[Intel-gfx] [PATCH 4/4] drm/i915: Only do a chipset flush after a clflush

[Chris Wilson]

Now that we skip clflushes more often, return a boolean indicating
whether the clflush was actually performed, and only if it was do the
chipset flush. (Though on most of the architectures where the clflush will
be skipped, the chipset flush is a no-op!)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h            |  2 +-
 drivers/gpu/drm/i915/i915_gem.c            | 19 ++++++++++---------
 drivers/gpu/drm/i915/i915_gem_exec.c       |  4 ++--
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  5 +++--
 4 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 93c4789..c07dfb9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1845,7 +1845,7 @@ static inline bool i915_terminally_wedged(struct i915_gpu_error *error)
 }
 
 void i915_gem_reset(struct drm_device *dev);
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj);
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_object_set_domain(struct drm_i915_gem_object *obj,
 					    uint32_t read_domains,
 					    uint32_t write_domain);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9805693..7b4c59c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -930,8 +930,8 @@ out:
 		 */
 		if (!needs_clflush_after &&
 		    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
-			i915_gem_clflush_object(obj);
-			i915_gem_chipset_flush(dev);
+			if (i915_gem_clflush_object(obj))
+				i915_gem_chipset_flush(dev);
 		}
 	}
 
@@ -3280,7 +3280,7 @@ err_unpin:
 	return ret;
 }
 
-void
+bool
 i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 {
 	/* If we don't have a page list set up, then we're not pinned
@@ -3288,14 +3288,14 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 	 * again at bind time.
 	 */
 	if (obj->pages == NULL)
-		return;
+		return false;
 
 	/*
 	 * Stolen memory is always coherent with the GPU as it is explicitly
 	 * marked as wc by the system, or the system is cache-coherent.
 	 */
 	if (obj->stolen)
-		return;
+		return false;
 
 	/* If the GPU is snooping the contents of the CPU cache,
 	 * we do not need to manually clear the CPU cache lines.  However,
@@ -3306,11 +3306,12 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 	 * tracking.
 	 */
 	if (!cpu_write_needs_clflush(obj))
-		return;
+		return false;
 
 	trace_i915_gem_object_clflush(obj);
-
 	drm_clflush_sg(obj->pages);
+
+	return true;
 }
 
 /** Flushes the GTT write domain for the object if it's dirty. */
@@ -3349,8 +3350,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
 	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU)
 		return;
 
-	i915_gem_clflush_object(obj);
-	i915_gem_chipset_flush(obj->base.dev);
+	if (i915_gem_clflush_object(obj))
+		i915_gem_chipset_flush(obj->base.dev);
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_exec.c b/drivers/gpu/drm/i915/i915_gem_exec.c
index d2ac077..2396b72 100644
--- a/drivers/gpu/drm/i915/i915_gem_exec.c
+++ b/drivers/gpu/drm/i915/i915_gem_exec.c
@@ -50,8 +50,8 @@ static int i915_gem_exec_flush_object(struct drm_i915_gem_object *obj,
 		return ret;
 
 	if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) {
-		i915_gem_clflush_object(obj);
-		i915_gem_chipset_flush(obj->base.dev);
+		if (i915_gem_clflush_object(obj))
+			i915_gem_chipset_flush(obj->base.dev);
 		obj->base.write_domain &= ~I915_GEM_DOMAIN_CPU;
 	}
 	if (obj->base.write_domain & I915_GEM_DOMAIN_GTT) {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 9939d2e..4d2fff5 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -708,6 +708,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 {
 	struct drm_i915_gem_object *obj;
 	uint32_t flush_domains = 0;
+	bool flush_chipset = false;
 	int ret;
 
 	list_for_each_entry(obj, objects, exec_list) {
@@ -716,12 +717,12 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 			return ret;
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			i915_gem_clflush_object(obj);
+			flush_chipset |= i915_gem_clflush_object(obj);
 
 		flush_domains |= obj->base.write_domain;
 	}
 
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
+	if (flush_chipset)
 		i915_gem_chipset_flush(ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
-- 
1.8.4.rc1