mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Johnny Fan <johnny.fan@cixtech.com>
To: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>,
	will@kernel.org, mark.rutland@arm.com,
	linux-arm-kernel@lists.infradead.org,
	linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	james.clark@linaro.org, jeremy.linton@arm.com,
	cix-kernel-upstream@cixtech.com, bob.zhang@cixtech.com,
	jie.fu@cixtech.com, Fugang Duan <fugang.duan@cixtech.com>
Subject: Re: [PATCH] perf: arm_spe: Support heterogeneous ACPI systems
Date: Mon, 19 Oct 2026 10:09:44 +0800	[thread overview]
Message-ID: <atV7wDlfmd7sermb@JohnnyFan> (raw)
In-Reply-To: <20261016100538.GE26205@e132581.arm.com>

On Fri, Oct 16, 2026 at 11:05:38AM +0100, Leo Yan wrote:
> SPE driver supports heterogeneous systems. If firmware creates proper
> devices based on CPU topology, the driver can probe multiple instances.
> 
> So "registration is limited to homogeneous systems" is not quite right.

You are right, I meant the ACPI registration path in arm_pmu_acpi.c. It
registers a single static SPE device, and only if every possible CPU
agrees on both the implementation tag (hetid) and the SPE interrupt
number -- a CPU that does not implement SPE reports 0, which breaks that
agreement, so a heterogeneous machine gets no SPE device at all (the
boot still succeeds; SPE is just absent). As Jeremy pointed out, the fix
is to group the CPUs by (hetid, GSIV) and create one device per group,
like DT does with PPI partitions. The driver already handles multiple
instances; how each one gets its supported_cpus is the plumbing question
I asked Marc about.


Thanks,

Johnny

      reply	other threads:[~2026-10-19  2:09 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-15  6:29 Johnny.Fan
2026-10-15 10:49 ` Marc Zyngier
2026-10-15 11:52   ` Johnny Fan
2026-10-15 15:58     ` Jeremy Linton
2026-10-16  4:20       ` Johnny Fan
2026-10-19 23:31         ` Jeremy Linton
2026-10-15 14:19   ` Leo Yan
2026-10-16  3:24     ` Johnny Fan
2026-10-16 10:05       ` Leo Yan
2026-10-19  2:09         ` Johnny Fan [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=atV7wDlfmd7sermb@JohnnyFan \
    --to=johnny.fan@cixtech.com \
    --cc=bob.zhang@cixtech.com \
    --cc=cix-kernel-upstream@cixtech.com \
    --cc=fugang.duan@cixtech.com \
    --cc=james.clark@linaro.org \
    --cc=jeremy.linton@arm.com \
    --cc=jie.fu@cixtech.com \
    --cc=leo.yan@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=will@kernel.org \
    /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

all inboxes | Powered by JetHome®