Index: llvm/trunk/include/llvm/CodeGen/Passes.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/Passes.h
+++ llvm/trunk/include/llvm/CodeGen/Passes.h
@@ -43,6 +43,9 @@
   /// the entry block.
   FunctionPass *createUnreachableBlockEliminationPass();
 
+  /// Insert mcount-like function calls.
+  FunctionPass *createCountingFunctionInserterPass();
+
   /// MachineFunctionPrinter pass - This pass prints out the machine function to
   /// the given stream as a debugging tool.
   MachineFunctionPass *
Index: llvm/trunk/include/llvm/InitializePasses.h
===================================================================
--- llvm/trunk/include/llvm/InitializePasses.h
+++ llvm/trunk/include/llvm/InitializePasses.h
@@ -92,6 +92,7 @@
 void initializeCallGraphViewerPass(PassRegistry&);
 void initializeCallGraphWrapperPassPass(PassRegistry &);
 void initializeCodeGenPreparePass(PassRegistry&);
+void initializeCountingFunctionInserterPass(PassRegistry&);
 void initializeConstantHoistingLegacyPassPass(PassRegistry&);
 void initializeConstantMergeLegacyPassPass(PassRegistry &);
 void initializeConstantPropagationPass(PassRegistry&);
Index: llvm/trunk/include/llvm/LinkAllPasses.h
===================================================================
--- llvm/trunk/include/llvm/LinkAllPasses.h
+++ llvm/trunk/include/llvm/LinkAllPasses.h
@@ -160,6 +160,7 @@
       (void) llvm::createInstCountPass();
       (void) llvm::createConstantHoistingPass();
       (void) llvm::createCodeGenPreparePass();
+      (void) llvm::createCountingFunctionInserterPass();
       (void) llvm::createEarlyCSEPass();
       (void) llvm::createGVNHoistPass();
       (void) llvm::createMergedLoadStoreMotionPass();
Index: llvm/trunk/lib/CodeGen/CMakeLists.txt
===================================================================
--- llvm/trunk/lib/CodeGen/CMakeLists.txt
+++ llvm/trunk/lib/CodeGen/CMakeLists.txt
@@ -10,6 +10,7 @@
   CallingConvLower.cpp
   CodeGen.cpp
   CodeGenPrepare.cpp
+  CountingFunctionInserter.cpp
   CriticalAntiDepBreaker.cpp
   DeadMachineInstructionElim.cpp
   DetectDeadLanes.cpp
Index: llvm/trunk/lib/CodeGen/CodeGen.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/CodeGen.cpp
+++ llvm/trunk/lib/CodeGen/CodeGen.cpp
@@ -23,6 +23,7 @@
   initializeAtomicExpandPass(Registry);
   initializeBranchFolderPassPass(Registry);
   initializeCodeGenPreparePass(Registry);
+  initializeCountingFunctionInserterPass(Registry);
   initializeDeadMachineInstructionElimPass(Registry);
   initializeDetectDeadLanesPass(Registry);
   initializeDwarfEHPreparePass(Registry);
Index: llvm/trunk/lib/CodeGen/CountingFunctionInserter.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/CountingFunctionInserter.cpp
+++ llvm/trunk/lib/CodeGen/CountingFunctionInserter.cpp
@@ -0,0 +1,62 @@
+//===- CountingFunctionInserter.cpp - Insert mcount-like function calls ---===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Insert calls to counter functions, such as mcount, intended to be called
+// once per function, at the beginning of each function.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/GlobalsModRef.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/Type.h"
+#include "llvm/Pass.h"
+using namespace llvm;
+
+namespace {
+  struct CountingFunctionInserter : public FunctionPass {
+    static char ID; // Pass identification, replacement for typeid
+    CountingFunctionInserter() : FunctionPass(ID) {
+      initializeCountingFunctionInserterPass(*PassRegistry::getPassRegistry());
+    }
+    
+    void getAnalysisUsage(AnalysisUsage &AU) const override {
+      AU.addPreserved<GlobalsAAWrapperPass>();
+    }
+
+    bool runOnFunction(Function &F) override {
+      std::string CountingFunctionName =
+        F.getFnAttribute("counting-function").getValueAsString();
+      if (CountingFunctionName.empty())
+        return false;
+
+      Type *VoidTy = Type::getVoidTy(F.getContext());
+      Constant *CountingFn =
+        F.getParent()->getOrInsertFunction(CountingFunctionName,
+                                           VoidTy, nullptr);
+      CallInst::Create(CountingFn, "", &*F.begin()->getFirstInsertionPt());
+      return true;
+    }
+  };
+  
+  char CountingFunctionInserter::ID = 0;
+}
+
+INITIALIZE_PASS(CountingFunctionInserter, "cfinserter", 
+                "Inserts calls to mcount-like functions", false, false)
+
+//===----------------------------------------------------------------------===//
+//
+// CountingFunctionInserter - Give any unnamed non-void instructions "tmp" names.
+//
+FunctionPass *llvm::createCountingFunctionInserterPass() {
+  return new CountingFunctionInserter();
+}
Index: llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
+++ llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
@@ -477,6 +477,9 @@
 
   if (getOptLevel() != CodeGenOpt::None && !DisablePartialLibcallInlining)
     addPass(createPartiallyInlineLibCallsPass());
+
+  // Insert calls to mcount-like functions.
+  addPass(createCountingFunctionInserterPass());
 }
 
 /// Turn exception handling constructs into something the code generators can
Index: llvm/trunk/test/CodeGen/PowerPC/mcount-insertion.ll
===================================================================
--- llvm/trunk/test/CodeGen/PowerPC/mcount-insertion.ll
+++ llvm/trunk/test/CodeGen/PowerPC/mcount-insertion.ll
@@ -0,0 +1,16 @@
+; RUN: llc < %s | FileCheck %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-bgq-linux"
+
+define void @test1() #0 {
+entry:
+  ret void
+
+; CHECK-LABEL: @test1
+; CHECK: bl mcount
+; CHECK-NOT: mcount
+; CHECK: blr
+}
+
+attributes #0 = { "counting-function"="mcount" }
+
Index: llvm/trunk/test/Transforms/CountingFunctionInserter/mcount.ll
===================================================================
--- llvm/trunk/test/Transforms/CountingFunctionInserter/mcount.ll
+++ llvm/trunk/test/Transforms/CountingFunctionInserter/mcount.ll
@@ -0,0 +1,27 @@
+; RUN: opt -S -cfinserter < %s | FileCheck %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-bgq-linux"
+
+define void @test1() #0 {
+entry:
+  ret void
+
+; CHECK-LABEL: define void @test1()
+; CHECK: entry:
+; CHECK-NEXT: call void @mcount()
+; CHECK: ret void
+}
+
+define void @test2() #1 {
+entry:
+  ret void
+
+; CHECK-LABEL: define void @test2()
+; CHECK: entry:
+; CHECK-NEXT: call void @.mcount()
+; CHECK: ret void
+}
+
+attributes #0 = { "counting-function"="mcount" }
+attributes #1 = { "counting-function"=".mcount" }
+
Index: llvm/trunk/tools/llc/llc.cpp
===================================================================
--- llvm/trunk/tools/llc/llc.cpp
+++ llvm/trunk/tools/llc/llc.cpp
@@ -254,6 +254,7 @@
   initializeCodeGen(*Registry);
   initializeLoopStrengthReducePass(*Registry);
   initializeLowerIntrinsicsPass(*Registry);
+  initializeCountingFunctionInserterPass(*Registry);
   initializeUnreachableBlockElimLegacyPassPass(*Registry);
 
   // Register the target printer for --version.
Index: llvm/trunk/tools/opt/opt.cpp
===================================================================
--- llvm/trunk/tools/opt/opt.cpp
+++ llvm/trunk/tools/opt/opt.cpp
@@ -384,6 +384,7 @@
   initializePreISelIntrinsicLoweringLegacyPassPass(Registry);
   initializeGlobalMergePass(Registry);
   initializeInterleavedAccessPass(Registry);
+  initializeCountingFunctionInserterPass(Registry);
   initializeUnreachableBlockElimLegacyPassPass(Registry);
 
 #ifdef LINK_POLLY_INTO_TOOLS