[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <967ed173-b556-4bfc-b3c8-ff0fc902b951@gmail.com>
Date: Mon, 11 Mar 2024 10:18:17 +0100
From: Richard Gobert <richardbgobert@...il.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com,
willemdebruijn.kernel@...il.com, dsahern@...nel.org, xeb@...l.ru,
shuah@...nel.org, idosch@...dia.com, razor@...ckwall.org,
amcohen@...dia.com, petrm@...dia.com, jbenc@...hat.com, bpoirier@...dia.com,
b.galvani@...il.com, gavinl@...dia.com, liujian56@...wei.com,
horms@...nel.org, linyunsheng@...wei.com, therbert@...gle.com,
netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: Re: [PATCH net-next v3 4/4] net: gro: move L3 flush checks to
tcp_gro_receive
Eric Dumazet wrote:
> On Sat, Mar 9, 2024 at 4:35 PM Richard Gobert <richardbgobert@...il.com> wrote:
>>
>> {inet,ipv6}_gro_receive functions perform flush checks (ttl, flags,
>> iph->id, ...) against all packets in a loop. These flush checks are
>> relevant only to tcp flows, and as such they're used to determine whether
>> the packets can be merged later in tcp_gro_receive.
>>
>> These checks are not relevant to UDP packets.
>
> I do not think this claim is true.
>
> Incoming packets -> GRO -> GSO -> forwarded packets
>
> The {GRO,GSO} step must be transparent, GRO is not LRO.
Sorry, I should rephrase myself. The patch preserves the
current logic in GRO. These L3 checks (ttl, flags, etc.) are written to
NAPI_GRO_CB(p)->{flush,flush_id}, and NAPI_GRO_CB(skb)->is_atomic - and
all of these are currently used only in tcp_gro_receive.
Powered by blists - more mailing lists