| Message ID | 20240607084420.3932875-1-leitao@debian.org (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 45403b12c29c5d9510ace1ad767ea4b13a4caf38 |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [net-next] ip_tunnel: Move stats allocation to core | expand |
On Fri, Jun 07, 2024 at 01:44:19AM -0700, Breno Leitao wrote: > With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and > convert veth & vrf"), stats allocation could be done on net core instead > of this driver. > > With this new approach, the driver doesn't have to bother with error > handling (allocation failure checking, making sure free happens in the > right spot, etc). This is core responsibility now. > > Move ip_tunnel driver to leverage the core allocation. > > All the ip_tunnel_init() users call ip_tunnel_init() as part of their > .ndo_init callback. The .ndo_init callback is called before the stats > allocation in netdev_register(), thus, the allocation will happen before > the netdev is visible. > > Signed-off-by: Breno Leitao <leitao@debian.org> Reviewed-by: Simon Horman <horms@kernel.org>
Hello: This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <kuba@kernel.org>: On Fri, 7 Jun 2024 01:44:19 -0700 you wrote: > With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and > convert veth & vrf"), stats allocation could be done on net core instead > of this driver. > > With this new approach, the driver doesn't have to bother with error > handling (allocation failure checking, making sure free happens in the > right spot, etc). This is core responsibility now. > > [...] Here is the summary with links: - [net-next] ip_tunnel: Move stats allocation to core https://git.kernel.org/netdev/net-next/c/45403b12c29c You are awesome, thank you!
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index bccef2fcf620..5cffad42fe8c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1099,7 +1099,6 @@ static void ip_tunnel_dev_free(struct net_device *dev) gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) @@ -1313,20 +1312,15 @@ int ip_tunnel_init(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); return err; }
With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and convert veth & vrf"), stats allocation could be done on net core instead of this driver. With this new approach, the driver doesn't have to bother with error handling (allocation failure checking, making sure free happens in the right spot, etc). This is core responsibility now. Move ip_tunnel driver to leverage the core allocation. All the ip_tunnel_init() users call ip_tunnel_init() as part of their .ndo_init callback. The .ndo_init callback is called before the stats allocation in netdev_register(), thus, the allocation will happen before the netdev is visible. Signed-off-by: Breno Leitao <leitao@debian.org> --- net/ipv4/ip_tunnel.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)