Commit a74fc62e authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

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: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250630121934.3399505-8-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 88fe1425

include/net/inet_hashtables.h

+1 −1
Original line number Diff line number Diff line
@@ -481,7 +481,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, 
					     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

+6 −5
Original line number Diff line number Diff line
@@ -472,7 +472,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, 


	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) {
@@ -486,7 +486,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, 
	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)
@@ -506,16 +506,17 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, 
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

+1 −1
Original line number Diff line number Diff line
@@ -390,7 +390,7 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) 
		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

+13 −11
Original line number Diff line number Diff line
@@ -311,18 +311,20 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, 
{

	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();
@@ -466,13 +468,13 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) 
 */

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,
@@ -869,7 +871,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) 
	struct net *net;

	u32 info = 0;



	net = dev_net_rcu(skb_dst(skb)->dev);

	net = skb_dst_dev_net_rcu(skb);



	/*

	 *	Incomplete header ?
@@ -1012,7 +1014,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) 
	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;
@@ -1182,7 +1184,7 @@ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) 
	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

+1 −1
Original line number Diff line number Diff line
@@ -427,7 +427,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) 


	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)