ceph: fix session locking in handle_caps, ceph_check_caps

Passing a session pointer to ceph_check_caps() used to mean it would leave
the session mutex locked.  That wasn't always possible if it wasn't passed
CHECK_CAPS_AUTHONLY.   If could unlock the passed session and lock a
differet session mutex, which was clearly wrong, and also emitted a
warning when it a racing CPU retook it and we did an unlock from the wrong
context.

This was only a problem when there was more than one MDS.

First, make ceph_check_caps unconditionally drop the session mutex, so that
it is free to lock other sessions as needed.  Then adjust the one caller
that passes in a session (handle_cap_grant) accordingly.

Signed-off-by: Sage Weil <sage@newdream.net>

1 files changed, 9 insertions, 5 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 726c8d445995..782848632e81 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1407,6 +1407,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
  */
 void ceph_check_caps(struct ceph_inode_info *ci, int flags,
                      struct ceph_mds_session *session)
+        __releases(session->s_mutex)
 {
         struct ceph_client *client = ceph_inode_to_client(&ci->vfs_inode);
         struct ceph_mds_client *mdsc = &client->mdsc;
@@ -1414,7 +1415,6 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
         struct ceph_cap *cap;
         int file_wanted, used;
         int took_snap_rwsem = 0;             /* true if mdsc->snap_rwsem held */
-        int drop_session_lock = session ? 0 : 1;
         int issued, implemented, want, retain, revoking, flushing = 0;
         int mds = -1;   /* keep track of how far we've gone through i_caps list
                            to avoid an infinite loop on retry */
@@ -1639,7 +1639,7 @@ ack:
         if (queue_invalidate)
                 ceph_queue_invalidate(inode);
 
-        if (session && drop_session_lock)
+        if (session)
                 mutex_unlock(&session->s_mutex);
         if (took_snap_rwsem)
                 up_read(&mdsc->snap_rwsem);
@@ -2688,14 +2688,17 @@ void ceph_handle_caps(struct ceph_mds_session *session,
         case CEPH_CAP_OP_REVOKE:
         case CEPH_CAP_OP_GRANT:
                 r = handle_cap_grant(inode, h, session, cap, msg->middle);
-                if (r == 1)
+                if (r == 1) {
                         ceph_check_caps(ceph_inode(inode),
                                         CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY,
                                         session);
-                else if (r == 2)
+                        session = NULL;
+                } else if (r == 2) {
                         ceph_check_caps(ceph_inode(inode),
                                         CHECK_CAPS_NODELAY,
                                         session);
+                        session = NULL;
+                }
                 break;
 
         case CEPH_CAP_OP_FLUSH_ACK:
@@ -2713,7 +2716,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
         }
 
 done:
-        mutex_unlock(&session->s_mutex);
+        if (session)
+                mutex_unlock(&session->s_mutex);
 
         if (check_caps)
                 ceph_check_caps(ceph_inode(inode), CHECK_CAPS_NODELAY, NULL);