X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=net%2Fceph%2Fmessenger.c;h=b872db5c498941020c05c6c77a9729b70cace120;hb=4a8616920860920abaa51193146fe36b38ef09aa;hp=23073cff648111c2a279488d77940c8d48b4b782;hpb=26ce171915f348abd1f41da1ed139d93750d987f;p=firefly-linux-kernel-4.4.55.git

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 23073cff6481..b872db5c4989 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -29,7 +29,47 @@
  * the sender.
  */
 
-/* State values for ceph_connection->sock_state; NEW is assumed to be 0 */
+/*
+ * We track the state of the socket on a given connection using
+ * values defined below.  The transition to a new socket state is
+ * handled by a function which verifies we aren't coming from an
+ * unexpected state.
+ *
+ *      --------
+ *      | NEW* |  transient initial state
+ *      --------
+ *          | con_sock_state_init()
+ *          v
+ *      ----------
+ *      | CLOSED |  initialized, but no socket (and no
+ *      ----------  TCP connection)
+ *       ^      \
+ *       |       \ con_sock_state_connecting()
+ *       |        ----------------------
+ *       |                              \
+ *       + con_sock_state_closed()       \
+ *       |+---------------------------    \
+ *       | \                          \    \
+ *       |  -----------                \    \
+ *       |  | CLOSING |  socket event;  \    \
+ *       |  -----------  await close     \    \
+ *       |       ^                        \   |
+ *       |       |                         \  |
+ *       |       + con_sock_state_closing() \ |
+ *       |      / \                         | |
+ *       |     /   ---------------          | |
+ *       |    /                   \         v v
+ *       |   /                    --------------
+ *       |  /    -----------------| CONNECTING |  socket created, TCP
+ *       |  |   /                 --------------  connect initiated
+ *       |  |   | con_sock_state_connected()
+ *       |  |   v
+ *      -------------
+ *      | CONNECTED |  TCP connection established
+ *      -------------
+ *
+ * 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 */
@@ -37,6 +77,26 @@
 #define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
 #define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
 
+/*
+ * connection states
+ */
+#define CON_STATE_CLOSED        1  /* -> PREOPEN */
+#define CON_STATE_PREOPEN       2  /* -> CONNECTING, CLOSED */
+#define CON_STATE_CONNECTING    3  /* -> NEGOTIATING, CLOSED */
+#define CON_STATE_NEGOTIATING   4  /* -> OPEN, CLOSED */
+#define CON_STATE_OPEN          5  /* -> STANDBY, CLOSED */
+#define CON_STATE_STANDBY       6  /* -> PREOPEN, CLOSED */
+
+/*
+ * ceph_connection flag bits
+ */
+#define CON_FLAG_LOSSYTX           0  /* we can close channel or drop
+				       * messages on errors */
+#define CON_FLAG_KEEPALIVE_PENDING 1  /* we need to send a keepalive */
+#define CON_FLAG_WRITE_PENDING	   2  /* we have data ready to send */
+#define CON_FLAG_SOCK_CLOSED	   3  /* socket state changed to closed */
+#define CON_FLAG_BACKOFF           4  /* need to retry queuing delayed work */
+
 /* static tag bytes (protocol control messages) */
 static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;
@@ -201,7 +261,8 @@ static void con_sock_state_closed(struct ceph_connection *con)
 
 	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))
+		    old_state != CON_SOCK_STATE_CLOSING &&
+		    old_state != CON_SOCK_STATE_CONNECTING))
 		printk("%s: unexpected old state %d\n", __func__, old_state);
 }
 
@@ -213,6 +274,9 @@ static void con_sock_state_closed(struct ceph_connection *con)
 static void ceph_sock_data_ready(struct sock *sk, int count_unused)
 {
 	struct ceph_connection *con = sk->sk_user_data;
+	if (atomic_read(&con->msgr->stopping)) {
+		return;
+	}
 
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
 		dout("%s on %p state = %lu, queueing work\n", __func__,
@@ -233,7 +297,7 @@ 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->flags)) {
+	if (test_bit(CON_FLAG_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);
@@ -252,22 +316,14 @@ static void ceph_sock_state_change(struct sock *sk)
 	dout("%s %p state = %lu sk_state = %u\n", __func__,
 	     con, con->state, sk->sk_state);
 
-	if (test_bit(CLOSED, &con->state))
-		return;
-
 	switch (sk->sk_state) {
 	case TCP_CLOSE:
 		dout("%s TCP_CLOSE\n", __func__);
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
 		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
-				con->error_msg = "socket closed";
-			queue_con(con);
-		}
+		set_bit(CON_FLAG_SOCK_CLOSED, &con->flags);
+		queue_con(con);
 		break;
 	case TCP_ESTABLISHED:
 		dout("%s TCP_ESTABLISHED\n", __func__);
@@ -397,11 +453,17 @@ static int con_close_socket(struct ceph_connection *con)
 	dout("con_close_socket on %p sock %p\n", con, con->sock);
 	if (!con->sock)
 		return 0;
-	set_bit(SOCK_CLOSED, &con->state);
 	rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
 	sock_release(con->sock);
 	con->sock = NULL;
-	clear_bit(SOCK_CLOSED, &con->state);
+
+	/*
+	 * Forcibly clear the SOCK_CLOSED flag.  It gets set
+	 * independent of the connection mutex, and we could have
+	 * received a socket close event before we had the chance to
+	 * shut the socket down.
+	 */
+	clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags);
 	con_sock_state_closed(con);
 	return rc;
 }
@@ -414,7 +476,7 @@ 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->ops->put(msg->con);
 	msg->con = NULL;
 
 	ceph_msg_put(msg);
@@ -440,7 +502,7 @@ static void reset_connection(struct ceph_connection *con)
 		con->in_msg->con = NULL;
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
-		ceph_con_put(con);
+		con->ops->put(con);
 	}
 
 	con->connect_seq = 0;
@@ -458,36 +520,42 @@ static void reset_connection(struct ceph_connection *con)
  */
 void ceph_con_close(struct ceph_connection *con)
 {
+	mutex_lock(&con->mutex);
 	dout("con_close %p peer %s\n", con,
 	     ceph_pr_addr(&con->peer_addr.in_addr));
-	clear_bit(NEGOTIATING, &con->state);
-	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
-	set_bit(CLOSED, &con->state);
+	con->state = CON_STATE_CLOSED;
 
-	clear_bit(LOSSYTX, &con->flags);  /* so we retry next connect */
-	clear_bit(KEEPALIVE_PENDING, &con->flags);
-	clear_bit(WRITE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_LOSSYTX, &con->flags); /* so we retry next connect */
+	clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 
-	mutex_lock(&con->mutex);
 	reset_connection(con);
 	con->peer_global_seq = 0;
 	cancel_delayed_work(&con->work);
+	con_close_socket(con);
 	mutex_unlock(&con->mutex);
-	queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_close);
 
 /*
  * Reopen a closed connection, with a new peer address.
  */
-void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
+void ceph_con_open(struct ceph_connection *con,
+		   __u8 entity_type, __u64 entity_num,
+		   struct ceph_entity_addr *addr)
 {
+	mutex_lock(&con->mutex);
 	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
-	set_bit(OPENING, &con->state);
-	WARN_ON(!test_and_clear_bit(CLOSED, &con->state));
+
+	BUG_ON(con->state != CON_STATE_CLOSED);
+	con->state = CON_STATE_PREOPEN;
+
+	con->peer_name.type = (__u8) entity_type;
+	con->peer_name.num = cpu_to_le64(entity_num);
 
 	memcpy(&con->peer_addr, addr, sizeof(*addr));
 	con->delay = 0;      /* reset backoff memory */
+	mutex_unlock(&con->mutex);
 	queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_open);
@@ -500,55 +568,27 @@ bool ceph_con_opened(struct ceph_connection *con)
 	return con->connect_seq > 0;
 }
 
-/*
- * generic get/put
- */
-struct ceph_connection *ceph_con_get(struct ceph_connection *con)
-{
-	int nref = __atomic_add_unless(&con->nref, 1, 0);
-
-	dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1);
-
-	return nref ? con : NULL;
-}
-
-void ceph_con_put(struct ceph_connection *con)
-{
-	int nref = atomic_dec_return(&con->nref);
-
-	BUG_ON(nref < 0);
-	if (nref == 0) {
-		BUG_ON(con->sock);
-		kfree(con);
-	}
-	dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref);
-}
-
 /*
  * initialize a new connection.
  */
 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)
+	struct ceph_messenger *msgr)
 {
 	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);
+	con->state = CON_STATE_CLOSED;
 }
 EXPORT_SYMBOL(ceph_con_init);
 
@@ -590,6 +630,53 @@ static void con_out_kvec_add(struct ceph_connection *con,
 	con->out_kvec_bytes += size;
 }
 
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+	if (!bio) {
+		*iter = NULL;
+		*seg = 0;
+		return;
+	}
+	*iter = bio;
+	*seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+	if (*bio_iter == NULL)
+		return;
+
+	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+	(*seg)++;
+	if (*seg == (*bio_iter)->bi_vcnt)
+		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
+static void prepare_write_message_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	BUG_ON(!msg);
+	BUG_ON(!msg->hdr.data_len);
+
+	/* initialize page iterator */
+	con->out_msg_pos.page = 0;
+	if (msg->pages)
+		con->out_msg_pos.page_pos = msg->page_alignment;
+	else
+		con->out_msg_pos.page_pos = 0;
+#ifdef CONFIG_BLOCK
+	if (msg->bio)
+		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+	con->out_msg_pos.data_pos = 0;
+	con->out_msg_pos.did_page_crc = false;
+	con->out_more = 1;  /* data + footer will follow */
+}
+
 /*
  * Prepare footer for currently outgoing message, and finish things
  * off.  Assumes out_kvec* are already valid.. we just add on to the end.
@@ -599,6 +686,8 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	struct ceph_msg *m = con->out_msg;
 	int v = con->out_kvec_left;
 
+	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
+
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
 	con->out_kvec[v].iov_base = &m->footer;
@@ -648,10 +737,6 @@ 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),
@@ -672,7 +757,7 @@ static void prepare_write_message(struct ceph_connection *con)
 	/* fill in crc (except data pages), footer */
 	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
 	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
+	con->out_msg->footer.flags = 0;
 
 	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
 	con->out_msg->footer.front_crc = cpu_to_le32(crc);
@@ -682,28 +767,19 @@ static void prepare_write_message(struct ceph_connection *con)
 		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
 	} else
 		con->out_msg->footer.middle_crc = 0;
-	con->out_msg->footer.data_crc = 0;
-	dout("prepare_write_message front_crc %u data_crc %u\n",
+	dout("%s front_crc %u middle_crc %u\n", __func__,
 	     le32_to_cpu(con->out_msg->footer.front_crc),
 	     le32_to_cpu(con->out_msg->footer.middle_crc));
 
 	/* is there a data payload? */
-	if (le32_to_cpu(m->hdr.data_len) > 0) {
-		/* initialize page iterator */
-		con->out_msg_pos.page = 0;
-		if (m->pages)
-			con->out_msg_pos.page_pos = m->page_alignment;
-		else
-			con->out_msg_pos.page_pos = 0;
-		con->out_msg_pos.data_pos = 0;
-		con->out_msg_pos.did_page_crc = false;
-		con->out_more = 1;  /* data + footer will follow */
-	} else {
+	con->out_msg->footer.data_crc = 0;
+	if (m->hdr.data_len)
+		prepare_write_message_data(con);
+	else
 		/* no, queue up footer too and be done */
 		prepare_write_message_footer(con);
-	}
 
-	set_bit(WRITE_PENDING, &con->flags);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -724,7 +800,7 @@ 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->flags);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -735,7 +811,7 @@ 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->flags);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -750,27 +826,21 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection
 	if (!con->ops->get_authorizer) {
 		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
 		con->out_connect.authorizer_len = 0;
-
 		return NULL;
 	}
 
 	/* Can't hold the mutex while getting authorizer */
-
 	mutex_unlock(&con->mutex);
-
 	auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry);
-
 	mutex_lock(&con->mutex);
 
 	if (IS_ERR(auth))
 		return auth;
-	if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->flags))
+	if (con->state != CON_STATE_NEGOTIATING)
 		return ERR_PTR(-EAGAIN);
 
 	con->auth_reply_buf = auth->authorizer_reply_buf;
 	con->auth_reply_buf_len = auth->authorizer_reply_buf_len;
-
-
 	return auth;
 }
 
@@ -784,7 +854,7 @@ static void prepare_write_banner(struct ceph_connection *con)
 					&con->msgr->my_enc_addr);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->flags);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 static int prepare_write_connect(struct ceph_connection *con)
@@ -827,6 +897,7 @@ static int prepare_write_connect(struct ceph_connection *con)
 	con->out_connect.authorizer_len = auth ?
 		cpu_to_le32(auth->authorizer_buf_len) : 0;
 
+	con_out_kvec_reset(con);
 	con_out_kvec_add(con, sizeof (con->out_connect),
 					&con->out_connect);
 	if (auth && auth->authorizer_buf_len)
@@ -834,7 +905,7 @@ static int prepare_write_connect(struct ceph_connection *con)
 					auth->authorizer_buf);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->flags);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 
 	return 0;
 }
@@ -882,30 +953,34 @@ out:
 	return ret;  /* done! */
 }
 
-#ifdef CONFIG_BLOCK
-static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+static void out_msg_pos_next(struct ceph_connection *con, struct page *page,
+			size_t len, size_t sent, bool in_trail)
 {
-	if (!bio) {
-		*iter = NULL;
-		*seg = 0;
-		return;
-	}
-	*iter = bio;
-	*seg = bio->bi_idx;
-}
+	struct ceph_msg *msg = con->out_msg;
 
-static void iter_bio_next(struct bio **bio_iter, int *seg)
-{
-	if (*bio_iter == NULL)
-		return;
+	BUG_ON(!msg);
+	BUG_ON(!sent);
 
-	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+	con->out_msg_pos.data_pos += sent;
+	con->out_msg_pos.page_pos += sent;
+	if (sent < len)
+		return;
 
-	(*seg)++;
-	if (*seg == (*bio_iter)->bi_vcnt)
-		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
-}
+	BUG_ON(sent != len);
+	con->out_msg_pos.page_pos = 0;
+	con->out_msg_pos.page++;
+	con->out_msg_pos.did_page_crc = false;
+	if (in_trail)
+		list_move_tail(&page->lru,
+			       &msg->trail->head);
+	else if (msg->pagelist)
+		list_move_tail(&page->lru,
+			       &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+	else if (msg->bio)
+		iter_bio_next(&msg->bio_iter, &msg->bio_seg);
 #endif
+}
 
 /*
  * Write as much message data payload as we can.  If we finish, queue
@@ -922,41 +997,36 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 	bool do_datacrc = !con->msgr->nocrc;
 	int ret;
 	int total_max_write;
-	int in_trail = 0;
-	size_t trail_len = (msg->trail ? msg->trail->length : 0);
+	bool in_trail = false;
+	const size_t trail_len = (msg->trail ? msg->trail->length : 0);
+	const size_t trail_off = data_len - trail_len;
 
 	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
-	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
+	     con, msg, con->out_msg_pos.page, msg->nr_pages,
 	     con->out_msg_pos.page_pos);
 
-#ifdef CONFIG_BLOCK
-	if (msg->bio && !msg->bio_iter)
-		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
-#endif
-
+	/*
+	 * Iterate through each page that contains data to be
+	 * written, and send as much as possible for each.
+	 *
+	 * If we are calculating the data crc (the default), we will
+	 * need to map the page.  If we have no pages, they have
+	 * been revoked, so use the zero page.
+	 */
 	while (data_len > con->out_msg_pos.data_pos) {
 		struct page *page = NULL;
 		int max_write = PAGE_SIZE;
 		int bio_offset = 0;
 
-		total_max_write = data_len - trail_len -
-			con->out_msg_pos.data_pos;
-
-		/*
-		 * if we are calculating the data crc (the default), we need
-		 * to map the page.  if our pages[] has been revoked, use the
-		 * zero page.
-		 */
-
-		/* have we reached the trail part of the data? */
-		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
-			in_trail = 1;
+		in_trail = in_trail || con->out_msg_pos.data_pos >= trail_off;
+		if (!in_trail)
+			total_max_write = trail_off - con->out_msg_pos.data_pos;
 
+		if (in_trail) {
 			total_max_write = data_len - con->out_msg_pos.data_pos;
 
 			page = list_first_entry(&msg->trail->head,
 						struct page, lru);
-			max_write = PAGE_SIZE;
 		} else if (msg->pages) {
 			page = msg->pages[con->out_msg_pos.page];
 		} else if (msg->pagelist) {
@@ -979,15 +1049,14 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 
 		if (do_datacrc && !con->out_msg_pos.did_page_crc) {
 			void *base;
-			u32 crc;
-			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+			u32 crc = le32_to_cpu(msg->footer.data_crc);
 			char *kaddr;
 
 			kaddr = kmap(page);
 			BUG_ON(kaddr == NULL);
 			base = kaddr + con->out_msg_pos.page_pos + bio_offset;
-			crc = crc32c(tmpcrc, base, len);
-			con->out_msg->footer.data_crc = cpu_to_le32(crc);
+			crc = crc32c(crc, base, len);
+			msg->footer.data_crc = cpu_to_le32(crc);
 			con->out_msg_pos.did_page_crc = true;
 		}
 		ret = ceph_tcp_sendpage(con->sock, page,
@@ -1000,30 +1069,14 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 		if (ret <= 0)
 			goto out;
 
-		con->out_msg_pos.data_pos += ret;
-		con->out_msg_pos.page_pos += ret;
-		if (ret == len) {
-			con->out_msg_pos.page_pos = 0;
-			con->out_msg_pos.page++;
-			con->out_msg_pos.did_page_crc = false;
-			if (in_trail)
-				list_move_tail(&page->lru,
-					       &msg->trail->head);
-			else if (msg->pagelist)
-				list_move_tail(&page->lru,
-					       &msg->pagelist->head);
-#ifdef CONFIG_BLOCK
-			else if (msg->bio)
-				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
-#endif
-		}
+		out_msg_pos_next(con, page, len, (size_t) ret, in_trail);
 	}
 
 	dout("write_partial_msg_pages %p msg %p done\n", con, msg);
 
 	/* prepare and queue up footer, too */
 	if (!do_datacrc)
-		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
 	con_out_kvec_reset(con);
 	prepare_write_message_footer(con);
 	ret = 1;
@@ -1436,15 +1489,14 @@ static int process_banner(struct ceph_connection *con)
 		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
 	}
 
-	set_bit(NEGOTIATING, &con->state);
-	prepare_read_connect(con);
 	return 0;
 }
 
 static void fail_protocol(struct ceph_connection *con)
 {
 	reset_connection(con);
-	set_bit(CLOSED, &con->state);  /* in case there's queued work */
+	BUG_ON(con->state != CON_STATE_NEGOTIATING);
+	con->state = CON_STATE_CLOSED;
 }
 
 static int process_connect(struct ceph_connection *con)
@@ -1487,7 +1539,6 @@ static int process_connect(struct ceph_connection *con)
 			return -1;
 		}
 		con->auth_retry = 1;
-		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1503,12 +1554,11 @@ static int process_connect(struct ceph_connection *con)
 		 * dropped messages.
 		 */
 		dout("process_connect got RESET peer seq %u\n",
-		     le32_to_cpu(con->in_connect.connect_seq));
+		     le32_to_cpu(con->in_reply.connect_seq));
 		pr_err("%s%lld %s connection reset\n",
 		       ENTITY_NAME(con->peer_name),
 		       ceph_pr_addr(&con->peer_addr.in_addr));
 		reset_connection(con);
-		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1520,8 +1570,7 @@ static int process_connect(struct ceph_connection *con)
 		if (con->ops->peer_reset)
 			con->ops->peer_reset(con);
 		mutex_lock(&con->mutex);
-		if (test_bit(CLOSED, &con->state) ||
-		    test_bit(OPENING, &con->state))
+		if (con->state != CON_STATE_NEGOTIATING)
 			return -EAGAIN;
 		break;
 
@@ -1530,11 +1579,10 @@ static int process_connect(struct ceph_connection *con)
 		 * If we sent a smaller connect_seq than the peer has, try
 		 * again with a larger value.
 		 */
-		dout("process_connect got RETRY my seq = %u, peer_seq = %u\n",
+		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
 		     le32_to_cpu(con->out_connect.connect_seq),
-		     le32_to_cpu(con->in_connect.connect_seq));
-		con->connect_seq = le32_to_cpu(con->in_connect.connect_seq);
-		con_out_kvec_reset(con);
+		     le32_to_cpu(con->in_reply.connect_seq));
+		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1548,10 +1596,9 @@ static int process_connect(struct ceph_connection *con)
 		 */
 		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
 		     con->peer_global_seq,
-		     le32_to_cpu(con->in_connect.global_seq));
+		     le32_to_cpu(con->in_reply.global_seq));
 		get_global_seq(con->msgr,
-			       le32_to_cpu(con->in_connect.global_seq));
-		con_out_kvec_reset(con);
+			       le32_to_cpu(con->in_reply.global_seq));
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1569,7 +1616,10 @@ static int process_connect(struct ceph_connection *con)
 			fail_protocol(con);
 			return -1;
 		}
-		clear_bit(CONNECTING, &con->state);
+
+		BUG_ON(con->state != CON_STATE_NEGOTIATING);
+		con->state = CON_STATE_OPEN;
+
 		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
 		con->connect_seq++;
 		con->peer_features = server_feat;
@@ -1581,7 +1631,9 @@ 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->flags);
+			set_bit(CON_FLAG_LOSSYTX, &con->flags);
+
+		con->delay = 0;      /* reset backoff memory */
 
 		prepare_read_tag(con);
 		break;
@@ -1712,9 +1764,6 @@ static int read_partial_message_bio(struct ceph_connection *con,
 	void *p;
 	int ret, left;
 
-	if (IS_ERR(bv))
-		return PTR_ERR(bv);
-
 	left = min((int)(data_len - con->in_msg_pos.data_pos),
 		   (int)(bv->bv_len - con->in_msg_pos.page_pos));
 
@@ -1831,6 +1880,11 @@ static int read_partial_message(struct ceph_connection *con)
 		else
 			con->in_msg_pos.page_pos = 0;
 		con->in_msg_pos.data_pos = 0;
+
+#ifdef CONFIG_BLOCK
+		if (m->bio)
+			init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
 	}
 
 	/* front */
@@ -1847,10 +1901,6 @@ static int read_partial_message(struct ceph_connection *con)
 		if (ret <= 0)
 			return ret;
 	}
-#ifdef CONFIG_BLOCK
-	if (m->bio && !m->bio_iter)
-		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
-#endif
 
 	/* (page) data */
 	while (con->in_msg_pos.data_pos < data_len) {
@@ -1861,7 +1911,7 @@ static int read_partial_message(struct ceph_connection *con)
 				return ret;
 #ifdef CONFIG_BLOCK
 		} else if (m->bio) {
-
+			BUG_ON(!m->bio_iter);
 			ret = read_partial_message_bio(con,
 						 &m->bio_iter, &m->bio_seg,
 						 data_len, do_datacrc);
@@ -1919,7 +1969,7 @@ static void process_message(struct ceph_connection *con)
 	con->in_msg->con = NULL;
 	msg = con->in_msg;
 	con->in_msg = NULL;
-	ceph_con_put(con);
+	con->ops->put(con);
 
 	/* if first message, set peer_name */
 	if (con->peer_name.type == 0)
@@ -1951,22 +2001,18 @@ static int try_write(struct ceph_connection *con)
 {
 	int ret = 1;
 
-	dout("try_write start %p state %lu nref %d\n", con, con->state,
-	     atomic_read(&con->nref));
+	dout("try_write start %p state %lu\n", con, con->state);
 
 more:
 	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
 
 	/* open the socket first? */
-	if (con->sock == NULL) {
-		clear_bit(NEGOTIATING, &con->state);
-		set_bit(CONNECTING, &con->state);
+	if (con->state == CON_STATE_PREOPEN) {
+		BUG_ON(con->sock);
+		con->state = CON_STATE_CONNECTING;
 
 		con_out_kvec_reset(con);
 		prepare_write_banner(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			goto out;
 		prepare_read_banner(con);
 
 		BUG_ON(con->in_msg);
@@ -2014,7 +2060,7 @@ more_kvec:
 	}
 
 do_next:
-	if (!test_bit(CONNECTING, &con->state)) {
+	if (con->state == CON_STATE_OPEN) {
 		/* is anything else pending? */
 		if (!list_empty(&con->out_queue)) {
 			prepare_write_message(con);
@@ -2024,14 +2070,15 @@ do_next:
 			prepare_write_ack(con);
 			goto more;
 		}
-		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->flags)) {
+		if (test_and_clear_bit(CON_FLAG_KEEPALIVE_PENDING,
+				       &con->flags)) {
 			prepare_write_keepalive(con);
 			goto more;
 		}
 	}
 
 	/* Nothing to do! */
-	clear_bit(WRITE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 	dout("try_write nothing else to write.\n");
 	ret = 0;
 out:
@@ -2048,38 +2095,42 @@ static int try_read(struct ceph_connection *con)
 {
 	int ret = -1;
 
-	if (!con->sock)
-		return 0;
-
-	if (test_bit(STANDBY, &con->state))
+more:
+	dout("try_read start on %p state %lu\n", con, con->state);
+	if (con->state != CON_STATE_CONNECTING &&
+	    con->state != CON_STATE_NEGOTIATING &&
+	    con->state != CON_STATE_OPEN)
 		return 0;
 
-	dout("try_read start on %p\n", con);
+	BUG_ON(!con->sock);
 
-more:
 	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
 	     con->in_base_pos);
 
-	/*
-	 * process_connect and process_message drop and re-take
-	 * con->mutex.  make sure we handle a racing close or reopen.
-	 */
-	if (test_bit(CLOSED, &con->state) ||
-	    test_bit(OPENING, &con->state)) {
-		ret = -EAGAIN;
+	if (con->state == CON_STATE_CONNECTING) {
+		dout("try_read connecting\n");
+		ret = read_partial_banner(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_banner(con);
+		if (ret < 0)
+			goto out;
+
+		BUG_ON(con->state != CON_STATE_CONNECTING);
+		con->state = CON_STATE_NEGOTIATING;
+
+		/* Banner is good, exchange connection info */
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			goto out;
+		prepare_read_connect(con);
+
+		/* Send connection info before awaiting response */
 		goto out;
 	}
 
-	if (test_bit(CONNECTING, &con->state)) {
-		if (!test_bit(NEGOTIATING, &con->state)) {
-			dout("try_read connecting\n");
-			ret = read_partial_banner(con);
-			if (ret <= 0)
-				goto out;
-			ret = process_banner(con);
-			if (ret < 0)
-				goto out;
-		}
+	if (con->state == CON_STATE_NEGOTIATING) {
+		dout("try_read negotiating\n");
 		ret = read_partial_connect(con);
 		if (ret <= 0)
 			goto out;
@@ -2089,6 +2140,8 @@ more:
 		goto more;
 	}
 
+	BUG_ON(con->state != CON_STATE_OPEN);
+
 	if (con->in_base_pos < 0) {
 		/*
 		 * skipping + discarding content.
@@ -2122,7 +2175,8 @@ more:
 			prepare_read_ack(con);
 			break;
 		case CEPH_MSGR_TAG_CLOSE:
-			set_bit(CLOSED, &con->state);   /* fixme */
+			con_close_socket(con);
+			con->state = CON_STATE_CLOSED;
 			goto out;
 		default:
 			goto bad_tag;
@@ -2197,7 +2251,26 @@ static void con_work(struct work_struct *work)
 
 	mutex_lock(&con->mutex);
 restart:
-	if (test_and_clear_bit(BACKOFF, &con->flags)) {
+	if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) {
+		switch (con->state) {
+		case CON_STATE_CONNECTING:
+			con->error_msg = "connection failed";
+			break;
+		case CON_STATE_NEGOTIATING:
+			con->error_msg = "negotiation failed";
+			break;
+		case CON_STATE_OPEN:
+			con->error_msg = "socket closed";
+			break;
+		default:
+			dout("unrecognized con state %d\n", (int)con->state);
+			con->error_msg = "unrecognized con state";
+			BUG();
+		}
+		goto fault;
+	}
+
+	if (test_and_clear_bit(CON_FLAG_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))) {
@@ -2211,35 +2284,35 @@ restart:
 		}
 	}
 
-	if (test_bit(STANDBY, &con->state)) {
+	if (con->state == CON_STATE_STANDBY) {
 		dout("con_work %p STANDBY\n", con);
 		goto done;
 	}
-	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
-		dout("con_work CLOSED\n");
-		con_close_socket(con);
+	if (con->state == CON_STATE_CLOSED) {
+		dout("con_work %p CLOSED\n", con);
+		BUG_ON(con->sock);
 		goto done;
 	}
-	if (test_and_clear_bit(OPENING, &con->state)) {
-		/* reopen w/ new peer */
+	if (con->state == CON_STATE_PREOPEN) {
 		dout("con_work OPENING\n");
-		con_close_socket(con);
+		BUG_ON(con->sock);
 	}
 
-	if (test_and_clear_bit(SOCK_CLOSED, &con->flags))
-		goto fault;
-
 	ret = try_read(con);
 	if (ret == -EAGAIN)
 		goto restart;
-	if (ret < 0)
+	if (ret < 0) {
+		con->error_msg = "socket error on read";
 		goto fault;
+	}
 
 	ret = try_write(con);
 	if (ret == -EAGAIN)
 		goto restart;
-	if (ret < 0)
+	if (ret < 0) {
+		con->error_msg = "socket error on write";
 		goto fault;
+	}
 
 done:
 	mutex_unlock(&con->mutex);
@@ -2260,28 +2333,31 @@ fault:
  */
 static void ceph_fault(struct ceph_connection *con)
 {
+	mutex_lock(&con->mutex);
+
 	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
 	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	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->flags)) {
-		dout("fault on LOSSYTX channel\n");
-		goto out;
-	}
-
-	mutex_lock(&con->mutex);
-	if (test_bit(CLOSED, &con->state))
-		goto out_unlock;
+	BUG_ON(con->state != CON_STATE_CONNECTING &&
+	       con->state != CON_STATE_NEGOTIATING &&
+	       con->state != CON_STATE_OPEN);
 
 	con_close_socket(con);
 
+	if (test_bit(CON_FLAG_LOSSYTX, &con->flags)) {
+		dout("fault on LOSSYTX channel, marking CLOSED\n");
+		con->state = CON_STATE_CLOSED;
+		goto out_unlock;
+	}
+
 	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);
+		con->ops->put(con);
 	}
 
 	/* Requeue anything that hasn't been acked */
@@ -2290,12 +2366,13 @@ 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->flags)) {
+	    !test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		clear_bit(WRITE_PENDING, &con->flags);
-		set_bit(STANDBY, &con->state);
+		clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
+		con->state = CON_STATE_STANDBY;
 	} else {
 		/* retry after a delay. */
+		con->state = CON_STATE_PREOPEN;
 		if (con->delay == 0)
 			con->delay = BASE_DELAY_INTERVAL;
 		else if (con->delay < MAX_DELAY_INTERVAL)
@@ -2316,13 +2393,12 @@ static void ceph_fault(struct ceph_connection *con)
 			 * that when con_work restarts we schedule the
 			 * delay then.
 			 */
-			set_bit(BACKOFF, &con->flags);
+			set_bit(CON_FLAG_BACKOFF, &con->flags);
 		}
 	}
 
 out_unlock:
 	mutex_unlock(&con->mutex);
-out:
 	/*
 	 * in case we faulted due to authentication, invalidate our
 	 * current tickets so that we can get new ones.
@@ -2361,6 +2437,8 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 	encode_my_addr(msgr);
 	msgr->nocrc = nocrc;
 
+	atomic_set(&msgr->stopping, 0);
+
 	dout("%s %p\n", __func__, msgr);
 }
 EXPORT_SYMBOL(ceph_messenger_init);
@@ -2368,13 +2446,12 @@ EXPORT_SYMBOL(ceph_messenger_init);
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
-	if (test_and_clear_bit(STANDBY, &con->state)) {
-		mutex_lock(&con->mutex);
+	if (con->state == CON_STATE_STANDBY) {
 		dout("clear_standby %p and ++connect_seq\n", con);
+		con->state = CON_STATE_PREOPEN;
 		con->connect_seq++;
-		WARN_ON(test_bit(WRITE_PENDING, &con->flags));
-		WARN_ON(test_bit(KEEPALIVE_PENDING, &con->flags));
-		mutex_unlock(&con->mutex);
+		WARN_ON(test_bit(CON_FLAG_WRITE_PENDING, &con->flags));
+		WARN_ON(test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags));
 	}
 }
 
@@ -2383,24 +2460,22 @@ static void clear_standby(struct ceph_connection *con)
  */
 void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 {
-	if (test_bit(CLOSED, &con->state)) {
-		dout("con_send %p closed, dropping %p\n", con, msg);
-		ceph_msg_put(msg);
-		return;
-	}
-
 	/* set src+dst */
 	msg->hdr.src = con->msgr->inst.name;
-
 	BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len));
-
 	msg->needs_out_seq = true;
 
-	/* queue */
 	mutex_lock(&con->mutex);
 
+	if (con->state == CON_STATE_CLOSED) {
+		dout("con_send %p closed, dropping %p\n", con, msg);
+		ceph_msg_put(msg);
+		mutex_unlock(&con->mutex);
+		return;
+	}
+
 	BUG_ON(msg->con != NULL);
-	msg->con = ceph_con_get(con);
+	msg->con = con->ops->get(con);
 	BUG_ON(msg->con == NULL);
 
 	BUG_ON(!list_empty(&msg->list_head));
@@ -2411,12 +2486,13 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 	     le32_to_cpu(msg->hdr.front_len),
 	     le32_to_cpu(msg->hdr.middle_len),
 	     le32_to_cpu(msg->hdr.data_len));
+
+	clear_standby(con);
 	mutex_unlock(&con->mutex);
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
-	clear_standby(con);
-	if (test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
+	if (test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);
@@ -2436,7 +2512,7 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 		dout("%s %p msg %p - was on queue\n", __func__, con, msg);
 		list_del_init(&msg->list_head);
 		BUG_ON(msg->con == NULL);
-		ceph_con_put(msg->con);
+		msg->con->ops->put(msg->con);
 		msg->con = NULL;
 		msg->hdr.seq = 0;
 
@@ -2502,9 +2578,11 @@ void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 void ceph_con_keepalive(struct ceph_connection *con)
 {
 	dout("con_keepalive %p\n", con);
+	mutex_lock(&con->mutex);
 	clear_standby(con);
-	if (test_and_set_bit(KEEPALIVE_PENDING, &con->flags) == 0 &&
-	    test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
+	mutex_unlock(&con->mutex);
+	if (test_and_set_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags) == 0 &&
+	    test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);
@@ -2646,7 +2724,7 @@ static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
 		con->in_msg = con->ops->alloc_msg(con, hdr, &skip);
 		mutex_lock(&con->mutex);
 		if (con->in_msg) {
-			con->in_msg->con = ceph_con_get(con);
+			con->in_msg->con = con->ops->get(con);
 			BUG_ON(con->in_msg->con == NULL);
 		}
 		if (skip)
@@ -2662,7 +2740,7 @@ static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
 			       type, front_len);
 			return false;
 		}
-		con->in_msg->con = ceph_con_get(con);
+		con->in_msg->con = con->ops->get(con);
 		BUG_ON(con->in_msg->con == NULL);
 		con->in_msg->page_alignment = le16_to_cpu(hdr->data_off);
 	}