ipv6: lockless IPV6_MTU_DISCOVER implementation

Most np->pmtudisc reads are racy.

Move this 3bit field on a full byte, add annotations
and make IPV6_MTU_DISCOVER setsockopt() lockless.

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

7 files changed, 24 insertions, 22 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f288a35f157f..10f521a6a9c8 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -243,13 +243,12 @@ struct ipv6_pinfo {
 	} rxopt;
 
 	/* sockopt flags */
-	__u16			sndflow:1,
-				pmtudisc:3,
-				padding:1,	/* 1 bit hole */
+	__u8			sndflow:1,
 				srcprefs:3;	/* 001: prefer temporary address
 						 * 010: prefer public address
 						 * 100: prefer care-of address
 						 */
+	__u8			pmtudisc;
 	__u8			min_hopcount;
 	__u8			tclass;
 	__be32			rcv_flowinfo;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index b32539bb0fb0..b1ea49900b4a 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -266,7 +266,7 @@ static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb)
 	const struct dst_entry *dst = skb_dst(skb);
 	unsigned int mtu;
 
-	if (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) {
+	if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) {
 		mtu = READ_ONCE(dst->dev->mtu);
 		mtu -= lwtunnel_headroom(dst->lwtstate, mtu);
 	} else {
@@ -277,14 +277,18 @@ static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb)
 
 static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
 {
-	return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE &&
-	       inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc);
+
+	return pmtudisc != IPV6_PMTUDISC_INTERFACE &&
+	       pmtudisc != IPV6_PMTUDISC_OMIT;
 }
 
 static inline bool ip6_sk_ignore_df(const struct sock *sk)
 {
-	return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO ||
-	       inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc);
+
+	return pmtudisc < IPV6_PMTUDISC_DO ||
+	       pmtudisc == IPV6_PMTUDISC_OMIT;
 }
 
 static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f87d8491d7e2..7e5d9eeb990f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1436,10 +1436,10 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	v6_cork->hop_limit = ipc6->hlimit;
 	v6_cork->tclass = ipc6->tclass;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
 	else
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 			READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
 
 	frag_size = READ_ONCE(np->frag_size);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index c22a492e0536..85ea42644dcb 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -493,6 +493,13 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		inet6_assign_bit(RTALERT_ISOLATE, sk, valbool);
 		return 0;
+	case IPV6_MTU_DISCOVER:
+		if (optlen < sizeof(int))
+			return -EINVAL;
+		if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
+			return -EINVAL;
+		WRITE_ONCE(np->pmtudisc, val);
+		return 0;
 	}
 	if (needs_rtnl)
 		rtnl_lock();
@@ -941,14 +948,6 @@ done:
 			goto e_inval;
 		retv = ip6_ra_control(sk, val);
 		break;
-	case IPV6_MTU_DISCOVER:
-		if (optlen < sizeof(int))
-			goto e_inval;
-		if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
-			goto e_inval;
-		np->pmtudisc = val;
-		retv = 0;
-		break;
 	case IPV6_FLOWINFO_SEND:
 		if (optlen < sizeof(int))
 			goto e_inval;
@@ -1374,7 +1373,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_MTU_DISCOVER:
-		val = np->pmtudisc;
+		val = READ_ONCE(np->pmtudisc);
 		break;
 
 	case IPV6_RECVERR:
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 71f6bdccfa1f..47372cceb98f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -307,7 +307,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
 	harderr = icmpv6_err_convert(type, code, &err);
 	if (type == ICMPV6_PKT_TOOBIG) {
 		ip6_sk_update_pmtu(skb, sk, info);
-		harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
+		harderr = (READ_ONCE(np->pmtudisc) == IPV6_PMTUDISC_DO);
 	}
 	if (type == NDISC_REDIRECT) {
 		ip6_sk_redirect(skb, sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 90e873689b88..c17e19fece1b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -598,7 +598,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (!ip6_sk_accept_pmtu(sk))
 			goto out;
 		ip6_sk_update_pmtu(skb, sk, info);
-		if (np->pmtudisc != IPV6_PMTUDISC_DONT)
+		if (READ_ONCE(np->pmtudisc) != IPV6_PMTUDISC_DONT)
 			harderr = 1;
 	}
 	if (type == NDISC_REDIRECT) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index df1b33b61059..5820a8156c47 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1341,7 +1341,7 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		/* IPV6_MTU_DISCOVER */
-		np->pmtudisc = val;
+		WRITE_ONCE(np->pmtudisc, val);
 	}
 #endif
 	release_sock(sk);