From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753020AbaKRELg (ORCPT ); Mon, 17 Nov 2014 23:11:36 -0500 Received: from mx1.redhat.com ([209.132.183.28]:26146 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752591AbaKRELf (ORCPT ); Mon, 17 Nov 2014 23:11:35 -0500 Date: Mon, 17 Nov 2014 23:11:05 -0500 From: Dave Jones To: Linux Kernel Cc: peterz@infradead.org Subject: Re: 3.18-rc2 perf add_event_to_ctx warning Message-ID: <20141118041105.GA5519@redhat.com> Mail-Followup-To: Dave Jones , Linux Kernel , peterz@infradead.org References: <20141030234029.GA28961@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20141030234029.GA28961@redhat.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Oct 30, 2014 at 07:40:29PM -0400, Dave Jones wrote: > WARNING: CPU: 3 PID: 5167 at kernel/events/core.c:1133 add_event_to_ctx+0x1ce/0x1f0() > CPU: 3 PID: 5167 Comm: trinity-c4 Not tainted 3.18.0-rc2+ #79 > 0000000000000009 0000000071bbcfa0 ffff880235ef3c48 ffffffffbd86ef44 > 0000000000000000 0000000000000000 ffff880235ef3c88 ffffffffbd07f1f1 > ffff880235ef3c78 ffff880233e6eee8 ffff880089e4c0f8 0000000001a2978c > Call Trace: > [] dump_stack+0x4f/0x7c > [] warn_slowpath_common+0x81/0xa0 > [] warn_slowpath_null+0x1a/0x20 > [] add_event_to_ctx+0x1ce/0x1f0 > [] __perf_install_in_context+0xe3/0x1b0 > [] remote_function+0x53/0x70 > [] ? schedule_orphans_remove.part.49+0x60/0x60 > [] generic_exec_single+0x156/0x1d0 > [] ? schedule_orphans_remove.part.49+0x60/0x60 > [] smp_call_function_single+0x66/0x110 > [] ? wait_rcu_gp+0x8e/0xb0 > [] task_function_call+0x53/0x80 > [] ? perf_cpu_hrtimer_handler+0x260/0x260 > [] perf_install_in_context+0x83/0xf0 > [] SYSC_perf_event_open+0xb70/0xc70 > [] ? debug_smp_processor_id+0x17/0x20 > [] SyS_perf_event_open+0x9/0x10 > [] tracesys_phase2+0xd4/0xd9 > ---[ end trace 88ffecbb23768dcb ]--- > > > 1133 WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); Still seeing this (unsurprising, as perf hasn't changed any between rc2 & rc5). Any thoughts on this one ? I've not managed to isolate a testcase for it, but I see it every week or so. Dave