From: Shivaji Kant <shivajikant@google.com>
Date: Wed, 29 Oct 2025 06:54:19 +0000 (+0000)
Subject: net: devmem: refresh devmem TX dst in case of route invalidation
X-Git-Tag: v6.18-rc4~24^2~1
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=6a2108c78069fda000729b88c97b1eba0405e6d7;p=thirdparty%2Fkernel%2Fstable.git

net: devmem: refresh devmem TX dst in case of route invalidation

The zero-copy Device Memory (Devmem) transmit path
relies on the socket's route cache (`dst_entry`) to
validate that the packet is being sent via the network
device to which the DMA buffer was bound.

However, this check incorrectly fails and returns `-ENODEV`
if the socket's route cache entry (`dst`) is merely missing
or expired (`dst == NULL`). This scenario is observed during
network events, such as when flow steering rules are deleted,
leading to a temporary route cache invalidation.

This patch fixes -ENODEV error for `net_devmem_get_binding()`
by doing the following:

1.  It attempts to rebuild the route via `rebuild_header()`
if the route is initially missing (`dst == NULL`). This
allows the TCP/IP stack to recover from transient route
cache misses.
2.  It uses `rcu_read_lock()` and `dst_dev_rcu()` to safely
access the network device pointer (`dst_dev`) from the
route, preventing use-after-free conditions if the
device is concurrently removed.
3.  It maintains the critical safety check by validating
that the retrieved destination device (`dst_dev`) is
exactly the device registered in the Devmem binding
(`binding->dev`).

These changes prevent unnecessary ENODEV failures while
maintaining the critical safety requirement that the
Devmem resources are only used on the bound network device.

Reviewed-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: Vedant Mathur <vedantmathur@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Fixes: bd61848900bf ("net: devmem: Implement TX path")
Signed-off-by: Shivaji Kant <shivajikant@google.com>
Link: https://patch.msgid.link/20251029065420.3489943-1-shivajikant@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---

diff --git a/net/core/devmem.c b/net/core/devmem.c
index d9de31a6cc7f..1d04754bc756 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -17,6 +17,7 @@
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
 #include <net/sock.h>
+#include <net/tcp.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
@@ -357,7 +358,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
 							 unsigned int dmabuf_id)
 {
 	struct net_devmem_dmabuf_binding *binding;
-	struct dst_entry *dst = __sk_dst_get(sk);
+	struct net_device *dst_dev;
+	struct dst_entry *dst;
 	int err = 0;
 
 	binding = net_devmem_lookup_dmabuf(dmabuf_id);
@@ -366,16 +368,35 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
 		goto out_err;
 	}
 
+	rcu_read_lock();
+	dst = __sk_dst_get(sk);
+	/* If dst is NULL (route expired), attempt to rebuild it. */
+	if (unlikely(!dst)) {
+		if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) {
+			err = -EHOSTUNREACH;
+			goto out_unlock;
+		}
+		dst = __sk_dst_get(sk);
+		if (unlikely(!dst)) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
 	/* The dma-addrs in this binding are only reachable to the corresponding
 	 * net_device.
 	 */
-	if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) {
+	dst_dev = dst_dev_rcu(dst);
+	if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) {
 		err = -ENODEV;
-		goto out_err;
+		goto out_unlock;
 	}
 
+	rcu_read_unlock();
 	return binding;
 
+out_unlock:
+	rcu_read_unlock();
 out_err:
 	if (binding)
 		net_devmem_dmabuf_binding_put(binding);