Fall back to the selection dag isel to select tail calls.

This shouldn't affect codegen for -O0 compiles as tail call markers are not
emitted in unoptimized compiles.  Testing with the external/internal nightly
test suite reveals no change in compile time performance.  Testing with -O1,
-O2 and -O3 with fast-isel enabled did not cause any compile-time or
execution-time failures.  All tests were performed on my x86 machine.
I'll monitor our arm testers to ensure no regressions occur there.

In an upcoming clang patch I will be marking the objc_autoreleaseReturnValue
and objc_retainAutoreleaseReturnValue as tail calls unconditionally.  While
it's theoretically true that this is just an optimization, it's an
optimization that we very much want to happen even at -O0, or else ARC
applications become substantially harder to debug.

Part of rdar://12553082

llvm-svn: 169796

6 files changed, 20 insertions, 17 deletions

diff --git a/llvm/include/llvm/CodeGen/FastISel.h b/llvm/include/llvm/CodeGen/FastISel.h
index 5c872b14fd8..05619050a31 100644
--- a/llvm/include/llvm/CodeGen/FastISel.h
+++ b/llvm/include/llvm/CodeGen/FastISel.h
@@ -131,6 +131,10 @@ public:
   /// into the current block.
   void recomputeInsertPt();
 
+  /// removeDeadCode - Remove all dead instructions between the I and E.
+  void removeDeadCode(MachineBasicBlock::iterator I,
+                      MachineBasicBlock::iterator E);
+
   struct SavePoint {
     MachineBasicBlock::iterator InsertPt;
     DebugLoc DL;
@@ -395,10 +399,6 @@ private:
 
   /// hasTrivialKill - Test whether the given value has exactly one use.
   bool hasTrivialKill(const Value *V) const;
-
-  /// removeDeadCode - Remove all dead instructions between the I and E.
-  void removeDeadCode(MachineBasicBlock::iterator I,
-                      MachineBasicBlock::iterator E);
 };
 
 }
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 97d975ecb72..ee8f272093a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -5273,11 +5273,6 @@ void SelectionDAGBuilder::LowerCallTo(ImmutableCallSite CS, SDValue Callee,
       !isInTailCallPosition(CS, CS.getAttributes().getRetAttributes(), TLI))
     isTailCall = false;
 
-  // If there's a possibility that fast-isel has already selected some amount
-  // of the current basic block, don't emit a tail call.
-  if (isTailCall && TM.Options.EnableFastISel)
-    isTailCall = false;
-
   TargetLowering::
   CallLoweringInfo CLI(getRoot(), RetTy, FTy, isTailCall, Callee, Args, DAG,
                        getCurDebugLoc(), CS);
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
index ca252743d8d..c755d729d54 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
@@ -1113,19 +1113,21 @@ void SelectionDAGISel::SelectAllBasicBlocks(const Function &Fn) {
           }
 
           bool HadTailCall = false;
+          MachineBasicBlock::iterator SavedInsertPt = FuncInfo->InsertPt;
           SelectBasicBlock(Inst, BI, HadTailCall);
 
-          // Recompute NumFastIselRemaining as Selection DAG instruction
-          // selection may have handled the call, input args, etc.
-          unsigned RemainingNow = std::distance(Begin, BI);
-          NumFastIselFailures += NumFastIselRemaining - RemainingNow;
-
           // If the call was emitted as a tail call, we're done with the block.
+          // We also need to delete any previously emitted instructions.
           if (HadTailCall) {
+            FastIS->removeDeadCode(SavedInsertPt, FuncInfo->MBB->end());
             --BI;
             break;
           }
 
+          // Recompute NumFastIselRemaining as Selection DAG instruction
+          // selection may have handled the call, input args, etc.
+          unsigned RemainingNow = std::distance(Begin, BI);
+          NumFastIselFailures += NumFastIselRemaining - RemainingNow;
           NumFastIselRemaining = RemainingNow;
           continue;
         }
diff --git a/llvm/lib/Target/ARM/ARMFastISel.cpp b/llvm/lib/Target/ARM/ARMFastISel.cpp
index 21bb1476440..c3a5e6472ef 100644
--- a/llvm/lib/Target/ARM/ARMFastISel.cpp
+++ b/llvm/lib/Target/ARM/ARMFastISel.cpp
@@ -2284,6 +2284,9 @@ bool ARMFastISel::SelectCall(const Instruction *I,
   // Can't handle inline asm.
   if (isa<InlineAsm>(Callee)) return false;
 
+  // Allow SelectionDAG isel to handle tail calls.
+  if (CI->isTailCall()) return false;
+
   // Check the calling convention.
   ImmutableCallSite CS(CI);
   CallingConv::ID CC = CS.getCallingConv();
diff --git a/llvm/lib/Target/X86/X86FastISel.cpp b/llvm/lib/Target/X86/X86FastISel.cpp
index b26b9d7e299..3e78b4c0a1a 100644
--- a/llvm/lib/Target/X86/X86FastISel.cpp
+++ b/llvm/lib/Target/X86/X86FastISel.cpp
@@ -1529,6 +1529,10 @@ bool X86FastISel::X86SelectCall(const Instruction *I) {
   if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI))
     return X86VisitIntrinsicCall(*II);
 
+  // Allow SelectionDAG isel to handle tail calls.
+  if (cast<CallInst>(I)->isTailCall())
+    return false;
+
   return DoSelectCall(I, 0);
 }
 
diff --git a/llvm/test/CodeGen/X86/tailcall-fastisel.ll b/llvm/test/CodeGen/X86/tailcall-fastisel.ll
index 7f92af4dca9..9962d719882 100644
--- a/llvm/test/CodeGen/X86/tailcall-fastisel.ll
+++ b/llvm/test/CodeGen/X86/tailcall-fastisel.ll
@@ -1,12 +1,11 @@
-; RUN: llc < %s -march=x86-64 -tailcallopt -fast-isel | not grep TAILCALL
-
-; Fast-isel shouldn't attempt to cope with tail calls.
+; RUN: llc < %s -march=x86-64 -tailcallopt -fast-isel -fast-isel-abort | FileCheck %s
 
 %0 = type { i64, i32, i8* }
 
 define fastcc i8* @"visit_array_aux<`Reference>"(%0 %arg, i32 %arg1) nounwind {
 fail:                                             ; preds = %entry
   %tmp20 = tail call fastcc i8* @"visit_array_aux<`Reference>"(%0 %arg, i32 undef) ; <i8*> [#uses=1]
+; CHECK: jmp "_visit_array_aux<`Reference>" ## TAILCALL
   ret i8* %tmp20
 }