[AArch64] Match the windows canonical callee saved register order [alternative 3]

[mstorsjo]

Summary

Another alternative form of D88642 - simpler pairing logic, but more flipping/reversing needed elsewhere instead.

[efriedma]

I think I prefer this approach.

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

2079

It's not obvious what "Inc" and "IncrementSign" are supposed to mean.

[efriedma]

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

2198

Both here and at the other call to setObjectAlignment(), maybe add a comment describing what the stack layout actually looks like as a result of the padding? Would help make it clear why the codepaths are separate.

[mstorsjo]

Gave some variables a more descriptive name, added more comments about stack object alignment/gaps.

[efriedma]

LGTM

llvm/lib/Target/AArch64/AArch64FrameLowering.h

restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
                               const TargetRegisterInfo *TRI) const override;
 
   /// Can this function use the red zone for local allocations.
   bool canUseRedZone(const MachineFunction &MF) const;
 
   bool hasFP(const MachineFunction &MF) const override;
   bool hasReservedCallFrame(const MachineFunction &MF) const override;
 
+  bool
+  assignCalleeSavedSpillSlots(MachineFunction &MF,
+                              const TargetRegisterInfo *TRI,
+                              std::vector<CalleeSavedInfo> &CSI) const override;
+
   void determineCalleeSaves(MachineFunction &MF, BitVector &SavedRegs,
                             RegScavenger *RS) const override;
 
   /// Returns true if the target will correctly handle shrink wrapping.
   bool enableShrinkWrapping(const MachineFunction &MF) const override {
     return true;
   }
 

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

static void computeCalleeSaveRegisterPairs(
   unsigned Count = CSI.size();
   (void)CC;
   // MachO's compact unwind format relies on all registers being stored in
   // pairs.
   assert((!produceCompactUnwindFrame(MF) ||
           CC == CallingConv::PreserveMost ||
           (Count & 1) == 0) &&
          "Odd number of callee-saved regs to spill!");
   int ByteOffset = AFI->getCalleeSavedStackSize();
+  int StackFillDir = -1;
+  int RegInc = 1;
+  unsigned FirstReg = 0;
+  if (NeedsWinCFI) {
+    // For WinCFI, fill the stack from the bottom up.
+    ByteOffset = 0;
+    StackFillDir = 1;
+    // As the CSI array is reversed to match PrologEpilogInserter, iterate
+    // backwards, to pair up registers starting from lower numbered registers.
+    RegInc = -1;
+    FirstReg = Count - 1;
+  }
   int ScalableByteOffset = AFI->getSVECalleeSavedStackSize();
-  // On Linux, we will have either one or zero non-paired register.  On Windows
-  // with CFI, we can have multiple unpaired registers in order to utilize the
-  // available unwind codes.  This flag assures that the alignment fixup is done
-  // only once, as intened.
-  bool FixupDone = false;
 
-  for (unsigned i = 0; i < Count; ++i) {
+  // When iterating backwards, the loop condition relies on unsigned wraparound.
+  for (unsigned i = FirstReg; i < Count; i += RegInc) {
     RegPairInfo RPI;
     RPI.Reg1 = CSI[i].getReg();
 
     if (AArch64::GPR64RegClass.contains(RPI.Reg1))
       RPI.Type = RegPairInfo::GPR;
     else if (AArch64::FPR64RegClass.contains(RPI.Reg1))
       RPI.Type = RegPairInfo::FPR64;
     else if (AArch64::FPR128RegClass.contains(RPI.Reg1))
       RPI.Type = RegPairInfo::FPR128;
     else if (AArch64::ZPRRegClass.contains(RPI.Reg1))
       RPI.Type = RegPairInfo::ZPR;
     else if (AArch64::PPRRegClass.contains(RPI.Reg1))
       RPI.Type = RegPairInfo::PPR;
     else
       llvm_unreachable("Unsupported register class.");
 
     // Add the next reg to the pair if it is in the same register class.
-    if (i + 1 < Count) {
-      unsigned NextReg = CSI[i + 1].getReg();
+    if (unsigned(i + RegInc) < Count) {
+      unsigned NextReg = CSI[i + RegInc].getReg();
       switch (RPI.Type) {
       case RegPairInfo::GPR:
         if (AArch64::GPR64RegClass.contains(NextReg) &&
             !invalidateRegisterPairing(RPI.Reg1, NextReg, IsWindows, NeedsWinCFI,
                                        NeedsFrameRecord))
           RPI.Reg2 = NextReg;
         break;
       case RegPairInfo::FPR64:
for (unsigned i = FirstReg; i < Count; i += RegInc) {
 
     // GPRs and FPRs are saved in pairs of 64-bit regs. We expect the CSI
     // list to come in sorted by frame index so that we can issue the store
     // pair instructions directly. Assert if we see anything otherwise.
     //
     // The order of the registers in the list is controlled by
     // getCalleeSavedRegs(), so they will always be in-order, as well.
     assert((!RPI.isPaired() ||
-            (CSI[i].getFrameIdx() + 1 == CSI[i + 1].getFrameIdx())) &&
+            (CSI[i].getFrameIdx() + RegInc == CSI[i + RegInc].getFrameIdx())) &&
            "Out of order callee saved regs!");
 
     assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg2 != AArch64::FP ||
             RPI.Reg1 == AArch64::LR) &&
            "FrameRecord must be allocated together with LR");
 
     // Windows AAPCS has FP and LR reversed.
     assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg1 != AArch64::FP ||
             RPI.Reg2 == AArch64::LR) &&
            "FrameRecord must be allocated together with LR");
 
     // MachO's compact unwind format relies on all registers being stored in
     // adjacent register pairs.
     assert((!produceCompactUnwindFrame(MF) ||
             CC == CallingConv::PreserveMost ||
             (RPI.isPaired() &&
              ((RPI.Reg1 == AArch64::LR && RPI.Reg2 == AArch64::FP) ||
               RPI.Reg1 + 1 == RPI.Reg2))) &&
            "Callee-save registers not saved as adjacent register pair!");
 
     RPI.FrameIdx = CSI[i].getFrameIdx();
+    if (NeedsWinCFI &&
+        RPI.isPaired()) // RPI.FrameIdx must be the lower index of the pair
+      RPI.FrameIdx = CSI[i + RegInc].getFrameIdx();
 
     int Scale = RPI.getScale();
+
+    int OffsetPre = RPI.isScalable() ? ScalableByteOffset : ByteOffset;
+    assert(OffsetPre % Scale == 0);
+
     if (RPI.isScalable())
-      ScalableByteOffset -= Scale;
+      ScalableByteOffset += StackFillDir * Scale;
     else
-      ByteOffset -= RPI.isPaired() ? 2 * Scale : Scale;
+      ByteOffset += StackFillDir * (RPI.isPaired() ? 2 * Scale : Scale);
 
     assert(!(RPI.isScalable() && RPI.isPaired()) &&
            "Paired spill/fill instructions don't exist for SVE vectors");
 
     // Round up size of non-pair to pair size if we need to pad the
     // callee-save area to ensure 16-byte alignment.
-    if (AFI->hasCalleeSaveStackFreeSpace() && !FixupDone &&
+    if (AFI->hasCalleeSaveStackFreeSpace() && !NeedsWinCFI &&
         !RPI.isScalable() && RPI.Type != RegPairInfo::FPR128 &&
         !RPI.isPaired()) {
-      FixupDone = true;
-      ByteOffset -= 8;
+      ByteOffset += 8 * StackFillDir;
       assert(ByteOffset % 16 == 0);
       assert(MFI.getObjectAlign(RPI.FrameIdx) <= Align(16));
+      // A stack frame with a gap looks like this, bottom up:
+      // d9, d8. x21, gap, x20, x19.
+      // Set extra alignment on the x21 object (the only unpaired register)
+      // to create the gap above it.
       MFI.setObjectAlignment(RPI.FrameIdx, Align(16));
     }
 
-    int Offset = RPI.isScalable() ? ScalableByteOffset : ByteOffset;
-    assert(Offset % Scale == 0);
+    int OffsetPost = RPI.isScalable() ? ScalableByteOffset : ByteOffset;
+    assert(OffsetPost % Scale == 0);
+    // If filling top down (default), we want the offset after incrementing it.
+    // If fillibg bootom up (WinCFI) we need the original offset.
+    int Offset = NeedsWinCFI ? OffsetPre : OffsetPost;
     RPI.Offset = Offset / Scale;
 
     assert(((!RPI.isScalable() && RPI.Offset >= -64 && RPI.Offset <= 63) ||
             (RPI.isScalable() && RPI.Offset >= -256 && RPI.Offset <= 255)) &&
            "Offset out of bounds for LDP/STP immediate");
 
     // Save the offset to frame record so that the FP register can point to the
     // innermost frame record (spilled FP and LR registers).
     if (NeedsFrameRecord && ((!IsWindows && RPI.Reg1 == AArch64::LR &&
                               RPI.Reg2 == AArch64::FP) ||
                              (IsWindows && RPI.Reg1 == AArch64::FP &&
                               RPI.Reg2 == AArch64::LR)))
       AFI->setCalleeSaveBaseToFrameRecordOffset(Offset);
 
     RegPairs.push_back(RPI);
     if (RPI.isPaired())
-      ++i;
+      i += RegInc;
+  }
+  if (NeedsWinCFI) {
+    // If we need an alignment gap in the stack, align the topmost stack
+    // object. A stack frame with a gap looks like this, bottom up:
+    // x19, d8. d9, gap.
+    // Set extra alignment on the topmost stack object (the first element in
+    // CSI, which goes top down), to create the gap above it.
+    if (AFI->hasCalleeSaveStackFreeSpace())
+      MFI.setObjectAlignment(CSI[0].getFrameIdx(), Align(16));
+    // We iterated bottom up over the registers; flip RegPairs back to top
+    // down order.
+    std::reverse(RegPairs.begin(), RegPairs.end());
   }
 }
 
 bool AArch64FrameLowering::spillCalleeSavedRegisters(
     MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
     ArrayRef<CalleeSavedInfo> CSI, const TargetRegisterInfo *TRI) const {
   MachineFunction &MF = *MBB.getParent();
   const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
void AArch64FrameLowering::determineCalleeSaves(MachineFunction &MF,
 
   // Round up to register pair alignment to avoid additional SP adjustment
   // instructions.
   AFI->setCalleeSavedStackSize(AlignedCSStackSize);
   AFI->setCalleeSaveStackHasFreeSpace(AlignedCSStackSize != CSStackSize);
   AFI->setSVECalleeSavedStackSize(alignTo(SVECSStackSize, 16));
 }
 
+bool AArch64FrameLowering::assignCalleeSavedSpillSlots(
+    MachineFunction &MF, const TargetRegisterInfo *TRI,
+    std::vector<CalleeSavedInfo> &CSI) const {
+  bool NeedsWinCFI = needsWinCFI(MF);
+  // To match the canonical windows frame layout, reverse the list of
+  // callee saved registers to get them laid out by PrologEpilogInserter
+  // in the right order. (PrologEpilogInserter allocates stack objects top
+  // down. Windows canonical prologs store higher numbered registers at
+  // the top, thus have the CSI array start from the highest registers.)
+  if (NeedsWinCFI)
+    std::reverse(CSI.begin(), CSI.end());
+  // Let the generic code do the rest of the setup.
+  return false;
+}
+
 bool AArch64FrameLowering::enableStackSlotScavenging(
     const MachineFunction &MF) const {
   const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
   return AFI->hasCalleeSaveStackFreeSpace();
 }
 
 /// returns true if there are any SVE callee saves.
 static bool getSVECalleeSaveSlotRange(const MachineFrameInfo &MFI,

llvm/test/CodeGen/AArch64/seh-finally.ll

; CHECK: bl      foo
   call void @foo(i32 %1)
   ret void
 }
 
 ; 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: mov     x29, sp
+; CHECK: add     x29, sp, #8
 ; CHECK: sub     x9, sp, #16
 ; CHECK: and     sp, x9, #0xffffffffffffffe0
 ; CHECK: mov     x19, sp
 ; CHECK: mov     x0, #-2
-; CHECK: stur    x0, [x29, #32]
+; CHECK: stur    x0, [x29, #24]
 ; CHECK: .set .Lstack_realign$frame_escape_0, 0
 ; CHECK: ldr     w0, [x19]
 ; 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
; CHECK: bl      foo
   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: mov     x29, sp
+; CHECK: add     x29, sp, #8
 ; CHECK: sub     x9, sp, #48
 ; CHECK: and     sp, x9, #0xffffffffffffffe0
 ; CHECK: mov     x19, sp
 ; CHECK: mov     x1, #-2
-; CHECK: stur    x1, [x29, #32]
+; CHECK: stur    x1, [x29, #24]
 ; CHECK: .set .Lvla_and_realign$frame_escape_0, 32
-; CHECK: str     w0, [x29, #44]
-; CHECK: ldr     w8, [x29, #44]
+; CHECK: str     w0, [x29, #36]
+; CHECK: ldr     w8, [x29, #36]
 ; CHECK: mov     x9, sp
-; CHECK: str     x9, [x29, #24]
+; CHECK: str     x9, [x29, #16]
 ; CHECK: str     x8, [x19, #24]
 ; 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

llvm/test/CodeGen/AArch64/sponentry.ll

define dso_local void @foo([24 x i64]*) {
   %8 = bitcast i64* %7 to i8*
   %9 = call i32 @_setjmpex(i8* %8, i8* %5)
   store i32 %9, i32* %3, align 4
   ret void
 }
 
 ; CHECK: foo:
 ; CHECK: sub     sp, sp, #448
-; CHECK: add     x29, sp, #416
-; CHECK: add     x1, x29, #32
+; CHECK: add     x29, sp, #424
+; CHECK: add     x1, x29, #24
 ; CHECK: bl      _setjmpex
 
 ; NOFP: sub     sp, sp, #432
 ; NOFP: add     x1, sp, #432
 
 define dso_local void @var_args(i8*, ...) {
   %2 = alloca i8*, align 8
   %3 = alloca i8*, align 8

llvm/test/CodeGen/AArch64/win64_vararg.ll

 declare void @llvm.va_end(i8*)
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
 
 declare i32 @__stdio_common_vsprintf(i64, i8*, i64, i8*, i8*, i8*) local_unnamed_addr #3
 declare i64* @__local_stdio_printf_options() local_unnamed_addr #4
 
 ; CHECK-LABEL: fp
-; CHECK: stp     x29, x30, [sp, #-96]
+; CHECK: stp     x19, x20, [sp, #-96]
 ; CHECK: str     x21,      [sp, #16]
-; CHECK: stp     x19, x20, [sp, #32]
-; CHECK: mov     x29, sp
-; CHECK: add     x8, x29, #56
+; CHECK: stp     x29, x30, [sp, #24]
+; CHECK: add     x29, sp, #24
+; CHECK: add     x8, x29, #32
 ; CHECK: mov     x19, x2
 ; CHECK: mov     x20, x1
 ; CHECK: mov     x21, x0
-; CHECK: stp     x3, x4, [x29, #56]
-; CHECK: stp     x5, x6, [x29, #72]
-; CHECK: str     x7, [x29, #88]
-; CHECK: str     x8, [x29, #24]
+; CHECK: stp     x3, x4, [x29, #32]
+; CHECK: stp     x5, x6, [x29, #48]
+; CHECK: str     x7, [x29, #64]
+; CHECK: str     x8, [x29, #16]
 ; CHECK: bl      __local_stdio_printf_options
 ; CHECK: ldr     x8, [x0]
-; CHECK: add     x5, x29, #56
+; CHECK: add     x5, x29, #32
 ; CHECK: mov     x1, x21
 ; CHECK: mov     x2, x20
 ; CHECK: orr     x0, x8, #0x2
 ; CHECK: mov     x3, x19
 ; CHECK: mov     x4, xzr
 ; CHECK: bl      __stdio_common_vsprintf
 ; CHECK: cmp     w0, #0
 ; CHECK: csinv   w0, w0, wzr, ge
-; CHECK: ldp     x19, x20, [sp, #32]
+; CHECK: ldp     x29, x30, [sp, #24]
 ; CHECK: ldr     x21,      [sp, #16]
-; CHECK: ldp     x29, x30, [sp], #96
+; CHECK: ldp     x19, x20, [sp], #96
 ; CHECK: ret
 define i32 @fp(i8*, i64, i8*, ...) local_unnamed_addr #6 {
   %4 = alloca i8*, align 8
   %5 = bitcast i8** %4 to i8*
   call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %5) #2
   call void @llvm.va_start(i8* nonnull %5)
   %6 = load i8*, i8** %4, align 8
   %7 = call i64* @__local_stdio_printf_options() #2
   %8 = load i64, i64* %7, align 8
   %9 = or i64 %8, 2
   %10 = call i32 @__stdio_common_vsprintf(i64 %9, i8* %0, i64 %1, i8* %2, i8* null, i8* %6) #2
   %11 = icmp sgt i32 %10, -1
   %12 = select i1 %11, i32 %10, i32 -1
   call void @llvm.va_end(i8* nonnull %5)
   call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %5) #2
   ret i32 %12
 }
 
 attributes #6 = { "frame-pointer"="all" }
 
 ; CHECK-LABEL: vla
-; CHECK: stp     x29, x30, [sp, #-112]!
-; CHECK: str     x23, [sp, #16]
-; CHECK: stp     x21, x22, [sp, #32]
-; CHECK: stp     x19, x20, [sp, #48]
-; CHECK: mov     x29, sp
-; CHECK: add     x8, x29, #64
-; CHECK: str     x8, [x29, #24]
+; CHECK: stp     x19, x20, [sp, #-112]!
+; CHECK: stp     x21, x22, [sp, #16]
+; CHECK: str     x23,      [sp, #32]
+; CHECK: stp     x29, x30, [sp, #40]
+; CHECK: add     x29, sp, #40
+; CHECK: add     x8, x29, #24
+; CHECK: str     x8, [x29, #16]
 ; CHECK: mov     w8, w0
 ; CHECK: add     x8, x8, #15
 ; CHECK: lsr     x15, x8, #4
 ; CHECK: mov     x19, x1
 ; CHECK: mov     [[REG2:x[0-9]+]], sp
-; CHECK: stp     x2, x3, [x29, #64]
-; CHECK: stp     x4, x5, [x29, #80]
-; CHECK: stp     x6, x7, [x29, #96]
+; CHECK: stp     x2, x3, [x29, #24]
+; CHECK: stp     x4, x5, [x29, #40]
+; CHECK: stp     x6, x7, [x29, #56]
 ; CHECK: bl      __chkstk
 ; CHECK: mov     x8, sp
 ; CHECK: sub     [[REG:x[0-9]+]], x8, x15, lsl #4
 ; CHECK: mov     sp, [[REG]]
-; CHECK: ldr     [[REG3:x[0-9]+]], [x29, #24]
+; CHECK: ldr     [[REG3:x[0-9]+]], [x29, #16]
 ; CHECK: sxtw    [[REG4:x[0-9]+]], w0
 ; CHECK: bl      __local_stdio_printf_options
 ; CHECK: ldr     x8, [x0]
 ; CHECK: mov     x1, [[REG]]
 ; CHECK: mov     x2, [[REG4]]
 ; CHECK: mov     x3, x19
 ; CHECK: orr     x0, x8, #0x2
 ; CHECK: mov     x4, xzr
 ; CHECK: mov     x5, [[REG3]]
 ; CHECK: bl      __stdio_common_vsprintf
 ; CHECK: mov     sp, [[REG2]]
-; CHECK: mov     sp, x29
-; CHECK: ldp     x19, x20, [sp, #48]
-; CHECK: ldp     x21, x22, [sp, #32]
-; CHECK: ldr     x23, [sp, #16]
-; CHECK: ldp     x29, x30, [sp], #112
+; CHECK: sub     sp, x29, #40
+; CHECK: ldp     x29, x30, [sp, #40]
+; CHECK: ldr     x23,      [sp, #32]
+; CHECK: ldp     x21, x22, [sp, #16]
+; CHECK: ldp     x19, x20, [sp], #112
 ; CHECK: ret
 define void @vla(i32, i8*, ...) local_unnamed_addr {
   %3 = alloca i8*, align 8
   %4 = bitcast i8** %3 to i8*
   call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %4) #5
   call void @llvm.va_start(i8* nonnull %4)
   %5 = zext i32 %0 to i64
   %6 = call i8* @llvm.stacksave()
define void @vla(i32, i8*, ...) local_unnamed_addr {
   ret void
 }
 
 declare i8* @llvm.stacksave()
 declare void @llvm.stackrestore(i8*)
 
 ; CHECK-LABEL: snprintf
 ; CHECK-DAG: sub     sp,  sp, #96
-; CHECK-DAG: str     x30, [sp, #16]
-; CHECK-DAG: str     x21, [sp, #24]
-; CHECK-DAG: stp     x19, x20, [sp, #32]
+; CHECK-DAG: stp     x19, x20, [sp, #16]
+; CHECK-DAG: str     x21, [sp, #32]
+; CHECK-DAG: str     x30, [sp, #40]
 ; CHECK-DAG: add     x8, sp, #56
 ; CHECK-DAG: mov     x19, x2
 ; CHECK-DAG: mov     x20, x1
 ; CHECK-DAG: mov     x21, x0
 ; CHECK-DAG: stp     x3, x4, [sp, #56]
 ; CHECK-DAG: stp     x5, x6, [sp, #72]
 ; CHECK-DAG: str     x7, [sp, #88]
 ; CHECK-DAG: str     x8, [sp, #8]
 ; CHECK-DAG: bl      __local_stdio_printf_options
 ; CHECK-DAG: ldr     x8, [x0]
 ; CHECK-DAG: add     x5, sp, #56
 ; CHECK-DAG: mov     x1, x21
 ; CHECK-DAG: mov     x2, x20
 ; CHECK-DAG: orr     x0, x8, #0x2
 ; CHECK-DAG: mov     x3, x19
 ; CHECK-DAG: mov     x4, xzr
 ; CHECK-DAG: bl      __stdio_common_vsprintf
-; CHECK-DAG: ldr     x30, [sp, #16]
-; CHECK-DAG: ldr     x21, [sp, #24]
-; CHECK-DAG: ldp     x19, x20, [sp, #32]
+; CHECK-DAG: ldr     x30, [sp, #40]
+; CHECK-DAG: ldr     x21, [sp, #32]
+; CHECK-DAG: ldp     x19, x20, [sp, #16]
 ; CHECK-DAG: cmp     w0, #0
 ; CHECK-DAG: csinv   w0, w0, wzr, ge
 ; CHECK-DAG: add     sp, sp, #96
 ; CHECK-DAG: ret
 define i32 @snprintf(i8*, i64, i8*, ...) local_unnamed_addr #5 {
   %4 = alloca i8*, align 8
   %5 = bitcast i8** %4 to i8*
   call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %5) #2

llvm/test/CodeGen/AArch64/wineh-frame-scavenge.mir

+# RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
+# RUN:   -stop-after=prologepilog | FileCheck %s
+# Check where the stack variable is placed
+
+# CHECK:      - { id: 0, name: '', type: default, offset: -4, size: 4, alignment: 4,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+# CHECK-NEXT:     local-offset: -4, debug-info-variable: '', debug-info-expression: '',
+# CHECK-NEXT:     debug-info-location: '' }
+# CHECK-NEXT: - { id: 1, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '$x23', callee-saved-restored: true,
+# CHECK-NEXT:     debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+# CHECK-NEXT: - { id: 2, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '$x22', callee-saved-restored: true,
+# CHECK-NEXT:     debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+# CHECK-NEXT: - { id: 3, name: '', type: spill-slot, offset: -32, size: 8, alignment: 8,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '$x21', callee-saved-restored: true,
+# CHECK-NEXT:     debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+# CHECK-NEXT: - { id: 4, name: '', type: spill-slot, offset: -40, size: 8, alignment: 8,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '$x20', callee-saved-restored: true,
+# CHECK-NEXT:     debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+# CHECK-NEXT: - { id: 5, name: '', type: spill-slot, offset: -48, size: 8, alignment: 8,
+# CHECK-NEXT:     stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true,
+# CHECK-NEXT:     debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+
+# CHECK:      early-clobber $sp = frame-setup STPXpre killed $x19, killed $x20, $sp, -6 :: (store 8 into %stack.4), (store 8 into %stack.5)
+# CHECK-NEXT: frame-setup SEH_SaveRegP_X 19, 20, -48
+# CHECK-NEXT: frame-setup STPXi killed $x21, killed $x22, $sp, 2 :: (store 8 into %stack.2), (store 8 into %stack.3)
+# CHECK-NEXT: frame-setup SEH_SaveRegP 21, 22, 16
+# CHECK-NEXT: frame-setup STRXui killed $x23, $sp, 4 :: (store 8 into %stack.1)
+# CHECK-NEXT: frame-setup SEH_SaveReg 23, 32
+# CHECK-NEXT: frame-setup SEH_PrologEnd
+
+
+...
+---
+name:            func
+alignment:       4
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:       []
+liveins:         []
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    4
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 0
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  4
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: default, offset: 0, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+      local-offset: -4, debug-info-variable: '', debug-info-expression: '',
+      debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  bb.0.entry:
+    liveins: $x0, $x23, $x21, $x22, $x19, $x20
+
+    renamable $x8 = ADDXri %stack.0, 0, 0
+    $x19 = ADDXrr $x0, $x8
+    $x20 = ADDXrr $x19, $x0
+    $x21 = ADDXrr $x20, killed $x19
+    $x22 = ADDXrr $x21, killed $x20
+    $x23 = ADDXrr $x22, killed $x21
+    $x0 = ADDXrr $x0, killed $x23
+
+    RET_ReallyLR
+
+...

llvm/test/CodeGen/AArch64/wineh-frame0.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check save_regp_x, save_regp
 
-# CHECK:        early-clobber $sp = frame-setup STPXpre killed $x27, killed $x28, $sp, -10
-# CHECK-NEXT:   frame-setup SEH_SaveRegP_X 27, 28, -80
-# CHECK-NEXT:   frame-setup STPXi killed $x25, killed $x26, $sp, 2
-# CHECK-NEXT:   frame-setup SEH_SaveRegP 25, 26, 16
+# CHECK:        early-clobber $sp = frame-setup STPXpre killed $x19, killed $x20, $sp, -10
+# CHECK-NEXT:   frame-setup SEH_SaveRegP_X 19, 20, -80
+# CHECK-NEXT:   frame-setup STPXi killed $x21, killed $x22, $sp, 2
+# CHECK-NEXT:   frame-setup SEH_SaveRegP 21, 22, 16
 # CHECK-NEXT:   frame-setup STPXi killed $x23, killed $x24, $sp, 4
 # CHECK-NEXT:   frame-setup SEH_SaveRegP 23, 24, 32
-# CHECK-NEXT:   frame-setup STPXi killed $x21, killed $x22, $sp, 6
-# CHECK-NEXT:   frame-setup SEH_SaveRegP 21, 22, 48
-# CHECK-NEXT:   frame-setup STPXi killed $x19, killed $x20, $sp, 8
-# CHECK-NEXT:   frame-setup SEH_SaveRegP 19, 20, 64
+# CHECK-NEXT:   frame-setup STPXi killed $x25, killed $x26, $sp, 6
+# CHECK-NEXT:   frame-setup SEH_SaveRegP 25, 26, 48
+# CHECK-NEXT:   frame-setup STPXi killed $x27, killed $x28, $sp, 8
+# CHECK-NEXT:   frame-setup SEH_SaveRegP 27, 28, 64
 # CHECK-NEXT:   frame-setup SEH_PrologEnd
 # CHECK:        frame-destroy SEH_EpilogStart
-# CHECK-NEXT:   $x19, $x20 = frame-destroy LDPXi $sp, 8
-# CHECK-NEXT:   frame-destroy SEH_SaveRegP 19, 20, 64
-# CHECK-NEXT:   $x21, $x22 = frame-destroy LDPXi $sp, 6
-# CHECK-NEXT:   frame-destroy SEH_SaveRegP 21, 22, 48
+# CHECK-NEXT:   $x27, $x28 = frame-destroy LDPXi $sp, 8
+# CHECK-NEXT:   frame-destroy SEH_SaveRegP 27, 28, 64
+# CHECK-NEXT:   $x25, $x26 = frame-destroy LDPXi $sp, 6
+# CHECK-NEXT:   frame-destroy SEH_SaveRegP 25, 26, 48
 # CHECK-NEXT:   $x23, $x24 = frame-destroy LDPXi $sp, 4
 # CHECK-NEXT:   frame-destroy SEH_SaveRegP 23, 24, 32
-# CHECK-NEXT:   $x25, $x26 = frame-destroy LDPXi $sp, 2
-# CHECK-NEXT:   frame-destroy SEH_SaveRegP 25, 26, 16
-# CHECK-NEXT:   early-clobber $sp, $x27, $x28 = frame-destroy LDPXpost $sp, 10
-# CHECK-NEXT:   frame-destroy SEH_SaveRegP_X 27, 28, -80
+# CHECK-NEXT:   $x21, $x22 = frame-destroy LDPXi $sp, 2
+# CHECK-NEXT:   frame-destroy SEH_SaveRegP 21, 22, 16
+# CHECK-NEXT:   early-clobber $sp, $x19, $x20 = frame-destroy LDPXpost $sp, 10
+# CHECK-NEXT:   frame-destroy SEH_SaveRegP_X 19, 20, -80
 # CHECK-NEXT:   frame-destroy SEH_EpilogEnd
 # CHECK-NEXT:   RET_ReallyLR implicit $x0
 
 ...
 ---
 name:            test
 alignment:       4
 tracksRegLiveness: true

llvm/test/CodeGen/AArch64/wineh-frame1.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check save_fregp_x, save_fregp
 
-# CHECK:         early-clobber $sp = frame-setup STPDpre killed $d10, killed $d11, $sp, -14
-# CHECK-NEXT:    frame-setup SEH_SaveFRegP_X 10, 11, -112
-# CHECK-NEXT:    frame-setup STPDi killed $d8, killed $d9, $sp, 2
-# CHECK-NEXT:    frame-setup SEH_SaveFRegP 8, 9, 16
-# CHECK-NEXT:    frame-setup STPXi killed $x27, killed $x28, $sp, 4
-# CHECK-NEXT:    frame-setup SEH_SaveRegP 27, 28, 32
+# CHECK:         early-clobber $sp = frame-setup STPXpre killed $x19, killed $x20, $sp, -14
+# CHECK-NEXT:    frame-setup SEH_SaveRegP_X 19, 20, -112
+# CHECK-NEXT:    frame-setup STPXi killed $x21, killed $x22, $sp, 2
+# CHECK-NEXT:    frame-setup SEH_SaveRegP 21, 22, 16
+# CHECK-NEXT:    frame-setup STPXi killed $x23, killed $x24, $sp, 4
+# CHECK-NEXT:    frame-setup SEH_SaveRegP 23, 24, 32
 # CHECK-NEXT:    frame-setup STPXi killed $x25, killed $x26, $sp, 6
 # CHECK-NEXT:    frame-setup SEH_SaveRegP 25, 26, 48
-# CHECK-NEXT:    frame-setup STPXi killed $x23, killed $x24, $sp, 8
-# CHECK-NEXT:    frame-setup SEH_SaveRegP 23, 24, 64
-# CHECK-NEXT:    frame-setup STPXi killed $x21, killed $x22, $sp, 10
-# CHECK-NEXT:    frame-setup SEH_SaveRegP 21, 22, 80
-# CHECK-NEXT:    frame-setup STPXi killed $x19, killed $x20, $sp, 12
-# CHECK-NEXT:    frame-setup SEH_SaveRegP 19, 20, 96
+# CHECK-NEXT:    frame-setup STPXi killed $x27, killed $x28, $sp, 8
+# CHECK-NEXT:    frame-setup SEH_SaveRegP 27, 28, 64
+# CHECK-NEXT:    frame-setup STPDi killed $d8, killed $d9, $sp, 10
+# CHECK-NEXT:    frame-setup SEH_SaveFRegP 8, 9, 80
+# CHECK-NEXT:    frame-setup STPDi killed $d10, killed $d11, $sp, 12
+# CHECK-NEXT:    frame-setup SEH_SaveFRegP 10, 11, 96
 # CHECK-NEXT:    frame-setup SEH_PrologEnd
 # CHECK:         frame-destroy SEH_EpilogStart
-# CHECK-NEXT:    $x19, $x20 = frame-destroy LDPXi $sp, 12
-# CHECK-NEXT:    frame-destroy SEH_SaveRegP 19, 20, 96
-# CHECK-NEXT:    $x21, $x22 = frame-destroy LDPXi $sp, 10
-# CHECK-NEXT:    frame-destroy SEH_SaveRegP 21, 22, 80
-# CHECK-NEXT:    $x23, $x24 = frame-destroy LDPXi $sp, 8
-# CHECK-NEXT:    frame-destroy SEH_SaveRegP 23, 24, 64
+# CHECK-NEXT:    $d10, $d11 = frame-destroy LDPDi $sp, 12
+# CHECK-NEXT:    frame-destroy SEH_SaveFRegP 10, 11, 96
+# CHECK-NEXT:    $d8, $d9 = frame-destroy LDPDi $sp, 10
+# CHECK-NEXT:    frame-destroy SEH_SaveFRegP 8, 9, 80
+# CHECK-NEXT:    $x27, $x28 = frame-destroy LDPXi $sp, 8
+# CHECK-NEXT:    frame-destroy SEH_SaveRegP 27, 28, 64
 # CHECK-NEXT:    $x25, $x26 = frame-destroy LDPXi $sp, 6
 # CHECK-NEXT:    frame-destroy SEH_SaveRegP 25, 26, 48
-# CHECK-NEXT:    $x27, $x28 = frame-destroy LDPXi $sp, 4
-# CHECK-NEXT:    frame-destroy SEH_SaveRegP 27, 28, 32
-# CHECK-NEXT:    $d8, $d9 = frame-destroy LDPDi $sp, 2
-# CHECK-NEXT:    frame-destroy SEH_SaveFRegP 8, 9, 16
-# CHECK-NEXT:    early-clobber $sp, $d10, $d11 = frame-destroy LDPDpost $sp, 14
-# CHECK-NEXT:    frame-destroy SEH_SaveFRegP_X 10, 11, -112
+# CHECK-NEXT:    $x23, $x24 = frame-destroy LDPXi $sp, 4
+# CHECK-NEXT:    frame-destroy SEH_SaveRegP 23, 24, 32
+# CHECK-NEXT:    $x21, $x22 = frame-destroy LDPXi $sp, 2
+# CHECK-NEXT:    frame-destroy SEH_SaveRegP 21, 22, 16
+# CHECK-NEXT:    early-clobber $sp, $x19, $x20 = frame-destroy LDPXpost $sp, 14
+# CHECK-NEXT:    frame-destroy SEH_SaveRegP_X 19, 20, -112
 # CHECK-NEXT:    frame-destroy SEH_EpilogEnd
 # CHECK-NEXT:    RET_ReallyLR implicit $x0
 ...
 ---
 name:            test
 alignment:       4
 exposesReturnsTwice: false
 legalized:       false

llvm/test/CodeGen/AArch64/wineh-frame2.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check save_freg_x, save_frep, save_reg
 
-# CHECK:       early-clobber $sp = frame-setup STRDpre killed $d12, $sp, -48
-# CHECK-NEXT:  frame-setup SEH_SaveFReg_X 12, -48
-# CHECK-NEXT:  frame-setup STPDi killed $d10, killed $d11, $sp, 1
-# CHECK-NEXT:  frame-setup SEH_SaveFRegP 10, 11, 8
-# CHECK-NEXT:  frame-setup STPDi killed $d8, killed $d9, $sp, 3
-# CHECK-NEXT:  frame-setup SEH_SaveFRegP 8, 9, 24
-# CHECK-NEXT:  frame-setup STRXui killed $x19, $sp, 5
-# CHECK-NEXT:  frame-setup SEH_SaveReg 19, 40
+# CHECK:       early-clobber $sp = frame-setup STRXpre killed $x19, $sp, -48
+# CHECK-NEXT:  frame-setup SEH_SaveReg_X 19, -48
+# CHECK-NEXT:  frame-setup STPDi killed $d8, killed $d9, $sp, 1
+# CHECK-NEXT:  frame-setup SEH_SaveFRegP 8, 9, 8
+# CHECK-NEXT:  frame-setup STPDi killed $d10, killed $d11, $sp, 3
+# CHECK-NEXT:  frame-setup SEH_SaveFRegP 10, 11, 24
+# CHECK-NEXT:  frame-setup STRDui killed $d12, $sp, 5
+# CHECK-NEXT:  frame-setup SEH_SaveFReg 12, 40
 # CHECK-NEXT:  frame-setup SEH_PrologEnd
 # CHECK:       frame-destroy SEH_EpilogStart
-# CHECK-NEXT:  $x19 = frame-destroy LDRXui $sp, 5
-# CHECK-NEXT:  frame-destroy SEH_SaveReg 19, 40
-# CHECK-NEXT:  $d8, $d9 = frame-destroy LDPDi $sp, 3
-# CHECK-NEXT:  frame-destroy SEH_SaveFRegP 8, 9, 24
-# CHECK-NEXT:  $d10, $d11 = frame-destroy LDPDi $sp, 1
-# CHECK-NEXT:  frame-destroy SEH_SaveFRegP 10, 11, 8
-# CHECK-NEXT:  early-clobber $sp, $d12 = frame-destroy LDRDpost $sp, 48
-# CHECK-NEXT:  frame-destroy SEH_SaveFReg_X 12, -48
+# CHECK-NEXT:  $d12 = frame-destroy LDRDui $sp, 5
+# CHECK-NEXT:  frame-destroy SEH_SaveFReg 12, 40
+# CHECK-NEXT:  $d10, $d11 = frame-destroy LDPDi $sp, 3
+# CHECK-NEXT:  frame-destroy SEH_SaveFRegP 10, 11, 24
+# CHECK-NEXT:  $d8, $d9 = frame-destroy LDPDi $sp, 1
+# CHECK-NEXT:  frame-destroy SEH_SaveFRegP 8, 9, 8
+# CHECK-NEXT:  early-clobber $sp, $x19 = frame-destroy LDRXpost $sp, 48
+# CHECK-NEXT:  frame-destroy SEH_SaveReg_X 19, -48
 # CHECK-NEXT:  frame-destroy SEH_EpilogEnd
 # CHECK-NEXT:  RET_ReallyLR implicit $x0
 ...
 ---
 name:            test
 alignment:       4
 exposesReturnsTwice: false
 legalized:       false

llvm/test/CodeGen/AArch64/wineh-frame3.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check save_reg_x, save_reg
 
-# CHECK:      early-clobber $sp = frame-setup STRXpre killed $x22, $sp, -16
-# CHECK-NEXT: frame-setup SEH_SaveReg_X 22, -16
-# CHECK-NEXT: frame-setup STRXui killed $x19, $sp, 1
-# CHECK-NEXT: frame-setup SEH_SaveReg 19, 8
+# CHECK:      early-clobber $sp = frame-setup STRXpre killed $x19, $sp, -16
+# CHECK-NEXT: frame-setup SEH_SaveReg_X 19, -16
+# CHECK-NEXT: frame-setup STRXui killed $x22, $sp, 1
+# CHECK-NEXT: frame-setup SEH_SaveReg 22, 8
 # CHECK-NEXT: frame-setup SEH_PrologEnd
 # CHECK:      frame-destroy SEH_EpilogStart
-# CHECK-NEXT: $x19 = frame-destroy LDRXui $sp, 1
-# CHECK-NEXT: frame-destroy SEH_SaveReg 19, 8
-# CHECK-NEXT: early-clobber $sp, $x22 = frame-destroy LDRXpost $sp, 16
-# CHECK-NEXT: frame-destroy SEH_SaveReg_X 22, -16
+# CHECK-NEXT: $x22 = frame-destroy LDRXui $sp, 1
+# CHECK-NEXT: frame-destroy SEH_SaveReg 22, 8
+# CHECK-NEXT: early-clobber $sp, $x19 = frame-destroy LDRXpost $sp, 16
+# CHECK-NEXT: frame-destroy SEH_SaveReg_X 19, -16
 # CHECK-NEXT: frame-destroy SEH_EpilogEnd
 # CHECK-NEXT: RET_ReallyLR implicit $x0
 ...
 ---
 name:            test
 alignment:       4
 exposesReturnsTwice: false
 legalized:       false

llvm/test/CodeGen/AArch64/wineh-frame4.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check save_freg_x, save_freg
 
-# CHECK:       early-clobber $sp = frame-setup STRDpre killed $d10, $sp, -16
-# CHECK-NEXT:  frame-setup SEH_SaveFReg_X 10, -16
-# CHECK-NEXT:  frame-setup STRDui killed $d8, $sp, 1 :: (store 8 into %stack.0)
-# CHECK-NEXT:  frame-setup SEH_SaveFReg 8, 8
+# CHECK:       early-clobber $sp = frame-setup STRDpre killed $d8, $sp, -16
+# CHECK-NEXT:  frame-setup SEH_SaveFReg_X 8, -16
+# CHECK-NEXT:  frame-setup STRDui killed $d10, $sp, 1 :: (store 8 into %stack.0)
+# CHECK-NEXT:  frame-setup SEH_SaveFReg 10, 8
 # CHECK-NEXT:  frame-setup SEH_PrologEnd
 # CHECK:       frame-destroy SEH_EpilogStart
-# CHECK-NEXT:  $d8 = frame-destroy LDRDui $sp, 1 :: (load 8 from %stack.0)
-# CHECK-NEXT:  frame-destroy SEH_SaveFReg 8, 8
-# CHECK-NEXT:  early-clobber $sp, $d10 = frame-destroy LDRDpost $sp, 16 :: (load 8 from %stack.1)
-# CHECK-NEXT:  frame-destroy SEH_SaveFReg_X 10, -16
+# CHECK-NEXT:  $d10 = frame-destroy LDRDui $sp, 1 :: (load 8 from %stack.0)
+# CHECK-NEXT:  frame-destroy SEH_SaveFReg 10, 8
+# CHECK-NEXT:  early-clobber $sp, $d8 = frame-destroy LDRDpost $sp, 16 :: (load 8 from %stack.1)
+# CHECK-NEXT:  frame-destroy SEH_SaveFReg_X 8, -16
 # CHECK-NEXT:  frame-destroy SEH_EpilogEnd
 # CHECK-NEXT:  RET_ReallyLR implicit $x0
 ...
 ---
 name:            test
 alignment:       4
 exposesReturnsTwice: false
 legalized:       false

llvm/test/CodeGen/AArch64/wineh-frame5.mir

 # RUN: llc -o - %s -mtriple=aarch64-windows -start-before=prologepilog \
 # RUN:   -stop-after=prologepilog | FileCheck %s
 # Check multiple epilogues, save_reg, save_reg_x.
 
 # CHECK-LABEL:   bb.0.entry:
-# CHECK:         early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4
-# CHECK-NEXT:    frame-setup SEH_SaveFPLR_X -32
-# CHECK-NEXT:    frame-setup STRXui killed $x19, $sp, 2
-# CHECK-NEXT:    frame-setup SEH_SaveReg 19, 16
+# CHECK:         early-clobber $sp = frame-setup STRXpre killed $x19, $sp, -32
+# CHECK-NEXT:    frame-setup SEH_SaveReg_X 19, -32
+# CHECK-NEXT:    frame-setup STPXi killed $fp, killed $lr, $sp, 1
+# CHECK-NEXT:    frame-setup SEH_SaveFPLR 8
 # CHECK-NEXT:    $sp = frame-setup SUBXri $sp, 496, 0
 # CHECK-NEXT:    frame-setup SEH_StackAlloc 496
 # CHECK-NEXT:    frame-setup SEH_PrologEnd
 
 # CHECK-LABEL:   bb.1.if.then:
 # CHECK:         frame-destroy SEH_EpilogStart
 # CHECK-NEXT:    $sp = frame-destroy ADDXri $sp, 496, 0
 # CHECK-NEXT:    frame-destroy SEH_StackAlloc 496
-# CHECK-NEXT:    $x19 = frame-destroy LDRXui $sp, 2
-# CHECK-NEXT:    frame-destroy SEH_SaveReg 19, 16
-# CHECK-NEXT:    early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 4
-# CHECK-NEXT:    frame-destroy SEH_SaveFPLR_X -32
+# CHECK-NEXT:    $fp, $lr = frame-destroy LDPXi $sp, 1
+# CHECK-NEXT:    frame-destroy SEH_SaveFPLR 8
+# CHECK-NEXT:    early-clobber $sp, $x19 = frame-destroy LDRXpost $sp, 32
+# CHECK-NEXT:    frame-destroy SEH_SaveReg_X 19, -32
 # CHECK-NEXT:    frame-destroy SEH_EpilogEnd
 # CHECK-NEXT:    TCRETURNdi @"?func2@@YAHXZ", 0, csr_aarch64_aapcs, implicit $sp
 
 
 --- |
   target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
   target triple = "aarch64-unknown-windows-msvc19.11.0"
 

llvm/test/CodeGen/AArch64/wineh-try-catch-realign.ll

 ; RUN: llc -o - %s -mtriple=aarch64-windows -verify-machineinstrs | FileCheck %s
 
 ; Make sure we have a base pointer.
 ; CHECK-LABEL: "?a@@YAXXZ":
 ; CHECK: and     sp, x9, #0xffffffffffffffc0
 ; CHECK: mov     x19, sp
 
 ; Make sure the funclet prologue/epilogue are correct: specifically,
 ; it shouldn't access the parent's frame via sp, and the prologue and
 ; epilogue should be symmetrical.
 ; CHECK-LABEL: "?catch$2@?0??a@@YAXXZ@4HA":
-; CHECK:      stp     x29, x30, [sp, #-32]!
-; CHECK-NEXT: .seh_save_fplr_x 32
-; CHECK-NEXT: str     x28, [sp, #16]
-; CHECK-NEXT: .seh_save_reg x28, 16
-; CHECK-NEXT: str     x19, [sp, #24]
-; CHECK-NEXT: .seh_save_reg x19, 24
+; CHECK:      str     x19, [sp, #-32]!
+; CHECK-NEXT: .seh_save_reg_x x19, 32
+; CHECK-NEXT: str     x28, [sp, #8]
+; CHECK-NEXT: .seh_save_reg x28, 8
+; CHECK-NEXT: stp     x29, x30, [sp, #16]
+; CHECK-NEXT: .seh_save_fplr 16
 ; CHECK-NEXT: .seh_endprologue
 ; CHECK-NEXT: add     x0, x19, #0
 ; CHECK-NEXT: mov     w1, wzr
 ; CHECK-NEXT: bl      "?bb@@YAXPEAHH@Z"
 ; CHECK-NEXT: adrp    x0, .LBB0_1
 ; CHECK-NEXT: add     x0, x0, .LBB0_1
 ; CHECK-NEXT: .seh_startepilogue
-; CHECK-NEXT: ldr     x19, [sp, #24]
-; CHECK-NEXT: .seh_save_reg x19, 24
-; CHECK-NEXT: ldr     x28, [sp, #16]
-; CHECK-NEXT: .seh_save_reg x28, 16
-; CHECK-NEXT: ldp     x29, x30, [sp], #32
-; CHECK-NEXT: .seh_save_fplr_x 32
+; CHECK-NEXT: ldp     x29, x30, [sp, #16]
+; CHECK-NEXT: .seh_save_fplr 16
+; CHECK-NEXT: ldr     x28, [sp, #8]
+; CHECK-NEXT: .seh_save_reg x28, 8
+; CHECK-NEXT: ldr     x19, [sp], #32
+; CHECK-NEXT: .seh_save_reg_x x19, 32
 ; CHECK-NEXT: .seh_endepilogue
 ; CHECK-NEXT: ret
 
 
 target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-windows-msvc19.11.0"
 
 define dso_local void @"?a@@YAXXZ"() personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) {

llvm/test/CodeGen/AArch64/wineh-try-catch.ll

 ; 3) That the locals are accessed using the frame pointer in both the funclet
 ;    and the parent function.
 
 ; The following checks that the unwind help object has -2 stored into it at
 ; fp + 16, which is on-entry sp - 16.
 ; We check this offset in the table later on.
 
 ; CHECK-LABEL: "?func@@YAHXZ":
-; CHECK:       stp     x29, x30, [sp, #-64]!
-; CHECK:       str     x28, [sp, #16]
-; CHECK:       str     x21, [sp, #24]
-; CHECK:       stp     x19, x20, [sp, #32]
-; CHECK:       mov     x29, sp
+; CHECK:       stp     x19, x20, [sp, #-64]!
+; CHECK:       str     x21, [sp, #16]
+; CHECK:       str     x28, [sp, #24]
+; CHECK:       stp     x29, x30, [sp, #32]
+; CHECK:       add     x29, sp, #32
 ; CHECK:       sub     sp, sp, #624
 ; CHECK:       mov     x19, sp
 ; CHECK:       mov     x0, #-2
-; CHECK:       stur    x0, [x29, #48]
+; CHECK:       stur    x0, [x29, #16]
 
 ; Now check that x is stored at fp - 20.  We check that this is the same
 ; location accessed from the funclet to retrieve x.
 ; CHECK:       mov     w8, #1
 ; CHECK:       stur    w8, [x29, [[X_OFFSET:#-[1-9][0-9]+]]
 
 ; Check the offset off the frame pointer at which B is located.
 ; Check the same offset is used to pass the address of B to init2 in the
 ; funclet.
 ; CHECK:       sub     x0, x29, [[B_OFFSET:#[1-9][0-9]+]]
 ; CHECK:       bl      "?init@@YAXPEAH@Z"
 
 ; This is the label for the throw that is encoded in the ip2state.
 ; We are inside the try block, where we make a call to func2
 ; CHECK-LABEL: .Ltmp0:
 ; CHECK:       bl      "?func2@@YAHXZ
 
 ; CHECK:        [[CATCHRETDEST:.LBB0_[0-9]+]]:      ; %catchret.dest
 
 ; Check the catch funclet.
 ; CHECK-LABEL: "?catch$2@?0??func@@YAHXZ@4HA":
 
 ; Check that the stack space is allocated only for the callee saved registers.
-; CHECK:       stp     x29, x30, [sp, #-48]!
-; CHECK:       str     x28, [sp, #16]
-; CHECK:       str     x21, [sp, #24]
-; CHECK:       stp     x19, x20, [sp, #32]
+; CHECK:       stp     x19, x20, [sp, #-48]!
+; CHECK:       str     x21, [sp, #16]
+; CHECK:       str     x28, [sp, #24]
+; CHECK:       stp     x29, x30, [sp, #32]
 ; CHECK:       add     x20, x19, #12
 
 ; Check that there are no further stack updates.
 ; CHECK-NOT:   sub     sp, sp
 
 ; Check that the stack address passed to init2 is off the frame pointer, and
 ; that it matches the address of B in the parent function.
 ; CHECK:       sub     x0, x29, [[B_OFFSET]]

 ; CHECK-NEXT:         .word   4                       ; IPMapEntries
 ; CHECK-NEXT:         .word   ("$ip2state$?func@@YAHXZ")@IMGREL ; IPToStateXData
 ; CHECK-NEXT:         .word   -16                     ; UnwindHelp
 
 ; UNWIND: Function: ?func@@YAHXZ (0x0)
 ; UNWIND: Prologue [
 ; UNWIND-NEXT: ; nop
 ; UNWIND-NEXT: ; sub sp, #624
-; UNWIND-NEXT: ; mov fp, sp
-; UNWIND-NEXT: ; stp x19, x20, [sp, #32]
-; UNWIND-NEXT: ; str x21, [sp, #24]
-; UNWIND-NEXT: ; str x28, [sp, #16]
-; UNWIND-NEXT: ; stp x29, x30, [sp, #-64]!
+; UNWIND-NEXT: ; add fp, sp, #32
+; UNWIND-NEXT: ; stp x29, x30, [sp, #32]
+; UNWIND-NEXT: ; str x28, [sp, #24]
+; UNWIND-NEXT: ; str x21, [sp, #16]
+; UNWIND-NEXT: ; stp x19, x20, [sp, #-64]!
 ; UNWIND-NEXT: ; end
 ; UNWIND: Function: ?catch$2@?0??func@@YAHXZ@4HA
 ; UNWIND: Prologue [
-; UNWIND-NEXT: ; stp x19, x20, [sp, #32]
-; UNWIND-NEXT: ; str x21, [sp, #24]
-; UNWIND-NEXT: ; str x28, [sp, #16]
-; UNWIND-NEXT: ; stp x29, x30, [sp, #-48]!
+; UNWIND-NEXT: ; stp x29, x30, [sp, #32]
+; UNWIND-NEXT: ; str x28, [sp, #24]
+; UNWIND-NEXT: ; str x21, [sp, #16]
+; UNWIND-NEXT: ; stp x19, x20, [sp, #-48]!
 ; UNWIND-NEXT: ; end
 
 target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-windows-msvc19.11.0"
 
 %rtti.TypeDescriptor2 = type { i8**, i8*, [3 x i8] }
 %eh.CatchableType = type { i32, i32, i32, i32, i32, i32, i32 }
 %eh.CatchableTypeArray.1 = type { i32, [1 x i32] }

llvm/test/CodeGen/AArch64/wineh_shrinkwrap.mir

 # RUN: llc -O2 -o - %s -mtriple=aarch64-windows -start-before=shrink-wrap \
 # RUN:   -stop-after=prologepilog | FileCheck %s --check-prefix=WIN64
 # RUN: llc -O2 -o - %s -mtriple=aarch64-linux -start-before=shrink-wrap \
 # RUN:   -stop-after=prologepilog | FileCheck %s --check-prefix=LINUX
 
 # This tests checks that shrink wrapping bails out on Windows AMR64 due to the
 # use of Windows CFI.  We don't currently support fragments for WIndows EH on
 # ARM64.
 # The same test gets shrink wrapped on Linux ARM64.
 
 # WIN64-LABEL: bb.0.entry:
-# WIN64: early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4
+# WIN64: early-clobber $sp = frame-setup STRXpre killed $x19, $sp, -32
 # WIN64-LABEL: bb.1:
 # WIN64-LABEL: bb.2.if.then:
 
 # LINUX-LABEL: bb.0.entry:
 # LINUX-LABEL: bb.1:
 # LINUX-LABEL: bb.2.if.then:
 # LINUX: early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -32
 --- |