[Intel-gfx] [PATCH v2 2/2] drm/i915/bxt: work around HW context corruption due to coherency problem

[Imre Deak]

On Fri, 2015-09-18 at 10:02 +0100, Chris Wilson wrote:
> On Thu, Sep 17, 2015 at 07:17:44PM +0300, Imre Deak wrote:
> > The execlist context object is mapped with a CPU/GPU coherent mapping
> > everywhere, but on BXT A stepping due to a HW issue the coherency is not
> > guaranteed. To work around this flush the context object after pinning
> > it (to flush cache lines left by the context initialization/read-back
> > from backing storage) and mark it as uncached so later updates during
> > context switching will be coherent.
> > 
> > I noticed this problem via a GPU hang, where IPEHR pointed to an invalid
> > opcode value. I couldn't find this value on the ring but looking at the
> > contents of the active context object it turned out to be a parameter
> > dword of a bigger command there. The original command opcode itself
> > was zeroed out, based on the above I assume due to a CPU writeback of
> > the corresponding cacheline. When restoring the context the GPU would
> > jump over the zeroed out opcode and hang when trying to execute the
> > above parameter dword.
> > 
> > I could easily reproduce this by running igt/gem_render_copy_redux and
> > gem_tiled_blits/basic in parallel, but I guess it could be triggered by
> > anything involving frequent switches between two separate contexts. With
> > this workaround I couldn't reproduce the problem.
> > 
> > v2:
> > - instead of clflushing after updating the tail and PDP values during
> >   context switching, map the corresponding page as uncached to avoid a
> >   race between CPU and GPU, both updating the same cacheline at the same
> >   time (Ville)
> 
> No. Changing PAT involves a stop_machine() and is severely detrimental
> to performance (context creation overhead does impact userspace).

Hm, where on that path is stop_machine(), I haven't found it. I guess
there is an overhead because of the TLB flush on each CPU, I haven't
benchmarked it. If that's a real issue (atm this is only a w/a for
stepping A) we could have a cache of uncached pages.

> Mapping it as uncached doesn't remove the race anyway.

Please explain, I do believe it does.

--Imre