ipv4: adopt dst_dev, skb_dst_dev and skb_dst_dev_net[_rcu]

Use the new helpers as a first step to deal with
potential dst->dev races.

Signed-off-by: Eric Dumazet <[e-mail]>
Reviewed-by: Kuniyuki Iwashima <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/net/inet_hashtables.h

···
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct net *net = dev_net_rcu(skb_dst(skb)->dev);
+	struct net *net = skb_dst_dev_net_rcu(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct sock *sk;
 

include/net/ip.h

···
 
 	rcu_read_lock();
 
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding) {
···
 	if (mtu)
 		goto out;
 
-	mtu = READ_ONCE(dst->dev->mtu);
+	mtu = READ_ONCE(dst_dev(dst)->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
 		if (rt->rt_uses_gateway && mtu > 576)
···
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 					  const struct sk_buff *skb)
 {
+	const struct dst_entry *dst = skb_dst(skb);
 	unsigned int mtu;
 
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
-		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
+		return ip_dst_mtu_maybe_forward(dst, forwarding);
 	}
 
-	mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
-	return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
+	mtu = min(READ_ONCE(dst_dev(dst)->mtu), IP_MAX_MTU);
+	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
 struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len,

include/net/route.h

···
 		const struct net *net;
 
 		rcu_read_lock();
-		net = dev_net_rcu(dst->dev);
+		net = dev_net_rcu(dst_dev(dst));
 		hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 		rcu_read_unlock();
 	}

net/ipv4/icmp.c

···
 {
 	struct dst_entry *dst = &rt->dst;
 	struct inet_peer *peer;
+	struct net_device *dev;
 	bool rc = true;
 
 	if (!apply_ratelimit)
 		return true;
 
 	/* No rate limit on loopback */
-	if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
+	dev = dst_dev(dst);
+	if (dev && (dev->flags & IFF_LOOPBACK))
 		goto out;
 
 	rcu_read_lock();
 	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr,
-			       l3mdev_master_ifindex_rcu(dst->dev));
+			       l3mdev_master_ifindex_rcu(dev));
 	rc = inet_peer_xrlim_allow(peer,
 				   READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
 	rcu_read_unlock();
···
  */
 static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
 {
-	struct net_device *route_lookup_dev = NULL;
+	struct net_device *dev = skb->dev;
+	const struct dst_entry *dst;
 
-	if (skb->dev)
-		route_lookup_dev = skb->dev;
-	else if (skb_dst(skb))
-		route_lookup_dev = skb_dst(skb)->dev;
-	return route_lookup_dev;
+	if (dev)
+		return dev;
+	dst = skb_dst(skb);
+	return dst ? dst_dev(dst) : NULL;
 }
 
 static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
···
 	struct net *net;
 	u32 info = 0;
 
-	net = dev_net_rcu(skb_dst(skb)->dev);
+	net = skb_dst_dev_net_rcu(skb);
 
 	/*
 	 *	Incomplete header ?
···
 	struct icmp_bxm icmp_param;
 	struct net *net;
 
-	net = dev_net_rcu(skb_dst(skb)->dev);
+	net = skb_dst_dev_net_rcu(skb);
 	/* should there be an ICMP stat for ignored echos? */
 	if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
 		return SKB_NOT_DROPPED_YET;
···
 	return SKB_NOT_DROPPED_YET;
 
 out_err:
-	__ICMP_INC_STATS(dev_net_rcu(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
+	__ICMP_INC_STATS(skb_dst_dev_net_rcu(skb), ICMP_MIB_INERRORS);
 	return SKB_DROP_REASON_PKT_TOO_SMALL;
 }
 

net/ipv4/igmp.c

···
 
 	pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen);
 
-	return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
+	return ip_local_out(skb_dst_dev_net(skb), skb->sk, skb);
 }
 
 static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)

net/ipv4/ip_fragment.c

···
 /* Process an incoming IP datagram fragment. */
 int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
-	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
+	struct net_device *dev = skb->dev ? : skb_dst_dev(skb);
 	int vif = l3mdev_master_ifindex_rcu(dev);
 	struct ipq *qp;
 

net/ipv4/ip_output.c

···
 	skb->protocol = htons(ETH_P_IP);
 
 	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
-		       net, sk, skb, NULL, skb_dst(skb)->dev,
+		       net, sk, skb, NULL, skb_dst_dev(skb),
 		       dst_output);
 }
 
···
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct rtable *rt = dst_rtable(dst);
-	struct net_device *dev = dst->dev;
+	struct net_device *dev = dst_dev(dst);
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	bool is_v6gw = false;
···
 
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
+	struct net_device *dev = skb_dst_dev(skb), *indev = skb->dev;
 
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);

net/ipv4/ip_vti.c

···
 		goto tx_error_icmp;
 	}
 
-	tdev = dst->dev;
+	tdev = dst_dev(dst);
 
 	if (tdev == dev) {
 		dst_release(dst);
···
 xmit:
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
 	skb_dst_set(skb, dst);
-	skb->dev = skb_dst(skb)->dev;
+	skb->dev = skb_dst_dev(skb);
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)

net/ipv4/netfilter.c

···
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
 int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
 {
+	struct net_device *dev = skb_dst_dev(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
 	__u8 flags;
-	struct net_device *dev = skb_dst(skb)->dev;
 	struct flow_keys flkeys;
 	unsigned int hh_len;
 
···
 #endif
 
 	/* Change in oif may mean change in hh_len. */
-	hh_len = skb_dst(skb)->dev->hard_header_len;
+	hh_len = skb_dst_dev(skb)->hard_header_len;
 	if (skb_headroom(skb) < hh_len &&
 	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
 				0, GFP_ATOMIC))

net/ipv4/route.c

···
 					   const void *daddr)
 {
 	const struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
+	struct net_device *dev = dst_dev(dst);
 	struct neighbour *n;
 
 	rcu_read_lock();
···
 static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 {
 	const struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
+	struct net_device *dev = dst_dev(dst);
 	const __be32 *pkey = daddr;
 
 	if (rt->rt_gw_family == AF_INET) {
···
 		return;
 
 	rcu_read_lock();
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	if (mtu < net->ipv4.ip_rt_min_pmtu) {
 		lock = true;
 		mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
···
 	struct net *net;
 
 	rcu_read_lock();
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
 				   net->ipv4.ip_rt_min_advmss);
 	rcu_read_unlock();

net/ipv4/tcp_fastopen.c

···
 void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net_device *dev;
 	struct dst_entry *dst;
 	struct sk_buff *skb;
 
···
 	} else if (tp->syn_fastopen_ch &&
 		   atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
 		dst = sk_dst_get(sk);
-		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
+		dev = dst ? dst_dev(dst) : NULL;
+		if (!(dev && (dev->flags & IFF_LOOPBACK)))
 			atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
 		dst_release(dst);
 	}

net/ipv4/tcp_ipv4.c

···
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
-	net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
+	net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb);
 
 	/* Invalid TCP option size or twice included auth */
 	if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh))

net/ipv4/tcp_metrics.c

···
 					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
-	struct net *net;
 	bool reclaim = false;
+	struct net *net;
 
 	spin_lock_bh(&tcp_metrics_lock);
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 
 	/* While waiting for the spin-lock the cache might have been populated
 	 * with this entry and so we have to check again.
···
 		return NULL;
 	}
 
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 
···
 	else
 		return NULL;
 
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 

net/ipv4/xfrm4_output.c

···
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-			    net, sk, skb, skb->dev, skb_dst(skb)->dev,
+			    net, sk, skb, skb->dev, skb_dst_dev(skb),
 			    __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }