On Fri, 26 Oct 2018 10:20:49 +0200 (CEST) Mark Kettenis <mark.kette...@xs4all.nl> wrote:
> > Date: Fri, 26 Oct 2018 09:31:56 +1100 > > From: Jonathan Gray <j...@jsg.id.au> > > > > On Thu, Oct 25, 2018 at 08:12:13PM +0200, Mark Kettenis wrote: > > > Found the issue. The kernel advertises support for the I915_MMAP_WC > > > option, but we don't actually implement that functonality correctly > > > :(. As a result we create a cachable mapping instead of a > > > write-combining (uncached) one. On hardware generations that aren't > > > cache coherent this means that the hardware may see stale memory > > > contents. So the GPU starts executing some random garbage which is > > > very likely to result in a hang. > > > > > > The diff below stops advertising I915_MMAP_WC support. This is a > > > workaround. I'm looking into implementing I915_MMAP_WC properly, but > > > that may require a bit of uvm surgery. > > > > Thanks for tracking this down, ok jsg@ if you also make > > i915_gem_mmap_ioctl() error on args->flags & I915_MMAP_WC. > > I committed the diff as-is last night since Theo wanted to get a > usuable snap out because of the Xorg thing. > > My plan is to have a proper I915_MMAP_WC implementation ready soon anyway. Thanks a lot for this. In fact you have more quick with workaround than me with another report of other issues on this platform. I've discovered myself also those hangs and strangely behaving iridium/firefox. Now, everything seems to be fine again. Thanks! Karel
