diff --git a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
@@ -798,7 +798,8 @@
   if (!HiddenArgNumBytes)
     return;
 
-  auto &DL = Func.getParent()->getDataLayout();
+  const Module *M = Func.getParent();
+  auto &DL = M->getDataLayout();
   auto Int64Ty = Type::getInt64Ty(Func.getContext());
 
   if (HiddenArgNumBytes >= 8)
@@ -814,16 +815,16 @@
   auto Int8PtrTy =
       Type::getInt8PtrTy(Func.getContext(), AMDGPUAS::GLOBAL_ADDRESS);
 
-  // Emit "printf buffer" argument if printf is used, otherwise emit dummy
-  // "none" argument.
+  // Emit "printf buffer" argument if printf is used, emit "hostcall buffer"
+  // if "hostcall" module flag is set, otherwise emit dummy "none" argument.
   if (HiddenArgNumBytes >= 32) {
-    if (Func.getParent()->getNamedMetadata("llvm.printf.fmts"))
+    if (M->getNamedMetadata("llvm.printf.fmts"))
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_printf_buffer", Offset,
                     Args);
-    else if (Func.getParent()->getFunction("__ockl_hostcall_internal")) {
+    else if (M->getModuleFlag("amdgpu_hostcall")) {
       // The printf runtime binding pass should have ensured that hostcall and
       // printf are not used in the same module.
-      assert(!Func.getParent()->getNamedMetadata("llvm.printf.fmts"));
+      assert(!M->getNamedMetadata("llvm.printf.fmts"));
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_hostcall_buffer", Offset,
                     Args);
     } else
diff --git a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
--- a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
+++ b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
@@ -63,6 +63,7 @@
   auto Int64Ty = Builder.getInt64Ty();
   auto M = Builder.GetInsertBlock()->getModule();
   auto Fn = M->getOrInsertFunction("__ockl_printf_begin", Int64Ty, Int64Ty);
+  M->addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1);
   return Builder.CreateCall(Fn, Version);
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll
--- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll
@@ -29,8 +29,6 @@
 ; CHECK:          .name:           test_kernel
 ; CHECK:          .symbol:         test_kernel.kd
 
-declare <2 x i64> @__ockl_hostcall_internal(i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64)
-
 define amdgpu_kernel void @test_kernel(i8 %a) #0
     !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
     !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
@@ -51,4 +49,7 @@
 !opencl.ocl.version = !{!90}
 !90 = !{i32 2, i32 0}
 
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"amdgpu_hostcall", i32 1}
+
 ; PARSER: AMDGPU HSA Metadata Parser Test: PASS