Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752844AbdCOUQa (ORCPT ); Wed, 15 Mar 2017 16:16:30 -0400 Received: from mail-vk0-f54.google.com ([209.85.213.54]:34062 "EHLO mail-vk0-f54.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750877AbdCOUQ2 (ORCPT ); Wed, 15 Mar 2017 16:16:28 -0400 MIME-Version: 1.0 In-Reply-To: References: <20170313165507.GJ3312@twins.programming.kicks-ass.net> From: Andy Lutomirski Date: Wed, 15 Mar 2017 13:16:06 -0700 Message-ID: Subject: Re: perf: race with automatic rdpmc() disabling To: Vince Weaver Cc: Andy Lutomirski , Peter Zijlstra , "linux-kernel@vger.kernel.org" , Ingo Molnar , Arnaldo Carvalho de Melo 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: 1888 Lines: 48 On Tue, Mar 14, 2017 at 9:45 AM, Vince Weaver wrote: > On Tue, 14 Mar 2017, Andy Lutomirski wrote: > >> On Mon, Mar 13, 2017 at 2:05 PM, Andy Lutomirski wrote: >> > On Mon, Mar 13, 2017 at 9:55 AM, Peter Zijlstra wrote: >> >> On Mon, Mar 13, 2017 at 09:44:02AM -0700, Andy Lutomirski wrote: >> >>> static void x86_pmu_event_mapped(struct perf_event *event) >> >>> { >> >>> if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) >> >>> return; >> >>> >> >>> if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) >> >>> >> >>> <-- thread 1 stalls here >> >>> >> >>> on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); >> >>> } >> >>> >> >>> Suppose you start with perf_rdpmc_allowed == 0. Thread 1 runs >> >>> x86_pmu_event_mapped and gets preempted (or just runs slowly) where I >> >>> marked. Then thread 2 runs the whole function, does *not* update CR4, >> >>> returns to userspace, and GPFs. >> >>> >> >>> The big hammer solution is to stick a per-mm mutex around it. Let me >> >>> ponder whether a smaller hammer is available. >> >> >> >> Reminds me a bit of what we ended up with in kernel/jump_label.c:static_key_slow_inc(). >> >> >> >> >> > >> > One thing I don't get: isn't mmap_sem held for write the whole time? >> >> mmap_sem is indeed held, so my theory is wrong. I can reproduce it, >> but I don't see the bug yet... > > It could still be a PAPI bug, as I'm having absolutely no luck trying to > come up with a plain perf_event reproducer. > > Let me dig through the PAPI code again and make sure I'm not missing > something. Can you give this a try: https://git.kernel.org/pub/scm/linux/kernel/git/luto/linux.git/commit/?h=x86/fixes&id=9edb8154863ba1a7f6f1f15ffe6aecf3cf32bf21 (The link doesn't work yet but it should in a minute or two.) --Andy