[XRay][compiler-rt] Use a single global volatile recursion guard for FDR handlers

[dberris]

Summary

Before this change, the recursion guard for the flight data recorder
(FDR) mode handlers were independent. This change makes it so that when
a handler is already in the process of running and somehow the same or
another handler starts running -- say in a signal handler, while the
XRay handler is executing -- then we can use the same thread-local
recursion guard to stop the second handler from running.

lib/xray/xray_fdr_logging.cc

 #include "xray_utils.h"
 
 namespace __xray {
 
 // Global BufferQueue.
 // NOTE: This is a pointer to avoid having to do atomic operations at
 // initialization time. This is OK to leak as there will only be one bufferqueue
 // for the runtime, initialized once through the fdrInit(...) sequence.
-std::shared_ptr<BufferQueue>* BQ = nullptr;
+std::shared_ptr<BufferQueue> *BQ = nullptr;
 
 __sanitizer::atomic_sint32_t LogFlushStatus = {
     XRayLogFlushStatus::XRAY_LOG_NOT_FLUSHING};
 
 FDRLoggingOptions FDROptions;
 
 __sanitizer::SpinMutex FDROptionsMutex;
 

 }
 
 void fdrLoggingHandleCustomEvent(void *Event,
                                  std::size_t EventSize) XRAY_NEVER_INSTRUMENT {
   using namespace __xray_fdr_internal;
   auto TSC_CPU = getTimestamp();
   auto &TSC = std::get<0>(TSC_CPU);
   auto &CPU = std::get<1>(TSC_CPU);
-  thread_local bool Running = false;
   RecursionGuard Guard{Running};
   if (!Guard) {
     assert(Running && "RecursionGuard is buggy!");
     return;
   }
   if (EventSize > std::numeric_limits<int32_t>::max()) {
     using Empty = struct {};
     static Empty Once = [&] {

 }
 
 } // namespace __xray
 
 static auto UNUSED Unused = [] {
   using namespace __xray;
   if (flags()->xray_fdr_log) {
     XRayLogImpl Impl{
-        fdrLoggingInit, fdrLoggingFinalize, fdrLoggingHandleArg0,
+        fdrLoggingInit,
+        fdrLoggingFinalize,
+        fdrLoggingHandleArg0,
         fdrLoggingFlush,
     };
     __xray_set_log_impl(Impl);
   }
   return true;
 }();

lib/xray/xray_fdr_logging_impl.h

inline void endBufferIfFull() XRAY_NEVER_INSTRUMENT {
   if ((TLD.RecordPtr + MetadataRecSize) - BufferStart == MetadataRecSize) {
     writeEOBMetadata();
     if (!releaseThreadLocalBuffer(*TLD.LocalBQ))
       return;
     TLD.RecordPtr = nullptr;
   }
 }
 
+thread_local volatile bool Running = false;
+
 inline void processFunctionHook(
     int32_t FuncId, XRayEntryType Entry, uint64_t TSC, unsigned char CPU,
     int (*wall_clock_reader)(clockid_t, struct timespec *),
     __sanitizer::atomic_sint32_t &LoggingStatus,
     const std::shared_ptr<BufferQueue> &BQ) XRAY_NEVER_INSTRUMENT {
   // Prevent signal handler recursion, so in case we're already in a log writing
   // mode and the signal handler comes in (and is also instrumented) then we
   // don't want to be clobbering potentially partial writes already happening in
   // the thread. We use a simple thread_local latch to only allow one on-going
   // handleArg0 to happen at any given time.
-  thread_local volatile bool Running = false;
   RecursionGuard Guard{Running};
   if (!Guard) {
     assert(Running == true && "RecursionGuard is buggy!");
     return;
   }
 
   auto &TLD = getThreadLocalData();