modify printPrintfOutput to be an atomic operation

Mutex was added to kernel_imp for atomic operation during
printPrintfOutput on kernel.

Related-To: LOCI-3681

Signed-off-by: Zhang, Winston <winston.zhang@intel.com>

level_zero/core/source/kernel/kernel_imp.cpp

@@ -974,6 +974,7 @@ void KernelImp::createPrintfBuffer() {
 }
 
 void KernelImp::printPrintfOutput(bool hangDetected) {
+    std::lock_guard<std::mutex> lock(this->printfLock);
     PrintfHandler::printOutput(kernelImmData, this->printfBuffer, module->getDevice(), hangDetected);
 }
 

level_zero/core/source/kernel/kernel_imp.h

@@ -14,6 +14,7 @@
 #include "level_zero/core/source/kernel/kernel.h"
 
 #include <memory>
+#include <mutex>
 
 namespace L0 {
 
@@ -230,6 +231,7 @@ struct KernelImp : Kernel {
     std::unique_ptr<NEO::ImplicitArgs> pImplicitArgs;
 
     std::unique_ptr<KernelExt> pExtension;
+    std::mutex printfLock;
 };
 
 } // namespace L0