Merge pull request #6403 from degasus/master

OGL: Use glBufferData on Mali.

Source/Core/VideoBackends/OGL/StreamBuffer.cpp

@@ -376,7 +376,12 @@ std::unique_ptr<StreamBuffer> StreamBuffer::Create(u32 type, u32 size)
 
     // don't fall back to MapAnd* for Nvidia drivers
     if (DriverDetails::HasBug(DriverDetails::BUG_BROKEN_UNSYNC_MAPPING))
+    {
+      if (DriverDetails::HasBug(DriverDetails::BUG_BROKEN_BUFFER_STREAM))
+        return std::make_unique<BufferData>(type, size);
+      else
         return std::make_unique<BufferSubData>(type, size);
+    }
 
     // mapping fallback
     if (g_ogl_config.bSupportsGLSync)

Source/Core/VideoCommon/DriverDetails.cpp

@@ -82,6 +82,8 @@ static BugInfo m_known_bugs[] = {
      BUG_BROKEN_UNSYNC_MAPPING, -1.0, -1.0, true},
     {API_OPENGL, OS_LINUX, VENDOR_NVIDIA, DRIVER_NVIDIA, Family::UNKNOWN, BUG_BROKEN_UNSYNC_MAPPING,
      -1.0, -1.0, true},
+    {API_OPENGL, OS_ALL, VENDOR_ARM, DRIVER_ARM, Family::UNKNOWN, BUG_BROKEN_UNSYNC_MAPPING, -1.0,
+     -1.0, true},
     {API_OPENGL, OS_WINDOWS, VENDOR_INTEL, DRIVER_INTEL, Family::UNKNOWN,
      BUG_INTEL_BROKEN_BUFFER_STORAGE, 101810.3907, 101810.3960, true},
     {API_OPENGL, OS_ALL, VENDOR_ATI, DRIVER_ATI, Family::UNKNOWN, BUG_SLOW_GETBUFFERSUBDATA, -1.0,

Source/Core/VideoCommon/DriverDetails.h

@@ -125,13 +125,17 @@ enum Bug
   // Intel HD 4000 series isn't affected by the bug
   BUG_PRIMITIVE_RESTART,
   // Bug: unsync mapping doesn't work fine
-  // Affected devices: Nvidia driver
+  // Affected devices: Nvidia driver, ARM Mali
   // Started Version: -1
   // Ended Version: -1
   // The Nvidia driver (both Windows + Linux) doesn't like unsync mapping performance wise.
   // Because of their threaded behavior, they seem not to handle unsync mapping complete unsync,
   // in fact, they serialize the driver which adds a much bigger overhead.
   // Workaround: Use BufferSubData
+  // The Mali behavior is even worse: They just ignore the unsychronized flag and stall the GPU.
+  // Workaround: As they were even too lazy to implement asynchronous buffer updates,
+  //             BufferSubData stalls as well, so we have to use the slowest possible path:
+  //             Alloc one buffer per draw call with BufferData.
   // TODO: some Windows AMD driver/GPU combination seems also affected
   //       but as they all support pinned memory, it doesn't matter
   BUG_BROKEN_UNSYNC_MAPPING,