[C2y] Claim conformance to WG14 N3254 (#97581)

The test coverage for this has to lean on LLVM's test coverage for the
actual TBAA behavior, but this demonstrates that Clang emits reasonable
LLVM IR to support this construct. It would be surprising should LLVM
break this pattern given how ubiquitous the pattern is in the wild.

The paper can be found at:
https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3254.pdf

2 files changed, 150 insertions, 1 deletions

diff --git a/clang/test/C/C2y/n3254.c b/clang/test/C/C2y/n3254.c
new file mode 100644
index 0000000..e08659cf
--- /dev/null
+++ b/clang/test/C/C2y/n3254.c
@@ -0,0 +1,149 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple=x86_64 -std=c2y %s -emit-llvm -o - | FileCheck %s
+
+/* WG14 N3254: Yes
+ * Accessing byte arrays
+ *
+ * NB: this basically boils down to how LLVM handles TBAA, so the best we can
+ * do for a Clang test is to test that the LLVM IR we pass is reasonable and we
+ * presume that LLVM has the test coverage to ensure that this behavior isn't
+ * regressed.
+ */
+
+struct S {
+  int x;
+  char c;
+  float f;
+};
+
+#define DECL_BUFFER(Ty, Name) alignas(Ty) unsigned char Name[sizeof(Ty)]
+
+// CHECK-LABEL: define dso_local i32 @foo(
+// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[BUFFER:%.*]] = alloca [12 x i8], align 1
+// CHECK-NEXT:    [[S_PTR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    call void @llvm.memset.p0.i64(ptr align 1 [[BUFFER]], i8 0, i64 12, i1 false)
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[X]], align 4
+// CHECK-NEXT:    ret i32 [[TMP1]]
+//
+int foo() {
+  DECL_BUFFER(struct S, buffer) = {};
+  struct S *s_ptr = (struct S *)buffer;
+  return s_ptr->x;
+}
+
+// CHECK-LABEL: define dso_local signext i8 @bar(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[BUFFER:%.*]] = alloca [12 x i8], align 1
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 1
+// CHECK-NEXT:    store i8 97, ptr [[C]], align 1
+// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[C2:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 1
+// CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr [[C2]], align 1
+// CHECK-NEXT:    ret i8 [[TMP0]]
+//
+char bar() {
+  DECL_BUFFER(struct S, buffer);
+  ((struct S *)buffer)->c = 'a';
+  return ((struct S *)buffer)->c;
+}
+
+// CHECK-LABEL: define dso_local float @baz(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[BUFFER:%.*]] = alloca [12 x i8], align 1
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 2
+// CHECK-NEXT:    store float 3.000000e+00, ptr [[F]], align 1
+// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 2
+// CHECK-NEXT:    [[TMP0:%.*]] = load float, ptr [[F2]], align 1
+// CHECK-NEXT:    ret float [[TMP0]]
+//
+float baz() {
+  DECL_BUFFER(struct S, buffer);
+  ((struct S *)buffer)->f = 3.0f;
+  return ((const struct S *)buffer)->f;
+}
+
+struct T {
+  DECL_BUFFER(struct S, buffer);
+};
+
+// CHECK-LABEL: define dso_local signext i8 @quux(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[T:%.*]] = alloca [[STRUCT_T:%.*]], align 1
+// CHECK-NEXT:    [[S_PTR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    call void @llvm.memset.p0.i64(ptr align 1 [[T]], i8 0, i64 12, i1 false)
+// CHECK-NEXT:    [[BUFFER:%.*]] = getelementptr inbounds [[STRUCT_T]], ptr [[T]], i32 0, i32 0
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 1
+// CHECK-NEXT:    [[TMP1:%.*]] = load i8, ptr [[C]], align 4
+// CHECK-NEXT:    ret i8 [[TMP1]]
+//
+char quux() {
+  struct T t = {};
+  struct S *s_ptr = (struct S *)t.buffer;
+  return s_ptr->c;
+}
+
+// CHECK-LABEL: define dso_local float @quibble(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[BUFFER:%.*]] = alloca [12 x i8], align 1
+// CHECK-NEXT:    [[T_PTR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[S_PTR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    call void @llvm.memset.p0.i64(ptr align 1 [[BUFFER]], i8 0, i64 12, i1 false)
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[T_PTR]], align 8
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[T_PTR]], align 8
+// CHECK-NEXT:    [[BUFFER1:%.*]] = getelementptr inbounds [[STRUCT_T:%.*]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT:    [[ARRAYDECAY2:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER1]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY2]], ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP1]], i32 0, i32 2
+// CHECK-NEXT:    [[TMP2:%.*]] = load float, ptr [[F]], align 4
+// CHECK-NEXT:    ret float [[TMP2]]
+//
+float quibble() {
+  DECL_BUFFER(struct T, buffer) = {};
+  const struct T *t_ptr = (struct T *)buffer;
+  const struct S *s_ptr = (struct S *)t_ptr->buffer;
+  return s_ptr->f;
+}
+
+// CHECK-LABEL: define dso_local i32 @quorble(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[BUFFER:%.*]] = alloca [12 x i8], align 1
+// CHECK-NEXT:    [[S_PTR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[BUFFER1:%.*]] = getelementptr inbounds [[STRUCT_T:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 0
+// CHECK-NEXT:    [[ARRAYDECAY2:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER1]], i64 0, i64 0
+// CHECK-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY2]], i32 0, i32 0
+// CHECK-NEXT:    store i32 12, ptr [[X]], align 1
+// CHECK-NEXT:    [[ARRAYDECAY3:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
+// CHECK-NEXT:    [[BUFFER4:%.*]] = getelementptr inbounds [[STRUCT_T]], ptr [[ARRAYDECAY3]], i32 0, i32 0
+// CHECK-NEXT:    [[ARRAYDECAY5:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER4]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY5]], ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
+// CHECK-NEXT:    [[X6:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[X6]], align 4
+// CHECK-NEXT:    ret i32 [[TMP1]]
+//
+int quorble() {
+  DECL_BUFFER(struct T, buffer);
+  ((struct S *)((struct T *)buffer)->buffer)->x = 12;
+  const struct S *s_ptr = (struct S *)((struct T *)buffer)->buffer;
+  return s_ptr->x;
+}
diff --git a/clang/www/c_status.html b/clang/www/c_status.html
index 3fb1efc..2030e1e 100644
--- a/clang/www/c_status.html
+++ b/clang/www/c_status.html
@@ -1260,7 +1260,7 @@ conforms by not defining the <code>__STDC_IEC_559_COMPLEX__</code> macro.
     <tr>
       <td>Accessing byte arrays</td>
       <td><a href="https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3254.pdf">N3254</a></td>
-      <td class="unknown" align="center">Unknown</td>
+      <td class="full" align="center">Yes</td>
     </tr>
     <tr>
       <td>Slay some earthly demons I</td>