From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753268AbbBYNxa (ORCPT <rfc822;w@1wt.eu>);
	Wed, 25 Feb 2015 08:53:30 -0500
Received: from mail-wg0-f49.google.com ([74.125.82.49]:44042 "EHLO
	mail-wg0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753035AbbBYNx0 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 25 Feb 2015 08:53:26 -0500
Date: Wed, 25 Feb 2015 14:53:21 +0100
From: Ingo Molnar <mingo@kernel.org>
To: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>,
        Andy Lutomirski <luto@amacapital.net>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Steven Rostedt <rostedt@goodmis.org>, Borislav Petkov <bp@alien8.de>,
        "H. Peter Anvin" <hpa@zytor.com>, Oleg Nesterov <oleg@redhat.com>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Alexei Starovoitov <ast@plumgrid.com>, Will Drewry <wad@chromium.org>,
        Kees Cook <keescook@chromium.org>, X86 ML <x86@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 2/4] x86: get rid of KERNEL_STACK_OFFSET
Message-ID: <20150225135321.GA767@gmail.com>
References: <1424803895-4420-1-git-send-email-dvlasenk@redhat.com>
 <1424803895-4420-2-git-send-email-dvlasenk@redhat.com>
 <20150225085351.GA16165@gmail.com>
 <CAK1hOcONsacP+6dQQcjuk8J7XAmh1WiN+3O62tP9ib8eYxStGg@mail.gmail.com>
 <54EDCD31.3000203@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <54EDCD31.3000203@redhat.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


* Denys Vlasenko <dvlasenk@redhat.com> wrote:

> > The decision on how exactly we should fix 
> > KERNEL_STACK_OFFSET (set it to SIZEOF_PTREGS or to 
> > zero) depends on whether we switch to using PUSHes, or 
> > not. What do you think?

Yes.

> A data point. I implemented push-based creation of 
> pt_regs and benchmarked it. The patch is on top of all my 
> latest patches sent to ML.
> 
> On SandyBridge CPU, it does not get slower: seems to be 1 
> cycle faster per syscall.
> 
> We lose a number of large insns there:
> 
>     text           data     bss     dec     hex filename
> -   9863              0       0    9863    2687 entry_64.o
> +   9671              0       0    9671    25c7 entry_64.o

That's a nice reduction in I$ footprint ...

> +	/* Construct struct pt_regs on stack */
> +	pushq	$__USER_DS		/* pt_regs->ss */
> +	pushq	PER_CPU_VAR(old_rsp)	/* pt_regs->sp */
> +	pushq	%r11			/* pt_regs->flags */

Btw., this could also construct all the dwarf annotations 
in a natural, maintainable fashion - pushq_cfi and friends?

> +	pushq	$__USER_CS		/* pt_regs->cs */
> +	pushq	%rcx			/* pt_regs->ip */
> +	pushq	%rax			/* pt_regs->orig_ax */
> +	pushq	%rdi			/* pt_regs->di */
> +	pushq	%rsi			/* pt_regs->si */
> +	pushq	%rdx			/* pt_regs->dx */
> +	pushq	%rcx			/* pt_regs->cx */
> +	pushq	$-ENOSYS		/* pt_regs->ax */
> +	pushq	%r8			/* pt_regs->r8 */
> +	pushq	%r9			/* pt_regs->r9 */
> +	pushq	%r10			/* pt_regs->r10 */
> +	sub	$(7*8),%rsp /* pt_regs->r11,bp,bx,r12-15 */

So the 'SUB' there is a bit sad, but push sequences are 
generally easier to read, so I like it altogether.

Then we could indeed get rid of KERNEL_STACK_OFFSET.

Thanks,

	Ingo