Attempt to fix dynamic stack realignment for thumb1 functions. It is in fact

useful if an optimization assumes the stack has been realigned.  Credit to
Eli for his assistance.
rdar://10043857

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140924 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
index 7c42342229a266bbd40086a59d88d594157ea3d3..48e3c524606bcdb787ea8217f220316d18811f16 100644 (file)
--- a/lib/Target/ARM/ARMBaseRegisterInfo.cpp
+++ b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
@@ -626,13 +626,10 @@ bool ARMBaseRegisterInfo::hasBasePointer(const MachineFunction &MF) const {
 
 bool ARMBaseRegisterInfo::canRealignStack(const MachineFunction &MF) const {
   const MachineFrameInfo *MFI = MF.getFrameInfo();
-  const ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
   // We can't realign the stack if:
   // 1. Dynamic stack realignment is explicitly disabled,
-  // 2. This is a Thumb1 function (it's not useful, so we don't bother), or
-  // 3. There are VLAs in the function and the base pointer is disabled.
-  return (RealignStack && !AFI->isThumb1OnlyFunction() &&
-          (!MFI->hasVarSizedObjects() || EnableBasePointer));
+  // 2. There are VLAs in the function and the base pointer is disabled.
+  return (RealignStack && (!MFI->hasVarSizedObjects() || EnableBasePointer));
 }
 
 bool ARMBaseRegisterInfo::

diff --git a/lib/Target/ARM/ARMFrameLowering.cpp b/lib/Target/ARM/ARMFrameLowering.cpp
index 2d1de6fe8e9d1a38b41606efb5dd515a4d33ae65..4bac6c5fa952bfa71d04c87cc0deaf6c9db961df 100644 (file)
--- a/lib/Target/ARM/ARMFrameLowering.cpp
+++ b/lib/Target/ARM/ARMFrameLowering.cpp
@@ -881,10 +881,12 @@ ARMFrameLowering::processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
     // for sure what the stack size will be, but for this, an estimate is good
     // enough. If there anything changes it, it'll be a spill, which implies
     // we've used all the registers and so R4 is already used, so not marking
-    // it here will be OK.
+    // it here will be OK.  Also spill R4 if Thumb1 function requires stack
+    // realignment.
     // FIXME: It will be better just to find spare register here.
     unsigned StackSize = estimateStackSize(MF);
-    if (MFI->hasVarSizedObjects() || StackSize > 508)
+    if (MFI->hasVarSizedObjects() || RegInfo->needsStackRealignment(MF) ||
+        StackSize > 508)
       MF.getRegInfo().setPhysRegUsed(ARM::R4);
   }
 

diff --git a/lib/Target/ARM/Thumb1FrameLowering.cpp b/lib/Target/ARM/Thumb1FrameLowering.cpp
index d4d59ea59da1171e77a3c2d0e814e42c7433f72c..9ff3ffcfa2b0d78fc898f476c923d53d1515843b 100644 (file)
--- a/lib/Target/ARM/Thumb1FrameLowering.cpp
+++ b/lib/Target/ARM/Thumb1FrameLowering.cpp
@@ -155,6 +155,27 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF) const {
   AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
   AFI->setDPRCalleeSavedAreaSize(DPRCSSize);
 
+  if (RegInfo->needsStackRealignment(MF)) {
+    // We cannot use sp as source/dest register here, thus we're emitting the
+    // following sequence:
+    // mov r4, sp
+    // lsrs r4, r4, Log2MaxAlign
+    // lsls r4, r4, Log2MaxAlign
+    // mov sp, r4
+    unsigned MaxAlign = MFI->getMaxAlignment();
+    unsigned Log2MaxAlign = Log2_32(MaxAlign);
+    AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::R4)
+                   .addReg(ARM::SP, RegState::Kill));
+    AddDefaultPred(AddDefaultT1CC(BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSRri), ARM::R4))
+                   .addReg(ARM::R4, RegState::Kill)
+                   .addImm(Log2MaxAlign));
+    AddDefaultPred(AddDefaultT1CC(BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSLri), ARM::R4))
+                   .addReg(ARM::R4, RegState::Kill)
+                   .addImm(Log2MaxAlign));
+    AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::SP)
+                   .addReg(ARM::R4, RegState::Kill));
+  }
+
   // If we need a base pointer, set it up here. It's whatever the value
   // of the stack pointer is at this point. Any variable size objects
   // will be allocated after this, so we can still use the base pointer