Merge branch 'devel' into for-linus

10 files changed, 505 insertions, 383 deletions

diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 5592883e1e4..afd91c78ce8 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -17,28 +17,6 @@ config SUNRPC_XPRT_RDMA
 
 	  If unsure, say N.
 
-config SUNRPC_REGISTER_V4
-	bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)"
-	depends on SUNRPC && EXPERIMENTAL
-	default n
-	help
-	  Sun added support for registering RPC services at an IPv6
-	  address by creating two new versions of the rpcbind protocol
-	  (RFC 1833).
-
-	  This option enables support in the kernel RPC server for
-	  registering kernel RPC services via version 4 of the rpcbind
-	  protocol.  If you enable this option, you must run a portmapper
-	  daemon that supports rpcbind protocol version 4.
-
-	  Serving NFS over IPv6 from knfsd (the kernel's NFS server)
-	  requires that you enable this option and use a portmapper that
-	  supports rpcbind version 4.
-
-	  If unsure, say N to get traditional behavior (register kernel
-	  RPC services using only rpcbind version 2).  Distributions
-	  using the legacy Linux portmapper daemon must say N here.
-
 config RPCSEC_GSS_KRB5
 	tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
 	depends on SUNRPC && EXPERIMENTAL
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 836f15c0c4a..5abab094441 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1032,27 +1032,20 @@ call_connect_status(struct rpc_task *task)
 	dprint_status(task);
 
 	task->tk_status = 0;
-	if (status >= 0) {
+	if (status >= 0 || status == -EAGAIN) {
 		clnt->cl_stats->netreconn++;
 		task->tk_action = call_transmit;
 		return;
 	}
 
-	/* Something failed: remote service port may have changed */
-	rpc_force_rebind(clnt);
-
 	switch (status) {
-	case -ENOTCONN:
-	case -EAGAIN:
-		task->tk_action = call_bind;
-		if (!RPC_IS_SOFT(task))
-			return;
 		/* if soft mounted, test if we've timed out */
 	case -ETIMEDOUT:
 		task->tk_action = call_timeout;
-		return;
+		break;
+	default:
+		rpc_exit(task, -EIO);
 	}
-	rpc_exit(task, -EIO);
 }
 
 /*
@@ -1105,14 +1098,26 @@ static void
 call_transmit_status(struct rpc_task *task)
 {
 	task->tk_action = call_status;
-	/*
-	 * Special case: if we've been waiting on the socket's write_space()
-	 * callback, then don't call xprt_end_transmit().
-	 */
-	if (task->tk_status == -EAGAIN)
-		return;
-	xprt_end_transmit(task);
-	rpc_task_force_reencode(task);
+	switch (task->tk_status) {
+	case -EAGAIN:
+		break;
+	default:
+		xprt_end_transmit(task);
+		/*
+		 * Special cases: if we've been waiting on the
+		 * socket's write_space() callback, or if the
+		 * socket just returned a connection error,
+		 * then hold onto the transport lock.
+		 */
+	case -ECONNREFUSED:
+	case -ECONNRESET:
+	case -ENOTCONN:
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -EPIPE:
+		rpc_task_force_reencode(task);
+	}
 }
 
 /*
@@ -1152,9 +1157,12 @@ call_status(struct rpc_task *task)
 			xprt_conditional_disconnect(task->tk_xprt,
 					req->rq_connect_cookie);
 		break;
+	case -ECONNRESET:
 	case -ECONNREFUSED:
-	case -ENOTCONN:
 		rpc_force_rebind(clnt);
+		rpc_delay(task, 3*HZ);
+	case -EPIPE:
+	case -ENOTCONN:
 		task->tk_action = call_bind;
 		break;
 	case -EAGAIN:
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 03ae007641e..beee6da3303 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -63,9 +63,16 @@ enum {
  * r_owner
  *
  * The "owner" is allowed to unset a service in the rpcbind database.
- * We always use the following (arbitrary) fixed string.
+ *
+ * For AF_LOCAL SET/UNSET requests, rpcbind treats this string as a
+ * UID which it maps to a local user name via a password lookup.
+ * In all other cases it is ignored.
+ *
+ * For SET/UNSET requests, user space provides a value, even for
+ * network requests, and GETADDR uses an empty string.  We follow
+ * those precedents here.
  */
-#define RPCB_OWNER_STRING	"rpcb"
+#define RPCB_OWNER_STRING	"0"
 #define RPCB_MAXOWNERLEN	sizeof(RPCB_OWNER_STRING)
 
 static void			rpcb_getport_done(struct rpc_task *, void *);
@@ -124,12 +131,6 @@ static const struct sockaddr_in rpcb_inaddr_loopback = {
 	.sin_port		= htons(RPCBIND_PORT),
 };
 
-static const struct sockaddr_in6 rpcb_in6addr_loopback = {
-	.sin6_family		= AF_INET6,
-	.sin6_addr		= IN6ADDR_LOOPBACK_INIT,
-	.sin6_port		= htons(RPCBIND_PORT),
-};
-
 static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr,
 					  size_t addrlen, u32 version)
 {
@@ -176,9 +177,10 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
 	return rpc_create(&args);
 }
 
-static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
-			      u32 version, struct rpc_message *msg)
+static int rpcb_register_call(const u32 version, struct rpc_message *msg)
 {
+	struct sockaddr *addr = (struct sockaddr *)&rpcb_inaddr_loopback;
+	size_t addrlen = sizeof(rpcb_inaddr_loopback);
 	struct rpc_clnt *rpcb_clnt;
 	int result, error = 0;
 
@@ -192,7 +194,7 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
 		error = PTR_ERR(rpcb_clnt);
 
 	if (error < 0) {
-		printk(KERN_WARNING "RPC: failed to contact local rpcbind "
+		dprintk("RPC:       failed to contact local rpcbind "
 				"server (errno %d).\n", -error);
 		return error;
 	}
@@ -254,25 +256,23 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port)
 	if (port)
 		msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET];
 
-	return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
-					sizeof(rpcb_inaddr_loopback),
-					RPCBVERS_2, &msg);
+	return rpcb_register_call(RPCBVERS_2, &msg);
 }
 
 /*
  * Fill in AF_INET family-specific arguments to register
  */
-static int rpcb_register_netid4(struct sockaddr_in *address_to_register,
-				struct rpc_message *msg)
+static int rpcb_register_inet4(const struct sockaddr *sap,
+			       struct rpc_message *msg)
 {
+	const struct sockaddr_in *sin = (const struct sockaddr_in *)sap;
 	struct rpcbind_args *map = msg->rpc_argp;
-	unsigned short port = ntohs(address_to_register->sin_port);
+	unsigned short port = ntohs(sin->sin_port);
 	char buf[32];
 
 	/* Construct AF_INET universal address */
 	snprintf(buf, sizeof(buf), "%pI4.%u.%u",
-		 &address_to_register->sin_addr.s_addr,
-		 port >> 8, port & 0xff);
+		 &sin->sin_addr.s_addr, port >> 8, port & 0xff);
 	map->r_addr = buf;
 
 	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
@@ -284,29 +284,27 @@ static int rpcb_register_netid4(struct sockaddr_in *address_to_register,
 	if (port)
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
 
-	return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
-					sizeof(rpcb_inaddr_loopback),
-					RPCBVERS_4, msg);
+	return rpcb_register_call(RPCBVERS_4, msg);
 }
 
 /*
  * Fill in AF_INET6 family-specific arguments to register
  */
-static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
-				struct rpc_message *msg)
+static int rpcb_register_inet6(const struct sockaddr *sap,
+			       struct rpc_message *msg)
 {
+	const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap;
 	struct rpcbind_args *map = msg->rpc_argp;
-	unsigned short port = ntohs(address_to_register->sin6_port);
+	unsigned short port = ntohs(sin6->sin6_port);
 	char buf[64];
 
 	/* Construct AF_INET6 universal address */
-	if (ipv6_addr_any(&address_to_register->sin6_addr))
+	if (ipv6_addr_any(&sin6->sin6_addr))
 		snprintf(buf, sizeof(buf), "::.%u.%u",
 				port >> 8, port & 0xff);
 	else
 		snprintf(buf, sizeof(buf), "%pI6.%u.%u",
-			 &address_to_register->sin6_addr,
-			 port >> 8, port & 0xff);
+			 &sin6->sin6_addr, port >> 8, port & 0xff);
 	map->r_addr = buf;
 
 	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
@@ -318,9 +316,21 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
 	if (port)
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
 
-	return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback,
-					sizeof(rpcb_in6addr_loopback),
-					RPCBVERS_4, msg);
+	return rpcb_register_call(RPCBVERS_4, msg);
+}
+
+static int rpcb_unregister_all_protofamilies(struct rpc_message *msg)
+{
+	struct rpcbind_args *map = msg->rpc_argp;
+
+	dprintk("RPC:       unregistering [%u, %u, '%s'] with "
+		"local rpcbind\n",
+			map->r_prog, map->r_vers, map->r_netid);
+
+	map->r_addr = "";
+	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
+
+	return rpcb_register_call(RPCBVERS_4, msg);
 }
 
 /**
@@ -340,10 +350,11 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
  * invoke this function once for each [program, version, address,
  * netid] tuple they wish to advertise.
  *
- * Callers may also unregister RPC services that are no longer
- * available by setting the port number in the passed-in address
- * to zero.  Callers pass a netid of "" to unregister all
- * transport netids associated with [program, version, address].
+ * Callers may also unregister RPC services that are registered at a
+ * specific address by setting the port number in @address to zero.
+ * They may unregister all registered protocol families at once for
+ * a service by passing a NULL @address argument.  If @netid is ""
+ * then all netids for [program, version, address] are unregistered.
  *
  * This function uses rpcbind protocol version 4 to contact the
  * local rpcbind daemon.  The local rpcbind daemon must support
@@ -378,13 +389,14 @@ int rpcb_v4_register(const u32 program, const u32 version,
 		.rpc_argp	= &map,
 	};
 
+	if (address == NULL)
+		return rpcb_unregister_all_protofamilies(&msg);
+
 	switch (address->sa_family) {
 	case AF_INET:
-		return rpcb_register_netid4((struct sockaddr_in *)address,
-					    &msg);
+		return rpcb_register_inet4(address, &msg);
 	case AF_INET6:
-		return rpcb_register_netid6((struct sockaddr_in6 *)address,
-					    &msg);
+		return rpcb_register_inet6(address, &msg);
 	}
 
 	return -EAFNOSUPPORT;
@@ -579,7 +591,7 @@ void rpcb_getport_async(struct rpc_task *task)
 	map->r_xprt = xprt_get(xprt);
 	map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID);
 	map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR);
-	map->r_owner = RPCB_OWNER_STRING;	/* ignored for GETADDR */
+	map->r_owner = "";
 	map->r_status = -EIO;
 
 	child = rpcb_call_async(rpcb_clnt, map, proc);
@@ -703,11 +715,16 @@ static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p,
 	*portp = 0;
 	addr_len = ntohl(*p++);
 
+	if (addr_len == 0) {
+		dprintk("RPC:       rpcb_decode_getaddr: "
+					"service is not registered\n");
+		return 0;
+	}
+
 	/*
-	 * Simple sanity check.  The smallest possible universal
-	 * address is an IPv4 address string containing 11 bytes.
+	 * Simple sanity check.
 	 */
-	if (addr_len < 11 || addr_len > RPCBIND_MAXUADDRLEN)
+	if (addr_len > RPCBIND_MAXUADDRLEN)
 		goto out_err;
 
 	/*
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index bb507e2bb94..9f2f2412a2f 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -359,7 +359,7 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu)
  */
 static struct svc_serv *
 __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
-	   sa_family_t family, void (*shutdown)(struct svc_serv *serv))
+	     void (*shutdown)(struct svc_serv *serv))
 {
 	struct svc_serv	*serv;
 	unsigned int vers;
@@ -368,7 +368,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 
 	if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
 		return NULL;
-	serv->sv_family    = family;
 	serv->sv_name      = prog->pg_name;
 	serv->sv_program   = prog;
 	serv->sv_nrthreads = 1;
@@ -427,21 +426,21 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 
 struct svc_serv *
 svc_create(struct svc_program *prog, unsigned int bufsize,
-		sa_family_t family, void (*shutdown)(struct svc_serv *serv))
+	   void (*shutdown)(struct svc_serv *serv))
 {
-	return __svc_create(prog, bufsize, /*npools*/1, family, shutdown);
+	return __svc_create(prog, bufsize, /*npools*/1, shutdown);
 }
 EXPORT_SYMBOL_GPL(svc_create);
 
 struct svc_serv *
 svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
-		  sa_family_t family, void (*shutdown)(struct svc_serv *serv),
+		  void (*shutdown)(struct svc_serv *serv),
 		  svc_thread_fn func, struct module *mod)
 {
 	struct svc_serv *serv;
 	unsigned int npools = svc_pool_map_get();
 
-	serv = __svc_create(prog, bufsize, npools, family, shutdown);
+	serv = __svc_create(prog, bufsize, npools, shutdown);
 
 	if (serv != NULL) {
 		serv->sv_function = func;
@@ -719,8 +718,6 @@ svc_exit_thread(struct svc_rqst *rqstp)
 }
 EXPORT_SYMBOL_GPL(svc_exit_thread);
 
-#ifdef CONFIG_SUNRPC_REGISTER_V4
-
 /*
  * Register an "inet" protocol family netid with the local
  * rpcbind daemon via an rpcbind v4 SET request.
@@ -735,12 +732,13 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
 				const unsigned short protocol,
 				const unsigned short port)
 {
-	struct sockaddr_in sin = {
+	const struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
 		.sin_addr.s_addr	= htonl(INADDR_ANY),
 		.sin_port		= htons(port),
 	};
-	char *netid;
+	const char *netid;
+	int error;
 
 	switch (protocol) {
 	case IPPROTO_UDP:
@@ -750,13 +748,23 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
 		netid = RPCBIND_NETID_TCP;
 		break;
 	default:
-		return -EPROTONOSUPPORT;
+		return -ENOPROTOOPT;
 	}
 
-	return rpcb_v4_register(program, version,
-				(struct sockaddr *)&sin, netid);
+	error = rpcb_v4_register(program, version,
+					(const struct sockaddr *)&sin, netid);
+
+	/*
+	 * User space didn't support rpcbind v4, so retry this
+	 * registration request with the legacy rpcbind v2 protocol.
+	 */
+	if (error == -EPROTONOSUPPORT)
+		error = rpcb_register(program, version, protocol, port);
+
+	return error;
 }
 
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 /*
  * Register an "inet6" protocol family netid with the local
  * rpcbind daemon via an rpcbind v4 SET request.
@@ -771,12 +779,13 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
 				const unsigned short protocol,
 				const unsigned short port)
 {
-	struct sockaddr_in6 sin6 = {
+	const struct sockaddr_in6 sin6 = {
 		.sin6_family		= AF_INET6,
 		.sin6_addr		= IN6ADDR_ANY_INIT,
 		.sin6_port		= htons(port),
 	};
-	char *netid;
+	const char *netid;
+	int error;
 
 	switch (protocol) {
 	case IPPROTO_UDP:
@@ -786,12 +795,22 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
 		netid = RPCBIND_NETID_TCP6;
 		break;
 	default:
-		return -EPROTONOSUPPORT;
+		return -ENOPROTOOPT;
 	}
 
-	return rpcb_v4_register(program, version,
-				(struct sockaddr *)&sin6, netid);
+	error = rpcb_v4_register(program, version,
+					(const struct sockaddr *)&sin6, netid);
+
+	/*
+	 * User space didn't support rpcbind version 4, so we won't
+	 * use a PF_INET6 listener.
+	 */
+	if (error == -EPROTONOSUPPORT)
+		error = -EAFNOSUPPORT;
+
+	return error;
 }
+#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 
 /*
  * Register a kernel RPC service via rpcbind version 4.
@@ -799,69 +818,43 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
  * Returns zero on success; a negative errno value is returned
  * if any error occurs.
  */
-static int __svc_register(const u32 program, const u32 version,
-			  const sa_family_t family,
+static int __svc_register(const char *progname,
+			  const u32 program, const u32 version,
+			  const int family,
 			  const unsigned short protocol,
 			  const unsigned short port)
 {
-	int error;
+	int error = -EAFNOSUPPORT;
 
 	switch (family) {
-	case AF_INET:
-		return __svc_rpcb_register4(program, version,
+	case PF_INET:
+		error = __svc_rpcb_register4(program, version,
 						protocol, port);
-	case AF_INET6:
+		break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	case PF_INET6:
 		error = __svc_rpcb_register6(program, version,
 						protocol, port);
-		if (error < 0)
-			return error;
-
-		/*
-		 * Work around bug in some versions of Linux rpcbind
-		 * which don't allow registration of both inet and
-		 * inet6 netids.
-		 *
-		 * Error return ignored for now.
-		 */
-		__svc_rpcb_register4(program, version,
-						protocol, port);
-		return 0;
+#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 	}
 
-	return -EAFNOSUPPORT;
-}
-
-#else	/* CONFIG_SUNRPC_REGISTER_V4 */
-
-/*
- * Register a kernel RPC service via rpcbind version 2.
- *
- * Returns zero on success; a negative errno value is returned
- * if any error occurs.
- */
-static int __svc_register(const u32 program, const u32 version,
-			  sa_family_t family,
-			  const unsigned short protocol,
-			  const unsigned short port)
-{
-	if (family != AF_INET)
-		return -EAFNOSUPPORT;
-
-	return rpcb_register(program, version, protocol, port);
+	if (error < 0)
+		printk(KERN_WARNING "svc: failed to register %sv%u RPC "
+			"service (errno %d).\n", progname, version, -error);
+	return error;
 }
 
-#endif /* CONFIG_SUNRPC_REGISTER_V4 */
-
 /**
  * svc_register - register an RPC service with the local portmapper
  * @serv: svc_serv struct for the service to register
+ * @family: protocol family of service's listener socket
  * @proto: transport protocol number to advertise
  * @port: port to advertise
  *
- * Service is registered for any address in serv's address family
+ * Service is registered for any address in the passed-in protocol family
  */
-int svc_register(const struct svc_serv *serv, const unsigned short proto,
-		 const unsigned short port)
+int svc_register(const struct svc_serv *serv, const int family,
+		 const unsigned short proto, const unsigned short port)
 {
 	struct svc_program	*progp;
 	unsigned int		i;
@@ -879,15 +872,15 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto,
 					i,
 					proto == IPPROTO_UDP?  "udp" : "tcp",
 					port,
-					serv->sv_family,
+					family,
 					progp->pg_vers[i]->vs_hidden?
 						" (but not telling portmap)" : "");
 
 			if (progp->pg_vers[i]->vs_hidden)
 				continue;
 
-			error = __svc_register(progp->pg_prog, i,
-						serv->sv_family, proto, port);
+			error = __svc_register(progp->pg_name, progp->pg_prog,
+						i, family, proto, port);
 			if (error < 0)
 				break;
 		}
@@ -896,38 +889,31 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto,
 	return error;
 }
 
-#ifdef CONFIG_SUNRPC_REGISTER_V4
-
+/*
+ * If user space is running rpcbind, it should take the v4 UNSET
+ * and clear everything for this [program, version].  If user space
+ * is running portmap, it will reject the v4 UNSET, but won't have
+ * any "inet6" entries anyway.  So a PMAP_UNSET should be sufficient
+ * in this case to clear all existing entries for [program, version].
+ */
 static void __svc_unregister(const u32 program, const u32 version,
 			     const char *progname)
 {
-	struct sockaddr_in6 sin6 = {
-		.sin6_family		= AF_INET6,
-		.sin6_addr		= IN6ADDR_ANY_INIT,
-		.sin6_port		= 0,
-	};
 	int error;
 
-	error = rpcb_v4_register(program, version,
-				(struct sockaddr *)&sin6, "");
-	dprintk("svc: %s(%sv%u), error %d\n",
-			__func__, progname, version, error);
-}
-
-#else	/* CONFIG_SUNRPC_REGISTER_V4 */
+	error = rpcb_v4_register(program, version, NULL, "");
 
-static void __svc_unregister(const u32 program, const u32 version,
-			     const char *progname)
-{
-	int error;
+	/*
+	 * User space didn't support rpcbind v4, so retry this
+	 * request with the legacy rpcbind v2 protocol.
+	 */
+	if (error == -EPROTONOSUPPORT)
+		error = rpcb_register(program, version, 0, 0);
 
-	error = rpcb_register(program, version, 0, 0);
 	dprintk("svc: %s(%sv%u), error %d\n",
 			__func__, progname, version, error);
 }
 
-#endif	/* CONFIG_SUNRPC_REGISTER_V4 */
-
 /*
  * All netids, bind addresses and ports registered for [program, version]
  * are removed from the local rpcbind database (if the service is not
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index e588df5d6b3..2819ee093f3 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -161,7 +161,9 @@ EXPORT_SYMBOL_GPL(svc_xprt_init);
 
 static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 					 struct svc_serv *serv,
-					 unsigned short port, int flags)
+					 const int family,
+					 const unsigned short port,
+					 int flags)
 {
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
@@ -176,12 +178,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	struct sockaddr *sap;
 	size_t len;
 
-	switch (serv->sv_family) {
-	case AF_INET:
+	switch (family) {
+	case PF_INET:
 		sap = (struct sockaddr *)&sin;
 		len = sizeof(sin);
 		break;
-	case AF_INET6:
+	case PF_INET6:
 		sap = (struct sockaddr *)&sin6;
 		len = sizeof(sin6);
 		break;
@@ -192,7 +194,8 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	return xcl->xcl_ops->xpo_create(serv, sap, len, flags);
 }
 
-int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
+int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
+		    const int family, const unsigned short port,
 		    int flags)
 {
 	struct svc_xprt_class *xcl;
@@ -209,7 +212,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 			goto err;
 
 		spin_unlock(&svc_xprt_class_lock);
-		newxprt = __svc_xpo_create(xcl, serv, port, flags);
+		newxprt = __svc_xpo_create(xcl, serv, family, port, flags);
 		if (IS_ERR(newxprt)) {
 			module_put(xcl->xcl_owner);
 			return PTR_ERR(newxprt);
@@ -1033,7 +1036,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt)
 	return dr;
 }
 
-/*
+/**
+ * svc_find_xprt - find an RPC transport instance
+ * @serv: pointer to svc_serv to search
+ * @xcl_name: C string containing transport's class name
+ * @af: Address family of transport's local address
+ * @port: transport's IP port number
+ *
  * Return the transport instance pointer for the endpoint accepting
  * connections/peer traffic from the specified transport class,
  * address family and port.
@@ -1042,14 +1051,14 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt)
  * wild-card, and will result in matching the first transport in the
  * service's list that has a matching class name.
  */
-struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name,
-			       int af, int port)
+struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name,
+			       const sa_family_t af, const unsigned short port)
 {
 	struct svc_xprt *xprt;
 	struct svc_xprt *found = NULL;
 
 	/* Sanity check the args */
-	if (!serv || !xcl_name)
+	if (serv == NULL || xcl_name == NULL)
 		return found;
 
 	spin_lock_bh(&serv->sv_lock);
@@ -1058,7 +1067,7 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name,
 			continue;
 		if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family)
 			continue;
-		if (port && port != svc_xprt_local_port(xprt))
+		if (port != 0 && port != svc_xprt_local_port(xprt))
 			continue;
 		found = xprt;
 		svc_xprt_get(xprt);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 5763e6460fe..9d504234af4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1110,7 +1110,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
-	int		val;
 
 	dprintk("svc: svc_setup_socket %p\n", sock);
 	if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) {
@@ -1122,7 +1121,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 
 	/* Register socket with portmapper */
 	if (*errp >= 0 && pmap_register)
-		*errp = svc_register(serv, inet->sk_protocol,
+		*errp = svc_register(serv, inet->sk_family, inet->sk_protocol,
 				     ntohs(inet_sk(inet)->sport));
 
 	if (*errp < 0) {
@@ -1143,18 +1142,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	else
 		svc_tcp_init(svsk, serv);
 
-	/*
-	 * We start one listener per sv_serv.  We want AF_INET
-	 * requests to be automatically shunted to our AF_INET6
-	 * listener using a mapped IPv4 address.  Make sure
-	 * no-one starts an equivalent IPv4 listener, which
-	 * would steal our incoming connections.
-	 */
-	val = 0;
-	if (serv->sv_family == AF_INET6)
-		kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
-					(char *)&val, sizeof(val));
-
 	dprintk("svc: svc_setup_socket created %p (inet %p)\n",
 				svsk, svsk->sk_sk);
 
@@ -1222,6 +1209,8 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	struct sockaddr_storage addr;
 	struct sockaddr *newsin = (struct sockaddr *)&addr;
 	int		newlen;
+	int		family;
+	int		val;
 	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 
 	dprintk("svc: svc_create_socket(%s, %d, %s)\n",
@@ -1233,14 +1222,35 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 				"sockets supported\n");
 		return ERR_PTR(-EINVAL);
 	}
+
 	type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM;
+	switch (sin->sa_family) {
+	case AF_INET6:
+		family = PF_INET6;
+		break;
+	case AF_INET:
+		family = PF_INET;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
 
-	error = sock_create_kern(sin->sa_family, type, protocol, &sock);
+	error = sock_create_kern(family, type, protocol, &sock);
 	if (error < 0)
 		return ERR_PTR(error);
 
 	svc_reclassify_socket(sock);
 
+	/*
+	 * If this is an PF_INET6 listener, we want to avoid
+	 * getting requests from IPv4 remotes.  Those should
+	 * be shunted to a PF_INET listener via rpcbind.
+	 */
+	val = 1;
+	if (family == PF_INET6)
+		kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
+					(char *)&val, sizeof(val));
+
 	if (type == SOCK_STREAM)
 		sock->sk->sk_reuse = 1;		/* allow address reuse */
 	error = kernel_bind(sock, sin, len);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 62098d101a1..a0bfe53f162 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -152,6 +152,37 @@ out:
 EXPORT_SYMBOL_GPL(xprt_unregister_transport);
 
 /**
+ * xprt_load_transport - load a transport implementation
+ * @transport_name: transport to load
+ *
+ * Returns:
+ * 0:		transport successfully loaded
+ * -ENOENT:	transport module not available
+ */
+int xprt_load_transport(const char *transport_name)
+{
+	struct xprt_class *t;
+	char module_name[sizeof t->name + 5];
+	int result;
+
+	result = 0;
+	spin_lock(&xprt_list_lock);
+	list_for_each_entry(t, &xprt_list, list) {
+		if (strcmp(t->name, transport_name) == 0) {
+			spin_unlock(&xprt_list_lock);
+			goto out;
+		}
+	}
+	spin_unlock(&xprt_list_lock);
+	strcpy(module_name, "xprt");
+	strncat(module_name, transport_name, sizeof t->name);
+	result = request_module(module_name);
+out:
+	return result;
+}
+EXPORT_SYMBOL_GPL(xprt_load_transport);
+
+/**
  * xprt_reserve_xprt - serialize write access to transports
  * @task: task that is requesting access to the transport
  *
@@ -580,7 +611,7 @@ void xprt_disconnect_done(struct rpc_xprt *xprt)
 	dprintk("RPC:       disconnected transport %p\n", xprt);
 	spin_lock_bh(&xprt->transport_lock);
 	xprt_clear_connected(xprt);
-	xprt_wake_pending_tasks(xprt, -ENOTCONN);
+	xprt_wake_pending_tasks(xprt, -EAGAIN);
 	spin_unlock_bh(&xprt->transport_lock);
 }
 EXPORT_SYMBOL_GPL(xprt_disconnect_done);
@@ -598,7 +629,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt)
 	/* Try to schedule an autoclose RPC call */
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
 		queue_work(rpciod_workqueue, &xprt->task_cleanup);
-	xprt_wake_pending_tasks(xprt, -ENOTCONN);
+	xprt_wake_pending_tasks(xprt, -EAGAIN);
 	spin_unlock_bh(&xprt->transport_lock);
 }
 
@@ -625,7 +656,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
 	/* Try to schedule an autoclose RPC call */
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
 		queue_work(rpciod_workqueue, &xprt->task_cleanup);
-	xprt_wake_pending_tasks(xprt, -ENOTCONN);
+	xprt_wake_pending_tasks(xprt, -EAGAIN);
 out:
 	spin_unlock_bh(&xprt->transport_lock);
 }
@@ -695,9 +726,8 @@ static void xprt_connect_status(struct rpc_task *task)
 	}
 
 	switch (task->tk_status) {
-	case -ENOTCONN:
-		dprintk("RPC: %5u xprt_connect_status: connection broken\n",
-				task->tk_pid);
+	case -EAGAIN:
+		dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid);
 		break;
 	case -ETIMEDOUT:
 		dprintk("RPC: %5u xprt_connect_status: connect attempt timed "
@@ -818,15 +848,8 @@ int xprt_prepare_transmit(struct rpc_task *task)
 		err = req->rq_received;
 		goto out_unlock;
 	}
-	if (!xprt->ops->reserve_xprt(task)) {
+	if (!xprt->ops->reserve_xprt(task))
 		err = -EAGAIN;
-		goto out_unlock;
-	}
-
-	if (!xprt_connected(xprt)) {
-		err = -ENOTCONN;
-		goto out_unlock;
-	}
 out_unlock:
 	spin_unlock_bh(&xprt->transport_lock);
 	return err;
@@ -870,32 +893,26 @@ void xprt_transmit(struct rpc_task *task)
 	req->rq_connect_cookie = xprt->connect_cookie;
 	req->rq_xtime = jiffies;
 	status = xprt->ops->send_request(task);
-	if (status == 0) {
-		dprintk("RPC: %5u xmit complete\n", task->tk_pid);
-		spin_lock_bh(&xprt->transport_lock);
+	if (status != 0) {
+		task->tk_status = status;
+		return;
+	}
 
-		xprt->ops->set_retrans_timeout(task);
+	dprintk("RPC: %5u xmit complete\n", task->tk_pid);
+	spin_lock_bh(&xprt->transport_lock);
 
-		xprt->stat.sends++;
-		xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs;
-		xprt->stat.bklog_u += xprt->backlog.qlen;
+	xprt->ops->set_retrans_timeout(task);
 
-		/* Don't race with disconnect */
-		if (!xprt_connected(xprt))
-			task->tk_status = -ENOTCONN;
-		else if (!req->rq_received)
-			rpc_sleep_on(&xprt->pending, task, xprt_timer);
-		spin_unlock_bh(&xprt->transport_lock);
-		return;
-	}
+	xprt->stat.sends++;
+	xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs;
+	xprt->stat.bklog_u += xprt->backlog.qlen;
 
-	/* Note: at this point, task->tk_sleeping has not yet been set,
-	 *	 hence there is no danger of the waking up task being put on
-	 *	 schedq, and being picked up by a parallel run of rpciod().
-	 */
-	task->tk_status = status;
-	if (status == -ECONNREFUSED)
-		rpc_sleep_on(&xprt->sending, task, NULL);
+	/* Don't race with disconnect */
+	if (!xprt_connected(xprt))
+		task->tk_status = -ENOTCONN;
+	else if (!req->rq_received)
+		rpc_sleep_on(&xprt->pending, task, xprt_timer);
+	spin_unlock_bh(&xprt->transport_lock);
 }
 
 static inline void do_xprt_reserve(struct rpc_task *task)
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 14106d26bb9..e5e28d1946a 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -310,6 +310,19 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
 		__func__, pad, destp, rqst->rq_slen, curlen);
 
 	copy_len = rqst->rq_snd_buf.page_len;
+
+	if (rqst->rq_snd_buf.tail[0].iov_len) {
+		curlen = rqst->rq_snd_buf.tail[0].iov_len;
+		if (destp + copy_len != rqst->rq_snd_buf.tail[0].iov_base) {
+			memmove(destp + copy_len,
+				rqst->rq_snd_buf.tail[0].iov_base, curlen);
+			r_xprt->rx_stats.pullup_copy_count += curlen;
+		}
+		dprintk("RPC:       %s: tail destp 0x%p len %d\n",
+			__func__, destp + copy_len, curlen);
+		rqst->rq_svec[0].iov_len += curlen;
+	}
+
 	r_xprt->rx_stats.pullup_copy_count += copy_len;
 	npages = PAGE_ALIGN(rqst->rq_snd_buf.page_base+copy_len) >> PAGE_SHIFT;
 	for (i = 0; copy_len && i < npages; i++) {
@@ -332,17 +345,6 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
 		destp += cur