Commit 9351590
cifs: properly invalidate cached root handle when closing it
Cached root file was not being completely invalidated sometimes.
Reproducing:
- With a DFS share with 2 targets, one disabled and one enabled
- start some I/O on the mount
# while true; do ls /mnt/dfs; done
- at the same time, disable the enabled target and enable the disabled
one
- wait for DFS cache to expire
- on reconnect, the previous cached root handle should be invalid, but
open_cached_dir_by_dentry() will still try to use it, but throws a
use-after-free warning (kref_get())
Make smb2_close_cached_fid() invalidate all fields every time, but only
send an SMB2_close() when the entry is still valid.
Signed-off-by: Enzo Matsumiya <ematsumiya@suse.de>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>1 parent 8d014f5 commit 9351590
1 file changed
Lines changed: 13 additions & 7 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
689 | 689 | | |
690 | 690 | | |
691 | 691 | | |
692 | | - | |
693 | | - | |
694 | | - | |
695 | | - | |
696 | | - | |
697 | | - | |
698 | | - | |
| 692 | + | |
| 693 | + | |
| 694 | + | |
| 695 | + | |
| 696 | + | |
| 697 | + | |
| 698 | + | |
| 699 | + | |
| 700 | + | |
| 701 | + | |
| 702 | + | |
| 703 | + | |
| 704 | + | |
699 | 705 | | |
700 | 706 | | |
701 | 707 | | |
| |||
0 commit comments