2 files changed, 34 insertions, 26 deletions

diff --git a/llvm/lib/CodeGen/Analysis.cpp b/llvm/lib/CodeGen/Analysis.cpp
index ebbcaeb3057..6582d24da82 100644
--- a/llvm/lib/CodeGen/Analysis.cpp
+++ b/llvm/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;
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index 15600af4d39..3bdf60c172a 100644
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/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);
     }
   }