[AArch64] Break the dependency between FP and SP when possible.

When the SP in not changed because of realignment/VLAs etc., we restore the SP
by using the previous value of SP and not the FP. Breaking the dependency will
help in cases when the epilog of a callee is close to the epilog of the caller;
for then "sub sp, fp, #" depends on the load restoring the FP in the epilog of
the callee.

http://reviews.llvm.org/D18060
Patch by Aditya Kumar and Evandro Menezes.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@263458 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/AArch64/AArch64FrameLowering.cpp

@@ -396,6 +396,7 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
     BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
       .addReg(scratchSPReg, RegState::Kill)
       .addImm(andMaskEncoded);
+    AFI->setStackRealigned(true);
   }
 
   // If we need a base pointer, set it up here. It's whatever the value of the
@@ -607,10 +608,13 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
   // FIXME: Rather than doing the math here, we should instead just use
   // non-post-indexed loads for the restores if we aren't actually going to
   // be able to save any instructions.
-  if (NumBytes || MFI->hasVarSizedObjects())
+  if (MFI->hasVarSizedObjects() || AFI->isStackRealigned())
     emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::FP,
                     -AFI->getCalleeSavedStackSize() + 16, TII,
                     MachineInstr::FrameDestroy);
+  else if (NumBytes)
+    emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::SP, NumBytes, TII,
+                    MachineInstr::FrameDestroy);
 
   // This must be placed after the callee-save restore code because that code
   // assumes the SP is at the same location as it was after the callee-save save

lib/Target/AArch64/AArch64MachineFunctionInfo.h

@@ -79,18 +79,22 @@ class AArch64FunctionInfo : public MachineFunctionInfo {
   /// copies.
   bool IsSplitCSR;
 
+  /// True when the stack gets realigned dynamically because the size of stack
+  /// frame is unknown at compile time. e.g., in case of VLAs.
+  bool StackRealigned;
+
 public:
   AArch64FunctionInfo()
       : BytesInStackArgArea(0), ArgumentStackToRestore(0), HasStackFrame(false),
         NumLocalDynamicTLSAccesses(0), VarArgsStackIndex(0), VarArgsGPRIndex(0),
         VarArgsGPRSize(0), VarArgsFPRIndex(0), VarArgsFPRSize(0),
-        IsSplitCSR(false) {}
+        IsSplitCSR(false), StackRealigned(false) {}
 
   explicit AArch64FunctionInfo(MachineFunction &MF)
       : BytesInStackArgArea(0), ArgumentStackToRestore(0), HasStackFrame(false),
         NumLocalDynamicTLSAccesses(0), VarArgsStackIndex(0), VarArgsGPRIndex(0),
         VarArgsGPRSize(0), VarArgsFPRIndex(0), VarArgsFPRSize(0),
-        IsSplitCSR(false) {
+        IsSplitCSR(false), StackRealigned(false) {
     (void)MF;
   }
 
@@ -105,6 +109,9 @@ public:
   bool hasStackFrame() const { return HasStackFrame; }
   void setHasStackFrame(bool s) { HasStackFrame = s; }
 
+  bool isStackRealigned() const { return StackRealigned; }
+  void setStackRealigned(bool s) { StackRealigned = s; }
+
   bool isSplitCSR() const { return IsSplitCSR; }
   void setIsSplitCSR(bool s) { IsSplitCSR = s; }
 

test/CodeGen/AArch64/arm64-hello.ll

@@ -9,7 +9,7 @@
 ; CHECK:	adrp	x0, L_.str@PAGE
 ; CHECK:	add	x0, x0, L_.str@PAGEOFF
 ; CHECK-NEXT:	bl	_puts
-; CHECK-NEXT:	mov	sp, x29
+; CHECK-NEXT:	add	sp, sp, #16
 ; CHECK-NEXT:	ldp	x29, x30, [sp], #16
 ; CHECK-NEXT:	ret
 

test/CodeGen/AArch64/arm64-patchpoint.ll

@@ -29,7 +29,7 @@ entry:
 ; CHECK:       mov x29, sp
 ; CHECK-NEXT:  sub sp, sp, #32
 ; CHECK:       Ltmp
-; CHECK:       mov sp, x29
+; CHECK:       add sp, sp, #32
 ; CHECK:       ret
 
 define void @caller_meta_leaf() {

test/CodeGen/AArch64/arm64-shrink-wrapping.ll

@@ -33,8 +33,8 @@ target triple = "arm64-apple-ios"
 ; Without shrink-wrapping, epilogue is in the exit block.
 ; DISABLE: [[EXIT_LABEL]]:
 ; Epilogue code.
-; CHECK-NEXT: mov sp, [[SAVE_SP]]
-; CHECK-NEXT: ldp [[SAVE_SP]], [[CSR]], [sp], #16
+; CHECK-NEXT: add sp, sp, #16
+; CHECK-NEXT: ldp x{{[0-9]+}}, [[CSR]], [sp], #16
 ;
 ; With shrink-wrapping, exit block is a simple return.
 ; ENABLE: [[EXIT_LABEL]]:
@@ -473,7 +473,7 @@ if.end:                                           ; preds = %for.body, %if.else
 ; DISABLE: [[IFEND_LABEL]]: ; %if.end
 ;
 ; Epilogue code.
-; CHECK: mov sp, [[NEW_SP]]
+; CHECK: add sp, sp, #48
 ; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #16
 ; CHECK-NEXT: ret
 ;

test/CodeGen/AArch64/fastcc.ll

@@ -42,12 +42,12 @@ define fastcc void @func_stack0() {
 ; CHECK-TAIL-NOT: sub sp, sp
 
   ret void
-; CHECK: mov sp, x29
+; CHECK: add sp, sp, #32
 ; CHECK-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-NEXT: ret
 
 
-; CHECK-TAIL: mov sp, x29
+; CHECK-TAIL: add sp, sp, #32
 ; CHECK-TAIL-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-TAIL-NEXT: ret
 }
@@ -91,12 +91,12 @@ define fastcc void @func_stack8([8 x i32], i32 %stacked) {
 ; CHECK-TAIL-NOT: sub sp, sp
 
   ret void
-; CHECK: mov sp, x29
+; CHECK: add sp, sp, #32
 ; CHECK-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-NEXT: ret
 
 
-; CHECK-TAIL: mov sp, x29
+; CHECK-TAIL: add sp, sp, #32
 ; CHECK-TAIL-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-TAIL-NEXT: add     sp, sp, #16
 ; CHECK-TAIL-NEXT: ret
@@ -136,11 +136,11 @@ define fastcc void @func_stack32([8 x i32], i128 %stacked0, i128 %stacked1) {
 ; CHECK-TAIL-NOT: sub sp, sp
 
   ret void
-; CHECK: mov sp, x29
+; CHECK: add sp, sp, #32
 ; CHECK-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-NEXT: ret
 
-; CHECK-TAIL: mov sp, x29
+; CHECK-TAIL: add sp, sp, #32
 ; CHECK-TAIL-NEXT: ldp     x29, x30, [sp], #16
 ; CHECK-TAIL-NEXT: add     sp, sp, #32
 ; CHECK-TAIL-NEXT: ret