Quoting Chris Wilson (2019-04-03 08:54:41)
> Quoting Tvrtko Ursulin (2019-04-02 14:17:30)
> >
> > On 25/03/2019 09:03, Chris Wilson wrote:
> > > @@ -727,17 +695,19 @@ i915_request_alloc(struct intel_engine_cs *engine,
> > > struct i915_gem_context *ctx)
> > > if (ret)
> > > go
Quoting Tvrtko Ursulin (2019-04-02 14:17:30)
>
> On 25/03/2019 09:03, Chris Wilson wrote:
> > @@ -727,17 +695,19 @@ i915_request_alloc(struct intel_engine_cs *engine,
> > struct i915_gem_context *ctx)
> > if (ret)
> > goto err_unwind;
> >
> > - ret = engine->request_all
On 25/03/2019 09:03, Chris Wilson wrote:
Start acquiring the logical intel_context and using that as our primary
means for request allocation. This is the initial step to allow us to
avoid requiring struct_mutex for request allocation along the
perma-pinned kernel context, but it also provides a