Re: [PATCH v2 net-next v2 3/5] net: add code for TCP fraglist GRO

[Felix Fietkau <nbd@nbd.name>]

On 25.04.24 17:18, Willem de Bruijn wrote:
> Felix Fietkau wrote:
>> This implements fraglist GRO similar to how it's handled in UDP, however
>> no functional changes are added yet. The next change adds a heuristic for
>> using fraglist GRO instead of regular GRO.
>> 
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c |  9 +++++++++
>>  2 files changed, 31 insertions(+)
>> 
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index e455f884190c..68157130c264 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -336,6 +336,19 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
>>  	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
>>  	flush |= skb_cmp_decrypted(p, skb);
>>  
>> +	if (NAPI_GRO_CB(p)->is_flist) {
>> +		flush |= (__force int)(flags ^ tcp_flag_word(th2));
> 
> What is the purpose of this check, given the existing check above
> 
>          flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
>                    ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));

The fraglist codepath is not updating the TCP flags of the first packet, 
so the extra check ensures it doesn't have to.

- Felix