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 S965388AbcKJRkF (ORCPT <rfc822;w@1wt.eu>);
        Thu, 10 Nov 2016 12:40:05 -0500
Received: from frisell.zx2c4.com ([192.95.5.64]:50970 "EHLO frisell.zx2c4.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S965117AbcKJRkC (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 10 Nov 2016 12:40:02 -0500
MIME-Version: 1.0
In-Reply-To: <alpine.DEB.2.20.1611101351260.3501@nanos>
References: <CAHmME9oSUcAXVMhpLt0bqa9DKHE8rd3u+3JDb_wgviZnOpP7JA@mail.gmail.com>
 <alpine.DEB.2.20.1611092227200.3501@nanos> <CAHmME9pGoRogjHSSy-G-sB4-cHMGcjCeW9PSrNw1h5FsKzfWAw@mail.gmail.com>
 <alpine.DEB.2.20.1611100959040.3501@nanos> <CAHmME9pHYA82M3iDNfDtDE96gFaZORSsEAn_KnePd3rhFioqHQ@mail.gmail.com>
 <alpine.DEB.2.20.1611101351260.3501@nanos>
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 10 Nov 2016 18:39:54 +0100
X-Gmail-Original-Message-ID: <CAHmME9rv8CfgY87S_HVN3njc2RnisjoxzfZxY=H=2FzZkrQqLg@mail.gmail.com>
Message-ID: <CAHmME9rv8CfgY87S_HVN3njc2RnisjoxzfZxY=H=2FzZkrQqLg@mail.gmail.com>
Subject: Re: Proposal: HAVE_SEPARATE_IRQ_STACK?
To: Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>, linux-mips@linux-mips.org,
        linux-mm@kvack.org, WireGuard mailing list <wireguard@lists.zx2c4.com>,
        k@vodka.home.kg
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Hi Thomas,

On Thu, Nov 10, 2016 at 2:00 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> Do not even think about going there. That's going to be a major
> mess.

Lol! Okay. Thank you for reigning in my clearly reckless
propensities... Sometimes playing in traffic is awfully tempting.

>
> As a short time workaround you can increase THREAD_SIZE_ORDER for now and
> then fix it proper with switching to seperate irq stacks.

Okay. I think in the end I'll kmalloc, accept the 16% slowdown [1],
and focus efforts on having a separate IRQ stack. Matt emailed in this
thread saying he was already looking into it, so I think by the time
that slowdown makes a difference, we'll have the right pieces in place
anyway.

Thanks for the guidance here.

Regards,
Jason

[1] https://git.zx2c4.com/WireGuard/commit/?id=cc3d7df096a88cdf96d016bdcb2f78fa03abb6f3