[GlobalISel] Defer setting HasCalls on MachineFrameInfo to selection time.

[aemerson]

Summary

We currently always set the HasCalls on MFI during translation and legalization if we're handling a call or legalizing to a libcall. However, if that call is later optimized to a tail call then we don't need the flag. The flag being set to true causes frame lowering to always save and restore FP/LR, which adds unnecessary code.

This change does the same thing as SelectionDAG and ports over some code that scans instructions after selection, using TargetInstrInfo to determine if target opcodes are known calls.

Code size geomean improvements on CTMark:
-O0 : 0.1%
-Os : 0.3%

[arsenm]

LGTM. This also solves reporting calls for things lowered to libcalls

llvm/lib/CodeGen/GlobalISel/InstructionSelect.cpp

237–238

You can check theses directly on MI

llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp

if (CLI->supportSwiftError() && isSwiftError(Arg)) {
       Args.emplace_back(makeArrayRef(SwiftInVReg));
       SwiftErrorVReg =
           SwiftError.getOrCreateVRegDefAt(&I, &MIRBuilder.getMBB(), Arg);
       continue;
     }
     Args.push_back(getOrCreateVRegs(*Arg));
   }
 
-  MF->getFrameInfo().setHasCalls(true);
+  // We don't set HasCalls on MFI here yet because call lowering may decide to
+  // optimize into tail calls. Instead, we defer that to selection where a final
+  // scan is done to check if any instructions are calls.
   bool Success =
       CLI->lowerCall(MIRBuilder, CS, Res, Args, SwiftErrorVReg,
                      [&]() { return getOrCreateVReg(*CS.getCalledValue()); });
 
   // Check if we just inserted a tail call.
   if (Success) {
     assert(!HasTailCall && "Can't tail call return twice from block?");
     const TargetInstrInfo *TII = MF->getSubtarget().getInstrInfo();

llvm/lib/CodeGen/GlobalISel/InstructionSelect.cpp

 #include "llvm/CodeGen/GlobalISel/InstructionSelect.h"
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
 #include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
 #include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
 #include "llvm/CodeGen/GlobalISel/Utils.h"
 #include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h"
+#include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/Config/config.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
if (MF.size() != NumBlocks) {
     R << "inserting blocks is not supported yet";
     reportGISelFailure(MF, TPC, MORE, R);
     return false;
   }
 #endif
   auto &TLI = *MF.getSubtarget().getTargetLowering();
   TLI.finalizeLowering(MF);
 
+  // Determine if there are any calls in this machine function. Ported from
+  // SelectionDAG.
+  auto *TII = MF.getSubtarget().getInstrInfo();
+  MachineFrameInfo &MFI = MF.getFrameInfo();
+  for (const auto &MBB : MF) {
+    if (MFI.hasCalls() && MF.hasInlineAsm())
+      break;
+
+    for (const auto &MI : MBB) {
+      const MCInstrDesc &MCID = TII->get(MI.getOpcode());
+      if ((MCID.isCall() && !MCID.isReturn()) ||
+          MI.isStackAligningInlineAsm()) {
+        MFI.setHasCalls(true);
+      }
+      if (MI.isInlineAsm()) {
+        MF.setHasInlineAsm(true);
+      }
+    }
+  }
+
+
   LLVM_DEBUG({
     dbgs() << "Rules covered by selecting function: " << MF.getName() << ":";
     for (auto RuleID : CoverageInfo.covered())
       dbgs() << " id" << RuleID;
     dbgs() << "\n\n";
   });
   CoverageInfo.emit(CoveragePrefix,
                     MF.getSubtarget()

llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp

 LegalizerHelper::LegalizeResult
 llvm::createLibcall(MachineIRBuilder &MIRBuilder, RTLIB::Libcall Libcall,
                     const CallLowering::ArgInfo &Result,
                     ArrayRef<CallLowering::ArgInfo> Args) {
   auto &CLI = *MIRBuilder.getMF().getSubtarget().getCallLowering();
   auto &TLI = *MIRBuilder.getMF().getSubtarget().getTargetLowering();
   const char *Name = TLI.getLibcallName(Libcall);
 
-  MIRBuilder.getMF().getFrameInfo().setHasCalls(true);
-
   CallLowering::CallLoweringInfo Info;
   Info.CallConv = TLI.getLibcallCallingConv(Libcall);
   Info.Callee = MachineOperand::CreateES(Name);
   Info.OrigRet = Result;
   std::copy(Args.begin(), Args.end(), std::back_inserter(Info.OrigArgs));
   if (!CLI.lowerCall(MIRBuilder, Info))
     return LegalizerHelper::UnableToLegalize;
 
case Intrinsic::memmove:
     RTLibcall = RTLIB::MEMMOVE;
     break;
   default:
     return LegalizerHelper::UnableToLegalize;
   }
   const char *Name = TLI.getLibcallName(RTLibcall);
 
   MIRBuilder.setInstr(MI);
-  MIRBuilder.getMF().getFrameInfo().setHasCalls(true);
 
   CallLowering::CallLoweringInfo Info;
   Info.CallConv = TLI.getLibcallCallingConv(RTLibcall);
   Info.Callee = MachineOperand::CreateES(Name);
   Info.OrigRet = CallLowering::ArgInfo({0}, Type::getVoidTy(Ctx));
   Info.IsTailCall = isLibCallInTailPosition(MI);
 
   std::copy(Args.begin(), Args.end(), std::back_inserter(Info.OrigArgs));

llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll

 ; CHECK: $w1 = COPY [[LD3]](s32)
 ; CHECK: RET_ReallyLR implicit $d0, implicit $x0, implicit $w1
 define {double, i64, i32} @test_struct_return({double, i64, i32}* %addr) {
   %val = load {double, i64, i32}, {double, i64, i32}* %addr
   ret {double, i64, i32} %val
 }
 
 ; CHECK-LABEL: name: test_arr_call
-; CHECK: hasCalls: true
 ; CHECK: %0:_(p0) = COPY $x0
 ; CHECK: [[LD1:%[0-9]+]]:_(s64) = G_LOAD %0(p0) :: (load 8 from %ir.addr)
 ; CHECK: [[CST1:%[0-9]+]]:_(s64) = G_CONSTANT i64 8
 ; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_GEP %0, [[CST1]](s64)
 ; CHECK: [[LD2:%[0-9]+]]:_(s64) = G_LOAD [[GEP1]](p0) :: (load 8 from %ir.addr + 8)
 ; CHECK: [[CST2:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
 ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_GEP %0, [[CST2]](s64)
 ; CHECK: [[LD3:%[0-9]+]]:_(s64) = G_LOAD [[GEP2]](p0) :: (load 8 from %ir.addr + 16)

llvm/test/CodeGen/AArch64/GlobalISel/tail-call-no-save-fp-lr.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc %s -verify-machineinstrs -mtriple aarch64-apple-darwin -global-isel -global-isel-abort=1 -o - 2>&1 | FileCheck %s
+
+; Check that we get a tail call to foo without saving fp/lr.
+define void @bar(i32 %a) #1 {
+; CHECK-LABEL: bar:
+; CHECK:       ; %bb.0: ; %entry
+; CHECK-NEXT:    b _zoo
+entry:
+  tail call void @zoo(i32 undef)
+  ret void
+}
+
+define void @zoo(i32 %a) {
+entry:
+  ret void
+}
+
+attributes #1 = { "frame-pointer"="all" }
+