[Mesa-dev] [PATCH v5 REBASE] anv: enable VK_EXT_shader_stencil_export

[Gustavo Lima Chaves]

v2:
An attempt to support SpvExecutionModeStencilRefReplacingEXT's behavior
also follows, with the interpretation to said mode being we prevent
writes to the built-in FragStencilRefEXT variable when the execution
mode isn't set.

v3:
A more cautious reading of 1db44252d01bf7539452ccc2b5210c74b8dcd573 led
me to a missing change that would stop (what I later discovered were)
GPU hangs on the CTS test written to exercize this.

v4:
Turn FragStencilRefEXT decoration usage without StencilRefReplacingEXT
mode into a warning, instead of trying to make the variable read-only.
If we are to follow the originating extension on GL, the built-in
variable in question should never be readable anyway.
---
 src/compiler/shader_info.h         | 2 ++
 src/compiler/spirv/spirv_to_nir.c  | 4 ++++
 src/compiler/spirv/vtn_variables.c | 5 +++++
 src/intel/vulkan/anv_extensions.py | 2 ++
 src/intel/vulkan/anv_pipeline.c    | 1 +
 src/intel/vulkan/genX_pipeline.c   | 1 +
 6 files changed, 15 insertions(+)

diff --git a/src/compiler/shader_info.h b/src/compiler/shader_info.h
index 2ea9266bf8..3217a0b3e9 100644
--- a/src/compiler/shader_info.h
+++ b/src/compiler/shader_info.h
@@ -171,6 +171,8 @@ typedef struct shader_info {
 
          bool pixel_center_integer;
 
+         bool outputs_stencil;
+
          /** gl_FragDepth layout for ARB_conservative_depth. */
          enum gl_frag_depth_layout depth_layout;
       } fs;
diff --git a/src/compiler/spirv/spirv_to_nir.c b/src/compiler/spirv/spirv_to_nir.c
index 6e81f768f0..1648595dcb 100644
--- a/src/compiler/spirv/spirv_to_nir.c
+++ b/src/compiler/spirv/spirv_to_nir.c
@@ -3553,6 +3553,10 @@ vtn_handle_execution_mode(struct vtn_builder *b, struct vtn_value *entry_point,
    case SpvExecutionModeContractionOff:
       break; /* OpenCL */
 
+   case SpvExecutionModeStencilRefReplacingEXT:
+      b->shader->info.fs.outputs_stencil = true;
+      break;
+
    default:
       vtn_fail("Unhandled execution mode");
    }
diff --git a/src/compiler/spirv/vtn_variables.c b/src/compiler/spirv/vtn_variables.c
index 8abf9a9197..c7d03be563 100644
--- a/src/compiler/spirv/vtn_variables.c
+++ b/src/compiler/spirv/vtn_variables.c
@@ -1438,6 +1438,11 @@ apply_var_decoration(struct vtn_builder *b, nir_variable *nir_var,
       case SpvBuiltInFragCoord:
          nir_var->data.pixel_center_integer = b->pixel_center_integer;
          break;
+      case SpvBuiltInFragStencilRefEXT:
+         if (!b->shader->info.fs.outputs_stencil)
+             vtn_warn("The StencilRefReplacingEXT mode should be declared when"
+                      " the decoration FragStencilRefEXT is used on a variable");
+         break;
       default:
          break;
       }
diff --git a/src/intel/vulkan/anv_extensions.py b/src/intel/vulkan/anv_extensions.py
index d0b70a0405..a73fcb53fc 100644
--- a/src/intel/vulkan/anv_extensions.py
+++ b/src/intel/vulkan/anv_extensions.py
@@ -111,6 +111,8 @@ EXTENSIONS = [
     Extension('VK_EXT_external_memory_dma_buf',           1, True),
     Extension('VK_EXT_global_priority',                   1,
               'device->has_context_priority'),
+    Extension('VK_EXT_shader_stencil_export',             1,
+              'device->info.gen >= 9'),
 ]
 
 class VkVersion:
diff --git a/src/intel/vulkan/anv_pipeline.c b/src/intel/vulkan/anv_pipeline.c
index 4ca1e0be34..1d8338bde8 100644
--- a/src/intel/vulkan/anv_pipeline.c
+++ b/src/intel/vulkan/anv_pipeline.c
@@ -144,6 +144,7 @@ anv_shader_compile_to_nir(struct anv_pipeline *pipeline,
          .multiview = true,
          .variable_pointers = true,
          .storage_16bit = device->instance->physicalDevice.info.gen >= 8,
+         .stencil_export = device->instance->physicalDevice.info.gen >= 9,
          .subgroup_arithmetic = true,
          .subgroup_basic = true,
          .subgroup_ballot = true,
diff --git a/src/intel/vulkan/genX_pipeline.c b/src/intel/vulkan/genX_pipeline.c
index eb2d414735..5b52378aee 100644
--- a/src/intel/vulkan/genX_pipeline.c
+++ b/src/intel/vulkan/genX_pipeline.c
@@ -1600,6 +1600,7 @@ emit_3dstate_ps_extra(struct anv_pipeline *pipeline,
          ps.PixelShaderHasUAV = true;
 
 #if GEN_GEN >= 9
+      ps.PixelShaderComputesStencil = wm_prog_data->computed_stencil;
       ps.PixelShaderPullsBary    = wm_prog_data->pulls_bary;
       ps.InputCoverageMaskState  = wm_prog_data->uses_sample_mask ?
                                    ICMS_INNER_CONSERVATIVE : ICMS_NONE;
-- 
2.14.3