[XRay][compiler-rt] Always place the CPU record first for every buffer

Summary:
In FDR Mode, when we set up a new buffer for a thread that's just
overflowed, we must place the CPU identifier with the TSC record as the
first record. This is so that we can reconstruct all the function
entry/exit with deltas rooted on a TSC record for the CPU at the
beginning of the buffer.

Without doing this, the tools are rejecting the log for cases when we've
overflown and have different buffers that don't have the CPU and TSC
records as the first entry in the buffers.

Reviewers: pelikan

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D38995

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@315987 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 16 insertions, 9 deletions

diff --git a/lib/xray/xray_fdr_logging.cc b/lib/xray/xray_fdr_logging.cc
index bd79893f6..90eb6c572 100644
--- a/lib/xray/xray_fdr_logging.cc
+++ b/lib/xray/xray_fdr_logging.cc
@@ -206,17 +206,17 @@ getTimestamp() XRAY_NEVER_INSTRUMENT {
 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 @@ void fdrLoggingHandleCustomEvent(void *Event,
   //   - 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;
   }
diff --git a/lib/xray/xray_fdr_logging_impl.h b/lib/xray/xray_fdr_logging_impl.h
index aec205e8a..f7c77c6c2 100644
--- a/lib/xray/xray_fdr_logging_impl.h
+++ b/lib/xray/xray_fdr_logging_impl.h
@@ -532,7 +532,8 @@ inline bool releaseThreadLocalBuffer(BufferQueue &BQArg) {
   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 @@ inline bool prepareBuffer(int (*wall_clock_reader)(clockid_t,
       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 @@ inline bool isLogInitializedAndReady(
     }
 
     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 @@ inline void processFunctionHook(
   // 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;
   }