[XRay] Add CPU ID in Custom Event FDR Records

[dberris]

Summary

This change cuts across compiler-rt and llvm, to increment the FDR log
version number to 4, and include the CPU ID in the custom event records.

This is a step towards allowing us to change the llvm::xray::Trace
object to start representing both custom and typed events in the stream
of records. Follow-on changes will allow us to change the kinds of
records we're presenting in the stream of traces, to incorporate the
data in custom/typed events.

A follow-on change will handle the typed event case, where it may not
fit within the 15-byte buffer for metadata records.

This work is part of the larger effort to enable writing analysis and
processing tools using a common in-memory representation of the events
found in traces. The work will focus on porting existing tools in LLVM
to use the common representation and informing the design of a
library/framework for expressing trace event analysis as C++ programs.

[mboerger]

LGTM

lib/xray/xray_fdr_controller.h

bool customEvent(uint64_t TSC, uint16_t CPU, const void *Event,
     if (finalized() ||
         !prepareBuffer((2 * sizeof(MetadataRecord)) + EventSize) ||
         functionPreamble(TSC, CPU) == PreambleResult::InvalidBuffer)
       return returnBuffer();
 
     LatestTSC = 0;
     UndoableFunctionEnters = 0;
     UndoableTailExits = 0;
-    return W.writeCustomEvent(TSC, Event, EventSize);
+    return W.writeCustomEvent(TSC, CPU, Event, EventSize);
   }
 
   bool typedEvent(uint64_t TSC, uint16_t CPU, uint16_t EventType,
                   const void *Event, int32_t EventSize) XRAY_NEVER_INSTRUMENT {
     if (finalized() ||
         !prepareBuffer((2 * sizeof(MetadataRecord)) + EventSize) ||
         functionPreamble(TSC, CPU) == PreambleResult::InvalidBuffer)
       return returnBuffer();

lib/xray/xray_fdr_log_writer.h

bool writeFunction(FunctionRecordKind Kind, int32_t FuncId, int32_t Delta) {
     R.Type = 0;
     R.RecordKind = uint8_t(Kind);
     R.FuncId = FuncId;
     R.TSCDelta = Delta;
     writeRecord(R);
     return true;
   }
 
-  bool writeCustomEvent(uint64_t TSC, const void *Event, int32_t EventSize) {
+  bool writeCustomEvent(uint64_t TSC, uint16_t CPU, const void *Event,
+                        int32_t EventSize) {
     writeMetadata<MetadataRecord::RecordKinds::CustomEventMarker>(EventSize,
-                                                                  TSC);
+                                                                  TSC, CPU);
     internal_memcpy(NextRecord, Event, EventSize);
     NextRecord += EventSize;
     atomic_fetch_add(&Buffer.Extents, EventSize, memory_order_acq_rel);
     return true;
   }
 
   bool writeTypedEvent(uint64_t TSC, uint16_t EventType, const void *Event,
                        int32_t EventSize) {

lib/xray/xray_fdr_logging.cc

static XRayFileHeader &fdrCommonHeaderInfo() {
   static pthread_once_t OnceInit = PTHREAD_ONCE_INIT;
   static bool TSCSupported = true;
   static uint64_t CycleFrequency = NanosecondsPerSecond;
   pthread_once(&OnceInit, +[] {
     XRayFileHeader &H = reinterpret_cast<XRayFileHeader &>(HStorage);
     // Version 2 of the log writes the extents of the buffer, instead of
     // relying on an end-of-buffer record.
     // Version 3 includes PID metadata record
-    H.Version = 3;
+    // Version 4 includes CPU data in the custom event records
+    H.Version = 4;
     H.Type = FileTypes::FDR_LOG;
 
     // Test for required CPU features and cache the cycle frequency
     TSCSupported = probeRequiredCPUFeatures();
     if (TSCSupported)
       CycleFrequency = getTSCFrequency();
     H.CycleFrequency = CycleFrequency;