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;
User-Agent: Cyrus-JMAP/3.5.0-alpha0-448-gae190416c7-fm-20210505.004-gae190416
Mime-Version: 1.0
Message-Id: <c6b08bd7-816f-4683-9f68-716634d1529e@www.fastmail.com>
In-Reply-To: <CAJvTdK=ZRFxh1=e0q7JbtNDfQWrS1d3TzrMHGiTg2Eaq1LsRSw@mail.gmail.com>
References: <20210523193259.26200-1-chang.seok.bae@intel.com>
 <20210523193259.26200-25-chang.seok.bae@intel.com>
 <de9f67eb-2be7-8950-749e-cc8eef5cc142@kernel.org>
 <CAJvTdK=ZRFxh1=e0q7JbtNDfQWrS1d3TzrMHGiTg2Eaq1LsRSw@mail.gmail.com>
Date:   Mon, 24 May 2021 21:47:53 -0700
From:   "Andy Lutomirski" <luto@kernel.org>
To:     "Len Brown" <lenb@kernel.org>
Cc:     "Bae, Chang Seok" <chang.seok.bae@intel.com>,
        "Borislav Petkov" <bp@suse.de>,
        "Thomas Gleixner" <tglx@linutronix.de>,
        "Ingo Molnar" <mingo@kernel.org>,
        "the arch/x86 maintainers" <x86@kernel.org>,
        "Brown, Len" <len.brown@intel.com>,
        "Dave Hansen" <dave.hansen@intel.com>,
        "Liu, Jing2" <jing2.liu@intel.com>,
        "Shankar, Ravi V" <ravi.v.shankar@intel.com>,
        "Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>
Subject: =?UTF-8?Q?Re:_[PATCH_v5_24/28]_x86/fpu/xstate:_Use_per-task_xstate_mask_?=
 =?UTF-8?Q?for_saving_xstate_in_signal_frame?=
Content-Type: text/plain;charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: bulk


On Mon, May 24, 2021, at 11:06 AM, Len Brown wrote:
> On Sun, May 23, 2021 at 11:15 PM Andy Lutomirski <luto@kernel.org> wro=
te:
> >
> > If I'm reading this right, it means that tasks that have ever used A=
MX
> > get one format and tasks that haven't get another one.
>=20
> No.  The format of the XSTATE on the signal stack is uncompressed XSAV=
E
> format for both AMX and non-AMX tasks, both before and after this patc=
h.
> That is because XSAVE gets the format from XCR0.  It gets the fields
> to write from the run-time parameter.
>=20
> So the change here allows a non-AMX task to skip writing data (zeros)
> to the AMX region of its XSTATE buffer.

I misread the patch. I still think this patch is useless.

>=20
> The subsequent patch adds the further optimization of (manually) check=
ing
> for INIT state for an AMX-task and also skip writing data (zeros) in t=
hat case.
>=20
> We should have done this optimization for AVX-512, but instead we
> guaranteed writing zeros, which I think is a waste of both transfer ti=
me
> and cache footprint.

If no one depends on it, it=E2=80=99s not ABI.