net: implement lockless SO_PRIORITY

This is a followup of 8bf43be799d4 ("net: annotate data-races
around sk->sk_priority").

sk->sk_priority can be read and written without holding the socket lock.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

22 files changed, 34 insertions, 33 deletions

diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index c7236daa2415..9fa0b246902b 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -664,7 +664,7 @@ out_unlock:
 
 sendit:
 	if (skb->sk)
-		skb->priority = skb->sk->sk_priority;
+		skb->priority = READ_ONCE(skb->sk->sk_priority);
 	if (dev_queue_xmit(skb))
 		goto drop;
 sent:
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 5db805d5f74d..558e158c98d0 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -939,7 +939,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev)
 	sock_init_data(NULL, sk);
 
 	sk->sk_type     = osk->sk_type;
-	sk->sk_priority = osk->sk_priority;
+	sk->sk_priority = READ_ONCE(osk->sk_priority);
 	sk->sk_protocol = osk->sk_protocol;
 	sk->sk_rcvbuf   = osk->sk_rcvbuf;
 	sk->sk_sndbuf   = osk->sk_sndbuf;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 3bdfc3f1e73d..e50d3d102078 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1615,7 +1615,7 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
 		return ERR_PTR(-ENOTCONN);
 	}
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 
 	bt_cb(skb)->l2cap.chan = chan;
 
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index b28c976f52a0..14c431663233 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -884,7 +884,7 @@ static struct sk_buff *j1939_sk_alloc_skb(struct net_device *ndev,
 	skcb = j1939_skb_to_cb(skb);
 	memset(skcb, 0, sizeof(*skcb));
 	skcb->addr = jsk->addr;
-	skcb->priority = j1939_prio(sk->sk_priority);
+	skcb->priority = j1939_prio(READ_ONCE(sk->sk_priority));
 
 	if (msg->msg_name) {
 		struct sockaddr_can *addr = msg->msg_name;
diff --git a/net/can/raw.c b/net/can/raw.c
index d50c3f3d892f..73468d2ebd51 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -881,7 +881,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	}
 
 	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;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index a5995750c5c5..1fdc0a0d8ff2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -806,9 +806,7 @@ EXPORT_SYMBOL(sock_no_linger);
 
 void sock_set_priority(struct sock *sk, u32 priority)
 {
-	lock_sock(sk);
 	WRITE_ONCE(sk->sk_priority, priority);
-	release_sock(sk);
 }
 EXPORT_SYMBOL(sock_set_priority);
 
@@ -1118,6 +1116,18 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 
 	valbool = val ? 1 : 0;
 
+	/* handle options which do not require locking the socket. */
+	switch (optname) {
+	case SO_PRIORITY:
+		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)) {
+			sock_set_priority(sk, val);
+			return 0;
+		}
+		return -EPERM;
+	}
+
 	sockopt_lock_sock(sk);
 
 	switch (optname) {
@@ -1213,15 +1223,6 @@ set_sndbuf:
 		sk->sk_no_check_tx = valbool;
 		break;
 
-	case SO_PRIORITY:
-		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))
-			WRITE_ONCE(sk->sk_priority, val);
-		else
-			ret = -EPERM;
-		break;
-
 	case SO_LINGER:
 		if (optlen < sizeof(ling)) {
 			ret = -EINVAL;	/* 1003.1g */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 80b956b39252..8d344b219f84 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -239,7 +239,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 		if (!opt)
 			opt = rcu_dereference(np->opt);
 		err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt,
-			       np->tclass, sk->sk_priority);
+			       np->tclass, READ_ONCE(sk->sk_priority));
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e13a84433413..9f0bd518901a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -165,7 +165,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 		 * For cgroup2 classid is always zero.
 		 */
 		if (!classid)
-			classid = sk->sk_priority;
+			classid = READ_ONCE(sk->sk_priority);
 
 		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
 			goto errout;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4ab877cf6d35..6b14097e80ad 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1449,7 +1449,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 		ip_options_build(skb, opt, cork->addr, rt);
 	}
 
-	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
+	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
 	skb->mark = cork->mark;
 	skb->tstamp = cork->transmit_time;
 	/*
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f13eb7e23d03..95e972be0c05 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -828,7 +828,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		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;
+				   inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
 		transmit_time = tcp_transmit_time(sk);
 		xfrm_sk_clone_policy(ctl_sk, sk);
 		txhash = (sk->sk_state == TCP_TIME_WAIT) ?
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index eee8ab1bfa0e..3f87611077ef 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -292,7 +292,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 
 		tw->tw_transparent	= inet_test_bit(TRANSPARENT, sk);
 		tw->tw_mark		= sk->sk_mark;
-		tw->tw_priority		= sk->sk_priority;
+		tw->tw_priority		= READ_ONCE(sk->sk_priority);
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 0c50dcd35fe8..80043e46117c 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -133,7 +133,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	fl6.daddr = sk->sk_v6_daddr;
 
 	res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       np->tclass,  sk->sk_priority);
+		       np->tclass, READ_ONCE(sk->sk_priority));
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 951ba8089b5b..cdaa9275e990 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1984,7 +1984,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
 	skb->tstamp = cork->base.transmit_time;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 94afb8d0f2d0..8a6e2e97f673 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -565,7 +565,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (!opt)
 			opt = rcu_dereference(np->opt);
 		err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark),
-			       opt, tclass, sk->sk_priority);
+			       opt, tclass, READ_ONCE(sk->sk_priority));
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -1058,7 +1058,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 			trace_tcp_send_reset(sk, skb);
 			if (inet6_test_bit(REPFLOW, sk))
 				label = ip6_flowlabel(ipv6h);
-			priority = sk->sk_priority;
+			priority = READ_ONCE(sk->sk_priority);
 			txhash = sk->sk_txhash;
 		}
 		if (sk->sk_state == TCP_TIME_WAIT) {
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 8260202c0066..f3485a6b35e7 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -89,7 +89,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in
 			sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val);
 			break;
 		case SO_PRIORITY:
-			ssk->sk_priority = val;
+			WRITE_ONCE(ssk->sk_priority, val);
 			break;
 		case SO_SNDBUF:
 		case SO_SNDBUFFORCE:
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 96e91ab71573..0eed00184adf 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -487,7 +487,7 @@ static struct sock *nr_make_new(struct sock *osk)
 	sock_init_data(NULL, sk);
 
 	sk->sk_type     = osk->sk_type;
-	sk->sk_priority = osk->sk_priority;
+	sk->sk_priority = READ_ONCE(osk->sk_priority);
 	sk->sk_protocol = osk->sk_protocol;
 	sk->sk_rcvbuf   = osk->sk_rcvbuf;
 	sk->sk_sndbuf   = osk->sk_sndbuf;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 49dafe9ac72f..0cc5a4e19900 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -583,7 +583,7 @@ static struct sock *rose_make_new(struct sock *osk)
 #endif
 
 	sk->sk_type     = osk->sk_type;
-	sk->sk_priority = osk->sk_priority;
+	sk->sk_priority = READ_ONCE(osk->sk_priority);
 	sk->sk_protocol = osk->sk_protocol;
 	sk->sk_rcvbuf   = osk->sk_rcvbuf;
 	sk->sk_sndbuf   = osk->sk_sndbuf;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index da34fd4c9269..09d8afd04a2a 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -546,7 +546,7 @@ META_COLLECTOR(int_sk_prio)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_priority;
+	dst->value = READ_ONCE(sk->sk_priority);
 }
 
 META_COLLECTOR(int_sk_rcvlowat)
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 5c0ed5909d85..24368f755ab1 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -247,7 +247,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
 		rcu_read_lock();
 		res = ip6_xmit(sk, skb, fl6, sk->sk_mark,
 			       rcu_dereference(np->opt),
-			       tclass, sk->sk_priority);
+			       tclass, READ_ONCE(sk->sk_priority));
 		rcu_read_unlock();
 		return res;
 	}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index bacdd971615e..297681601414 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -493,7 +493,7 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
 	nsk->sk_sndtimeo = osk->sk_sndtimeo;
 	nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
 	nsk->sk_mark = READ_ONCE(osk->sk_mark);
-	nsk->sk_priority = osk->sk_priority;
+	nsk->sk_priority = READ_ONCE(osk->sk_priority);
 	nsk->sk_rcvlowat = osk->sk_rcvlowat;
 	nsk->sk_bound_dev_if = osk->sk_bound_dev_if;
 	nsk->sk_err = osk->sk_err;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 0fb5143bec7a..aad8ffeaee04 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -598,7 +598,7 @@ static struct sock *x25_make_new(struct sock *osk)
 	x25 = x25_sk(sk);
 
 	sk->sk_type        = osk->sk_type;
-	sk->sk_priority    = osk->sk_priority;
+	sk->sk_priority    = READ_ONCE(osk->sk_priority);
 	sk->sk_protocol    = osk->sk_protocol;
 	sk->sk_rcvbuf      = osk->sk_rcvbuf;
 	sk->sk_sndbuf      = osk->sk_sndbuf;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 7482d0aca504..f5e96e0d6e01 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -684,7 +684,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	}
 
 	skb->dev = dev;
-	skb->priority = xs->sk.sk_priority;
+	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
 	xsk_set_destructor_arg(skb);