Linux-RISC-V Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Jisheng Zhang <jszhang@kernel.org>
To: Andy Chiu <tchiu@tenstorrent.com>
Cc: Paul Walmsley <pjw@kernel.org>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Alexandre Ghiti <alex@ghiti.fr>,
	linux-riscv@lists.infradead.org, mpe@oss.tenstorrent.com,
	andybnac@gmail.com, Anton Blanchard <antonb@tenstorrent.com>,
	Nicholas Piggin <npiggin@oss.tenstorrent.com>,
	dfustini@oss.tenstorrent.com, greentime.hu@sifive.com
Subject: Re: [PATCH v1] riscv: irqflags: Conditionally enable interrupts in arch_local_irq_restore()
Date: Wed, 11 Nov 2026 12:05:08 +0800	[thread overview]
Message-ID: <avPpdL_iZhiU4b08@xhacker> (raw)
In-Reply-To: <20261110225040.1146439-1-tchiu@tenstorrent.com>

On Tue, Nov 10, 2026 at 04:50:38PM -0600, Andy Chiu wrote:
> From: Anton Blanchard <antonb@tenstorrent.com>
> 
> The Tenstorrent Ascalon core has an optimization that reduces pipeline
> synchronisation for immediate writes of SIE. This optimization does not
> work with register-based CSR writes, which occur when restoring flags in
> arch_local_irq_restore().
> 
> Refactor arch_local_irq_restore() to conditionally call
> arch_local_irq_enable() only when saved flags indicate interrupts were
> enabled.
> 
> On a simple nginx benchmark serving a small static HTML file this patch
> improves performance by 4%.
> 
> Signed-off-by: Anton Blanchard <antonb@tenstorrent.com>
> Co-developed-by: Nicholas Piggin <npiggin@oss.tenstorrent.com>
> Signed-off-by: Nicholas Piggin <npiggin@oss.tenstorrent.com>
> Signed-off-by: Andy Chiu <tchiu@tenstorrent.com>

Reviewed-by: Jisheng Zhang <jszhang@kernel.org>

> ---
>  arch/riscv/include/asm/irqflags.h | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
> index 6fd8cbfcfcc7..5b1bca17bdc4 100644
> --- a/arch/riscv/include/asm/irqflags.h
> +++ b/arch/riscv/include/asm/irqflags.h
> @@ -48,7 +48,8 @@ static inline int arch_irqs_disabled(void)
>  /* set interrupt enabled status */
>  static inline void arch_local_irq_restore(unsigned long flags)
>  {
> -	csr_set(CSR_STATUS, flags & SR_IE);
> +	if (!arch_irqs_disabled_flags(flags))
> +		arch_local_irq_enable();
>  }
>  
>  #endif /* _ASM_RISCV_IRQFLAGS_H */
> 
> base-commit: 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4
> -- 
> 2.43.0
> 
> 
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv

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

      reply	other threads:[~2026-11-11  4:25 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-10 22:50 [PATCH v1] riscv: irqflags: Conditionally enable interrupts in arch_local_irq_restore() Andy Chiu
2026-11-11  4:05 ` Jisheng Zhang [this message]

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=avPpdL_iZhiU4b08@xhacker \
    --to=jszhang@kernel.org \
    --cc=alex@ghiti.fr \
    --cc=andybnac@gmail.com \
    --cc=antonb@tenstorrent.com \
    --cc=aou@eecs.berkeley.edu \
    --cc=dfustini@oss.tenstorrent.com \
    --cc=greentime.hu@sifive.com \
    --cc=linux-riscv@lists.infradead.org \
    --cc=mpe@oss.tenstorrent.com \
    --cc=npiggin@oss.tenstorrent.com \
    --cc=palmer@dabbelt.com \
    --cc=pjw@kernel.org \
    --cc=tchiu@tenstorrent.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox