proto.c

linux 内核源代码

/*
 *  net/dccp/proto.c
 *
 *  An implementation of the DCCP protocol
 *  Arnaldo Carvalho de Melo <[e-mail]>
 *
 *	This program is free software; you can redistribute it and/or modify it
 *	under the terms of the GNU General Public License version 2 as
 *	published by the Free Software Foundation.
 */

#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/random.h>
#include <net/checksum.h>

#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/xfrm.h>

#include <asm/ioctls.h>
#include <asm/semaphore.h>
#include <linux/spinlock.h>
#include <linux/timer.h>
#include <linux/delay.h>
#include <linux/poll.h>

#include "ccid.h"
#include "dccp.h"
#include "feat.h"

DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;

EXPORT_SYMBOL_GPL(dccp_statistics);

atomic_t dccp_orphan_count = ATOMIC_INIT(0);

EXPORT_SYMBOL_GPL(dccp_orphan_count);

struct inet_hashinfo __cacheline_aligned dccp_hashinfo = {
	.lhash_lock	= RW_LOCK_UNLOCKED,
	.lhash_users	= ATOMIC_INIT(0),
	.lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait),
};

EXPORT_SYMBOL_GPL(dccp_hashinfo);

/* the maximum queue length for tx in packets. 0 is no limit */
int sysctl_dccp_tx_qlen __read_mostly = 5;

void dccp_set_state(struct sock *sk, const int state)
{
	const int oldstate = sk->sk_state;

	dccp_pr_debug("%s(%p) %-10.10s -> %s\n",
		      dccp_role(sk), sk,
		      dccp_state_name(oldstate), dccp_state_name(state));
	WARN_ON(state == oldstate);

	switch (state) {
	case DCCP_OPEN:
		if (oldstate != DCCP_OPEN)
			DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
		break;

	case DCCP_CLOSED:
		if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN)
			DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);

		sk->sk_prot->unhash(sk);
		if (inet_csk(sk)->icsk_bind_hash != NULL &&
		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
			inet_put_port(&dccp_hashinfo, sk);
		/* fall through */
	default:
		if (oldstate == DCCP_OPEN)
			DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
	}

	/* Change state AFTER socket is unhashed to avoid closed
	 * socket sitting in hash tables.
	 */
	sk->sk_state = state;
}

EXPORT_SYMBOL_GPL(dccp_set_state);

void dccp_done(struct sock *sk)
{
	dccp_set_state(sk, DCCP_CLOSED);
	dccp_clear_xmit_timers(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_state_change(sk);
	else
		inet_csk_destroy_sock(sk);
}

EXPORT_SYMBOL_GPL(dccp_done);

const char *dccp_packet_name(const int type)
{
	static const char *dccp_packet_names[] = {
		[DCCP_PKT_REQUEST]  = "REQUEST",
		[DCCP_PKT_RESPONSE] = "RESPONSE",
		[DCCP_PKT_DATA]	    = "DATA",
		[DCCP_PKT_ACK]	    = "ACK",
		[DCCP_PKT_DATAACK]  = "DATAACK",
		[DCCP_PKT_CLOSEREQ] = "CLOSEREQ",
		[DCCP_PKT_CLOSE]    = "CLOSE",
		[DCCP_PKT_RESET]    = "RESET",
		[DCCP_PKT_SYNC]	    = "SYNC",
		[DCCP_PKT_SYNCACK]  = "SYNCACK",
	};

	if (type >= DCCP_NR_PKT_TYPES)
		return "INVALID";
	else
		return dccp_packet_names[type];
}

EXPORT_SYMBOL_GPL(dccp_packet_name);

const char *dccp_state_name(const int state)
{
	static char *dccp_state_names[] = {
	[DCCP_OPEN]	  = "OPEN",
	[DCCP_REQUESTING] = "REQUESTING",
	[DCCP_PARTOPEN]	  = "PARTOPEN",
	[DCCP_LISTEN]	  = "LISTEN",
	[DCCP_RESPOND]	  = "RESPOND",
	[DCCP_CLOSING]	  = "CLOSING",
	[DCCP_TIME_WAIT]  = "TIME_WAIT",
	[DCCP_CLOSED]	  = "CLOSED",
	};

	if (state >= DCCP_MAX_STATES)
		return "INVALID STATE!";
	else
		return dccp_state_names[state];
}

EXPORT_SYMBOL_GPL(dccp_state_name);

void dccp_hash(struct sock *sk)
{
	inet_hash(&dccp_hashinfo, sk);
}

EXPORT_SYMBOL_GPL(dccp_hash);

void dccp_unhash(struct sock *sk)
{
	inet_unhash(&dccp_hashinfo, sk);
}

EXPORT_SYMBOL_GPL(dccp_unhash);

int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_minisock *dmsk = dccp_msk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	dccp_minisock_init(&dp->dccps_minisock);

	/*
	 * FIXME: We're hardcoding the CCID, and doing this at this point makes
	 * the listening (master) sock get CCID control blocks, which is not
	 * necessary, but for now, to not mess with the test userspace apps,
	 * lets leave it here, later the real solution is to do this in a
	 * setsockopt(CCIDs-I-want/accept). -acme
	 */
	if (likely(ctl_sock_initialized)) {
		int rc = dccp_feat_init(dmsk);

		if (rc)
			return rc;

		if (dmsk->dccpms_send_ack_vector) {
			dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL);
			if (dp->dccps_hc_rx_ackvec == NULL)
				return -ENOMEM;
		}
		dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid,
						      sk, GFP_KERNEL);
		dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid,
						      sk, GFP_KERNEL);
		if (unlikely(dp->dccps_hc_rx_ccid == NULL ||
			     dp->dccps_hc_tx_ccid == NULL)) {
			ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
			ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
			if (dmsk->dccpms_send_ack_vector) {
				dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
				dp->dccps_hc_rx_ackvec = NULL;
			}
			dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
			return -ENOMEM;
		}
	} else {
		/* control socket doesn't need feat nego */
		INIT_LIST_HEAD(&dmsk->dccpms_pending);
		INIT_LIST_HEAD(&dmsk->dccpms_conf);
	}

	dccp_init_xmit_timers(sk);
	icsk->icsk_rto		= DCCP_TIMEOUT_INIT;
	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
	sk->sk_state		= DCCP_CLOSED;
	sk->sk_write_space	= dccp_write_space;
	icsk->icsk_sync_mss	= dccp_sync_mss;
	dp->dccps_mss_cache	= 536;
	dp->dccps_rate_last	= jiffies;
	dp->dccps_role		= DCCP_ROLE_UNDEFINED;
	dp->dccps_service	= DCCP_SERVICE_CODE_IS_ABSENT;
	dp->dccps_l_ack_ratio	= dp->dccps_r_ack_ratio = 1;

	return 0;
}

EXPORT_SYMBOL_GPL(dccp_init_sock);

int dccp_destroy_sock(struct sock *sk)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_minisock *dmsk = dccp_msk(sk);

	/*
	 * DCCP doesn't use sk_write_queue, just sk_send_head
	 * for retransmissions
	 */
	if (sk->sk_send_head != NULL) {
		kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;
	}

	/* Clean up a referenced DCCP bind bucket. */
	if (inet_csk(sk)->icsk_bind_hash != NULL)
		inet_put_port(&dccp_hashinfo, sk);

	kfree(dp->dccps_service_list);
	dp->dccps_service_list = NULL;

	if (dmsk->dccpms_send_ack_vector) {
		dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
		dp->dccps_hc_rx_ackvec = NULL;
	}
	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;

	/* clean up feature negotiation state */
	dccp_feat_clean(dmsk);

	return 0;
}

EXPORT_SYMBOL_GPL(dccp_destroy_sock);

static inline int dccp_listen_start(struct sock *sk, int backlog)
{
	struct dccp_sock *dp = dccp_sk(sk);

	dp->dccps_role = DCCP_ROLE_LISTEN;
	return inet_csk_listen_start(sk, backlog);
}

int dccp_disconnect(struct sock *sk, int flags)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet = inet_sk(sk);
	int err = 0;
	const int old_state = sk->sk_state;

	if (old_state != DCCP_CLOSED)
		dccp_set_state(sk, DCCP_CLOSED);

	/* ABORT function of RFC793 */
	if (old_state == DCCP_LISTEN) {
		inet_csk_listen_stop(sk);
	/* FIXME: do the active reset thing */
	} else if (old_state == DCCP_REQUESTING)
		sk->sk_err = ECONNRESET;

	dccp_clear_xmit_timers(sk);
	__skb_queue_purge(&sk->sk_receive_queue);
	if (sk->sk_send_head != NULL) {
		__kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;
	}

	inet->dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);

	icsk->icsk_backoff = 0;
	inet_csk_delack_init(sk);
	__sk_dst_reset(sk);

	BUG_TRAP(!inet->num || icsk->icsk_bind_hash);

	sk->sk_error_report(sk);
	return err;
}

EXPORT_SYMBOL_GPL(dccp_disconnect);

/*
 *	Wait for a DCCP event.
 *
 *	Note that we don't need to lock the socket, as the upper poll layers
 *	take care of normal races (between the test and the event) and we don't
 *	go look at any of the socket buffers directly.
 */
unsigned int dccp_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);
	if (sk->sk_state == DCCP_LISTEN)
		return inet_csk_listen_poll(sk);

	/* Socket is not locked. We are protected from async events
	   by poll logic and correct handling of state changes
	   made by another threads is impossible in any case.
	 */

	mask = 0;
	if (sk->sk_err)
		mask = POLLERR;

	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
		mask |= POLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLIN | POLLRDNORM | POLLRDHUP;

	/* Connected? */
	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
		if (atomic_read(&sk->sk_rmem_alloc) > 0)
			mask |= POLLIN | POLLRDNORM;

		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
			if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
				mask |= POLLOUT | POLLWRNORM;
			} else {  /* send SIGIO later */
				set_bit(SOCK_ASYNC_NOSPACE,
					&sk->sk_socket->flags);
				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);

				/* Race breaker. If space is freed after
				 * wspace test but before the flags are set,
				 * IO signal will be lost.
				 */
				if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
					mask |= POLLOUT | POLLWRNORM;
			}
		}
	}
	return mask;
}

EXPORT_SYMBOL_GPL(dccp_poll);

int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	int rc = -ENOTCONN;

	lock_sock(sk);

	if (sk->sk_state == DCCP_LISTEN)
		goto out;

	switch (cmd) {
	case SIOCINQ: {
		struct sk_buff *skb;
		unsigned long amount = 0;

		skb = skb_peek(&sk->sk_receive_queue);
		if (skb != NULL) {
			/*
			 * We will only return the amount of this packet since
			 * that is all that will be read.
			 */
			amount = skb->len;
		}
		rc = put_user(amount, (int __user *)arg);
	}
		break;
	default:
		rc = -ENOIOCTLCMD;
		break;
	}
out:
	release_sock(sk);
	return rc;
}

EXPORT_SYMBOL_GPL(dccp_ioctl);

static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
				   char __user *optval, int optlen)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_service_list *sl = NULL;

	if (service == DCCP_SERVICE_INVALID_VALUE ||
	    optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32))
		return -EINVAL;

	if (optlen > sizeof(service)) {
		sl = kmalloc(optlen, GFP_KERNEL);
		if (sl == NULL)
			return -ENOMEM;

		sl->dccpsl_nr = optlen / sizeof(u32) - 1;
		if (copy_from_user(sl->dccpsl_list,
				   optval + sizeof(service),
				   optlen - sizeof(service)) ||
		    dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
			kfree(sl);
			return -EFAULT;
		}
	}

	lock_sock(sk);
	dp->dccps_service = service;

	kfree(dp->dccps_service_list);

	dp->dccps_service_list = sl;
	release_sock(sk);
	return 0;
}

/* byte 1 is feature.  the rest is the preference list */
static int dccp_setsockopt_change(struct sock *sk, int type,
				  struct dccp_so_feat __user *optval)
{
	struct dccp_so_feat opt;
	u8 *val;
	int rc;

	if (copy_from_user(&opt, optval, sizeof(opt)))
		return -EFAULT;

	val = kmalloc(opt.dccpsf_len, GFP_KERNEL);
	if (!val)
		return -ENOMEM;

	if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) {
		rc = -EFAULT;
		goto out_free_val;
	}

	rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat,
			      val, opt.dccpsf_len, GFP_KERNEL);
	if (rc)
		goto out_free_val;

out:
	return rc;

out_free_val:
	kfree(val);
	goto out;
}

static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
		char __user *optval, int optlen)
{
	struct dccp_sock *dp = dccp_sk(sk);
	int val, err = 0;

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	if (optname == DCCP_SOCKOPT_SERVICE)
		return dccp_setsockopt_service(sk, val, optval, optlen);

	lock_sock(sk);
	switch (optname) {
	case DCCP_SOCKOPT_PACKET_SIZE:
		DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
		err = 0;
		break;
	case DCCP_SOCKOPT_CHANGE_L:
		if (optlen != sizeof(struct dccp_so_feat))
			err = -EINVAL;
		else
			err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L,
						     (struct dccp_so_feat __user *)
						     optval);
		break;
	case DCCP_SOCKOPT_CHANGE_R:
		if (optlen != sizeof(struct dccp_so_feat))
			err = -EINVAL;
		else
			err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R,
						     (struct dccp_so_feat __user *)
						     optval);
		break;
	case DCCP_SOCKOPT_SEND_CSCOV:	/* sender side, RFC 4340, sec. 9.2 */
		if (val < 0 || val > 15)
			err = -EINVAL;
		else
			dp->dccps_pcslen = val;
		break;
	case DCCP_SOCKOPT_RECV_CSCOV:	/* receiver side, RFC 4340 sec. 9.2.1 */
		if (val < 0 || val > 15)
			err = -EINVAL;
		else {
			dp->dccps_pcrlen = val;
			/* FIXME: add feature negotiation,
			 * ChangeL(MinimumChecksumCoverage, val) */
		}
		break;
	default:
		err = -ENOPROTOOPT;
		break;
	}

	release_sock(sk);
	return err;
}

int dccp_setsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int optlen)
{
	if (level != SOL_DCCP)
		return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
							     optname, optval,
							     optlen);
	return do_dccp_setsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL_GPL(dccp_setsockopt);

#ifdef CONFIG_COMPAT
int compat_dccp_setsockopt(struct sock *sk, int level, int optname,
			   char __user *optval, int optlen)
{
	if (level != SOL_DCCP)
		return inet_csk_compat_setsockopt(sk, level, optname,
						  optval, optlen);
	return do_dccp_setsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL_GPL(compat_dccp_setsockopt);
#endif

static int dccp_getsockopt_service(struct sock *sk, int len,
				   __be32 __user *optval,
				   int __user *optlen)
{
	const struct dccp_sock *dp = dccp_sk(sk);
	const struct dccp_service_list *sl;
	int err = -ENOENT, slen = 0, total_len = sizeof(u32);

	lock_sock(sk);
	if ((sl = dp->dccps_service_list) != NULL) {