Index: compiler-rt/trunk/lib/xray/xray_fdr_logging.cc
===================================================================
--- compiler-rt/trunk/lib/xray/xray_fdr_logging.cc
+++ compiler-rt/trunk/lib/xray/xray_fdr_logging.cc
@@ -206,17 +206,17 @@
 void fdrLoggingHandleArg0(int32_t FuncId,
                           XRayEntryType Entry) XRAY_NEVER_INSTRUMENT {
   auto TSC_CPU = getTimestamp();
-  __xray_fdr_internal::processFunctionHook(
-      FuncId, Entry, std::get<0>(TSC_CPU), std::get<1>(TSC_CPU), 0,
-      clock_gettime, *BQ);
+  __xray_fdr_internal::processFunctionHook(FuncId, Entry, std::get<0>(TSC_CPU),
+                                           std::get<1>(TSC_CPU), 0,
+                                           clock_gettime, *BQ);
 }
 
 void fdrLoggingHandleArg1(int32_t FuncId, XRayEntryType Entry,
                           uint64_t Arg) XRAY_NEVER_INSTRUMENT {
   auto TSC_CPU = getTimestamp();
-  __xray_fdr_internal::processFunctionHook(
-      FuncId, Entry, std::get<0>(TSC_CPU), std::get<1>(TSC_CPU), Arg,
-      clock_gettime, *BQ);
+  __xray_fdr_internal::processFunctionHook(FuncId, Entry, std::get<0>(TSC_CPU),
+                                           std::get<1>(TSC_CPU), Arg,
+                                           clock_gettime, *BQ);
 }
 
 void fdrLoggingHandleCustomEvent(void *Event,
@@ -248,7 +248,7 @@
   //   - The metadata record we're going to write. (16 bytes)
   //   - The additional data we're going to write. Currently, that's the size of
   //   the event we're going to dump into the log as free-form bytes.
-  if (!prepareBuffer(clock_gettime, MetadataRecSize + EventSize)) {
+  if (!prepareBuffer(TSC, CPU, clock_gettime, MetadataRecSize + EventSize)) {
     TLD.LocalBQ = nullptr;
     return;
   }
Index: compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h
===================================================================
--- compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h
+++ compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h
@@ -532,7 +532,8 @@
   return true;
 }
 
-inline bool prepareBuffer(int (*wall_clock_reader)(clockid_t,
+inline bool prepareBuffer(uint64_t TSC, unsigned char CPU,
+                          int (*wall_clock_reader)(clockid_t,
                                                    struct timespec *),
                           size_t MaxSize) XRAY_NEVER_INSTRUMENT {
   auto &TLD = getThreadLocalData();
@@ -549,6 +550,9 @@
       return false;
     }
     setupNewBuffer(wall_clock_reader);
+
+    // Always write the CPU metadata as the first record in the buffer.
+    writeNewCPUIdMetadata(CPU, TSC);
   }
   return true;
 }
@@ -599,6 +603,9 @@
     }
 
     setupNewBuffer(wall_clock_reader);
+
+    // Always write the CPU metadata as the first record in the buffer.
+    writeNewCPUIdMetadata(CPU, TSC);
   }
 
   if (TLD.CurrentCPU == std::numeric_limits<uint16_t>::max()) {
@@ -728,7 +735,7 @@
   // bytes in the end of the buffer, we need to write out the EOB, get a new
   // Buffer, set it up properly before doing any further writing.
   size_t MaxSize = FunctionRecSize + 2 * MetadataRecSize;
-  if (!prepareBuffer(wall_clock_reader, MaxSize)) {
+  if (!prepareBuffer(TSC, CPU, wall_clock_reader, MaxSize)) {
     TLD.LocalBQ = nullptr;
     return;
   }