github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-07 06:17:02 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

ipv6: Batch rt6_uncached_list_flush_dev() in netdev_run_todo().

Browse Source 
IPv6 uncached routes are linked to the global per-cpu lists,
rt6_uncached_list.

When unregistering a netdev, rt6_uncached_list_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.

Because it now runs without RTNL, rt->dst.dev and rt->rt6i_idev->dev
may transition to NETREG_UNREGISTERED at different times.  Thus, we
must check that both devices are blackhole_netdev before unlinking
the route; otherwise, the remaining device reference would not be
flushed when the other device is unregistered.

In addition, since netdev_run_todo() runs even when IPv6 is disabled,
rt6_uncached_list_flush_dev() must check ipv6_mod_enabled() before
touching rt6_uncached_list.

Note also that netdev_run_todo() cannot be called before
rt6_uncached_list is initialised because:

  1. unregister_netdevice_many_notify() panics when
     dev_boot_phase == 1 (net_dev_init() is subsys_initcall()).

  2. the only device registered before fs_initcall_sync() is
     loopback and loopback_net_init() panics in case of failure.

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>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Chris J Arges <carges@cloudflare.com>
Link: https://patch.msgid.link/20261001204752.2572265-7-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Kuniyuki Iwashima 2026-10-01 20:47:18 +00:00 committed by Jakub Kicinski
parent ca68547990
commit f12d290799
3 changed files with 27 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
include/net/ip6_route.h
View File

@ -231,6 +231,13 @@ void rt6_multipath_rebalance(struct fib6_info *f6i);
void rt6_uncached_list_add(struct rt6_info *rt);
void rt6_uncached_list_del(struct rt6_info *rt);
#ifdef CONFIG_IPV6
void rt6_uncached_list_flush_dev(struct net_device *dev);
#else
static inline void rt6_uncached_list_flush_dev(struct net_device *dev)
{
}
#endif
static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb)
{

5
net/core/dev.c
View File

@ -131,6 +131,7 @@
#include <net/mpls.h>
#include <net/route.h>
#include <linux/ipv6.h>
#include <net/ip6_route.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/random.h>
@ -11887,8 +11888,10 @@ void netdev_run_todo(void)
linkwatch_sync_dev(dev);
}
if (!list_empty(&list))
if (!list_empty(&list)) {
rt_flush_dev(NULL);
rt6_uncached_list_flush_dev(NULL);
}
cnt = 0;
while (!list_empty(&list)) {

24
net/ipv6/route.c
View File

@ -158,10 +158,16 @@ void rt6_uncached_list_del(struct rt6_info *rt)
}
}
static void rt6_uncached_list_flush_dev(struct net_device *dev)
void rt6_uncached_list_flush_dev(struct net_device *dev)
{
int cpu;
if (!ipv6_mod_enabled())
return;
if (dev && dev->dismantle)
return;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
struct rt6_info *rt, *safe;
@ -173,22 +179,24 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) {
struct inet6_dev *rt_idev = rt->rt6i_idev;
struct net_device *rt_dev = rt->dst.dev;
bool handled = false;
if (rt_idev && rt_idev->dev == dev) {
if (rt_idev &&
(dev ? rt_idev->dev == dev :
READ_ONCE(rt_idev->dev->reg_state) == NETREG_UNREGISTERED)) {
rt->rt6i_idev = in6_dev_get(blackhole_netdev);
in6_dev_put(rt_idev);
handled = true;
}
if (rt_dev == dev) {
rt->dst.dev = blackhole_netdev;
if (dev ? rt_dev == dev :
READ_ONCE(rt_dev->reg_state) == NETREG_UNREGISTERED) {
rcu_assign_pointer(rt->dst.dev_rcu, blackhole_netdev);
netdev_ref_replace(rt_dev, blackhole_netdev,
&rt->dst.dev_tracker,
GFP_ATOMIC);
handled = true;
}
if (handled)
if (rt->dst.dev == blackhole_netdev &&
(!rt->rt6i_idev || rt->rt6i_idev->dev == blackhole_netdev))
list_del_init(&rt->dst.rt_uncached);
}
spin_unlock_bh(&ul->lock);