[PATCH 36/52] drm/i915: Reduce presumption of request ordering for barriers

[Chris Wilson]

---
 drivers/gpu/drm/i915/i915_drv.h         |  3 ++
 drivers/gpu/drm/i915/i915_gem_context.c | 66 ++-----------------------
 drivers/gpu/drm/i915/i915_request.c     |  1 +
 drivers/gpu/drm/i915/intel_engine_cs.c  |  5 ++
 4 files changed, 14 insertions(+), 61 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a2387f89eb0..eb04017a66ca 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1988,6 +1988,7 @@ struct drm_i915_private {
 
 		struct list_head active_rings;
 		struct list_head closed_vma;
+		unsigned long active_engines;
 		u32 active_requests;
 
 		/**
@@ -2097,6 +2098,8 @@ static inline struct drm_i915_private *huc_to_i915(struct intel_huc *huc)
 	     (tmp__) ? \
 	     ((engine__) = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : \
 	     0;)
+#define for_each_active_engine(engine__, i915__, tmp__) \
+	for_each_engine_masked((engine__), (i915__), (i915__)->gt.active_engines, (tmp__))
 
 enum hdmi_force_audio {
 	HDMI_AUDIO_OFF_DVI = -2,	/* no aux data for HDMI-DVI converter */
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index ea8e818d22bf..4a19382ac820 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -666,80 +666,25 @@ last_request_on_engine(struct i915_timeline *timeline,
 	return NULL;
 }
 
-static bool engine_has_kernel_context_barrier(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *i915 = engine->i915;
-	const struct intel_context * const ce =
-		to_intel_context(i915->kernel_context, engine);
-	struct i915_timeline *barrier = ce->ring->timeline;
-	struct intel_ring *ring;
-	bool any_active = false;
-
-	lockdep_assert_held(&i915->drm.struct_mutex);
-	list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
-		struct i915_request *rq;
-
-		rq = last_request_on_engine(ring->timeline, engine);
-		if (!rq)
-			continue;
-
-		any_active = true;
-
-		if (rq->hw_context == ce)
-			continue;
-
-		/*
-		 * Was this request submitted after the previous
-		 * switch-to-kernel-context?
-		 */
-		if (!i915_timeline_sync_is_later(barrier, &rq->fence)) {
-			GEM_TRACE("%s needs barrier for %llx:%lld\n",
-				  ring->timeline->name,
-				  rq->fence.context,
-				  rq->fence.seqno);
-			return false;
-		}
-
-		GEM_TRACE("%s has barrier after %llx:%lld\n",
-			  ring->timeline->name,
-			  rq->fence.context,
-			  rq->fence.seqno);
-	}
-
-	/*
-	 * If any other timeline was still active and behind the last barrier,
-	 * then our last switch-to-kernel-context must still be queued and
-	 * will run last (leaving the engine in the kernel context when it
-	 * eventually idles).
-	 */
-	if (any_active)
-		return true;
-
-	/* The engine is idle; check that it is idling in the kernel context. */
-	return engine->last_retired_context == ce;
-}
-
 int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	unsigned long tmp;
 
 	GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake));
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915->kernel_context);
 
-	i915_retire_requests(i915);
+	/* Inoperable, so presume the GPU is safely pointing into the void! */
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
 
-	for_each_engine(engine, i915, id) {
+	for_each_active_engine(engine, i915, tmp) {
 		struct intel_ring *ring;
 		struct i915_request *rq;
 
 		GEM_BUG_ON(!to_intel_context(i915->kernel_context, engine));
-		if (engine_has_kernel_context_barrier(engine))
-			continue;
-
-		GEM_TRACE("emit barrier on %s\n", engine->name);
 
 		rq = i915_request_alloc(engine, i915->kernel_context);
 		if (IS_ERR(rq))
@@ -763,7 +708,6 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 			i915_sw_fence_await_sw_fence_gfp(&rq->submit,
 							 &prev->submit,
 							 I915_FENCE_GFP);
-			i915_timeline_sync_set(rq->timeline, &prev->fence);
 		}
 
 		i915_request_add(rq);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 77d4dbfcf80f..559794e9ee0e 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1069,6 +1069,7 @@ void i915_request_add(struct i915_request *request)
 		GEM_TRACE("marking %s as active\n", ring->timeline->name);
 		list_add(&ring->active_link, &request->i915->gt.active_rings);
 	}
+	request->i915->gt.active_engines |= request->engine->mask;
 	request->emitted_jiffies = jiffies;
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index f6b7398d4710..d174e1ffbeaf 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1074,6 +1074,9 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
+	if (!engine->context_size)
+		return true;
+
 	/*
 	 * Check the last context seen by the engine. If active, it will be
 	 * the last request that remains in the timeline. When idle, it is
@@ -1173,6 +1176,8 @@ void intel_engines_park(struct drm_i915_private *i915)
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 		engine->execlists.no_priolist = false;
 	}
+
+	i915->gt.active_engines = 0;
 }
 
 /**
-- 
2.20.1