[Mesa-dev] [PATCH 14/20] radeonsi: reserve a parameter slot for FMASK resources in shaders

[Marek Olšák]

---
 src/gallium/drivers/radeonsi/radeonsi_shader.c |  7 ++--
 src/gallium/drivers/radeonsi/radeonsi_shader.h | 58 ++++++++++++++------------
 src/gallium/drivers/radeonsi/si_state_draw.c   |  1 +
 3 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi/radeonsi_shader.c
index 18dde61..2806045 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_shader.c
+++ b/src/gallium/drivers/radeonsi/radeonsi_shader.c
@@ -1209,7 +1209,7 @@ static void create_function(struct si_shader_context *si_shader_ctx)
 {
 	struct lp_build_tgsi_context *bld_base = &si_shader_ctx->radeon_bld.soa.bld_base;
 	struct gallivm_state *gallivm = bld_base->base.gallivm;
-	LLVMTypeRef params[20], f32, i8, i32, v2i32, v3i32;
+	LLVMTypeRef params[SI_MAX_PARAMS], f32, i8, i32, v2i32, v3i32;
 	unsigned i;
 
 	i8 = LLVMInt8TypeInContext(gallivm->context);
@@ -1221,6 +1221,7 @@ static void create_function(struct si_shader_context *si_shader_ctx)
 	params[SI_PARAM_CONST] = LLVMPointerType(LLVMVectorType(i8, 16), CONST_ADDR_SPACE);
 	params[SI_PARAM_SAMPLER] = params[SI_PARAM_CONST];
 	params[SI_PARAM_RESOURCE] = LLVMPointerType(LLVMVectorType(i8, 32), CONST_ADDR_SPACE);
+	params[SI_PARAM_FMASK_RESOURCE] = params[SI_PARAM_RESOURCE];
 
 	if (si_shader_ctx->type == TGSI_PROCESSOR_VERTEX) {
 		params[SI_PARAM_VERTEX_BUFFER] = params[SI_PARAM_SAMPLER];
@@ -1229,7 +1230,7 @@ static void create_function(struct si_shader_context *si_shader_ctx)
 		params[SI_PARAM_DUMMY_0] = i32;
 		params[SI_PARAM_DUMMY_1] = i32;
 		params[SI_PARAM_INSTANCE_ID] = i32;
-		radeon_llvm_create_func(&si_shader_ctx->radeon_bld, params, 9);
+		radeon_llvm_create_func(&si_shader_ctx->radeon_bld, params, 10);
 
 	} else {
 		params[SI_PARAM_PRIM_MASK] = i32;
@@ -1249,7 +1250,7 @@ static void create_function(struct si_shader_context *si_shader_ctx)
 		params[SI_PARAM_ANCILLARY] = f32;
 		params[SI_PARAM_SAMPLE_COVERAGE] = f32;
 		params[SI_PARAM_POS_FIXED_PT] = f32;
-		radeon_llvm_create_func(&si_shader_ctx->radeon_bld, params, 20);
+		radeon_llvm_create_func(&si_shader_ctx->radeon_bld, params, 21);
 	}
 
 	radeon_llvm_shader_type(si_shader_ctx->radeon_bld.main_fn, si_shader_ctx->type);
diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.h b/src/gallium/drivers/radeonsi/radeonsi_shader.h
index 2ce34b9..836b144 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_shader.h
+++ b/src/gallium/drivers/radeonsi/radeonsi_shader.h
@@ -34,43 +34,47 @@
 #define SI_SGPR_CONST		0
 #define SI_SGPR_SAMPLER		2
 #define SI_SGPR_RESOURCE	4
-#define SI_SGPR_VERTEX_BUFFER	6
-#define SI_SGPR_START_INSTANCE	8
+#define SI_SGPR_FMASK_RESOURCE	6
+#define SI_SGPR_VERTEX_BUFFER	8
+#define SI_SGPR_START_INSTANCE	10
 
-#define SI_VS_NUM_USER_SGPR	9
-#define SI_PS_NUM_USER_SGPR	6
+#define SI_VS_NUM_USER_SGPR	11
+#define SI_PS_NUM_USER_SGPR	8
 
 /* LLVM function parameter indices */
 #define SI_PARAM_CONST		0
 #define SI_PARAM_SAMPLER	1
 #define SI_PARAM_RESOURCE	2
+#define SI_PARAM_FMASK_RESOURCE	3
 
 /* VS only parameters */
-#define SI_PARAM_VERTEX_BUFFER	3
-#define SI_PARAM_START_INSTANCE	4
-#define SI_PARAM_VERTEX_ID	5
-#define SI_PARAM_DUMMY_0	6
-#define SI_PARAM_DUMMY_1	7
-#define SI_PARAM_INSTANCE_ID	8
+#define SI_PARAM_VERTEX_BUFFER	4
+#define SI_PARAM_START_INSTANCE	5
+#define SI_PARAM_VERTEX_ID	6
+#define SI_PARAM_DUMMY_0	7
+#define SI_PARAM_DUMMY_1	8
+#define SI_PARAM_INSTANCE_ID	9
 
 /* PS only parameters */
-#define SI_PARAM_PRIM_MASK		3
-#define SI_PARAM_PERSP_SAMPLE		4
-#define SI_PARAM_PERSP_CENTER		5
-#define SI_PARAM_PERSP_CENTROID		6
-#define SI_PARAM_PERSP_PULL_MODEL	7
-#define SI_PARAM_LINEAR_SAMPLE		8
-#define SI_PARAM_LINEAR_CENTER		9
-#define SI_PARAM_LINEAR_CENTROID	10
-#define SI_PARAM_LINE_STIPPLE_TEX	11
-#define SI_PARAM_POS_X_FLOAT		12
-#define SI_PARAM_POS_Y_FLOAT		13
-#define SI_PARAM_POS_Z_FLOAT		14
-#define SI_PARAM_POS_W_FLOAT		15
-#define SI_PARAM_FRONT_FACE		16
-#define SI_PARAM_ANCILLARY		17
-#define SI_PARAM_SAMPLE_COVERAGE	18
-#define SI_PARAM_POS_FIXED_PT		19
+#define SI_PARAM_PRIM_MASK		4
+#define SI_PARAM_PERSP_SAMPLE		5
+#define SI_PARAM_PERSP_CENTER		6
+#define SI_PARAM_PERSP_CENTROID		7
+#define SI_PARAM_PERSP_PULL_MODEL	8
+#define SI_PARAM_LINEAR_SAMPLE		9
+#define SI_PARAM_LINEAR_CENTER		10
+#define SI_PARAM_LINEAR_CENTROID	11
+#define SI_PARAM_LINE_STIPPLE_TEX	12
+#define SI_PARAM_POS_X_FLOAT		13
+#define SI_PARAM_POS_Y_FLOAT		14
+#define SI_PARAM_POS_Z_FLOAT		15
+#define SI_PARAM_POS_W_FLOAT		16
+#define SI_PARAM_FRONT_FACE		17
+#define SI_PARAM_ANCILLARY		18
+#define SI_PARAM_SAMPLE_COVERAGE	19
+#define SI_PARAM_POS_FIXED_PT		20
+
+#define SI_MAX_PARAMS			21
 
 struct si_shader_io {
 	unsigned		name;
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index 746ace6..4208fa7 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -241,6 +241,7 @@ static void si_pipe_shader_ps(struct pipe_context *ctx, struct si_pipe_shader *s
 		/* Last 2 reserved SGPRs are used for VCC */
 		num_sgprs = num_user_sgprs + 2;
 	}
+	num_sgprs += 1; /* XXX this fixes VM faults */
 	assert(num_sgprs <= 104);
 
 	si_pm4_set_reg(pm4, R_00B028_SPI_SHADER_PGM_RSRC1_PS,
-- 
1.8.1.2