[29/47] drm/i915: Reduce presumption of request ordering for barriers

Submitted by Chris Wilson on Feb. 8, 2019, 8:52 p.m.

Details

Message ID 20190208205259.2450-29-chris@chris-wilson.co.uk
State New
Series "Series without cover letter"
Headers show

Commit Message

Chris Wilson Feb. 8, 2019, 8:52 p.m.
---
 drivers/gpu/drm/i915/i915_drv.h               |  1 +
 drivers/gpu/drm/i915/i915_gem.c               | 13 ++--
 drivers/gpu/drm/i915/i915_gem_context.c       | 66 +------------------
 drivers/gpu/drm/i915/i915_gem_context.h       |  3 +-
 drivers/gpu/drm/i915/i915_gem_evict.c         |  2 +-
 drivers/gpu/drm/i915/i915_request.c           |  1 +
 drivers/gpu/drm/i915/intel_engine_cs.c        |  5 ++
 .../gpu/drm/i915/selftests/i915_gem_context.c |  3 +-
 .../gpu/drm/i915/selftests/igt_flush_test.c   |  2 +-
 .../gpu/drm/i915/selftests/mock_gem_device.c  |  4 ++
 10 files changed, 28 insertions(+), 72 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f47bee1efd16..02dd0316cd5f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1992,6 +1992,7 @@  struct drm_i915_private {
 
 		struct list_head active_rings;
 		struct list_head closed_vma;
+		unsigned long active_engines;
 		u32 active_requests;
 
 		/**
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 989278aba8d7..4b0b4f61ec1d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2965,9 +2965,10 @@  static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 	}
 }
 
-static bool switch_to_kernel_context_sync(struct drm_i915_private *i915)
+static bool switch_to_kernel_context_sync(struct drm_i915_private *i915,
+					  unsigned long mask)
 {
-	if (i915_gem_switch_to_kernel_context(i915))
+	if (i915_gem_switch_to_kernel_context(i915, mask))
 		return false;
 
 	if (i915_gem_wait_for_idle(i915,
@@ -2982,7 +2983,8 @@  static bool switch_to_kernel_context_sync(struct drm_i915_private *i915)
 
 static bool load_power_context(struct drm_i915_private *i915)
 {
-	if (!switch_to_kernel_context_sync(i915))
+	/* Force loading the kernel context on all engines */
+	if (!switch_to_kernel_context_sync(i915, -1))
 		return false;
 
 	/*
@@ -3031,7 +3033,8 @@  i915_gem_idle_work_handler(struct work_struct *work)
 	if (!gt->active_requests && !work_pending(&gt->idle_work.work)) {
 		++gt->active_requests; /* don't requeue idle */
 
-		if (!switch_to_kernel_context_sync(i915)) {
+		if (!switch_to_kernel_context_sync(i915,
+						   i915->gt.active_engines)) {
 			dev_err(i915->drm.dev,
 				"Failed to idle engines, declaring wedged!\n");
 			GEM_TRACE_DUMP();
@@ -4505,7 +4508,7 @@  void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	if (!switch_to_kernel_context_sync(i915)) {
+	if (!switch_to_kernel_context_sync(i915, i915->gt.active_engines)) {
 		/* Forcibly cancel outstanding work and leave the gpu quiet. */
 		i915_gem_set_wedged(i915);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 1bdb067845f2..582a7015e6a4 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -682,63 +682,10 @@  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)
+int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915,
+				      unsigned long mask)
 {
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 
 	GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake));
 
@@ -749,17 +696,11 @@  int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return 0;
 
-	i915_retire_requests(i915);
-
-	for_each_engine(engine, i915, id) {
+	for_each_engine_masked(engine, i915, mask, mask) {
 		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))
@@ -783,7 +724,6 @@  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_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index ca150a764c24..651f2e4badb6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -354,7 +354,8 @@  int i915_gem_context_open(struct drm_i915_private *i915,
 void i915_gem_context_close(struct drm_file *file);
 
 int i915_switch_context(struct i915_request *rq);
-int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv);
+int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915,
+				      unsigned long engine_mask);
 
 void i915_gem_context_release(struct kref *ctx_ref);
 struct i915_gem_context *
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 68d74c50ac39..7d8e90dfca84 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -62,7 +62,7 @@  static int ggtt_flush(struct drm_i915_private *i915)
 	 * the hopes that we can then remove contexts and the like only
 	 * bound by their active reference.
 	 */
-	err = i915_gem_switch_to_kernel_context(i915);
+	err = i915_gem_switch_to_kernel_context(i915, i915->gt.active_engines);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 84976e1f476b..adbbead64d04 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1061,6 +1061,7 @@  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 45e38877ab17..0f2f8a10149d 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1114,6 +1114,9 @@  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
@@ -1213,6 +1216,8 @@  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;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index f8931086eb70..08a4dd697e25 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -1512,7 +1512,8 @@  static int __igt_switch_to_kernel_context(struct drm_i915_private *i915,
 			}
 		}
 
-		err = i915_gem_switch_to_kernel_context(i915);
+		err = i915_gem_switch_to_kernel_context(i915,
+							i915->gt.active_engines);
 		if (err)
 			return err;
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index af66e3d4e23a..e6a3395459f1 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -14,7 +14,7 @@  int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 	cond_resched();
 
 	if (flags & I915_WAIT_LOCKED &&
-	    i915_gem_switch_to_kernel_context(i915)) {
+	    i915_gem_switch_to_kernel_context(i915, i915->gt.active_engines)) {
 		pr_err("Failed to switch back to kernel context; declaring wedged\n");
 		i915_gem_set_wedged(i915);
 	}
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 5a98caba6d69..d00679e21415 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -112,6 +112,10 @@  static void mock_retire_work_handler(struct work_struct *work)
 
 static void mock_idle_work_handler(struct work_struct *work)
 {
+	struct drm_i915_private *i915 =
+		container_of(work, typeof(*i915), gt.idle_work.work);
+
+	i915->gt.active_engines = 0;
 }
 
 static int pm_domain_resume(struct device *dev)