From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756281AbZDBEbd (ORCPT ); Thu, 2 Apr 2009 00:31:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751483AbZDBEbY (ORCPT ); Thu, 2 Apr 2009 00:31:24 -0400 Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:46474 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1751238AbZDBEbX (ORCPT ); Thu, 2 Apr 2009 00:31:23 -0400 Date: Wed, 01 Apr 2009 21:31:12 -0700 (PDT) Message-Id: <20090401.213112.96144152.davem@davemloft.net> To: tj@kernel.org CC: linux-kernel@vger.kernel.org Subject: More problems in setup_pcpu_remap() From: David Miller X-Mailer: Mew version 6.1 on Emacs 22.1 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The way this code is currently designed, it can exhaust all of the VMALLOC address space on both x86 and x86_64, and then some. It allocates PMD_SIZE * num_possible_cpus() of vmalloc space. PMD_SIZE is 2MB, num_possible_cpus() can be up to 4096.... which can easily exceed (VMALLOC_END - VMALLOC_START) Initially I had set out to implement sparc64 support for the new per-cpu stuff, but it looks like I'm stuck finding bugs in the x86 implementation instead :-)