Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

All conflicts seemed rather trivial, with some guidance from
Saeed Mameed on the tc_ct.c one.

Signed-off-by: David S. Miller <davem@davemloft.net>

12 files changed, 61 insertions, 19 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 956a806649f7..e30515f89802 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 
 	ipcm_init(&ipc);
 	inet->tos = ip_hdr(skb)->tos;
-	sk->sk_mark = mark;
+	ipc.sockc.mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 
@@ -710,10 +710,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	icmp_param.skb	  = skb_in;
 	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
-	sk->sk_mark = mark;
 	ipcm_init(&ipc);
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param.replyopts.opt;
+	ipc.sockc.mark = mark;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d946356187ed..61f802d5350c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1708,7 +1708,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
-	sk->sk_mark = fl4.flowi4_mark;
+	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
 	if (unlikely(err)) {
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 181b7a2a0247..f8b419e2475c 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -844,3 +844,21 @@ void ip_tunnel_unneed_metadata(void)
 	static_branch_dec(&ip_tunnel_metadata_cnt);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
+
+/* Returns either the correct skb->protocol value, or 0 if invalid. */
+__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
+{
+	if (skb_network_header(skb) >= skb->head &&
+	    (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
+	    ip_hdr(skb)->version == 4)
+		return htons(ETH_P_IP);
+	if (skb_network_header(skb) >= skb->head &&
+	    (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
+	    ipv6_hdr(skb)->version == 6)
+		return htons(ETH_P_IPV6);
+	return 0;
+}
+EXPORT_SYMBOL(ip_tunnel_parse_protocol);
+
+const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol };
+EXPORT_SYMBOL(ip_tunnel_header_ops);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1d9c8cff5ac3..460ca1099e8a 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -441,6 +441,7 @@ static const struct net_device_ops vti_netdev_ops = {
 static void vti_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &vti_netdev_ops;
+	dev->header_ops		= &ip_tunnel_header_ops;
 	dev->type		= ARPHRD_TUNNEL;
 	ip_tunnel_setup(dev, vti_net_id);
 }
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 40fea52c8277..75d35e76bec2 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -361,6 +361,7 @@ static const struct net_device_ops ipip_netdev_ops = {
 static void ipip_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipip_netdev_ops;
+	dev->header_ops		= &ip_tunnel_header_ops;
 
 	dev->type		= ARPHRD_TUNNEL;
 	dev->flags		= IFF_NOARP;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 535427292194..df6fbefe44d4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
 			   sk->sk_uid);
 
+	fl4.fl4_icmp_type = user_icmph.type;
+	fl4.fl4_icmp_code = user_icmph.code;
+
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1d7076b78e63..a01efa062f6b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2027,7 +2027,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		      const struct sk_buff *hint)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	struct rtable *rt = (struct rtable *)hint;
+	struct rtable *rt = skb_rtable(hint);
 	struct net *net = dev_net(dev);
 	int err = -EINVAL;
 	u32 tag = 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index de36c91d32ea..254b6a4cc95b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2691,6 +2691,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;
+	if (icsk->icsk_ca_ops->release)
+		icsk->icsk_ca_ops->release(sk);
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
@@ -3246,10 +3249,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
-			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
-		else
-			err = -EINVAL;
+		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
@@ -4033,11 +4033,14 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
+	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
-	sg_init_one(&sg, key->key, key->keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
-	return crypto_ahash_update(hp->md5_req);
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* We use data_race() because tcp_md5_do_add() might change key->key under us */
+	return data_race(crypto_ahash_update(hp->md5_req));
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 3172e31987be..62878cf26d9c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc77309ea15b..61c808864f6b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4604,6 +4604,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
+		sk->sk_data_ready(sk);
 		tcp_drop(sk, skb);
 		return;
 	}
@@ -4850,6 +4851,7 @@ queue_and_out:
 			sk_forced_mem_schedule(sk, skb->truesize);
 		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+			sk->sk_data_ready(sk);
 			goto drop;
 		}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ea0df9fd7618..116c11a0aaed 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1111,9 +1111,21 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
 	if (key) {
-		/* Pre-existing entry - just update that one. */
-		memcpy(key->key, newkey, newkeylen);
-		key->keylen = newkeylen;
+		/* Pre-existing entry - just update that one.
+		 * Note that the key might be used concurrently.
+		 * data_race() is telling kcsan that we do not care of
+		 * key mismatches, since changing MD5 key on live flows
+		 * can lead to packet drops.
+		 */
+		data_race(memcpy(key->key, newkey, newkeylen));
+
+		/* Pairs with READ_ONCE() in tcp_md5_hash_key().
+		 * Also note that a reader could catch new key->keylen value
+		 * but old key->key[], this is the reason we use __GFP_ZERO
+		 * at sock_kmalloc() time below these lines.
+		 */
+		WRITE_ONCE(key->keylen, newkeylen);
+
 		return 0;
 	}
 
@@ -1129,7 +1141,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
-	key = sock_kmalloc(sk, sizeof(*key), gfp);
+	key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
 	if (!key)
 		return -ENOMEM;
 	if (!tcp_alloc_md5sig_pool()) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 04b70fe31fa2..2d563efcee0d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -700,7 +700,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
-				       struct tcp_fastopen_cookie *foc)
+				       struct tcp_fastopen_cookie *foc,
+				       enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -715,7 +716,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		 * rather than TS in order to fit in better with old,
 		 * buggy kernels, but that was deemed to be unnecessary.
 		 */
-		ireq->tstamp_ok &= !ireq->sack_ok;
+		if (synack_type != TCP_SYNACK_COOKIE)
+			ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 #endif
 
@@ -3402,7 +3404,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+					     foc, synack_type) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);