[COFF, ARM64] Fix localaddress to handle stack realignment and variable size objects

Summary: This fixes using the correct stack registers for SEH when stack realignment is needed or when variable size objects are present.

Reviewers: rnk, efriedma, ssijaric, TomTan

Reviewed By: rnk, efriedma

Subscribers: javed.absar, kristof.beyls, llvm-commits

Differential Revision: https://reviews.llvm.org/D57183

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@352923 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/CodeGen/MachineFunction.h b/include/llvm/CodeGen/MachineFunction.h
index 670b2d501af342e38829a7fb745b4b6c62e129ea..34ceb15aebde134847ca213f69c0aafdd854c062 100644 (file)
--- a/include/llvm/CodeGen/MachineFunction.h
+++ b/include/llvm/CodeGen/MachineFunction.h
@@ -328,7 +328,6 @@ class MachineFunction {
   bool CallsUnwindInit = false;
   bool HasEHScopes = false;
   bool HasEHFunclets = false;
-  bool HasLocalEscape = false;
 
   /// List of C++ TypeInfo used.
   std::vector<const GlobalValue *> TypeInfos;
@@ -811,9 +810,6 @@ public:
   bool hasEHFunclets() const { return HasEHFunclets; }
   void setHasEHFunclets(bool V) { HasEHFunclets = V; }
 
-  bool hasLocalEscape() const { return HasLocalEscape; }
-  void setHasLocalEscape(bool V) { HasLocalEscape = V; }
-
   /// Find or create an LandingPadInfo for the specified MachineBasicBlock.
   LandingPadInfo &getOrCreateLandingPadInfo(MachineBasicBlock *LandingPad);
 

diff --git a/include/llvm/CodeGen/TargetFrameLowering.h b/include/llvm/CodeGen/TargetFrameLowering.h
index 021f7d2a269688d38c4805b79d3e6faf4ec46b14..754ee5cba01f541df55cca62974ae78671f1d2bf 100644 (file)
--- a/include/llvm/CodeGen/TargetFrameLowering.h
+++ b/include/llvm/CodeGen/TargetFrameLowering.h
@@ -261,6 +261,17 @@ public:
     return getFrameIndexReference(MF, FI, FrameReg);
   }
 
+  /// getNonLocalFrameIndexReference - This method returns the offset used to
+  /// reference a frame index location. The offset can be from either FP/BP/SP
+  /// based on which base register is returned by llvm.localaddress.
+  virtual int getNonLocalFrameIndexReference(const MachineFunction &MF,
+                                       int FI) const {
+    // By default, dispatch to getFrameIndexReference. Interested targets can
+    // override this.
+    unsigned FrameReg;
+    return getFrameIndexReference(MF, FI, FrameReg);
+  }
+
   /// This method determines which of the registers reported by
   /// TargetRegisterInfo::getCalleeSavedRegs() should actually get saved.
   /// The default implementation checks populates the \p SavedRegs bitset with

diff --git a/lib/CodeGen/AsmPrinter/WinException.cpp b/lib/CodeGen/AsmPrinter/WinException.cpp
index 882859afc48850af135210a20fb2fbe0c9c3abc9..c870419056ba669971a376c9753d39b44390bb8b 100644 (file)
--- a/lib/CodeGen/AsmPrinter/WinException.cpp
+++ b/lib/CodeGen/AsmPrinter/WinException.cpp
@@ -937,11 +937,7 @@ void WinException::emitEHRegistrationOffsetLabel(const WinEHFuncInfo &FuncInfo,
   int FI = FuncInfo.EHRegNodeFrameIndex;
   if (FI != INT_MAX) {
     const TargetFrameLowering *TFI = Asm->MF->getSubtarget().getFrameLowering();
-    unsigned UnusedReg;
-    // FIXME: getFrameIndexReference needs to match the behavior of
-    // AArch64RegisterInfo::hasBasePointer in which one of the scenarios where
-    // SP is used is if frame size >= 256.
-    Offset = TFI->getFrameIndexReference(*Asm->MF, FI, UnusedReg);
+    Offset = TFI->getNonLocalFrameIndexReference(*Asm->MF, FI);
   }
 
   MCContext &Ctx = Asm->OutContext;

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 49eeeffab5f82effe985156f8475cbb39406ec5f..1111a3e00450d3df3b2df91d3fd823cea59c8263 100644 (file)
--- a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -6220,8 +6220,6 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
           .addFrameIndex(FI);
     }
 
-    MF.setHasLocalEscape(true);
-
     return nullptr;
   }
 

diff --git a/lib/Target/AArch64/AArch64FrameLowering.cpp b/lib/Target/AArch64/AArch64FrameLowering.cpp
index 8b199fc091a5b6ea60dd000953c42a6f276a8ab5..bce9df84f1567e211d3526d22558b774574dab4f 100644 (file)
--- a/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -227,10 +227,6 @@ bool AArch64FrameLowering::hasFP(const MachineFunction &MF) const {
       MFI.getMaxCallFrameSize() > DefaultSafeSPDisplacement)
     return true;
 
-  // Win64 SEH requires frame pointer if funclets are present.
-  if (MF.hasLocalEscape())
-    return true;
-
   return false;
 }
 
@@ -1469,19 +1465,44 @@ int AArch64FrameLowering::getFrameIndexReference(const MachineFunction &MF,
   return resolveFrameIndexReference(MF, FI, FrameReg);
 }
 
+int AArch64FrameLowering::getNonLocalFrameIndexReference(
+  const MachineFunction &MF, int FI) const {
+  return getSEHFrameIndexOffset(MF, FI);
+}
+
+static int getFPOffset(const MachineFunction &MF, int FI) {
+  const auto &MFI = MF.getFrameInfo();
+  const auto *AFI = MF.getInfo<AArch64FunctionInfo>();
+  const auto &Subtarget = MF.getSubtarget<AArch64Subtarget>();
+  bool IsWin64 =
+      Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());
+  unsigned FixedObject = IsWin64 ? alignTo(AFI->getVarArgsGPRSize(), 16) : 0;
+  return MFI.getObjectOffset(FI) + FixedObject + 16;
+}
+
+static int getStackOffset(const MachineFunction &MF, int FI) {
+  const auto &MFI = MF.getFrameInfo();
+  return MFI.getObjectOffset(FI) + MFI.getStackSize();
+}
+
+int AArch64FrameLowering::getSEHFrameIndexOffset(const MachineFunction &MF,
+                                                 int FI) const {
+  const auto *RegInfo = static_cast<const AArch64RegisterInfo *>(
+      MF.getSubtarget().getRegisterInfo());
+  return RegInfo->getLocalAddressRegister(MF) == AArch64::FP ?
+         getFPOffset(MF, FI) : getStackOffset(MF, FI);
+}
+
 int AArch64FrameLowering::resolveFrameIndexReference(const MachineFunction &MF,
                                                      int FI, unsigned &FrameReg,
                                                      bool PreferFP) const {
-  const MachineFrameInfo &MFI = MF.getFrameInfo();
-  const AArch64RegisterInfo *RegInfo = static_cast<const AArch64RegisterInfo *>(
+  const auto &MFI = MF.getFrameInfo();
+  const auto *RegInfo = static_cast<const AArch64RegisterInfo *>(
       MF.getSubtarget().getRegisterInfo());
-  const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
-  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
-  bool IsWin64 =
-      Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());
-  unsigned FixedObject = IsWin64 ? alignTo(AFI->getVarArgsGPRSize(), 16) : 0;
-  int FPOffset = MFI.getObjectOffset(FI) + FixedObject + 16;
-  int Offset = MFI.getObjectOffset(FI) + MFI.getStackSize();
+  const auto *AFI = MF.getInfo<AArch64FunctionInfo>();
+  const auto &Subtarget = MF.getSubtarget<AArch64Subtarget>();
+  int FPOffset = getFPOffset(MF, FI);
+  int Offset = getStackOffset(MF, FI);
   bool isFixed = MFI.isFixedObjectIndex(FI);
   bool isCSR = !isFixed && MFI.getObjectOffset(FI) >=
                                -((int)AFI->getCalleeSavedStackSize());

diff --git a/lib/Target/AArch64/AArch64FrameLowering.h b/lib/Target/AArch64/AArch64FrameLowering.h
index ab063841f6a36e66dcc207f2c43a91d109850e12..f4bbeb4bdaef8434107d71b57993b02c9bf16fac 100644 (file)
--- a/lib/Target/AArch64/AArch64FrameLowering.h
+++ b/lib/Target/AArch64/AArch64FrameLowering.h
@@ -78,6 +78,9 @@ public:
   int getFrameIndexReferencePreferSP(const MachineFunction &MF, int FI,
                                      unsigned &FrameReg,
                                      bool IgnoreSPUpdates) const override;
+  int getNonLocalFrameIndexReference(const MachineFunction &MF,
+                               int FI) const override;
+  int getSEHFrameIndexOffset(const MachineFunction &MF, int FI) const;
 
 private:
   bool shouldCombineCSRLocalStackBump(MachineFunction &MF,

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 361e2eaa7b09f285ca3aa3f6bb4f2f94dd56ee5a..dd2ecca70a698981c98633f42bff7725652b4552 100644 (file)
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -2744,15 +2744,9 @@ SDValue AArch64TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
                        Op.getOperand(1), Op.getOperand(2));
 
   case Intrinsic::localaddress: {
-    // Returns one of the stack, base, or frame pointer registers, depending on
-    // which is used to reference local variables.
-    MachineFunction &MF = DAG.getMachineFunction();
-    const AArch64RegisterInfo *RegInfo = Subtarget->getRegisterInfo();
-    unsigned Reg;
-    if (RegInfo->hasBasePointer(MF))
-      Reg = RegInfo->getBaseRegister();
-    else // This function handles the SP or FP case.
-      Reg = RegInfo->getFrameRegister(MF);
+    const auto &MF = DAG.getMachineFunction();
+    const auto *RegInfo = Subtarget->getRegisterInfo();
+    unsigned Reg = RegInfo->getLocalAddressRegister(MF);
     return DAG.getCopyFromReg(DAG.getEntryNode(), dl, Reg,
                               Op.getSimpleValueType());
   }

diff --git a/lib/Target/AArch64/AArch64RegisterInfo.cpp b/lib/Target/AArch64/AArch64RegisterInfo.cpp
index ae0e39745e83966176dd4409d77deb23ea4cedb4..0d423a8893a994f3b74af7e96db708a29ceb2789 100644 (file)
--- a/lib/Target/AArch64/AArch64RegisterInfo.cpp
+++ b/lib/Target/AArch64/AArch64RegisterInfo.cpp
@@ -463,15 +463,16 @@ void AArch64RegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II,
     return;
   }
 
-  // Modify MI as necessary to handle as much of 'Offset' as possible
-  Offset = TFI->resolveFrameIndexReference(MF, FrameIndex, FrameReg);
-
   if (MI.getOpcode() == TargetOpcode::LOCAL_ESCAPE) {
     MachineOperand &FI = MI.getOperand(FIOperandNum);
+    Offset = TFI->getNonLocalFrameIndexReference(MF, FrameIndex);
     FI.ChangeToImmediate(Offset);
     return;
   }
 
+  // Modify MI as necessary to handle as much of 'Offset' as possible
+  Offset = TFI->getFrameIndexReference(MF, FrameIndex, FrameReg);
+
   if (rewriteAArch64FrameIndex(MI, FIOperandNum, FrameReg, Offset, TII))
     return;
 
@@ -525,3 +526,13 @@ unsigned AArch64RegisterInfo::getRegPressureLimit(const TargetRegisterClass *RC,
     return 16;
   }
 }
+
+unsigned AArch64RegisterInfo::getLocalAddressRegister(
+  const MachineFunction &MF) const {
+  const auto &MFI = MF.getFrameInfo();
+  if (!MF.hasEHFunclets() && !MFI.hasVarSizedObjects())
+    return AArch64::SP;
+  else if (needsStackRealignment(MF))
+    return getBaseRegister();
+  return getFrameRegister(MF);
+}

diff --git a/lib/Target/AArch64/AArch64RegisterInfo.h b/lib/Target/AArch64/AArch64RegisterInfo.h
index 1608f23bb9ee33fe3a9fef0e1911b8010f870346..3d83fcefef051f59c54ca93972d1d41a5d4167ef 100644 (file)
--- a/lib/Target/AArch64/AArch64RegisterInfo.h
+++ b/lib/Target/AArch64/AArch64RegisterInfo.h
@@ -121,6 +121,8 @@ public:
   bool trackLivenessAfterRegAlloc(const MachineFunction&) const override {
     return true;
   }
+
+  unsigned getLocalAddressRegister(const MachineFunction &MF) const;
 };
 
 } // end namespace llvm

diff --git a/test/CodeGen/AArch64/seh-finally.ll b/test/CodeGen/AArch64/seh-finally.ll
index 3cbbd03385c5fb3f4cc9db43e34bbb40a9493be9..2a7b2a925f3784ca244c29ca84eb900491957fc8 100644 (file)
--- a/test/CodeGen/AArch64/seh-finally.ll
+++ b/test/CodeGen/AArch64/seh-finally.ll
@@ -1,67 +1,283 @@
 ; RUN: llc -mtriple arm64-windows -o - %s | FileCheck %s
 
-; Function Attrs: noinline optnone uwtable
-define dso_local i32 @foo() {
+; struct S { int x; };
+; void foo(int n);
+; void foo(struct S o);
+; void simple_seh() {
+;   struct S o;
+; 
+;   __try { foo(o.x); }
+;   __finally { foo(o.x); }
+; }
+; void stack_realign() {
+;   struct S __declspec(align(32)) o;
+; 
+;   __try { foo(o.x); }
+;   __finally { foo(o.x); }
+; }
+; void vla_present(int n) {
+;   int vla[n];
+; 
+;   __try { foo(n); }
+;   __finally { foo(n); }
+; }
+; void vla_and_realign(int n) {
+;   struct S __declspec(align(32)) o;
+;   int vla[n];
+; 
+;   __try { foo(o.x); }
+;   __finally { foo(o.x); }
+; }
+
+%struct.S = type { i32 }
+
+; Test simple SEH (__try/__finally).
+define void @simple_seh() #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
 entry:
-; CHECK-LABEL: foo
-; CHECK: orr     w8, wzr, #0x1
-; CHECK: mov     w0, wzr
-; CHECK: mov     x1, x29
-; CHECK: .set .Lfoo$frame_escape_0, -4
-; CHECK: stur    w8, [x29, #-4]
-; CHECK: bl      "?fin$0@0@foo@@"
-; CHECK: ldur    w0, [x29, #-4]
+; CHECK-LABEL: simple_seh
+; CHECK: add     x29, sp, #16
+; CHECK: orr     x1, xzr, #0xfffffffffffffffe
+; CHECK: stur    x1, [x29, #-16]
+; CHECK: .set .Lsimple_seh$frame_escape_0, -8
+; CHECK: ldur    w0, [x29, #-8]
+; CHECK: bl      foo
+
+  %o = alloca %struct.S, align 4
+  call void (...) @llvm.localescape(%struct.S* %o)
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %0 = load i32, i32* %x, align 4
+  invoke void @foo(i32 %0) #5
+          to label %invoke.cont unwind label %ehcleanup
 
-  %count = alloca i32, align 4
-  call void (...) @llvm.localescape(i32* %count)
-  store i32 0, i32* %count, align 4
-  %0 = load i32, i32* %count, align 4
-  %add = add nsw i32 %0, 1
-  store i32 %add, i32* %count, align 4
+invoke.cont:                                      ; preds = %entry
   %1 = call i8* @llvm.localaddress()
-  call void @"?fin$0@0@foo@@"(i8 0, i8* %1)
-  %2 = load i32, i32* %count, align 4
-  ret i32 %2
+  call void @fin_simple_seh(i8 0, i8* %1)
+  ret void
+
+ehcleanup:                                        ; preds = %entry
+  %2 = cleanuppad within none []
+  %3 = call i8* @llvm.localaddress()
+  call void @fin_simple_seh(i8 1, i8* %3) [ "funclet"(token %2) ]
+  cleanupret from %2 unwind to caller
 }
 
-define internal void @"?fin$0@0@foo@@"(i8 %abnormal_termination, i8* %frame_pointer) {
+define void @fin_simple_seh(i8 %abnormal_termination, i8* %frame_pointer) {
 entry:
-; CHECK-LABEL: @"?fin$0@0@foo@@"
-; CHECK: sub     sp, sp, #16
-; CHECK: str     x1, [sp, #8]
-; CHECK: strb    w0, [sp, #7]
-; CHECK: movz    x8, #:abs_g1_s:.Lfoo$frame_escape_0
-; CHECK: movk    x8, #:abs_g0_nc:.Lfoo$frame_escape_0
-; CHECK: add     x8, x1, x8
-; CHECK: ldr     w9, [x8]
-; CHECK: add     w9, w9, #1
-; CHECK: str     w9, [x8]
+; CHECK-LABEL: fin_simple_seh
+; CHECK: movz    x8, #:abs_g1_s:.Lsimple_seh$frame_escape_0
+; CHECK: movk    x8, #:abs_g0_nc:.Lsimple_seh$frame_escape_0
+; CHECK: strb    w0, [sp, #15]
+; CHECK: ldr     w0, [x1, x8]
+; CHECK: bl      foo
 
   %frame_pointer.addr = alloca i8*, align 8
   %abnormal_termination.addr = alloca i8, align 1
-  %0 = call i8* @llvm.localrecover(i8* bitcast (i32 ()* @foo to i8*), i8* %frame_pointer, i32 0)
-  %count = bitcast i8* %0 to i32*
+  %0 = call i8* @llvm.localrecover(i8* bitcast (void ()* @simple_seh to i8*), i8* %frame_pointer, i32 0)
+  %o = bitcast i8* %0 to %struct.S*
   store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
   store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
-  %1 = zext i8 %abnormal_termination to i32
-  %cmp = icmp eq i32 %1, 0
-  br i1 %cmp, label %if.then, label %if.end
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %1 = load i32, i32* %x, align 4
+  call void @foo(i32 %1)
+  ret void
+}
 
-if.then:                                          ; preds = %entry
-  %2 = load i32, i32* %count, align 4
-  %add = add nsw i32 %2, 1
-  store i32 %add, i32* %count, align 4
-  br label %if.end
+; Test SEH when stack realignment is needed in case highly aligned stack objects are present.
+define void @stack_realign() #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
+entry:
+; CHECK-LABEL: stack_realign
+; CHECK: add     x29, sp, #16
+; CHECK: sub     x9, sp, #64
+; CHECK: and     sp, x9, #0xffffffffffffffe0
+; CHECK: mov     x19, sp
+; CHECK: orr     x1, xzr, #0xfffffffffffffffe
+; CHECK: stur    x1, [x19, #16]
+; CHECK: .set .Lstack_realign$frame_escape_0, 32
+; CHECK: ldr     w0, [x19, #32]
+; CHECK: bl      foo
+
+  %o = alloca %struct.S, align 32
+  call void (...) @llvm.localescape(%struct.S* %o)
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %0 = load i32, i32* %x, align 32
+  invoke void @foo(i32 %0) #5
+          to label %invoke.cont unwind label %ehcleanup
 
-if.end:                                           ; preds = %if.then, %entry
+invoke.cont:                                      ; preds = %entry
+  %1 = call i8* @llvm.localaddress()
+  call void @fin_stack_realign(i8 0, i8* %1)
   ret void
+
+ehcleanup:                                        ; preds = %entry
+  %2 = cleanuppad within none []
+  %3 = call i8* @llvm.localaddress()
+  call void @fin_stack_realign(i8 1, i8* %3) [ "funclet"(token %2) ]
+  cleanupret from %2 unwind to caller
 }
 
-; Function Attrs: nounwind readnone
-declare i8* @llvm.localrecover(i8*, i8*, i32)
+define void @fin_stack_realign(i8 %abnormal_termination, i8* %frame_pointer) {
+entry:
+; CHECK-LABEL: fin_stack_realign
+; CHECK: movz    x8, #:abs_g1_s:.Lstack_realign$frame_escape_0
+; CHECK: movk    x8, #:abs_g0_nc:.Lstack_realign$frame_escape_0
+; CHECK: strb    w0, [sp, #15]
+; CHECK: ldr     w0, [x1, x8]
+; CHECK: bl      foo
 
-; Function Attrs: nounwind readnone
-declare i8* @llvm.localaddress()
+  %frame_pointer.addr = alloca i8*, align 8
+  %abnormal_termination.addr = alloca i8, align 1
+  %0 = call i8* @llvm.localrecover(i8* bitcast (void ()* @stack_realign to i8*), i8* %frame_pointer, i32 0)
+  %o = bitcast i8* %0 to %struct.S*
+  store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
+  store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %1 = load i32, i32* %x, align 32
+  call void @foo(i32 %1)
+  ret void
+}
+
+; Test SEH when variable size objects are present on the stack. Note: Escaped vla's are current not supported by SEH.
+define void @vla_present(i32 %n) #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
+entry:
+; CHECK-LABEL: vla_present
+; CHECK: add     x29, sp, #32
+; CHECK: orr     x1, xzr, #0xfffffffffffffffe
+; CHECK: stur    x1, [x29, #-32]
+; CHECK: .set .Lvla_present$frame_escape_0, -4
+; CHECK: stur    w0, [x29, #-4]
+; CHECK: ldur    w8, [x29, #-4]
+; CHECK: mov     x9, sp
+; CHECK: stur    x9, [x29, #-16]
+; CHECK: stur    x8, [x29, #-24]
+; CHECK: ldur    w0, [x29, #-4]
+; CHECK: bl      foo
+
+  %n.addr = alloca i32, align 4
+  %saved_stack = alloca i8*, align 8
+  %__vla_expr0 = alloca i64, align 8
+  call void (...) @llvm.localescape(i32* %n.addr)
+  store i32 %n, i32* %n.addr, align 4
+  %0 = load i32, i32* %n.addr, align 4
+  %1 = zext i32 %0 to i64
+  %2 = call i8* @llvm.stacksave()
+  store i8* %2, i8** %saved_stack, align 8
+  %vla = alloca i32, i64 %1, align 4
+  store i64 %1, i64* %__vla_expr0, align 8
+  %3 = load i32, i32* %n.addr, align 4
+  invoke void @foo(i32 %3) #5
+          to label %invoke.cont unwind label %ehcleanup
+
+invoke.cont:                                      ; preds = %entry
+  %4 = call i8* @llvm.localaddress()
+  call void @fin_vla_present(i8 0, i8* %4)
+  %5 = load i8*, i8** %saved_stack, align 8
+  call void @llvm.stackrestore(i8* %5)
+  ret void
+
+ehcleanup:                                        ; preds = %entry
+  %6 = cleanuppad within none []
+  %7 = call i8* @llvm.localaddress()
+  call void @fin_vla_present(i8 1, i8* %7) [ "funclet"(token %6) ]
+  cleanupret from %6 unwind to caller
+}
 
-; Function Attrs: nounwind
+define void @fin_vla_present(i8 %abnormal_termination, i8* %frame_pointer) {
+entry:
+; CHECK-LABEL: fin_vla_present
+; CHECK: movz    x8, #:abs_g1_s:.Lvla_present$frame_escape_0
+; CHECK: movk    x8, #:abs_g0_nc:.Lvla_present$frame_escape_0
+; CHECK: strb    w0, [sp, #15]
+; CHECK: ldr     w0, [x1, x8]
+; CHECK: bl      foo
+
+  %frame_pointer.addr = alloca i8*, align 8
+  %abnormal_termination.addr = alloca i8, align 1
+  %0 = call i8* @llvm.localrecover(i8* bitcast (void (i32)* @vla_present to i8*), i8* %frame_pointer, i32 0)
+  %n.addr = bitcast i8* %0 to i32*
+  store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
+  store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
+  %1 = load i32, i32* %n.addr, align 4
+  call void @foo(i32 %1)
+  ret void
+}
+
+; Test when both vla's and highly aligned objects are present on stack.
+define void @vla_and_realign(i32 %n) #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
+entry:
+; CHECK-LABEL: vla_and_realign
+; CHECK: add     x29, sp, #16
+; CHECK: sub     x9, sp, #64
+; CHECK: and     sp, x9, #0xffffffffffffffe0
+; CHECK: mov     x19, sp
+; CHECK: orr     x1, xzr, #0xfffffffffffffffe
+; CHECK: stur    x1, [x19]
+; CHECK: .set .Lvla_and_realign$frame_escape_0, 32
+; CHECK: stur    w0, [x29, #-4]
+; CHECK: ldur    w8, [x29, #-4]
+; CHECK: mov     x9, sp
+; CHECK: str     x9, [x19, #24]
+; CHECK: str     x8, [x19, #16]
+; CHECK: ldr     w0, [x19, #32]
+; CHECK: bl      foo
+
+  %n.addr = alloca i32, align 4
+  %o = alloca %struct.S, align 32
+  %saved_stack = alloca i8*, align 8
+  %__vla_expr0 = alloca i64, align 8
+  call void (...) @llvm.localescape(%struct.S* %o)
+  store i32 %n, i32* %n.addr, align 4
+  %0 = load i32, i32* %n.addr, align 4
+  %1 = zext i32 %0 to i64
+  %2 = call i8* @llvm.stacksave()
+  store i8* %2, i8** %saved_stack, align 8
+  %vla = alloca i32, i64 %1, align 4
+  store i64 %1, i64* %__vla_expr0, align 8
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %3 = load i32, i32* %x, align 32
+  invoke void @foo(i32 %3) #5
+          to label %invoke.cont unwind label %ehcleanup
+
+invoke.cont:                                      ; preds = %entry
+  %4 = call i8* @llvm.localaddress()
+  call void @fin_vla_and_realign(i8 0, i8* %4)
+  %5 = load i8*, i8** %saved_stack, align 8
+  call void @llvm.stackrestore(i8* %5)
+  ret void
+
+ehcleanup:                                        ; preds = %entry
+  %6 = cleanuppad within none []
+  %7 = call i8* @llvm.localaddress()
+  call void @fin_vla_and_realign(i8 1, i8* %7) [ "funclet"(token %6) ]
+  cleanupret from %6 unwind to caller
+}
+
+define void @fin_vla_and_realign(i8 %abnormal_termination, i8* %frame_pointer) {
+entry:
+; CHECK-LABEL: fin_vla_and_realign
+; CHECK: movz    x8, #:abs_g1_s:.Lvla_and_realign$frame_escape_0
+; CHECK: movk    x8, #:abs_g0_nc:.Lvla_and_realign$frame_escape_0
+; CHECK: strb    w0, [sp, #15]
+; CHECK: ldr     w0, [x1, x8]
+; CHECK: bl      foo
+
+  %frame_pointer.addr = alloca i8*, align 8
+  %abnormal_termination.addr = alloca i8, align 1
+  %0 = call i8* @llvm.localrecover(i8* bitcast (void (i32)* @vla_and_realign to i8*), i8* %frame_pointer, i32 0)
+  %o = bitcast i8* %0 to %struct.S*
+  store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
+  store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
+  %x = getelementptr inbounds %struct.S, %struct.S* %o, i32 0, i32 0
+  %1 = load i32, i32* %x, align 32
+  call void @foo(i32 %1)
+  ret void
+}
+
+declare void @foo(i32)
+declare void @llvm.stackrestore(i8*)
+declare i8* @llvm.stacksave()
+declare i8* @llvm.localrecover(i8*, i8*, i32)
+declare i8* @llvm.localaddress()
 declare void @llvm.localescape(...)
+declare i32 @__C_specific_handler(...)
+
+attributes #0 = { noinline optnone }

diff --git a/test/CodeGen/AArch64/seh-localescape.ll b/test/CodeGen/AArch64/seh-localescape.ll
deleted file mode 100644 (file)
index 0a16750..0000000
--- a/test/CodeGen/AArch64/seh-localescape.ll
+++ /dev/null
@@ -1,30 +0,0 @@
-; RUN: llc -mtriple arm64-windows %s -o - | FileCheck %s
-
-; Function Attrs: noinline nounwind optnone uwtable
-define dso_local i32 @foo() {
-entry:
-; CHECK-LABEL: foo
-; CHECK: .set .Lfoo$frame_escape_0, -4
-
-  %count = alloca i32, align 4
-  call void (...) @llvm.localescape(i32* %count)
-  ret i32 0
-}
-
-define internal i32 @"?filt$0@0@foo@@"(i8* %exception_pointers, i8* %frame_pointer) {
-entry:
-; CHECK-LABEL: @"?filt$0@0@foo@@"
-; CHECK: movz    x8, #:abs_g1_s:.Lfoo$frame_escape_0
-; CHECK: movk    x8, #:abs_g0_nc:.Lfoo$frame_escape_0
-
-  %0 = call i8* @llvm.localrecover(i8* bitcast (i32 ()* @foo to i8*), i8* %frame_pointer, i32 0)
-  %count = bitcast i8* %0 to i32*
-  %1 = load i32, i32* %count, align 4
-  ret i32 %1
-}
-
-; Function Attrs: nounwind readnone
-declare i8* @llvm.localrecover(i8*, i8*, i32) #2
-
-; Function Attrs: nounwind
-declare void @llvm.localescape(...) #3