Release 4.11 net/ipv4/tcp_ipv4.c

/*
 * INET         An implementation of the TCP/IP protocol suite for the LINUX
 *              operating system.  INET is implemented using the  BSD Socket
 *              interface as the means of communication with the user level.
 *
 *              Implementation of the Transmission Control Protocol(TCP).
 *
 *              IPv4 specific functions
 *
 *
 *              code split from:
 *              linux/ipv4/tcp.c
 *              linux/ipv4/tcp_input.c
 *              linux/ipv4/tcp_output.c
 *
 *              See tcp.c for author information
 *
 *      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.
 */

/*
 * Changes:
 *              David S. Miller :       New socket lookup architecture.
 *                                      This code is dedicated to John Dyson.
 *              David S. Miller :       Change semantics of established hash,
 *                                      half is devoted to TIME_WAIT sockets
 *                                      and the rest go in the other half.
 *              Andi Kleen :            Add support for syncookies and fixed
 *                                      some bugs: ip options weren't passed to
 *                                      the TCP layer, missed a check for an
 *                                      ACK bit.
 *              Andi Kleen :            Implemented fast path mtu discovery.
 *                                      Fixed many serious bugs in the
 *                                      request_sock handling and moved
 *                                      most of it into the af independent code.
 *                                      Added tail drop and some other bugfixes.
 *                                      Added new listen semantics.
 *              Mike McLagan    :       Routing by source
 *      Juan Jose Ciarlante:            ip_dynaddr bits
 *              Andi Kleen:             various fixes.
 *      Vitaly E. Lavrov        :       Transparent proxy revived after year
 *                                      coma.
 *      Andi Kleen              :       Fix new listen.
 *      Andi Kleen              :       Fix accept error reporting.
 *      YOSHIFUJI Hideaki @USAGI and:   Support IPV6_V6ONLY socket option, which
 *      Alexey Kuznetsov                allow both IPv4 and IPv6 sockets to bind
 *                                      a single port at the same time.
 */


#define pr_fmt(fmt) "TCP: " fmt

#include <linux/bottom_half.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/times.h>
#include <linux/slab.h>

#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
#include <net/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/secure_seq.h>
#include <net/busy_poll.h>

#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/stddef.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <crypto/hash.h>
#include <linux/scatterlist.h>


int sysctl_tcp_low_latency __read_mostly;

#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
#endif


struct inet_hashinfo tcp_hashinfo;

EXPORT_SYMBOL(tcp_hashinfo);



static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
{
	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
					  ip_hdr(skb)->saddr,
					  tcp_hdr(skb)->dest,
					  tcp_hdr(skb)->source, tsoff);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
36
72.00%
3
37.50%
Florian Westphal
7
14.00%
1
12.50%
Linus Torvalds
4
8.00%
1
12.50%
David S. Miller
2
4.00%
2
25.00%
Eric Dumazet
1
2.00%
1
12.50%
Total
50
100.00%
8
100.00%



int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
	struct tcp_sock *tp = tcp_sk(sk);

	/* With PAWS, it is safe from the viewpoint
           of data integrity. Even without PAWS it is safe provided sequence
           spaces do not overlap i.e. at data rates <= 80Mbit/sec.

           Actually, the idea is close to VJ's one, only timestamp cache is
           held not per host, but per port pair and TW bucket is used as state
           holder.

           If TW bucket has been already destroyed we fall back to VJ's scheme
           and use initial timestamp retrieved from peer table.
         */
	if (tcptw->tw_ts_recent_stamp &&
	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
		if (tp->write_seq == 0)
			tp->write_seq = 1;
		tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
		tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
		sock_hold(sktw);
		return 1;
	}

	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
121
92.37%
1
25.00%
Haishuang Yan
7
5.34%
1
25.00%
James Morris
2
1.53%
1
25.00%
Ian Morris
1
0.76%
1
25.00%
Total
131
100.00%
4
100.00%


EXPORT_SYMBOL_GPL(tcp_twsk_unique);

/* This will initiate an outgoing connection. */


int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	__be16 orig_sport, orig_dport;
	__be32 daddr, nexthop;
	struct flowi4 *fl4;
	struct rtable *rt;
	int err;
	u32 seq;
	struct ip_options_rcu *inet_opt;
	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	nexthop = daddr = usin->sin_addr.s_addr;
	inet_opt = rcu_dereference_protected(inet->inet_opt,
					     lockdep_sock_is_held(sk));
	if (inet_opt && inet_opt->opt.srr) {
		if (!daddr)
			return -EINVAL;
		nexthop = inet_opt->opt.faddr;
	}

	orig_sport = inet->inet_sport;
	orig_dport = usin->sin_port;
	fl4 = &inet->cork.fl.u.ip4;
	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
			      IPPROTO_TCP,
			      orig_sport, orig_dport, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		if (err == -ENETUNREACH)
			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
		return err;
	}

	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
		ip_rt_put(rt);
		return -ENETUNREACH;
	}

	if (!inet_opt || !inet_opt->opt.srr)
		daddr = fl4->daddr;

	if (!inet->inet_saddr)
		inet->inet_saddr = fl4->saddr;
	sk_rcv_saddr_set(sk, inet->inet_saddr);

	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
		/* Reset inherited state */
		tp->rx_opt.ts_recent	   = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		if (likely(!tp->repair))
			tp->write_seq	   = 0;
	}

	if (tcp_death_row->sysctl_tw_recycle &&
	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
		tcp_fetch_timewait_stamp(sk, &rt->dst);

	inet->inet_dport = usin->sin_port;
	sk_daddr_set(sk, daddr);

	inet_csk(sk)->icsk_ext_hdr_len = 0;
	if (inet_opt)
		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;

	tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;

	/* Socket identity is still unknown (sport may be zero).
         * However we set state to SYN-SENT and not releasing socket
         * lock select source port, enter ourselves into the hash tables and
         * complete initialization after this.
         */
	tcp_set_state(sk, TCP_SYN_SENT);
	err = inet_hash_connect(tcp_death_row, sk);
	if (err)
		goto failure;

	sk_set_txhash(sk);

	rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
			       inet->inet_sport, inet->inet_dport, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		rt = NULL;
		goto failure;
	}
	/* OK, now commit destination to socket.  */
	sk->sk_gso_type = SKB_GSO_TCPV4;
	sk_setup_caps(sk, &rt->dst);
	rt = NULL;

	if (likely(!tp->repair)) {
		seq = secure_tcp_sequence_number(inet->inet_saddr,
						 inet->inet_daddr,
						 inet->inet_sport,
						 usin->sin_port,
						 &tp->tsoffset);
		if (!tp->write_seq)
			tp->write_seq = seq;
	}

	inet->inet_id = tp->write_seq ^ jiffies;

	if (tcp_fastopen_defer_connect(sk, &err))
		return err;
	if (err)
		goto failure;

	err = tcp_connect(sk);

	if (err)
		goto failure;

	return 0;

failure:
	/*
         * This unhashes the socket and releases the local port,
         * if necessary.
         */
	tcp_set_state(sk, TCP_CLOSE);
	ip_rt_put(rt);
	sk->sk_route_caps = 0;
	inet->inet_dport = 0;
	return err;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
206
30.21%
13
21.31%
David S. Miller
143
20.97%
11
18.03%
Alexey Kuznetsov
66
9.68%
2
3.28%
Linus Torvalds (pre-git)
64
9.38%
11
18.03%
Eric Dumazet
55
8.06%
5
8.20%
Wei Wang
24
3.52%
1
1.64%
Pavel Emelyanov
22
3.23%
2
3.28%
Alexey Kodanev
19
2.79%
1
1.64%
Stephen Hemminger
18
2.64%
1
1.64%
Haishuang Yan
16
2.35%
1
1.64%
Linus Torvalds
16
2.35%
3
4.92%
Wei Dong
12
1.76%
1
1.64%
Herbert Xu
6
0.88%
1
1.64%
Florian Westphal
5
0.73%
1
1.64%
Sathya Perla
4
0.59%
1
1.64%
William Allen Simpson
1
0.15%
1
1.64%
Patrick McHardy
1
0.15%
1
1.64%
Al Viro
1
0.15%
1
1.64%
Steven Cole
1
0.15%
1
1.64%
Hannes Frederic Sowa
1
0.15%
1
1.64%
Tom Herbert
1
0.15%
1
1.64%
Total
682
100.00%
61
100.00%


EXPORT_SYMBOL(tcp_v4_connect);

/*
 * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191.
 * It can be called through tcp_release_cb() if socket was owned by user
 * at the time tcp_v4_err() was called to handle ICMP message.
 */


void tcp_v4_mtu_reduced(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct dst_entry *dst;
	u32 mtu;

	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
		return;
	mtu = tcp_sk(sk)->mtu_info;
	dst = inet_csk_update_pmtu(sk, mtu);
	if (!dst)
		return;

	/* Something is about to be wrong... Remember soft error
         * for the case, if this connection will not able to recover.
         */
	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
		sk->sk_err_soft = EMSGSIZE;

	mtu = dst_mtu(dst);

	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
	    ip_sk_accept_pmtu(sk) &&
	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
		tcp_sync_mss(sk, mtu);

		/* Resend the TCP packet because it's
                 * clear that the old packet has been
                 * dropped. This is the new "fast" path mtu
                 * discovery.
                 */
		tcp_simple_retransmit(sk);
	} /* else let the usual retransmit timer handle it */
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
61
44.53%
5
31.25%
Eric Dumazet
35
25.55%
2
12.50%
David S. Miller
16
11.68%
2
12.50%
Alexey Kuznetsov
10
7.30%
1
6.25%
Arnaldo Carvalho de Melo
8
5.84%
4
25.00%
Hannes Frederic Sowa
5
3.65%
1
6.25%
Herbert Xu
2
1.46%
1
6.25%
Total
137
100.00%
16
100.00%


EXPORT_SYMBOL(tcp_v4_mtu_reduced);



static void do_redirect(struct sk_buff *skb, struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_check(sk, 0);

	if (dst)
		dst->ops->redirect(dst, sk, skb);
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
David S. Miller
45
100.00%
2
100.00%
Total
45
100.00%
2
100.00%

/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */


void tcp_req_err(struct sock *sk, u32 seq, bool abort)
{
	struct request_sock *req = inet_reqsk(sk);
	struct net *net = sock_net(sk);

	/* ICMPs are not backlogged, hence we cannot get
         * an established socket here.
         */
	if (seq != tcp_rsk(req)->snt_isn) {
		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
	} else if (abort) {
		/*
                 * Still in SYN_RECV, just remove it silently.
                 * There is no good way to pass the error to the newly
                 * created socket, and POSIX does not want network
                 * errors returned from accept().
                 */
		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
		tcp_listendrop(req->rsk_listener);
	}
	reqsk_put(req);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
83
96.51%
5
83.33%
Fan Du
3
3.49%
1
16.67%
Total
86
100.00%
6
100.00%


EXPORT_SYMBOL(tcp_req_err);

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  After adjustment
 * header points to the first 8 bytes of the tcp header.  We need
 * to find the appropriate port.
 *
 * The locking strategy used here is very "optimistic". When
 * someone else accesses the socket the ICMP is just dropped
 * and for some paths there is no check at all.
 * A more general error queue to queue errors for later handling
 * is probably better.
 *
 */



void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
{
	const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
	struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
	struct inet_connection_sock *icsk;
	struct tcp_sock *tp;
	struct inet_sock *inet;
	const int type = icmp_hdr(icmp_skb)->type;
	const int code = icmp_hdr(icmp_skb)->code;
	struct sock *sk;
	struct sk_buff *skb;
	struct request_sock *fastopen;
	__u32 seq, snd_una;
	__u32 remaining;
	int err;
	struct net *net = dev_net(icmp_skb->dev);

	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
				       th->dest, iph->saddr, ntohs(th->source),
				       inet_iif(icmp_skb));
	if (!sk) {
		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
		return;
	}
	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put(inet_twsk(sk));
		return;
	}
	seq = ntohl(th->seq);
	if (sk->sk_state == TCP_NEW_SYN_RECV)
		return tcp_req_err(sk, seq,
				  type == ICMP_PARAMETERPROB ||
				  type == ICMP_TIME_EXCEEDED ||
				  (type == ICMP_DEST_UNREACH &&
				   (code == ICMP_NET_UNREACH ||
				    code == ICMP_HOST_UNREACH)));

	bh_lock_sock(sk);
	/* If too many ICMPs get dropped on busy
         * servers this needs to be solved differently.
         * We do take care of PMTU discovery (RFC1191) special case :
         * we can receive locally generated ICMP messages while socket is held.
         */
	if (sock_owned_by_user(sk)) {
		if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED))
			__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
	}
	if (sk->sk_state == TCP_CLOSE)
		goto out;

	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
		goto out;
	}

	icsk = inet_csk(sk);
	tp = tcp_sk(sk);
	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
	fastopen = tp->fastopen_rsk;
	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, snd_una, tp->snd_nxt)) {
		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	switch (type) {
	case ICMP_REDIRECT:
		if (!sock_owned_by_user(sk))
			do_redirect(icmp_skb, sk);
		goto out;
	case ICMP_SOURCE_QUENCH:
		/* Just silently ignore these. */
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out;

		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
			/* We are not interested in TCP_LISTEN and open_requests
                         * (SYN-ACKs send out by Linux are always <576bytes so
                         * they should go through unfragmented).
                         */
			if (sk->sk_state == TCP_LISTEN)
				goto out;

			tp->mtu_info = info;
			if (!sock_owned_by_user(sk)) {
				tcp_v4_mtu_reduced(sk);
			} else {
				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags))
					sock_hold(sk);
			}
			goto out;
		}

		err = icmp_err_convert[code].errno;
		/* check if icmp_skb allows revert of backoff
                 * (see draft-zimmermann-tcp-lcd) */
		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
			break;
		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
		    !icsk->icsk_backoff || fastopen)
			break;

		if (sock_owned_by_user(sk))
			break;

		icsk->icsk_backoff--;
		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
					       TCP_TIMEOUT_INIT;
		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);

		skb = tcp_write_queue_head(sk);
		BUG_ON(!skb);

		remaining = icsk->icsk_rto -
			    min(icsk->icsk_rto,
				tcp_time_stamp - tcp_skb_timestamp(skb));

		if (remaining) {
			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
						  remaining, TCP_RTO_MAX);
		} else {
			/* RTO revert clocked out retransmission.
                         * Will retransmit now */
			tcp_retransmit_timer(sk);
		}

		break;
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	default:
		goto out;
	}

	switch (sk->sk_state) {
	case TCP_SYN_SENT:
	case TCP_SYN_RECV:
		/* Only in fast or simultaneous open. If a fast open socket is
                 * is already accepted it is treated as a connected one below.
                 */
		if (fastopen && !fastopen->sk)
			break;

		if (!sock_owned_by_user(sk)) {
			sk->sk_err = err;

			sk->sk_error_report(sk);

			tcp_done(sk);
		} else {
			sk->sk_err_soft = err;
		}
		goto out;
	}

	/* If we've already connected we will keep trying
         * until we time out, or the user gives up.
         *
         * rfc1122 4.2.3.9 allows to consider as hard errors
         * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
         * but it is obsoleted by pmtu discovery).
         *
         * Note, that in modern internet, where routing is unreliable
         * and in each dark corner broken firewalls sit, sending random
         * errors ordered by their masters even this two messages finally lose
         * their original sense (even Linux sends invalid PORT_UNREACHs)
         *
         * Now we are in compliance with RFCs.
         *                                                      --ANK (980905)
         */

	inet = inet_sk(sk);
	if (!sock_owned_by_user(sk) && inet->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else	{ /* Only an error on timeout */
		sk->sk_err_soft = err;
	}

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
316
40.41%
8
16.33%
Damian Lukowski
133
17.01%
2
4.08%
Eric Dumazet
126
16.11%
13
26.53%
David S. Miller
37
4.73%
4
8.16%
Yuchung Cheng
37
4.73%
1
2.04%
Arnaldo Carvalho de Melo
29
3.71%
8
16.33%
Stephen Hemminger
27
3.45%
1
2.04%
Linus Torvalds
22
2.81%
1
2.04%
Pavel Emelyanov
19
2.43%
4
8.16%
Benjamin LaHaise
12
1.53%
1
2.04%
Jerry Chu
9
1.15%
2
4.08%
Jon Maxwell
8
1.02%
1
2.04%
Hideaki Yoshifuji / 吉藤英明
6
0.77%
2
4.08%
Ian Morris
1
0.13%
1
2.04%
Total
782
100.00%
49
100.00%



void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
	struct tcphdr *th = tcp_hdr(skb);

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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds
37
33.04%
1
10.00%
Linus Torvalds (pre-git)
35
31.25%
2
20.00%
Herbert Xu
28
25.00%
2
20.00%
Arnaldo Carvalho de Melo
9
8.04%
2
20.00%
Al Viro
1
0.89%
1
10.00%
Patrick McHardy
1
0.89%
1
10.00%
David S. Miller
1
0.89%
1
10.00%
Total
112
100.00%
10
100.00%

/* This routine computes an IPv4 TCP checksum. */


void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
{
	const struct inet_sock *inet = inet_sk(sk);

	__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Herbert Xu
38
97.44%
1
50.00%
Eric Dumazet
1
2.56%
1
50.00%
Total
39
100.00%
2
100.00%


EXPORT_SYMBOL(tcp_v4_send_check);

/*
 *      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(const struct sock *sk, struct sk_buff *skb)
{
	const 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 = NULL;
	const __u8 *hash_location = NULL;
	unsigned char newhash[16];
	int genhash;
	struct sock *sk1 = NULL;
#endif
	struct net *net;

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

	/* If sk not NULL, it means we did a successful lookup and incoming
         * route had to be correct. prequeue might have dropped our dst.
         */
	if (!sk && skb_rtable(skb)->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);

	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
#ifdef CONFIG_TCP_MD5SIG
	rcu_read_lock();
	hash_location = tcp_parse_md5sig_option(th);
	if (sk && sk_fullsock(sk)) {
		key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
					&ip_hdr(skb)->saddr, AF_INET);
	} else if (hash_location) {
		/*
                 * active side is lost. Try to find listening socket through
                 * source port, and then find md5 key through listening socket.
                 * we are not loose security here:
                 * Incoming packet is checked with md5 hash with finding key,
                 * no RST generated if md5 hash doesn't match.
                 */
		sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
					     ip_hdr(skb)->saddr,
					     th->source, ip_hdr(skb)->daddr,
					     ntohs(th->source), inet_iif(skb));
		/* don't send rst if it can't find key */
		if (!sk1)
			goto out;

		key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
					&ip_hdr(skb)->saddr, AF_INET);
		if (!key)
			goto out;


		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
		if (genhash || memcmp(hash_location, newhash, 16) != 0)
			goto out;

	}

	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_md5_hash_hdr((__u8 *) &rep.opt[1],
				     key, ip_hdr(skb)->saddr,
				     ip_hdr(skb)->daddr, &rep.th);
	}
#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;
	arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0;

	/* When socket is gone, all binding information is lost.
         * routing might fail in this case. No choice here, if we choose to force
         * input interface, we will misroute in case of asymmetric route.
         */
	if (sk)
		arg.bound_dev_if = sk->sk_bound_dev_if;

	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));

	arg.tos = ip_hdr(skb)->tos;
	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
	local_bh_disable();
	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
			      &arg, arg.iov[0].iov_len);

	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
	local_bh_enable();

#ifdef CONFIG_TCP_MD5SIG
out:
	rcu_read_unlock();
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
226
28.61%
12
26.09%
Hideaki Yoshifuji / 吉藤英明
171
21.65%
2
4.35%
Shawn Lu
149
18.86%
2
4.35%
Eric Dumazet
77
9.75%
12
26.09%
Florian Westphal
55
6.96%
2
4.35%
Lorenzo Colitti
20
2.53%
1
2.17%
Arnaldo Carvalho de Melo
18
2.28%
3
6.52%
KOVACS Krisztian
16
2.03%
1
2.17%
David S. Miller
15
1.90%
2
4.35%
Tom Herbert
11
1.39%
1
2.17%
Pavel Emelyanov
11
1.39%
2
4.35%
Ilpo Järvinen
10
1.27%
2
4.35%
Alexey Kuznetsov
5
0.63%
1
2.17%
Craig Gallek
4
0.51%
1
2.17%
Adam Langley
1
0.13%
1
2.17%
Al Viro
1
0.13%
1
2.17%
Total
790
100.00%
46
100.00%

/* 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(const struct sock *sk,
			    struct sk_buff *skb, u32 seq, u32 ack,
			    u32 win, u32 tsval, u32 tsecr, int oif,
			    struct tcp_md5sig_key *key,
			    int reply_flags, u8 tos)
{
	const 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 net *net = sock_net(sk);
	struct ip_reply_arg arg;

	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 (tsecr) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
				   (TCPOPT_TIMESTAMP << 8) |
				   TCPOLEN_TIMESTAMP);
		rep.opt[1] = htonl(tsval);
		rep.opt[2] = htonl(tsecr);
		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
	if (key) {
		int offset = (tsecr) ? 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_md5_hash_hdr((__u8 *) &rep.opt[offset],
				    key, ip_hdr(skb)->saddr,
				    ip_hdr(skb)->daddr, &rep.th);
	}
#endif
	arg.flags = reply_flags;
	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 (oif)
		arg.bound_dev_if = oif;
	arg.tos = tos;
	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
	local_bh_disable();
	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
			      &arg, arg.iov[0].iov_len);

	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
	local_bh_enable();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
307
52.48%
13
31.71%
Hideaki Yoshifuji / 吉藤英明
140
23.93%
4
9.76%
Eric Dumazet
40
6.84%
8
19.51%
Lorenzo Colitti
31
5.30%
1
2.44%
Arnaldo Carvalho de Melo
19
3.25%
4
9.76%
David S. Miller
15
2.56%
2
4.88%
KOVACS Krisztian
9
1.54%
1
2.44%
Andrey Vagin
8
1.37%
1
2.44%
Patrick McHardy
8
1.37%
1
2.44%
Pavel Emelyanov
3
0.51%
2
4.88%
Adam Langley
3
0.51%
2
4.88%
Al Viro
1
0.17%
1
2.44%
Craig Schlenter
1
0.17%
1
2.44%
Total
585
100.00%
41
100.00%



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(sk, skb,
			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
			tcp_time_stamp + tcptw->tw_ts_offset,
			tcptw->tw_ts_recent,
			tw->tw_bound_dev_if,
			tcp_twsk_md5_key(tcptw),
			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
			tw->tw_tos
			);

	inet_twsk_put(tw);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
42
44.21%
6
46.15%
Arnaldo Carvalho de Melo
24
25.26%
2
15.38%
Hideaki Yoshifuji / 吉藤英明
9
9.47%
1
7.69%
KOVACS Krisztian
8
8.42%
1
7.69%
Eric Dumazet
6
6.32%
2
15.38%
Andrey Vagin
6
6.32%
1
7.69%
Total
95
100.00%
13
100.00%



static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req)
{
	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
         * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
         */
	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
					     tcp_sk(sk)->snd_nxt;

	/* RFC 7323 2.3
         * The window field (SEG.WND) of every outgoing segment, with the
         * exception of <SYN> segments, MUST be right-shifted by
         * Rcv.Wind.Shift bits:
         */
	tcp_v4_send_ack(sk, skb, seq,
			tcp_rsk(req)->rcv_nxt,
			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
			tcp_time_stamp + tcp_rsk(req)->ts_off,
			req->ts_recent,
			0,
			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
					  AF_INET),
			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
			ip_hdr(skb)->tos);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
37
28.24%
6
33.33%
Linus Torvalds (pre-git)
31
23.66%
4
22.22%
Jerry Chu
17
12.98%
1
5.56%
Hideaki Yoshifuji / 吉藤英明
13
9.92%
1
5.56%
KOVACS Krisztian
11
8.40%
1
5.56%
Arnaldo Carvalho de Melo
8
6.11%
2
11.11%
Florian Westphal
7
5.34%
1
5.56%
Gui Jianfeng
5
3.82%
1
5.56%
Andrey Vagin
2
1.53%
1
5.56%
Total
131
100.00%
18
100.00%

/*
 *      Send a SYN-ACK after having received a SYN.
 *      This still operates on a request_sock only, not on a big
 *      socket.
 */


static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
			      struct flowi *fl,
			      struct request_sock *req,
			      struct tcp_fastopen_cookie *foc,
			      enum tcp_synack_type synack_type)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct flowi4 fl4;
	int err = -1;
	struct sk_buff *skb;

	/* First, grab a route. */
	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
		return -1;

	skb = tcp_make_synack(sk, dst, req, foc, synack_type);

	if (skb) {
		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);

		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
					    ireq->ir_rmt_addr,
					    ireq->opt);
		err = net_xmit_eval(err);
	}

	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
90
58.82%
4
20.00%
Arnaldo Carvalho de Melo
19
12.42%
4
20.00%
Eric Dumazet
11
7.19%
4
20.00%
David S. Miller
7
4.58%
1
5.00%
Octavian Purdila
6
3.92%
2
10.00%
William Allen Simpson
6
3.92%
1
5.00%
Yuchung Cheng
5
3.27%
1
5.00%
Gerrit Renker
4
2.61%
1
5.00%
Denis V. Lunev
4
2.61%
1
5.00%
Herbert Xu
1
0.65%
1
5.00%
Total
153
100.00%
20
100.00%

/*
 *      IPv4 request_sock destructor.
 */


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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
16
76.19%
3
60.00%
Arnaldo Carvalho de Melo
5
23.81%
2
40.00%
Total
21
100.00%
5
100.00%

#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.  */


struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
					 const union tcp_md5_addr *addr,
					 int family)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	unsigned int size = sizeof(struct in_addr);
	const struct tcp_md5sig_info *md5sig;

	/* caller either holds rcu_read_lock() or socket lock */
	md5sig = rcu_dereference_check(tp->md5sig_info,
				       lockdep_sock_is_held(sk));
	if (!md5sig)
		return NULL;
#if IS_ENABLED(CONFIG_IPV6)
	if (family == AF_INET6)
		size = sizeof(struct in6_addr);
#endif
	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
		if (key->family != family)
			continue;
		if (!memcmp(&key->addr, addr, size))
			return key;
	}
	return NULL;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
91
65.47%
5
71.43%
Hideaki Yoshifuji / 吉藤英明
47
33.81%
1
14.29%
Hannes Frederic Sowa
1
0.72%
1
14.29%
Total
139
100.00%
7
100.00%


EXPORT_SYMBOL(tcp_md5_do_lookup);



struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
					 const struct sock *addr_sk)
{
	const union tcp_md5_addr *addr;

	addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr;
	return tcp_md5_do_lookup(sk, addr, AF_INET);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
28
58.33%
4
80.00%
Hideaki Yoshifuji / 吉藤英明
20
41.67%
1
20.00%
Total
48
100.00%
5
100.00%


EXPORT_SYMBOL(tcp_v4_md5_lookup);

/* This can be called on a newly created socket, from other files */


int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
{
	/* Add Key to the list */
	struct tcp_md5sig_key *key;
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_info *md5sig;

	key = tcp_md5_do_lookup(sk, addr, family);
	if (key) {
		/* Pre-existing entry - just update that one. */
		memcpy(key->key, newkey, newkeylen);
		key->keylen = newkeylen;
		return 0;
	}

	md5sig = rcu_dereference_protected(tp->md5sig_info,
					   lockdep_sock_is_held(sk));
	if (!md5sig) {
		md5sig = kmalloc(sizeof(*md5sig), gfp);
		if (!md5sig)
			return -ENOMEM;

		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
		INIT_HLIST_HEAD(&md5sig->head);
		rcu_assign_pointer(tp->md5sig_info, md5sig);
	}

	key = sock_kmalloc(sk, sizeof(*key), gfp);
	if (!key)
		return -ENOMEM;
	if (!tcp_alloc_md5sig_pool()) {
		sock_kfree_s(sk, key, sizeof(*key));
		return -ENOMEM;
	}

	memcpy(key->key, newkey, newkeylen);
	key->keylen = newkeylen;
	key->family = family;
	memcpy(&key->addr, addr,
	       (family == AF_INET6) ? sizeof(struct in6_addr) :
				      sizeof(struct in_addr));
	hlist_add_head_rcu(&key->node, &md5sig->head);
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
132
48.53%
6
46.15%
Hideaki Yoshifuji / 吉藤英明
127
46.69%
1
7.69%
Arnaldo Carvalho de Melo
4
1.47%
1
7.69%
Zheng Yan
3
1.10%
1
7.69%
David S. Miller
3
1.10%
1
7.69%
Aydin Arik
1
0.37%
1
7.69%
Hannes Frederic Sowa
1
0.37%
1
7.69%
Matthias M. Dellweg
1
0.37%
1
7.69%
Total
272
100.00%
13
100.00%


EXPORT_SYMBOL(tcp_md5_do_add);



int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
	struct tcp_md5sig_key *key;

	key = tcp_md5_do_lookup(sk, addr, family);
	if (!key)
		return -ENOENT;
	hlist_del_rcu(&key->node);
	atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
	kfree_rcu(key, rcu);
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
46
60.53%
2
50.00%
Hideaki Yoshifuji / 吉藤英明
29
38.16%
1
25.00%
Aydin Arik
1
1.32%
1
25.00%
Total
76
100.00%
4
100.00%


EXPORT_SYMBOL(tcp_md5_do_del);



static void tcp_clear_md5_list(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	struct hlist_node *n;
	struct tcp_md5sig_info *md5sig;

	md5sig = rcu_dereference_protected(tp->md5sig_info, 1);

	hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
		hlist_del_rcu(&key->node);
		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
		kfree_rcu(key, rcu);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
61
69.32%
3
60.00%
Hideaki Yoshifuji / 吉藤英明
26
29.55%
1
20.00%
Stephen Hemminger
1
1.14%
1
20.00%
Total
88
100.00%
5
100.00%



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;

	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_keylen)
		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
				      AF_INET);

	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
		return -EINVAL;

	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
			      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
			      GFP_KERNEL);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
128
84.77%
1
50.00%
Eric Dumazet
23
15.23%
1
50.00%
Total
151
100.00%
2
100.00%



static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp,
				   __be32 daddr, __be32 saddr,
				   const struct tcphdr *th, int nbytes)
{
	struct tcp4_pseudohdr *bp;
	struct scatterlist sg;
	struct tcphdr *_th;

	bp = hp->scratch;
	bp->saddr = saddr;
	bp->daddr = daddr;
	bp->pad = 0;
	bp->protocol = IPPROTO_TCP;
	bp->len = cpu_to_be16(nbytes);

	_th = (struct tcphdr *)(bp + 1);
	memcpy(_th, th, sizeof(*th));
	_th->check = 0;

	sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
	ahash_request_set_crypt(hp->md5_req, &sg, NULL,
				sizeof(*bp) + sizeof(*th));
	return crypto_ahash_update(hp->md5_req);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
64
39.26%
2
40.00%
Eric Dumazet
57
34.97%
1
20.00%
Adam Langley
30
18.40%
1
20.00%
Herbert Xu
12
7.36%
1
20.00%
Total
163
100.00%
5
100.00%



static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, const struct tcphdr *th)
{
	struct tcp_md5sig_pool *hp;
	struct ahash_request *req;

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	req = hp->md5_req;

	if (crypto_ahash_init(req))
		goto clear_hash;
	if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	ahash_request_set_crypt(req, NULL, md5_hash, 0);
	if (crypto_ahash_final(req))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Adam Langley
92
62.59%
1
14.29%
Hideaki Yoshifuji / 吉藤英明
31
21.09%
2
28.57%
Herbert Xu
19
12.93%
1
14.29%
Eric Dumazet
5
3.40%
3
42.86%
Total
147
100.00%
7
100.00%



int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
			const struct sock *sk,
			const struct sk_buff *skb)
{
	struct tcp_md5sig_pool *hp;
	struct ahash_request *req;
	const struct tcphdr *th = tcp_hdr(skb);
	__be32 saddr, daddr;

	if (sk) { /* valid for establish/request sockets */
		saddr = sk->sk_rcv_saddr;
		daddr = sk->sk_daddr;
	} else {
		const struct iphdr *iph = ip_hdr(skb);
		saddr = iph->saddr;
		daddr = iph->daddr;
	}

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	req = hp->md5_req;

	if (crypto_ahash_init(req))
		goto clear_hash;

	if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len))
		goto clear_hash;
	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	ahash_request_set_crypt(req, NULL, md5_hash, 0);
	if (crypto_ahash_final(req))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Adam Langley
130
58.30%
1
16.67%
Hideaki Yoshifuji / 吉藤英明
64
28.70%
1
16.67%
Herbert Xu
19
8.52%
1
16.67%
Eric Dumazet
10
4.48%
3
50.00%
Total
223
100.00%
6
100.00%


EXPORT_SYMBOL(tcp_v4_md5_hash_skb);

#endif

/* Called with rcu_read_lock() */


static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
				    const struct sk_buff *skb)
{
#ifdef CONFIG_TCP_MD5SIG
	/*
         * This gets called for each TCP segment that arrives
         * so we want to be efficient.
         * We have 3 drop cases:
         * o No MD5 hash and one expected.
         * o MD5 hash and we're not expecting one.
         * o MD5 hash and its wrong.
         */
	const __u8 *hash_location = NULL;
	struct tcp_md5sig_key *hash_expected;
	const struct iphdr *iph = ip_hdr(skb);
	const struct tcphdr *th = tcp_hdr(skb);
	int genhash;
	unsigned char newhash[16];

	hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
					  AF_INET);
	hash_location = tcp_parse_md5sig_option(th);

	/* We've parsed the options - do we have a hash? */
	if (!hash_expected && !hash_location)
		return false;

	if (hash_expected && !hash_location) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
		return true;
	}

	if (!hash_expected && hash_location) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
		return true;
	}

	/* Okay, so this is hash_expected and hash_location -
         * so we need to calculate the checksum.
         */
	genhash = tcp_v4_md5_hash_skb(newhash,
				      hash_expected,
				      NULL, skb);

	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
				     &iph->saddr, ntohs(th->source),
				     &iph->daddr, ntohs(th->dest),
				     genhash ? " tcp_v4_calc_md5_hash failed"
				     : "");
		return true;
	}
	return false;
#endif
	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
174
74.04%
2
11.76%
Eric Dumazet
39
16.60%
8
47.06%
Arnaldo Carvalho de Melo
7
2.98%
2
11.76%
David S. Miller
6
2.55%
1
5.88%
Linus Torvalds (pre-git)
3
1.28%
1
5.88%
Harvey Harrison
3
1.28%
1
5.88%
Adam Langley
2
0.85%
1
5.88%
Joe Perches
1
0.43%
1
5.88%
Total
235
100.00%
17
100.00%



static void tcp_v4_init_req(struct request_sock *req,
			    const struct sock *sk_listener,
			    struct sk_buff *skb)
{
	struct inet_request_sock *ireq = inet_rsk(req);

	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
	ireq->opt = tcp_v4_save_options(skb);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Octavian Purdila
53
74.65%
1
33.33%
Eric Dumazet
18
25.35%
2
66.67%
Total
71
100.00%
3
100.00%



static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
					  struct flowi *fl,
					  const struct request_sock *req,
					  bool *strict)
{
	struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);

	if (strict) {
		if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
			*strict = true;
		else
			*strict = false;
	}

	return dst;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Octavian Purdila
84
98.82%
1
50.00%
Eric Dumazet
1
1.18%
1
50.00%
Total
85
100.00%
2
100.00%


struct request_sock_ops tcp_request_sock_ops __read_mostly = {
	.family		=	PF_INET,
	.obj_size	=	sizeof(struct tcp_request_sock),
	.rtx_syn_ack	=	tcp_rtx_synack,
	.send_ack	=	tcp_v4_reqsk_send_ack,
	.destructor	=	tcp_v4_reqsk_destructor,
	.send_reset	=	tcp_v4_send_reset,
	.syn_ack_timeout =	tcp_syn_ack_timeout,
};


static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
	.mss_clamp	=	TCP_MSS_DEFAULT,
#ifdef CONFIG_TCP_MD5SIG
	.req_md5_lookup	=	tcp_v4_md5_lookup,
	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
#endif
	.init_req	=	tcp_v4_init_req,
#ifdef CONFIG_SYN_COOKIES
	.cookie_init_seq =	cookie_v4_init_sequence,
#endif
	.route_req	=	tcp_v4_route_req,
	.init_seq	=	tcp_v4_init_sequence,
	.send_synack	=	tcp_v4_send_synack,
};



int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	/* Never answer to SYNs send to broadcast or multicast */
	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	return tcp_conn_request(&tcp_request_sock_ops,
				&tcp_request_sock_ipv4_ops, sk, skb);

drop:
	tcp_listendrop(sk);
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
39
67.24%
4
30.77%
Eric Dumazet
4
6.90%
2
15.38%
Vijay Subramanian
4
6.90%
1
7.69%
Octavian Purdila
4
6.90%
2
15.38%
Arnaldo Carvalho de Melo
3
5.17%
2
15.38%
Paul Moore
3
5.17%
1
7.69%
Hannes Frederic Sowa
1
1.72%
1
7.69%
Total
58
100.00%
13
100.00%


EXPORT_SYMBOL(tcp_v4_conn_request);


/*
 * The three way handshake has completed - we got a valid synack -
 * now create the new socket.
 */


struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req,
				  struct dst_entry *dst,
				  struct request_sock *req_unhash,
				  bool *own_req)
{
	struct inet_request_sock *ireq;
	struct inet_sock *newinet;
	struct tcp_sock *newtp;
	struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
#endif
	struct ip_options_rcu *inet_opt;

	if (sk_acceptq_is_full(sk))
		goto exit_overflow;

	newsk = tcp_create_openreq_child(sk, req, skb);
	if (!newsk)
		goto exit_nonewsk;

	newsk->sk_gso_type = SKB_GSO_TCPV4;
	inet_sk_rx_dst_set(newsk, skb);

	newtp		      = tcp_sk(newsk);
	newinet		      = inet_sk(newsk);
	ireq		      = inet_rsk(req);
	sk_daddr_set(newsk, ireq->ir_rmt_addr);
	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
	newsk->sk_bound_dev_if = ireq->ir_iif;
	newinet->inet_saddr	      = ireq->ir_loc_addr;
	inet_opt	      = ireq->opt;
	rcu_assign_pointer(newinet->inet_opt, inet_opt);
	ireq->opt	      = NULL;
	newinet->mc_index     = inet_iif(skb);
	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
	newinet->rcv_tos      = ip_hdr(skb)->tos;
	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (inet_opt)
		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
	newinet->inet_id = newtp->write_seq ^ jiffies;

	if (!dst) {
		dst = inet_csk_route_child_sock(sk, newsk, req);
		if (!dst)
			goto put_and_exit;
	} else {
		/* syncookie case : see end of cookie_v4_check() */
	}
	sk_setup_caps(newsk, dst);

	tcp_ca_openreq_child(newsk, dst);

	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));

	tcp_initialize_rcv_mss(newsk);

#ifdef CONFIG_TCP_MD5SIG
	/* Copy over the MD5 key from the original socket */
	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
				AF_INET);
	if (key) {
		/*
                 * We're using one, so create a matching key
                 * on the newsk structure. If we fail to get
                 * memory, then we end up not copying the key
                 * across. Shucks.
                 */
		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
			       AF_INET, key->key, key->keylen, GFP_ATOMIC);
		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
	}
#endif

	if (__inet_inherit_port(sk, newsk) < 0)
		goto put_and_exit;
	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
	if (*own_req)
		tcp_move_syn(newtp, req);

	return newsk;

exit_overflow:
	NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit_nonewsk:
	dst_release(dst);
exit:
	tcp_listendrop(sk);
	return NULL;
put_and_exit:
	inet_csk_prepare_forced_close(newsk);
	tcp_done(newsk);
	goto exit;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
146
30.10%
13
23.21%
Eric Dumazet
119
24.54%
16
28.57%
David S. Miller
52
10.72%
3
5.36%
Hideaki Yoshifuji / 吉藤英明
40
8.25%
2
3.57%
Arnaldo Carvalho de Melo
35
7.22%
8
14.29%
Balazs Scheidler
20
4.12%
1
1.79%
Jiri Benc
11
2.27%
1
1.79%
Linus Torvalds
8
1.65%
1
1.79%
David Ahern
8
1.65%
1
1.79%
Pavel Emelyanov
8
1.65%
1
1.79%
Tom Quetchenbach
8
1.65%
1
1.79%
Herbert Xu
7
1.44%
2
3.57%
Daniel Borkmann
7
1.44%
1
1.79%
Neal Cardwell
7
1.44%
1
1.79%
Adam Langley
3
0.62%
1
1.79%
Alexey Kuznetsov
3
0.62%
1
1.79%
Christoph Paasch
2
0.41%
1
1.79%
John Dykstra
1
0.21%
1
1.79%
Total
485
100.00%
56
100.00%


EXPORT_SYMBOL(tcp_v4_syn_recv_sock);



static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
{
#ifdef CONFIG_SYN_COOKIES
	const struct tcphdr *th = tcp_hdr(skb);

	if (!th->syn)
		sk = cookie_v4_check(sk, skb);
#endif
	return sk;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
45
84.91%
3
50.00%
Eric Dumazet
5
9.43%
2
33.33%
Arnaldo Carvalho de Melo
3
5.66%
1
16.67%
Total
53
100.00%
6
100.00%

/* The socket must have it's spinlock held when we get
 * here, unless it is a TCP_LISTEN socket.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */


int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sock *rsk;

	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		struct dst_entry *dst = sk->sk_rx_dst;

		sock_rps_save_rxhash(sk, skb);
		sk_mark_napi_id(sk, skb);
		if (dst) {
			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
			    !dst->ops->check(dst, 0)) {
				dst_release(dst);
				sk->sk_rx_dst = NULL;
			}
		}
		tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
		return 0;
	}

	if (tcp_checksum_complete(skb))
		goto csum_err;

	if (sk->sk_state == TCP_LISTEN) {
		struct sock *nsk = tcp_v4_cookie_check(sk, skb);

		if (!nsk)
			goto discard;
		if (nsk != sk) {
			sock_rps_save_rxhash(nsk, skb);
			sk_mark_napi_id(nsk, skb);
			if (tcp_child_process(sk, nsk, skb)) {
				rsk = nsk;
				goto reset;
			}
			return 0;
		}
	} else
		sock_rps_save_rxhash(sk, skb);

	if (tcp_rcv_state_process(sk, skb)) {
		rsk = sk;
		goto reset;
	}
	return 0;

reset:
	tcp_v4_send_reset(rsk, skb);
discard:
	kfree_skb(skb);
	/* Be careful here. If this function gets more complicated and
         * gcc suffers from register pressure on the x86, sk (in %ebx)
         * might be destroyed here. This current version compiles correctly,
         * but you have been warned.
         */
	return 0;

csum_err:
	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
	goto discard;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
145
52.54%
9
34.62%
Eric Dumazet
69
25.00%
9
34.62%
David S. Miller
29
10.51%
1
3.85%
Hideaki Yoshifuji / 吉藤英明
21
7.61%
2
7.69%
Arnaldo Carvalho de Melo
6
2.17%
3
11.54%
Pavel Emelyanov
5
1.81%
1
3.85%
Ian Morris
1
0.36%
1
3.85%
Total
276
100.00%
26
100.00%


EXPORT_SYMBOL(tcp_v4_do_rcv);



void tcp_v4_early_demux(struct sk_buff *skb)
{
	const struct iphdr *iph;
	const struct tcphdr *th;
	struct sock *sk;

	if (skb->pkt_type != PACKET_HOST)
		return;

	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
		return;

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

	if (th->doff < sizeof(struct tcphdr) / 4)
		return;

	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
				       iph->saddr, th->source,
				       iph->daddr, ntohs(th->dest),
				       skb->skb_iif);
	if (sk) {
		skb->sk = sk;
		skb->destructor = sock_edemux;
		if (sk_fullsock(sk)) {
			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);

			if (dst)
				dst = dst_check(dst, 0);
			if (dst &&
			    inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
				skb_dst_set_noref(skb, dst);
		}
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David S. Miller
172
87.31%
4
40.00%
Eric Dumazet
19
9.64%
4
40.00%
Vijay Subramanian
3
1.52%
1
10.00%
Michal Kubeček
3
1.52%
1
10.00%
Total
197
100.00%
10
100.00%

/* Packet is added to VJ-style prequeue for processing in process
 * context, if a reader task is waiting. Apparently, this exciting
 * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
 * failed somewhere. Latency? Burstiness? Well, at least now we will
 * see, why it failed. 8)8)                               --ANK
 *
 */


bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (sysctl_tcp_low_latency || !tp->ucopy.task)
		return false;

	if (skb->len <= tcp_hdrlen(skb) &&
	    skb_queue_len(&tp->ucopy.prequeue) == 0)
		return false;

	/* Before escaping RCU protected region, we need to take care of skb
         * dst. Prequeue is only enabled for established sockets.
         * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
         * Instead of doing full sk_rx_dst validity here, let's perform
         * an optimistic check.
         */
	if (likely(sk->sk_rx_dst))
		skb_dst_drop(skb);
	else
		skb_dst_force_safe(skb);

	__skb_queue_tail(&tp->ucopy.prequeue, skb);
	tp->ucopy.memory += skb->truesize;
	if (skb_queue_len(&tp->ucopy.prequeue) >= 32 ||
	    tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
		struct sk_buff *skb1;

		BUG_ON(sock_owned_by_user(sk));
		__NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED,
				skb_queue_len(&tp->ucopy.prequeue));

		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
			sk_backlog_rcv(sk, skb1);

		tp->ucopy.memory = 0;
	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
		wake_up_interruptible_sync_poll(sk_sleep(sk),
					   POLLIN | POLLRDNORM | POLLRDBAND);
		if (!inet_csk_ack_scheduled(sk))
			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
						  (3 * tcp_rto_min(sk)) / 4,
						  TCP_RTO_MAX);
	}
	return true;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
266
98.52%
4
80.00%
David S. Miller
4
1.48%
1
20.00%
Total
270
100.00%
5
100.00%


EXPORT_SYMBOL(tcp_prequeue);



bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;

	/* Only socket owner can try to collapse/prune rx queues
         * to reduce memory overhead, so add a little headroom here.
         * Few sockets backlog are possibly concurrently non empty.
         */
	limit += 64*1024;

	/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
         * we can fix skb->truesize to its real value to avoid future drops.
         * This is valid because skb is not yet charged to the socket.
         * It has been noticed pure SACK packets were sometimes dropped
         * (if cooked by drivers without copybreak feature).
         */
	skb_condense(skb);

	if (unlikely(sk_add_backlog(sk, skb, limit))) {
		bh_unlock_sock(sk);
		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
		return true;
	}
	return false;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
76
100.00%
2
100.00%
Total
76
100.00%
2
100.00%


EXPORT_SYMBOL(tcp_add_backlog);



int tcp_filter(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = (struct tcphdr *)skb->data;
	unsigned int eaten = skb->len;
	int err;

	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
	if (!err) {
		eaten -= skb->len;
		TCP_SKB_CB(skb)->end_seq -= eaten;
	}
	return err;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
80
100.00%
1
100.00%
Total
80
100.00%
1
100.00%


EXPORT_SYMBOL(tcp_filter);

/*
 *      From tcp_input.c
 */



int tcp_v4_rcv(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	const struct iphdr *iph;
	const struct tcphdr *th;
	bool refcounted;
	struct sock *sk;
	int ret;

	if (skb->pkt_type != PACKET_HOST)
		goto discard_it;

	/* Count it even if it's bad */
	__TCP_INC_STATS(net, TCP_MIB_INSEGS);

	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		goto discard_it;

	th = (const struct tcphdr *)skb->data;

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

	/* An explanation is required here, I think.
         * Packet length and doff are validated by header prediction,
         * provided case of th->doff==0 is eliminated.
         * So, we defer the checks. */

	if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo))
		goto csum_error;

	th = (const struct tcphdr *)skb->data;
	iph = ip_hdr(skb);
	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
         * barrier() makes sure compiler wont play fool^Waliasing games.
         */
	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
		sizeof(struct inet_skb_parm));
	barrier();

	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)->tcp_flags = tcp_flag_byte(th);
	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
	TCP_SKB_CB(skb)->sacked	 = 0;

lookup:
	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
			       th->dest, &refcounted);
	if (!sk)
		goto no_tcp_socket;

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

	if (sk->sk_state == TCP_NEW_SYN_RECV) {
		struct request_sock *req = inet_reqsk(sk);
		struct sock *nsk;

		sk = req->rsk_listener;
		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
			sk_drops_add(sk, skb);
			reqsk_put(req);
			goto discard_it;
		}
		if (unlikely(sk->sk_state != TCP_LISTEN)) {
			inet_csk_reqsk_queue_drop_and_put(sk, req);
			goto lookup;
		}
		/* We own a reference on the listener, increase it again
                 * as we might lose it too soon.
                 */
		sock_hold(sk);
		refcounted = true;
		nsk = tcp_check_req(sk, skb, req, false);
		if (!nsk) {
			reqsk_put(req);
			goto discard_and_relse;
		}
		if (nsk == sk) {
			reqsk_put(req);
		} else if (tcp_child_process(sk, nsk, skb)) {
			tcp_v4_send_reset(nsk, skb);
			goto discard_and_relse;
		} else {
			sock_put(sk);
			return 0;
		}
	}
	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
		goto discard_and_relse;
	}

	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;

	if (tcp_v4_inbound_md5_hash(sk, skb))
		goto discard_and_relse;

	nf_reset(skb);

	if (tcp_filter(sk, skb))
		goto discard_and_relse;
	th = (const struct tcphdr *)skb->data;
	iph = ip_hdr(skb);

	skb->dev = NULL;

	if (sk->sk_state == TCP_LISTEN) {
		ret = tcp_v4_do_rcv(sk, skb);
		goto put_and_return;
	}

	sk_incoming_cpu_update(sk);

	bh_lock_sock_nested(sk);
	tcp_segs_in(tcp_sk(sk), skb);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
		if (!tcp_prequeue(sk, skb))
			ret = tcp_v4_do_rcv(sk, skb);
	} else if (tcp_add_backlog(sk, skb)) {
		goto discard_and_relse;
	}
	bh_unlock_sock(sk);

put_and_return:
	if (refcounted)
		sock_put(sk);

	return ret;

no_tcp_socket:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (tcp_checksum_complete(skb)) {
csum_error:
		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
bad_packet:
		__TCP_INC_STATS(net, TCP_MIB_INERRS);
	} else {
		tcp_v4_send_reset(NULL, skb);
	}

discard_it:
	/* Discard frame. */
	kfree_skb(skb);
	return 0;

discard_and_relse:
	sk_drops_add(sk, skb);
	if (refcounted)
		sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}

	if (tcp_checksum_complete(skb)) {
		inet_twsk_put(inet_twsk(sk));
		goto csum_error;
	}
	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
	case TCP_TW_SYN: {
		struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
							&tcp_hashinfo, skb,
							__tcp_hdrlen(th),
							iph->saddr, th->source,
							iph->daddr, th->dest,
							inet_iif(skb));
		if (sk2) {
			inet_twsk_deschedule_put(inet_twsk(sk));
			sk = sk2;
			refcounted = false;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v4_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		tcp_v4_send_reset(sk, skb);
		inet_twsk_deschedule_put(inet_twsk(sk));
		goto discard_it;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
363
36.85%
22
32.35%
Linus Torvalds (pre-git)
362
36.75%
15
22.06%
Linus Torvalds
48
4.87%
1
1.47%
Alexey Kuznetsov
35
3.55%
1
1.47%
Arnaldo Carvalho de Melo
27
2.74%
7
10.29%
Hideaki Yoshifuji / 吉藤英明
22
2.23%
5
7.35%
Stephen Hemminger
17
1.73%
2
2.94%
Florian Westphal
16
1.62%
1
1.47%
Tom Herbert
13
1.32%
2
2.94%
Craig Gallek
12
1.22%
1
1.47%
Dmitry Popov
12
1.22%
1
1.47%
Nivedita Singhvi
11
1.12%
1
1.47%
James Morris
11
1.12%
1
1.47%
Yi Zhu
9
0.91%
1
1.47%
Marcelo Ricardo Leitner
8
0.81%
1
1.47%
Pavel Emelyanov
8
0.81%
2
2.94%
Patrick McHardy
5
0.51%
1
1.47%
Benjamin LaHaise
3
0.30%
1
1.47%
Martin KaFai Lau
2
0.20%
1
1.47%
Ingo Molnar
1
0.10%
1
1.47%
Total
985
100.00%
68
100.00%


static struct timewait_sock_ops tcp_timewait_sock_ops = {
	.twsk_obj_size	= sizeof(struct tcp_timewait_sock),
	.twsk_unique	= tcp_twsk_unique,
	.twsk_destructor= tcp_twsk_destructor,
};



void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);

	if (dst && dst_hold_safe(dst)) {
		sk->sk_rx_dst = dst;
		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
	}
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
54
100.00%
3
100.00%
Total
54
100.00%
3
100.00%


EXPORT_SYMBOL(inet_sk_rx_dst_set);


const struct inet_connection_sock_af_ops ipv4_specific = {
	.queue_xmit	   = ip_queue_xmit,
	.send_check	   = tcp_v4_send_check,
	.rebuild_header	   = inet_sk_rebuild_header,
	.sk_rx_dst_set	   = inet_sk_rx_dst_set,
	.conn_request	   = tcp_v4_conn_request,
	.syn_recv_sock	   = tcp_v4_syn_recv_sock,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
	.mtu_reduced	   = tcp_v4_mtu_reduced,
};

EXPORT_SYMBOL(ipv4_specific);

#ifdef CONFIG_TCP_MD5SIG

static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
	.md5_lookup		= tcp_v4_md5_lookup,
	.calc_md5_hash		= tcp_v4_md5_hash_skb,
	.md5_parse		= tcp_v4_parse_md5_keys,
};
#endif

/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */


static int tcp_v4_init_sock(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	tcp_init_sock(sk);

	icsk->icsk_af_ops = &ipv4_specific;

#ifdef CONFIG_TCP_MD5SIG
	tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific;
#endif

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
21
41.18%
1
12.50%
Arnaldo Carvalho de Melo
11
21.57%
2
25.00%
Hideaki Yoshifuji / 吉藤英明
11
21.57%
1
12.50%
David S. Miller
4
7.84%
1
12.50%
Linus Torvalds
2
3.92%
1
12.50%
Thomas Graf
1
1.96%
1
12.50%
Neal Cardwell
1
1.96%
1
12.50%
Total
51
100.00%
8
100.00%



void tcp_v4_destroy_sock(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_clear_xmit_timers(sk);

	tcp_cleanup_congestion_control(sk);

	/* Cleanup up the write buffer. */
	tcp_write_queue_purge(sk);

	/* Cleans up our, hopefully empty, out_of_order_queue. */
	skb_rbtree_purge(&tp->out_of_order_queue);

#ifdef CONFIG_TCP_MD5SIG
	/* Clean up the MD5 key list, if any */
	if (tp->md5sig_info) {
		tcp_clear_md5_list(sk);
		kfree_rcu(tp->md5sig_info, rcu);
		tp->md5sig_info = NULL;
	}
#endif

	/* Clean prequeue, it must be empty really */
	__skb_queue_purge(&tp->ucopy.prequeue);

	/* Clean up a referenced TCP bind bucket. */
	if (inet_csk(sk)->icsk_bind_hash)
		inet_put_port(sk);

	BUG_ON(tp->fastopen_rsk);

	/* If socket is aborted during connect operation */
	tcp_free_fastopen_req(tp);
	tcp_saved_syn_free(tp);

	sk_sockets_allocated_dec(sk);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
55
42.97%
5
20.83%
Hideaki Yoshifuji / 吉藤英明
28
21.88%
1
4.17%
Eric Dumazet
9
7.03%
3
12.50%
Arnaldo Carvalho de Melo
8
6.25%
5
20.83%
Jerry Chu
7
5.47%
1
4.17%
Yuchung Cheng
6
4.69%
1
4.17%
David S. Miller
4
3.12%
2
8.33%
Stephen Hemminger
4
3.12%
1
4.17%
Glauber de Oliveira Costa
2
1.56%
1
4.17%
Christopher Leech
2
1.56%
1
4.17%
Yaogong Wang
1
0.78%
1
4.17%
Linus Torvalds
1
0.78%
1
4.17%
Brian Haley
1
0.78%
1
4.17%
Total
128
100.00%
24
100.00%


EXPORT_SYMBOL(tcp_v4_destroy_sock);

#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */

/*
 * Get next listener socket follow cur.  If cur is NULL, get first socket
 * starting from bucket given in st->bucket; when st->bucket is zero the
 * very first socket in the hash table is returned.
 */


static void *listening_get_next(struct seq_file *seq, void *cur)
{
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);
	struct inet_listen_hashbucket *ilb;
	struct sock *sk = cur;

	if (!sk) {
get_head:
		ilb = &tcp_hashinfo.listening_hash[st->bucket];
		spin_lock(&ilb->lock);
		sk = sk_head(&ilb->head);
		st->offset = 0;
		goto get_sk;
	}
	ilb = &tcp_hashinfo.listening_hash[st->bucket];
	++st->num;
	++st->offset;

	sk = sk_next(sk);
get_sk:
	sk_for_each_from(sk) {
		if (!net_eq(sock_net(sk), net))
			continue;
		if (sk->sk_family == st->family)
			return sk;
	}
	spin_unlock(&ilb->lock);
	st->offset = 0;
	if (++st->bucket < INET_LHTABLE_SIZE)
		goto get_head;
	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
85
45.21%
4
22.22%
Arnaldo Carvalho de Melo
50
26.60%
4
22.22%
Linus Torvalds (pre-git)
14
7.45%
2
11.11%
Pavel Emelyanov
12
6.38%
1
5.56%
Herbert Xu
11
5.85%
2
11.11%
Hideaki Yoshifuji / 吉藤英明
7
3.72%
2
11.11%
Tom Herbert
6
3.19%
1
5.56%
Daniel Lezcano
2
1.06%
1
5.56%
David S. Miller
1
0.53%
1
5.56%
Total
188
100.00%
18
100.00%



static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	st->bucket = 0;
	st->offset = 0;
	rc = listening_get_next(seq, NULL);

	while (rc && *pos) {
		rc = listening_get_next(seq, rc);
		--*pos;
	}
	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
41
54.67%
1
25.00%
Tom Herbert
25
33.33%
1
25.00%
Tim Shepard
6
8.00%
1
25.00%
Herbert Xu
3
4.00%
1
25.00%
Total
75
100.00%
4
100.00%



static inline bool empty_bucket(const struct tcp_iter_state *st)
{
	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andi Kleen
26
89.66%
1
25.00%
Eric Dumazet
3
10.34%
3
75.00%
Total
29
100.00%
4
100.00%

/*
 * Get first established socket starting from bucket given in st->bucket.
 * If st->bucket is zero, the very first socket in the hash is returned.
 */


static void *established_get_first(struct seq_file *seq)
{
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);
	void *rc = NULL;

	st->offset = 0;
	for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
		struct sock *sk;
		struct hlist_nulls_node *node;
		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);

		/* Lockless fast path for the common case of empty buckets */
		if (empty_bucket(st))
			continue;

		spin_lock_bh(lock);
		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
			if (sk->sk_family != st->family ||
			    !net_eq(sock_net(sk), net)) {
				continue;
			}
			rc = sk;
			goto out;
		}
		spin_unlock_bh(lock);
	}
out:
	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
73
48.67%
4
22.22%
Linus Torvalds (pre-git)
24
16.00%
3
16.67%
Eric Dumazet
15
10.00%
4
22.22%
Hideaki Yoshifuji / 吉藤英明
12
8.00%
3
16.67%
Daniel Lezcano
9
6.00%
1
5.56%
Andi Kleen
9
6.00%
1
5.56%
Denis V. Lunev
4
2.67%
1
5.56%
Tom Herbert
4
2.67%
1
5.56%
Total
150
100.00%
18
100.00%



static void *established_get_next(struct seq_file *seq, void *cur)
{
	struct sock *sk = cur;
	struct hlist_nulls_node *node;
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);

	++st->num;
	++st->offset;

	sk = sk_nulls_next(sk);

	sk_nulls_for_each_from(sk, node) {
		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
			return sk;
	}

	spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
	++st->bucket;
	return established_get_first(seq);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
67
56.30%
4
30.77%
Eric Dumazet
19
15.97%
2
15.38%
Hideaki Yoshifuji / 吉藤英明
10
8.40%
3
23.08%
Daniel Lezcano
9
7.56%
1
7.69%
Tim Shepard
5
4.20%
1
7.69%
Tom Herbert
5
4.20%
1
7.69%
Denis V. Lunev
4
3.36%
1
7.69%
Total
119
100.00%
13
100.00%



static void *established_get_idx(struct seq_file *seq, loff_t pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	st->bucket = 0;
	rc = established_get_first(seq);

	while (rc && pos) {
		rc = established_get_next(seq, rc);
		--pos;
	}
	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
39
60.94%
1
33.33%
Tom Herbert
19
29.69%
1
33.33%
Tim Shepard
6
9.38%
1
33.33%
Total
64
100.00%
3
100.00%



static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
{
	void *rc;
	struct tcp_iter_state *st = seq->private;

	st->state = TCP_SEQ_STATE_LISTENING;
	rc	  = listening_get_idx(seq, &pos);

	if (!rc) {
		st->state = TCP_SEQ_STATE_ESTABLISHED;
		rc	  = established_get_idx(seq, pos);
	}

	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
69
100.00%
1
100.00%
Total
69
100.00%
1
100.00%



static void *tcp_seek_last_pos(struct seq_file *seq)
{
	struct tcp_iter_state *st = seq->private;
	int offset = st->offset;
	int orig_num = st->num;
	void *rc = NULL;

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
		if (st->bucket >= INET_LHTABLE_SIZE)
			break;
		st->state = TCP_SEQ_STATE_LISTENING;
		rc = listening_get_next(seq, NULL);
		while (offset-- && rc)
			rc = listening_get_next(seq, rc);
		if (rc)
			break;
		st->bucket = 0;
		st->state = TCP_SEQ_STATE_ESTABLISHED;
		/* Fallthrough */
	case TCP_SEQ_STATE_ESTABLISHED:
		if (st->bucket > tcp_hashinfo.ehash_mask)
			break;
		rc = established_get_first(seq);
		while (offset-- && rc)
			rc = established_get_next(seq, rc);
	}

	st->num = orig_num;

	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tom Herbert
152
97.44%
1
50.00%
Eric Dumazet
4
2.56%
1
50.00%
Total
156
100.00%
2
100.00%



static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	if (*pos && *pos == st->last_pos) {
		rc = tcp_seek_last_pos(seq);
		if (rc)
			goto out;
	}

	st->state = TCP_SEQ_STATE_LISTENING;
	st->num = 0;
	st->bucket = 0;
	st->offset = 0;
	rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;

out:
	st->last_pos = *pos;
	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tom Herbert
58
52.73%
1
20.00%
Arnaldo Carvalho de Melo
30
27.27%
1
20.00%
Tim Shepard
15
13.64%
1
20.00%
Hirofumi Ogawa
6
5.45%
1
20.00%
Joe Perches
1
0.91%
1
20.00%
Total
110
100.00%
5
100.00%



static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc = NULL;

	if (v == SEQ_START_TOKEN) {
		rc = tcp_get_idx(seq, 0);
		goto out;
	}

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
		rc = listening_get_next(seq, v);
		if (!rc) {
			st->state = TCP_SEQ_STATE_ESTABLISHED;
			st->bucket = 0;
			st->offset = 0;
			rc	  = established_get_first(seq);
		}
		break;
	case TCP_SEQ_STATE_ESTABLISHED:
		rc = established_get_next(seq, v);
		break;
	}
out:
	++*pos;
	st->last_pos = *pos;
	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
108
78.83%
1
33.33%
Tom Herbert
28
20.44%
1
33.33%
Joe Perches
1
0.73%
1
33.33%
Total
137
100.00%
3
100.00%



static void tcp_seq_stop(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st = seq->private;

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
		if (v != SEQ_START_TOKEN)
			spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock);
		break;
	case TCP_SEQ_STATE_ESTABLISHED:
		if (v)
			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
		break;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
57
73.08%
3
33.33%
Eric Dumazet
15
19.23%
4
44.44%
Anders Gustafsson
5
6.41%
1
11.11%
Joe Perches
1
1.28%
1
11.11%
Total
78
100.00%
9
100.00%



int tcp_seq_open(struct inode *inode, struct file *file)
{
	struct tcp_seq_afinfo *afinfo = PDE_DATA(inode);
	struct tcp_iter_state *s;
	int err;

	err = seq_open_net(inode, file, &afinfo->seq_ops,
			  sizeof(struct tcp_iter_state));
	if (err < 0)
		return err;

	s = ((struct seq_file *)file->private_data)->private;
	s->family		= afinfo->family;
	s->last_pos		= 0;
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
38
40.43%
2
25.00%
Denis V. Lunev
30
31.91%
2
25.00%
Arnaldo Carvalho de Melo
10
10.64%
1
12.50%
Daniel Lezcano
9
9.57%
1
12.50%
Tom Herbert
6
6.38%
1
12.50%
Al Viro
1
1.06%
1
12.50%
Total
94
100.00%
8
100.00%


EXPORT_SYMBOL(tcp_seq_open);



int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
{
	int rc = 0;
	struct proc_dir_entry *p;

	afinfo->seq_ops.start		= tcp_seq_start;
	afinfo->seq_ops.next		= tcp_seq_next;
	afinfo->seq_ops.stop		= tcp_seq_stop;

	p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
			     afinfo->seq_fops, afinfo);
	if (!p)
		rc = -ENOMEM;
	return rc;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
48
57.83%
2
40.00%
Denis V. Lunev
30
36.14%
2
40.00%
Daniel Lezcano
5
6.02%
1
20.00%
Total
83
100.00%
5
100.00%


EXPORT_SYMBOL(tcp_proc_register);



void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
	remove_proc_entry(afinfo->name, net->proc_net);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
16
61.54%
1
33.33%
Gao Feng
5
19.23%
1
33.33%
Daniel Lezcano
5
19.23%
1
33.33%
Total
26
100.00%
3
100.00%


EXPORT_SYMBOL(tcp_proc_unregister);



static void get_openreq4(const struct request_sock *req,
			 struct seq_file *f, int i)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	long delta = req->rsk_timer.expires - jiffies;

	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK",
		i,
		ireq->ir_loc_addr,
		ireq->ir_num,
		ireq->ir_rmt_addr,
		ntohs(ireq->ir_rmt_port),
		TCP_SYN_RECV,
		0, 0, /* could print option size, but that is af dependent. */
		1,    /* timers active (only the expire timer) */
		jiffies_delta_to_clock_t(delta),
		req->num_timeout,
		from_kuid_munged(seq_user_ns(f),
				 sock_i_uid(req->rsk_listener)),
		0,  /* non standard timer */
		0, /* open_requests have no inode */
		0,
		req);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
59
51.30%
1
6.67%
Arnaldo Carvalho de Melo
20
17.39%
3
20.00%
Eric Dumazet
20
17.39%
7
46.67%
Eric W. Biedermann
8
6.96%
1
6.67%
Pavel Emelyanov
5
4.35%
1
6.67%
David S. Miller
2
1.74%
1
6.67%
Tetsuo Handa
1
0.87%
1
6.67%
Total
115
100.00%
15
100.00%



static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
{
	int timer_active;
	unsigned long timer_expires;
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	const struct inet_sock *inet = inet_sk(sk);
	const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
	__be32 dest = inet->inet_daddr;
	__be32 src = inet->inet_rcv_saddr;
	__u16 destp = ntohs(inet->inet_dport);
	__u16 srcp = ntohs(inet->inet_sport);
	int rx_queue;
	int state;

	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
		timer_active	= 1;
		timer_expires	= icsk->icsk_timeout;
	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
		timer_active	= 4;
		timer_expires	= icsk->icsk_timeout;
	} else if (timer_pending(&sk->sk_timer)) {
		timer_active	= 2;
		timer_expires	= sk->sk_timer.expires;
	} else {
		timer_active	= 0;
		timer_expires = jiffies;
	}

	state = sk_state_load(sk);
	if (state == TCP_LISTEN)
		rx_queue = sk->sk_ack_backlog;
	else
		/* Because we don't lock the socket,
                 * we might find a transient negative value.
                 */
		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);

	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
		i, src, srcp, dest, destp, state,
		tp->write_seq - tp->snd_una,
		rx_queue,
		timer_active,
		jiffies_delta_to_clock_t(timer_expires - jiffies),
		icsk->icsk_retransmits,
		from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)),
		icsk->icsk_probes_out,
		sock_i_ino(sk),
		atomic_read(&sk->sk_refcnt), sk,
		jiffies_to_clock_t(icsk->icsk_rto),
		jiffies_to_clock_t(icsk->icsk_ack.ato),
		(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
		tp->snd_cwnd,
		state == TCP_LISTEN ?
		    fastopenq->max_qlen :
		    (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
246
66.13%
6
25.00%
Eric Dumazet
56
15.05%
6
25.00%
Jerry Chu
20
5.38%
1
4.17%
Ilpo Järvinen
13
3.49%
2
8.33%
Eric W. Biedermann
8
2.15%
1
4.17%
Yuchung Cheng
6
1.61%
1
4.17%
Stephen Hemminger
6
1.61%
1
4.17%
Nandita Dukkipati
6
1.61%
1
4.17%
Pavel Emelyanov
5
1.34%
1
4.17%
Al Viro
2
0.54%
1
4.17%
David S. Miller
2
0.54%
1
4.17%
Tetsuo Handa
1
0.27%
1
4.17%
Hideaki Yoshifuji / 吉藤英明
1
0.27%
1
4.17%
Total
372
100.00%
24
100.00%



static void get_timewait4_sock(const struct inet_timewait_sock *tw,
			       struct seq_file *f, int i)
{
	long delta = tw->tw_timer.expires - jiffies;
	__be32 dest, src;
	__u16 destp, srcp;

	dest  = tw->tw_daddr;
	src   = tw->tw_rcv_saddr;
	destp = ntohs(tw->tw_dport);
	srcp  = ntohs(tw->tw_sport);

	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK",
		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
		3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
		atomic_read(&tw->tw_refcnt), tw);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
85
69.67%
3
20.00%
Eric Dumazet
14
11.48%
3
20.00%
Linus Torvalds (pre-git)
13
10.66%
4
26.67%
Pavel Emelyanov
5
4.10%
1
6.67%
David S. Miller
2
1.64%
1
6.67%
Tetsuo Handa
1
0.82%
1
6.67%
Al Viro
1
0.82%
1
6.67%
Hideaki Yoshifuji / 吉藤英明
1
0.82%
1
6.67%
Total
122
100.00%
15
100.00%


#define TMPSZ 150



static int tcp4_seq_show(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st;
	struct sock *sk = v;

	seq_setwidth(seq, TMPSZ - 1);
	if (v == SEQ_START_TOKEN) {
		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
			   "rx_queue tr tm->when retrnsmt   uid  timeout "
			   "inode");
		goto out;
	}
	st = seq->private;

	if (sk->sk_state == TCP_TIME_WAIT)
		get_timewait4_sock(v, seq, st->num);
	else if (sk->sk_state == TCP_NEW_SYN_RECV)
		get_openreq4(v, seq, st->num);
	else
		get_tcp4_sock(v, seq, st->num);
out:
	seq_pad(seq, '\n');
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
45
36.00%
1
9.09%
Linus Torvalds (pre-git)
33
26.40%
4
36.36%
Eric Dumazet
28
22.40%
2
18.18%
Tetsuo Handa
14
11.20%
1
9.09%
Pavel Emelyanov
3
2.40%
1
9.09%
Hideaki Yoshifuji / 吉藤英明
1
0.80%
1
9.09%
Joe Perches
1
0.80%
1
9.09%
Total
125
100.00%
11
100.00%


static const struct file_operations tcp_afinfo_seq_fops = {
	.owner   = THIS_MODULE,
	.open    = tcp_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_net
};


static struct tcp_seq_afinfo tcp4_seq_afinfo = {
	.name		= "tcp",
	.family		= AF_INET,
	.seq_fops	= &tcp_afinfo_seq_fops,
	.seq_ops	= {
		.show		= tcp4_seq_show,
        },
};



static int __net_init tcp4_proc_init_net(struct net *net)
{
	return tcp_proc_register(net, &tcp4_seq_afinfo);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
12
57.14%
1
25.00%
Arnaldo Carvalho de Melo
6
28.57%
1
25.00%
Hideaki Yoshifuji / 吉藤英明
2
9.52%
1
25.00%
Alexey Dobriyan
1
4.76%
1
25.00%
Total
21
100.00%
4
100.00%



static void __net_exit tcp4_proc_exit_net(struct net *net)
{
	tcp_proc_unregister(net, &tcp4_seq_afinfo);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
15
75.00%
1
25.00%
Hideaki Yoshifuji / 吉藤英明
2
10.00%
1
25.00%
Daniel Lezcano
2
10.00%
1
25.00%
Alexey Dobriyan
1
5.00%
1
25.00%
Total
20
100.00%
4
100.00%


static struct pernet_operations tcp4_net_ops = {
	.init = tcp4_proc_init_net,
	.exit = tcp4_proc_exit_net,
};



int __init tcp4_proc_init(void)
{
	return register_pernet_subsys(&tcp4_net_ops);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
13
86.67%
1
50.00%
Linus Torvalds (pre-git)
2
13.33%
1
50.00%
Total
15
100.00%
2
100.00%



void tcp4_proc_exit(void)
{
	unregister_pernet_subsys(&tcp4_net_ops);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Arnaldo Carvalho de Melo
9
69.23%
1
33.33%
Hideaki Yoshifuji / 吉藤英明
2
15.38%
1
33.33%
Pavel Emelyanov
2
15.38%
1
33.33%
Total
13
100.00%
3
100.00%

#endif /* CONFIG_PROC_FS */


struct proto tcp_prot = {
	.name			= "TCP",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= inet_csk_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v4_init_sock,
	.destroy		= tcp_v4_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.keepalive		= tcp_set_keepalive,
	.recvmsg		= tcp_recvmsg,
	.sendmsg		= tcp_sendmsg,
	.sendpage		= tcp_sendpage,
	.backlog_rcv		= tcp_v4_do_rcv,
	.release_cb		= tcp_release_cb,
	.hash			= inet_hash,
	.unhash			= inet_unhash,
	.get_port		= inet_csk_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.stream_memory_free	= tcp_stream_memory_free,
	.sockets_allocated	= &tcp_sockets_allocated,
	.orphan_count		= &tcp_orphan_count,
	.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,
	.obj_size		= sizeof(struct tcp_sock),
	.slab_flags		= SLAB_DESTROY_BY_RCU,
	.twsk_prot		= &tcp_timewait_sock_ops,
	.rsk_prot		= &tcp_request_sock_ops,
	.h.hashinfo		= &tcp_hashinfo,
	.no_autobind		= true,
#ifdef CONFIG_COMPAT
	.compat_setsockopt	= compat_tcp_setsockopt,
	.compat_getsockopt	= compat_tcp_getsockopt,
#endif
	.diag_destroy		= tcp_abort,
};

EXPORT_SYMBOL(tcp_prot);



static void __net_exit tcp_sk_exit(struct net *net)
{
	int cpu;

	for_each_possible_cpu(cpu)
		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
	free_percpu(net->ipv4.tcp_sk);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
43
100.00%
1
100.00%
Total
43
100.00%
1
100.00%



static int __net_init tcp_sk_init(struct net *net)
{
	int res, cpu, cnt;

	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
	if (!net->ipv4.tcp_sk)
		return -ENOMEM;

	for_each_possible_cpu(cpu) {
		struct sock *sk;

		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
					   IPPROTO_TCP, net);
		if (res)
			goto fail;
		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
	}

	net->ipv4.sysctl_tcp_ecn = 2;
	net->ipv4.sysctl_tcp_ecn_fallback = 1;

	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;

	net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
	net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;

	net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES;
	net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES;
	net->ipv4.sysctl_tcp_syncookies = 1;
	net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH;
	net->ipv4.sysctl_tcp_retries1 = TCP_RETR1;
	net->ipv4.sysctl_tcp_retries2 = TCP_RETR2;
	net->ipv4.sysctl_tcp_orphan_retries = 0;
	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
	net->ipv4.sysctl_tcp_tw_reuse = 0;

	cnt = tcp_hashinfo.ehash_mask + 1;
	net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;

	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);

	return 0;
fail:
	tcp_sk_exit(net);

	return res;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
96
30.28%
3
11.11%
Nikolay Borisov
95
29.97%
12
44.44%
Haishuang Yan
70
22.08%
3
11.11%
Fan Du
24
7.57%
3
11.11%
Denis V. Lunev
12
3.79%
1
3.70%
Hannes Frederic Sowa
8
2.52%
1
3.70%
Daniel Borkmann
8
2.52%
1
3.70%
Linus Torvalds (pre-git)
3
0.95%
2
7.41%
David S. Miller
1
0.32%
1
3.70%
Total
317
100.00%
27
100.00%



static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
	inet_twsk_purge(&tcp_hashinfo, AF_INET);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric W. Biedermann
11
55.00%
1
33.33%
Daniel Lezcano
8
40.00%
1
33.33%
Denis V. Lunev
1
5.00%
1
33.33%
Total
20
100.00%
3
100.00%


static struct pernet_operations __net_initdata tcp_sk_ops = {
       .init	   = tcp_sk_init,
       .exit	   = tcp_sk_exit,
       .exit_batch = tcp_sk_exit_batch,
};



void __init tcp_v4_init(void)
{
	if (register_pernet_subsys(&tcp_sk_ops))
		panic("Failed to create the TCP control socket.\n");
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Denis V. Lunev
12
57.14%
2
40.00%
Linus Torvalds (pre-git)
7
33.33%
1
20.00%
Eric W. Biedermann
1
4.76%
1
20.00%
Linus Torvalds
1
4.76%
1
20.00%
Total
21
100.00%
5
100.00%

Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
2559
21.87%
126
27.04%
Linus Torvalds (pre-git)
2229
19.05%
45
9.66%
Arnaldo Carvalho de Melo
1758
15.03%
49
10.52%
Hideaki Yoshifuji / 吉藤英明
1460
12.48%
15
3.22%
David S. Miller
593
5.07%
36
7.73%
Tom Herbert
330
2.82%
4
0.86%
Adam Langley
266
2.27%
2
0.43%
Octavian Purdila
194
1.66%
9
1.93%
Pavel Emelyanov
167
1.43%
12
2.58%
Herbert Xu
151
1.29%
8
1.72%
Shawn Lu
149
1.27%
2
0.43%
Linus Torvalds
139
1.19%
6
1.29%
Damian Lukowski
133
1.14%
2
0.43%
Denis V. Lunev
127
1.09%
8
1.72%
Alexey Kuznetsov
124
1.06%
5
1.07%
Nikolay Borisov
95
0.81%
12
2.58%
Haishuang Yan
93
0.79%
3
0.64%
Florian Westphal
90
0.77%
3
0.64%
Stephen Hemminger
77
0.66%
9
1.93%
Rusty Russell
58
0.50%
1
0.21%
Lorenzo Colitti
56
0.48%
2
0.43%
Yuchung Cheng
54
0.46%
4
0.86%
Jerry Chu
53
0.45%
2
0.43%
Daniel Lezcano
49
0.42%
3
0.64%
KOVACS Krisztian
44
0.38%
1
0.21%
Eric W. Biedermann
41
0.35%
5
1.07%
Arjan van de Ven
40
0.34%
1
0.21%
Andi Kleen
35
0.30%
1
0.21%
Tim Shepard
32
0.27%
2
0.43%
Fan Du
27
0.23%
4
0.86%
Wei Wang
24
0.21%
1
0.21%
Ilpo Järvinen
23
0.20%
4
0.86%
Balazs Scheidler
20
0.17%
1
0.21%
Alexey Kodanev
19
0.16%
1
0.21%
Neal Cardwell
18
0.15%
3
0.64%
Hannes Frederic Sowa
17
0.15%
3
0.64%
Tetsuo Handa
17
0.15%
1
0.21%
Andrey Vagin
16
0.14%
1
0.21%
Craig Gallek
16
0.14%
1
0.21%
Benjamin LaHaise
15
0.13%
1
0.21%
Changli Gao
15
0.13%
1
0.21%
Patrick McHardy
15
0.13%
4
0.86%
Dmitry Mishin
15
0.13%
1
0.21%
Daniel Borkmann
15
0.13%
2
0.43%
James Morris
13
0.11%
2
0.43%
Joe Perches
12
0.10%
3
0.64%
Dmitry Popov
12
0.10%
1
0.21%
Wei Dong
12
0.10%
1
0.21%
Nivedita Singhvi
11
0.09%
1
0.21%
Jiri Benc
11
0.09%
1
0.21%
Yi Zhu
9
0.08%
1
0.21%
David Ahern
8
0.07%
1
0.21%
Marcelo Ricardo Leitner
8
0.07%
1
0.21%
Tom Quetchenbach
8
0.07%
1
0.21%
Al Viro
8
0.07%
5
1.07%
Jon Maxwell
8
0.07%
1
0.21%
Vijay Subramanian
7
0.06%
2
0.43%
William Allen Simpson
7
0.06%
2
0.43%
Nandita Dukkipati
6
0.05%
1
0.21%
Andrew Morton
6
0.05%
1
0.21%
Hirofumi Ogawa
6
0.05%
1
0.21%
John Dykstra
6
0.05%
2
0.43%
Gao Feng
5
0.04%
1
0.21%
Ursula Braun
5
0.04%
1
0.21%
Gui Jianfeng
5
0.04%
1
0.21%
Anders Gustafsson
5
0.04%
1
0.21%
Gerrit Renker
4
0.03%
1
0.21%
Sathya Perla
4
0.03%
1
0.21%
Harvey Harrison
3
0.03%
1
0.21%
Tejun Heo
3
0.03%
1
0.21%
Paul Moore
3
0.03%
1
0.21%
Zheng Yan
3
0.03%
1
0.21%
Michal Kubeček
3
0.03%
1
0.21%
Eliezer Tamir
3
0.03%
2
0.43%
Adrian Bunk
3
0.03%
2
0.43%
Ian Morris
3
0.03%
1
0.21%
Alexey Dobriyan
2
0.02%
1
0.21%
Brian Haley
2
0.02%
2
0.43%
Martin KaFai Lau
2
0.02%
1
0.21%
Aydin Arik
2
0.02%
1
0.21%
Christopher Leech
2
0.02%
1
0.21%
Glauber de Oliveira Costa
2
0.02%
1
0.21%
Christoph Paasch
2
0.02%
1
0.21%
Yaogong Wang
1
0.01%
1
0.21%
Matthias M. Dellweg
1
0.01%
1
0.21%
Craig Schlenter
1
0.01%
1
0.21%
Steven Cole
1
0.01%
1
0.21%
Ingo Molnar
1
0.01%
1
0.21%
Thomas Graf
1
0.01%
1
0.21%
Kris Katterjohn
1
0.01%
1
0.21%
Total
11699
100.00%
466
100.00%
Directory: net/ipv4

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.