From mboxrd@z Thu Jan  1 00:00:00 1970
From: Marcelo Tosatti <mtosatti@redhat.com>
Subject: Re: Linux x86 guest panics in skb_copy_bits
Date: Mon, 4 May 2009 19:40:06 -0300
Message-ID: <20090504224006.GB10616@amt.cnet>
References: <ce02da610905031140w76c44964sac142c1965621e98@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: kvm@vger.kernel.org
To: Justin Dossey <jbd@justindossey.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.redhat.com ([66.187.237.31]:52594 "EHLO mx2.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751912AbZEDWlI (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 4 May 2009 18:41:08 -0400
Content-Disposition: inline
In-Reply-To: <ce02da610905031140w76c44964sac142c1965621e98@mail.gmail.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Justin,

On Sun, May 03, 2009 at 11:40:47AM -0700, Justin Dossey wrote:
> Hi all,
>=20
> I have a pretty straightforward setup.
>=20
> Hypervisor:
> dual xeon e5205 running Gentoo Linux
> kernel 2.6.27 with virtio devices enabled
> kvm 84
> libvirt 0.5.1
>=20
> Guest:
> 32-bit, virtio for nic and disk, qcow2.
> Linux 2.6.28.
>=20
> Network is bridged using tap and brctl.
>=20
> I'm running Apache on the guest.=A0 Whenever I send enough data throu=
gh
> the virtual NIC, I get a panic in skb_copy_bits.=A0 I've tried using =
the
> e1000 driver instead of the virtio one, but that makes no difference.
>=20
> Has anyone else seen this behavior before?=A0 I got this on 2.6.27 an=
d 2.6.28.
>=20
> Here's a snippet:
>=20
> [280204.340016]=A0 [<c02253e2>] panic+0x4e/0xea
> [280204.340016]=A0 [<c05906b9>] oops_end+0x8f/0xa3
> [280204.340016]=A0 [<c0204e94>] die+0x57/0x5f
> [280204.340016]=A0 [<c0592192>] do_page_fault+0x605/0x6bc
> [280204.340016]=A0 [<c059010d>] ? _spin_lock+0x15/0x18
> [280204.340016]=A0 [<c04bfad8>] ? __qdisc_run+0xe6/0x1a7
> [280204.340016]=A0 [<c0591b8d>] ? do_page_fault+0x0/0x6bc
> [280204.340016]=A0 [<c0590482>] error_code+0x72/0x78
> [280204.340016]=A0 [<c04ace8c>] ? skb_copy_bits+0x4f/0x1c4
> [280204.340016]=A0 [<c0215864>] ? kvm_set_pte+0x26/0x29
> [280204.340016]=A0 [<c054889c>] xdr_skb_read_bits+0x1f/0x37
> [280204.340016]=A0 [<c054872b>] xdr_partial_copy_from_skb+
> 0x117/0x16c
> [280204.340016]=A0 [<c0549ec4>] xs_tcp_data_recv+0x245/0x3de
> [280204.340016]=A0 [<c054887d>] ? xdr_skb_read_bits+0x0/0x37
> [280204.340016]=A0 [<c04e07d6>] tcp_read_sock+0x8c/0x1e2
> [280204.340016]=A0 [<c0549c7f>] ? xs_tcp_data_recv+0x0/0x3de
> [280204.340016]=A0 [<c054a5d1>] xs_tcp_data_ready+0x54/0x64
> [280204.340016]=A0 [<c04e9469>] tcp_rcv_established+0x524/0x7b7
> [280204.340016]=A0 [<c04ee4b2>] tcp_v4_do_rcv+0x173/0x2dc

Seems to be an issue with paravirt mmu. Do you happen to have
CONFIG_DEBUG_PAGEALLOC turned on your guests?