Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934419AbeAKPps (ORCPT + 1 other); Thu, 11 Jan 2018 10:45:48 -0500 Received: from mx1.redhat.com ([209.132.183.28]:55380 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933794AbeAKPpp (ORCPT ); Thu, 11 Jan 2018 10:45:45 -0500 Date: Thu, 11 Jan 2018 16:45:22 +0100 From: Jiri Olsa To: "Liang, Kan" Cc: peterz@infradead.org, mingo@redhat.com, acme@kernel.org, linux-kernel@vger.kernel.org, tglx@linutronix.de, eranian@google.com, ak@linux.intel.com Subject: Re: [RESEND PATCH V2 3/4] perf/x86/intel: drain PEBS buffer in event read Message-ID: <20180111154522.GA3955@krava> References: <1515424516-143728-1-git-send-email-kan.liang@intel.com> <1515424516-143728-4-git-send-email-kan.liang@intel.com> <20180110103929.GB18942@krava> <6bb19af0-24e5-d711-cb6f-139eb99253c1@linux.intel.com> <20180111111001.GC31767@krava> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.9.1 (2017-09-22) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.30]); Thu, 11 Jan 2018 15:45:40 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: On Thu, Jan 11, 2018 at 10:21:25AM -0500, Liang, Kan wrote: SNIP > > > > hum, but the PEBS drain is specific just for > > PERF_X86_EVENT_AUTO_RELOAD events, right? > > Accurately, PEBS drain is specific for PERF_X86_EVENT_FREERUNNING here. > PERF_X86_EVENT_FREERUNNING event must be _AUTO_RELOAD event. > But in some cases, _AUTO_RELOAD event cannot be _FREERUNNING event. > > Only the event which is both _FREERUNNING and _AUTO_RELOAD need to do PEBS > drain in _read(). > > So it does the check in intel_pmu_pebs_read() > + if (pebs_needs_sched_cb(cpuc)) > + return intel_pmu_drain_pebs_buffer(); > > > > > wrt readability maybe you could add function like: > > The existing function pebs_needs_sched_cb() can do the check. > We just need to expose it, and also the intel_pmu_drain_pebs_buffer(). > > But to be honest, I still cannot see a reason for that. > It could save a call to intel_pmu_pebs_read(), but _read() is not critical > path. It doesn't save much. hum, pmu->read is also called for PERF_SAMPLE_READ for sample, check perf_output_read for non sampling event you shouldn't be able to create PEBS event, there's check in x86_pmu_hw_config I agree it does not save much, it just confused me while I was reading the code, like why is this needed for all events with precise_ip jirka