[clang] Apply MS ABI details on __builtin_ms_va_list on non-windows platforms on x86_64

[mstorsjo]

Summary

This fixes inconsistencies in the ms_abi.c testcase.

Also add a couple cases of missing double pointers in the windows part
of the testcase; the outcome of building that testcase on windows hasn't
changed, but the previous form of the test was imprecise (checking
for "%[[STRUCT_FOO]]*" when clang actually generates "%[[STRUCT_FOO]]**"),
which still used to match.

Ideally this would share code with the native Windows case, but
X86_64ABIInfo and WinX86_64ABIInfo aren't superclasses/subclasses of
each other so it's impractical, and the code to share currently only
consists of a couple lines.

[rnk]

lgtm

clang/lib/CodeGen/TargetInfo.cpp

Address X86_64ABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
   CGF.EmitBlock(ContBlock);
   Address ResAddr = emitMergePHI(CGF, RegAddr, InRegBlock, MemAddr, InMemBlock,
                                  "vaarg.addr");
   return ResAddr;
 }
 
 Address X86_64ABIInfo::EmitMSVAArg(CodeGenFunction &CGF, Address VAListAddr,
                                    QualType Ty) const {
-  return emitVoidPtrVAArg(CGF, VAListAddr, Ty, /*indirect*/ false,
+  // MS x64 ABI requirement: "Any argument that doesn't fit in 8 bytes, or is
+  // not 1, 2, 4, or 8 bytes, must be passed by reference."
+  uint64_t Width = getContext().getTypeSize(Ty);
+  bool IsIndirect = Width > 64 || !llvm::isPowerOf2_64(Width);
+
+  return emitVoidPtrVAArg(CGF, VAListAddr, Ty, IsIndirect,
                           CGF.getContext().getTypeInfoInChars(Ty),
                           CharUnits::fromQuantity(8),
                           /*allowHigherAlign*/ false);
 }
 
 ABIArgInfo WinX86_64ABIInfo::reclassifyHvaArgForVectorCall(
     QualType Ty, unsigned &FreeSSERegs, const ABIArgInfo &current) const {
   const Type *Base = nullptr;

clang/test/CodeGen/ms_abi.c

void __attribute__((ms_abi)) f4(int a, ...) {
   // FREEBSD: %[[AP_CUR:.*]] = load i8*, i8** %[[AP]]
   // FREEBSD-NEXT: %[[AP_NEXT:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR]], i64 8
   // FREEBSD-NEXT: store i8* %[[AP_NEXT]], i8** %[[AP]]
   // FREEBSD-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*
-  // FIXME: These are different now. We probably need __builtin_ms_va_arg.
   double _Complex c = __builtin_va_arg(ap, double _Complex);
   // FREEBSD: %[[AP_CUR2:.*]] = load i8*, i8** %[[AP]]
-  // FREEBSD-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 16
+  // FREEBSD-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 8
   // FREEBSD-NEXT: store i8* %[[AP_NEXT2]], i8** %[[AP]]
-  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR2]] to { double, double }*
+  // FREEBSD-NEXT: %[[CUR2:.*]] = bitcast i8* %[[AP_CUR2]] to { double, double }**
+  // FREEBSD-NEXT: load { double, double }*, { double, double }** %[[CUR2]]
   // WIN64: %[[AP_CUR2:.*]] = load i8*, i8** %[[AP]]
   // WIN64-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 8
   // WIN64-NEXT: store i8* %[[AP_NEXT2]], i8** %[[AP]]
   // WIN64-NEXT: %[[CUR2:.*]] = bitcast i8* %[[AP_CUR2]] to { double, double }**
   // WIN64-NEXT: load { double, double }*, { double, double }** %[[CUR2]]
   struct foo d = __builtin_va_arg(ap, struct foo);
   // FREEBSD: %[[AP_CUR3:.*]] = load i8*, i8** %[[AP]]
-  // FREEBSD-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 16
+  // FREEBSD-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 8
   // FREEBSD-NEXT: store i8* %[[AP_NEXT3]], i8** %[[AP]]
-  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]*
+  // FREEBSD-NEXT: %[[CUR3:.*]] = bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]*
+  // FREEBSD-NEXT: load %[[STRUCT_FOO]]*, %[[STRUCT_FOO]]** %[[CUR3]]
   // WIN64: %[[AP_CUR3:.*]] = load i8*, i8** %[[AP]]
   // WIN64-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 8
   // WIN64-NEXT: store i8* %[[AP_NEXT3]], i8** %[[AP]]
   // WIN64-NEXT: %[[CUR3:.*]] = bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]*
   // WIN64-NEXT: load %[[STRUCT_FOO]]*, %[[STRUCT_FOO]]** %[[CUR3]]
   __builtin_ms_va_list ap2;
   __builtin_ms_va_copy(ap2, ap);
   // FREEBSD: %[[AP_VAL:.*]] = load i8*, i8** %[[AP]]
void __attribute__((sysv_abi)) f6(__builtin_ms_va_list ap) {
   // FREEBSD-NEXT: store i8* %[[AP_NEXT]], i8** %[[AP]]
   // FREEBSD-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*
   double _Complex c = __builtin_va_arg(ap, double _Complex);
   // FREEBSD: %[[AP_CUR2:.*]] = load i8*, i8** %[[AP]]
-  // FREEBSD-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 16
+  // FREEBSD-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 8
   // FREEBSD-NEXT: store i8* %[[AP_NEXT2]], i8** %[[AP]]
-  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR2]] to { double, double }*
+  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR2]] to { double, double }**
   // WIN64: %[[AP_CUR2:.*]] = load i8*, i8** %[[AP]]
   // WIN64-NEXT: %[[AP_NEXT2:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR2]], i64 8
   // WIN64-NEXT: store i8* %[[AP_NEXT2]], i8** %[[AP]]
-  // WIN64-NEXT: bitcast i8* %[[AP_CUR2]] to { double, double }*
+  // WIN64-NEXT: bitcast i8* %[[AP_CUR2]] to { double, double }**
   struct foo d = __builtin_va_arg(ap, struct foo);
   // FREEBSD: %[[AP_CUR3:.*]] = load i8*, i8** %[[AP]]
-  // FREEBSD-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 16
+  // FREEBSD-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 8
   // FREEBSD-NEXT: store i8* %[[AP_NEXT3]], i8** %[[AP]]
-  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]*
+  // FREEBSD-NEXT: bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]**
   // WIN64: %[[AP_CUR3:.*]] = load i8*, i8** %[[AP]]
   // WIN64-NEXT: %[[AP_NEXT3:.*]] = getelementptr inbounds i8, i8* %[[AP_CUR3]], i64 8
   // WIN64-NEXT: store i8* %[[AP_NEXT3]], i8** %[[AP]]
-  // WIN64-NEXT: bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]*
+  // WIN64-NEXT: bitcast i8* %[[AP_CUR3]] to %[[STRUCT_FOO]]**
   __builtin_ms_va_list ap2;
   __builtin_ms_va_copy(ap2, ap);
   // FREEBSD: %[[AP_VAL:.*]] = load i8*, i8** %[[AP]]
   // FREEBSD-NEXT: store i8* %[[AP_VAL]], i8** %[[AP2:.*]]
   // WIN64: %[[AP_VAL:.*]] = load i8*, i8** %[[AP]]
   // WIN64-NEXT: store i8* %[[AP_VAL]], i8** %[[AP2:.*]]
 }