ipv6: lockless IPV6_DONTFRAG implementation

Move np->dontfrag flag to inet->inet_flags to fix data-races.

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

11 files changed, 16 insertions, 17 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index e3be5dc21b7d..57d563f1d4b1 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -252,7 +252,6 @@ struct ipv6_pinfo {
 						 * 010: prefer public address
 						 * 100: prefer care-of address
 						 */
-				dontfrag:1,
 				rtalert_isolate:1;
 	__u8			min_hopcount;
 	__u8			tclass;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index f1af64a40673..ac75324e9e1e 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -273,6 +273,7 @@ enum {
 	INET_FLAGS_MC6_ALL	= 22,
 	INET_FLAGS_AUTOFLOWLABEL_SET = 23,
 	INET_FLAGS_AUTOFLOWLABEL = 24,
+	INET_FLAGS_DONTFRAG	= 25,
 };
 
 /* cmsg flags for inet */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4b6cbec059e2..5a1f2993680d 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -373,12 +373,12 @@ static inline void ipcm6_init(struct ipcm6_cookie *ipc6)
 }
 
 static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6,
-				 const struct ipv6_pinfo *np)
+				 const struct sock *sk)
 {
 	*ipc6 = (struct ipcm6_cookie) {
 		.hlimit = -1,
-		.tclass = np->tclass,
-		.dontfrag = np->dontfrag,
+		.tclass = inet6_sk(sk)->tclass,
+		.dontfrag = inet6_test_bit(DONTFRAG, sk),
 	};
 }
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 363c7d510554..98d7aa78adda 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2166,7 +2166,7 @@ static inline bool xfrm6_local_dontfrag(const struct sock *sk)
 
 	proto = sk->sk_protocol;
 	if (proto == IPPROTO_UDP || proto == IPPROTO_RAW)
-		return inet6_sk(sk)->dontfrag;
+		return inet6_test_bit(DONTFRAG, sk);
 
 	return false;
 }
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 93a594a901d1..8fb4a791881a 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -588,7 +588,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	ipcm6_init_sk(&ipc6, np);
+	ipcm6_init_sk(&ipc6, sk);
 	ipc6.sockc.mark = mark;
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
@@ -791,7 +791,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 	msg.offset = 0;
 	msg.type = type;
 
-	ipcm6_init_sk(&ipc6, np);
+	ipcm6_init_sk(&ipc6, sk);
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 	ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
 	ipc6.sockc.mark = mark;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 47aa42f93ccd..8851fe5d45a0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -2092,7 +2092,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 		return ERR_PTR(err);
 	}
 	if (ipc6->dontfrag < 0)
-		ipc6->dontfrag = inet6_sk(sk)->dontfrag;
+		ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk);
 
 	err = __ip6_append_data(sk, &queue, cork, &v6_cork,
 				&current->task_frag, getfrag, from,
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d5d428a695f7..33dd4dd872e6 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -478,6 +478,9 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		inet6_assign_bit(AUTOFLOWLABEL, sk, valbool);
 		inet6_set_bit(AUTOFLOWLABEL_SET, sk);
 		return 0;
+	case IPV6_DONTFRAG:
+		inet6_assign_bit(DONTFRAG, sk, valbool);
+		return 0;
 	}
 	if (needs_rtnl)
 		rtnl_lock();
@@ -970,10 +973,6 @@ done:
 			goto e_inval;
 		retv = __ip6_sock_set_addr_preferences(sk, val);
 		break;
-	case IPV6_DONTFRAG:
-		np->dontfrag = valbool;
-		retv = 0;
-		break;
 	case IPV6_RECVFRAGSIZE:
 		np->rxopt.bits.recvfragsize = valbool;
 		retv = 0;
@@ -1442,7 +1441,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_DONTFRAG:
-		val = np->dontfrag;
+		val = inet6_test_bit(DONTFRAG, sk);
 		break;
 
 	case IPV6_AUTOFLOWLABEL:
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 5831aaa53d75..4444b61eb23b 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -118,7 +118,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	     l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if))
 		return -EINVAL;
 
-	ipcm6_init_sk(&ipc6, np);
+	ipcm6_init_sk(&ipc6, sk);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 42fcec3ecf5e..cc9673c1809f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -898,7 +898,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = np->dontfrag;
+		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
 
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f60ba4295435..e4301500741a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1595,7 +1595,7 @@ back_from_confirm:
 
 do_append_data:
 	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = np->dontfrag;
+		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
 	up->len += ulen;
 	err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
 			      &ipc6, fl6, (struct rt6_info *)dst,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ed8ebb6f5909..40af2431e73a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -621,7 +621,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = np->dontfrag;
+		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
 
 	if (msg->msg_flags & MSG_CONFIRM)
 		goto do_confirm;