tcp_ipv6.c

Linux Kernel 2.6.9 for OMAP1710

	if (th->doff < sizeof(struct tcphdr)/4)
		goto bad_packet;
	if (!pskb_may_pull(skb, th->doff*4))
		goto discard_it;

	if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
	     tcp_v6_checksum_init(skb) < 0))
		goto bad_packet;

	th = skb->h.th;
	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
				    skb->len - th->doff*4);
	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
	TCP_SKB_CB(skb)->when = 0;
	TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(skb->nh.ipv6h);
	TCP_SKB_CB(skb)->sacked = 0;

	sk = __tcp_v6_lookup(&skb->nh.ipv6h->saddr, th->source,
			     &skb->nh.ipv6h->daddr, ntohs(th->dest), tcp_v6_iif(skb));

	if (!sk)
		goto no_tcp_socket;

process:
	if (sk->sk_state == TCP_TIME_WAIT)
		goto do_time_wait;

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;

	if (sk_filter(sk, skb, 0))
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock(sk);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
		if (!tcp_prequeue(sk, skb))
			ret = tcp_v6_do_rcv(sk, skb);
	} else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);

	sock_put(sk);
	return ret ? -1 : 0;

no_tcp_socket:
	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
bad_packet:
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
	} else {
		tcp_v6_send_reset(skb);
	}

discard_it:

	/*
	 *	Discard frame
	 */

	kfree_skb(skb);
	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}

	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}

	switch(tcp_timewait_state_process((struct tcp_tw_bucket *)sk,
					  skb, th, skb->len)) {
	case TCP_TW_SYN:
	{
		struct sock *sk2;

		sk2 = tcp_v6_lookup_listener(&skb->nh.ipv6h->daddr, ntohs(th->dest), tcp_v6_iif(skb));
		if (sk2 != NULL) {
			tcp_tw_deschedule((struct tcp_tw_bucket *)sk);
			tcp_tw_put((struct tcp_tw_bucket *)sk);
			sk = sk2;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v6_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		goto no_tcp_socket;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

static int tcp_v6_rebuild_header(struct sock *sk)
{
	int err;
	struct dst_entry *dst;
	struct ipv6_pinfo *np = inet6_sk(sk);

	dst = __sk_dst_check(sk, np->dst_cookie);

	if (dst == NULL) {
		struct inet_opt *inet = inet_sk(sk);
		struct in6_addr *final_p = NULL, final;
		struct flowi fl;

		memset(&fl, 0, sizeof(fl));
		fl.proto = IPPROTO_TCP;
		ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
		fl.fl6_flowlabel = np->flow_label;
		fl.oif = sk->sk_bound_dev_if;
		fl.fl_ip_dport = inet->dport;
		fl.fl_ip_sport = inet->sport;

		if (np->opt && np->opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}

		err = ip6_dst_lookup(sk, &dst, &fl);
		if (err) {
			sk->sk_route_caps = 0;
			return err;
		}
		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
			sk->sk_err_soft = -err;
			dst_release(dst);
			return err;
		}

		ip6_dst_store(sk, dst, NULL);
		sk->sk_route_caps = dst->dev->features &
			~(NETIF_F_IP_CSUM | NETIF_F_TSO);
		tcp_sk(sk)->ext2_header_len = dst->header_len;
	}

	return 0;
}

static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok)
{
	struct sock *sk = skb->sk;
	struct inet_opt *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct flowi fl;
	struct dst_entry *dst;

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
	fl.fl6_flowlabel = np->flow_label;
	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
	fl.oif = sk->sk_bound_dev_if;
	fl.fl_ip_sport = inet->sport;
	fl.fl_ip_dport = inet->dport;

	if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
	}

	dst = __sk_dst_check(sk, np->dst_cookie);

	if (dst == NULL) {
		int err = ip6_dst_lookup(sk, &dst, &fl);

		if (err) {
			sk->sk_err_soft = -err;
			return err;
		}

		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
			sk->sk_route_caps = 0;
			dst_release(dst);
			return err;
		}

		ip6_dst_store(sk, dst, NULL);
		sk->sk_route_caps = dst->dev->features &
			~(NETIF_F_IP_CSUM | NETIF_F_TSO);
		tcp_sk(sk)->ext2_header_len = dst->header_len;
	}

	skb->dst = dst_clone(dst);

	/* Restore final destination back after routing done */
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);

	return ip6_xmit(sk, skb, &fl, np->opt, 0);
}

static void v6_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;

	sin6->sin6_family = AF_INET6;
	ipv6_addr_copy(&sin6->sin6_addr, &np->daddr);
	sin6->sin6_port	= inet_sk(sk)->dport;
	/* We do not store received flowlabel for TCP */
	sin6->sin6_flowinfo = 0;
	sin6->sin6_scope_id = 0;
	if (sk->sk_bound_dev_if &&
	    ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
		sin6->sin6_scope_id = sk->sk_bound_dev_if;
}

static int tcp_v6_remember_stamp(struct sock *sk)
{
	/* Alas, not yet... */
	return 0;
}

static struct tcp_func ipv6_specific = {
	.queue_xmit	=	tcp_v6_xmit,
	.send_check	=	tcp_v6_send_check,
	.rebuild_header	=	tcp_v6_rebuild_header,
	.conn_request	=	tcp_v6_conn_request,
	.syn_recv_sock	=	tcp_v6_syn_recv_sock,
	.remember_stamp	=	tcp_v6_remember_stamp,
	.net_header_len	=	sizeof(struct ipv6hdr),

	.setsockopt	=	ipv6_setsockopt,
	.getsockopt	=	ipv6_getsockopt,
	.addr2sockaddr	=	v6_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in6)
};

/*
 *	TCP over IPv4 via INET6 API
 */

static struct tcp_func ipv6_mapped = {
	.queue_xmit	=	ip_queue_xmit,
	.send_check	=	tcp_v4_send_check,
	.rebuild_header	=	tcp_v4_rebuild_header,
	.conn_request	=	tcp_v6_conn_request,
	.syn_recv_sock	=	tcp_v6_syn_recv_sock,
	.remember_stamp	=	tcp_v4_remember_stamp,
	.net_header_len	=	sizeof(struct iphdr),

	.setsockopt	=	ipv6_setsockopt,
	.getsockopt	=	ipv6_getsockopt,
	.addr2sockaddr	=	v6_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in6)
};



/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
static int tcp_v6_init_sock(struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);

	skb_queue_head_init(&tp->out_of_order_queue);
	tcp_init_xmit_timers(sk);
	tcp_prequeue_init(tp);

	tp->rto  = TCP_TIMEOUT_INIT;
	tp->mdev = TCP_TIMEOUT_INIT;

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = 2;

	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache_std = tp->mss_cache = 536;

	tp->reordering = sysctl_tcp_reordering;

	sk->sk_state = TCP_CLOSE;

	tp->af_specific = &ipv6_specific;

	sk->sk_write_space = sk_stream_write_space;
	sk->sk_use_write_queue = 1;

	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	atomic_inc(&tcp_sockets_allocated);

	return 0;
}

static int tcp_v6_destroy_sock(struct sock *sk)
{
	extern int tcp_v4_destroy_sock(struct sock *sk);

	tcp_v4_destroy_sock(sk);
	return inet6_destroy_sock(sk);
}

/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq, 
			 struct sock *sk, struct open_request *req, int i, int uid)
{
	struct in6_addr *dest, *src;
	int ttd = req->expires - jiffies;

	if (ttd < 0)
		ttd = 0;

	src = &req->af.v6_req.loc_addr;
	dest = &req->af.v6_req.rmt_addr;
	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3],
		   ntohs(inet_sk(sk)->sport),
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3],
		   ntohs(req->rmt_port),
		   TCP_SYN_RECV,
		   0,0, /* could print option size, but that is af dependent. */
		   1,   /* timers active (only the expire timer) */  
		   jiffies_to_clock_t(ttd), 
		   req->retrans,
		   uid,
		   0,  /* non standard timer */  
		   0, /* open_requests have no inode */
		   0, req);
}

static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
{
	struct in6_addr *dest, *src;
	__u16 destp, srcp;
	int timer_active;
	unsigned long timer_expires;
	struct inet_opt *inet = inet_sk(sp);
	struct tcp_opt *tp = tcp_sk(sp);
	struct ipv6_pinfo *np = inet6_sk(sp);

	dest  = &np->daddr;
	src   = &np->rcv_saddr;
	destp = ntohs(inet->dport);
	srcp  = ntohs(inet->sport);
	if (tp->pending == TCP_TIME_RETRANS) {
		timer_active	= 1;
		timer_expires	= tp->timeout;
	} else if (tp->pending == TCP_TIME_PROBE0) {
		timer_active	= 4;
		timer_expires	= tp->timeout;
	} else if (timer_pending(&sp->sk_timer)) {
		timer_active	= 2;
		timer_expires	= sp->sk_timer.expires;
	} else {
		timer_active	= 0;
		timer_expires = jiffies;
	}

	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %u %u %u %u %d\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
		   sp->sk_state, 
		   tp->write_seq-tp->snd_una, tp->rcv_nxt-tp->copied_seq,
		   timer_active,
		   jiffies_to_clock_t(timer_expires - jiffies),
		   tp->retransmits,
		   sock_i_uid(sp),
		   tp->probes_out,
		   sock_i_ino(sp),
		   atomic_read(&sp->sk_refcnt), sp,
		   tp->rto, tp->ack.ato, (tp->ack.quick<<1)|tp->ack.pingpong,
		   tp->snd_cwnd, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh
		   );
}

static void get_timewait6_sock(struct seq_file *seq, 
			       struct tcp_tw_bucket *tw, int i)
{
	struct in6_addr *dest, *src;
	__u16 destp, srcp;
	int ttd = tw->tw_ttd - jiffies;

	if (ttd < 0)
		ttd = 0;

	dest  = &tw->tw_v6_daddr;
	src   = &tw->tw_v6_rcv_saddr;
	destp = ntohs(tw->tw_dport);
	srcp  = ntohs(tw->tw_sport);

	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
		   tw->tw_substate, 0, 0,
		   3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
		   atomic_read(&tw->tw_refcnt), tw);
}

#ifdef CONFIG_PROC_FS
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st;

	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
			 "  sl  "
			 "local_address                         "
			 "remote_address                        "
			 "st tx_queue rx_queue tr tm->when retrnsmt"
			 "   uid  timeout inode\n");
		goto out;
	}
	st = seq->private;

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
	case TCP_SEQ_STATE_ESTABLISHED:
		get_tcp6_sock(seq, v, st->num);
		break;
	case TCP_SEQ_STATE_OPENREQ:
		get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
		get_timewait6_sock(seq, v, st->num);
		break;
	}
out:
	return 0;
}

static struct file_operations tcp6_seq_fops;
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "tcp6",
	.family		= AF_INET6,
	.seq_show	= tcp6_seq_show,
	.seq_fops	= &tcp6_seq_fops,
};

int __init tcp6_proc_init(void)
{
	return tcp_proc_register(&tcp6_seq_afinfo);
}

void tcp6_proc_exit(void)
{
	tcp_proc_unregister(&tcp6_seq_afinfo);
}
#endif

struct proto tcpv6_prot = {
	.name			= "TCPv6",
	.close			= tcp_close,
	.connect		= tcp_v6_connect,
	.disconnect		= tcp_disconnect,
	.accept			= tcp_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v6_init_sock,
	.destroy		= tcp_v6_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.sendmsg		= tcp_sendmsg,
	.recvmsg		= tcp_recvmsg,
	.backlog_rcv		= tcp_v6_do_rcv,
	.hash			= tcp_v6_hash,
	.unhash			= tcp_unhash,
	.get_port		= tcp_v6_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.memory_allocated	= &tcp_memory_allocated,
	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_mem		= sysctl_tcp_mem,
	.sysctl_wmem		= sysctl_tcp_wmem,
	.sysctl_rmem		= sysctl_tcp_rmem,
	.max_header		= MAX_TCP_HEADER,
	.slab_obj_size		= sizeof(struct tcp6_sock),
};

static struct inet6_protocol tcpv6_protocol = {
	.handler	=	tcp_v6_rcv,
	.err_handler	=	tcp_v6_err,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

extern struct proto_ops inet6_stream_ops;

static struct inet_protosw tcpv6_protosw = {
	.type		=	SOCK_STREAM,
	.protocol	=	IPPROTO_TCP,
	.prot		=	&tcpv6_prot,
	.ops		=	&inet6_stream_ops,
	.capability	=	-1,
	.no_check	=	0,
	.flags		=	INET_PROTOSW_PERMANENT,
};

void __init tcpv6_init(void)
{
	/* register inet6 protocol */
	if (inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP) < 0)
		printk(KERN_ERR "tcpv6_init: Could not register protocol\n");
	inet6_register_protosw(&tcpv6_protosw);
}