[AArch64] Rewrite stack frame handling for win64 vararg functions

The previous attempt, which made do with a single offset in
computeCalleeSaveRegisterPairs, wasn't quite enough. The previous
attempt only worked as long as CombineSPBump == true (since the
offset would be adjusted later in fixupCalleeSaveRestoreStackOffset).

Instead include the size for the fixed stack area used for win64
varargs in calculations in emitPrologue/emitEpilogue. The stack
consists of mainly three parts;
- AFI->getLocalStackSize()
- AFI->getCalleeSavedStackSize()
- FixedObject

Most of the places in the code which previously used the CSStackSize
now use PrologueSaveSize instead, which is the sum of the latter
two, while some cases which need exactly the middle one use
AFI->getCalleeSavedStackSize() explicitly instead of a local variable.

In addition to moving the offsetting into emitPrologue/emitEpilogue
(which fixes functions with CombineSPBump == false), also set the
frame pointer to point to the right location, where the frame pointer
and link register actually are stored. In addition to the prologue/epilogue,
this also requires changes to resolveFrameIndexReference.

Add tests for a function that keeps a frame pointer and another one
that uses a VLA.

Differential Revision: https://reviews.llvm.org/D35919

llvm-svn: 309744

1 files changed, 30 insertions, 22 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index 4907d082eda..7c6a9999040 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -506,19 +506,23 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
     return;
   }
 
-  auto CSStackSize = AFI->getCalleeSavedStackSize();
+  bool IsWin64 =
+      Subtarget.isCallingConvWin64(MF.getFunction()->getCallingConv());
+  unsigned FixedObject = IsWin64 ? alignTo(AFI->getVarArgsGPRSize(), 16) : 0;
+
+  auto PrologueSaveSize = AFI->getCalleeSavedStackSize() + FixedObject;
   // All of the remaining stack allocations are for locals.
-  AFI->setLocalStackSize(NumBytes - CSStackSize);
+  AFI->setLocalStackSize(NumBytes - PrologueSaveSize);
 
   bool CombineSPBump = shouldCombineCSRLocalStackBump(MF, NumBytes);
   if (CombineSPBump) {
     emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP, -NumBytes, TII,
                     MachineInstr::FrameSetup);
     NumBytes = 0;
-  } else if (CSStackSize != 0) {
+  } else if (PrologueSaveSize != 0) {
     MBBI = convertCalleeSaveRestoreToSPPrePostIncDec(MBB, MBBI, DL, TII,
-                                                     -CSStackSize);
-    NumBytes -= CSStackSize;
+                                                     -PrologueSaveSize);
+    NumBytes -= PrologueSaveSize;
   }
   assert(NumBytes >= 0 && "Negative stack allocation size!?");
 
@@ -532,8 +536,9 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
     ++MBBI;
   }
   if (HasFP) {
-    // Only set up FP if we actually need to. Frame pointer is fp = sp - 16.
-    int FPOffset = CSStackSize - 16;
+    // Only set up FP if we actually need to. Frame pointer is fp =
+    // sp - fixedobject - 16.
+    int FPOffset = AFI->getCalleeSavedStackSize() - 16;
     if (CombineSPBump)
       FPOffset += AFI->getLocalStackSize();
 
@@ -672,8 +677,8 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
     if (HasFP) {
       // Define the current CFA rule to use the provided FP.
       unsigned Reg = RegInfo->getDwarfRegNum(FramePtr, true);
-      unsigned CFIIndex = MF.addFrameInst(
-          MCCFIInstruction::createDefCfa(nullptr, Reg, 2 * StackGrowth));
+      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
+          nullptr, Reg, 2 * StackGrowth - FixedObject));
       BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
           .addCFIIndex(CFIIndex)
           .setMIFlags(MachineInstr::FrameSetup);
@@ -759,12 +764,16 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
   // AArch64TargetLowering::LowerCall figures out ArgumentPopSize and keeps
   // it as the 2nd argument of AArch64ISD::TC_RETURN.
 
-  auto CSStackSize = AFI->getCalleeSavedStackSize();
+  bool IsWin64 =
+      Subtarget.isCallingConvWin64(MF.getFunction()->getCallingConv());
+  unsigned FixedObject = IsWin64 ? alignTo(AFI->getVarArgsGPRSize(), 16) : 0;
+
+  auto PrologueSaveSize = AFI->getCalleeSavedStackSize() + FixedObject;
   bool CombineSPBump = shouldCombineCSRLocalStackBump(MF, NumBytes);
 
-  if (!CombineSPBump && CSStackSize != 0)
+  if (!CombineSPBump && PrologueSaveSize != 0)
     convertCalleeSaveRestoreToSPPrePostIncDec(
-        MBB, std::prev(MBB.getFirstTerminator()), DL, TII, CSStackSize);
+        MBB, std::prev(MBB.getFirstTerminator()), DL, TII, PrologueSaveSize);
 
   // Move past the restores of the callee-saved registers.
   MachineBasicBlock::iterator LastPopI = MBB.getFirstTerminator();
@@ -786,7 +795,7 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
     return;
   }
 
-  NumBytes -= CSStackSize;
+  NumBytes -= PrologueSaveSize;
   assert(NumBytes >= 0 && "Negative stack allocation size!?");
 
   if (!hasFP(MF)) {
@@ -796,7 +805,7 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
     if (RedZone && ArgumentPopSize == 0)
       return;
 
-    bool NoCalleeSaveRestore = CSStackSize == 0;
+    bool NoCalleeSaveRestore = PrologueSaveSize == 0;
     int StackRestoreBytes = RedZone ? 0 : NumBytes;
     if (NoCalleeSaveRestore)
       StackRestoreBytes += ArgumentPopSize;
@@ -815,7 +824,8 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
   // be able to save any instructions.
   if (MFI.hasVarSizedObjects() || AFI->isStackRealigned())
     emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::FP,
-                    -CSStackSize + 16, TII, MachineInstr::FrameDestroy);
+                    -AFI->getCalleeSavedStackSize() + 16, TII,
+                    MachineInstr::FrameDestroy);
   else if (NumBytes)
     emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::SP, NumBytes, TII,
                     MachineInstr::FrameDestroy);
@@ -845,7 +855,11 @@ int AArch64FrameLowering::resolveFrameIndexReference(const MachineFunction &MF,
   const AArch64RegisterInfo *RegInfo = static_cast<const AArch64RegisterInfo *>(
       MF.getSubtarget().getRegisterInfo());
   const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
-  int FPOffset = MFI.getObjectOffset(FI) + 16;
+  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();
   bool isFixed = MFI.isFixedObjectIndex(FI);
 
@@ -956,12 +970,6 @@ static void computeCalleeSaveRegisterPairs(
          "Odd number of callee-saved regs to spill!");
   int Offset = AFI->getCalleeSavedStackSize();
 
-  unsigned GPRSaveSize = AFI->getVarArgsGPRSize();
-  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
-  bool IsWin64 = Subtarget.isCallingConvWin64(MF.getFunction()->getCallingConv());
-  if (IsWin64)
-    Offset -= alignTo(GPRSaveSize, 16);
-
   for (unsigned i = 0; i < Count; ++i) {
     RegPairInfo RPI;
     RPI.Reg1 = CSI[i].getReg();