drm/radeon: make ib size variable

This avoid to waste ib pool size and avoid a bunch of wait for
previous ib to finish.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/r100.c

@@ -3708,7 +3708,7 @@ int r100_ib_test(struct radeon_device *rdev)
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
-	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib);
+	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, 256);
 	if (r) {
 		return r;
 	}

drivers/gpu/drm/radeon/r600.c

@@ -2711,7 +2711,7 @@ int r600_ib_test(struct radeon_device *rdev, int ring)
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
-	r = radeon_ib_get(rdev, ring, &ib);
+	r = radeon_ib_get(rdev, ring, &ib, 256);
 	if (r) {
 		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
 		return r;

drivers/gpu/drm/radeon/r600_blit_kms.c

@@ -619,16 +619,17 @@ void r600_blit_fini(struct radeon_device *rdev)
 	radeon_bo_unref(&rdev->r600_blit.shader_obj);
 }
 
-static int r600_vb_ib_get(struct radeon_device *rdev)
+static int r600_vb_ib_get(struct radeon_device *rdev, unsigned size)
 {
 	int r;
-	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->r600_blit.vb_ib);
+	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX,
+			  &rdev->r600_blit.vb_ib, size);
 	if (r) {
 		DRM_ERROR("failed to get IB for vertex buffer\n");
 		return r;
 	}
 
-	rdev->r600_blit.vb_total = 64*1024;
+	rdev->r600_blit.vb_total = size;
 	rdev->r600_blit.vb_used = 0;
 	return 0;
 }
@@ -693,10 +694,6 @@ int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages)
 	int num_loops = 0;
 	int dwords_per_loop = rdev->r600_blit.ring_size_per_loop;
 
-	r = r600_vb_ib_get(rdev);
-	if (r)
-		return r;
-
 	/* num loops */
 	while (num_gpu_pages) {
 		num_gpu_pages -=
@@ -705,6 +702,11 @@ int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages)
 		num_loops++;
 	}
 
+	/* 48 bytes for vertex per loop */
+	r = r600_vb_ib_get(rdev, (num_loops*48)+256);
+	if (r)
+		return r;
+
 	/* calculate number of loops correctly */
 	ring_size = num_loops * dwords_per_loop;
 	ring_size += rdev->r600_blit.ring_size_common;

drivers/gpu/drm/radeon/radeon.h

@@ -638,7 +638,8 @@ struct r600_blit {
 
 void r600_blit_suspend(struct radeon_device *rdev);
 
-int radeon_ib_get(struct radeon_device *rdev, int ring, struct radeon_ib **ib);
+int radeon_ib_get(struct radeon_device *rdev, int ring,
+		  struct radeon_ib **ib, unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);

drivers/gpu/drm/radeon/radeon_cs.c

@@ -246,7 +246,9 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		radeon_mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
-	r =  radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &parser.ib);
+	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
+	r =  radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &parser.ib,
+			   ib_chunk->length_dw * 4);
 	if (r) {
 		DRM_ERROR("Failed to get ib !\n");
 		radeon_cs_parser_fini(&parser, r);
@@ -264,7 +266,6 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	/* Copy the packet into the IB, the parser will read from the
 	 * input memory (cached) and write to the IB (which can be
 	 * uncached). */
-	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
 	parser.ib->length_dw = ib_chunk->length_dw;
 	r = radeon_cs_parse(&parser);
 	if (r || parser.parser_error) {

drivers/gpu/drm/radeon/radeon_ring.c

@@ -93,13 +93,16 @@ static bool radeon_ib_try_free(struct radeon_device *rdev,
 	return done;
 }
 
-int radeon_ib_get(struct radeon_device *rdev, int ring, struct radeon_ib **ib)
+int radeon_ib_get(struct radeon_device *rdev, int ring,
+		  struct radeon_ib **ib, unsigned size)
 {
 	struct radeon_fence *fence;
 	unsigned cretry = 0;
 	int r = 0, i, idx;
 
 	*ib = NULL;
+	/* align size on 256 bytes */
+	size = ALIGN(size, 256);
 
 	r = radeon_fence_create(rdev, &fence, ring);
 	if (r) {
@@ -122,7 +125,7 @@ int radeon_ib_get(struct radeon_device *rdev, int ring, struct radeon_ib **ib)
 		if (rdev->ib_pool.ibs[idx].fence == NULL) {
 			r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
 					     &rdev->ib_pool.ibs[idx].sa_bo,
-					     64*1024, 64);
+					     size, 256);
 			if (!r) {
 				*ib = &rdev->ib_pool.ibs[idx];
 				(*ib)->ptr = rdev->ib_pool.sa_manager.cpu_ptr;