Message-ID: <ec534eacabf5c859930eb5ca7f417f7f01197d24.camel@redhat.com>
Subject: Re: [net PATCH] skb: Do mix page pool and page referenced frags in
 GRO
From:   Paolo Abeni <pabeni@redhat.com>
To:     Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>
Cc:     Yunsheng Lin <linyunsheng@huawei.com>,
        Alexander Duyck <alexander.duyck@gmail.com>, nbd@nbd.name,
        davem@davemloft.net, hawk@kernel.org, ilias.apalodimas@linaro.org,
        linux-kernel@vger.kernel.org, lorenzo@kernel.org,
        netdev@vger.kernel.org
Date:   Mon, 30 Jan 2023 09:50:08 +0100
In-Reply-To: <CANn89iKgZU4Q+THXupzZi4hETuKuCOvOB=iHpp5JzQTNv_Fg_A@mail.gmail.com>
References: <04e27096-9ace-07eb-aa51-1663714a586d@nbd.name>
         <167475990764.1934330.11960904198087757911.stgit@localhost.localdomain>
         <cde24ed8-1852-ce93-69f3-ff378731f52c@huawei.com>
         <20230127212646.4cfeb475@kernel.org>
         <CANn89iKgZU4Q+THXupzZi4hETuKuCOvOB=iHpp5JzQTNv_Fg_A@mail.gmail.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.46.3 (3.46.3-1.fc37) 
MIME-Version: 1.0
Precedence: bulk

On Sat, 2023-01-28 at 08:08 +0100, Eric Dumazet wrote:
> On Sat, Jan 28, 2023 at 6:26 AM Jakub Kicinski <kuba@kernel.org> wrote:
> >=20
> > On Sat, 28 Jan 2023 10:37:47 +0800 Yunsheng Lin wrote:
> > > If we are not allowing gro for the above case, setting NAPI_GRO_CB(p)=
->flush
> > > to 1 in gro_list_prepare() seems to be making more sense so that the =
above
> > > case has the same handling as skb_has_frag_list() handling?
> > > https://elixir.bootlin.com/linux/v6.2-rc4/source/net/core/gro.c#L503
> > >=20
> > > As it seems to avoid some unnecessary operation according to comment
> > > in tcp4_gro_receive():
> > > https://elixir.bootlin.com/linux/v6.2-rc4/source/net/ipv4/tcp_offload=
.c#L322
> >=20
> > The frag_list case can be determined with just the input skb.
> > For pp_recycle we need to compare input skb's pp_recycle with
> > the pp_recycle of the skb already held by GRO.
> >=20
> > I'll hold off with applying a bit longer tho, in case Eric
> > wants to chime in with an ack or opinion.
>=20
> We can say that we are adding in the fast path an expensive check
> about an unlikely condition.
>=20
> GRO is by far the most expensive component in our stack.

Slightly related to the above: currently the GRO engine performs the
skb metadata check for every packet. My understanding is that even with
XDP enabled and ebpf running on the given packet, the skb should=20
usually have meta_len =3D=3D 0.=C2=A0

What about setting 'skb->slow_gro' together with meta_len and moving
the skb_metadata_differs() check under the slow_gro guard?

Cheers,

Paolo