Merge branch 'inet-more-data-race-fixes'

Eric Dumazet says:

====================
inet: more data-race fixes

This series fixes some existing data-races on inet fields:

inet->mc_ttl, inet->pmtudisc, inet->tos, inet->uc_index,
inet->mc_index and inet->mc_addr.

While fixing them, we convert eight socket options
to lockless implementation.

v2: addressed David Ahern feedback on ("inet: implement lockless IP_TOS")
    Added David Reviewed-by: tag on other patches.
====================

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 */
@@ -434,19 +434,22 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
 
 static inline bool ip_sk_accept_pmtu(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
-	       inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
+
+	return pmtudisc != IP_PMTUDISC_INTERFACE &&
+	       pmtudisc != IP_PMTUDISC_OMIT;
 }
 
 static inline bool ip_sk_use_pmtu(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
+	return READ_ONCE(inet_sk(sk)->pmtudisc) < IP_PMTUDISC_PROBE;
 }
 
 static inline bool ip_sk_ignore_df(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
-	       inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
+
+	return pmtudisc < IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_OMIT;
 }
 
 static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
@@ -807,6 +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/datagram.c

@@ -39,11 +39,11 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
 		if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
-			oif = inet->mc_index;
+			oif = READ_ONCE(inet->mc_index);
 		if (!saddr)
-			saddr = inet->mc_addr;
+			saddr = READ_ONCE(inet->mc_addr);
 	} else if (!oif) {
-		oif = inet->uc_index;
+		oif = READ_ONCE(inet->uc_index);
 	}
 	fl4 = &inet->cork.fl.u.ip4;
 	rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif,

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);
 
@@ -1387,8 +1387,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	struct ip_options *opt = NULL;
 	struct rtable *rt = (struct rtable *)cork->dst;
 	struct iphdr *iph;
+	u8 pmtudisc, ttl;
 	__be16 df = 0;
-	__u8 ttl;
 
 	skb = __skb_dequeue(queue);
 	if (!skb)
@@ -1418,8 +1418,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	/* DF bit is set when we want to see DF on outgoing frames.
 	 * If ignore_df is set too, we still allow to fragment this frame
 	 * locally. */
-	if (inet->pmtudisc == IP_PMTUDISC_DO ||
-	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
+	pmtudisc = READ_ONCE(inet->pmtudisc);
+	if (pmtudisc == IP_PMTUDISC_DO ||
+	    pmtudisc == IP_PMTUDISC_PROBE ||
 	    (skb->len <= dst_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
@@ -1430,14 +1431,14 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	if (cork->ttl != 0)
 		ttl = cork->ttl;
 	else if (rt->rt_type == RTN_MULTICAST)
-		ttl = inet->mc_ttl;
+		ttl = READ_ONCE(inet->mc_ttl);
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
 
 	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;