[vk] Fast UBO: fix tracking, resize heuristics, add debug guard

src/core/device_memory_manager.h

@@ -109,6 +109,9 @@ public:
 
     void ReadBlock(DAddr address, void* dest_pointer, size_t size);
     void ReadBlockUnsafe(DAddr address, void* dest_pointer, size_t size);
+#ifdef YUZU_DEBUG
+    bool ReadBlockFastChecked(DAddr address, void* dest_pointer, size_t size);
+#endif
     void WriteBlock(DAddr address, const void* src_pointer, size_t size);
     void WriteBlockUnsafe(DAddr address, const void* src_pointer, size_t size);
 

src/core/device_memory_manager.inc

@@ -467,6 +467,29 @@ void DeviceMemoryManager<Traits>::ReadBlockUnsafe(DAddr address, void* dest_poin
         });
 }
 
+#ifdef YUZU_DEBUG
+template <typename Traits>
+bool DeviceMemoryManager<Traits>::ReadBlockFastChecked(DAddr address, void* dest_pointer,
+                                                       size_t size) {
+    bool success = true;
+    WalkBlock(
+        address, size,
+        [&](size_t copy_amount, DAddr current_vaddr) {
+            LOG_CRITICAL(Render, "DeviceMemory OOB/unmapped: addr=0x{:x} size={}", current_vaddr,
+                         size);
+            std::memset(dest_pointer, 0, copy_amount);
+            success = false;
+        },
+        [&](size_t copy_amount, const u8* const src_ptr) {
+            std::memcpy(dest_pointer, src_ptr, copy_amount);
+        },
+        [&](const std::size_t copy_amount) {
+            dest_pointer = static_cast<u8*>(dest_pointer) + copy_amount;
+        });
+    return success;
+}
+#endif
+
 template <typename Traits>
 void DeviceMemoryManager<Traits>::WriteBlockUnsafe(DAddr address, const void* src_pointer,
                                                    size_t size) {

src/video_core/buffer_cache/buffer_cache.h

@@ -806,7 +806,7 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
                     channel_state->uniform_buffer_binding_sizes[stage][binding_index] != size;
                 if (should_fast_bind) {
                     // We only have to bind when the currently bound buffer is not the fast version
-                    channel_state->fast_bound_uniform_buffers[stage] |= 1U << binding_index;
+                    channel_state->fast_bound_uniform_buffers[stage] |= 1u << binding_index;
                     channel_state->uniform_buffer_binding_sizes[stage][binding_index] = size;
                     runtime.BindFastUniformBuffer(stage, binding_index, size);
                 }
@@ -815,13 +815,22 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
                 return;
             }
         }
-        if constexpr (IS_OPENGL) {
-            channel_state->fast_bound_uniform_buffers[stage] |= 1U << binding_index;
+        channel_state->fast_bound_uniform_buffers[stage] |= 1u << binding_index;
         channel_state->uniform_buffer_binding_sizes[stage][binding_index] = size;
-        }
         // Stream buffer path to avoid stalling on non-Nvidia drivers or Vulkan
         const std::span<u8> span = runtime.BindMappedUniformBuffer(stage, binding_index, size);
+#ifdef YUZU_DEBUG
+        ASSERT(binding_index < NUM_GRAPHICS_UNIFORM_BUFFERS);
+        ASSERT(span.size() >= size && "UBO stream span too small");
+        if (!device_memory.ReadBlockFastChecked(device_addr, span.data(), size)) {
+            LOG_CRITICAL(Render, "DeviceMemory OOB/unmapped: addr=0x{:x} size={}", device_addr, size);
+            channel_state->fast_bound_uniform_buffers[stage] &= ~(1u << binding_index);
+            ASSERT(false);
+            return;
+        }
+#else
         device_memory.ReadBlockUnsafe(device_addr, span.data(), size);
+#endif
         return;
     }
     // Classic cached path
@@ -830,7 +839,8 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     }
     // Skip binding if it's not needed and if the bound buffer is not the fast version
     // This exists to avoid instances where the fast buffer is bound and a GPU write happens
-    needs_bind |= HasFastUniformBufferBound(stage, binding_index);
+    const bool was_fast_bound = HasFastUniformBufferBound(stage, binding_index);
+    needs_bind |= was_fast_bound;
     if constexpr (HAS_PERSISTENT_UNIFORM_BUFFER_BINDINGS) {
         needs_bind |= channel_state->uniform_buffer_binding_sizes[stage][binding_index] != size;
     }
@@ -839,9 +849,6 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     }
     const u32 offset = buffer.Offset(device_addr);
     if constexpr (IS_OPENGL) {
-        // Fast buffer will be unbound
-        channel_state->fast_bound_uniform_buffers[stage] &= ~(1U << binding_index);
-
         // Mark the index as dirty if offset doesn't match
         const bool is_copy_bind = offset != 0 && !runtime.SupportsNonZeroUniformOffset();
         channel_state->dirty_uniform_buffers[stage] |= (is_copy_bind ? 1U : 0U) << index;
@@ -855,6 +862,7 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     } else {
         runtime.BindUniformBuffer(buffer, offset, size);
     }
+    channel_state->fast_bound_uniform_buffers[stage] &= ~(1u << binding_index);
 }
 
 template <class P>
@@ -1789,12 +1797,7 @@ std::span<u8> BufferCache<P>::ImmediateBuffer(size_t wanted_capacity) {
 
 template <class P>
 bool BufferCache<P>::HasFastUniformBufferBound(size_t stage, u32 binding_index) const noexcept {
-    if constexpr (IS_OPENGL) {
-        return ((channel_state->fast_bound_uniform_buffers[stage] >> binding_index) & 1) != 0;
-    } else {
-        // Only OpenGL has fast uniform buffers
-        return false;
-    }
+    return ((channel_state->fast_bound_uniform_buffers[stage] >> binding_index) & 1u) != 0;
 }
 
 template <class P>

src/video_core/buffer_cache/buffer_cache_base.h

@@ -53,6 +53,7 @@ constexpr u32 NUM_COMPUTE_UNIFORM_BUFFERS = 8;
 constexpr u32 NUM_STORAGE_BUFFERS = 16;
 constexpr u32 NUM_TEXTURE_BUFFERS = 32;
 constexpr u32 NUM_STAGES = 5;
+static_assert(NUM_GRAPHICS_UNIFORM_BUFFERS <= 32, "fast bitmask must fit u32");
 
 using UniformBufferSizes = std::array<std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS>, NUM_STAGES>;
 using ComputeUniformBufferSizes = std::array<u32, NUM_COMPUTE_UNIFORM_BUFFERS>;
@@ -137,8 +138,8 @@ public:
     u32 written_compute_texture_buffers = 0;
     u32 image_compute_texture_buffers = 0;
 
-    std::array<u32, 16> uniform_cache_hits{};
-    std::array<u32, 16> uniform_cache_shots{};
+    std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS> uniform_cache_hits{};
+    std::array<u32, NUM_GRAPHICS_UNIFORM_BUFFERS> uniform_cache_shots{};
 
     u32 uniform_buffer_skip_cache_size = DEFAULT_SKIP_CACHE_SIZE;