ocfs2: fix race between dio and recover orphan

During direct io the inode will be added to orphan first and then
deleted from orphan.  There is a race window that the orphan entry will
be deleted twice and thus trigger the BUG when validating
OCFS2_DIO_ORPHANED_FL in ocfs2_del_inode_from_orphan.

ocfs2_direct_IO_write
    ...
    ocfs2_add_inode_to_orphan
    >>>>>>>> race window.
             1) another node may rm the file and then down, this node
             take care of orphan recovery and clear flag
             OCFS2_DIO_ORPHANED_FL.
             2) since rw lock is unlocked, it may race with another
             orphan recovery and append dio.
    ocfs2_del_inode_from_orphan

So take inode mutex lock when recovering orphans and make rw unlock at the
end of aio write in case of append dio.

Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reported-by: Yiwen Jiang <jiangyiwen@huawei.com>
Cc: Weiwei Wang <wangww631@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Joseph Qi
2015-09-04 15:43:37 -07:00
committed by Linus Torvalds
parent 81cf09edc7
commit 512f62acbd
6 changed files with 24 additions and 41 deletions

View File

@@ -2601,27 +2601,6 @@ leave:
return status;
}
static int ocfs2_dio_orphan_recovered(struct inode *inode)
{
int ret;
struct buffer_head *di_bh = NULL;
struct ocfs2_dinode *di = NULL;
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
return 0;
}
di = (struct ocfs2_dinode *) di_bh->b_data;
ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
return ret;
}
#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
struct inode *inode)
{
@@ -2633,7 +2612,6 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
handle_t *handle = NULL;
struct ocfs2_dinode *di = NULL;
restart:
status = ocfs2_inode_lock(inode, &di_bh, 1);
if (status < 0) {
mlog_errno(status);
@@ -2643,15 +2621,21 @@ restart:
di = (struct ocfs2_dinode *) di_bh->b_data;
/*
* Another append dio crashed?
* If so, wait for recovery first.
* If so, manually recover it first.
*/
if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
ocfs2_dio_orphan_recovered(inode),
msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
goto restart;
status = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail_unlock_inode;
}
status = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_inode;
}
}
status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,