X-Git-Url: https://git.kernelconcepts.de/?a=blobdiff_plain;f=net%2Fceph%2Fmessenger.c;h=5e9f61d6d2340ef932068dc88d65609b593d4f63;hb=9a64e8e0ace51b309fdcff4b4754b3649250382a;hp=2ca491fc50e2bfd77fcef2ef67e08b4e58ca8f78;hpb=e22004235a900213625acd6583ac913d5a30c155;p=karo-tx-linux.git

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 2ca491fc50e2..5e9f61d6d234 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -29,6 +29,14 @@
  * the sender.
  */
 
+/* State values for ceph_connection->sock_state; NEW is assumed to be 0 */
+
+#define CON_SOCK_STATE_NEW		0	/* -> CLOSED */
+#define CON_SOCK_STATE_CLOSED		1	/* -> CONNECTING */
+#define CON_SOCK_STATE_CONNECTING	2	/* -> CONNECTED or -> CLOSING */
+#define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
+#define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
+
 /* static tag bytes (protocol control messages) */
 static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;
@@ -147,6 +155,55 @@ void ceph_msgr_flush(void)
 }
 EXPORT_SYMBOL(ceph_msgr_flush);
 
+/* Connection socket state transition functions */
+
+static void con_sock_state_init(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_NEW))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_connecting(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTING);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CLOSED))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_connected(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_closing(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSING);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING &&
+			old_state != CON_SOCK_STATE_CONNECTED &&
+			old_state != CON_SOCK_STATE_CLOSING))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_closed(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTED &&
+			old_state != CON_SOCK_STATE_CLOSING))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+}
 
 /*
  * socket callback functions
@@ -176,7 +233,7 @@ static void ceph_sock_write_space(struct sock *sk)
 	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
 	 * and net/core/stream.c:sk_stream_write_space().
 	 */
-	if (test_bit(WRITE_PENDING, &con->state)) {
+	if (test_bit(WRITE_PENDING, &con->flags)) {
 		if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
 			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
@@ -203,7 +260,8 @@ static void ceph_sock_state_change(struct sock *sk)
 		dout("%s TCP_CLOSE\n", __func__);
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
-		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
+		con_sock_state_closing(con);
+		if (test_and_set_bit(SOCK_CLOSED, &con->flags) == 0) {
 			if (test_bit(CONNECTING, &con->state))
 				con->error_msg = "connection failed";
 			else
@@ -213,6 +271,7 @@ static void ceph_sock_state_change(struct sock *sk)
 		break;
 	case TCP_ESTABLISHED:
 		dout("%s TCP_ESTABLISHED\n", __func__);
+		con_sock_state_connected(con);
 		queue_con(con);
 		break;
 	default:	/* Everything else is uninteresting */
@@ -262,6 +321,7 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 
 	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
 
+	con_sock_state_connecting(con);
 	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
 				 O_NONBLOCK);
 	if (ret == -EINPROGRESS) {
@@ -277,7 +337,6 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 	con->sock = sock;
-
 	return 0;
 }
 
@@ -343,6 +402,7 @@ static int con_close_socket(struct ceph_connection *con)
 	sock_release(con->sock);
 	con->sock = NULL;
 	clear_bit(SOCK_CLOSED, &con->state);
+	con_sock_state_closed(con);
 	return rc;
 }
 
@@ -353,6 +413,10 @@ static int con_close_socket(struct ceph_connection *con)
 static void ceph_msg_remove(struct ceph_msg *msg)
 {
 	list_del_init(&msg->list_head);
+	BUG_ON(msg->con == NULL);
+	ceph_con_put(msg->con);
+	msg->con = NULL;
+
 	ceph_msg_put(msg);
 }
 static void ceph_msg_remove_list(struct list_head *head)
@@ -372,8 +436,11 @@ static void reset_connection(struct ceph_connection *con)
 	ceph_msg_remove_list(&con->out_sent);
 
 	if (con->in_msg) {
+		BUG_ON(con->in_msg->con != con);
+		con->in_msg->con = NULL;
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
+		ceph_con_put(con->in_msg->con);
 	}
 
 	con->connect_seq = 0;
@@ -393,11 +460,14 @@ void ceph_con_close(struct ceph_connection *con)
 {
 	dout("con_close %p peer %s\n", con,
 	     ceph_pr_addr(&con->peer_addr.in_addr));
-	set_bit(CLOSED, &con->state);  /* in case there's queued work */
+	clear_bit(NEGOTIATING, &con->state);
 	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
-	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
-	clear_bit(KEEPALIVE_PENDING, &con->state);
-	clear_bit(WRITE_PENDING, &con->state);
+	set_bit(CLOSED, &con->state);
+
+	clear_bit(LOSSYTX, &con->flags);  /* so we retry next connect */
+	clear_bit(KEEPALIVE_PENDING, &con->flags);
+	clear_bit(WRITE_PENDING, &con->flags);
+
 	mutex_lock(&con->mutex);
 	reset_connection(con);
 	con->peer_global_seq = 0;
@@ -414,7 +484,8 @@ void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
 {
 	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
 	set_bit(OPENING, &con->state);
-	clear_bit(CLOSED, &con->state);
+	WARN_ON(!test_and_clear_bit(CLOSED, &con->state));
+
 	memcpy(&con->peer_addr, addr, sizeof(*addr));
 	con->delay = 0;      /* reset backoff memory */
 	queue_con(con);
@@ -456,16 +527,28 @@ void ceph_con_put(struct ceph_connection *con)
 /*
  * initialize a new connection.
  */
-void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
+void ceph_con_init(struct ceph_connection *con, void *private,
+	const struct ceph_connection_operations *ops,
+	struct ceph_messenger *msgr, __u8 entity_type, __u64 entity_num)
 {
 	dout("con_init %p\n", con);
 	memset(con, 0, sizeof(*con));
+	con->private = private;
+	con->ops = ops;
 	atomic_set(&con->nref, 1);
 	con->msgr = msgr;
+
+	con_sock_state_init(con);
+
+	con->peer_name.type = (__u8) entity_type;
+	con->peer_name.num = cpu_to_le64(entity_num);
+
 	mutex_init(&con->mutex);
 	INIT_LIST_HEAD(&con->out_queue);
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, con_work);
+
+	set_bit(CLOSED, &con->state);
 }
 EXPORT_SYMBOL(ceph_con_init);
 
@@ -548,8 +631,10 @@ static void prepare_write_message(struct ceph_connection *con)
 			&con->out_temp_ack);
 	}
 
+	BUG_ON(list_empty(&con->out_queue));
 	m = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
 	con->out_msg = m;
+	BUG_ON(m->con != con);
 
 	/* put message on sent list */
 	ceph_msg_get(m);
@@ -563,6 +648,10 @@ static void prepare_write_message(struct ceph_connection *con)
 		m->hdr.seq = cpu_to_le64(++con->out_seq);
 		m->needs_out_seq = false;
 	}
+#ifdef CONFIG_BLOCK
+	else
+		m->bio_iter = NULL;
+#endif
 
 	dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n",
 	     m, con->out_seq, le16_to_cpu(m->hdr.type),
@@ -614,7 +703,7 @@ static void prepare_write_message(struct ceph_connection *con)
 		prepare_write_message_footer(con);
 	}
 
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -635,7 +724,7 @@ static void prepare_write_ack(struct ceph_connection *con)
 				&con->out_temp_ack);
 
 	con->out_more = 1;  /* more will follow.. eventually.. */
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -646,7 +735,7 @@ static void prepare_write_keepalive(struct ceph_connection *con)
 	dout("prepare_write_keepalive %p\n", con);
 	con_out_kvec_reset(con);
 	con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -675,7 +764,7 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection
 
 	if (IS_ERR(auth))
 		return auth;
-	if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->state))
+	if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->flags))
 		return ERR_PTR(-EAGAIN);
 
 	con->auth_reply_buf = auth->authorizer_reply_buf;
@@ -695,12 +784,12 @@ static void prepare_write_banner(struct ceph_connection *con)
 					&con->msgr->my_enc_addr);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 static int prepare_write_connect(struct ceph_connection *con)
 {
-	unsigned global_seq = get_global_seq(con->msgr, 0);
+	unsigned int global_seq = get_global_seq(con->msgr, 0);
 	int proto;
 	int auth_proto;
 	struct ceph_auth_handshake *auth;
@@ -745,7 +834,7 @@ static int prepare_write_connect(struct ceph_connection *con)
 					auth->authorizer_buf);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 
 	return 0;
 }
@@ -828,7 +917,7 @@ static void iter_bio_next(struct bio **bio_iter, int *seg)
 static int write_partial_msg_pages(struct ceph_connection *con)
 {
 	struct ceph_msg *msg = con->out_msg;
-	unsigned data_len = le32_to_cpu(msg->hdr.data_len);
+	unsigned int data_len = le32_to_cpu(msg->hdr.data_len);
 	size_t len;
 	bool do_datacrc = !con->msgr->nocrc;
 	int ret;
@@ -1492,7 +1581,7 @@ static int process_connect(struct ceph_connection *con)
 			le32_to_cpu(con->in_reply.connect_seq));
 
 		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			set_bit(LOSSYTX, &con->state);
+			set_bit(LOSSYTX, &con->flags);
 
 		prepare_read_tag(con);
 		break;
@@ -1578,14 +1667,13 @@ static int read_partial_message_section(struct ceph_connection *con,
 	return 1;
 }
 
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
-				struct ceph_msg_header *hdr,
-				int *skip);
+static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
+				struct ceph_msg_header *hdr);
 
 
 static int read_partial_message_pages(struct ceph_connection *con,
 				      struct page **pages,
-				      unsigned data_len, bool do_datacrc)
+				      unsigned int data_len, bool do_datacrc)
 {
 	void *p;
 	int ret;
@@ -1618,7 +1706,7 @@ static int read_partial_message_pages(struct ceph_connection *con,
 #ifdef CONFIG_BLOCK
 static int read_partial_message_bio(struct ceph_connection *con,
 				    struct bio **bio_iter, int *bio_seg,
-				    unsigned data_len, bool do_datacrc)
+				    unsigned int data_len, bool do_datacrc)
 {
 	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
 	void *p;
@@ -1661,9 +1749,8 @@ static int read_partial_message(struct ceph_connection *con)
 	int size;
 	int end;
 	int ret;
-	unsigned front_len, middle_len, data_len;
+	unsigned int front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
-	int skip;
 	u64 seq;
 	u32 crc;
 
@@ -1716,9 +1803,7 @@ static int read_partial_message(struct ceph_connection *con)
 	if (!con->in_msg) {
 		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
 		     con->in_hdr.front_len, con->in_hdr.data_len);
-		skip = 0;
-		con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip);
-		if (skip) {
+		if (ceph_con_in_msg_alloc(con, &con->in_hdr)) {
 			/* skip this message */
 			dout("alloc_msg said skip message\n");
 			BUG_ON(con->in_msg);
@@ -1733,6 +1818,8 @@ static int read_partial_message(struct ceph_connection *con)
 				"error allocating memory for incoming message";
 			return -ENOMEM;
 		}
+
+		BUG_ON(con->in_msg->con != con);
 		m = con->in_msg;
 		m->front.iov_len = 0;    /* haven't read it yet */
 		if (m->middle)
@@ -1828,8 +1915,11 @@ static void process_message(struct ceph_connection *con)
 {
 	struct ceph_msg *msg;
 
+	BUG_ON(con->in_msg->con != con);
+	con->in_msg->con = NULL;
 	msg = con->in_msg;
 	con->in_msg = NULL;
+	ceph_con_put(con);
 
 	/* if first message, set peer_name */
 	if (con->peer_name.type == 0)
@@ -1869,14 +1959,15 @@ more:
 
 	/* open the socket first? */
 	if (con->sock == NULL) {
+		clear_bit(NEGOTIATING, &con->state);
+		set_bit(CONNECTING, &con->state);
+
 		con_out_kvec_reset(con);
 		prepare_write_banner(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			goto out;
 		prepare_read_banner(con);
-		set_bit(CONNECTING, &con->state);
-		clear_bit(NEGOTIATING, &con->state);
 
 		BUG_ON(con->in_msg);
 		con->in_tag = CEPH_MSGR_TAG_READY;
@@ -1933,14 +2024,14 @@ do_next:
 			prepare_write_ack(con);
 			goto more;
 		}
-		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) {
+		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->flags)) {
 			prepare_write_keepalive(con);
 			goto more;
 		}
 	}
 
 	/* Nothing to do! */
-	clear_bit(WRITE_PENDING, &con->state);
+	clear_bit(WRITE_PENDING, &con->flags);
 	dout("try_write nothing else to write.\n");
 	ret = 0;
 out:
@@ -2106,7 +2197,7 @@ static void con_work(struct work_struct *work)
 
 	mutex_lock(&con->mutex);
 restart:
-	if (test_and_clear_bit(BACKOFF, &con->state)) {
+	if (test_and_clear_bit(BACKOFF, &con->flags)) {
 		dout("con_work %p backing off\n", con);
 		if (queue_delayed_work(ceph_msgr_wq, &con->work,
 				       round_jiffies_relative(con->delay))) {
@@ -2135,7 +2226,7 @@ restart:
 		con_close_socket(con);
 	}
 
-	if (test_and_clear_bit(SOCK_CLOSED, &con->state))
+	if (test_and_clear_bit(SOCK_CLOSED, &con->flags))
 		goto fault;
 
 	ret = try_read(con);
@@ -2174,7 +2265,7 @@ static void ceph_fault(struct ceph_connection *con)
 	dout("fault %p state %lu to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
-	if (test_bit(LOSSYTX, &con->state)) {
+	if (test_bit(LOSSYTX, &con->flags)) {
 		dout("fault on LOSSYTX channel\n");
 		goto out;
 	}
@@ -2186,8 +2277,11 @@ static void ceph_fault(struct ceph_connection *con)
 	con_close_socket(con);
 
 	if (con->in_msg) {
+		BUG_ON(con->in_msg->con != con);
+		con->in_msg->con = NULL;
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
+		ceph_con_put(con);
 	}
 
 	/* Requeue anything that hasn't been acked */
@@ -2196,9 +2290,9 @@ static void ceph_fault(struct ceph_connection *con)
 	/* If there are no messages queued or keepalive pending, place
 	 * the connection in a STANDBY state */
 	if (list_empty(&con->out_queue) &&
-	    !test_bit(KEEPALIVE_PENDING, &con->state)) {
+	    !test_bit(KEEPALIVE_PENDING, &con->flags)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		clear_bit(WRITE_PENDING, &con->state);
+		clear_bit(WRITE_PENDING, &con->flags);
 		set_bit(STANDBY, &con->state);
 	} else {
 		/* retry after a delay. */
@@ -2222,7 +2316,7 @@ static void ceph_fault(struct ceph_connection *con)
 			 * that when con_work restarts we schedule the
 			 * delay then.
 			 */
-			set_bit(BACKOFF, &con->state);
+			set_bit(BACKOFF, &con->flags);
 		}
 	}
 
@@ -2245,18 +2339,14 @@ out:
 
 
 /*
- * create a new messenger instance
+ * initialize a new messenger instance
  */
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
-					     u32 supported_features,
-					     u32 required_features)
+void ceph_messenger_init(struct ceph_messenger *msgr,
+			struct ceph_entity_addr *myaddr,
+			u32 supported_features,
+			u32 required_features,
+			bool nocrc)
 {
-	struct ceph_messenger *msgr;
-
-	msgr = kzalloc(sizeof(*msgr), GFP_KERNEL);
-	if (msgr == NULL)
-		return ERR_PTR(-ENOMEM);
-
 	msgr->supported_features = supported_features;
 	msgr->required_features = required_features;
 
@@ -2269,19 +2359,11 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
 	msgr->inst.addr.type = 0;
 	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
 	encode_my_addr(msgr);
+	msgr->nocrc = nocrc;
 
-	dout("messenger_create %p\n", msgr);
-	return msgr;
+	dout("%s %p\n", __func__, msgr);
 }
-EXPORT_SYMBOL(ceph_messenger_create);
-
-void ceph_messenger_destroy(struct ceph_messenger *msgr)
-{
-	dout("destroy %p\n", msgr);
-	kfree(msgr);
-	dout("destroyed messenger %p\n", msgr);
-}
-EXPORT_SYMBOL(ceph_messenger_destroy);
+EXPORT_SYMBOL(ceph_messenger_init);
 
 static void clear_standby(struct ceph_connection *con)
 {
@@ -2290,8 +2372,8 @@ static void clear_standby(struct ceph_connection *con)
 		mutex_lock(&con->mutex);
 		dout("clear_standby %p and ++connect_seq\n", con);
 		con->connect_seq++;
-		WARN_ON(test_bit(WRITE_PENDING, &con->state));
-		WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state));
+		WARN_ON(test_bit(WRITE_PENDING, &con->flags));
+		WARN_ON(test_bit(KEEPALIVE_PENDING, &con->flags));
 		mutex_unlock(&con->mutex);
 	}
 }
@@ -2316,6 +2398,11 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	/* queue */
 	mutex_lock(&con->mutex);
+
+	BUG_ON(msg->con != NULL);
+	msg->con = ceph_con_get(con);
+	BUG_ON(msg->con == NULL);
+
 	BUG_ON(!list_empty(&msg->list_head));
 	list_add_tail(&msg->list_head, &con->out_queue);
 	dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg,
@@ -2329,7 +2416,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
 	clear_standby(con);
-	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+	if (test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);
@@ -2337,24 +2424,34 @@ EXPORT_SYMBOL(ceph_con_send);
 /*
  * Revoke a message that was previously queued for send
  */
-void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke(struct ceph_msg *msg)
 {
+	struct ceph_connection *con = msg->con;
+
+	if (!con)
+		return;		/* Message not in our possession */
+
 	mutex_lock(&con->mutex);
 	if (!list_empty(&msg->list_head)) {
-		dout("con_revoke %p msg %p - was on queue\n", con, msg);
+		dout("%s %p msg %p - was on queue\n", __func__, con, msg);
 		list_del_init(&msg->list_head);
-		ceph_msg_put(msg);
+		BUG_ON(msg->con == NULL);
+		ceph_con_put(msg->con);
+		msg->con = NULL;
 		msg->hdr.seq = 0;
+
+		ceph_msg_put(msg);
 	}
 	if (con->out_msg == msg) {
-		dout("con_revoke %p msg %p - was sending\n", con, msg);
+		dout("%s %p msg %p - was sending\n", __func__, con, msg);
 		con->out_msg = NULL;
 		if (con->out_kvec_is_msg) {
 			con->out_skip = con->out_kvec_bytes;
 			con->out_kvec_is_msg = false;
 		}
-		ceph_msg_put(msg);
 		msg->hdr.seq = 0;
+
+		ceph_msg_put(msg);
 	}
 	mutex_unlock(&con->mutex);
 }
@@ -2362,17 +2459,27 @@ void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
 /*
  * Revoke a message that we may be reading data into
  */
-void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 {
+	struct ceph_connection *con;
+
+	BUG_ON(msg == NULL);
+	if (!msg->con) {
+		dout("%s msg %p null con\n", __func__, msg);
+
+		return;		/* Message not in our possession */
+	}
+
+	con = msg->con;
 	mutex_lock(&con->mutex);
-	if (con->in_msg && con->in_msg == msg) {
-		unsigned front_len = le32_to_cpu(con->in_hdr.front_len);
-		unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len);
-		unsigned data_len = le32_to_cpu(con->in_hdr.data_len);
+	if (con->in_msg == msg) {
+		unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
+		unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
+		unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
 
 		/* skip rest of message */
-		dout("con_revoke_pages %p msg %p revoked\n", con, msg);
-			con->in_base_pos = con->in_base_pos -
+		dout("%s %p msg %p revoked\n", __func__, con, msg);
+		con->in_base_pos = con->in_base_pos -
 				sizeof(struct ceph_msg_header) -
 				front_len -
 				middle_len -
@@ -2383,8 +2490,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
 		con->in_tag = CEPH_MSGR_TAG_READY;
 		con->in_seq++;
 	} else {
-		dout("con_revoke_pages %p msg %p pages %p no-op\n",
-		     con, con->in_msg, msg);
+		dout("%s %p in_msg %p msg %p no-op\n",
+		     __func__, con, con->in_msg, msg);
 	}
 	mutex_unlock(&con->mutex);
 }
@@ -2396,8 +2503,8 @@ void ceph_con_keepalive(struct ceph_connection *con)
 {
 	dout("con_keepalive %p\n", con);
 	clear_standby(con);
-	if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
-	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+	if (test_and_set_bit(KEEPALIVE_PENDING, &con->flags) == 0 &&
+	    test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);
@@ -2416,6 +2523,8 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	if (m == NULL)
 		goto out;
 	kref_init(&m->kref);
+
+	m->con = NULL;
 	INIT_LIST_HEAD(&m->list_head);
 
 	m->hdr.tid = 0;
@@ -2511,46 +2620,63 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
 }
 
 /*
- * Generic message allocator, for incoming messages.
+ * Allocate a message for receiving an incoming message on a
+ * connection, and save the result in con->in_msg.  Uses the
+ * connection's private alloc_msg op if available.
+ *
+ * Returns true if the message should be skipped, false otherwise.
+ * If true is returned (skip message), con->in_msg will be NULL.
+ * If false is returned, con->in_msg will contain a pointer to the
+ * newly-allocated message, or NULL in case of memory exhaustion.
  */
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
-				struct ceph_msg_header *hdr,
-				int *skip)
+static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
+				struct ceph_msg_header *hdr)
 {
 	int type = le16_to_cpu(hdr->type);
 	int front_len = le32_to_cpu(hdr->front_len);
 	int middle_len = le32_to_cpu(hdr->middle_len);
-	struct ceph_msg *msg = NULL;
 	int ret;
 
+	BUG_ON(con->in_msg != NULL);
+
 	if (con->ops->alloc_msg) {
+		int skip = 0;
+
 		mutex_unlock(&con->mutex);
-		msg = con->ops->alloc_msg(con, hdr, skip);
+		con->in_msg = con->ops->alloc_msg(con, hdr, &skip);
 		mutex_lock(&con->mutex);
-		if (!msg || *skip)
-			return NULL;
+		if (con->in_msg) {
+			con->in_msg->con = ceph_con_get(con);
+			BUG_ON(con->in_msg->con == NULL);
+		}
+		if (skip)
+			con->in_msg = NULL;
+
+		if (!con->in_msg)
+			return skip != 0;
 	}
-	if (!msg) {
-		*skip = 0;
-		msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
-		if (!msg) {
+	if (!con->in_msg) {
+		con->in_msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
+		if (!con->in_msg) {
 			pr_err("unable to allocate msg type %d len %d\n",
 			       type, front_len);
-			return NULL;
+			return false;
 		}
-		msg->page_alignment = le16_to_cpu(hdr->data_off);
+		con->in_msg->con = ceph_con_get(con);
+		BUG_ON(con->in_msg->con == NULL);
+		con->in_msg->page_alignment = le16_to_cpu(hdr->data_off);
 	}
-	memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
+	memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
 
-	if (middle_len && !msg->middle) {
-		ret = ceph_alloc_middle(con, msg);
+	if (middle_len && !con->in_msg->middle) {
+		ret = ceph_alloc_middle(con, con->in_msg);
 		if (ret < 0) {
-			ceph_msg_put(msg);
-			return NULL;
+			ceph_msg_put(con->in_msg);
+			con->in_msg = NULL;
 		}
 	}
 
-	return msg;
+	return false;
 }