[PATCH 5.15.y 2/3] net: dst: introduce dst->dev_rcu

[Sasha Levin <sashal@kernel.org>]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit caedcc5b6df1b2e2b5f39079e3369c1d4d5c5f50 ]

Followup of commit 88fe14253e18 ("net: dst: add four helpers
to annotate data-races around dst->dev").

We want to gradually add explicit RCU protection to dst->dev,
including lockdep support.

Add an union to alias dst->dev_rcu and dst->dev.

Add dst_dev_net_rcu() helper.

Fixes: 4a6ce2b6f2ec ("net: introduce a new function dst_dev_put()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250828195823.3958522-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 2640e6419594 ("net: advertise TCP MSS from the configured MTU, not the learned PMTU")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/dst.h | 11 ++++++-----
 include/net/ip.h  | 15 +++++++++++----
 net/core/dst.c    |  2 +-
 net/ipv4/route.c  |  2 +-
 4 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 9de6b49cfd3dd..0b30871014742 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -23,7 +23,10 @@
 struct sk_buff;
 
 struct dst_entry {
-	struct net_device       *dev;
+	union {
+		struct net_device       *dev;
+		struct net_device __rcu *dev_rcu;
+	};
 	struct  dst_ops	        *ops;
 	unsigned long		_metrics;
 	unsigned long           expires;
@@ -556,9 +559,7 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
 
 static inline struct net_device *dst_dev_rcu(const struct dst_entry *dst)
 {
-	/* In the future, use rcu_dereference(dst->dev) */
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return READ_ONCE(dst->dev);
+	return rcu_dereference(dst->dev_rcu);
 }
 
 #define dst_dev_net_rcu(dst) dev_net_rcu(dst_dev_rcu(dst))
@@ -585,7 +586,7 @@ static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)
 
 static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb)
 {
-	return dev_net_rcu(skb_dst_dev(skb));
+	return dev_net_rcu(skb_dst_dev_rcu(skb));
 }
 
 struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
diff --git a/include/net/ip.h b/include/net/ip.h
index e25a2d5519c5e..8c9f7b40d6fef 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -441,8 +441,13 @@ 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(dst));
-	unsigned int mtu;
+	const struct net_device *dev;
+	unsigned int mtu, res;
+	struct net *net;
+
+	rcu_read_lock();
+	dev = dst_dev_rcu(dst);
+	net = dev_net_rcu(dev);
 
 	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
@@ -457,7 +462,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	if (mtu)
 		goto out;
 
-	mtu = READ_ONCE(dst_dev(dst)->mtu);
+	mtu = READ_ONCE(dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
 		if (rt->rt_uses_gateway && mtu > 576)
@@ -466,8 +471,10 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 
 out:
 	mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
+	res = mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+	rcu_read_unlock();
 
-	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+	return res;
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
diff --git a/net/core/dst.c b/net/core/dst.c
index 8707b7ffe4210..4376f04ac5145 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,7 +151,7 @@ void dst_dev_put(struct dst_entry *dst)
 		dst->ops->ifdown(dst, dev, true);
 	WRITE_ONCE(dst->input, dst_discard);
 	WRITE_ONCE(dst->output, dst_discard_out);
-	WRITE_ONCE(dst->dev, blackhole_netdev);
+	rcu_assign_pointer(dst->dev_rcu, blackhole_netdev);
 	dev_hold(dst->dev);
 	dev_put(dev);
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f61bc949f601a..65b539c94125f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -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(dst));
+	net = dst_dev_net_rcu(dst);
 	if (mtu < net->ipv4.ip_rt_min_pmtu) {
 		lock = true;
 		mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
-- 
2.53.0