Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 03e6b7a..4804b6d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/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>
@@ -90,6 +87,18 @@
}
#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)
{
struct dst_entry *dst = skb_dst(skb);
@@ -99,7 +108,7 @@
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 +147,7 @@
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 +171,7 @@
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);
}
@@ -206,7 +215,7 @@
!ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
- tp->write_seq = 0;
+ WRITE_ONCE(tp->write_seq, 0);
}
sk->sk_v6_daddr = usin->sin6_addr;
@@ -220,8 +229,6 @@
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;
@@ -304,10 +311,11 @@
if (likely(!tp->repair)) {
if (!tp->write_seq)
- tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
- sk->sk_v6_daddr.s6_addr32,
- inet->inet_sport,
- inet->inet_dport);
+ WRITE_ONCE(tp->write_seq,
+ secure_tcpv6_seq(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
+ inet->inet_sport,
+ inet->inet_dport));
tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
@@ -349,7 +357,7 @@
}
}
-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;
@@ -371,17 +379,19 @@
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)
@@ -390,14 +400,14 @@
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)) {
@@ -405,7 +415,7 @@
goto out;
}
- np = inet6_sk(sk);
+ np = tcp_inet6_sk(sk);
if (type == NDISC_REDIRECT) {
if (!sock_owned_by_user(sk)) {
@@ -467,6 +477,7 @@
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
@@ -477,7 +488,7 @@
enum tcp_synack_type synack_type)
{
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;
@@ -502,7 +513,8 @@
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass);
+ err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass,
+ sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -734,14 +746,15 @@
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);
@@ -792,7 +805,7 @@
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;
@@ -872,9 +885,17 @@
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;
@@ -888,7 +909,8 @@
dst = ip6_dst_lookup_flow(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,
+ priority);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -901,15 +923,18 @@
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)
@@ -921,6 +946,7 @@
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);
@@ -934,7 +960,7 @@
* 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,
@@ -962,11 +988,25 @@
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, 0,
+ label, priority);
#ifdef CONFIG_TCP_MD5SIG
out:
@@ -977,10 +1017,10 @@
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)
@@ -992,7 +1032,7 @@
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);
}
@@ -1015,7 +1055,7 @@
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);
+ 0, 0, sk->sk_priority);
}
@@ -1030,6 +1070,21 @@
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)
{
if (skb->protocol == htons(ETH_P_IP))
@@ -1064,9 +1119,8 @@
{
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;
struct tcp_sock *newtp;
struct sock *newsk;
@@ -1086,11 +1140,10 @@
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));
@@ -1108,11 +1161,11 @@
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
- newnp->mcast_oif = tcp_v6_iif(skb);
- newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
- newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+ newnp->mcast_oif = inet_iif(skb);
+ newnp->mcast_hops = ip_hdr(skb)->ttl;
+ newnp->rcv_flowinfo = 0;
if (np->repflow)
- newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+ newnp->flow_label = 0;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1154,12 +1207,11 @@
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));
@@ -1274,9 +1326,9 @@
*/
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.
@@ -1424,8 +1476,9 @@
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);
const struct tcphdr *th;
const struct ipv6hdr *hdr;
@@ -1522,7 +1575,7 @@
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;
}
@@ -1552,12 +1605,17 @@
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);
@@ -1637,7 +1695,7 @@
goto discard_it;
}
-static void tcp_v6_early_demux(struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
@@ -1667,7 +1725,7 @@
struct dst_entry *dst = READ_ONCE(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);
@@ -1838,7 +1896,8 @@
/* 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);
+ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ READ_ONCE(tp->copied_seq), 0);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
@@ -1849,7 +1908,7 @@
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
state,
- tp->write_seq - tp->snd_una,
+ READ_ONCE(tp->write_seq) - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
@@ -1860,7 +1919,7 @@
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 :