Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   Andy Lutomirski <luto@amacapital.net>
Mime-Version: 1.0 (1.0)
Subject: Re: recvfrom/recvmsg performance and CONFIG_HARDENED_USERCOPY
Date:   Mon, 9 Dec 2019 10:43:19 -0800
Message-Id: <F6840B11-060A-48F2-9FFE-774E73C50765@amacapital.net>
References: <efffc167eff1475f94f745f733171d59@AcuMS.aculab.com>
Cc:     Eric Dumazet <eric.dumazet@gmail.com>,
        network dev <netdev@vger.kernel.org>,
        "x86@kernel.org" <x86@kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
In-Reply-To: <efffc167eff1475f94f745f733171d59@AcuMS.aculab.com>
To:     David Laight <David.Laight@aculab.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On Dec 9, 2019, at 3:01 AM, David Laight <David.Laight@aculab.com> wrote:
>=20
> =EF=BB=BFFrom: Eric Dumazet
>> Sent: 06 December 2019 14:22
> ...
>> Real question is : Do you actually need to use recvmsg() instead of recvf=
rom() ?
>> If recvmsg() provides additional cmsg, this is not surprising it is more e=
xpensive.
>=20
> Except I'm not passing in a buffer for it.
> The reason I'm looking at recvmsg is that I'd like to use recvmmsg it orde=
r to
> read out more than one message from a socket without doing an extra poll()=
.
> Note that I don't expect there to be a second message most of the time and=

> almost never a third one.
>=20
> Although I think that will only ever 'win' if recvmmsg() called vfs_poll()=
 to find
> if there was more data to read before doing any of the copy_from_user() et=
c

I would suggest a more general improvement: add a -EAGAIN fast path to recvm=
sg().  If the socket is nonblocking and has no data to read, then there shou=
ldn=E2=80=99t be a need to process the iovec at all.=