[CGP] Be less conservative about tail-duplicating a ret to allow tail calls

CGP tail-duplicates rets into blocks that end with a call that feed the ret.
This puts the call in tail position, potentially allowing the DAG builder to
lower it as a tail call. To avoid tail duplication in cases where we won't
form the tail call, CGP tried to predict whether this is going to be possible,
and avoids doing it when lowering as a tail call will definitely fail.
However, it was being too conservative by always throwing away calls to
functions with a signext/zeroext attribute on the return type.

Instead, we can use the same logic the builder uses to determine whether the
attributes work out.

Differential Revision: https://reviews.llvm.org/D24315


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@280894 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/CodeGen/Analysis.h

@@ -105,11 +105,21 @@ ISD::CondCode getICmpCondCode(ICmpInst::Predicate Pred);
 /// This function only tests target-independent requirements.
 bool isInTailCallPosition(ImmutableCallSite CS, const TargetMachine &TM);
 
+/// Test if given that the input instruction is in the tail call position, if
+/// there is an attribute mismatch between the caller and the callee that will
+/// inhibit tail call optimizations.
+/// \p AllowDifferingSizes is an output parameter which, if forming a tail call
+/// is permitted, determines whether it's permitted only if the size of the
+/// caller's and callee's return types match exactly.
+bool attributesPermitTailCall(const Function *F, const Instruction *I,
+                              const ReturnInst *Ret,
+                              const TargetLoweringBase &TLI,
+                              bool *AllowDifferingSizes = nullptr);
+
 /// Test if given that the input instruction is in the tail call position if the
 /// return type or any attributes of the function will inhibit tail call
 /// optimization.
-bool returnTypeIsEligibleForTailCall(const Function *F,
-                                     const Instruction *I,
+bool returnTypeIsEligibleForTailCall(const Function *F, const Instruction *I,
                                      const ReturnInst *Ret,
                                      const TargetLoweringBase &TLI);
 

lib/CodeGen/Analysis.cpp

@@ -525,19 +525,15 @@ bool llvm::isInTailCallPosition(ImmutableCallSite CS, const TargetMachine &TM) {
       F, I, Ret, *TM.getSubtargetImpl(*F)->getTargetLowering());
 }
 
-bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
-                                           const Instruction *I,
-                                           const ReturnInst *Ret,
-                                           const TargetLoweringBase &TLI) {
-  // If the block ends with a void return or unreachable, it doesn't matter
-  // what the call's return type is.
-  if (!Ret || Ret->getNumOperands() == 0) return true;
+bool llvm::attributesPermitTailCall(const Function *F, const Instruction *I,
+                                    const ReturnInst *Ret,
+                                    const TargetLoweringBase &TLI,
+                                    bool *AllowDifferingSizes) {
+  // ADS may be null, so don't write to it directly.
+  bool DummyADS;
+  bool &ADS = AllowDifferingSizes ? *AllowDifferingSizes : DummyADS;
+  ADS = true;
 
-  // If the return value is undef, it doesn't matter what the call's
-  // return type is.
-  if (isa<UndefValue>(Ret->getOperand(0))) return true;
-
-  // Make sure the attributes attached to each return are compatible.
   AttrBuilder CallerAttrs(F->getAttributes(),
                           AttributeSet::ReturnIndex);
   AttrBuilder CalleeAttrs(cast<CallInst>(I)->getAttributes(),
@@ -548,19 +544,18 @@ bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
   CallerAttrs = CallerAttrs.removeAttribute(Attribute::NoAlias);
   CalleeAttrs = CalleeAttrs.removeAttribute(Attribute::NoAlias);
 
-  bool AllowDifferingSizes = true;
   if (CallerAttrs.contains(Attribute::ZExt)) {
     if (!CalleeAttrs.contains(Attribute::ZExt))
       return false;
 
-    AllowDifferingSizes = false;
+    ADS = false;
     CallerAttrs.removeAttribute(Attribute::ZExt);
     CalleeAttrs.removeAttribute(Attribute::ZExt);
   } else if (CallerAttrs.contains(Attribute::SExt)) {
     if (!CalleeAttrs.contains(Attribute::SExt))
       return false;
 
-    AllowDifferingSizes = false;
+    ADS = false;
     CallerAttrs.removeAttribute(Attribute::SExt);
     CalleeAttrs.removeAttribute(Attribute::SExt);
   }
@@ -568,7 +563,24 @@ bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
   // If they're still different, there's some facet we don't understand
   // (currently only "inreg", but in future who knows). It may be OK but the
   // only safe option is to reject the tail call.
-  if (CallerAttrs != CalleeAttrs)
+  return CallerAttrs == CalleeAttrs;
+}
+
+bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
+                                           const Instruction *I,
+                                           const ReturnInst *Ret,
+                                           const TargetLoweringBase &TLI) {
+  // If the block ends with a void return or unreachable, it doesn't matter
+  // what the call's return type is.
+  if (!Ret || Ret->getNumOperands() == 0) return true;
+
+  // If the return value is undef, it doesn't matter what the call's
+  // return type is.
+  if (isa<UndefValue>(Ret->getOperand(0))) return true;
+
+  // Make sure the attributes attached to each return are compatible.
+  bool AllowDifferingSizes;
+  if (!attributesPermitTailCall(F, I, Ret, TLI, &AllowDifferingSizes))
     return false;
 
   const Value *RetVal = Ret->getOperand(0), *CallVal = I;

lib/CodeGen/CodeGenPrepare.cpp

@@ -23,6 +23,7 @@
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
+#include "llvm/CodeGen/Analysis.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
@@ -1983,14 +1984,6 @@ bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
   if (PN && PN->getParent() != BB)
     return false;
 
-  // It's not safe to eliminate the sign / zero extension of the return value.
-  // See llvm::isInTailCallPosition().
-  const Function *F = BB->getParent();
-  AttributeSet CallerAttrs = F->getAttributes();
-  if (CallerAttrs.hasAttribute(AttributeSet::ReturnIndex, Attribute::ZExt) ||
-      CallerAttrs.hasAttribute(AttributeSet::ReturnIndex, Attribute::SExt))
-    return false;
-
   // Make sure there are no instructions between the PHI and return, or that the
   // return is the first instruction in the block.
   if (PN) {
@@ -2010,13 +2003,15 @@ bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
 
   /// Only dup the ReturnInst if the CallInst is likely to be emitted as a tail
   /// call.
+  const Function *F = BB->getParent();
   SmallVector<CallInst*, 4> TailCalls;
   if (PN) {
     for (unsigned I = 0, E = PN->getNumIncomingValues(); I != E; ++I) {
       CallInst *CI = dyn_cast<CallInst>(PN->getIncomingValue(I));
       // Make sure the phi value is indeed produced by the tail call.
       if (CI && CI->hasOneUse() && CI->getParent() == PN->getIncomingBlock(I) &&
-          TLI->mayBeEmittedAsTailCall(CI))
+          TLI->mayBeEmittedAsTailCall(CI) &&
+          attributesPermitTailCall(F, CI, RetI, *TLI))
         TailCalls.push_back(CI);
     }
   } else {
@@ -2033,7 +2028,8 @@ bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
         continue;
 
       CallInst *CI = dyn_cast<CallInst>(&*RI);
-      if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI))
+      if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI) &&
+          attributesPermitTailCall(F, CI, RetI, *TLI))
         TailCalls.push_back(CI);
     }
   }

test/CodeGen/X86/tailcall-cgp-dup.ll

@@ -85,3 +85,23 @@ someThingWithValue.exit:                          ; preds = %if.else.i, %if.then
   %retval.0.i = bitcast i8* %retval.0.in.i to %0*
   ret %0* %retval.0.i
 }
+
+
+; Correctly handle zext returns.
+declare zeroext i1 @foo_i1()
+
+; CHECK-LABEL: zext_i1
+; CHECK: jmp _foo_i1
+define zeroext i1 @zext_i1(i1 %k) {
+entry:
+  br i1 %k, label %land.end, label %land.rhs
+
+land.rhs:                                         ; preds = %entry
+  %call1 = tail call zeroext i1 @foo_i1()
+  br label %land.end
+
+land.end:                                         ; preds = %entry, %land.rhs
+  %0 = phi i1 [ false, %entry ], [ %call1, %land.rhs ]
+  ret i1 %0
+}
+