Add support for dynamic stack realignment when in thumb1 mode.

rdar://10288916


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142337 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 72 insertions, 11 deletions

diff --git a/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
index 7c42342229..48e3c52460 100644
--- 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 2d1de6fe8e..4bac6c5fa9 100644
--- 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 d8481778c0..ad1edc8dd8 100644
--- a/lib/Target/ARM/Thumb1FrameLowering.cpp
+++ b/lib/Target/ARM/Thumb1FrameLowering.cpp
@@ -155,10 +155,32 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF) const {
   AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
   AFI->setDPRCalleeSavedAreaSize(DPRCSSize);
 
-  // Thumb1 does not currently support dynamic stack realignment.  Report a
-  // fatal error rather then silently generate bad code.
-  if (RegInfo->needsStackRealignment(MF))
-      report_fatal_error("Dynamic stack realignment not supported for thumb1.");
+  // If we need dynamic stack realignment, do it here. Be paranoid and make
+  // sure if we also have VLAs, we have a base pointer for frame access.
+  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));
+
+    AFI->setShouldRestoreSPFromFP(true);    
+  }
 
   // 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
diff --git a/test/CodeGen/ARM/thumb1-dynrealign.ll b/test/CodeGen/ARM/thumb1-dynrealign.ll
new file mode 100644
index 0000000000..fa14fb42a3
--- /dev/null
+++ b/test/CodeGen/ARM/thumb1-dynrealign.ll
@@ -0,0 +1,40 @@
+; RUN: llc < %s -mtriple=thumbv6-apple-darwin | FileCheck %s
+
+; Normal load from SP
+define void @SP(i32 %i) nounwind uwtable ssp {
+entry:
+; CHECK: @SP
+; CHECK: push	{r7, lr}
+; CHECK-NEXT: mov r7, sp
+; CHECK-NEXT: sub sp, #4
+; CHECK-NEXT: mov r1, sp 
+; CHECK-NEXT: str r0, [r1]
+; CHECK-NEXT: mov r0, sp
+; CHECK-NEXT: blx _SP_
+; CHECK-NEXT: add sp, #4
+; CHECK-NEXT: pop {r7, pc}
+  %i.addr = alloca i32, align 4
+  store i32 %i, i32* %i.addr, align 4
+  call void @SP_(i32* %i.addr)
+  ret void
+}
+
+declare void @SP_(i32*)
+
+; Dynamic stack realignment
+define void @FP(double %a) nounwind uwtable ssp {
+entry:
+; CHECK: mov r4, sp
+; CHECK-NEXT: lsrs r4, r4, #3
+; CHECK-NEXT: lsls r4, r4, #3
+; CHECK-NEXT: mov sp, r4
+; Restore from FP
+; CHECK: subs r4, r7, #4
+; CHECK: mov sp, r4
+  %a.addr = alloca double, align 8
+  store double %a, double* %a.addr, align 8
+  call void @FP_(double* %a.addr)
+  ret void
+}
+
+declare void @FP_(double*)