From: Kuniyuki Iwashima <kuniyu@google.com>
To: David Ahern <dsahern@kernel.org>,
Ido Schimmel <idosch@nvidia.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S . Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@kernel.org>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>,
Chris J Arges <carges@cloudflare.com>,
Kuniyuki Iwashima <kuniyu@google.com>,
Kuniyuki Iwashima <kuni1840@gmail.com>,
netdev@vger.kernel.org
Subject: [PATCH v3 net-next 5/6] ipv4: Batch rt_flush_dev() in netdev_run_todo().
Date: Thu, 1 Oct 2026 20:47:17 +0000 [thread overview]
Message-ID: <20261001204752.2572265-6-kuniyu@google.com> (raw)
In-Reply-To: <20261001204752.2572265-1-kuniyu@google.com>
IPv4 uncached routes are linked to the global per-cpu lists,
rt_uncached_list.
When unregistering a netdev, rt_flush_dev() iterates over the
potentially long lists to find uncached routes tied to the device
and swap it with blackhole_netdev.
Since it is called for every device in dying netns under RTNL,
it adds O(N_dev x (N_cpu + N_route)) costs to any batched device
unregistration.
Let's call it once per batched device unregistration without RTNL.
Note that rt_flush_dev() must be called after setting dev->reg_state
to NETREG_UNREGISTERED. Otherwise, because rt_flush_dev(NULL) runs
without RTNL, it could race with unregister_netdevice_many_notify()
and prematurely purge routes for NETREG_UNREGISTERING dev, for
which flush_all_backlogs() has not been called yet.
Reported-by: Chris J Arges <carges@cloudflare.com>
Closes: https://lore.kernel.org/netdev/20260917-hash-bucket-route-lists-v3-0-30493a37b6eb@cloudflare.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
include/net/route.h | 6 ++++++
net/core/dev.c | 4 ++++
net/ipv4/route.c | 11 +++++++++--
3 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 6b55de2e4df8..3fccd31eb74d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -129,7 +129,13 @@ struct in_device;
int ip_rt_init(void);
void rt_cache_flush(struct net *net);
+#ifdef CONFIG_INET
void rt_flush_dev(struct net_device *dev);
+#else
+static inline void rt_flush_dev(struct net_device *dev)
+{
+}
+#endif
static inline void inet_sk_init_flowi4(const struct inet_sock *inet,
struct flowi4 *fl4)
diff --git a/net/core/dev.c b/net/core/dev.c
index a8eb382f40ca..7dba0292f052 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -129,6 +129,7 @@
#include <linux/ip.h>
#include <net/ip.h>
#include <net/mpls.h>
+#include <net/route.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
@@ -11838,6 +11839,9 @@ void netdev_run_todo(void)
linkwatch_sync_dev(dev);
}
+ if (!list_empty(&list))
+ rt_flush_dev(NULL);
+
cnt = 0;
while (!list_empty(&list)) {
dev = netdev_wait_allrefs_any(&list);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d7da2f1acbb5..1b641901f10d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1587,6 +1587,9 @@ void rt_flush_dev(struct net_device *dev)
struct rtable *rt, *safe;
int cpu;
+ if (dev && dev->dismantle)
+ return;
+
for_each_possible_cpu(cpu) {
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
@@ -1595,10 +1598,14 @@ void rt_flush_dev(struct net_device *dev)
spin_lock_bh(&ul->lock);
list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) {
- if (rt->dst.dev != dev)
+ struct net_device *rt_dev = rt->dst.dev;
+
+ if (dev ? rt_dev != dev :
+ READ_ONCE(rt_dev->reg_state) != NETREG_UNREGISTERED)
continue;
+
rcu_assign_pointer(rt->dst.dev_rcu, blackhole_netdev);
- netdev_ref_replace(dev, blackhole_netdev,
+ netdev_ref_replace(rt_dev, blackhole_netdev,
&rt->dst.dev_tracker, GFP_ATOMIC);
list_del_init(&rt->dst.rt_uncached);
}
--
2.56.0.rc1.315.gc6ed9934b7-goog
next prev parent reply other threads:[~2026-10-01 20:48 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-01 20:47 [PATCH v3 net-next 0/6] ip: Batch flushing uncached routes per batched device unregistration Kuniyuki Iwashima
2026-10-01 20:47 ` [PATCH v3 net-next 1/6] net: Order blackhole_netdev_init(), inet_init(), and inet6_init() Kuniyuki Iwashima
2026-10-05 12:18 ` Fernando Fernandez Mancera
2026-10-01 20:47 ` [PATCH v3 net-next 2/6] ipv4: Inline inet_blackhole_dev_init() to devinet_init() Kuniyuki Iwashima
2026-10-04 23:02 ` netdev-bot+sashiko
2026-10-01 20:47 ` [PATCH v3 net-next 3/6] net: Rename dev_isalive() to netif_is_alive() Kuniyuki Iwashima
2026-10-01 20:47 ` [PATCH v3 net-next 4/6] xfrm: Check netif_is_alive() in xfrm_bundle_create() and xfrm_create_dummy_bundle() Kuniyuki Iwashima
2026-10-01 20:47 ` Kuniyuki Iwashima [this message]
2026-10-04 23:02 ` [PATCH v3 net-next 5/6] ipv4: Batch rt_flush_dev() in netdev_run_todo() netdev-bot+sashiko
2026-10-05 0:51 ` Kuniyuki Iwashima
2026-10-01 20:47 ` [PATCH v3 net-next 6/6] ipv6: Batch rt6_uncached_list_flush_dev() " Kuniyuki Iwashima
2026-10-04 23:02 ` netdev-bot+sashiko
2026-10-05 0:49 ` Kuniyuki Iwashima
2026-10-06 8:12 ` [PATCH v3 net-next 0/6] ip: Batch flushing uncached routes per batched device unregistration Ido Schimmel
2026-10-06 17:45 ` Kuniyuki Iwashima
2026-10-06 20:07 ` Chris Arges
2026-10-06 23:10 ` patchwork-bot+netdevbpf
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261001204752.2572265-6-kuniyu@google.com \
--to=kuniyu@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=carges@cloudflare.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@kernel.org \
--cc=horms@kernel.org \
--cc=idosch@nvidia.com \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox