drm/i915: Make fb_tracking.lock a spinlock

We only need a very lightweight mechanism here as the locking is only
used for co-ordinating a bitfield.

v2: Move the cheap unlikely tests into the caller
v3: Move the kerneldoc into the header (now separated out into
intel_fronbuffer.h for better kerneldoc and readability)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtien <joonas.lahtinen@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-20-git-send-email-chris@chris-wilson.co.uk

4 files changed, 71 insertions, 56 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7ba99057c317..b26f5b1f466b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1669,7 +1669,7 @@ struct intel_pipe_crc {
 };
 
 struct i915_frontbuffer_tracking {
-	struct mutex lock;
+	spinlock_t lock;
 
 	/*
 	 * Tracking bits for delayed frontbuffer flushing du to gpu activity or
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1960705c50c2..68110b9d98b7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4455,7 +4455,7 @@ i915_gem_load_init(struct drm_device *dev)
 
 	dev_priv->mm.interruptible = true;
 
-	mutex_init(&dev_priv->fb_tracking.lock);
+	spin_lock_init(&dev_priv->fb_tracking.lock);
 }
 
 void i915_gem_load_cleanup(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index b83a70016b12..f15486aee7f8 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -66,35 +66,19 @@
 #include "intel_frontbuffer.h"
 #include "i915_drv.h"
 
-/**
- * intel_fb_obj_invalidate - invalidate frontbuffer object
- * @obj: GEM object to invalidate
- * @origin: which operation caused the invalidation
- *
- * This function gets called every time rendering on the given object starts and
- * frontbuffer caching (fbc, low refresh rate for DRRS, panel self refresh) must
- * be invalidated. For ORIGIN_CS any subsequent invalidation will be delayed
- * until the rendering completes or a flip on this frontbuffer plane is
- * scheduled.
- */
-void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
-			     enum fb_op_origin origin)
+void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+			       enum fb_op_origin origin)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (!obj->frontbuffer_bits)
-		return;
-
 	if (origin == ORIGIN_CS) {
-		mutex_lock(&dev_priv->fb_tracking.lock);
-		dev_priv->fb_tracking.busy_bits
-			|= obj->frontbuffer_bits;
-		dev_priv->fb_tracking.flip_bits
-			&= ~obj->frontbuffer_bits;
-		mutex_unlock(&dev_priv->fb_tracking.lock);
+		spin_lock(&dev_priv->fb_tracking.lock);
+		dev_priv->fb_tracking.busy_bits |= obj->frontbuffer_bits;
+		dev_priv->fb_tracking.flip_bits &= ~obj->frontbuffer_bits;
+		spin_unlock(&dev_priv->fb_tracking.lock);
 	}
 
 	intel_psr_invalidate(dev, obj->frontbuffer_bits);
@@ -121,9 +105,9 @@ static void intel_frontbuffer_flush(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Delay flushing when rings are still busy.*/
-	mutex_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&dev_priv->fb_tracking.lock);
 	frontbuffer_bits &= ~dev_priv->fb_tracking.busy_bits;
-	mutex_unlock(&dev_priv->fb_tracking.lock);
+	spin_unlock(&dev_priv->fb_tracking.lock);
 
 	if (!frontbuffer_bits)
 		return;
@@ -133,18 +117,9 @@ static void intel_frontbuffer_flush(struct drm_device *dev,
 	intel_fbc_flush(dev_priv, frontbuffer_bits, origin);
 }
 
-/**
- * intel_fb_obj_flush - flush frontbuffer object
- * @obj: GEM object to flush
- * @retire: set when retiring asynchronous rendering
- * @origin: which operation caused the flush
- *
- * This function gets called every time rendering on the given object has
- * completed and frontbuffer caching can be started again. If @retire is true
- * then any delayed flushes will be unblocked.
- */
-void intel_fb_obj_flush(struct drm_i915_gem_object *obj,
-			bool retire, enum fb_op_origin origin)
+void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
+			  bool retire,
+			  enum fb_op_origin origin)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -152,21 +127,18 @@ void intel_fb_obj_flush(struct drm_i915_gem_object *obj,
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (!obj->frontbuffer_bits)
-		return;
-
 	frontbuffer_bits = obj->frontbuffer_bits;
 
 	if (retire) {
-		mutex_lock(&dev_priv->fb_tracking.lock);
+		spin_lock(&dev_priv->fb_tracking.lock);
 		/* Filter out new bits since rendering started. */
 		frontbuffer_bits &= dev_priv->fb_tracking.busy_bits;
-
 		dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-		mutex_unlock(&dev_priv->fb_tracking.lock);
+		spin_unlock(&dev_priv->fb_tracking.lock);
 	}
 
-	intel_frontbuffer_flush(dev, frontbuffer_bits, origin);
+	if (frontbuffer_bits)
+		intel_frontbuffer_flush(dev, frontbuffer_bits, origin);
 }
 
 /**
@@ -186,11 +158,11 @@ void intel_frontbuffer_flip_prepare(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	mutex_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&dev_priv->fb_tracking.lock);
 	dev_priv->fb_tracking.flip_bits |= frontbuffer_bits;
 	/* Remove stale busy bits due to the old buffer. */
 	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-	mutex_unlock(&dev_priv->fb_tracking.lock);
+	spin_unlock(&dev_priv->fb_tracking.lock);
 
 	intel_psr_single_frame_update(dev, frontbuffer_bits);
 }
@@ -210,13 +182,14 @@ void intel_frontbuffer_flip_complete(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	mutex_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&dev_priv->fb_tracking.lock);
 	/* Mask any cancelled flips. */
 	frontbuffer_bits &= dev_priv->fb_tracking.flip_bits;
 	dev_priv->fb_tracking.flip_bits &= ~frontbuffer_bits;
-	mutex_unlock(&dev_priv->fb_tracking.lock);
+	spin_unlock(&dev_priv->fb_tracking.lock);
 
-	intel_frontbuffer_flush(dev, frontbuffer_bits, ORIGIN_FLIP);
+	if (frontbuffer_bits)
+		intel_frontbuffer_flush(dev, frontbuffer_bits, ORIGIN_FLIP);
 }
 
 /**
@@ -235,10 +208,10 @@ void intel_frontbuffer_flip(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	mutex_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&dev_priv->fb_tracking.lock);
 	/* Remove stale busy bits due to the old buffer. */
 	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-	mutex_unlock(&dev_priv->fb_tracking.lock);
+	spin_unlock(&dev_priv->fb_tracking.lock);
 
 	intel_frontbuffer_flush(dev, frontbuffer_bits, ORIGIN_FLIP);
 }
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.h b/drivers/gpu/drm/i915/intel_frontbuffer.h
index 3d0061454bd5..60a0ec179108 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.h
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.h
@@ -28,15 +28,57 @@ struct drm_device;
 struct drm_i915_private;
 struct drm_i915_gem_object;
 
-void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
-			     enum fb_op_origin origin);
 void intel_frontbuffer_flip_prepare(struct drm_device *dev,
 				    unsigned frontbuffer_bits);
 void intel_frontbuffer_flip_complete(struct drm_device *dev,
 				     unsigned frontbuffer_bits);
 void intel_frontbuffer_flip(struct drm_device *dev,
 			    unsigned frontbuffer_bits);
-void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire,
-			enum fb_op_origin origin);
+
+void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+			       enum fb_op_origin origin);
+void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
+			  bool retire,
+			  enum fb_op_origin origin);
+
+/**
+ * intel_fb_obj_invalidate - invalidate frontbuffer object
+ * @obj: GEM object to invalidate
+ * @origin: which operation caused the invalidation
+ *
+ * This function gets called every time rendering on the given object starts and
+ * frontbuffer caching (fbc, low refresh rate for DRRS, panel self refresh) must
+ * be invalidated. For ORIGIN_CS any subsequent invalidation will be delayed
+ * until the rendering completes or a flip on this frontbuffer plane is
+ * scheduled.
+ */
+static inline void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+					   enum fb_op_origin origin)
+{
+	if (!obj->frontbuffer_bits)
+		return;
+
+	__intel_fb_obj_invalidate(obj, origin);
+}
+
+/**
+ * intel_fb_obj_flush - flush frontbuffer object
+ * @obj: GEM object to flush
+ * @retire: set when retiring asynchronous rendering
+ * @origin: which operation caused the flush
+ *
+ * This function gets called every time rendering on the given object has
+ * completed and frontbuffer caching can be started again. If @retire is true
+ * then any delayed flushes will be unblocked.
+ */
+static inline void intel_fb_obj_flush(struct drm_i915_gem_object *obj,
+				      bool retire,
+				      enum fb_op_origin origin)
+{
+	if (!obj->frontbuffer_bits)
+		return;
+
+	__intel_fb_obj_flush(obj, retire, origin);
+}
 
 #endif /* __INTEL_FRONTBUFFER_H__ */