From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/net/ipv6/tcp_ipv6.c | 406 +++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 278 insertions(+), 128 deletions(-)
diff --git a/kernel/net/ipv6/tcp_ipv6.c b/kernel/net/ipv6/tcp_ipv6.c
index e8d2067..a68f75d 100644
--- a/kernel/net/ipv6/tcp_ipv6.c
+++ b/kernel/net/ipv6/tcp_ipv6.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* TCP over IPv6
* Linux INET6 implementation
@@ -16,11 +17,6 @@
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file.
- *
- * 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.
*/
#include <linux/bottom_half.h>
@@ -43,6 +39,7 @@
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
+#include <linux/indirect_call_wrapper.h>
#include <net/tcp.h>
#include <net/ndisc.h>
@@ -78,17 +75,30 @@
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static const struct inet_connection_sock_af_ops ipv6_mapped;
-static const struct inet_connection_sock_af_ops ipv6_specific;
+const struct inet_connection_sock_af_ops ipv6_specific;
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#else
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
- const struct in6_addr *addr)
+ const struct in6_addr *addr,
+ int l3index)
{
return NULL;
}
#endif
+
+/* Helper returning the inet6 address from a given tcp socket.
+ * It can be used in TCP stack instead of inet6_sk(sk).
+ * This avoids a dereference and allow compiler optimizations.
+ * It is a specialized version of inet6_sk_generic().
+ */
+static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk)
+{
+ unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo);
+
+ return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
+}
static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
@@ -97,9 +107,9 @@
if (dst && dst_hold_safe(dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
- sk->sk_rx_dst = dst;
+ rcu_assign_pointer(sk->sk_rx_dst, dst);
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
+ tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
}
@@ -138,7 +148,7 @@
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
@@ -162,7 +172,7 @@
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
fl6_sock_release(flowlabel);
}
@@ -220,8 +230,6 @@
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
- SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
-
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
@@ -230,6 +238,8 @@
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
+ if (sk_is_mptcp(sk))
+ mptcpv6_handle_mapped(sk, true);
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -240,6 +250,8 @@
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
+ if (sk_is_mptcp(sk))
+ mptcpv6_handle_mapped(sk, false);
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
@@ -257,6 +269,7 @@
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
+ fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
@@ -266,7 +279,7 @@
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
- security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -327,6 +340,8 @@
late_failure:
tcp_set_state(sk, TCP_CLOSE);
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ inet_reset_saddr(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
@@ -359,7 +374,7 @@
}
}
-static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -381,17 +396,19 @@
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = ntohl(th->seq);
fatal = icmpv6_err_convert(type, code, &err);
- if (sk->sk_state == TCP_NEW_SYN_RECV)
- return tcp_req_err(sk, seq, fatal);
+ if (sk->sk_state == TCP_NEW_SYN_RECV) {
+ tcp_req_err(sk, seq, fatal);
+ return 0;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -400,14 +417,14 @@
if (sk->sk_state == TCP_CLOSE)
goto out;
- if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
+ if (ipv6_hdr(skb)->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
tp = tcp_sk(sk);
/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
- fastopen = tp->fastopen_rsk;
+ fastopen = rcu_dereference(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)) {
@@ -415,7 +432,7 @@
goto out;
}
- np = inet6_sk(sk);
+ np = tcp_inet6_sk(sk);
if (type == NDISC_REDIRECT) {
if (!sock_owned_by_user(sk)) {
@@ -459,10 +476,12 @@
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.
+ * already accepted it is treated as a connected one below.
*/
if (fastopen && !fastopen->sk)
break;
+
+ ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
@@ -472,6 +491,15 @@
} else
sk->sk_err_soft = err;
goto out;
+ case TCP_LISTEN:
+ break;
+ default:
+ /* check if this ICMP message allows revert of backoff.
+ * (see RFC 6069)
+ */
+ if (!fastopen && type == ICMPV6_DEST_UNREACH &&
+ code == ICMPV6_NOROUTE)
+ tcp_ld_RTO_revert(sk, seq);
}
if (!sock_owned_by_user(sk) && np->recverr) {
@@ -483,6 +511,7 @@
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
@@ -490,21 +519,23 @@
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
- struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
int err = -ENOMEM;
+ u8 tclass;
/* First, grab a route. */
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
IPPROTO_TCP)) == NULL)
goto done;
- skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+ skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -514,12 +545,21 @@
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+ tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
+ (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+ (np->tclass & INET_ECN_MASK) :
+ np->tclass;
+
+ if (!INET_ECN_is_capable(tclass) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tclass |= INET_ECN_ECT_0;
+
rcu_read_lock();
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
- np->tclass);
+ tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -537,28 +577,36 @@
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
- const struct in6_addr *addr)
+ const struct in6_addr *addr,
+ int l3index)
{
- return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6);
+ return tcp_md5_do_lookup(sk, l3index,
+ (union tcp_md5_addr *)addr, AF_INET6);
}
static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk,
const struct sock *addr_sk)
{
- return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr);
+ int l3index;
+
+ l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
+ addr_sk->sk_bound_dev_if);
+ return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr,
+ l3index);
}
static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
- char __user *optval, int optlen)
+ sockptr_t optval, int optlen)
{
struct tcp_md5sig cmd;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
+ int l3index = 0;
u8 prefixlen;
if (optlen < sizeof(cmd))
return -EINVAL;
- if (copy_from_user(&cmd, optval, sizeof(cmd)))
+ if (copy_from_sockptr(&cmd, optval, sizeof(cmd)))
return -EFAULT;
if (sin6->sin6_family != AF_INET6)
@@ -574,12 +622,30 @@
prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
}
+ if (optname == TCP_MD5SIG_EXT &&
+ cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex);
+ if (dev && netif_is_l3_master(dev))
+ l3index = dev->ifindex;
+ rcu_read_unlock();
+
+ /* ok to reference set/not set outside of rcu;
+ * right now device MUST be an L3 master
+ */
+ if (!dev || !l3index)
+ return -EINVAL;
+ }
+
if (!cmd.tcpm_keylen) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
- AF_INET, prefixlen);
+ AF_INET, prefixlen,
+ l3index);
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
- AF_INET6, prefixlen);
+ AF_INET6, prefixlen, l3index);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
@@ -587,12 +653,13 @@
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
- AF_INET, prefixlen, cmd.tcpm_key,
- cmd.tcpm_keylen, GFP_KERNEL);
+ AF_INET, prefixlen, l3index,
+ cmd.tcpm_key, cmd.tcpm_keylen,
+ GFP_KERNEL);
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
- AF_INET6, prefixlen, cmd.tcpm_key,
- cmd.tcpm_keylen, GFP_KERNEL);
+ AF_INET6, prefixlen, l3index,
+ cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
@@ -703,17 +770,23 @@
#endif
static bool tcp_v6_inbound_md5_hash(const struct sock *sk,
- const struct sk_buff *skb)
+ const struct sk_buff *skb,
+ int dif, int sdif)
{
#ifdef CONFIG_TCP_MD5SIG
const __u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
- int genhash;
+ int genhash, l3index;
u8 newhash[16];
- hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr);
+ /* sdif set, means packet ingressed via a device
+ * in an L3 domain and dif is set to the l3mdev
+ */
+ l3index = sdif ? dif : 0;
+
+ hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr, l3index);
hash_location = tcp_parse_md5sig_option(th);
/* We've parsed the options - do we have a hash? */
@@ -737,10 +810,10 @@
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
- net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
+ net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n",
genhash ? "failed" : "mismatch",
&ip6h->saddr, ntohs(th->source),
- &ip6h->daddr, ntohs(th->dest));
+ &ip6h->daddr, ntohs(th->dest), l3index);
return true;
}
#endif
@@ -751,14 +824,15 @@
const struct sock *sk_listener,
struct sk_buff *skb)
{
+ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
struct inet_request_sock *ireq = inet_rsk(req);
- const struct ipv6_pinfo *np = inet6_sk(sk_listener);
+ const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
/* So that link locals have meaning */
- if (!sk_listener->sk_bound_dev_if &&
+ if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = tcp_v6_iif(skb);
@@ -789,7 +863,7 @@
.syn_ack_timeout = tcp_syn_ack_timeout,
};
-static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
sizeof(struct ipv6hdr),
#ifdef CONFIG_TCP_MD5SIG
@@ -809,7 +883,7 @@
static void tcp_v6_send_response(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 rst,
- u8 tclass, __be32 label)
+ u8 tclass, __be32 label, u32 priority)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
@@ -889,14 +963,22 @@
fl6.flowi6_oif = oif;
}
- if (sk)
- mark = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_mark : sk->sk_mark;
+ if (sk) {
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ mark = inet_twsk(sk)->tw_mark;
+ /* autoflowlabel relies on buff->hash */
+ skb_set_hash(buff, inet_twsk(sk)->tw_txhash,
+ PKT_HASH_TYPE_L4);
+ } else {
+ mark = sk->sk_mark;
+ }
+ buff->tstamp = tcp_transmit_time(sk);
+ }
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark;
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
- security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+ security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
* Underlying function will use this to retrieve the network
@@ -905,7 +987,8 @@
dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
- ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
+ ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
+ tclass & ~INET_ECN_MASK, priority);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -918,15 +1001,18 @@
static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
{
const struct tcphdr *th = tcp_hdr(skb);
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
u32 seq = 0, ack_seq = 0;
struct tcp_md5sig_key *key = NULL;
#ifdef CONFIG_TCP_MD5SIG
const __u8 *hash_location = NULL;
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
unsigned char newhash[16];
int genhash;
struct sock *sk1 = NULL;
#endif
+ __be32 label = 0;
+ u32 priority = 0;
+ struct net *net;
int oif = 0;
if (th->rst)
@@ -938,12 +1024,23 @@
if (!sk && !ipv6_unicast_destination(skb))
return;
+ 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_v6_md5_do_lookup(sk, &ipv6h->saddr);
+ int l3index;
+
+ /* sdif set, means packet ingressed via a device
+ * in an L3 domain and inet_iif is set to it.
+ */
+ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0;
+ key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index);
} else if (hash_location) {
+ int dif = tcp_v6_iif_l3_slave(skb);
+ int sdif = tcp_v6_sdif(skb);
+ int l3index;
+
/*
* active side is lost. Try to find listening socket through
* source port, and then find md5 key through listening socket.
@@ -951,17 +1048,20 @@
* Incoming packet is checked with md5 hash with finding key,
* no RST generated if md5 hash doesn't match.
*/
- sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
+ sk1 = inet6_lookup_listener(net,
&tcp_hashinfo, NULL, 0,
&ipv6h->saddr,
th->source, &ipv6h->daddr,
- ntohs(th->source),
- tcp_v6_iif_l3_slave(skb),
- tcp_v6_sdif(skb));
+ ntohs(th->source), dif, sdif);
if (!sk1)
goto out;
- key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
+ /* sdif set, means packet ingressed via a device
+ * in an L3 domain and dif is set to it.
+ */
+ l3index = tcp_v6_sdif(skb) ? dif : 0;
+
+ key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index);
if (!key)
goto out;
@@ -979,11 +1079,25 @@
if (sk) {
oif = sk->sk_bound_dev_if;
- if (sk_fullsock(sk))
+ if (sk_fullsock(sk)) {
+ const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
+
trace_tcp_send_reset(sk, skb);
+ if (np->repflow)
+ label = ip6_flowlabel(ipv6h);
+ priority = sk->sk_priority;
+ }
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
+ priority = inet_twsk(sk)->tw_priority;
+ }
+ } else {
+ if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET)
+ label = ip6_flowlabel(ipv6h);
}
- tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+ tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1,
+ ipv6_get_dsfield(ipv6h), label, priority);
#ifdef CONFIG_TCP_MD5SIG
out:
@@ -994,10 +1108,10 @@
static void tcp_v6_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, u8 tclass,
- __be32 label)
+ __be32 label, u32 priority)
{
tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
- tclass, label);
+ tclass, label, priority);
}
static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -1009,7 +1123,7 @@
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp_raw() + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
- tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
+ tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority);
inet_twsk_put(tw);
}
@@ -1017,6 +1131,10 @@
static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
+ int l3index;
+
+ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0;
+
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
@@ -1030,9 +1148,9 @@
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
- req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
- 0, 0);
+ READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
+ ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority);
}
@@ -1045,6 +1163,21 @@
sk = cookie_v6_check(sk, skb);
#endif
return sk;
+}
+
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+ struct tcphdr *th, u32 *cookie)
+{
+ u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+ mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops,
+ &tcp_request_sock_ipv6_ops, sk, th);
+ if (mss) {
+ *cookie = __cookie_v6_init_sequence(iph, th, &mss);
+ tcp_synq_overflow(sk);
+ }
+#endif
+ return mss;
}
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
@@ -1086,14 +1219,15 @@
{
struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp;
- const struct ipv6_pinfo *np = inet6_sk(sk);
+ const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
- struct tcp6_sock *newtcp6sk;
struct inet_sock *newinet;
+ bool found_dup_sk = false;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
+ int l3index;
#endif
struct flowi6 fl6;
@@ -1108,11 +1242,10 @@
if (!newsk)
return NULL;
- newtcp6sk = (struct tcp6_sock *)newsk;
- inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
+ inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
newinet = inet_sk(newsk);
- newnp = inet6_sk(newsk);
+ newnp = tcp_inet6_sk(newsk);
newtp = tcp_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
@@ -1120,6 +1253,8 @@
newnp->saddr = newsk->sk_v6_rcv_saddr;
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
+ if (sk_is_mptcp(newsk))
+ mptcpv6_handle_mapped(newsk, true);
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -1176,12 +1311,11 @@
ip6_dst_store(newsk, dst, NULL, NULL);
inet6_sk_rx_dst_set(newsk, skb);
- newtcp6sk = (struct tcp6_sock *)newsk;
- inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
+ inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
- newnp = inet6_sk(newsk);
+ newnp = tcp_inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
@@ -1209,6 +1343,12 @@
newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
if (np->repflow)
newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+
+ /* Set ToS of the new socket based upon the value of incoming SYN.
+ * ECT bits are set later in tcp_init_transfer().
+ */
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
+ newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
/* Clone native IPv6 options from listening socket (if any)
@@ -1239,8 +1379,10 @@
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
#ifdef CONFIG_TCP_MD5SIG
+ l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
+
/* Copy over the MD5 key from the original socket */
- key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr);
+ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index);
if (key) {
/* We're using one, so create a matching key
* on the newsk structure. If we fail to get
@@ -1248,7 +1390,7 @@
* across. Shucks.
*/
tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
- AF_INET6, 128, key->key, key->keylen,
+ AF_INET6, 128, l3index, key->key, key->keylen,
sk_gfp_mask(sk, GFP_ATOMIC));
}
#endif
@@ -1258,20 +1400,27 @@
tcp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (*own_req) {
tcp_move_syn(newtp, req);
/* Clone pktoptions received with SYN, if we own the req */
if (ireq->pktopts) {
- newnp->pktoptions = skb_clone(ireq->pktopts,
- sk_gfp_mask(sk, GFP_ATOMIC));
+ newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
- if (newnp->pktoptions) {
+ if (newnp->pktoptions)
tcp_v6_restore_cb(newnp->pktoptions);
- skb_set_owner_r(newnp->pktoptions, newsk);
- }
+ }
+ } else {
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
}
}
@@ -1296,9 +1445,9 @@
*/
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct tcp_sock *tp;
+ struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct sk_buff *opt_skb = NULL;
+ struct tcp_sock *tp;
/* Imagine: socket is IPv6. IPv4 packet arrives,
goes to IPv4 receive handler and backlogged.
@@ -1330,18 +1479,21 @@
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+ opt_skb = skb_clone_and_charge_r(skb, sk);
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst;
+
+ dst = rcu_dereference_protected(sk->sk_rx_dst,
+ lockdep_sock_is_held(sk));
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, np->rx_dst_cookie) == NULL) {
+ RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
dst_release(dst);
- sk->sk_rx_dst = NULL;
}
}
@@ -1409,7 +1561,6 @@
if (np->repflow)
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
- skb_set_owner_r(opt_skb, sk);
tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
@@ -1446,9 +1597,11 @@
skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
}
-static int tcp_v6_rcv(struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
{
+ struct sk_buff *skb_to_free;
int sdif = inet6_sdif(skb);
+ int dif = inet6_iif(skb);
const struct tcphdr *th;
const struct ipv6hdr *hdr;
bool refcounted;
@@ -1497,7 +1650,7 @@
struct sock *nsk;
sk = req->rsk_listener;
- if (tcp_v6_inbound_md5_hash(sk, skb)) {
+ if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) {
sk_drops_add(sk, skb);
reqsk_put(req);
goto discard_it;
@@ -1544,7 +1697,7 @@
return 0;
}
}
- if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
+ if (hdr->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
goto discard_and_relse;
}
@@ -1552,7 +1705,7 @@
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
- if (tcp_v6_inbound_md5_hash(sk, skb))
+ if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif))
goto discard_and_relse;
if (tcp_filter(sk, skb))
@@ -1574,12 +1727,17 @@
tcp_segs_in(tcp_sk(sk), skb);
ret = 0;
if (!sock_owned_by_user(sk)) {
+ skb_to_free = sk->sk_rx_skb_cache;
+ sk->sk_rx_skb_cache = NULL;
ret = tcp_v6_do_rcv(sk, skb);
- } else if (tcp_add_backlog(sk, skb)) {
- goto discard_and_relse;
+ } else {
+ if (tcp_add_backlog(sk, skb))
+ goto discard_and_relse;
+ skb_to_free = NULL;
}
bh_unlock_sock(sk);
-
+ if (skb_to_free)
+ __kfree_skb(skb_to_free);
put_and_return:
if (refcounted)
sock_put(sk);
@@ -1645,7 +1803,7 @@
}
}
/* to ACK */
- /* fall through */
+ fallthrough;
case TCP_TW_ACK:
tcp_v6_timewait_ack(sk, skb);
break;
@@ -1659,7 +1817,7 @@
goto discard_it;
}
-static void tcp_v6_early_demux(struct sk_buff *skb)
+void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
@@ -1686,10 +1844,10 @@
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk_fullsock(sk)) {
- struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+ struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
- dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+ dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie);
if (dst &&
inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
@@ -1703,7 +1861,14 @@
.twsk_destructor = tcp_twsk_destructor,
};
-static const struct inet_connection_sock_af_ops ipv6_specific = {
+INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ __tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
+}
+
+const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
@@ -1716,10 +1881,6 @@
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_ipv6_setsockopt,
- .compat_getsockopt = compat_ipv6_getsockopt,
-#endif
.mtu_reduced = tcp_v6_mtu_reduced,
};
@@ -1746,10 +1907,6 @@
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_ipv6_setsockopt,
- .compat_getsockopt = compat_ipv6_getsockopt,
-#endif
.mtu_reduced = tcp_v4_mtu_reduced,
};
@@ -1777,12 +1934,6 @@
#endif
return 0;
-}
-
-static void tcp_v6_destroy_sock(struct sock *sk)
-{
- tcp_v4_destroy_sock(sk);
- inet6_destroy_sock(sk);
}
#ifdef CONFIG_PROC_FS
@@ -1855,7 +2006,7 @@
state = inet_sk_state_load(sp);
if (state == TCP_LISTEN)
- rx_queue = sp->sk_ack_backlog;
+ rx_queue = READ_ONCE(sp->sk_ack_backlog);
else
/* Because we don't lock the socket,
* we might find a transient negative value.
@@ -1883,7 +2034,7 @@
refcount_read(&sp->sk_refcnt), sp,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
- (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
+ (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp),
tp->snd_cwnd,
state == TCP_LISTEN ?
fastopenq->max_qlen :
@@ -1977,7 +2128,7 @@
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v6_init_sock,
- .destroy = tcp_v6_destroy_sock,
+ .destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
@@ -2007,19 +2158,11 @@
.rsk_prot = &tcp6_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_GPL(tcpv6_prot);
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol tcpv6_protocol = {
- .early_demux = tcp_v6_early_demux,
- .early_demux_handler = tcp_v6_early_demux,
+static const struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
@@ -2072,9 +2215,16 @@
ret = register_pernet_subsys(&tcpv6_net_ops);
if (ret)
goto out_tcpv6_protosw;
+
+ ret = mptcpv6_init();
+ if (ret)
+ goto out_tcpv6_pernet_subsys;
+
out:
return ret;
+out_tcpv6_pernet_subsys:
+ unregister_pernet_subsys(&tcpv6_net_ops);
out_tcpv6_protosw:
inet6_unregister_protosw(&tcpv6_protosw);
out_tcpv6_protocol:
--
Gitblit v1.6.2