ceph: take i_mutex before getting Fw cap

There is deadlock as illustrated bellow. The fix is taking i_mutex
before getting Fw cap reference.

      write                    truncate                 MDS
---------------------     --------------------      --------------
get Fw cap
                          lock i_mutex
lock i_mutex (blocked)
                          request setattr.size  ->
                                                <-   revoke Fw cap

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
This commit is contained in:
Yan, Zheng 2013-04-12 16:11:10 +08:00 committed by Sage Weil
parent 26be88087a
commit 37505d5768
2 changed files with 13 additions and 12 deletions

View File

@ -2052,6 +2052,13 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
goto out;
}
/* finish pending truncate */
while (ci->i_truncate_pending) {
spin_unlock(&ci->i_ceph_lock);
__ceph_do_pending_vmtruncate(inode, !(need & CEPH_CAP_FILE_WR));
spin_lock(&ci->i_ceph_lock);
}
if (need & CEPH_CAP_FILE_WR) {
if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) {
dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
@ -2073,12 +2080,6 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
}
have = __ceph_caps_issued(ci, &implemented);
/*
* disallow writes while a truncate is pending
*/
if (ci->i_truncate_pending)
have &= ~CEPH_CAP_FILE_WR;
if ((have & need) == need) {
/*
* Look at (implemented & ~have & not) so that we keep waiting

View File

@ -651,7 +651,6 @@ static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
inode, ceph_vinop(inode), pos, (unsigned)len, inode);
again:
__ceph_do_pending_vmtruncate(inode, true);
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
@ -728,7 +727,7 @@ retry_snap:
ret = -ENOSPC;
goto out;
}
__ceph_do_pending_vmtruncate(inode, true);
mutex_lock(&inode->i_mutex);
dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
inode->i_size);
@ -737,8 +736,10 @@ retry_snap:
else
want = CEPH_CAP_FILE_BUFFER;
ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
if (ret < 0)
goto out_put;
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
goto out;
}
dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
@ -748,10 +749,10 @@ retry_snap:
(iocb->ki_filp->f_flags & O_DIRECT) ||
(inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
(fi->flags & CEPH_F_SYNC)) {
mutex_unlock(&inode->i_mutex);
ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,
&iocb->ki_pos);
} else {
mutex_lock(&inode->i_mutex);
ret = __generic_file_aio_write(iocb, iov, nr_segs,
&iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
@ -766,7 +767,6 @@ retry_snap:
__mark_inode_dirty(inode, dirty);
}
out_put:
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
ceph_cap_string(got));