drm/radeon/kms: fix alignment when allocating buffers

We were previously dropping alignment requests on the floor
when allocating buffers so we always ended up page aligned.
Certain tiling modes on 6xx+ require larger alignment which
wasn't happening before.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Cc: Jerome Glisse <j.glisse@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/evergreen_blit_kms.c

@@ -459,7 +459,7 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	obj_size += evergreen_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
-	r = radeon_bo_create(rdev, NULL, obj_size, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&rdev->r600_blit.shader_obj);
 	if (r) {
 		DRM_ERROR("evergreen failed to allocate shader\n");

drivers/gpu/drm/radeon/r600.c

@@ -2718,7 +2718,7 @@ static int r600_ih_ring_alloc(struct radeon_device *rdev)
 	/* Allocate ring buffer */
 	if (rdev->ih.ring_obj == NULL) {
 		r = radeon_bo_create(rdev, NULL, rdev->ih.ring_size,
-				     true,
+				     PAGE_SIZE, true,
 				     RADEON_GEM_DOMAIN_GTT,
 				     &rdev->ih.ring_obj);
 		if (r) {

drivers/gpu/drm/radeon/r600_blit_kms.c

@@ -501,7 +501,7 @@ int r600_blit_init(struct radeon_device *rdev)
 	obj_size += r6xx_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
-	r = radeon_bo_create(rdev, NULL, obj_size, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&rdev->r600_blit.shader_obj);
 	if (r) {
 		DRM_ERROR("r600 failed to allocate shader\n");

drivers/gpu/drm/radeon/radeon_benchmark.c

@@ -41,7 +41,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 
 	size = bsize;
 	n = 1024;
-	r = radeon_bo_create(rdev, NULL, size, true, sdomain, &sobj);
+	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, sdomain, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -53,7 +53,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = radeon_bo_create(rdev, NULL, size, true, ddomain, &dobj);
+	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, ddomain, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}

drivers/gpu/drm/radeon/radeon_device.c

@@ -180,7 +180,7 @@ int radeon_wb_init(struct radeon_device *rdev)
 	int r;
 
 	if (rdev->wb.wb_obj == NULL) {
-		r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE, true,
+		r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
 				RADEON_GEM_DOMAIN_GTT, &rdev->wb.wb_obj);
 		if (r) {
 			dev_warn(rdev->dev, "(%d) create WB bo failed\n", r);

drivers/gpu/drm/radeon/radeon_gart.c

@@ -79,8 +79,8 @@ int radeon_gart_table_vram_alloc(struct radeon_device *rdev)
 
 	if (rdev->gart.table.vram.robj == NULL) {
 		r = radeon_bo_create(rdev, NULL, rdev->gart.table_size,
-					true, RADEON_GEM_DOMAIN_VRAM,
-					&rdev->gart.table.vram.robj);
+				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+				     &rdev->gart.table.vram.robj);
 		if (r) {
 			return r;
 		}

drivers/gpu/drm/radeon/radeon_gem.c

@@ -67,7 +67,7 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size,
 	if (alignment < PAGE_SIZE) {
 		alignment = PAGE_SIZE;
 	}
-	r = radeon_bo_create(rdev, gobj, size, kernel, initial_domain, &robj);
+	r = radeon_bo_create(rdev, gobj, size, alignment, kernel, initial_domain, &robj);
 	if (r) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to allocate GEM object (%d, %d, %u, %d)\n",

drivers/gpu/drm/radeon/radeon_object.c

@@ -86,11 +86,12 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 }
 
 int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj,
-			unsigned long size, bool kernel, u32 domain,
-			struct radeon_bo **bo_ptr)
+		     unsigned long size, int byte_align, bool kernel, u32 domain,
+		     struct radeon_bo **bo_ptr)
 {
 	struct radeon_bo *bo;
 	enum ttm_bo_type type;
+	int page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
 	int r;
 
 	if (unlikely(rdev->mman.bdev.dev_mapping == NULL)) {
@@ -115,7 +116,7 @@ retry:
 	/* Kernel allocation are uninterruptible */
 	mutex_lock(&rdev->vram_mutex);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
-			&bo->placement, 0, 0, !kernel, NULL, size,
+			&bo->placement, page_align, 0, !kernel, NULL, size,
 			&radeon_ttm_bo_destroy);
 	mutex_unlock(&rdev->vram_mutex);
 	if (unlikely(r != 0)) {

drivers/gpu/drm/radeon/radeon_object.h

@@ -137,9 +137,10 @@ static inline int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
 }
 
 extern int radeon_bo_create(struct radeon_device *rdev,
-				struct drm_gem_object *gobj, unsigned long size,
-				bool kernel, u32 domain,
-				struct radeon_bo **bo_ptr);
+			    struct drm_gem_object *gobj, unsigned long size,
+			    int byte_align,
+			    bool kernel, u32 domain,
+			    struct radeon_bo **bo_ptr);
 extern int radeon_bo_kmap(struct radeon_bo *bo, void **ptr);
 extern void radeon_bo_kunmap(struct radeon_bo *bo);
 extern void radeon_bo_unref(struct radeon_bo **bo);

drivers/gpu/drm/radeon/radeon_ring.c

@@ -176,8 +176,8 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	INIT_LIST_HEAD(&rdev->ib_pool.bogus_ib);
 	/* Allocate 1M object buffer */
 	r = radeon_bo_create(rdev, NULL,  RADEON_IB_POOL_SIZE*64*1024,
-				true, RADEON_GEM_DOMAIN_GTT,
-				&rdev->ib_pool.robj);
+			     PAGE_SIZE, true, RADEON_GEM_DOMAIN_GTT,
+			     &rdev->ib_pool.robj);
 	if (r) {
 		DRM_ERROR("radeon: failed to ib pool (%d).\n", r);
 		return r;
@@ -332,7 +332,7 @@ int radeon_ring_init(struct radeon_device *rdev, unsigned ring_size)
 	rdev->cp.ring_size = ring_size;
 	/* Allocate ring buffer */
 	if (rdev->cp.ring_obj == NULL) {
-		r = radeon_bo_create(rdev, NULL, rdev->cp.ring_size, true,
+		r = radeon_bo_create(rdev, NULL, rdev->cp.ring_size, PAGE_SIZE, true,
 					RADEON_GEM_DOMAIN_GTT,
 					&rdev->cp.ring_obj);
 		if (r) {

drivers/gpu/drm/radeon/radeon_test.c

@@ -52,7 +52,7 @@ void radeon_test_moves(struct radeon_device *rdev)
 		goto out_cleanup;
 	}
 
-	r = radeon_bo_create(rdev, NULL, size, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
@@ -71,7 +71,7 @@ void radeon_test_moves(struct radeon_device *rdev)
 		void **gtt_start, **gtt_end;
 		void **vram_start, **vram_end;
 
-		r = radeon_bo_create(rdev, NULL, size, true,
+		r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true,
 					 RADEON_GEM_DOMAIN_GTT, gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);

drivers/gpu/drm/radeon/radeon_ttm.c

@@ -529,7 +529,7 @@ int radeon_ttm_init(struct radeon_device *rdev)
 		DRM_ERROR("Failed initializing VRAM heap.\n");
 		return r;
 	}
-	r = radeon_bo_create(rdev, NULL, 256 * 1024, true,
+	r = radeon_bo_create(rdev, NULL, 256 * 1024, PAGE_SIZE, true,
 				RADEON_GEM_DOMAIN_VRAM,
 				&rdev->stollen_vga_memory);
 	if (r) {

drivers/gpu/drm/radeon/rv770.c

@@ -915,8 +915,8 @@ static int rv770_vram_scratch_init(struct radeon_device *rdev)
 
 	if (rdev->vram_scratch.robj == NULL) {
 		r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE,
-					true, RADEON_GEM_DOMAIN_VRAM,
-					&rdev->vram_scratch.robj);
+				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+				     &rdev->vram_scratch.robj);
 		if (r) {
 			return r;
 		}