[AArch64] Fix generated types for ARM64EC variadic entry thunk targets (llvm#80595)

ISel handles filling in x4/x5 when calling variadic functions as they
don't correspond to the 5th/6th X64 arguments but rather to the end of
the shadow space on the stack and the size in bytes of all stack
parameters (ignored and written as 0 for calls from entry thunks).

Will PR a follow up with ISel handling after this is merged.

Author: bylaws

llvm/lib/Target/AArch64/AArch64Arm64ECCallLowering.cpp

@@ -43,6 +43,8 @@ static cl::opt<bool> GenerateThunks("arm64ec-generate-thunks", cl::Hidden,
 
 namespace {
 
+enum class ThunkType { GuestExit, Entry, Exit };
+
 class AArch64Arm64ECCallLowering : public ModulePass {
 public:
   static char ID;
@@ -69,14 +71,14 @@ class AArch64Arm64ECCallLowering : public ModulePass {
   Type *I64Ty;
   Type *VoidTy;
 
-  void getThunkType(FunctionType *FT, AttributeList AttrList, bool EntryThunk,
+  void getThunkType(FunctionType *FT, AttributeList AttrList, ThunkType TT,
                     raw_ostream &Out, FunctionType *&Arm64Ty,
                     FunctionType *&X64Ty);
   void getThunkRetType(FunctionType *FT, AttributeList AttrList,
                        raw_ostream &Out, Type *&Arm64RetTy, Type *&X64RetTy,
                        SmallVectorImpl<Type *> &Arm64ArgTypes,
                        SmallVectorImpl<Type *> &X64ArgTypes, bool &HasSretPtr);
-  void getThunkArgTypes(FunctionType *FT, AttributeList AttrList,
+  void getThunkArgTypes(FunctionType *FT, AttributeList AttrList, ThunkType TT,
                         raw_ostream &Out,
                         SmallVectorImpl<Type *> &Arm64ArgTypes,
                         SmallVectorImpl<Type *> &X64ArgTypes, bool HasSretPtr);
@@ -89,10 +91,11 @@ class AArch64Arm64ECCallLowering : public ModulePass {
 
 void AArch64Arm64ECCallLowering::getThunkType(FunctionType *FT,
                                               AttributeList AttrList,
-                                              bool EntryThunk, raw_ostream &Out,
+                                              ThunkType TT, raw_ostream &Out,
                                               FunctionType *&Arm64Ty,
                                               FunctionType *&X64Ty) {
-  Out << (EntryThunk ? "$ientry_thunk$cdecl$" : "$iexit_thunk$cdecl$");
+  Out << (TT == ThunkType::Entry ? "$ientry_thunk$cdecl$"
+                                 : "$iexit_thunk$cdecl$");
 
   Type *Arm64RetTy;
   Type *X64RetTy;
@@ -102,23 +105,25 @@ void AArch64Arm64ECCallLowering::getThunkType(FunctionType *FT,
 
   // The first argument to a thunk is the called function, stored in x9.
   // For exit thunks, we pass the called function down to the emulator;
-  // for entry thunks, we just call the Arm64 function directly.
-  if (!EntryThunk)
+  // for entry/guest exit thunks, we just call the Arm64 function directly.
+  if (TT == ThunkType::Exit)
     Arm64ArgTypes.push_back(PtrTy);
   X64ArgTypes.push_back(PtrTy);
 
   bool HasSretPtr = false;
   getThunkRetType(FT, AttrList, Out, Arm64RetTy, X64RetTy, Arm64ArgTypes,
                   X64ArgTypes, HasSretPtr);
 
-  getThunkArgTypes(FT, AttrList, Out, Arm64ArgTypes, X64ArgTypes, HasSretPtr);
+  getThunkArgTypes(FT, AttrList, TT, Out, Arm64ArgTypes, X64ArgTypes,
+                   HasSretPtr);
 
-  Arm64Ty = FunctionType::get(Arm64RetTy, Arm64ArgTypes, false);
+  Arm64Ty = FunctionType::get(Arm64RetTy, Arm64ArgTypes,
+                              TT == ThunkType::Entry && FT->isVarArg());
   X64Ty = FunctionType::get(X64RetTy, X64ArgTypes, false);
 }
 
 void AArch64Arm64ECCallLowering::getThunkArgTypes(
-    FunctionType *FT, AttributeList AttrList, raw_ostream &Out,
+    FunctionType *FT, AttributeList AttrList, ThunkType TT, raw_ostream &Out,
     SmallVectorImpl<Type *> &Arm64ArgTypes,
     SmallVectorImpl<Type *> &X64ArgTypes, bool HasSretPtr) {
 
@@ -151,14 +156,16 @@ void AArch64Arm64ECCallLowering::getThunkArgTypes(
       X64ArgTypes.push_back(I64Ty);
     }
 
-    // x4
-    Arm64ArgTypes.push_back(PtrTy);
-    X64ArgTypes.push_back(PtrTy);
-    // x5
-    Arm64ArgTypes.push_back(I64Ty);
-    // FIXME: x5 isn't actually passed/used by the x64 side; revisit once we
-    // have proper isel for varargs
-    X64ArgTypes.push_back(I64Ty);
+    if (TT != ThunkType::Entry) {
+      // x4
+      Arm64ArgTypes.push_back(PtrTy);
+      X64ArgTypes.push_back(PtrTy);
+      // x5
+      Arm64ArgTypes.push_back(I64Ty);
+      // FIXME: x5 isn't actually passed/used by the x64 side; revisit once we
+      // have proper isel for varargs
+      X64ArgTypes.push_back(I64Ty);
+    }
     return;
   }
 
@@ -339,8 +346,7 @@ Function *AArch64Arm64ECCallLowering::buildExitThunk(FunctionType *FT,
   SmallString<256> ExitThunkName;
   llvm::raw_svector_ostream ExitThunkStream(ExitThunkName);
   FunctionType *Arm64Ty, *X64Ty;
-  getThunkType(FT, Attrs, /*EntryThunk*/ false, ExitThunkStream, Arm64Ty,
-               X64Ty);
+  getThunkType(FT, Attrs, ThunkType::Exit, ExitThunkStream, Arm64Ty, X64Ty);
   if (Function *F = M->getFunction(ExitThunkName))
     return F;
 
@@ -443,7 +449,7 @@ Function *AArch64Arm64ECCallLowering::buildEntryThunk(Function *F) {
   SmallString<256> EntryThunkName;
   llvm::raw_svector_ostream EntryThunkStream(EntryThunkName);
   FunctionType *Arm64Ty, *X64Ty;
-  getThunkType(F->getFunctionType(), F->getAttributes(), /*EntryThunk*/ true,
+  getThunkType(F->getFunctionType(), F->getAttributes(), ThunkType::Entry,
                EntryThunkStream, Arm64Ty, X64Ty);
   if (Function *F = M->getFunction(EntryThunkName))
     return F;
@@ -518,7 +524,7 @@ Function *AArch64Arm64ECCallLowering::buildEntryThunk(Function *F) {
 Function *AArch64Arm64ECCallLowering::buildGuestExitThunk(Function *F) {
   llvm::raw_null_ostream NullThunkName;
   FunctionType *Arm64Ty, *X64Ty;
-  getThunkType(F->getFunctionType(), F->getAttributes(), /*EntryThunk*/ true,
+  getThunkType(F->getFunctionType(), F->getAttributes(), ThunkType::GuestExit,
                NullThunkName, Arm64Ty, X64Ty);
   auto MangledName = getArm64ECMangledFunctionName(F->getName().str());
   assert(MangledName && "Can't guest exit to function that's already native");

llvm/test/CodeGen/AArch64/arm64ec-entry-thunks.ll

@@ -147,8 +147,8 @@ define void @has_varargs(...) nounwind {
 ; CHECK-NEXT:     add     x29, sp, #160
 ; CHECK-NEXT:     .seh_add_fp     160
 ; CHECK-NEXT:     .seh_endprologue
-; CHECK-NEXT:     ldp     x8, x5, [x4, #32]
-; CHECK-NEXT:     mov     x4, x8
+; CHECK-NEXT:     mov     x4, sp
+; CHECK-NEXT:     mov     x5, xzr
 ; CHECK-NEXT:     blr     x9
 ; CHECK-NEXT:     adrp    x8, __os_arm64x_dispatch_ret
 ; CHECK-NEXT:     ldr     x0, [x8, :lo12:__os_arm64x_dispatch_ret]