[Mesa-dev] [PATCH] radeonsi: add BOs after need_cs_space

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

need_cs_space may clear the buffer list.

Fixes: 951d60f8cdc88 "radeonsi: delay adding BOs at the beginning of IBs until the first draw"
---
 src/gallium/drivers/radeonsi/si_compute.c    | 6 +++---
 src/gallium/drivers/radeonsi/si_state_draw.c | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/si_compute.c b/src/gallium/drivers/radeonsi/si_compute.c
index 2f444a3a1b8..541d7e6f118 100644
--- a/src/gallium/drivers/radeonsi/si_compute.c
+++ b/src/gallium/drivers/radeonsi/si_compute.c
@@ -878,40 +878,40 @@ static void si_launch_grid(
 
 	if (sctx->has_graphics) {
 		if (sctx->last_num_draw_calls != sctx->num_draw_calls) {
 			si_update_fb_dirtiness_after_rendering(sctx);
 			sctx->last_num_draw_calls = sctx->num_draw_calls;
 		}
 
 		si_decompress_textures(sctx, 1 << PIPE_SHADER_COMPUTE);
 	}
 
-	if (sctx->bo_list_add_all_compute_resources)
-		si_compute_resources_add_all_to_bo_list(sctx);
-
 	/* Add buffer sizes for memory checking in need_cs_space. */
 	si_context_add_resource_size(sctx, &program->shader.bo->b.b);
 	/* TODO: add the scratch buffer */
 
 	if (info->indirect) {
 		si_context_add_resource_size(sctx, info->indirect);
 
 		/* Indirect buffers use TC L2 on GFX9, but not older hw. */
 		if (sctx->chip_class <= VI &&
 		    si_resource(info->indirect)->TC_L2_dirty) {
 			sctx->flags |= SI_CONTEXT_WRITEBACK_GLOBAL_L2;
 			si_resource(info->indirect)->TC_L2_dirty = false;
 		}
 	}
 
 	si_need_gfx_cs_space(sctx);
 
+	if (sctx->bo_list_add_all_compute_resources)
+		si_compute_resources_add_all_to_bo_list(sctx);
+
 	if (!sctx->cs_shader_state.initialized)
 		si_initialize_compute(sctx);
 
 	if (sctx->flags)
 		si_emit_cache_flush(sctx);
 
 	if (!si_switch_compute_shader(sctx, program, &program->shader,
 					code_object, info->pc))
 		return;
 
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index d2c74152337..8e01e1b35e1 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -1287,23 +1287,20 @@ static void si_draw_vbo(struct pipe_context *ctx, const struct pipe_draw_info *i
 		sctx->last_dirty_tex_counter = dirty_tex_counter;
 		sctx->framebuffer.dirty_cbufs |=
 			((1 << sctx->framebuffer.state.nr_cbufs) - 1);
 		sctx->framebuffer.dirty_zsbuf = true;
 		si_mark_atom_dirty(sctx, &sctx->atoms.s.framebuffer);
 		si_update_all_texture_descriptors(sctx);
 	}
 
 	si_decompress_textures(sctx, u_bit_consecutive(0, SI_NUM_GRAPHICS_SHADERS));
 
-	if (sctx->bo_list_add_all_gfx_resources)
-		si_gfx_resources_add_all_to_bo_list(sctx);
-
 	/* Set the rasterization primitive type.
 	 *
 	 * This must be done after si_decompress_textures, which can call
 	 * draw_vbo recursively, and before si_update_shaders, which uses
 	 * current_rast_prim for this draw_vbo call. */
 	if (sctx->gs_shader.cso)
 		rast_prim = sctx->gs_shader.cso->gs_output_prim;
 	else if (sctx->tes_shader.cso) {
 		if (sctx->tes_shader.cso->info.properties[TGSI_PROPERTY_TES_POINT_MODE])
 			rast_prim = PIPE_PRIM_POINTS;
@@ -1431,20 +1428,23 @@ static void si_draw_vbo(struct pipe_context *ctx, const struct pipe_draw_info *i
 			if (indirect->indirect_draw_count &&
 			    si_resource(indirect->indirect_draw_count)->TC_L2_dirty) {
 				sctx->flags |= SI_CONTEXT_WRITEBACK_GLOBAL_L2;
 				si_resource(indirect->indirect_draw_count)->TC_L2_dirty = false;
 			}
 		}
 	}
 
 	si_need_gfx_cs_space(sctx);
 
+	if (sctx->bo_list_add_all_gfx_resources)
+		si_gfx_resources_add_all_to_bo_list(sctx);
+
 	/* Since we've called si_context_add_resource_size for vertex buffers,
 	 * this must be called after si_need_cs_space, because we must let
 	 * need_cs_space flush before we add buffers to the buffer list.
 	 */
 	if (!si_upload_vertex_buffer_descriptors(sctx))
 		goto return_cleanup;
 
 	/* Vega10/Raven scissor bug workaround. When any context register is
 	 * written (i.e. the GPU rolls the context), PA_SC_VPORT_SCISSOR
 	 * registers must be written too.
-- 
2.17.1