Re: [PATCH v3 net-next v3 6/6] net: add heuristic for enabling TCP fraglist GRO

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@xxxxxxxx> wrote:
>
> When forwarding TCP after GRO, software segmentation is very expensive,
> especially when the checksum needs to be recalculated.
> One case where that's currently unavoidable is when routing packets over
> PPPoE. Performance improves significantly when using fraglist GRO
> implemented in the same way as for UDP.
>
> When NETIF_F_GRO_FRAGLIST is enabled, perform a lookup for an established
> socket in the same netns as the receiving device. While this may not
> cover all relevant use cases in multi-netns configurations, it should be
> good enough for most configurations that need this.
>
> Here's a measurement of running 2 TCP streams through a MediaTek MT7622
> device (2-core Cortex-A53), which runs NAT with flow offload enabled from
> one ethernet port to PPPoE on another ethernet port + cake qdisc set to
> 1Gbps.
>
> rx-gro-list off: 630 Mbit/s, CPU 35% idle
> rx-gro-list on:  770 Mbit/s, CPU 40% idle
>
> Signe-off-by: Felix Fietkau <nbd@xxxxxxxx>
> ---
>  net/ipv4/tcp_offload.c   | 30 ++++++++++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c | 33 +++++++++++++++++++++++++++++++++
>  2 files changed, 63 insertions(+)
>
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index ee5403760775..2ae83f4394dc 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -406,6 +406,34 @@ void tcp_gro_complete(struct sk_buff *skb)
>  }
>  EXPORT_SYMBOL(tcp_gro_complete);
>
> +static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
> +                                   struct tcphdr *th)
> +{
> +       const struct iphdr *iph = skb_gro_network_header(skb);
> +       struct net *net = dev_net(skb->dev);

Could you defer the initializations of iph and net after the
NETIF_F_GRO_FRAGLIST check ?

dev_net() has an implicit READ_ONCE() ...

> +       struct sk_buff *p;
> +       struct sock *sk;
> +       int iif, sdif;
> +
> +       if (!(skb->dev->features & NETIF_F_GRO_FRAGLIST))
> +               return;
> +
> +       p = tcp_gro_lookup(head, th);
> +       if (p) {
> +               NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist;
> +               return;
> +       }
> +
> +       inet_get_iif_sdif(skb, &iif, &sdif);
> +       sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
> +                                      iph->saddr, th->source,
> +                                      iph->daddr, ntohs(th->dest),
> +                                      iif, sdif);
> +       NAPI_GRO_CB(skb)->is_flist = !sk;
> +       if (sk)
> +               sock_put(sk);
> +}
> +
>  INDIRECT_CALLABLE_SCOPE
>  struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
>  {
> @@ -421,6 +449,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
>         if (!th)
>                 goto flush;
>
> +       tcp4_check_fraglist_gro(head, skb, th);
> +
>         return tcp_gro_receive(head, skb, th);
>
>  flush:
> diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
> index c01ace2e9ff0..1ab45cca3936 100644
> --- a/net/ipv6/tcpv6_offload.c
> +++ b/net/ipv6/tcpv6_offload.c
> @@ -7,12 +7,43 @@
>   */
>  #include <linux/indirect_call_wrapper.h>
>  #include <linux/skbuff.h>
> +#include <net/inet6_hashtables.h>
>  #include <net/gro.h>
>  #include <net/protocol.h>
>  #include <net/tcp.h>
>  #include <net/ip6_checksum.h>
>  #include "ip6_offload.h"
>
> +static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
> +                                   struct tcphdr *th)
> +{
> +#if IS_ENABLED(CONFIG_IPV6)
> +       const struct ipv6hdr *hdr = skb_gro_network_header(skb);
> +       struct net *net = dev_net(skb->dev);

Same remark here.

> +       struct sk_buff *p;
> +       struct sock *sk;
> +       int iif, sdif;
> +
> +       if (!(skb->dev->features & NETIF_F_GRO_FRAGLIST))
> +               return;
> +
> +       p = tcp_gro_lookup(head, th);
> +       if (p) {
> +               NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist;
> +               return;
> +       }
> +
> +       inet6_get_iif_sdif(skb, &iif, &sdif);
> +       sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
> +                                       &hdr->saddr, th->source,
> +                                       &hdr->daddr, ntohs(th->dest),
> +                                       iif, sdif);
> +       NAPI_GRO_CB(skb)->is_flist = !sk;
> +       if (sk)
> +               sock_put(sk);
> +#endif /* IS_ENABLED(CONFIG_IPV6) */
> +}
> +
>  INDIRECT_CALLABLE_SCOPE
>  struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
>  {
> @@ -28,6 +59,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
>         if (!th)
>                 goto flush;
>
> +       tcp6_check_fraglist_gro(head, skb, th);
> +
>         return tcp_gro_receive(head, skb, th);
>
>  flush:
> --
> 2.44.0
>