23:06:40 -04:00
buffer.c	fs: buffer: move allocation failure loop into the allocator	2013-10-16 21:35:53 -07:00
char_dev.c	Merge branch 'for-3.13/core' of git://git.kernel.dk/linux-block	2013-11-14 12:08:14 +09:00
compat_binfmt_elf.c
compat_ioctl.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
compat.c	[readdir] constify ->actor	2013-06-29 12:57:05 +04:00
coredump.c	dump_emit(): use __kernel_write(), not vfs_write()	2013-11-15 22:04:09 -05:00
coredump.h
dcache.c	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace	2014-01-17 17:29:36 -08:00
dcookies.c
direct-io.c	direct-io: Use return from cmpxchg to decide of assignment happened	2013-09-09 10:47:42 -07:00
drop_caches.c	shrinker: add node awareness	2013-09-10 18:56:31 -04:00
eventfd.c
eventpoll.c	epoll: do not take the nested ep->mtx on EPOLL_CTL_DEL	2014-01-02 14:40:30 -08:00
exec.c	Merge git://git.infradead.org/users/eparis/audit	2013-11-21 19:18:14 -08:00
fcntl.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
fhandle.c
file_table.c	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs	2013-11-13 15:34:18 +09:00
file.c
filesystems.c
fs_struct.c	seqcount: Add lockdep functionality to seqcount/seqlock structures	2013-11-06 12:40:26 +01:00
fs-writeback.c	writeback: Fix data corruption on NFS	2013-12-14 04:21:26 +08:00
generic_acl.c
inode.c	locks: break delegations on any attribute modification	2013-11-09 00:16:44 -05:00
internal.h	get rid of s_files and files_lock	2013-11-09 00:16:20 -05:00
ioctl.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
ioprio.c
Kconfig
Kconfig.binfmt
libfs.c	consolidate simple ->d_delete() instances	2013-11-15 22:04:17 -05:00
locks.c	locks: missing unlock on error in generic_add_lease()	2013-11-13 07:30:53 -05:00
Makefile
mbcache.c	fs: convert fs shrinkers to new scan/count API	2013-09-10 18:56:31 -04:00
mount.h	RCU'd vfsmounts	2013-11-09 00:16:19 -05:00
mpage.c
namei.c	dcache: allow word-at-a-time name hashing with big-endian CPUs	2013-12-12 10:39:01 -08:00
namespace.c	vfs: Fix a regression in mounting proc	2013-11-26 20:54:52 -08:00
no-block.c
open.c	locks: break delegations on any attribute modification	2013-11-09 00:16:44 -05:00
pipe.c	vfs: fix subtle use-after-free of pipe_inode_info	2013-12-02 09:44:51 -08:00
pnode.c	split __lookup_mnt() in two functions	2013-10-24 23:35:00 -04:00
pnode.h	vfs: Don't copy mount bind mounts of /proc/<pid>/ns/mnt between namespaces	2013-08-26 18:42:15 -07:00
posix_acl.c
proc_namespace.c	don't bother with vfsmount_lock in mounts_poll()	2013-10-24 23:34:59 -04:00
read_write.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
readdir.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
select.c	Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs	2013-11-13 15:34:18 +09:00
seq_file.c	seq_file: always clear m->count when we free m->buf	2013-11-18 19:07:53 -08:00
signalfd.c
splice.c	file->f_op is never NULL...	2013-10-24 23:34:54 -04:00
stack.c
stat.c	vfs: split out vfs_getattr_nosec	2013-11-09 00:16:31 -05:00
statfs.c	vfs: allow O_PATH file descriptors for fstatfs()	2013-10-12 13:12:31 -07:00
super.c	get rid of s_files and files_lock	2013-11-09 00:16:20 -05:00
sync.c	Merge branch 'akpm' (patches from Andrew Morton)	2013-11-13 15:45:43 +09:00
timerfd.c	timerfd: Add alarm timers	2013-05-29 12:57:34 -07:00
utimes.c	locks: break delegations on any attribute modification	2013-11-09 00:16:44 -05:00
xattr_acl.c
xattr.c