net: dst: add four helpers to annotate data-races around dst->dev

[ Upstream commit 88fe14253e181878c2ddb51a298ae8c468a63010 ]

dst->dev is read locklessly in many contexts,
and written in dst_dev_put().

Fixing all the races is going to need many changes.

We probably will have to add full RCU protection.

Add three helpers to ease this painful process.

static inline struct net_device *dst_dev(const struct dst_entry *dst)
{
       return READ_ONCE(dst->dev);
}

static inline struct net_device *skb_dst_dev(const struct sk_buff *skb)
{
       return dst_dev(skb_dst(skb));
}

static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)
{
       return dev_net(skb_dst_dev(skb));
}

static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb)
{
       return dev_net_rcu(skb_dst_dev(skb));
}

Fixes: 4a6ce2b6f2ec ("net: introduce a new function dst_dev_put()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250630121934.3399505-7-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/dst.h b/include/net/dst.h
index e18826cd05595299f057ccb8c00aafb15bcd5d7e..23ee8139a75630e56064d0ebbbb74a385dac4889 100644 (file)
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -561,6 +561,26 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
                dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 }
 
+static inline struct net_device *dst_dev(const struct dst_entry *dst)
+{
+       return READ_ONCE(dst->dev);
+}
+
+static inline struct net_device *skb_dst_dev(const struct sk_buff *skb)
+{
+       return dst_dev(skb_dst(skb));
+}
+
+static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)
+{
+       return dev_net(skb_dst_dev(skb));
+}
+
+static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb)
+{
+       return dev_net_rcu(skb_dst_dev(skb));
+}
+
 struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
 void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
                               struct sk_buff *skb, u32 mtu, bool confirm_neigh);

diff --git a/net/core/dst.c b/net/core/dst.c
index cc990706b64515ebe387befbe77d75153479a4bb..9a0ddef8bee43042bfcdb40b72602ae69521a6dd 100644 (file)
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -150,7 +150,7 @@ void dst_dev_put(struct dst_entry *dst)
                dst->ops->ifdown(dst, dev);
        WRITE_ONCE(dst->input, dst_discard);
        WRITE_ONCE(dst->output, dst_discard_out);
-       dst->dev = blackhole_netdev;
+       WRITE_ONCE(dst->dev, blackhole_netdev);
        netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker,
                           GFP_ATOMIC);
 }
@@ -263,7 +263,7 @@ unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
 {
        unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
-       return mtu ? : dst->dev->mtu;
+       return mtu ? : dst_dev(dst)->mtu;
 }
 EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
 

diff --git a/net/core/sock.c b/net/core/sock.c
index b5723adab4ebf740cec7adf1ab50eda94e0a1684..a5f248a91404267c597930c41117887f8d910007 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2534,8 +2534,8 @@ static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst)
                   !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr));
 #endif
        /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
-       max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) :
-                       READ_ONCE(dst->dev->gso_ipv4_max_size);
+       max_size = is_ipv6 ? READ_ONCE(dst_dev(dst)->gso_max_size) :
+                       READ_ONCE(dst_dev(dst)->gso_ipv4_max_size);
        if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk))
                max_size = GSO_LEGACY_MAX_SIZE;
 
@@ -2546,7 +2546,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
        u32 max_segs = 1;
 
-       sk->sk_route_caps = dst->dev->features;
+       sk->sk_route_caps = dst_dev(dst)->features;
        if (sk_is_tcp(sk)) {
                struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -2564,7 +2564,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
                        sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
                        sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst);
                        /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
-                       max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
+                       max_segs = max_t(u32, READ_ONCE(dst_dev(dst)->gso_max_segs), 1);
                }
        }
        sk->sk_gso_max_segs = max_segs;