[video_core] fix std::bitset<> dirty tracker OOB, fix slightly wrong estimate

Signed-off-by: lizzie <lizzie@eden-emu.dev>

src/video_core/buffer_cache/buffer_cache.h

@@ -1252,8 +1252,7 @@ void BufferCache<P>::UpdateIndexBuffer() {
     const GPUVAddr gpu_addr_end = index_buffer_ref.EndAddress();
     const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(gpu_addr_begin);
     const u32 address_size = static_cast<u32>(gpu_addr_end - gpu_addr_begin);
-    const u32 draw_size =
-        (index_buffer_ref.count + index_buffer_ref.first) * index_buffer_ref.FormatSizeInBytes();
+    const u32 draw_size = (index_buffer_ref.count + index_buffer_ref.first) * u32(index_buffer_ref.FormatSizeInBytes());
     const u32 size = (std::min)(address_size, draw_size);
     if (size == 0 || !device_addr) {
         channel_state->index_buffer = NULL_BINDING;

src/video_core/dma_pusher.cpp

@@ -181,12 +181,12 @@ void DmaPusher::CallMethod(u32 argument) const {
         });
     } else {
         auto subchannel = subchannels[dma_state.subchannel];
-        if (!subchannel->execution_mask[dma_state.method]) {
-            subchannel->method_sink.emplace_back(dma_state.method, argument);
-        } else {
+        if (subchannel->execution_mask[dma_state.method]) {
             subchannel->ConsumeSink();
             subchannel->current_dma_segment = dma_state.dma_get + dma_state.dma_word_offset;
             subchannel->CallMethod(dma_state.method, argument, dma_state.is_last_call);
+        } else {
+            subchannel->method_sink.emplace_back(dma_state.method, argument);
         }
     }
 }

src/video_core/engines/maxwell_3d.cpp

@@ -270,31 +270,20 @@ u32 Maxwell3D::GetMaxCurrentVertices() {
 size_t Maxwell3D::EstimateIndexBufferSize() {
     GPUVAddr start_address = regs.index_buffer.StartAddress();
     GPUVAddr end_address = regs.index_buffer.EndAddress();
-    static constexpr std::array<size_t, 3> max_sizes = {(std::numeric_limits<u8>::max)(),
-                                                        (std::numeric_limits<u16>::max)(),
-                                                        (std::numeric_limits<u32>::max)()};
-    const size_t byte_size = regs.index_buffer.FormatSizeInBytes();
-    const size_t log2_byte_size = Common::Log2Ceil64(byte_size);
-    const size_t cap{GetMaxCurrentVertices() * 4 * byte_size};
-    const size_t lower_cap =
-        std::min<size_t>(static_cast<size_t>(end_address - start_address), cap);
-    return std::min<size_t>(
-        memory_manager.GetMemoryLayoutSize(start_address, byte_size * max_sizes[log2_byte_size]) /
-            byte_size,
-        lower_cap);
+    auto const byte_size = regs.index_buffer.FormatSizeInBytes();
+    auto const max_size = 1ull << (byte_size * CHAR_BIT);
+    auto const upper_cap = GetMaxCurrentVertices() * 4 * byte_size;
+    auto const lower_cap = std::min<size_t>(size_t(end_address - start_address), upper_cap);
+    return std::min<size_t>(memory_manager.GetMemoryLayoutSize(start_address, byte_size * max_size) / byte_size, lower_cap);
 }
 
 u32 Maxwell3D::ProcessShadowRam(u32 method, u32 argument) {
     // Keep track of the register value in shadow_state when requested.
-    const auto control = shadow_state.shadow_ram_control;
-    if (control == Regs::ShadowRamControl::Track ||
-        control == Regs::ShadowRamControl::TrackWithFilter) {
-        shadow_state.reg_array[method] = argument;
-        return argument;
-    }
-    if (control == Regs::ShadowRamControl::Replay) {
+    auto const c = shadow_state.shadow_ram_control;
+    if (c == Regs::ShadowRamControl::Track || c == Regs::ShadowRamControl::TrackWithFilter)
+        return shadow_state.reg_array[method] = argument;
+    else if (c == Regs::ShadowRamControl::Replay)
         return shadow_state.reg_array[method];
-    }
     return argument;
 }
 
@@ -317,10 +306,8 @@ void Maxwell3D::ConsumeSinkImpl() {
 
 void Maxwell3D::ProcessDirtyRegisters(u32 method, u32 argument) {
     regs.reg_array[method] = argument;
-
-    for (const auto& table : dirty.tables) {
+    for (auto const& table : dirty.tables)
         dirty.flags[table[method]] = true;
-    }
 }
 
 void Maxwell3D::ProcessMethodCall(u32 method, u32 argument, u32 nonshadow_argument, bool is_last_call) {

src/video_core/engines/maxwell_3d.h

@@ -2215,7 +2215,7 @@ public:
             u32 first;
             u32 count;
 
-            unsigned FormatSizeInBytes() const {
+            size_t FormatSizeInBytes() const {
                 switch (format) {
                 case IndexFormat::UnsignedByte:
                     return 1;
@@ -2224,7 +2224,7 @@ public:
                 case IndexFormat::UnsignedInt:
                     return 4;
                 }
-                ASSERT(false);
+                UNREACHABLE();
                 return 1;
             }
 
@@ -3148,9 +3148,9 @@ public:
     }
 
     struct DirtyState {
-        using Flags = std::bitset<(std::numeric_limits<u8>::max)()>;
+        using Flags = std::bitset<(std::numeric_limits<u8>::max)() + 1>;
         using Table = std::array<u8, Regs::NUM_REGS>;
-        using Tables = std::array<Table, 2>;
+        using Tables = std::array<std::array<u8, Regs::NUM_REGS>, 2>;
 
         Flags flags;
         Tables tables{};

src/video_core/renderer_vulkan/vk_state_tracker.cpp

@@ -24,11 +24,8 @@ using namespace Dirty;
 using namespace VideoCommon::Dirty;
 using Tegra::Engines::Maxwell3D;
 using Regs = Maxwell3D::Regs;
-using Tables = Maxwell3D::DirtyState::Tables;
-using Table = Maxwell3D::DirtyState::Table;
-using Flags = Maxwell3D::DirtyState::Flags;
 
-Flags MakeInvalidationFlags() {
+Maxwell3D::DirtyState::Flags MakeInvalidationFlags() {
     static constexpr int INVALIDATION_FLAGS[]{
         Viewports,
         Scissors,
@@ -68,7 +65,7 @@ Flags MakeInvalidationFlags() {
         LineStippleEnable,
         LineStippleParams,
     };
-    Flags flags{};
+    Maxwell3D::DirtyState::Flags flags{};
     for (const int flag : INVALIDATION_FLAGS) {
         flags[flag] = true;
     }
@@ -84,7 +81,7 @@ Flags MakeInvalidationFlags() {
     return flags;
 }
 
-void SetupDirtyViewports(Tables& tables) {
+void SetupDirtyViewports(Maxwell3D::DirtyState::Tables& tables) {
     FillBlock(tables[0], OFF(viewport_transform), NUM(viewport_transform), Viewports);
     FillBlock(tables[0], OFF(viewports), NUM(viewports), Viewports);
     FillBlock(tables[1], OFF(surface_clip), NUM(surface_clip), Viewports);
@@ -92,26 +89,26 @@ void SetupDirtyViewports(Tables& tables) {
     tables[1][OFF(window_origin)] = Viewports;
 }
 
-void SetupDirtyScissors(Tables& tables) {
+void SetupDirtyScissors(Maxwell3D::DirtyState::Tables& tables) {
     FillBlock(tables[0], OFF(scissor_test), NUM(scissor_test), Scissors);
 }
 
-void SetupDirtyDepthBias(Tables& tables) {
+void SetupDirtyDepthBias(Maxwell3D::DirtyState::Tables& tables) {
     auto& table = tables[0];
     table[OFF(depth_bias)] = DepthBias;
     table[OFF(depth_bias_clamp)] = DepthBias;
     table[OFF(slope_scale_depth_bias)] = DepthBias;
 }
 
-void SetupDirtyBlendConstants(Tables& tables) {
+void SetupDirtyBlendConstants(Maxwell3D::DirtyState::Tables& tables) {
     FillBlock(tables[0], OFF(blend_color), NUM(blend_color), BlendConstants);
 }
 
-void SetupDirtyDepthBounds(Tables& tables) {
+void SetupDirtyDepthBounds(Maxwell3D::DirtyState::Tables& tables) {
     FillBlock(tables[0], OFF(depth_bounds), NUM(depth_bounds), DepthBounds);
 }
 
-void SetupDirtyStencilProperties(Tables& tables) {
+void SetupDirtyStencilProperties(Maxwell3D::DirtyState::Tables& tables) {
     const auto setup = [&](size_t position, u8 flag) {
         tables[0][position] = flag;
         tables[1][position] = StencilProperties;
@@ -125,18 +122,18 @@ void SetupDirtyStencilProperties(Tables& tables) {
     setup(OFF(stencil_back_func_mask), StencilCompare);
 }
 
-void SetupDirtyLineWidth(Tables& tables) {
+void SetupDirtyLineWidth(Maxwell3D::DirtyState::Tables& tables) {
     tables[0][OFF(line_width_smooth)] = LineWidth;
     tables[0][OFF(line_width_aliased)] = LineWidth;
 }
 
-void SetupDirtyCullMode(Tables& tables) {
+void SetupDirtyCullMode(Maxwell3D::DirtyState::Tables& tables) {
     auto& table = tables[0];
     table[OFF(gl_cull_face)] = CullMode;
     table[OFF(gl_cull_test_enabled)] = CullMode;
 }
 
-void SetupDirtyStateEnable(Tables& tables) {
+void SetupDirtyStateEnable(Maxwell3D::DirtyState::Tables& tables) {
     const auto setup = [&](size_t position, u8 flag) {
         tables[0][position] = flag;
         tables[1][position] = StateEnable;
@@ -157,17 +154,17 @@ void SetupDirtyStateEnable(Tables& tables) {
     setup(OFF(anti_alias_alpha_control.alpha_to_one), AlphaToOneEnable);
 }
 
-void SetupDirtyDepthCompareOp(Tables& tables) {
+void SetupDirtyDepthCompareOp(Maxwell3D::DirtyState::Tables& tables) {
     tables[0][OFF(depth_test_func)] = DepthCompareOp;
 }
 
-void SetupDirtyFrontFace(Tables& tables) {
+void SetupDirtyFrontFace(Maxwell3D::DirtyState::Tables& tables) {
     auto& table = tables[0];
     table[OFF(gl_front_face)] = FrontFace;
     table[OFF(window_origin)] = FrontFace;
 }
 
-void SetupDirtyStencilOp(Tables& tables) {
+void SetupDirtyStencilOp(Maxwell3D::DirtyState::Tables& tables) {
     auto& table = tables[0];
     table[OFF(stencil_front_op.fail)] = StencilOp;
     table[OFF(stencil_front_op.zfail)] = StencilOp;
@@ -182,7 +179,7 @@ void SetupDirtyStencilOp(Tables& tables) {
     tables[1][OFF(stencil_two_side_enable)] = StencilOp;
 }
 
-void SetupDirtyBlending(Tables& tables) {
+void SetupDirtyBlending(Maxwell3D::DirtyState::Tables& tables) {
     tables[0][OFF(color_mask_common)] = Blending;
     tables[1][OFF(color_mask_common)] = ColorMask;
     tables[0][OFF(blend_per_target_enabled)] = Blending;
@@ -196,11 +193,11 @@ void SetupDirtyBlending(Tables& tables) {
     FillBlock(tables[1], OFF(blend_per_target), NUM(blend_per_target), BlendEquations);
 }
 
-void SetupDirtySpecialOps(Tables& tables) {
+void SetupDirtySpecialOps(Maxwell3D::DirtyState::Tables& tables) {
     tables[0][OFF(logic_op.op)] = LogicOp;
 }
 
-void SetupDirtyViewportSwizzles(Tables& tables) {
+void SetupDirtyViewportSwizzles(Maxwell3D::DirtyState::Tables& tables) {
     static constexpr size_t swizzle_offset = 6;
     for (size_t index = 0; index < Regs::NumViewports; ++index) {
         tables[1][OFF(viewport_transform) + index * NUM(viewport_transform[0]) + swizzle_offset] =
@@ -208,7 +205,7 @@ void SetupDirtyViewportSwizzles(Tables& tables) {
     }
 }
 
-void SetupDirtyVertexAttributes(Tables& tables) {
+void SetupDirtyVertexAttributes(Maxwell3D::DirtyState::Tables& tables) {
     for (size_t i = 0; i < Regs::NumVertexAttributes; ++i) {
         const size_t offset = OFF(vertex_attrib_format) + i * NUM(vertex_attrib_format[0]);
         FillBlock(tables[0], offset, NUM(vertex_attrib_format[0]), VertexAttribute0 + i);
@@ -216,7 +213,7 @@ void SetupDirtyVertexAttributes(Tables& tables) {
     FillBlock(tables[1], OFF(vertex_attrib_format), Regs::NumVertexAttributes, VertexInput);
 }
 
-void SetupDirtyVertexBindings(Tables& tables) {
+void SetupDirtyVertexBindings(Maxwell3D::DirtyState::Tables& tables) {
     // Do NOT include stride here, it's implicit in VertexBuffer
     static constexpr size_t divisor_offset = 3;
     for (size_t i = 0; i < Regs::NumVertexArrays; ++i) {
@@ -228,7 +225,7 @@ void SetupDirtyVertexBindings(Tables& tables) {
     }
 }
 
-void SetupRasterModes(Tables &tables) {
+void SetupRasterModes(Maxwell3D::DirtyState::Tables &tables) {
     auto& table = tables[0];
 
     table[OFF(line_stipple_params)] = LineStippleParams;