Commit e6a9467e authored by Darrick J. Wong's avatar Darrick J. Wong Committed by Linus Torvalds

ocfs2: fix inode bh swapping mixup in ocfs2_reflink_inodes_lock

ocfs2_reflink_inodes_lock() can swap the inode1/inode2 variables so that
we always grab cluster locks in order of increasing inode number.

Unfortunately, we forget to swap the inode record buffer head pointers
when we've done this, which leads to incorrect bookkeepping when we're
trying to make the two inodes have the same refcount tree.

This has the effect of causing filesystem shutdowns if you're trying to
reflink data from inode 100 into inode 97, where inode 100 already has a
refcount tree attached and inode 97 doesn't.  The reflink code decides
to copy the refcount tree pointer from 100 to 97, but uses inode 97's
inode record to open the tree root (which it doesn't have) and blows up.
This issue causes filesystem shutdowns and metadata corruption!

Link: http://lkml.kernel.org/r/20190312214910.GK20533@magnolia
Fixes: 29ac8e85 ("ocfs2: implement the VFS clone_range, copy_range, and dedupe_range features")
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: default avatarJoseph Qi <jiangqi903@gmail.com>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 9b7ea46a
...@@ -4719,22 +4719,23 @@ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, ...@@ -4719,22 +4719,23 @@ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode,
/* Lock an inode and grab a bh pointing to the inode. */ /* Lock an inode and grab a bh pointing to the inode. */
int ocfs2_reflink_inodes_lock(struct inode *s_inode, int ocfs2_reflink_inodes_lock(struct inode *s_inode,
struct buffer_head **bh1, struct buffer_head **bh_s,
struct inode *t_inode, struct inode *t_inode,
struct buffer_head **bh2) struct buffer_head **bh_t)
{ {
struct inode *inode1; struct inode *inode1 = s_inode;
struct inode *inode2; struct inode *inode2 = t_inode;
struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi1;
struct ocfs2_inode_info *oi2; struct ocfs2_inode_info *oi2;
struct buffer_head *bh1 = NULL;
struct buffer_head *bh2 = NULL;
bool same_inode = (s_inode == t_inode); bool same_inode = (s_inode == t_inode);
bool need_swap = (inode1->i_ino > inode2->i_ino);
int status; int status;
/* First grab the VFS and rw locks. */ /* First grab the VFS and rw locks. */
lock_two_nondirectories(s_inode, t_inode); lock_two_nondirectories(s_inode, t_inode);
inode1 = s_inode; if (need_swap)
inode2 = t_inode;
if (inode1->i_ino > inode2->i_ino)
swap(inode1, inode2); swap(inode1, inode2);
status = ocfs2_rw_lock(inode1, 1); status = ocfs2_rw_lock(inode1, 1);
...@@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, ...@@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno,
(unsigned long long)oi2->ip_blkno); (unsigned long long)oi2->ip_blkno);
if (*bh1)
*bh1 = NULL;
if (*bh2)
*bh2 = NULL;
/* We always want to lock the one with the lower lockid first. */ /* We always want to lock the one with the lower lockid first. */
if (oi1->ip_blkno > oi2->ip_blkno) if (oi1->ip_blkno > oi2->ip_blkno)
mlog_errno(-ENOLCK); mlog_errno(-ENOLCK);
/* lock id1 */ /* lock id1 */
status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); status = ocfs2_inode_lock_nested(inode1, &bh1, 1,
OI_LS_REFLINK_TARGET);
if (status < 0) { if (status < 0) {
if (status != -ENOENT) if (status != -ENOENT)
mlog_errno(status); mlog_errno(status);
...@@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, ...@@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
/* lock id2 */ /* lock id2 */
if (!same_inode) { if (!same_inode) {
status = ocfs2_inode_lock_nested(inode2, bh2, 1, status = ocfs2_inode_lock_nested(inode2, &bh2, 1,
OI_LS_REFLINK_TARGET); OI_LS_REFLINK_TARGET);
if (status < 0) { if (status < 0) {
if (status != -ENOENT) if (status != -ENOENT)
mlog_errno(status); mlog_errno(status);
goto out_cl1; goto out_cl1;
} }
} else } else {
*bh2 = *bh1; bh2 = bh1;
}
/*
* If we swapped inode order above, we have to swap the buffer heads
* before passing them back to the caller.
*/
if (need_swap)
swap(bh1, bh2);
*bh_s = bh1;
*bh_t = bh2;
trace_ocfs2_double_lock_end( trace_ocfs2_double_lock_end(
(unsigned long long)oi1->ip_blkno, (unsigned long long)oi1->ip_blkno,
...@@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, ...@@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
out_cl1: out_cl1:
ocfs2_inode_unlock(inode1, 1); ocfs2_inode_unlock(inode1, 1);
brelse(*bh1); brelse(bh1);
*bh1 = NULL;
out_rw2: out_rw2:
ocfs2_rw_unlock(inode2, 1); ocfs2_rw_unlock(inode2, 1);
out_i2: out_i2:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment