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();