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

Pull Ceph changes from Sage Weil:
 "On the RBD side, there is a conversion to blk-mq from Christoph,
  several long-standing bug fixes from Ilya, and some cleanup from
  Rickard Strandqvist.

  On the CephFS side there is a long list of fixes from Zheng, including
  improved session handling, a few IO path fixes, some dcache management
  correctness fixes, and several blocking while !TASK_RUNNING fixes.

  The core code gets a few cleanups and Chaitanya has added support for
  TCP_NODELAY (which has been used on the server side for ages but we
  somehow missed on the kernel client).

  There is also an update to MAINTAINERS to fix up some email addresses
  and reflect that Ilya and Zheng are doing most of the maintenance for
  RBD and CephFS these days.  Do not be surprised to see a pull request
  come from one of them in the future if I am unavailable for some
  reason"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (27 commits)
  MAINTAINERS: update Ceph and RBD maintainers
  libceph: kfree() in put_osd() shouldn't depend on authorizer
  libceph: fix double __remove_osd() problem
  rbd: convert to blk-mq
  ceph: return error for traceless reply race
  ceph: fix dentry leaks
  ceph: re-send requests when MDS enters reconnecting stage
  ceph: show nocephx_require_signatures and notcp_nodelay options
  libceph: tcp_nodelay support
  rbd: do not treat standalone as flatten
  ceph: fix atomic_open snapdir
  ceph: properly mark empty directory as complete
  client: include kernel version in client metadata
  ceph: provide seperate {inode,file}_operations for snapdir
  ceph: fix request time stamp encoding
  ceph: fix reading inline data when i_size > PAGE_SIZE
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_close_sessions)
  ceph: avoid block operation when !TASK_RUNNING (ceph_get_caps)
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_sync)
  rbd: fix error paths in rbd_dev_refresh()
  ...

6 files changed, 54 insertions, 162 deletions

diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 5d5ab67f516d..ec565508e904 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -239,6 +239,8 @@ enum {
 	Opt_nocrc,
 	Opt_cephx_require_signatures,
 	Opt_nocephx_require_signatures,
+	Opt_tcp_nodelay,
+	Opt_notcp_nodelay,
 };
 
 static match_table_t opt_tokens = {
@@ -259,6 +261,8 @@ static match_table_t opt_tokens = {
 	{Opt_nocrc, "nocrc"},
 	{Opt_cephx_require_signatures, "cephx_require_signatures"},
 	{Opt_nocephx_require_signatures, "nocephx_require_signatures"},
+	{Opt_tcp_nodelay, "tcp_nodelay"},
+	{Opt_notcp_nodelay, "notcp_nodelay"},
 	{-1, NULL}
 };
 
@@ -457,6 +461,7 @@ ceph_parse_options(char *options, const char *dev_name,
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
+
 		case Opt_cephx_require_signatures:
 			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
 			break;
@@ -464,6 +469,13 @@ ceph_parse_options(char *options, const char *dev_name,
 			opt->flags |= CEPH_OPT_NOMSGAUTH;
 			break;
 
+		case Opt_tcp_nodelay:
+			opt->flags |= CEPH_OPT_TCP_NODELAY;
+			break;
+		case Opt_notcp_nodelay:
+			opt->flags &= ~CEPH_OPT_TCP_NODELAY;
+			break;
+
 		default:
 			BUG_ON(token);
 		}
@@ -518,10 +530,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
+
 	ceph_messenger_init(&client->msgr, myaddr,
 		client->supported_features,
 		client->required_features,
-		ceph_test_opt(client, NOCRC));
+		ceph_test_opt(client, NOCRC),
+		ceph_test_opt(client, TCP_NODELAY));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 30560202f57b..139a9cb19b0c 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -42,17 +42,3 @@ const char *ceph_osd_state_name(int s)
 		return "???";
 	}
 }
-
-const char *ceph_pool_op_name(int op)
-{
-	switch (op) {
-	case POOL_OP_CREATE: return "create";
-	case POOL_OP_DELETE: return "delete";
-	case POOL_OP_AUID_CHANGE: return "auid change";
-	case POOL_OP_CREATE_SNAP: return "create snap";
-	case POOL_OP_DELETE_SNAP: return "delete snap";
-	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
-	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
-	}
-	return "???";
-}
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index d2d525529f87..14d9995097cc 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -127,8 +127,6 @@ static int monc_show(struct seq_file *s, void *p)
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
 			seq_printf(s, "%llu statfs\n", req->tid);
-		else if (op == CEPH_MSG_POOLOP)
-			seq_printf(s, "%llu poolop\n", req->tid);
 		else if (op == CEPH_MSG_MON_GET_VERSION)
 			seq_printf(s, "%llu mon_get_version", req->tid);
 		else
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 33a2f201e460..6b3f54ed65ba 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -510,6 +510,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 
+	if (con->msgr->tcp_nodelay) {
+		int optval = 1;
+
+		ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+					(char *)&optval, sizeof(optval));
+		if (ret)
+			pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d",
+			       ret);
+	}
+
 	sk_set_memalloc(sock->sk);
 
 	con->sock = sock;
@@ -2922,7 +2932,8 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 			struct ceph_entity_addr *myaddr,
 			u64 supported_features,
 			u64 required_features,
-			bool nocrc)
+			bool nocrc,
+			bool tcp_nodelay)
 {
 	msgr->supported_features = supported_features;
 	msgr->required_features = required_features;
@@ -2937,6 +2948,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
 	encode_my_addr(msgr);
 	msgr->nocrc = nocrc;
+	msgr->tcp_nodelay = tcp_nodelay;
 
 	atomic_set(&msgr->stopping, 0);
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index f2148e22b148..2b3cf05e87b0 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -410,7 +410,7 @@ out_unlocked:
 }
 
 /*
- * generic requests (e.g., statfs, poolop)
+ * generic requests (currently statfs, mon_get_version)
  */
 static struct ceph_mon_generic_request *__lookup_generic_req(
 	struct ceph_mon_client *monc, u64 tid)
@@ -569,7 +569,7 @@ static void handle_statfs_reply(struct ceph_mon_client *monc,
 	return;
 
 bad:
-	pr_err("corrupt generic reply, tid %llu\n", tid);
+	pr_err("corrupt statfs reply, tid %llu\n", tid);
 	ceph_msg_dump(msg);
 }
 
@@ -588,7 +588,6 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
 
 	kref_init(&req->kref);
 	req->buf = buf;
-	req->buf_len = sizeof(*buf);
 	init_completion(&req->completion);
 
 	err = -ENOMEM;
@@ -611,7 +610,7 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
 	err = do_generic_request(monc, req);
 
 out:
-	kref_put(&req->kref, release_generic_request);
+	put_generic_request(req);
 	return err;
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
@@ -647,7 +646,7 @@ static void handle_get_version_reply(struct ceph_mon_client *monc,
 
 	return;
 bad:
-	pr_err("corrupt mon_get_version reply\n");
+	pr_err("corrupt mon_get_version reply, tid %llu\n", tid);
 	ceph_msg_dump(msg);
 }
 
@@ -670,7 +669,6 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
 
 	kref_init(&req->kref);
 	req->buf = newest;
-	req->buf_len = sizeof(*newest);
 	init_completion(&req->completion);
 
 	req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
@@ -701,134 +699,12 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
 
 	mutex_unlock(&monc->mutex);
 out:
-	kref_put(&req->kref, release_generic_request);
+	put_generic_request(req);
 	return err;
 }
 EXPORT_SYMBOL(ceph_monc_do_get_version);
 
 /*
- * pool ops
- */
-static int get_poolop_reply_buf(const char *src, size_t src_len,
-				char *dst, size_t dst_len)
-{
-	u32 buf_len;
-
-	if (src_len != sizeof(u32) + dst_len)
-		return -EINVAL;
-
-	buf_len = le32_to_cpu(*(__le32 *)src);
-	if (buf_len != dst_len)
-		return -EINVAL;
-
-	memcpy(dst, src + sizeof(u32), dst_len);
-	return 0;
-}
-
-static void handle_poolop_reply(struct ceph_mon_client *monc,
-				struct ceph_msg *msg)
-{
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_poolop_reply *reply = msg->front.iov_base;
-	u64 tid = le64_to_cpu(msg->hdr.tid);
-
-	if (msg->front.iov_len < sizeof(*reply))
-		goto bad;
-	dout("handle_poolop_reply %p tid %llu\n", msg, tid);
-
-	mutex_lock(&monc->mutex);
-	req = __lookup_generic_req(monc, tid);
-	if (req) {
-		if (req->buf_len &&
-		    get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply),
-				     msg->front.iov_len - sizeof(*reply),
-				     req->buf, req->buf_len) < 0) {
-			mutex_unlock(&monc->mutex);
-			goto bad;
-		}
-		req->result = le32_to_cpu(reply->reply_code);
-		get_generic_request(req);
-	}
-	mutex_unlock(&monc->mutex);
-	if (req) {
-		complete(&req->completion);
-		put_generic_request(req);
-	}
-	return;
-
-bad:
-	pr_err("corrupt generic reply, tid %llu\n", tid);
-	ceph_msg_dump(msg);
-}
-
-/*
- * Do a synchronous pool op.
- */
-static int do_poolop(struct ceph_mon_client *monc, u32 op,
-			u32 pool, u64 snapid,
-			char *buf, int len)
-{
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_poolop *h;
-	int err;
-
-	req = kzalloc(sizeof(*req), GFP_NOFS);
-	if (!req)
-		return -ENOMEM;
-
-	kref_init(&req->kref);
-	req->buf = buf;
-	req->buf_len = len;
-	init_completion(&req->completion);
-
-	err = -ENOMEM;
-	req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS,
-				    true);
-	if (!req->request)
-		goto out;
-	req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS,
-				  true);
-	if (!req->reply)
-		goto out;
-
-	/* fill out request */
-	req->request->hdr.version = cpu_to_le16(2);
-	h = req->request->front.iov_base;
-	h->monhdr.have_version = 0;
-	h->monhdr.session_mon = cpu_to_le16(-1);
-	h->monhdr.session_mon_tid = 0;
-	h->fsid = monc->monmap->fsid;
-	h->pool = cpu_to_le32(pool);
-	h->op = cpu_to_le32(op);
-	h->auid = 0;
-	h->snapid = cpu_to_le64(snapid);
-	h->name_len = 0;
-
-	err = do_generic_request(monc, req);
-
-out:
-	kref_put(&req->kref, release_generic_request);
-	return err;
-}
-
-int ceph_monc_create_snapid(struct ceph_mon_client *monc,
-			    u32 pool, u64 *snapid)
-{
-	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
-				   pool, 0, (char *)snapid, sizeof(*snapid));
-
-}
-EXPORT_SYMBOL(ceph_monc_create_snapid);
-
-int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
-			    u32 pool, u64 snapid)
-{
-	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
-				   pool, snapid, NULL, 0);
-
-}
-
-/*
  * Resend pending generic requests.
  */
 static void __resend_generic_request(struct ceph_mon_client *monc)
@@ -1112,10 +988,6 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		handle_get_version_reply(monc, msg);
 		break;
 
-	case CEPH_MSG_POOLOP_REPLY:
-		handle_poolop_reply(monc, msg);
-		break;
-
 	case CEPH_MSG_MON_MAP:
 		ceph_monc_handle_map(monc, msg);
 		break;
@@ -1154,7 +1026,6 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MON_SUBSCRIBE_ACK:
 		m = ceph_msg_get(monc->m_subscribe_ack);
 		break;
-	case CEPH_MSG_POOLOP_REPLY:
 	case CEPH_MSG_STATFS_REPLY:
 		return get_generic_reply(con, hdr, skip);
 	case CEPH_MSG_AUTH_REPLY:
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 53299c7b0ca4..41a4abc7e98e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1035,10 +1035,11 @@ static void put_osd(struct ceph_osd *osd)
 {
 	dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
 	     atomic_read(&osd->o_ref) - 1);
-	if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) {
+	if (atomic_dec_and_test(&osd->o_ref)) {
 		struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth;
 
-		ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer);
+		if (osd->o_auth.authorizer)
+			ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer);
 		kfree(osd);
 	}
 }
@@ -1048,14 +1049,24 @@ static void put_osd(struct ceph_osd *osd)
  */
 static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 {
-	dout("__remove_osd %p\n", osd);
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
 	WARN_ON(!list_empty(&osd->o_requests));
 	WARN_ON(!list_empty(&osd->o_linger_requests));
 
-	rb_erase(&osd->o_node, &osdc->osds);
 	list_del_init(&osd->o_osd_lru);
-	ceph_con_close(&osd->o_con);
-	put_osd(osd);
+	rb_erase(&osd->o_node, &osdc->osds);
+	RB_CLEAR_NODE(&osd->o_node);
+}
+
+static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+
+	if (!RB_EMPTY_NODE(&osd->o_node)) {
+		ceph_con_close(&osd->o_con);
+		__remove_osd(osdc, osd);
+		put_osd(osd);
+	}
 }
 
 static void remove_all_osds(struct ceph_osd_client *osdc)
@@ -1065,7 +1076,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc)
 	while (!RB_EMPTY_ROOT(&osdc->osds)) {
 		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
 						struct ceph_osd, o_node);
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1106,7 +1117,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc)
 	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
 		if (time_before(jiffies, osd->lru_ttl))
 			break;
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1121,8 +1132,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 	dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
 	if (list_empty(&osd->o_requests) &&
 	    list_empty(&osd->o_linger_requests)) {
-		__remove_osd(osdc, osd);
-
+		remove_osd(osdc, osd);
 		return -ENODEV;
 	}
 
@@ -1926,6 +1936,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
 {
 	struct rb_node *p, *n;
 
+	dout("%s %p\n", __func__, osdc);
 	for (p = rb_first(&osdc->osds); p; p = n) {
 		struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);