Re: [PATCH net-next] net: inline eth_type_trans() fast path

[Alexander Lobakin <aleksander.lobakin@intel.com>]

From: Edumazet@kernel.org <edumazet@kernel.org>
Date: Thu, 1 Oct 2026 19:10:46 +0200

> On Thu, Oct 1, 2026 at 5:58 PM Alexander Lobakin
> <aleksander.lobakin@intel.com> wrote:
>>
>> From: Edumazet@kernel.org <edumazet@kernel.org>
>> Date: Wed, 30 Sep 2026 19:29:57 +0200
>>
>>> eth_type_trans() is called once per received packet by most
>>> Ethernet drivers, and by core helpers (napi_gro_frags(),
>>> xdp_build_skb_from_*(), veth, tun, tunnels, loopback...).
>>>
>>> With CONFIG_MITIGATION_RETHUNK / SRSO, the call and return
>>> are not free anymore.
>>>
>>> Add eth_type_trans_inline(), handling the common case inline:
>>> unicast frame sent to dev->dev_addr, with a real ethertype,
>>> on a device which is not a DSA conduit. All other frames
>>> (multicast, broadcast, otherhost, 802.2, runts, DSA)
>>> are handled by the out-of-line eth_type_trans().
>>>
>>> eth_type_trans() is now a macro calling eth_type_trans_inline(),
>>> so that all existing callers get the fast path. The out-of-line
>>> version remains exported, and can be called with
>>> (eth_type_trans)(skb, dev). bpf_prog_test_run_skb() uses this
>>
>> Shouldn't it get renamed to e.g. eth_type_trans_slow() to avoid this
>> confusion?
> 
> This was my initial idea, but this would make the patch a bit more
> invasive and touch bpf selftests, something like:
> 
> Let me know if I should send a V2 and CC bpf maintainers, thanks!
> 
> diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
> index 513354e928cb58f837fdc93a77f2e896de1ef916..8f4e9dd18001a4c32455fefd74fe38db270756d1
> 100644
> --- a/net/bpf/test_run.c
> +++ b/net/bpf/test_run.c
> @@ -1165,7 +1165,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog,
> const union bpf_attr *kattr,
>                         goto out;
>                 }
>         }
> -       skb->protocol = eth_type_trans(skb, dev);
> +       /* Always call the out-of-line version, for fentry/fexit selftests. */
> +       skb->protocol = eth_type_trans_slow(skb, dev);
>         skb_reset_network_header(skb);
> 
>         switch (skb->protocol) {
> diff --git a/tools/testing/selftests/bpf/progs/core_kern.c
> b/tools/testing/selftests/bpf/progs/core_kern.c
> index 004f2acef2eb0b0d80184423a3e8ba399feee1f3..fca26af98a7b92898a4adfde19f63b342f29db74
> 100644
> --- a/tools/testing/selftests/bpf/progs/core_kern.c
> +++ b/tools/testing/selftests/bpf/progs/core_kern.c
> @@ -47,14 +47,14 @@ int BPF_PROG(tp_xdp_devmap_xmit_multi, const
> struct net_device
>         return randmap(from_dev->ifindex, from_dev);
>  }
> 
> -SEC("fentry/eth_type_trans")
> +SEC("fentry/eth_type_trans_slow")
>  int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb,
>              struct net_device *dev, unsigned short protocol)
>  {
>         return randmap(dev->ifindex + skb->len, dev);
>  }
> 
> -SEC("fexit/eth_type_trans")
> +SEC("fexit/eth_type_trans_slow")
>  int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb,
>              struct net_device *dev, unsigned short protocol)
>  {
> diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c
> b/tools/testing/selftests/bpf/progs/kfree_skb.c
> index 7236da72ce8055f9a0165d3b4334a04d17d110b8..678c15c151944b44e276cf1280c77cb436ff7b10
> 100644
> --- a/tools/testing/selftests/bpf/progs/kfree_skb.c
> +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
> @@ -114,7 +114,7 @@ struct {
>         bool fexit_test_ok;
>  } result = {};
> 
> -SEC("fentry/eth_type_trans")
> +SEC("fentry/eth_type_trans_slow")
>  int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct
> net_device *dev,
>              unsigned short protocol)
>  {
> @@ -132,7 +132,7 @@ int BPF_PROG(fentry_eth_type_trans, struct sk_buff
> *skb, struct net_device *dev,
>         return 0;
>  }
> 
> -SEC("fexit/eth_type_trans")
> +SEC("fexit/eth_type_trans_slow")
>  int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
>              unsigned short protocol)
>  {

This shouldn't break anything, but CCing bpf just in case.

Thanks,
Olek