[XRay][compiler-rt] Remove more STL dependenices from FDR mode

[dberris]

Summary

This change removes dependencies on STL types:

• std::aligned_storage -- we're using manually-aligned character buffers instead for metadata and function records.
• std::tuple -- use a plain old struct instead.

This is an incremental step in removing all STL references from the
compiler-rt implementation of XRay (llvm.org/PR32274).

[dblaikie]

compiler-rt/lib/xray/xray_fdr_logging.cc

212–213

All upper/underscores doesn't seem to match the LLVM naming convention here

[dberris]

• fixup: follow naming convention for local variables

[dberris]

• fixup: fix alignment of array, and undo unnecessary formatting

compiler-rt/lib/xray/xray_fdr_logging.cc

 // This file is a part of XRay, a dynamic runtime instrumentation system.
 //
 // Here we implement the Flight Data Recorder mode for XRay, where we use
 // compact structures to store records in memory as well as when writing out the
 // data to files.
 //
 //===----------------------------------------------------------------------===//
 #include "xray_fdr_logging.h"
-#include <algorithm>
-#include <bitset>
-#include <cerrno>
-#include <cstring>
 #include <sys/syscall.h>
 #include <sys/time.h>
 #include <time.h>
 #include <unistd.h>
-#include <unordered_map>
 
 #include "sanitizer_common/sanitizer_atomic.h"
 #include "sanitizer_common/sanitizer_common.h"
 #include "xray/xray_interface.h"
 #include "xray/xray_records.h"
 #include "xray_buffer_queue.h"
 #include "xray_defs.h"
 #include "xray_fdr_logging_impl.h"
if (CurrentFlushingStatus == XRayLogFlushStatus::XRAY_LOG_NOT_FLUSHING)
       break;
     CurrentFlushingStatus = XRayLogFlushStatus::XRAY_LOG_FLUSHED;
   }
 
   // At this point, we know that the status is flushed, and that we can assume
   return XRayLogInitStatus::XRAY_LOG_UNINITIALIZED;
 }
 
-static std::tuple<uint64_t, unsigned char>
-getTimestamp() XRAY_NEVER_INSTRUMENT {
+struct TSCAndCPU {
+  uint64_t TSC;
+  unsigned char CPU;
+};
+
+static TSCAndCPU getTimestamp() XRAY_NEVER_INSTRUMENT {
   // We want to get the TSC as early as possible, so that we can check whether
   // we've seen this CPU before. We also do it before we load anything else, to
   // allow for forward progress with the scheduling.
-  unsigned char CPU;
-  uint64_t TSC;
+  TSCAndCPU Result;
 
   // Test once for required CPU features
   static bool TSCSupported = probeRequiredCPUFeatures();
 
   if (TSCSupported) {
-    TSC = __xray::readTSC(CPU);
+    Result.TSC = __xray::readTSC(Result.CPU);
   } else {
     // FIXME: This code needs refactoring as it appears in multiple locations
     timespec TS;
     int result = clock_gettime(CLOCK_REALTIME, &TS);
     if (result != 0) {
       Report("clock_gettime(2) return %d, errno=%d", result, int(errno));
       TS = {0, 0};
     }
-    CPU = 0;
-    TSC = TS.tv_sec * __xray::NanosecondsPerSecond + TS.tv_nsec;
+    Result.CPU = 0;
+    Result.TSC = TS.tv_sec * __xray::NanosecondsPerSecond + TS.tv_nsec;
   }
-  return std::make_tuple(TSC, CPU);
+  return Result;
 }
 
 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);
+  auto TC = getTimestamp();
+  __xray_fdr_internal::processFunctionHook(FuncId, Entry, TC.TSC,
+                                           TC.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);
+  auto TC = getTimestamp();
+  __xray_fdr_internal::processFunctionHook(
+      FuncId, Entry, TC.TSC, TC.CPU, Arg, clock_gettime, *BQ);
 }
 
 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);
+  auto TC = getTimestamp();
+  auto &TSC = TC.TSC;
+  auto &CPU = TC.CPU;
   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 = [&] {
void fdrLoggingHandleCustomEvent(void *Event,
   // Write the custom event metadata record, which consists of the following
   // information:
   //   - 8 bytes (64-bits) for the full TSC when the event started.
   //   - 4 bytes (32-bits) for the length of the data.
   MetadataRecord CustomEvent;
   CustomEvent.Type = uint8_t(RecordType::Metadata);
   CustomEvent.RecordKind =
       uint8_t(MetadataRecord::RecordKinds::CustomEventMarker);
-  constexpr auto TSCSize = sizeof(std::get<0>(TSC_CPU));
+  constexpr auto TSCSize = sizeof(TC.TSC);
   std::memcpy(&CustomEvent.Data, &ReducedEventSize, sizeof(int32_t));
   std::memcpy(&CustomEvent.Data[sizeof(int32_t)], &TSC, TSCSize);
   std::memcpy(TLD.RecordPtr, &CustomEvent, sizeof(CustomEvent));
   TLD.RecordPtr += sizeof(CustomEvent);
   std::memcpy(TLD.RecordPtr, Event, ReducedEventSize);
   endBufferIfFull();
 }
 

compiler-rt/lib/xray/xray_fdr_logging_impl.h

 // Data Recorder mode for XRay, where we use compact structures to store records
 // in memory as well as when writing out the data to files.
 //
 //===----------------------------------------------------------------------===//
 #ifndef XRAY_XRAY_FDR_LOGGING_IMPL_H
 #define XRAY_XRAY_FDR_LOGGING_IMPL_H
 
 #include <cassert>
-#include <cstdint>
+#include <cstddef>
 #include <cstring>
 #include <limits>
-#include <memory>
 #include <pthread.h>
-#include <string>
 #include <sys/syscall.h>
 #include <time.h>
 #include <unistd.h>
 
+// FIXME: Implement analogues to std::shared_ptr and std::weak_ptr
+#include <memory>
+
 #include "sanitizer_common/sanitizer_common.h"
 #include "xray/xray_log_interface.h"
 #include "xray_buffer_queue.h"
 #include "xray_defs.h"
 #include "xray_fdr_log_records.h"
 #include "xray_flags.h"
 #include "xray_tsc.h"
 

 
 /// TSC Wrap records are written when a TSC delta encoding scheme overflows.
 static void writeTSCWrapMetadata(uint64_t TSC);
 
 // Group together thread-local-data in a struct, then hide it behind a function
 // call so that it can be initialized on first use instead of as a global. We
 // force the alignment to 64-bytes for x86 cache line alignment, as this
 // structure is used in the hot path of implementation.
-struct ALIGNED(64) ThreadLocalData {
+struct alignas(64) ThreadLocalData {
   BufferQueue::Buffer Buffer;
   char *RecordPtr = nullptr;
   // The number of FunctionEntry records immediately preceding RecordPtr.
   uint8_t NumConsecutiveFnEnters = 0;
 
   // The number of adjacent, consecutive pairs of FunctionEntry, Tail Exit
   // records preceding RecordPtr.
   uint8_t NumTailCalls = 0;

 // With the approach taken where, we attempt to avoid the potential for
 // deadlocks by relying instead on pthread's memory management routines.
 static ThreadLocalData &getThreadLocalData() {
   thread_local pthread_key_t key;
 
   // We need aligned, uninitialized storage for the TLS object which is
   // trivially destructible. We're going to use this as raw storage and
   // placement-new the ThreadLocalData object into it later.
-  thread_local std::aligned_storage<sizeof(ThreadLocalData),
-                                    alignof(ThreadLocalData)>::type TLSBuffer;
+  alignas(alignof(ThreadLocalData)) thread_local unsigned char
+      TLSBuffer[sizeof(ThreadLocalData)];
 
   // Ensure that we only actually ever do the pthread initialization once.
   thread_local bool UNUSED Unused = [] {
     new (&TLSBuffer) ThreadLocalData();
     auto result = pthread_key_create(&key, +[](void *) {
       auto &TLD = *reinterpret_cast<ThreadLocalData *>(&TLSBuffer);
       auto &RecordPtr = TLD.RecordPtr;
       auto &Buffers = TLD.LocalBQ;
if (result != 0) {
       Report("Failed to allocate thread-local data through pthread; error=%d",
              result);
       return false;
     }
     pthread_setspecific(key, &TLSBuffer);
     return true;
   }();
 
-  return *reinterpret_cast<ThreadLocalData *>(&TLSBuffer);
+  return *reinterpret_cast<ThreadLocalData *>(TLSBuffer);
 }
 
 //-----------------------------------------------------------------------------|
 // The rest of the file is implementation.                                     |
 //-----------------------------------------------------------------------------|
 // Functions are implemented in the header for inlining since we don't want    |
 // to grow the stack when we've hijacked the binary for logging.               |
 //-----------------------------------------------------------------------------|
public:
   }
 };
 
 } // namespace
 
 inline void writeNewBufferPreamble(pid_t Tid, timespec TS,
                                    char *&MemPtr) XRAY_NEVER_INSTRUMENT {
   static constexpr int InitRecordsCount = 2;
-  std::aligned_storage<sizeof(MetadataRecord)>::type Records[InitRecordsCount];
+  alignas(alignof(MetadataRecord)) unsigned char
+      Records[InitRecordsCount * MetadataRecSize];
   {
     // Write out a MetadataRecord to signify that this is the start of a new
     // buffer, associated with a particular thread, with a new CPU.  For the
     // data, we have 15 bytes to squeeze as much information as we can.  At this
     // point we only write down the following bytes:
     //   - Thread ID (pid_t, 4 bytes)
-    auto &NewBuffer = *reinterpret_cast<MetadataRecord *>(&Records[0]);
+    auto &NewBuffer = *reinterpret_cast<MetadataRecord *>(Records);
     NewBuffer.Type = uint8_t(RecordType::Metadata);
     NewBuffer.RecordKind = uint8_t(MetadataRecord::RecordKinds::NewBuffer);
     std::memcpy(&NewBuffer.Data, &Tid, sizeof(pid_t));
   }
   // Also write the WalltimeMarker record.
   {
     static_assert(sizeof(time_t) <= 8, "time_t needs to be at most 8 bytes");
-    auto &WalltimeMarker = *reinterpret_cast<MetadataRecord *>(&Records[1]);
+    auto &WalltimeMarker =
+        *reinterpret_cast<MetadataRecord *>(Records + MetadataRecSize);
     WalltimeMarker.Type = uint8_t(RecordType::Metadata);
     WalltimeMarker.RecordKind =
         uint8_t(MetadataRecord::RecordKinds::WalltimeMarker);
 
     // We only really need microsecond precision here, and enforce across
     // platforms that we need 64-bit seconds and 32-bit microseconds encoded in
     // the Metadata record.
     int32_t Micros = TS.tv_nsec / 1000;
static inline void writeCallArgumentMetadata(uint64_t A) XRAY_NEVER_INSTRUMENT {
   std::memcpy(CallArg.Data, &A, sizeof(A));
   std::memcpy(TLD.RecordPtr, &CallArg, sizeof(MetadataRecord));
   TLD.RecordPtr += sizeof(MetadataRecord);
 }
 
 static inline void writeFunctionRecord(int FuncId, uint32_t TSCDelta,
                                        XRayEntryType EntryType,
                                        char *&MemPtr) XRAY_NEVER_INSTRUMENT {
-  std::aligned_storage<sizeof(FunctionRecord), alignof(FunctionRecord)>::type
-      AlignedFuncRecordBuffer;
-  auto &FuncRecord =
-      *reinterpret_cast<FunctionRecord *>(&AlignedFuncRecordBuffer);
+  FunctionRecord FuncRecord;
   FuncRecord.Type = uint8_t(RecordType::Function);
   // Only take 28 bits of the function id.
   FuncRecord.FuncId = FuncId & ~(0x0F << 28);
   FuncRecord.TSCDelta = TSCDelta;
 
   auto &TLD = getThreadLocalData();
   switch (EntryType) {
   case XRayEntryType::ENTRY:
static bool Once = [&] {
              FuncId);
       return true;
     }();
     (void)Once;
     return;
   }
   }
 
-  std::memcpy(MemPtr, &AlignedFuncRecordBuffer, sizeof(FunctionRecord));
+  std::memcpy(MemPtr, &FuncRecord, sizeof(FunctionRecord));
   MemPtr += sizeof(FunctionRecord);
 }
 
 static uint64_t thresholdTicks() {
   static uint64_t TicksPerSec = probeRequiredCPUFeatures()
                                     ? getTSCFrequency()
                                     : __xray::NanosecondsPerSecond;
   static const uint64_t ThresholdTicks =
       TicksPerSec * flags()->xray_fdr_log_func_duration_threshold_us / 1000000;
   return ThresholdTicks;
 }
 
 // Re-point the thread local pointer into this thread's Buffer before the recent
 // "Function Entry" record and any "Tail Call Exit" records after that.
 static void rewindRecentCall(uint64_t TSC, uint64_t &LastTSC,
                              uint64_t &LastFunctionEntryTSC, int32_t FuncId) {
-  using AlignedFuncStorage =
-      std::aligned_storage<sizeof(FunctionRecord),
-                           alignof(FunctionRecord)>::type;
   auto &TLD = getThreadLocalData();
   TLD.RecordPtr -= FunctionRecSize;
-  AlignedFuncStorage AlignedFuncRecordBuffer;
-  const auto &FuncRecord = *reinterpret_cast<FunctionRecord *>(
-      std::memcpy(&AlignedFuncRecordBuffer, TLD.RecordPtr, FunctionRecSize));
+  FunctionRecord FuncRecord;
+  std::memcpy(&FuncRecord, TLD.RecordPtr, FunctionRecSize);
   assert(FuncRecord.RecordKind ==
              uint8_t(FunctionRecord::RecordKinds::FunctionEnter) &&
          "Expected to find function entry recording when rewinding.");
   assert(FuncRecord.FuncId == (FuncId & ~(0x0F << 28)) &&
          "Expected matching function id when rewinding Exit");
   --TLD.NumConsecutiveFnEnters;
   LastTSC -= FuncRecord.TSCDelta;
 
   // We unwound one call. Update the state and return without writing a log.
   if (TLD.NumConsecutiveFnEnters != 0) {
     LastFunctionEntryTSC -= FuncRecord.TSCDelta;
     return;
   }
 
   // Otherwise we've rewound the stack of all function entries, we might be
   // able to rewind further by erasing tail call functions that are being
   // exited from via this exit.
   LastFunctionEntryTSC = 0;
   auto RewindingTSC = LastTSC;
   auto RewindingRecordPtr = TLD.RecordPtr - FunctionRecSize;
   while (TLD.NumTailCalls > 0) {
-    AlignedFuncStorage TailExitRecordBuffer;
     // Rewind the TSC back over the TAIL EXIT record.
-    const auto &ExpectedTailExit =
-        *reinterpret_cast<FunctionRecord *>(std::memcpy(
-            &TailExitRecordBuffer, RewindingRecordPtr, FunctionRecSize));
+    FunctionRecord ExpectedTailExit;
+    std::memcpy(&ExpectedTailExit, RewindingRecordPtr, FunctionRecSize);
 
     assert(ExpectedTailExit.RecordKind ==
                uint8_t(FunctionRecord::RecordKinds::FunctionTailExit) &&
            "Expected to find tail exit when rewinding.");
     RewindingRecordPtr -= FunctionRecSize;
     RewindingTSC -= ExpectedTailExit.TSCDelta;
-    AlignedFuncStorage FunctionEntryBuffer;
-    const auto &ExpectedFunctionEntry = *reinterpret_cast<FunctionRecord *>(
-        std::memcpy(&FunctionEntryBuffer, RewindingRecordPtr, FunctionRecSize));
+    FunctionRecord ExpectedFunctionEntry;
+    std::memcpy(&ExpectedFunctionEntry, RewindingRecordPtr, FunctionRecSize);
     assert(ExpectedFunctionEntry.RecordKind ==
                uint8_t(FunctionRecord::RecordKinds::FunctionEnter) &&
            "Expected to find function entry when rewinding tail call.");
     assert(ExpectedFunctionEntry.FuncId == ExpectedTailExit.FuncId &&
            "Expected funcids to match when rewinding tail call.");
 
     // This tail call exceeded the threshold duration. It will not be erased.
     if ((TSC - RewindingTSC) >= thresholdTicks()) {