radeonsi: Fix hardware state for dual source blending

Set up CB_SHADER_MASK register according to pixel shader exports, and enable
some minimal state for colour buffer 1 in case dual source blending is used.

4 files changed, 17 insertions, 6 deletions

diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi/radeonsi_shader.c
index 484f7ecfcdb..3e023f8600d 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_shader.c
+++ b/src/gallium/drivers/radeonsi/radeonsi_shader.c
@@ -461,6 +461,8 @@ static void si_llvm_init_export_args(struct lp_build_tgsi_context *bld_base,
 			else
 				si_shader_ctx->shader->spi_shader_col_format |=
 					V_028714_SPI_SHADER_32_ABGR << (4 * cbuf);
+
+			si_shader_ctx->shader->cb_shader_mask |= 0xf << (4 * cbuf);
 		}
 	}
 
@@ -806,6 +808,7 @@ static void si_llvm_emit_epilogue(struct lp_build_tgsi_context * bld_base)
 
 		si_shader_ctx->shader->spi_shader_col_format |=
 			V_028714_SPI_SHADER_32_ABGR;
+		si_shader_ctx->shader->cb_shader_mask |= S_02823C_OUTPUT0_ENABLE(0xf);
 	}
 
 	/* Specify whether the EXEC mask represents the valid mask */
@@ -830,6 +833,8 @@ static void si_llvm_emit_epilogue(struct lp_build_tgsi_context * bld_base)
 
 			si_shader_ctx->shader->spi_shader_col_format |=
 				si_shader_ctx->shader->spi_shader_col_format << 4;
+			si_shader_ctx->shader->cb_shader_mask |=
+				si_shader_ctx->shader->cb_shader_mask << 4;
 		}
 
 		last_args[3] = lp_build_const_int32(base->gallivm, V_008DFC_SQ_EXP_MRT);
diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.h b/src/gallium/drivers/radeonsi/radeonsi_shader.h
index 01b8b5d3b73..33e81c7d6d0 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_shader.h
+++ b/src/gallium/drivers/radeonsi/radeonsi_shader.h
@@ -140,6 +140,7 @@ struct si_pipe_shader {
 	unsigned			num_vgprs;
 	unsigned			spi_ps_input_ena;
 	unsigned			spi_shader_col_format;
+	unsigned			cb_shader_mask;
 	unsigned			sprite_coord_enable;
 	unsigned			so_strides[4];
 	union si_shader_key		key;
diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c
index dec535ca597..e7dc792b93c 100644
--- a/src/gallium/drivers/radeonsi/si_state.c
+++ b/src/gallium/drivers/radeonsi/si_state.c
@@ -1728,6 +1728,12 @@ static void si_cb(struct r600_context *rctx, struct si_pm4_state *pm4,
 	si_pm4_set_reg(pm4, R_028C70_CB_COLOR0_INFO + cb * 0x3C, color_info);
 	si_pm4_set_reg(pm4, R_028C74_CB_COLOR0_ATTRIB + cb * 0x3C, color_attrib);
 
+	/* set CB_COLOR1_INFO for possible dual-src blending */
+	if (state->nr_cbufs == 1) {
+		assert(cb == 0);
+		si_pm4_set_reg(pm4, R_028C70_CB_COLOR0_INFO + 1 * 0x3C, color_info);
+	}
+
 	/* Determine pixel shader export format */
 	max_comp_size = si_colorformat_max_comp_size(format);
 	if (ntype == V_028C70_NUMBER_SRGB ||
@@ -1735,6 +1741,9 @@ static void si_cb(struct r600_context *rctx, struct si_pm4_state *pm4,
 	     max_comp_size <= 10) ||
 	    (ntype == V_028C70_NUMBER_FLOAT && max_comp_size <= 16)) {
 		rctx->export_16bpc |= 1 << cb;
+		/* set SPI_SHADER_COL_FORMAT for possible dual-src blending */
+		if (state->nr_cbufs == 1)
+			rctx->export_16bpc |= 1 << 1;
 	}
 }
 
@@ -1811,7 +1820,7 @@ static void si_set_framebuffer_state(struct pipe_context *ctx,
 {
 	struct r600_context *rctx = (struct r600_context *)ctx;
 	struct si_pm4_state *pm4 = CALLOC_STRUCT(si_pm4_state);
-	uint32_t shader_mask, tl, br;
+	uint32_t tl, br;
 	int tl_x, tl_y, br_x, br_y;
 
 	if (pm4 == NULL)
@@ -1832,10 +1841,6 @@ static void si_set_framebuffer_state(struct pipe_context *ctx,
 	assert(!(rctx->export_16bpc & ~0xff));
 	si_db(rctx, pm4, state);
 
-	shader_mask = 0;
-	for (int i = 0; i < state->nr_cbufs; i++) {
-		shader_mask |= 0xf << (i * 4);
-	}
 	tl_x = 0;
 	tl_y = 0;
 	br_x = state->width;
@@ -1854,7 +1859,6 @@ static void si_set_framebuffer_state(struct pipe_context *ctx,
 	si_pm4_set_reg(pm4, R_028208_PA_SC_WINDOW_SCISSOR_BR, br);
 	si_pm4_set_reg(pm4, R_028200_PA_SC_WINDOW_OFFSET, 0x00000000);
 	si_pm4_set_reg(pm4, R_028230_PA_SC_EDGERULE, 0xAAAAAAAA);
-	si_pm4_set_reg(pm4, R_02823C_CB_SHADER_MASK, shader_mask);
 	si_pm4_set_reg(pm4, R_028BE0_PA_SC_AA_CONFIG, 0x00000000);
 
 	si_pm4_set_state(rctx, framebuffer, pm4);
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index ae571a4fb54..09c741fa3f1 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -213,6 +213,7 @@ static void si_pipe_shader_ps(struct pipe_context *ctx, struct si_pipe_shader *s
 	si_pm4_set_reg(pm4, R_028710_SPI_SHADER_Z_FORMAT, spi_shader_z_format);
 	si_pm4_set_reg(pm4, R_028714_SPI_SHADER_COL_FORMAT,
 		       shader->spi_shader_col_format);
+	si_pm4_set_reg(pm4, R_02823C_CB_SHADER_MASK, shader->cb_shader_mask);
 
 	va = r600_resource_va(ctx->screen, (void *)shader->bo);
 	si_pm4_add_bo(pm4, shader->bo, RADEON_USAGE_READ);