Handle leading underscores in update_cc_test_checks.py (llvm#121800)

momchil-velikov · kazutakahirata · commit fe97054dcb12 · 2025-01-13T11:44:14.000-08:00
For some ABIs `update_cc_test_checks.py` is unable to generate tests
because of the mismatch between the mangled function names reported by
clang's `-asd-dump` and the function names in LLVM IR.

This patch fixes it by striping the leading underscore from the mangled
name for global functions if the data layout string says they have one.
diff --git a/clang/test/utils/update_cc_test_checks/Inputs/c-symbol-mangling.c b/clang/test/utils/update_cc_test_checks/Inputs/c-symbol-mangling.c
@@ -18,7 +18,6 @@
 // UTC_ARGS: --enable
 
 #ifdef __arm__
-/// FIXME: UTC does not find this function, but can find all others.
 typedef __attribute__((neon_vector_type(8))) __INT8_TYPE__ int8x8_t;
 int8x8_t test_vaba_s8(int8x8_t a, int8x8_t b, int8x8_t c) {
   return a + b + c;
diff --git a/clang/test/utils/update_cc_test_checks/Inputs/c-symbol-mangling.c.expected b/clang/test/utils/update_cc_test_checks/Inputs/c-symbol-mangling.c.expected
@@ -18,8 +18,22 @@
 // UTC_ARGS: --enable
 
 #ifdef __arm__
-/// FIXME: UTC does not find this function, but can find all others.
 typedef __attribute__((neon_vector_type(8))) __INT8_TYPE__ int8x8_t;
+// THUMB-DARWIN-LABEL: @test_vaba_s8(
+// THUMB-DARWIN-NEXT:  entry:
+// THUMB-DARWIN-NEXT:    [[A_ADDR:%.*]] = alloca <8 x i8>, align 8
+// THUMB-DARWIN-NEXT:    [[B_ADDR:%.*]] = alloca <8 x i8>, align 8
+// THUMB-DARWIN-NEXT:    [[C_ADDR:%.*]] = alloca <8 x i8>, align 8
+// THUMB-DARWIN-NEXT:    store <8 x i8> [[A:%.*]], ptr [[A_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    store <8 x i8> [[B:%.*]], ptr [[B_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    store <8 x i8> [[C:%.*]], ptr [[C_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    [[TMP0:%.*]] = load <8 x i8>, ptr [[A_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    [[TMP1:%.*]] = load <8 x i8>, ptr [[B_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    [[ADD:%.*]] = add <8 x i8> [[TMP0]], [[TMP1]]
+// THUMB-DARWIN-NEXT:    [[TMP2:%.*]] = load <8 x i8>, ptr [[C_ADDR]], align 8
+// THUMB-DARWIN-NEXT:    [[ADD1:%.*]] = add <8 x i8> [[ADD]], [[TMP2]]
+// THUMB-DARWIN-NEXT:    ret <8 x i8> [[ADD1]]
+//
 int8x8_t test_vaba_s8(int8x8_t a, int8x8_t b, int8x8_t c) {
   return a + b + c;
 }
diff --git a/llvm/utils/UpdateTestChecks/common.py b/llvm/utils/UpdateTestChecks/common.py
@@ -557,6 +557,10 @@ def invoke_tool(exe, cmd_args, ir, preprocess_cmd=None, verbose=False):
 UTC_AVOID = "NOTE: Do not autogenerate"
 UNUSED_NOTE = "NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:"
 
+DATA_LAYOUT_RE = re.compile(
+    r"target\s+datalayout\s+=\s+\"(?P<layout>.+)\"$", flags=(re.M | re.S)
+)
+
 OPT_FUNCTION_RE = re.compile(
     r"^(\s*;\s*Function\sAttrs:\s(?P<attrs>[\w\s():,]+?))?\s*define\s+(?P<funcdef_attrs_and_ret>[^@]*)@(?P<func>[\w.$-]+?)\s*"
     r"(?P<args_and_sig>\((\)|(.*?[\w.-]+?)\))[^{]*\{)\n(?P<body>.*?)^\}$",
@@ -651,6 +655,18 @@ def get_triple_from_march(march):
     return "x86"
 
 
+def get_globals_name_prefix(raw_tool_output):
+    m = DATA_LAYOUT_RE.search(raw_tool_output)
+    if not m:
+        return None
+    data_layout = m.group("layout")
+    idx = data_layout.find("m:")
+    if idx < 0:
+        return None
+    ch = data_layout[idx + 2]
+    return "_" if ch == "o" or ch == "x" else None
+
+
 def apply_filters(line, filters):
     has_filter = False
     for f in filters:
diff --git a/llvm/utils/update_cc_test_checks.py b/llvm/utils/update_cc_test_checks.py
@@ -34,7 +34,7 @@
 }
 
 
-def get_line2func_list(args, clang_args):
+def get_line2func_list(args, clang_args, globals_name_prefix):
     ret = collections.defaultdict(list)
     # Use clang's JSON AST dump to get the mangled name
     json_dump_args = [args.clang] + clang_args + ["-fsyntax-only", "-o", "-"]
@@ -122,6 +122,14 @@ def parse_clang_ast_json(node, loc, search):
         if search is None:
             search = spell
         mangled = node.get("mangledName", spell)
+        # Clang's AST dump includes the globals prefix, but when Clang emits
+        # LLVM IR this is not included and instead added as part of the asm
+        # output. Strip it from the mangled name of globals when needed
+        # (see DataLayout::getGlobalPrefix()).
+        if globals_name_prefix:
+            storage = node.get("storageClass", None)
+            if storage != "static" and mangled[0] == globals_name_prefix:
+                mangled = mangled[1:]
         ret[int(line) - 1].append((spell, mangled, search))
 
     ast = json.loads(stdout)
@@ -249,10 +257,10 @@ def config():
     return args, parser
 
 
-def get_function_body(builder, args, filename, clang_args, extra_commands, prefixes):
+def get_function_body(
+    builder, args, filename, clang_args, extra_commands, prefixes, raw_tool_output
+):
     # TODO Clean up duplication of asm/common build_function_body_dictionary
-    # Invoke external tool and extract function bodies.
-    raw_tool_output = common.invoke_tool(args.clang, clang_args, filename)
     for extra_command in extra_commands:
         extra_args = shlex.split(extra_command)
         with tempfile.NamedTemporaryFile() as f:
@@ -383,13 +391,23 @@ def main():
             common.debug("Extracted clang cmd: clang {}".format(clang_args))
             common.debug("Extracted FileCheck prefixes: {}".format(prefixes))
 
+            # Invoke external tool and extract function bodies.
+            raw_tool_output = common.invoke_tool(ti.args.clang, clang_args, ti.path)
             get_function_body(
-                builder, ti.args, ti.path, clang_args, extra_commands, prefixes
+                builder,
+                ti.args,
+                ti.path,
+                clang_args,
+                extra_commands,
+                prefixes,
+                raw_tool_output,
             )
 
             # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to
             # mangled names. Forward all clang args for now.
-            for k, v in get_line2func_list(ti.args, clang_args).items():
+            for k, v in get_line2func_list(
+                ti.args, clang_args, common.get_globals_name_prefix(raw_tool_output)
+            ).items():
                 line2func_list[k].extend(v)
 
         func_dict = builder.finish_and_get_func_dict()
