P4 to Git Change 1529531 by gandryey@gera-w8 on 2018/03/20 11:50:12

SWDEV-79445 - OCL generic changes and code clean-up
	- Fix a regression in the AMF test and reenable the suballoc optimization. Rearrange the locks around cache field access only to avoid calling memory release under the cache lock.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#53 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#287 edit

rocclr/runtime/device/pal/palprogram.cpp

@@ -86,12 +86,12 @@ void Segment::copy(size_t offset, const void* src, size_t size) {
   if (cpuAccess_ != nullptr) {
     amd::Os::fastMemcpy(cpuAddress(offset), src, size);
   } else {
-    amd::ScopedLock k(gpuAccess_->dev().xferMgr().lockXfer());
     VirtualGPU& gpu = *gpuAccess_->dev().xferQueue();
     Memory& xferBuf = gpuAccess_->dev().xferWrite().acquire();
     size_t tmpSize = std::min(static_cast<size_t>(xferBuf.size()), size);
     size_t srcOffs = 0;
     while (size != 0) {
+      amd::ScopedLock k(gpuAccess_->dev().xferMgr().lockXfer());
       xferBuf.hostWrite(&gpu, reinterpret_cast<const_address>(src) + srcOffs, 0, tmpSize);
       xferBuf.partialMemCopyTo(gpu, 0, (offset + srcOffs), tmpSize, *gpuAccess_, false, true);
       size -= tmpSize;