[PATCH 4/4] drm/i915: Opportunistically reduce flushing at execbuf

[Ben Widawsky]

If we're moving a bunch of buffers from the CPU domain to the GPU domain, and
we've already blown out the entire cache via a wbinvd, there is nothing more to
do.

With this and the previous patches, I am seeing a 3x FPS increase on a certain
benchmark which uses a giant 2d array texture. Unless I missed something in the
code, it should only effect non-LLC i915 platforms.

I haven't yet run any numbers for other benchmarks, nor have I attempted to
check if various conformance tests still pass.

NOTE: As mentioned in the previous patch, if one can easily obtain the largest
buffer and attempt to flush it first, the results would be even more desirable.

Cc: DRI Development <dri-devel at lists.freedesktop.org>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_drv.h            |  3 ++-
 drivers/gpu/drm/i915/i915_gem.c            | 12 +++++-------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  8 +++++---
 drivers/gpu/drm/i915/intel_lrc.c           |  8 +++++---
 4 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d68c75f..fdb92a3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2642,7 +2642,8 @@ static inline bool i915_stop_ring_allow_warn(struct drm_i915_private *dev_priv)
 }
 
 void i915_gem_reset(struct drm_device *dev);
-bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
+enum drm_cache_flush
+i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int i915_gem_init_rings(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index de241eb..3746738 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3608,7 +3608,7 @@ err_unpin:
 	return vma;
 }
 
-bool
+enum drm_cache_flush
 i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			bool force)
 {
@@ -3617,14 +3617,14 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	 * again at bind time.
 	 */
 	if (obj->pages == NULL)
-		return false;
+		return DRM_CACHE_FLUSH_NONE;
 
 	/*
 	 * 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 || obj->phys_handle)
-		return false;
+		return DRM_CACHE_FLUSH_NONE;
 
 	/* If the GPU is snooping the contents of the CPU cache,
 	 * we do not need to manually clear the CPU cache lines.  However,
@@ -3635,12 +3635,10 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	 * tracking.
 	 */
 	if (!force && cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
-		return false;
+		return DRM_CACHE_FLUSH_NONE;
 
 	trace_i915_gem_object_clflush(obj);
-	drm_clflush_sg(obj->pages);
-
-	return true;
+	return drm_clflush_sg(obj->pages);
 }
 
 /** Flushes the GTT write domain for the object if it's dirty. */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0c25f62..e8eb9e9 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -827,7 +827,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 {
 	struct i915_vma *vma;
 	uint32_t flush_domains = 0;
-	bool flush_chipset = false;
+	enum drm_cache_flush flush_chipset = DRM_CACHE_FLUSH_NONE;
 	int ret;
 
 	list_for_each_entry(vma, vmas, exec_list) {
@@ -836,8 +836,10 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 		if (ret)
 			return ret;
 
-		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			flush_chipset |= i915_gem_clflush_object(obj, false);
+		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU &&
+		    flush_chipset != DRM_CACHE_FLUSH_WBINVD) {
+			flush_chipset = i915_gem_clflush_object(obj, false);
+		}
 
 		flush_domains |= obj->base.write_domain;
 	}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 89b5577..a6c6ebd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -611,7 +611,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
 	struct intel_engine_cs *ring = ringbuf->ring;
 	struct i915_vma *vma;
 	uint32_t flush_domains = 0;
-	bool flush_chipset = false;
+	enum drm_cache_flush flush_chipset = DRM_CACHE_FLUSH_NONE;
 	int ret;
 
 	list_for_each_entry(vma, vmas, exec_list) {
@@ -621,8 +621,10 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
 		if (ret)
 			return ret;
 
-		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			flush_chipset |= i915_gem_clflush_object(obj, false);
+		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU &&
+		    flush_chipset != DRM_CACHE_FLUSH_WBINVD) {
+			flush_chipset = i915_gem_clflush_object(obj, false);
+		}
 
 		flush_domains |= obj->base.write_domain;
 	}
-- 
2.1.3