ipv6: lockless IPV6_MULTICAST_HOPS implementation

This fixes data-races around np->mcast_hops,
and make IPV6_MULTICAST_HOPS lockless.

Note that np->mcast_hops is never negative,
thus can fit an u8 field instead of s16.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 21 insertions, 25 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 68cf1ca94914..9cc278b5e4f4 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -214,15 +214,8 @@ struct ipv6_pinfo {
 	__u32			frag_size;
 
 	s16			hop_limit;
+	u8			mcast_hops;
 
-#if defined(__BIG_ENDIAN_BITFIELD)
-	/* Packed in 16bits. */
-	__s16			mcast_hops:9;
-	__u16			__unused_2:7,
-#else
-	__u16			__unused_2:7;
-	__s16			mcast_hops:9;
-#endif
 	int			ucast_oif;
 	int			mcast_oif;
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 2e8e7e31e02e..8a04a8985336 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -914,7 +914,7 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
 	int hlimit;
 
 	if (ipv6_addr_is_multicast(&fl6->daddr))
-		hlimit = np->mcast_hops;
+		hlimit = READ_ONCE(np->mcast_hops);
 	else
 		hlimit = READ_ONCE(np->hop_limit);
 	if (hlimit < 0)
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 33f6ccf6ba77..83617a16b98e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -676,7 +676,7 @@ ipv6_pktoptions:
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
 			np->mcast_oif = inet6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
-			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
+			WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit);
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
 		if (np->repflow)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 755fac85a120..5fff19a87c75 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -431,6 +431,16 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet6_assign_bit(MC6_LOOP, sk, valbool);
 		return 0;
+	case IPV6_MULTICAST_HOPS:
+		if (sk->sk_type == SOCK_STREAM)
+			return retv;
+		if (optlen < sizeof(int))
+			return -EINVAL;
+		if (val > 255 || val < -1)
+			return -EINVAL;
+		WRITE_ONCE(np->mcast_hops,
+			   val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
+		return 0;
 	}
 	if (needs_rtnl)
 		rtnl_lock();
@@ -751,16 +761,6 @@ done:
 		break;
 	}
 
-	case IPV6_MULTICAST_HOPS:
-		if (sk->sk_type == SOCK_STREAM)
-			break;
-		if (optlen < sizeof(int))
-			goto e_inval;
-		if (val > 255 || val < -1)
-			goto e_inval;
-		np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
-		retv = 0;
-		break;
 
 	case IPV6_UNICAST_IF:
 	{
@@ -1180,7 +1180,8 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxhlim) {
-				int hlim = np->mcast_hops;
+				int hlim = READ_ONCE(np->mcast_hops);
+
 				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
 			}
 			if (np->rxopt.bits.rxtclass) {
@@ -1197,7 +1198,8 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxohlim) {
-				int hlim = np->mcast_hops;
+				int hlim = READ_ONCE(np->mcast_hops);
+
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
 			}
 			if (np->rxopt.bits.rxflow) {
@@ -1349,7 +1351,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (optname == IPV6_UNICAST_HOPS)
 			val = READ_ONCE(np->hop_limit);
 		else
-			val = np->mcast_hops;
+			val = READ_ONCE(np->mcast_hops);
 
 		if (val < 0) {
 			rcu_read_lock();
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3a88545a265d..54db5fab318b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1542,7 +1542,8 @@ ipv6_pktoptions:
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
 			np->mcast_oif = tcp_v6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
-			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
+			WRITE_ONCE(np->mcast_hops,
+				   ipv6_hdr(opt_skb)->hop_limit);
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
 		if (np->repflow)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3c2251cabd04..df1b33b61059 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1322,7 +1322,7 @@ static void set_mcast_ttl(struct sock *sk, u_char ttl)
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		/* IPV6_MULTICAST_HOPS */
-		np->mcast_hops = ttl;
+		WRITE_ONCE(np->mcast_hops, ttl);
 	}
 #endif
 	release_sock(sk);