Maxwell3D: Implement State Dirty Flags.

src/video_core/engines/maxwell_3d.cpp

@@ -159,6 +159,88 @@ void Maxwell3D::InitDirtySettings() {
         sizeof(regs.shader_config[0]) * Regs::MaxShaderProgram / sizeof(u32);
     set_block(MAXWELL3D_REG_INDEX(shader_config[0]), shader_registers_count,
               DIRTY_REGS_POS(shaders));
+
+    // State
+
+    // Viewport
+    constexpr u32 viewport_dirty_reg = DIRTY_REGS_POS(viewport);
+    constexpr u32 viewport_start = MAXWELL3D_REG_INDEX(viewports);
+    constexpr u32 viewport_size = sizeof(regs.viewports) / sizeof(u32);
+    set_block(viewport_start, viewport_size, viewport_dirty_reg);
+    constexpr u32 view_volume_start = MAXWELL3D_REG_INDEX(view_volume_clip_control);
+    constexpr u32 view_volume_size = sizeof(regs.view_volume_clip_control) / sizeof(u32);
+    set_block(view_volume_start, view_volume_size, viewport_dirty_reg);
+
+    // Viewport transformation
+    constexpr u32 viewport_trans_start = MAXWELL3D_REG_INDEX(viewport_transform);
+    constexpr u32 viewport_trans_size = sizeof(regs.viewport_transform) / sizeof(u32);
+    set_block(viewport_trans_start, viewport_trans_size, DIRTY_REGS_POS(viewport_transform));
+
+    // Cullmode
+    constexpr u32 cull_mode_start = MAXWELL3D_REG_INDEX(cull);
+    constexpr u32 cull_mode_size = sizeof(regs.cull) / sizeof(u32);
+    set_block(cull_mode_start, cull_mode_size, DIRTY_REGS_POS(cull_mode));
+
+    // Screen y control
+    dirty_pointers[MAXWELL3D_REG_INDEX(screen_y_control)] = DIRTY_REGS_POS(screen_y_control);
+
+    // Primitive Restart
+    constexpr u32 primitive_restart_start = MAXWELL3D_REG_INDEX(primitive_restart);
+    constexpr u32 primitive_restart_size = sizeof(regs.primitive_restart) / sizeof(u32);
+    set_block(primitive_restart_start, primitive_restart_size, DIRTY_REGS_POS(primitive_restart));
+
+    // Depth Test
+    constexpr u32 depth_test_dirty_reg = DIRTY_REGS_POS(depth_test);
+    dirty_pointers[MAXWELL3D_REG_INDEX(depth_test_enable)] = depth_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(depth_write_enabled)] = depth_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(depth_test_func)] = depth_test_dirty_reg;
+
+    // Stencil Test
+    constexpr u32 stencil_test_dirty_reg = DIRTY_REGS_POS(stencil_test);
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_enable)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_func_func)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_func_ref)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_func_mask)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_op_fail)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_op_zfail)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_op_zpass)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_front_mask)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_two_side_enable)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_func_func)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_func_ref)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_func_mask)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_op_fail)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_op_zfail)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_op_zpass)] = stencil_test_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(stencil_back_mask)] = stencil_test_dirty_reg;
+
+    // Color Mask
+    constexpr u32 color_mask_dirty_reg = DIRTY_REGS_POS(color_mask);
+    dirty_pointers[MAXWELL3D_REG_INDEX(color_mask_common)] = color_mask_dirty_reg;
+    set_block(MAXWELL3D_REG_INDEX(color_mask), sizeof(regs.color_mask) / sizeof(u32),
+              color_mask_dirty_reg);
+    // Blend State
+    constexpr u32 blend_state_dirty_reg = DIRTY_REGS_POS(blend_state);
+    set_block(MAXWELL3D_REG_INDEX(blend_color), sizeof(regs.blend_color) / sizeof(u32),
+              blend_state_dirty_reg);
+    dirty_pointers[MAXWELL3D_REG_INDEX(independent_blend_enable)] = blend_state_dirty_reg;
+    set_block(MAXWELL3D_REG_INDEX(blend), sizeof(regs.blend) / sizeof(u32), blend_state_dirty_reg);
+    set_block(MAXWELL3D_REG_INDEX(independent_blend), sizeof(regs.independent_blend) / sizeof(u32),
+              blend_state_dirty_reg);
+
+    // Scissor State
+    constexpr u32 scissor_test_dirty_reg = DIRTY_REGS_POS(scissor_test);
+    set_block(MAXWELL3D_REG_INDEX(scissor_test), sizeof(regs.scissor_test) / sizeof(u32),
+              scissor_test_dirty_reg);
+
+    // Polygon Offset
+    constexpr u32 polygon_offset_dirty_reg = DIRTY_REGS_POS(polygon_offset);
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_fill_enable)] = polygon_offset_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_line_enable)] = polygon_offset_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_point_enable)] = polygon_offset_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_units)] = polygon_offset_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_factor)] = polygon_offset_dirty_reg;
+    dirty_pointers[MAXWELL3D_REG_INDEX(polygon_offset_clamp)] = polygon_offset_dirty_reg;
 }
 
 void Maxwell3D::CallMacroMethod(u32 method, std::vector<u32> parameters) {

src/video_core/engines/maxwell_3d.h

@@ -1148,22 +1148,20 @@ public:
                 bool shaders;
                 // State
                 bool viewport;
-                bool clip_enabled;
                 bool clip_coefficient;
                 bool cull_mode;
                 bool primitive_restart;
                 bool depth_test;
                 bool stencil_test;
                 bool blend_state;
-                bool logic_op;
-                bool fragment_color_clamp;
-                bool multi_sample;
                 bool scissor_test;
                 bool transform_feedback;
-                bool point;
                 bool color_mask;
                 bool polygon_offset;
-                bool alpha_test;
+
+                // Complementary
+                bool viewport_transform;
+                bool screen_y_control;
 
                 bool memory_general;
             };

src/video_core/renderer_opengl/gl_rasterizer.cpp

@@ -936,56 +936,53 @@ void RasterizerOpenGL::SyncClipCoef() {
 }
 
 void RasterizerOpenGL::SyncCullMode() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+
+    const auto& regs = maxwell3d.regs;
 
     state.cull.enabled = regs.cull.enabled != 0;
+    state.cull.front_face = MaxwellToGL::FrontFace(regs.cull.front_face);
+    state.cull.mode = MaxwellToGL::CullFace(regs.cull.cull_face);
 
-    if (state.cull.enabled) {
+    const bool flip_triangles{regs.screen_y_control.triangle_rast_flip == 0 ||
-        state.cull.front_face = MaxwellToGL::FrontFace(regs.cull.front_face);
+                              regs.viewport_transform[0].scale_y < 0.0f};
-        state.cull.mode = MaxwellToGL::CullFace(regs.cull.cull_face);
 
-        const bool flip_triangles{regs.screen_y_control.triangle_rast_flip == 0 ||
+    // If the GPU is configured to flip the rasterized triangles, then we need to flip the
-                                  regs.viewport_transform[0].scale_y < 0.0f};
+    // notion of front and back. Note: We flip the triangles when the value of the register is 0
-
+    // because OpenGL already does it for us.
-        // If the GPU is configured to flip the rasterized triangles, then we need to flip the
+    if (flip_triangles) {
-        // notion of front and back. Note: We flip the triangles when the value of the register is 0
+        if (state.cull.front_face == GL_CCW)
-        // because OpenGL already does it for us.
+            state.cull.front_face = GL_CW;
-        if (flip_triangles) {
+        else if (state.cull.front_face == GL_CW)
-            if (state.cull.front_face == GL_CCW)
+            state.cull.front_face = GL_CCW;
-                state.cull.front_face = GL_CW;
-            else if (state.cull.front_face == GL_CW)
-                state.cull.front_face = GL_CCW;
-        }
     }
 }
 
 void RasterizerOpenGL::SyncPrimitiveRestart() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+    const auto& regs = maxwell3d.regs;
 
     state.primitive_restart.enabled = regs.primitive_restart.enabled;
     state.primitive_restart.index = regs.primitive_restart.index;
 }
 
 void RasterizerOpenGL::SyncDepthTestState() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+    const auto& regs = maxwell3d.regs;
 
     state.depth.test_enabled = regs.depth_test_enable != 0;
     state.depth.write_mask = regs.depth_write_enabled ? GL_TRUE : GL_FALSE;
-
-    if (!state.depth.test_enabled)
-        return;
-
     state.depth.test_func = MaxwellToGL::ComparisonOp(regs.depth_test_func);
 }
 
 void RasterizerOpenGL::SyncStencilTestState() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
-    state.stencil.test_enabled = regs.stencil_enable != 0;
+    if (!maxwell3d.dirty.stencil_test) {
-
-    if (!regs.stencil_enable) {
         return;
     }
+    const auto& regs = maxwell3d.regs;
 
+    state.stencil.test_enabled = regs.stencil_enable != 0;
     state.stencil.front.test_func = MaxwellToGL::ComparisonOp(regs.stencil_front_func_func);
     state.stencil.front.test_ref = regs.stencil_front_func_ref;
     state.stencil.front.test_mask = regs.stencil_front_func_mask;
@@ -1010,10 +1007,17 @@ void RasterizerOpenGL::SyncStencilTestState() {
         state.stencil.back.action_depth_fail = GL_KEEP;
         state.stencil.back.action_depth_pass = GL_KEEP;
     }
+    state.MarkDirtyStencilState(true);
+    maxwell3d.dirty.stencil_test = false;
 }
 
 void RasterizerOpenGL::SyncColorMask() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+    if (!maxwell3d.dirty.color_mask) {
+        return;
+    }
+    const auto& regs = maxwell3d.regs;
+
     const std::size_t count =
         regs.independent_blend_enable ? Tegra::Engines::Maxwell3D::Regs::NumRenderTargets : 1;
     for (std::size_t i = 0; i < count; i++) {
@@ -1024,6 +1028,9 @@ void RasterizerOpenGL::SyncColorMask() {
         dest.blue_enabled = (source.B == 0) ? GL_FALSE : GL_TRUE;
         dest.alpha_enabled = (source.A == 0) ? GL_FALSE : GL_TRUE;
     }
+
+    state.MarkDirtyColorMask(true);
+    maxwell3d.dirty.color_mask = false;
 }
 
 void RasterizerOpenGL::SyncMultiSampleState() {
@@ -1038,7 +1045,11 @@ void RasterizerOpenGL::SyncFragmentColorClampState() {
 }
 
 void RasterizerOpenGL::SyncBlendState() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+    if (!maxwell3d.dirty.blend_state) {
+        return;
+    }
+    const auto& regs = maxwell3d.regs;
 
     state.blend_color.red = regs.blend_color.r;
     state.blend_color.green = regs.blend_color.g;
@@ -1061,6 +1072,8 @@ void RasterizerOpenGL::SyncBlendState() {
         for (std::size_t i = 1; i < Tegra::Engines::Maxwell3D::Regs::NumRenderTargets; i++) {
             state.blend[i].enabled = false;
         }
+        maxwell3d.dirty.blend_state = false;
+        state.MarkDirtyBlendState(true);
         return;
     }
 
@@ -1077,6 +1090,9 @@ void RasterizerOpenGL::SyncBlendState() {
         blend.src_a_func = MaxwellToGL::BlendFunc(src.factor_source_a);
         blend.dst_a_func = MaxwellToGL::BlendFunc(src.factor_dest_a);
     }
+
+    state.MarkDirtyBlendState(true);
+    maxwell3d.dirty.blend_state = false;
 }
 
 void RasterizerOpenGL::SyncLogicOpState() {
@@ -1128,13 +1144,21 @@ void RasterizerOpenGL::SyncPointState() {
 }
 
 void RasterizerOpenGL::SyncPolygonOffset() {
-    const auto& regs = system.GPU().Maxwell3D().regs;
+    auto& maxwell3d = system.GPU().Maxwell3D();
+    if (!maxwell3d.dirty.polygon_offset) {
+        return;
+    }
+    const auto& regs = maxwell3d.regs;
+
     state.polygon_offset.fill_enable = regs.polygon_offset_fill_enable != 0;
     state.polygon_offset.line_enable = regs.polygon_offset_line_enable != 0;
     state.polygon_offset.point_enable = regs.polygon_offset_point_enable != 0;
     state.polygon_offset.units = regs.polygon_offset_units;
     state.polygon_offset.factor = regs.polygon_offset_factor;
     state.polygon_offset.clamp = regs.polygon_offset_clamp;
+
+    state.MarkDirtyPolygonOffset(true);
+    maxwell3d.dirty.polygon_offset = false;
 }
 
 void RasterizerOpenGL::SyncAlphaTest() {

src/video_core/renderer_opengl/gl_state.cpp

@@ -526,7 +526,7 @@ void OpenGLState::ApplySamplers() const {
     }
 }
 
-void OpenGLState::Apply() const {
+void OpenGLState::Apply() {
     MICROPROFILE_SCOPE(OpenGL_State);
     ApplyFramebufferState();
     ApplyVertexArrayState();
@@ -536,19 +536,31 @@ void OpenGLState::Apply() const {
     ApplyPointSize();
     ApplyFragmentColorClamp();
     ApplyMultisample();
+    if (dirty.color_mask) {
+        ApplyColorMask();
+        dirty.color_mask = false;
+    }
     ApplyDepthClamp();
-    ApplyColorMask();
     ApplyViewport();
-    ApplyStencilTest();
+    if (dirty.stencil_state) {
+        ApplyStencilTest();
+        dirty.stencil_state = false;
+    }
     ApplySRgb();
     ApplyCulling();
     ApplyDepth();
     ApplyPrimitiveRestart();
-    ApplyBlending();
+    if (dirty.blend_state) {
+        ApplyBlending();
+        dirty.blend_state = false;
+    }
     ApplyLogicOp();
     ApplyTextures();
     ApplySamplers();
-    ApplyPolygonOffset();
+    if (dirty.polygon_offset) {
+        ApplyPolygonOffset();
+        dirty.polygon_offset = false;
+    }
     ApplyAlphaTest();
 }
 

src/video_core/renderer_opengl/gl_state.h

@@ -196,7 +196,7 @@ public:
     }
 
     /// Apply this state as the current OpenGL state
-    void Apply() const;
+    void Apply();
 
     void ApplyFramebufferState() const;
     void ApplyVertexArrayState() const;
@@ -237,11 +237,46 @@ public:
     /// Viewport does not affects glClearBuffer so emulate viewport using scissor test
     void EmulateViewportWithScissor();
 
+    void MarkDirtyBlendState(const bool is_dirty) {
+        dirty.blend_state = is_dirty;
+    }
+
+    void MarkDirtyStencilState(const bool is_dirty) {
+        dirty.stencil_state = is_dirty;
+    }
+
+    void MarkDirtyViewportState(const bool is_dirty) {
+        dirty.viewport_state = is_dirty;
+    }
+
+    void MarkDirtyPolygonOffset(const bool is_dirty) {
+        dirty.polygon_offset = is_dirty;
+    }
+
+    void MarkDirtyColorMask(const bool is_dirty) {
+        dirty.color_mask = is_dirty;
+    }
+
+    void AllDirty() {
+        dirty.blend_state = true;
+        dirty.stencil_state = true;
+        dirty.viewport_state = true;
+        dirty.polygon_offset = true;
+        dirty.color_mask = true;
+    }
+
 private:
     static OpenGLState cur_state;
 
     // Workaround for sRGB problems caused by QT not supporting srgb output
     static bool s_rgb_used;
+    struct {
+        bool blend_state;
+        bool stencil_state;
+        bool viewport_state;
+        bool polygon_offset;
+        bool color_mask;
+    } dirty{};
 };
 
 } // namespace OpenGL

src/video_core/renderer_opengl/gl_texture_cache.cpp

@@ -485,11 +485,15 @@ void TextureCacheOpenGL::ImageBlit(View& src_view, View& dst_view,
     const auto& dst_params{dst_view->GetSurfaceParams()};
 
     OpenGLState prev_state{OpenGLState::GetCurState()};
-    SCOPE_EXIT({ prev_state.Apply(); });
+    SCOPE_EXIT({
+        prev_state.AllDirty();
+        prev_state.Apply();
+    });
 
     OpenGLState state;
     state.draw.read_framebuffer = src_framebuffer.handle;
     state.draw.draw_framebuffer = dst_framebuffer.handle;
+    state.AllDirty();
     state.Apply();
 
     u32 buffers{};