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;
Message-ID: <26cfc85cf1beebc600428e24f12f49c961540071.camel@linux.intel.com>
Subject: Re: [PATCH] x86/sgx: Replace kmap/kunmap_atomic calls
From:   Kristen Carlson Accardi <kristen@linux.intel.com>
To:     Jarkko Sakkinen <jarkko@kernel.org>,
        Dave Hansen <dave.hansen@intel.com>
Cc:     Ira Weiny <ira.weiny@intel.com>, linux-kernel@vger.kernel.org,
        linux-sgx@vger.kernel.org,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>
Date:   Thu, 13 Oct 2022 09:03:01 -0700
In-Reply-To: <Y0biN3/JsZMa0yUr@kernel.org>
References: <20220929160647.362798-1-kristen@linux.intel.com>
         <Y0BEV+Xgkrln8xoh@iweiny-desk3> <Y0ZphugZZBhlv/vT@kernel.org>
         <711f8036-787a-571e-1c0d-1a258175ebb2@intel.com>
         <Y0bUK6krEQdnFlOg@kernel.org> <Y0biN3/JsZMa0yUr@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.44.4 (3.44.4-1.module_f36+15386+a24ad1a3) 
MIME-Version: 1.0
Precedence: bulk

On Wed, 2022-10-12 at 18:50 +0300, Jarkko Sakkinen wrote:
> On Wed, Oct 12, 2022 at 05:50:19PM +0300, Jarkko Sakkinen wrote:
> > On Wed, Oct 12, 2022 at 07:13:26AM -0700, Dave Hansen wrote:
> > > On 10/12/22 00:15, Jarkko Sakkinen wrote:
> > > > There's no data to show that this change would be useful to do.
> > >=20
> > > Jarkko, I think the overall transition to kmap_local_page() is a
> > > good
> > > one.=C2=A0 It is a superior API and having it around will pave the wa=
y
> > > for
> > > new features.=C2=A0 I don't think we should demand 'data' for each an=
d
> > > every
> > > one of these.
> > >=20
> > > Please take a look around the tree and see how other maintainers
> > > are
> > > handling these patches.=C2=A0 They're not limited to SGX.
> >=20
> > Sure, I'll take a look for comparison.
>=20
> Yeah, I think it is pretty solid idea.
>=20
> Looking at the decription:
>=20
> "It is not necessary to disable page faults or preemption when
> using kmap calls, so replace kmap_atomic() and kunmap_atomic()
> calls with more the more appropriate kmap_local_page() and
> kunmap_local() calls."
>=20
> We did not pick kmap_atomic() because it disables preeemption,
> i.e. it was not a "design choice". I'd rather phrase this as
> along the lines:
>=20
> "Migrate to the newer kmap_local_page() interface from kmap_atomic()
> in order to move away from per-CPU maps to pre-task_struct maps.
> This in effect removes the need to disable preemption in the
> local CPU while kmap is active, and thus vastly reduces overall
> system latency."
>=20
> Can be improved or written completely otherwise. I just wrote it
> in the way that I had understood the whole deal in the first place.
>=20
> BR, Jarkko

Thanks for looking into this Jarkko - I will update the commit log for
the next version.

Kristen