/*
   * linux/net/sunrpc/xprtsock.c
   *
   * Client-side transport implementation for sockets.
   *

   * TCP callback races fixes (C) 1998 Red Hat
   * TCP send fixes (C) 1998 Red Hat

   * TCP NFS related read + write fixes
   *  (C) 1999 Dave Airlie, University of Limerick, Ireland <airlied@linux.ie>
   *
   * Rewrite of larges part of the code in order to stabilize TCP stuff.
   * Fix behaviour when socket buffer is full.
   *  (C) 1999 Trond Myklebust <trond.myklebust@fys.uio.no>

   *
   * IP socket transport implementation, (C) 2005 Chuck Lever <cel@netapp.com>

   *
   * IPv6 support contributed by Gilles Quillard, Bull Open Source, 2005.
   *   <gilles.quillard@bull.net>

   */
  
  #include <linux/types.h>

  #include <linux/string.h>

  #include <linux/slab.h>

  #include <linux/module.h>

  #include <linux/capability.h>

  #include <linux/pagemap.h>
  #include <linux/errno.h>
  #include <linux/socket.h>
  #include <linux/in.h>
  #include <linux/net.h>
  #include <linux/mm.h>

  #include <linux/un.h>

  #include <linux/udp.h>
  #include <linux/tcp.h>
  #include <linux/sunrpc/clnt.h>

  #include <linux/sunrpc/sched.h>

  #include <linux/sunrpc/svcsock.h>

  #include <linux/sunrpc/xprtsock.h>

  #include <linux/file.h>

  #ifdef CONFIG_SUNRPC_BACKCHANNEL

  #include <linux/sunrpc/bc_xprt.h>
  #endif

  
  #include <net/sock.h>
  #include <net/checksum.h>
  #include <net/udp.h>
  #include <net/tcp.h>

  #include "sunrpc.h"

  
  static void xs_close(struct rpc_xprt *xprt);

  /*

   * xprtsock tunables
   */
  unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE;

  unsigned int xprt_tcp_slot_table_entries = RPC_MIN_SLOT_TABLE;
  unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE;

  
  unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
  unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;

  #define XS_TCP_LINGER_TO	(15U * HZ)

  static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;

  /*

   * We can register our own files under /proc/sys/sunrpc by
   * calling register_sysctl_table() again.  The files in that
   * directory become the union of all files registered there.
   *
   * We simply need to make sure that we don't collide with
   * someone else's file names!
   */
  
  #ifdef RPC_DEBUG
  
  static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
  static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;

  static unsigned int max_tcp_slot_table_limit = RPC_MAX_SLOT_TABLE_LIMIT;

  static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT;
  static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT;
  
  static struct ctl_table_header *sunrpc_table_header;
  
  /*
   * FIXME: changing the UDP slot table size should also resize the UDP
   *        socket buffers for existing UDP transports
   */
  static ctl_table xs_tunables_table[] = {
  	{

  		.procname	= "udp_slot_table_entries",
  		.data		= &xprt_udp_slot_table_entries,
  		.maxlen		= sizeof(unsigned int),
  		.mode		= 0644,

  		.proc_handler	= proc_dointvec_minmax,

  		.extra1		= &min_slot_table_size,
  		.extra2		= &max_slot_table_size
  	},
  	{

  		.procname	= "tcp_slot_table_entries",
  		.data		= &xprt_tcp_slot_table_entries,
  		.maxlen		= sizeof(unsigned int),
  		.mode		= 0644,

  		.proc_handler	= proc_dointvec_minmax,

  		.extra1		= &min_slot_table_size,
  		.extra2		= &max_slot_table_size
  	},
  	{

  		.procname	= "tcp_max_slot_table_entries",
  		.data		= &xprt_max_tcp_slot_table_entries,
  		.maxlen		= sizeof(unsigned int),
  		.mode		= 0644,
  		.proc_handler	= proc_dointvec_minmax,
  		.extra1		= &min_slot_table_size,
  		.extra2		= &max_tcp_slot_table_limit
  	},
  	{

  		.procname	= "min_resvport",
  		.data		= &xprt_min_resvport,
  		.maxlen		= sizeof(unsigned int),
  		.mode		= 0644,

  		.proc_handler	= proc_dointvec_minmax,

  		.extra1		= &xprt_min_resvport_limit,
  		.extra2		= &xprt_max_resvport_limit
  	},
  	{

  		.procname	= "max_resvport",
  		.data		= &xprt_max_resvport,
  		.maxlen		= sizeof(unsigned int),
  		.mode		= 0644,

  		.proc_handler	= proc_dointvec_minmax,

  		.extra1		= &xprt_min_resvport_limit,
  		.extra2		= &xprt_max_resvport_limit
  	},
  	{

  		.procname	= "tcp_fin_timeout",
  		.data		= &xs_tcp_fin_timeout,
  		.maxlen		= sizeof(xs_tcp_fin_timeout),
  		.mode		= 0644,

  		.proc_handler	= proc_dointvec_jiffies,

  	},

  	{ },

  };
  
  static ctl_table sunrpc_table[] = {
  	{

  		.procname	= "sunrpc",
  		.mode		= 0555,
  		.child		= xs_tunables_table
  	},

  	{ },

  };
  
  #endif
  
  /*

   * Wait duration for a reply from the RPC portmapper.
   */
  #define XS_BIND_TO		(60U * HZ)
  
  /*
   * Delay if a UDP socket connect error occurs.  This is most likely some
   * kind of resource problem on the local host.
   */
  #define XS_UDP_REEST_TO		(2U * HZ)
  
  /*
   * The reestablish timeout allows clients to delay for a bit before attempting
   * to reconnect to a server that just dropped our connection.
   *
   * We implement an exponential backoff when trying to reestablish a TCP
   * transport connection with the server.  Some servers like to drop a TCP
   * connection when they are overworked, so we start with a short timeout and
   * increase over time if the server is down or not responding.
   */
  #define XS_TCP_INIT_REEST_TO	(3U * HZ)
  #define XS_TCP_MAX_REEST_TO	(5U * 60 * HZ)
  
  /*
   * TCP idle timeout; client drops the transport socket if it is idle
   * for this long.  Note that we also timeout UDP sockets to prevent
   * holding port numbers when there is no RPC traffic.
   */
  #define XS_IDLE_DISC_TO		(5U * 60 * HZ)

  #ifdef RPC_DEBUG
  # undef  RPC_DEBUG_DATA

  # define RPCDBG_FACILITY	RPCDBG_TRANS

  #endif

  #ifdef RPC_DEBUG_DATA

  static void xs_pktdump(char *msg, u32 *packet, unsigned int count)

  {

  	u8 *buf = (u8 *) packet;
  	int j;

  	dprintk("RPC:       %s
  ", msg);

  	for (j = 0; j < count && j < 128; j += 4) {
  		if (!(j & 31)) {
  			if (j)
  				dprintk("
  ");
  			dprintk("0x%04x ", j);
  		}
  		dprintk("%02x%02x%02x%02x ",
  			buf[j], buf[j+1], buf[j+2], buf[j+3]);
  	}
  	dprintk("
  ");
  }
  #else

  static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)

  {
  	/* NOP */
  }
  #endif

  struct sock_xprt {
  	struct rpc_xprt		xprt;

  
  	/*
  	 * Network layer
  	 */
  	struct socket *		sock;
  	struct sock *		inet;

  
  	/*
  	 * State of TCP reply receive
  	 */
  	__be32			tcp_fraghdr,

  				tcp_xid,
  				tcp_calldir;

  
  	u32			tcp_offset,
  				tcp_reclen;
  
  	unsigned long		tcp_copied,
  				tcp_flags;

  
  	/*
  	 * Connection of transports
  	 */

  	struct delayed_work	connect_worker;

  	struct sockaddr_storage	srcaddr;
  	unsigned short		srcport;

  
  	/*
  	 * UDP socket buffer size parameters
  	 */
  	size_t			rcvsize,
  				sndsize;

  
  	/*
  	 * Saved socket callback addresses
  	 */
  	void			(*old_data_ready)(struct sock *, int);
  	void			(*old_state_change)(struct sock *);
  	void			(*old_write_space)(struct sock *);

  	void			(*old_error_report)(struct sock *);

  };

  /*
   * TCP receive state flags
   */
  #define TCP_RCV_LAST_FRAG	(1UL << 0)
  #define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
  #define TCP_RCV_COPY_XID	(1UL << 2)
  #define TCP_RCV_COPY_DATA	(1UL << 3)

  #define TCP_RCV_READ_CALLDIR	(1UL << 4)
  #define TCP_RCV_COPY_CALLDIR	(1UL << 5)

  
  /*
   * TCP RPC flags
   */

  #define TCP_RPC_REPLY		(1UL << 6)

  static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
  {
  	return (struct sockaddr *) &xprt->addr;
  }

  static inline struct sockaddr_un *xs_addr_un(struct rpc_xprt *xprt)
  {
  	return (struct sockaddr_un *) &xprt->addr;
  }

  static inline struct sockaddr_in *xs_addr_in(struct rpc_xprt *xprt)

  {

  	return (struct sockaddr_in *) &xprt->addr;
  }
  
  static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt)
  {
  	return (struct sockaddr_in6 *) &xprt->addr;
  }

  static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)

  {

  	struct sockaddr *sap = xs_addr(xprt);

  	struct sockaddr_in6 *sin6;
  	struct sockaddr_in *sin;

  	struct sockaddr_un *sun;

  	char buf[128];

  	switch (sap->sa_family) {

  	case AF_LOCAL:
  		sun = xs_addr_un(xprt);
  		strlcpy(buf, sun->sun_path, sizeof(buf));
  		xprt->address_strings[RPC_DISPLAY_ADDR] =
  						kstrdup(buf, GFP_KERNEL);
  		break;

  	case AF_INET:

  		(void)rpc_ntop(sap, buf, sizeof(buf));
  		xprt->address_strings[RPC_DISPLAY_ADDR] =
  						kstrdup(buf, GFP_KERNEL);

  		sin = xs_addr_in(xprt);

  		snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));

  		break;
  	case AF_INET6:

  		(void)rpc_ntop(sap, buf, sizeof(buf));
  		xprt->address_strings[RPC_DISPLAY_ADDR] =
  						kstrdup(buf, GFP_KERNEL);

  		sin6 = xs_addr_in6(xprt);

  		snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);

  		break;
  	default:
  		BUG();

  	}

  	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);

  }

  static void xs_format_common_peer_ports(struct rpc_xprt *xprt)

  {

  	struct sockaddr *sap = xs_addr(xprt);
  	char buf[128];

  	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));

  	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);

  	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));

  	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
  }

  static void xs_format_peer_addresses(struct rpc_xprt *xprt,
  				     const char *protocol,
  				     const char *netid)

  {

  	xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;

  	xprt->address_strings[RPC_DISPLAY_NETID] = netid;

  	xs_format_common_peer_addresses(xprt);

  	xs_format_common_peer_ports(xprt);

  }

  static void xs_update_peer_port(struct rpc_xprt *xprt)

  {

  	kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
  	kfree(xprt->address_strings[RPC_DISPLAY_PORT]);

  	xs_format_common_peer_ports(xprt);

  }
  
  static void xs_free_peer_addresses(struct rpc_xprt *xprt)
  {

  	unsigned int i;
  
  	for (i = 0; i < RPC_DISPLAY_MAX; i++)
  		switch (i) {
  		case RPC_DISPLAY_PROTO:
  		case RPC_DISPLAY_NETID:
  			continue;
  		default:
  			kfree(xprt->address_strings[i]);
  		}

  }

  #define XS_SENDMSG_FLAGS	(MSG_DONTWAIT | MSG_NOSIGNAL)

  static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more)

  {

  	struct msghdr msg = {
  		.msg_name	= addr,
  		.msg_namelen	= addrlen,

  		.msg_flags	= XS_SENDMSG_FLAGS | (more ? MSG_MORE : 0),
  	};
  	struct kvec iov = {
  		.iov_base	= vec->iov_base + base,
  		.iov_len	= vec->iov_len - base,

  	};

  	if (iov.iov_len != 0)

  		return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
  	return kernel_sendmsg(sock, &msg, NULL, 0, 0);
  }

  static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)

  {

  	struct page **ppage;
  	unsigned int remainder;
  	int err, sent = 0;
  
  	remainder = xdr->page_len - base;
  	base += xdr->page_base;
  	ppage = xdr->pages + (base >> PAGE_SHIFT);
  	base &= ~PAGE_MASK;
  	for(;;) {
  		unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
  		int flags = XS_SENDMSG_FLAGS;

  		remainder -= len;
  		if (remainder != 0 || more)
  			flags |= MSG_MORE;
  		err = sock->ops->sendpage(sock, *ppage, base, len, flags);
  		if (remainder == 0 || err != len)
  			break;
  		sent += err;
  		ppage++;
  		base = 0;
  	}
  	if (sent == 0)
  		return err;
  	if (err > 0)
  		sent += err;
  	return sent;

  }

  /**
   * xs_sendpages - write pages directly to a socket
   * @sock: socket to send on
   * @addr: UDP only -- address of destination
   * @addrlen: UDP only -- length of destination address
   * @xdr: buffer containing this request
   * @base: starting position in the buffer
   *

   */

  static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)

  {

  	unsigned int remainder = xdr->len - base;
  	int err, sent = 0;

  	if (unlikely(!sock))

  		return -ENOTSOCK;

  
  	clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);

  	if (base != 0) {
  		addr = NULL;
  		addrlen = 0;
  	}

  	if (base < xdr->head[0].iov_len || addr != NULL) {
  		unsigned int len = xdr->head[0].iov_len - base;
  		remainder -= len;
  		err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
  		if (remainder == 0 || err != len)

  			goto out;

  		sent += err;

  		base = 0;
  	} else

  		base -= xdr->head[0].iov_len;

  	if (base < xdr->page_len) {
  		unsigned int len = xdr->page_len - base;
  		remainder -= len;
  		err = xs_send_pagedata(sock, xdr, base, remainder != 0);
  		if (remainder == 0 || err != len)

  			goto out;

  		sent += err;

  		base = 0;

  	} else
  		base -= xdr->page_len;
  
  	if (base >= xdr->tail[0].iov_len)
  		return sent;
  	err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);

  out:

  	if (sent == 0)
  		return err;
  	if (err > 0)
  		sent += err;
  	return sent;

  }

  static void xs_nospace_callback(struct rpc_task *task)
  {
  	struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);
  
  	transport->inet->sk_write_pending--;
  	clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
  }

  /**

   * xs_nospace - place task on wait queue if transmit was incomplete
   * @task: task to put to sleep

   *

   */

  static int xs_nospace(struct rpc_task *task)

  {

  	struct rpc_rqst *req = task->tk_rqstp;
  	struct rpc_xprt *xprt = req->rq_xprt;

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	int ret = -EAGAIN;

  	dprintk("RPC: %5u xmit incomplete (%u left of %u)
  ",

  			task->tk_pid, req->rq_slen - req->rq_bytes_sent,
  			req->rq_slen);

  	/* Protect against races with write_space */
  	spin_lock_bh(&xprt->transport_lock);
  
  	/* Don't race with disconnect */
  	if (xprt_connected(xprt)) {
  		if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
  			/*
  			 * Notify TCP that we're limited by the application
  			 * window size
  			 */
  			set_bit(SOCK_NOSPACE, &transport->sock->flags);
  			transport->inet->sk_write_pending++;
  			/* ...and wait for more buffer space */
  			xprt_wait_for_buffer_space(task, xs_nospace_callback);
  		}
  	} else {
  		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);

  		ret = -ENOTCONN;

  	}

  	spin_unlock_bh(&xprt->transport_lock);

  	return ret;

  }

  /*
   * Construct a stream transport record marker in @buf.
   */
  static inline void xs_encode_stream_record_marker(struct xdr_buf *buf)
  {
  	u32 reclen = buf->len - sizeof(rpc_fraghdr);
  	rpc_fraghdr *base = buf->head[0].iov_base;
  	*base = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | reclen);
  }

  /**

   * xs_local_send_request - write an RPC request to an AF_LOCAL socket
   * @task: RPC task that manages the state of an RPC request
   *
   * Return values:
   *        0:	The request has been sent
   *   EAGAIN:	The socket was blocked, please call again later to
   *		complete the request
   * ENOTCONN:	Caller needs to invoke connect logic then call again
   *    other:	Some other error occured, the request was not sent
   */
  static int xs_local_send_request(struct rpc_task *task)
  {
  	struct rpc_rqst *req = task->tk_rqstp;
  	struct rpc_xprt *xprt = req->rq_xprt;
  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);
  	struct xdr_buf *xdr = &req->rq_snd_buf;
  	int status;
  
  	xs_encode_stream_record_marker(&req->rq_snd_buf);
  
  	xs_pktdump("packet data:",
  			req->rq_svec->iov_base, req->rq_svec->iov_len);
  
  	status = xs_sendpages(transport->sock, NULL, 0,
  						xdr, req->rq_bytes_sent);
  	dprintk("RPC:       %s(%u) = %d
  ",
  			__func__, xdr->len - req->rq_bytes_sent, status);
  	if (likely(status >= 0)) {
  		req->rq_bytes_sent += status;
  		req->rq_xmit_bytes_sent += status;
  		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
  			req->rq_bytes_sent = 0;
  			return 0;
  		}
  		status = -EAGAIN;
  	}
  
  	switch (status) {
  	case -EAGAIN:
  		status = xs_nospace(task);
  		break;
  	default:
  		dprintk("RPC:       sendmsg returned unrecognized error %d
  ",
  			-status);
  	case -EPIPE:
  		xs_close(xprt);
  		status = -ENOTCONN;
  	}
  
  	return status;
  }
  
  /**

   * xs_udp_send_request - write an RPC request to a UDP socket
   * @task: address of RPC task that manages the state of an RPC request
   *
   * Return values:
   *        0:	The request has been sent
   *   EAGAIN:	The socket was blocked, please call again later to
   *		complete the request
   * ENOTCONN:	Caller needs to invoke connect logic then call again

   *    other:	Some other error occurred, the request was not sent

   */
  static int xs_udp_send_request(struct rpc_task *task)
  {
  	struct rpc_rqst *req = task->tk_rqstp;
  	struct rpc_xprt *xprt = req->rq_xprt;

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	struct xdr_buf *xdr = &req->rq_snd_buf;
  	int status;

  	xs_pktdump("packet data:",

  				req->rq_svec->iov_base,
  				req->rq_svec->iov_len);

  	if (!xprt_bound(xprt))
  		return -ENOTCONN;

  	status = xs_sendpages(transport->sock,

  			      xs_addr(xprt),

  			      xprt->addrlen, xdr,
  			      req->rq_bytes_sent);

  	dprintk("RPC:       xs_udp_send_request(%u) = %d
  ",

  			xdr->len - req->rq_bytes_sent, status);

  	if (status >= 0) {

  		req->rq_xmit_bytes_sent += status;

  		if (status >= req->rq_slen)
  			return 0;
  		/* Still some bytes left; set up for a retry later. */

  		status = -EAGAIN;

  	}

  	switch (status) {

  	case -ENOTSOCK:
  		status = -ENOTCONN;
  		/* Should we call xs_close() here? */
  		break;

  	case -EAGAIN:

  		status = xs_nospace(task);

  		break;

  	default:
  		dprintk("RPC:       sendmsg returned unrecognized error %d
  ",
  			-status);

  	case -ENETUNREACH:
  	case -EPIPE:

  	case -ECONNREFUSED:
  		/* When the server has died, an ICMP port unreachable message

  		 * prompts ECONNREFUSED. */

  		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);

  	}

  	return status;

  }

  /**
   * xs_tcp_shutdown - gracefully shut down a TCP socket
   * @xprt: transport
   *
   * Initiates a graceful shutdown of the TCP socket by calling the
   * equivalent of shutdown(SHUT_WR);
   */
  static void xs_tcp_shutdown(struct rpc_xprt *xprt)
  {
  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
  	struct socket *sock = transport->sock;
  
  	if (sock != NULL)
  		kernel_sock_shutdown(sock, SHUT_WR);
  }

  /**

   * xs_tcp_send_request - write an RPC request to a TCP socket

   * @task: address of RPC task that manages the state of an RPC request
   *
   * Return values:

   *        0:	The request has been sent
   *   EAGAIN:	The socket was blocked, please call again later to
   *		complete the request
   * ENOTCONN:	Caller needs to invoke connect logic then call again

   *    other:	Some other error occurred, the request was not sent

   *
   * XXX: In the case of soft timeouts, should we eventually give up

   *	if sendmsg is not able to make progress?

   */

  static int xs_tcp_send_request(struct rpc_task *task)

  {
  	struct rpc_rqst *req = task->tk_rqstp;
  	struct rpc_xprt *xprt = req->rq_xprt;

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	struct xdr_buf *xdr = &req->rq_snd_buf;

  	int status;

  	xs_encode_stream_record_marker(&req->rq_snd_buf);

  	xs_pktdump("packet data:",
  				req->rq_svec->iov_base,
  				req->rq_svec->iov_len);

  
  	/* Continue transmitting the packet/record. We must be careful
  	 * to cope with writespace callbacks arriving _after_ we have

  	 * called sendmsg(). */

  	while (1) {

  		status = xs_sendpages(transport->sock,
  					NULL, 0, xdr, req->rq_bytes_sent);

  		dprintk("RPC:       xs_tcp_send_request(%u) = %d
  ",

  				xdr->len - req->rq_bytes_sent, status);

  		if (unlikely(status < 0))

  			break;

  		/* If we've sent the entire packet, immediately
  		 * reset the count of bytes sent. */
  		req->rq_bytes_sent += status;

  		req->rq_xmit_bytes_sent += status;

  		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
  			req->rq_bytes_sent = 0;
  			return 0;
  		}

  		if (status != 0)
  			continue;

  		status = -EAGAIN;

  		break;

  	}

  	switch (status) {

  	case -ENOTSOCK:
  		status = -ENOTCONN;
  		/* Should we call xs_close() here? */
  		break;

  	case -EAGAIN:

  		status = xs_nospace(task);

  		break;

  	default:
  		dprintk("RPC:       sendmsg returned unrecognized error %d
  ",
  			-status);

  	case -ECONNRESET:

  	case -EPIPE:

  		xs_tcp_shutdown(xprt);
  	case -ECONNREFUSED:

  	case -ENOTCONN:

  		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);

  	}

  	return status;
  }

  /**

   * xs_tcp_release_xprt - clean up after a tcp transmission
   * @xprt: transport
   * @task: rpc task
   *
   * This cleans up if an error causes us to abort the transmission of a request.
   * In this case, the socket may need to be reset in order to avoid confusing
   * the server.
   */
  static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
  {
  	struct rpc_rqst *req;
  
  	if (task != xprt->snd_task)
  		return;
  	if (task == NULL)
  		goto out_release;
  	req = task->tk_rqstp;

  	if (req == NULL)
  		goto out_release;

  	if (req->rq_bytes_sent == 0)
  		goto out_release;
  	if (req->rq_bytes_sent == req->rq_snd_buf.len)
  		goto out_release;
  	set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state);
  out_release:
  	xprt_release_xprt(xprt, task);
  }

  static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
  {
  	transport->old_data_ready = sk->sk_data_ready;
  	transport->old_state_change = sk->sk_state_change;
  	transport->old_write_space = sk->sk_write_space;
  	transport->old_error_report = sk->sk_error_report;
  }
  
  static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
  {
  	sk->sk_data_ready = transport->old_data_ready;
  	sk->sk_state_change = transport->old_state_change;
  	sk->sk_write_space = transport->old_write_space;
  	sk->sk_error_report = transport->old_error_report;
  }

  static void xs_reset_transport(struct sock_xprt *transport)

  {

  	struct socket *sock = transport->sock;
  	struct sock *sk = transport->inet;

  	if (sk == NULL)
  		return;

  	transport->srcport = 0;

  	write_lock_bh(&sk->sk_callback_lock);

  	transport->inet = NULL;
  	transport->sock = NULL;

  	sk->sk_user_data = NULL;

  
  	xs_restore_old_callbacks(transport, sk);

  	write_unlock_bh(&sk->sk_callback_lock);

  	sk->sk_no_check = 0;

  
  	sock_release(sock);

  }
  
  /**
   * xs_close - close a socket
   * @xprt: transport
   *
   * This is used when all requests are complete; ie, no DRC state remains
   * on the server we want to save.

   *
   * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with
   * xs_reset_transport() zeroing the socket from underneath a writer.

   */
  static void xs_close(struct rpc_xprt *xprt)
  {
  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
  
  	dprintk("RPC:       xs_close xprt %p
  ", xprt);
  
  	xs_reset_transport(transport);

  	xprt->reestablish_timeout = 0;

  	smp_mb__before_clear_bit();

  	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);

  	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);

  	clear_bit(XPRT_CLOSING, &xprt->state);

  	smp_mb__after_clear_bit();

  	xprt_disconnect_done(xprt);

  }

  static void xs_tcp_close(struct rpc_xprt *xprt)
  {
  	if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
  		xs_close(xprt);
  	else
  		xs_tcp_shutdown(xprt);
  }

  /**
   * xs_destroy - prepare to shutdown a transport
   * @xprt: doomed transport
   *
   */
  static void xs_destroy(struct rpc_xprt *xprt)

  {

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	dprintk("RPC:       xs_destroy xprt %p
  ", xprt);

  	cancel_delayed_work_sync(&transport->connect_worker);

  	xs_close(xprt);

  	xs_free_peer_addresses(xprt);

  	xprt_free(xprt);

  	module_put(THIS_MODULE);

  }

  static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
  {
  	return (struct rpc_xprt *) sk->sk_user_data;
  }

  static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
  {
  	struct xdr_skb_reader desc = {
  		.skb		= skb,
  		.offset		= sizeof(rpc_fraghdr),
  		.count		= skb->len - sizeof(rpc_fraghdr),
  	};
  
  	if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
  		return -1;
  	if (desc.count)
  		return -1;
  	return 0;
  }
  
  /**
   * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
   * @sk: socket with data to read
   * @len: how much data to read
   *
   * Currently this assumes we can read the whole reply in a single gulp.
   */
  static void xs_local_data_ready(struct sock *sk, int len)
  {
  	struct rpc_task *task;
  	struct rpc_xprt *xprt;
  	struct rpc_rqst *rovr;
  	struct sk_buff *skb;
  	int err, repsize, copied;
  	u32 _xid;
  	__be32 *xp;
  
  	read_lock_bh(&sk->sk_callback_lock);
  	dprintk("RPC:       %s...
  ", __func__);
  	xprt = xprt_from_sock(sk);
  	if (xprt == NULL)
  		goto out;
  
  	skb = skb_recv_datagram(sk, 0, 1, &err);
  	if (skb == NULL)
  		goto out;
  
  	if (xprt->shutdown)
  		goto dropit;
  
  	repsize = skb->len - sizeof(rpc_fraghdr);
  	if (repsize < 4) {
  		dprintk("RPC:       impossible RPC reply size %d
  ", repsize);
  		goto dropit;
  	}
  
  	/* Copy the XID from the skb... */
  	xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid);
  	if (xp == NULL)
  		goto dropit;
  
  	/* Look up and lock the request corresponding to the given XID */
  	spin_lock(&xprt->transport_lock);
  	rovr = xprt_lookup_rqst(xprt, *xp);
  	if (!rovr)
  		goto out_unlock;
  	task = rovr->rq_task;
  
  	copied = rovr->rq_private_buf.buflen;
  	if (copied > repsize)
  		copied = repsize;
  
  	if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) {
  		dprintk("RPC:       sk_buff copy failed
  ");
  		goto out_unlock;
  	}
  
  	xprt_complete_rqst(task, copied);
  
   out_unlock:
  	spin_unlock(&xprt->transport_lock);
   dropit:
  	skb_free_datagram(sk, skb);
   out:
  	read_unlock_bh(&sk->sk_callback_lock);
  }

  /**
   * xs_udp_data_ready - "data ready" callback for UDP sockets
   * @sk: socket with data to read
   * @len: how much data to read
   *

   */

  static void xs_udp_data_ready(struct sock *sk, int len)

  {

  	struct rpc_task *task;
  	struct rpc_xprt *xprt;

  	struct rpc_rqst *rovr;

  	struct sk_buff *skb;

  	int err, repsize, copied;

  	u32 _xid;
  	__be32 *xp;

  	read_lock_bh(&sk->sk_callback_lock);

  	dprintk("RPC:       xs_udp_data_ready...
  ");

  	if (!(xprt = xprt_from_sock(sk)))

  		goto out;

  
  	if ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL)
  		goto out;
  
  	if (xprt->shutdown)
  		goto dropit;
  
  	repsize = skb->len - sizeof(struct udphdr);
  	if (repsize < 4) {

  		dprintk("RPC:       impossible RPC reply size %d!
  ", repsize);

  		goto dropit;
  	}
  
  	/* Copy the XID from the skb... */
  	xp = skb_header_pointer(skb, sizeof(struct udphdr),
  				sizeof(_xid), &_xid);
  	if (xp == NULL)
  		goto dropit;
  
  	/* Look up and lock the request corresponding to the given XID */

  	spin_lock(&xprt->transport_lock);

  	rovr = xprt_lookup_rqst(xprt, *xp);
  	if (!rovr)
  		goto out_unlock;
  	task = rovr->rq_task;

  	if ((copied = rovr->rq_private_buf.buflen) > repsize)
  		copied = repsize;
  
  	/* Suck it into the iovec, verify checksum if not done by hw. */

  	if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) {
  		UDPX_INC_STATS_BH(sk, UDP_MIB_INERRORS);

  		goto out_unlock;

  	}
  
  	UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS);

  
  	/* Something worked... */

  	dst_confirm(skb_dst(skb));

  	xprt_adjust_cwnd(task, copied);

  	xprt_complete_rqst(task, copied);

  
   out_unlock:

  	spin_unlock(&xprt->transport_lock);

   dropit:
  	skb_free_datagram(sk, skb);
   out:

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)

  {

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	size_t len, used;
  	char *p;

  	p = ((char *) &transport->tcp_fraghdr) + transport->tcp_offset;
  	len = sizeof(transport->tcp_fraghdr) - transport->tcp_offset;

  	used = xdr_skb_read_bits(desc, p, len);

  	transport->tcp_offset += used;

  	if (used != len)
  		return;

  	transport->tcp_reclen = ntohl(transport->tcp_fraghdr);
  	if (transport->tcp_reclen & RPC_LAST_STREAM_FRAGMENT)

  		transport->tcp_flags |= TCP_RCV_LAST_FRAG;

  	else

  		transport->tcp_flags &= ~TCP_RCV_LAST_FRAG;

  	transport->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK;

  	transport->tcp_flags &= ~TCP_RCV_COPY_FRAGHDR;

  	transport->tcp_offset = 0;

  	/* Sanity check of the record length */

  	if (unlikely(transport->tcp_reclen < 8)) {

  		dprintk("RPC:       invalid TCP record fragment length
  ");

  		xprt_force_disconnect(xprt);

  		return;

  	}

  	dprintk("RPC:       reading TCP record fragment of length %d
  ",

  			transport->tcp_reclen);

  }

  static void xs_tcp_check_fraghdr(struct sock_xprt *transport)

  {

  	if (transport->tcp_offset == transport->tcp_reclen) {

  		transport->tcp_flags |= TCP_RCV_COPY_FRAGHDR;

  		transport->tcp_offset = 0;

  		if (transport->tcp_flags & TCP_RCV_LAST_FRAG) {
  			transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
  			transport->tcp_flags |= TCP_RCV_COPY_XID;

  			transport->tcp_copied = 0;

  		}
  	}
  }

  static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_reader *desc)

  {
  	size_t len, used;
  	char *p;

  	len = sizeof(transport->tcp_xid) - transport->tcp_offset;

  	dprintk("RPC:       reading XID (%Zu bytes)
  ", len);

  	p = ((char *) &transport->tcp_xid) + transport->tcp_offset;

  	used = xdr_skb_read_bits(desc, p, len);

  	transport->tcp_offset += used;

  	if (used != len)
  		return;

  	transport->tcp_flags &= ~TCP_RCV_COPY_XID;

  	transport->tcp_flags |= TCP_RCV_READ_CALLDIR;

  	transport->tcp_copied = 4;

  	dprintk("RPC:       reading %s XID %08x
  ",
  			(transport->tcp_flags & TCP_RPC_REPLY) ? "reply for"
  							      : "request with",

  			ntohl(transport->tcp_xid));
  	xs_tcp_check_fraghdr(transport);

  }

  static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
  				       struct xdr_skb_reader *desc)

  {

  	size_t len, used;
  	u32 offset;

  	char *p;

  
  	/*
  	 * We want transport->tcp_offset to be 8 at the end of this routine
  	 * (4 bytes for the xid and 4 bytes for the call/reply flag).
  	 * When this function is called for the first time,
  	 * transport->tcp_offset is 4 (after having already read the xid).
  	 */
  	offset = transport->tcp_offset - sizeof(transport->tcp_xid);

  	len = sizeof(transport->tcp_calldir) - offset;

  	dprintk("RPC:       reading CALL/REPLY flag (%Zu bytes)
  ", len);

  	p = ((char *) &transport->tcp_calldir) + offset;
  	used = xdr_skb_read_bits(desc, p, len);

  	transport->tcp_offset += used;
  	if (used != len)
  		return;

  	transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR;

  	/*
  	 * We don't yet have the XDR buffer, so we will write the calldir
  	 * out after we get the buffer from the 'struct rpc_rqst'
  	 */

  	switch (ntohl(transport->tcp_calldir)) {
  	case RPC_REPLY:
  		transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
  		transport->tcp_flags |= TCP_RCV_COPY_DATA;

  		transport->tcp_flags |= TCP_RPC_REPLY;

  		break;
  	case RPC_CALL:
  		transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
  		transport->tcp_flags |= TCP_RCV_COPY_DATA;

  		transport->tcp_flags &= ~TCP_RPC_REPLY;

  		break;
  	default:
  		dprintk("RPC:       invalid request message type
  ");
  		xprt_force_disconnect(&transport->xprt);
  	}

  	xs_tcp_check_fraghdr(transport);
  }

  static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
  				     struct xdr_skb_reader *desc,
  				     struct rpc_rqst *req)

  {

  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);

  	struct xdr_buf *rcvbuf;
  	size_t len;
  	ssize_t r;

  	rcvbuf = &req->rq_private_buf;

  
  	if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) {
  		/*
  		 * Save the RPC direction in the XDR buffer
  		 */

  		memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied,

  			&transport->tcp_calldir,
  			sizeof(transport->tcp_calldir));
  		transport->tcp_copied += sizeof(transport->tcp_calldir);

  		transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR;

  	}

  	len = desc->count;

  	if (len > transport->tcp_reclen - transport->tcp_offset) {

  		struct xdr_skb_reader my_desc;

  		len = transport->tcp_reclen - transport->tcp_offset;

  		memcpy(&my_desc, desc, sizeof(my_desc));
  		my_desc.count = len;

  		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,

  					  &my_desc, xdr_skb_read_bits);

  		desc->count -= r;
  		desc->offset += r;
  	} else

  		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,

  					  desc, xdr_skb_read_bits);

  
  	if (r > 0) {

  		transport->tcp_copied += r;
  		transport->tcp_offset += r;

  	}
  	if (r != len) {
  		/* Error when copying to the receive buffer,
  		 * usually because we weren't able to allocate
  		 * additional buffer pages. All we can do now

  		 * is turn off TCP_RCV_COPY_DATA, so the request

  		 * will not receive any additional updates,
  		 * and time out.
  		 * Any remaining data from this record will
  		 * be discarded.
  		 */

  		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;

  		dprintk("RPC:       XID %08x truncated request
  ",

  				ntohl(transport->tcp_xid));

  		dprintk("RPC:       xprt = %p, tcp_copied = %lu, "
  				"tcp_offset = %u, tcp_reclen = %u
  ",
  				xprt, transport->tcp_copied,
  				transport->tcp_offset, transport->tcp_reclen);

  		return;

  	}

  	dprintk("RPC:       XID %08x read %Zd bytes
  ",

  			ntohl(transport->tcp_xid), r);

  	dprintk("RPC:       xprt = %p, tcp_copied = %lu, tcp_offset = %u, "
  			"tcp_reclen = %u
  ", xprt, transport->tcp_copied,
  			transport->tcp_offset, transport->tcp_reclen);

  
  	if (transport->tcp_copied == req->rq_private_buf.buflen)

  		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;

  	else if (transport->tcp_offset == transport->tcp_reclen) {

  		if (transport->tcp_flags & TCP_RCV_LAST_FRAG)
  			transport->tcp_flags &= ~TCP_RCV_COPY_DATA;

  	}

  }
  
  /*
   * Finds the request corresponding to the RPC xid and invokes the common
   * tcp read code to read the data.
   */
  static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
  				    struct xdr_skb_reader *desc)
  {
  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);
  	struct rpc_rqst *req;
  
  	dprintk("RPC:       read reply XID %08x
  ", ntohl(transport->tcp_xid));
  
  	/* Find and lock the request corresponding to this xid */
  	spin_lock(&xprt->transport_lock);
  	req = xprt_lookup_rqst(xprt, transport->tcp_xid);
  	if (!req) {
  		dprintk("RPC:       XID %08x request not found!
  ",
  				ntohl(transport->tcp_xid));
  		spin_unlock(&xprt->transport_lock);
  		return -1;
  	}
  
  	xs_tcp_read_common(xprt, desc, req);

  	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))

  		xprt_complete_rqst(req->rq_task, transport->tcp_copied);

  	spin_unlock(&xprt->transport_lock);

  	return 0;
  }

  #if defined(CONFIG_SUNRPC_BACKCHANNEL)

  /*
   * Obtains an rpc_rqst previously allocated and invokes the common
   * tcp read code to read the data.  The result is placed in the callback
   * queue.
   * If we're unable to obtain the rpc_rqst we schedule the closing of the
   * connection and return -1.
   */
  static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
  				       struct xdr_skb_reader *desc)
  {
  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);
  	struct rpc_rqst *req;
  
  	req = xprt_alloc_bc_request(xprt);
  	if (req == NULL) {
  		printk(KERN_WARNING "Callback slot table overflowed
  ");
  		xprt_force_disconnect(xprt);
  		return -1;
  	}
  
  	req->rq_xid = transport->tcp_xid;
  	dprintk("RPC:       read callback  XID %08x
  ", ntohl(req->rq_xid));
  	xs_tcp_read_common(xprt, desc, req);
  
  	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
  		struct svc_serv *bc_serv = xprt->bc_serv;
  
  		/*
  		 * Add callback request to callback list.  The callback
  		 * service sleeps on the sv_cb_waitq waiting for new
  		 * requests.  Wake it up after adding enqueing the
  		 * request.
  		 */
  		dprintk("RPC:       add callback request to list
  ");
  		spin_lock(&bc_serv->sv_cb_lock);
  		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
  		spin_unlock(&bc_serv->sv_cb_lock);
  		wake_up(&bc_serv->sv_cb_waitq);
  	}
  
  	req->rq_private_buf.len = transport->tcp_copied;
  
  	return 0;
  }
  
  static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
  					struct xdr_skb_reader *desc)
  {
  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);
  
  	return (transport->tcp_flags & TCP_RPC_REPLY) ?
  		xs_tcp_read_reply(xprt, desc) :
  		xs_tcp_read_callback(xprt, desc);
  }
  #else
  static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
  					struct xdr_skb_reader *desc)
  {
  	return xs_tcp_read_reply(xprt, desc);
  }

  #endif /* CONFIG_SUNRPC_BACKCHANNEL */

  
  /*
   * Read data off the transport.  This can be either an RPC_CALL or an
   * RPC_REPLY.  Relay the processing to helper functions.
   */
  static void xs_tcp_read_data(struct rpc_xprt *xprt,
  				    struct xdr_skb_reader *desc)
  {
  	struct sock_xprt *transport =
  				container_of(xprt, struct sock_xprt, xprt);
  
  	if (_xs_tcp_read_data(xprt, desc) == 0)
  		xs_tcp_check_fraghdr(transport);
  	else {
  		/*
  		 * The transport_lock protects the request handling.
  		 * There's no need to hold it to update the tcp_flags.
  		 */
  		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
  	}

  }

  static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)

  {
  	size_t len;

  	len = transport->tcp_reclen - transport->tcp_offset;

  	if (len > desc->count)
  		len = desc->count;
  	desc->count -= len;
  	desc->offset += len;

  	transport->tcp_offset += len;

  	dprintk("RPC:       discarded %Zu bytes
  ", len);

  	xs_tcp_check_fraghdr(transport);

  }

  static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)

  {
  	struct rpc_xprt *xprt = rd_desc->arg.data;

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

  	struct xdr_skb_reader desc = {

  		.skb	= skb,
  		.offset	= offset,
  		.count	= len,

  	};

  	dprintk("RPC:       xs_tcp_data_recv started
  ");

  	do {
  		/* Read in a new fragment marker if necessary */
  		/* Can we ever really expect to get completely empty fragments? */

  		if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {

  			xs_tcp_read_fraghdr(xprt, &desc);

  			continue;
  		}
  		/* Read in the xid if necessary */

  		if (transport->tcp_flags & TCP_RCV_COPY_XID) {

  			xs_tcp_read_xid(transport, &desc);

  			continue;
  		}

  		/* Read in the call/reply flag */

  		if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) {

  			xs_tcp_read_calldir(transport, &desc);
  			continue;
  		}

  		/* Read in the request data */

  		if (transport->tcp_flags & TCP_RCV_COPY_DATA) {

  			xs_tcp_read_data(xprt, &desc);

  			continue;
  		}
  		/* Skip over any trailing bytes on short reads */

  		xs_tcp_read_discard(transport, &desc);

  	} while (desc.count);

  	dprintk("RPC:       xs_tcp_data_recv done
  ");

  	return len - desc.count;
  }

  /**
   * xs_tcp_data_ready - "data ready" callback for TCP sockets
   * @sk: socket with data to read
   * @bytes: how much data to read
   *
   */
  static void xs_tcp_data_ready(struct sock *sk, int bytes)

  {
  	struct rpc_xprt *xprt;
  	read_descriptor_t rd_desc;

  	int read;

  	dprintk("RPC:       xs_tcp_data_ready...
  ");

  	read_lock_bh(&sk->sk_callback_lock);

  	if (!(xprt = xprt_from_sock(sk)))

  		goto out;

  	if (xprt->shutdown)
  		goto out;

  	/* Any data means we had a useful conversation, so
  	 * the we don't need to delay the next reconnect
  	 */
  	if (xprt->reestablish_timeout)
  		xprt->reestablish_timeout = 0;

  	/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */

  	rd_desc.arg.data = xprt;

  	do {
  		rd_desc.count = 65536;
  		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
  	} while (read > 0);

  out:

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  /*
   * Do the equivalent of linger/linger2 handling for dealing with
   * broken servers that don't close the socket in a timely
   * fashion
   */
  static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt,
  		unsigned long timeout)
  {
  	struct sock_xprt *transport;
  
  	if (xprt_test_and_set_connecting(xprt))
  		return;
  	set_bit(XPRT_CONNECTION_ABORT, &xprt->state);
  	transport = container_of(xprt, struct sock_xprt, xprt);
  	queue_delayed_work(rpciod_workqueue, &transport->connect_worker,
  			   timeout);
  }
  
  static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
  {
  	struct sock_xprt *transport;
  
  	transport = container_of(xprt, struct sock_xprt, xprt);
  
  	if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) ||
  	    !cancel_delayed_work(&transport->connect_worker))
  		return;
  	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
  	xprt_clear_connecting(xprt);
  }
  
  static void xs_sock_mark_closed(struct rpc_xprt *xprt)
  {
  	smp_mb__before_clear_bit();
  	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
  	clear_bit(XPRT_CLOSING, &xprt->state);
  	smp_mb__after_clear_bit();
  	/* Mark transport as closed and wake up all pending tasks */
  	xprt_disconnect_done(xprt);
  }

  /**
   * xs_tcp_state_change - callback to handle TCP socket state changes
   * @sk: socket whose state has changed
   *
   */
  static void xs_tcp_state_change(struct sock *sk)

  {

  	struct rpc_xprt *xprt;

  	read_lock_bh(&sk->sk_callback_lock);

  	if (!(xprt = xprt_from_sock(sk)))
  		goto out;

  	dprintk("RPC:       xs_tcp_state_change client %p...
  ", xprt);

  	dprintk("RPC:       state %x conn %d dead %d zapped %d sk_shutdown %d
  ",

  			sk->sk_state, xprt_connected(xprt),
  			sock_flag(sk, SOCK_DEAD),

  			sock_flag(sk, SOCK_ZAPPED),
  			sk->sk_shutdown);

  
  	switch (sk->sk_state) {
  	case TCP_ESTABLISHED:

  		spin_lock(&xprt->transport_lock);

  		if (!xprt_test_and_set_connected(xprt)) {

  			struct sock_xprt *transport = container_of(xprt,
  					struct sock_xprt, xprt);

  			/* Reset TCP record info */

  			transport->tcp_offset = 0;
  			transport->tcp_reclen = 0;
  			transport->tcp_copied = 0;

  			transport->tcp_flags =
  				TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;

  			xprt_wake_pending_tasks(xprt, -EAGAIN);

  		}

  		spin_unlock(&xprt->transport_lock);

  		break;

  	case TCP_FIN_WAIT1:
  		/* The client initiated a shutdown of the socket */

  		xprt->connect_cookie++;

  		xprt->reestablish_timeout = 0;

  		set_bit(XPRT_CLOSING, &xprt->state);
  		smp_mb__before_clear_bit();
  		clear_bit(XPRT_CONNECTED, &xprt->state);

  		clear_bit(XPRT_CLOSE_WAIT, &xprt->state);

  		smp_mb__after_clear_bit();

  		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);

  		break;

  	case TCP_CLOSE_WAIT:

  		/* The server initiated a shutdown of the socket */

  		xprt_force_disconnect(xprt);

  		xprt->connect_cookie++;

  	case TCP_CLOSING:
  		/*
  		 * If the server closed down the connection, make sure that
  		 * we back off before reconnecting
  		 */
  		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
  			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;

  		break;
  	case TCP_LAST_ACK:

  		set_bit(XPRT_CLOSING, &xprt->state);

  		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);

  		smp_mb__before_clear_bit();
  		clear_bit(XPRT_CONNECTED, &xprt->state);
  		smp_mb__after_clear_bit();
  		break;
  	case TCP_CLOSE:

  		xs_tcp_cancel_linger_timeout(xprt);
  		xs_sock_mark_closed(xprt);

  	}
   out:

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  /**

   * xs_error_report - callback mainly for catching socket errors

   * @sk: socket
   */

  static void xs_error_report(struct sock *sk)

  {
  	struct rpc_xprt *xprt;

  	read_lock_bh(&sk->sk_callback_lock);

  	if (!(xprt = xprt_from_sock(sk)))
  		goto out;
  	dprintk("RPC:       %s client %p...
  "
  			"RPC:       error %d
  ",
  			__func__, xprt, sk->sk_err);

  	xprt_wake_pending_tasks(xprt, -EAGAIN);

  out:

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  static void xs_write_space(struct sock *sk)
  {
  	struct socket *sock;
  	struct rpc_xprt *xprt;
  
  	if (unlikely(!(sock = sk->sk_socket)))
  		return;
  	clear_bit(SOCK_NOSPACE, &sock->flags);
  
  	if (unlikely(!(xprt = xprt_from_sock(sk))))
  		return;
  	if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
  		return;
  
  	xprt_write_space(xprt);
  }

  /**

   * xs_udp_write_space - callback invoked when socket buffer space
   *                             becomes available

   * @sk: socket whose state has changed
   *

   * Called when more output buffer space is available for this socket.
   * We try not to wake our writers until they can make "significant"

   * progress, otherwise we'll waste resources thrashing kernel_sendmsg

   * with a bunch of small requests.
   */

  static void xs_udp_write_space(struct sock *sk)

  {

  	read_lock_bh(&sk->sk_callback_lock);

  	/* from net/core/sock.c:sock_def_write_space */

  	if (sock_writeable(sk))
  		xs_write_space(sk);

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  /**
   * xs_tcp_write_space - callback invoked when socket buffer space
   *                             becomes available
   * @sk: socket whose state has changed
   *
   * Called when more output buffer space is available for this socket.
   * We try not to wake our writers until they can make "significant"
   * progress, otherwise we'll waste resources thrashing kernel_sendmsg
   * with a bunch of small requests.
   */
  static void xs_tcp_write_space(struct sock *sk)
  {

  	read_lock_bh(&sk->sk_callback_lock);

  
  	/* from net/core/stream.c:sk_stream_write_space */

  	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
  		xs_write_space(sk);

  	read_unlock_bh(&sk->sk_callback_lock);

  }

  static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)

  {

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
  	struct sock *sk = transport->inet;

  	if (transport->rcvsize) {

  		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;

  		sk->sk_rcvbuf = transport->rcvsize * xprt->max_reqs * 2;

  	}

  	if (transport->sndsize) {

  		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;

  		sk->sk_sndbuf = transport->sndsize * xprt->max_reqs * 2;

  		sk->sk_write_space(sk);
  	}
  }

  /**

   * xs_udp_set_buffer_size - set send and receive limits

   * @xprt: generic transport

   * @sndsize: requested size of send buffer, in bytes
   * @rcvsize: requested size of receive buffer, in bytes

   *

   * Set socket send and receive buffer size limits.

   */

  static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize)

  {

  	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
  
  	transport->sndsize = 0;

  	if (sndsize)

  		transport->sndsize = sndsize + 1024;
  	transport->rcvsize = 0;

  	if (rcvsize)

  		transport->rcvsize = rcvsize + 1024;

  
  	xs_udp_do_set_buffer_size(xprt);

  }

  /**
   * xs_udp_timer - called when a retransmit timeout occurs on a UDP transport
   * @task: task that timed out
   *
   * Adjust the congestion window after a retransmit timeout has occurred.
   */
  static void xs_udp_timer(struct rpc_task *task)
  {
  	xprt_adjust_cwnd(task, -ETIMEDOUT);
  }

  static unsigned short xs_get_random_port(void)
  {
  	unsigned short range = xprt_max_resvport - xprt_min_resvport;
  	unsigned short rand = (unsigned short) net_random() % range;
  	return rand + xprt_min_resvport;
  }

  /**
   * xs_set_port - reset the port number in the remote endpoint address
   * @xprt: generic transport
   * @port: new port number
   *
   */
  static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
  {

  	dprintk("RPC:       setting port for xprt %p to %u
  ", xprt, port);

  	rpc_set_port(xs_addr(xprt), port);
  	xs_update_peer_port(xprt);

  }

  static unsigned short xs_get_srcport(struct sock_xprt *transport)

  {

  	unsigned short port = transport->srcport;

  
  	if (port == 0 && transport->xprt.resvport)
  		port = xs_get_random_port();
  	return port;
  }

  static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)

  {

  	if (transport->srcport != 0)
  		transport->srcport = 0;

  	if (!transport->xprt.resvport)
  		return 0;
  	if (port <= xprt_min_resvport || port > xprt_max_resvport)
  		return xprt_max_resvport;
  	return --port;
  }

  static int xs_bind(struct sock_xprt *transport, struct socket *sock)

  {

  	struct sockaddr_storage myaddr;

  	int err, nloop = 0;

  	unsigned short port = xs_get_srcport(transport);

  	unsigned short last;

  	memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);