mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-21 01:51:18 +00:00
a6703c7115
Whenever we attempt to do a non-aligned direct IO write with O_DSYNC, we end up triggering an assertion and crashing. Example reproducer: $ cat test.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV > /dev/null mount $DEV $MNT # Do a direct IO write with O_DSYNC into a non-aligned range... xfs_io -f -d -s -c "pwrite -S 0xab -b 64K 1111 64K" $MNT/foobar umount $MNT When running the reproducer an assertion fails and produces the following trace: [ 2418.403134] assertion failed: !current->journal_info || flush != BTRFS_RESERVE_FLUSH_DATA, in fs/btrfs/space-info.c:1467 [ 2418.403745] ------------[ cut here ]------------ [ 2418.404306] kernel BUG at fs/btrfs/ctree.h:3286! [ 2418.404862] invalid opcode: 0000 [#2] PREEMPT SMP DEBUG_PAGEALLOC PTI [ 2418.405451] CPU: 1 PID: 64705 Comm: xfs_io Tainted: G D 5.10.15-btrfs-next-87 #1 [ 2418.406026] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 2418.407228] RIP: 0010:assertfail.constprop.0+0x18/0x26 [btrfs] [ 2418.407835] Code: e6 48 c7 (...) [ 2418.409078] RSP: 0018:ffffb06080d13c98 EFLAGS: 00010246 [ 2418.409696] RAX: 000000000000006c RBX: ffff994c1debbf08 RCX: 0000000000000000 [ 2418.410302] RDX: 0000000000000000 RSI: 0000000000000027 RDI: 00000000ffffffff [ 2418.410904] RBP: ffff994c21770000 R08: 0000000000000000 R09: 0000000000000000 [ 2418.411504] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000010000 [ 2418.412111] R13: ffff994c22198400 R14: ffff994c21770000 R15: 0000000000000000 [ 2418.412713] FS: 00007f54fd7aff00(0000) GS:ffff994d35200000(0000) knlGS:0000000000000000 [ 2418.413326] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 2418.413933] CR2: 000056549596d000 CR3: 000000010b928003 CR4: 0000000000370ee0 [ 2418.414528] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 2418.415109] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 2418.415669] Call Trace: [ 2418.416254] btrfs_reserve_data_bytes.cold+0x22/0x22 [btrfs] [ 2418.416812] btrfs_check_data_free_space+0x4c/0xa0 [btrfs] [ 2418.417380] btrfs_buffered_write+0x1b0/0x7f0 [btrfs] [ 2418.418315] btrfs_file_write_iter+0x2a9/0x770 [btrfs] [ 2418.418920] new_sync_write+0x11f/0x1c0 [ 2418.419430] vfs_write+0x2bb/0x3b0 [ 2418.419972] __x64_sys_pwrite64+0x90/0xc0 [ 2418.420486] do_syscall_64+0x33/0x80 [ 2418.420979] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 2418.421486] RIP: 0033:0x7f54fda0b986 [ 2418.421981] Code: 48 c7 c0 (...) [ 2418.423019] RSP: 002b:00007ffc40569c38 EFLAGS: 00000246 ORIG_RAX: 0000000000000012 [ 2418.423547] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f54fda0b986 [ 2418.424075] RDX: 0000000000010000 RSI: 000056549595e000 RDI: 0000000000000003 [ 2418.424596] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000400 [ 2418.425119] R10: 0000000000000400 R11: 0000000000000246 R12: 00000000ffffffff [ 2418.425644] R13: 0000000000000400 R14: 0000000000010000 R15: 0000000000000000 [ 2418.426148] Modules linked in: btrfs blake2b_generic (...) [ 2418.429540] ---[ end trace ef2aeb44dc0afa34 ]--- 1) At btrfs_file_write_iter() we set current->journal_info to BTRFS_DIO_SYNC_STUB; 2) We then call __btrfs_direct_write(), which calls btrfs_direct_IO(); 3) We can't do the direct IO write because it starts at a non-aligned offset (1111). So at btrfs_direct_IO() we return -EINVAL (coming from check_direct_IO() which does the alignment check), but we leave current->journal_info set to BTRFS_DIO_SYNC_STUB - we only clear it at btrfs_dio_iomap_begin(), because we assume we always get there; 4) Then at __btrfs_direct_write() we see that the attempt to do the direct IO write was not successful, 0 bytes written, so we fallback to a buffered write by calling btrfs_buffered_write(); 5) There we call btrfs_check_data_free_space() which in turn calls btrfs_alloc_data_chunk_ondemand() and that calls btrfs_reserve_data_bytes() with flush == BTRFS_RESERVE_FLUSH_DATA; 6) Then at btrfs_reserve_data_bytes() we have current->journal_info set to BTRFS_DIO_SYNC_STUB, therefore not NULL, and flush has the value BTRFS_RESERVE_FLUSH_DATA, triggering the second assertion: int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush) { struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; int ret; ASSERT(flush == BTRFS_RESERVE_FLUSH_DATA || flush == BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE); ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_DATA); (...) So fix that by setting the journal to NULL whenever check_direct_IO() returns a failure. This bug only affects 5.10 kernels, and the regression was introduced in 5.10-rc1 by commit |
||
---|---|---|
.. | ||
9p | ||
adfs | ||
affs | ||
afs | ||
autofs | ||
befs | ||
bfs | ||
btrfs | ||
cachefiles | ||
ceph | ||
cifs | ||
coda | ||
configfs | ||
cramfs | ||
crypto | ||
debugfs | ||
devpts | ||
dlm | ||
ecryptfs | ||
efivarfs | ||
efs | ||
erofs | ||
exfat | ||
exportfs | ||
ext2 | ||
ext4 | ||
f2fs | ||
fat | ||
freevxfs | ||
fscache | ||
fuse | ||
gfs2 | ||
hfs | ||
hfsplus | ||
hostfs | ||
hpfs | ||
hugetlbfs | ||
iomap | ||
isofs | ||
jbd2 | ||
jffs2 | ||
jfs | ||
kernfs | ||
lockd | ||
minix | ||
nfs | ||
nfs_common | ||
nfsd | ||
nilfs2 | ||
nls | ||
notify | ||
ntfs | ||
ocfs2 | ||
omfs | ||
openpromfs | ||
orangefs | ||
overlayfs | ||
proc | ||
pstore | ||
qnx4 | ||
qnx6 | ||
quota | ||
ramfs | ||
reiserfs | ||
romfs | ||
squashfs | ||
sysfs | ||
sysv | ||
tracefs | ||
ubifs | ||
udf | ||
ufs | ||
unicode | ||
vboxsf | ||
verity | ||
xfs | ||
zonefs | ||
aio.c | ||
anon_inodes.c | ||
attr.c | ||
bad_inode.c | ||
binfmt_aout.c | ||
binfmt_elf.c | ||
binfmt_elf_fdpic.c | ||
binfmt_em86.c | ||
binfmt_flat.c | ||
binfmt_misc.c | ||
binfmt_script.c | ||
block_dev.c | ||
buffer.c | ||
char_dev.c | ||
compat_binfmt_elf.c | ||
coredump.c | ||
d_path.c | ||
dax.c | ||
dcache.c | ||
dcookies.c | ||
direct-io.c | ||
drop_caches.c | ||
eventfd.c | ||
eventpoll.c | ||
exec.c | ||
fcntl.c | ||
fhandle.c | ||
file.c | ||
file_table.c | ||
filesystems.c | ||
fs-writeback.c | ||
fs_context.c | ||
fs_parser.c | ||
fs_pin.c | ||
fs_struct.c | ||
fs_types.c | ||
fsopen.c | ||
init.c | ||
inode.c | ||
internal.h | ||
io-wq.c | ||
io-wq.h | ||
io_uring.c | ||
ioctl.c | ||
Kconfig | ||
Kconfig.binfmt | ||
kernel_read_file.c | ||
libfs.c | ||
locks.c | ||
Makefile | ||
mbcache.c | ||
mount.h | ||
mpage.c | ||
namei.c | ||
namespace.c | ||
no-block.c | ||
nsfs.c | ||
open.c | ||
pipe.c | ||
pnode.c | ||
pnode.h | ||
posix_acl.c | ||
proc_namespace.c | ||
read_write.c | ||
readdir.c | ||
remap_range.c | ||
select.c | ||
seq_file.c | ||
signalfd.c | ||
splice.c | ||
stack.c | ||
stat.c | ||
statfs.c | ||
super.c | ||
sync.c | ||
timerfd.c | ||
userfaultfd.c | ||
utimes.c | ||
xattr.c |