Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 01 Aug 2023 09:14:08 -0400
From:   Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To:     Eric Dumazet <edumazet@google.com>,
        Tahsin Erdogan <trdgn@amazon.com>
Cc:     "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Herbert Xu <herbert@gondor.apana.org.au>,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Message-ID: <64c905205b2f4_1b41af2947@willemb.c.googlers.com.notmuch>
In-Reply-To: <CANn89iLghUDUSbNv-QOgyJ4dv5DhXGL60caeuVMnHW4HZQVJmg@mail.gmail.com>
References: <20230731230736.109216-1-trdgn@amazon.com>
 <CANn89iLV0iEeQy19wn+Vfmhpgr6srVpf3L+oBvuDyLRQXfoMug@mail.gmail.com>
 <CANn89iLghUDUSbNv-QOgyJ4dv5DhXGL60caeuVMnHW4HZQVJmg@mail.gmail.com>
Subject: Re: [PATCH v2] tun: avoid high-order page allocation for packet
 header
Mime-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

Eric Dumazet wrote:
> On Tue, Aug 1, 2023 at 11:37=E2=80=AFAM Eric Dumazet <edumazet@google.c=
om> wrote:
> >
> > On Tue, Aug 1, 2023 at 1:07=E2=80=AFAM Tahsin Erdogan <trdgn@amazon.c=
om> wrote:
> > >
> > > When GSO is not enabled and a packet is transmitted via writev(), a=
ll
> > > payload is treated as header which requires a contiguous memory all=
ocation.
> > > This allocation request is harder to satisfy, and may even fail if =
there is
> > > enough fragmentation.
> > >
> > > Note that sendmsg() code path limits the linear copy length, so thi=
s change
> > > makes writev() and sendmsg() more consistent.
> > >
> > > Signed-off-by: Tahsin Erdogan <trdgn@amazon.com>
> > > ---
> >
> > I will have to tweak one existing packetdrill test, nothing major.
> >
> > Tested-by: Eric Dumazet <edumazet@google.com>
> > Reviewed-by: Eric Dumazet <edumazet@google.com>
> =

> I have to take this back, sorry.
> =

> We need to change alloc_skb_with_frags() and tun.c to attempt
> high-order allocations,
> otherwise tun users sending very large buffers will regress.
> (Even if this _could_ fail as you pointed out if memory is tight/fragme=
nted)
> =

> I am working to make the change in alloc_skb_with_frags() and in tun,
> we can apply your patch after this prereq.

This exactly same allocation logic also exists in packet_alloc_skb and
tap_alloc_skb. If changing one of them, perhaps should address convert
all at the same time, to keep behavior consistent.=