[igt-dev] [PATCH i-g-t v2 08/10] tests/i915/exec_fence: add timeline fence tests

[Chris Wilson]

Quoting Lionel Landwerlin (2019-11-22 15:43:11)
> On 22/11/2019 17:26, Chris Wilson wrote:
> > Quoting Lionel Landwerlin (2019-11-22 13:02:58)
> >> We can now give a tuple (handle, point_value) for timeline semaphores.
> >>
> >> v2: Fix up syncobj-timeline-repeat test (Lionel)
> >>      Update following kernel rename
> >>
> >> v3: Add more ordering tests for syncobj/buffer handle state (Chris)
> > Another question, do we worry about sw_sync imported fences being
> > handles differently to native?
> > -Chris
> 
> What do you mean by differently?

We have is_i915_fence() with branching paths for internal/external, and
within the syncobj timeline mixed fence contexts cause a hard barrier,
so may present interesting effects at the uAPI layer?

> Thing is sw_sync can delay the signaling forever so you could build a 
> case exhausting memory if you really wanted.

Except we don't allow indefinite waits for external fences such as
sw_sync and wrap them in auto-expiring fences.

> Whereas my understand of other dma-fences is that they should be short 
> lived.

Endless. How's that going to end? Badly.
-Chris