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 <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250630121934.3399505-8-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 833d4313bc1e ("mptcp: reset blackhole on success with non-loopback ifaces")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index da818fb0205fed6b4120946bc032e67e046b716f..3c4118c63cfe1bc4e20ef4a3620da8a1f403a348 100644 (file)
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -492,7 +492,7 @@ 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;
 

diff --git a/include/net/ip.h b/include/net/ip.h
index bd201278c55a58656e683cbfe32a421bf4524d28..5f0f1215d2f923bd02f16208edef04c5dddd2abd 100644 (file)
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -475,7 +475,7 @@ 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) {
@@ -489,7 +489,7 @@ 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)
@@ -509,16 +509,17 @@ out:
 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,

diff --git a/include/net/route.h b/include/net/route.h
index 8a11d19f897bb2787e9c5a8c575c57e404b6d60e..232b7bf55ba2219abbac60165c230e1e67573b4e 100644 (file)
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -369,7 +369,7 @@ 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 8f11870b77377d87eda3219dd7df13a5a2ba0b7c..508b23204edc5bd593e59b567225945913587b44 100644 (file)
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -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();
@@ -468,13 +470,13 @@ out_bh_enable:
  */
 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,
@@ -873,7 +875,7 @@ 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 ?
@@ -1016,7 +1018,7 @@ 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;
@@ -1186,7 +1188,7 @@ 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;
 }
 

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 9bf09de6a2e77c32f5eed565db8fd6c14bc7ea86..f4a87b90351e942deecddbe0a0293be862483569 100644 (file)
--- 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 9ca0a183a55ffad26df0af94464cb3df5b9e1abe..183856b0b74094a5b7c942408e9fac31160799a4 100644 (file)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -488,7 +488,7 @@ out_fail:
 /* 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 49811c9281d424bc4b43b8e9075da9fe724773cb..4d432e314bcb28039599f7556a83f10ee360f23d 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -117,7 +117,7 @@ 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);
 }
 
@@ -200,7 +200,7 @@ 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 = 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;
@@ -426,7 +426,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 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);

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f0b4419cef349329bf9ecad8d581111979786029..fc9516166307112d961883cc10e56abfb31a9622 100644 (file)
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -229,7 +229,7 @@ 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);
@@ -259,7 +259,7 @@ 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 e0aab66cd92511c921c08a9319a20c19e477a716..dff06b9eb6607fed7a29a7a77b625c5733bcac81 100644 (file)
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -20,12 +20,12 @@
 /* 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 261ddb6542a40fe28551a1064e523679c5c2b8b7..7d04df4fc66084b2a5fbff421574abe8751a2db3 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -413,7 +413,7 @@ 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();
@@ -440,7 +440,7 @@ 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) {
@@ -1025,7 +1025,7 @@ 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);
@@ -1323,7 +1323,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
        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();

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 408985eb74eeface6217691e48d84b8c0d3a95e6..86c995dc1c5e5b50205ef02a58671f0a1a0b381b 100644 (file)
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -558,6 +558,7 @@ 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;
 
@@ -575,7 +576,8 @@ 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 d8976753d4e47e0421d463c1d7792634ed2a5ee6..1572562b0498c9d825e2c67226d835c3aa941e33 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -786,7 +786,7 @@ 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);
 
        /* Invalid TCP option size or twice included auth */
        if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh))

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4251670e328c83b55eff7bbda3cc3d97d78563a8..03c068ea27b6ad3283b8365f31706c11ecdd07f2 100644 (file)
--- 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 3cff51ba72bb019d920554fa653937d729469b32..0ae67d537499a247c139a49e83f6f68dbc5114fa 100644 (file)
--- 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));
 }