From gordon@lost.iafrica.com Mon Apr 26 04:13:56 1999
Return-Path: <gordon@lost.iafrica.com>
Received: from lost.iafrica.com (lost.iafrica.com [196.31.1.30])
	by hub.freebsd.org (Postfix) with ESMTP id 863D5150E1
	for <FreeBSD-gnats-submit@freebsd.org>; Mon, 26 Apr 1999 04:13:43 -0700 (PDT)
	(envelope-from gordon@lost.iafrica.com)
Received: from gordon by lost.iafrica.com with local (Exim 2.12 #1)
	id 10bjKY-000KIu-00
	for FreeBSD-gnats-submit@freebsd.org; Mon, 26 Apr 1999 13:13:42 +0200
Message-Id: <E10bjKY-000KIu-00@lost.iafrica.com>
Date: Mon, 26 Apr 1999 13:13:42 +0200
From: gvg@uunet.co.za
Sender: "Gordon Greeff,UUNET - Cape Town,+27.21.658.8720,+27.82.770.3587" <gordon@lost.iafrica.com>
Reply-To: gvg@uunet.co.za
To: FreeBSD-gnats-submit@freebsd.org
Subject: panic: page fault in generic_bzero
X-Send-Pr-Version: 3.2

>Number:         11330
>Category:       kern
>Synopsis:       page fault in generic_bzero
>Confidential:   no
>Severity:       critical
>Priority:       high
>Responsible:    freebsd-bugs
>State:          closed
>Quarter:        
>Keywords:       
>Date-Required:  
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Mon Apr 26 04:20:00 PDT 1999
>Closed-Date:    Tue May 16 14:35:35 PDT 2000
>Last-Modified:  Tue May 16 14:37:07 PDT 2000
>Originator:     Gordon Greeff
>Release:        FreeBSD 3.1-STABLE i386
>Organization:
UUNET South Africa
>Environment:

FreeBSD proxy05.iafrica.com 3.1-STABLE FreeBSD 3.1-STABLE #0: Mon Apr 26 12:54:10 SAST 1999     gordon@proxy05.iafrica.com:/usr/src/sys/compile/PROXY05  i386 

machine         "i386"
cpu             "I686_CPU"
ident           "PROXY05"
maxusers        512

options         INET                    #InterNETworking
options         FFS                     #Berkeley Fast Filesystem
options         FFS_ROOT                #FFS usable as root device [keep this!]
#options                MFS                     #Memory Filesystem
#options                NFS                     #Network Filesystem
#options                PROCFS                  #Process filesystem
options         "COMPAT_43"             #Compatible with BSD 4.3 [KEEP THIS!]
options         SCSI_DELAY=15000        #Be pessimistic about Joe SCSI device
options         SOFTUPDATES

config          kernel  root on da0

controller      isa0
controller      pci0

controller      fdc0    at isa? port "IO_FD1" bio irq 6 drq 2
disk            fd0     at fdc0 drive 0
# A single entry for any of these controllers (ncr, ahb, ahc) is
# sufficient for any number of installed devices.
controller      ahc0
controller      ncr0
controller      scbus0
device          da0
device          pass0

# atkbdc0 controlls both the keyboard and the PS/2 mouse
controller      atkbdc0 at isa? port IO_KBD tty
device          atkbd0  at isa? tty irq 1
device          psm0    at isa? tty irq 12
device          vga0    at isa? port ? conflicts

# splash screen/screen saver
pseudo-device   splash

# syscons is the default console driver, resembling an SCO console
device          sc0     at isa? tty

device          npx0    at isa? port IO_NPX irq 13

device          sio0    at isa? port "IO_COM1" flags 0x10 tty irq 4
device          sio1    at isa? port "IO_COM2" tty irq 3

# Order is important here due to intrusive probes, do *not* alphabetize
# this list of network interfaces until the probes have been fixed.
# Right now it appears that the ie0 must be probed before ep0. See
# revision 1.20 of this file.
device fxp0
device xl0

pseudo-device   loop
pseudo-device   ether
pseudo-device   pty     128
pseudo-device   ccd     4
pseudo-device   gzip            # Exec gzipped a.out's

# KTRACE enables the system-call tracing facility ktrace(2).
# This adds 4 KB bloat to your kernel, and slightly increases
# the costs of each syscall.

# This provides support for System V shared memory and message queues.
#
options         SYSVSHM
options         SYSVMSG


>Description:

	repeatable panic "page fault in kernel mode".
	nm kernel |sort |less (and eyeball) shows problem to
	lie in generic_bzero in /sys/i386/i386/support.s

>How-To-Repeat:

	when disks are under high load (multiple cp -R's of /usr/src onto
	a ccd) it happens within a few seconds

>Fix:
	
	unknown

>Release-Note:
>Audit-Trail:

 Date: Mon, 26 Apr 1999 13:22:45 +0200
 From: Poul-Henning Kamp <phk@critter.freebsd.dk>
 To: gvg@uunet.co.za
 Cc: FreeBSD-gnats-submit@FreeBSD.ORG
 Subject: Re: kern/11330: panic: page fault in generic_bzero 

 Last time I saw this, my CPU-fan had stopped.
 
 generic_bcopy and friends really stress the I/O section of the CPU
 so any weakness is likely to trigger here first.
 
 Check your hardware.
 
 --
 Poul-Henning Kamp             FreeBSD coreteam member
 phk@FreeBSD.ORG               "Real hackers run -current on their laptop."
 FreeBSD -- It will take a long time before progress goes too far!


 Date: Mon, 26 Apr 1999 14:13:36 +0200 (SAST)
 From: Gordon Greeff <gvg@uunet.co.za>
 Reply-To: Gordon Greeff <gvg@uunet.co.za>
 To: Poul-Henning Kamp <phk@critter.freebsd.dk>
 Cc: FreeBSD-gnats-submit@FreeBSD.ORG
 In-Reply-To: <15544.925125765@critter.freebsd.dk>
 Subject: Re: kern/11330: panic: page fault in generic_bzero 

 On Mon, 26 Apr 1999, Poul-Henning Kamp wrote:
 
 >generic_bcopy and friends really stress the I/O section of the CPU
 >so any weakness is likely to trigger here first.
 
 thanks for the quick response :)
 
 the box had 512MB RAM, so i took half out and it is working fine
 took out the other half and put the first set back in, and still worked
 
 so looks like a problem addressing 512MB RAM
 
 i haven't been following -current -bugs lately, but i did a quick search
 on the archives and could not find any documented problems
 
 any more advice would be greatly appreciated.
 
 this also isn't really a pr any more (i don't think) so please feel free
 to tell me to take is to -questions or something like that
 
 --gvg (gordon greeff)
   http://lost.iafrica.com


 Date: Mon, 26 Apr 1999 14:47:57 +0200
 From: Poul-Henning Kamp <phk@critter.freebsd.dk>
 To: Gordon Greeff <gvg@uunet.co.za>
 Cc: FreeBSD-gnats-submit@FreeBSD.ORG
 In-Reply-To: Your message of "Mon, 26 Apr 1999 14:13:36 +0200."
              <Pine.BSF.3.96.990426141011.69700P-100000@lost.iafrica.com> 
 Subject: Re: kern/11330: panic: page fault in generic_bzero 

 In message <Pine.BSF.3.96.990426141011.69700P-100000@lost.iafrica.com>, Gordon 
 Greeff writes:
 >On Mon, 26 Apr 1999, Poul-Henning Kamp wrote:
 >
 >>generic_bcopy and friends really stress the I/O section of the CPU
 >>so any weakness is likely to trigger here first.
 >
 >thanks for the quick response :)
 >
 >the box had 512MB RAM, so i took half out and it is working fine
 >took out the other half and put the first set back in, and still worked
 >
 >so looks like a problem addressing 512MB RAM
 
 We've seen similar problems here.  It seems to indicate that one has
 to be a bit picky about the RAM used in large machines...
 
 --
 Poul-Henning Kamp             FreeBSD coreteam member
 phk@FreeBSD.ORG               "Real hackers run -current on their laptop."
 FreeBSD -- It will take a long time before progress goes too far!


From: Dag-Erling Smorgrav <des@flood.ping.uio.no>
To: gvg@uunet.co.za
Cc: FreeBSD-gnats-submit@FreeBSD.ORG
Subject: Re: kern/11330: panic: page fault in generic_bzero
Date: 01 May 1999 12:29:14 +0200

 gvg@uunet.co.za writes:
 > 	repeatable panic "page fault in kernel mode".
 > 	nm kernel |sort |less (and eyeball) shows problem to
 > 	lie in generic_bzero in /sys/i386/i386/support.s
 
 Which means nothing, except that some portion of the kernel called
 bzero with an invalid pointer as argument. We need a stack trace and,
 if possible, a core dump and a copy of the kernel that generated it
 (preferrably with symbls).
 
 DES
 -- 
 Dag-Erling Smorgrav - des@flood.ping.uio.no
 
State-Changed-From-To: open->closed 
State-Changed-By: hoek 
State-Changed-When: Tue May 16 14:35:35 PDT 2000 
State-Changed-Why:  
No progress after a year.  Some suggestion that it might have been 
a hardware problem.  If necessary, I can re-open this PR if the  
problem hasn't fixed itself, or a new PR can be filed. 
>Unformatted:
