Merge tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The two main items are support for disabling automatic rbd exclusive
  lock transfers from myself and the long awaited -ENOSPC handling
  series from Jeff.

  The former will allow rbd users to take advantage of exclusive lock's
  built-in blacklist/break-lock functionality while staying in control
  of who owns the lock. With the latter in place, we will abort
  filesystem writes on -ENOSPC instead of having them block
  indefinitely.

  Beyond that we've got the usual pile of filesystem fixes from Zheng,
  some refcount_t conversion patches from Elena and a patch for an
  ancient open() flags handling bug from Alexander"

* tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client: (31 commits)
  ceph: fix memory leak in __ceph_setxattr()
  ceph: fix file open flags on ppc64
  ceph: choose readdir frag based on previous readdir reply
  rbd: exclusive map option
  rbd: return ResponseMessage result from rbd_handle_request_lock()
  rbd: kill rbd_is_lock_supported()
  rbd: support updating the lock cookie without releasing the lock
  rbd: store lock cookie
  rbd: ignore unlock errors
  rbd: fix error handling around rbd_init_disk()
  rbd: move rbd_unregister_watch() call into rbd_dev_image_release()
  rbd: move rbd_dev_destroy() call out of rbd_dev_image_release()
  ceph: when seeing write errors on an inode, switch to sync writes
  Revert "ceph: SetPageError() for writeback pages if writepages fails"
  ceph: handle epoch barriers in cap messages
  libceph: add an epoch_barrier field to struct ceph_osd_client
  libceph: abort already submitted but abortable requests when map or pool goes full
  libceph: allow requests to return immediately on full conditions if caller wishes
  libceph: remove req->r_replay_version
  ceph: make seeky readdir more efficient
  ...

1 files changed, 59 insertions, 16 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1d3fa90d40b9..f38e56fa9712 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -189,6 +189,7 @@ static int parse_reply_info_dir(void **p, void *end,
 		info->dir_end = !!(flags & CEPH_READDIR_FRAG_END);
 		info->dir_complete = !!(flags & CEPH_READDIR_FRAG_COMPLETE);
 		info->hash_order = !!(flags & CEPH_READDIR_HASH_ORDER);
+		info->offset_hash = !!(flags & CEPH_READDIR_OFFSET_HASH);
 	}
 	if (num == 0)
 		goto done;
@@ -378,9 +379,9 @@ const char *ceph_session_state_name(int s)
 
 static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
 {
-	if (atomic_inc_not_zero(&s->s_ref)) {
+	if (refcount_inc_not_zero(&s->s_ref)) {
 		dout("mdsc get_session %p %d -> %d\n", s,
-		     atomic_read(&s->s_ref)-1, atomic_read(&s->s_ref));
+		     refcount_read(&s->s_ref)-1, refcount_read(&s->s_ref));
 		return s;
 	} else {
 		dout("mdsc get_session %p 0 -- FAIL", s);
@@ -391,8 +392,8 @@ static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
 void ceph_put_mds_session(struct ceph_mds_session *s)
 {
 	dout("mdsc put_session %p %d -> %d\n", s,
-	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
-	if (atomic_dec_and_test(&s->s_ref)) {
+	     refcount_read(&s->s_ref), refcount_read(&s->s_ref)-1);
+	if (refcount_dec_and_test(&s->s_ref)) {
 		if (s->s_auth.authorizer)
 			ceph_auth_destroy_authorizer(s->s_auth.authorizer);
 		kfree(s);
@@ -411,7 +412,7 @@ struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc,
 		return NULL;
 	session = mdsc->sessions[mds];
 	dout("lookup_mds_session %p %d\n", session,
-	     atomic_read(&session->s_ref));
+	     refcount_read(&session->s_ref));
 	get_session(session);
 	return session;
 }
@@ -441,7 +442,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 {
 	struct ceph_mds_session *s;
 
-	if (mds >= mdsc->mdsmap->m_max_mds)
+	if (mds >= mdsc->mdsmap->m_num_mds)
 		return ERR_PTR(-EINVAL);
 
 	s = kzalloc(sizeof(*s), GFP_NOFS);
@@ -466,7 +467,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	INIT_LIST_HEAD(&s->s_caps);
 	s->s_nr_caps = 0;
 	s->s_trim_caps = 0;
-	atomic_set(&s->s_ref, 1);
+	refcount_set(&s->s_ref, 1);
 	INIT_LIST_HEAD(&s->s_waiting);
 	INIT_LIST_HEAD(&s->s_unsafe);
 	s->s_num_cap_releases = 0;
@@ -494,7 +495,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	}
 	mdsc->sessions[mds] = s;
 	atomic_inc(&mdsc->num_sessions);
-	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
+	refcount_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
 	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
 		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
@@ -1004,7 +1005,7 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc,
 	struct ceph_mds_session *ts;
 	int i, mds = session->s_mds;
 
-	if (mds >= mdsc->mdsmap->m_max_mds)
+	if (mds >= mdsc->mdsmap->m_num_mds)
 		return;
 
 	mi = &mdsc->mdsmap->m_info[mds];
@@ -1551,9 +1552,15 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
 	struct ceph_msg *msg = NULL;
 	struct ceph_mds_cap_release *head;
 	struct ceph_mds_cap_item *item;
+	struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
 	struct ceph_cap *cap;
 	LIST_HEAD(tmp_list);
 	int num_cap_releases;
+	__le32	barrier, *cap_barrier;
+
+	down_read(&osdc->lock);
+	barrier = cpu_to_le32(osdc->epoch_barrier);
+	up_read(&osdc->lock);
 
 	spin_lock(&session->s_cap_lock);
 again:
@@ -1571,7 +1578,11 @@ again:
 			head = msg->front.iov_base;
 			head->num = cpu_to_le32(0);
 			msg->front.iov_len = sizeof(*head);
+
+			msg->hdr.version = cpu_to_le16(2);
+			msg->hdr.compat_version = cpu_to_le16(1);
 		}
+
 		cap = list_first_entry(&tmp_list, struct ceph_cap,
 					session_caps);
 		list_del(&cap->session_caps);
@@ -1589,6 +1600,11 @@ again:
 		ceph_put_cap(mdsc, cap);
 
 		if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+			// Append cap_barrier field
+			cap_barrier = msg->front.iov_base + msg->front.iov_len;
+			*cap_barrier = barrier;
+			msg->front.iov_len += sizeof(*cap_barrier);
+
 			msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 			dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
 			ceph_con_send(&session->s_con, msg);
@@ -1604,6 +1620,11 @@ again:
 	spin_unlock(&session->s_cap_lock);
 
 	if (msg) {
+		// Append cap_barrier field
+		cap_barrier = msg->front.iov_base + msg->front.iov_len;
+		*cap_barrier = barrier;
+		msg->front.iov_len += sizeof(*cap_barrier);
+
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 		dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
 		ceph_con_send(&session->s_con, msg);
@@ -1993,7 +2014,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
 	if (req->r_pagelist) {
 		struct ceph_pagelist *pagelist = req->r_pagelist;
-		atomic_inc(&pagelist->refcnt);
+		refcount_inc(&pagelist->refcnt);
 		ceph_msg_data_add_pagelist(msg, pagelist);
 		msg->hdr.data_len = cpu_to_le32(pagelist->length);
 	} else {
@@ -2640,8 +2661,10 @@ static void handle_session(struct ceph_mds_session *session,
 	seq = le64_to_cpu(h->seq);
 
 	mutex_lock(&mdsc->mutex);
-	if (op == CEPH_SESSION_CLOSE)
+	if (op == CEPH_SESSION_CLOSE) {
+		get_session(session);
 		__unregister_session(mdsc, session);
+	}
 	/* FIXME: this ttl calculation is generous */
 	session->s_ttl = jiffies + HZ*mdsc->mdsmap->m_session_autoclose;
 	mutex_unlock(&mdsc->mutex);
@@ -2730,6 +2753,8 @@ static void handle_session(struct ceph_mds_session *session,
 			kick_requests(mdsc, mds);
 		mutex_unlock(&mdsc->mutex);
 	}
+	if (op == CEPH_SESSION_CLOSE)
+		ceph_put_mds_session(session);
 	return;
 
 bad:
@@ -3109,7 +3134,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 	dout("check_new_map new %u old %u\n",
 	     newmap->m_epoch, oldmap->m_epoch);
 
-	for (i = 0; i < oldmap->m_max_mds && i < mdsc->max_sessions; i++) {
+	for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) {
 		if (mdsc->sessions[i] == NULL)
 			continue;
 		s = mdsc->sessions[i];
@@ -3123,15 +3148,33 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		     ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
 		     ceph_session_state_name(s->s_state));
 
-		if (i >= newmap->m_max_mds ||
+		if (i >= newmap->m_num_mds ||
 		    memcmp(ceph_mdsmap_get_addr(oldmap, i),
 			   ceph_mdsmap_get_addr(newmap, i),
 			   sizeof(struct ceph_entity_addr))) {
 			if (s->s_state == CEPH_MDS_SESSION_OPENING) {
 				/* the session never opened, just close it
 				 * out now */
+				get_session(s);
+				__unregister_session(mdsc, s);
 				__wake_requests(mdsc, &s->s_waiting);
+				ceph_put_mds_session(s);
+			} else if (i >= newmap->m_num_mds) {
+				/* force close session for stopped mds */
+				get_session(s);
 				__unregister_session(mdsc, s);
+				__wake_requests(mdsc, &s->s_waiting);
+				kick_requests(mdsc, i);
+				mutex_unlock(&mdsc->mutex);
+
+				mutex_lock(&s->s_mutex);
+				cleanup_session_requests(mdsc, s);
+				remove_session_caps(s);
+				mutex_unlock(&s->s_mutex);
+
+				ceph_put_mds_session(s);
+
+				mutex_lock(&mdsc->mutex);
 			} else {
 				/* just close it */
 				mutex_unlock(&mdsc->mutex);
@@ -3169,7 +3212,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		}
 	}
 
-	for (i = 0; i < newmap->m_max_mds && i < mdsc->max_sessions; i++) {
+	for (i = 0; i < newmap->m_num_mds && i < mdsc->max_sessions; i++) {
 		s = mdsc->sessions[i];
 		if (!s)
 			continue;
@@ -3883,7 +3926,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con)
 	struct ceph_mds_session *s = con->private;
 
 	if (get_session(s)) {
-		dout("mdsc con_get %p ok (%d)\n", s, atomic_read(&s->s_ref));
+		dout("mdsc con_get %p ok (%d)\n", s, refcount_read(&s->s_ref));
 		return con;
 	}
 	dout("mdsc con_get %p FAIL\n", s);
@@ -3894,7 +3937,7 @@ static void con_put(struct ceph_connection *con)
 {
 	struct ceph_mds_session *s = con->private;
 
-	dout("mdsc con_put %p (%d)\n", s, atomic_read(&s->s_ref) - 1);
+	dout("mdsc con_put %p (%d)\n", s, refcount_read(&s->s_ref) - 1);
 	ceph_put_mds_session(s);
 }