net: annotate data-races around sk->sk_priority

sk_getsockopt() runs locklessly. This means sk->sk_priority
can be read while other threads are changing its value.

Other reads also happen without socket lock being held.

Add missing annotations where needed.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 14 insertions, 13 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index f11e19c7edfb..6d4f28efe29a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -806,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger);
 void sock_set_priority(struct sock *sk, u32 priority)
 {
 	lock_sock(sk);
-	sk->sk_priority = priority;
+	WRITE_ONCE(sk->sk_priority, priority);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(sock_set_priority);
@@ -1216,7 +1216,7 @@ set_sndbuf:
 		if ((val >= 0 && val <= 6) ||
 		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
 		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
-			sk->sk_priority = val;
+			WRITE_ONCE(sk->sk_priority, val);
 		else
 			ret = -EPERM;
 		break;
@@ -1685,7 +1685,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PRIORITY:
-		v.val = sk->sk_priority;
+		v.val = READ_ONCE(sk->sk_priority);
 		break;
 
 	case SO_LINGER:
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bcdbf448324a..54d2d3a2d850 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -184,7 +184,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 		ip_options_build(skb, &opt->opt, daddr, rt);
 	}
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	if (!skb->mark)
 		skb->mark = READ_ONCE(sk->sk_mark);
 
@@ -528,7 +528,7 @@ packet_routed:
 			     skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
 
 	res = ip_local_out(net, sk, skb);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8e97d8d4cc9d..d41bce8927b2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -592,7 +592,7 @@ void __ip_sock_set_tos(struct sock *sk, int val)
 	}
 	if (inet_sk(sk)->tos != val) {
 		inet_sk(sk)->tos = val;
-		sk->sk_priority = rt_tos2priority(val);
+		WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
 		sk_dst_reset(sk);
 	}
 }
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7782ff5e6539..cb381f5aa464 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -348,7 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		goto error;
 	skb_reserve(skb, hlen);
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 894653be033a..a59cc4b83861 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -933,7 +933,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
 	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
-			   inet_twsk(sk)->tw_priority : sk->sk_priority;
+			   inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
 	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 39b7d727ba40..49381f35b623 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -614,7 +614,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb_reserve(skb, hlen);
 
 	skb->protocol = htons(ETH_P_IPV6);
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3ec563742ac4..6e86721e1cdb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1128,7 +1128,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
-			ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority,
+			ipv6_get_dsfield(ipv6_hdr(skb)), 0,
+			READ_ONCE(sk->sk_priority),
 			READ_ONCE(tcp_rsk(req)->txhash));
 }
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d9aa21a2b3a1..a4631cb457a9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2050,7 +2050,7 @@ retry:
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
 	skb->tstamp = sockc.transmit_time;
 
@@ -2585,7 +2585,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = po->sk.sk_priority;
+	skb->priority = READ_ONCE(po->sk.sk_priority);
 	skb->mark = READ_ONCE(po->sk.sk_mark);
 	skb->tstamp = sockc->transmit_time;
 	skb_setup_tx_timestamp(skb, sockc->tsflags);
@@ -3061,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc.mark;
 	skb->tstamp = sockc.transmit_time;