Updated the signature for some stack related intrinsics (CLANG)

[cdevadas]

Summary

This patch includes the intrinsics
int_addressofreturnaddress,
int_frameaddress & int_sponentry.
This patch should go along with the
changes in https://reviews.llvm.org/D64561

[cdevadas]

Added alloca address space.

[arsenm]

Can you add AMDGPU tests for these showing the correct address space is used

[cdevadas]

updated test/CodeGenOpenCL/builtins-generic-amdgcn.cl to vaildate the address space.

[arsenm]

LGTM

lib/CodeGen/CGBuiltin.cpp

if (SJKind == MSVCSetJmpKind::_setjmp3) {
     Name = "_setjmp3";
     Arg1Ty = CGF.Int32Ty;
     Arg1 = llvm::ConstantInt::get(CGF.IntTy, 0);
     IsVarArg = true;
   } else {
     Name = SJKind == MSVCSetJmpKind::_setjmp ? "_setjmp" : "_setjmpex";
     Arg1Ty = CGF.Int8PtrTy;
     if (CGF.getTarget().getTriple().getArch() == llvm::Triple::aarch64) {
-      Arg1 = CGF.Builder.CreateCall(CGF.CGM.getIntrinsic(Intrinsic::sponentry));
+      Arg1 = CGF.Builder.CreateCall(
+          CGF.CGM.getIntrinsic(Intrinsic::sponentry, CGF.AllocaInt8PtrTy));
     } else
-      Arg1 = CGF.Builder.CreateCall(CGF.CGM.getIntrinsic(Intrinsic::frameaddress),
-                                    llvm::ConstantInt::get(CGF.Int32Ty, 0));
+      Arg1 = CGF.Builder.CreateCall(
+          CGF.CGM.getIntrinsic(Intrinsic::frameaddress, CGF.AllocaInt8PtrTy),
   }
 
   // Mark the call site and declaration with ReturnsTwice.
   llvm::Type *ArgTypes[2] = {CGF.Int8PtrTy, Arg1Ty};
   llvm::AttributeList ReturnsTwiceAttr = llvm::AttributeList::get(
       CGF.getLLVMContext(), llvm::AttributeList::FunctionIndex,
       llvm::Attribute::ReturnsTwice);
   llvm::FunctionCallee SetJmpFn = CGF.CGM.CreateRuntimeFunction(

   }
   case Builtin::BI_ReturnAddress: {
     Function *F = CGM.getIntrinsic(Intrinsic::returnaddress);
     return RValue::get(Builder.CreateCall(F, Builder.getInt32(0)));
   }
   case Builtin::BI__builtin_frame_address: {
     Value *Depth = ConstantEmitter(*this).emitAbstract(E->getArg(0),
                                                    getContext().UnsignedIntTy);
-    Function *F = CGM.getIntrinsic(Intrinsic::frameaddress);
+    Function *F = CGM.getIntrinsic(Intrinsic::frameaddress, AllocaInt8PtrTy);
     return RValue::get(Builder.CreateCall(F, Depth));
   }
   case Builtin::BI__builtin_extract_return_addr: {
     Value *Address = EmitScalarExpr(E->getArg(0));
     Value *Result = getTargetHooks().decodeReturnAddress(*this, Address);
     return RValue::get(Result);
   }
   case Builtin::BI__builtin_frob_return_addr: {
case Builtin::BI__builtin_extend_pointer: {
     else
       return RValue::get(Builder.CreateZExt(Result, Int64Ty, "extend.zext"));
   }
   case Builtin::BI__builtin_setjmp: {
     // Buffer is a void**.
     Address Buf = EmitPointerWithAlignment(E->getArg(0));
 
     // Store the frame pointer to the setjmp buffer.
-    Value *FrameAddr =
-      Builder.CreateCall(CGM.getIntrinsic(Intrinsic::frameaddress),
-                         ConstantInt::get(Int32Ty, 0));
+    Value *FrameAddr = Builder.CreateCall(
+        CGM.getIntrinsic(Intrinsic::frameaddress, AllocaInt8PtrTy),
     Builder.CreateStore(FrameAddr, Buf);
 
     // Store the stack pointer to the setjmp buffer.
     Value *StackAddr =
         Builder.CreateCall(CGM.getIntrinsic(Intrinsic::stacksave));
     Address StackSaveSlot = Builder.CreateConstInBoundsGEP(Buf, 2);
     Builder.CreateStore(StackAddr, StackSaveSlot);
 
if (BuiltinID == AArch64::BI_ReadStatusReg ||
 
     llvm::Function *F = CGM.getIntrinsic(llvm::Intrinsic::write_register, Types);
     llvm::Value *ArgValue = EmitScalarExpr(E->getArg(1));
 
     return Builder.CreateCall(F, { Metadata, ArgValue });
   }
 
   if (BuiltinID == AArch64::BI_AddressOfReturnAddress) {
-    llvm::Function *F = CGM.getIntrinsic(Intrinsic::addressofreturnaddress);
+    llvm::Function *F =
+        CGM.getIntrinsic(Intrinsic::addressofreturnaddress, AllocaInt8PtrTy);
     return Builder.CreateCall(F);
   }
 
   if (BuiltinID == AArch64::BI__builtin_sponentry) {
-    llvm::Function *F = CGM.getIntrinsic(Intrinsic::sponentry);
+    llvm::Function *F = CGM.getIntrinsic(Intrinsic::sponentry, AllocaInt8PtrTy);
     return Builder.CreateCall(F);
   }
 
   // Find out if any arguments are required to be integer constant
   // expressions.
   unsigned ICEArguments = 0;
   ASTContext::GetBuiltinTypeError Error;
   getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
case X86::BI_InterlockedCompareExchange128: {
     Builder.CreateStore(Builder.CreateExtractValue(CXI, 0), ComparandResult);
 
     // Get the success boolean and zero extend it to i8.
     Value *Success = Builder.CreateExtractValue(CXI, 1);
     return Builder.CreateZExt(Success, ConvertType(E->getType()));
   }
 
   case X86::BI_AddressOfReturnAddress: {
-    Function *F = CGM.getIntrinsic(Intrinsic::addressofreturnaddress);
+    Function *F =
+        CGM.getIntrinsic(Intrinsic::addressofreturnaddress, AllocaInt8PtrTy);
     return Builder.CreateCall(F);
   }
   case X86::BI__stosb: {
     // We treat __stosb as a volatile memset - it may not generate "rep stosb"
     // instruction, but it will create a memset that won't be optimized away.
     return Builder.CreateMemSet(Ops[0], Ops[1], Ops[2], 1, true);
   }
   case X86::BI__ud2:

lib/CodeGen/CGException.cpp

void CodeGenFunction::EmitCapturedLocals(CodeGenFunction &ParentCGF,
 
   llvm::Value *EntryFP = nullptr;
   CGBuilderTy Builder(CGM, AllocaInsertPt);
   if (IsFilter && CGM.getTarget().getTriple().getArch() == llvm::Triple::x86) {
     // 32-bit SEH filters need to be careful about FP recovery.  The end of the
     // EH registration is passed in as the EBP physical register.  We can
     // recover that with llvm.frameaddress(1).
     EntryFP = Builder.CreateCall(
-        CGM.getIntrinsic(llvm::Intrinsic::frameaddress), {Builder.getInt32(1)});
+        CGM.getIntrinsic(llvm::Intrinsic::frameaddress, AllocaInt8PtrTy),
+        {Builder.getInt32(1)});
   } else {
     // Otherwise, for x64 and 32-bit finally functions, the parent FP is the
     // second parameter.
     auto AI = CurFn->arg_begin();
     ++AI;
     EntryFP = &*AI;
   }
 

test/CodeGen/builtin-sponentry.c

 // RUN: %clang_cc1 -triple aarch64-windows-gnu -Oz -emit-llvm %s -o - | FileCheck %s
 
 void *test_sponentry() {
   return __builtin_sponentry();
 }
 // CHECK-LABEL: define dso_local i8* @test_sponentry()
-// CHECK: = tail call i8* @llvm.sponentry()
+// CHECK: = tail call i8* @llvm.sponentry.p0i8()
 // CHECK: ret i8*

test/CodeGen/exceptions-seh.c

 // CHECK: store i32 -42, i32* %[[success:[^ ]*]]
 //
 // CHECK: %[[res:[^ ]*]] = load i32, i32* %[[success]]
 // CHECK: ret i32 %[[res]]
 
 // 32-bit SEH needs this filter to save the exception code.
 //
 // X86-LABEL: define internal i32 @"?filt$0@0@safe_div@@"()
-// X86: %[[ebp:[^ ]*]] = call i8* @llvm.frameaddress(i32 1)
+// X86: %[[ebp:[^ ]*]] = call i8* @llvm.frameaddress.p0i8(i32 1)
 // X86: %[[fp:[^ ]*]] = call i8* @llvm.eh.recoverfp(i8* bitcast (i32 (i32, i32, i32*)* @safe_div to i8*), i8* %[[ebp]])
 // X86: call i8* @llvm.localrecover(i8* bitcast (i32 (i32, i32, i32*)* @safe_div to i8*), i8* %[[fp]], i32 0)
 // X86: load i8*, i8**
 // X86: load i32*, i32**
 // X86: load i32, i32*
 // X86: store i32 %{{.*}}, i32*
 // X86: ret i32 1
 

 // X64: %[[fp:[^ ]*]] = call i8* @llvm.eh.recoverfp(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %frame_pointer)
 // X64: call i8* @llvm.localrecover(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %[[fp]], i32 0)
 //
 // ARM64-LABEL: define internal i32 @"?filt$0@0@filter_expr_capture@@"(i8* %exception_pointers, i8* %frame_pointer)
 // ARM64: %[[fp:[^ ]*]] = call i8* @llvm.eh.recoverfp(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %frame_pointer)
 // ARM64: call i8* @llvm.localrecover(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %[[fp]], i32 0)
 //
 // X86-LABEL: define internal i32 @"?filt$0@0@filter_expr_capture@@"()
-// X86: %[[ebp:[^ ]*]] = call i8* @llvm.frameaddress(i32 1)
+// X86: %[[ebp:[^ ]*]] = call i8* @llvm.frameaddress.p0i8(i32 1)
 // X86: %[[fp:[^ ]*]] = call i8* @llvm.eh.recoverfp(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %[[ebp]])
 // X86: call i8* @llvm.localrecover(i8* bitcast (i32 ()* @filter_expr_capture to i8*), i8* %[[fp]], i32 0)
 //
 // CHECK: store i32 -1, i32* %{{.*}}
 // CHECK: ret i32 -1
 
 int nested_try(void) {
   int r = 42;

test/CodeGen/integer-overflow.c

void test1() {
   // DEFAULT: add i16 {{.*}}, -1
   // WRAPV: add i16 {{.*}}, -1
   // TRAPV: add i16 {{.*}}, -1
   // CATCH_UB: add i16 {{.*}}, -1
   --PR9350_short_dec;
 
   // PR24256: don't instrument __builtin_frame_address.
   __builtin_frame_address(0 + 0);
-  // DEFAULT:  call i8* @llvm.frameaddress(i32 0)
-  // WRAPV:    call i8* @llvm.frameaddress(i32 0)
-  // TRAPV:    call i8* @llvm.frameaddress(i32 0)
-  // CATCH_UB: call i8* @llvm.frameaddress(i32 0)
+  // DEFAULT:  call i8* @llvm.frameaddress.p0i8(i32 0)
+  // WRAPV:    call i8* @llvm.frameaddress.p0i8(i32 0)
+  // TRAPV:    call i8* @llvm.frameaddress.p0i8(i32 0)
+  // CATCH_UB: call i8* @llvm.frameaddress.p0i8(i32 0)
 }

test/CodeGen/ms-intrinsics.c

 // CHECK: = tail call i8* @llvm.returnaddress(i32 0)
 // CHECK: ret i8*
 
 #if defined(__i386__) || defined(__x86_64__) || defined (__aarch64__)
 void *test_AddressOfReturnAddress() {
   return _AddressOfReturnAddress();
 }
 // CHECK-INTEL-LABEL: define dso_local i8* @test_AddressOfReturnAddress()
-// CHECK-INTEL: = tail call i8* @llvm.addressofreturnaddress()
+// CHECK-INTEL: = tail call i8* @llvm.addressofreturnaddress.p0i8()
 // CHECK-INTEL: ret i8*
 #endif
 
 unsigned char test_BitScanForward(unsigned long *Index, unsigned long Mask) {
   return _BitScanForward(Index, Mask);
 }
 // CHECK: define{{.*}}i8 @test_BitScanForward(i32* {{[a-z_ ]*}}%Index, i32 {{[a-z_ ]*}}%Mask){{.*}}{
 // CHECK:   [[ISNOTZERO:%[a-z0-9._]+]] = icmp eq i32 %Mask, 0

test/CodeGen/ms-setjmp.c

 
 int test_setjmp() {
   return _setjmp(jb);
   // I386-LABEL: define dso_local i32 @test_setjmp
   // I386:       %[[call:.*]] = call i32 (i8*, i32, ...) @_setjmp3(i8* getelementptr inbounds ([1 x i8], [1 x i8]* @jb, i32 0, i32 0), i32 0)
   // I386-NEXT:  ret i32 %[[call]]
 
   // X64-LABEL: define dso_local i32 @test_setjmp
-  // X64:       %[[addr:.*]] = call i8* @llvm.frameaddress(i32 0)
+  // X64:       %[[addr:.*]] = call i8* @llvm.frameaddress.p0i8(i32 0)
   // X64:       %[[call:.*]] = call i32 @_setjmp(i8* getelementptr inbounds ([1 x i8], [1 x i8]* @jb, i64 0, i64 0), i8* %[[addr]])
   // X64-NEXT:  ret i32 %[[call]]
 
   // AARCH64-LABEL: define dso_local i32 @test_setjmp
-  // AARCH64:       %[[addr:.*]] = call i8* @llvm.sponentry()
+  // AARCH64:       %[[addr:.*]] = call i8* @llvm.sponentry.p0i8()
   // AARCH64:       %[[call:.*]] = call i32 @_setjmpex(i8* getelementptr inbounds ([1 x i8], [1 x i8]* @jb, i64 0, i64 0), i8* %[[addr]])
   // AARCH64-NEXT:  ret i32 %[[call]]
 }
 
 int test_setjmpex() {
   return _setjmpex(jb);
   // X64-LABEL: define dso_local i32 @test_setjmpex
-  // X64:       %[[addr:.*]] = call i8* @llvm.frameaddress(i32 0)
+  // X64:       %[[addr:.*]] = call i8* @llvm.frameaddress.p0i8(i32 0)
   // X64:       %[[call:.*]] = call i32 @_setjmpex(i8* getelementptr inbounds ([1 x i8], [1 x i8]* @jb, i64 0, i64 0), i8* %[[addr]])
   // X64-NEXT:  ret i32 %[[call]]
 
   // AARCH64-LABEL: define dso_local i32 @test_setjmpex
-  // AARCH64:       %[[addr:.*]] = call i8* @llvm.sponentry()
+  // AARCH64:       %[[addr:.*]] = call i8* @llvm.sponentry.p0i8()
   // AARCH64:       %[[call:.*]] = call i32 @_setjmpex(i8* getelementptr inbounds ([1 x i8], [1 x i8]* @jb, i64 0, i64 0), i8* %[[addr]])
   // AARCH64-NEXT:  ret i32 %[[call]]
 }

test/CodeGenOpenCL/builtins-generic-amdgcn.cl

 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
 
 // CHECK-LABEL: @test_builtin_clz(
 // CHECK: tail call i32 @llvm.ctlz.i32(i32 %a, i1 true)
 void test_builtin_clz(global int* out, int a)
 {
   *out = __builtin_clz(a);
 }
 
 // CHECK-LABEL: @test_builtin_clzl(
 // CHECK: tail call i64 @llvm.ctlz.i64(i64 %a, i1 true)
 void test_builtin_clzl(global long* out, long a)
 {
   *out = __builtin_clzl(a);
 }
+
+// CHECK: tail call i8 addrspace(5)* @llvm.frameaddress.p5i8(i32 0)
+void test_builtin_frame_address(int *out) {
+    *out = __builtin_frame_address(0);
+}