linux/fs/btrfs/disk-io.h

141 lines
5.2 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#ifndef BTRFS_DISK_IO_H
#define BTRFS_DISK_IO_H
#include <linux/sizes.h>
#include <linux/compiler_types.h>
#include "ctree.h"
#include "fs.h"
struct block_device;
struct super_block;
struct extent_buffer;
struct btrfs_device;
struct btrfs_fs_devices;
struct btrfs_fs_info;
struct btrfs_super_block;
struct btrfs_trans_handle;
struct btrfs_tree_parent_check;
struct btrfs_transaction;
#define BTRFS_SUPER_MIRROR_MAX 3
#define BTRFS_SUPER_MIRROR_SHIFT 12
/*
* Fixed blocksize for all devices, applies to specific ways of reading
* metadata like superblock. Must meet the set_blocksize requirements.
*
* Do not change.
*/
#define BTRFS_BDEV_BLOCKSIZE (4096)
static inline u64 btrfs_sb_offset(int mirror)
{
u64 start = SZ_16K;
if (mirror)
return start << (BTRFS_SUPER_MIRROR_SHIFT * mirror);
return BTRFS_SUPER_INFO_OFFSET;
}
void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
struct btrfs_tree_parent_check *check);
struct extent_buffer *btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info,
u64 bytenr, u64 owner_root,
int level);
int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info);
int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
const struct btrfs_super_block *disk_sb);
int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options);
void __cold close_ctree(struct btrfs_fs_info *fs_info);
btrfs: check superblock to ensure the fs was not modified at thaw time [BACKGROUND] There is an incident report that, one user hibernated the system, with one btrfs on removable device still mounted. Then by some incident, the btrfs got mounted and modified by another system/OS, then back to the hibernated system. After resuming from the hibernation, new write happened into the victim btrfs. Now the fs is completely broken, since the underlying btrfs is no longer the same one before the hibernation, and the user lost their data due to various transid mismatch. [REPRODUCER] We can emulate the situation using the following small script: truncate -s 1G $dev mkfs.btrfs -f $dev mount $dev $mnt fsstress -w -d $mnt -n 500 sync xfs_freeze -f $mnt cp $dev $dev.backup # There is no way to mount the same cloned fs on the same system, # as the conflicting fsid will be rejected by btrfs. # Thus here we have to wipe the fs using a different btrfs. mkfs.btrfs -f $dev.backup dd if=$dev.backup of=$dev bs=1M xfs_freeze -u $mnt fsstress -w -d $mnt -n 20 umount $mnt btrfs check $dev The final fsck will fail due to some tree blocks has incorrect fsid. This is enough to emulate the problem hit by the unfortunate user. [ENHANCEMENT] Although such case should not be that common, it can still happen from time to time. From the view of btrfs, we can detect any unexpected super block change, and if there is any unexpected change, we just mark the fs read-only, and thaw the fs. By this we can limit the damage to minimal, and I hope no one would lose their data by this anymore. Suggested-by: Goffredo Baroncelli <kreijack@libero.it> Link: https://lore.kernel.org/linux-btrfs/83bf3b4b-7f4c-387a-b286-9251e3991e34@bluemole.com/ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-24 12:16:22 +00:00
int btrfs_validate_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb, int mirror_num);
btrfs: fix compat_ro checks against remount [BUG] Even with commit 81d5d61454c3 ("btrfs: enhance unsupported compat RO flags handling"), btrfs can still mount a fs with unsupported compat_ro flags read-only, then remount it RW: # btrfs ins dump-super /dev/loop0 | grep compat_ro_flags -A 3 compat_ro_flags 0x403 ( FREE_SPACE_TREE | FREE_SPACE_TREE_VALID | unknown flag: 0x400 ) # mount /dev/loop0 /mnt/btrfs mount: /mnt/btrfs: wrong fs type, bad option, bad superblock on /dev/loop0, missing codepage or helper program, or other error. dmesg(1) may have more information after failed mount system call. ^^^ RW mount failed as expected ^^^ # dmesg -t | tail -n5 loop0: detected capacity change from 0 to 1048576 BTRFS: device fsid cb5b82f5-0fdd-4d81-9b4b-78533c324afa devid 1 transid 7 /dev/loop0 scanned by mount (1146) BTRFS info (device loop0): using crc32c (crc32c-intel) checksum algorithm BTRFS info (device loop0): using free space tree BTRFS error (device loop0): cannot mount read-write because of unknown compat_ro features (0x403) BTRFS error (device loop0): open_ctree failed # mount /dev/loop0 -o ro /mnt/btrfs # mount -o remount,rw /mnt/btrfs ^^^ RW remount succeeded unexpectedly ^^^ [CAUSE] Currently we use btrfs_check_features() to check compat_ro flags against our current mount flags. That function get reused between open_ctree() and btrfs_remount(). But for btrfs_remount(), the super block we passed in still has the old mount flags, thus btrfs_check_features() still believes we're mounting read-only. [FIX] Replace the existing @sb argument with @is_rw_mount. As originally we only use @sb to determine if the mount is RW. Now it's callers' responsibility to determine if the mount is RW, and since there are only two callers, the check is pretty simple: - caller in open_ctree() Just pass !sb_rdonly(). - caller in btrfs_remount() Pass !(*flags & SB_RDONLY), as our check should be against the new flags. Now we can correctly reject the RW remount: # mount /dev/loop0 -o ro /mnt/btrfs # mount -o remount,rw /mnt/btrfs mount: /mnt/btrfs: mount point not mounted or bad option. dmesg(1) may have more information after failed mount system call. # dmesg -t | tail -n 1 BTRFS error (device loop0: state M): cannot mount read-write because of unknown compat_ro features (0x403) Reported-by: Chung-Chiang Cheng <shepjeng@gmail.com> Fixes: 81d5d61454c3 ("btrfs: enhance unsupported compat RO flags handling") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-12-21 23:59:17 +00:00
int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
btrfs: check superblock to ensure the fs was not modified at thaw time [BACKGROUND] There is an incident report that, one user hibernated the system, with one btrfs on removable device still mounted. Then by some incident, the btrfs got mounted and modified by another system/OS, then back to the hibernated system. After resuming from the hibernation, new write happened into the victim btrfs. Now the fs is completely broken, since the underlying btrfs is no longer the same one before the hibernation, and the user lost their data due to various transid mismatch. [REPRODUCER] We can emulate the situation using the following small script: truncate -s 1G $dev mkfs.btrfs -f $dev mount $dev $mnt fsstress -w -d $mnt -n 500 sync xfs_freeze -f $mnt cp $dev $dev.backup # There is no way to mount the same cloned fs on the same system, # as the conflicting fsid will be rejected by btrfs. # Thus here we have to wipe the fs using a different btrfs. mkfs.btrfs -f $dev.backup dd if=$dev.backup of=$dev bs=1M xfs_freeze -u $mnt fsstress -w -d $mnt -n 20 umount $mnt btrfs check $dev The final fsck will fail due to some tree blocks has incorrect fsid. This is enough to emulate the problem hit by the unfortunate user. [ENHANCEMENT] Although such case should not be that common, it can still happen from time to time. From the view of btrfs, we can detect any unexpected super block change, and if there is any unexpected change, we just mark the fs read-only, and thaw the fs. By this we can limit the damage to minimal, and I hope no one would lose their data by this anymore. Suggested-by: Goffredo Baroncelli <kreijack@libero.it> Link: https://lore.kernel.org/linux-btrfs/83bf3b4b-7f4c-387a-b286-9251e3991e34@bluemole.com/ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-24 12:16:22 +00:00
int copy_num, bool drop_cache);
int btrfs_commit_super(struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
struct btrfs_key *key);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
Btrfs: fix oops caused by the space balance and dead roots When doing space balance and subvolume destroy at the same time, we met the following oops: kernel BUG at fs/btrfs/relocation.c:2247! RIP: 0010: [<ffffffffa04cec16>] prepare_to_merge+0x154/0x1f0 [btrfs] Call Trace: [<ffffffffa04b5ab7>] relocate_block_group+0x466/0x4e6 [btrfs] [<ffffffffa04b5c7a>] btrfs_relocate_block_group+0x143/0x275 [btrfs] [<ffffffffa0495c56>] btrfs_relocate_chunk.isra.27+0x5c/0x5a2 [btrfs] [<ffffffffa0459871>] ? btrfs_item_key_to_cpu+0x15/0x31 [btrfs] [<ffffffffa048b46a>] ? btrfs_get_token_64+0x7e/0xcd [btrfs] [<ffffffffa04a3467>] ? btrfs_tree_read_unlock_blocking+0xb2/0xb7 [btrfs] [<ffffffffa049907d>] btrfs_balance+0x9c7/0xb6f [btrfs] [<ffffffffa049ef84>] btrfs_ioctl_balance+0x234/0x2ac [btrfs] [<ffffffffa04a1e8e>] btrfs_ioctl+0xd87/0x1ef9 [btrfs] [<ffffffff81122f53>] ? path_openat+0x234/0x4db [<ffffffff813c3b78>] ? __do_page_fault+0x31d/0x391 [<ffffffff810f8ab6>] ? vma_link+0x74/0x94 [<ffffffff811250f5>] vfs_ioctl+0x1d/0x39 [<ffffffff811258c8>] do_vfs_ioctl+0x32d/0x3e2 [<ffffffff811259d4>] SyS_ioctl+0x57/0x83 [<ffffffff813c3bfa>] ? do_page_fault+0xe/0x10 [<ffffffff813c73c2>] system_call_fastpath+0x16/0x1b It is because we returned the error number if the reference of the root was 0 when doing space relocation. It was not right here, because though the root was dead(refs == 0), but the space it held still need be relocated, or we could not remove the block group. So in this case, we should return the root no matter it is dead or not. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Josef Bacik <jbacik@fusionio.com> Signed-off-by: Chris Mason <chris.mason@fusionio.com>
2013-09-25 13:47:44 +00:00
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, bool check_ref);
btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong@gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+=tHJX7nb9DPw@mail.gmail.com/ CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-16 02:17:36 +00:00
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
btrfs: fix double free of anonymous device after snapshot creation failure When creating a snapshot we may do a double free of an anonymous device in case there's an error committing the transaction. The second free may result in freeing an anonymous device number that was allocated by some other subsystem in the kernel or another btrfs filesystem. The steps that lead to this: 1) At ioctl.c:create_snapshot() we allocate an anonymous device number and assign it to pending_snapshot->anon_dev; 2) Then we call btrfs_commit_transaction() and end up at transaction.c:create_pending_snapshot(); 3) There we call btrfs_get_new_fs_root() and pass it the anonymous device number stored in pending_snapshot->anon_dev; 4) btrfs_get_new_fs_root() frees that anonymous device number because btrfs_lookup_fs_root() returned a root - someone else did a lookup of the new root already, which could some task doing backref walking; 5) After that some error happens in the transaction commit path, and at ioctl.c:create_snapshot() we jump to the 'fail' label, and after that we free again the same anonymous device number, which in the meanwhile may have been reallocated somewhere else, because pending_snapshot->anon_dev still has the same value as in step 1. Recently syzbot ran into this and reported the following trace: ------------[ cut here ]------------ ida_free called for id=51 which is not allocated. WARNING: CPU: 1 PID: 31038 at lib/idr.c:525 ida_free+0x370/0x420 lib/idr.c:525 Modules linked in: CPU: 1 PID: 31038 Comm: syz-executor.2 Not tainted 6.8.0-rc4-syzkaller-00410-gc02197fc9076 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 RIP: 0010:ida_free+0x370/0x420 lib/idr.c:525 Code: 10 42 80 3c 28 (...) RSP: 0018:ffffc90015a67300 EFLAGS: 00010246 RAX: be5130472f5dd000 RBX: 0000000000000033 RCX: 0000000000040000 RDX: ffffc90009a7a000 RSI: 000000000003ffff RDI: 0000000000040000 RBP: ffffc90015a673f0 R08: ffffffff81577992 R09: 1ffff92002b4cdb4 R10: dffffc0000000000 R11: fffff52002b4cdb5 R12: 0000000000000246 R13: dffffc0000000000 R14: ffffffff8e256b80 R15: 0000000000000246 FS: 00007fca3f4b46c0(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f167a17b978 CR3: 000000001ed26000 CR4: 0000000000350ef0 Call Trace: <TASK> btrfs_get_root_ref+0xa48/0xaf0 fs/btrfs/disk-io.c:1346 create_pending_snapshot+0xff2/0x2bc0 fs/btrfs/transaction.c:1837 create_pending_snapshots+0x195/0x1d0 fs/btrfs/transaction.c:1931 btrfs_commit_transaction+0xf1c/0x3740 fs/btrfs/transaction.c:2404 create_snapshot+0x507/0x880 fs/btrfs/ioctl.c:848 btrfs_mksubvol+0x5d0/0x750 fs/btrfs/ioctl.c:998 btrfs_mksnapshot+0xb5/0xf0 fs/btrfs/ioctl.c:1044 __btrfs_ioctl_snap_create+0x387/0x4b0 fs/btrfs/ioctl.c:1306 btrfs_ioctl_snap_create_v2+0x1ca/0x400 fs/btrfs/ioctl.c:1393 btrfs_ioctl+0xa74/0xd40 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0xfe/0x170 fs/ioctl.c:857 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7fca3e67dda9 Code: 28 00 00 00 (...) RSP: 002b:00007fca3f4b40c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fca3e7abf80 RCX: 00007fca3e67dda9 RDX: 00000000200005c0 RSI: 0000000050009417 RDI: 0000000000000003 RBP: 00007fca3e6ca47a R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fca3e7abf80 R15: 00007fff6bf95658 </TASK> Where we get an explicit message where we attempt to free an anonymous device number that is not currently allocated. It happens in a different code path from the example below, at btrfs_get_root_ref(), so this change may not fix the case triggered by syzbot. To fix at least the code path from the example above, change btrfs_get_root_ref() and its callers to receive a dev_t pointer argument for the anonymous device number, so that in case it frees the number, it also resets it to 0, so that up in the call chain we don't attempt to do the double free. CC: stable@vger.kernel.org # 5.10+ Link: https://lore.kernel.org/linux-btrfs/000000000000f673a1061202f630@google.com/ Fixes: e03ee2fe873e ("btrfs: do not ASSERT() if the newly created subvolume already got read") Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-02-23 16:38:43 +00:00
u64 objectid, dev_t *anon_dev);
btrfs: add a helper to read the tree_root commit root for backref lookup I got the following lockdep splat with tree locks converted to rwsem patches on btrfs/104: ====================================================== WARNING: possible circular locking dependency detected 5.9.0+ #102 Not tainted ------------------------------------------------------ btrfs-cleaner/903 is trying to acquire lock: ffff8e7fab6ffe30 (btrfs-root-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x170 but task is already holding lock: ffff8e7fab628a88 (&fs_info->commit_root_sem){++++}-{3:3}, at: btrfs_find_all_roots+0x41/0x80 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&fs_info->commit_root_sem){++++}-{3:3}: down_read+0x40/0x130 caching_thread+0x53/0x5a0 btrfs_work_helper+0xfa/0x520 process_one_work+0x238/0x540 worker_thread+0x55/0x3c0 kthread+0x13a/0x150 ret_from_fork+0x1f/0x30 -> #2 (&caching_ctl->mutex){+.+.}-{3:3}: __mutex_lock+0x7e/0x7b0 btrfs_cache_block_group+0x1e0/0x510 find_free_extent+0xb6e/0x12f0 btrfs_reserve_extent+0xb3/0x1b0 btrfs_alloc_tree_block+0xb1/0x330 alloc_tree_block_no_bg_flush+0x4f/0x60 __btrfs_cow_block+0x11d/0x580 btrfs_cow_block+0x10c/0x220 commit_cowonly_roots+0x47/0x2e0 btrfs_commit_transaction+0x595/0xbd0 sync_filesystem+0x74/0x90 generic_shutdown_super+0x22/0x100 kill_anon_super+0x14/0x30 btrfs_kill_super+0x12/0x20 deactivate_locked_super+0x36/0xa0 cleanup_mnt+0x12d/0x190 task_work_run+0x5c/0xa0 exit_to_user_mode_prepare+0x1df/0x200 syscall_exit_to_user_mode+0x54/0x280 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #1 (&space_info->groups_sem){++++}-{3:3}: down_read+0x40/0x130 find_free_extent+0x2ed/0x12f0 btrfs_reserve_extent+0xb3/0x1b0 btrfs_alloc_tree_block+0xb1/0x330 alloc_tree_block_no_bg_flush+0x4f/0x60 __btrfs_cow_block+0x11d/0x580 btrfs_cow_block+0x10c/0x220 commit_cowonly_roots+0x47/0x2e0 btrfs_commit_transaction+0x595/0xbd0 sync_filesystem+0x74/0x90 generic_shutdown_super+0x22/0x100 kill_anon_super+0x14/0x30 btrfs_kill_super+0x12/0x20 deactivate_locked_super+0x36/0xa0 cleanup_mnt+0x12d/0x190 task_work_run+0x5c/0xa0 exit_to_user_mode_prepare+0x1df/0x200 syscall_exit_to_user_mode+0x54/0x280 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #0 (btrfs-root-00){++++}-{3:3}: __lock_acquire+0x1167/0x2150 lock_acquire+0xb9/0x3d0 down_read_nested+0x43/0x130 __btrfs_tree_read_lock+0x32/0x170 __btrfs_read_lock_root_node+0x3a/0x50 btrfs_search_slot+0x614/0x9d0 btrfs_find_root+0x35/0x1b0 btrfs_read_tree_root+0x61/0x120 btrfs_get_root_ref+0x14b/0x600 find_parent_nodes+0x3e6/0x1b30 btrfs_find_all_roots_safe+0xb4/0x130 btrfs_find_all_roots+0x60/0x80 btrfs_qgroup_trace_extent_post+0x27/0x40 btrfs_add_delayed_data_ref+0x3fd/0x460 btrfs_free_extent+0x42/0x100 __btrfs_mod_ref+0x1d7/0x2f0 walk_up_proc+0x11c/0x400 walk_up_tree+0xf0/0x180 btrfs_drop_snapshot+0x1c7/0x780 btrfs_clean_one_deleted_snapshot+0xfb/0x110 cleaner_kthread+0xd4/0x140 kthread+0x13a/0x150 ret_from_fork+0x1f/0x30 other info that might help us debug this: Chain exists of: btrfs-root-00 --> &caching_ctl->mutex --> &fs_info->commit_root_sem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&fs_info->commit_root_sem); lock(&caching_ctl->mutex); lock(&fs_info->commit_root_sem); lock(btrfs-root-00); *** DEADLOCK *** 3 locks held by btrfs-cleaner/903: #0: ffff8e7fab628838 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: cleaner_kthread+0x6e/0x140 #1: ffff8e7faadac640 (sb_internal){.+.+}-{0:0}, at: start_transaction+0x40b/0x5c0 #2: ffff8e7fab628a88 (&fs_info->commit_root_sem){++++}-{3:3}, at: btrfs_find_all_roots+0x41/0x80 stack backtrace: CPU: 0 PID: 903 Comm: btrfs-cleaner Not tainted 5.9.0+ #102 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014 Call Trace: dump_stack+0x8b/0xb0 check_noncircular+0xcf/0xf0 __lock_acquire+0x1167/0x2150 ? __bfs+0x42/0x210 lock_acquire+0xb9/0x3d0 ? __btrfs_tree_read_lock+0x32/0x170 down_read_nested+0x43/0x130 ? __btrfs_tree_read_lock+0x32/0x170 __btrfs_tree_read_lock+0x32/0x170 __btrfs_read_lock_root_node+0x3a/0x50 btrfs_search_slot+0x614/0x9d0 ? find_held_lock+0x2b/0x80 btrfs_find_root+0x35/0x1b0 ? do_raw_spin_unlock+0x4b/0xa0 btrfs_read_tree_root+0x61/0x120 btrfs_get_root_ref+0x14b/0x600 find_parent_nodes+0x3e6/0x1b30 btrfs_find_all_roots_safe+0xb4/0x130 btrfs_find_all_roots+0x60/0x80 btrfs_qgroup_trace_extent_post+0x27/0x40 btrfs_add_delayed_data_ref+0x3fd/0x460 btrfs_free_extent+0x42/0x100 __btrfs_mod_ref+0x1d7/0x2f0 walk_up_proc+0x11c/0x400 walk_up_tree+0xf0/0x180 btrfs_drop_snapshot+0x1c7/0x780 ? btrfs_clean_one_deleted_snapshot+0x73/0x110 btrfs_clean_one_deleted_snapshot+0xfb/0x110 cleaner_kthread+0xd4/0x140 ? btrfs_alloc_root+0x50/0x50 kthread+0x13a/0x150 ? kthread_create_worker_on_cpu+0x40/0x40 ret_from_fork+0x1f/0x30 BTRFS info (device sdb): disk space caching is enabled BTRFS info (device sdb): has skinny extents This happens because qgroups does a backref lookup when we create a delayed ref. From here it may have to look up a root from an indirect ref, which does a normal lookup on the tree_root, which takes the read lock on the tree_root nodes. To fix this we need to add a variant for looking up roots that searches the commit root of the tree_root. Then when we do the backref search using the commit root we are sure to not take any locks on the tree_root nodes. This gets rid of the lockdep splat when running btrfs/104. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-19 20:02:31 +00:00
struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
struct btrfs_path *path,
u64 objectid);
int btrfs_global_root_insert(struct btrfs_root *root);
void btrfs_global_root_delete(struct btrfs_root *root);
struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info,
struct btrfs_key *key);
struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr);
struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr);
struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info);
Btrfs: fix oops caused by the space balance and dead roots When doing space balance and subvolume destroy at the same time, we met the following oops: kernel BUG at fs/btrfs/relocation.c:2247! RIP: 0010: [<ffffffffa04cec16>] prepare_to_merge+0x154/0x1f0 [btrfs] Call Trace: [<ffffffffa04b5ab7>] relocate_block_group+0x466/0x4e6 [btrfs] [<ffffffffa04b5c7a>] btrfs_relocate_block_group+0x143/0x275 [btrfs] [<ffffffffa0495c56>] btrfs_relocate_chunk.isra.27+0x5c/0x5a2 [btrfs] [<ffffffffa0459871>] ? btrfs_item_key_to_cpu+0x15/0x31 [btrfs] [<ffffffffa048b46a>] ? btrfs_get_token_64+0x7e/0xcd [btrfs] [<ffffffffa04a3467>] ? btrfs_tree_read_unlock_blocking+0xb2/0xb7 [btrfs] [<ffffffffa049907d>] btrfs_balance+0x9c7/0xb6f [btrfs] [<ffffffffa049ef84>] btrfs_ioctl_balance+0x234/0x2ac [btrfs] [<ffffffffa04a1e8e>] btrfs_ioctl+0xd87/0x1ef9 [btrfs] [<ffffffff81122f53>] ? path_openat+0x234/0x4db [<ffffffff813c3b78>] ? __do_page_fault+0x31d/0x391 [<ffffffff810f8ab6>] ? vma_link+0x74/0x94 [<ffffffff811250f5>] vfs_ioctl+0x1d/0x39 [<ffffffff811258c8>] do_vfs_ioctl+0x32d/0x3e2 [<ffffffff811259d4>] SyS_ioctl+0x57/0x83 [<ffffffff813c3bfa>] ? do_page_fault+0xe/0x10 [<ffffffff813c73c2>] system_call_fastpath+0x16/0x1b It is because we returned the error number if the reference of the root was 0 when doing space relocation. It was not right here, because though the root was dead(refs == 0), but the space it held still need be relocated, or we could not remove the block group. So in this case, we should return the root no matter it is dead or not. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Josef Bacik <jbacik@fusionio.com> Signed-off-by: Chris Mason <chris.mason@fusionio.com>
2013-09-25 13:47:44 +00:00
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info);
void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
int btrfs_validate_extent_buffer(struct extent_buffer *eb,
struct btrfs_tree_parent_check *check);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
#endif
/*
* This function is used to grab the root, and avoid it is freed when we
* access it. But it doesn't ensure that the tree is not dropped.
*
* If you want to ensure the whole tree is safe, you should use
* fs_info->subvol_srcu
*/
static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root)
{
if (!root)
return NULL;
if (refcount_inc_not_zero(&root->refs))
return root;
return NULL;
}
void btrfs_put_root(struct btrfs_root *root);
void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans,
struct extent_buffer *buf);
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
int atomic);
int btrfs_read_extent_buffer(struct extent_buffer *buf,
struct btrfs_tree_parent_check *check);
blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio);
int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
u64 objectid);
int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid);
int btrfs_init_root_free_objectid(struct btrfs_root *root);
#endif