1 files changed, 18 insertions, 6 deletions
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index d33ebdd..0d52b00 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -579,6 +579,12 @@ static bool windowsRequiresStackProbe(MachineFunction &MF,
          !F.hasFnAttribute("no-stack-arg-probe");
 }
 
+static bool needsWinCFI(const MachineFunction &MF) {
+  const Function &F = MF.getFunction();
+  return MF.getTarget().getMCAsmInfo()->usesWindowsCFI() &&
+         F.needsUnwindTableEntry();
+}
+
 bool AArch64FrameLowering::shouldCombineCSRLocalStackBump(
     MachineFunction &MF, uint64_t StackBumpBytes) const {
   AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
@@ -589,6 +595,18 @@ bool AArch64FrameLowering::shouldCombineCSRLocalStackBump(
   if (AFI->getLocalStackSize() == 0)
     return false;
 
+  // For WinCFI, if optimizing for size, prefer to not combine the stack bump
+  // (to force a stp with predecrement) to match the packed unwind format,
+  // provided that there actually are any callee saved registers to merge the
+  // decrement with.
+  // This is potentially marginally slower, but allows using the packed
+  // unwind format for functions that both have a local area and callee saved
+  // registers. Using the packed unwind format notably reduces the size of
+  // the unwind info.
+  if (needsWinCFI(MF) && AFI->getCalleeSavedStackSize() > 0 &&
+      MF.getFunction().hasOptSize())
+    return false;
+
   // 512 is the maximum immediate for stp/ldp that will be used for
   // callee-save save/restores
   if (StackBumpBytes >= 512 || windowsRequiresStackProbe(MF, StackBumpBytes))
@@ -982,12 +1000,6 @@ static void adaptForLdStOpt(MachineBasicBlock &MBB,
   //
 }
 
-static bool needsWinCFI(const MachineFunction &MF) {
-  const Function &F = MF.getFunction();
-  return MF.getTarget().getMCAsmInfo()->usesWindowsCFI() &&
-         F.needsUnwindTableEntry();
-}
-
 static bool isTargetWindows(const MachineFunction &MF) {
   return MF.getSubtarget<AArch64Subtarget>().isTargetWindows();
 }