1 files changed, 82 insertions, 40 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2f8039a26b08..92282f98dc82 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -7,18 +8,12 @@
  *
  *		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.
  */
 
 /*
@@ -126,11 +121,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
 			if (ipv6_addr_loopback(&tw->tw_v6_daddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_daddr) &&
-			     (tw->tw_v6_daddr.s6_addr[12] == 127)) ||
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) ||
 			    ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) &&
-			     (tw->tw_v6_rcv_saddr.s6_addr[12] == 127)))
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr))
 				loopback = true;
 		} else
 #endif
@@ -169,9 +162,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 		 * without appearing to create any others.
 		 */
 		if (likely(!tp->repair)) {
-			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-			if (tp->write_seq == 0)
-				tp->write_seq = 1;
+			u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+			if (!seq)
+				seq = 1;
+			WRITE_ONCE(tp->write_seq, seq);
 			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
 			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
 		}
@@ -258,7 +253,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tp->rx_opt.ts_recent	   = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		if (likely(!tp->repair))
-			tp->write_seq	   = 0;
+			WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	inet->inet_dport = usin->sin_port;
@@ -296,16 +291,17 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcp_seq(inet->inet_saddr,
-						       inet->inet_daddr,
-						       inet->inet_sport,
-						       usin->sin_port);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcp_seq(inet->inet_saddr,
+						  inet->inet_daddr,
+						  inet->inet_sport,
+						  usin->sin_port));
 		tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
 						 inet->inet_saddr,
 						 inet->inet_daddr);
 	}
 
-	inet->inet_id = tp->write_seq ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
@@ -483,7 +479,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	icsk = inet_csk(sk);
 	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)) {
@@ -667,8 +663,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	int genhash;
 	struct sock *sk1 = NULL;
 #endif
-	struct net *net;
+	u64 transmit_time = 0;
 	struct sock *ctl_sk;
+	struct net *net;
 
 	/* Never send a reset in response to a reset. */
 	if (th->rst)
@@ -771,14 +768,19 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	arg.tos = ip_hdr(skb)->tos;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
-	if (sk)
+	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
+		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+				   inet_twsk(sk)->tw_priority : sk->sk_priority;
+		transmit_time = tcp_transmit_time(sk);
+	}
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
-			      &arg, arg.iov[0].iov_len);
+			      &arg, arg.iov[0].iov_len,
+			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
@@ -813,6 +815,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	struct net *net = sock_net(sk);
 	struct ip_reply_arg arg;
 	struct sock *ctl_sk;
+	u64 transmit_time;
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -863,14 +866,17 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	arg.tos = tos;
 	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
-	if (sk)
-		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
-				   inet_twsk(sk)->tw_mark : sk->sk_mark;
+	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
+			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+			   inet_twsk(sk)->tw_priority : sk->sk_priority;
+	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
-			      &arg, arg.iov[0].iov_len);
+			      &arg, arg.iov[0].iov_len,
+			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
@@ -1442,7 +1448,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	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;
+	newinet->inet_id = prandom_u32();
 
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
@@ -1514,6 +1520,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+			 struct tcphdr *th, u32 *cookie)
+{
+	u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+	mss = tcp_get_syncookie_mss(&tcp_request_sock_ops,
+				    &tcp_request_sock_ipv4_ops, sk, th);
+	if (mss) {
+		*cookie = __cookie_v4_init_sequence(iph, th, &mss);
+		tcp_synq_overflow(sk);
+	}
+#endif
+	return mss;
+}
+
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
@@ -1624,7 +1645,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
+	u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
 	struct skb_shared_info *shinfo;
 	const struct tcphdr *th;
 	struct tcphdr *thtail;
@@ -1673,7 +1694,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
 	    TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
 	    ((TCP_SKB_CB(tail)->tcp_flags |
-	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+	    !((TCP_SKB_CB(tail)->tcp_flags &
+	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
 #ifdef CONFIG_TLS_DEVICE
@@ -1692,6 +1715,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
 			TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
 
+		/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+		 * thtail->fin, so that the fast path in tcp_rcv_established()
+		 * is not entered if we append a packet with a FIN.
+		 * SYN, RST, URG are not present.
+		 * ACK is set on both packets.
+		 * PSH : we do not really care in TCP stack,
+		 *       at least for 'GRO' packets.
+		 */
+		thtail->fin |= th->fin;
 		TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
@@ -1774,6 +1806,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct sk_buff *skb_to_free;
 	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
@@ -1884,7 +1917,7 @@ process:
 	if (tcp_v4_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
@@ -1905,11 +1938,17 @@ process:
 	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_v4_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)
@@ -2083,7 +2122,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk);
+	BUG_ON(rcu_access_pointer(tp->fastopen_rsk));
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
@@ -2412,17 +2451,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
-		rx_queue = sk->sk_ack_backlog;
+		rx_queue = READ_ONCE(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);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      READ_ONCE(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,
+		READ_ONCE(tp->write_seq) - tp->snd_una,
 		rx_queue,
 		timer_active,
 		jiffies_delta_to_clock_t(timer_expires - jiffies),
@@ -2615,8 +2655,10 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_ecn_fallback = 1;
 
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+	net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
 	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
+	net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS;
 
 	net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
 	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
@@ -2637,7 +2679,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
-	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;