I have a 2x ultra IIe 300 Mhz  Enterprise 2 that i can ship to anyone who 
is working on SMP.


On Thu, 13 Sep 2007, Chris Ross wrote:

> Date: Thu, 13 Sep 2007 21:28:40 -0400
> From: Chris Ross <cross+netbsd@distal.com>
> To: Martin Husemann <martin@duskware.de>
> Cc: port-sparc64@NetBSD.org
> Subject: Re: SMP status
> 
>
> On Aug 25, 2007, at 15:47, Martin Husemann wrote:
>> Hi folks,
>> 
>> I think a -current GENERIC.MP kernel should be able to boot into
>> single user shell on all supported machines. Beware, it will crash
>> soon if you do serious stuff ;-)
>> 
>> If you have a MP machine, it would be good if you could test this and
>> tell me if it crashes before reaching the shell prompt.
>
> Okay.  I just obtained a Ultra Enterprise 420R, with 4 450 Mhz US-2's in it, 
> and 4GB of memory.  When I try to build a -current GENERIC.MP (build from 
> today's sources, 13-Sept-2007), I see the following when it tries to mount 
> the nfs root:
>
> (n.b. I was previously mounting an nfs root on a GENERIC.MP sparc64 machine, 
> so it's not a generic NFS problem.  Let me know if you'd like me to hook the 
> ultra-2 back up and try again with the same code...)
>
> Copyright (c) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005,
>   2006, 2007
>   The NetBSD Foundation, Inc.  All rights reserved.
> Copyright (c) 1982, 1986, 1989, 1991, 1993
>   The Regents of the University of California.  All rights reserved.
>
> NetBSD 4.99.31 (GENERIC.MP) #3: Thu Sep 13 20:55:57 EDT 2007
>       cross@host:/data/obj/NetBSD.sparc64/data/NetBSD/src/sys/arch/sparc64/compile/GENERIC.MP
> total memory = 4096 MB
> avail memory = 4007 MB
> bootpath: /pci@1f,4000/network@1,1
> mainbus0 (root): SUNW,Ultra-80: hostid 80e8b7d8
> cpu0 at mainbus0: SUNW,UltraSPARC-II @ 450.035 MHz, UPA id 0
> cpu0: 32K instruction (32 b/l), 16K data (32 b/l), 4096K external (64 b/l)
> cpu1 at mainbus0: SUNW,UltraSPARC-II @ 450.035 MHz, UPA id 1
> cpu1: 32K instruction (32 b/l), 16K data (32 b/l), 4096K external (64 b/l)
> cpu2 at mainbus0: SUNW,UltraSPARC-II @ 450.035 MHz, UPA id 2
> cpu2: 32K instruction (32 b/l), 16K data (32 b/l), 4096K external (64 b/l)
> cpu3 at mainbus0: SUNW,UltraSPARC-II @ 450.035 MHz, UPA id 3
> cpu3: 32K instruction (32 b/l), 16K data (32 b/l), 4096K external (64 b/l)
> psycho0 at mainbus0 addr 0xfffb4000
> SUNW,psycho: impl 0, version 4: ign 7c0 bus range 0 to 0; PCI bus 0
> DVMA map: fe000000 to ffffe000
> IOTSB: 433e000 to 4346000
> pci0 at psycho0
> pci0: i/o space, memory space enabled
> ebus0 at pci0 dev 1 function 0
> ebus0: Sun Microsystems PCIO Ebus2, revision 0x01
> auxio0 at ebus0 addr 726000-726003, 728000-728003, 72a000-72a003, 
> 72c000-72c003, 72f000-72f003
> power at ebus0 addr 724000-724003 ipl 37 not configured
> SUNW,pll at ebus0 addr 504000-504002 not configured
> sc at ebus0 addr 500000-500007 not configured
> sab0 at ebus0 addr 400000-40007f ipl 43: rev 3.2
> sabtty0 at sab0 port 0: console i/o
> sabtty1 at sab0 port 1
> com0 at ebus0 addr 3083f8-3083ff ipl 41: ns16550a, working fifo
> kbd0 at com0
> com1 at ebus0 addr 3062f8-3062ff ipl 42: ns16550a, working fifo
> ms0 at com1
> wsmouse0 at ms0 mux 0
> lpt0 at ebus0 addr 3043bc-3043cb, 300398-300399, 700000-70000f ipl 34
> fdthree at ebus0 addr 3023f0-3023f7, 706000-70600f, 720000-720003 ipl 39 not 
> configured
> clock0 at ebus0 addr 0-1fff: mk48t59
> flashprom at ebus0 addr 0-fffff not configured
> hme0 at pci0 dev 1 function 1: Sun Happy Meal Ethernet, rev. 1
> hme0: interrupting at ivec 3021
> hme0: Ethernet address 08:00:20:e8:b7:d8
> ukphy0 at hme0 phy 1: Generic IEEE 802.3u media interface
> ukphy0: OUI 0x0006b8, model 0x000c, rev. 1
> ukphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
> esiop0 at pci0 dev 3 function 0: Symbios Logic 53c875 (ultra-wide scsi)
> esiop0: using on-board RAM
> esiop0: interrupting at ivec 1820
> scsibus0 at esiop0: 16 targets, 8 luns per target
> esiop1 at pci0 dev 3 function 1: Symbios Logic 53c875 (ultra-wide scsi)
> esiop1: using on-board RAM
> esiop1: interrupting at ivec 1826
> scsibus1 at esiop1: 16 targets, 8 luns per target
> esiop2 at pci0 dev 2 function 0: Symbios Logic 53c875 (ultra-wide scsi)
> esiop2: using on-board RAM
> esiop2: interrupting at ivec 1810
> scsibus2 at esiop2: 16 targets, 8 luns per target
> esiop3 at pci0 dev 2 function 1: Symbios Logic 53c875 (ultra-wide scsi)
> esiop3: using on-board RAM
> esiop3: interrupting at ivec 1811
> scsibus3 at esiop3: 16 targets, 8 luns per target
> machfb0 at pci0 dev 5 function 0: ATI Technologies Rage XL (rev. 0x27)
> machfb0: 16 MB aperture at 0x01000000, 4 KB registers at 0x02000000
> machfb0: ref_freq=29.498MHz
> machfb0: 8188 KB SGRAM 114.992 MHz, maximum RAMDAC clock 230 MHz
> mach64_get_mode: 1152 5304 5432 1528 900 902 938 937
> machfb0: initial resolution 1152x864 at 8 bpp
> machfb0: attached to /dev/fb0
> machfb0: initializing the DSP
> wsdisplay1 at machfb0 kbdmux 1
> wsdisplay1: screen 0-3 added (default)
> psycho1 at mainbus0 addr 0xfffc6000
> SUNW,psycho: impl 0, version 4: ign 7c0 bus range 128 to 128; PCI bus 128
> pci1 at psycho1
> pci1: i/o space, memory space enabled
> Schneider & Koch SK-9821 v2.0 (ethernet network, revision 0x16) at pci1 dev 1 
> function 0 not configured
> timer0 at mainbus0 addr 0xfff9fc00 irq vectors 7ec and 7ed
> pcons at mainbus0 not configured
> wskbd0 at kbd0 mux 1
> scsibus0: waiting 2 seconds for devices to settle...
> scsibus1: waiting 2 seconds for devices to settle...
> scsibus2: waiting 2 seconds for devices to settle...
> scsibus3: waiting 2 seconds for devices to settle...
> cd0 at scsibus0 target 6 lun 0: <TOSHIBA, DVD-ROM SD-M1401, 1009> cdrom 
> removable
> cd0: sync (50.00ns offset 16), 8-bit (20.000MB/s) transfers
> kbd0: reset failed
> Kernelized RAIDframe activated
> root on hme0
> nfs_boot: trying DHCP/BOOTP
> nfs_boot: DHCP next-server: 206.138.151.36
> nfs_boot: my_domain=distal.com
> nfs_boot: my_addr=206.138.151.49
> nfs_boot: my_mask=255.255.255.0
> nfs_boot: gateway=206.138.151.1
> root on 206.138.151.36:/export/sparc64/nfsroot
> root file system type: nfs
> trap: textfault at 40962780!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
> trap: textfault at 409da540!! sending SIGILL due to trap 16: illegal 
> instruction
>
>
> ....and those trap's continue until I power the machine off...
>
> Any idea?  Is this a 4GB of memory thing?  Again, I'll try to confirm later 
> that this *doesn't* happen with with dual-CPU Ultra-2 I had been testing with 
> a couple weeks ago.  I've confirmed that a GENERIC kernel from this same 
> source tree comes up alright on this 4 CPU machine...  It drops to the 
> single-user shell as expected.
>
> Thanks....
>
>                                                        - Chris