If a nilfs2 filesystem is downgraded to read-only due to metadata
corruption on disk and is remounted read/write, or if emergency
read-only remount is performed, detaching a log writer and
synchronizing the filesystem can be done at the same time.
In these cases, use-after-free of the log writer (hereinafter
nilfs->ns_writer) can happen as shown in the scenario below:
Task1 Task2
-------------------------------- ------------------------------
nilfs_construct_segment
nilfs_segctor_sync
init_wait
init_waitqueue_entry
add_wait_queue
schedule
nilfs_remount (R/W remount case)
nilfs_attach_log_writer
nilfs_detach_log_writer
nilfs_segctor_destroy
kfree
finish_wait
_raw_spin_lock_irqsave
__raw_spin_lock_irqsave
do_raw_spin_lock
debug_spin_lock_before <-- use-after-free
While Task1 is sleeping, nilfs->ns_writer is freed by Task2. After
Task1 waked up, Task1 accesses nilfs->ns_writer which is already
freed. This scenario diagram is based on the Shigeru Yoshida's post
[1].
This patch fixes the issue by not detaching nilfs->ns_writer on
remount so that this UAF race doesn't happen. Along with this change,
this patch also inserts a few necessary read-only checks with
superblock instance where only the ns_writer pointer was used to check
if the filesystem is read-only.
Link: https://syzkaller.appspot.com/bug?id=79a4c002e960419ca173d55e863bd09e8112df8b
Link: https://lkml.kernel.org/r/20221103141759.1836312-1-syoshida@xxxxxxxxxx [1]
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@xxxxxxxxx>
Reported-by: syzbot+f816fa82f8783f7a02bb@xxxxxxxxxxxxxxxxxxxxxxxxx
Reported-by: Shigeru Yoshida <syoshida@xxxxxxxxxx>
Tested-by: Ryusuke Konishi <konishi.ryusuke@xxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
fs/nilfs2/segment.c | 15 ++++++++-------
fs/nilfs2/super.c | 2 --
2 files changed, 8 insertions(+), 9 deletions(-)
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index b4cebad21b48..3335ef352915 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -317,7 +317,7 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb)
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_sc_info *sci = nilfs->ns_writer;
- if (!sci || !sci->sc_flush_request)
+ if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request)
return;
set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
@@ -2242,7 +2242,7 @@ int nilfs_construct_segment(struct super_block *sb)
struct nilfs_sc_info *sci = nilfs->ns_writer;
struct nilfs_transaction_info *ti;
- if (!sci)
+ if (sb_rdonly(sb) || unlikely(!sci))
return -EROFS;
/* A call inside transactions causes a deadlock. */
@@ -2280,7 +2280,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
struct nilfs_transaction_info ti;
int err = 0;
- if (!sci)
+ if (sb_rdonly(sb) || unlikely(!sci))
return -EROFS;
nilfs_transaction_lock(sb, &ti, 0);
@@ -2776,11 +2776,12 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
if (nilfs->ns_writer) {
/*
- * This happens if the filesystem was remounted
- * read/write after nilfs_error degenerated it into a
- * read-only mount.
+ * This happens if the filesystem is made read-only by
+ * __nilfs_error or nilfs_remount and then remounted
+ * read/write. In these cases, reuse the existing
+ * writer.
*/
- nilfs_detach_log_writer(sb);
+ return 0;
}
nilfs->ns_writer = nilfs_segctor_new(sb, root);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index ba108f915391..6edb6e0dd61f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1133,8 +1133,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out;
if (*flags & SB_RDONLY) {
- /* Shutting down log writer */
- nilfs_detach_log_writer(sb);
sb->s_flags |= SB_RDONLY;
/*
--
2.34.1
