Index: include/llvm/CodeGen/AsmPrinter.h
===================================================================
--- include/llvm/CodeGen/AsmPrinter.h
+++ include/llvm/CodeGen/AsmPrinter.h
@@ -173,6 +173,10 @@
   bool isCFIMoveForDebugging = false;
 
 protected:
+  /// Extension point for XRay to customize the generation of a synthetic
+  /// reference past the function body.
+  virtual void emitXRaySyntheticRef(MCSymbol* Symbol);
+
   explicit AsmPrinter(TargetMachine &TM, std::unique_ptr<MCStreamer> Streamer);
 
 public:
Index: lib/CodeGen/AsmPrinter/AsmPrinter.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -2771,6 +2771,12 @@
   Out->EmitZeros(2 * Bytes - 2);  // Pad the previous two entries
 }
 
+void AsmPrinter::emitXRaySyntheticRef(MCSymbol* Symbol) {
+  auto WordSizeBytes = MAI->getCodePointerSize();
+  OutStreamer->EmitCodeAlignment(16);
+  OutStreamer->EmitSymbolValue(Symbol, WordSizeBytes, false);
+}
+
 void AsmPrinter::emitXRayTable() {
   if (Sleds.empty())
     return;
@@ -2809,8 +2815,7 @@
   // this is happening after the last return instruction.
   auto WordSizeBytes = MAI->getCodePointerSize();
   MCSymbol *IdxRef = OutContext.createTempSymbol("xray_fn_idx_synth_", true);
-  OutStreamer->EmitCodeAlignment(16);
-  OutStreamer->EmitSymbolValue(IdxRef, WordSizeBytes, false);
+  emitXRaySyntheticRef(IdxRef);
 
   // Now we switch to the instrumentation map section. Because this is done
   // per-function, we are able to create an index entry that will represent the
Index: lib/Target/X86/X86AsmPrinter.h
===================================================================
--- lib/Target/X86/X86AsmPrinter.h
+++ lib/Target/X86/X86AsmPrinter.h
@@ -137,6 +137,10 @@
   }
 
   bool runOnMachineFunction(MachineFunction &F) override;
+
+protected:
+  /// Special implementation for X86 of synthetic reference generation in X86.
+  void emitXRaySyntheticRef(MCSymbol* Symbol) override;
 };
 
 } // end namespace llvm
Index: lib/Target/X86/X86AsmPrinter.cpp
===================================================================
--- lib/Target/X86/X86AsmPrinter.cpp
+++ lib/Target/X86/X86AsmPrinter.cpp
@@ -31,6 +31,7 @@
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCInstBuilder.h"
 #include "llvm/MC/MCSectionCOFF.h"
 #include "llvm/MC/MCSectionMachO.h"
 #include "llvm/MC/MCStreamer.h"
Index: lib/Target/X86/X86MCInstLower.cpp
===================================================================
--- lib/Target/X86/X86MCInstLower.cpp
+++ lib/Target/X86/X86MCInstLower.cpp
@@ -78,6 +78,19 @@
 static void EmitNops(MCStreamer &OS, unsigned NumBytes, bool Is64Bit,
                      const MCSubtargetInfo &STI);
 
+/// emitXRaySyntheticRef - Appropriately size the synthetic reference to use
+/// instructions and nop paddings before the actual relocation/symbol.
+void X86AsmPrinter::emitXRaySyntheticRef(MCSymbol* Symbol) {
+  auto WordSizeBytes = MAI->getCodePointerSize();
+
+  // Use int3 and then a 7-byte nop aligned to 16-bytes. This allows us to use
+  // 16 bytes for the synthetic reference, so that we are 16-byte aligned.
+  OutStreamer->EmitCodeAlignment(2 * WordSizeBytes);
+  OutStreamer->EmitInstruction(MCInstBuilder(X86::INT3), getSubtargetInfo());
+  EmitNops(*OutStreamer, 7u, getSubtarget().is64Bit(), getSubtargetInfo());
+  OutStreamer->EmitSymbolValue(Symbol, WordSizeBytes);
+}
+
 void X86AsmPrinter::StackMapShadowTracker::count(MCInst &Inst,
                                                  const MCSubtargetInfo &STI,
                                                  MCCodeEmitter *CodeEmitter) {
Index: test/CodeGen/X86/xray-attribute-instrumentation.ll
===================================================================
--- test/CodeGen/X86/xray-attribute-instrumentation.ll
+++ test/CodeGen/X86/xray-attribute-instrumentation.ll
@@ -14,7 +14,9 @@
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_0
+; CHECK-NEXT:  int3
+; CHECK-NEXT:  nopl 512(%rax)
+; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_0{{.*}}
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
 ; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .quad {{.*}}xray_sled_0
@@ -51,7 +53,9 @@
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_1
+; CHECK-NEXT:  int3
+; CHECK-NEXT:  nopl 512(%rax)
+; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_1{{.*}}
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
 ; CHECK-LABEL: Lxray_sleds_start1:
 ; CHECK:       .quad {{.*}}xray_sled_2
Index: test/CodeGen/X86/xray-tail-call-sled.ll
===================================================================
--- test/CodeGen/X86/xray-tail-call-sled.ll
+++ test/CodeGen/X86/xray-tail-call-sled.ll
@@ -14,6 +14,8 @@
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
+; CHECK-NEXT:  int3
+; CHECK-NEXT:  nopl 512(%rax)
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_0{{.*}}
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
 ; CHECK-LABEL: Lxray_sleds_start0:
@@ -41,6 +43,8 @@
   ret i32 %retval
 }
 ; CHECK:       .p2align 4, 0x90
+; CHECK-NEXT:  int3
+; CHECK-NEXT:  nopl 512(%rax)
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_1{{.*}}
 ; CHECK-LABEL: Lxray_sleds_start1:
 ; CHECK:       .quad {{.*}}xray_sled_2