[Intel-gfx] [PATCH] drm/i915: Fix unfenced alignment on pre-G33 hardware

[Chris Wilson]

Align unfenced buffers on older hardware to the power-of-two object size.
The docs suggest that it should be possible to align only to a power-of-two
tile height, but using the already computed fence size is easier and
always correct. We also have to make sure that we unbind misaligned buffers
upon tiling changes.

Reported-and-tested-by: Sitosfe Wheeler <sitsofe at yahoo.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=36326
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---

Updated to pass tiling_mode to all the gtt size/alignment functions for
consistency and to prevent any more lurking bugs.

---
 drivers/gpu/drm/i915/i915_drv.h        |    3 +-
 drivers/gpu/drm/i915/i915_gem.c        |   47 +++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_gem_tiling.c |    3 +-
 3 files changed, 26 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2798d27..a9492d9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1216,7 +1216,8 @@ void i915_gem_free_all_phys_object(struct drm_device *dev);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
 
 uint32_t
-i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj,
+				    int tiling_mode);
 
 int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2e0d891..4c4f6c3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1374,13 +1374,14 @@ i915_gem_free_mmap_offset(struct drm_i915_gem_object *obj)
 }
 
 static uint32_t
-i915_gem_get_gtt_size(struct drm_i915_gem_object *obj)
+i915_gem_get_gtt_size(struct drm_i915_gem_object *obj,
+		      int tiling_mode)
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t size;
 
 	if (INTEL_INFO(dev)->gen >= 4 ||
-	    obj->tiling_mode == I915_TILING_NONE)
+	    tiling_mode == I915_TILING_NONE)
 		return obj->base.size;
 
 	/* Previous chips need a power-of-two fence region when tiling */
@@ -1403,7 +1404,8 @@ i915_gem_get_gtt_size(struct drm_i915_gem_object *obj)
  * potential fence register mapping.
  */
 static uint32_t
-i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj)
+i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj,
+			   int tiling_mode)
 {
 	struct drm_device *dev = obj->base.dev;
 
@@ -1411,51 +1413,45 @@ i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj)
 	 * Minimum alignment is 4k (GTT page size), but might be greater
 	 * if a fence register is needed for the object.
 	 */
-	if (INTEL_INFO(dev)->gen >= 4 ||
-	    obj->tiling_mode == I915_TILING_NONE)
+	if (INTEL_INFO(dev)->gen >= 4 || tiling_mode == I915_TILING_NONE)
 		return 4096;
 
 	/*
 	 * Previous chips need to be aligned to the size of the smallest
 	 * fence register that can contain the object.
 	 */
-	return i915_gem_get_gtt_size(obj);
+	return i915_gem_get_gtt_size(obj, tiling_mode);
 }
 
 /**
  * i915_gem_get_unfenced_gtt_alignment - return required GTT alignment for an
  *					 unfenced object
  * @obj: object to check
+ * @tiling_mode: tiling mode of the object
  *
  * Return the required GTT alignment for an object, only taking into account
  * unfenced tiled surface requirements.
  */
 uint32_t
-i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
+i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj,
+				    int tiling_mode)
 {
 	struct drm_device *dev = obj->base.dev;
-	int tile_height;
+
+	if (tiling_mode == I915_TILING_NONE)
+		return 4096;
 
 	/*
 	 * Minimum alignment is 4k (GTT page size) for sane hw.
 	 */
-	if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev) ||
-	    obj->tiling_mode == I915_TILING_NONE)
+	if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev))
 		return 4096;
 
-	/*
-	 * Older chips need unfenced tiled buffers to be aligned to the left
-	 * edge of an even tile row (where tile rows are counted as if the bo is
-	 * placed in a fenced gtt region).
+	/* Previous hardware however needs to be aligned to a power-of-two
+	 * tile height. The simplest method for determining this is to reuse
+	 * the power-of-tile object size.
 	 */
-	if (IS_GEN2(dev))
-		tile_height = 16;
-	else if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
-		tile_height = 32;
-	else
-		tile_height = 8;
-
-	return tile_height * obj->stride * 2;
+	return i915_gem_get_gtt_size(obj, tiling_mode);
 }
 
 int
@@ -2786,9 +2782,10 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 		return -EINVAL;
 	}
 
-	fence_size = i915_gem_get_gtt_size(obj);
-	fence_alignment = i915_gem_get_gtt_alignment(obj);
-	unfenced_alignment = i915_gem_get_unfenced_gtt_alignment(obj);
+	fence_size = i915_gem_get_gtt_size(obj, obj->tiling_mode);
+	fence_alignment = i915_gem_get_gtt_alignment(obj, obj->tiling_mode);
+	unfenced_alignment =
+		i915_gem_get_unfenced_gtt_alignment(obj, obj->tiling_mode);
 
 	if (alignment == 0)
 		alignment = map_and_fenceable ? fence_alignment :
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 82d70fd..8433b97 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -348,7 +348,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		/* Rebind if we need a change of alignment */
 		if (!obj->map_and_fenceable) {
 			u32 unfenced_alignment =
-				i915_gem_get_unfenced_gtt_alignment(obj);
+				i915_gem_get_unfenced_gtt_alignment(obj,
+								    args->tiling_mode);
 			if (obj->gtt_offset & (unfenced_alignment - 1))
 				ret = i915_gem_object_unbind(obj);
 		}
-- 
1.7.5.4