Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755451AbaBRKTO (ORCPT ); Tue, 18 Feb 2014 05:19:14 -0500 Received: from cam-admin0.cambridge.arm.com ([217.140.96.50]:52559 "EHLO cam-admin0.cambridge.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754896AbaBRKTJ (ORCPT ); Tue, 18 Feb 2014 05:19:09 -0500 Date: Tue, 18 Feb 2014 10:18:31 +0000 From: Will Deacon To: Drew Richardson Cc: "linux-kernel@vger.kernel.org" , Peter Zijlstra , Arnaldo , Pawel Moll , Wade Cherry Subject: Re: Perf Oops on 3.14-rc2 Message-ID: <20140218101831.GB4178@mudshark.cambridge.arm.com> References: <20140210221758.GB11542@dreric01-Precision-T1600> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140210221758.GB11542@dreric01-Precision-T1600> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Feb 10, 2014 at 10:17:59PM +0000, Drew Richardson wrote: > While adding CPU on/offlining support during perf captures I get an > Oops both on ARM as well as my desktop x86_64. Below is a small > program that duplicates the issue. [...] FWIW I can reproduce this easily with -rc3 on my x86 laptop running hackbench in parallel with a tweaked version of your test (using _SC_NPROCESSORS_ONLN instead of _SC_NPROCESSORS_CONF and hotplugging off both CPU2 and CPU3). I've included part of the log below, but I also saw a WARN which I unfortunately only managed to get a photo of. http://www.willdeacon.ukfsn.org/bitbucket/oopsen/x86/ Will --->8 BUG: unable to handle kernel NULL pointer dereference at 0000000000000078 IP: [] perf_event_aux_ctx+0x4e/0x80 PGD 0 Oops: 0000 [#1608] SMP Modules linked in: CPU: 1 PID: 2270 Comm: hackbench Tainted: G D W 3.14.0-rc3 #2 Hardware name: System76, Inc. Lemur Ultra/Lemur Ultra, BIOS 4.6.4 10/07/2011 task: ffff8800d1ec6180 ti: ffff8800d1fb4000 task.ti: ffff8800d1fb4000 RIP: 0010:[] [] perf_event_aux_ctx+0x4e/0x80 RSP: 0018:ffff8800d1fb5d98 EFLAGS: 00010207 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000000fffd8 RDX: 0000000000000001 RSI: 00000000000fffd8 RDI: ffff8800d1fb5c98 RBP: ffff88021fa55e60 R08: 00000000000fffd8 R09: 00000000df1aa3e9 R10: ffffffff8108790e R11: ffffea000347dec0 R12: ffff8800d1fb5e18 R13: ffffffff8111f580 R14: ffff8800d1fb5e18 R15: ffff8800d1ec6180 FS: 0000000000000000(0000) GS:ffff88021fa40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000078 CR3: 0000000001ad5000 CR4: 00000000000407e0 Stack: 00007f8618b68cc0 0000000000000000 ffff8800d1ec6180 ffffffff81ae17e0 0000000000000000 ffffffff8111f580 ffff8800d1ec6180 ffffffff811196cb 0000000000000064 ffffffff81ae17e0 0000000000000004 0000000000000000 Call Trace: [] ? perf_event_task_tick+0xe0/0xe0 [] ? perf_event_aux+0x9b/0xd0 [] ? perf_event_task+0x78/0xa0 [] ? perf_event_exit_task+0xb0/0x200 [] ? do_exit+0x2b8/0xa00 [] ? vfs_write+0x17c/0x1e0 [] ? do_group_exit+0x38/0xa0 [] ? SyS_exit_group+0x12/0x20 [] ? system_call_fastpath+0x16/0x1b Code: 39 eb 75 27 eb 47 0f 1f 80 00 00 00 00 65 8b 14 25 1c b0 00 00 39 d0 74 26 48 8b 03 48 89 44 24 08 48 8b 5c 24 08 48 39 eb 74 22 <44> 8b 4b 78 45 85 c9 78 e5 8b 83 3c 02 00 00 83 f8 ff 75 ce 4c RIP [] perf_event_aux_ctx+0x4e/0x80 RSP CR2: 0000000000000078 ---[ end trace 0e9345db7c92edc0 ]--- Fixing recursive fault but reboot is needed! -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/