Index: include/xray/xray_interface.h
===================================================================
--- include/xray/xray_interface.h
+++ include/xray/xray_interface.h
@@ -18,7 +18,7 @@
 
 extern "C" {
 
-enum XRayEntryType { ENTRY = 0, EXIT = 1 };
+enum XRayEntryType { ENTRY = 0, EXIT = 1, TAIL = 2 };
 
 // Provide a function to invoke for when instrumentation points are hit. This is
 // a user-visible control surface that overrides the default implementation. The
Index: lib/xray/xray_interface.cc
===================================================================
--- lib/xray/xray_interface.cc
+++ lib/xray/xray_interface.cc
@@ -259,6 +259,37 @@
         // FIXME: Write out the nops still?
       }
     }
+
+    if (Sled.Kind == XRayEntryType::TAIL) {
+      // FIXME: Implement this in a more extensible manner, per-platform.
+      // Here we do the dance of replacing the tail call sled with a similar
+      // sequence as the entry sled, but jump to the exit sled instead, so we
+      // can treat tail call exits as if they were normal exits. In the future
+      // we'd need to distinguish between non-tail exits and tail exits for
+      // better information preservation.
+      int64_t TrampolineOffset = reinterpret_cast<int64_t>(__xray_FunctionExit) - (static_cast<int64_t>(Sled.Address) + 11);
+      if (TrampolineOffset < MinOffset || TrampolineOffset > MaxOffset) {
+        Report("XRay Exit trampoline (%p) too far from sled (%p); distance = "
+               "%ld\n",
+               __xray_FunctionExit, reinterpret_cast<void *>(Sled.Address),
+               TrampolineOffset);
+        continue;
+      }
+      if (Enable) {
+        *reinterpret_cast<uint32_t *>(Sled.Address + 2) = FuncId;
+        *reinterpret_cast<uint8_t *>(Sled.Address + 6) = CallOpCode;
+        *reinterpret_cast<uint32_t *>(Sled.Address + 7) = TrampolineOffset;
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), MovR10Seq,
+            std::memory_order_release);
+      } else {
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), Jmp9Seq,
+            std::memory_order_release);
+        // FIXME: Write out the nops still?
+      }
+    }
+
   }
   XRayPatching.store(false, std::memory_order_release);
   PatchingSuccess = true;