Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S938703AbcKPKiP (ORCPT ); Wed, 16 Nov 2016 05:38:15 -0500 Received: from foss.arm.com ([217.140.101.70]:46996 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753600AbcKPKiL (ORCPT ); Wed, 16 Nov 2016 05:38:11 -0500 Date: Wed, 16 Nov 2016 10:37:29 +0000 From: Mark Rutland To: "Leeder, Neil" Cc: Will Deacon , Catalin Marinas , Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo , linux-arm-msm@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Mark Langsdorf , Mark Salter , Jon Masters , Timur Tabi , cov@codeaurora.org Subject: Re: [PATCH v7] soc: qcom: add l2 cache perf events driver Message-ID: <20161116103729.GB11228@leverpostej> References: <1477687813-11412-1-git-send-email-nleeder@codeaurora.org> <20161109175413.GE17020@leverpostej> <20161109181652.GK17771@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1089 Lines: 28 On Fri, Nov 11, 2016 at 04:52:35PM -0500, Leeder, Neil wrote: > So is there a use-case for individual uncore PMUs when they can't be > used in task mode or per-cpu? > > The main (only?) use will be in system mode, in which case surely it > makes sense to provide a single aggregated count? If you are aware of the system topology, the numbers may be more useful than the summed count. If you aren't, it's still possible to sum them in userspace. Having them summed by the kernel means that the kernel is implying it supports group semantics that it cannot, since it cannot start/stop all counters in a group atomically if they're split across several units. > With individual PMUs exposed there will be potentially dozens of > nodes for userspace to collect from which would make perf > command-line usage unwieldy at best. FWIW, for uncore/system PMUs, even on x86 there are a number of independent units. Some PMUs (those which are symmetric across the topology) get hidden behind the same struct PMU, but instances are still isolated (and their values not summed). Thanks, Mark.