skip 1st 2nd dispatches extended to linux. vk_staging_buffer_pool.cpp clamp moved to buffer_cache.h

- Clamp staging buffer size to 2GB to prevent Vulkan allocation failures
- Add size validation in MappedUploadMemory to avoid buffer overruns

src/video_core/buffer_cache/buffer_cache.h

@@ -1508,7 +1508,10 @@ void BufferCache<P>::MappedUploadMemory([[maybe_unused]] Buffer& buffer,
                                         [[maybe_unused]] u64 total_size_bytes,
                                         [[maybe_unused]] std::span<BufferCopy> copies) {
     if constexpr (USE_MEMORY_MAPS) {
-        auto upload_staging = runtime.UploadStagingBuffer(total_size_bytes);
+        constexpr u64 MAX_STAGING_SIZE = 2_GiB;
+        auto upload_staging = runtime.UploadStagingBuffer((std::min)(total_size_bytes, MAX_STAGING_SIZE));
+        if (upload_staging.mapped_span.size() < total_size_bytes) return;
+        //auto upload_staging = runtime.UploadStagingBuffer(total_size_bytes);
         const std::span<u8> staging_pointer = upload_staging.mapped_span;
         for (BufferCopy& copy : copies) {
             u8* const src_pointer = staging_pointer.data() + copy.src_offset;

src/video_core/engines/maxwell_dma.cpp

@@ -92,19 +92,25 @@ void MaxwellDMA::Launch() {
             }
         }
     } else {
-        // TODO: allow multisized components.
+        // TODO: xbzk: multisized components support.
+        // validadte this widely!
+        // shipped in PR 3164.
         auto& accelerate = rasterizer->AccessAccelerateDMA();
         const bool is_const_a_dst = regs.remap_const.dst_x == RemapConst::Swizzle::CONST_A;
         if (regs.launch_dma.remap_enable != 0 && is_const_a_dst) {
-            ASSERT(regs.remap_const.component_size_minus_one == 3);
+            const u32 remap_components_size = regs.remap_const.component_size_minus_one + 1;
             accelerate.BufferClear(regs.offset_out, regs.line_length_in,
                                    regs.remap_const.remap_consta_value);
-            read_buffer.resize_destructive(regs.line_length_in * sizeof(u32));
-            std::span<u32> span(reinterpret_cast<u32*>(read_buffer.data()), regs.line_length_in);
-            std::ranges::fill(span, regs.remap_const.remap_consta_value);
+            read_buffer.resize_destructive(regs.line_length_in * remap_components_size);
+            for (u32 i = 0; i < regs.line_length_in; ++i) {
+                for (u32 j = 0; j < remap_components_size; ++j) {
+                    read_buffer[i * remap_components_size + j] =
+                        (regs.remap_const.remap_consta_value >> (j * 8)) & 0xFF;
+                }
+            }
             memory_manager.WriteBlockUnsafe(regs.offset_out,
-                                            reinterpret_cast<u8*>(read_buffer.data()),
-                                            regs.line_length_in * sizeof(u32));
+                                            read_buffer.data(),
+                                            regs.line_length_in * remap_components_size);
         } else {
             memory_manager.FlushCaching();
             const auto convert_linear_2_blocklinear_addr = [](u64 address) {

src/video_core/renderer_vulkan/vk_rasterizer.cpp

@@ -479,6 +479,14 @@ void RasterizerVulkan::Clear(u32 layer_count) {
 }
 
 void RasterizerVulkan::DispatchCompute() {
+#if defined(ANDROID) || defined(__linux__)
+    static u32 dispatch_count = 0;
+    if (dispatch_count < 2) {
+        dispatch_count++;
+        return;
+    }
+#endif
+
     FlushWork();
     gpu_memory->FlushCaching();