drm/i915/gt: Hold a wakeref for the active VM

There may be a disconnect between the GT used by the engine and the GT
used for the VM, requiring us to hold a wakeref on both while the GPU is
active with this request.

v2: added explanation to __queue_and_release_pm
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[ahajda: removed not-yet-upstremed wakeref tracking bits]
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230330-hold_wakeref_for_active_vm-v2-1-724d201499c2@intel.com

drivers/gpu/drm/i915/gt/intel_context.h

@@ -14,6 +14,7 @@
 #include "i915_drv.h"
 #include "intel_context_types.h"
 #include "intel_engine_types.h"
+#include "intel_gt_pm.h"
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
 #include "i915_trace.h"
@@ -207,8 +208,11 @@ void intel_context_exit_engine(struct intel_context *ce);
 static inline void intel_context_enter(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->timeline->mutex);
-	if (!ce->active_count++)
+	if (ce->active_count++)
+		return;
+
 	ce->ops->enter(ce);
+	intel_gt_pm_get(ce->vm->gt);
 }
 
 static inline void intel_context_mark_active(struct intel_context *ce)
@@ -222,7 +226,10 @@ static inline void intel_context_exit(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->timeline->mutex);
 	GEM_BUG_ON(!ce->active_count);
-	if (!--ce->active_count)
+	if (--ce->active_count)
+		return;
+
+	intel_gt_pm_put_async(ce->vm->gt);
 	ce->ops->exit(ce);
 }
 

drivers/gpu/drm/i915/gt/intel_engine_pm.c

@@ -114,6 +114,15 @@ __queue_and_release_pm(struct i915_request *rq,
 
 	ENGINE_TRACE(engine, "parking\n");
 
+	/*
+	 * Open coded one half of intel_context_enter, which we have to omit
+	 * here (see the large comment below) and because the other part must
+	 * not be called due constructing directly with __i915_request_create
+	 * which increments active count via intel_context_mark_active.
+	 */
+	GEM_BUG_ON(rq->context->active_count != 1);
+	__intel_gt_pm_get(engine->gt);
+
 	/*
 	 * We have to serialise all potential retirement paths with our
 	 * submission, as we don't want to underflow either the