X86: Allow conditional tail calls in Win64 "leaf" functions (PR26302)

[hans]

Summary

We can't use Jcc to leave a Win64 function in general, because that confuses the unwinder. However, for "leaf" functions, that is, functions where the return address is always on top of the stack and which don't have unwind info, it's OK.

This depends on https://reviews.llvm.org/D24748

[rnk]

lgtm

llvm/trunk/lib/Target/X86/X86ExpandPseudo.cpp

if (Opcode == X86::TCRETURNdi || Opcode == X86::TCRETURNdicc ||
       switch (Opcode) {
       case X86::TCRETURNdi:
         Op = X86::TAILJMPd;
         break;
       case X86::TCRETURNdicc:
         Op = X86::TAILJMPd_CC;
         break;
       case X86::TCRETURNdi64cc:
-        assert(!IsWin64 && "Conditional tail calls confuse the Win64 unwinder.");
-        // TODO: We could do it for Win64 "leaf" functions though; PR30337.
+        assert(!MBB.getParent()->hasWinCFI() &&
+               "Conditional tail calls confuse "
+               "the Win64 unwinder.");
         Op = X86::TAILJMPd64_CC;
         break;
       default:
         // Note: Win64 uses REX prefixes indirect jumps out of functions, but
         // not direct ones.
         Op = X86::TAILJMPd64;
         break;
       }

llvm/trunk/lib/Target/X86/X86InstrInfo.cpp

bool X86InstrInfo::canMakeTailCallConditional(
     SmallVectorImpl<MachineOperand> &BranchCond,
     const MachineInstr &TailCall) const {
   if (TailCall.getOpcode() != X86::TCRETURNdi &&
       TailCall.getOpcode() != X86::TCRETURNdi64) {
     // Only direct calls can be done with a conditional branch.
     return false;
   }
 
-  if (Subtarget.isTargetWin64()) {
+  const MachineFunction *MF = TailCall.getParent()->getParent();
+  if (Subtarget.isTargetWin64() && MF->hasWinCFI()) {
     // Conditional tail calls confuse the Win64 unwinder.
-    // TODO: Allow them for "leaf" functions; PR30337.
     return false;
   }
 
   assert(BranchCond.size() == 1);
   if (BranchCond[0].getImm() > X86::LAST_VALID_COND) {
     // Can't make a conditional tail call with this condition.
     return false;
   }
 
-  const X86MachineFunctionInfo *X86FI =
-      TailCall.getParent()->getParent()->getInfo<X86MachineFunctionInfo>();
+  const X86MachineFunctionInfo *X86FI = MF->getInfo<X86MachineFunctionInfo>();
   if (X86FI->getTCReturnAddrDelta() != 0 ||
       TailCall.getOperand(1).getImm() != 0) {
     // A conditional tail call cannot do any stack adjustment.
     return false;
   }
 
   return true;
 }

llvm/trunk/test/CodeGen/X86/conditional-tailcall.ll

-; RUN: llc < %s -mtriple=i686-linux -show-mc-encoding | FileCheck %s
-; RUN: llc < %s -mtriple=x86_64-linux -show-mc-encoding | FileCheck %s
+; RUN: llc < %s -mtriple=i686-linux -show-mc-encoding | FileCheck -check-prefix=CHECK %s
+; RUN: llc < %s -mtriple=x86_64-linux -show-mc-encoding | FileCheck -check-prefix=CHECK %s
+; RUN: llc < %s -mtriple=x86_64-win32 -show-mc-encoding | FileCheck -check-prefix=CHECK -check-prefix=WIN64 %s
 
 declare void @foo()
 declare void @bar()
 
 define void @f(i32 %x, i32 %y) optsize {
 entry:
   %p = icmp eq i32 %x, %y
   br i1 %p, label %bb1, label %bb2
 bb1:
   tail call void @foo()
   ret void
 bb2:
   tail call void @bar()
   ret void
 
 ; CHECK-LABEL: f:
 ; CHECK: cmp
 ; CHECK: jne bar
 ; Check that the asm doesn't just look good, but uses the correct encoding.
 ; CHECK: encoding: [0x75,A]
 ; CHECK: jmp foo
 }
 
+define void @f_non_leaf(i32 %x, i32 %y) optsize {
+entry:
+  ; Force %ebx to be spilled on the stack, turning this into
+  ; not a "leaf" function for Win64.
+  tail call void asm sideeffect "", "~{ebx}"()
+
+  %p = icmp eq i32 %x, %y
+  br i1 %p, label %bb1, label %bb2
+bb1:
+  tail call void @foo()
+  ret void
+bb2:
+  tail call void @bar()
+  ret void
+
+; CHECK-LABEL: f_non_leaf:
+; WIN64-NOT: je foo
+; WIN64-NOT: jne bar
+; WIN64: jne
+; WIN64: jmp foo
+; WIN64: jmp bar
+}
 
 declare x86_thiscallcc zeroext i1 @baz(i8*, i32)
 define x86_thiscallcc zeroext i1 @BlockPlacementTest(i8* %this, i32 %x) optsize {
 entry:
   %and = and i32 %x, 42
   %tobool = icmp eq i32 %and, 0
   br i1 %tobool, label %land.end, label %land.rhs