[Intel-gfx] [PATCH 5/5] drm/i915: Cancel non-persistent contexts on close

[Chris Wilson]

Quoting Chris Wilson (2019-08-06 14:47:25)
> Normally, we rely on our hangcheck to prevent persistent batches from
> hogging the GPU. However, if the user disables hangcheck, this mechanism
> breaks down. Despite our insistence that this is unsafe, the users are
> equally insistent that they want to use endless batches and will disable
> the hangcheck mechanism. We are looking are perhaps replacing hangcheck
> with a softer mechanism, that sends a pulse down the engine to check if
> it is well. We can use the same preemptive pulse to flush an active
> persistent context off the GPU upon context close, preventing resources
> being lost and unkillable requests remaining on the GPU, after process
> termination. To avoid changing the ABI and accidentally breaking
> existing userspace, we make the persistence of a context explicit and
> enable it by default. Userspace can opt out of persistent mode (forcing
> requests to be cancelled when the context is closed by process
> termination or explicitly) by a context parameter, or to facilitate
> existing use-cases by disabling hangcheck (i915.enable_hangcheck=0).
> (Note, one of the outcomes for supporting endless mode will be the
> removal of hangchecking, at which point opting into persistent mode will
> be mandatory, or maybe the default.)

For the record, I've finally run into examples of desktop clients
exiting before their rendering is shown. No longer hypothetical.
-Chris