ipv6: lockless IPV6_UNICAST_HOPS implementation

Some np->hop_limit accesses are racy, when socket lock is not held.

Add missing annotations and switch to full lockless implementation.
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/linux/ipv6.h

@@ -213,17 +213,7 @@ struct ipv6_pinfo {
 	__be32			flow_label;
 	__u32			frag_size;
 
-	/*
-	 * Packed in 16bits.
-	 * Omit one shift by putting the signed field at MSB.
-	 */
-#if defined(__BIG_ENDIAN_BITFIELD)
-	__s16			hop_limit:9;
-	__u16			__unused_1:7;
-#else
-	__u16			__unused_1:7;
-	__s16			hop_limit:9;
-#endif
+	s16			hop_limit;
 
 #if defined(__BIG_ENDIAN_BITFIELD)
 	/* Packed in 16bits. */

include/net/ipv6.h

@@ -916,7 +916,7 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
 	if (ipv6_addr_is_multicast(&fl6->daddr))
 		hlimit = np->mcast_hops;
 	else
-		hlimit = np->hop_limit;
+		hlimit = READ_ONCE(np->hop_limit);
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 	return hlimit;

net/ipv6/ip6_output.c

@@ -309,7 +309,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	 *	Fill in the IPv6 header
 	 */
 	if (np)
-		hlimit = np->hop_limit;
+		hlimit = READ_ONCE(np->hop_limit);
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 

net/ipv6/ipv6_sockglue.c

@@ -415,6 +415,16 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_setsockopt(sk, optname, optval, optlen);
 
+	/* Handle options that can be set without locking the socket. */
+	switch (optname) {
+	case IPV6_UNICAST_HOPS:
+		if (optlen < sizeof(int))
+			return -EINVAL;
+		if (val > 255 || val < -1)
+			return -EINVAL;
+		WRITE_ONCE(np->hop_limit, val);
+		return 0;
+	}
 	if (needs_rtnl)
 		rtnl_lock();
 	sockopt_lock_sock(sk);
@@ -733,14 +743,6 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 	}
-	case IPV6_UNICAST_HOPS:
-		if (optlen < sizeof(int))
-			goto e_inval;
-		if (val > 255 || val < -1)
-			goto e_inval;
-		np->hop_limit = val;
-		retv = 0;
-		break;
 
 	case IPV6_MULTICAST_HOPS:
 		if (sk->sk_type == SOCK_STREAM)
@@ -1347,7 +1349,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		struct dst_entry *dst;
 
 		if (optname == IPV6_UNICAST_HOPS)
-			val = np->hop_limit;
+			val = READ_ONCE(np->hop_limit);
 		else
 			val = np->mcast_hops;
 

net/ipv6/mcast.c

@@ -1716,7 +1716,7 @@ static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb,
 
 	hdr->payload_len = htons(len);
 	hdr->nexthdr = proto;
-	hdr->hop_limit = inet6_sk(sk)->hop_limit;
+	hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit);
 
 	hdr->saddr = *saddr;
 	hdr->daddr = *daddr;

net/ipv6/ndisc.c

@@ -500,7 +500,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
 					      csum_partial(icmp6h,
 							   skb->len, 0));
 
-	ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len);
+	ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len);
 
 	rcu_read_lock();
 	idev = __in6_dev_get(dst->dev);