From owner-freebsd-current@FreeBSD.ORG  Tue Aug 26 07:36:49 2003
Return-Path: <owner-freebsd-current@FreeBSD.ORG>
Delivered-To: freebsd-current@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id AD42A16A4BF; Tue, 26 Aug 2003 07:36:49 -0700 (PDT)
Received: from casselton.net (casselton.net [63.165.140.2])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id 96C4143FCB; Tue, 26 Aug 2003 07:36:48 -0700 (PDT)
	(envelope-from tinguely@casselton.net)
Received: from casselton.net (localhost [127.0.0.1])
	by casselton.net (8.12.8p1/8.12.8) with ESMTP id h7QEamtX076247;
	Tue, 26 Aug 2003 09:36:48 -0500 (CDT)
	(envelope-from tinguely@casselton.net)
Received: (from tinguely@localhost)
	by casselton.net (8.12.8p1/8.12.8/Submit) id h7QEal0s076246;
	Tue, 26 Aug 2003 09:36:47 -0500 (CDT)
Date: Tue, 26 Aug 2003 09:36:47 -0500 (CDT)
From: Mark Tinguely <tinguely@casselton.net>
Message-Id: <200308261436.h7QEal0s076246@casselton.net>
To: l.ertl@univie.ac.at, tinguely@casselton.net
In-Reply-To: <20030826160918.P29045@pcle2.cc.univie.ac.at>
cc: alc@freebsd.org
cc: bmilekic@freebsd.org
cc: current@freebsd.org
Subject: Re: Another pmap related panic
X-BeenThere: freebsd-current@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
List-Id: Discussions about the use of FreeBSD-current
	<freebsd-current.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-current>
List-Post: <mailto:freebsd-current@freebsd.org>
List-Help: <mailto:freebsd-current-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Tue, 26 Aug 2003 14:36:49 -0000

Thank-you,

The fact that pmap_pte_quick() panics on the untrue mutex should
indicate that it is possible that 2 processors may enter pmap_pte_quick()
at the same time and therefore it is possible to have the one processor
invalidate the VA/PA mapping using PADDR1/PMAP1. If that is true then
the first processor should trap/panic when dereferencing the VA address.

If the above is true, a PADDR1 mutex could be added, or use a seperate
PADDR/PMAP per processor. Looks like there is already mutex for the
copy maps. Did you want me to work up a test PADDR mutex?

--Mark.