From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755443Ab1ATLMy (ORCPT ); Thu, 20 Jan 2011 06:12:54 -0500 Received: from mail-ww0-f44.google.com ([74.125.82.44]:46498 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755260Ab1ATLMw (ORCPT ); Thu, 20 Jan 2011 06:12:52 -0500 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=SExkOeXaavNaDVC6gVizj8/5zo7KD9nWRSFvZM4glUWi1hHdl3v0lZHz2HLB/+eSU1 UBL7Wc/dEV+6wgbkmi22tRPihzg3ct90OIKZqKRUBirgoubLra+4YpjNGvF97BjANjEb +Sy19wSMCZXR1POiMNAlslancp09RbKlga4m8= Subject: Re: percpu related boot crash on x86 From: Eric Dumazet To: Peter Zijlstra Cc: Pekka Enberg , Ingo Molnar , Tejun Heo , Linus Torvalds , Linux Kernel Mailing List , Thomas Gleixner , "H. Peter Anvin" , Andrew Morton In-Reply-To: <1295520467.28776.153.camel@laptop> References: <20110119120200.GA1057@elte.hu> <1295441307.28776.15.camel@laptop> <20110119131329.GB14096@mtj.dyndns.org> <20110119205353.GA14810@elte.hu> <20110119231116.GA3896@elte.hu> <4D37F2C9.8000906@kernel.org> <1295520467.28776.153.camel@laptop> Content-Type: text/plain; charset="UTF-8" Date: Thu, 20 Jan 2011 12:12:47 +0100 Message-ID: <1295521967.2825.15.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 jeudi 20 janvier 2011 à 11:47 +0100, Peter Zijlstra a écrit : > On Thu, 2011-01-20 at 10:31 +0200, Pekka Enberg wrote: > > if (!irqs_disabled()) > > > > guard around the debugging code to make vfree() always work with IRQs > > disabled. > > That won't be sufficient, __purge_vmap_area_lazy() needs to call > flush_tlb_kernel_range() occasionally. > > There really is a good reason vmalloc()/vfree() don't work with > interrupts disabled. > Hmm, I would try to increase PERCPU_DYNAMIC_RESERVE, or pcpu_mem_alloc() could try to use kzalloc() even for allocations bigger than one PAGE, and fallback to vzalloc(). We have more alloc_percpu() uses, we also should try to use first chunk if possible.