1 files changed, 2453 insertions, 0 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
new file mode 100644
index 00000000000..0e8157ee5d4
--- /dev/null
+++ b/net/ceph/messenger.c
@@ -0,0 +1,2453 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/crc32c.h>
+#include <linux/ctype.h>
+#include <linux/highmem.h>
+#include <linux/inet.h>
+#include <linux/kthread.h>
+#include <linux/net.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/string.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <net/tcp.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
+
+/*
+ * Ceph uses the messenger to exchange ceph_msg messages with other
+ * hosts in the system.  The messenger provides ordered and reliable
+ * delivery.  We tolerate TCP disconnects by reconnecting (with
+ * exponential backoff) in the case of a fault (disconnection, bad
+ * crc, protocol error).  Acks allow sent messages to be discarded by
+ * the sender.
+ */
+
+/* static tag bytes (protocol control messages) */
+static char tag_msg = CEPH_MSGR_TAG_MSG;
+static char tag_ack = CEPH_MSGR_TAG_ACK;
+static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
+
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key socket_class;
+#endif
+
+
+static void queue_con(struct ceph_connection *con);
+static void con_work(struct work_struct *);
+static void ceph_fault(struct ceph_connection *con);
+
+/*
+ * nicely render a sockaddr as a string.
+ */
+#define MAX_ADDR_STR 20
+#define MAX_ADDR_STR_LEN 60
+static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
+static DEFINE_SPINLOCK(addr_str_lock);
+static int last_addr_str;
+
+const char *ceph_pr_addr(const struct sockaddr_storage *ss)
+{
+	int i;
+	char *s;
+	struct sockaddr_in *in4 = (void *)ss;
+	struct sockaddr_in6 *in6 = (void *)ss;
+
+	spin_lock(&addr_str_lock);
+	i = last_addr_str++;
+	if (last_addr_str == MAX_ADDR_STR)
+		last_addr_str = 0;
+	spin_unlock(&addr_str_lock);
+	s = addr_str[i];
+
+	switch (ss->ss_family) {
+	case AF_INET:
+		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr,
+			 (unsigned int)ntohs(in4->sin_port));
+		break;
+
+	case AF_INET6:
+		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr,
+			 (unsigned int)ntohs(in6->sin6_port));
+		break;
+
+	default:
+		sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family);
+	}
+
+	return s;
+}
+EXPORT_SYMBOL(ceph_pr_addr);
+
+static void encode_my_addr(struct ceph_messenger *msgr)
+{
+	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
+	ceph_encode_addr(&msgr->my_enc_addr);
+}
+
+/*
+ * work queue for all reading and writing to/from the socket.
+ */
+struct workqueue_struct *ceph_msgr_wq;
+
+int ceph_msgr_init(void)
+{
+	ceph_msgr_wq = create_workqueue("ceph-msgr");
+	if (IS_ERR(ceph_msgr_wq)) {
+		int ret = PTR_ERR(ceph_msgr_wq);
+		pr_err("msgr_init failed to create workqueue: %d\n", ret);
+		ceph_msgr_wq = NULL;
+		return ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_msgr_init);
+
+void ceph_msgr_exit(void)
+{
+	destroy_workqueue(ceph_msgr_wq);
+}
+EXPORT_SYMBOL(ceph_msgr_exit);
+
+void ceph_msgr_flush(void)
+{
+	flush_workqueue(ceph_msgr_wq);
+}
+EXPORT_SYMBOL(ceph_msgr_flush);
+
+
+/*
+ * socket callback functions
+ */
+
+/* data available on socket, or listen socket received a connect */
+static void ceph_data_ready(struct sock *sk, int count_unused)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+	if (sk->sk_state != TCP_CLOSE_WAIT) {
+		dout("ceph_data_ready on %p state = %lu, queueing work\n",
+		     con, con->state);
+		queue_con(con);
+	}
+}
+
+/* socket has buffer space for writing */
+static void ceph_write_space(struct sock *sk)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+
+	/* only queue to workqueue if there is data we want to write. */
+	if (test_bit(WRITE_PENDING, &con->state)) {
+		dout("ceph_write_space %p queueing write work\n", con);
+		queue_con(con);
+	} else {
+		dout("ceph_write_space %p nothing to write\n", con);
+	}
+
+	/* since we have our own write_space, clear the SOCK_NOSPACE flag */
+	clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+}
+
+/* socket's state has changed */
+static void ceph_state_change(struct sock *sk)
+{
+	struct ceph_connection *con =
+		(struct ceph_connection *)sk->sk_user_data;
+
+	dout("ceph_state_change %p state = %lu sk_state = %u\n",
+	     con, con->state, sk->sk_state);
+
+	if (test_bit(CLOSED, &con->state))
+		return;
+
+	switch (sk->sk_state) {
+	case TCP_CLOSE:
+		dout("ceph_state_change TCP_CLOSE\n");
+	case TCP_CLOSE_WAIT:
+		dout("ceph_state_change TCP_CLOSE_WAIT\n");
+		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
+			if (test_bit(CONNECTING, &con->state))
+				con->error_msg = "connection failed";
+			else
+				con->error_msg = "socket closed";
+			queue_con(con);
+		}
+		break;
+	case TCP_ESTABLISHED:
+		dout("ceph_state_change TCP_ESTABLISHED\n");
+		queue_con(con);
+		break;
+	}
+}
+
+/*
+ * set up socket callbacks
+ */
+static void set_sock_callbacks(struct socket *sock,
+			       struct ceph_connection *con)
+{
+	struct sock *sk = sock->sk;
+	sk->sk_user_data = (void *)con;
+	sk->sk_data_ready = ceph_data_ready;
+	sk->sk_write_space = ceph_write_space;
+	sk->sk_state_change = ceph_state_change;
+}
+
+
+/*
+ * socket helpers
+ */
+
+/*
+ * initiate connection to a remote socket.
+ */
+static struct socket *ceph_tcp_connect(struct ceph_connection *con)
+{
+	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
+	struct socket *sock;
+	int ret;
+
+	BUG_ON(con->sock);
+	ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM,
+			       IPPROTO_TCP, &sock);
+	if (ret)
+		return ERR_PTR(ret);
+	con->sock = sock;
+	sock->sk->sk_allocation = GFP_NOFS;
+
+#ifdef CONFIG_LOCKDEP
+	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
+#endif
+
+	set_sock_callbacks(sock, con);
+
+	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
+
+	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
+				 O_NONBLOCK);
+	if (ret == -EINPROGRESS) {
+		dout("connect %s EINPROGRESS sk_state = %u\n",
+		     ceph_pr_addr(&con->peer_addr.in_addr),
+		     sock->sk->sk_state);
+		ret = 0;
+	}
+	if (ret < 0) {
+		pr_err("connect %s error %d\n",
+		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
+		sock_release(sock);
+		con->sock = NULL;
+		con->error_msg = "connect error";
+	}
+
+	if (ret < 0)
+		return ERR_PTR(ret);
+	return sock;
+}
+
+static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
+{
+	struct kvec iov = {buf, len};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+
+	return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
+}
+
+/*
+ * write something.  @more is true if caller will be sending more data
+ * shortly.
+ */
+static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
+		     size_t kvlen, size_t len, int more)
+{
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+
+	if (more)
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
+
+	return kernel_sendmsg(sock, &msg, iov, kvlen, len);
+}
+
+
+/*
+ * Shutdown/close the socket for the given connection.
+ */
+static int con_close_socket(struct ceph_connection *con)
+{
+	int rc;
+
+	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);
+	return rc;
+}
+
+/*
+ * Reset a connection.  Discard all incoming and outgoing messages
+ * and clear *_seq state.
+ */
+static void ceph_msg_remove(struct ceph_msg *msg)
+{
+	list_del_init(&msg->list_head);
+	ceph_msg_put(msg);
+}
+static void ceph_msg_remove_list(struct list_head *head)
+{
+	while (!list_empty(head)) {
+		struct ceph_msg *msg = list_first_entry(head, struct ceph_msg,
+							list_head);
+		ceph_msg_remove(msg);
+	}
+}
+
+static void reset_connection(struct ceph_connection *con)
+{
+	/* reset connection, out_queue, msg_ and connect_seq */
+	/* discard existing out_queue and msg_seq */
+	ceph_msg_remove_list(&con->out_queue);
+	ceph_msg_remove_list(&con->out_sent);
+
+	if (con->in_msg) {
+		ceph_msg_put(con->in_msg);
+		con->in_msg = NULL;
+	}
+
+	con->connect_seq = 0;
+	con->out_seq = 0;
+	if (con->out_msg) {
+		ceph_msg_put(con->out_msg);
+		con->out_msg = NULL;
+	}
+	con->out_keepalive_pending = false;
+	con->in_seq = 0;
+	con->in_seq_acked = 0;
+}
+
+/*
+ * mark a peer down.  drop any open connections.
+ */
+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(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);
+	mutex_lock(&con->mutex);
+	reset_connection(con);
+	con->peer_global_seq = 0;
+	cancel_delayed_work(&con->work);
+	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)
+{
+	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
+	set_bit(OPENING, &con->state);
+	clear_bit(CLOSED, &con->state);
+	memcpy(&con->peer_addr, addr, sizeof(*addr));
+	con->delay = 0;      /* reset backoff memory */
+	queue_con(con);
+}
+EXPORT_SYMBOL(ceph_con_open);
+
+/*
+ * return true if this connection ever successfully opened
+ */
+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)
+{
+	dout("con_get %p nref = %d -> %d\n", con,
+	     atomic_read(&con->nref), atomic_read(&con->nref) + 1);
+	if (atomic_inc_not_zero(&con->nref))
+		return con;
+	return NULL;
+}
+
+void ceph_con_put(struct ceph_connection *con)
+{
+	dout("con_put %p nref = %d -> %d\n", con,
+	     atomic_read(&con->nref), atomic_read(&con->nref) - 1);
+	BUG_ON(atomic_read(&con->nref) == 0);
+	if (atomic_dec_and_test(&con->nref)) {
+		BUG_ON(con->sock);
+		kfree(con);
+	}
+}
+
+/*
+ * initialize a new connection.
+ */
+void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
+{
+	dout("con_init %p\n", con);
+	memset(con, 0, sizeof(*con));
+	atomic_set(&con->nref, 1);
+	con->msgr = msgr;
+	mutex_init(&con->mutex);
+	INIT_LIST_HEAD(&con->out_queue);
+	INIT_LIST_HEAD(&con->out_sent);
+	INIT_DELAYED_WORK(&con->work, con_work);
+}
+EXPORT_SYMBOL(ceph_con_init);
+
+
+/*
+ * We maintain a global counter to order connection attempts.  Get
+ * a unique seq greater than @gt.
+ */
+static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
+{
+	u32 ret;
+
+	spin_lock(&msgr->global_seq_lock);
+	if (msgr->global_seq < gt)
+		msgr->global_seq = gt;
+	ret = ++msgr->global_seq;
+	spin_unlock(&msgr->global_seq_lock);
+	return ret;
+}
+
+
+/*
+ * Prepare footer for currently outgoing message, and finish things
+ * off.  Assumes out_kvec* are already valid.. we just add on to the end.
+ */
+static void prepare_write_message_footer(struct ceph_connection *con, int v)
+{
+	struct ceph_msg *m = con->out_msg;
+
+	dout("prepare_write_message_footer %p\n", con);
+	con->out_kvec_is_msg = true;
+	con->out_kvec[v].iov_base = &m->footer;
+	con->out_kvec[v].iov_len = sizeof(m->footer);
+	con->out_kvec_bytes += sizeof(m->footer);
+	con->out_kvec_left++;
+	con->out_more = m->more_to_follow;
+	con->out_msg_done = true;
+}
+
+/*
+ * Prepare headers for the next outgoing message.
+ */
+static void prepare_write_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m;
+	int v = 0;
+
+	con->out_kvec_bytes = 0;
+	con->out_kvec_is_msg = true;
+	con->out_msg_done = false;
+
+	/* Sneak an ack in there first?  If we can get it into the same
+	 * TCP packet that's a good thing. */
+	if (con->in_seq > con->in_seq_acked) {
+		con->in_seq_acked = con->in_seq;
+		con->out_kvec[v].iov_base = &tag_ack;
+		con->out_kvec[v++].iov_len = 1;
+		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+		con->out_kvec[v].iov_base = &con->out_temp_ack;
+		con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack);
+		con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
+	}
+
+	m = list_first_entry(&con->out_queue,
+		       struct ceph_msg, list_head);
+	con->out_msg = m;
+	if (test_bit(LOSSYTX, &con->state)) {
+		list_del_init(&m->list_head);
+	} else {
+		/* put message on sent list */
+		ceph_msg_get(m);
+		list_move_tail(&m->list_head, &con->out_sent);
+	}
+
+	/*
+	 * only assign outgoing seq # if we haven't sent this message
+	 * yet.  if it is requeued, resend with it's original seq.
+	 */
+	if (m->needs_out_seq) {
+		m->hdr.seq = cpu_to_le64(++con->out_seq);
+		m->needs_out_seq = false;
+	}
+
+	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),
+	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
+	     le32_to_cpu(m->hdr.data_len),
+	     m->nr_pages);
+	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
+
+	/* tag + hdr + front + middle */
+	con->out_kvec[v].iov_base = &tag_msg;
+	con->out_kvec[v++].iov_len = 1;
+	con->out_kvec[v].iov_base = &m->hdr;
+	con->out_kvec[v++].iov_len = sizeof(m->hdr);
+	con->out_kvec[v++] = m->front;
+	if (m->middle)
+		con->out_kvec[v++] = m->middle->vec;
+	con->out_kvec_left = v;
+	con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len +
+		(m->middle ? m->middle->vec.iov_len : 0);
+	con->out_kvec_cur = con->out_kvec;
+
+	/* fill in crc (except data pages), footer */
+	con->out_msg->hdr.crc =
+		cpu_to_le32(crc32c(0, (void *)&m->hdr,
+				      sizeof(m->hdr) - sizeof(m->hdr.crc)));
+	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
+	con->out_msg->footer.front_crc =
+		cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len));
+	if (m->middle)
+		con->out_msg->footer.middle_crc =
+			cpu_to_le32(crc32c(0, m->middle->vec.iov_base,
+					   m->middle->vec.iov_len));
+	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",
+	     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 =
+				le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		else
+			con->out_msg_pos.page_pos = 0;
+		con->out_msg_pos.data_pos = 0;
+		con->out_msg_pos.did_page_crc = 0;
+		con->out_more = 1;  /* data + footer will follow */
+	} else {
+		/* no, queue up footer too and be done */
+		prepare_write_message_footer(con, v);
+	}
+
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Prepare an ack.
+ */
+static void prepare_write_ack(struct ceph_connection *con)
+{
+	dout("prepare_write_ack %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con->out_kvec[0].iov_base = &tag_ack;
+	con->out_kvec[0].iov_len = 1;
+	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con->out_kvec[1].iov_base = &con->out_temp_ack;
+	con->out_kvec[1].iov_len = sizeof(con->out_temp_ack);
+	con->out_kvec_left = 2;
+	con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 1;  /* more will follow.. eventually.. */
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Prepare to write keepalive byte.
+ */
+static void prepare_write_keepalive(struct ceph_connection *con)
+{
+	dout("prepare_write_keepalive %p\n", con);
+	con->out_kvec[0].iov_base = &tag_keepalive;
+	con->out_kvec[0].iov_len = 1;
+	con->out_kvec_left = 1;
+	con->out_kvec_bytes = 1;
+	con->out_kvec_cur = con->out_kvec;
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+/*
+ * Connection negotiation.
+ */
+
+static void prepare_connect_authorizer(struct ceph_connection *con)
+{
+	void *auth_buf;
+	int auth_len = 0;
+	int auth_protocol = 0;
+
+	mutex_unlock(&con->mutex);
+	if (con->ops->get_authorizer)
+		con->ops->get_authorizer(con, &auth_buf, &auth_len,
+					 &auth_protocol, &con->auth_reply_buf,
+					 &con->auth_reply_buf_len,
+					 con->auth_retry);
+	mutex_lock(&con->mutex);
+
+	con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
+	con->out_connect.authorizer_len = cpu_to_le32(auth_len);
+
+	con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
+	con->out_kvec[con->out_kvec_left].iov_len = auth_len;
+	con->out_kvec_left++;
+	con->out_kvec_bytes += auth_len;
+}
+
+/*
+ * We connected to a peer and are saying hello.
+ */
+static void prepare_write_banner(struct ceph_messenger *msgr,
+				 struct ceph_connection *con)
+{
+	int len = strlen(CEPH_BANNER);
+
+	con->out_kvec[0].iov_base = CEPH_BANNER;
+	con->out_kvec[0].iov_len = len;
+	con->out_kvec[1].iov_base = &msgr->my_enc_addr;
+	con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr);
+	con->out_kvec_left = 2;
+	con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 0;
+	set_bit(WRITE_PENDING, &con->state);
+}
+
+static void prepare_write_connect(struct ceph_messenger *msgr,
+				  struct ceph_connection *con,
+				  int after_banner)
+{
+	unsigned global_seq = get_global_seq(con->msgr, 0);
+	int proto;
+
+	switch (con->peer_name.type) {
+	case CEPH_ENTITY_TYPE_MON:
+		proto = CEPH_MONC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_OSD:
+		proto = CEPH_OSDC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_MDS:
+		proto = CEPH_MDSC_PROTOCOL;
+		break;
+	default:
+		BUG();
+	}
+
+	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
+	     con->connect_seq, global_seq, proto);
+
+	con->out_connect.features = cpu_to_le64(msgr->supported_features);
+	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
+	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
+	con->out_connect.global_seq = cpu_to_le32(global_seq);
+	con->out_connect.protocol_version = cpu_to_le32(proto);
+	con->out_connect.flags = 0;
+
+	if (!after_banner) {
+		con->out_kvec_left = 0;
+		con->out_kvec_bytes = 0;
+	}
+	con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect;
+	con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect);
+	con->out_kvec_left++;
+	con->out_kvec_bytes += sizeof(con->out_connect);
+	con->out_kvec_cur = con->out_kvec;
+	con->out_more = 0;
+	set_bit(WRITE_PENDING, &con->state);
+
+	prepare_connect_authorizer(con);
+}
+
+
+/*
+ * write as much of pending kvecs to the socket as we can.
+ *  1 -> done
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_kvec(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
+	while (con->out_kvec_bytes > 0) {
+		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
+				       con->out_kvec_left, con->out_kvec_bytes,
+				       con->out_more);
+		if (ret <= 0)
+			goto out;
+		con->out_kvec_bytes -= ret;
+		if (con->out_kvec_bytes == 0)
+			break;            /* done */
+		while (ret > 0) {
+			if (ret >= con->out_kvec_cur->iov_len) {
+				ret -= con->out_kvec_cur->iov_len;
+				con->out_kvec_cur++;
+				con->out_kvec_left--;
+			} else {
+				con->out_kvec_cur->iov_len -= ret;
+				con->out_kvec_cur->iov_base += ret;
+				ret = 0;
+				break;
+			}
+		}
+	}
+	con->out_kvec_left = 0;
+	con->out_kvec_is_msg = false;
+	ret = 1;
+out:
+	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
+	     con->out_kvec_bytes, con->out_kvec_left, ret);
+	return ret;  /* done! */
+}
+
+#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
+
+/*
+ * Write as much message data payload as we can.  If we finish, queue
+ * up the footer.
+ *  1 -> done, footer is now queued in out_kvec[].
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+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);
+	size_t len;
+	int crc = con->msgr->nocrc;
+	int ret;
+	int total_max_write;
+	int in_trail = 0;
+	size_t trail_len = (msg->trail ? msg->trail->length : 0);
+
+	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->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
+
+	while (data_len > con->out_msg_pos.data_pos) {
+		struct page *page = NULL;
+		void *kaddr = NULL;
+		int max_write = PAGE_SIZE;
+		int page_shift = 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;
+
+			total_max_write = data_len - con->out_msg_pos.data_pos;
+
+			page = list_first_entry(&msg->trail->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+			max_write = PAGE_SIZE;
+		} else if (msg->pages) {
+			page = msg->pages[con->out_msg_pos.page];
+			if (crc)
+				kaddr = kmap(page);
+		} else if (msg->pagelist) {
+			page = list_first_entry(&msg->pagelist->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+#ifdef CONFIG_BLOCK
+		} else if (msg->bio) {
+			struct bio_vec *bv;
+
+			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
+			page = bv->bv_page;
+			page_shift = bv->bv_offset;
+			if (crc)
+				kaddr = kmap(page) + page_shift;
+			max_write = bv->bv_len;
+#endif
+		} else {
+			page = con->msgr->zero_page;
+			if (crc)
+				kaddr = page_address(con->msgr->zero_page);
+		}
+		len = min_t(int, max_write - con->out_msg_pos.page_pos,
+			    total_max_write);
+
+		if (crc && !con->out_msg_pos.did_page_crc) {
+			void *base = kaddr + con->out_msg_pos.page_pos;
+			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+
+			BUG_ON(kaddr == NULL);
+			con->out_msg->footer.data_crc =
+				cpu_to_le32(crc32c(tmpcrc, base, len));
+			con->out_msg_pos.did_page_crc = 1;
+		}
+		ret = kernel_sendpage(con->sock, page,
+				      con->out_msg_pos.page_pos + page_shift,
+				      len,
+				      MSG_DONTWAIT | MSG_NOSIGNAL |
+				      MSG_MORE);
+
+		if (crc &&
+		    (msg->pages || msg->pagelist || msg->bio || in_trail))
+			kunmap(page);
+
+		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 = 0;
+			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
+		}
+	}
+
+	dout("write_partial_msg_pages %p msg %p done\n", con, msg);
+
+	/* prepare and queue up footer, too */
+	if (!crc)
+		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+	con->out_kvec_bytes = 0;
+	con->out_kvec_left = 0;
+	con->out_kvec_cur = con->out_kvec;
+	prepare_write_message_footer(con, 0);
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * write some zeros
+ */
+static int write_partial_skip(struct ceph_connection *con)
+{
+	int ret;
+
+	while (con->out_skip > 0) {
+		struct kvec iov = {
+			.iov_base = page_address(con->msgr->zero_page),
+			.iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE)
+		};
+
+		ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1);
+		if (ret <= 0)
+			goto out;
+		con->out_skip -= ret;
+	}
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * Prepare to read connection handshake, or an ack.
+ */
+static void prepare_read_banner(struct ceph_connection *con)
+{
+	dout("prepare_read_banner %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_connect(struct ceph_connection *con)
+{
+	dout("prepare_read_connect %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_ack %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_tag(struct ceph_connection *con)
+{
+	dout("prepare_read_tag %p\n", con);
+	con->in_base_pos = 0;
+	con->in_tag = CEPH_MSGR_TAG_READY;
+}
+
+/*
+ * Prepare to read a message.
+ */
+static int prepare_read_message(struct ceph_connection *con)
+{
+	dout("prepare_read_message %p\n", con);
+	BUG_ON(con->in_msg != NULL);
+	con->in_base_pos = 0;
+	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
+	return 0;
+}
+
+
+static int read_partial(struct ceph_connection *con,
+			int *to, int size, void *object)
+{
+	*to += size;
+	while (con->in_base_pos < *to) {
+		int left = *to - con->in_base_pos;
+		int have = size - left;
+		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
+		if (ret <= 0)
+			return ret;
+		con->in_base_pos += ret;
+	}
+	return 1;
+}
+
+
+/*
+ * Read all or part of the connect-side handshake on a new connection
+ */
+static int read_partial_banner(struct ceph_connection *con)
+{
+	int ret, to = 0;
+
+	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
+
+	/* peer's banner */
+	ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, sizeof(con->actual_peer_addr),
+			   &con->actual_peer_addr);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, sizeof(con->peer_addr_for_me),
+			   &con->peer_addr_for_me);
+	if (ret <= 0)
+		goto out;
+out:
+	return ret;
+}
+
+static int read_partial_connect(struct ceph_connection *con)
+{
+	int ret, to = 0;
+
+	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
+
+	ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply);
+	if (ret <= 0)
+		goto out;
+	ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len),
+			   con->auth_reply_buf);
+	if (ret <= 0)
+		goto out;
+
+	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
+	     con, (int)con->in_reply.tag,
+	     le32_to_cpu(con->in_reply.connect_seq),
+	     le32_to_cpu(con->in_reply.global_seq));
+out:
+	return ret;
+
+}
+
+/*
+ * Verify the hello banner looks okay.
+ */
+static int verify_hello(struct ceph_connection *con)
+{
+	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
+		pr_err("connect to %s got bad banner\n",
+		       ceph_pr_addr(&con->peer_addr.in_addr));
+		con->error_msg = "protocol error, bad banner";
+		return -1;
+	}
+	return 0;
+}
+
+static bool addr_is_blank(struct sockaddr_storage *ss)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
+	case AF_INET6:
+		return
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
+		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
+	}
+	return false;
+}
+
+static int addr_port(struct sockaddr_storage *ss)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		return ntohs(((struct sockaddr_in *)ss)->sin_port);
+	case AF_INET6:
+		return ntohs(((struct sockaddr_in6 *)ss)->sin6_port);
+	}
+	return 0;
+}
+
+static void addr_set_port(struct sockaddr_storage *ss, int p)
+{
+	switch (ss->ss_family) {
+	case AF_INET:
+		((struct sockaddr_in *)ss)->sin_port = htons(p);
+	case AF_INET6:
+		((struct sockaddr_in6 *)ss)->sin6_port = htons(p);
+	}
+}
+
+/*
+ * Parse an ip[:port] list into an addr array.  Use the default
+ * monitor port if a port isn't specified.
+ */
+int ceph_parse_ips(const char *c, const char *end,
+		   struct ceph_entity_addr *addr,
+		   int max_count, int *count)
+{
+	int i;
+	const char *p = c;
+
+	dout("parse_ips on '%.*s'\n", (int)(end-c), c);
+	for (i = 0; i < max_count; i++) {
+		const char *ipend;
+		struct sockaddr_storage *ss = &addr[i].in_addr;
+		struct sockaddr_in *in4 = (void *)ss;
+		struct sockaddr_in6 *in6 = (void *)ss;
+		int port;
+		char delim = ',';
+
+		if (*p == '[') {
+			delim = ']';
+			p++;
+		}
+
+		memset(ss, 0, sizeof(*ss));
+		if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr,
+			     delim, &ipend))
+			ss->ss_family = AF_INET;
+		else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr,
+				  delim, &ipend))
+			ss->ss_family = AF_INET6;
+		else
+			goto bad;
+		p = ipend;
+
+		if (delim == ']') {
+			if (*p != ']') {
+				dout("missing matching ']'\n");
+				goto bad;
+			}
+			p++;
+		}
+
+		/* port? */
+		if (p < end && *p == ':') {
+			port = 0;
+			p++;
+			while (p < end && *p >= '0' && *p <= '9') {
+				port = (port * 10) + (*p - '0');
+				p++;
+			}
+			if (port > 65535 || port == 0)
+				goto bad;
+		} else {
+			port = CEPH_MON_PORT;
+		}
+
+		addr_set_port(ss, port);
+
+		dout("parse_ips got %s\n", ceph_pr_addr(ss));
+
+		if (p == end)
+			break;
+		if (*p != ',')
+			goto bad;
+		p++;
+	}
+
+	if (p != end)
+		goto bad;
+
+	if (count)
+		*count = i + 1;
+	return 0;
+
+bad:
+	pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ceph_parse_ips);
+
+static int process_banner(struct ceph_connection *con)
+{
+	dout("process_banner on %p\n", con);
+
+	if (verify_hello(con) < 0)
+		return -1;
+
+	ceph_decode_addr(&con->actual_peer_addr);
+	ceph_decode_addr(&con->peer_addr_for_me);
+
+	/*
+	 * Make sure the other end is who we wanted.  note that the other
+	 * end may not yet know their ip address, so if it's 0.0.0.0, give
+	 * them the benefit of the doubt.
+	 */
+	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
+		   sizeof(con->peer_addr)) != 0 &&
+	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
+	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
+		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
+			   ceph_pr_addr(&con->peer_addr.in_addr),
+			   (int)le32_to_cpu(con->peer_addr.nonce),
+			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
+			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -1;
+	}
+
+	/*
+	 * did we learn our address?
+	 */
+	if (addr_is_blank(&con->msgr->inst.addr.in_addr)) {
+		int port = addr_port(&con->msgr->inst.addr.in_addr);
+
+		memcpy(&con->msgr->inst.addr.in_addr,
+		       &con->peer_addr_for_me.in_addr,
+		       sizeof(con->peer_addr_for_me.in_addr));
+		addr_set_port(&con->msgr->inst.addr.in_addr, port);
+		encode_my_addr(con->msgr);
+		dout("process_banner learned my addr is %s\n",
+		     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)
+{