Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1751938AbbKPIyP (ORCPT <rfc822;w@1wt.eu>);
	Mon, 16 Nov 2015 03:54:15 -0500
Received: from www.linutronix.de ([62.245.132.108]:37547 "EHLO
	Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750911AbbKPIyK (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 16 Nov 2015 03:54:10 -0500
Date: Mon, 16 Nov 2015 09:53:27 +0100 (CET)
From: Thomas Gleixner <tglx@linutronix.de>
To: Linus Torvalds <torvalds@linux-foundation.org>
cc: Kyle Sanderson <kyle.leet@gmail.com>,
        Linux-Kernal <linux-kernel@vger.kernel.org>
Subject: Re: BUG: unable to handle kernel paging request at
 ffffe8ff7fc00001
In-Reply-To: <CA+55aFzTTUYqSWRsiX_XnouKQbXMweLS0JFeyEXe72dWA--1Rw@mail.gmail.com>
Message-ID: <alpine.DEB.2.11.1511160935520.3761@nanos>
References: <CACsaVZK1cbH+Aq+zG8zNs=wk7jacFTpnwJo8bQvy6L_bd4XLFQ@mail.gmail.com> <CA+55aFzTTUYqSWRsiX_XnouKQbXMweLS0JFeyEXe72dWA--1Rw@mail.gmail.com>
User-Agent: Alpine 2.11 (DEB 23 2013-08-11)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Linutronix-Spam-Score: -1.0
X-Linutronix-Spam-Level: -
X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required,  ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 1704
Lines: 52

On Sun, 15 Nov 2015, Linus Torvalds wrote:
> On Sun, Nov 15, 2015 at 2:28 PM, Kyle Sanderson <kyle.leet@gmail.com> wrote:
> > [] BUG: unable to handle kernel paging request at ffffe8ff7fc00001
> > [] IP: [<ffffffff810a174f>] kstat_irqs+0x4f/0x90
> > [] CPU: 2 PID: 1078 Comm: usage.pl Not tainted 4.1.7-hardened-r1 #1
> > [] Hardware name: Supermicro Super Server/X10SRi-F, BIOS 1.0b 04/21/2015
> RSI: 000060f700000001
> > [] Call Trace:
> > []  [<>] kstat_irqs_usr+0x1e/0x40

> The code ends up being
> 
>   mov    0x48(%r13),%rsi
>   mov    __per_cpu_offset(,%rcx,8),%rcx
>   add    (%rsi,%rcx,1),%ebx <-- trapping instruction
> 
> which is just the
> 
>    sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
> 
> part of kstat_irqs().
> 
> Your registers being
> 
>    RSI: 000060f700000001
>    RCX: ffff88087fc00000
> 
> and it's RSI that makes no sense - RCX looks like a real kernel
> pointer. So it looks like it's the "desc->kstat_irqs" thing that is
> for some reason garbage.
> 
> I don't see any sane possible reason this would happen, though.
> Thomas, does this look like anything you've seen before?

No. What's strange is that this does explode while reading
/proc/interrupts and it did not happen when interrupt accounting took
place. 

Though this looks like memory corruption and it might be an interrupt
which fired only at boot time, i.e. before the corruption happened.

No idea how to decode that. Kyle, is that reproducible?

Thanks,

	tglx

--
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/