[clang] [Clang] Emit TBAA info for enums in C (PR #73326)

Fri Nov 24 05:31:18 PST 2023

llvmbot wrote:




@llvm/pr-subscribers-clang-codegen

Author: David Sherwood (david-arm)

<details>
<summary>Changes</summary>

When emitting TBAA information for enums in C code we currently just treat the data as an 'omnipotent char'. However, with C strict aliasing this means we fail to optimise certain cases. For example, in the SPEC2017 xz benchmark there are structs that contain arrays of enums, and clang pessmistically assumes that accesses to those enums could alias with other struct members that have a different type.

According to

https://en.cppreference.com/w/c/language/enum

enums should be treated as 'int' types unless
explicitly specified (C23) or if 'int' would not be large enough to hold all the enumerated values. In the latter case the compiler is free to choose a suitable integer that would hold all such values.

When compiling C code this patch generates TBAA
information for the enum by using an equivalent integer of the size clang has already chosen for the enum. I have ignored C++ for now because the rules are more complex.

New test added here:

  clang/test/CodeGen/tbaa.c

---
Full diff: https://github.com/llvm/llvm-project/pull/73326.diff


2 Files Affected:

- (modified) clang/lib/CodeGen/CodeGenTBAA.cpp (+4-1) 
- (added) clang/test/CodeGen/tbaa.c (+116) 


``````````diff

diff --git a/clang/lib/CodeGen/CodeGenTBAA.cpp b/clang/lib/CodeGen/CodeGenTBAA.cpp
index 8705d3d65f1a573..f59d3d422d5209d 100644
--- a/clang/lib/CodeGen/CodeGenTBAA.cpp
+++ b/clang/lib/CodeGen/CodeGenTBAA.cpp
@@ -196,11 +196,14 @@ llvm::MDNode *CodeGenTBAA::getTypeInfoHelper(const Type *Ty) {
   // Enum types are distinct types. In C++ they have "underlying types",
   // however they aren't related for TBAA.
   if (const EnumType *ETy = dyn_cast<EnumType>(Ty)) {
+    if (!Features.CPlusPlus)
+      return getTypeInfo(Context.getIntTypeForBitwidth(Size * 8, 0));
+
     // In C++ mode, types have linkage, so we can rely on the ODR and
     // on their mangled names, if they're external.
     // TODO: Is there a way to get a program-wide unique name for a
     // decl with local linkage or no linkage?
-    if (!Features.CPlusPlus || !ETy->getDecl()->isExternallyVisible())
+    if (!ETy->getDecl()->isExternallyVisible())
       return getChar();
 
     SmallString<256> OutName;
diff --git a/clang/test/CodeGen/tbaa.c b/clang/test/CodeGen/tbaa.c
new file mode 100644
index 000000000000000..0ab81f60a71941c
--- /dev/null
+++ b/clang/test/CodeGen/tbaa.c
@@ -0,0 +1,116 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -no-struct-path-tbaa -disable-llvm-passes %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-passes %s -emit-llvm -o - | FileCheck %s -check-prefixes=PATH
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O0 -disable-llvm-passes %s -emit-llvm -o - | FileCheck %s -check-prefix=NO-TBAA
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -relaxed-aliasing -disable-llvm-passes %s -emit-llvm -o - | FileCheck %s -check-prefix=NO-TBAA
+// Test TBAA metadata generated by front-end.
+//
+// NO-TBAA-NOT: !tbaa
+
+typedef unsigned char uint8_t;
+typedef unsigned short uint16_t;
+typedef unsigned int uint32_t;
+typedef unsigned long long uint64_t;
+
+typedef enum {
+  RED_AUTO_32,
+  GREEN_AUTO_32,
+  BLUE_AUTO_32
+} EnumAuto32;
+
+typedef enum {
+  RED_AUTO_64,
+  GREEN_AUTO_64,
+  BLUE_AUTO_64 = 0x100000000ull
+} EnumAuto64;
+
+typedef enum : uint16_t {
+  RED_16,
+  GREEN_16,
+  BLUE_16
+} Enum16;
+
+typedef enum : uint8_t {
+  RED_8,
+  GREEN_8,
+  BLUE_8
+} Enum8;
+
+uint32_t g0(EnumAuto32 *E, uint32_t *val) {
+// CHECK-LABEL: define{{.*}} i32 @g0(
+// CHECK: store i32 5, ptr %{{.*}}, align 4, !tbaa [[TAG_i32:!.*]]
+// CHECK: store i32 0, ptr %{{.*}}, align 4, !tbaa [[TAG_i32]]
+// CHECK: load i32, ptr %{{.*}}, align 4, !tbaa [[TAG_i32]]
+// PATH-LABEL: define{{.*}} i32 @g0(
+// PATH: store i32 5, ptr %{{.*}}, align 4, !tbaa [[TAG_i32:!.*]]
+// PATH: store i32 0, ptr %{{.*}}, align 4, !tbaa [[TAG_i32]]
+// PATH: load i32, ptr %{{.*}}, align 4, !tbaa [[TAG_i32]]
+  *val = 5;
+  *E = RED_AUTO_32;
+  return *val;
+}
+
+uint64_t g1(EnumAuto64 *E, uint64_t *val) {
+// CHECK-LABEL: define{{.*}} i64 @g1(
+// CHECK: store i64 5, ptr %{{.*}}, align 8, !tbaa [[TAG_i64:!.*]]
+// CHECK: store i64 0, ptr %{{.*}}, align 8, !tbaa [[TAG_long:!.*]]
+// CHECK: load i64, ptr %{{.*}}, align 8, !tbaa [[TAG_i64]]
+// PATH-LABEL: define{{.*}} i64 @g1(
+// PATH: store i64 5, ptr %{{.*}}, align 8, !tbaa [[TAG_i64:!.*]]
+// PATH: store i64 0, ptr %{{.*}}, align 8, !tbaa [[TAG_long:!.*]]
+// PATH: load i64, ptr %{{.*}}, align 8, !tbaa [[TAG_i64]]
+  *val = 5;
+  *E = RED_AUTO_64;
+  return *val;
+}
+
+uint16_t g2(Enum16 *E, uint16_t *val) {
+// CHECK-LABEL: define{{.*}} i16 @g2(
+// CHECK: store i16 5, ptr %{{.*}}, align 2, !tbaa [[TAG_i16:!.*]]
+// CHECK: store i16 0, ptr %{{.*}}, align 2, !tbaa [[TAG_i16]]
+// CHECK: load i16, ptr %{{.*}}, align 2, !tbaa [[TAG_i16]]
+// PATH-LABEL: define{{.*}} i16 @g2(
+// PATH: store i16 5, ptr %{{.*}}, align 2, !tbaa [[TAG_i16:!.*]]
+// PATH: store i16 0, ptr %{{.*}}, align 2, !tbaa [[TAG_i16]]
+// PATH: load i16, ptr %{{.*}}, align 2, !tbaa [[TAG_i16]]
+  *val = 5;
+  *E = RED_16;
+  return *val;
+}
+
+uint8_t g3(Enum8 *E, uint8_t *val) {
+// CHECK-LABEL: define{{.*}} i8 @g3(
+// CHECK: store i8 5, ptr %{{.*}}, align 1, !tbaa [[TAG_i8:!.*]]
+// CHECK: store i8 0, ptr %{{.*}}, align 1, !tbaa [[TAG_i8]]
+// CHECK: load i8, ptr %{{.*}}, align 1, !tbaa [[TAG_i8]]
+// PATH-LABEL: define{{.*}} i8 @g3(
+// PATH: store i8 5, ptr %{{.*}}, align 1, !tbaa [[TAG_i8:!.*]]
+// PATH: store i8 0, ptr %{{.*}}, align 1, !tbaa [[TAG_i8]]
+// PATH: load i8, ptr %{{.*}}, align 1, !tbaa [[TAG_i8]]
+  *val = 5;
+  *E = RED_8;
+  return *val;
+}
+
+// CHECK: [[TYPE_char:!.*]] = !{!"omnipotent char", [[TAG_c_tbaa:!.*]],
+// CHECK: [[TAG_c_tbaa]] = !{!"Simple C/C++ TBAA"}
+// CHECK: [[TAG_i32]] = !{[[TYPE_i32:!.*]], [[TYPE_i32]], i64 0}
+// CHECK: [[TYPE_i32]] = !{!"int", [[TYPE_char]],
+// CHECK: [[TAG_i64]] = !{[[TYPE_i64:!.*]], [[TYPE_i64]], i64 0}
+// CHECK: [[TYPE_i64]] = !{!"long long", [[TYPE_char]],
+// CHECK: [[TAG_long]] = !{[[TYPE_long:!.*]], [[TYPE_long]], i64 0}
+// CHECK: [[TYPE_long]] = !{!"long", [[TYPE_char]],
+// CHECK: [[TAG_i16]] = !{[[TYPE_i16:!.*]], [[TYPE_i16]], i64 0}
+// CHECK: [[TYPE_i16]] = !{!"short", [[TYPE_char]],
+// CHECK: [[TAG_i8]] = !{[[TYPE_i8:!.*]], [[TYPE_char]], i64 0}
+
+// PATH: [[TYPE_char:!.*]] = !{!"omnipotent char", [[TAG_c_tbaa:!.*]],
+// PATH: [[TAG_c_tbaa]] = !{!"Simple C/C++ TBAA"}
+// PATH: [[TAG_i32]] = !{[[TYPE_i32:!.*]], [[TYPE_i32]], i64 0}
+// PATH: [[TYPE_i32]] = !{!"int", [[TYPE_char]],
+// PATH: [[TAG_i64]] = !{[[TYPE_i64:!.*]], [[TYPE_i64]], i64 0}
+// PATH: [[TYPE_i64]] = !{!"long long", [[TYPE_char]],
+// PATH: [[TAG_long]] = !{[[TYPE_long:!.*]], [[TYPE_long]], i64 0}
+// PATH: [[TYPE_long]] = !{!"long", [[TYPE_char]],
+// PATH: [[TAG_i16]] = !{[[TYPE_i16:!.*]], [[TYPE_i16]], i64 0}
+// PATH: [[TYPE_i16]] = !{!"short", [[TYPE_char]],
+// PATH: [[TAG_i8]] = !{[[TYPE_i8:!.*]], [[TYPE_char]], i64 0}

``````````

</details>


https://github.com/llvm/llvm-project/pull/73326
