From db686880dcade127da4fb1a9462b669027469376 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Jul 2026 07:37:01 -0400 Subject: [PATCH] ipv4: adopt dst_dev, skb_dst_dev and skb_dst_dev_net[_rcu] [ Upstream commit a74fc62eec155ca5a6da8ff3856f3dc87fe24558 ] Use the new helpers as a first step to deal with potential dst->dev races. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250630121934.3399505-8-edumazet@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: c9c9b37f8c55 ("netfilter: nf_queue: pin bridge device while NFQUEUE holds fake dst") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/net/inet_hashtables.h | 2 +- include/net/ip.h | 11 ++++++----- include/net/route.h | 2 +- net/ipv4/icmp.c | 24 +++++++++++++----------- net/ipv4/igmp.c | 2 +- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_output.c | 4 ++-- net/ipv4/ip_vti.c | 4 ++-- net/ipv4/netfilter.c | 4 ++-- net/ipv4/route.c | 6 +++--- net/ipv4/tcp_fastopen.c | 4 +++- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_metrics.c | 8 ++++---- net/ipv4/xfrm4_output.c | 2 +- 14 files changed, 41 insertions(+), 36 deletions(-) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 03cb18838dcf..43317a06c86f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -356,7 +356,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, if (sk) return sk; - return __inet_lookup(dev_net_rcu(skb_dst(skb)->dev), hashinfo, skb, + return __inet_lookup(skb_dst_dev_net_rcu(skb), hashinfo, skb, doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), sdif, refcounted); diff --git a/include/net/ip.h b/include/net/ip.h index e1a93c339109..e25a2d5519c5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -441,7 +441,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net *net = dev_net(dst->dev); + struct net *net = dev_net(dst_dev(dst)); unsigned int mtu; if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || @@ -457,7 +457,7 @@ 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) @@ -473,16 +473,17 @@ 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 net *net, struct nlattr *fc_mx, diff --git a/include/net/route.h b/include/net/route.h index 39be632a9822..e05d549dbe3d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -358,7 +358,7 @@ 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(); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 9c363f44a694..49c94aebac32 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -318,6 +318,7 @@ 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; int vif; @@ -325,10 +326,11 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, goto out; /* 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; - vif = l3mdev_master_ifindex(dst->dev); + vif = l3mdev_master_ifindex(dev); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); rc = inet_peer_xrlim_allow(peer, READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); @@ -474,13 +476,13 @@ 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, @@ -882,7 +884,7 @@ static bool icmp_unreach(struct sk_buff *skb) struct net *net; u32 info = 0; - net = dev_net(skb_dst(skb)->dev); + net = skb_dst_dev_net(skb); /* * Incomplete header ? @@ -1023,7 +1025,7 @@ static bool icmp_echo(struct sk_buff *skb) struct icmp_bxm icmp_param; struct net *net; - net = dev_net(skb_dst(skb)->dev); + net = skb_dst_dev_net(skb); /* should there be an ICMP stat for ignored echos? */ if (net->ipv4.sysctl_icmp_echo_ignore_all) return true; @@ -1200,7 +1202,7 @@ static bool icmp_timestamp(struct sk_buff *skb) return true; out_err: - __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(skb_dst_dev_net(skb), ICMP_MIB_INERRORS); return false; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d25c5ef46e41..f47f3972f981 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -424,7 +424,7 @@ 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) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index ec2264adf2a6..23312d028af2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -475,7 +475,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, /* 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; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 5d8f8a5901bc..1d353f3c4403 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -113,7 +113,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) 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); } @@ -195,7 +195,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct 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; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 7487ceeda6e9..b1d4d59026cd 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -226,7 +226,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error_icmp; } - tdev = dst->dev; + tdev = dst_dev(dst); if (tdev == dev) { dst_release(dst); @@ -256,7 +256,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, 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) diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index aff707988e23..4d8ccc55ccc0 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -19,12 +19,12 @@ /* 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; @@ -74,7 +74,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un #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)) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f2edfa85223c..5b277e12f398 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -424,7 +424,7 @@ static struct neighbour *ipv4_neigh_lookup(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); struct neighbour *n; rcu_read_lock_bh(); @@ -451,7 +451,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, 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) { @@ -1074,7 +1074,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) 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); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e9b5d6f10c56..1c50867d3e7e 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -559,6 +559,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) 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; @@ -576,7 +577,8 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) } 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); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d35003b110e2..f7693166c516 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -718,7 +718,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) 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); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 882e58d51179..2b7230308ea9 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -166,11 +166,11 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, 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. @@ -273,7 +273,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, 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); @@ -318,7 +318,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, 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); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 3cff51ba72bb..0ae67d537499 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -31,7 +31,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) 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)); }