radeonsi/gfx9: fix VM fault with fetched instance divisors

We need to account for SGPR locations in merged shaders.

This case is exercised by KHR-GL45.enhanced_layouts.vertex_attrib_locations

Fixes: 79c2e7388c7f ("radeonsi/gfx9: use SPI_SHADER_USER_DATA_COMMON")
Reviewed-by: Marek Olšák <[email protected]>

2 files changed, 12 insertions, 5 deletions

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index c1a310275c1..e6b14f92056 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -5883,11 +5883,13 @@ static void si_get_vs_prolog_key(const struct tgsi_shader_info *info,
 	key->vs_prolog.num_input_sgprs = num_input_sgprs;
 	key->vs_prolog.last_input = MAX2(1, info->num_inputs) - 1;
 	key->vs_prolog.as_ls = shader_out->key.as_ls;
+	key->vs_prolog.as_es = shader_out->key.as_es;
 
 	if (shader_out->selector->type == PIPE_SHADER_TESS_CTRL) {
 		key->vs_prolog.as_ls = 1;
 		key->vs_prolog.num_merged_next_stage_vgprs = 2;
 	} else if (shader_out->selector->type == PIPE_SHADER_GEOMETRY) {
+		key->vs_prolog.as_es = 1;
 		key->vs_prolog.num_merged_next_stage_vgprs = 5;
 	}
 
@@ -6768,6 +6770,8 @@ si_get_shader_part(struct si_screen *sscreen,
 
 	switch (type) {
 	case PIPE_SHADER_VERTEX:
+		shader.key.as_ls = key->vs_prolog.as_ls;
+		shader.key.as_es = key->vs_prolog.as_es;
 		break;
 	case PIPE_SHADER_TESS_CTRL:
 		assert(!prolog);
@@ -6810,10 +6814,15 @@ out:
 static LLVMValueRef si_prolog_get_rw_buffers(struct si_shader_context *ctx)
 {
 	LLVMValueRef ptr[2], list;
+	bool is_merged_shader =
+		ctx->screen->b.chip_class >= GFX9 &&
+		(ctx->type == PIPE_SHADER_TESS_CTRL ||
+		 ctx->type == PIPE_SHADER_GEOMETRY ||
+		 ctx->shader->key.as_ls || ctx->shader->key.as_es);
 
 	/* Get the pointer to rw buffers. */
-	ptr[0] = LLVMGetParam(ctx->main_fn, SI_SGPR_RW_BUFFERS);
-	ptr[1] = LLVMGetParam(ctx->main_fn, SI_SGPR_RW_BUFFERS_HI);
+	ptr[0] = LLVMGetParam(ctx->main_fn, (is_merged_shader ? 8 : 0) + SI_SGPR_RW_BUFFERS);
+	ptr[1] = LLVMGetParam(ctx->main_fn, (is_merged_shader ? 8 : 0) + SI_SGPR_RW_BUFFERS_HI);
 	list = lp_build_gather_values(&ctx->gallivm, ptr, 2);
 	list = LLVMBuildBitCast(ctx->ac.builder, list, ctx->i64, "");
 	list = LLVMBuildIntToPtr(ctx->ac.builder, list,
diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index 41851627a87..148356b87ff 100644
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -149,9 +149,6 @@ struct nir_shader;
 
 /* SGPR user data indices */
 enum {
-	/* GFX9 merged shaders have RW_BUFFERS among the first 8 system SGPRs,
-	 * and these two are used for other purposes.
-	 */
 	SI_SGPR_RW_BUFFERS,  /* rings (& stream-out, VS only) */
 	SI_SGPR_RW_BUFFERS_HI,
 	SI_SGPR_BINDLESS_SAMPLERS_AND_IMAGES,
@@ -455,6 +452,7 @@ union si_shader_part_key {
 		unsigned	num_merged_next_stage_vgprs:3;
 		unsigned	last_input:4;
 		unsigned	as_ls:1;
+		unsigned	as_es:1;
 		/* Prologs for monolithic shaders shouldn't set EXEC. */
 		unsigned	is_monolithic:1;
 	} vs_prolog;