tcp_ipv4.c

linux 内核源代码

	bh_unlock_sock(sk);
	sock_put(sk);
}

/* This routine computes an IPv4 TCP checksum. */
void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
{
	struct inet_sock *inet = inet_sk(sk);
	struct tcphdr *th = tcp_hdr(skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		th->check = ~tcp_v4_check(len, inet->saddr,
					  inet->daddr, 0);
		skb->csum_start = skb_transport_header(skb) - skb->head;
		skb->csum_offset = offsetof(struct tcphdr, check);
	} else {
		th->check = tcp_v4_check(len, inet->saddr, inet->daddr,
					 csum_partial((char *)th,
						      th->doff << 2,
						      skb->csum));
	}
}

int tcp_v4_gso_send_check(struct sk_buff *skb)
{
	const struct iphdr *iph;
	struct tcphdr *th;

	if (!pskb_may_pull(skb, sizeof(*th)))
		return -EINVAL;

	iph = ip_hdr(skb);
	th = tcp_hdr(skb);

	th->check = 0;
	th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0);
	skb->csum_start = skb_transport_header(skb) - skb->head;
	skb->csum_offset = offsetof(struct tcphdr, check);
	skb->ip_summed = CHECKSUM_PARTIAL;
	return 0;
}

/*
 *	This routine will send an RST to the other tcp.
 *
 *	Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
 *		      for reset.
 *	Answer: if a packet caused RST, it is not for a socket
 *		existing in our system, if it is matched to a socket,
 *		it is just duplicate segment or bug in other side's TCP.
 *		So that we build reply only basing on parameters
 *		arrived with segment.
 *	Exception: precedence violation. We do not implement it in any case.
 */

static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = tcp_hdr(skb);
	struct {
		struct tcphdr th;
#ifdef CONFIG_TCP_MD5SIG
		__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
#endif
	} rep;
	struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
#endif

	/* Never send a reset in response to a reset. */
	if (th->rst)
		return;

	if (((struct rtable *)skb->dst)->rt_type != RTN_LOCAL)
		return;

	/* Swap the send and the receive. */
	memset(&rep, 0, sizeof(rep));
	rep.th.dest   = th->source;
	rep.th.source = th->dest;
	rep.th.doff   = sizeof(struct tcphdr) / 4;
	rep.th.rst    = 1;

	if (th->ack) {
		rep.th.seq = th->ack_seq;
	} else {
		rep.th.ack = 1;
		rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
				       skb->len - (th->doff << 2));
	}

	memset(&arg, 0, sizeof(arg));
	arg.iov[0].iov_base = (unsigned char *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);

#ifdef CONFIG_TCP_MD5SIG
	key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL;
	if (key) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
				   (TCPOPT_NOP << 16) |
				   (TCPOPT_MD5SIG << 8) |
				   TCPOLEN_MD5SIG);
		/* Update length and the length the header thinks exists */
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len / 4;

		tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[1],
					key,
					ip_hdr(skb)->daddr,
					ip_hdr(skb)->saddr,
					&rep.th, IPPROTO_TCP,
					arg.iov[0].iov_len);
	}
#endif
	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
				      ip_hdr(skb)->saddr, /* XXX */
				      sizeof(struct tcphdr), IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;

	ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);

	TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
	TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
}

/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
   outside socket context is ugly, certainly. What can I do?
 */

static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
			    struct sk_buff *skb, u32 seq, u32 ack,
			    u32 win, u32 ts)
{
	struct tcphdr *th = tcp_hdr(skb);
	struct {
		struct tcphdr th;
		__be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
#ifdef CONFIG_TCP_MD5SIG
			   + (TCPOLEN_MD5SIG_ALIGNED >> 2)
#endif
			];
	} rep;
	struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
	struct tcp_md5sig_key tw_key;
#endif

	memset(&rep.th, 0, sizeof(struct tcphdr));
	memset(&arg, 0, sizeof(arg));

	arg.iov[0].iov_base = (unsigned char *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);
	if (ts) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
				   (TCPOPT_TIMESTAMP << 8) |
				   TCPOLEN_TIMESTAMP);
		rep.opt[1] = htonl(tcp_time_stamp);
		rep.opt[2] = htonl(ts);
		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
	}

	/* Swap the send and the receive. */
	rep.th.dest    = th->source;
	rep.th.source  = th->dest;
	rep.th.doff    = arg.iov[0].iov_len / 4;
	rep.th.seq     = htonl(seq);
	rep.th.ack_seq = htonl(ack);
	rep.th.ack     = 1;
	rep.th.window  = htons(win);

#ifdef CONFIG_TCP_MD5SIG
	/*
	 * The SKB holds an imcoming packet, but may not have a valid ->sk
	 * pointer. This is especially the case when we're dealing with a
	 * TIME_WAIT ack, because the sk structure is long gone, and only
	 * the tcp_timewait_sock remains. So the md5 key is stashed in that
	 * structure, and we use it in preference.  I believe that (twsk ||
	 * skb->sk) holds true, but we program defensively.
	 */
	if (!twsk && skb->sk) {
		key = tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr);
	} else if (twsk && twsk->tw_md5_keylen) {
		tw_key.key = twsk->tw_md5_key;
		tw_key.keylen = twsk->tw_md5_keylen;
		key = &tw_key;
	} else
		key = NULL;

	if (key) {
		int offset = (ts) ? 3 : 0;

		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
					  (TCPOPT_NOP << 16) |
					  (TCPOPT_MD5SIG << 8) |
					  TCPOLEN_MD5SIG);
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len/4;

		tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[offset],
					key,
					ip_hdr(skb)->daddr,
					ip_hdr(skb)->saddr,
					&rep.th, IPPROTO_TCP,
					arg.iov[0].iov_len);
	}
#endif
	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
				      ip_hdr(skb)->saddr, /* XXX */
				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
	if (twsk)
		arg.bound_dev_if = twsk->tw_sk.tw_bound_dev_if;

	ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);

	TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
}

static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
	struct inet_timewait_sock *tw = inet_twsk(sk);
	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);

	tcp_v4_send_ack(tcptw, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
			tcptw->tw_ts_recent);

	inet_twsk_put(tw);
}

static void tcp_v4_reqsk_send_ack(struct sk_buff *skb,
				  struct request_sock *req)
{
	tcp_v4_send_ack(NULL, skb, tcp_rsk(req)->snt_isn + 1,
			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
			req->ts_recent);
}

/*
 *	Send a SYN-ACK after having received an ACK.
 *	This still operates on a request_sock only, not on a big
 *	socket.
 */
static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
			      struct dst_entry *dst)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int err = -1;
	struct sk_buff * skb;

	/* First, grab a route. */
	if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
		goto out;

	skb = tcp_make_synack(sk, dst, req);

	if (skb) {
		struct tcphdr *th = tcp_hdr(skb);

		th->check = tcp_v4_check(skb->len,
					 ireq->loc_addr,
					 ireq->rmt_addr,
					 csum_partial((char *)th, skb->len,
						      skb->csum));

		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
					    ireq->rmt_addr,
					    ireq->opt);
		err = net_xmit_eval(err);
	}

out:
	dst_release(dst);
	return err;
}

/*
 *	IPv4 request_sock destructor.
 */
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
	kfree(inet_rsk(req)->opt);
}

#ifdef CONFIG_SYN_COOKIES
static void syn_flood_warning(struct sk_buff *skb)
{
	static unsigned long warntime;

	if (time_after(jiffies, (warntime + HZ * 60))) {
		warntime = jiffies;
		printk(KERN_INFO
		       "possible SYN flooding on port %d. Sending cookies.\n",
		       ntohs(tcp_hdr(skb)->dest));
	}
}
#endif

/*
 * Save and compile IPv4 options into the request_sock if needed.
 */
static struct ip_options *tcp_v4_save_options(struct sock *sk,
					      struct sk_buff *skb)
{
	struct ip_options *opt = &(IPCB(skb)->opt);
	struct ip_options *dopt = NULL;

	if (opt && opt->optlen) {
		int opt_size = optlength(opt);
		dopt = kmalloc(opt_size, GFP_ATOMIC);
		if (dopt) {
			if (ip_options_echo(dopt, skb)) {
				kfree(dopt);
				dopt = NULL;
			}
		}
	}
	return dopt;
}

#ifdef CONFIG_TCP_MD5SIG
/*
 * RFC2385 MD5 checksumming requires a mapping of
 * IP address->MD5 Key.
 * We need to maintain these in the sk structure.
 */

/* Find the Key structure for an address.  */
static struct tcp_md5sig_key *
			tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int i;

	if (!tp->md5sig_info || !tp->md5sig_info->entries4)
		return NULL;
	for (i = 0; i < tp->md5sig_info->entries4; i++) {
		if (tp->md5sig_info->keys4[i].addr == addr)
			return &tp->md5sig_info->keys4[i].base;
	}
	return NULL;
}

struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
					 struct sock *addr_sk)
{
	return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr);
}

EXPORT_SYMBOL(tcp_v4_md5_lookup);

static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
						      struct request_sock *req)
{
	return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
}

/* This can be called on a newly created socket, from other files */
int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
		      u8 *newkey, u8 newkeylen)
{
	/* Add Key to the list */
	struct tcp_md5sig_key *key;
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp4_md5sig_key *keys;

	key = tcp_v4_md5_do_lookup(sk, addr);
	if (key) {
		/* Pre-existing entry - just update that one. */
		kfree(key->key);
		key->key = newkey;
		key->keylen = newkeylen;
	} else {
		struct tcp_md5sig_info *md5sig;

		if (!tp->md5sig_info) {
			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
						  GFP_ATOMIC);
			if (!tp->md5sig_info) {
				kfree(newkey);
				return -ENOMEM;
			}
			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
		}
		if (tcp_alloc_md5sig_pool() == NULL) {
			kfree(newkey);
			return -ENOMEM;
		}
		md5sig = tp->md5sig_info;

		if (md5sig->alloced4 == md5sig->entries4) {
			keys = kmalloc((sizeof(*keys) *
					(md5sig->entries4 + 1)), GFP_ATOMIC);
			if (!keys) {
				kfree(newkey);
				tcp_free_md5sig_pool();
				return -ENOMEM;
			}

			if (md5sig->entries4)
				memcpy(keys, md5sig->keys4,
				       sizeof(*keys) * md5sig->entries4);

			/* Free old key list, and reference new one */
			kfree(md5sig->keys4);
			md5sig->keys4 = keys;
			md5sig->alloced4++;
		}
		md5sig->entries4++;
		md5sig->keys4[md5sig->entries4 - 1].addr        = addr;
		md5sig->keys4[md5sig->entries4 - 1].base.key    = newkey;
		md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen;
	}
	return 0;
}

EXPORT_SYMBOL(tcp_v4_md5_do_add);

static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
			       u8 *newkey, u8 newkeylen)
{
	return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr,
				 newkey, newkeylen);
}

int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int i;

	for (i = 0; i < tp->md5sig_info->entries4; i++) {
		if (tp->md5sig_info->keys4[i].addr == addr) {
			/* Free the key */
			kfree(tp->md5sig_info->keys4[i].base.key);
			tp->md5sig_info->entries4--;

			if (tp->md5sig_info->entries4 == 0) {
				kfree(tp->md5sig_info->keys4);
				tp->md5sig_info->keys4 = NULL;
				tp->md5sig_info->alloced4 = 0;
			} else if (tp->md5sig_info->entries4 != i) {
				/* Need to do some manipulation */
				memmove(&tp->md5sig_info->keys4[i],
					&tp->md5sig_info->keys4[i+1],
					(tp->md5sig_info->entries4 - i) *
					 sizeof(struct tcp4_md5sig_key));
			}
			tcp_free_md5sig_pool();
			return 0;
		}
	}
	return -ENOENT;
}

EXPORT_SYMBOL(tcp_v4_md5_do_del);

static void tcp_v4_clear_md5_list(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Free each key, then the set of key keys,
	 * the crypto element, and then decrement our
	 * hold on the last resort crypto.
	 */
	if (tp->md5sig_info->entries4) {
		int i;
		for (i = 0; i < tp->md5sig_info->entries4; i++)
			kfree(tp->md5sig_info->keys4[i].base.key);
		tp->md5sig_info->entries4 = 0;
		tcp_free_md5sig_pool();
	}
	if (tp->md5sig_info->keys4) {
		kfree(tp->md5sig_info->keys4);
		tp->md5sig_info->keys4 = NULL;
		tp->md5sig_info->alloced4  = 0;
	}
}

static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
				 int optlen)
{
	struct tcp_md5sig cmd;
	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
	u8 *newkey;

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

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

	if (sin->sin_family != AF_INET)
		return -EINVAL;

	if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
		if (!tcp_sk(sk)->md5sig_info)