Merge pull request #10837 from liamwhite/mali-support

android: Mali support

10 files changed, 86 insertions, 18 deletions

diff --git a/src/video_core/renderer_vulkan/blit_image.cpp b/src/video_core/renderer_vulkan/blit_image.cpp
index cf2964a3f..28d4b15a0 100644
--- a/src/video_core/renderer_vulkan/blit_image.cpp
+++ b/src/video_core/renderer_vulkan/blit_image.cpp
@@ -495,6 +495,9 @@ void BlitImageHelper::BlitDepthStencil(const Framebuffer* dst_framebuffer,
                                        const Region2D& dst_region, const Region2D& src_region,
                                        Tegra::Engines::Fermi2D::Filter filter,
                                        Tegra::Engines::Fermi2D::Operation operation) {
+    if (!device.IsExtShaderStencilExportSupported()) {
+        return;
+    }
     ASSERT(filter == Tegra::Engines::Fermi2D::Filter::Point);
     ASSERT(operation == Tegra::Engines::Fermi2D::Operation::SrcCopy);
     const BlitImagePipelineKey key{
diff --git a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
index 9a0b10568..a8540339d 100644
--- a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
+++ b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
@@ -259,6 +259,26 @@ FormatInfo SurfaceFormat(const Device& device, FormatType format_type, bool with
             break;
         }
     }
+    // Transcode on hardware that doesn't support BCn natively
+    if (!device.IsOptimalBcnSupported() && VideoCore::Surface::IsPixelFormatBCn(pixel_format)) {
+        const bool is_srgb = with_srgb && VideoCore::Surface::IsPixelFormatSRGB(pixel_format);
+        if (pixel_format == PixelFormat::BC4_SNORM) {
+            tuple.format = VK_FORMAT_R8_SNORM;
+        } else if (pixel_format == PixelFormat::BC4_UNORM) {
+            tuple.format = VK_FORMAT_R8_UNORM;
+        } else if (pixel_format == PixelFormat::BC5_SNORM) {
+            tuple.format = VK_FORMAT_R8G8_SNORM;
+        } else if (pixel_format == PixelFormat::BC5_UNORM) {
+            tuple.format = VK_FORMAT_R8G8_UNORM;
+        } else if (pixel_format == PixelFormat::BC6H_SFLOAT ||
+                   pixel_format == PixelFormat::BC6H_UFLOAT) {
+            tuple.format = VK_FORMAT_R16G16B16A16_SFLOAT;
+        } else if (is_srgb) {
+            tuple.format = VK_FORMAT_A8B8G8R8_SRGB_PACK32;
+        } else {
+            tuple.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
+        }
+    }
     const bool attachable = (tuple.usage & Attachable) != 0;
     const bool storage = (tuple.usage & Storage) != 0;
 
diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.cpp b/src/video_core/renderer_vulkan/renderer_vulkan.cpp
index ddf28ca28..454bb66a4 100644
--- a/src/video_core/renderer_vulkan/renderer_vulkan.cpp
+++ b/src/video_core/renderer_vulkan/renderer_vulkan.cpp
@@ -12,6 +12,7 @@
 #include <fmt/format.h>
 
 #include "common/logging/log.h"
+#include "common/polyfill_ranges.h"
 #include "common/scope_exit.h"
 #include "common/settings.h"
 #include "common/telemetry.h"
@@ -65,6 +66,21 @@ std::string BuildCommaSeparatedExtensions(
     return fmt::format("{}", fmt::join(available_extensions, ","));
 }
 
+DebugCallback MakeDebugCallback(const vk::Instance& instance, const vk::InstanceDispatch& dld) {
+    if (!Settings::values.renderer_debug) {
+        return DebugCallback{};
+    }
+    const std::optional properties = vk::EnumerateInstanceExtensionProperties(dld);
+    const auto it = std::ranges::find_if(*properties, [](const auto& prop) {
+        return std::strcmp(VK_EXT_DEBUG_UTILS_EXTENSION_NAME, prop.extensionName) == 0;
+    });
+    if (it != properties->end()) {
+        return CreateDebugUtilsCallback(instance);
+    } else {
+        return CreateDebugReportCallback(instance);
+    }
+}
+
 } // Anonymous namespace
 
 Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld,
@@ -87,7 +103,7 @@ RendererVulkan::RendererVulkan(Core::TelemetrySession& telemetry_session_,
       cpu_memory(cpu_memory_), gpu(gpu_), library(OpenLibrary(context.get())),
       instance(CreateInstance(*library, dld, VK_API_VERSION_1_1, render_window.GetWindowInfo().type,
                               Settings::values.renderer_debug.GetValue())),
-      debug_callback(Settings::values.renderer_debug ? CreateDebugCallback(instance) : nullptr),
+      debug_callback(MakeDebugCallback(instance, dld)),
       surface(CreateSurface(instance, render_window.GetWindowInfo())),
       device(CreateDevice(instance, dld, *surface)), memory_allocator(device), state_tracker(),
       scheduler(device, state_tracker),
diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.h b/src/video_core/renderer_vulkan/renderer_vulkan.h
index b2e8cbd1b..ca22c0baa 100644
--- a/src/video_core/renderer_vulkan/renderer_vulkan.h
+++ b/src/video_core/renderer_vulkan/renderer_vulkan.h
@@ -5,6 +5,7 @@
 
 #include <memory>
 #include <string>
+#include <variant>
 
 #include "common/dynamic_library.h"
 #include "video_core/renderer_base.h"
@@ -33,6 +34,8 @@ class GPU;
 
 namespace Vulkan {
 
+using DebugCallback = std::variant<vk::DebugUtilsMessenger, vk::DebugReportCallback>;
+
 Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld,
                     VkSurfaceKHR surface);
 
@@ -71,7 +74,7 @@ private:
     vk::InstanceDispatch dld;
 
     vk::Instance instance;
-    vk::DebugUtilsMessenger debug_callback;
+    DebugCallback debug_callback;
     vk::SurfaceKHR surface;
 
     ScreenInfo screen_info;
diff --git a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
index 660f7c9ff..b72f95235 100644
--- a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
@@ -590,7 +590,8 @@ void BufferCacheRuntime::ReserveNullBuffer() {
         .pNext = nullptr,
         .flags = 0,
         .size = 4,
-        .usage = VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT,
+        .usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT |
+                 VK_BUFFER_USAGE_TRANSFER_DST_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
diff --git a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
index c1595642e..ad35cacac 100644
--- a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
+++ b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
@@ -652,13 +652,14 @@ void GraphicsPipeline::MakePipeline(VkRenderPass render_pass) {
         .pNext = nullptr,
         .negativeOneToOne = key.state.ndc_minus_one_to_one.Value() != 0 ? VK_TRUE : VK_FALSE,
     };
+    const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
     VkPipelineViewportStateCreateInfo viewport_ci{
         .sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
-        .viewportCount = Maxwell::NumViewports,
+        .viewportCount = num_viewports,
         .pViewports = nullptr,
-        .scissorCount = Maxwell::NumViewports,
+        .scissorCount = num_viewports,
         .pScissors = nullptr,
     };
     if (device.IsNvViewportSwizzleSupported()) {
diff --git a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
index 9f316113c..d600c4e61 100644
--- a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
@@ -309,7 +309,7 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device
         .support_int16 = device.IsShaderInt16Supported(),
         .support_int64 = device.IsShaderInt64Supported(),
         .support_vertex_instance_id = false,
-        .support_float_controls = true,
+        .support_float_controls = device.IsKhrShaderFloatControlsSupported(),
         .support_separate_denorm_behavior =
             float_control.denormBehaviorIndependence == VK_SHADER_FLOAT_CONTROLS_INDEPENDENCE_ALL,
         .support_separate_rounding_mode =
@@ -325,12 +325,13 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device
         .support_fp64_signed_zero_nan_preserve =
             float_control.shaderSignedZeroInfNanPreserveFloat64 != VK_FALSE,
         .support_explicit_workgroup_layout = device.IsKhrWorkgroupMemoryExplicitLayoutSupported(),
-        .support_vote = true,
+        .support_vote = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_VOTE_BIT),
         .support_viewport_index_layer_non_geometry =
             device.IsExtShaderViewportIndexLayerSupported(),
         .support_viewport_mask = device.IsNvViewportArray2Supported(),
         .support_typeless_image_loads = device.IsFormatlessImageLoadSupported(),
-        .support_demote_to_helper_invocation = true,
+        .support_demote_to_helper_invocation =
+            device.IsExtShaderDemoteToHelperInvocationSupported(),
         .support_int64_atomics = device.IsExtShaderAtomicInt64Supported(),
         .support_derivative_control = true,
         .support_geometry_shader_passthrough = device.IsNvGeometryShaderPassthroughSupported(),
diff --git a/src/video_core/renderer_vulkan/vk_rasterizer.cpp b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
index 84e3a30cc..f7c0d939a 100644
--- a/src/video_core/renderer_vulkan/vk_rasterizer.cpp
+++ b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
@@ -315,7 +315,14 @@ void RasterizerVulkan::Clear(u32 layer_count) {
     FlushWork();
     gpu_memory->FlushCaching();
 
+#if ANDROID
+    if (Settings::IsGPULevelHigh()) {
+        // This is problematic on Android, disable on GPU Normal.
+        query_cache.UpdateCounters();
+    }
+#else
     query_cache.UpdateCounters();
+#endif
 
     auto& regs = maxwell3d->regs;
     const bool use_color = regs.clear_surface.R || regs.clear_surface.G || regs.clear_surface.B ||
@@ -925,7 +932,7 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg
     }
     const bool is_rescaling{texture_cache.IsRescaling()};
     const float scale = is_rescaling ? Settings::values.resolution_info.up_factor : 1.0f;
-    const std::array viewports{
+    const std::array viewport_list{
         GetViewportState(device, regs, 0, scale),  GetViewportState(device, regs, 1, scale),
         GetViewportState(device, regs, 2, scale),  GetViewportState(device, regs, 3, scale),
         GetViewportState(device, regs, 4, scale),  GetViewportState(device, regs, 5, scale),
@@ -935,7 +942,11 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg
         GetViewportState(device, regs, 12, scale), GetViewportState(device, regs, 13, scale),
         GetViewportState(device, regs, 14, scale), GetViewportState(device, regs, 15, scale),
     };
-    scheduler.Record([viewports](vk::CommandBuffer cmdbuf) { cmdbuf.SetViewport(0, viewports); });
+    scheduler.Record([this, viewport_list](vk::CommandBuffer cmdbuf) {
+        const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
+        const vk::Span<VkViewport> viewports(viewport_list.data(), num_viewports);
+        cmdbuf.SetViewport(0, viewports);
+    });
 }
 
 void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs) {
@@ -948,7 +959,7 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs
         up_scale = Settings::values.resolution_info.up_scale;
         down_shift = Settings::values.resolution_info.down_shift;
     }
-    const std::array scissors{
+    const std::array scissor_list{
         GetScissorState(regs, 0, up_scale, down_shift),
         GetScissorState(regs, 1, up_scale, down_shift),
         GetScissorState(regs, 2, up_scale, down_shift),
@@ -966,7 +977,11 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs
         GetScissorState(regs, 14, up_scale, down_shift),
         GetScissorState(regs, 15, up_scale, down_shift),
     };
-    scheduler.Record([scissors](vk::CommandBuffer cmdbuf) { cmdbuf.SetScissor(0, scissors); });
+    scheduler.Record([this, scissor_list](vk::CommandBuffer cmdbuf) {
+        const u32 num_scissors = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
+        const vk::Span<VkRect2D> scissors(scissor_list.data(), num_scissors);
+        cmdbuf.SetScissor(0, scissors);
+    });
 }
 
 void RasterizerVulkan::UpdateDepthBias(Tegra::Engines::Maxwell3D::Regs& regs) {
diff --git a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
index 62b251a9b..ce92f66ab 100644
--- a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
+++ b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
@@ -38,18 +38,20 @@ size_t Region(size_t iterator) noexcept {
 StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_,
                                      Scheduler& scheduler_)
     : device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_} {
-    const VkBufferCreateInfo stream_ci = {
+    VkBufferCreateInfo stream_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = STREAM_BUFFER_SIZE,
         .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT |
-                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
-                 VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT,
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
     };
+    if (device.IsExtTransformFeedbackSupported()) {
+        stream_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
+    }
     stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
     if (device.HasDebuggingToolAttached()) {
         stream_buffer.SetObjectNameEXT("Stream Buffer");
@@ -164,19 +166,21 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
 StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage,
                                                         bool deferred) {
     const u32 log2 = Common::Log2Ceil64(size);
-    const VkBufferCreateInfo buffer_ci = {
+    VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = 1ULL << log2,
         .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT |
                  VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
-                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT |
-                 VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT,
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
     };
+    if (device.IsExtTransformFeedbackSupported()) {
+        buffer_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
+    }
     vk::Buffer buffer = memory_allocator.CreateBuffer(buffer_ci, usage);
     if (device.HasDebuggingToolAttached()) {
         ++buffer_index;
diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.cpp b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
index ce6acc30c..8385b5509 100644
--- a/src/video_core/renderer_vulkan/vk_texture_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
@@ -1279,6 +1279,10 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
         flags |= VideoCommon::ImageFlagBits::Converted;
         flags |= VideoCommon::ImageFlagBits::CostlyLoad;
     }
+    if (IsPixelFormatBCn(info.format) && !runtime->device.IsOptimalBcnSupported()) {
+        flags |= VideoCommon::ImageFlagBits::Converted;
+        flags |= VideoCommon::ImageFlagBits::CostlyLoad;
+    }
     if (runtime->device.HasDebuggingToolAttached()) {
         original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
     }