Re: [Intel-gfx] [PATCH 3/4] drm/i915/guc: kill doorbell code and selftests

2019-11-18 Thread Daniele Ceraolo Spurio
On 11/14/19 3:56 PM, John Harrison wrote: On 11/6/2019 14:25, Daniele Ceraolo Spurio wrote: Instead of relying on the workqueue, the upcoming reworked GuC submission flow will offer the host driver indipendent control over independent the execution status of each context submitted to GuC. A

Re: [Intel-gfx] [PATCH 3/4] drm/i915/guc: kill doorbell code and selftests

2019-11-14 Thread John Harrison
On 11/6/2019 14:25, Daniele Ceraolo Spurio wrote: Instead of relying on the workqueue, the upcoming reworked GuC submission flow will offer the host driver indipendent control over independent the execution status of each context submitted to GuC. As part of this, the doorbell usage model has

[Intel-gfx] [PATCH 3/4] drm/i915/guc: kill doorbell code and selftests

2019-11-06 Thread Daniele Ceraolo Spurio
Instead of relying on the workqueue, the upcoming reworked GuC submission flow will offer the host driver indipendent control over the execution status of each context submitted to GuC. As part of this, the doorbell usage model has been reworked, with each doorbell being paired to a single lrc and