All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Radim Krčmář" <rkrcmar@ventanamicro.com>
To: "Vivian Wang" <wangruikang@iscas.ac.cn>,
	"Drew Fustini" <fustini@kernel.org>,
	"Palmer Dabbelt" <palmer@dabbelt.com>,
	"Björn Töpel" <bjorn@rivosinc.com>,
	"Alexandre Ghiti" <alex@ghiti.fr>,
	"Paul Walmsley" <paul.walmsley@sifive.com>,
	"Samuel Holland" <samuel.holland@sifive.com>,
	"Drew Fustini" <dfustini@tenstorrent.com>,
	"Andy Chiu" <andybnac@gmail.com>,
	"Conor Dooley" <conor.dooley@microchip.com>,
	linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Cc: "linux-riscv" <linux-riscv-bounces@lists.infradead.org>
Subject: Re: [PATCH] riscv: Add sysctl to control discard of vstate during syscall
Date: Fri, 25 Jul 2025 12:18:23 +0200	[thread overview]
Message-ID: <DBL2588APTCA.2XUKQCJ0DW89C@ventanamicro.com> (raw)
In-Reply-To: <cc82c938-def3-4df6-9fc9-fc321af7d54a@iscas.ac.cn>

2025-07-24T05:55:54+08:00, Vivian Wang <wangruikang@iscas.ac.cn>:
> On 7/19/25 11:39, Drew Fustini wrote:
>> From: Drew Fustini <dfustini@tenstorrent.com>
>> Clobbering the vector registers can significantly increase system call
>> latency for some implementations. To mitigate this performance impact, a
>> policy mechanism is provided to administrators, distro maintainers, and
>> developers to control vector state discard in the form of a sysctl knob:
>
> So I had an idea: Is it possible to avoid repeatedly discarding the
> state on every syscall by setting VS to Initial after discarding, and
> avoiding discarding when VS is Initial? So:
>
> if (VS == Clean || VS == Dirty) {
>     clobber;
>     VS = Initial;
> }
>
> This would avoid this problem with syscall-heavy user programs while
> adding minimum overhead for everything else.

I think your proposal improves the existing code, but if a userspace is
using vectors, it's likely also restoring them after a syscall, so the
state would immediately get dirty, and the next syscall would again
needlessly clobber vector registers.

Preserving the vector state still seems better for userspaces that use
both vectors and syscalls.

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

WARNING: multiple messages have this Message-ID (diff)
From: "Radim Krčmář" <rkrcmar@ventanamicro.com>
To: "Vivian Wang" <wangruikang@iscas.ac.cn>,
	"Drew Fustini" <fustini@kernel.org>,
	"Palmer Dabbelt" <palmer@dabbelt.com>,
	"Björn Töpel" <bjorn@rivosinc.com>,
	"Alexandre Ghiti" <alex@ghiti.fr>,
	"Paul Walmsley" <paul.walmsley@sifive.com>,
	"Samuel Holland" <samuel.holland@sifive.com>,
	"Drew Fustini" <dfustini@tenstorrent.com>,
	"Andy Chiu" <andybnac@gmail.com>,
	"Conor Dooley" <conor.dooley@microchip.com>,
	linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Cc: "linux-riscv" <linux-riscv-bounces@lists.infradead.org>
Subject: Re: [PATCH] riscv: Add sysctl to control discard of vstate during syscall
Date: Fri, 25 Jul 2025 12:18:23 +0200	[thread overview]
Message-ID: <DBL2588APTCA.2XUKQCJ0DW89C@ventanamicro.com> (raw)
In-Reply-To: <cc82c938-def3-4df6-9fc9-fc321af7d54a@iscas.ac.cn>

2025-07-24T05:55:54+08:00, Vivian Wang <wangruikang@iscas.ac.cn>:
> On 7/19/25 11:39, Drew Fustini wrote:
>> From: Drew Fustini <dfustini@tenstorrent.com>
>> Clobbering the vector registers can significantly increase system call
>> latency for some implementations. To mitigate this performance impact, a
>> policy mechanism is provided to administrators, distro maintainers, and
>> developers to control vector state discard in the form of a sysctl knob:
>
> So I had an idea: Is it possible to avoid repeatedly discarding the
> state on every syscall by setting VS to Initial after discarding, and
> avoiding discarding when VS is Initial? So:
>
> if (VS == Clean || VS == Dirty) {
>     clobber;
>     VS = Initial;
> }
>
> This would avoid this problem with syscall-heavy user programs while
> adding minimum overhead for everything else.

I think your proposal improves the existing code, but if a userspace is
using vectors, it's likely also restoring them after a syscall, so the
state would immediately get dirty, and the next syscall would again
needlessly clobber vector registers.

Preserving the vector state still seems better for userspaces that use
both vectors and syscalls.

  reply	other threads:[~2025-07-25 11:13 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-19  3:39 [PATCH] riscv: Add sysctl to control discard of vstate during syscall Drew Fustini
2025-07-19  3:39 ` Drew Fustini
2025-07-21 12:13 ` Darius Rad
2025-07-21 12:13   ` Darius Rad
2025-07-21 20:59   ` Drew Fustini
2025-07-21 20:59     ` Drew Fustini
2025-07-21 21:28     ` Drew Fustini
2025-07-21 21:28       ` Drew Fustini
2025-07-21 12:35 ` Radim Krčmář
2025-07-21 12:35   ` Radim Krčmář
2025-07-21 14:54   ` Radim Krčmář
2025-07-21 14:54     ` Radim Krčmář
2025-07-21 21:20     ` Drew Fustini
2025-07-21 21:20       ` Drew Fustini
2025-07-31  1:05     ` Palmer Dabbelt
2025-07-31  1:05       ` Palmer Dabbelt
2025-07-31 12:24       ` Radim Krčmář
2025-07-31 12:24         ` Radim Krčmář
2025-08-01 21:41       ` Drew Fustini
2025-08-01 21:41         ` Drew Fustini
2025-08-05 18:51         ` Drew Fustini
2025-08-05 18:51           ` Drew Fustini
2025-07-21 21:16   ` Drew Fustini
2025-07-21 21:16     ` Drew Fustini
2025-07-27 17:29     ` Drew Fustini
2025-07-27 17:29       ` Drew Fustini
2025-07-23 21:55 ` Vivian Wang
2025-07-23 21:55   ` Vivian Wang
2025-07-25 10:18   ` Radim Krčmář [this message]
2025-07-25 10:18     ` Radim Krčmář
2025-07-25 15:01     ` Vivian Wang
2025-07-25 15:01       ` Vivian Wang
2025-07-25 18:47       ` Radim Krčmář
2025-07-25 18:47         ` Radim Krčmář
2025-07-26 18:37         ` Drew Fustini
2025-07-26 18:37           ` Drew Fustini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=DBL2588APTCA.2XUKQCJ0DW89C@ventanamicro.com \
    --to=rkrcmar@ventanamicro.com \
    --cc=alex@ghiti.fr \
    --cc=andybnac@gmail.com \
    --cc=bjorn@rivosinc.com \
    --cc=conor.dooley@microchip.com \
    --cc=dfustini@tenstorrent.com \
    --cc=fustini@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv-bounces@lists.infradead.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=samuel.holland@sifive.com \
    --cc=wangruikang@iscas.ac.cn \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.