diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-10-04 10:05:13 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-10-04 10:05:13 -0700 |
commit | 79eb2c07afbe4d165734ea61a258dd8410ec6624 (patch) | |
tree | 40144fe701942830adcece5474846015afe87361 /fs/btrfs/disk-io.c | |
parent | b7a838ee7e8904c14e5d6ca2d0029bbad70fb761 (diff) | |
parent | d6e7ac65d4c106149d08a0ffba39fc516ae3d21b (diff) |
Merge tag 'for-6.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
- in incremental send, fix invalid clone operation for file that got
its size decreased
- fix __counted_by() annotation of send path cache entries, we do not
store the terminating NUL
- fix a longstanding bug in relocation (and quite hard to hit by
chance), drop back reference cache that can get out of sync after
transaction commit
- wait for fixup worker kthread before finishing umount
- add missing raid-stripe-tree extent for NOCOW files, zoned mode
cannot have NOCOW files but RST is meant to be a standalone feature
- handle transaction start error during relocation, avoid potential
NULL pointer dereference of relocation control structure (reported by
syzbot)
- disable module-wide rate limiting of debug level messages
- minor fix to tracepoint definition (reported by checkpatch.pl)
* tag 'for-6.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: disable rate limiting when debug enabled
btrfs: wait for fixup workers before stopping cleaner kthread during umount
btrfs: fix a NULL pointer dereference when failed to start a new trasacntion
btrfs: send: fix invalid clone operation for file that got its size decreased
btrfs: tracepoints: end assignment with semicolon at btrfs_qgroup_extent event class
btrfs: drop the backref cache during relocation if we commit
btrfs: also add stripe entries for NOCOW writes
btrfs: send: fix buffer overflow detection when copying path to cache entry
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r-- | fs/btrfs/disk-io.c | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 831fb901683c..4ad5db619b00 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4256,6 +4256,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_cleanup_defrag_inodes(fs_info); /* + * Wait for any fixup workers to complete. + * If we don't wait for them here and they are still running by the time + * we call kthread_stop() against the cleaner kthread further below, we + * get an use-after-free on the cleaner because the fixup worker adds an + * inode to the list of delayed iputs and then attempts to wakeup the + * cleaner kthread, which was already stopped and destroyed. We parked + * already the cleaner, but below we run all pending delayed iputs. + */ + btrfs_flush_workqueue(fs_info->fixup_workers); + + /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we |