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;
Date:   Thu, 1 Jun 2023 13:18:56 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Thomas Richter <tmricht@linux.ibm.com>
Cc:     Ian Rogers <irogers@google.com>, Marc Zyngier <maz@kernel.org>,
        Oliver Upton <oliver.upton@linux.dev>,
        Ravi Bangoria <ravi.bangoria@amd.com>,
        Nathan Chancellor <nathan@kernel.org>, namhyung@kernel.org,
        eranian@google.com, acme@kernel.org, mark.rutland@arm.com,
        jolsa@kernel.org, bp@alien8.de, kan.liang@linux.intel.com,
        adrian.hunter@intel.com, maddy@linux.ibm.com, x86@kernel.org,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
        sandipan.das@amd.com, ananth.narayan@amd.com,
        santosh.shukla@amd.com, kvmarm@lists.linux.dev
Subject: Re: [PATCH v4 3/4] perf/core: Remove pmu linear searching code
Message-ID: <20230601111856.GW4253@hirez.programming.kicks-ass.net>
References: <ZG+FLdP2kkfI1m2Z@linux.dev>
 <CAP-5=fWYbzmTETgqJ11y22=JaXDM0gnb4qR6KYeRGmFXw08f-Q@mail.gmail.com>
 <86jzwtdhmk.wl-maz@kernel.org>
 <CAP-5=fVW6KbUbbEfF3mEFvTfFDC5yKSjSpa+w3D55dG3CNUERw@mail.gmail.com>
 <86h6rxd3gh.wl-maz@kernel.org>
 <0075d8a9-2df4-86eb-8171-8995f59904e0@linux.ibm.com>
 <CAP-5=fXo0t+buDrmf7SyTD97gmTWGoDAO2YXWyav+_79O3MZ0w@mail.gmail.com>
 <a1f27798-0b06-7dc3-028b-038512947306@linux.ibm.com>
 <CAP-5=fVw3vSEu7yGFDnZi8c3VUFJu_XEZtY9ZcTsD7ip2imR6Q@mail.gmail.com>
 <aa2f8581-6440-87c0-1578-157719f7543e@linux.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <aa2f8581-6440-87c0-1578-157719f7543e@linux.ibm.com>
Precedence: bulk

On Thu, Jun 01, 2023 at 01:02:30PM +0200, Thomas Richter wrote:

> PS: I have the feeling, it gets complicated to have multiple hardware PMUs
> per platform.

Recently someone was poking around giving the pmu device a parent, this
would, I think, result in sysfs links, which could be used to decide
what's what.

Core pmus would have the CPU device as their parent, while memory
controller thingies would link to the relevant node or something.

Ofc. all that's future-work/pending.