From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753556Ab0INOIX (ORCPT ); Tue, 14 Sep 2010 10:08:23 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:38685 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751160Ab0INOIW convert rfc822-to-8bit (ORCPT ); Tue, 14 Sep 2010 10:08:22 -0400 Subject: Re: [tip:perf/core] perf: Rework the PMU methods From: Peter Zijlstra To: Michael Cree Cc: mingo@redhat.com, dengcheng.zhu@gmail.com, yanmin_zhang@linux.intel.com, gorcunov@gmail.com, fweisbec@gmail.com, robert.richter@amd.com, ming.m.lin@intel.com, tglx@linutronix.de, hpa@zytor.com, paulus@samba.org, linux-kernel@vger.kernel.org, eranian@googlemail.com, will.deacon@arm.com, lethal@linux-sh.org, davem@davemloft.net, mingo@elte.hu, linux-alpha@vger.kernel.org In-Reply-To: <4C8F4A3E.5070603@orcon.net.nz> References:

<4C8B3AD3.5050309@orcon.net.nz> <1284198035.2251.29.camel@laptop> <4C8C6611.20206@orcon.net.nz> <1284380153.2275.261.camel@laptop> <1284383927.2275.284.camel@laptop> <4C8F4A3E.5070603@orcon.net.nz> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT Date: Tue, 14 Sep 2010 16:07:53 +0200 Message-ID: <1284473273.2275.514.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.28.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2010-09-14 at 22:11 +1200, Michael Cree wrote: > > [ 818.575752] Unable to handle kernel paging request at virtual address > 0000000000000060 > [ 818.575752] perf(4935): Oops 0 > [ 818.575752] pc = [] ra = [] ps > = 0000 Not tainted > [ 818.575752] pc is at put_ctx+0x18/0xb0 > [ 818.575752] ra is at free_event+0xec/0x220 > [ 818.575752] v0 = 0000000000000000 t0 = 0000000000000000 t1 = > 0000000000000002 > [ 818.575752] t2 = 0000000000000000 t3 = 0000000000000000 t4 = > fffffc000063e4b0 > [ 818.575752] t5 = fffffc0034837000 t6 = fffffc0034837000 t7 = > fffffc003abe0000 > [ 818.575752] s0 = 0000000000000000 s1 = 0000000000000000 s2 = > 0000000000000000 > [ 818.575752] s3 = ffffffffffffffff s4 = 0000000000000000 s5 = > 0000000000000053 > [ 818.575752] s6 = fffffc0034836c00 > [ 818.575752] a0 = 0000000000000000 a1 = fffffc00311a6980 a2 = > 0000000000000000 > [ 818.575752] a3 = 0000000000000001 a4 = fffffc0000797110 a5 = > 00000001200055f8 > [ 818.575752] t8 = 0000000000000001 t9 = 00000001200396f4 t10= > 0000000000000000 > [ 818.575752] t11= 000000000000000a pv = fffffc000031d650 at = > fffffc000036f8bc > [ 818.575752] gp = fffffc00007d6e40 sp = fffffc003abe3e18 > [ 818.575752] Disabling lock debugging due to kernel taint > [ 818.575752] Trace: > [ 818.575752] [] free_event+0xec/0x220 > [ 818.575752] [] SyS_perf_event_open+0x2a4/0x6f0 > [ 818.575752] [] entSys+0xa4/0xc0 > [ 818.575752] > [ 818.575752] Code: 27bb0047 23bdb5a0 23defff0 b53e0008 b75e0000 > 47f00409 40403121 Does the below cure that? --- commit 0c67b40872326a5340cab51d79a192a5fbaeb484 Author: Peter Zijlstra Date: Mon Sep 13 11:15:58 2010 +0200 perf: Fix free_event() With the context rework stuff we can actually end up freeing an event before it gets attached to a context. Reported-by: Cyrill Gorcunov Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar diff --git a/kernel/perf_event.c b/kernel/perf_event.c index bc46bff..440f9ca 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2150,7 +2150,9 @@ static void free_event(struct perf_event *event) if (event->destroy) event->destroy(event); - put_ctx(event->ctx); + if (event->ctx) + put_ctx(event->ctx); + call_rcu(&event->rcu_head, free_event_rcu); }