On Fri, Jan 7, 2011 at 7:24 PM, Konrad Rzeszutek Wilk
[off-list ref] wrote:

On Fri, Jan 07, 2011 at 05:47:59PM +0000, Prasad Joshi wrote:

quoted

2011/1/7 Konrad Rzeszutek Wilk [off-list ref]:

quoted

quoted

quoted

The errors

[    3.778476] [drm:r100_ring_test] *ERROR* radeon: ring test failed
(sracth(0x15E4)=0xCAFEDEAD)
[    3.781010] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
[    3.782542] radeon 0000:00:04.0: failled initializing CP (-22).
[    3.784006] radeon 0000:00:04.0: Disabling GPU acceleration

Seem to be disabling GPU functionality. For now, I am interested in
Graphics functionality of the ATI card and not GPGPU functionality.

I will appreciate if you can help me with some information on solving
this problem. Let me know if I should be asking this question on
another forum. Please keep me in CC.

Looks like dri-devel material, added to CC.

As a first guess, maybe the system memory pages accessed by the GPU GART
aren't the same ones intended for this by the VM.

I actually have patches for that (sorry for the late reply).

Try:
git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git devel/ttm.pci-api.v3

I could access the git repository, but was not able to get those
patches form the repository. Frankly speaking, I don't know how to get
those patches.

quoted

quoted

But I am not sure if they would make any difference here. You said
you are using KVM-QEMU - you must also be using an IOMMU? Does the IOMMU
give you any errors?

Yes I want to pass-through the ATI Radeon card to VM in KVM. I have
enabled the IOMMU support and it works perfectly alright. I tried
passing through a network card it worked.

Should I try the patch you suggested?

Go for it. I am still at lost why you would see those errors unless..
well, what is the DMA code that gets turned on when you run your guest?
What do you see for 'PCI-DMA' ? Is it bounce buffer or swiotlb?
How much memory do you pass to the guest? less than 4GB?

I am trying these things on Uni server, I will let you know the
answers by tomorrow.

Thanks and Regards,
Prasad