Re: [PATCH v4 net-next v4 6/6] net: add heuristic for enabling TCP fraglist GRO

[Felix Fietkau <nbd@nbd.name>]

On 30.04.24 12:31, Paolo Abeni wrote:
> On Tue, 2024-04-30 at 12:23 +0200, Felix Fietkau wrote:
>> On 30.04.24 12:12, Paolo Abeni wrote:
>> > On Sat, 2024-04-27 at 20:23 +0200, Felix Fietkau 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@nbd.name>
>> > > ---
>> > >  net/ipv4/tcp_offload.c   | 32 ++++++++++++++++++++++++++++++++
>> > >  net/ipv6/tcpv6_offload.c | 35 +++++++++++++++++++++++++++++++++++
>> > >  2 files changed, 67 insertions(+)
>> > > 
>> > > diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> > > index 87ae9808e260..3e9b8c6f9c8c 100644
>> > > --- a/net/ipv4/tcp_offload.c
>> > > +++ b/net/ipv4/tcp_offload.c
>> > > @@ -407,6 +407,36 @@ 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;
>> > > +	struct sk_buff *p;
>> > > +	struct sock *sk;
>> > > +	struct net *net;
>> > > +	int iif, sdif;
>> > > +
>> > > +	if (!(skb->dev->features & NETIF_F_GRO_FRAGLIST))
>> > 
>> > Should we add an 'unlikely()' here to pair with unlikely(is_flist) in
>> > *gro_receive / *gro_complete?
>> Not sure if unlikely() will make any difference here. I think it makes 
>> more sense in the other places than here.
> 
> Why? AFAICS this will be called for every packet on the wire, exactly
> as the code getting this annotation in patch 3/6.

I had compared assembly after adding an annotation and didn't see a 
difference. However, my annotation was wrong.
When I add: if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST)))
the generated code is different, and I probably should use that.

- Felix