[net-next-2.6.git] / net / rxrpc / af_rxrpc.c

/* 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/net.h>
#include <linux/skbuff.h>
#include <linux/poll.h>
#include <linux/proc_fs.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 rxrpc_debug; // = RXRPC_DEBUG_KPROTO;
module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO);
MODULE_PARM_DESC(rxrpc_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;

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);
	read_lock(&sk->sk_callback_lock);
	if (rxrpc_writable(sk)) {
		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
			wake_up_interruptible(sk->sk_sleep);
		sk_wake_async(sk, 2, POLL_OUT);
	}
	read_unlock(&sk->sk_callback_lock);
}

/*
 * 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 @ %u.%u.%u.%u",
		       ntohs(srx->transport.sin.sin_port),
		       NIPQUAD(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)
{
	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_KERNEL);
	if (IS_ERR(peer))
		return ERR_PTR(PTR_ERR(peer));

	/* find a transport */
	trans = rxrpc_get_transport(rx->local, peer, GFP_KERNEL);
	rxrpc_put_peer(peer);
	_leave(" = %p", trans);
	return trans;
}

/*
 * 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);
	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);
		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, int optlen)
{
	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
	unsigned 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))
				goto error;
			ret = -EISCONN;
			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
				goto error;
			ret = get_user(min_sec_level,
				       (unsigned __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;

	poll_wait(file, sk->sk_sleep, 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 socket *sock, int protocol)
{
	struct rxrpc_sock *rx;
	struct sock *sk;

	_enter("%p,%d", sock, protocol);

	/* 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(PF_RXRPC, GFP_KERNEL, &rxrpc_proto, 1);
	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);

	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
	BUG_TRAP(sk_unhashed(sk));
	BUG_TRAP(!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_scheduled_work();
	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 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)
{
	struct sk_buff *dummy_skb;
	int ret = -1;

	BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof(dummy_skb->cb));

	rxrpc_epoch = htonl(xtime.tv_sec);

	rxrpc_call_jar = kmem_cache_create(
		"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
		SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!rxrpc_call_jar) {
		printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n");
		ret = -ENOMEM;
		goto error_call_jar;
	}

	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;
	}

#ifdef CONFIG_PROC_FS
	proc_net_fops_create("rxrpc_calls", 0, &rxrpc_call_seq_fops);
	proc_net_fops_create("rxrpc_conns", 0, &rxrpc_connection_seq_fops);
#endif
	return 0;

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:
	kmem_cache_destroy(rxrpc_call_jar);
error_call_jar:
	return ret;
}

/*
 * unregister the RxRPC protocol
 */
static void __exit af_rxrpc_exit(void)
{
	_enter("");
	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_scheduled_work();
	proc_net_remove("rxrpc_conns");
	proc_net_remove("rxrpc_calls");
	kmem_cache_destroy(rxrpc_call_jar);
	_leave("");
}

module_init(af_rxrpc_init);
module_exit(af_rxrpc_exit);
Commit	Line	Data
17926a79 DH	1	/* AF_RXRPC implementation
	2	*
	3	* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
	4	* Written by David Howells (dhowells@redhat.com)
	5	*
	6	* This program is free software; you can redistribute it and/or
	7	* modify it under the terms of the GNU General Public License
	8	* as published by the Free Software Foundation; either version
	9	* 2 of the License, or (at your option) any later version.
	10	*/
	11
	12	#include <linux/module.h>
	13	#include <linux/net.h>
	14	#include <linux/skbuff.h>
	15	#include <linux/poll.h>
	16	#include <linux/proc_fs.h>
	17	#include <net/sock.h>
	18	#include <net/af_rxrpc.h>
	19	#include "ar-internal.h"
	20
	21	MODULE_DESCRIPTION("RxRPC network protocol");
	22	MODULE_AUTHOR("Red Hat, Inc.");
	23	MODULE_LICENSE("GPL");
	24	MODULE_ALIAS_NETPROTO(PF_RXRPC);
	25
	26	unsigned rxrpc_debug; // = RXRPC_DEBUG_KPROTO;
	27	module_param_named(debug, rxrpc_debug, uint, S_IWUSR \| S_IRUGO);
	28	MODULE_PARM_DESC(rxrpc_debug, "RxRPC debugging mask");
	29
	30	static int sysctl_rxrpc_max_qlen __read_mostly = 10;
	31
	32	static struct proto rxrpc_proto;
	33	static const struct proto_ops rxrpc_rpc_ops;
	34
	35	/* local epoch for detecting local-end reset */
	36	__be32 rxrpc_epoch;
	37
	38	/* current debugging ID */
	39	atomic_t rxrpc_debug_id;
	40
	41	/* count of skbs currently in use */
	42	atomic_t rxrpc_n_skbs;
	43
	44	static void rxrpc_sock_destructor(struct sock *);
	45
	46	/*
	47	* see if an RxRPC socket is currently writable
	48	*/
	49	static inline int rxrpc_writable(struct sock *sk)
	50	{
	51	return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf;
	52	}
	53
	54	/*
	55	* wait for write bufferage to become available
	56	*/
	57	static void rxrpc_write_space(struct sock *sk)
	58	{
	59	_enter("%p", sk);
	60	read_lock(&sk->sk_callback_lock);
	61	if (rxrpc_writable(sk)) {
	62	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
	63	wake_up_interruptible(sk->sk_sleep);
	64	sk_wake_async(sk, 2, POLL_OUT);
65	}
66	read_unlock(&sk->sk_callback_lock);
67	}
68
69	/*
70	* validate an RxRPC address
71	*/
72	static int rxrpc_validate_address(struct rxrpc_sock *rx,
73	struct sockaddr_rxrpc *srx,
74	int len)
75	{
76	if (len < sizeof(struct sockaddr_rxrpc))
77	return -EINVAL;
78
79	if (srx->srx_family != AF_RXRPC)
80	return -EAFNOSUPPORT;
81
82	if (srx->transport_type != SOCK_DGRAM)
83	return -ESOCKTNOSUPPORT;
84
85	len -= offsetof(struct sockaddr_rxrpc, transport);
86	if (srx->transport_len < sizeof(sa_family_t) \|\|
87	srx->transport_len > len)
88	return -EINVAL;
89
90	if (srx->transport.family != rx->proto)
91	return -EAFNOSUPPORT;
92
93	switch (srx->transport.family) {
94	case AF_INET:
95	_debug("INET: %x @ %u.%u.%u.%u",
96	ntohs(srx->transport.sin.sin_port),
97	NIPQUAD(srx->transport.sin.sin_addr));
98	if (srx->transport_len > 8)
99	memset((void *)&srx->transport + 8, 0,
100	srx->transport_len - 8);
101	break;
102
103	case AF_INET6:
104	default:
105	return -EAFNOSUPPORT;
106	}
107
108	return 0;
109	}
110
111	/*
112	* bind a local address to an RxRPC socket
113	*/
114	static int rxrpc_bind(struct socket sock, struct sockaddr saddr, int len)
115	{
116	struct sockaddr_rxrpc srx = (struct sockaddr_rxrpc ) saddr;
117	struct sock *sk = sock->sk;
118	struct rxrpc_local *local;
119	struct rxrpc_sock rx = rxrpc_sk(sk), prx;
120	__be16 service_id;
121	int ret;
122
123	_enter("%p,%p,%d", rx, saddr, len);
124
125	ret = rxrpc_validate_address(rx, srx, len);
126	if (ret < 0)
127	goto error;
128
129	lock_sock(&rx->sk);
130
131	if (rx->sk.sk_state != RXRPC_UNCONNECTED) {
132	ret = -EINVAL;
133	goto error_unlock;
134	}
135
136	memcpy(&rx->srx, srx, sizeof(rx->srx));
137
138	/* find a local transport endpoint if we don't have one already */
139	local = rxrpc_lookup_local(&rx->srx);
140	if (IS_ERR(local)) {
141	ret = PTR_ERR(local);
142	goto error_unlock;
143	}
144
145	rx->local = local;
146	if (srx->srx_service) {
147	service_id = htons(srx->srx_service);
148	write_lock_bh(&local->services_lock);
149	list_for_each_entry(prx, &local->services, listen_link) {
150	if (prx->service_id == service_id)
151	goto service_in_use;
152	}
153
154	rx->service_id = service_id;
155	list_add_tail(&rx->listen_link, &local->services);
156	write_unlock_bh(&local->services_lock);
157
158	rx->sk.sk_state = RXRPC_SERVER_BOUND;
159	} else {
160	rx->sk.sk_state = RXRPC_CLIENT_BOUND;
161	}
162
163	release_sock(&rx->sk);
164	_leave(" = 0");
165	return 0;
166
167	service_in_use:
168	ret = -EADDRINUSE;
169	write_unlock_bh(&local->services_lock);
170	error_unlock:
171	release_sock(&rx->sk);
172	error:
173	_leave(" = %d", ret);
174	return ret;
175	}
176
177	/*
178	* set the number of pending calls permitted on a listening socket
179	*/
180	static int rxrpc_listen(struct socket *sock, int backlog)
181	{
182	struct sock *sk = sock->sk;
183	struct rxrpc_sock *rx = rxrpc_sk(sk);
184	int ret;
185
186	_enter("%p,%d", rx, backlog);
187
188	lock_sock(&rx->sk);
189
190	switch (rx->sk.sk_state) {
191	case RXRPC_UNCONNECTED:
192	ret = -EADDRNOTAVAIL;
193	break;
194	case RXRPC_CLIENT_BOUND:
195	case RXRPC_CLIENT_CONNECTED:
196	default:
197	ret = -EBUSY;
198	break;
199	case RXRPC_SERVER_BOUND:
200	ASSERT(rx->local != NULL);
201	sk->sk_max_ack_backlog = backlog;
202	rx->sk.sk_state = RXRPC_SERVER_LISTENING;
203	ret = 0;
204	break;
205	}
206
207	release_sock(&rx->sk);
208	_leave(" = %d", ret);
209	return ret;
210	}
211
212	/*
213	* find a transport by address
214	*/
215	static struct rxrpc_transport rxrpc_name_to_transport(struct socket sock,
216	struct sockaddr *addr,
217	int addr_len, int flags)
218	{
219	struct sockaddr_rxrpc srx = (struct sockaddr_rxrpc ) addr;
220	struct rxrpc_transport *trans;
221	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
222	struct rxrpc_peer *peer;
223
224	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
225
226	ASSERT(rx->local != NULL);
227	ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED);
228
229	if (rx->srx.transport_type != srx->transport_type)
230	return ERR_PTR(-ESOCKTNOSUPPORT);
231	if (rx->srx.transport.family != srx->transport.family)
232	return ERR_PTR(-EAFNOSUPPORT);
233
234	/* find a remote transport endpoint from the local one */
235	peer = rxrpc_get_peer(srx, GFP_KERNEL);
236	if (IS_ERR(peer))
237	return ERR_PTR(PTR_ERR(peer));
238
239	/* find a transport */
240	trans = rxrpc_get_transport(rx->local, peer, GFP_KERNEL);
241	rxrpc_put_peer(peer);
242	_leave(" = %p", trans);
243	return trans;
244	}
245
246	/*
247	* connect an RxRPC socket
248	* - this just targets it at a specific destination; no actual connection
249	* negotiation takes place
250	*/
251	static int rxrpc_connect(struct socket sock, struct sockaddr addr,
252	int addr_len, int flags)
253	{
254	struct sockaddr_rxrpc srx = (struct sockaddr_rxrpc ) addr;
255	struct sock *sk = sock->sk;
256	struct rxrpc_transport *trans;
257	struct rxrpc_local *local;
258	struct rxrpc_sock *rx = rxrpc_sk(sk);
259	int ret;
260
261	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
262
263	ret = rxrpc_validate_address(rx, srx, addr_len);
264	if (ret < 0) {
265	_leave(" = %d [bad addr]", ret);
266	return ret;
267	}
268
269	lock_sock(&rx->sk);
270
271	switch (rx->sk.sk_state) {
272	case RXRPC_UNCONNECTED:
273	/* find a local transport endpoint if we don't have one already */
274	ASSERTCMP(rx->local, ==, NULL);
275	rx->srx.srx_family = AF_RXRPC;
276	rx->srx.srx_service = 0;
277	rx->srx.transport_type = srx->transport_type;
278	rx->srx.transport_len = sizeof(sa_family_t);
279	rx->srx.transport.family = srx->transport.family;
280	local = rxrpc_lookup_local(&rx->srx);
281	if (IS_ERR(local)) {
282	release_sock(&rx->sk);
283	return PTR_ERR(local);
284	}
285	rx->local = local;
286	rx->sk.sk_state = RXRPC_CLIENT_BOUND;
287	case RXRPC_CLIENT_BOUND:
288	break;
289	case RXRPC_CLIENT_CONNECTED:
290	release_sock(&rx->sk);
291	return -EISCONN;
292	default:
293	release_sock(&rx->sk);
294	return -EBUSY; /* server sockets can't connect as well */
295	}
296
297	trans = rxrpc_name_to_transport(sock, addr, addr_len, flags);
298	if (IS_ERR(trans)) {
299	release_sock(&rx->sk);
300	_leave(" = %ld", PTR_ERR(trans));
301	return PTR_ERR(trans);
302	}
303
304	rx->trans = trans;
305	rx->service_id = htons(srx->srx_service);
306	rx->sk.sk_state = RXRPC_CLIENT_CONNECTED;
307
308	release_sock(&rx->sk);
309	return 0;
310	}
311
312	/*
313	* send a message through an RxRPC socket
314	* - in a client this does a number of things:
315	* - finds/sets up a connection for the security specified (if any)
316	* - initiates a call (ID in control data)
317	* - ends the request phase of a call (if MSG_MORE is not set)
318	* - sends a call data packet
319	* - may send an abort (abort code in control data)
320	*/
321	static int rxrpc_sendmsg(struct kiocb iocb, struct socket sock,
322	struct msghdr *m, size_t len)
323	{
324	struct rxrpc_transport *trans;
325	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
326	int ret;
327
328	_enter(",{%d},,%zu", rx->sk.sk_state, len);
329
330	if (m->msg_flags & MSG_OOB)
331	return -EOPNOTSUPP;
332
333	if (m->msg_name) {
334	ret = rxrpc_validate_address(rx, m->msg_name, m->msg_namelen);
335	if (ret < 0) {
336	_leave(" = %d [bad addr]", ret);
337	return ret;
338	}
339	}
340
341	trans = NULL;
342	lock_sock(&rx->sk);
343
344	if (m->msg_name) {
345	ret = -EISCONN;
346	trans = rxrpc_name_to_transport(sock, m->msg_name,
347	m->msg_namelen, 0);
348	if (IS_ERR(trans)) {
349	ret = PTR_ERR(trans);
350	trans = NULL;
351	goto out;
352	}
353	} else {
354	trans = rx->trans;
355	if (trans)
356	atomic_inc(&trans->usage);
357	}
358
359	switch (rx->sk.sk_state) {
360	case RXRPC_SERVER_LISTENING:
361	if (!m->msg_name) {
362	ret = rxrpc_server_sendmsg(iocb, rx, m, len);
363	break;
364	}
365	case RXRPC_SERVER_BOUND:
366	case RXRPC_CLIENT_BOUND:
367	if (!m->msg_name) {
368	ret = -ENOTCONN;
369	break;
370	}
371	case RXRPC_CLIENT_CONNECTED:
372	ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len);
373	break;
374	default:
375	ret = -ENOTCONN;
376	break;
377	}
378
379	out:
380	release_sock(&rx->sk);
381	if (trans)
382	rxrpc_put_transport(trans);
383	_leave(" = %d", ret);
384	return ret;
385	}
386
387	/*
388	* set RxRPC socket options
389	*/
390	static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
391	char __user *optval, int optlen)
392	{
393	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
394	unsigned min_sec_level;
395	int ret;
396
397	_enter(",%d,%d,,%d", level, optname, optlen);
398
399	lock_sock(&rx->sk);
400	ret = -EOPNOTSUPP;
401
402	if (level == SOL_RXRPC) {
403	switch (optname) {
404	case RXRPC_EXCLUSIVE_CONNECTION:
405	ret = -EINVAL;
406	if (optlen != 0)
407	goto error;
408	ret = -EISCONN;
409	if (rx->sk.sk_state != RXRPC_UNCONNECTED)
410	goto error;
411	set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags);
412	goto success;
413
414	case RXRPC_SECURITY_KEY:
415	ret = -EINVAL;
416	if (rx->key)
417	goto error;
418	ret = -EISCONN;
419	if (rx->sk.sk_state != RXRPC_UNCONNECTED)
420	goto error;
421	ret = rxrpc_request_key(rx, optval, optlen);
422	goto error;
423
424	case RXRPC_SECURITY_KEYRING:
425	ret = -EINVAL;
426	if (rx->key)
427	goto error;
428	ret = -EISCONN;
429	if (rx->sk.sk_state != RXRPC_UNCONNECTED)
430	goto error;
431	ret = rxrpc_server_keyring(rx, optval, optlen);
432	goto error;
433
434	case RXRPC_MIN_SECURITY_LEVEL:
435	ret = -EINVAL;
436	if (optlen != sizeof(unsigned))
437	goto error;
438	ret = -EISCONN;
439	if (rx->sk.sk_state != RXRPC_UNCONNECTED)
440	goto error;
441	ret = get_user(min_sec_level,
442	(unsigned __user *) optval);
443	if (ret < 0)
444	goto error;
445	ret = -EINVAL;
446	if (min_sec_level > RXRPC_SECURITY_MAX)
447	goto error;
448	rx->min_sec_level = min_sec_level;
449	goto success;
450
451	default:
452	break;
453	}
454	}
455
456	success:
457	ret = 0;
458	error:
459	release_sock(&rx->sk);
460	return ret;
461	}
462
463	/*
464	* permit an RxRPC socket to be polled
465	*/
466	static unsigned int rxrpc_poll(struct file file, struct socket sock,
467	poll_table *wait)
468	{
469	unsigned int mask;
470	struct sock *sk = sock->sk;
471
472	poll_wait(file, sk->sk_sleep, wait);
473	mask = 0;
474
475	/* the socket is readable if there are any messages waiting on the Rx
476	* queue */
477	if (!skb_queue_empty(&sk->sk_receive_queue))
478	mask \|= POLLIN \| POLLRDNORM;
479
480	/* the socket is writable if there is space to add new data to the
481	* socket; there is no guarantee that any particular call in progress
482	* on the socket may have space in the Tx ACK window */
483	if (rxrpc_writable(sk))
484	mask \|= POLLOUT \| POLLWRNORM;
485
486	return mask;
487	}
488
489	/*
490	* create an RxRPC socket
491	*/
492	static int rxrpc_create(struct socket *sock, int protocol)
493	{
494	struct rxrpc_sock *rx;
495	struct sock *sk;
496
497	_enter("%p,%d", sock, protocol);
498
499	/* we support transport protocol UDP only */
500	if (protocol != PF_INET)
501	return -EPROTONOSUPPORT;
502
503	if (sock->type != SOCK_DGRAM)
504	return -ESOCKTNOSUPPORT;
505
506	sock->ops = &rxrpc_rpc_ops;
507	sock->state = SS_UNCONNECTED;
508
509	sk = sk_alloc(PF_RXRPC, GFP_KERNEL, &rxrpc_proto, 1);
510	if (!sk)
511	return -ENOMEM;
512
513	sock_init_data(sock, sk);
514	sk->sk_state = RXRPC_UNCONNECTED;
515	sk->sk_write_space = rxrpc_write_space;
516	sk->sk_max_ack_backlog = sysctl_rxrpc_max_qlen;
517	sk->sk_destruct = rxrpc_sock_destructor;
518
519	rx = rxrpc_sk(sk);
520	rx->proto = protocol;
521	rx->calls = RB_ROOT;
522
523	INIT_LIST_HEAD(&rx->listen_link);
524	INIT_LIST_HEAD(&rx->secureq);
525	INIT_LIST_HEAD(&rx->acceptq);
526	rwlock_init(&rx->call_lock);
527	memset(&rx->srx, 0, sizeof(rx->srx));
528
529	_leave(" = 0 [%p]", rx);
530	return 0;
531	}
532
533	/*
534	* RxRPC socket destructor
535	*/
536	static void rxrpc_sock_destructor(struct sock *sk)
537	{
538	_enter("%p", sk);
539
540	rxrpc_purge_queue(&sk->sk_receive_queue);
541
542	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
543	BUG_TRAP(sk_unhashed(sk));
544	BUG_TRAP(!sk->sk_socket);
545
546	if (!sock_flag(sk, SOCK_DEAD)) {
547	printk("Attempt to release alive rxrpc socket: %p\n", sk);
548	return;
549	}
550	}
551
552	/*
553	* release an RxRPC socket
554	*/
555	static int rxrpc_release_sock(struct sock *sk)
556	{
557	struct rxrpc_sock *rx = rxrpc_sk(sk);
558
559	_enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt));
560
561	/* declare the socket closed for business */
562	sock_orphan(sk);
563	sk->sk_shutdown = SHUTDOWN_MASK;
564
565	spin_lock_bh(&sk->sk_receive_queue.lock);
566	sk->sk_state = RXRPC_CLOSE;
567	spin_unlock_bh(&sk->sk_receive_queue.lock);
568
569	ASSERTCMP(rx->listen_link.next, !=, LIST_POISON1);
570
571	if (!list_empty(&rx->listen_link)) {
572	write_lock_bh(&rx->local->services_lock);
573	list_del(&rx->listen_link);
574	write_unlock_bh(&rx->local->services_lock);
575	}
576
577	/* try to flush out this socket */
578	rxrpc_release_calls_on_socket(rx);
579	flush_scheduled_work();
580	rxrpc_purge_queue(&sk->sk_receive_queue);
581
582	if (rx->conn) {
583	rxrpc_put_connection(rx->conn);
584	rx->conn = NULL;
585	}
586
587	if (rx->bundle) {
588	rxrpc_put_bundle(rx->trans, rx->bundle);
589	rx->bundle = NULL;
590	}
591	if (rx->trans) {
592	rxrpc_put_transport(rx->trans);
593	rx->trans = NULL;
594	}
595	if (rx->local) {
596	rxrpc_put_local(rx->local);
597	rx->local = NULL;
598	}
599
600	key_put(rx->key);
601	rx->key = NULL;
602	key_put(rx->securities);
603	rx->securities = NULL;
604	sock_put(sk);
605
606	_leave(" = 0");
607	return 0;
608	}
609
610	/*
611	* release an RxRPC BSD socket on close() or equivalent
612	*/
613	static int rxrpc_release(struct socket *sock)
614	{
615	struct sock *sk = sock->sk;
616
617	_enter("%p{%p}", sock, sk);
618
619	if (!sk)
620	return 0;
621
622	sock->sk = NULL;
623
624	return rxrpc_release_sock(sk);
625	}
626
627	/*
628	* RxRPC network protocol
629	*/
630	static const struct proto_ops rxrpc_rpc_ops = {
631	.family = PF_UNIX,
632	.owner = THIS_MODULE,
633	.release = rxrpc_release,
634	.bind = rxrpc_bind,
635	.connect = rxrpc_connect,
636	.socketpair = sock_no_socketpair,
637	.accept = sock_no_accept,
638	.getname = sock_no_getname,
639	.poll = rxrpc_poll,
640	.ioctl = sock_no_ioctl,
641	.listen = rxrpc_listen,
642	.shutdown = sock_no_shutdown,
643	.setsockopt = rxrpc_setsockopt,
644	.getsockopt = sock_no_getsockopt,
645	.sendmsg = rxrpc_sendmsg,
646	.recvmsg = rxrpc_recvmsg,
647	.mmap = sock_no_mmap,
648	.sendpage = sock_no_sendpage,
649	};
650
651	static struct proto rxrpc_proto = {
652	.name = "RXRPC",
653	.owner = THIS_MODULE,
654	.obj_size = sizeof(struct rxrpc_sock),
655	.max_header = sizeof(struct rxrpc_header),
656	};
657
658	static struct net_proto_family rxrpc_family_ops = {
659	.family = PF_RXRPC,
660	.create = rxrpc_create,
661	.owner = THIS_MODULE,
662	};
663
664	/*
665	* initialise and register the RxRPC protocol
666	*/
667	static int __init af_rxrpc_init(void)
668	{
669	struct sk_buff *dummy_skb;
670	int ret = -1;
671
672	BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof(dummy_skb->cb));
673
674	rxrpc_epoch = htonl(xtime.tv_sec);
675
676	rxrpc_call_jar = kmem_cache_create(
677	"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
678	SLAB_HWCACHE_ALIGN, NULL, NULL);
679	if (!rxrpc_call_jar) {
680	printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n");
681	ret = -ENOMEM;
682	goto error_call_jar;
683	}
684
685	ret = proto_register(&rxrpc_proto, 1);
686	if (ret < 0) {
687	printk(KERN_CRIT "RxRPC: Cannot register protocol\n");
688	goto error_proto;
689	}
690
691	ret = sock_register(&rxrpc_family_ops);
692	if (ret < 0) {
693	printk(KERN_CRIT "RxRPC: Cannot register socket family\n");
694	goto error_sock;
695	}
696
697	ret = register_key_type(&key_type_rxrpc);
698	if (ret < 0) {
699	printk(KERN_CRIT "RxRPC: Cannot register client key type\n");
700	goto error_key_type;
701	}
702
703	ret = register_key_type(&key_type_rxrpc_s);
704	if (ret < 0) {
705	printk(KERN_CRIT "RxRPC: Cannot register server key type\n");
706	goto error_key_type_s;
707	}
708
709	#ifdef CONFIG_PROC_FS
710	proc_net_fops_create("rxrpc_calls", 0, &rxrpc_call_seq_fops);
711	proc_net_fops_create("rxrpc_conns", 0, &rxrpc_connection_seq_fops);
712	#endif
713	return 0;
714
715	error_key_type_s:
716	unregister_key_type(&key_type_rxrpc);
717	error_key_type:
718	sock_unregister(PF_RXRPC);
719	error_sock:
720	proto_unregister(&rxrpc_proto);
721	error_proto:
722	kmem_cache_destroy(rxrpc_call_jar);
723	error_call_jar:
724	return ret;
725	}
726
727	/*
728	* unregister the RxRPC protocol
729	*/
730	static void __exit af_rxrpc_exit(void)
731	{
732	_enter("");
733	unregister_key_type(&key_type_rxrpc_s);
734	unregister_key_type(&key_type_rxrpc);
735	sock_unregister(PF_RXRPC);
736	proto_unregister(&rxrpc_proto);
737	rxrpc_destroy_all_calls();
738	rxrpc_destroy_all_connections();
739	rxrpc_destroy_all_transports();
740	rxrpc_destroy_all_peers();
741	rxrpc_destroy_all_locals();
742
743	ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0);
744
745	_debug("flush scheduled work");
746	flush_scheduled_work();
747	proc_net_remove("rxrpc_conns");
748	proc_net_remove("rxrpc_calls");
749	kmem_cache_destroy(rxrpc_call_jar);
750	_leave("");
751	}
752
753	module_init(af_rxrpc_init);
754	module_exit(af_rxrpc_exit);