Re: [PATCH 2/2] drm/radeon: implement dynamic PTs allocation via SA

On Don, 2012-09-27 at 16:18 +0400, Dmitry Cherkassov wrote:

Hi Michel.

2012/9/27 Michel Dänzer michel@daenzer.net:

...

On Die, 2012-09-25 at 18:44 +0400, Dmitry Cherkasov wrote:

...

make dynamic allocation of page tables on demand in radeon_vm_update_pte

Signed-off-by: Dmitry Cherkasov Dmitrii.Cherkasov@amd.com

This change caused many piglit tests to fail for me on SI with

    radeon: The kernel rejected CS, see dmesg for more information.

There was no corresponding dmesg output though.

Thanks for testing.

So there was no information about GPU hang etc?

No.

Have all failed piglit tests been working without dynamic pte patch?

Not sure about all of them, but thousands of them did. Of course, it's possible that it was just something breaking at some point and all CS ioctl calls failing after that.