Fixed MTP to work with TWRP

net/rxrpc/Kconfig

@@ -0,0 +1,44 @@
+#
+# RxRPC session sockets
+#
+
+config AF_RXRPC
+	tristate "RxRPC session sockets"
+	depends on INET
+	select CRYPTO
+	select KEYS
+	help
+	  Say Y or M here to include support for RxRPC session sockets (just
+	  the transport part, not the presentation part: (un)marshalling is
+	  left to the application).
+
+	  These are used for AFS kernel filesystem and userspace utilities.
+
+	  This module at the moment only supports client operations and is
+	  currently incomplete.
+
+	  See Documentation/networking/rxrpc.txt.
+
+
+config AF_RXRPC_DEBUG
+	bool "RxRPC dynamic debugging"
+	depends on AF_RXRPC
+	help
+	  Say Y here to make runtime controllable debugging messages appear.
+
+	  See Documentation/networking/rxrpc.txt.
+
+
+config RXKAD
+	tristate "RxRPC Kerberos security"
+	depends on AF_RXRPC
+	select CRYPTO
+	select CRYPTO_MANAGER
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_PCBC
+	select CRYPTO_FCRYPT
+	help
+	  Provide kerberos 4 and AFS kaserver security handling for AF_RXRPC
+	  through the use of the key retention service.
+
+	  See Documentation/networking/rxrpc.txt.

net/rxrpc/Makefile

@@ -0,0 +1,28 @@
+#
+# Makefile for Linux kernel RxRPC
+#
+
+af-rxrpc-y := \
+	af_rxrpc.o \
+	ar-accept.o \
+	ar-ack.o \
+	ar-call.o \
+	ar-connection.o \
+	ar-connevent.o \
+	ar-error.o \
+	ar-input.o \
+	ar-key.o \
+	ar-local.o \
+	ar-output.o \
+	ar-peer.o \
+	ar-recvmsg.o \
+	ar-security.o \
+	ar-skbuff.o \
+	ar-transport.o
+
+af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o
+af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o
+
+obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o
+
+obj-$(CONFIG_RXKAD) += rxkad.o

net/rxrpc/af_rxrpc.c

@@ -0,0 +1,899 @@
+/* AF_RXRPC implementation
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/net.h>
+#include <linux/slab.h>
+#include <linux/skbuff.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/key-type.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+MODULE_DESCRIPTION("RxRPC network protocol");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_RXRPC);
+
+unsigned int rxrpc_debug; // = RXRPC_DEBUG_KPROTO;
+module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(debug, "RxRPC debugging mask");
+
+static int sysctl_rxrpc_max_qlen __read_mostly = 10;
+
+static struct proto rxrpc_proto;
+static const struct proto_ops rxrpc_rpc_ops;
+
+/* local epoch for detecting local-end reset */
+__be32 rxrpc_epoch;
+
+/* current debugging ID */
+atomic_t rxrpc_debug_id;
+
+/* count of skbs currently in use */
+atomic_t rxrpc_n_skbs;
+
+struct workqueue_struct *rxrpc_workqueue;
+
+static void rxrpc_sock_destructor(struct sock *);
+
+/*
+ * see if an RxRPC socket is currently writable
+ */
+static inline int rxrpc_writable(struct sock *sk)
+{
+	return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf;
+}
+
+/*
+ * wait for write bufferage to become available
+ */
+static void rxrpc_write_space(struct sock *sk)
+{
+	_enter("%p", sk);
+	rcu_read_lock();
+	if (rxrpc_writable(sk)) {
+		struct socket_wq *wq = rcu_dereference(sk->sk_wq);
+
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible(&wq->wait);
+		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * validate an RxRPC address
+ */
+static int rxrpc_validate_address(struct rxrpc_sock *rx,
+				  struct sockaddr_rxrpc *srx,
+				  int len)
+{
+	if (len < sizeof(struct sockaddr_rxrpc))
+		return -EINVAL;
+
+	if (srx->srx_family != AF_RXRPC)
+		return -EAFNOSUPPORT;
+
+	if (srx->transport_type != SOCK_DGRAM)
+		return -ESOCKTNOSUPPORT;
+
+	len -= offsetof(struct sockaddr_rxrpc, transport);
+	if (srx->transport_len < sizeof(sa_family_t) ||
+	    srx->transport_len > len)
+		return -EINVAL;
+
+	if (srx->transport.family != rx->proto)
+		return -EAFNOSUPPORT;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		_debug("INET: %x @ %pI4",
+		       ntohs(srx->transport.sin.sin_port),
+		       &srx->transport.sin.sin_addr);
+		if (srx->transport_len > 8)
+			memset((void *)&srx->transport + 8, 0,
+			       srx->transport_len - 8);
+		break;
+
+	case AF_INET6:
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	return 0;
+}
+
+/*
+ * bind a local address to an RxRPC socket
+ */
+static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
+{
+	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) saddr;
+	struct sock *sk = sock->sk;
+	struct rxrpc_local *local;
+	struct rxrpc_sock *rx = rxrpc_sk(sk), *prx;
+	__be16 service_id;
+	int ret;
+
+	_enter("%p,%p,%d", rx, saddr, len);
+
+	ret = rxrpc_validate_address(rx, srx, len);
+	if (ret < 0)
+		goto error;
+
+	lock_sock(&rx->sk);
+
+	if (rx->sk.sk_state != RXRPC_UNCONNECTED) {
+		ret = -EINVAL;
+		goto error_unlock;
+	}
+
+	memcpy(&rx->srx, srx, sizeof(rx->srx));
+
+	/* find a local transport endpoint if we don't have one already */
+	local = rxrpc_lookup_local(&rx->srx);
+	if (IS_ERR(local)) {
+		ret = PTR_ERR(local);
+		goto error_unlock;
+	}
+
+	rx->local = local;
+	if (srx->srx_service) {
+		service_id = htons(srx->srx_service);
+		write_lock_bh(&local->services_lock);
+		list_for_each_entry(prx, &local->services, listen_link) {
+			if (prx->service_id == service_id)
+				goto service_in_use;
+		}
+
+		rx->service_id = service_id;
+		list_add_tail(&rx->listen_link, &local->services);
+		write_unlock_bh(&local->services_lock);
+
+		rx->sk.sk_state = RXRPC_SERVER_BOUND;
+	} else {
+		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+	}
+
+	release_sock(&rx->sk);
+	_leave(" = 0");
+	return 0;
+
+service_in_use:
+	ret = -EADDRINUSE;
+	write_unlock_bh(&local->services_lock);
+error_unlock:
+	release_sock(&rx->sk);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * set the number of pending calls permitted on a listening socket
+ */
+static int rxrpc_listen(struct socket *sock, int backlog)
+{
+	struct sock *sk = sock->sk;
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	int ret;
+
+	_enter("%p,%d", rx, backlog);
+
+	lock_sock(&rx->sk);
+
+	switch (rx->sk.sk_state) {
+	case RXRPC_UNCONNECTED:
+		ret = -EADDRNOTAVAIL;
+		break;
+	case RXRPC_CLIENT_BOUND:
+	case RXRPC_CLIENT_CONNECTED:
+	default:
+		ret = -EBUSY;
+		break;
+	case RXRPC_SERVER_BOUND:
+		ASSERT(rx->local != NULL);
+		sk->sk_max_ack_backlog = backlog;
+		rx->sk.sk_state = RXRPC_SERVER_LISTENING;
+		ret = 0;
+		break;
+	}
+
+	release_sock(&rx->sk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * find a transport by address
+ */
+static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock,
+						       struct sockaddr *addr,
+						       int addr_len, int flags,
+						       gfp_t gfp)
+{
+	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
+	struct rxrpc_transport *trans;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	struct rxrpc_peer *peer;
+
+	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
+
+	ASSERT(rx->local != NULL);
+	ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED);
+
+	if (rx->srx.transport_type != srx->transport_type)
+		return ERR_PTR(-ESOCKTNOSUPPORT);
+	if (rx->srx.transport.family != srx->transport.family)
+		return ERR_PTR(-EAFNOSUPPORT);
+
+	/* find a remote transport endpoint from the local one */
+	peer = rxrpc_get_peer(srx, gfp);
+	if (IS_ERR(peer))
+		return ERR_CAST(peer);
+
+	/* find a transport */
+	trans = rxrpc_get_transport(rx->local, peer, gfp);
+	rxrpc_put_peer(peer);
+	_leave(" = %p", trans);
+	return trans;
+}
+
+/**
+ * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
+ * @sock: The socket on which to make the call
+ * @srx: The address of the peer to contact (defaults to socket setting)
+ * @key: The security context to use (defaults to socket setting)
+ * @user_call_ID: The ID to use
+ *
+ * Allow a kernel service to begin a call on the nominated socket.  This just
+ * sets up all the internal tracking structures and allocates connection and
+ * call IDs as appropriate.  The call to be used is returned.
+ *
+ * The default socket destination address and security may be overridden by
+ * supplying @srx and @key.
+ */
+struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
+					   struct sockaddr_rxrpc *srx,
+					   struct key *key,
+					   unsigned long user_call_ID,
+					   gfp_t gfp)
+{
+	struct rxrpc_conn_bundle *bundle;
+	struct rxrpc_transport *trans;
+	struct rxrpc_call *call;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	__be16 service_id;
+
+	_enter(",,%x,%lx", key_serial(key), user_call_ID);
+
+	lock_sock(&rx->sk);
+
+	if (srx) {
+		trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx,
+						sizeof(*srx), 0, gfp);
+		if (IS_ERR(trans)) {
+			call = ERR_CAST(trans);
+			trans = NULL;
+			goto out_notrans;
+		}
+	} else {
+		trans = rx->trans;
+		if (!trans) {
+			call = ERR_PTR(-ENOTCONN);
+			goto out_notrans;
+		}
+		atomic_inc(&trans->usage);
+	}
+
+	service_id = rx->service_id;
+	if (srx)
+		service_id = htons(srx->srx_service);
+
+	if (!key)
+		key = rx->key;
+	if (key && !key->payload.data)
+		key = NULL; /* a no-security key */
+
+	bundle = rxrpc_get_bundle(rx, trans, key, service_id, gfp);
+	if (IS_ERR(bundle)) {
+		call = ERR_CAST(bundle);
+		goto out;
+	}
+
+	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true,
+				     gfp);
+	rxrpc_put_bundle(trans, bundle);
+out:
+	rxrpc_put_transport(trans);
+out_notrans:
+	release_sock(&rx->sk);
+	_leave(" = %p", call);
+	return call;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_begin_call);
+
+/**
+ * rxrpc_kernel_end_call - Allow a kernel service to end a call it was using
+ * @call: The call to end
+ *
+ * Allow a kernel service to end a call it was using.  The call must be
+ * complete before this is called (the call should be aborted if necessary).
+ */
+void rxrpc_kernel_end_call(struct rxrpc_call *call)
+{
+	_enter("%d{%d}", call->debug_id, atomic_read(&call->usage));
+	rxrpc_remove_user_ID(call->socket, call);
+	rxrpc_put_call(call);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_end_call);
+
+/**
+ * rxrpc_kernel_intercept_rx_messages - Intercept received RxRPC messages
+ * @sock: The socket to intercept received messages on
+ * @interceptor: The function to pass the messages to
+ *
+ * Allow a kernel service to intercept messages heading for the Rx queue on an
+ * RxRPC socket.  They get passed to the specified function instead.
+ * @interceptor should free the socket buffers it is given.  @interceptor is
+ * called with the socket receive queue spinlock held and softirqs disabled -
+ * this ensures that the messages will be delivered in the right order.
+ */
+void rxrpc_kernel_intercept_rx_messages(struct socket *sock,
+					rxrpc_interceptor_t interceptor)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+
+	_enter("");
+	rx->interceptor = interceptor;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages);
+
+/*
+ * connect an RxRPC socket
+ * - this just targets it at a specific destination; no actual connection
+ *   negotiation takes place
+ */
+static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
+			 int addr_len, int flags)
+{
+	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
+	struct sock *sk = sock->sk;
+	struct rxrpc_transport *trans;
+	struct rxrpc_local *local;
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	int ret;
+
+	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
+
+	ret = rxrpc_validate_address(rx, srx, addr_len);
+	if (ret < 0) {
+		_leave(" = %d [bad addr]", ret);
+		return ret;
+	}
+
+	lock_sock(&rx->sk);
+
+	switch (rx->sk.sk_state) {
+	case RXRPC_UNCONNECTED:
+		/* find a local transport endpoint if we don't have one already */
+		ASSERTCMP(rx->local, ==, NULL);
+		rx->srx.srx_family = AF_RXRPC;
+		rx->srx.srx_service = 0;
+		rx->srx.transport_type = srx->transport_type;
+		rx->srx.transport_len = sizeof(sa_family_t);
+		rx->srx.transport.family = srx->transport.family;
+		local = rxrpc_lookup_local(&rx->srx);
+		if (IS_ERR(local)) {
+			release_sock(&rx->sk);
+			return PTR_ERR(local);
+		}
+		rx->local = local;
+		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+	case RXRPC_CLIENT_BOUND:
+		break;
+	case RXRPC_CLIENT_CONNECTED:
+		release_sock(&rx->sk);
+		return -EISCONN;
+	default:
+		release_sock(&rx->sk);
+		return -EBUSY; /* server sockets can't connect as well */
+	}
+
+	trans = rxrpc_name_to_transport(sock, addr, addr_len, flags,
+					GFP_KERNEL);
+	if (IS_ERR(trans)) {
+		release_sock(&rx->sk);
+		_leave(" = %ld", PTR_ERR(trans));
+		return PTR_ERR(trans);
+	}
+
+	rx->trans = trans;
+	rx->service_id = htons(srx->srx_service);
+	rx->sk.sk_state = RXRPC_CLIENT_CONNECTED;
+
+	release_sock(&rx->sk);
+	return 0;
+}
+
+/*
+ * send a message through an RxRPC socket
+ * - in a client this does a number of things:
+ *   - finds/sets up a connection for the security specified (if any)
+ *   - initiates a call (ID in control data)
+ *   - ends the request phase of a call (if MSG_MORE is not set)
+ *   - sends a call data packet
+ *   - may send an abort (abort code in control data)
+ */
+static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
+			 struct msghdr *m, size_t len)
+{
+	struct rxrpc_transport *trans;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	int ret;
+
+	_enter(",{%d},,%zu", rx->sk.sk_state, len);
+
+	if (m->msg_flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
+	if (m->msg_name) {
+		ret = rxrpc_validate_address(rx, m->msg_name, m->msg_namelen);
+		if (ret < 0) {
+			_leave(" = %d [bad addr]", ret);
+			return ret;
+		}
+	}
+
+	trans = NULL;
+	lock_sock(&rx->sk);
+
+	if (m->msg_name) {
+		ret = -EISCONN;
+		trans = rxrpc_name_to_transport(sock, m->msg_name,
+						m->msg_namelen, 0, GFP_KERNEL);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			trans = NULL;
+			goto out;
+		}
+	} else {
+		trans = rx->trans;
+		if (trans)
+			atomic_inc(&trans->usage);
+	}
+
+	switch (rx->sk.sk_state) {
+	case RXRPC_SERVER_LISTENING:
+		if (!m->msg_name) {
+			ret = rxrpc_server_sendmsg(iocb, rx, m, len);
+			break;
+		}
+	case RXRPC_SERVER_BOUND:
+	case RXRPC_CLIENT_BOUND:
+		if (!m->msg_name) {
+			ret = -ENOTCONN;
+			break;
+		}
+	case RXRPC_CLIENT_CONNECTED:
+		ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len);
+		break;
+	default:
+		ret = -ENOTCONN;
+		break;
+	}
+
+out:
+	release_sock(&rx->sk);
+	if (trans)
+		rxrpc_put_transport(trans);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * set RxRPC socket options
+ */
+static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
+			    char __user *optval, unsigned int optlen)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	unsigned int min_sec_level;
+	int ret;
+
+	_enter(",%d,%d,,%d", level, optname, optlen);
+
+	lock_sock(&rx->sk);
+	ret = -EOPNOTSUPP;
+
+	if (level == SOL_RXRPC) {
+		switch (optname) {
+		case RXRPC_EXCLUSIVE_CONNECTION:
+			ret = -EINVAL;
+			if (optlen != 0)
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+				goto error;
+			set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags);
+			goto success;
+
+		case RXRPC_SECURITY_KEY:
+			ret = -EINVAL;
+			if (rx->key)
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+				goto error;
+			ret = rxrpc_request_key(rx, optval, optlen);
+			goto error;
+
+		case RXRPC_SECURITY_KEYRING:
+			ret = -EINVAL;
+			if (rx->key)
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+				goto error;
+			ret = rxrpc_server_keyring(rx, optval, optlen);
+			goto error;
+
+		case RXRPC_MIN_SECURITY_LEVEL:
+			ret = -EINVAL;
+			if (optlen != sizeof(unsigned int))
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+				goto error;
+			ret = get_user(min_sec_level,
+				       (unsigned int __user *) optval);
+			if (ret < 0)
+				goto error;
+			ret = -EINVAL;
+			if (min_sec_level > RXRPC_SECURITY_MAX)
+				goto error;
+			rx->min_sec_level = min_sec_level;
+			goto success;
+
+		default:
+			break;
+		}
+	}
+
+success:
+	ret = 0;
+error:
+	release_sock(&rx->sk);
+	return ret;
+}
+
+/*
+ * permit an RxRPC socket to be polled
+ */
+static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
+{
+	unsigned int mask;
+	struct sock *sk = sock->sk;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
+
+	/* the socket is readable if there are any messages waiting on the Rx
+	 * queue */
+	if (!skb_queue_empty(&sk->sk_receive_queue))
+		mask |= POLLIN | POLLRDNORM;
+
+	/* the socket is writable if there is space to add new data to the
+	 * socket; there is no guarantee that any particular call in progress
+	 * on the socket may have space in the Tx ACK window */
+	if (rxrpc_writable(sk))
+		mask |= POLLOUT | POLLWRNORM;
+
+	return mask;
+}
+
+/*
+ * create an RxRPC socket
+ */
+static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
+			int kern)
+{
+	struct rxrpc_sock *rx;
+	struct sock *sk;
+
+	_enter("%p,%d", sock, protocol);
+
+	if (!net_eq(net, &init_net))
+		return -EAFNOSUPPORT;
+
+	/* we support transport protocol UDP only */
+	if (protocol != PF_INET)
+		return -EPROTONOSUPPORT;
+
+	if (sock->type != SOCK_DGRAM)
+		return -ESOCKTNOSUPPORT;
+
+	sock->ops = &rxrpc_rpc_ops;
+	sock->state = SS_UNCONNECTED;
+
+	sk = sk_alloc(net, PF_RXRPC, GFP_KERNEL, &rxrpc_proto);
+	if (!sk)
+		return -ENOMEM;
+
+	sock_init_data(sock, sk);
+	sk->sk_state		= RXRPC_UNCONNECTED;
+	sk->sk_write_space	= rxrpc_write_space;
+	sk->sk_max_ack_backlog	= sysctl_rxrpc_max_qlen;
+	sk->sk_destruct		= rxrpc_sock_destructor;
+
+	rx = rxrpc_sk(sk);
+	rx->proto = protocol;
+	rx->calls = RB_ROOT;
+
+	INIT_LIST_HEAD(&rx->listen_link);
+	INIT_LIST_HEAD(&rx->secureq);
+	INIT_LIST_HEAD(&rx->acceptq);
+	rwlock_init(&rx->call_lock);
+	memset(&rx->srx, 0, sizeof(rx->srx));
+
+	_leave(" = 0 [%p]", rx);
+	return 0;
+}
+
+/*
+ * RxRPC socket destructor
+ */
+static void rxrpc_sock_destructor(struct sock *sk)
+{
+	_enter("%p", sk);
+
+	rxrpc_purge_queue(&sk->sk_receive_queue);
+
+	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
+	WARN_ON(!sk_unhashed(sk));
+	WARN_ON(sk->sk_socket);
+
+	if (!sock_flag(sk, SOCK_DEAD)) {
+		printk("Attempt to release alive rxrpc socket: %p\n", sk);
+		return;
+	}
+}
+
+/*
+ * release an RxRPC socket
+ */
+static int rxrpc_release_sock(struct sock *sk)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+
+	_enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt));
+
+	/* declare the socket closed for business */
+	sock_orphan(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	sk->sk_state = RXRPC_CLOSE;
+	spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+	ASSERTCMP(rx->listen_link.next, !=, LIST_POISON1);
+
+	if (!list_empty(&rx->listen_link)) {
+		write_lock_bh(&rx->local->services_lock);
+		list_del(&rx->listen_link);
+		write_unlock_bh(&rx->local->services_lock);
+	}
+
+	/* try to flush out this socket */
+	rxrpc_release_calls_on_socket(rx);
+	flush_workqueue(rxrpc_workqueue);
+	rxrpc_purge_queue(&sk->sk_receive_queue);
+
+	if (rx->conn) {
+		rxrpc_put_connection(rx->conn);
+		rx->conn = NULL;
+	}
+
+	if (rx->bundle) {
+		rxrpc_put_bundle(rx->trans, rx->bundle);
+		rx->bundle = NULL;
+	}
+	if (rx->trans) {
+		rxrpc_put_transport(rx->trans);
+		rx->trans = NULL;
+	}
+	if (rx->local) {
+		rxrpc_put_local(rx->local);
+		rx->local = NULL;
+	}
+
+	key_put(rx->key);
+	rx->key = NULL;
+	key_put(rx->securities);
+	rx->securities = NULL;
+	sock_put(sk);
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * release an RxRPC BSD socket on close() or equivalent
+ */
+static int rxrpc_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	_enter("%p{%p}", sock, sk);
+
+	if (!sk)
+		return 0;
+
+	sock->sk = NULL;
+
+	return rxrpc_release_sock(sk);
+}
+
+/*
+ * RxRPC network protocol
+ */
+static const struct proto_ops rxrpc_rpc_ops = {
+	.family		= PF_UNIX,
+	.owner		= THIS_MODULE,
+	.release	= rxrpc_release,
+	.bind		= rxrpc_bind,
+	.connect	= rxrpc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= sock_no_accept,
+	.getname	= sock_no_getname,
+	.poll		= rxrpc_poll,
+	.ioctl		= sock_no_ioctl,
+	.listen		= rxrpc_listen,
+	.shutdown	= sock_no_shutdown,
+	.setsockopt	= rxrpc_setsockopt,
+	.getsockopt	= sock_no_getsockopt,
+	.sendmsg	= rxrpc_sendmsg,
+	.recvmsg	= rxrpc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.sendpage	= sock_no_sendpage,
+};
+
+static struct proto rxrpc_proto = {
+	.name		= "RXRPC",
+	.owner		= THIS_MODULE,
+	.obj_size	= sizeof(struct rxrpc_sock),
+	.max_header	= sizeof(struct rxrpc_header),
+};
+
+static const struct net_proto_family rxrpc_family_ops = {
+	.family	= PF_RXRPC,
+	.create = rxrpc_create,
+	.owner	= THIS_MODULE,
+};
+
+/*
+ * initialise and register the RxRPC protocol
+ */
+static int __init af_rxrpc_init(void)
+{
+	int ret = -1;
+
+	BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb));
+
+	rxrpc_epoch = htonl(get_seconds());
+
+	ret = -ENOMEM;
+	rxrpc_call_jar = kmem_cache_create(
+		"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
+		SLAB_HWCACHE_ALIGN, NULL);
+	if (!rxrpc_call_jar) {
+		printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n");
+		goto error_call_jar;
+	}
+
+	rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1);
+	if (!rxrpc_workqueue) {
+		printk(KERN_NOTICE "RxRPC: Failed to allocate work queue\n");
+		goto error_work_queue;
+	}
+
+	ret = proto_register(&rxrpc_proto, 1);
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register protocol\n");
+		goto error_proto;
+	}
+
+	ret = sock_register(&rxrpc_family_ops);
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register socket family\n");
+		goto error_sock;
+	}
+
+	ret = register_key_type(&key_type_rxrpc);
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register client key type\n");
+		goto error_key_type;
+	}
+
+	ret = register_key_type(&key_type_rxrpc_s);
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register server key type\n");
+		goto error_key_type_s;
+	}
+
+	ret = rxrpc_sysctl_init();
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register sysctls\n");
+		goto error_sysctls;
+	}
+
+#ifdef CONFIG_PROC_FS
+	proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops);
+	proc_create("rxrpc_conns", 0, init_net.proc_net,
+		    &rxrpc_connection_seq_fops);
+#endif
+	return 0;
+
+error_sysctls:
+	unregister_key_type(&key_type_rxrpc_s);
+error_key_type_s:
+	unregister_key_type(&key_type_rxrpc);
+error_key_type:
+	sock_unregister(PF_RXRPC);
+error_sock:
+	proto_unregister(&rxrpc_proto);
+error_proto:
+	destroy_workqueue(rxrpc_workqueue);
+error_work_queue:
+	kmem_cache_destroy(rxrpc_call_jar);
+error_call_jar:
+	return ret;
+}
+
+/*
+ * unregister the RxRPC protocol
+ */
+static void __exit af_rxrpc_exit(void)
+{
+	_enter("");
+	rxrpc_sysctl_exit();
+	unregister_key_type(&key_type_rxrpc_s);
+	unregister_key_type(&key_type_rxrpc);
+	sock_unregister(PF_RXRPC);
+	proto_unregister(&rxrpc_proto);
+	rxrpc_destroy_all_calls();
+	rxrpc_destroy_all_connections();
+	rxrpc_destroy_all_transports();
+	rxrpc_destroy_all_peers();
+	rxrpc_destroy_all_locals();
+
+	ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0);
+
+	_debug("flush scheduled work");
+	flush_workqueue(rxrpc_workqueue);
+	remove_proc_entry("rxrpc_conns", init_net.proc_net);
+	remove_proc_entry("rxrpc_calls", init_net.proc_net);
+	destroy_workqueue(rxrpc_workqueue);
+	kmem_cache_destroy(rxrpc_call_jar);
+	_leave("");
+}
+
+module_init(af_rxrpc_init);
+module_exit(af_rxrpc_exit);

net/rxrpc/ar-accept.c

@@ -0,0 +1,510 @@
+/* incoming call handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <linux/gfp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include "ar-internal.h"
+
+/*
+ * generate a connection-level abort
+ */
+static int rxrpc_busy(struct rxrpc_local *local, struct sockaddr_rxrpc *srx,
+		      struct rxrpc_header *hdr)
+{
+	struct msghdr msg;
+	struct kvec iov[1];
+	size_t len;
+	int ret;
+
+	_enter("%d,,", local->debug_id);
+
+	msg.msg_name	= &srx->transport.sin;
+	msg.msg_namelen	= sizeof(srx->transport.sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	hdr->seq	= 0;
+	hdr->type	= RXRPC_PACKET_TYPE_BUSY;
+	hdr->flags	= 0;
+	hdr->userStatus	= 0;
+	hdr->_rsvd	= 0;
+
+	iov[0].iov_base	= hdr;
+	iov[0].iov_len	= sizeof(*hdr);
+
+	len = iov[0].iov_len;
+
+	hdr->serial = htonl(1);
+	_proto("Tx BUSY %%%u", ntohl(hdr->serial));
+
+	ret = kernel_sendmsg(local->socket, &msg, iov, 1, len);
+	if (ret < 0) {
+		_leave(" = -EAGAIN [sendmsg failed: %d]", ret);
+		return -EAGAIN;
+	}
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * accept an incoming call that needs peer, transport and/or connection setting
+ * up
+ */
+static int rxrpc_accept_incoming_call(struct rxrpc_local *local,
+				      struct rxrpc_sock *rx,
+				      struct sk_buff *skb,
+				      struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_connection *conn;
+	struct rxrpc_transport *trans;
+	struct rxrpc_skb_priv *sp, *nsp;
+	struct rxrpc_peer *peer;
+	struct rxrpc_call *call;
+	struct sk_buff *notification;
+	int ret;
+
+	_enter("");
+
+	sp = rxrpc_skb(skb);
+
+	/* get a notification message to send to the server app */
+	notification = alloc_skb(0, GFP_NOFS);
+	if (!notification) {
+		_debug("no memory");
+		ret = -ENOMEM;
+		goto error_nofree;
+	}
+	rxrpc_new_skb(notification);
+	notification->mark = RXRPC_SKB_MARK_NEW_CALL;
+
+	peer = rxrpc_get_peer(srx, GFP_NOIO);
+	if (IS_ERR(peer)) {
+		_debug("no peer");
+		ret = -EBUSY;
+		goto error;
+	}
+
+	trans = rxrpc_get_transport(local, peer, GFP_NOIO);
+	rxrpc_put_peer(peer);
+	if (IS_ERR(trans)) {
+		_debug("no trans");
+		ret = -EBUSY;
+		goto error;
+	}
+
+	conn = rxrpc_incoming_connection(trans, &sp->hdr, GFP_NOIO);
+	rxrpc_put_transport(trans);
+	if (IS_ERR(conn)) {
+		_debug("no conn");
+		ret = PTR_ERR(conn);
+		goto error;
+	}
+
+	call = rxrpc_incoming_call(rx, conn, &sp->hdr, GFP_NOIO);
+	rxrpc_put_connection(conn);
+	if (IS_ERR(call)) {
+		_debug("no call");
+		ret = PTR_ERR(call);
+		goto error;
+	}
+
+	/* attach the call to the socket */
+	read_lock_bh(&local->services_lock);
+	if (rx->sk.sk_state == RXRPC_CLOSE)
+		goto invalid_service;
+
+	write_lock(&rx->call_lock);
+	if (!test_and_set_bit(RXRPC_CALL_INIT_ACCEPT, &call->flags)) {
+		rxrpc_get_call(call);
+
+		spin_lock(&call->conn->state_lock);
+		if (sp->hdr.securityIndex > 0 &&
+		    call->conn->state == RXRPC_CONN_SERVER_UNSECURED) {
+			_debug("await conn sec");
+			list_add_tail(&call->accept_link, &rx->secureq);
+			call->conn->state = RXRPC_CONN_SERVER_CHALLENGING;
+			atomic_inc(&call->conn->usage);
+			set_bit(RXRPC_CONN_CHALLENGE, &call->conn->events);
+			rxrpc_queue_conn(call->conn);
+		} else {
+			_debug("conn ready");
+			call->state = RXRPC_CALL_SERVER_ACCEPTING;
+			list_add_tail(&call->accept_link, &rx->acceptq);
+			rxrpc_get_call(call);
+			nsp = rxrpc_skb(notification);
+			nsp->call = call;
+
+			ASSERTCMP(atomic_read(&call->usage), >=, 3);
+
+			_debug("notify");
+			spin_lock(&call->lock);
+			ret = rxrpc_queue_rcv_skb(call, notification, true,
+						  false);
+			spin_unlock(&call->lock);
+			notification = NULL;
+			BUG_ON(ret < 0);
+		}
+		spin_unlock(&call->conn->state_lock);
+
+		_debug("queued");
+	}
+	write_unlock(&rx->call_lock);
+
+	_debug("process");
+	rxrpc_fast_process_packet(call, skb);
+
+	_debug("done");
+	read_unlock_bh(&local->services_lock);
+	rxrpc_free_skb(notification);
+	rxrpc_put_call(call);
+	_leave(" = 0");
+	return 0;
+
+invalid_service:
+	_debug("invalid");
+	read_unlock_bh(&local->services_lock);
+
+	read_lock_bh(&call->state_lock);
+	if (!test_bit(RXRPC_CALL_RELEASE, &call->flags) &&
+	    !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events)) {
+		rxrpc_get_call(call);
+		rxrpc_queue_call(call);
+	}
+	read_unlock_bh(&call->state_lock);
+	rxrpc_put_call(call);
+	ret = -ECONNREFUSED;
+error:
+	rxrpc_free_skb(notification);
+error_nofree:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * accept incoming calls that need peer, transport and/or connection setting up
+ * - the packets we get are all incoming client DATA packets that have seq == 1
+ */
+void rxrpc_accept_incoming_calls(struct work_struct *work)
+{
+	struct rxrpc_local *local =
+		container_of(work, struct rxrpc_local, acceptor);
+	struct rxrpc_skb_priv *sp;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_sock *rx;
+	struct sk_buff *skb;
+	__be16 service_id;
+	int ret;
+
+	_enter("%d", local->debug_id);
+
+	read_lock_bh(&rxrpc_local_lock);
+	if (atomic_read(&local->usage) > 0)
+		rxrpc_get_local(local);
+	else
+		local = NULL;
+	read_unlock_bh(&rxrpc_local_lock);
+	if (!local) {
+		_leave(" [local dead]");
+		return;
+	}
+
+process_next_packet:
+	skb = skb_dequeue(&local->accept_queue);
+	if (!skb) {
+		rxrpc_put_local(local);
+		_leave("\n");
+		return;
+	}
+
+	_net("incoming call skb %p", skb);
+
+	sp = rxrpc_skb(skb);
+
+	/* determine the remote address */
+	memset(&srx, 0, sizeof(srx));
+	srx.srx_family = AF_RXRPC;
+	srx.transport.family = local->srx.transport.family;
+	srx.transport_type = local->srx.transport_type;
+	switch (srx.transport.family) {
+	case AF_INET:
+		srx.transport_len = sizeof(struct sockaddr_in);
+		srx.transport.sin.sin_port = udp_hdr(skb)->source;
+		srx.transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+		break;
+	default:
+		goto busy;
+	}
+
+	/* get the socket providing the service */
+	service_id = sp->hdr.serviceId;
+	read_lock_bh(&local->services_lock);
+	list_for_each_entry(rx, &local->services, listen_link) {
+		if (rx->service_id == service_id &&
+		    rx->sk.sk_state != RXRPC_CLOSE)
+			goto found_service;
+	}
+	read_unlock_bh(&local->services_lock);
+	goto invalid_service;
+
+found_service:
+	_debug("found service %hd", ntohs(rx->service_id));
+	if (sk_acceptq_is_full(&rx->sk))
+		goto backlog_full;
+	sk_acceptq_added(&rx->sk);
+	sock_hold(&rx->sk);
+	read_unlock_bh(&local->services_lock);
+
+	ret = rxrpc_accept_incoming_call(local, rx, skb, &srx);
+	if (ret < 0)
+		sk_acceptq_removed(&rx->sk);
+	sock_put(&rx->sk);
+	switch (ret) {
+	case -ECONNRESET: /* old calls are ignored */
+	case -ECONNABORTED: /* aborted calls are reaborted or ignored */
+	case 0:
+		goto process_next_packet;
+	case -ECONNREFUSED:
+		goto invalid_service;
+	case -EBUSY:
+		goto busy;
+	case -EKEYREJECTED:
+		goto security_mismatch;
+	default:
+		BUG();
+	}
+
+backlog_full:
+	read_unlock_bh(&local->services_lock);
+busy:
+	rxrpc_busy(local, &srx, &sp->hdr);
+	rxrpc_free_skb(skb);
+	goto process_next_packet;
+
+invalid_service:
+	skb->priority = RX_INVALID_OPERATION;
+	rxrpc_reject_packet(local, skb);
+	goto process_next_packet;
+
+	/* can't change connection security type mid-flow */
+security_mismatch:
+	skb->priority = RX_PROTOCOL_ERROR;
+	rxrpc_reject_packet(local, skb);
+	goto process_next_packet;
+}
+
+/*
+ * handle acceptance of a call by userspace
+ * - assign the user call ID to the call at the front of the queue
+ */
+struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
+				     unsigned long user_call_ID)
+{
+	struct rxrpc_call *call;
+	struct rb_node *parent, **pp;
+	int ret;
+
+	_enter(",%lx", user_call_ID);
+
+	ASSERT(!irqs_disabled());
+
+	write_lock(&rx->call_lock);
+
+	ret = -ENODATA;
+	if (list_empty(&rx->acceptq))
+		goto out;
+
+	/* check the user ID isn't already in use */
+	ret = -EBADSLT;
+	pp = &rx->calls.rb_node;
+	parent = NULL;
+	while (*pp) {
+		parent = *pp;
+		call = rb_entry(parent, struct rxrpc_call, sock_node);
+
+		if (user_call_ID < call->user_call_ID)
+			pp = &(*pp)->rb_left;
+		else if (user_call_ID > call->user_call_ID)
+			pp = &(*pp)->rb_right;
+		else
+			goto out;
+	}
+
+	/* dequeue the first call and check it's still valid */
+	call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link);
+	list_del_init(&call->accept_link);
+	sk_acceptq_removed(&rx->sk);
+
+	write_lock_bh(&call->state_lock);
+	switch (call->state) {
+	case RXRPC_CALL_SERVER_ACCEPTING:
+		call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+		break;
+	case RXRPC_CALL_REMOTELY_ABORTED:
+	case RXRPC_CALL_LOCALLY_ABORTED:
+		ret = -ECONNABORTED;
+		goto out_release;
+	case RXRPC_CALL_NETWORK_ERROR:
+		ret = call->conn->error;
+		goto out_release;
+	case RXRPC_CALL_DEAD:
+		ret = -ETIME;
+		goto out_discard;
+	default:
+		BUG();
+	}
+
+	/* formalise the acceptance */
+	call->user_call_ID = user_call_ID;
+	rb_link_node(&call->sock_node, parent, pp);
+	rb_insert_color(&call->sock_node, &rx->calls);
+	if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags))
+		BUG();
+	if (test_and_set_bit(RXRPC_CALL_ACCEPTED, &call->events))
+		BUG();
+	rxrpc_queue_call(call);
+
+	rxrpc_get_call(call);
+	write_unlock_bh(&call->state_lock);
+	write_unlock(&rx->call_lock);
+	_leave(" = %p{%d}", call, call->debug_id);
+	return call;
+
+	/* if the call is already dying or dead, then we leave the socket's ref
+	 * on it to be released by rxrpc_dead_call_expired() as induced by
+	 * rxrpc_release_call() */
+out_release:
+	_debug("release %p", call);
+	if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
+	    !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events))
+		rxrpc_queue_call(call);
+out_discard:
+	write_unlock_bh(&call->state_lock);
+	_debug("discard %p", call);
+out:
+	write_unlock(&rx->call_lock);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * handle rejectance of a call by userspace
+ * - reject the call at the front of the queue
+ */
+int rxrpc_reject_call(struct rxrpc_sock *rx)
+{
+	struct rxrpc_call *call;
+	int ret;
+
+	_enter("");
+
+	ASSERT(!irqs_disabled());
+
+	write_lock(&rx->call_lock);
+
+	ret = -ENODATA;
+	if (list_empty(&rx->acceptq))
+		goto out;
+
+	/* dequeue the first call and check it's still valid */
+	call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link);
+	list_del_init(&call->accept_link);
+	sk_acceptq_removed(&rx->sk);
+
+	write_lock_bh(&call->state_lock);
+	switch (call->state) {
+	case RXRPC_CALL_SERVER_ACCEPTING:
+		call->state = RXRPC_CALL_SERVER_BUSY;
+		if (test_and_set_bit(RXRPC_CALL_REJECT_BUSY, &call->events))
+			rxrpc_queue_call(call);
+		ret = 0;
+		goto out_release;
+	case RXRPC_CALL_REMOTELY_ABORTED:
+	case RXRPC_CALL_LOCALLY_ABORTED:
+		ret = -ECONNABORTED;
+		goto out_release;
+	case RXRPC_CALL_NETWORK_ERROR:
+		ret = call->conn->error;
+		goto out_release;
+	case RXRPC_CALL_DEAD:
+		ret = -ETIME;
+		goto out_discard;
+	default:
+		BUG();
+	}
+
+	/* if the call is already dying or dead, then we leave the socket's ref
+	 * on it to be released by rxrpc_dead_call_expired() as induced by
+	 * rxrpc_release_call() */
+out_release:
+	_debug("release %p", call);
+	if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
+	    !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events))
+		rxrpc_queue_call(call);
+out_discard:
+	write_unlock_bh(&call->state_lock);
+	_debug("discard %p", call);
+out:
+	write_unlock(&rx->call_lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/**
+ * rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call
+ * @sock: The socket on which the impending call is waiting
+ * @user_call_ID: The tag to attach to the call
+ *
+ * Allow a kernel service to accept an incoming call, assuming the incoming
+ * call is still valid.
+ */
+struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock,
+					    unsigned long user_call_ID)
+{
+	struct rxrpc_call *call;
+
+	_enter(",%lx", user_call_ID);
+	call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID);
+	_leave(" = %p", call);
+	return call;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_accept_call);
+
+/**
+ * rxrpc_kernel_reject_call - Allow a kernel service to reject an incoming call
+ * @sock: The socket on which the impending call is waiting
+ *
+ * Allow a kernel service to reject an incoming call with a BUSY message,
+ * assuming the incoming call is still valid.
+ */
+int rxrpc_kernel_reject_call(struct socket *sock)
+{
+	int ret;
+
+	_enter("");
+	ret = rxrpc_reject_call(rxrpc_sk(sock->sk));
+	_leave(" = %d", ret);
+	return ret;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_reject_call);

net/rxrpc/ar-connection.c

@@ -0,0 +1,928 @@
+/* RxRPC virtual connection handler
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * Time till a connection expires after last use (in seconds).
+ */
+unsigned rxrpc_connection_expiry = 10 * 60;
+
+static void rxrpc_connection_reaper(struct work_struct *work);
+
+LIST_HEAD(rxrpc_connections);
+DEFINE_RWLOCK(rxrpc_connection_lock);
+static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
+
+/*
+ * allocate a new client connection bundle
+ */
+static struct rxrpc_conn_bundle *rxrpc_alloc_bundle(gfp_t gfp)
+{
+	struct rxrpc_conn_bundle *bundle;
+
+	_enter("");
+
+	bundle = kzalloc(sizeof(struct rxrpc_conn_bundle), gfp);
+	if (bundle) {
+		INIT_LIST_HEAD(&bundle->unused_conns);
+		INIT_LIST_HEAD(&bundle->avail_conns);
+		INIT_LIST_HEAD(&bundle->busy_conns);
+		init_waitqueue_head(&bundle->chanwait);
+		atomic_set(&bundle->usage, 1);
+	}
+
+	_leave(" = %p", bundle);
+	return bundle;
+}
+
+/*
+ * compare bundle parameters with what we're looking for
+ * - return -ve, 0 or +ve
+ */
+static inline
+int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle,
+		     struct key *key, __be16 service_id)
+{
+	return (bundle->service_id - service_id) ?:
+		((unsigned long) bundle->key - (unsigned long) key);
+}
+
+/*
+ * get bundle of client connections that a client socket can make use of
+ */
+struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
+					   struct rxrpc_transport *trans,
+					   struct key *key,
+					   __be16 service_id,
+					   gfp_t gfp)
+{
+	struct rxrpc_conn_bundle *bundle, *candidate;
+	struct rb_node *p, *parent, **pp;
+
+	_enter("%p{%x},%x,%hx,",
+	       rx, key_serial(key), trans->debug_id, ntohs(service_id));
+
+	if (rx->trans == trans && rx->bundle) {
+		atomic_inc(&rx->bundle->usage);
+		return rx->bundle;
+	}
+
+	/* search the extant bundles first for one that matches the specified
+	 * user ID */
+	spin_lock(&trans->client_lock);
+
+	p = trans->bundles.rb_node;
+	while (p) {
+		bundle = rb_entry(p, struct rxrpc_conn_bundle, node);
+
+		if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
+			p = p->rb_left;
+		else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
+			p = p->rb_right;
+		else
+			goto found_extant_bundle;
+	}
+
+	spin_unlock(&trans->client_lock);
+
+	/* not yet present - create a candidate for a new record and then
+	 * redo the search */
+	candidate = rxrpc_alloc_bundle(gfp);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	candidate->key = key_get(key);
+	candidate->service_id = service_id;
+
+	spin_lock(&trans->client_lock);
+
+	pp = &trans->bundles.rb_node;
+	parent = NULL;
+	while (*pp) {
+		parent = *pp;
+		bundle = rb_entry(parent, struct rxrpc_conn_bundle, node);
+
+		if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
+			pp = &(*pp)->rb_left;
+		else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
+			pp = &(*pp)->rb_right;
+		else
+			goto found_extant_second;
+	}
+
+	/* second search also failed; add the new bundle */
+	bundle = candidate;
+	candidate = NULL;
+
+	rb_link_node(&bundle->node, parent, pp);
+	rb_insert_color(&bundle->node, &trans->bundles);
+	spin_unlock(&trans->client_lock);
+	_net("BUNDLE new on trans %d", trans->debug_id);
+	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
+		atomic_inc(&bundle->usage);
+		rx->bundle = bundle;
+	}
+	_leave(" = %p [new]", bundle);
+	return bundle;
+
+	/* we found the bundle in the list immediately */
+found_extant_bundle:
+	atomic_inc(&bundle->usage);
+	spin_unlock(&trans->client_lock);
+	_net("BUNDLE old on trans %d", trans->debug_id);
+	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
+		atomic_inc(&bundle->usage);
+		rx->bundle = bundle;
+	}
+	_leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage));
+	return bundle;
+
+	/* we found the bundle on the second time through the list */
+found_extant_second:
+	atomic_inc(&bundle->usage);
+	spin_unlock(&trans->client_lock);
+	kfree(candidate);
+	_net("BUNDLE old2 on trans %d", trans->debug_id);
+	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
+		atomic_inc(&bundle->usage);
+		rx->bundle = bundle;
+	}
+	_leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage));
+	return bundle;
+}
+
+/*
+ * release a bundle
+ */
+void rxrpc_put_bundle(struct rxrpc_transport *trans,
+		      struct rxrpc_conn_bundle *bundle)
+{
+	_enter("%p,%p{%d}",trans, bundle, atomic_read(&bundle->usage));
+
+	if (atomic_dec_and_lock(&bundle->usage, &trans->client_lock)) {
+		_debug("Destroy bundle");
+		rb_erase(&bundle->node, &trans->bundles);
+		spin_unlock(&trans->client_lock);
+		ASSERT(list_empty(&bundle->unused_conns));
+		ASSERT(list_empty(&bundle->avail_conns));
+		ASSERT(list_empty(&bundle->busy_conns));
+		ASSERTCMP(bundle->num_conns, ==, 0);
+		key_put(bundle->key);
+		kfree(bundle);
+	}
+
+	_leave("");
+}
+
+/*
+ * allocate a new connection
+ */
+static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
+{
+	struct rxrpc_connection *conn;
+
+	_enter("");
+
+	conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
+	if (conn) {
+		INIT_WORK(&conn->processor, &rxrpc_process_connection);
+		INIT_LIST_HEAD(&conn->bundle_link);
+		conn->calls = RB_ROOT;
+		skb_queue_head_init(&conn->rx_queue);
+		rwlock_init(&conn->lock);
+		spin_lock_init(&conn->state_lock);
+		atomic_set(&conn->usage, 1);
+		conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		conn->avail_calls = RXRPC_MAXCALLS;
+		conn->size_align = 4;
+		conn->header_size = sizeof(struct rxrpc_header);
+	}
+
+	_leave(" = %p{%d}", conn, conn ? conn->debug_id : 0);
+	return conn;
+}
+
+/*
+ * assign a connection ID to a connection and add it to the transport's
+ * connection lookup tree
+ * - called with transport client lock held
+ */
+static void rxrpc_assign_connection_id(struct rxrpc_connection *conn)
+{
+	struct rxrpc_connection *xconn;
+	struct rb_node *parent, **p;
+	__be32 epoch;
+	u32 real_conn_id;
+
+	_enter("");
+
+	epoch = conn->epoch;
+
+	write_lock_bh(&conn->trans->conn_lock);
+
+	conn->trans->conn_idcounter += RXRPC_CID_INC;
+	if (conn->trans->conn_idcounter < RXRPC_CID_INC)
+		conn->trans->conn_idcounter = RXRPC_CID_INC;
+	real_conn_id = conn->trans->conn_idcounter;
+
+attempt_insertion:
+	parent = NULL;
+	p = &conn->trans->client_conns.rb_node;
+
+	while (*p) {
+		parent = *p;
+		xconn = rb_entry(parent, struct rxrpc_connection, node);
+
+		if (epoch < xconn->epoch)
+			p = &(*p)->rb_left;
+		else if (epoch > xconn->epoch)
+			p = &(*p)->rb_right;
+		else if (real_conn_id < xconn->real_conn_id)
+			p = &(*p)->rb_left;
+		else if (real_conn_id > xconn->real_conn_id)
+			p = &(*p)->rb_right;
+		else
+			goto id_exists;
+	}
+
+	/* we've found a suitable hole - arrange for this connection to occupy
+	 * it */
+	rb_link_node(&conn->node, parent, p);
+	rb_insert_color(&conn->node, &conn->trans->client_conns);
+
+	conn->real_conn_id = real_conn_id;
+	conn->cid = htonl(real_conn_id);
+	write_unlock_bh(&conn->trans->conn_lock);
+	_leave(" [CONNID %x CID %x]", real_conn_id, ntohl(conn->cid));
+	return;
+
+	/* we found a connection with the proposed ID - walk the tree from that
+	 * point looking for the next unused ID */
+id_exists:
+	for (;;) {
+		real_conn_id += RXRPC_CID_INC;
+		if (real_conn_id < RXRPC_CID_INC) {
+			real_conn_id = RXRPC_CID_INC;
+			conn->trans->conn_idcounter = real_conn_id;
+			goto attempt_insertion;
+		}
+
+		parent = rb_next(parent);
+		if (!parent)
+			goto attempt_insertion;
+
+		xconn = rb_entry(parent, struct rxrpc_connection, node);
+		if (epoch < xconn->epoch ||
+		    real_conn_id < xconn->real_conn_id)
+			goto attempt_insertion;
+	}
+}
+
+/*
+ * add a call to a connection's call-by-ID tree
+ */
+static void rxrpc_add_call_ID_to_conn(struct rxrpc_connection *conn,
+				      struct rxrpc_call *call)
+{
+	struct rxrpc_call *xcall;
+	struct rb_node *parent, **p;
+	__be32 call_id;
+
+	write_lock_bh(&conn->lock);
+
+	call_id = call->call_id;
+	p = &conn->calls.rb_node;
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		xcall = rb_entry(parent, struct rxrpc_call, conn_node);
+
+		if (call_id < xcall->call_id)
+			p = &(*p)->rb_left;
+		else if (call_id > xcall->call_id)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&call->conn_node, parent, p);
+	rb_insert_color(&call->conn_node, &conn->calls);
+
+	write_unlock_bh(&conn->lock);
+}
+
+/*
+ * connect a call on an exclusive connection
+ */
+static int rxrpc_connect_exclusive(struct rxrpc_sock *rx,
+				   struct rxrpc_transport *trans,
+				   __be16 service_id,
+				   struct rxrpc_call *call,
+				   gfp_t gfp)
+{
+	struct rxrpc_connection *conn;
+	int chan, ret;
+
+	_enter("");
+
+	conn = rx->conn;
+	if (!conn) {
+		/* not yet present - create a candidate for a new connection
+		 * and then redo the check */
+		conn = rxrpc_alloc_connection(gfp);
+		if (!conn) {
+			_leave(" = -ENOMEM");
+			return -ENOMEM;
+		}
+
+		conn->trans = trans;
+		conn->bundle = NULL;
+		conn->service_id = service_id;
+		conn->epoch = rxrpc_epoch;
+		conn->in_clientflag = 0;
+		conn->out_clientflag = RXRPC_CLIENT_INITIATED;
+		conn->cid = 0;
+		conn->state = RXRPC_CONN_CLIENT;
+		conn->avail_calls = RXRPC_MAXCALLS - 1;
+		conn->security_level = rx->min_sec_level;
+		conn->key = key_get(rx->key);
+
+		ret = rxrpc_init_client_conn_security(conn);
+		if (ret < 0) {
+			key_put(conn->key);
+			kfree(conn);
+			_leave(" = %d [key]", ret);
+			return ret;
+		}
+
+		write_lock_bh(&rxrpc_connection_lock);
+		list_add_tail(&conn->link, &rxrpc_connections);
+		write_unlock_bh(&rxrpc_connection_lock);
+
+		spin_lock(&trans->client_lock);
+		atomic_inc(&trans->usage);
+
+		_net("CONNECT EXCL new %d on TRANS %d",
+		     conn->debug_id, conn->trans->debug_id);
+
+		rxrpc_assign_connection_id(conn);
+		rx->conn = conn;
+	} else {
+		spin_lock(&trans->client_lock);
+	}
+
+	/* we've got a connection with a free channel and we can now attach the
+	 * call to it
+	 * - we're holding the transport's client lock
+	 * - we're holding a reference on the connection
+	 */
+	for (chan = 0; chan < RXRPC_MAXCALLS; chan++)
+		if (!conn->channels[chan])
+			goto found_channel;
+	goto no_free_channels;
+
+found_channel:
+	atomic_inc(&conn->usage);
+	conn->channels[chan] = call;
+	call->conn = conn;
+	call->channel = chan;
+	call->cid = conn->cid | htonl(chan);
+	call->call_id = htonl(++conn->call_counter);
+
+	_net("CONNECT client on conn %d chan %d as call %x",
+	     conn->debug_id, chan, ntohl(call->call_id));
+
+	spin_unlock(&trans->client_lock);
+
+	rxrpc_add_call_ID_to_conn(conn, call);
+	_leave(" = 0");
+	return 0;
+
+no_free_channels:
+	spin_unlock(&trans->client_lock);
+	_leave(" = -ENOSR");
+	return -ENOSR;
+}
+
+/*
+ * find a connection for a call
+ * - called in process context with IRQs enabled
+ */
+int rxrpc_connect_call(struct rxrpc_sock *rx,
+		       struct rxrpc_transport *trans,
+		       struct rxrpc_conn_bundle *bundle,
+		       struct rxrpc_call *call,
+		       gfp_t gfp)
+{
+	struct rxrpc_connection *conn, *candidate;
+	int chan, ret;
+
+	DECLARE_WAITQUEUE(myself, current);
+
+	_enter("%p,%lx,", rx, call->user_call_ID);
+
+	if (test_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags))
+		return rxrpc_connect_exclusive(rx, trans, bundle->service_id,
+					       call, gfp);
+
+	spin_lock(&trans->client_lock);
+	for (;;) {
+		/* see if the bundle has a call slot available */
+		if (!list_empty(&bundle->avail_conns)) {
+			_debug("avail");
+			conn = list_entry(bundle->avail_conns.next,
+					  struct rxrpc_connection,
+					  bundle_link);
+			if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
+				list_del_init(&conn->bundle_link);
+				bundle->num_conns--;
+				continue;
+			}
+			if (--conn->avail_calls == 0)
+				list_move(&conn->bundle_link,
+					  &bundle->busy_conns);
+			ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS);
+			ASSERT(conn->channels[0] == NULL ||
+			       conn->channels[1] == NULL ||
+			       conn->channels[2] == NULL ||
+			       conn->channels[3] == NULL);
+			atomic_inc(&conn->usage);
+			break;
+		}
+
+		if (!list_empty(&bundle->unused_conns)) {
+			_debug("unused");
+			conn = list_entry(bundle->unused_conns.next,
+					  struct rxrpc_connection,
+					  bundle_link);
+			if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
+				list_del_init(&conn->bundle_link);
+				bundle->num_conns--;
+				continue;
+			}
+			ASSERTCMP(conn->avail_calls, ==, RXRPC_MAXCALLS);
+			conn->avail_calls = RXRPC_MAXCALLS - 1;
+			ASSERT(conn->channels[0] == NULL &&
+			       conn->channels[1] == NULL &&
+			       conn->channels[2] == NULL &&
+			       conn->channels[3] == NULL);
+			atomic_inc(&conn->usage);
+			list_move(&conn->bundle_link, &bundle->avail_conns);
+			break;
+		}
+
+		/* need to allocate a new connection */
+		_debug("get new conn [%d]", bundle->num_conns);
+
+		spin_unlock(&trans->client_lock);
+
+		if (signal_pending(current))
+			goto interrupted;
+
+		if (bundle->num_conns >= 20) {
+			_debug("too many conns");
+
+			if (!(gfp & __GFP_WAIT)) {
+				_leave(" = -EAGAIN");
+				return -EAGAIN;
+			}
+
+			add_wait_queue(&bundle->chanwait, &myself);
+			for (;;) {
+				set_current_state(TASK_INTERRUPTIBLE);
+				if (bundle->num_conns < 20 ||
+				    !list_empty(&bundle->unused_conns) ||
+				    !list_empty(&bundle->avail_conns))
+					break;
+				if (signal_pending(current))
+					goto interrupted_dequeue;
+				schedule();
+			}
+			remove_wait_queue(&bundle->chanwait, &myself);
+			__set_current_state(TASK_RUNNING);
+			spin_lock(&trans->client_lock);
+			continue;
+		}
+
+		/* not yet present - create a candidate for a new connection and then
+		 * redo the check */
+		candidate = rxrpc_alloc_connection(gfp);
+		if (!candidate) {
+			_leave(" = -ENOMEM");
+			return -ENOMEM;
+		}
+
+		candidate->trans = trans;
+		candidate->bundle = bundle;
+		candidate->service_id = bundle->service_id;
+		candidate->epoch = rxrpc_epoch;
+		candidate->in_clientflag = 0;
+		candidate->out_clientflag = RXRPC_CLIENT_INITIATED;
+		candidate->cid = 0;
+		candidate->state = RXRPC_CONN_CLIENT;
+		candidate->avail_calls = RXRPC_MAXCALLS;
+		candidate->security_level = rx->min_sec_level;
+		candidate->key = key_get(bundle->key);
+
+		ret = rxrpc_init_client_conn_security(candidate);
+		if (ret < 0) {
+			key_put(candidate->key);
+			kfree(candidate);
+			_leave(" = %d [key]", ret);
+			return ret;
+		}
+
+		write_lock_bh(&rxrpc_connection_lock);
+		list_add_tail(&candidate->link, &rxrpc_connections);
+		write_unlock_bh(&rxrpc_connection_lock);
+
+		spin_lock(&trans->client_lock);
+
+		list_add(&candidate->bundle_link, &bundle->unused_conns);
+		bundle->num_conns++;
+		atomic_inc(&bundle->usage);
+		atomic_inc(&trans->usage);
+
+		_net("CONNECT new %d on TRANS %d",
+		     candidate->debug_id, candidate->trans->debug_id);
+
+		rxrpc_assign_connection_id(candidate);
+		if (candidate->security)
+			candidate->security->prime_packet_security(candidate);
+
+		/* leave the candidate lurking in zombie mode attached to the
+		 * bundle until we're ready for it */
+		rxrpc_put_connection(candidate);
+		candidate = NULL;
+	}
+
+	/* we've got a connection with a free channel and we can now attach the
+	 * call to it
+	 * - we're holding the transport's client lock
+	 * - we're holding a reference on the connection
+	 * - we're holding a reference on the bundle
+	 */
+	for (chan = 0; chan < RXRPC_MAXCALLS; chan++)
+		if (!conn->channels[chan])
+			goto found_channel;
+	ASSERT(conn->channels[0] == NULL ||
+	       conn->channels[1] == NULL ||
+	       conn->channels[2] == NULL ||
+	       conn->channels[3] == NULL);
+	BUG();
+
+found_channel:
+	conn->channels[chan] = call;
+	call->conn = conn;
+	call->channel = chan;
+	call->cid = conn->cid | htonl(chan);
+	call->call_id = htonl(++conn->call_counter);
+
+	_net("CONNECT client on conn %d chan %d as call %x",
+	     conn->debug_id, chan, ntohl(call->call_id));
+
+	ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS);
+	spin_unlock(&trans->client_lock);
+
+	rxrpc_add_call_ID_to_conn(conn, call);
+
+	_leave(" = 0");
+	return 0;
+
+interrupted_dequeue:
+	remove_wait_queue(&bundle->chanwait, &myself);
+	__set_current_state(TASK_RUNNING);
+interrupted:
+	_leave(" = -ERESTARTSYS");
+	return -ERESTARTSYS;
+}
+
+/*
+ * get a record of an incoming connection
+ */
+struct rxrpc_connection *
+rxrpc_incoming_connection(struct rxrpc_transport *trans,
+			  struct rxrpc_header *hdr,
+			  gfp_t gfp)
+{
+	struct rxrpc_connection *conn, *candidate = NULL;
+	struct rb_node *p, **pp;
+	const char *new = "old";
+	__be32 epoch;
+	u32 conn_id;
+
+	_enter("");
+
+	ASSERT(hdr->flags & RXRPC_CLIENT_INITIATED);
+
+	epoch = hdr->epoch;
+	conn_id = ntohl(hdr->cid) & RXRPC_CIDMASK;
+
+	/* search the connection list first */
+	read_lock_bh(&trans->conn_lock);
+
+	p = trans->server_conns.rb_node;
+	while (p) {
+		conn = rb_entry(p, struct rxrpc_connection, node);
+
+		_debug("maybe %x", conn->real_conn_id);
+
+		if (epoch < conn->epoch)
+			p = p->rb_left;
+		else if (epoch > conn->epoch)
+			p = p->rb_right;
+		else if (conn_id < conn->real_conn_id)
+			p = p->rb_left;
+		else if (conn_id > conn->real_conn_id)
+			p = p->rb_right;
+		else
+			goto found_extant_connection;
+	}
+	read_unlock_bh(&trans->conn_lock);
+
+	/* not yet present - create a candidate for a new record and then
+	 * redo the search */
+	candidate = rxrpc_alloc_connection(gfp);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	candidate->trans = trans;
+	candidate->epoch = hdr->epoch;
+	candidate->cid = hdr->cid & cpu_to_be32(RXRPC_CIDMASK);
+	candidate->service_id = hdr->serviceId;
+	candidate->security_ix = hdr->securityIndex;
+	candidate->in_clientflag = RXRPC_CLIENT_INITIATED;
+	candidate->out_clientflag = 0;
+	candidate->real_conn_id = conn_id;
+	candidate->state = RXRPC_CONN_SERVER;
+	if (candidate->service_id)
+		candidate->state = RXRPC_CONN_SERVER_UNSECURED;
+
+	write_lock_bh(&trans->conn_lock);
+
+	pp = &trans->server_conns.rb_node;
+	p = NULL;
+	while (*pp) {
+		p = *pp;
+		conn = rb_entry(p, struct rxrpc_connection, node);
+
+		if (epoch < conn->epoch)
+			pp = &(*pp)->rb_left;
+		else if (epoch > conn->epoch)
+			pp = &(*pp)->rb_right;
+		else if (conn_id < conn->real_conn_id)
+			pp = &(*pp)->rb_left;
+		else if (conn_id > conn->real_conn_id)
+			pp = &(*pp)->rb_right;
+		else
+			goto found_extant_second;
+	}
+
+	/* we can now add the new candidate to the list */
+	conn = candidate;
+	candidate = NULL;
+	rb_link_node(&conn->node, p, pp);
+	rb_insert_color(&conn->node, &trans->server_conns);
+	atomic_inc(&conn->trans->usage);
+
+	write_unlock_bh(&trans->conn_lock);
+
+	write_lock_bh(&rxrpc_connection_lock);
+	list_add_tail(&conn->link, &rxrpc_connections);
+	write_unlock_bh(&rxrpc_connection_lock);
+
+	new = "new";
+
+success:
+	_net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->real_conn_id);
+
+	_leave(" = %p {u=%d}", conn, atomic_read(&conn->usage));
+	return conn;
+
+	/* we found the connection in the list immediately */
+found_extant_connection:
+	if (hdr->securityIndex != conn->security_ix) {
+		read_unlock_bh(&trans->conn_lock);
+		goto security_mismatch;
+	}
+	atomic_inc(&conn->usage);
+	read_unlock_bh(&trans->conn_lock);
+	goto success;
+
+	/* we found the connection on the second time through the list */
+found_extant_second:
+	if (hdr->securityIndex != conn->security_ix) {
+		write_unlock_bh(&trans->conn_lock);
+		goto security_mismatch;
+	}
+	atomic_inc(&conn->usage);
+	write_unlock_bh(&trans->conn_lock);
+	kfree(candidate);
+	goto success;
+
+security_mismatch:
+	kfree(candidate);
+	_leave(" = -EKEYREJECTED");
+	return ERR_PTR(-EKEYREJECTED);
+}
+
+/*
+ * find a connection based on transport and RxRPC connection ID for an incoming
+ * packet
+ */
+struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *trans,
+					       struct rxrpc_header *hdr)
+{
+	struct rxrpc_connection *conn;
+	struct rb_node *p;
+	__be32 epoch;
+	u32 conn_id;
+
+	_enter(",{%x,%x}", ntohl(hdr->cid), hdr->flags);
+
+	read_lock_bh(&trans->conn_lock);
+
+	conn_id = ntohl(hdr->cid) & RXRPC_CIDMASK;
+	epoch = hdr->epoch;
+
+	if (hdr->flags & RXRPC_CLIENT_INITIATED)
+		p = trans->server_conns.rb_node;
+	else
+		p = trans->client_conns.rb_node;
+
+	while (p) {
+		conn = rb_entry(p, struct rxrpc_connection, node);
+
+		_debug("maybe %x", conn->real_conn_id);
+
+		if (epoch < conn->epoch)
+			p = p->rb_left;
+		else if (epoch > conn->epoch)
+			p = p->rb_right;
+		else if (conn_id < conn->real_conn_id)
+			p = p->rb_left;
+		else if (conn_id > conn->real_conn_id)
+			p = p->rb_right;
+		else
+			goto found;
+	}
+
+	read_unlock_bh(&trans->conn_lock);
+	_leave(" = NULL");
+	return NULL;
+
+found:
+	atomic_inc(&conn->usage);
+	read_unlock_bh(&trans->conn_lock);
+	_leave(" = %p", conn);
+	return conn;
+}
+
+/*
+ * release a virtual connection
+ */
+void rxrpc_put_connection(struct rxrpc_connection *conn)
+{
+	_enter("%p{u=%d,d=%d}",
+	       conn, atomic_read(&conn->usage), conn->debug_id);
+
+	ASSERTCMP(atomic_read(&conn->usage), >, 0);
+
+	conn->put_time = get_seconds();
+	if (atomic_dec_and_test(&conn->usage)) {
+		_debug("zombie");
+		rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+	}
+
+	_leave("");
+}
+
+/*
+ * destroy a virtual connection
+ */
+static void rxrpc_destroy_connection(struct rxrpc_connection *conn)
+{
+	_enter("%p{%d}", conn, atomic_read(&conn->usage));
+
+	ASSERTCMP(atomic_read(&conn->usage), ==, 0);
+
+	_net("DESTROY CONN %d", conn->debug_id);
+
+	if (conn->bundle)
+		rxrpc_put_bundle(conn->trans, conn->bundle);
+
+	ASSERT(RB_EMPTY_ROOT(&conn->calls));
+	rxrpc_purge_queue(&conn->rx_queue);
+
+	rxrpc_clear_conn_security(conn);
+	rxrpc_put_transport(conn->trans);
+	kfree(conn);
+	_leave("");
+}
+
+/*
+ * reap dead connections
+ */
+static void rxrpc_connection_reaper(struct work_struct *work)
+{
+	struct rxrpc_connection *conn, *_p;
+	unsigned long now, earliest, reap_time;
+
+	LIST_HEAD(graveyard);
+
+	_enter("");
+
+	now = get_seconds();
+	earliest = ULONG_MAX;
+
+	write_lock_bh(&rxrpc_connection_lock);
+	list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) {
+		_debug("reap CONN %d { u=%d,t=%ld }",
+		       conn->debug_id, atomic_read(&conn->usage),
+		       (long) now - (long) conn->put_time);
+
+		if (likely(atomic_read(&conn->usage) > 0))
+			continue;
+
+		spin_lock(&conn->trans->client_lock);
+		write_lock(&conn->trans->conn_lock);
+		reap_time = conn->put_time + rxrpc_connection_expiry;
+
+		if (atomic_read(&conn->usage) > 0) {
+			;
+		} else if (reap_time <= now) {
+			list_move_tail(&conn->link, &graveyard);
+			if (conn->out_clientflag)
+				rb_erase(&conn->node,
+					 &conn->trans->client_conns);
+			else
+				rb_erase(&conn->node,
+					 &conn->trans->server_conns);
+			if (conn->bundle) {
+				list_del_init(&conn->bundle_link);
+				conn->bundle->num_conns--;
+			}
+
+		} else if (reap_time < earliest) {
+			earliest = reap_time;
+		}
+
+		write_unlock(&conn->trans->conn_lock);
+		spin_unlock(&conn->trans->client_lock);
+	}
+	write_unlock_bh(&rxrpc_connection_lock);
+
+	if (earliest != ULONG_MAX) {
+		_debug("reschedule reaper %ld", (long) earliest - now);
+		ASSERTCMP(earliest, >, now);
+		rxrpc_queue_delayed_work(&rxrpc_connection_reap,
+					 (earliest - now) * HZ);
+	}
+
+	/* then destroy all those pulled out */
+	while (!list_empty(&graveyard)) {
+		conn = list_entry(graveyard.next, struct rxrpc_connection,
+				  link);
+		list_del_init(&conn->link);
+
+		ASSERTCMP(atomic_read(&conn->usage), ==, 0);
+		rxrpc_destroy_connection(conn);
+	}
+
+	_leave("");
+}
+
+/*
+ * preemptively destroy all the connection records rather than waiting for them
+ * to time out
+ */
+void __exit rxrpc_destroy_all_connections(void)
+{
+	_enter("");
+
+	rxrpc_connection_expiry = 0;
+	cancel_delayed_work(&rxrpc_connection_reap);
+	rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+
+	_leave("");
+}

net/rxrpc/ar-connevent.c

@@ -0,0 +1,405 @@
+/* connection-level event handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include "ar-internal.h"
+
+/*
+ * pass a connection-level abort onto all calls on that connection
+ */
+static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state,
+			      u32 abort_code)
+{
+	struct rxrpc_call *call;
+	struct rb_node *p;
+
+	_enter("{%d},%x", conn->debug_id, abort_code);
+
+	read_lock_bh(&conn->lock);
+
+	for (p = rb_first(&conn->calls); p; p = rb_next(p)) {
+		call = rb_entry(p, struct rxrpc_call, conn_node);
+		write_lock(&call->state_lock);
+		if (call->state <= RXRPC_CALL_COMPLETE) {
+			call->state = state;
+			call->abort_code = abort_code;
+			if (state == RXRPC_CALL_LOCALLY_ABORTED)
+				set_bit(RXRPC_CALL_CONN_ABORT, &call->events);
+			else
+				set_bit(RXRPC_CALL_RCVD_ABORT, &call->events);
+			rxrpc_queue_call(call);
+		}
+		write_unlock(&call->state_lock);
+	}
+
+	read_unlock_bh(&conn->lock);
+	_leave("");
+}
+
+/*
+ * generate a connection-level abort
+ */
+static int rxrpc_abort_connection(struct rxrpc_connection *conn,
+				  u32 error, u32 abort_code)
+{
+	struct rxrpc_header hdr;
+	struct msghdr msg;
+	struct kvec iov[2];
+	__be32 word;
+	size_t len;
+	int ret;
+
+	_enter("%d,,%u,%u", conn->debug_id, error, abort_code);
+
+	/* generate a connection-level abort */
+	spin_lock_bh(&conn->state_lock);
+	if (conn->state < RXRPC_CONN_REMOTELY_ABORTED) {
+		conn->state = RXRPC_CONN_LOCALLY_ABORTED;
+		conn->error = error;
+		spin_unlock_bh(&conn->state_lock);
+	} else {
+		spin_unlock_bh(&conn->state_lock);
+		_leave(" = 0 [already dead]");
+		return 0;
+	}
+
+	rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code);
+
+	msg.msg_name	= &conn->trans->peer->srx.transport.sin;
+	msg.msg_namelen	= sizeof(conn->trans->peer->srx.transport.sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	hdr.epoch	= conn->epoch;
+	hdr.cid		= conn->cid;
+	hdr.callNumber	= 0;
+	hdr.seq		= 0;
+	hdr.type	= RXRPC_PACKET_TYPE_ABORT;
+	hdr.flags	= conn->out_clientflag;
+	hdr.userStatus	= 0;
+	hdr.securityIndex = conn->security_ix;
+	hdr._rsvd	= 0;
+	hdr.serviceId	= conn->service_id;
+
+	word = htonl(abort_code);
+
+	iov[0].iov_base	= &hdr;
+	iov[0].iov_len	= sizeof(hdr);
+	iov[1].iov_base	= &word;
+	iov[1].iov_len	= sizeof(word);
+
+	len = iov[0].iov_len + iov[1].iov_len;
+
+	hdr.serial = htonl(atomic_inc_return(&conn->serial));
+	_proto("Tx CONN ABORT %%%u { %d }", ntohl(hdr.serial), abort_code);
+
+	ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len);
+	if (ret < 0) {
+		_debug("sendmsg failed: %d", ret);
+		return -EAGAIN;
+	}
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * mark a call as being on a now-secured channel
+ * - must be called with softirqs disabled
+ */
+static void rxrpc_call_is_secure(struct rxrpc_call *call)
+{
+	_enter("%p", call);
+	if (call) {
+		read_lock(&call->state_lock);
+		if (call->state < RXRPC_CALL_COMPLETE &&
+		    !test_and_set_bit(RXRPC_CALL_SECURED, &call->events))
+			rxrpc_queue_call(call);
+		read_unlock(&call->state_lock);
+	}
+}
+
+/*
+ * connection-level Rx packet processor
+ */
+static int rxrpc_process_event(struct rxrpc_connection *conn,
+			       struct sk_buff *skb,
+			       u32 *_abort_code)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	__be32 tmp;
+	u32 serial;
+	int loop, ret;
+
+	if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
+		kleave(" = -ECONNABORTED [%u]", conn->state);
+		return -ECONNABORTED;
+	}
+
+	serial = ntohl(sp->hdr.serial);
+
+	_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, serial);
+
+	switch (sp->hdr.type) {
+	case RXRPC_PACKET_TYPE_ABORT:
+		if (skb_copy_bits(skb, 0, &tmp, sizeof(tmp)) < 0)
+			return -EPROTO;
+		_proto("Rx ABORT %%%u { ac=%d }", serial, ntohl(tmp));
+
+		conn->state = RXRPC_CONN_REMOTELY_ABORTED;
+		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED,
+				  ntohl(tmp));
+		return -ECONNABORTED;
+
+	case RXRPC_PACKET_TYPE_CHALLENGE:
+		if (conn->security)
+			return conn->security->respond_to_challenge(
+				conn, skb, _abort_code);
+		return -EPROTO;
+
+	case RXRPC_PACKET_TYPE_RESPONSE:
+		if (!conn->security)
+			return -EPROTO;
+
+		ret = conn->security->verify_response(conn, skb, _abort_code);
+		if (ret < 0)
+			return ret;
+
+		ret = conn->security->init_connection_security(conn);
+		if (ret < 0)
+			return ret;
+
+		conn->security->prime_packet_security(conn);
+		read_lock_bh(&conn->lock);
+		spin_lock(&conn->state_lock);
+
+		if (conn->state == RXRPC_CONN_SERVER_CHALLENGING) {
+			conn->state = RXRPC_CONN_SERVER;
+			for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+				rxrpc_call_is_secure(conn->channels[loop]);
+		}
+
+		spin_unlock(&conn->state_lock);
+		read_unlock_bh(&conn->lock);
+		return 0;
+
+	default:
+		_leave(" = -EPROTO [%u]", sp->hdr.type);
+		return -EPROTO;
+	}
+}
+
+/*
+ * set up security and issue a challenge
+ */
+static void rxrpc_secure_connection(struct rxrpc_connection *conn)
+{
+	u32 abort_code;
+	int ret;
+
+	_enter("{%d}", conn->debug_id);
+
+	ASSERT(conn->security_ix != 0);
+
+	if (!conn->key) {
+		_debug("set up security");
+		ret = rxrpc_init_server_conn_security(conn);
+		switch (ret) {
+		case 0:
+			break;
+		case -ENOENT:
+			abort_code = RX_CALL_DEAD;
+			goto abort;
+		default:
+			abort_code = RXKADNOAUTH;
+			goto abort;
+		}
+	}
+
+	ASSERT(conn->security != NULL);
+
+	if (conn->security->issue_challenge(conn) < 0) {
+		abort_code = RX_CALL_DEAD;
+		ret = -ENOMEM;
+		goto abort;
+	}
+
+	_leave("");
+	return;
+
+abort:
+	_debug("abort %d, %d", ret, abort_code);
+	rxrpc_abort_connection(conn, -ret, abort_code);
+	_leave(" [aborted]");
+}
+
+/*
+ * connection-level event processor
+ */
+void rxrpc_process_connection(struct work_struct *work)
+{
+	struct rxrpc_connection *conn =
+		container_of(work, struct rxrpc_connection, processor);
+	struct sk_buff *skb;
+	u32 abort_code = RX_PROTOCOL_ERROR;
+	int ret;
+
+	_enter("{%d}", conn->debug_id);
+
+	atomic_inc(&conn->usage);
+
+	if (test_and_clear_bit(RXRPC_CONN_CHALLENGE, &conn->events)) {
+		rxrpc_secure_connection(conn);
+		rxrpc_put_connection(conn);
+	}
+
+	/* go through the conn-level event packets, releasing the ref on this
+	 * connection that each one has when we've finished with it */
+	while ((skb = skb_dequeue(&conn->rx_queue))) {
+		ret = rxrpc_process_event(conn, skb, &abort_code);
+		switch (ret) {
+		case -EPROTO:
+		case -EKEYEXPIRED:
+		case -EKEYREJECTED:
+			goto protocol_error;
+		case -EAGAIN:
+			goto requeue_and_leave;
+		case -ECONNABORTED:
+		default:
+			rxrpc_put_connection(conn);
+			rxrpc_free_skb(skb);
+			break;
+		}
+	}
+
+out:
+	rxrpc_put_connection(conn);
+	_leave("");
+	return;
+
+requeue_and_leave:
+	skb_queue_head(&conn->rx_queue, skb);
+	goto out;
+
+protocol_error:
+	if (rxrpc_abort_connection(conn, -ret, abort_code) < 0)
+		goto requeue_and_leave;
+	rxrpc_put_connection(conn);
+	rxrpc_free_skb(skb);
+	_leave(" [EPROTO]");
+	goto out;
+}
+
+/*
+ * put a packet up for transport-level abort
+ */
+void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb)
+{
+	CHECK_SLAB_OKAY(&local->usage);
+
+	if (!atomic_inc_not_zero(&local->usage)) {
+		printk("resurrected on reject\n");
+		BUG();
+	}
+
+	skb_queue_tail(&local->reject_queue, skb);
+	rxrpc_queue_work(&local->rejecter);
+}
+
+/*
+ * reject packets through the local endpoint
+ */
+void rxrpc_reject_packets(struct work_struct *work)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_in sin;
+	} sa;
+	struct rxrpc_skb_priv *sp;
+	struct rxrpc_header hdr;
+	struct rxrpc_local *local;
+	struct sk_buff *skb;
+	struct msghdr msg;
+	struct kvec iov[2];
+	size_t size;
+	__be32 code;
+
+	local = container_of(work, struct rxrpc_local, rejecter);
+	rxrpc_get_local(local);
+
+	_enter("%d", local->debug_id);
+
+	iov[0].iov_base = &hdr;
+	iov[0].iov_len = sizeof(hdr);
+	iov[1].iov_base = &code;
+	iov[1].iov_len = sizeof(code);
+	size = sizeof(hdr) + sizeof(code);
+
+	msg.msg_name = &sa;
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags = 0;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa.sa_family = local->srx.transport.family;
+	switch (sa.sa.sa_family) {
+	case AF_INET:
+		msg.msg_namelen = sizeof(sa.sin);
+		break;
+	default:
+		msg.msg_namelen = 0;
+		break;
+	}
+
+	memset(&hdr, 0, sizeof(hdr));
+	hdr.type = RXRPC_PACKET_TYPE_ABORT;
+
+	while ((skb = skb_dequeue(&local->reject_queue))) {
+		sp = rxrpc_skb(skb);
+		switch (sa.sa.sa_family) {
+		case AF_INET:
+			sa.sin.sin_port = udp_hdr(skb)->source;
+			sa.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+			code = htonl(skb->priority);
+
+			hdr.epoch = sp->hdr.epoch;
+			hdr.cid = sp->hdr.cid;
+			hdr.callNumber = sp->hdr.callNumber;
+			hdr.serviceId = sp->hdr.serviceId;
+			hdr.flags = sp->hdr.flags;
+			hdr.flags ^= RXRPC_CLIENT_INITIATED;
+			hdr.flags &= RXRPC_CLIENT_INITIATED;
+
+			kernel_sendmsg(local->socket, &msg, iov, 2, size);
+			break;
+
+		default:
+			break;
+		}
+
+		rxrpc_free_skb(skb);
+		rxrpc_put_local(local);
+	}
+
+	rxrpc_put_local(local);
+	_leave("");
+}

net/rxrpc/ar-error.c

@@ -0,0 +1,236 @@
+/* Error message handling (ICMP)
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include "ar-internal.h"
+
+/*
+ * handle an error received on the local endpoint
+ */
+void rxrpc_UDP_error_report(struct sock *sk)
+{
+	struct sock_exterr_skb *serr;
+	struct rxrpc_transport *trans;
+	struct rxrpc_local *local = sk->sk_user_data;
+	struct rxrpc_peer *peer;
+	struct sk_buff *skb;
+	__be32 addr;
+	__be16 port;
+
+	_enter("%p{%d}", sk, local->debug_id);
+
+	skb = sock_dequeue_err_skb(sk);
+	if (!skb) {
+		_leave("UDP socket errqueue empty");
+		return;
+	}
+
+	rxrpc_new_skb(skb);
+
+	serr = SKB_EXT_ERR(skb);
+	addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
+	port = serr->port;
+
+	_net("Rx UDP Error from %pI4:%hu", &addr, ntohs(port));
+	_debug("Msg l:%d d:%d", skb->len, skb->data_len);
+
+	peer = rxrpc_find_peer(local, addr, port);
+	if (IS_ERR(peer)) {
+		rxrpc_free_skb(skb);
+		_leave(" [no peer]");
+		return;
+	}
+
+	trans = rxrpc_find_transport(local, peer);
+	if (!trans) {
+		rxrpc_put_peer(peer);
+		rxrpc_free_skb(skb);
+		_leave(" [no trans]");
+		return;
+	}
+
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
+	    serr->ee.ee_type == ICMP_DEST_UNREACH &&
+	    serr->ee.ee_code == ICMP_FRAG_NEEDED
+	    ) {
+		u32 mtu = serr->ee.ee_info;
+
+		_net("Rx Received ICMP Fragmentation Needed (%d)", mtu);
+
+		/* wind down the local interface MTU */
+		if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
+			peer->if_mtu = mtu;
+			_net("I/F MTU %u", mtu);
+		}
+
+		if (mtu == 0) {
+			/* they didn't give us a size, estimate one */
+			mtu = peer->if_mtu;
+			if (mtu > 1500) {
+				mtu >>= 1;
+				if (mtu < 1500)
+					mtu = 1500;
+			} else {
+				mtu -= 100;
+				if (mtu < peer->hdrsize)
+					mtu = peer->hdrsize + 4;
+			}
+		}
+
+		if (mtu < peer->mtu) {
+			spin_lock_bh(&peer->lock);
+			peer->mtu = mtu;
+			peer->maxdata = peer->mtu - peer->hdrsize;
+			spin_unlock_bh(&peer->lock);
+			_net("Net MTU %u (maxdata %u)",
+			     peer->mtu, peer->maxdata);
+		}
+	}
+
+	rxrpc_put_peer(peer);
+
+	/* pass the transport ref to error_handler to release */
+	skb_queue_tail(&trans->error_queue, skb);
+	rxrpc_queue_work(&trans->error_handler);
+
+	_leave("");
+}
+
+/*
+ * deal with UDP error messages
+ */
+void rxrpc_UDP_error_handler(struct work_struct *work)
+{
+	struct sock_extended_err *ee;
+	struct sock_exterr_skb *serr;
+	struct rxrpc_transport *trans =
+		container_of(work, struct rxrpc_transport, error_handler);
+	struct sk_buff *skb;
+	int err;
+
+	_enter("");
+
+	skb = skb_dequeue(&trans->error_queue);
+	if (!skb)
+		return;
+
+	serr = SKB_EXT_ERR(skb);
+	ee = &serr->ee;
+
+	_net("Rx Error o=%d t=%d c=%d e=%d",
+	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
+
+	err = ee->ee_errno;
+
+	switch (ee->ee_origin) {
+	case SO_EE_ORIGIN_ICMP:
+		switch (ee->ee_type) {
+		case ICMP_DEST_UNREACH:
+			switch (ee->ee_code) {
+			case ICMP_NET_UNREACH:
+				_net("Rx Received ICMP Network Unreachable");
+				err = ENETUNREACH;
+				break;
+			case ICMP_HOST_UNREACH:
+				_net("Rx Received ICMP Host Unreachable");
+				err = EHOSTUNREACH;
+				break;
+			case ICMP_PORT_UNREACH:
+				_net("Rx Received ICMP Port Unreachable");
+				err = ECONNREFUSED;
+				break;
+			case ICMP_FRAG_NEEDED:
+				_net("Rx Received ICMP Fragmentation Needed (%d)",
+				     ee->ee_info);
+				err = 0; /* dealt with elsewhere */
+				break;
+			case ICMP_NET_UNKNOWN:
+				_net("Rx Received ICMP Unknown Network");
+				err = ENETUNREACH;
+				break;
+			case ICMP_HOST_UNKNOWN:
+				_net("Rx Received ICMP Unknown Host");
+				err = EHOSTUNREACH;
+				break;
+			default:
+				_net("Rx Received ICMP DestUnreach code=%u",
+				     ee->ee_code);
+				break;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			_net("Rx Received ICMP TTL Exceeded");
+			break;
+
+		default:
+			_proto("Rx Received ICMP error { type=%u code=%u }",
+			       ee->ee_type, ee->ee_code);
+			break;
+		}
+		break;
+
+	case SO_EE_ORIGIN_LOCAL:
+		_proto("Rx Received local error { error=%d }",
+		       ee->ee_errno);
+		break;
+
+	case SO_EE_ORIGIN_NONE:
+	case SO_EE_ORIGIN_ICMP6:
+	default:
+		_proto("Rx Received error report { orig=%u }",
+		       ee->ee_origin);
+		break;
+	}
+
+	/* terminate all the affected calls if there's an unrecoverable
+	 * error */
+	if (err) {
+		struct rxrpc_call *call, *_n;
+
+		_debug("ISSUE ERROR %d", err);
+
+		spin_lock_bh(&trans->peer->lock);
+		trans->peer->net_error = err;
+
+		list_for_each_entry_safe(call, _n, &trans->peer->error_targets,
+					 error_link) {
+			write_lock(&call->state_lock);
+			if (call->state != RXRPC_CALL_COMPLETE &&
+			    call->state < RXRPC_CALL_NETWORK_ERROR) {
+				call->state = RXRPC_CALL_NETWORK_ERROR;
+				set_bit(RXRPC_CALL_RCVD_ERROR, &call->events);
+				rxrpc_queue_call(call);
+			}
+			write_unlock(&call->state_lock);
+			list_del_init(&call->error_link);
+		}
+
+		spin_unlock_bh(&trans->peer->lock);
+	}
+
+	if (!skb_queue_empty(&trans->error_queue))
+		rxrpc_queue_work(&trans->error_handler);
+
+	rxrpc_free_skb(skb);
+	rxrpc_put_transport(trans);
+	_leave("");
+}

net/rxrpc/ar-input.c

@@ -0,0 +1,767 @@
+/* RxRPC packet reception
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <linux/gfp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/net_namespace.h>
+#include "ar-internal.h"
+
+const char *rxrpc_pkts[] = {
+	"?00",
+	"DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG",
+	"?09", "?10", "?11", "?12", "?13", "?14", "?15"
+};
+
+/*
+ * queue a packet for recvmsg to pass to userspace
+ * - the caller must hold a lock on call->lock
+ * - must not be called with interrupts disabled (sk_filter() disables BH's)
+ * - eats the packet whether successful or not
+ * - there must be just one reference to the packet, which the caller passes to
+ *   this function
+ */
+int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
+			bool force, bool terminal)
+{
+	struct rxrpc_skb_priv *sp;
+	struct rxrpc_sock *rx = call->socket;
+	struct sock *sk;
+	int ret;
+
+	_enter(",,%d,%d", force, terminal);
+
+	ASSERT(!irqs_disabled());
+
+	sp = rxrpc_skb(skb);
+	ASSERTCMP(sp->call, ==, call);
+
+	/* if we've already posted the terminal message for a call, then we
+	 * don't post any more */
+	if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) {
+		_debug("already terminated");
+		ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE);
+		skb->destructor = NULL;
+		sp->call = NULL;
+		rxrpc_put_call(call);
+		rxrpc_free_skb(skb);
+		return 0;
+	}
+
+	sk = &rx->sk;
+
+	if (!force) {
+		/* cast skb->rcvbuf to unsigned...  It's pointless, but
+		 * reduces number of warnings when compiling with -W
+		 * --ANK */
+//		ret = -ENOBUFS;
+//		if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
+//		    (unsigned int) sk->sk_rcvbuf)
+//			goto out;
+
+		ret = sk_filter(sk, skb);
+		if (ret < 0)
+			goto out;
+	}
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags) &&
+	    !test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
+	    call->socket->sk.sk_state != RXRPC_CLOSE) {
+		skb->destructor = rxrpc_packet_destructor;
+		skb->dev = NULL;
+		skb->sk = sk;
+		atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+
+		if (terminal) {
+			_debug("<<<< TERMINAL MESSAGE >>>>");
+			set_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags);
+		}
+
+		/* allow interception by a kernel service */
+		if (rx->interceptor) {
+			rx->interceptor(sk, call->user_call_ID, skb);
+			spin_unlock_bh(&sk->sk_receive_queue.lock);
+		} else {
+			_net("post skb %p", skb);
+			__skb_queue_tail(&sk->sk_receive_queue, skb);
+			spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+			if (!sock_flag(sk, SOCK_DEAD))
+				sk->sk_data_ready(sk);
+		}
+		skb = NULL;
+	} else {
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+	}
+	ret = 0;
+
+out:
+	/* release the socket buffer */
+	if (skb) {
+		skb->destructor = NULL;
+		sp->call = NULL;
+		rxrpc_put_call(call);
+		rxrpc_free_skb(skb);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * process a DATA packet, posting the packet to the appropriate queue
+ * - eats the packet if successful
+ */
+static int rxrpc_fast_process_data(struct rxrpc_call *call,
+				   struct sk_buff *skb, u32 seq)
+{
+	struct rxrpc_skb_priv *sp;
+	bool terminal;
+	int ret, ackbit, ack;
+
+	_enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq);
+
+	sp = rxrpc_skb(skb);
+	ASSERTCMP(sp->call, ==, NULL);
+
+	spin_lock(&call->lock);
+
+	if (call->state > RXRPC_CALL_COMPLETE)
+		goto discard;
+
+	ASSERTCMP(call->rx_data_expect, >=, call->rx_data_post);
+	ASSERTCMP(call->rx_data_post, >=, call->rx_data_recv);
+	ASSERTCMP(call->rx_data_recv, >=, call->rx_data_eaten);
+
+	if (seq < call->rx_data_post) {
+		_debug("dup #%u [-%u]", seq, call->rx_data_post);
+		ack = RXRPC_ACK_DUPLICATE;
+		ret = -ENOBUFS;
+		goto discard_and_ack;
+	}
+
+	/* we may already have the packet in the out of sequence queue */
+	ackbit = seq - (call->rx_data_eaten + 1);
+	ASSERTCMP(ackbit, >=, 0);
+	if (__test_and_set_bit(ackbit, call->ackr_window)) {
+		_debug("dup oos #%u [%u,%u]",
+		       seq, call->rx_data_eaten, call->rx_data_post);
+		ack = RXRPC_ACK_DUPLICATE;
+		goto discard_and_ack;
+	}
+
+	if (seq >= call->ackr_win_top) {
+		_debug("exceed #%u [%u]", seq, call->ackr_win_top);
+		__clear_bit(ackbit, call->ackr_window);
+		ack = RXRPC_ACK_EXCEEDS_WINDOW;
+		goto discard_and_ack;
+	}
+
+	if (seq == call->rx_data_expect) {
+		clear_bit(RXRPC_CALL_EXPECT_OOS, &call->flags);
+		call->rx_data_expect++;
+	} else if (seq > call->rx_data_expect) {
+		_debug("oos #%u [%u]", seq, call->rx_data_expect);
+		call->rx_data_expect = seq + 1;
+		if (test_and_set_bit(RXRPC_CALL_EXPECT_OOS, &call->flags)) {
+			ack = RXRPC_ACK_OUT_OF_SEQUENCE;
+			goto enqueue_and_ack;
+		}
+		goto enqueue_packet;
+	}
+
+	if (seq != call->rx_data_post) {
+		_debug("ahead #%u [%u]", seq, call->rx_data_post);
+		goto enqueue_packet;
+	}
+
+	if (test_bit(RXRPC_CALL_RCVD_LAST, &call->flags))
+		goto protocol_error;
+
+	/* if the packet need security things doing to it, then it goes down
+	 * the slow path */
+	if (call->conn->security)
+		goto enqueue_packet;
+
+	sp->call = call;
+	rxrpc_get_call(call);
+	terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) &&
+		    !(sp->hdr.flags & RXRPC_CLIENT_INITIATED));
+	ret = rxrpc_queue_rcv_skb(call, skb, false, terminal);
+	if (ret < 0) {
+		if (ret == -ENOMEM || ret == -ENOBUFS) {
+			__clear_bit(ackbit, call->ackr_window);
+			ack = RXRPC_ACK_NOSPACE;
+			goto discard_and_ack;
+		}
+		goto out;
+	}
+
+	skb = NULL;
+
+	_debug("post #%u", seq);
+	ASSERTCMP(call->rx_data_post, ==, seq);
+	call->rx_data_post++;
+
+	if (sp->hdr.flags & RXRPC_LAST_PACKET)
+		set_bit(RXRPC_CALL_RCVD_LAST, &call->flags);
+
+	/* if we've reached an out of sequence packet then we need to drain
+	 * that queue into the socket Rx queue now */
+	if (call->rx_data_post == call->rx_first_oos) {
+		_debug("drain rx oos now");
+		read_lock(&call->state_lock);
+		if (call->state < RXRPC_CALL_COMPLETE &&
+		    !test_and_set_bit(RXRPC_CALL_DRAIN_RX_OOS, &call->events))
+			rxrpc_queue_call(call);
+		read_unlock(&call->state_lock);
+	}
+
+	spin_unlock(&call->lock);
+	atomic_inc(&call->ackr_not_idle);
+	rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false);
+	_leave(" = 0 [posted]");
+	return 0;
+
+protocol_error:
+	ret = -EBADMSG;
+out:
+	spin_unlock(&call->lock);
+	_leave(" = %d", ret);
+	return ret;
+
+discard_and_ack:
+	_debug("discard and ACK packet %p", skb);
+	__rxrpc_propose_ACK(call, ack, sp->hdr.serial, true);
+discard:
+	spin_unlock(&call->lock);
+	rxrpc_free_skb(skb);
+	_leave(" = 0 [discarded]");
+	return 0;
+
+enqueue_and_ack:
+	__rxrpc_propose_ACK(call, ack, sp->hdr.serial, true);
+enqueue_packet:
+	_net("defer skb %p", skb);
+	spin_unlock(&call->lock);
+	skb_queue_tail(&call->rx_queue, skb);
+	atomic_inc(&call->ackr_not_idle);
+	read_lock(&call->state_lock);
+	if (call->state < RXRPC_CALL_DEAD)
+		rxrpc_queue_call(call);
+	read_unlock(&call->state_lock);
+	_leave(" = 0 [queued]");
+	return 0;
+}
+
+/*
+ * assume an implicit ACKALL of the transmission phase of a client socket upon
+ * reception of the first reply packet
+ */
+static void rxrpc_assume_implicit_ackall(struct rxrpc_call *call, u32 serial)
+{
+	write_lock_bh(&call->state_lock);
+
+	switch (call->state) {
+	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
+		call->state = RXRPC_CALL_CLIENT_RECV_REPLY;
+		call->acks_latest = serial;
+
+		_debug("implicit ACKALL %%%u", call->acks_latest);
+		set_bit(RXRPC_CALL_RCVD_ACKALL, &call->events);
+		write_unlock_bh(&call->state_lock);
+
+		if (try_to_del_timer_sync(&call->resend_timer) >= 0) {
+			clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events);
+			clear_bit(RXRPC_CALL_RESEND, &call->events);
+			clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
+		}
+		break;
+
+	default:
+		write_unlock_bh(&call->state_lock);
+		break;
+	}
+}
+
+/*
+ * post an incoming packet to the nominated call to deal with
+ * - must get rid of the sk_buff, either by freeing it or by queuing it
+ */
+void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	__be32 _abort_code;
+	u32 serial, hi_serial, seq, abort_code;
+
+	_enter("%p,%p", call, skb);
+
+	ASSERT(!irqs_disabled());
+
+#if 0 // INJECT RX ERROR
+	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) {
+		static int skip = 0;
+		if (++skip == 3) {
+			printk("DROPPED 3RD PACKET!!!!!!!!!!!!!\n");
+			skip = 0;
+			goto free_packet;
+		}
+	}
+#endif
+
+	/* track the latest serial number on this connection for ACK packet
+	 * information */
+	serial = ntohl(sp->hdr.serial);
+	hi_serial = atomic_read(&call->conn->hi_serial);
+	while (serial > hi_serial)
+		hi_serial = atomic_cmpxchg(&call->conn->hi_serial, hi_serial,
+					   serial);
+
+	/* request ACK generation for any ACK or DATA packet that requests
+	 * it */
+	if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
+		_proto("ACK Requested on %%%u", serial);
+		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false);
+	}
+
+	switch (sp->hdr.type) {
+	case RXRPC_PACKET_TYPE_ABORT:
+		_debug("abort");
+
+		if (skb_copy_bits(skb, 0, &_abort_code,
+				  sizeof(_abort_code)) < 0)
+			goto protocol_error;
+
+		abort_code = ntohl(_abort_code);
+		_proto("Rx ABORT %%%u { %x }", serial, abort_code);
+
+		write_lock_bh(&call->state_lock);
+		if (call->state < RXRPC_CALL_COMPLETE) {
+			call->state = RXRPC_CALL_REMOTELY_ABORTED;
+			call->abort_code = abort_code;
+			set_bit(RXRPC_CALL_RCVD_ABORT, &call->events);
+			rxrpc_queue_call(call);
+		}
+		goto free_packet_unlock;
+
+	case RXRPC_PACKET_TYPE_BUSY:
+		_proto("Rx BUSY %%%u", serial);
+
+		if (call->conn->out_clientflag)
+			goto protocol_error;
+
+		write_lock_bh(&call->state_lock);
+		switch (call->state) {
+		case RXRPC_CALL_CLIENT_SEND_REQUEST:
+			call->state = RXRPC_CALL_SERVER_BUSY;
+			set_bit(RXRPC_CALL_RCVD_BUSY, &call->events);
+			rxrpc_queue_call(call);
+		case RXRPC_CALL_SERVER_BUSY:
+			goto free_packet_unlock;
+		default:
+			goto protocol_error_locked;
+		}
+
+	default:
+		_proto("Rx %s %%%u", rxrpc_pkts[sp->hdr.type], serial);
+		goto protocol_error;
+
+	case RXRPC_PACKET_TYPE_DATA:
+		seq = ntohl(sp->hdr.seq);
+
+		_proto("Rx DATA %%%u { #%u }", serial, seq);
+
+		if (seq == 0)
+			goto protocol_error;
+
+		call->ackr_prev_seq = sp->hdr.seq;
+
+		/* received data implicitly ACKs all of the request packets we
+		 * sent when we're acting as a client */
+		if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
+			rxrpc_assume_implicit_ackall(call, serial);
+
+		switch (rxrpc_fast_process_data(call, skb, seq)) {
+		case 0:
+			skb = NULL;
+			goto done;
+
+		default:
+			BUG();
+
+			/* data packet received beyond the last packet */
+		case -EBADMSG:
+			goto protocol_error;
+		}
+
+	case RXRPC_PACKET_TYPE_ACKALL:
+	case RXRPC_PACKET_TYPE_ACK:
+		/* ACK processing is done in process context */
+		read_lock_bh(&call->state_lock);
+		if (call->state < RXRPC_CALL_DEAD) {
+			skb_queue_tail(&call->rx_queue, skb);
+			rxrpc_queue_call(call);
+			skb = NULL;
+		}
+		read_unlock_bh(&call->state_lock);
+		goto free_packet;
+	}
+
+protocol_error:
+	_debug("protocol error");
+	write_lock_bh(&call->state_lock);
+protocol_error_locked:
+	if (call->state <= RXRPC_CALL_COMPLETE) {
+		call->state = RXRPC_CALL_LOCALLY_ABORTED;
+		call->abort_code = RX_PROTOCOL_ERROR;
+		set_bit(RXRPC_CALL_ABORT, &call->events);
+		rxrpc_queue_call(call);
+	}
+free_packet_unlock:
+	write_unlock_bh(&call->state_lock);
+free_packet:
+	rxrpc_free_skb(skb);
+done:
+	_leave("");
+}
+
+/*
+ * split up a jumbo data packet
+ */
+static void rxrpc_process_jumbo_packet(struct rxrpc_call *call,
+				       struct sk_buff *jumbo)
+{
+	struct rxrpc_jumbo_header jhdr;
+	struct rxrpc_skb_priv *sp;
+	struct sk_buff *part;
+
+	_enter(",{%u,%u}", jumbo->data_len, jumbo->len);
+
+	sp = rxrpc_skb(jumbo);
+
+	do {
+		sp->hdr.flags &= ~RXRPC_JUMBO_PACKET;
+
+		/* make a clone to represent the first subpacket in what's left
+		 * of the jumbo packet */
+		part = skb_clone(jumbo, GFP_ATOMIC);
+		if (!part) {
+			/* simply ditch the tail in the event of ENOMEM */
+			pskb_trim(jumbo, RXRPC_JUMBO_DATALEN);
+			break;
+		}
+		rxrpc_new_skb(part);
+
+		pskb_trim(part, RXRPC_JUMBO_DATALEN);
+
+		if (!pskb_pull(jumbo, RXRPC_JUMBO_DATALEN))
+			goto protocol_error;
+
+		if (skb_copy_bits(jumbo, 0, &jhdr, sizeof(jhdr)) < 0)
+			goto protocol_error;
+		if (!pskb_pull(jumbo, sizeof(jhdr)))
+			BUG();
+
+		sp->hdr.seq	= htonl(ntohl(sp->hdr.seq) + 1);
+		sp->hdr.serial	= htonl(ntohl(sp->hdr.serial) + 1);
+		sp->hdr.flags	= jhdr.flags;
+		sp->hdr._rsvd	= jhdr._rsvd;
+
+		_proto("Rx DATA Jumbo %%%u", ntohl(sp->hdr.serial) - 1);
+
+		rxrpc_fast_process_packet(call, part);
+		part = NULL;
+
+	} while (sp->hdr.flags & RXRPC_JUMBO_PACKET);
+
+	rxrpc_fast_process_packet(call, jumbo);
+	_leave("");
+	return;
+
+protocol_error:
+	_debug("protocol error");
+	rxrpc_free_skb(part);
+	rxrpc_free_skb(jumbo);
+	write_lock_bh(&call->state_lock);
+	if (call->state <= RXRPC_CALL_COMPLETE) {
+		call->state = RXRPC_CALL_LOCALLY_ABORTED;
+		call->abort_code = RX_PROTOCOL_ERROR;
+		set_bit(RXRPC_CALL_ABORT, &call->events);
+		rxrpc_queue_call(call);
+	}
+	write_unlock_bh(&call->state_lock);
+	_leave("");
+}
+
+/*
+ * post an incoming packet to the appropriate call/socket to deal with
+ * - must get rid of the sk_buff, either by freeing it or by queuing it
+ */
+static void rxrpc_post_packet_to_call(struct rxrpc_call *call,
+				      struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp;
+
+	_enter("%p,%p", call, skb);
+
+	sp = rxrpc_skb(skb);
+
+	_debug("extant call [%d]", call->state);
+
+	read_lock(&call->state_lock);
+	switch (call->state) {
+	case RXRPC_CALL_LOCALLY_ABORTED:
+		if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) {
+			rxrpc_queue_call(call);
+			goto free_unlock;
+		}
+	case RXRPC_CALL_REMOTELY_ABORTED:
+	case RXRPC_CALL_NETWORK_ERROR:
+	case RXRPC_CALL_DEAD:
+		goto dead_call;
+	case RXRPC_CALL_COMPLETE:
+	case RXRPC_CALL_CLIENT_FINAL_ACK:
+		/* complete server call */
+		if (call->conn->in_clientflag)
+			goto dead_call;
+		/* resend last packet of a completed call */
+		_debug("final ack again");
+		rxrpc_get_call(call);
+		set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
+		rxrpc_queue_call(call);
+		goto free_unlock;
+	default:
+		break;
+	}
+
+	read_unlock(&call->state_lock);
+	rxrpc_get_call(call);
+
+	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+	    sp->hdr.flags & RXRPC_JUMBO_PACKET)
+		rxrpc_process_jumbo_packet(call, skb);
+	else
+		rxrpc_fast_process_packet(call, skb);
+
+	rxrpc_put_call(call);
+	goto done;
+
+dead_call:
+	if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+		skb->priority = RX_CALL_DEAD;
+		rxrpc_reject_packet(call->conn->trans->local, skb);
+		goto unlock;
+	}
+free_unlock:
+	rxrpc_free_skb(skb);
+unlock:
+	read_unlock(&call->state_lock);
+done:
+	_leave("");
+}
+
+/*
+ * post connection-level events to the connection
+ * - this includes challenges, responses and some aborts
+ */
+static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
+				      struct sk_buff *skb)
+{
+	_enter("%p,%p", conn, skb);
+
+	atomic_inc(&conn->usage);
+	skb_queue_tail(&conn->rx_queue, skb);
+	rxrpc_queue_conn(conn);
+}
+
+static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
+					       struct sk_buff *skb,
+					       struct rxrpc_skb_priv *sp)
+{
+	struct rxrpc_peer *peer;
+	struct rxrpc_transport *trans;
+	struct rxrpc_connection *conn;
+
+	peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr,
+				udp_hdr(skb)->source);
+	if (IS_ERR(peer))
+		goto cant_find_conn;
+
+	trans = rxrpc_find_transport(local, peer);
+	rxrpc_put_peer(peer);
+	if (!trans)
+		goto cant_find_conn;
+
+	conn = rxrpc_find_connection(trans, &sp->hdr);
+	rxrpc_put_transport(trans);
+	if (!conn)
+		goto cant_find_conn;
+
+	return conn;
+cant_find_conn:
+	return NULL;
+}
+
+/*
+ * handle data received on the local endpoint
+ * - may be called in interrupt context
+ */
+void rxrpc_data_ready(struct sock *sk)
+{
+	struct rxrpc_skb_priv *sp;
+	struct rxrpc_local *local;
+	struct sk_buff *skb;
+	int ret;
+
+	_enter("%p", sk);
+
+	ASSERT(!irqs_disabled());
+
+	read_lock_bh(&rxrpc_local_lock);
+	local = sk->sk_user_data;
+	if (local && atomic_read(&local->usage) > 0)
+		rxrpc_get_local(local);
+	else
+		local = NULL;
+	read_unlock_bh(&rxrpc_local_lock);
+	if (!local) {
+		_leave(" [local dead]");
+		return;
+	}
+
+	skb = skb_recv_datagram(sk, 0, 1, &ret);
+	if (!skb) {
+		rxrpc_put_local(local);
+		if (ret == -EAGAIN)
+			return;
+		_debug("UDP socket error %d", ret);
+		return;
+	}
+
+	rxrpc_new_skb(skb);
+
+	_net("recv skb %p", skb);
+
+	/* we'll probably need to checksum it (didn't call sock_recvmsg) */
+	if (skb_checksum_complete(skb)) {
+		rxrpc_free_skb(skb);
+		rxrpc_put_local(local);
+		UDP_INC_STATS_BH(&init_net, UDP_MIB_INERRORS, 0);
+		_leave(" [CSUM failed]");
+		return;
+	}
+
+	UDP_INC_STATS_BH(&init_net, UDP_MIB_INDATAGRAMS, 0);
+
+	/* the socket buffer we have is owned by UDP, with UDP's data all over
+	 * it, but we really want our own */
+	skb_orphan(skb);
+	sp = rxrpc_skb(skb);
+	memset(sp, 0, sizeof(*sp));
+
+	_net("Rx UDP packet from %08x:%04hu",
+	     ntohl(ip_hdr(skb)->saddr), ntohs(udp_hdr(skb)->source));
+
+	/* dig out the RxRPC connection details */
+	if (skb_copy_bits(skb, sizeof(struct udphdr), &sp->hdr,
+			  sizeof(sp->hdr)) < 0)
+		goto bad_message;
+	if (!pskb_pull(skb, sizeof(struct udphdr) + sizeof(sp->hdr)))
+		BUG();
+
+	_net("Rx RxRPC %s ep=%x call=%x:%x",
+	     sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient",
+	     ntohl(sp->hdr.epoch),
+	     ntohl(sp->hdr.cid),
+	     ntohl(sp->hdr.callNumber));
+
+	if (sp->hdr.type == 0 || sp->hdr.type >= RXRPC_N_PACKET_TYPES) {
+		_proto("Rx Bad Packet Type %u", sp->hdr.type);
+		goto bad_message;
+	}
+
+	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
+		goto bad_message;
+
+	if (sp->hdr.callNumber == 0) {
+		/* This is a connection-level packet. These should be
+		 * fairly rare, so the extra overhead of looking them up the
+		 * old-fashioned way doesn't really hurt */
+		struct rxrpc_connection *conn;
+
+		conn = rxrpc_conn_from_local(local, skb, sp);
+		if (!conn)
+			goto cant_route_call;
+
+		_debug("CONN %p {%d}", conn, conn->debug_id);
+		rxrpc_post_packet_to_conn(conn, skb);
+		rxrpc_put_connection(conn);
+	} else {
+		struct rxrpc_call *call;
+		u8 in_clientflag = 0;
+
+		if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+			in_clientflag = RXRPC_CLIENT_INITIATED;
+		call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid,
+					    sp->hdr.callNumber, sp->hdr.epoch,
+					    sp->hdr.serviceId, local, AF_INET,
+					    (u8 *)&ip_hdr(skb)->saddr);
+		if (call)
+			rxrpc_post_packet_to_call(call, skb);
+		else
+			goto cant_route_call;
+	}
+	rxrpc_put_local(local);
+	return;
+
+cant_route_call:
+	_debug("can't route call");
+	if (sp->hdr.flags & RXRPC_CLIENT_INITIATED &&
+	    sp->hdr.type == RXRPC_PACKET_TYPE_DATA) {
+		if (sp->hdr.seq == cpu_to_be32(1)) {
+			_debug("first packet");
+			skb_queue_tail(&local->accept_queue, skb);
+			rxrpc_queue_work(&local->acceptor);
+			rxrpc_put_local(local);
+			_leave(" [incoming]");
+			return;
+		}
+		skb->priority = RX_INVALID_OPERATION;
+	} else {
+		skb->priority = RX_CALL_DEAD;
+	}
+
+	if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+		_debug("reject type %d",sp->hdr.type);
+		rxrpc_reject_packet(local, skb);
+	}
+	rxrpc_put_local(local);
+	_leave(" [no call]");
+	return;
+
+bad_message:
+	skb->priority = RX_PROTOCOL_ERROR;
+	rxrpc_reject_packet(local, skb);
+	rxrpc_put_local(local);
+	_leave(" [badmsg]");
+}

net/rxrpc/ar-internal.h

@@ -0,0 +1,812 @@
+/* AF_RXRPC internal definitions
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <rxrpc/packet.h>
+
+#if 0
+#define CHECK_SLAB_OKAY(X)				     \
+	BUG_ON(atomic_read((X)) >> (sizeof(atomic_t) - 2) == \
+	       (POISON_FREE << 8 | POISON_FREE))
+#else
+#define CHECK_SLAB_OKAY(X) do {} while(0)
+#endif
+
+#define FCRYPT_BSIZE 8
+struct rxrpc_crypt {
+	union {
+		u8	x[FCRYPT_BSIZE];
+		__be32	n[2];
+	};
+} __attribute__((aligned(8)));
+
+#define rxrpc_queue_work(WS)	queue_work(rxrpc_workqueue, (WS))
+#define rxrpc_queue_delayed_work(WS,D)	\
+	queue_delayed_work(rxrpc_workqueue, (WS), (D))
+
+#define rxrpc_queue_call(CALL)	rxrpc_queue_work(&(CALL)->processor)
+#define rxrpc_queue_conn(CONN)	rxrpc_queue_work(&(CONN)->processor)
+
+/*
+ * sk_state for RxRPC sockets
+ */
+enum {
+	RXRPC_UNCONNECTED = 0,
+	RXRPC_CLIENT_BOUND,		/* client local address bound */
+	RXRPC_CLIENT_CONNECTED,		/* client is connected */
+	RXRPC_SERVER_BOUND,		/* server local address bound */
+	RXRPC_SERVER_LISTENING,		/* server listening for connections */
+	RXRPC_CLOSE,			/* socket is being closed */
+};
+
+/*
+ * RxRPC socket definition
+ */
+struct rxrpc_sock {
+	/* WARNING: sk has to be the first member */
+	struct sock		sk;
+	rxrpc_interceptor_t	interceptor;	/* kernel service Rx interceptor function */
+	struct rxrpc_local	*local;		/* local endpoint */
+	struct rxrpc_transport	*trans;		/* transport handler */
+	struct rxrpc_conn_bundle *bundle;	/* virtual connection bundle */
+	struct rxrpc_connection	*conn;		/* exclusive virtual connection */
+	struct list_head	listen_link;	/* link in the local endpoint's listen list */
+	struct list_head	secureq;	/* calls awaiting connection security clearance */
+	struct list_head	acceptq;	/* calls awaiting acceptance */
+	struct key		*key;		/* security for this socket */
+	struct key		*securities;	/* list of server security descriptors */
+	struct rb_root		calls;		/* outstanding calls on this socket */
+	unsigned long		flags;
+#define RXRPC_SOCK_EXCLUSIVE_CONN	1	/* exclusive connection for a client socket */
+	rwlock_t		call_lock;	/* lock for calls */
+	u32			min_sec_level;	/* minimum security level */
+#define RXRPC_SECURITY_MAX	RXRPC_SECURITY_ENCRYPT
+	struct sockaddr_rxrpc	srx;		/* local address */
+	sa_family_t		proto;		/* protocol created with */
+	__be16			service_id;	/* service ID of local/remote service */
+};
+
+#define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk)
+
+/*
+ * RxRPC socket buffer private variables
+ * - max 48 bytes (struct sk_buff::cb)
+ */
+struct rxrpc_skb_priv {
+	struct rxrpc_call	*call;		/* call with which associated */
+	unsigned long		resend_at;	/* time in jiffies at which to resend */
+	union {
+		unsigned int	offset;		/* offset into buffer of next read */
+		int		remain;		/* amount of space remaining for next write */
+		u32		error;		/* network error code */
+		bool		need_resend;	/* T if needs resending */
+	};
+
+	struct rxrpc_header	hdr;		/* RxRPC packet header from this packet */
+};
+
+#define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb)
+
+enum rxrpc_command {
+	RXRPC_CMD_SEND_DATA,		/* send data message */
+	RXRPC_CMD_SEND_ABORT,		/* request abort generation */
+	RXRPC_CMD_ACCEPT,		/* [server] accept incoming call */
+	RXRPC_CMD_REJECT_BUSY,		/* [server] reject a call as busy */
+};
+
+/*
+ * RxRPC security module interface
+ */
+struct rxrpc_security {
+	struct module		*owner;		/* providing module */
+	struct list_head	link;		/* link in master list */
+	const char		*name;		/* name of this service */
+	u8			security_index;	/* security type provided */
+
+	/* initialise a connection's security */
+	int (*init_connection_security)(struct rxrpc_connection *);
+
+	/* prime a connection's packet security */
+	void (*prime_packet_security)(struct rxrpc_connection *);
+
+	/* impose security on a packet */
+	int (*secure_packet)(const struct rxrpc_call *,
+			     struct sk_buff *,
+			     size_t,
+			     void *);
+
+	/* verify the security on a received packet */
+	int (*verify_packet)(const struct rxrpc_call *, struct sk_buff *,
+			     u32 *);
+
+	/* issue a challenge */
+	int (*issue_challenge)(struct rxrpc_connection *);
+
+	/* respond to a challenge */
+	int (*respond_to_challenge)(struct rxrpc_connection *,
+				    struct sk_buff *,
+				    u32 *);
+
+	/* verify a response */
+	int (*verify_response)(struct rxrpc_connection *,
+			       struct sk_buff *,
+			       u32 *);
+
+	/* clear connection security */
+	void (*clear)(struct rxrpc_connection *);
+};
+
+/*
+ * RxRPC local transport endpoint definition
+ * - matched by local port, address and protocol type
+ */
+struct rxrpc_local {
+	struct socket		*socket;	/* my UDP socket */
+	struct work_struct	destroyer;	/* endpoint destroyer */
+	struct work_struct	acceptor;	/* incoming call processor */
+	struct work_struct	rejecter;	/* packet reject writer */
+	struct list_head	services;	/* services listening on this endpoint */
+	struct list_head	link;		/* link in endpoint list */
+	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
+	struct sk_buff_head	accept_queue;	/* incoming calls awaiting acceptance */
+	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
+	spinlock_t		lock;		/* access lock */
+	rwlock_t		services_lock;	/* lock for services list */
+	atomic_t		usage;
+	int			debug_id;	/* debug ID for printks */
+	volatile char		error_rcvd;	/* T if received ICMP error outstanding */
+	struct sockaddr_rxrpc	srx;		/* local address */
+};
+
+/*
+ * RxRPC remote transport endpoint definition
+ * - matched by remote port, address and protocol type
+ * - holds the connection ID counter for connections between the two endpoints
+ */
+struct rxrpc_peer {
+	struct work_struct	destroyer;	/* peer destroyer */
+	struct list_head	link;		/* link in master peer list */
+	struct list_head	error_targets;	/* targets for net error distribution */
+	spinlock_t		lock;		/* access lock */
+	atomic_t		usage;
+	unsigned int		if_mtu;		/* interface MTU for this peer */
+	unsigned int		mtu;		/* network MTU for this peer */
+	unsigned int		maxdata;	/* data size (MTU - hdrsize) */
+	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
+	int			debug_id;	/* debug ID for printks */
+	int			net_error;	/* network error distributed */
+	struct sockaddr_rxrpc	srx;		/* remote address */
+
+	/* calculated RTT cache */
+#define RXRPC_RTT_CACHE_SIZE 32
+	suseconds_t		rtt;		/* current RTT estimate (in uS) */
+	unsigned int		rtt_point;	/* next entry at which to insert */
+	unsigned int		rtt_usage;	/* amount of cache actually used */
+	suseconds_t		rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* calculated RTT cache */
+};
+
+/*
+ * RxRPC point-to-point transport / connection manager definition
+ * - handles a bundle of connections between two endpoints
+ * - matched by { local, peer }
+ */
+struct rxrpc_transport {
+	struct rxrpc_local	*local;		/* local transport endpoint */
+	struct rxrpc_peer	*peer;		/* remote transport endpoint */
+	struct work_struct	error_handler;	/* network error distributor */
+	struct rb_root		bundles;	/* client connection bundles on this transport */
+	struct rb_root		client_conns;	/* client connections on this transport */
+	struct rb_root		server_conns;	/* server connections on this transport */
+	struct list_head	link;		/* link in master session list */
+	struct sk_buff_head	error_queue;	/* error packets awaiting processing */
+	time_t			put_time;	/* time at which to reap */
+	spinlock_t		client_lock;	/* client connection allocation lock */
+	rwlock_t		conn_lock;	/* lock for active/dead connections */
+	atomic_t		usage;
+	int			debug_id;	/* debug ID for printks */
+	unsigned int		conn_idcounter;	/* connection ID counter (client) */
+};
+
+/*
+ * RxRPC client connection bundle
+ * - matched by { transport, service_id, key }
+ */
+struct rxrpc_conn_bundle {
+	struct rb_node		node;		/* node in transport's lookup tree */
+	struct list_head	unused_conns;	/* unused connections in this bundle */
+	struct list_head	avail_conns;	/* available connections in this bundle */
+	struct list_head	busy_conns;	/* busy connections in this bundle */
+	struct key		*key;		/* security for this bundle */
+	wait_queue_head_t	chanwait;	/* wait for channel to become available */
+	atomic_t		usage;
+	int			debug_id;	/* debug ID for printks */
+	unsigned short		num_conns;	/* number of connections in this bundle */
+	__be16			service_id;	/* service ID */
+	u8			security_ix;	/* security type */
+};
+
+/*
+ * RxRPC connection definition
+ * - matched by { transport, service_id, conn_id, direction, key }
+ * - each connection can only handle four simultaneous calls
+ */
+struct rxrpc_connection {
+	struct rxrpc_transport	*trans;		/* transport session */
+	struct rxrpc_conn_bundle *bundle;	/* connection bundle (client) */
+	struct work_struct	processor;	/* connection event processor */
+	struct rb_node		node;		/* node in transport's lookup tree */
+	struct list_head	link;		/* link in master connection list */
+	struct list_head	bundle_link;	/* link in bundle */
+	struct rb_root		calls;		/* calls on this connection */
+	struct sk_buff_head	rx_queue;	/* received conn-level packets */
+	struct rxrpc_call	*channels[RXRPC_MAXCALLS]; /* channels (active calls) */
+	struct rxrpc_security	*security;	/* applied security module */
+	struct key		*key;		/* security for this connection (client) */
+	struct key		*server_key;	/* security for this service */
+	struct crypto_blkcipher	*cipher;	/* encryption handle */
+	struct rxrpc_crypt	csum_iv;	/* packet checksum base */
+	unsigned long		events;
+#define RXRPC_CONN_CHALLENGE	0		/* send challenge packet */
+	time_t			put_time;	/* time at which to reap */
+	rwlock_t		lock;		/* access lock */
+	spinlock_t		state_lock;	/* state-change lock */
+	atomic_t		usage;
+	u32			real_conn_id;	/* connection ID (host-endian) */
+	enum {					/* current state of connection */
+		RXRPC_CONN_UNUSED,		/* - connection not yet attempted */
+		RXRPC_CONN_CLIENT,		/* - client connection */
+		RXRPC_CONN_SERVER_UNSECURED,	/* - server unsecured connection */
+		RXRPC_CONN_SERVER_CHALLENGING,	/* - server challenging for security */
+		RXRPC_CONN_SERVER,		/* - server secured connection */
+		RXRPC_CONN_REMOTELY_ABORTED,	/* - conn aborted by peer */
+		RXRPC_CONN_LOCALLY_ABORTED,	/* - conn aborted locally */
+		RXRPC_CONN_NETWORK_ERROR,	/* - conn terminated by network error */
+	} state;
+	int			error;		/* error code for local abort */
+	int			debug_id;	/* debug ID for printks */
+	unsigned int		call_counter;	/* call ID counter */
+	atomic_t		serial;		/* packet serial number counter */
+	atomic_t		hi_serial;	/* highest serial number received */
+	u8			avail_calls;	/* number of calls available */
+	u8			size_align;	/* data size alignment (for security) */
+	u8			header_size;	/* rxrpc + security header size */
+	u8			security_size;	/* security header size */
+	u32			security_level;	/* security level negotiated */
+	u32			security_nonce;	/* response re-use preventer */
+
+	/* the following are all in net order */
+	__be32			epoch;		/* epoch of this connection */
+	__be32			cid;		/* connection ID */
+	__be16			service_id;	/* service ID */
+	u8			security_ix;	/* security type */
+	u8			in_clientflag;	/* RXRPC_CLIENT_INITIATED if we are server */
+	u8			out_clientflag;	/* RXRPC_CLIENT_INITIATED if we are client */
+};
+
+/*
+ * RxRPC call definition
+ * - matched by { connection, call_id }
+ */
+struct rxrpc_call {
+	struct rxrpc_connection	*conn;		/* connection carrying call */
+	struct rxrpc_sock	*socket;	/* socket responsible */
+	struct timer_list	lifetimer;	/* lifetime remaining on call */
+	struct timer_list	deadspan;	/* reap timer for re-ACK'ing, etc  */
+	struct timer_list	ack_timer;	/* ACK generation timer */
+	struct timer_list	resend_timer;	/* Tx resend timer */
+	struct work_struct	destroyer;	/* call destroyer */
+	struct work_struct	processor;	/* packet processor and ACK generator */
+	struct list_head	link;		/* link in master call list */
+	struct list_head	error_link;	/* link in error distribution list */
+	struct list_head	accept_link;	/* calls awaiting acceptance */
+	struct rb_node		sock_node;	/* node in socket call tree */
+	struct rb_node		conn_node;	/* node in connection call tree */
+	struct sk_buff_head	rx_queue;	/* received packets */
+	struct sk_buff_head	rx_oos_queue;	/* packets received out of sequence */
+	struct sk_buff		*tx_pending;	/* Tx socket buffer being filled */
+	wait_queue_head_t	tx_waitq;	/* wait for Tx window space to become available */
+	unsigned long		user_call_ID;	/* user-defined call ID */
+	unsigned long		creation_jif;	/* time of call creation */
+	unsigned long		flags;
+#define RXRPC_CALL_RELEASED	0	/* call has been released - no more message to userspace */
+#define RXRPC_CALL_TERMINAL_MSG	1	/* call has given the socket its final message */
+#define RXRPC_CALL_RCVD_LAST	2	/* all packets received */
+#define RXRPC_CALL_RUN_RTIMER	3	/* Tx resend timer started */
+#define RXRPC_CALL_TX_SOFT_ACK	4	/* sent some soft ACKs */
+#define RXRPC_CALL_PROC_BUSY	5	/* the processor is busy */
+#define RXRPC_CALL_INIT_ACCEPT	6	/* acceptance was initiated */
+#define RXRPC_CALL_HAS_USERID	7	/* has a user ID attached */
+#define RXRPC_CALL_EXPECT_OOS	8	/* expect out of sequence packets */
+	unsigned long		events;
+#define RXRPC_CALL_RCVD_ACKALL	0	/* ACKALL or reply received */
+#define RXRPC_CALL_RCVD_BUSY	1	/* busy packet received */
+#define RXRPC_CALL_RCVD_ABORT	2	/* abort packet received */
+#define RXRPC_CALL_RCVD_ERROR	3	/* network error received */
+#define RXRPC_CALL_ACK_FINAL	4	/* need to generate final ACK (and release call) */
+#define RXRPC_CALL_ACK		5	/* need to generate ACK */
+#define RXRPC_CALL_REJECT_BUSY	6	/* need to generate busy message */
+#define RXRPC_CALL_ABORT	7	/* need to generate abort */
+#define RXRPC_CALL_CONN_ABORT	8	/* local connection abort generated */
+#define RXRPC_CALL_RESEND_TIMER	9	/* Tx resend timer expired */
+#define RXRPC_CALL_RESEND	10	/* Tx resend required */
+#define RXRPC_CALL_DRAIN_RX_OOS	11	/* drain the Rx out of sequence queue */
+#define RXRPC_CALL_LIFE_TIMER	12	/* call's lifetimer ran out */
+#define RXRPC_CALL_ACCEPTED	13	/* incoming call accepted by userspace app */
+#define RXRPC_CALL_SECURED	14	/* incoming call's connection is now secure */
+#define RXRPC_CALL_POST_ACCEPT	15	/* need to post an "accept?" message to the app */
+#define RXRPC_CALL_RELEASE	16	/* need to release the call's resources */
+
+	spinlock_t		lock;
+	rwlock_t		state_lock;	/* lock for state transition */
+	atomic_t		usage;
+	atomic_t		sequence;	/* Tx data packet sequence counter */
+	u32			abort_code;	/* local/remote abort code */
+	enum {					/* current state of call */
+		RXRPC_CALL_CLIENT_SEND_REQUEST,	/* - client sending request phase */
+		RXRPC_CALL_CLIENT_AWAIT_REPLY,	/* - client awaiting reply */
+		RXRPC_CALL_CLIENT_RECV_REPLY,	/* - client receiving reply phase */
+		RXRPC_CALL_CLIENT_FINAL_ACK,	/* - client sending final ACK phase */
+		RXRPC_CALL_SERVER_SECURING,	/* - server securing request connection */
+		RXRPC_CALL_SERVER_ACCEPTING,	/* - server accepting request */
+		RXRPC_CALL_SERVER_RECV_REQUEST,	/* - server receiving request */
+		RXRPC_CALL_SERVER_ACK_REQUEST,	/* - server pending ACK of request */
+		RXRPC_CALL_SERVER_SEND_REPLY,	/* - server sending reply */
+		RXRPC_CALL_SERVER_AWAIT_ACK,	/* - server awaiting final ACK */
+		RXRPC_CALL_COMPLETE,		/* - call completed */
+		RXRPC_CALL_SERVER_BUSY,		/* - call rejected by busy server */
+		RXRPC_CALL_REMOTELY_ABORTED,	/* - call aborted by peer */
+		RXRPC_CALL_LOCALLY_ABORTED,	/* - call aborted locally on error or close */
+		RXRPC_CALL_NETWORK_ERROR,	/* - call terminated by network error */
+		RXRPC_CALL_DEAD,		/* - call is dead */
+	} state;
+	int			debug_id;	/* debug ID for printks */
+	u8			channel;	/* connection channel occupied by this call */
+
+	/* transmission-phase ACK management */
+	u8			acks_head;	/* offset into window of first entry */
+	u8			acks_tail;	/* offset into window of last entry */
+	u8			acks_winsz;	/* size of un-ACK'd window */
+	u8			acks_unacked;	/* lowest unacked packet in last ACK received */
+	int			acks_latest;	/* serial number of latest ACK received */
+	rxrpc_seq_t		acks_hard;	/* highest definitively ACK'd msg seq */
+	unsigned long		*acks_window;	/* sent packet window
+						 * - elements are pointers with LSB set if ACK'd
+						 */
+
+	/* receive-phase ACK management */
+	rxrpc_seq_t		rx_data_expect;	/* next data seq ID expected to be received */
+	rxrpc_seq_t		rx_data_post;	/* next data seq ID expected to be posted */
+	rxrpc_seq_t		rx_data_recv;	/* last data seq ID encountered by recvmsg */
+	rxrpc_seq_t		rx_data_eaten;	/* last data seq ID consumed by recvmsg */
+	rxrpc_seq_t		rx_first_oos;	/* first packet in rx_oos_queue (or 0) */
+	rxrpc_seq_t		ackr_win_top;	/* top of ACK window (rx_data_eaten is bottom) */
+	rxrpc_seq_net_t		ackr_prev_seq;	/* previous sequence number received */
+	u8			ackr_reason;	/* reason to ACK */
+	__be32			ackr_serial;	/* serial of packet being ACK'd */
+	atomic_t		ackr_not_idle;	/* number of packets in Rx queue */
+
+	/* received packet records, 1 bit per record */
+#define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG)
+	unsigned long		ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1];
+
+	struct hlist_node	hash_node;
+	unsigned long		hash_key;	/* Full hash key */
+	u8			in_clientflag;	/* Copy of conn->in_clientflag for hashing */
+	struct rxrpc_local	*local;		/* Local endpoint. Used for hashing. */
+	sa_family_t		proto;		/* Frame protocol */
+	/* the following should all be in net order */
+	__be32			cid;		/* connection ID + channel index  */
+	__be32			call_id;	/* call ID on connection  */
+	__be32			epoch;		/* epoch of this connection */
+	__be16			service_id;	/* service ID */
+	union {					/* Peer IP address for hashing */
+		__be32	ipv4_addr;
+		__u8	ipv6_addr[16];		/* Anticipates eventual IPv6 support */
+	} peer_ip;
+};
+
+/*
+ * locally abort an RxRPC call
+ */
+static inline void rxrpc_abort_call(struct rxrpc_call *call, u32 abort_code)
+{
+	write_lock_bh(&call->state_lock);
+	if (call->state < RXRPC_CALL_COMPLETE) {
+		call->abort_code = abort_code;
+		call->state = RXRPC_CALL_LOCALLY_ABORTED;
+		set_bit(RXRPC_CALL_ABORT, &call->events);
+	}
+	write_unlock_bh(&call->state_lock);
+}
+
+/*
+ * af_rxrpc.c
+ */
+extern atomic_t rxrpc_n_skbs;
+extern __be32 rxrpc_epoch;
+extern atomic_t rxrpc_debug_id;
+extern struct workqueue_struct *rxrpc_workqueue;
+
+/*
+ * ar-accept.c
+ */
+void rxrpc_accept_incoming_calls(struct work_struct *);
+struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
+int rxrpc_reject_call(struct rxrpc_sock *);
+
+/*
+ * ar-ack.c
+ */
+extern unsigned rxrpc_requested_ack_delay;
+extern unsigned rxrpc_soft_ack_delay;
+extern unsigned rxrpc_idle_ack_delay;
+extern unsigned rxrpc_rx_window_size;
+extern unsigned rxrpc_rx_mtu;
+extern unsigned rxrpc_rx_jumbo_max;
+
+void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
+void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
+void rxrpc_process_call(struct work_struct *);
+
+/*
+ * ar-call.c
+ */
+extern unsigned rxrpc_max_call_lifetime;
+extern unsigned rxrpc_dead_call_expiry;
+extern struct kmem_cache *rxrpc_call_jar;
+extern struct list_head rxrpc_calls;
+extern rwlock_t rxrpc_call_lock;
+
+struct rxrpc_call *rxrpc_find_call_hash(u8,  __be32, __be32, __be32,
+					__be16, void *, sa_family_t, const u8 *);
+struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *,
+					 struct rxrpc_transport *,
+					 struct rxrpc_conn_bundle *,
+					 unsigned long, int, gfp_t);
+struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *,
+				       struct rxrpc_connection *,
+				       struct rxrpc_header *, gfp_t);
+struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long);
+void rxrpc_release_call(struct rxrpc_call *);
+void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
+void __rxrpc_put_call(struct rxrpc_call *);
+void __exit rxrpc_destroy_all_calls(void);
+
+/*
+ * ar-connection.c
+ */
+extern unsigned rxrpc_connection_expiry;
+extern struct list_head rxrpc_connections;
+extern rwlock_t rxrpc_connection_lock;
+
+struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *,
+					   struct rxrpc_transport *,
+					   struct key *, __be16, gfp_t);
+void rxrpc_put_bundle(struct rxrpc_transport *, struct rxrpc_conn_bundle *);
+int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_transport *,
+		       struct rxrpc_conn_bundle *, struct rxrpc_call *, gfp_t);
+void rxrpc_put_connection(struct rxrpc_connection *);
+void __exit rxrpc_destroy_all_connections(void);
+struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *,
+					       struct rxrpc_header *);
+extern struct rxrpc_connection *
+rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_header *,
+			  gfp_t);
+
+/*
+ * ar-connevent.c
+ */
+void rxrpc_process_connection(struct work_struct *);
+void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *);
+void rxrpc_reject_packets(struct work_struct *);
+
+/*
+ * ar-error.c
+ */
+void rxrpc_UDP_error_report(struct sock *);
+void rxrpc_UDP_error_handler(struct work_struct *);
+
+/*
+ * ar-input.c
+ */
+extern const char *rxrpc_pkts[];
+
+void rxrpc_data_ready(struct sock *);
+int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
+void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
+
+/*
+ * ar-local.c
+ */
+extern rwlock_t rxrpc_local_lock;
+
+struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *);
+void rxrpc_put_local(struct rxrpc_local *);
+void __exit rxrpc_destroy_all_locals(void);
+
+/*
+ * ar-key.c
+ */
+extern struct key_type key_type_rxrpc;
+extern struct key_type key_type_rxrpc_s;
+
+int rxrpc_request_key(struct rxrpc_sock *, char __user *, int);
+int rxrpc_server_keyring(struct rxrpc_sock *, char __user *, int);
+int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
+			      u32);
+
+/*
+ * ar-output.c
+ */
+extern unsigned rxrpc_resend_timeout;
+
+int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
+int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *,
+			 struct rxrpc_transport *, struct msghdr *, size_t);
+int rxrpc_server_sendmsg(struct kiocb *, struct rxrpc_sock *, struct msghdr *,
+			 size_t);
+
+/*
+ * ar-peer.c
+ */
+struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *, gfp_t);
+void rxrpc_put_peer(struct rxrpc_peer *);
+struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *, __be32, __be16);
+void __exit rxrpc_destroy_all_peers(void);
+
+/*
+ * ar-proc.c
+ */
+extern const char *const rxrpc_call_states[];
+extern const struct file_operations rxrpc_call_seq_fops;
+extern const struct file_operations rxrpc_connection_seq_fops;
+
+/*
+ * ar-recvmsg.c
+ */
+void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
+int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
+		  int);
+
+/*
+ * ar-security.c
+ */
+int rxrpc_register_security(struct rxrpc_security *);
+void rxrpc_unregister_security(struct rxrpc_security *);
+int rxrpc_init_client_conn_security(struct rxrpc_connection *);
+int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+int rxrpc_secure_packet(const struct rxrpc_call *, struct sk_buff *, size_t,
+			void *);
+int rxrpc_verify_packet(const struct rxrpc_call *, struct sk_buff *, u32 *);
+void rxrpc_clear_conn_security(struct rxrpc_connection *);
+
+/*
+ * ar-skbuff.c
+ */
+void rxrpc_packet_destructor(struct sk_buff *);
+
+/*
+ * ar-transport.c
+ */
+extern unsigned rxrpc_transport_expiry;
+
+struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
+					    struct rxrpc_peer *, gfp_t);
+void rxrpc_put_transport(struct rxrpc_transport *);
+void __exit rxrpc_destroy_all_transports(void);
+struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
+					     struct rxrpc_peer *);
+
+/*
+ * sysctl.c
+ */
+#ifdef CONFIG_SYSCTL
+extern int __init rxrpc_sysctl_init(void);
+extern void rxrpc_sysctl_exit(void);
+#else
+static inline int __init rxrpc_sysctl_init(void) { return 0; }
+static inline void rxrpc_sysctl_exit(void) {}
+#endif
+
+/*
+ * debug tracing
+ */
+extern unsigned int rxrpc_debug;
+
+#define dbgprintk(FMT,...) \
+	printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__)
+
+#define kenter(FMT,...)	dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
+#define kleave(FMT,...)	dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
+#define kdebug(FMT,...)	dbgprintk("    "FMT ,##__VA_ARGS__)
+#define kproto(FMT,...)	dbgprintk("### "FMT ,##__VA_ARGS__)
+#define knet(FMT,...)	dbgprintk("@@@ "FMT ,##__VA_ARGS__)
+
+
+#if defined(__KDEBUG)
+#define _enter(FMT,...)	kenter(FMT,##__VA_ARGS__)
+#define _leave(FMT,...)	kleave(FMT,##__VA_ARGS__)
+#define _debug(FMT,...)	kdebug(FMT,##__VA_ARGS__)
+#define _proto(FMT,...)	kproto(FMT,##__VA_ARGS__)
+#define _net(FMT,...)	knet(FMT,##__VA_ARGS__)
+
+#elif defined(CONFIG_AF_RXRPC_DEBUG)
+#define RXRPC_DEBUG_KENTER	0x01
+#define RXRPC_DEBUG_KLEAVE	0x02
+#define RXRPC_DEBUG_KDEBUG	0x04
+#define RXRPC_DEBUG_KPROTO	0x08
+#define RXRPC_DEBUG_KNET	0x10
+
+#define _enter(FMT,...)					\
+do {							\
+	if (unlikely(rxrpc_debug & RXRPC_DEBUG_KENTER))	\
+		kenter(FMT,##__VA_ARGS__);		\
+} while (0)
+
+#define _leave(FMT,...)					\
+do {							\
+	if (unlikely(rxrpc_debug & RXRPC_DEBUG_KLEAVE))	\
+		kleave(FMT,##__VA_ARGS__);		\
+} while (0)
+
+#define _debug(FMT,...)					\
+do {							\
+	if (unlikely(rxrpc_debug & RXRPC_DEBUG_KDEBUG))	\
+		kdebug(FMT,##__VA_ARGS__);		\
+} while (0)
+
+#define _proto(FMT,...)					\
+do {							\
+	if (unlikely(rxrpc_debug & RXRPC_DEBUG_KPROTO))	\
+		kproto(FMT,##__VA_ARGS__);		\
+} while (0)
+
+#define _net(FMT,...)					\
+do {							\
+	if (unlikely(rxrpc_debug & RXRPC_DEBUG_KNET))	\
+		knet(FMT,##__VA_ARGS__);		\
+} while (0)
+
+#else
+#define _enter(FMT,...)	no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
+#define _leave(FMT,...)	no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
+#define _debug(FMT,...)	no_printk("    "FMT ,##__VA_ARGS__)
+#define _proto(FMT,...)	no_printk("### "FMT ,##__VA_ARGS__)
+#define _net(FMT,...)	no_printk("@@@ "FMT ,##__VA_ARGS__)
+#endif
+
+/*
+ * debug assertion checking
+ */
+#if 1 // defined(__KDEBUGALL)
+
+#define ASSERT(X)						\
+do {								\
+	if (unlikely(!(X))) {					\
+		printk(KERN_ERR "\n");				\
+		printk(KERN_ERR "RxRPC: Assertion failed\n");	\
+		BUG();						\
+	}							\
+} while(0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "RxRPC: Assertion failed\n");		\
+		printk(KERN_ERR "%lu " #OP " %lu is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n",	\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while(0)
+
+#define ASSERTIF(C, X)						\
+do {								\
+	if (unlikely((C) && !(X))) {				\
+		printk(KERN_ERR "\n");				\
+		printk(KERN_ERR "RxRPC: Assertion failed\n");	\
+		BUG();						\
+	}							\
+} while(0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "RxRPC: Assertion failed\n");		\
+		printk(KERN_ERR "%lu " #OP " %lu is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n",	\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while(0)
+
+#else
+
+#define ASSERT(X)				\
+do {						\
+} while(0)
+
+#define ASSERTCMP(X, OP, Y)			\
+do {						\
+} while(0)
+
+#define ASSERTIF(C, X)				\
+do {						\
+} while(0)
+
+#define ASSERTIFCMP(C, X, OP, Y)		\
+do {						\
+} while(0)
+
+#endif /* __KDEBUGALL */
+
+/*
+ * socket buffer accounting / leak finding
+ */
+static inline void __rxrpc_new_skb(struct sk_buff *skb, const char *fn)
+{
+	//_net("new skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs));
+	//atomic_inc(&rxrpc_n_skbs);
+}
+
+#define rxrpc_new_skb(skb) __rxrpc_new_skb((skb), __func__)
+
+static inline void __rxrpc_kill_skb(struct sk_buff *skb, const char *fn)
+{
+	//_net("kill skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs));
+	//atomic_dec(&rxrpc_n_skbs);
+}
+
+#define rxrpc_kill_skb(skb) __rxrpc_kill_skb((skb), __func__)
+
+static inline void __rxrpc_free_skb(struct sk_buff *skb, const char *fn)
+{
+	if (skb) {
+		CHECK_SLAB_OKAY(&skb->users);
+		//_net("free skb %p %s [%d]",
+		//     skb, fn, atomic_read(&rxrpc_n_skbs));
+		//atomic_dec(&rxrpc_n_skbs);
+		kfree_skb(skb);
+	}
+}
+
+#define rxrpc_free_skb(skb) __rxrpc_free_skb((skb), __func__)
+
+static inline void rxrpc_purge_queue(struct sk_buff_head *list)
+{
+	struct sk_buff *skb;
+	while ((skb = skb_dequeue((list))) != NULL)
+		rxrpc_free_skb(skb);
+}
+
+static inline void __rxrpc_get_local(struct rxrpc_local *local, const char *f)
+{
+	CHECK_SLAB_OKAY(&local->usage);
+	if (atomic_inc_return(&local->usage) == 1)
+		printk("resurrected (%s)\n", f);
+}
+
+#define rxrpc_get_local(LOCAL) __rxrpc_get_local((LOCAL), __func__)
+
+#define rxrpc_get_call(CALL)				\
+do {							\
+	CHECK_SLAB_OKAY(&(CALL)->usage);		\
+	if (atomic_inc_return(&(CALL)->usage) == 1)	\
+		BUG();					\
+} while(0)
+
+#define rxrpc_put_call(CALL)				\
+do {							\
+	__rxrpc_put_call(CALL);				\
+} while(0)

net/rxrpc/ar-local.c

@@ -0,0 +1,310 @@
+/* AF_RXRPC local endpoint management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static LIST_HEAD(rxrpc_locals);
+DEFINE_RWLOCK(rxrpc_local_lock);
+static DECLARE_RWSEM(rxrpc_local_sem);
+static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
+
+static void rxrpc_destroy_local(struct work_struct *work);
+
+/*
+ * allocate a new local
+ */
+static
+struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+
+	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
+	if (local) {
+		INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
+		INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
+		INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
+		INIT_LIST_HEAD(&local->services);
+		INIT_LIST_HEAD(&local->link);
+		init_rwsem(&local->defrag_sem);
+		skb_queue_head_init(&local->accept_queue);
+		skb_queue_head_init(&local->reject_queue);
+		spin_lock_init(&local->lock);
+		rwlock_init(&local->services_lock);
+		atomic_set(&local->usage, 1);
+		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		memcpy(&local->srx, srx, sizeof(*srx));
+	}
+
+	_leave(" = %p", local);
+	return local;
+}
+
+/*
+ * create the local socket
+ * - must be called with rxrpc_local_sem writelocked
+ */
+static int rxrpc_create_local(struct rxrpc_local *local)
+{
+	struct sock *sock;
+	int ret, opt;
+
+	_enter("%p{%d}", local, local->srx.transport_type);
+
+	/* create a socket to represent the local endpoint */
+	ret = sock_create_kern(PF_INET, local->srx.transport_type, IPPROTO_UDP,
+			       &local->socket);
+	if (ret < 0) {
+		_leave(" = %d [socket]", ret);
+		return ret;
+	}
+
+	/* if a local address was supplied then bind it */
+	if (local->srx.transport_len > sizeof(sa_family_t)) {
+		_debug("bind");
+		ret = kernel_bind(local->socket,
+				  (struct sockaddr *) &local->srx.transport,
+				  local->srx.transport_len);
+		if (ret < 0) {
+			_debug("bind failed");
+			goto error;
+		}
+	}
+
+	/* we want to receive ICMP errors */
+	opt = 1;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	/* we want to set the don't fragment bit */
+	opt = IP_PMTUDISC_DO;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	write_lock_bh(&rxrpc_local_lock);
+	list_add(&local->link, &rxrpc_locals);
+	write_unlock_bh(&rxrpc_local_lock);
+
+	/* set the socket up */
+	sock = local->socket->sk;
+	sock->sk_user_data	= local;
+	sock->sk_data_ready	= rxrpc_data_ready;
+	sock->sk_error_report	= rxrpc_UDP_error_report;
+	_leave(" = 0");
+	return 0;
+
+error:
+	kernel_sock_shutdown(local->socket, SHUT_RDWR);
+	local->socket->sk->sk_user_data = NULL;
+	sock_release(local->socket);
+	local->socket = NULL;
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * create a new local endpoint using the specified UDP address
+ */
+struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+	int ret;
+
+	_enter("{%d,%u,%pI4+%hu}",
+	       srx->transport_type,
+	       srx->transport.family,
+	       &srx->transport.sin.sin_addr,
+	       ntohs(srx->transport.sin.sin_port));
+
+	down_write(&rxrpc_local_sem);
+
+	/* see if we have a suitable local local endpoint already */
+	read_lock_bh(&rxrpc_local_lock);
+
+	list_for_each_entry(local, &rxrpc_locals, link) {
+		_debug("CMP {%d,%u,%pI4+%hu}",
+		       local->srx.transport_type,
+		       local->srx.transport.family,
+		       &local->srx.transport.sin.sin_addr,
+		       ntohs(local->srx.transport.sin.sin_port));
+
+		if (local->srx.transport_type != srx->transport_type ||
+		    local->srx.transport.family != srx->transport.family)
+			continue;
+
+		switch (srx->transport.family) {
+		case AF_INET:
+			if (local->srx.transport.sin.sin_port !=
+			    srx->transport.sin.sin_port)
+				continue;
+			if (memcmp(&local->srx.transport.sin.sin_addr,
+				   &srx->transport.sin.sin_addr,
+				   sizeof(struct in_addr)) != 0)
+				continue;
+			goto found_local;
+
+		default:
+			BUG();
+		}
+	}
+
+	read_unlock_bh(&rxrpc_local_lock);
+
+	/* we didn't find one, so we need to create one */
+	local = rxrpc_alloc_local(srx);
+	if (!local) {
+		up_write(&rxrpc_local_sem);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	ret = rxrpc_create_local(local);
+	if (ret < 0) {
+		up_write(&rxrpc_local_sem);
+		kfree(local);
+		_leave(" = %d", ret);
+		return ERR_PTR(ret);
+	}
+
+	up_write(&rxrpc_local_sem);
+
+	_net("LOCAL new %d {%d,%u,%pI4+%hu}",
+	     local->debug_id,
+	     local->srx.transport_type,
+	     local->srx.transport.family,
+	     &local->srx.transport.sin.sin_addr,
+	     ntohs(local->srx.transport.sin.sin_port));
+
+	_leave(" = %p [new]", local);
+	return local;
+
+found_local:
+	rxrpc_get_local(local);
+	read_unlock_bh(&rxrpc_local_lock);
+	up_write(&rxrpc_local_sem);
+
+	_net("LOCAL old %d {%d,%u,%pI4+%hu}",
+	     local->debug_id,
+	     local->srx.transport_type,
+	     local->srx.transport.family,
+	     &local->srx.transport.sin.sin_addr,
+	     ntohs(local->srx.transport.sin.sin_port));
+
+	_leave(" = %p [reuse]", local);
+	return local;
+}
+
+/*
+ * release a local endpoint
+ */
+void rxrpc_put_local(struct rxrpc_local *local)
+{
+	_enter("%p{u=%d}", local, atomic_read(&local->usage));
+
+	ASSERTCMP(atomic_read(&local->usage), >, 0);
+
+	/* to prevent a race, the decrement and the dequeue must be effectively
+	 * atomic */
+	write_lock_bh(&rxrpc_local_lock);
+	if (unlikely(atomic_dec_and_test(&local->usage))) {
+		_debug("destroy local");
+		rxrpc_queue_work(&local->destroyer);
+	}
+	write_unlock_bh(&rxrpc_local_lock);
+	_leave("");
+}
+
+/*
+ * destroy a local endpoint
+ */
+static void rxrpc_destroy_local(struct work_struct *work)
+{
+	struct rxrpc_local *local =
+		container_of(work, struct rxrpc_local, destroyer);
+
+	_enter("%p{%d}", local, atomic_read(&local->usage));
+
+	down_write(&rxrpc_local_sem);
+
+	write_lock_bh(&rxrpc_local_lock);
+	if (atomic_read(&local->usage) > 0) {
+		write_unlock_bh(&rxrpc_local_lock);
+		up_read(&rxrpc_local_sem);
+		_leave(" [resurrected]");
+		return;
+	}
+
+	list_del(&local->link);
+	local->socket->sk->sk_user_data = NULL;
+	write_unlock_bh(&rxrpc_local_lock);
+
+	downgrade_write(&rxrpc_local_sem);
+
+	ASSERT(list_empty(&local->services));
+	ASSERT(!work_pending(&local->acceptor));
+	ASSERT(!work_pending(&local->rejecter));
+
+	/* finish cleaning up the local descriptor */
+	rxrpc_purge_queue(&local->accept_queue);
+	rxrpc_purge_queue(&local->reject_queue);
+	kernel_sock_shutdown(local->socket, SHUT_RDWR);
+	sock_release(local->socket);
+
+	up_read(&rxrpc_local_sem);
+
+	_net("DESTROY LOCAL %d", local->debug_id);
+	kfree(local);
+
+	if (list_empty(&rxrpc_locals))
+		wake_up_all(&rxrpc_local_wq);
+
+	_leave("");
+}
+
+/*
+ * preemptively destroy all local local endpoint rather than waiting for
+ * them to be destroyed
+ */
+void __exit rxrpc_destroy_all_locals(void)
+{
+	DECLARE_WAITQUEUE(myself,current);
+
+	_enter("");
+
+	/* we simply have to wait for them to go away */
+	if (!list_empty(&rxrpc_locals)) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		add_wait_queue(&rxrpc_local_wq, &myself);
+
+		while (!list_empty(&rxrpc_locals)) {
+			schedule();
+			set_current_state(TASK_UNINTERRUPTIBLE);
+		}
+
+		remove_wait_queue(&rxrpc_local_wq, &myself);
+		set_current_state(TASK_RUNNING);
+	}
+
+	_leave("");
+}

net/rxrpc/ar-output.c

@@ -0,0 +1,746 @@
+/* RxRPC packet transmission
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/net.h>
+#include <linux/gfp.h>
+#include <linux/skbuff.h>
+#include <linux/circ_buf.h>
+#include <linux/export.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * Time till packet resend (in jiffies).
+ */
+unsigned rxrpc_resend_timeout = 4 * HZ;
+
+static int rxrpc_send_data(struct kiocb *iocb,
+			   struct rxrpc_sock *rx,
+			   struct rxrpc_call *call,
+			   struct msghdr *msg, size_t len);
+
+/*
+ * extract control messages from the sendmsg() control buffer
+ */
+static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
+			      unsigned long *user_call_ID,
+			      enum rxrpc_command *command,
+			      u32 *abort_code,
+			      bool server)
+{
+	struct cmsghdr *cmsg;
+	int len;
+
+	*command = RXRPC_CMD_SEND_DATA;
+
+	if (msg->msg_controllen == 0)
+		return -EINVAL;
+
+	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+		if (!CMSG_OK(msg, cmsg))
+			return -EINVAL;
+
+		len = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+		_debug("CMSG %d, %d, %d",
+		       cmsg->cmsg_level, cmsg->cmsg_type, len);
+
+		if (cmsg->cmsg_level != SOL_RXRPC)
+			continue;
+
+		switch (cmsg->cmsg_type) {
+		case RXRPC_USER_CALL_ID:
+			if (msg->msg_flags & MSG_CMSG_COMPAT) {
+				if (len != sizeof(u32))
+					return -EINVAL;
+				*user_call_ID = *(u32 *) CMSG_DATA(cmsg);
+			} else {
+				if (len != sizeof(unsigned long))
+					return -EINVAL;
+				*user_call_ID = *(unsigned long *)
+					CMSG_DATA(cmsg);
+			}
+			_debug("User Call ID %lx", *user_call_ID);
+			break;
+
+		case RXRPC_ABORT:
+			if (*command != RXRPC_CMD_SEND_DATA)
+				return -EINVAL;
+			*command = RXRPC_CMD_SEND_ABORT;
+			if (len != sizeof(*abort_code))
+				return -EINVAL;
+			*abort_code = *(unsigned int *) CMSG_DATA(cmsg);
+			_debug("Abort %x", *abort_code);
+			if (*abort_code == 0)
+				return -EINVAL;
+			break;
+
+		case RXRPC_ACCEPT:
+			if (*command != RXRPC_CMD_SEND_DATA)
+				return -EINVAL;
+			*command = RXRPC_CMD_ACCEPT;
+			if (len != 0)
+				return -EINVAL;
+			if (!server)
+				return -EISCONN;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * abort a call, sending an ABORT packet to the peer
+ */
+static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code)
+{
+	write_lock_bh(&call->state_lock);
+
+	if (call->state <= RXRPC_CALL_COMPLETE) {
+		call->state = RXRPC_CALL_LOCALLY_ABORTED;
+		call->abort_code = abort_code;
+		set_bit(RXRPC_CALL_ABORT, &call->events);
+		del_timer_sync(&call->resend_timer);
+		del_timer_sync(&call->ack_timer);
+		clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events);
+		clear_bit(RXRPC_CALL_ACK, &call->events);
+		clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
+		rxrpc_queue_call(call);
+	}
+
+	write_unlock_bh(&call->state_lock);
+}
+
+/*
+ * send a message forming part of a client call through an RxRPC socket
+ * - caller holds the socket locked
+ * - the socket may be either a client socket or a server socket
+ */
+int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
+			 struct rxrpc_transport *trans, struct msghdr *msg,
+			 size_t len)
+{
+	struct rxrpc_conn_bundle *bundle;
+	enum rxrpc_command cmd;
+	struct rxrpc_call *call;
+	unsigned long user_call_ID = 0;
+	struct key *key;
+	__be16 service_id;
+	u32 abort_code = 0;
+	int ret;
+
+	_enter("");
+
+	ASSERT(trans != NULL);
+
+	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
+				 false);
+	if (ret < 0)
+		return ret;
+
+	bundle = NULL;
+	if (trans) {
+		service_id = rx->service_id;
+		if (msg->msg_name) {
+			DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx,
+					 msg->msg_name);
+			service_id = htons(srx->srx_service);
+		}
+		key = rx->key;
+		if (key && !rx->key->payload.data)
+			key = NULL;
+		bundle = rxrpc_get_bundle(rx, trans, key, service_id,
+					  GFP_KERNEL);
+		if (IS_ERR(bundle))
+			return PTR_ERR(bundle);
+	}
+
+	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID,
+				     abort_code == 0, GFP_KERNEL);
+	if (trans)
+		rxrpc_put_bundle(trans, bundle);
+	if (IS_ERR(call)) {
+		_leave(" = %ld", PTR_ERR(call));
+		return PTR_ERR(call);
+	}
+
+	_debug("CALL %d USR %lx ST %d on CONN %p",
+	       call->debug_id, call->user_call_ID, call->state, call->conn);
+
+	if (call->state >= RXRPC_CALL_COMPLETE) {
+		/* it's too late for this call */
+		ret = -ESHUTDOWN;
+	} else if (cmd == RXRPC_CMD_SEND_ABORT) {
+		rxrpc_send_abort(call, abort_code);
+	} else if (cmd != RXRPC_CMD_SEND_DATA) {
+		ret = -EINVAL;
+	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+		/* request phase complete for this client call */
+		ret = -EPROTO;
+	} else {
+		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+	}
+
+	rxrpc_put_call(call);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/**
+ * rxrpc_kernel_send_data - Allow a kernel service to send data on a call
+ * @call: The call to send data through
+ * @msg: The data to send
+ * @len: The amount of data to send
+ *
+ * Allow a kernel service to send data on a call.  The call must be in an state
+ * appropriate to sending data.  No control data should be supplied in @msg,
+ * nor should an address be supplied.  MSG_MORE should be flagged if there's
+ * more data to come, otherwise this data will end the transmission phase.
+ */
+int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
+			   size_t len)
+{
+	int ret;
+
+	_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+
+	ASSERTCMP(msg->msg_name, ==, NULL);
+	ASSERTCMP(msg->msg_control, ==, NULL);
+
+	lock_sock(&call->socket->sk);
+
+	_debug("CALL %d USR %lx ST %d on CONN %p",
+	       call->debug_id, call->user_call_ID, call->state, call->conn);
+
+	if (call->state >= RXRPC_CALL_COMPLETE) {
+		ret = -ESHUTDOWN; /* it's too late for this call */
+	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		ret = -EPROTO; /* request phase complete for this client call */
+	} else {
+		mm_segment_t oldfs = get_fs();
+		set_fs(KERNEL_DS);
+		ret = rxrpc_send_data(NULL, call->socket, call, msg, len);
+		set_fs(oldfs);
+	}
+
+	release_sock(&call->socket->sk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_send_data);
+
+/**
+ * rxrpc_kernel_abort_call - Allow a kernel service to abort a call
+ * @call: The call to be aborted
+ * @abort_code: The abort code to stick into the ABORT packet
+ *
+ * Allow a kernel service to abort a call, if it's still in an abortable state.
+ */
+void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code)
+{
+	_enter("{%d},%d", call->debug_id, abort_code);
+
+	lock_sock(&call->socket->sk);
+
+	_debug("CALL %d USR %lx ST %d on CONN %p",
+	       call->debug_id, call->user_call_ID, call->state, call->conn);
+
+	if (call->state < RXRPC_CALL_COMPLETE)
+		rxrpc_send_abort(call, abort_code);
+
+	release_sock(&call->socket->sk);
+	_leave("");
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_abort_call);
+
+/*
+ * send a message through a server socket
+ * - caller holds the socket locked
+ */
+int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
+			 struct msghdr *msg, size_t len)
+{
+	enum rxrpc_command cmd;
+	struct rxrpc_call *call;
+	unsigned long user_call_ID = 0;
+	u32 abort_code = 0;
+	int ret;
+
+	_enter("");
+
+	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
+				 true);
+	if (ret < 0)
+		return ret;
+
+	if (cmd == RXRPC_CMD_ACCEPT) {
+		call = rxrpc_accept_call(rx, user_call_ID);
+		if (IS_ERR(call))
+			return PTR_ERR(call);
+		rxrpc_put_call(call);
+		return 0;
+	}
+
+	call = rxrpc_find_server_call(rx, user_call_ID);
+	if (!call)
+		return -EBADSLT;
+	if (call->state >= RXRPC_CALL_COMPLETE) {
+		ret = -ESHUTDOWN;
+		goto out;
+	}
+
+	switch (cmd) {
+	case RXRPC_CMD_SEND_DATA:
+		if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+		    call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		    call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+			/* Tx phase not yet begun for this call */
+			ret = -EPROTO;
+			break;
+		}
+
+		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+		break;
+
+	case RXRPC_CMD_SEND_ABORT:
+		rxrpc_send_abort(call, abort_code);
+		break;
+	default:
+		BUG();
+	}
+
+	out:
+	rxrpc_put_call(call);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * send a packet through the transport endpoint
+ */
+int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb)
+{
+	struct kvec iov[1];
+	struct msghdr msg;
+	int ret, opt;
+
+	_enter(",{%d}", skb->len);
+
+	iov[0].iov_base = skb->head;
+	iov[0].iov_len = skb->len;
+
+	msg.msg_name = &trans->peer->srx.transport.sin;
+	msg.msg_namelen = sizeof(trans->peer->srx.transport.sin);
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags = 0;
+
+	/* send the packet with the don't fragment bit set if we currently
+	 * think it's small enough */
+	if (skb->len - sizeof(struct rxrpc_header) < trans->peer->maxdata) {
+		down_read(&trans->local->defrag_sem);
+		/* send the packet by UDP
+		 * - returns -EMSGSIZE if UDP would have to fragment the packet
+		 *   to go out of the interface
+		 *   - in which case, we'll have processed the ICMP error
+		 *     message and update the peer record
+		 */
+		ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1,
+				     iov[0].iov_len);
+
+		up_read(&trans->local->defrag_sem);
+		if (ret == -EMSGSIZE)
+			goto send_fragmentable;
+
+		_leave(" = %d [%u]", ret, trans->peer->maxdata);
+		return ret;
+	}
+
+send_fragmentable:
+	/* attempt to send this message with fragmentation enabled */
+	_debug("send fragment");
+
+	down_write(&trans->local->defrag_sem);
+	opt = IP_PMTUDISC_DONT;
+	ret = kernel_setsockopt(trans->local->socket, SOL_IP, IP_MTU_DISCOVER,
+				(char *) &opt, sizeof(opt));
+	if (ret == 0) {
+		ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1,
+				     iov[0].iov_len);
+
+		opt = IP_PMTUDISC_DO;
+		kernel_setsockopt(trans->local->socket, SOL_IP,
+				  IP_MTU_DISCOVER, (char *) &opt, sizeof(opt));
+	}
+
+	up_write(&trans->local->defrag_sem);
+	_leave(" = %d [frag %u]", ret, trans->peer->maxdata);
+	return ret;
+}
+
+/*
+ * wait for space to appear in the transmit/ACK window
+ * - caller holds the socket locked
+ */
+static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
+				    struct rxrpc_call *call,
+				    long *timeo)
+{
+	DECLARE_WAITQUEUE(myself, current);
+	int ret;
+
+	_enter(",{%d},%ld",
+	       CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz),
+	       *timeo);
+
+	add_wait_queue(&call->tx_waitq, &myself);
+
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		ret = 0;
+		if (CIRC_SPACE(call->acks_head, call->acks_tail,
+			       call->acks_winsz) > 0)
+			break;
+		if (signal_pending(current)) {
+			ret = sock_intr_errno(*timeo);
+			break;
+		}
+
+		release_sock(&rx->sk);
+		*timeo = schedule_timeout(*timeo);
+		lock_sock(&rx->sk);
+	}
+
+	remove_wait_queue(&call->tx_waitq, &myself);
+	set_current_state(TASK_RUNNING);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * attempt to schedule an instant Tx resend
+ */
+static inline void rxrpc_instant_resend(struct rxrpc_call *call)
+{
+	read_lock_bh(&call->state_lock);
+	if (try_to_del_timer_sync(&call->resend_timer) >= 0) {
+		clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
+		if (call->state < RXRPC_CALL_COMPLETE &&
+		    !test_and_set_bit(RXRPC_CALL_RESEND_TIMER, &call->events))
+			rxrpc_queue_call(call);
+	}
+	read_unlock_bh(&call->state_lock);
+}
+
+/*
+ * queue a packet for transmission, set the resend timer and attempt
+ * to send the packet immediately
+ */
+static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
+			       bool last)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	int ret;
+
+	_net("queue skb %p [%d]", skb, call->acks_head);
+
+	ASSERT(call->acks_window != NULL);
+	call->acks_window[call->acks_head] = (unsigned long) skb;
+	smp_wmb();
+	call->acks_head = (call->acks_head + 1) & (call->acks_winsz - 1);
+
+	if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
+		_debug("________awaiting reply/ACK__________");
+		write_lock_bh(&call->state_lock);
+		switch (call->state) {
+		case RXRPC_CALL_CLIENT_SEND_REQUEST:
+			call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+			break;
+		case RXRPC_CALL_SERVER_ACK_REQUEST:
+			call->state = RXRPC_CALL_SERVER_SEND_REPLY;
+			if (!last)
+				break;
+		case RXRPC_CALL_SERVER_SEND_REPLY:
+			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
+			break;
+		default:
+			break;
+		}
+		write_unlock_bh(&call->state_lock);
+	}
+
+	_proto("Tx DATA %%%u { #%u }",
+	       ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
+
+	sp->need_resend = false;
+	sp->resend_at = jiffies + rxrpc_resend_timeout;
+	if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) {
+		_debug("run timer");
+		call->resend_timer.expires = sp->resend_at;
+		add_timer(&call->resend_timer);
+	}
+
+	/* attempt to cancel the rx-ACK timer, deferring reply transmission if
+	 * we're ACK'ing the request phase of an incoming call */
+	ret = -EAGAIN;
+	if (try_to_del_timer_sync(&call->ack_timer) >= 0) {
+		/* the packet may be freed by rxrpc_process_call() before this
+		 * returns */
+		ret = rxrpc_send_packet(call->conn->trans, skb);
+		_net("sent skb %p", skb);
+	} else {
+		_debug("failed to delete ACK timer");
+	}
+
+	if (ret < 0) {
+		_debug("need instant resend %d", ret);
+		sp->need_resend = true;
+		rxrpc_instant_resend(call);
+	}
+
+	_leave("");
+}
+
+/*
+ * send data through a socket
+ * - must be called in process context
+ * - caller holds the socket locked
+ */
+static int rxrpc_send_data(struct kiocb *iocb,
+			   struct rxrpc_sock *rx,
+			   struct rxrpc_call *call,
+			   struct msghdr *msg, size_t len)
+{
+	struct rxrpc_skb_priv *sp;
+	unsigned char __user *from;
+	struct sk_buff *skb;
+	struct iovec *iov;
+	struct sock *sk = &rx->sk;
+	long timeo;
+	bool more;
+	int ret, ioc, segment, copied;
+
+	_enter(",,,{%zu},%zu", msg->msg_iovlen, len);
+
+	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+	/* this should be in poll */
+	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+		return -EPIPE;
+
+	iov = msg->msg_iov;
+	ioc = msg->msg_iovlen - 1;
+	from = iov->iov_base;
+	segment = iov->iov_len;
+	iov++;
+	more = msg->msg_flags & MSG_MORE;
+
+	skb = call->tx_pending;
+	call->tx_pending = NULL;
+
+	copied = 0;
+	do {
+		int copy;
+
+		if (segment > len)
+			segment = len;
+
+		_debug("SEGMENT %d @%p", segment, from);
+
+		if (!skb) {
+			size_t size, chunk, max, space;
+
+			_debug("alloc");
+
+			if (CIRC_SPACE(call->acks_head, call->acks_tail,
+				       call->acks_winsz) <= 0) {
+				ret = -EAGAIN;
+				if (msg->msg_flags & MSG_DONTWAIT)
+					goto maybe_error;
+				ret = rxrpc_wait_for_tx_window(rx, call,
+							       &timeo);
+				if (ret < 0)
+					goto maybe_error;
+			}
+
+			max = call->conn->trans->peer->maxdata;
+			max -= call->conn->security_size;
+			max &= ~(call->conn->size_align - 1UL);
+
+			chunk = max;
+			if (chunk > len && !more)
+				chunk = len;
+
+			space = chunk + call->conn->size_align;
+			space &= ~(call->conn->size_align - 1UL);
+
+			size = space + call->conn->header_size;
+
+			_debug("SIZE: %zu/%zu/%zu", chunk, space, size);
+
+			/* create a buffer that we can retain until it's ACK'd */
+			skb = sock_alloc_send_skb(
+				sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
+			if (!skb)
+				goto maybe_error;
+
+			rxrpc_new_skb(skb);
+
+			_debug("ALLOC SEND %p", skb);
+
+			ASSERTCMP(skb->mark, ==, 0);
+
+			_debug("HS: %u", call->conn->header_size);
+			skb_reserve(skb, call->conn->header_size);
+			skb->len += call->conn->header_size;
+
+			sp = rxrpc_skb(skb);
+			sp->remain = chunk;
+			if (sp->remain > skb_tailroom(skb))
+				sp->remain = skb_tailroom(skb);
+
+			_net("skb: hr %d, tr %d, hl %d, rm %d",
+			       skb_headroom(skb),
+			       skb_tailroom(skb),
+			       skb_headlen(skb),
+			       sp->remain);
+
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		}
+
+		_debug("append");
+		sp = rxrpc_skb(skb);
+
+		/* append next segment of data to the current buffer */
+		copy = skb_tailroom(skb);
+		ASSERTCMP(copy, >, 0);
+		if (copy > segment)
+			copy = segment;
+		if (copy > sp->remain)
+			copy = sp->remain;
+
+		_debug("add");
+		ret = skb_add_data(skb, from, copy);
+		_debug("added");
+		if (ret < 0)
+			goto efault;
+		sp->remain -= copy;
+		skb->mark += copy;
+		copied += copy;
+
+		len -= copy;
+		segment -= copy;
+		from += copy;
+		while (segment == 0 && ioc > 0) {
+			from = iov->iov_base;
+			segment = iov->iov_len;
+			iov++;
+			ioc--;
+		}
+		if (len == 0) {
+			segment = 0;
+			ioc = 0;
+		}
+
+		/* check for the far side aborting the call or a network error
+		 * occurring */
+		if (call->state > RXRPC_CALL_COMPLETE)
+			goto call_aborted;
+
+		/* add the packet to the send queue if it's now full */
+		if (sp->remain <= 0 || (segment == 0 && !more)) {
+			struct rxrpc_connection *conn = call->conn;
+			uint32_t seq;
+			size_t pad;
+
+			/* pad out if we're using security */
+			if (conn->security) {
+				pad = conn->security_size + skb->mark;
+				pad = conn->size_align - pad;
+				pad &= conn->size_align - 1;
+				_debug("pad %zu", pad);
+				if (pad)
+					memset(skb_put(skb, pad), 0, pad);
+			}
+
+			seq = atomic_inc_return(&call->sequence);
+
+			sp->hdr.epoch = conn->epoch;
+			sp->hdr.cid = call->cid;
+			sp->hdr.callNumber = call->call_id;
+			sp->hdr.seq = htonl(seq);
+			sp->hdr.serial =
+				htonl(atomic_inc_return(&conn->serial));
+			sp->hdr.type = RXRPC_PACKET_TYPE_DATA;
+			sp->hdr.userStatus = 0;
+			sp->hdr.securityIndex = conn->security_ix;
+			sp->hdr._rsvd = 0;
+			sp->hdr.serviceId = conn->service_id;
+
+			sp->hdr.flags = conn->out_clientflag;
+			if (len == 0 && !more)
+				sp->hdr.flags |= RXRPC_LAST_PACKET;
+			else if (CIRC_SPACE(call->acks_head, call->acks_tail,
+					    call->acks_winsz) > 1)
+				sp->hdr.flags |= RXRPC_MORE_PACKETS;
+			if (more && seq & 1)
+				sp->hdr.flags |= RXRPC_REQUEST_ACK;
+
+			ret = rxrpc_secure_packet(
+				call, skb, skb->mark,
+				skb->head + sizeof(struct rxrpc_header));
+			if (ret < 0)
+				goto out;
+
+			memcpy(skb->head, &sp->hdr,
+			       sizeof(struct rxrpc_header));
+			rxrpc_queue_packet(call, skb, segment == 0 && !more);
+			skb = NULL;
+		}
+
+	} while (segment > 0);
+
+success:
+	ret = copied;
+out:
+	call->tx_pending = skb;
+	_leave(" = %d", ret);
+	return ret;
+
+call_aborted:
+	rxrpc_free_skb(skb);
+	if (call->state == RXRPC_CALL_NETWORK_ERROR)
+		ret = call->conn->trans->peer->net_error;
+	else
+		ret = -ECONNABORTED;
+	_leave(" = %d", ret);
+	return ret;
+
+maybe_error:
+	if (copied)
+		goto success;
+	goto out;
+
+efault:
+	ret = -EFAULT;
+	goto out;
+}

net/rxrpc/ar-peer.c

@@ -0,0 +1,303 @@
+/* RxRPC remote transport endpoint management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include "ar-internal.h"
+
+static LIST_HEAD(rxrpc_peers);
+static DEFINE_RWLOCK(rxrpc_peer_lock);
+static DECLARE_WAIT_QUEUE_HEAD(rxrpc_peer_wq);
+
+static void rxrpc_destroy_peer(struct work_struct *work);
+
+/*
+ * assess the MTU size for the network interface through which this peer is
+ * reached
+ */
+static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+{
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	peer->if_mtu = 1500;
+
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
+				   peer->srx.transport.sin.sin_addr.s_addr, 0,
+				   htons(7000), htons(7001),
+				   IPPROTO_UDP, 0, 0);
+	if (IS_ERR(rt)) {
+		_leave(" [route err %ld]", PTR_ERR(rt));
+		return;
+	}
+
+	peer->if_mtu = dst_mtu(&rt->dst);
+	dst_release(&rt->dst);
+
+	_leave(" [if_mtu %u]", peer->if_mtu);
+}
+
+/*
+ * allocate a new peer
+ */
+static struct rxrpc_peer *rxrpc_alloc_peer(struct sockaddr_rxrpc *srx,
+					   gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
+	if (peer) {
+		INIT_WORK(&peer->destroyer, &rxrpc_destroy_peer);
+		INIT_LIST_HEAD(&peer->link);
+		INIT_LIST_HEAD(&peer->error_targets);
+		spin_lock_init(&peer->lock);
+		atomic_set(&peer->usage, 1);
+		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		memcpy(&peer->srx, srx, sizeof(*srx));
+
+		rxrpc_assess_MTU_size(peer);
+		peer->mtu = peer->if_mtu;
+
+		if (srx->transport.family == AF_INET) {
+			peer->hdrsize = sizeof(struct iphdr);
+			switch (srx->transport_type) {
+			case SOCK_DGRAM:
+				peer->hdrsize += sizeof(struct udphdr);
+				break;
+			default:
+				BUG();
+				break;
+			}
+		} else {
+			BUG();
+		}
+
+		peer->hdrsize += sizeof(struct rxrpc_header);
+		peer->maxdata = peer->mtu - peer->hdrsize;
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * obtain a remote transport endpoint for the specified address
+ */
+struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_peer *peer, *candidate;
+	const char *new = "old";
+	int usage;
+
+	_enter("{%d,%d,%pI4+%hu}",
+	       srx->transport_type,
+	       srx->transport_len,
+	       &srx->transport.sin.sin_addr,
+	       ntohs(srx->transport.sin.sin_port));
+
+	/* search the peer list first */
+	read_lock_bh(&rxrpc_peer_lock);
+	list_for_each_entry(peer, &rxrpc_peers, link) {
+		_debug("check PEER %d { u=%d t=%d l=%d }",
+		       peer->debug_id,
+		       atomic_read(&peer->usage),
+		       peer->srx.transport_type,
+		       peer->srx.transport_len);
+
+		if (atomic_read(&peer->usage) > 0 &&
+		    peer->srx.transport_type == srx->transport_type &&
+		    peer->srx.transport_len == srx->transport_len &&
+		    memcmp(&peer->srx.transport,
+			   &srx->transport,
+			   srx->transport_len) == 0)
+			goto found_extant_peer;
+	}
+	read_unlock_bh(&rxrpc_peer_lock);
+
+	/* not yet present - create a candidate for a new record and then
+	 * redo the search */
+	candidate = rxrpc_alloc_peer(srx, gfp);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	write_lock_bh(&rxrpc_peer_lock);
+
+	list_for_each_entry(peer, &rxrpc_peers, link) {
+		if (atomic_read(&peer->usage) > 0 &&
+		    peer->srx.transport_type == srx->transport_type &&
+		    peer->srx.transport_len == srx->transport_len &&
+		    memcmp(&peer->srx.transport,
+			   &srx->transport,
+			   srx->transport_len) == 0)
+			goto found_extant_second;
+	}
+
+	/* we can now add the new candidate to the list */
+	peer = candidate;
+	candidate = NULL;
+	usage = atomic_read(&peer->usage);
+
+	list_add_tail(&peer->link, &rxrpc_peers);
+	write_unlock_bh(&rxrpc_peer_lock);
+	new = "new";
+
+success:
+	_net("PEER %s %d {%d,%u,%pI4+%hu}",
+	     new,
+	     peer->debug_id,
+	     peer->srx.transport_type,
+	     peer->srx.transport.family,
+	     &peer->srx.transport.sin.sin_addr,
+	     ntohs(peer->srx.transport.sin.sin_port));
+
+	_leave(" = %p {u=%d}", peer, usage);
+	return peer;
+
+	/* we found the peer in the list immediately */
+found_extant_peer:
+	usage = atomic_inc_return(&peer->usage);
+	read_unlock_bh(&rxrpc_peer_lock);
+	goto success;
+
+	/* we found the peer on the second time through the list */
+found_extant_second:
+	usage = atomic_inc_return(&peer->usage);
+	write_unlock_bh(&rxrpc_peer_lock);
+	kfree(candidate);
+	goto success;
+}
+
+/*
+ * find the peer associated with a packet
+ */
+struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *local,
+				   __be32 addr, __be16 port)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	/* search the peer list */
+	read_lock_bh(&rxrpc_peer_lock);
+
+	if (local->srx.transport.family == AF_INET &&
+	    local->srx.transport_type == SOCK_DGRAM
+	    ) {
+		list_for_each_entry(peer, &rxrpc_peers, link) {
+			if (atomic_read(&peer->usage) > 0 &&
+			    peer->srx.transport_type == SOCK_DGRAM &&
+			    peer->srx.transport.family == AF_INET &&
+			    peer->srx.transport.sin.sin_port == port &&
+			    peer->srx.transport.sin.sin_addr.s_addr == addr)
+				goto found_UDP_peer;
+		}
+
+		goto new_UDP_peer;
+	}
+
+	read_unlock_bh(&rxrpc_peer_lock);
+	_leave(" = -EAFNOSUPPORT");
+	return ERR_PTR(-EAFNOSUPPORT);
+
+found_UDP_peer:
+	_net("Rx UDP DGRAM from peer %d", peer->debug_id);
+	atomic_inc(&peer->usage);
+	read_unlock_bh(&rxrpc_peer_lock);
+	_leave(" = %p", peer);
+	return peer;
+
+new_UDP_peer:
+	_net("Rx UDP DGRAM from NEW peer");
+	read_unlock_bh(&rxrpc_peer_lock);
+	_leave(" = -EBUSY [new]");
+	return ERR_PTR(-EBUSY);
+}
+
+/*
+ * release a remote transport endpoint
+ */
+void rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	_enter("%p{u=%d}", peer, atomic_read(&peer->usage));
+
+	ASSERTCMP(atomic_read(&peer->usage), >, 0);
+
+	if (likely(!atomic_dec_and_test(&peer->usage))) {
+		_leave(" [in use]");
+		return;
+	}
+
+	rxrpc_queue_work(&peer->destroyer);
+	_leave("");
+}
+
+/*
+ * destroy a remote transport endpoint
+ */
+static void rxrpc_destroy_peer(struct work_struct *work)
+{
+	struct rxrpc_peer *peer =
+		container_of(work, struct rxrpc_peer, destroyer);
+
+	_enter("%p{%d}", peer, atomic_read(&peer->usage));
+
+	write_lock_bh(&rxrpc_peer_lock);
+	list_del(&peer->link);
+	write_unlock_bh(&rxrpc_peer_lock);
+
+	_net("DESTROY PEER %d", peer->debug_id);
+	kfree(peer);
+
+	if (list_empty(&rxrpc_peers))
+		wake_up_all(&rxrpc_peer_wq);
+	_leave("");
+}
+
+/*
+ * preemptively destroy all the peer records from a transport endpoint rather
+ * than waiting for them to time out
+ */
+void __exit rxrpc_destroy_all_peers(void)
+{
+	DECLARE_WAITQUEUE(myself,current);
+
+	_enter("");
+
+	/* we simply have to wait for them to go away */
+	if (!list_empty(&rxrpc_peers)) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		add_wait_queue(&rxrpc_peer_wq, &myself);
+
+		while (!list_empty(&rxrpc_peers)) {
+			schedule();
+			set_current_state(TASK_UNINTERRUPTIBLE);
+		}
+
+		remove_wait_queue(&rxrpc_peer_wq, &myself);
+		set_current_state(TASK_RUNNING);
+	}
+
+	_leave("");
+}

net/rxrpc/ar-proc.c

@@ -0,0 +1,192 @@
+/* /proc/net/ support for AF_RXRPC
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static const char *const rxrpc_conn_states[] = {
+	[RXRPC_CONN_UNUSED]		= "Unused  ",
+	[RXRPC_CONN_CLIENT]		= "Client  ",
+	[RXRPC_CONN_SERVER_UNSECURED]	= "SvUnsec ",
+	[RXRPC_CONN_SERVER_CHALLENGING]	= "SvChall ",
+	[RXRPC_CONN_SERVER]		= "SvSecure",
+	[RXRPC_CONN_REMOTELY_ABORTED]	= "RmtAbort",
+	[RXRPC_CONN_LOCALLY_ABORTED]	= "LocAbort",
+	[RXRPC_CONN_NETWORK_ERROR]	= "NetError",
+};
+
+/*
+ * generate a list of extant and dead calls in /proc/net/rxrpc_calls
+ */
+static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos)
+{
+	read_lock(&rxrpc_call_lock);
+	return seq_list_start_head(&rxrpc_calls, *_pos);
+}
+
+static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &rxrpc_calls, pos);
+}
+
+static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
+{
+	read_unlock(&rxrpc_call_lock);
+}
+
+static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
+{
+	struct rxrpc_transport *trans;
+	struct rxrpc_call *call;
+	char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1];
+
+	if (v == &rxrpc_calls) {
+		seq_puts(seq,
+			 "Proto Local                  Remote                "
+			 " SvID ConnID   CallID   End Use State    Abort   "
+			 " UserID\n");
+		return 0;
+	}
+
+	call = list_entry(v, struct rxrpc_call, link);
+	trans = call->conn->trans;
+
+	sprintf(lbuff, "%pI4:%u",
+		&trans->local->srx.transport.sin.sin_addr,
+		ntohs(trans->local->srx.transport.sin.sin_port));
+
+	sprintf(rbuff, "%pI4:%u",
+		&trans->peer->srx.transport.sin.sin_addr,
+		ntohs(trans->peer->srx.transport.sin.sin_port));
+
+	seq_printf(seq,
+		   "UDP   %-22.22s %-22.22s %4x %08x %08x %s %3u"
+		   " %-8.8s %08x %lx\n",
+		   lbuff,
+		   rbuff,
+		   ntohs(call->conn->service_id),
+		   ntohl(call->conn->cid),
+		   ntohl(call->call_id),
+		   call->conn->in_clientflag ? "Svc" : "Clt",
+		   atomic_read(&call->usage),
+		   rxrpc_call_states[call->state],
+		   call->abort_code,
+		   call->user_call_ID);
+
+	return 0;
+}
+
+static const struct seq_operations rxrpc_call_seq_ops = {
+	.start  = rxrpc_call_seq_start,
+	.next   = rxrpc_call_seq_next,
+	.stop   = rxrpc_call_seq_stop,
+	.show   = rxrpc_call_seq_show,
+};
+
+static int rxrpc_call_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &rxrpc_call_seq_ops);
+}
+
+const struct file_operations rxrpc_call_seq_fops = {
+	.owner		= THIS_MODULE,
+	.open		= rxrpc_call_seq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * generate a list of extant virtual connections in /proc/net/rxrpc_conns
+ */
+static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos)
+{
+	read_lock(&rxrpc_connection_lock);
+	return seq_list_start_head(&rxrpc_connections, *_pos);
+}
+
+static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v,
+				       loff_t *pos)
+{
+	return seq_list_next(v, &rxrpc_connections, pos);
+}
+
+static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v)
+{
+	read_unlock(&rxrpc_connection_lock);
+}
+
+static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
+{
+	struct rxrpc_connection *conn;
+	struct rxrpc_transport *trans;
+	char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1];
+
+	if (v == &rxrpc_connections) {
+		seq_puts(seq,
+			 "Proto Local                  Remote                "
+			 " SvID ConnID   Calls    End Use State    Key     "
+			 " Serial   ISerial\n"
+			 );
+		return 0;
+	}
+
+	conn = list_entry(v, struct rxrpc_connection, link);
+	trans = conn->trans;
+
+	sprintf(lbuff, "%pI4:%u",
+		&trans->local->srx.transport.sin.sin_addr,
+		ntohs(trans->local->srx.transport.sin.sin_port));
+
+	sprintf(rbuff, "%pI4:%u",
+		&trans->peer->srx.transport.sin.sin_addr,
+		ntohs(trans->peer->srx.transport.sin.sin_port));
+
+	seq_printf(seq,
+		   "UDP   %-22.22s %-22.22s %4x %08x %08x %s %3u"
+		   " %s %08x %08x %08x\n",
+		   lbuff,
+		   rbuff,
+		   ntohs(conn->service_id),
+		   ntohl(conn->cid),
+		   conn->call_counter,
+		   conn->in_clientflag ? "Svc" : "Clt",
+		   atomic_read(&conn->usage),
+		   rxrpc_conn_states[conn->state],
+		   key_serial(conn->key),
+		   atomic_read(&conn->serial),
+		   atomic_read(&conn->hi_serial));
+
+	return 0;
+}
+
+static const struct seq_operations rxrpc_connection_seq_ops = {
+	.start  = rxrpc_connection_seq_start,
+	.next   = rxrpc_connection_seq_next,
+	.stop   = rxrpc_connection_seq_stop,
+	.show   = rxrpc_connection_seq_show,
+};
+
+
+static int rxrpc_connection_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &rxrpc_connection_seq_ops);
+}
+
+const struct file_operations rxrpc_connection_seq_fops = {
+	.owner		= THIS_MODULE,
+	.open		= rxrpc_connection_seq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};

net/rxrpc/ar-recvmsg.c

@@ -0,0 +1,424 @@
+/* RxRPC recvmsg() implementation
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/export.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * removal a call's user ID from the socket tree to make the user ID available
+ * again and so that it won't be seen again in association with that call
+ */
+void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call)
+{
+	_debug("RELEASE CALL %d", call->debug_id);
+
+	if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
+		write_lock_bh(&rx->call_lock);
+		rb_erase(&call->sock_node, &call->socket->calls);
+		clear_bit(RXRPC_CALL_HAS_USERID, &call->flags);
+		write_unlock_bh(&rx->call_lock);
+	}
+
+	read_lock_bh(&call->state_lock);
+	if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
+	    !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events))
+		rxrpc_queue_call(call);
+	read_unlock_bh(&call->state_lock);
+}
+
+/*
+ * receive a message from an RxRPC socket
+ * - we need to be careful about two or more threads calling recvmsg
+ *   simultaneously
+ */
+int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
+		  struct msghdr *msg, size_t len, int flags)
+{
+	struct rxrpc_skb_priv *sp;
+	struct rxrpc_call *call = NULL, *continue_call = NULL;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	struct sk_buff *skb;
+	long timeo;
+	int copy, ret, ullen, offset, copied = 0;
+	u32 abort_code;
+
+	DEFINE_WAIT(wait);
+
+	_enter(",,,%zu,%d", len, flags);
+
+	if (flags & (MSG_OOB | MSG_TRUNC))
+		return -EOPNOTSUPP;
+
+	ullen = msg->msg_flags & MSG_CMSG_COMPAT ? 4 : sizeof(unsigned long);
+
+	timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT);
+	msg->msg_flags |= MSG_MORE;
+
+	lock_sock(&rx->sk);
+
+	for (;;) {
+		/* return immediately if a client socket has no outstanding
+		 * calls */
+		if (RB_EMPTY_ROOT(&rx->calls)) {
+			if (copied)
+				goto out;
+			if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
+				release_sock(&rx->sk);
+				if (continue_call)
+					rxrpc_put_call(continue_call);
+				return -ENODATA;
+			}
+		}
+
+		/* get the next message on the Rx queue */
+		skb = skb_peek(&rx->sk.sk_receive_queue);
+		if (!skb) {
+			/* nothing remains on the queue */
+			if (copied &&
+			    (flags & MSG_PEEK || timeo == 0))
+				goto out;
+
+			/* wait for a message to turn up */
+			release_sock(&rx->sk);
+			prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait,
+						  TASK_INTERRUPTIBLE);
+			ret = sock_error(&rx->sk);
+			if (ret)
+				goto wait_error;
+
+			if (skb_queue_empty(&rx->sk.sk_receive_queue)) {
+				if (signal_pending(current))
+					goto wait_interrupted;
+				timeo = schedule_timeout(timeo);
+			}
+			finish_wait(sk_sleep(&rx->sk), &wait);
+			lock_sock(&rx->sk);
+			continue;
+		}
+
+	peek_next_packet:
+		sp = rxrpc_skb(skb);
+		call = sp->call;
+		ASSERT(call != NULL);
+
+		_debug("next pkt %s", rxrpc_pkts[sp->hdr.type]);
+
+		/* make sure we wait for the state to be updated in this call */
+		spin_lock_bh(&call->lock);
+		spin_unlock_bh(&call->lock);
+
+		if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) {
+			_debug("packet from released call");
+			if (skb_dequeue(&rx->sk.sk_receive_queue) != skb)
+				BUG();
+			rxrpc_free_skb(skb);
+			continue;
+		}
+
+		/* determine whether to continue last data receive */
+		if (continue_call) {
+			_debug("maybe cont");
+			if (call != continue_call ||
+			    skb->mark != RXRPC_SKB_MARK_DATA) {
+				release_sock(&rx->sk);
+				rxrpc_put_call(continue_call);
+				_leave(" = %d [noncont]", copied);
+				return copied;
+			}
+		}
+
+		rxrpc_get_call(call);
+
+		/* copy the peer address and timestamp */
+		if (!continue_call) {
+			if (msg->msg_name) {
+				size_t len =
+					sizeof(call->conn->trans->peer->srx);
+				memcpy(msg->msg_name,
+				       &call->conn->trans->peer->srx, len);
+				msg->msg_namelen = len;
+			}
+			sock_recv_ts_and_drops(msg, &rx->sk, skb);
+		}
+
+		/* receive the message */
+		if (skb->mark != RXRPC_SKB_MARK_DATA)
+			goto receive_non_data_message;
+
+		_debug("recvmsg DATA #%u { %d, %d }",
+		       ntohl(sp->hdr.seq), skb->len, sp->offset);
+
+		if (!continue_call) {
+			/* only set the control data once per recvmsg() */
+			ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
+				       ullen, &call->user_call_ID);
+			if (ret < 0)
+				goto copy_error;
+			ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags));
+		}
+
+		ASSERTCMP(ntohl(sp->hdr.seq), >=, call->rx_data_recv);
+		ASSERTCMP(ntohl(sp->hdr.seq), <=, call->rx_data_recv + 1);
+		call->rx_data_recv = ntohl(sp->hdr.seq);
+
+		ASSERTCMP(ntohl(sp->hdr.seq), >, call->rx_data_eaten);
+
+		offset = sp->offset;
+		copy = skb->len - offset;
+		if (copy > len - copied)
+			copy = len - copied;
+
+		ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy);
+
+		if (ret < 0)
+			goto copy_error;
+
+		/* handle piecemeal consumption of data packets */
+		_debug("copied %d+%d", copy, copied);
+
+		offset += copy;
+		copied += copy;
+
+		if (!(flags & MSG_PEEK))
+			sp->offset = offset;
+
+		if (sp->offset < skb->len) {
+			_debug("buffer full");
+			ASSERTCMP(copied, ==, len);
+			break;
+		}
+
+		/* we transferred the whole data packet */
+		if (sp->hdr.flags & RXRPC_LAST_PACKET) {
+			_debug("last");
+			if (call->conn->out_clientflag) {
+				 /* last byte of reply received */
+				ret = copied;
+				goto terminal_message;
+			}
+
+			/* last bit of request received */
+			if (!(flags & MSG_PEEK)) {
+				_debug("eat packet");
+				if (skb_dequeue(&rx->sk.sk_receive_queue) !=
+				    skb)
+					BUG();
+				rxrpc_free_skb(skb);
+			}
+			msg->msg_flags &= ~MSG_MORE;
+			break;
+		}
+
+		/* move on to the next data message */
+		_debug("next");
+		if (!continue_call)
+			continue_call = sp->call;
+		else
+			rxrpc_put_call(call);
+		call = NULL;
+
+		if (flags & MSG_PEEK) {
+			_debug("peek next");
+			skb = skb->next;
+			if (skb == (struct sk_buff *) &rx->sk.sk_receive_queue)
+				break;
+			goto peek_next_packet;
+		}
+
+		_debug("eat packet");
+		if (skb_dequeue(&rx->sk.sk_receive_queue) != skb)
+			BUG();
+		rxrpc_free_skb(skb);
+	}
+
+	/* end of non-terminal data packet reception for the moment */
+	_debug("end rcv data");
+out:
+	release_sock(&rx->sk);
+	if (call)
+		rxrpc_put_call(call);
+	if (continue_call)
+		rxrpc_put_call(continue_call);
+	_leave(" = %d [data]", copied);
+	return copied;
+
+	/* handle non-DATA messages such as aborts, incoming connections and
+	 * final ACKs */
+receive_non_data_message:
+	_debug("non-data");
+
+	if (skb->mark == RXRPC_SKB_MARK_NEW_CALL) {
+		_debug("RECV NEW CALL");
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &abort_code);
+		if (ret < 0)
+			goto copy_error;
+		if (!(flags & MSG_PEEK)) {
+			if (skb_dequeue(&rx->sk.sk_receive_queue) != skb)
+				BUG();
+			rxrpc_free_skb(skb);
+		}
+		goto out;
+	}
+
+	ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
+		       ullen, &call->user_call_ID);
+	if (ret < 0)
+		goto copy_error;
+	ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags));
+
+	switch (skb->mark) {
+	case RXRPC_SKB_MARK_DATA:
+		BUG();
+	case RXRPC_SKB_MARK_FINAL_ACK:
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ACK, 0, &abort_code);
+		break;
+	case RXRPC_SKB_MARK_BUSY:
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_BUSY, 0, &abort_code);
+		break;
+	case RXRPC_SKB_MARK_REMOTE_ABORT:
+		abort_code = call->abort_code;
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code);
+		break;
+	case RXRPC_SKB_MARK_NET_ERROR:
+		_debug("RECV NET ERROR %d", sp->error);
+		abort_code = sp->error;
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &abort_code);
+		break;
+	case RXRPC_SKB_MARK_LOCAL_ERROR:
+		_debug("RECV LOCAL ERROR %d", sp->error);
+		abort_code = sp->error;
+		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4,
+			       &abort_code);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	if (ret < 0)
+		goto copy_error;
+
+terminal_message:
+	_debug("terminal");
+	msg->msg_flags &= ~MSG_MORE;
+	msg->msg_flags |= MSG_EOR;
+
+	if (!(flags & MSG_PEEK)) {
+		_net("free terminal skb %p", skb);
+		if (skb_dequeue(&rx->sk.sk_receive_queue) != skb)
+			BUG();
+		rxrpc_free_skb(skb);
+		rxrpc_remove_user_ID(rx, call);
+	}
+
+	release_sock(&rx->sk);
+	rxrpc_put_call(call);
+	if (continue_call)
+		rxrpc_put_call(continue_call);
+	_leave(" = %d", ret);
+	return ret;
+
+copy_error:
+	_debug("copy error");
+	release_sock(&rx->sk);
+	rxrpc_put_call(call);
+	if (continue_call)
+		rxrpc_put_call(continue_call);
+	_leave(" = %d", ret);
+	return ret;
+
+wait_interrupted:
+	ret = sock_intr_errno(timeo);
+wait_error:
+	finish_wait(sk_sleep(&rx->sk), &wait);
+	if (continue_call)
+		rxrpc_put_call(continue_call);
+	if (copied)
+		copied = ret;
+	_leave(" = %d [waitfail %d]", copied, ret);
+	return copied;
+
+}
+
+/**
+ * rxrpc_kernel_data_delivered - Record delivery of data message
+ * @skb: Message holding data
+ *
+ * Record the delivery of a data message.  This permits RxRPC to keep its
+ * tracking correct.  The socket buffer will be deleted.
+ */
+void rxrpc_kernel_data_delivered(struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_call *call = sp->call;
+
+	ASSERTCMP(ntohl(sp->hdr.seq), >=, call->rx_data_recv);
+	ASSERTCMP(ntohl(sp->hdr.seq), <=, call->rx_data_recv + 1);
+	call->rx_data_recv = ntohl(sp->hdr.seq);
+
+	ASSERTCMP(ntohl(sp->hdr.seq), >, call->rx_data_eaten);
+	rxrpc_free_skb(skb);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_data_delivered);
+
+/**
+ * rxrpc_kernel_is_data_last - Determine if data message is last one
+ * @skb: Message holding data
+ *
+ * Determine if data message is last one for the parent call.
+ */
+bool rxrpc_kernel_is_data_last(struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_DATA);
+
+	return sp->hdr.flags & RXRPC_LAST_PACKET;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_is_data_last);
+
+/**
+ * rxrpc_kernel_get_abort_code - Get the abort code from an RxRPC abort message
+ * @skb: Message indicating an abort
+ *
+ * Get the abort code from an RxRPC abort message.
+ */
+u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_REMOTE_ABORT);
+
+	return sp->call->abort_code;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_get_abort_code);
+
+/**
+ * rxrpc_kernel_get_error - Get the error number from an RxRPC error message
+ * @skb: Message indicating an error
+ *
+ * Get the error number from an RxRPC error message.
+ */
+int rxrpc_kernel_get_error_number(struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	return sp->error;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_get_error_number);

net/rxrpc/ar-security.c

@@ -0,0 +1,264 @@
+/* RxRPC security handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/crypto.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
+#include "ar-internal.h"
+
+static LIST_HEAD(rxrpc_security_methods);
+static DECLARE_RWSEM(rxrpc_security_sem);
+
+/*
+ * get an RxRPC security module
+ */
+static struct rxrpc_security *rxrpc_security_get(struct rxrpc_security *sec)
+{
+	return try_module_get(sec->owner) ? sec : NULL;
+}
+
+/*
+ * release an RxRPC security module
+ */
+static void rxrpc_security_put(struct rxrpc_security *sec)
+{
+	module_put(sec->owner);
+}
+
+/*
+ * look up an rxrpc security module
+ */
+static struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
+{
+	struct rxrpc_security *sec = NULL;
+
+	_enter("");
+
+	down_read(&rxrpc_security_sem);
+
+	list_for_each_entry(sec, &rxrpc_security_methods, link) {
+		if (sec->security_index == security_index) {
+			if (unlikely(!rxrpc_security_get(sec)))
+				break;
+			goto out;
+		}
+	}
+
+	sec = NULL;
+out:
+	up_read(&rxrpc_security_sem);
+	_leave(" = %p [%s]", sec, sec ? sec->name : "");
+	return sec;
+}
+
+/**
+ * rxrpc_register_security - register an RxRPC security handler
+ * @sec: security module
+ *
+ * register an RxRPC security handler for use by RxRPC
+ */
+int rxrpc_register_security(struct rxrpc_security *sec)
+{
+	struct rxrpc_security *psec;
+	int ret;
+
+	_enter("");
+	down_write(&rxrpc_security_sem);
+
+	ret = -EEXIST;
+	list_for_each_entry(psec, &rxrpc_security_methods, link) {
+		if (psec->security_index == sec->security_index)
+			goto out;
+	}
+
+	list_add(&sec->link, &rxrpc_security_methods);
+
+	printk(KERN_NOTICE "RxRPC: Registered security type %d '%s'\n",
+	       sec->security_index, sec->name);
+	ret = 0;
+
+out:
+	up_write(&rxrpc_security_sem);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(rxrpc_register_security);
+
+/**
+ * rxrpc_unregister_security - unregister an RxRPC security handler
+ * @sec: security module
+ *
+ * unregister an RxRPC security handler
+ */
+void rxrpc_unregister_security(struct rxrpc_security *sec)
+{
+
+	_enter("");
+	down_write(&rxrpc_security_sem);
+	list_del_init(&sec->link);
+	up_write(&rxrpc_security_sem);
+
+	printk(KERN_NOTICE "RxRPC: Unregistered security type %d '%s'\n",
+	       sec->security_index, sec->name);
+}
+
+EXPORT_SYMBOL_GPL(rxrpc_unregister_security);
+
+/*
+ * initialise the security on a client connection
+ */
+int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
+{
+	struct rxrpc_key_token *token;
+	struct rxrpc_security *sec;
+	struct key *key = conn->key;
+	int ret;
+
+	_enter("{%d},{%x}", conn->debug_id, key_serial(key));
+
+	if (!key)
+		return 0;
+
+	ret = key_validate(key);
+	if (ret < 0)
+		return ret;
+
+	if (!key->payload.data)
+		return -EKEYREJECTED;
+	token = key->payload.data;
+
+	sec = rxrpc_security_lookup(token->security_index);
+	if (!sec)
+		return -EKEYREJECTED;
+	conn->security = sec;
+
+	ret = conn->security->init_connection_security(conn);
+	if (ret < 0) {
+		rxrpc_security_put(conn->security);
+		conn->security = NULL;
+		return ret;
+	}
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * initialise the security on a server connection
+ */
+int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
+{
+	struct rxrpc_security *sec;
+	struct rxrpc_local *local = conn->trans->local;
+	struct rxrpc_sock *rx;
+	struct key *key;
+	key_ref_t kref;
+	char kdesc[5+1+3+1];
+
+	_enter("");
+
+	sprintf(kdesc, "%u:%u", ntohs(conn->service_id), conn->security_ix);
+
+	sec = rxrpc_security_lookup(conn->security_ix);
+	if (!sec) {
+		_leave(" = -ENOKEY [lookup]");
+		return -ENOKEY;
+	}
+
+	/* find the service */
+	read_lock_bh(&local->services_lock);
+	list_for_each_entry(rx, &local->services, listen_link) {
+		if (rx->service_id == conn->service_id)
+			goto found_service;
+	}
+
+	/* the service appears to have died */
+	read_unlock_bh(&local->services_lock);
+	rxrpc_security_put(sec);
+	_leave(" = -ENOENT");
+	return -ENOENT;
+
+found_service:
+	if (!rx->securities) {
+		read_unlock_bh(&local->services_lock);
+		rxrpc_security_put(sec);
+		_leave(" = -ENOKEY");
+		return -ENOKEY;
+	}
+
+	/* look through the service's keyring */
+	kref = keyring_search(make_key_ref(rx->securities, 1UL),
+			      &key_type_rxrpc_s, kdesc);
+	if (IS_ERR(kref)) {
+		read_unlock_bh(&local->services_lock);
+		rxrpc_security_put(sec);
+		_leave(" = %ld [search]", PTR_ERR(kref));
+		return PTR_ERR(kref);
+	}
+
+	key = key_ref_to_ptr(kref);
+	read_unlock_bh(&local->services_lock);
+
+	conn->server_key = key;
+	conn->security = sec;
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * secure a packet prior to transmission
+ */
+int rxrpc_secure_packet(const struct rxrpc_call *call,
+			struct sk_buff *skb,
+			size_t data_size,
+			void *sechdr)
+{
+	if (call->conn->security)
+		return call->conn->security->secure_packet(
+			call, skb, data_size, sechdr);
+	return 0;
+}
+
+/*
+ * secure a packet prior to transmission
+ */
+int rxrpc_verify_packet(const struct rxrpc_call *call, struct sk_buff *skb,
+			u32 *_abort_code)
+{
+	if (call->conn->security)
+		return call->conn->security->verify_packet(
+			call, skb, _abort_code);
+	return 0;
+}
+
+/*
+ * clear connection security
+ */
+void rxrpc_clear_conn_security(struct rxrpc_connection *conn)
+{
+	_enter("{%d}", conn->debug_id);
+
+	if (conn->security) {
+		conn->security->clear(conn);
+		rxrpc_security_put(conn->security);
+		conn->security = NULL;
+	}
+
+	key_put(conn->key);
+	key_put(conn->server_key);
+}

net/rxrpc/ar-skbuff.c

@@ -0,0 +1,137 @@
+/* ar-skbuff.c: socket buffer destruction handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * set up for the ACK at the end of the receive phase when we discard the final
+ * receive phase data packet
+ * - called with softirqs disabled
+ */
+static void rxrpc_request_final_ACK(struct rxrpc_call *call)
+{
+	/* the call may be aborted before we have a chance to ACK it */
+	write_lock(&call->state_lock);
+
+	switch (call->state) {
+	case RXRPC_CALL_CLIENT_RECV_REPLY:
+		call->state = RXRPC_CALL_CLIENT_FINAL_ACK;
+		_debug("request final ACK");
+
+		/* get an extra ref on the call for the final-ACK generator to
+		 * release */
+		rxrpc_get_call(call);
+		set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
+		if (try_to_del_timer_sync(&call->ack_timer) >= 0)
+			rxrpc_queue_call(call);
+		break;
+
+	case RXRPC_CALL_SERVER_RECV_REQUEST:
+		call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
+	default:
+		break;
+	}
+
+	write_unlock(&call->state_lock);
+}
+
+/*
+ * drop the bottom ACK off of the call ACK window and advance the window
+ */
+static void rxrpc_hard_ACK_data(struct rxrpc_call *call,
+				struct rxrpc_skb_priv *sp)
+{
+	int loop;
+	u32 seq;
+
+	spin_lock_bh(&call->lock);
+
+	_debug("hard ACK #%u", ntohl(sp->hdr.seq));
+
+	for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) {
+		call->ackr_window[loop] >>= 1;
+		call->ackr_window[loop] |=
+			call->ackr_window[loop + 1] << (BITS_PER_LONG - 1);
+	}
+
+	seq = ntohl(sp->hdr.seq);
+	ASSERTCMP(seq, ==, call->rx_data_eaten + 1);
+	call->rx_data_eaten = seq;
+
+	if (call->ackr_win_top < UINT_MAX)
+		call->ackr_win_top++;
+
+	ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE,
+		    call->rx_data_post, >=, call->rx_data_recv);
+	ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE,
+		    call->rx_data_recv, >=, call->rx_data_eaten);
+
+	if (sp->hdr.flags & RXRPC_LAST_PACKET) {
+		rxrpc_request_final_ACK(call);
+	} else if (atomic_dec_and_test(&call->ackr_not_idle) &&
+		   test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) {
+		/* We previously soft-ACK'd some received packets that have now
+		 * been consumed, so send a hard-ACK if no more packets are
+		 * immediately forthcoming to allow the transmitter to free up
+		 * its Tx bufferage.
+		 */
+		_debug("send Rx idle ACK");
+		__rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial,
+				    false);
+	}
+
+	spin_unlock_bh(&call->lock);
+}
+
+/*
+ * destroy a packet that has an RxRPC control buffer
+ * - advance the hard-ACK state of the parent call (done here in case something
+ *   in the kernel bypasses recvmsg() and steals the packet directly off of the
+ *   socket receive queue)
+ */
+void rxrpc_packet_destructor(struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_call *call = sp->call;
+
+	_enter("%p{%p}", skb, call);
+
+	if (call) {
+		/* send the final ACK on a client call */
+		if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA)
+			rxrpc_hard_ACK_data(call, sp);
+		rxrpc_put_call(call);
+		sp->call = NULL;
+	}
+
+	if (skb->sk)
+		sock_rfree(skb);
+	_leave("");
+}
+
+/**
+ * rxrpc_kernel_free_skb - Free an RxRPC socket buffer
+ * @skb: The socket buffer to be freed
+ *
+ * Let RxRPC free its own socket buffer, permitting it to maintain debug
+ * accounting.
+ */
+void rxrpc_kernel_free_skb(struct sk_buff *skb)
+{
+	rxrpc_free_skb(skb);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_free_skb);

net/rxrpc/ar-transport.c

@@ -0,0 +1,283 @@
+/* RxRPC point-to-point transport session management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * Time after last use at which transport record is cleaned up.
+ */
+unsigned rxrpc_transport_expiry = 3600 * 24;
+
+static void rxrpc_transport_reaper(struct work_struct *work);
+
+static LIST_HEAD(rxrpc_transports);
+static DEFINE_RWLOCK(rxrpc_transport_lock);
+static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper);
+
+/*
+ * allocate a new transport session manager
+ */
+static struct rxrpc_transport *rxrpc_alloc_transport(struct rxrpc_local *local,
+						     struct rxrpc_peer *peer,
+						     gfp_t gfp)
+{
+	struct rxrpc_transport *trans;
+
+	_enter("");
+
+	trans = kzalloc(sizeof(struct rxrpc_transport), gfp);
+	if (trans) {
+		trans->local = local;
+		trans->peer = peer;
+		INIT_LIST_HEAD(&trans->link);
+		trans->bundles = RB_ROOT;
+		trans->client_conns = RB_ROOT;
+		trans->server_conns = RB_ROOT;
+		skb_queue_head_init(&trans->error_queue);
+		spin_lock_init(&trans->client_lock);
+		rwlock_init(&trans->conn_lock);
+		atomic_set(&trans->usage, 1);
+		trans->debug_id = atomic_inc_return(&rxrpc_debug_id);
+
+		if (peer->srx.transport.family == AF_INET) {
+			switch (peer->srx.transport_type) {
+			case SOCK_DGRAM:
+				INIT_WORK(&trans->error_handler,
+					  rxrpc_UDP_error_handler);
+				break;
+			default:
+				BUG();
+				break;
+			}
+		} else {
+			BUG();
+		}
+	}
+
+	_leave(" = %p", trans);
+	return trans;
+}
+
+/*
+ * obtain a transport session for the nominated endpoints
+ */
+struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *local,
+					    struct rxrpc_peer *peer,
+					    gfp_t gfp)
+{
+	struct rxrpc_transport *trans, *candidate;
+	const char *new = "old";
+	int usage;
+
+	_enter("{%pI4+%hu},{%pI4+%hu},",
+	       &local->srx.transport.sin.sin_addr,
+	       ntohs(local->srx.transport.sin.sin_port),
+	       &peer->srx.transport.sin.sin_addr,
+	       ntohs(peer->srx.transport.sin.sin_port));
+
+	/* search the transport list first */
+	read_lock_bh(&rxrpc_transport_lock);
+	list_for_each_entry(trans, &rxrpc_transports, link) {
+		if (trans->local == local && trans->peer == peer)
+			goto found_extant_transport;
+	}
+	read_unlock_bh(&rxrpc_transport_lock);
+
+	/* not yet present - create a candidate for a new record and then
+	 * redo the search */
+	candidate = rxrpc_alloc_transport(local, peer, gfp);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	write_lock_bh(&rxrpc_transport_lock);
+
+	list_for_each_entry(trans, &rxrpc_transports, link) {
+		if (trans->local == local && trans->peer == peer)
+			goto found_extant_second;
+	}
+
+	/* we can now add the new candidate to the list */
+	trans = candidate;
+	candidate = NULL;
+	usage = atomic_read(&trans->usage);
+
+	rxrpc_get_local(trans->local);
+	atomic_inc(&trans->peer->usage);
+	list_add_tail(&trans->link, &rxrpc_transports);
+	write_unlock_bh(&rxrpc_transport_lock);
+	new = "new";
+
+success:
+	_net("TRANSPORT %s %d local %d -> peer %d",
+	     new,
+	     trans->debug_id,
+	     trans->local->debug_id,
+	     trans->peer->debug_id);
+
+	_leave(" = %p {u=%d}", trans, usage);
+	return trans;
+
+	/* we found the transport in the list immediately */
+found_extant_transport:
+	usage = atomic_inc_return(&trans->usage);
+	read_unlock_bh(&rxrpc_transport_lock);
+	goto success;
+
+	/* we found the transport on the second time through the list */
+found_extant_second:
+	usage = atomic_inc_return(&trans->usage);
+	write_unlock_bh(&rxrpc_transport_lock);
+	kfree(candidate);
+	goto success;
+}
+
+/*
+ * find the transport connecting two endpoints
+ */
+struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *local,
+					     struct rxrpc_peer *peer)
+{
+	struct rxrpc_transport *trans;
+
+	_enter("{%pI4+%hu},{%pI4+%hu},",
+	       &local->srx.transport.sin.sin_addr,
+	       ntohs(local->srx.transport.sin.sin_port),
+	       &peer->srx.transport.sin.sin_addr,
+	       ntohs(peer->srx.transport.sin.sin_port));
+
+	/* search the transport list */
+	read_lock_bh(&rxrpc_transport_lock);
+
+	list_for_each_entry(trans, &rxrpc_transports, link) {
+		if (trans->local == local && trans->peer == peer)
+			goto found_extant_transport;
+	}
+
+	read_unlock_bh(&rxrpc_transport_lock);
+	_leave(" = NULL");
+	return NULL;
+
+found_extant_transport:
+	atomic_inc(&trans->usage);
+	read_unlock_bh(&rxrpc_transport_lock);
+	_leave(" = %p", trans);
+	return trans;
+}
+
+/*
+ * release a transport session
+ */
+void rxrpc_put_transport(struct rxrpc_transport *trans)
+{
+	_enter("%p{u=%d}", trans, atomic_read(&trans->usage));
+
+	ASSERTCMP(atomic_read(&trans->usage), >, 0);
+
+	trans->put_time = get_seconds();
+	if (unlikely(atomic_dec_and_test(&trans->usage))) {
+		_debug("zombie");
+		/* let the reaper determine the timeout to avoid a race with
+		 * overextending the timeout if the reaper is running at the
+		 * same time */
+		rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
+	}
+	_leave("");
+}
+
+/*
+ * clean up a transport session
+ */
+static void rxrpc_cleanup_transport(struct rxrpc_transport *trans)
+{
+	_net("DESTROY TRANS %d", trans->debug_id);
+
+	rxrpc_purge_queue(&trans->error_queue);
+
+	rxrpc_put_local(trans->local);
+	rxrpc_put_peer(trans->peer);
+	kfree(trans);
+}
+
+/*
+ * reap dead transports that have passed their expiry date
+ */
+static void rxrpc_transport_reaper(struct work_struct *work)
+{
+	struct rxrpc_transport *trans, *_p;
+	unsigned long now, earliest, reap_time;
+
+	LIST_HEAD(graveyard);
+
+	_enter("");
+
+	now = get_seconds();
+	earliest = ULONG_MAX;
+
+	/* extract all the transports that have been dead too long */
+	write_lock_bh(&rxrpc_transport_lock);
+	list_for_each_entry_safe(trans, _p, &rxrpc_transports, link) {
+		_debug("reap TRANS %d { u=%d t=%ld }",
+		       trans->debug_id, atomic_read(&trans->usage),
+		       (long) now - (long) trans->put_time);
+
+		if (likely(atomic_read(&trans->usage) > 0))
+			continue;
+
+		reap_time = trans->put_time + rxrpc_transport_expiry;
+		if (reap_time <= now)
+			list_move_tail(&trans->link, &graveyard);
+		else if (reap_time < earliest)
+			earliest = reap_time;
+	}
+	write_unlock_bh(&rxrpc_transport_lock);
+
+	if (earliest != ULONG_MAX) {
+		_debug("reschedule reaper %ld", (long) earliest - now);
+		ASSERTCMP(earliest, >, now);
+		rxrpc_queue_delayed_work(&rxrpc_transport_reap,
+					 (earliest - now) * HZ);
+	}
+
+	/* then destroy all those pulled out */
+	while (!list_empty(&graveyard)) {
+		trans = list_entry(graveyard.next, struct rxrpc_transport,
+				   link);
+		list_del_init(&trans->link);
+
+		ASSERTCMP(atomic_read(&trans->usage), ==, 0);
+		rxrpc_cleanup_transport(trans);
+	}
+
+	_leave("");
+}
+
+/*
+ * preemptively destroy all the transport session records rather than waiting
+ * for them to time out
+ */
+void __exit rxrpc_destroy_all_transports(void)
+{
+	_enter("");
+
+	rxrpc_transport_expiry = 0;
+	cancel_delayed_work(&rxrpc_transport_reap);
+	rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
+
+	_leave("");
+}

net/rxrpc/sysctl.c

@@ -0,0 +1,146 @@
+/* sysctls for configuring RxRPC operating parameters
+ *
+ * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sysctl.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static struct ctl_table_header *rxrpc_sysctl_reg_table;
+static const unsigned zero = 0;
+static const unsigned one = 1;
+static const unsigned four = 4;
+static const unsigned n_65535 = 65535;
+static const unsigned n_max_acks = RXRPC_MAXACKS;
+
+/*
+ * RxRPC operating parameters.
+ *
+ * See Documentation/networking/rxrpc.txt and the variable definitions for more
+ * information on the individual parameters.
+ */
+static struct ctl_table rxrpc_sysctl_table[] = {
+	/* Values measured in milliseconds */
+	{
+		.procname	= "req_ack_delay",
+		.data		= &rxrpc_requested_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&zero,
+	},
+	{
+		.procname	= "soft_ack_delay",
+		.data		= &rxrpc_soft_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "idle_ack_delay",
+		.data		= &rxrpc_idle_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "resend_timeout",
+		.data		= &rxrpc_resend_timeout,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+
+	/* Values measured in seconds but used in jiffies */
+	{
+		.procname	= "max_call_lifetime",
+		.data		= &rxrpc_max_call_lifetime,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "dead_call_expiry",
+		.data		= &rxrpc_dead_call_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+		.extra1		= (void *)&one,
+	},
+
+	/* Values measured in seconds */
+	{
+		.procname	= "connection_expiry",
+		.data		= &rxrpc_connection_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "transport_expiry",
+		.data		= &rxrpc_transport_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+	},
+
+	/* Non-time values */
+	{
+		.procname	= "rx_window_size",
+		.data		= &rxrpc_rx_window_size,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra2		= (void *)&n_max_acks,
+	},
+	{
+		.procname	= "rx_mtu",
+		.data		= &rxrpc_rx_mtu,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra1		= (void *)&n_65535,
+	},
+	{
+		.procname	= "rx_jumbo_max",
+		.data		= &rxrpc_rx_jumbo_max,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra2		= (void *)&four,
+	},
+
+	{ }
+};
+
+int __init rxrpc_sysctl_init(void)
+{
+	rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc",
+						     rxrpc_sysctl_table);
+	if (!rxrpc_sysctl_reg_table)
+		return -ENOMEM;
+	return 0;
+}
+
+void rxrpc_sysctl_exit(void)
+{
+	if (rxrpc_sysctl_reg_table)
+		unregister_net_sysctl_table(rxrpc_sysctl_reg_table);
+}