Index: llvm/trunk/include/llvm/CodeGen/Passes.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/Passes.h
+++ llvm/trunk/include/llvm/CodeGen/Passes.h
@@ -286,6 +286,9 @@
   /// the target platform.
   extern char &XRayInstrumentationID;
 
+  /// This pass inserts FEntry calls
+  extern char &FEntryInserterID;
+
   /// \brief This pass implements the "patchable-function" attribute.
   extern char &PatchableFunctionID;
 
Index: llvm/trunk/include/llvm/InitializePasses.h
===================================================================
--- llvm/trunk/include/llvm/InitializePasses.h
+++ llvm/trunk/include/llvm/InitializePasses.h
@@ -131,6 +131,7 @@
 void initializeExpandISelPseudosPass(PassRegistry&);
 void initializeExpandPostRAPass(PassRegistry&);
 void initializeExternalAAWrapperPassPass(PassRegistry&);
+void initializeFEntryInserterPass(PassRegistry &);
 void initializeFinalizeMachineBundlesPass(PassRegistry&);
 void initializeFlattenCFGPassPass(PassRegistry&);
 void initializeFloat2IntLegacyPassPass(PassRegistry&);
Index: llvm/trunk/include/llvm/Target/Target.td
===================================================================
--- llvm/trunk/include/llvm/Target/Target.td
+++ llvm/trunk/include/llvm/Target/Target.td
@@ -998,6 +998,15 @@
   let hasSideEffects = 1;
   let isReturn = 1;
 }
+def FENTRY_CALL : Instruction {
+  let OutOperandList = (outs unknown:$dst);
+  let InOperandList = (ins variable_ops);
+  let AsmString = "# FEntry call";
+  let usesCustomInserter = 1;
+  let mayLoad = 1;
+  let mayStore = 1;
+  let hasSideEffects = 1;
+}
 
 // Generic opcodes used in GlobalISel.
 include "llvm/Target/GenericOpcodes.td"
Index: llvm/trunk/include/llvm/Target/TargetOpcodes.def
===================================================================
--- llvm/trunk/include/llvm/Target/TargetOpcodes.def
+++ llvm/trunk/include/llvm/Target/TargetOpcodes.def
@@ -107,6 +107,9 @@
 /// that must lie within the function and not contain another stackmap.
 HANDLE_TARGET_OPCODE(STACKMAP)
 
+/// FEntry all - This is a marker instruction which gets translated into a raw fentry call.
+HANDLE_TARGET_OPCODE(FENTRY_CALL)
+
 /// Patchable call instruction - this instruction represents a call to a
 /// constant address, followed by a series of NOPs. It is intended to
 /// support optimizations for dynamic languages (such as javascript) that
Index: llvm/trunk/lib/CodeGen/CMakeLists.txt
===================================================================
--- llvm/trunk/lib/CodeGen/CMakeLists.txt
+++ llvm/trunk/lib/CodeGen/CMakeLists.txt
@@ -23,6 +23,7 @@
   ExpandISelPseudos.cpp
   ExpandPostRAPseudos.cpp
   FaultMaps.cpp
+  FEntryInserter.cpp
   FuncletLayout.cpp
   GCMetadata.cpp
   GCMetadataPrinter.cpp
Index: llvm/trunk/lib/CodeGen/CodeGen.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/CodeGen.cpp
+++ llvm/trunk/lib/CodeGen/CodeGen.cpp
@@ -32,6 +32,7 @@
   initializeExpandISelPseudosPass(Registry);
   initializeExpandPostRAPass(Registry);
   initializeFinalizeMachineBundlesPass(Registry);
+  initializeFEntryInserterPass(Registry);
   initializeFuncletLayoutPass(Registry);
   initializeGCMachineCodeAnalysisPass(Registry);
   initializeGCModuleInfoPass(Registry);
Index: llvm/trunk/lib/CodeGen/FEntryInserter.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/FEntryInserter.cpp
+++ llvm/trunk/lib/CodeGen/FEntryInserter.cpp
@@ -0,0 +1,55 @@
+//===-- FEntryInsertion.cpp - Patchable prologues for LLVM -------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file edits function bodies to insert fentry calls.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Target/TargetFrameLowering.h"
+#include "llvm/Target/TargetInstrInfo.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
+
+using namespace llvm;
+
+namespace {
+struct FEntryInserter : public MachineFunctionPass {
+  static char ID; // Pass identification, replacement for typeid
+  FEntryInserter() : MachineFunctionPass(ID) {
+    initializeFEntryInserterPass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnMachineFunction(MachineFunction &F) override;
+};
+}
+
+bool FEntryInserter::runOnMachineFunction(MachineFunction &MF) {
+  const std::string FEntryName =
+      MF.getFunction()->getFnAttribute("fentry-call").getValueAsString();
+  if (FEntryName != "true")
+    return false;
+
+  auto &FirstMBB = *MF.begin();
+  auto &FirstMI = *FirstMBB.begin();
+
+  auto *TII = MF.getSubtarget().getInstrInfo();
+  BuildMI(FirstMBB, FirstMI, FirstMI.getDebugLoc(),
+          TII->get(TargetOpcode::FENTRY_CALL));
+  return true;
+}
+
+char FEntryInserter::ID = 0;
+char &llvm::FEntryInserterID = FEntryInserter::ID;
+INITIALIZE_PASS(FEntryInserter, "fentry-insert", "Insert fentry calls", false,
+                false)
Index: llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
+++ llvm/trunk/lib/CodeGen/TargetPassConfig.cpp
@@ -668,6 +668,9 @@
   addPass(&StackMapLivenessID, false);
   addPass(&LiveDebugValuesID, false);
 
+  // Insert before XRay Instrumentation.
+  addPass(&FEntryInserterID, false);
+
   addPass(&XRayInstrumentationID, false);
   addPass(&PatchableFunctionID, false);
 
Index: llvm/trunk/lib/Target/X86/X86AsmPrinter.h
===================================================================
--- llvm/trunk/lib/Target/X86/X86AsmPrinter.h
+++ llvm/trunk/lib/Target/X86/X86AsmPrinter.h
@@ -92,6 +92,8 @@
   void LowerPATCHABLE_RET(const MachineInstr &MI, X86MCInstLower &MCIL);
   void LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI, X86MCInstLower &MCIL);
 
+  void LowerFENTRY_CALL(const MachineInstr &MI, X86MCInstLower &MCIL);
+
   // Helper function that emits the XRay sleds we've collected for a particular
   // function.
   void EmitXRayTable();
Index: llvm/trunk/lib/Target/X86/X86MCInstLower.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86MCInstLower.cpp
+++ llvm/trunk/lib/Target/X86/X86MCInstLower.cpp
@@ -919,6 +919,19 @@
   OutStreamer->EmitInstruction(LoadMI, getSubtargetInfo());
 }
 
+void X86AsmPrinter::LowerFENTRY_CALL(const MachineInstr &MI,
+                                     X86MCInstLower &MCIL) {
+  bool Is64Bits = Subtarget->is64Bit();
+  MCContext &Ctx = OutStreamer->getContext();
+  MCSymbol *fentry = Ctx.getOrCreateSymbol("__fentry__");
+  const MCSymbolRefExpr *Op =
+      MCSymbolRefExpr::create(fentry, MCSymbolRefExpr::VK_None, Ctx);
+
+  EmitAndCountInstruction(
+      MCInstBuilder(Is64Bits ? X86::CALL64pcrel32 : X86::CALLpcrel32)
+          .addExpr(Op));
+}
+
 void X86AsmPrinter::LowerPATCHABLE_OP(const MachineInstr &MI,
                                       X86MCInstLower &MCIL) {
   // PATCHABLE_OP minsize, opcode, operands
@@ -1377,6 +1390,9 @@
   case TargetOpcode::FAULTING_LOAD_OP:
     return LowerFAULTING_LOAD_OP(*MI, MCInstLowering);
 
+  case TargetOpcode::FENTRY_CALL:
+    return LowerFENTRY_CALL(*MI, MCInstLowering);
+
   case TargetOpcode::PATCHABLE_OP:
     return LowerPATCHABLE_OP(*MI, MCInstLowering);
 
Index: llvm/trunk/test/CodeGen/X86/fentry-insertion.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/fentry-insertion.ll
+++ llvm/trunk/test/CodeGen/X86/fentry-insertion.ll
@@ -0,0 +1,16 @@
+; RUN: llc %s -o - | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @test1() #0 {
+entry:
+  ret void
+
+; CHECK-LABEL: @test1
+; CHECK: callq __fentry__
+; CHECK-NOT: mcount
+; CHECK: retq
+}
+
+attributes #0 = { "fentry-call"="true" }
+