[llvm] 4b3881e - Emit hidden hostcall argument for sanitized kernels

[Yaxun Liu via llvm-commits]

Author: Yaxun (Sam) Liu
Date: 2021-11-10T17:05:57-05:00
New Revision: 4b3881e9f319b6c4ec69160f16a49c128ffbd7dd

URL: https://github.com/llvm/llvm-project/commit/4b3881e9f319b6c4ec69160f16a49c128ffbd7dd
DIFF: https://github.com/llvm/llvm-project/commit/4b3881e9f319b6c4ec69160f16a49c128ffbd7dd.diff

LOG: Emit hidden hostcall argument for sanitized kernels

this patch - https://reviews.llvm.org/D110337 changes the way how hostcall
hidden argument is emitted for printf, but the sanitized kernels also use
hostcall buffer to report a error for invalid memory access, which is not
handled by the above patch and it leads to vdi runtime error:

Device::callbackQueue aborting with error : HSA_STATUS_ERROR_MEMORY_FAULT:
Agent attempted to access an inaccessible address. code: 0x2b

Patch by: Praveen Velliengiri

Reviewed by: Yaxun Liu, Matt Arsenault

Differential Revision: https://reviews.llvm.org/D112820

Added: 
    llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll

Modified: 
    clang/lib/CodeGen/CodeGenModule.cpp
    clang/test/CodeGenCUDA/amdgpu-asan.cu

Removed: 
    


################################################################################
diff  --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index a4c60f0c50c2d..c28c2e2e85d89 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -565,6 +565,7 @@ void CodeGenModule::Release() {
         "__amdgpu_device_library_preserve_asan_functions_ptr", nullptr,
         llvm::GlobalVariable::NotThreadLocal);
     addCompilerUsedGlobal(Var);
+    getModule().addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1);
   }
 
   emitLLVMUsed();

diff  --git a/clang/test/CodeGenCUDA/amdgpu-asan.cu b/clang/test/CodeGenCUDA/amdgpu-asan.cu
index e392b9617cdd9..d63e3cf12a74c 100644
--- a/clang/test/CodeGenCUDA/amdgpu-asan.cu
+++ b/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

diff  --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll
new file mode 100644
index 0000000000000..5b63af45bbe92
--- /dev/null
+++ b/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