ARM: use callee-saved list in the order they're actually saved.

When setting the frame pointer, the offset from SP is calculated based on the
stack slot it gets allocated, but this slot is in turn based on the order of
the CSR list so that list should match the order we actually save the registers
in. Mostly it did, but in the edge-case of MachO AAPCS targets it was wrong.

llvm-svn: 269459

llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp

@@ -60,8 +60,11 @@ static unsigned getFramePointerReg(const ARMSubtarget &STI) {
 const MCPhysReg*
 ARMBaseRegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
   const ARMSubtarget &STI = MF->getSubtarget<ARMSubtarget>();
+  bool UseSplitPush = STI.splitFramePushPop();
   const MCPhysReg *RegList =
-      STI.isTargetDarwin() ? CSR_iOS_SaveList : CSR_AAPCS_SaveList;
+      STI.isTargetDarwin()
+          ? CSR_iOS_SaveList
+          : (UseSplitPush ? CSR_AAPCS_SplitPush_SaveList : CSR_AAPCS_SaveList);
 
   const Function *F = MF->getFunction();
   if (F->getCallingConv() == CallingConv::GHC) {
@@ -72,7 +75,7 @@ ARMBaseRegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
     if (STI.isMClass()) {
       // M-class CPUs have hardware which saves the registers needed to allow a
       // function conforming to the AAPCS to function as a handler.
-      return CSR_AAPCS_SaveList;
+      return UseSplitPush ? CSR_AAPCS_SplitPush_SaveList : CSR_AAPCS_SaveList;
     } else if (F->getFnAttribute("interrupt").getValueAsString() == "FIQ") {
       // Fast interrupt mode gives the handler a private copy of R8-R14, so less
       // need to be saved to restore user-mode state.

llvm/lib/Target/ARM/ARMCallingConv.td

@@ -246,6 +246,14 @@ def CSR_NoRegs : CalleeSavedRegs<(add)>;
 def CSR_AAPCS : CalleeSavedRegs<(add LR, R11, R10, R9, R8, R7, R6, R5, R4,
                                      (sequence "D%u", 15, 8))>;
 
+// The order of callee-saved registers needs to match the order we actually push
+// them in FrameLowering, because this order is what's used by
+// PrologEpilogInserter to allocate frame index slots. So when R7 is the frame
+// pointer, we use this AAPCS alternative.
+def CSR_AAPCS_SplitPush : CalleeSavedRegs<(add LR, R7, R6, R5, R4,
+                                               R11, R10, R9, R8,
+                                               (sequence "D%u", 15, 8))>;
+
 // Constructors and destructors return 'this' in the ARM C++ ABI; since 'this'
 // and the pointer return value are both passed in R0 in these cases, this can
 // be partially modelled by treating R0 as a callee-saved register

llvm/lib/Target/ARM/ARMFrameLowering.cpp

@@ -355,7 +355,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
     case ARM::R10:
     case ARM::R11:
     case ARM::R12:
-      if (STI.isTargetMachO()) {
+      if (STI.splitFramePushPop()) {
         GPRCS2Size += 4;
         break;
       }
@@ -559,7 +559,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
       case ARM::R10:
       case ARM::R11:
       case ARM::R12:
-        if (STI.isTargetMachO())
+        if (STI.splitFramePushPop())
           break;
         // fallthrough
       case ARM::R0:
@@ -592,7 +592,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
       case ARM::R10:
       case ARM::R11:
       case ARM::R12:
-        if (STI.isTargetMachO()) {
+        if (STI.splitFramePushPop()) {
           unsigned DwarfReg =  MRI->getDwarfRegNum(Reg, true);
           unsigned Offset = MFI->getObjectOffset(FI);
           unsigned CFIIndex = MMI.addFrameInst(
@@ -904,7 +904,7 @@ void ARMFrameLowering::emitPushInst(MachineBasicBlock &MBB,
     unsigned LastReg = 0;
     for (; i != 0; --i) {
       unsigned Reg = CSI[i-1].getReg();
-      if (!(Func)(Reg, STI.isTargetMachO())) continue;
+      if (!(Func)(Reg, STI.splitFramePushPop())) continue;
 
       // D-registers in the aligned area DPRCS2 are NOT spilled here.
       if (Reg >= ARM::D8 && Reg < ARM::D8 + NumAlignedDPRCS2Regs)
@@ -985,7 +985,7 @@ void ARMFrameLowering::emitPopInst(MachineBasicBlock &MBB,
     bool DeleteRet = false;
     for (; i != 0; --i) {
       unsigned Reg = CSI[i-1].getReg();
-      if (!(Func)(Reg, STI.isTargetMachO())) continue;
+      if (!(Func)(Reg, STI.splitFramePushPop())) continue;
 
       // The aligned reloads from area DPRCS2 are not inserted here.
       if (Reg >= ARM::D8 && Reg < ARM::D8 + NumAlignedDPRCS2Regs)
@@ -1549,7 +1549,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF,
     if (Spilled) {
       NumGPRSpills++;
 
-      if (!STI.isTargetMachO()) {
+      if (!STI.splitFramePushPop()) {
         if (Reg == ARM::LR)
           LRSpilled = true;
         CS1Spilled = true;
@@ -1571,7 +1571,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF,
         break;
       }
     } else {
-      if (!STI.isTargetMachO()) {
+      if (!STI.splitFramePushPop()) {
         UnspilledCS1GPRs.push_back(Reg);
         continue;
       }

llvm/lib/Target/ARM/ARMSubtarget.h

@@ -455,6 +455,13 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
     return isTargetMachO() ? (ReserveR9 || !HasV6Ops) : ReserveR9;
   }
 
+  /// Returns true if the frame setup is split into two separate pushes (first
+  /// r0-r7,lr then r8-r11), principally so that the frame pointer is adjacent
+  /// to lr.
+  bool splitFramePushPop() const {
+    return isTargetMachO();
+  }
+
   bool useStride4VFPs(const MachineFunction &MF) const;
 
   bool useMovt(const MachineFunction &MF) const;

llvm/lib/Target/ARM/Thumb1FrameLowering.cpp

@@ -151,7 +151,7 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF,
     case ARM::R9:
     case ARM::R10:
     case ARM::R11:
-      if (STI.isTargetMachO()) {
+      if (STI.splitFramePushPop()) {
         GPRCS2Size += 4;
         break;
       }
@@ -213,7 +213,7 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF,
     case ARM::R10:
     case ARM::R11:
     case ARM::R12:
-      if (STI.isTargetMachO())
+      if (STI.splitFramePushPop())
         break;
       // fallthough
     case ARM::R0:

llvm/test/CodeGen/ARM/macho-frame-offset.ll

@@ -0,0 +1,12 @@
+; RUN: llc -mtriple thumbv7m-apple-macho -disable-fp-elim -o - %s | FileCheck %s
+
+define void @func() {
+; CHECK-LABEL: func:
+; CHECK: push {r6, r7, lr}
+; CHECK: add r7, sp, #4
+  call void @bar()
+  call void asm sideeffect "", "~{r11}"()
+  ret void
+}
+
+declare void @bar()