Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph updates from Sage Weil:
 "This time around we have a collection of CephFS fixes from Zheng
  around MDS failure handling and snapshots, support for a new CRUSH
  straw2 algorithm (to sync up with userspace) and several RBD cleanups
  and fixes from Ilya, an error path leak fix from Taesoo, and then an
  assorted collection of cleanups from others"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (28 commits)
  rbd: rbd_wq comment is obsolete
  libceph: announce support for straw2 buckets
  crush: straw2 bucket type with an efficient 64-bit crush_ln()
  crush: ensuring at most num-rep osds are selected
  crush: drop unnecessary include from mapper.c
  ceph: fix uninline data function
  ceph: rename snapshot support
  ceph: fix null pointer dereference in send_mds_reconnect()
  ceph: hold on to exclusive caps on complete directories
  libceph: simplify our debugfs attr macro
  ceph: show non-default options only
  libceph: expose client options through debugfs
  libceph, ceph: split ceph_show_options()
  rbd: mark block queue as non-rotational
  libceph: don't overwrite specific con error msgs
  ceph: cleanup unsafe requests when reconnecting is denied
  ceph: don't zero i_wrbuffer_ref when reconnecting is denied
  ceph: don't mark dirty caps when there is no auth cap
  ceph: keep i_snap_realm while there are writers
  libceph: osdmap.h: Add missing format newlines
  ...

1 files changed, 45 insertions, 16 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 71c073f38e54..0a2eb32ffe43 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1021,6 +1021,33 @@ static void cleanup_cap_releases(struct ceph_mds_session *session)
 	spin_unlock(&session->s_cap_lock);
 }
 
+static void cleanup_session_requests(struct ceph_mds_client *mdsc,
+				     struct ceph_mds_session *session)
+{
+	struct ceph_mds_request *req;
+	struct rb_node *p;
+
+	dout("cleanup_session_requests mds%d\n", session->s_mds);
+	mutex_lock(&mdsc->mutex);
+	while (!list_empty(&session->s_unsafe)) {
+		req = list_first_entry(&session->s_unsafe,
+				       struct ceph_mds_request, r_unsafe_item);
+		list_del_init(&req->r_unsafe_item);
+		pr_info(" dropping unsafe request %llu\n", req->r_tid);
+		__unregister_request(mdsc, req);
+	}
+	/* zero r_attempts, so kick_requests() will re-send requests */
+	p = rb_first(&mdsc->request_tree);
+	while (p) {
+		req = rb_entry(p, struct ceph_mds_request, r_node);
+		p = rb_next(p);
+		if (req->r_session &&
+		    req->r_session->s_mds == session->s_mds)
+			req->r_attempts = 0;
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
 /*
  * Helper to safely iterate over all caps associated with a session, with
  * special care taken to handle a racing __ceph_remove_cap().
@@ -1098,7 +1125,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	     cap, ci, &ci->vfs_inode);
 	spin_lock(&ci->i_ceph_lock);
 	__ceph_remove_cap(cap, false);
-	if (!__ceph_is_any_real_caps(ci)) {
+	if (!ci->i_auth_cap) {
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(inode->i_sb)->mdsc;
 
@@ -1120,13 +1147,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 			mdsc->num_cap_flushing--;
 			drop = 1;
 		}
-		if (drop && ci->i_wrbuffer_ref) {
-			pr_info(" dropping dirty data for %p %lld\n",
-				inode, ceph_ino(inode));
-			ci->i_wrbuffer_ref = 0;
-			ci->i_wrbuffer_ref_head = 0;
-			drop++;
-		}
 		spin_unlock(&mdsc->cap_dirty_lock);
 	}
 	spin_unlock(&ci->i_ceph_lock);
@@ -1853,7 +1873,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
  */
 static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 					       struct ceph_mds_request *req,
-					       int mds)
+					       int mds, bool drop_cap_releases)
 {
 	struct ceph_msg *msg;
 	struct ceph_mds_request_head *head;
@@ -1937,6 +1957,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		releases += ceph_encode_inode_release(&p,
 		      req->r_old_dentry->d_inode,
 		      mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
+
+	if (drop_cap_releases) {
+		releases = 0;
+		p = msg->front.iov_base + req->r_request_release_offset;
+	}
+
 	head->num_releases = cpu_to_le16(releases);
 
 	/* time stamp */
@@ -1989,7 +2015,7 @@ static void complete_request(struct ceph_mds_client *mdsc,
  */
 static int __prepare_send_request(struct ceph_mds_client *mdsc,
 				  struct ceph_mds_request *req,
-				  int mds)
+				  int mds, bool drop_cap_releases)
 {
 	struct ceph_mds_request_head *rhead;
 	struct ceph_msg *msg;
@@ -2048,7 +2074,7 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
 		ceph_msg_put(req->r_request);
 		req->r_request = NULL;
 	}
-	msg = create_request_message(mdsc, req, mds);
+	msg = create_request_message(mdsc, req, mds, drop_cap_releases);
 	if (IS_ERR(msg)) {
 		req->r_err = PTR_ERR(msg);
 		complete_request(mdsc, req);
@@ -2132,7 +2158,7 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	if (req->r_request_started == 0)   /* note request start time */
 		req->r_request_started = jiffies;
 
-	err = __prepare_send_request(mdsc, req, mds);
+	err = __prepare_send_request(mdsc, req, mds, false);
 	if (!err) {
 		ceph_msg_get(req->r_request);
 		ceph_con_send(&session->s_con, req->r_request);
@@ -2590,6 +2616,7 @@ static void handle_session(struct ceph_mds_session *session,
 	case CEPH_SESSION_CLOSE:
 		if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
 			pr_info("mds%d reconnect denied\n", session->s_mds);
+		cleanup_session_requests(mdsc, session);
 		remove_session_caps(session);
 		wake = 2; /* for good measure */
 		wake_up_all(&mdsc->session_close_wq);
@@ -2658,7 +2685,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 
 	mutex_lock(&mdsc->mutex);
 	list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) {
-		err = __prepare_send_request(mdsc, req, session->s_mds);
+		err = __prepare_send_request(mdsc, req, session->s_mds, true);
 		if (!err) {
 			ceph_msg_get(req->r_request);
 			ceph_con_send(&session->s_con, req->r_request);
@@ -2679,7 +2706,8 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 			continue; /* only old requests */
 		if (req->r_session &&
 		    req->r_session->s_mds == session->s_mds) {
-			err = __prepare_send_request(mdsc, req, session->s_mds);
+			err = __prepare_send_request(mdsc, req,
+						     session->s_mds, true);
 			if (!err) {
 				ceph_msg_get(req->r_request);
 				ceph_con_send(&session->s_con, req->r_request);
@@ -2864,7 +2892,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	spin_unlock(&session->s_cap_lock);
 
 	/* trim unused caps to reduce MDS's cache rejoin time */
-	shrink_dcache_parent(mdsc->fsc->sb->s_root);
+	if (mdsc->fsc->sb->s_root)
+		shrink_dcache_parent(mdsc->fsc->sb->s_root);
 
 	ceph_con_close(&session->s_con);
 	ceph_con_open(&session->s_con,
@@ -3133,7 +3162,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 		    di->lease_renew_from &&
 		    di->lease_renew_after == 0) {
 			unsigned long duration =
-				le32_to_cpu(h->duration_ms) * HZ / 1000;
+				msecs_to_jiffies(le32_to_cpu(h->duration_ms));
 
 			di->lease_seq = seq;
 			dentry->d_time = di->lease_renew_from + duration;