On Fri, 12 Jul 2013, Christian K?nig wrote:
> Hi Ilija, > > well that's very interesting and no it's quite unlikely that this is cause by > the DMA ring because the radeon_sa_bo structure should be allocated on system > memory and the GPU can usually only access it if you map it through GART. > OK that's good information to know. I'll do some more investigation on my end. > Is that easily reproducible for you? Is there already an open bugreport? > It typically happens out of the blue after several days of running, but it happens consistently (just like padding the radeon_sa_bo structure consistently suppresses the problem). However, like I said, my kernel is full of my own patches that don't live in the upstream tree, so I am not excluding the possibility that one of my hacks introduced the problem (though, I find it unlikely). I have not yet opened the bug report, because I first want to reproduce the problem with the upstream kernel that is free of my hacks. As soon as I do that, I'll write the ticket. -- Ilija