[ARM] Fix bug 39982 - pcs("aapcs-vfp") is not consistent

Correctly handle homogeneous aggregates when a
function's ABI is specified via the pcs attribute.

Bug: https://bugs.llvm.org/show_bug.cgi?id=39982
Differential Revision: https://reviews.llvm.org/D59094

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@356776 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/TargetInfo.cpp

@@ -5597,8 +5597,10 @@ public:
   ABIKind getABIKind() const { return Kind; }
 
 private:
-  ABIArgInfo classifyReturnType(QualType RetTy, bool isVariadic) const;
-  ABIArgInfo classifyArgumentType(QualType RetTy, bool isVariadic) const;
+  ABIArgInfo classifyReturnType(QualType RetTy, bool isVariadic,
+                                unsigned functionCallConv) const;
+  ABIArgInfo classifyArgumentType(QualType RetTy, bool isVariadic,
+                                  unsigned functionCallConv) const;
   ABIArgInfo classifyHomogeneousAggregate(QualType Ty, const Type *Base,
                                           uint64_t Members) const;
   ABIArgInfo coerceIllegalVector(QualType Ty) const;
@@ -5608,6 +5610,8 @@ private:
   bool isHomogeneousAggregateSmallEnough(const Type *Ty,
                                          uint64_t Members) const override;
 
+  bool isEffectivelyAAPCS_VFP(unsigned callConvention, bool acceptHalf) const;
+
   void computeInfo(CGFunctionInfo &FI) const override;
 
   Address EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
@@ -5728,11 +5732,13 @@ void WindowsARMTargetCodeGenInfo::setTargetAttributes(
 
 void ARMABIInfo::computeInfo(CGFunctionInfo &FI) const {
   if (!::classifyReturnType(getCXXABI(), FI, *this))
-    FI.getReturnInfo() =
-        classifyReturnType(FI.getReturnType(), FI.isVariadic());
+    FI.getReturnInfo() = classifyReturnType(FI.getReturnType(), FI.isVariadic(),
+                                            FI.getCallingConvention());
 
   for (auto &I : FI.arguments())
-    I.info = classifyArgumentType(I.type, FI.isVariadic());
+    I.info = classifyArgumentType(I.type, FI.isVariadic(),
+                                  FI.getCallingConvention());
+
 
   // Always honor user-specified calling convention.
   if (FI.getCallingConvention() != llvm::CallingConv::C)
@@ -5811,8 +5817,8 @@ ABIArgInfo ARMABIInfo::classifyHomogeneousAggregate(QualType Ty,
   return ABIArgInfo::getDirect(nullptr, 0, nullptr, false);
 }
 
-ABIArgInfo ARMABIInfo::classifyArgumentType(QualType Ty,
-                                            bool isVariadic) const {
+ABIArgInfo ARMABIInfo::classifyArgumentType(QualType Ty, bool isVariadic,
+                                            unsigned functionCallConv) const {
   // 6.1.2.1 The following argument types are VFP CPRCs:
   //   A single-precision floating-point type (including promoted
   //   half-precision types); A double-precision floating-point type;
@@ -5820,7 +5826,9 @@ ABIArgInfo ARMABIInfo::classifyArgumentType(QualType Ty,
   //   with a Base Type of a single- or double-precision floating-point type,
   //   64-bit containerized vectors or 128-bit containerized vectors with one
   //   to four Elements.
-  bool IsEffectivelyAAPCS_VFP = getABIKind() == AAPCS_VFP && !isVariadic;
+  // Variadic functions should always marshal to the base standard.
+  bool IsAAPCS_VFP =
+      !isVariadic && isEffectivelyAAPCS_VFP(functionCallConv, /* AAPCS16 */ false);
 
   Ty = useFirstFieldIfTransparentUnion(Ty);
 
@@ -5833,7 +5841,7 @@ ABIArgInfo ARMABIInfo::classifyArgumentType(QualType Ty,
   // half type natively, and does not need to interwork with AAPCS code.
   if ((Ty->isFloat16Type() || Ty->isHalfType()) &&
       !getContext().getLangOpts().NativeHalfArgsAndReturns) {
-    llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
+    llvm::Type *ResType = IsAAPCS_VFP ?
       llvm::Type::getFloatTy(getVMContext()) :
       llvm::Type::getInt32Ty(getVMContext());
     return ABIArgInfo::getDirect(ResType);
@@ -5857,7 +5865,7 @@ ABIArgInfo ARMABIInfo::classifyArgumentType(QualType Ty,
   if (isEmptyRecord(getContext(), Ty, true))
     return ABIArgInfo::getIgnore();
 
-  if (IsEffectivelyAAPCS_VFP) {
+  if (IsAAPCS_VFP) {
     // Homogeneous Aggregates need to be expanded when we can fit the aggregate
     // into VFP registers.
     const Type *Base = nullptr;
@@ -6014,10 +6022,12 @@ static bool isIntegerLikeType(QualType Ty, ASTContext &Context,
   return true;
 }
 
-ABIArgInfo ARMABIInfo::classifyReturnType(QualType RetTy,
-                                          bool isVariadic) const {
-  bool IsEffectivelyAAPCS_VFP =
-      (getABIKind() == AAPCS_VFP || getABIKind() == AAPCS16_VFP) && !isVariadic;
+ABIArgInfo ARMABIInfo::classifyReturnType(QualType RetTy, bool isVariadic,
+                                          unsigned functionCallConv) const {
+
+  // Variadic functions should always marshal to the base standard.
+  bool IsAAPCS_VFP =
+      !isVariadic && isEffectivelyAAPCS_VFP(functionCallConv, /* AAPCS16 */ true);
 
   if (RetTy->isVoidType())
     return ABIArgInfo::getIgnore();
@@ -6038,7 +6048,7 @@ ABIArgInfo ARMABIInfo::classifyReturnType(QualType RetTy,
   // half type natively, and does not need to interwork with AAPCS code.
   if ((RetTy->isFloat16Type() || RetTy->isHalfType()) &&
       !getContext().getLangOpts().NativeHalfArgsAndReturns) {
-    llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
+    llvm::Type *ResType = IsAAPCS_VFP ?
       llvm::Type::getFloatTy(getVMContext()) :
       llvm::Type::getInt32Ty(getVMContext());
     return ABIArgInfo::getDirect(ResType);
@@ -6087,7 +6097,7 @@ ABIArgInfo ARMABIInfo::classifyReturnType(QualType RetTy,
     return ABIArgInfo::getIgnore();
 
   // Check for homogeneous aggregates with AAPCS-VFP.
-  if (IsEffectivelyAAPCS_VFP) {
+  if (IsAAPCS_VFP) {
     const Type *Base = nullptr;
     uint64_t Members = 0;
     if (isHomogeneousAggregate(RetTy, Base, Members))
@@ -6192,6 +6202,16 @@ bool ARMABIInfo::isHomogeneousAggregateSmallEnough(const Type *Base,
   return Members <= 4;
 }
 
+bool ARMABIInfo::isEffectivelyAAPCS_VFP(unsigned callConvention,
+                                        bool acceptHalf) const {
+  // Give precedence to user-specified calling conventions.
+  if (callConvention != llvm::CallingConv::C)
+    return (callConvention == llvm::CallingConv::ARM_AAPCS_VFP);
+  else
+    return (getABIKind() == AAPCS_VFP) ||
+           (acceptHalf && (getABIKind() == AAPCS16_VFP));
+}
+
 Address ARMABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
                               QualType Ty) const {
   CharUnits SlotSize = CharUnits::fromQuantity(4);

test/CodeGenCXX/arm-pcs.cpp

@@ -0,0 +1,51 @@
+// Covers a bug fix for ABI selection with homogenous aggregates:
+//  See: https://bugs.llvm.org/show_bug.cgi?id=39982
+
+// REQUIRES: arm-registered-target
+// RUN: %clang -mfloat-abi=hard --target=armv7-unknown-linux-gnueabi -O3 -S -o - %s | FileCheck %s -check-prefixes=HARD,CHECK
+// RUN: %clang -mfloat-abi=softfp --target=armv7-unknown-linux-gnueabi -O3 -S -o - %s | FileCheck %s -check-prefixes=SOFTFP,CHECK
+// RUN: %clang -mfloat-abi=soft --target=armv7-unknown-linux-gnueabi -O3 -S -o - %s | FileCheck %s -check-prefixes=SOFT,CHECK
+
+struct S {
+  float f;
+  float d;
+  float c;
+  float t;
+};
+
+// Variadic functions should always marshal for the base standard.
+// See section 5.5 (Parameter Passing) of the AAPCS.
+float __attribute__((pcs("aapcs-vfp"))) variadic(S s, ...) {
+  // CHECK-NOT: vmov s{{[0-9]+}}, s{{[0-9]+}}
+  // CHECK: mov r{{[0-9]+}}, r{{[0-9]+}}
+  return s.d;
+}
+
+float no_attribute(S s) {
+  // SOFT: mov r{{[0-9]+}}, r{{[0-9]+}}
+  // SOFTFP: mov r{{[0-9]+}}, r{{[0-9]+}}
+  // HARD: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  return s.d;
+}
+
+float __attribute__((pcs("aapcs-vfp"))) baz(float x, float y) {
+  // CHECK-NOT: mov s{{[0-9]+}}, r{{[0-9]+}}
+  // SOFT: mov r{{[0-9]+}}, r{{[0-9]+}}
+  // SOFTFP: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  // HARD: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  return y;
+}
+
+float __attribute__((pcs("aapcs-vfp"))) foo(S s) {
+  // CHECK-NOT: mov s{{[0-9]+}}, r{{[0-9]+}}
+  // SOFT: mov r{{[0-9]+}}, r{{[0-9]+}}
+  // SOFTFP: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  // HARD: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  return s.d;
+}
+
+float __attribute__((pcs("aapcs"))) bar(S s) {
+  // CHECK-NOT: vmov.f32 s{{[0-9]+}}, s{{[0-9]+}}
+  // CHECK: mov r{{[0-9]+}}, r{{[0-9]+}}
+  return s.d;
+}