Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
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: strace of io_uring events?
Date:   Wed, 15 Jul 2020 07:35:50 -0700
Message-Id: <D9FAB37B-D059-4137-A115-616237D78640@amacapital.net>
References: <CAJfpegu3EwbBFTSJiPhm7eMyTK2MzijLUp1gcboOo3meMF_+Qg@mail.gmail.com>
Cc:     strace-devel@lists.strace.io, io-uring@vger.kernel.org,
        Pavel Begunkov <asml.silence@gmail.com>,
        Linux API <linux-api@vger.kernel.org>,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <CAJfpegu3EwbBFTSJiPhm7eMyTK2MzijLUp1gcboOo3meMF_+Qg@mail.gmail.com>
To:     Miklos Szeredi <miklos@szeredi.hu>,
        Kees Cook <keescook@chromium.org>,
        Christian Brauner <christian.brauner@ubuntu.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On Jul 15, 2020, at 4:12 AM, Miklos Szeredi <miklos@szeredi.hu> wrote:
>=20
> =EF=BB=BFHi,
>=20
> This thread is to discuss the possibility of stracing requests
> submitted through io_uring.   I'm not directly involved in io_uring
> development, so I'm posting this out of  interest in using strace on
> processes utilizing io_uring.
>=20
> io_uring gives the developer a way to bypass the syscall interface,
> which results in loss of information when tracing.  This is a strace
> fragment on  "io_uring-cp" from liburing:
>=20
> io_uring_enter(5, 40, 0, 0, NULL, 8)    =3D 40
> io_uring_enter(5, 1, 0, 0, NULL, 8)     =3D 1
> io_uring_enter(5, 1, 0, 0, NULL, 8)     =3D 1
> ...
>=20
> What really happens are read + write requests.  Without that
> information the strace output is mostly useless.
>=20
> This loss of information is not new, e.g. calls through the vdso or
> futext fast paths are also invisible to strace.  But losing filesystem
> I/O calls are a major blow, imo.
>=20
> What do people think?
>=20
> =46rom what I can tell, listing the submitted requests on
> io_uring_enter() would not be hard.  Request completion is
> asynchronous, however, and may not require  io_uring_enter() syscall.
> Am I correct?
>=20
> Is there some existing tracing infrastructure that strace could use to
> get async completion events?  Should we be introducing one?
>=20
>=20

Let=E2=80=99s add some seccomp folks. We probably also want to be able to ru=
n seccomp-like filters on io_uring requests. So maybe io_uring should call i=
nto seccomp-and-tracing code for each action.=