[Intel-gfx] [PATCH 10/15] drm/i915: Teach execbuffer to take the engine wakeref not GT

[Chris Wilson]

In the next patch, we would like to couple into the engine wakeref to
free the batch pool on idling. The caveat here is that we therefore want
to track the engine wakeref more precisely and to hold it instead of the
broader GT wakeref as we process the ioctl.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 36 ++++++++++++-------
 drivers/gpu/drm/i915/gt/intel_context.h       |  7 ++++
 2 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1c5dfbfad71b..f43eaaa5db5f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2143,13 +2143,35 @@ static int eb_pin_context(struct i915_execbuffer *eb, struct intel_context *ce)
 	if (err)
 		return err;
 
+	/*
+	 * Take a local wakeref for preparing to dispatch the execbuf as
+	 * we expect to access the hardware fairly frequently in the
+	 * process. Upon first dispatch, we acquire another prolonged
+	 * wakeref that we hold until the GPU has been idle for at least
+	 * 100ms.
+	 */
+	err = intel_context_timeline_lock(ce);
+	if (err)
+		goto err_unpin;
+
+	intel_context_enter(ce);
+	intel_context_timeline_unlock(ce);
+
 	eb->engine = ce->engine;
 	eb->context = ce;
 	return 0;
+
+err_unpin:
+	intel_context_unpin(ce);
+	return err;
 }
 
 static void eb_unpin_context(struct i915_execbuffer *eb)
 {
+	__intel_context_timeline_lock(eb->context);
+	intel_context_exit(eb->context);
+	intel_context_timeline_unlock(eb->context);
+
 	intel_context_unpin(eb->context);
 }
 
@@ -2430,18 +2452,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (unlikely(err))
 		goto err_destroy;
 
-	/*
-	 * Take a local wakeref for preparing to dispatch the execbuf as
-	 * we expect to access the hardware fairly frequently in the
-	 * process. Upon first dispatch, we acquire another prolonged
-	 * wakeref that we hold until the GPU has been idle for at least
-	 * 100ms.
-	 */
-	intel_gt_pm_get(&eb.i915->gt);
-
 	err = i915_mutex_lock_interruptible(dev);
 	if (err)
-		goto err_rpm;
+		goto err_context;
 
 	err = eb_select_engine(&eb, file, args);
 	if (unlikely(err))
@@ -2606,8 +2619,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb_unpin_context(&eb);
 err_unlock:
 	mutex_unlock(&dev->struct_mutex);
-err_rpm:
-	intel_gt_pm_put(&eb.i915->gt);
+err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 40cd8320fcc3..065ba4ac4e87 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -126,6 +126,13 @@ static inline void intel_context_put(struct intel_context *ce)
 	kref_put(&ce->ref, ce->ops->destroy);
 }
 
+static inline void
+__intel_context_timeline_lock(struct intel_context *ce)
+	__acquires(&ce->ring->timeline->mutex)
+{
+	mutex_lock(&ce->ring->timeline->mutex);
+}
+
 static inline int __must_check
 intel_context_timeline_lock(struct intel_context *ce)
 	__acquires(&ce->ring->timeline->mutex)
-- 
2.20.1