From owner-freebsd-smp  Thu Sep 24 22:47:22 1998
Return-Path: <owner-freebsd-smp@FreeBSD.ORG>
Received: (from majordom@localhost)
          by hub.freebsd.org (8.8.8/8.8.8) id WAA02336
          for freebsd-smp-outgoing; Thu, 24 Sep 1998 22:47:22 -0700 (PDT)
          (envelope-from owner-freebsd-smp@FreeBSD.ORG)
Received: from midten.fast.no (midten.fast.no [195.139.251.11])
          by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA02327;
          Thu, 24 Sep 1998 22:47:17 -0700 (PDT)
          (envelope-from tegge@fast.no)
Received: from fast.no (IDENT:tegge@midten.fast.no [195.139.251.11])
	by midten.fast.no (8.9.1/8.9.1) with ESMTP id HAA26153;
	Fri, 25 Sep 1998 07:43:51 +0200 (CEST)
Message-Id: <199809250543.HAA26153@midten.fast.no>
To: fn@radio-do.de
Cc: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG
Subject: Re: Weired top display at smp current kernel from today
From: Tor.Egge@fast.no
In-Reply-To: Your message of "Thu, 24 Sep 1998 18:20:25 +0200"
References: <19980924182025.A9605@radio-do.de>
X-Mailer: Mew version 1.70 on Emacs 19.34.1
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Date: Fri, 25 Sep 1998 07:43:46 +0200
Sender: owner-freebsd-smp@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.org

> On Thu, Sep 24, 1998 at 10:58:37AM +0200, Frank Nobis wrote:
> > 
> > I thought it was gone here, but...
> 
> I can now reproduce the problem, but yet don't understand why it happens.


Replacing the aout /sbin/init with an elf /sbin/init seems to be sufficient
to trigger this problem.

Looking at mp_lock using 

	gdb -k /kernel.gdb /dev/mem
	...
	print/x mp_lock
	

gave 0x1 or 0x1000001  with the aout /sbin/init, but
     0x2 or 0x1000002  with the elf  /sbin/init.

This means that when a cpu returns to userland, mp_lock is still 0x1 or
0x1000001.  Which blocks the other CPU until the CPU holding the giant
kernel lock enters _idle.

- Tor Egge

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-smp" in the body of the message