Target/X86: Tweak allocating shadow area (aka home) on Win64. It must be enough for caller to allocate one.

llvm-svn: 124949

3 files changed, 20 insertions, 9 deletions

diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
index 9722701ee20..0a3f931acf9 100644
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -397,11 +397,6 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
     if (HasFP) MinSize += SlotSize;
     StackSize = std::max(MinSize, StackSize > 128 ? StackSize - 128 : 0);
     MFI->setStackSize(StackSize);
-  } else if (IsWin64) {
-    // We need to always allocate 32 bytes as register spill area.
-    // FIXME: We might reuse these 32 bytes for leaf functions.
-    StackSize += 32;
-    MFI->setStackSize(StackSize);
   }
 
   // Insert stack pointer adjustment for later moving of return addr.  Only
diff --git a/llvm/lib/Target/X86/X86FrameLowering.h b/llvm/lib/Target/X86/X86FrameLowering.h
index c067e64fc01..d71108cd058 100644
--- a/llvm/lib/Target/X86/X86FrameLowering.h
+++ b/llvm/lib/Target/X86/X86FrameLowering.h
@@ -28,8 +28,7 @@ public:
   explicit X86FrameLowering(const X86TargetMachine &tm, const X86Subtarget &sti)
     : TargetFrameLowering(StackGrowsDown,
                           sti.getStackAlignment(),
-                          (sti.isTargetWin64() ? -40 :
-                           (sti.is64Bit() ? -8 : -4))),
+                          (sti.is64Bit() ? -8 : -4)),
       TM(tm), STI(sti) {
   }
 
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 69295f847ce..aa1301fd459 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -1544,6 +1544,12 @@ X86TargetLowering::LowerFormalArguments(SDValue Chain,
   SmallVector<CCValAssign, 16> ArgLocs;
   CCState CCInfo(CallConv, isVarArg, getTargetMachine(),
                  ArgLocs, *DAG.getContext());
+
+  // Allocate shadow area for Win64
+  if (IsWin64) {
+    CCInfo.AllocateStack(32, 8);
+  }
+
   CCInfo.AnalyzeFormalArguments(Ins, CC_X86);
 
   unsigned LastVal = ~0U;
@@ -1778,8 +1784,7 @@ X86TargetLowering::LowerMemOpCallTo(SDValue Chain,
                                     DebugLoc dl, SelectionDAG &DAG,
                                     const CCValAssign &VA,
                                     ISD::ArgFlagsTy Flags) const {
-  const unsigned FirstStackArgOffset = (Subtarget->isTargetWin64() ? 32 : 0);
-  unsigned LocMemOffset = FirstStackArgOffset + VA.getLocMemOffset();
+  unsigned LocMemOffset = VA.getLocMemOffset();
   SDValue PtrOff = DAG.getIntPtrConstant(LocMemOffset);
   PtrOff = DAG.getNode(ISD::ADD, dl, getPointerTy(), StackPtr, PtrOff);
   if (Flags.isByVal())
@@ -1864,6 +1869,12 @@ X86TargetLowering::LowerCall(SDValue Chain, SDValue Callee,
   SmallVector<CCValAssign, 16> ArgLocs;
   CCState CCInfo(CallConv, isVarArg, getTargetMachine(),
                  ArgLocs, *DAG.getContext());
+
+  // Allocate shadow area for Win64
+  if (IsWin64) {
+    CCInfo.AllocateStack(32, 8);
+  }
+
   CCInfo.AnalyzeCallOperands(Outs, CC_X86);
 
   // Get a count of how many bytes are to be pushed on the stack.
@@ -2447,6 +2458,12 @@ X86TargetLowering::IsEligibleForTailCallOptimization(SDValue Callee,
     SmallVector<CCValAssign, 16> ArgLocs;
     CCState CCInfo(CalleeCC, isVarArg, getTargetMachine(),
                    ArgLocs, *DAG.getContext());
+
+    // Allocate shadow area for Win64
+    if (Subtarget->isTargetWin64()) {
+      CCInfo.AllocateStack(32, 8);
+    }
+
     CCInfo.AnalyzeCallOperands(Outs, CC_X86);
     if (CCInfo.getNextStackOffset()) {
       MachineFunction &MF = DAG.getMachineFunction();