inet: implement lockless IP_TOS

Some reads of inet->tos are racy.

Add needed READ_ONCE() annotations and convert IP_TOS option lockless.

v2: missing changes in include/net/route.h (David Ahern)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip.h

@@ -258,7 +258,7 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
 
 static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
 {
-	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
+	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos));
 }
 
 /* datagram.c */
@@ -810,6 +810,5 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val);
 void ip_sock_set_pktinfo(struct sock *sk);
 void ip_sock_set_recverr(struct sock *sk);
 void ip_sock_set_tos(struct sock *sk, int val);
-void  __ip_sock_set_tos(struct sock *sk, int val);
 
 #endif	/* _IP_H */

include/net/route.h

@@ -37,7 +37,7 @@
 
 #define RTO_ONLINK	0x01
 
-#define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
+#define RT_CONN_FLAGS(sk)   (RT_TOS(READ_ONCE(inet_sk(sk)->tos)) | sock_flag(sk, SOCK_LOCALROUTE))
 #define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
 static inline __u8 ip_sock_rt_scope(const struct sock *sk)
@@ -50,7 +50,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk)
 
 static inline __u8 ip_sock_rt_tos(const struct sock *sk)
 {
-	return RT_TOS(inet_sk(sk)->tos);
+	return RT_TOS(READ_ONCE(inet_sk(sk)->tos));
 }
 
 struct ip_tunnel_info;

net/dccp/ipv4.c

@@ -511,7 +511,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
 					    rcu_dereference(ireq->ireq_opt),
-					    inet_sk(sk)->tos);
+					    READ_ONCE(inet_sk(sk)->tos));
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}

net/ipv4/inet_diag.c

@@ -134,7 +134,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	 * hence this needs to be included regardless of socket family.
 	 */
 	if (ext & (1 << (INET_DIAG_TOS - 1)))
-		if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
+		if (nla_put_u8(skb, INET_DIAG_TOS, READ_ONCE(inet->tos)) < 0)
 			goto errout;
 
 #if IS_ENABLED(CONFIG_IPV6)

net/ipv4/ip_output.c

@@ -544,7 +544,7 @@ EXPORT_SYMBOL(__ip_queue_xmit);
 
 int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 {
-	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+	return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos));
 }
 EXPORT_SYMBOL(ip_queue_xmit);
 
@@ -1438,7 +1438,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
-	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
+	iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos);
 	iph->frag_off = df;
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;

net/ipv4/ip_sockglue.c

@@ -585,25 +585,20 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	return err;
 }
 
-void __ip_sock_set_tos(struct sock *sk, int val)
+void ip_sock_set_tos(struct sock *sk, int val)
 {
+	u8 old_tos = READ_ONCE(inet_sk(sk)->tos);
+
 	if (sk->sk_type == SOCK_STREAM) {
 		val &= ~INET_ECN_MASK;
-		val |= inet_sk(sk)->tos & INET_ECN_MASK;
+		val |= old_tos & INET_ECN_MASK;
 	}
-	if (inet_sk(sk)->tos != val) {
-		inet_sk(sk)->tos = val;
+	if (old_tos != val) {
+		WRITE_ONCE(inet_sk(sk)->tos, val);
 		WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
 		sk_dst_reset(sk);
 	}
 }
-
-void ip_sock_set_tos(struct sock *sk, int val)
-{
-	lock_sock(sk);
-	__ip_sock_set_tos(sk, val);
-	release_sock(sk);
-}
 EXPORT_SYMBOL(ip_sock_set_tos);
 
 void ip_sock_set_freebind(struct sock *sk)
@@ -1050,6 +1045,9 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		return 0;
 	case IP_MTU_DISCOVER:
 		return ip_sock_set_mtu_discover(sk, val);
+	case IP_TOS:	/* This sets both TOS and Precedence */
+		ip_sock_set_tos(sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1104,9 +1102,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		break;
-	case IP_TOS:	/* This sets both TOS and Precedence */
-		__ip_sock_set_tos(sk, val);
-		break;
 	case IP_UNICAST_IF:
 	{
 		struct net_device *dev = NULL;
@@ -1593,6 +1588,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_MTU_DISCOVER:
 		val = READ_ONCE(inet->pmtudisc);
 		goto copyval;
+	case IP_TOS:
+		val = READ_ONCE(inet->tos);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1629,9 +1627,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		return 0;
 	}
-	case IP_TOS:
-		val = inet->tos;
-		break;
 	case IP_MTU:
 	{
 		struct dst_entry *dst;

net/ipv4/tcp_ipv4.c

@@ -1024,10 +1024,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
-		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
-				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
-				(inet_sk(sk)->tos & INET_ECN_MASK) :
-				inet_sk(sk)->tos;
+		tos = READ_ONCE(inet_sk(sk)->tos);
+
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
+			tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+			      (tos & INET_ECN_MASK);
 
 		if (!INET_ECN_is_capable(tos) &&
 		    tcp_bpf_ca_needs_ecn((struct sock *)req))

net/mptcp/sockopt.c

@@ -734,11 +734,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 
 	lock_sock(sk);
 	sockopt_seq_inc(msk);
-	val = inet_sk(sk)->tos;
+	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
-		__ip_sock_set_tos(ssk, val);
+		ip_sock_set_tos(ssk, val);
 	}
 	release_sock(sk);
 
@@ -1343,7 +1343,7 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case IP_TOS:
-		return mptcp_put_int_option(msk, optval, optlen, inet_sk(sk)->tos);
+		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
 	}
 
 	return -EOPNOTSUPP;
@@ -1411,7 +1411,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	ssk->sk_incoming_cpu = sk->sk_incoming_cpu;
 	ssk->sk_ipv6only = sk->sk_ipv6only;
-	__ip_sock_set_tos(ssk, inet_sk(sk)->tos);
+	ip_sock_set_tos(ssk, inet_sk(sk)->tos);
 
 	if (sk->sk_userlocks & tx_rx_locks) {
 		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;

net/sctp/protocol.c

@@ -426,7 +426,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct dst_entry *dst = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
-	__u8 tos = inet_sk(sk)->tos;
+	u8 tos = READ_ONCE(inet_sk(sk)->tos);
 
 	if (t->dscp & SCTP_DSCP_SET_MASK)
 		tos = t->dscp & SCTP_DSCP_VAL_MASK;
@@ -1057,7 +1057,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
 	struct flowi4 *fl4 = &t->fl.u.ip4;
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
-	__u8 dscp = inet->tos;
+	__u8 dscp = READ_ONCE(inet->tos);
 	__be16 df = 0;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,

tools/testing/selftests/net/mptcp/mptcp_connect.sh

@@ -716,7 +716,7 @@ run_test_transparent()
 	# the required infrastructure in MPTCP sockopt code. To support TOS, the
 	# following function has been exported (T). Not great but better than
 	# checking for a specific kernel version.
-	if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then
+	if ! mptcp_lib_kallsyms_has "T ip_sock_set_tos$"; then
 		echo "INFO: ${msg} not supported by the kernel: SKIP"
 		mptcp_lib_result_skip "${TEST_GROUP}"
 		return