From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755293Ab1DZM4t (ORCPT ); Tue, 26 Apr 2011 08:56:49 -0400 Received: from mail-ww0-f44.google.com ([74.125.82.44]:55154 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752694Ab1DZM4r (ORCPT ); Tue, 26 Apr 2011 08:56:47 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer:content-transfer-encoding; b=jLXceVByP3SqW6K9XA8odKdNMfHM2AkCXOnhgT8Q5E34bc6Js9jSxvqWaADV2BXLpq +O2EM4QzQSDBLp+W8L9ztbinjBRzgelQpfju+A0XYIsXpOreWU+qUlYcor8ruTuUV4Wa tueL0a/ooKrftIJPZ8zF9BBq9pTLFtG7uOVUY= Subject: Re: [BUG] perf and kmemcheck : fatal combination From: Eric Dumazet To: Peter Zijlstra Cc: Pekka Enberg , Ingo Molnar , Arnaldo Carvalho de Melo , Paul Mackerras , Vegard Nossum , linux-kernel , Mathieu Desnoyers In-Reply-To: <1303821188.20212.264.camel@twins> References: <1303747731.2747.182.camel@edumazet-laptop> <1303803525.20212.20.camel@twins> <20110426080443.GA806@elte.hu> <1303808257.3012.3.camel@edumazet-laptop> <1303811635.3358.21.camel@edumazet-laptop> <1303813668.3358.22.camel@edumazet-laptop> <1303820855.3358.49.camel@edumazet-laptop> <1303821188.20212.264.camel@twins> Content-Type: text/plain; charset="UTF-8" Date: Tue, 26 Apr 2011 14:56:43 +0200 Message-ID: <1303822603.3358.51.camel@edumazet-laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Le mardi 26 avril 2011 à 14:33 +0200, Peter Zijlstra a écrit : > On Tue, 2011-04-26 at 14:27 +0200, Eric Dumazet wrote: > > Thats far from trivial, maybe because we dont have NOTRACK api for > > percpu allocations ? > > We can't use per-cpu allocations from NMI context because of the same > problem, per-cpu uses vmalloc and vmalloc needs faults. Hence that > shouldn't be a problem. > > It looks like you covered most of it though, the buffer and the > callchain stuff, aside from that it should only use some static data. > > Pekka, what does kmemcheck do for .data and .bss things? Hmm, maybe I have a problem because of the WARN_ON in kmemcheck and my boot had "log_buf_len=32M", so kmemcheck was called again I am now trying to remve the line 634 from arch/x86/mm/kmemcheck/kmemcheck.c [ 4564.554310] WARNING: at arch/x86/mm/kmemcheck/kmemcheck.c:634 kmemcheck_fault+0xa9/0xc0() [ 4564.554312] Hardware name: ProLiant BL460c G6 [ 4564.554313] Modules linked in: nfsd lockd auth_rpcgss sunrpc tg3 libphy sg [last unloaded: x_tables] [ 4564.554319] Pid: 4276, comm: perf Not tainted 2.6.39-rc4-00369-g23cf772-dirty #561 [ 4564.554320] Call Trace: [ 4564.554322] [] ? kmemcheck_fault+0xa9/0xc0 [ 4564.554329] [] warn_slowpath_common+0x8b/0xc0 [ 4564.554331] [] warn_slowpath_null+0x15/0x20 [ 4564.554333] [] kmemcheck_fault+0xa9/0xc0 [ 4564.554337] [] do_page_fault+0x1fb/0x560 [ 4564.554342] [] ? put_dec+0x59/0x60 [ 4564.554344] [] ? number+0x301/0x330 [ 4564.554347] [] page_fault+0x1f/0x30 [ 4564.554352] [] ? vt_console_print+0x85/0x360 [ 4564.554355] [] ? vt_console_print+0x7a/0x360 [ 4564.554358] [] __call_console_drivers+0x89/0xa0 [ 4564.554360] [] _call_console_drivers+0x4b/0x80 [ 4564.554362] [] console_unlock+0xe7/0x1e0 [ 4564.554365] [] vprintk+0x1ee/0x4a0 [ 4564.554368] [] ? kmemcheck_fault+0xa9/0xc0 [ 4564.554370] [] printk+0x67/0x70 [ 4564.554372] [] ? kmemcheck_fault+0xa9/0xc0 [ 4564.554375] [] warn_slowpath_common+0x39/0xc0 [ 4564.554377] [] warn_slowpath_null+0x15/0x20 [ 4564.554379] [] kmemcheck_fault+0xa9/0xc0 [ 4564.554381] [] do_page_fault+0x1fb/0x560 [ 4564.554384] [] ? intel_pmu_drain_bts_buffer+0x2b/0x170 [ 4564.554387] [] page_fault+0x1f/0x30 [ 4564.554390] [] ? x86_perf_event_update+0x12/0x70 [ 4564.554392] [] ? intel_pmu_save_and_restart+0x11/0x20 [ 4564.554394] [] intel_pmu_handle_irq+0x1d4/0x420 [ 4564.554397] [] perf_event_nmi_handler+0x50/0xc0 [ 4564.554399] [] notifier_call_chain+0x53/0x80 [ 4564.554401] [] __atomic_notifier_call_chain+0x48/0x70 [ 4564.554404] [] atomic_notifier_call_chain+0x11/0x20 [ 4564.554406] [] notify_die+0x2e/0x30 [ 4564.554407] [] do_nmi+0x4f/0x200 [ 4564.554409] [] nmi+0x1a/0x20 [ 4564.554411] [] ? intel_pmu_enable_all+0x9d/0x110