Nvidia driver crashing/causing crashes with dual core Opteron?

[extremedannis]

I just got a dual core Opteron processor. Before that, nvidia's drivers worked fine for me. But now, after a while the screen will freeze but the mouse can still move. It's not possible to use ctrl+alt+backspace or ctrl+alt+f*.
It seems that this happens quicker if I do something video intensive, like Unreal 2003/Mupen64/etc.

I can still get in through ssh. This turns up in the output of dmesg:

[ 8864.692000] NVRM: Xid (0001:00): 8, Channel 00000002
[ 8864.692000] NVRM: Xid (0001:00): 29,  L1 -> L0
[ 8876.736000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8876.736000] NVRM: Xid (0001:00): 29,  L0 -> L0
[ 8889.780000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8902.828000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8914.872000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8927.916000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8939.944000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8952.988000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8965.036000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8978.080000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 8991.124000] NVRM: Xid (0001:00): 8, Channel 00000020
[ 9013.600000] BUG: soft lockup detected on CPU#1!
[ 9013.600000]  [<c015354c>] softlockup_tick+0x9c/0xf0
[ 9013.600000]  [<c0130643>] update_process_times+0x33/0x80
[ 9013.600000]  [<c01154b0>] smp_apic_timer_interrupt+0x70/0x80
[ 9013.600000]  [<c01042f8>] apic_timer_interrupt+0x28/0x30
[ 9013.600000]  [<f916d8ec>] _nv002718rm+0x14/0x18 [nvidia]
[ 9013.600000]  [<f92edb65>] _nv005692rm+0x75/0xa0 [nvidia]
[ 9013.600000]  [<c01154b5>] smp_apic_timer_interrupt+0x75/0x80
[ 9013.600000]  [<f92e5121>] _nv006552rm+0x181/0x594 [nvidia]
[ 9013.600000]  [<f915aeba>] _nv002933rm+0x26/0x2c [nvidia]
[ 9013.600000]  [<f92edb65>] _nv005692rm+0x75/0xa0 [nvidia]
[ 9013.600000]  [<f92e70a1>] _nv007696rm+0x195/0x1cc [nvidia]
[ 9013.600000]  [<f92e7090>] _nv007696rm+0x184/0x1cc [nvidia]
[ 9013.600000]  [<f92edb65>] _nv005692rm+0x75/0xa0 [nvidia]
[ 9013.600000]  [<f92ee0d0>] _nv005894rm+0x28/0x44 [nvidia]
[ 9013.600000]  [<f92e743e>] _nv006655rm+0x102/0x1bc [nvidia]
[ 9013.600000]  [<f92ee197>] _nv005892rm+0x23/0x28 [nvidia]
[ 9013.600000]  [<f9351d8c>] _nv004295rm+0xb8/0xc4 [nvidia]
[ 9013.600000]  [<f92ccc6b>] _nv006557rm+0x4f/0x13c [nvidia]
[ 9013.600000]  [<f92ccc80>] _nv006557rm+0x64/0x13c [nvidia]
[ 9013.600000]  [<f913deb7>] _nv009861rm+0x13/0x38 [nvidia]
[ 9013.600000]  [<f92e769d>] _nv006462rm+0x45/0xc8 [nvidia]
[ 9013.600000]  [<f913deb7>] _nv009861rm+0x13/0x38 [nvidia]
[ 9013.600000]  [<f92cf343>] _nv006585rm+0x1f/0x28 [nvidia]
[ 9013.600000]  [<f913deb7>] _nv009861rm+0x13/0x38 [nvidia]
[ 9013.600000]  [<f9141cef>] _nv009864rm+0x1f/0x130 [nvidia]
[ 9013.600000]  [<f914171a>] _nv009828rm+0x16/0x34 [nvidia]
[ 9013.600000]  [<f9141cef>] _nv009864rm+0x1f/0x130 [nvidia]
[ 9013.600000]  [<f916a04e>] _nv001952rm+0x32/0x244 [nvidia]
[ 9013.600000]  [<f9141787>] _nv009886rm+0x4f/0xd4 [nvidia]
[ 9013.600000]  [<f914f670>] _nv002043rm+0x3d0/0x400 [nvidia]
[ 9013.600000]  [<f914f64a>] _nv002043rm+0x3aa/0x400 [nvidia]
[ 9013.600000]  [<f913ecbf>] _nv009799rm+0x83/0xc4 [nvidia]
[ 9013.600000]  [<f913f3ae>] _nv009857rm+0x22/0x50 [nvidia]
[ 9013.600000]  [<f914ed9a>] _nv002038rm+0x86/0x274 [nvidia]
[ 9013.600000]  [<f913eb72>] _nv009850rm+0x16/0x3c [nvidia]
[ 9013.600000]  [<f914ec6a>] _nv002041rm+0x72/0x11c [nvidia]
[ 9013.600000]  [<f914e9dd>] _nv002044rm+0x3d/0x258 [nvidia]
[ 9013.600000]  [<f916bcb3>] _nv002687rm+0x1b/0x20 [nvidia]
[ 9013.600000]  [<f917324a>] _nv002020rm+0x52/0x78 [nvidia]
[ 9013.600000]  [<f917323d>] _nv002020rm+0x45/0x78 [nvidia]
[ 9013.600000]  [<f916c20a>] _nv002769rm+0x12/0x18 [nvidia]
[ 9013.600000]  [<f91749ea>] rm_free_unused_clients+0x2e/0x7c [nvidia]
[ 9013.600000]  [<f9174a18>] rm_free_unused_clients+0x5c/0x7c [nvidia]
[ 9013.600000]  [<c011e678>] __wake_up+0x38/0x50
[ 9013.600000]  [<f93ef167>] nv_kern_ctl_close+0x6c/0x8a [nvidia]
[ 9013.600000]  [<f93f09ae>] nv_kern_close+0x40/0x2f6 [nvidia]
[ 9013.600000]  [<c0177757>] __fput+0xa7/0x190
[ 9013.600000]  [<c0174af7>] filp_close+0x47/0x80
[ 9013.600000]  [<c01281af>] put_files_struct+0x8f/0xb0
[ 9013.600000]  [<c0129324>] do_exit+0x134/0x800
[ 9013.600000]  [<c0130180>] lock_timer_base+0x20/0x50
[ 9013.600000]  [<c01302b8>] __mod_timer+0x98/0xb0
[ 9013.600000]  [<c0129a16>] do_group_exit+0x26/0x80
[ 9013.600000]  [<c0133149>] get_signal_to_deliver+0x2a9/0x420
[ 9013.600000]  [<c0102803>] do_notify_resume+0x93/0x720
[ 9013.600000]  [<c0261bfe>] ide_intr+0xce/0x1f0
[ 9013.600000]  [<c0106c19>] timer_interrupt+0x59/0xb0
[ 9013.600000]  [<c01538d0>] handle_IRQ_event+0x30/0x60
[ 9013.600000]  [<c0155027>] handle_edge_irq+0x67/0x130
[ 9013.600000]  [<c0105b75>] do_IRQ+0x45/0x80
[ 9013.600000]  [<c010334b>] work_notifysig+0x13/0x18
[ 9013.600000]  =======================

I'm not sure what to do with this. Is this an nvidia driver bug? Or is something else the matter? Does anyone know what might help?

I am using nvidia driver 1.0-9631, and Ubuntu 7.04. Here is the kernel information: "Linux ubuntu 2.6.20-16-generic #2 SMP Thu Jun 7 20:19:32 UTC 2007 i686 GNU/Linux"

[zeb]

You'll find a lot of threads about crashes in this forum, and as far as I know they were linked to hyperthreading/double core. I too had those problems using 9631/9746/9755 drivers, but they seem to have been solved (in my case) with latest driver 100.14.11. But you did not tell which card you were using, maybe are you stuck with legacy drivers?
Hope this helps.

[extremedannis]

Sorry for the lack of info. I've got a GeForce 6200.

BTW, I think my problem was due to overclocking of the processor. I had slightly overclocked the processor, but now I have returned it to the factory setting of speed and the crash hasn't happened yet.

[netllama]

If you need further assistance, please see the forum sticky posts.

thanks,
Lonni