[llvm-branch-commits] [llvm-profgen][NFC] Reuse isLBRSample (PR #191595)

[via llvm-branch-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-pgo

Author: Amir Ayupov (aaupov)

<details>
<summary>Changes</summary>

Replace `StringRef::starts_with(" 0x")` calls with explicit `isLBRSample` checks.
This is needed to support buildid-prefixed addresses in a follow-up #<!-- -->190863.

---
Full diff: https://github.com/llvm/llvm-project/pull/191595.diff


2 Files Affected:

- (modified) llvm/tools/llvm-profgen/PerfReader.cpp (+13-8) 
- (modified) llvm/tools/llvm-profgen/PerfReader.h (+1-1) 


``````````diff
diff --git a/llvm/tools/llvm-profgen/PerfReader.cpp b/llvm/tools/llvm-profgen/PerfReader.cpp
index 9dda11a7ade50..b933a740ff55c 100644
--- a/llvm/tools/llvm-profgen/PerfReader.cpp
+++ b/llvm/tools/llvm-profgen/PerfReader.cpp
@@ -737,7 +737,7 @@ bool PerfScriptReader::extractCallstack(TraceStream &TraceIt,
   // It's in bottom-up order with each frame in one line.
 
   // Extract stack frames from sample
-  while (!TraceIt.isAtEoF() && !TraceIt.getCurrentLine().starts_with(" 0x")) {
+  while (!TraceIt.isAtEoF() && !isLBRSample(TraceIt.getCurrentLine(), true)) {
     StringRef FrameStr = TraceIt.getCurrentLine().ltrim();
     uint64_t FrameAddr = 0;
     if (parseAddress(FrameStr, FrameAddr)) {
@@ -785,7 +785,7 @@ bool PerfScriptReader::extractCallstack(TraceStream &TraceIt,
   // 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().starts_with(" 0x")) {
+  while (!TraceIt.isAtEoF() && !isLBRSample(TraceIt.getCurrentLine(), true)) {
     TraceIt.advance();
   }
   // Filter out broken stack sample. We may not have complete frame info
@@ -830,14 +830,14 @@ void HybridPerfReader::parseSample(TraceStream &TraceIt, uint64_t Count) {
   // Parsing call stack and populate into PerfSample.CallStack
   if (!extractCallstack(TraceIt, Sample->CallStack)) {
     // Skip the next LBR line matched current call stack
-    if (!TraceIt.isAtEoF() && TraceIt.getCurrentLine().starts_with(" 0x"))
+    if (!TraceIt.isAtEoF() && isLBRSample(TraceIt.getCurrentLine(), true))
       TraceIt.advance();
     return;
   }
 
   warnIfMissingMMap();
 
-  if (!TraceIt.isAtEoF() && TraceIt.getCurrentLine().starts_with(" 0x")) {
+  if (!TraceIt.isAtEoF() && isLBRSample(TraceIt.getCurrentLine(), true)) {
     // Parsing LBR stack and populate into PerfSample.LBRStack
     if (extractLBRStack(TraceIt, Sample->LBRStack)) {
       if (IgnoreStackSamples) {
@@ -1162,13 +1162,18 @@ void PerfScriptReader::parseAndAggregateTrace() {
 // 40062f 0x5c6313f/0x5c63170/P/-/-/0  0x5c630e7/0x5c63130/P/-/-/0 ...
 // A heuristic for fast detection by checking whether a
 // leading "  0x" and the '/' exist.
-bool PerfScriptReader::isLBRSample(StringRef Line) {
+bool PerfScriptReader::isLBRSample(StringRef Line, bool CheckLineStart) {
   // Skip the leading instruction pointer
   SmallVector<StringRef, 32> Records;
-  Line.trim().split(Records, " ", 2, false);
+  if (!CheckLineStart)
+    Line = Line.trim();
+  Line.split(Records, " ", 2, CheckLineStart);
   if (Records.size() < 2)
     return false;
-  if (Records[1].starts_with("0x") && Records[1].contains('/'))
+  StringRef Token = Records[1];
+  if (!Token.contains('/'))
+    return false;
+  if (Token.starts_with("0x"))
     return true;
   return false;
 }
@@ -1213,7 +1218,7 @@ PerfContent PerfScriptReader::checkPerfScriptType(StringRef FileName) {
       TraceIt.advance();
     }
     if (!TraceIt.isAtEoF()) {
-      if (isLBRSample(TraceIt.getCurrentLine())) {
+      if (isLBRSample(TraceIt.getCurrentLine(), false)) {
         if (Count > 0)
           return HasAggCount ? PerfContent::AggLBRStack : PerfContent::LBRStack;
         else
diff --git a/llvm/tools/llvm-profgen/PerfReader.h b/llvm/tools/llvm-profgen/PerfReader.h
index 83c4fb0447c5c..358d61067a4ef 100644
--- a/llvm/tools/llvm-profgen/PerfReader.h
+++ b/llvm/tools/llvm-profgen/PerfReader.h
@@ -636,7 +636,7 @@ class PerfScriptReader : public PerfReaderBase {
 
 protected:
   // Check whether a given line is LBR sample
-  static bool isLBRSample(StringRef Line);
+  static bool isLBRSample(StringRef Line, bool CheckLineStart);
   // Check whether a given line is MMAP event
   static bool isMMapEvent(StringRef Line);
   // Update base address based on mmap events

``````````

</details>


https://github.com/llvm/llvm-project/pull/191595