Re-apply r214881: Fix return sequence on armv4 thumb

This reverts r214893, re-applying r214881 with the test case relaxed a bit to
satiate the build bots.

POP on armv4t cannot be used to change thumb state (unilke later non-m-class
architectures), therefore we need a different return sequence that uses 'bx'
instead:

  POP {r3}
  ADD sp, #offset
  BX r3

This patch also fixes an issue where the return value in r3 would get clobbered
for functions that return 128 bits of data. In that case, we generate this
sequence instead:

  MOV ip, r3
  POP {r3}
  ADD sp, #offset
  MOV lr, r3
  MOV r3, ip
  BX lr

http://reviews.llvm.org/D4748

llvm-svn: 214928

1 files changed, 59 insertions, 19 deletions

diff --git a/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp b/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp
index 05852d814aa..6deab4f0887 100644
--- a/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp
+++ b/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp
@@ -388,28 +388,65 @@ void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
     }
   }
 
-  if (ArgRegsSaveSize) {
-    // Unlike T2 and ARM mode, the T1 pop instruction cannot restore
-    // to LR, and we can't pop the value directly to the PC since
-    // we need to update the SP after popping the value. Therefore, we
-    // pop the old LR into R3 as a temporary.
-
+  bool IsV4PopReturn = false;
+  for (const CalleeSavedInfo &CSI : MFI->getCalleeSavedInfo())
+    if (CSI.getReg() == ARM::LR)
+      IsV4PopReturn = true;
+  IsV4PopReturn &= STI.hasV4TOps() && !STI.hasV5TOps();
+
+  // Unlike T2 and ARM mode, the T1 pop instruction cannot restore
+  // to LR, and we can't pop the value directly to the PC since
+  // we need to update the SP after popping the value. So instead
+  // we have to emit:
+  //   POP {r3}
+  //   ADD sp, #offset
+  //   BX r3
+  // If this would clobber a return value, then generate this sequence instead:
+  //   MOV ip, r3
+  //   POP {r3}
+  //   ADD sp, #offset
+  //   MOV lr, r3
+  //   MOV r3, ip
+  //   BX lr
+  if (ArgRegsSaveSize || IsV4PopReturn) {
     // Get the last instruction, tBX_RET
     MBBI = MBB.getLastNonDebugInstr();
     assert (MBBI->getOpcode() == ARM::tBX_RET);
-    // Epilogue for vararg functions: pop LR to R3 and branch off it.
-    AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
-      .addReg(ARM::R3, RegState::Define);
-
-    emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
-
-    MachineInstrBuilder MIB =
-      BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX_RET_vararg))
-      .addReg(ARM::R3, RegState::Kill);
-    AddDefaultPred(MIB);
-    MIB.copyImplicitOps(&*MBBI);
-    // erase the old tBX_RET instruction
-    MBB.erase(MBBI);
+    DebugLoc dl = MBBI->getDebugLoc();
+
+    if (AFI->getReturnRegsCount() <= 3) {
+      // Epilogue: pop saved LR to R3 and branch off it. 
+      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
+        .addReg(ARM::R3, RegState::Define);
+
+      emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
+
+      MachineInstrBuilder MIB =
+        BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX))
+        .addReg(ARM::R3, RegState::Kill);
+      AddDefaultPred(MIB);
+      MIB.copyImplicitOps(&*MBBI);
+      // erase the old tBX_RET instruction
+      MBB.erase(MBBI);
+    } else {
+      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
+        .addReg(ARM::R12, RegState::Define)
+        .addReg(ARM::R3, RegState::Kill));
+
+      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
+        .addReg(ARM::R3, RegState::Define);
+
+      emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
+
+      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
+        .addReg(ARM::LR, RegState::Define)
+        .addReg(ARM::R3, RegState::Kill));
+
+      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
+        .addReg(ARM::R3, RegState::Define)
+        .addReg(ARM::R12, RegState::Kill));
+      // Keep the tBX_RET instruction
+    }
   }
 }
 
@@ -476,6 +513,9 @@ restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
       // Special epilogue for vararg functions. See emitEpilogue
       if (isVarArg)
         continue;
+      // ARMv4T requires BX, see emitEpilogue
+      if (STI.hasV4TOps() && !STI.hasV5TOps())
+        continue;
       Reg = ARM::PC;
       (*MIB).setDesc(TII.get(ARM::tPOP_RET));
       MIB.copyImplicitOps(&*MI);