Merge tag 'ceph-for-4.9-rc1' of git://github.com/ceph/ceph-client

Pull Ceph updates from Ilya Dryomov:
 "The big ticket item here is support for rbd exclusive-lock feature,
  with maintenance operations offloaded to userspace (Douglas Fuller,
  Mike Christie and myself). Another block device bullet is a series
  fixing up layering error paths (myself).

  On the filesystem side, we've got patches that improve our handling of
  buffered vs dio write races (Neil Brown) and a few assorted fixes from
  Zheng. Also included a couple of random cleanups and a minor CRUSH
  update"

* tag 'ceph-for-4.9-rc1' of git://github.com/ceph/ceph-client: (39 commits)
  crush: remove redundant local variable
  crush: don't normalize input of crush_ln iteratively
  libceph: ceph_build_auth() doesn't need ceph_auth_build_hello()
  libceph: use CEPH_AUTH_UNKNOWN in ceph_auth_build_hello()
  ceph: fix description for rsize and rasize mount options
  rbd: use kmalloc_array() in rbd_header_from_disk()
  ceph: use list_move instead of list_del/list_add
  ceph: handle CEPH_SESSION_REJECT message
  ceph: avoid accessing / when mounting a subpath
  ceph: fix mandatory flock check
  ceph: remove warning when ceph_releasepage() is called on dirty page
  ceph: ignore error from invalidate_inode_pages2_range() in direct write
  ceph: fix error handling of start_read()
  rbd: add rbd_obj_request_error() helper
  rbd: img_data requests don't own their page array
  rbd: don't call rbd_osd_req_format_read() for !img_data requests
  rbd: rework rbd_img_obj_exists_submit() error paths
  rbd: don't crash or leak on errors in rbd_img_obj_parent_read_full_callback()
  rbd: move bumping img_request refcount into rbd_obj_request_submit()
  rbd: mark the original request as done if stat request fails
  ...

1 files changed, 23 insertions, 7 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f72d4ae..815acd1 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -370,6 +370,7 @@ const char *ceph_session_state_name(int s)
 	case CEPH_MDS_SESSION_CLOSING: return "closing";
 	case CEPH_MDS_SESSION_RESTARTING: return "restarting";
 	case CEPH_MDS_SESSION_RECONNECTING: return "reconnecting";
+	case CEPH_MDS_SESSION_REJECTED: return "rejected";
 	default: return "???";
 	}
 }
@@ -1150,8 +1151,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		while (!list_empty(&ci->i_cap_flush_list)) {
 			cf = list_first_entry(&ci->i_cap_flush_list,
 					      struct ceph_cap_flush, i_list);
-			list_del(&cf->i_list);
-			list_add(&cf->i_list, &to_remove);
+			list_move(&cf->i_list, &to_remove);
 		}
 
 		spin_lock(&mdsc->cap_dirty_lock);
@@ -1378,7 +1378,7 @@ static int request_close_session(struct ceph_mds_client *mdsc,
 	if (!msg)
 		return -ENOMEM;
 	ceph_con_send(&session->s_con, msg);
-	return 0;
+	return 1;
 }
 
 /*
@@ -2131,6 +2131,10 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	     ceph_session_state_name(session->s_state));
 	if (session->s_state != CEPH_MDS_SESSION_OPEN &&
 	    session->s_state != CEPH_MDS_SESSION_HUNG) {
+		if (session->s_state == CEPH_MDS_SESSION_REJECTED) {
+			err = -EACCES;
+			goto out_session;
+		}
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
 		    session->s_state == CEPH_MDS_SESSION_CLOSING)
 			__open_session(mdsc, session);
@@ -2652,6 +2656,15 @@ static void handle_session(struct ceph_mds_session *session,
 		wake_up_session_caps(session, 0);
 		break;
 
+	case CEPH_SESSION_REJECT:
+		WARN_ON(session->s_state != CEPH_MDS_SESSION_OPENING);
+		pr_info("mds%d rejected session\n", session->s_mds);
+		session->s_state = CEPH_MDS_SESSION_REJECTED;
+		cleanup_session_requests(mdsc, session);
+		remove_session_caps(session);
+		wake = 2; /* for good measure */
+		break;
+
 	default:
 		pr_err("mdsc_handle_session bad op %d mds%d\n", op, mds);
 		WARN_ON(1);
@@ -3557,11 +3570,11 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 /*
  * true if all sessions are closed, or we force unmount
  */
-static bool done_closing_sessions(struct ceph_mds_client *mdsc)
+static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped)
 {
 	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 		return true;
-	return atomic_read(&mdsc->num_sessions) == 0;
+	return atomic_read(&mdsc->num_sessions) <= skipped;
 }
 
 /*
@@ -3572,6 +3585,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	struct ceph_options *opts = mdsc->fsc->client->options;
 	struct ceph_mds_session *session;
 	int i;
+	int skipped = 0;
 
 	dout("close_sessions\n");
 
@@ -3583,7 +3597,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 			continue;
 		mutex_unlock(&mdsc->mutex);
 		mutex_lock(&session->s_mutex);
-		__close_session(mdsc, session);
+		if (__close_session(mdsc, session) <= 0)
+			skipped++;
 		mutex_unlock(&session->s_mutex);
 		ceph_put_mds_session(session);
 		mutex_lock(&mdsc->mutex);
@@ -3591,7 +3606,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	mutex_unlock(&mdsc->mutex);
 
 	dout("waiting for sessions to close\n");
-	wait_event_timeout(mdsc->session_close_wq, done_closing_sessions(mdsc),
+	wait_event_timeout(mdsc->session_close_wq,
+			   done_closing_sessions(mdsc, skipped),
 			   ceph_timeout_jiffies(opts->mount_timeout));
 
 	/* tear down remaining sessions */