Received-SPF: pass (google.com: domain of linux-kernel+bounces-50040-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Precedence: bulk
MIME-Version: 1.0
References: <20240131155929.169961-1-alexghiti@rivosinc.com>
 <20240131155929.169961-5-alexghiti@rivosinc.com> <Zbuy1E7mz9Oui1Dl@andrea>
In-Reply-To: <Zbuy1E7mz9Oui1Dl@andrea>
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Fri, 2 Feb 2024 16:42:09 +0100
Message-ID: <CAHVXubgw0PEZMhFmjA0cAFQ2+_JOYjVfk41qRC9TFdSJtej++w@mail.gmail.com>
Subject: Re: [PATCH RFC/RFT v2 4/4] riscv: Stop emitting preventive sfence.vma
 for new userspace mappings with Svvptc
To: Andrea Parri <parri.andrea@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will@kernel.org>, 
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>, Michael Ellerman <mpe@ellerman.id.au>, 
	Nicholas Piggin <npiggin@gmail.com>, Christophe Leroy <christophe.leroy@csgroup.eu>, 
	Paul Walmsley <paul.walmsley@sifive.com>, Palmer Dabbelt <palmer@dabbelt.com>, 
	Albert Ou <aou@eecs.berkeley.edu>, Andrew Morton <akpm@linux-foundation.org>, 
	Ved Shanbhogue <ved@rivosinc.com>, Matt Evans <mev@rivosinc.com>, Dylan Jhong <dylan@andestech.com>, 
	linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, 
	linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, 
	linux-riscv@lists.infradead.org, linux-mm@kvack.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hi Andrea,

On Thu, Feb 1, 2024 at 4:03=E2=80=AFPM Andrea Parri <parri.andrea@gmail.com=
> wrote:
>
> On Wed, Jan 31, 2024 at 04:59:29PM +0100, Alexandre Ghiti wrote:
> > The preventive sfence.vma were emitted because new mappings must be mad=
e
> > visible to the page table walker but Svvptc guarantees that xRET act as
> > a fence, so no need to sfence.vma for the uarchs that implement this
> > extension.
>
> AFAIU, your first submission shows that you don't need that xRET property=
.
> Similarly for other archs.  What was rationale behind this Svvptc change?

Actually, the ARC has just changed its mind and removed this new
behaviour from the Svvptc extension, so we will take some gratuitous
page faults (but that should be outliners), which makes riscv similar
to x86 and arm64.

>
>
> > This allows to drastically reduce the number of sfence.vma emitted:
> >
> > * Ubuntu boot to login:
> > Before: ~630k sfence.vma
> > After:  ~200k sfence.vma
> >
> > * ltp - mmapstress01
> > Before: ~45k
> > After:  ~6.3k
> >
> > * lmbench - lat_pagefault
> > Before: ~665k
> > After:   832 (!)
> >
> > * lmbench - lat_mmap
> > Before: ~546k
> > After:   718 (!)
>
> This Svvptc seems to move/add the "burden" of the synchronization to xRET=
:
> Perhaps integrate the above counts w/ the perf gains in the cover letter?

Yes, I'll copy that to the cover letter.

Thanks for your interest!

Alex

>
>   Andrea