[AArch64] Add support for __builtin_ms_va_list on aarch64

Move builtins from the x86 specific scope into the global
scope. Their use is still limited to x86_64 and aarch64 though.

This allows wine on aarch64 to properly handle variadic functions.

Differential Revision: https://reviews.llvm.org/D34475

llvm-svn: 308218

clang/include/clang-c/Index.h

@@ -3205,7 +3205,7 @@ enum CXCallingConv {
   CXCallingConv_AAPCS_VFP = 7,
   CXCallingConv_X86RegCall = 8,
   CXCallingConv_IntelOclBicc = 9,
-  CXCallingConv_X86_64Win64 = 10,
+  CXCallingConv_Win64 = 10,
   CXCallingConv_X86_64SysV = 11,
   CXCallingConv_X86VectorCall = 12,
   CXCallingConv_Swift = 13,

clang/include/clang/Basic/Builtins.def

@@ -1413,6 +1413,11 @@ BUILTIN(__builtin_os_log_format, "v*v*cC*.", "p:0:nt")
 // Builtins for XRay
 BUILTIN(__xray_customevent, "vcC*z", "")
 
+// Win64-compatible va_list functions
+BUILTIN(__builtin_ms_va_start, "vc*&.", "nt")
+BUILTIN(__builtin_ms_va_end, "vc*&", "n")
+BUILTIN(__builtin_ms_va_copy, "vc*&c*&", "n")
+
 #undef BUILTIN
 #undef LIBBUILTIN
 #undef LANGBUILTIN

clang/include/clang/Basic/BuiltinsX86.def

@@ -34,11 +34,6 @@
 // can use it?
 BUILTIN(__builtin_cpu_supports, "bcC*", "nc")
 
-// Win64-compatible va_list functions
-BUILTIN(__builtin_ms_va_start, "vc*&.", "nt")
-BUILTIN(__builtin_ms_va_end, "vc*&", "n")
-BUILTIN(__builtin_ms_va_copy, "vc*&c*&", "n")
-
 // Undefined Values
 //
 TARGET_BUILTIN(__builtin_ia32_undef128, "V2d", "nc", "")

clang/include/clang/Basic/DiagnosticSemaKinds.td

@@ -8113,10 +8113,10 @@ def err_systemz_invalid_tabort_code : Error<
   "invalid transaction abort code">;
 def err_64_bit_builtin_32_bit_tgt : Error<
   "this builtin is only available on 64-bit targets">;
+def err_builtin_x64_aarch64_only : Error<
+  "this builtin is only available on x86-64 and aarch64 targets">;
 def err_ppc_builtin_only_on_pwr7 : Error<
   "this builtin is only valid on POWER7 or later CPUs">;
-def err_x86_builtin_64_only : Error<
-  "this builtin is only available on x86-64 targets">;
 def err_x86_builtin_invalid_rounding : Error<
   "invalid rounding argument">;
 def err_x86_builtin_invalid_scale : Error<

clang/include/clang/Basic/Specifiers.h

@@ -236,7 +236,7 @@ namespace clang {
     CC_X86ThisCall, // __attribute__((thiscall))
     CC_X86VectorCall, // __attribute__((vectorcall))
     CC_X86Pascal,   // __attribute__((pascal))
-    CC_X86_64Win64, // __attribute__((ms_abi))
+    CC_Win64,       // __attribute__((ms_abi))
     CC_X86_64SysV,  // __attribute__((sysv_abi))
     CC_X86RegCall, // __attribute__((regcall))
     CC_AAPCS,       // __attribute__((pcs("aapcs")))

clang/lib/AST/ItaniumMangle.cpp

@@ -2529,7 +2529,7 @@ StringRef CXXNameMangler::getCallingConvQualifierName(CallingConv CC) {
   case CC_X86ThisCall:
   case CC_X86VectorCall:
   case CC_X86Pascal:
-  case CC_X86_64Win64:
+  case CC_Win64:
   case CC_X86_64SysV:
   case CC_X86RegCall:
   case CC_AAPCS:

clang/lib/AST/MicrosoftMangle.cpp

@@ -2122,7 +2122,7 @@ void MicrosoftCXXNameMangler::mangleCallingConvention(CallingConv CC) {
   switch (CC) {
     default:
       llvm_unreachable("Unsupported CC for mangling");
-    case CC_X86_64Win64:
+    case CC_Win64:
     case CC_X86_64SysV:
     case CC_C: Out << 'A'; break;
     case CC_X86Pascal: Out << 'C'; break;

clang/lib/AST/Type.cpp

@@ -2630,7 +2630,7 @@ StringRef FunctionType::getNameForCallConv(CallingConv CC) {
   case CC_X86ThisCall: return "thiscall";
   case CC_X86Pascal: return "pascal";
   case CC_X86VectorCall: return "vectorcall";
-  case CC_X86_64Win64: return "ms_abi";
+  case CC_Win64: return "ms_abi";
   case CC_X86_64SysV: return "sysv_abi";
   case CC_X86RegCall : return "regcall";
   case CC_AAPCS: return "aapcs";

clang/lib/AST/TypePrinter.cpp

@@ -751,7 +751,7 @@ void TypePrinter::printFunctionAfter(const FunctionType::ExtInfo &Info,
     case CC_IntelOclBicc:
       OS << " __attribute__((intel_ocl_bicc))";
       break;
-    case CC_X86_64Win64:
+    case CC_Win64:
       OS << " __attribute__((ms_abi))";
       break;
     case CC_X86_64SysV:

clang/lib/Basic/Targets.cpp

@@ -4899,7 +4899,7 @@ class X86_64TargetInfo : public X86TargetInfo {
     case CC_Swift:
     case CC_X86VectorCall:
     case CC_IntelOclBicc:
-    case CC_X86_64Win64:
+    case CC_Win64:
     case CC_PreserveMost:
     case CC_PreserveAll:
     case CC_X86RegCall:
@@ -6290,6 +6290,9 @@ class AArch64TargetInfo : public TargetInfo {
     LongDoubleWidth = LongDoubleAlign = SuitableAlign = 128;
     LongDoubleFormat = &llvm::APFloat::IEEEquad();
 
+    // Make __builtin_ms_va_list available.
+    HasBuiltinMSVaList = true;
+
     // {} in inline assembly are neon specifiers, not assembly variant
     // specifiers.
     NoAsmVariants = true;
@@ -6473,6 +6476,7 @@ class AArch64TargetInfo : public TargetInfo {
     case CC_PreserveMost:
     case CC_PreserveAll:
     case CC_OpenCLKernel:
+    case CC_Win64:
       return CCCR_OK;
     default:
       return CCCR_Warning;

clang/lib/CodeGen/CGBuiltin.cpp

@@ -2795,6 +2795,33 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
       Arg1 = Builder.CreateTruncOrBitCast(Arg1, PTy1);
     return RValue::get(Builder.CreateCall(F, {Arg0Val, Arg1}));
   }
+
+  case Builtin::BI__builtin_ms_va_start:
+  case Builtin::BI__builtin_ms_va_end:
+    return RValue::get(
+        EmitVAStartEnd(EmitMSVAListRef(E->getArg(0)).getPointer(),
+                       BuiltinID == Builtin::BI__builtin_ms_va_start));
+
+  case Builtin::BI__builtin_ms_va_copy: {
+    // Lower this manually. We can't reliably determine whether or not any
+    // given va_copy() is for a Win64 va_list from the calling convention
+    // alone, because it's legal to do this from a System V ABI function.
+    // With opaque pointer types, we won't have enough information in LLVM
+    // IR to determine this from the argument types, either. Best to do it
+    // now, while we have enough information.
+    Address DestAddr = EmitMSVAListRef(E->getArg(0));
+    Address SrcAddr = EmitMSVAListRef(E->getArg(1));
+
+    llvm::Type *BPP = Int8PtrPtrTy;
+
+    DestAddr = Address(Builder.CreateBitCast(DestAddr.getPointer(), BPP, "cp"),
+                       DestAddr.getAlignment());
+    SrcAddr = Address(Builder.CreateBitCast(SrcAddr.getPointer(), BPP, "ap"),
+                      SrcAddr.getAlignment());
+
+    Value *ArgPtr = Builder.CreateLoad(SrcAddr, "ap.val");
+    return RValue::get(Builder.CreateStore(ArgPtr, DestAddr));
+  }
   }
 
   // If this is an alias for a lib function (e.g. __builtin_sin), emit
@@ -7223,31 +7250,6 @@ static Value *EmitX86SExtMask(CodeGenFunction &CGF, Value *Op,
 
 Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
                                            const CallExpr *E) {
-  if (BuiltinID == X86::BI__builtin_ms_va_start ||
-      BuiltinID == X86::BI__builtin_ms_va_end)
-    return EmitVAStartEnd(EmitMSVAListRef(E->getArg(0)).getPointer(),
-                          BuiltinID == X86::BI__builtin_ms_va_start);
-  if (BuiltinID == X86::BI__builtin_ms_va_copy) {
-    // Lower this manually. We can't reliably determine whether or not any
-    // given va_copy() is for a Win64 va_list from the calling convention
-    // alone, because it's legal to do this from a System V ABI function.
-    // With opaque pointer types, we won't have enough information in LLVM
-    // IR to determine this from the argument types, either. Best to do it
-    // now, while we have enough information.
-    Address DestAddr = EmitMSVAListRef(E->getArg(0));
-    Address SrcAddr = EmitMSVAListRef(E->getArg(1));
-
-    llvm::Type *BPP = Int8PtrPtrTy;
-
-    DestAddr = Address(Builder.CreateBitCast(DestAddr.getPointer(), BPP, "cp"),
-                       DestAddr.getAlignment());
-    SrcAddr = Address(Builder.CreateBitCast(SrcAddr.getPointer(), BPP, "ap"),
-                      SrcAddr.getAlignment());
-
-    Value *ArgPtr = Builder.CreateLoad(SrcAddr, "ap.val");
-    return Builder.CreateStore(ArgPtr, DestAddr);
-  }
-
   SmallVector<Value*, 4> Ops;
 
   // Find out if any arguments are required to be integer constant expressions.

clang/lib/CodeGen/CGCall.cpp

@@ -50,7 +50,7 @@ unsigned CodeGenTypes::ClangCallConvToLLVMCallConv(CallingConv CC) {
   case CC_X86FastCall: return llvm::CallingConv::X86_FastCall;
   case CC_X86RegCall: return llvm::CallingConv::X86_RegCall;
   case CC_X86ThisCall: return llvm::CallingConv::X86_ThisCall;
-  case CC_X86_64Win64: return llvm::CallingConv::Win64;
+  case CC_Win64: return llvm::CallingConv::Win64;
   case CC_X86_64SysV: return llvm::CallingConv::X86_64_SysV;
   case CC_AAPCS: return llvm::CallingConv::ARM_AAPCS;
   case CC_AAPCS_VFP: return llvm::CallingConv::ARM_AAPCS_VFP;
@@ -218,7 +218,7 @@ static CallingConv getCallingConventionForDecl(const Decl *D, bool IsWindows) {
     return CC_IntelOclBicc;
 
   if (D->hasAttr<MSABIAttr>())
-    return IsWindows ? CC_C : CC_X86_64Win64;
+    return IsWindows ? CC_C : CC_Win64;
 
   if (D->hasAttr<SysVABIAttr>())
     return IsWindows ? CC_X86_64SysV : CC_C;

clang/lib/CodeGen/CGDebugInfo.cpp

@@ -956,7 +956,7 @@ static unsigned getDwarfCC(CallingConv CC) {
     return llvm::dwarf::DW_CC_BORLAND_pascal;
 
   // FIXME: Create new DW_CC_ codes for these calling conventions.
-  case CC_X86_64Win64:
+  case CC_Win64:
   case CC_X86_64SysV:
   case CC_AAPCS:
   case CC_AAPCS_VFP:

clang/lib/Sema/SemaChecking.cpp

@@ -760,6 +760,7 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
     if (CheckObjCString(TheCall->getArg(0)))
       return ExprError();
     break;
+  case Builtin::BI__builtin_ms_va_start:
   case Builtin::BI__builtin_stdarg_start:
   case Builtin::BI__builtin_va_start:
     if (SemaBuiltinVAStart(BuiltinID, TheCall))
@@ -2102,9 +2103,6 @@ bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
   if (BuiltinID == X86::BI__builtin_cpu_supports)
     return SemaBuiltinCpuSupports(*this, TheCall);
 
-  if (BuiltinID == X86::BI__builtin_ms_va_start)
-    return SemaBuiltinVAStart(BuiltinID, TheCall);
-
   // If the intrinsic has rounding or SAE make sure its valid.
   if (CheckX86BuiltinRoundingOrSAE(BuiltinID, TheCall))
     return true;
@@ -3629,24 +3627,25 @@ ExprResult Sema::CheckOSLogFormatStringArg(Expr *Arg) {
 static bool checkVAStartABI(Sema &S, unsigned BuiltinID, Expr *Fn) {
   const llvm::Triple &TT = S.Context.getTargetInfo().getTriple();
   bool IsX64 = TT.getArch() == llvm::Triple::x86_64;
+  bool IsAArch64 = TT.getArch() == llvm::Triple::aarch64;
   bool IsWindows = TT.isOSWindows();
-  bool IsMSVAStart = BuiltinID == X86::BI__builtin_ms_va_start;
-  if (IsX64) {
+  bool IsMSVAStart = BuiltinID == Builtin::BI__builtin_ms_va_start;
+  if (IsX64 || IsAArch64) {
     clang::CallingConv CC = CC_C;
     if (const FunctionDecl *FD = S.getCurFunctionDecl())
       CC = FD->getType()->getAs<FunctionType>()->getCallConv();
     if (IsMSVAStart) {
       // Don't allow this in System V ABI functions.
-      if (CC == CC_X86_64SysV || (!IsWindows && CC != CC_X86_64Win64))
+      if (CC == CC_X86_64SysV || (!IsWindows && CC != CC_Win64))
         return S.Diag(Fn->getLocStart(),
                       diag::err_ms_va_start_used_in_sysv_function);
     } else {
-      // On x86-64 Unix, don't allow this in Win64 ABI functions.
+      // On x86-64/AArch64 Unix, don't allow this in Win64 ABI functions.
       // On x64 Windows, don't allow this in System V ABI functions.
       // (Yes, that means there's no corresponding way to support variadic
       // System V ABI functions on Windows.)
       if ((IsWindows && CC == CC_X86_64SysV) ||
-          (!IsWindows && CC == CC_X86_64Win64))
+          (!IsWindows && CC == CC_Win64))
         return S.Diag(Fn->getLocStart(),
                       diag::err_va_start_used_in_wrong_abi_function)
                << !IsWindows;
@@ -3655,7 +3654,7 @@ static bool checkVAStartABI(Sema &S, unsigned BuiltinID, Expr *Fn) {
   }
 
   if (IsMSVAStart)
-    return S.Diag(Fn->getLocStart(), diag::err_x86_builtin_64_only);
+    return S.Diag(Fn->getLocStart(), diag::err_builtin_x64_aarch64_only);
   return false;
 }
 

clang/lib/Sema/SemaDeclAttr.cpp

@@ -4280,7 +4280,7 @@ bool Sema::CheckCallingConvAttr(const AttributeList &attr, CallingConv &CC,
   case AttributeList::AT_RegCall: CC = CC_X86RegCall; break;
   case AttributeList::AT_MSABI:
     CC = Context.getTargetInfo().getTriple().isOSWindows() ? CC_C :
-                                                             CC_X86_64Win64;
+                                                             CC_Win64;
     break;
   case AttributeList::AT_SysVABI:
     CC = Context.getTargetInfo().getTriple().isOSWindows() ? CC_X86_64SysV :

clang/test/CodeGen/ms_abi_aarch64.c

@@ -0,0 +1,68 @@
+// RUN: %clang_cc1 -triple aarch64-linux-gnu -emit-llvm < %s | FileCheck -check-prefix=LINUX %s
+// RUN: %clang_cc1 -triple aarch64-pc-win32 -emit-llvm < %s | FileCheck -check-prefix=WIN64 %s
+
+void __attribute__((ms_abi)) f1(void);
+void f2(void);
+void f3(void) {
+  // LINUX-LABEL: define void @f3()
+  // WIN64-LABEL: define void @f3()
+  f1();
+  // LINUX: call win64cc void @f1()
+  // WIN64: call void @f1()
+  f2();
+  // LINUX: call void @f2()
+  // WIN64: call void @f2()
+}
+// LINUX: declare win64cc void @f1()
+// LINUX: declare void @f2()
+// WIN64: declare void @f1()
+// WIN64: declare void @f2()
+
+// Win64 ABI varargs
+void __attribute__((ms_abi)) f4(int a, ...) {
+  // LINUX-LABEL: define win64cc void @f4
+  // WIN64-LABEL: define void @f4
+  __builtin_ms_va_list ap;
+  __builtin_ms_va_start(ap, a);
+  // LINUX: %[[AP:.*]] = alloca i8*
+  // LINUX: call void @llvm.va_start
+  // WIN64: %[[AP:.*]] = alloca i8*
+  // WIN64: call void @llvm.va_start
+  int b = __builtin_va_arg(ap, int);
+  // LINUX: %[[AP_CUR:.*]] = load i8*, i8** %[[AP]]
+  // LINUX-NEXT: %[[AP_NEXT:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR]], i64 8
+  // LINUX-NEXT: store i8* %[[AP_NEXT]], i8** %[[AP]]
+  // LINUX-NEXT: bitcast i8* %[[AP_CUR]] to i32*
+  // WIN64: %[[AP_CUR:.*]] = load i8*, i8** %[[AP]]
+  // WIN64-NEXT: %[[AP_NEXT:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR]], i64 8
+  // WIN64-NEXT: store i8* %[[AP_NEXT]], i8** %[[AP]]
+  // WIN64-NEXT: bitcast i8* %[[AP_CUR]] to i32*
+  __builtin_ms_va_list ap2;
+  __builtin_ms_va_copy(ap2, ap);
+  // LINUX: %[[AP_VAL:.*]] = load i8*, i8** %[[AP]]
+  // LINUX-NEXT: store i8* %[[AP_VAL]], i8** %[[AP2:.*]]
+  // WIN64: %[[AP_VAL:.*]] = load i8*, i8** %[[AP]]
+  // WIN64-NEXT: store i8* %[[AP_VAL]], i8** %[[AP2:.*]]
+  __builtin_ms_va_end(ap);
+  // LINUX: call void @llvm.va_end
+  // WIN64: call void @llvm.va_end
+}
+
+// Let's verify that normal va_lists work right on Win64, too.
+void f5(int a, ...) {
+  // WIN64-LABEL: define void @f5
+  __builtin_va_list ap;
+  __builtin_va_start(ap, a);
+  // WIN64: %[[AP:.*]] = alloca i8*
+  // WIN64: call void @llvm.va_start
+  int b = __builtin_va_arg(ap, int);
+  // WIN64: %[[AP_CUR:.*]] = load i8*, i8** %[[AP]]
+  // WIN64-NEXT: %[[AP_NEXT:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR]], i64 8
+  // WIN64-NEXT: store i8* %[[AP_NEXT]], i8** %[[AP]]
+  // WIN64-NEXT: bitcast i8* %[[AP_CUR]] to i32*
+  __builtin_va_list ap2;
+  __builtin_va_copy(ap2, ap);
+  // WIN64: call void @llvm.va_copy
+  __builtin_va_end(ap);
+  // WIN64: call void @llvm.va_end
+}

clang/test/Sema/varargs-aarch64.c

@@ -0,0 +1,11 @@
+// RUN: %clang_cc1 -fsyntax-only -verify %s -triple aarch64-linux-gnu
+
+void f1(int a, ...) {
+  __builtin_ms_va_list ap;
+  __builtin_ms_va_start(ap, a); // expected-error {{'__builtin_ms_va_start' used in System V ABI function}}
+}
+
+void __attribute__((ms_abi)) f2(int a, ...) {
+  __builtin_va_list ap;
+  __builtin_va_start(ap, a); // expected-error {{'va_start' used in Win64 ABI function}}
+}

clang/test/Sema/varargs-x86-32.c

@@ -1,5 +1,5 @@
 // RUN: %clang_cc1 -fsyntax-only -verify %s -triple i386-apple-darwin9
 
 void foo(int a, ...) {
-  __builtin_ms_va_start((void *)0, a); // expected-error {{this builtin is only available on x86-64 targets}}
+  __builtin_ms_va_start((void *)0, a); // expected-error {{this builtin is only available on x86-64 and aarch64 targets}}
 }

clang/tools/libclang/CXType.cpp

@@ -611,7 +611,7 @@ CXCallingConv clang_getFunctionTypeCallingConv(CXType X) {
       TCALLINGCONV(X86Pascal);
       TCALLINGCONV(X86RegCall);
       TCALLINGCONV(X86VectorCall);
-      TCALLINGCONV(X86_64Win64);
+      TCALLINGCONV(Win64);
       TCALLINGCONV(X86_64SysV);
       TCALLINGCONV(AAPCS);
       TCALLINGCONV(AAPCS_VFP);