Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932274AbZICUpx (ORCPT ); Thu, 3 Sep 2009 16:45:53 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932243AbZICUpw (ORCPT ); Thu, 3 Sep 2009 16:45:52 -0400 Received: from claw.goop.org ([74.207.240.146]:41327 "EHLO claw.goop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932235AbZICUpw (ORCPT ); Thu, 3 Sep 2009 16:45:52 -0400 Message-ID: <4AA02B02.7080101@goop.org> Date: Thu, 03 Sep 2009 13:45:54 -0700 From: Jeremy Fitzhardinge User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.1) Gecko/20090814 Fedora/3.0-2.6.b3.fc11 Lightning/1.0pre Thunderbird/3.0b3 MIME-Version: 1.0 To: "H. Peter Anvin" CC: mingo@redhat.com, linux-kernel@vger.kernel.org, jeremy.fitzhardinge@citrix.com, stable@kernel.org, tglx@linutronix.de, mingo@elte.hu, linux-tip-commits@vger.kernel.org, Tejun Heo Subject: Re: [tip:x86/asm] x86/i386: Make sure stack-protector segment base is cache aligned References: <4AA01893.6000507@goop.org> <4AA02687.9080406@zytor.com> In-Reply-To: <4AA02687.9080406@zytor.com> X-Enigmail-Version: 0.97a Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1302 Lines: 30 On 09/03/09 13:26, H. Peter Anvin wrote: > With the new zero-based percpu segment, it seems we should be able to > subsume the stack protector into the percpu segment and reference both > via %gs -- we just have to reserve the first 24 bytes of the segment, > and being able to reduce the number of segments we need in the kernel is > good for multiple reasons. > > Tejun - am I missing something why that would be hard or impossible? > Two problems: * gcc generates %gs: references for stack-protector, but we use %fs for percpu data (because restoring %fs is faster if it's a null selector; TLS uses %gs). I guess we could use %fs if !CONFIG_CC_STACKPROTECTOR, or %gs if we are using it (though that has some fiddly ramifications for things like ptrace). * The i386 percpu %fs base is offset by -__per_cpu_start from the percpu variables, so we can directly refer to %fs:per_cpu__foo. I'm not sure what it would take to unify i386 to use the same scheme as x86-64. Neither looks insoluble. J -- 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/