3 files changed, 20 insertions, 4 deletions
diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index eb573450db5..ac427210288 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -5186,6 +5186,7 @@ static void create_function(struct si_shader_context *ctx)
 		break;
 
 	case PIPE_SHADER_TESS_CTRL:
+		params[SI_PARAM_TCS_OFFCHIP_LAYOUT] = ctx->i32;
 		params[SI_PARAM_TCS_OUT_OFFSETS] = ctx->i32;
 		params[SI_PARAM_TCS_OUT_LAYOUT] = ctx->i32;
 		params[SI_PARAM_TCS_IN_LAYOUT] = ctx->i32;
@@ -5211,6 +5212,7 @@ static void create_function(struct si_shader_context *ctx)
 		break;
 
 	case PIPE_SHADER_TESS_EVAL:
+		params[SI_PARAM_TCS_OFFCHIP_LAYOUT] = ctx->i32;
 		params[SI_PARAM_TCS_OUT_OFFSETS] = ctx->i32;
 		params[SI_PARAM_TCS_OUT_LAYOUT] = ctx->i32;
 		num_params = SI_PARAM_TCS_OUT_LAYOUT+1;
@@ -6768,6 +6770,7 @@ static bool si_compile_tcs_epilog(struct si_screen *sscreen,
 	params[SI_PARAM_SAMPLERS] = ctx.i64;
 	params[SI_PARAM_IMAGES] = ctx.i64;
 	params[SI_PARAM_SHADER_BUFFERS] = ctx.i64;
+	params[SI_PARAM_TCS_OFFCHIP_LAYOUT] = ctx.i32;
 	params[SI_PARAM_TCS_OUT_OFFSETS] = ctx.i32;
 	params[SI_PARAM_TCS_OUT_LAYOUT] = ctx.i32;
 	params[SI_PARAM_TCS_IN_LAYOUT] = ctx.i32;
diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index 7b1cbf9f6b0..26be25ea456 100644
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -107,7 +107,8 @@ enum {
 	SI_LS_NUM_USER_SGPR,
 
 	/* both TCS and TES */
-	SI_SGPR_TCS_OUT_OFFSETS	= SI_NUM_RESOURCE_SGPRS,
+	SI_SGPR_TCS_OFFCHIP_LAYOUT = SI_NUM_RESOURCE_SGPRS,
+	SI_SGPR_TCS_OUT_OFFSETS,
 	SI_SGPR_TCS_OUT_LAYOUT,
 	SI_TES_NUM_USER_SGPR,
 
@@ -147,11 +148,18 @@ enum {
 	SI_PARAM_LS_OUT_LAYOUT = SI_PARAM_START_INSTANCE + 1,
 	/* the other VS parameters are assigned dynamically */
 
+	/* Layout of TCS outputs in the offchip buffer
+	 *   [0:8] = the number of patches per threadgroup.
+	 *   [9:15] = the number of output vertices per patch.
+	 *   [16:31] = the offset of per patch attributes in the buffer in bytes.
+	 */
+	SI_PARAM_TCS_OFFCHIP_LAYOUT = SI_NUM_RESOURCE_PARAMS, /* for TCS & TES */
+
 	/* Offsets where TCS outputs and TCS patch outputs live in LDS:
 	 *   [0:15] = TCS output patch0 offset / 16, max = NUM_PATCHES * 32 * 32
 	 *   [16:31] = TCS output patch0 offset for per-patch / 16, max = NUM_PATCHES*32*32* + 32*32
 	 */
-	SI_PARAM_TCS_OUT_OFFSETS = SI_NUM_RESOURCE_PARAMS, /* for TCS & TES */
+	SI_PARAM_TCS_OUT_OFFSETS, /* for TCS & TES */
 
 	/* Layout of TCS outputs / TES inputs:
 	 *   [0:12] = stride between output patches in dwords, num_outputs * num_vertices * 4, max = 32*32*4
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index dab0dcce03b..e14a1c983f7 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -108,6 +108,7 @@ static void si_emit_derived_tess_state(struct si_context *sctx,
 	unsigned input_patch_size, output_patch_size, output_patch0_offset;
 	unsigned perpatch_output_offset, lds_size, ls_rsrc2;
 	unsigned tcs_in_layout, tcs_out_layout, tcs_out_offsets;
+	unsigned offchip_layout;
 
 	*num_patches = 1; /* TODO: calculate this */
 
@@ -183,6 +184,8 @@ static void si_emit_derived_tess_state(struct si_context *sctx,
 			 ((output_vertex_size / 4) << 13);
 	tcs_out_offsets = (output_patch0_offset / 16) |
 			  ((perpatch_output_offset / 16) << 16);
+	offchip_layout = (pervertex_output_patch_size * *num_patches << 16) |
+			 (num_tcs_output_cp << 9) | *num_patches;
 
 	/* Set them for LS. */
 	radeon_set_sh_reg(cs,
@@ -191,13 +194,15 @@ static void si_emit_derived_tess_state(struct si_context *sctx,
 
 	/* Set them for TCS. */
 	radeon_set_sh_reg_seq(cs,
-		R_00B430_SPI_SHADER_USER_DATA_HS_0 + SI_SGPR_TCS_OUT_OFFSETS * 4, 3);
+		R_00B430_SPI_SHADER_USER_DATA_HS_0 + SI_SGPR_TCS_OFFCHIP_LAYOUT * 4, 4);
+	radeon_emit(cs, offchip_layout);
 	radeon_emit(cs, tcs_out_offsets);
 	radeon_emit(cs, tcs_out_layout | (num_tcs_input_cp << 26));
 	radeon_emit(cs, tcs_in_layout);
 
 	/* Set them for TES. */
-	radeon_set_sh_reg_seq(cs, tes_sh_base + SI_SGPR_TCS_OUT_OFFSETS * 4, 2);
+	radeon_set_sh_reg_seq(cs, tes_sh_base + SI_SGPR_TCS_OFFCHIP_LAYOUT * 4, 3);
+	radeon_emit(cs, offchip_layout);
 	radeon_emit(cs, tcs_out_offsets);
 	radeon_emit(cs, tcs_out_layout | (num_tcs_output_cp << 26));
 }