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 S1763331AbcIOJ1k (ORCPT <rfc822;w@1wt.eu>);
        Thu, 15 Sep 2016 05:27:40 -0400
Received: from mail-wm0-f42.google.com ([74.125.82.42]:37652 "EHLO
        mail-wm0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1754070AbcIOJ1i (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 15 Sep 2016 05:27:38 -0400
Date: Thu, 15 Sep 2016 11:27:29 +0200
From: Ingo Molnar <mingo@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>, Borislav Petkov <bp@alien8.de>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Jann Horn <jann@thejh.net>, Andrew Lutomirski <luto@kernel.org>,
        Brian Gerst <brgerst@gmail.com>, Peter Anvin <hpa@zytor.com>,
        the arch/x86 maintainers <x86@kernel.org>
Subject: Re: [PATCH 08/12] x86/dumpstack: Pin the target stack in
 save_stack_trace_tsk()
Message-ID: <20160915092729.GA28075@gmail.com>
References: <cover.1473801993.git.luto@kernel.org>
 <7cd5e328dc75d8ccd912e5783665de34503f7c63.1473801993.git.luto@kernel.org>
 <20160915063747.GC13992@gmail.com>
 <CA+55aFxt=HLrELBE=BXUrWdh6LYs4gtu9S=yCruiDffq4HN80w@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CA+55aFxt=HLrELBE=BXUrWdh6LYs4gtu9S=yCruiDffq4HN80w@mail.gmail.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> It absolutely is - compared to the vmalloc costs. Andy has quite noticeable 
> slowdowns without the stack reuse - and the stack reuse requires the delayed 
> freeing. With the stack reuse, fork/exit actually sped up.

Ok, great, that's convincing!

I'm still applying it two-phase and I'll wait for v2 of the second half of the 
series, to have the fix Josh alluded to.

Thanks,

	Ingo