Index: clang/lib/CodeGen/CodeGenModule.cpp =================================================================== --- clang/lib/CodeGen/CodeGenModule.cpp +++ clang/lib/CodeGen/CodeGenModule.cpp @@ -565,6 +565,7 @@ "__amdgpu_device_library_preserve_asan_functions_ptr", nullptr, llvm::GlobalVariable::NotThreadLocal); addCompilerUsedGlobal(Var); + getModule().addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1); } emitLLVMUsed(); Index: clang/test/CodeGenCUDA/amdgpu-asan.cu =================================================================== --- clang/test/CodeGenCUDA/amdgpu-asan.cu +++ clang/test/CodeGenCUDA/amdgpu-asan.cu @@ -9,12 +9,12 @@ // RUN: %clang_cc1 %s -emit-llvm -o - -triple=amdgcn-amd-amdhsa \ // RUN: -fcuda-is-device -target-cpu gfx906 -fsanitize=address \ // RUN: -mlink-bitcode-file %t.asanrtl.bc -x hip \ -// RUN: | FileCheck -check-prefix=ASAN %s +// RUN: | FileCheck -check-prefixes=ASAN,MFCHECK %s // RUN: %clang_cc1 %s -emit-llvm -o - -triple=amdgcn-amd-amdhsa \ // RUN: -fcuda-is-device -target-cpu gfx906 -fsanitize=address \ // RUN: -O3 -mlink-bitcode-file %t.asanrtl.bc -x hip \ -// RUN: | FileCheck -check-prefix=ASAN %s +// RUN: | FileCheck -check-prefixes=ASAN,MFCHECK %s // RUN: %clang_cc1 %s -emit-llvm -o - -triple=amdgcn-amd-amdhsa \ // RUN: -fcuda-is-device -target-cpu gfx906 -x hip \ @@ -27,5 +27,8 @@ // ASAN-DAG: @llvm.compiler.used = {{.*}}@__amdgpu_device_library_preserve_asan_functions_ptr // ASAN-DAG: define weak void @__asan_report_load1(i64 %{{.*}}) +// MFCHECK: !llvm.module.flags = !{![[FLAG1:[0-9]+]], ![[FLAG2:[0-9]+]]} +// MFCHECK: ![[FLAG1]] = !{i32 4, !"amdgpu_hostcall", i32 1} + // CHECK-NOT: @__amdgpu_device_library_preserve_asan_functions // CHECK-NOT: @__asan_report_load1 Index: llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll =================================================================== --- /dev/null +++ llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll @@ -0,0 +1,54 @@ +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck %s + +; CHECK: --- +; CHECK: amdhsa.kernels: +; CHECK: - .args: +; CHECK-NEXT: - .name: a +; CHECK-NEXT: .offset: 0 +; CHECK-NEXT: .size: 1 +; CHECK-NEXT: .type_name: char +; CHECK-NEXT: .value_kind: by_value +; CHECK-NEXT: - .offset: 8 +; CHECK-NEXT: .size: 8 +; CHECK-NEXT: .value_kind: hidden_global_offset_x +; CHECK-NEXT: - .offset: 16 +; CHECK-NEXT: .size: 8 +; CHECK-NEXT: .value_kind: hidden_global_offset_y +; CHECK-NEXT: - .offset: 24 +; CHECK-NEXT: .size: 8 +; CHECK-NEXT: .value_kind: hidden_global_offset_z +; CHECK-NEXT: - .address_space: global +; CHECK-NEXT: .offset: 32 +; CHECK-NEXT: .size: 8 +; CHECK-NEXT: .value_kind: hidden_hostcall_buffer +; CHECK: .language: OpenCL C +; CHECK-NEXT: .language_version: +; CHECK-NEXT: - 2 +; CHECK-NEXT: - 0 +; CHECK: .name: test_kernel +; CHECK: .symbol: test_kernel.kd + +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 { + ret void +} + +; CHECK: amdhsa.version: +; CHECK-NEXT: - 1 +; CHECK-NEXT: - 0 + +attributes #0 = { sanitize_address "amdgpu-implicitarg-num-bytes"="48" } + +!1 = !{i32 0} +!2 = !{!"none"} +!3 = !{!"char"} +!4 = !{!""} + +!opencl.ocl.version = !{!90} +!90 = !{i32 2, i32 0} + +!llvm.module.flags = !{!0} +!0 = !{i32 4, !"amdgpu_hostcall", i32 1} + +; CHECK: AMDGPU HSA Metadata Parser Test: PASS