Merge branch 'net-data-races'

Eric Dumazet says:

====================
net: annotate data-races

This series was inspired by a syzbot/KCSAN report.

This will later also permit some optimizations,
like not having to lock the socket while reading/writing
some of its fields.
====================

Signed-off-by: David S. Miller <[email protected]>

include/net/inet_sock.h

@@ -107,11 +107,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 
 static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 {
-	if (!sk->sk_mark &&
-	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
+	u32 mark = READ_ONCE(sk->sk_mark);
+
+	if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
 		return skb->mark;
 
-	return sk->sk_mark;
+	return mark;
 }
 
 static inline int inet_request_bound_dev_if(const struct sock *sk,

include/net/ip.h

@@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 {
 	ipcm_init(ipcm);
 
-	ipcm->sockc.mark = inet->sk.sk_mark;
+	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
 	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;

include/net/route.h

@@ -168,7 +168,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
 {
-	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
+	flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos,
 			   RT_SCOPE_UNIVERSE, proto,
 			   sk ? inet_sk_flowi_flags(sk) : 0,
 			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
@@ -301,7 +301,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 	if (inet_sk(sk)->transparent)
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
-	flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk),
+	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
 			   src, dport, sport, sk->sk_uid);
 }

net/can/raw.c

@@ -865,7 +865,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
-	skb->mark = sk->sk_mark;
+	skb->mark = READ_ONCE(sk->sk_mark);
 	skb->tstamp = sockc.transmit_time;
 
 	skb_setup_tx_timestamp(skb, sockc.tsflags);

net/core/sock.c

@@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 {
 	struct __kernel_sock_timeval tv;
 	int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval);
+	long val;
 
 	if (err)
 		return err;
@@ -439,19 +440,20 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 	if (tv.tv_sec < 0) {
 		static int warned __read_mostly;
 
-		*timeo_p = 0;
+		WRITE_ONCE(*timeo_p, 0);
 		if (warned < 10 && net_ratelimit()) {
 			warned++;
 			pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
 				__func__, current->comm, task_pid_nr(current));
 		}
 		return 0;
 	}
-	*timeo_p = MAX_SCHEDULE_TIMEOUT;
-	if (tv.tv_sec == 0 && tv.tv_usec == 0)
-		return 0;
-	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
-		*timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
+	val = MAX_SCHEDULE_TIMEOUT;
+	if ((tv.tv_sec || tv.tv_usec) &&
+	    (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)))
+		val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec,
+						    USEC_PER_SEC / HZ);
+	WRITE_ONCE(*timeo_p, val);
 	return 0;
 }
 
@@ -804,7 +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);
@@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs)
 {
 	lock_sock(sk);
 	if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
-		sk->sk_sndtimeo = secs * HZ;
+		WRITE_ONCE(sk->sk_sndtimeo, secs * HZ);
 	else
-		sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+		WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(sock_set_sndtimeo);
@@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf);
 static void __sock_set_mark(struct sock *sk, u32 val)
 {
 	if (val != sk->sk_mark) {
-		sk->sk_mark = val;
+		WRITE_ONCE(sk->sk_mark, val);
 		sk_dst_reset(sk);
 	}
 }
@@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes)
 	bytes = round_down(bytes, PAGE_SIZE);
 
 	WARN_ON(bytes > sk->sk_reserved_mem);
-	sk->sk_reserved_mem -= bytes;
+	WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes);
 	sk_mem_reclaim(sk);
 }
 
@@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	}
 	sk->sk_forward_alloc += pages << PAGE_SHIFT;
 
-	sk->sk_reserved_mem += pages << PAGE_SHIFT;
+	WRITE_ONCE(sk->sk_reserved_mem,
+		   sk->sk_reserved_mem + (pages << PAGE_SHIFT));
 
 	return 0;
 }
@@ -1213,7 +1216,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		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;
@@ -1438,7 +1441,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 			cmpxchg(&sk->sk_pacing_status,
 				SK_PACING_NONE,
 				SK_PACING_NEEDED);
-		sk->sk_max_pacing_rate = ulval;
+		/* Pairs with READ_ONCE() from sk_getsockopt() */
+		WRITE_ONCE(sk->sk_max_pacing_rate, ulval);
 		sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
 		break;
 		}
@@ -1533,7 +1537,9 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		}
 		if ((u8)val == SOCK_TXREHASH_DEFAULT)
 			val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-		/* Paired with READ_ONCE() in tcp_rtx_synack() */
+		/* Paired with READ_ONCE() in tcp_rtx_synack()
+		 * and sk_getsockopt().
+		 */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		break;
 
@@ -1633,11 +1639,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_SNDBUF:
-		v.val = sk->sk_sndbuf;
+		v.val = READ_ONCE(sk->sk_sndbuf);
 		break;
 
 	case SO_RCVBUF:
-		v.val = sk->sk_rcvbuf;
+		v.val = READ_ONCE(sk->sk_rcvbuf);
 		break;
 
 	case SO_REUSEADDR:
@@ -1679,7 +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:
@@ -1717,16 +1723,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 	case SO_RCVTIMEO_OLD:
 	case SO_RCVTIMEO_NEW:
-		lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
+		lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v,
+				      SO_RCVTIMEO_OLD == optname);
 		break;
 
 	case SO_SNDTIMEO_OLD:
 	case SO_SNDTIMEO_NEW:
-		lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
+		lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v,
+				      SO_SNDTIMEO_OLD == optname);
 		break;
 
 	case SO_RCVLOWAT:
-		v.val = sk->sk_rcvlowat;
+		v.val = READ_ONCE(sk->sk_rcvlowat);
 		break;
 
 	case SO_SNDLOWAT:
@@ -1843,7 +1851,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 							 optval, optlen, len);
 
 	case SO_MARK:
-		v.val = sk->sk_mark;
+		v.val = READ_ONCE(sk->sk_mark);
 		break;
 
 	case SO_RCVMARK:
@@ -1862,7 +1870,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		if (!sock->ops->set_peek_off)
 			return -EOPNOTSUPP;
 
-		v.val = sk->sk_peek_off;
+		v.val = READ_ONCE(sk->sk_peek_off);
 		break;
 	case SO_NOFCS:
 		v.val = sock_flag(sk, SOCK_NOFCS);
@@ -1892,20 +1900,22 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
-		v.val = sk->sk_ll_usec;
+		v.val = READ_ONCE(sk->sk_ll_usec);
 		break;
 	case SO_PREFER_BUSY_POLL:
 		v.val = READ_ONCE(sk->sk_prefer_busy_poll);
 		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
+		/* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */
 		if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
 			lv = sizeof(v.ulval);
-			v.ulval = sk->sk_max_pacing_rate;
+			v.ulval = READ_ONCE(sk->sk_max_pacing_rate);
 		} else {
 			/* 32bit version */
-			v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
+			v.val = min_t(unsigned long, ~0U,
+				      READ_ONCE(sk->sk_max_pacing_rate));
 		}
 		break;
 
@@ -1973,11 +1983,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_RESERVE_MEM:
-		v.val = sk->sk_reserved_mem;
+		v.val = READ_ONCE(sk->sk_reserved_mem);
 		break;
 
 	case SO_TXREHASH:
-		v.val = sk->sk_txrehash;
+		/* Paired with WRITE_ONCE() in sk_setsockopt() */
+		v.val = READ_ONCE(sk->sk_txrehash);
 		break;
 
 	default:
@@ -3168,7 +3179,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim);
 
 int sk_set_peek_off(struct sock *sk, int val)
 {
-	sk->sk_peek_off = val;
+	WRITE_ONCE(sk->sk_peek_off, val);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sk_set_peek_off);

net/dccp/ipv6.c

@@ -238,8 +238,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass,
-			       sk->sk_priority);
+		err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt,
+			       np->tclass, sk->sk_priority);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}

net/ipv4/inet_diag.c

@@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
-	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
+	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark)))
 		goto errout;
 
 	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
@@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry.ifindex = sk->sk_bound_dev_if;
 	entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
 	if (sk_fullsock(sk))
-		entry.mark = sk->sk_mark;
+		entry.mark = READ_ONCE(sk->sk_mark);
 	else if (sk->sk_state == TCP_NEW_SYN_RECV)
 		entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
 	else if (sk->sk_state == TCP_TIME_WAIT)

net/ipv4/ip_output.c

@@ -184,9 +184,9 @@ 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 = sk->sk_mark;
+		skb->mark = READ_ONCE(sk->sk_mark);
 
 	/* Send it out. */
 	return ip_local_out(net, skb->sk, skb);
@@ -528,8 +528,8 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 			     skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
-	skb->priority = sk->sk_priority;
-	skb->mark = sk->sk_mark;
+	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->mark = READ_ONCE(sk->sk_mark);
 
 	res = ip_local_out(net, sk, skb);
 	rcu_read_unlock();

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);
 	}
 }

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);

net/ipv4/route.c

@@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 		const struct inet_sock *inet = inet_sk(sk);
 
 		oif = sk->sk_bound_dev_if;
-		mark = sk->sk_mark;
+		mark = READ_ONCE(sk->sk_mark);
 		tos = ip_sock_rt_tos(sk);
 		scope = ip_sock_rt_scope(sk);
 		prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
@@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
 			   ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
 			   ip_sock_rt_scope(sk),
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,

net/ipv4/tcp_ipv4.c

@@ -931,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk = this_cpu_read(ipv4_tcp_sk);
 	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
-			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+			   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,

net/ipv6/ping.c

@@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	ipcm6_init_sk(&ipc6, np);
 	ipc6.sockc.tsflags = sk->sk_tsflags;
-	ipc6.sockc.mark = sk->sk_mark;
+	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
 	fl6.flowi6_oif = oif;