linux-kernel - Re: [PATCH net-next 3/3] net: lantiq_xrx200: convert to build

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <7b491825-8359-86d0-7c1c-6b3cf3c67146@wp.pl>
Date:   Sat, 8 Jan 2022 17:44:30 +0100
From:   Aleksander Bajkowski <olek2@...pl>
To:     Eric Dumazet <eric.dumazet@...il.com>, tsbogend@...ha.franken.de,
        hauke@...ke-m.de, davem@...emloft.net, kuba@...nel.org,
        netdev@...r.kernel.org, linux-mips@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next 3/3] net: lantiq_xrx200: convert to build_skb

Hi Enric,

On 1/4/22 18:42, Eric Dumazet wrote:
> 
> On 1/4/22 07:11, Aleksander Jan Bajkowski wrote:
>> We can increase the efficiency of rx path by using buffers to receive
>> packets then build SKBs around them just before passing into the network
>> stack. In contrast, preallocating SKBs too early reduces CPU cache
>> efficiency.
>>
>> NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500):
>>
>>     Down        Up
>> Before    577 Mbps    648 Mbps
>> After    624 Mbps    695 Mbps
>>
>> Signed-off-by: Aleksander Jan Bajkowski <olek2@...pl>
>> ---
> 
> 
> Not sure why GRO is not yet implemented in this driver...
> 
> 


I changed netif_receive_skb() to napi_gro_receive() and did
some tests. I don't see any performance difference. Are any
further changes needed to support GRO?

Maybe this is because this MAC is connected to a DSA switch
and the napi_gro_receive() function cannot aggregate packets
until the DSA tag is removed.