[CSSPGO][llvm-profgen] Fix bug with parsing hybrid sample trace line

when we skip the call stack starting with an external address, we should also skip the bottom LBR entry, otherwise it will cause a truncated context issue.

Reviewed By: hoy, wenlei

Differential Revision: https://reviews.llvm.org/D95480

Author: wlei-llvm

llvm/test/tools/llvm-profgen/Inputs/inline-cs-noprobe.perfscript

@@ -1,5 +1,11 @@
 PERF_RECORD_MMAP2 2854748/2854748: [0x400000(0x1000) @ 0 00:1d 123291722 526021]: r-xp /home/inline-cs-noprobe.perfbin
 
+; test for an external or invalid top address, should skip the whole sample
+
+	        ffffffff
+	          40067e
+	5541f689495641d7
+ 0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x40069b/0x400670/M/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0  0x4006c8/0x40067e/P/-/-/0
 
 	          40067e
 	5541f689495641d7

llvm/tools/llvm-profgen/PerfReader.cpp

@@ -437,11 +437,12 @@ bool PerfReader::extractCallstack(TraceStream &TraceIt,
   ProfiledBinary *Binary = nullptr;
   while (!TraceIt.isAtEoF() && !TraceIt.getCurrentLine().startswith(" 0x")) {
     StringRef FrameStr = TraceIt.getCurrentLine().ltrim();
-    // We might get an empty line at the beginning or comments, skip it
     uint64_t FrameAddr = 0;
     if (FrameStr.getAsInteger(16, FrameAddr)) {
+      // We might parse a non-perf sample line like empty line and comments,
+      // skip it
       TraceIt.advance();
-      break;
+      return false;
     }
     TraceIt.advance();
     if (!Binary) {
@@ -468,9 +469,9 @@ bool PerfReader::extractCallstack(TraceStream &TraceIt,
     CallStack.emplace_back(FrameAddr);
   }
 
-  if (CallStack.empty())
-    return false;
   // Skip other unrelated line, find the next valid LBR line
+  // Note that even for empty call stack, we should skip the address at the
+  // bottom, otherwise the following pass may generate a truncated callstack
   while (!TraceIt.isAtEoF() && !TraceIt.getCurrentLine().startswith(" 0x")) {
     TraceIt.advance();
   }
@@ -482,7 +483,8 @@ bool PerfReader::extractCallstack(TraceStream &TraceIt,
   // of such case - when sample landed in prolog/epilog, somehow stack
   // walking will be broken in an unexpected way that higher frames will be
   // missing.
-  return !Binary->addressInPrologEpilog(CallStack.front());
+  return !CallStack.empty() &&
+         !Binary->addressInPrologEpilog(CallStack.front());
 }
 
 void PerfReader::parseHybridSample(TraceStream &TraceIt) {