diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 65665c9..8f428a8 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -499,7 +499,7 @@
 			 / sizeof (*ondisk))
 		return -EINVAL;
 	header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
-				snap_count * sizeof (*ondisk),
+				snap_count * sizeof(u64),
 				gfp_flags);
 	if (!header->snapc)
 		return -ENOMEM;
@@ -977,7 +977,7 @@
 	op = (void *)(replyhead + 1);
 	rc = le32_to_cpu(replyhead->result);
 	bytes = le64_to_cpu(op->extent.length);
-	read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ);
+	read_op = (le16_to_cpu(op->op) == CEPH_OSD_OP_READ);
 
 	dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc);
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 173b1d2..8b67304 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -54,7 +54,12 @@
 	(CONGESTION_ON_THRESH(congestion_kb) -				\
 	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))
 
-
+static inline struct ceph_snap_context *page_snap_context(struct page *page)
+{
+	if (PagePrivate(page))
+		return (void *)page->private;
+	return NULL;
+}
 
 /*
  * Dirty a page.  Optimistically adjust accounting, on the assumption
@@ -142,10 +147,9 @@
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
-	struct ceph_snap_context *snapc = (void *)page->private;
+	struct ceph_snap_context *snapc = page_snap_context(page);
 
 	BUG_ON(!PageLocked(page));
-	BUG_ON(!page->private);
 	BUG_ON(!PagePrivate(page));
 	BUG_ON(!page->mapping);
 
@@ -182,7 +186,6 @@
 	struct inode *inode = page->mapping ? page->mapping->host : NULL;
 	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
 	WARN_ON(PageDirty(page));
-	WARN_ON(page->private);
 	WARN_ON(PagePrivate(page));
 	return 0;
 }
@@ -443,7 +446,7 @@
 	osdc = &fsc->client->osdc;
 
 	/* verify this is a writeable snap context */
-	snapc = (void *)page->private;
+	snapc = page_snap_context(page);
 	if (snapc == NULL) {
 		dout("writepage %p page %p not dirty?\n", inode, page);
 		goto out;
@@ -451,7 +454,7 @@
 	oldest = get_oldest_context(inode, &snap_size);
 	if (snapc->seq > oldest->seq) {
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
-		     inode, page, (void *)page->private);
+		     inode, page, snapc);
 		/* we should only noop if called by kswapd */
 		WARN_ON((current->flags & PF_MEMALLOC) == 0);
 		ceph_put_snap_context(oldest);
@@ -591,7 +594,7 @@
 			clear_bdi_congested(&fsc->backing_dev_info,
 					    BLK_RW_ASYNC);
 
-		ceph_put_snap_context((void *)page->private);
+		ceph_put_snap_context(page_snap_context(page));
 		page->private = 0;
 		ClearPagePrivate(page);
 		dout("unlocking %d %p\n", i, page);
@@ -795,7 +798,7 @@
 			}
 
 			/* only if matching snap context */
-			pgsnapc = (void *)page->private;
+			pgsnapc = page_snap_context(page);
 			if (pgsnapc->seq > snapc->seq) {
 				dout("page snapc %p %lld > oldest %p %lld\n",
 				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
@@ -984,7 +987,7 @@
 	BUG_ON(!ci->i_snap_realm);
 	down_read(&mdsc->snap_rwsem);
 	BUG_ON(!ci->i_snap_realm->cached_context);
-	snapc = (void *)page->private;
+	snapc = page_snap_context(page);
 	if (snapc && snapc != ci->i_head_snapc) {
 		/*
 		 * this page is already dirty in another (older) snap
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 200bc87..ecd7f15 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -394,11 +394,8 @@
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
-	s->s_con.private = s;
-	s->s_con.ops = &mds_con_ops;
-	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
-	s->s_con.peer_name.num = cpu_to_le64(mds);
+	ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr,
+		CEPH_ENTITY_TYPE_MDS, mds);
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index e71d683..98ec36a 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -132,7 +132,7 @@
 	u32 supported_features;
 	u32 required_features;
 
-	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_messenger msgr;   /* messenger instance */
 	struct ceph_mon_client monc;
 	struct ceph_osd_client osdc;
 
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 2521a95..a334dbd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -31,9 +31,6 @@
 	int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
 	int (*invalidate_authorizer)(struct ceph_connection *con);
 
-	/* protocol version mismatch */
-	void (*bad_proto) (struct ceph_connection *con);
-
 	/* there was some error on the socket (disconnect, whatever) */
 	void (*fault) (struct ceph_connection *con);
 
@@ -80,7 +77,10 @@
 	unsigned nr_pages;              /* size of page array */
 	unsigned page_alignment;        /* io offset in first page */
 	struct ceph_pagelist *pagelist; /* instead of pages */
+
+	struct ceph_connection *con;
 	struct list_head list_head;
+
 	struct kref kref;
 	struct bio  *bio;		/* instead of pages/pagelist */
 	struct bio  *bio_iter;		/* bio iterator */
@@ -106,21 +106,25 @@
 #define MAX_DELAY_INTERVAL	(5 * 60 * HZ)
 
 /*
- * ceph_connection state bit flags
+ * ceph_connection flag bits
  */
+
 #define LOSSYTX         0  /* we can close channel or drop messages on errors */
-#define CONNECTING	1
-#define NEGOTIATING	2
 #define KEEPALIVE_PENDING      3
 #define WRITE_PENDING	4  /* we have data ready to send */
+#define SOCK_CLOSED	11 /* socket state changed to closed */
+#define BACKOFF         15
+
+/*
+ * ceph_connection states
+ */
+#define CONNECTING	1
+#define NEGOTIATING	2
 #define STANDBY		8  /* no outgoing messages, socket closed.  we keep
 			    * the ceph_connection around to maintain shared
 			    * state with the peer. */
 #define CLOSED		10 /* we've closed the connection */
-#define SOCK_CLOSED	11 /* socket state changed to closed */
 #define OPENING         13 /* open connection w/ (possibly new) peer */
-#define DEAD            14 /* dead, about to kfree */
-#define BACKOFF         15
 
 /*
  * A single connection with another host.
@@ -136,13 +140,18 @@
 	const struct ceph_connection_operations *ops;
 
 	struct ceph_messenger *msgr;
+
+	atomic_t sock_state;
 	struct socket *sock;
-	unsigned long state;	/* connection state (see flags above) */
+	struct ceph_entity_addr peer_addr; /* peer address */
+	struct ceph_entity_addr peer_addr_for_me;
+
+	unsigned long flags;
+	unsigned long state;
 	const char *error_msg;  /* error message, if any */
 
-	struct ceph_entity_addr peer_addr; /* peer address */
 	struct ceph_entity_name peer_name; /* peer name */
-	struct ceph_entity_addr peer_addr_for_me;
+
 	unsigned peer_features;
 	u32 connect_seq;      /* identify the most recent connection
 				 attempt for this connection, client */
@@ -215,21 +224,25 @@
 extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
 
-extern struct ceph_messenger *ceph_messenger_create(
-	struct ceph_entity_addr *myaddr,
-	u32 features, u32 required);
-extern void ceph_messenger_destroy(struct ceph_messenger *);
+extern void ceph_messenger_init(struct ceph_messenger *msgr,
+			struct ceph_entity_addr *myaddr,
+			u32 supported_features,
+			u32 required_features,
+			bool nocrc);
 
-extern void ceph_con_init(struct ceph_messenger *msgr,
-			  struct ceph_connection *con);
+extern 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);
 extern void ceph_con_open(struct ceph_connection *con,
 			  struct ceph_entity_addr *addr);
 extern bool ceph_con_opened(struct ceph_connection *con);
 extern void ceph_con_close(struct ceph_connection *con);
 extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke_message(struct ceph_connection *con,
-				  struct ceph_msg *msg);
+
+extern void ceph_msg_revoke(struct ceph_msg *msg);
+extern void ceph_msg_revoke_incoming(struct ceph_msg *msg);
+
 extern void ceph_con_keepalive(struct ceph_connection *con);
 extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
 extern void ceph_con_put(struct ceph_connection *con);
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index 545f859..2113e38 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -70,7 +70,7 @@
 	bool hunting;
 	int cur_mon;                       /* last monitor i contacted */
 	unsigned long sub_sent, sub_renew_after;
-	struct ceph_connection *con;
+	struct ceph_connection con;
 	bool have_fsid;
 
 	/* pending generic requests */
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index a776f75..58b09ef 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -468,19 +468,15 @@
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
-	client->msgr = ceph_messenger_create(myaddr,
-					     client->supported_features,
-					     client->required_features);
-	if (IS_ERR(client->msgr)) {
-		err = PTR_ERR(client->msgr);
-		goto fail;
-	}
-	client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	ceph_messenger_init(&client->msgr, myaddr,
+		client->supported_features,
+		client->required_features,
+		ceph_test_opt(client, NOCRC));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);
 	if (err < 0)
-		goto fail_msgr;
+		goto fail;
 	err = ceph_osdc_init(&client->osdc, client);
 	if (err < 0)
 		goto fail_monc;
@@ -489,8 +485,6 @@
 
 fail_monc:
 	ceph_monc_stop(&client->monc);
-fail_msgr:
-	ceph_messenger_destroy(client->msgr);
 fail:
 	kfree(client);
 	return ERR_PTR(err);
@@ -504,19 +498,10 @@
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
 
-	/*
-	 * make sure osd connections close out before destroying the
-	 * auth module, which is needed to free those connections'
-	 * ceph_authorizers.
-	 */
-	ceph_msgr_flush();
-
 	ceph_monc_stop(&client->monc);
 
 	ceph_debugfs_client_cleanup(client);
 
-	ceph_messenger_destroy(client->msgr);
-
 	ceph_destroy_options(client->options);
 
 	kfree(client);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 524f4e4..5e9f61d 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;
@@ -147,52 +155,101 @@
 }
 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
  */
 
 /* data available on socket, or listen socket received a connect */
-static void ceph_data_ready(struct sock *sk, int count_unused)
+static void ceph_sock_data_ready(struct sock *sk, int count_unused)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
-		dout("ceph_data_ready on %p state = %lu, queueing work\n",
+		dout("%s on %p state = %lu, queueing work\n", __func__,
 		     con, con->state);
 		queue_con(con);
 	}
 }
 
 /* socket has buffer space for writing */
-static void ceph_write_space(struct sock *sk)
+static void ceph_sock_write_space(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
 	/* only queue to workqueue if there is data we want to write,
 	 * and there is sufficient space in the socket buffer to accept
-	 * more data.  clear SOCK_NOSPACE so that ceph_write_space()
+	 * more data.  clear SOCK_NOSPACE so that ceph_sock_write_space()
 	 * doesn't get called again until try_write() fills the socket
 	 * 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("ceph_write_space %p queueing write work\n", con);
+			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 			queue_con(con);
 		}
 	} else {
-		dout("ceph_write_space %p nothing to write\n", con);
+		dout("%s %p nothing to write\n", __func__, con);
 	}
 }
 
 /* socket's state has changed */
-static void ceph_state_change(struct sock *sk)
+static void ceph_sock_state_change(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
-	dout("ceph_state_change %p state = %lu sk_state = %u\n",
+	dout("%s %p state = %lu sk_state = %u\n", __func__,
 	     con, con->state, sk->sk_state);
 
 	if (test_bit(CLOSED, &con->state))
@@ -200,10 +257,11 @@
 
 	switch (sk->sk_state) {
 	case TCP_CLOSE:
-		dout("ceph_state_change TCP_CLOSE\n");
+		dout("%s TCP_CLOSE\n", __func__);
 	case TCP_CLOSE_WAIT:
-		dout("ceph_state_change TCP_CLOSE_WAIT\n");
-		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
+		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
@@ -212,7 +270,8 @@
 		}
 		break;
 	case TCP_ESTABLISHED:
-		dout("ceph_state_change TCP_ESTABLISHED\n");
+		dout("%s TCP_ESTABLISHED\n", __func__);
+		con_sock_state_connected(con);
 		queue_con(con);
 		break;
 	default:	/* Everything else is uninteresting */
@@ -228,9 +287,9 @@
 {
 	struct sock *sk = sock->sk;
 	sk->sk_user_data = con;
-	sk->sk_data_ready = ceph_data_ready;
-	sk->sk_write_space = ceph_write_space;
-	sk->sk_state_change = ceph_state_change;
+	sk->sk_data_ready = ceph_sock_data_ready;
+	sk->sk_write_space = ceph_sock_write_space;
+	sk->sk_state_change = ceph_sock_state_change;
 }
 
 
@@ -262,6 +321,7 @@
 
 	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 @@
 		return ret;
 	}
 	con->sock = sock;
-
 	return 0;
 }
 
@@ -343,6 +402,7 @@
 	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 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 @@
 	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 @@
 {
 	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 @@
 {
 	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 @@
 /*
  * 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);
 
@@ -486,14 +569,14 @@
 	return ret;
 }
 
-static void ceph_con_out_kvec_reset(struct ceph_connection *con)
+static void con_out_kvec_reset(struct ceph_connection *con)
 {
 	con->out_kvec_left = 0;
 	con->out_kvec_bytes = 0;
 	con->out_kvec_cur = &con->out_kvec[0];
 }
 
-static void ceph_con_out_kvec_add(struct ceph_connection *con,
+static void con_out_kvec_add(struct ceph_connection *con,
 				size_t size, void *data)
 {
 	int index;
@@ -534,7 +617,7 @@
 	struct ceph_msg *m;
 	u32 crc;
 
-	ceph_con_out_kvec_reset(con);
+	con_out_kvec_reset(con);
 	con->out_kvec_is_msg = true;
 	con->out_msg_done = false;
 
@@ -542,14 +625,16 @@
 	 * TCP packet that's a good thing. */
 	if (con->in_seq > con->in_seq_acked) {
 		con->in_seq_acked = con->in_seq;
-		ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+		con_out_kvec_add(con, sizeof (con->out_temp_ack),
 			&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 @@
 		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),
@@ -572,12 +661,12 @@
 	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
 
 	/* tag + hdr + front + middle */
-	ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-	ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
-	ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+	con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
+	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
 
 	if (m->middle)
-		ceph_con_out_kvec_add(con, m->middle->vec.iov_len,
+		con_out_kvec_add(con, m->middle->vec.iov_len,
 			m->middle->vec.iov_base);
 
 	/* fill in crc (except data pages), footer */
@@ -614,7 +703,7 @@
 		prepare_write_message_footer(con);
 	}
 
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -626,16 +715,16 @@
 	     con->in_seq_acked, con->in_seq);
 	con->in_seq_acked = con->in_seq;
 
-	ceph_con_out_kvec_reset(con);
+	con_out_kvec_reset(con);
 
-	ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 
 	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+	con_out_kvec_add(con, sizeof (con->out_temp_ack),
 				&con->out_temp_ack);
 
 	con->out_more = 1;  /* more will follow.. eventually.. */
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -644,9 +733,9 @@
 static void prepare_write_keepalive(struct ceph_connection *con)
 {
 	dout("prepare_write_keepalive %p\n", con);
-	ceph_con_out_kvec_reset(con);
-	ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
-	set_bit(WRITE_PENDING, &con->state);
+	con_out_kvec_reset(con);
+	con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
+	set_bit(WRITE_PENDING, &con->flags);
 }
 
 /*
@@ -675,7 +764,7 @@
 
 	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;
@@ -690,12 +779,12 @@
  */
 static void prepare_write_banner(struct ceph_connection *con)
 {
-	ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
-	ceph_con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
+	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
 					&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)
@@ -738,14 +827,14 @@
 	con->out_connect.authorizer_len = auth ?
 		cpu_to_le32(auth->authorizer_buf_len) : 0;
 
-	ceph_con_out_kvec_add(con, sizeof (con->out_connect),
+	con_out_kvec_add(con, sizeof (con->out_connect),
 					&con->out_connect);
 	if (auth && auth->authorizer_buf_len)
-		ceph_con_out_kvec_add(con, auth->authorizer_buf_len,
+		con_out_kvec_add(con, auth->authorizer_buf_len,
 					auth->authorizer_buf);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(WRITE_PENDING, &con->flags);
 
 	return 0;
 }
@@ -935,7 +1024,7 @@
 	/* prepare and queue up footer, too */
 	if (!do_datacrc)
 		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
-	ceph_con_out_kvec_reset(con);
+	con_out_kvec_reset(con);
 	prepare_write_message_footer(con);
 	ret = 1;
 out:
@@ -1356,11 +1445,6 @@
 {
 	reset_connection(con);
 	set_bit(CLOSED, &con->state);  /* in case there's queued work */
-
-	mutex_unlock(&con->mutex);
-	if (con->ops->bad_proto)
-		con->ops->bad_proto(con);
-	mutex_lock(&con->mutex);
 }
 
 static int process_connect(struct ceph_connection *con)
@@ -1403,7 +1487,7 @@
 			return -1;
 		}
 		con->auth_retry = 1;
-		ceph_con_out_kvec_reset(con);
+		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1424,7 +1508,7 @@
 		       ENTITY_NAME(con->peer_name),
 		       ceph_pr_addr(&con->peer_addr.in_addr));
 		reset_connection(con);
-		ceph_con_out_kvec_reset(con);
+		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1450,7 +1534,7 @@
 		     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);
-		ceph_con_out_kvec_reset(con);
+		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1467,7 +1551,7 @@
 		     le32_to_cpu(con->in_connect.global_seq));
 		get_global_seq(con->msgr,
 			       le32_to_cpu(con->in_connect.global_seq));
-		ceph_con_out_kvec_reset(con);
+		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
@@ -1497,7 +1581,7 @@
 			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;
@@ -1583,9 +1667,8 @@
 	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,
@@ -1668,7 +1751,6 @@
 	int ret;
 	unsigned int front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
-	int skip;
 	u64 seq;
 	u32 crc;
 
@@ -1721,9 +1803,7 @@
 	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);
@@ -1738,6 +1818,8 @@
 				"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)
@@ -1833,8 +1915,11 @@
 {
 	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)
@@ -1874,14 +1959,15 @@
 
 	/* open the socket first? */
 	if (con->sock == NULL) {
-		ceph_con_out_kvec_reset(con);
+		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;
@@ -1938,14 +2024,14 @@
 			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:
@@ -2087,12 +2173,6 @@
  */
 static void queue_con(struct ceph_connection *con)
 {
-	if (test_bit(DEAD, &con->state)) {
-		dout("queue_con %p ignoring: DEAD\n",
-		     con);
-		return;
-	}
-
 	if (!con->ops->get(con)) {
 		dout("queue_con %p ref count 0\n", con);
 		return;
@@ -2117,7 +2197,7 @@
 
 	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))) {
@@ -2146,7 +2226,7 @@
 		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);
@@ -2185,7 +2265,7 @@
 	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;
 	}
@@ -2197,8 +2277,11 @@
 	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 */
@@ -2207,9 +2290,9 @@
 	/* 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. */
@@ -2233,7 +2316,7 @@
 			 * that when con_work restarts we schedule the
 			 * delay then.
 			 */
-			set_bit(BACKOFF, &con->state);
+			set_bit(BACKOFF, &con->flags);
 		}
 	}
 
@@ -2256,18 +2339,14 @@
 
 
 /*
- * 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;
 
@@ -2280,19 +2359,11 @@
 	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)
 {
@@ -2301,8 +2372,8 @@
 		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);
 	}
 }
@@ -2327,6 +2398,11 @@
 
 	/* 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,
@@ -2340,7 +2416,7 @@
 	/* 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);
@@ -2348,24 +2424,34 @@
 /*
  * 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);
 }
@@ -2373,17 +2459,27 @@
 /*
  * 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) {
+	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 -
@@ -2394,8 +2490,8 @@
 		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);
 }
@@ -2407,8 +2503,8 @@
 {
 	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);
@@ -2427,6 +2523,8 @@
 	if (m == NULL)
 		goto out;
 	kref_init(&m->kref);
+
+	m->con = NULL;
 	INIT_LIST_HEAD(&m->list_head);
 
 	m->hdr.tid = 0;
@@ -2522,46 +2620,63 @@
 }
 
 /*
- * 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;
 }
 
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 10d6008..e9db3de 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -106,9 +106,9 @@
 	monc->pending_auth = 1;
 	monc->m_auth->front.iov_len = len;
 	monc->m_auth->hdr.front_len = cpu_to_le32(len);
-	ceph_con_revoke(monc->con, monc->m_auth);
+	ceph_msg_revoke(monc->m_auth);
 	ceph_msg_get(monc->m_auth);  /* keep our ref */
-	ceph_con_send(monc->con, monc->m_auth);
+	ceph_con_send(&monc->con, monc->m_auth);
 }
 
 /*
@@ -117,8 +117,9 @@
 static void __close_session(struct ceph_mon_client *monc)
 {
 	dout("__close_session closing mon%d\n", monc->cur_mon);
-	ceph_con_revoke(monc->con, monc->m_auth);
-	ceph_con_close(monc->con);
+	ceph_msg_revoke(monc->m_auth);
+	ceph_con_close(&monc->con);
+	monc->con.private = NULL;
 	monc->cur_mon = -1;
 	monc->pending_auth = 0;
 	ceph_auth_reset(monc->auth);
@@ -141,10 +142,12 @@
 		monc->sub_renew_after = jiffies;  /* i.e., expired */
 		monc->want_next_osdmap = !!monc->want_next_osdmap;
 
+		ceph_con_init(&monc->con, monc, &mon_con_ops,
+			&monc->client->msgr,
+			CEPH_ENTITY_TYPE_MON, monc->cur_mon);
+
 		dout("open_session mon%d opening\n", monc->cur_mon);
-		monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON;
-		monc->con->peer_name.num = cpu_to_le64(monc->cur_mon);
-		ceph_con_open(monc->con,
+		ceph_con_open(&monc->con,
 			      &monc->monmap->mon_inst[monc->cur_mon].addr);
 
 		/* initiatiate authentication handshake */
@@ -226,8 +229,8 @@
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
-		ceph_con_revoke(monc->con, msg);
-		ceph_con_send(monc->con, ceph_msg_get(msg));
+		ceph_msg_revoke(msg);
+		ceph_con_send(&monc->con, ceph_msg_get(msg));
 
 		monc->sub_sent = jiffies | 1;  /* never 0 */
 	}
@@ -247,7 +250,7 @@
 	if (monc->hunting) {
 		pr_info("mon%d %s session established\n",
 			monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 		monc->hunting = false;
 	}
 	dout("handle_subscribe_ack after %d seconds\n", seconds);
@@ -439,6 +442,7 @@
 		m = NULL;
 	} else {
 		dout("get_generic_reply %lld got %p\n", tid, req->reply);
+		*skip = 0;
 		m = ceph_msg_get(req->reply);
 		/*
 		 * we don't need to track the connection reading into
@@ -461,7 +465,7 @@
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
-	ceph_con_send(monc->con, ceph_msg_get(req->request));
+	ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	mutex_unlock(&monc->mutex);
 
 	err = wait_for_completion_interruptible(&req->completion);
@@ -684,8 +688,8 @@
 
 	for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) {
 		req = rb_entry(p, struct ceph_mon_generic_request, node);
-		ceph_con_revoke(monc->con, req->request);
-		ceph_con_send(monc->con, ceph_msg_get(req->request));
+		ceph_msg_revoke(req->request);
+		ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	}
 }
 
@@ -705,7 +709,7 @@
 		__close_session(monc);
 		__open_session(monc);  /* continue hunting */
 	} else {
-		ceph_con_keepalive(monc->con);
+		ceph_con_keepalive(&monc->con);
 
 		__validate_auth(monc);
 
@@ -760,19 +764,12 @@
 		goto out;
 
 	/* connection */
-	monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL);
-	if (!monc->con)
-		goto out_monmap;
-	ceph_con_init(monc->client->msgr, monc->con);
-	monc->con->private = monc;
-	monc->con->ops = &mon_con_ops;
-
 	/* authentication */
 	monc->auth = ceph_auth_init(cl->options->name,
 				    cl->options->key);
 	if (IS_ERR(monc->auth)) {
 		err = PTR_ERR(monc->auth);
-		goto out_con;
+		goto out_monmap;
 	}
 	monc->auth->want_keys =
 		CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON |
@@ -824,8 +821,6 @@
 	ceph_msg_put(monc->m_subscribe_ack);
 out_auth:
 	ceph_auth_destroy(monc->auth);
-out_con:
-	monc->con->ops->put(monc->con);
 out_monmap:
 	kfree(monc->monmap);
 out:
@@ -841,12 +836,16 @@
 	mutex_lock(&monc->mutex);
 	__close_session(monc);
 
-	monc->con->private = NULL;
-	monc->con->ops->put(monc->con);
-	monc->con = NULL;
-
 	mutex_unlock(&monc->mutex);
 
+	/*
+	 * flush msgr queue before we destroy ourselves to ensure that:
+	 *  - any work that references our embedded con is finished.
+	 *  - any osd_client or other work that may reference an authorizer
+	 *    finishes before we shut down the auth subsystem.
+	 */
+	ceph_msgr_flush();
+
 	ceph_auth_destroy(monc->auth);
 
 	ceph_msg_put(monc->m_auth);
@@ -880,8 +879,8 @@
 	} else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) {
 		dout("authenticated, starting session\n");
 
-		monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
-		monc->client->msgr->inst.name.num =
+		monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
+		monc->client->msgr.inst.name.num =
 					cpu_to_le64(monc->auth->global_id);
 
 		__send_subscribe(monc);
@@ -992,6 +991,8 @@
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
+		if (!m)
+			return NULL;	/* ENOMEM--return skip == 0 */
 		break;
 	}
 
@@ -1021,7 +1022,7 @@
 	if (!monc->hunting)
 		pr_info("mon%d %s session lost, "
 			"hunting for new mon\n", monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 
 	__close_session(monc);
 	if (!monc->hunting) {
@@ -1036,9 +1037,23 @@
 	mutex_unlock(&monc->mutex);
 }
 
+/*
+ * We can ignore refcounting on the connection struct, as all references
+ * will come from the messenger workqueue, which is drained prior to
+ * mon_client destruction.
+ */
+static struct ceph_connection *con_get(struct ceph_connection *con)
+{
+	return con;
+}
+
+static void con_put(struct ceph_connection *con)
+{
+}
+
 static const struct ceph_connection_operations mon_con_ops = {
-	.get = ceph_con_get,
-	.put = ceph_con_put,
+	.get = con_get,
+	.put = con_put,
 	.dispatch = dispatch,
 	.fault = mon_fault,
 	.alloc_msg = mon_alloc_msg,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 1ffebed..db2da54 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -139,15 +139,14 @@
 
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
+	if (req->r_con_filling_msg) {
+		dout("%s revoking pages %p from con %p\n", __func__,
+		     req->r_pages, req->r_con_filling_msg);
+		ceph_msg_revoke_incoming(req->r_reply);
+		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
+	}
 	if (req->r_reply)
 		ceph_msg_put(req->r_reply);
-	if (req->r_con_filling_msg) {
-		dout("release_request revoking pages %p from con %p\n",
-		     req->r_pages, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg,
-				      req->r_reply);
-		ceph_con_put(req->r_con_filling_msg);
-	}
 	if (req->r_own_pages)
 		ceph_release_page_vector(req->r_pages,
 					 req->r_num_pages);
@@ -624,7 +623,7 @@
 /*
  * Track open sessions with osds.
  */
-static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
+static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
 {
 	struct ceph_osd *osd;
 
@@ -634,15 +633,14 @@
 
 	atomic_set(&osd->o_ref, 1);
 	osd->o_osdc = osdc;
+	osd->o_osd = onum;
 	INIT_LIST_HEAD(&osd->o_requests);
 	INIT_LIST_HEAD(&osd->o_linger_requests);
 	INIT_LIST_HEAD(&osd->o_osd_lru);
 	osd->o_incarnation = 1;
 
-	ceph_con_init(osdc->client->msgr, &osd->o_con);
-	osd->o_con.private = osd;
-	osd->o_con.ops = &osd_con_ops;
-	osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD;
+	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr,
+		CEPH_ENTITY_TYPE_OSD, onum);
 
 	INIT_LIST_HEAD(&osd->o_keepalive_item);
 	return osd;
@@ -853,7 +851,7 @@
 
 	if (req->r_osd) {
 		/* make sure the original request isn't in flight. */
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 
 		list_del_init(&req->r_osd_item);
 		if (list_empty(&req->r_osd->o_requests) &&
@@ -880,7 +878,7 @@
 static void __cancel_request(struct ceph_osd_request *req)
 {
 	if (req->r_sent && req->r_osd) {
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 		req->r_sent = 0;
 	}
 }
@@ -998,15 +996,13 @@
 	req->r_osd = __lookup_osd(osdc, o);
 	if (!req->r_osd && o >= 0) {
 		err = -ENOMEM;
-		req->r_osd = create_osd(osdc);
+		req->r_osd = create_osd(osdc, o);
 		if (!req->r_osd) {
 			list_move(&req->r_req_lru_item, &osdc->req_notarget);
 			goto out;
 		}
 
 		dout("map_request osd %p is osd%d\n", req->r_osd, o);
-		req->r_osd->o_osd = o;
-		req->r_osd->o_con.peer_name.num = cpu_to_le64(o);
 		__insert_osd(osdc, req->r_osd);
 
 		ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]);
@@ -1216,7 +1212,7 @@
 	if (req->r_con_filling_msg == con && req->r_reply == msg) {
 		dout(" dropping con_filling_msg ref %p\n", con);
 		req->r_con_filling_msg = NULL;
-		ceph_con_put(con);
+		con->ops->put(con);
 	}
 
 	if (!req->r_got_reply) {
@@ -1391,7 +1387,7 @@
 			     epoch, maplen);
 			newmap = osdmap_apply_incremental(&p, next,
 							  osdc->osdmap,
-							  osdc->client->msgr);
+							  &osdc->client->msgr);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;
@@ -2025,10 +2021,10 @@
 	}
 
 	if (req->r_con_filling_msg) {
-		dout("get_reply revoking msg %p from old con %p\n",
+		dout("%s revoking msg %p from old con %p\n", __func__,
 		     req->r_reply, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply);
-		ceph_con_put(req->r_con_filling_msg);
+		ceph_msg_revoke_incoming(req->r_reply);
+		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
 		req->r_con_filling_msg = NULL;
 	}
 
@@ -2063,7 +2059,7 @@
 #endif
 	}
 	*skip = 0;
-	req->r_con_filling_msg = ceph_con_get(con);
+	req->r_con_filling_msg = con->ops->get(con);
 	dout("get_reply tid %lld %p\n", tid, m);
 
 out:
@@ -2080,6 +2076,7 @@
 	int type = le16_to_cpu(hdr->type);
 	int front = le32_to_cpu(hdr->front_len);
 
+	*skip = 0;
 	switch (type) {
 	case CEPH_MSG_OSD_MAP:
 	case CEPH_MSG_WATCH_NOTIFY:
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 81e3b84..9600674 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -488,15 +488,16 @@
 		ceph_decode_32_safe(p, end, pool, bad);
 		ceph_decode_32_safe(p, end, len, bad);
 		dout("  pool %d len %d\n", pool, len);
+		ceph_decode_need(p, end, len, bad);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (pi) {
+			char *name = kstrndup(*p, len, GFP_NOFS);
+
+			if (!name)
+				return -ENOMEM;
 			kfree(pi->name);
-			pi->name = kmalloc(len + 1, GFP_NOFS);
-			if (pi->name) {
-				memcpy(pi->name, *p, len);
-				pi->name[len] = '\0';
-				dout("  name is %s\n", pi->name);
-			}
+			pi->name = name;
+			dout("  name is %s\n", pi->name);
 		}
 		*p += len;
 	}
@@ -666,6 +667,9 @@
 		ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
 		ceph_decode_copy(p, &pgid, sizeof(pgid));
 		n = ceph_decode_32(p);
+		err = -EINVAL;
+		if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
+			goto bad;
 		ceph_decode_need(p, end, n * sizeof(u32), bad);
 		err = -ENOMEM;
 		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
@@ -889,6 +893,10 @@
 			(void) __remove_pg_mapping(&map->pg_temp, pgid);
 
 			/* insert */
+			if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) {
+				err = -EINVAL;
+				goto bad;
+			}
 			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
 			if (!pg) {
 				err = -ENOMEM;