3 files changed, 50 insertions, 23 deletions

diff --git a/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
index 171b323..42159c9 100644
--- a/lib/Target/ARM/ARMBaseRegisterInfo.cpp
+++ b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
@@ -694,10 +694,11 @@ ARMBaseRegisterInfo::processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
   MachineFrameInfo *MFI = MF.getFrameInfo();
 
   // Spill R4 if Thumb2 function requires stack realignment - it will be used as
-  // scratch register.
+  // scratch register. Also spill R4 if Thumb2 function has varsized objects,
+  // since it's always posible to restore sp from fp in a single instruction.
   // FIXME: It will be better just to find spare register here.
-  if (needsStackRealignment(MF) &&
-      AFI->isThumb2Function())
+  if (AFI->isThumb2Function() &&
+      (MFI->hasVarSizedObjects() || needsStackRealignment(MF)))
     MF.getRegInfo().setPhysRegUsed(ARM::R4);
 
   // Spill LR if Thumb1 function uses variable length argument lists.
diff --git a/lib/Target/ARM/ARMFrameInfo.cpp b/lib/Target/ARM/ARMFrameInfo.cpp
index 7766b1f..62f3f98 100644
--- a/lib/Target/ARM/ARMFrameInfo.cpp
+++ b/lib/Target/ARM/ARMFrameInfo.cpp
@@ -17,6 +17,7 @@
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/Target/TargetOptions.h"
 
 using namespace llvm;
@@ -212,15 +213,21 @@ void ARMFrameInfo::emitPrologue(MachineFunction &MF) const {
   if (NumBytes) {
     // Adjust SP after all the callee-save spills.
     emitSPUpdate(isARM, MBB, MBBI, dl, TII, -NumBytes);
-    if (HasFP)
+    if (HasFP && isARM)
+      // Restore from fp only in ARM mode: e.g. sub sp, r7, #24
+      // Note it's not safe to do this in Thumb2 mode because it would have
+      // taken two instructions:
+      // mov sp, r7
+      // sub sp, #24
+      // If an interrupt is taken between the two instructions, then sp is in
+      // an inconsistent state (pointing to the middle of callee-saved area).
+      // The interrupt handler can end up clobbering the registers.
       AFI->setShouldRestoreSPFromFP(true);
   }
 
-  if (STI.isTargetELF() && hasFP(MF)) {
+  if (STI.isTargetELF() && hasFP(MF))
     MFI->setOffsetAdjustment(MFI->getOffsetAdjustment() -
                              AFI->getFramePtrSpillOffset());
-    AFI->setShouldRestoreSPFromFP(true);
-  }
 
   AFI->setGPRCalleeSavedArea1Size(GPRCS1Size);
   AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
@@ -275,7 +282,7 @@ void ARMFrameInfo::emitPrologue(MachineFunction &MF) const {
 
   // If the frame has variable sized objects then the epilogue must restore
   // the sp from fp.
-  if (!AFI->shouldRestoreSPFromFP() && MFI->hasVarSizedObjects())
+  if (MFI->hasVarSizedObjects())
     AFI->setShouldRestoreSPFromFP(true);
 }
 
@@ -326,9 +333,21 @@ void ARMFrameInfo::emitEpilogue(MachineFunction &MF,
         if (isARM)
           emitARMRegPlusImmediate(MBB, MBBI, dl, ARM::SP, FramePtr, -NumBytes,
                                   ARMCC::AL, 0, TII);
-        else
-          emitT2RegPlusImmediate(MBB, MBBI, dl, ARM::SP, FramePtr, -NumBytes,
+        else {
+          // It's not possible to restore SP from FP in a single instruction.
+          // For Darwin, this looks like:
+          // mov sp, r7
+          // sub sp, #24
+          // This is bad, if an interrupt is taken after the mov, sp is in an
+          // inconsistent state.
+          // Use the first callee-saved register as a scratch register.
+          assert(MF.getRegInfo().isPhysRegUsed(ARM::R4) &&
+                 "No scratch register to restore SP from FP!");
+          emitT2RegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
                                  ARMCC::AL, 0, TII);
+          BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVgpr2gpr), ARM::SP)
+            .addReg(ARM::R4);
+        }
       } else {
         // Thumb2 or ARM.
         if (isARM)
diff --git a/lib/Target/ARM/Thumb1FrameInfo.cpp b/lib/Target/ARM/Thumb1FrameInfo.cpp
index 6a3c1e1..bb1faf5 100644
--- a/lib/Target/ARM/Thumb1FrameInfo.cpp
+++ b/lib/Target/ARM/Thumb1FrameInfo.cpp
@@ -17,6 +17,7 @@
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
 
 using namespace llvm;
 
@@ -117,13 +118,6 @@ void Thumb1FrameInfo::emitPrologue(MachineFunction &MF) const {
       dl = MBBI->getDebugLoc();
   }
 
-  // Adjust FP so it point to the stack slot that contains the previous FP.
-  if (hasFP(MF)) {
-    BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
-      .addFrameIndex(FramePtrSpillFI).addImm(0);
-    AFI->setShouldRestoreSPFromFP(true);
-  }
-
   // Determine starting offsets of spill areas.
   unsigned DPRCSOffset  = NumBytes - (GPRCS1Size + GPRCS2Size + DPRCSSize);
   unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
@@ -132,12 +126,21 @@ void Thumb1FrameInfo::emitPrologue(MachineFunction &MF) const {
   AFI->setGPRCalleeSavedArea1Offset(GPRCS1Offset);
   AFI->setGPRCalleeSavedArea2Offset(GPRCS2Offset);
   AFI->setDPRCalleeSavedAreaOffset(DPRCSOffset);
-
   NumBytes = DPRCSOffset;
-  if (NumBytes) {
+
+  // Adjust FP so it point to the stack slot that contains the previous FP.
+  if (hasFP(MF)) {
+    BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
+      .addFrameIndex(FramePtrSpillFI).addImm(0);
+    if (NumBytes > 7)
+      // If offset is > 7 then sp cannot be adjusted in a single instruction,
+      // try restoring from fp instead.
+      AFI->setShouldRestoreSPFromFP(true);
+  }
+
+  if (NumBytes)
     // Insert it after all the callee-save spills.
     emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes);
-  }
 
   if (STI.isTargetELF() && hasFP(MF))
     MFI->setOffsetAdjustment(MFI->getOffsetAdjustment() -
@@ -219,10 +222,14 @@ void Thumb1FrameInfo::emitEpilogue(MachineFunction &MF,
       NumBytes = AFI->getFramePtrSpillOffset() - NumBytes;
       // Reset SP based on frame pointer only if the stack frame extends beyond
       // frame pointer stack slot or target is ELF and the function has FP.
-      if (NumBytes)
-        emitThumbRegPlusImmediate(MBB, MBBI, ARM::SP, FramePtr, -NumBytes,
+      if (NumBytes) {
+        assert(MF.getRegInfo().isPhysRegUsed(ARM::R4) &&
+               "No scratch register to restore SP from FP!");
+        emitThumbRegPlusImmediate(MBB, MBBI, ARM::R4, FramePtr, -NumBytes,
                                   TII, *RegInfo, dl);
-      else
+        BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVtgpr2gpr), ARM::SP)
+          .addReg(ARM::R4);
+      } else
         BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVtgpr2gpr), ARM::SP)
           .addReg(FramePtr);
     } else {