[05/15] drm/xe: Introduce an xe_validation wrapper around drm_exec

[Simon Richter]

Hi,

On 8/18/25 11:19 AM, Matthew Brost wrote:

>> ... causes a NULL pointer to be recorded for the scoped guard here, which
>> is then passed to xe_validation_ctx_fini on scope exit, causing

> Yep. Thomas and I agree [1] this is a bug.

Ah, excellent.

It is also really easy to trigger this, happened after a few seconds in 
during a Piglit run for me, on a single GPU as a normal user, just a lot 
of clients starting and stopping in parallel.

    Simon