Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751844AbdGRAHa (ORCPT ); Mon, 17 Jul 2017 20:07:30 -0400 Received: from mail-yw0-f195.google.com ([209.85.161.195]:34586 "EHLO mail-yw0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751775AbdGRAH2 (ORCPT ); Mon, 17 Jul 2017 20:07:28 -0400 MIME-Version: 1.0 In-Reply-To: References: <20170628101248.GB5981@leverpostej> <20170628105600.GC5981@leverpostej> <20170628174900.GG8252@leverpostej> <20170704090313.xyb5lntyy55ga7dm@hirez.programming.kicks-ass.net> <20170704093345.GB19649@leverpostej> <20170704102159.GB20062@leverpostej> <20170711090358.6si4un4guz6dbxkz@gmail.com> From: Kyle Huey Date: Mon, 17 Jul 2017 17:07:26 -0700 Message-ID: Subject: Re: [PATCH] perf/core: generate overflow signal when samples are dropped (WAS: Re: [REGRESSION] perf/core: PMU interrupts dropped if we entered the kernel in the "skid" region) To: Ingo Molnar Cc: Mark Rutland , gregkh@linuxfoundation.org, Peter Zijlstra , Vince Weaver , "Jin, Yao" , stable@vger.kernel.org, Alexander Shishkin , Arnaldo Carvalho de Melo , Jiri Olsa , Linus Torvalds , Namhyung Kim , Stephane Eranian , Thomas Gleixner , acme@kernel.org, jolsa@kernel.org, kan.liang@intel.com, Will Deacon , open list , "Robert O'Callahan" Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2064 Lines: 47 On Tue, Jul 11, 2017 at 8:32 AM, Kyle Huey wrote: > On Tue, Jul 11, 2017 at 2:03 AM, Ingo Molnar wrote: >> >> * Kyle Huey wrote: >> >>> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan wrote: >>> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote: >>> >> Should any of those be moved into the "should be dropped" pile? >>> > >>> > Why not be conservative and clear every sample you're not sure about? >>> > >>> > We'd appreciate a fix sooner rather than later here, since rr is >>> > currently broken on every stable Linux kernel and our attempts to >>> > implement a workaround have failed. >>> > >>> > (We have separate "interrupt" and "measure" counters, and I thought we >>> > might work around this regression by programming the "interrupt" >>> > counter to count kernel events as well as user events (interrupting >>> > early is OK), but that caused our (completely separate) "measure" >>> > counter to report off-by-one results (!), which seems to be a >>> > different bug present on a range of older kernels.) >>> >>> This seems to have stalled out here unfortunately. >>> >>> Can we get a consensus (from ingo or peterz?) on Mark's question? Or, >>> alternatively, can we move the patch at the top of this thread forward >>> on the stable branches until we do reach an answer to that question? >>> >>> We've abandoned hope of working around this problem in rr and are >>> currently broken for all of our users with an up-to-date kernel, so >>> the situation for us is rather dire at the moment I'm afraid. >> >> Sorry about that - I've queued up a revert for the original commit and will send >> the fix to Linus later today. I've added a -stable tag as well so it can be >> forwarded to Greg the moment it hits upstream. > > Great, thank you. > > - Kyle Hi again, I saw that the revert landed on perf/urgent but it doesn't look like that got pulled by Linus in time for 4.13-rc1. Consider this a gentle poke to please get this merged :) - Kyle