[vulkan] Fix TOTK dark squares

Qualcomm and Turnip use different subpixel rounding for Vulkan texture
gather coordinates than the Switch's Maxwell GPU. This can select the
wrong texels near texture boundaries, producing large black squares in TOTK

src/video_core/buffer_cache/buffer_cache.h

@@ -1738,64 +1738,36 @@ void BufferCache<P>::TouchBuffer(Buffer& buffer, BufferId buffer_id) noexcept {
 
 template <class P>
 bool BufferCache<P>::SynchronizeBuffer(Buffer& buffer, DAddr device_addr, u32 size) {
-#ifdef __ANDROID__
-    const bool use_optimized_vertex_buffers = Settings::values.use_optimized_vertex_buffers.GetValue();
-#else
-    constexpr bool use_optimized_vertex_buffers = true;
-#endif
-
-    if (use_optimized_vertex_buffers) {
-        upload_copies.clear();
-        u64 total_size_bytes = 0;
-        u64 largest_copy = 0;
-        const DAddr buffer_start = buffer.cpu_addr_cached;
-        const auto add_upload = [&](DAddr start, DAddr end) {
-            if (start == end) return;
-            const u64 range_size = end - start;
-            upload_copies.push_back(BufferCopy{
-                .src_offset = total_size_bytes,
-                .dst_offset = start - buffer_start,
-                .size = range_size,
-            });
-            total_size_bytes += range_size;
-            largest_copy = (std::max)(largest_copy, range_size);
-        };
-        memory_tracker.ForEachUploadRange(device_addr, size, [&](u64 device_addr_out, u64 range_size) {
-            DAddr upload_start = device_addr_out;
-            gpu_modified_ranges.ForEachInRange(device_addr_out, range_size, [&](DAddr gpu_start, DAddr gpu_end) {
-                add_upload(upload_start, gpu_start);
-                upload_start = gpu_end;
-            });
-            add_upload(upload_start, device_addr_out + range_size);
+    upload_copies.clear();
+    u64 total_size_bytes = 0;
+    u64 largest_copy = 0;
+    const DAddr buffer_start = buffer.cpu_addr_cached;
+    const auto add_upload = [&](DAddr start, DAddr end) {
+        if (start == end) return;
+        const u64 range_size = end - start;
+        upload_copies.push_back(BufferCopy{
+            .src_offset = total_size_bytes,
+            .dst_offset = start - buffer_start,
+            .size = range_size,
         });
-        if (total_size_bytes == 0) {
-            return true;
-        }
-        const std::span<BufferCopy> copies_span(upload_copies.data(), upload_copies.size());
-        UploadMemory(buffer, total_size_bytes, largest_copy, copies_span);
-        any_buffer_uploaded = true;
-        return false;
-    } else {
-        boost::container::small_vector<BufferCopy, 4> copies;
-        u64 total_size_bytes = 0;
-        u64 largest_copy = 0;
-        DAddr buffer_start = buffer.CpuAddr();
-        memory_tracker.ForEachUploadRange(device_addr, size, [&](u64 device_addr_out, u64 range_size) {
-            copies.push_back(BufferCopy{
-                .src_offset = total_size_bytes,
-                .dst_offset = device_addr_out - buffer_start,
-                .size = range_size,
-            });
-            total_size_bytes += range_size;
-            largest_copy = (std::max)(largest_copy, range_size);
+        total_size_bytes += range_size;
+        largest_copy = (std::max)(largest_copy, range_size);
+    };
+    memory_tracker.ForEachUploadRange(device_addr, size, [&](u64 device_addr_out, u64 range_size) {
+        DAddr upload_start = device_addr_out;
+        gpu_modified_ranges.ForEachInRange(device_addr_out, range_size, [&](DAddr gpu_start, DAddr gpu_end) {
+            add_upload(upload_start, gpu_start);
+            upload_start = gpu_end;
         });
-        if (total_size_bytes == 0) {
-            return true;
-        }
-        const std::span<BufferCopy> copies_span(copies.data(), copies.size());
-        UploadMemory(buffer, total_size_bytes, largest_copy, copies_span);
-        return false;
+        add_upload(upload_start, device_addr_out + range_size);
+    });
+    if (total_size_bytes == 0) {
+        return true;
     }
+    const std::span<BufferCopy> copies_span(upload_copies.data(), upload_copies.size());
+    UploadMemory(buffer, total_size_bytes, largest_copy, copies_span);
+    any_buffer_uploaded = true;
+    return false;
 }
 
 template <class P>

src/video_core/renderer_vulkan/vk_pipeline_cache.cpp

@@ -447,7 +447,9 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
                                        driver_id == VK_DRIVER_ID_AMD_OPEN_SOURCE ||
                                        driver_id == VK_DRIVER_ID_MESA_RADV ||
                                        driver_id == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS ||
-                                       driver_id == VK_DRIVER_ID_INTEL_OPEN_SOURCE_MESA,
+                                       driver_id == VK_DRIVER_ID_INTEL_OPEN_SOURCE_MESA ||
+                                       driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY ||
+                                       driver_id == VK_DRIVER_ID_MESA_TURNIP,
 
         .has_broken_spirv_clamp = driver_id == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS,
         .has_broken_spirv_position_input = driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY,