Cleanup loggings and comments

Author: HighW4y2H3ll

llvm/test/tools/llvm-profgen/missing-dwarf.test

@@ -7,9 +7,7 @@
 ; Test --load-function-from-symbol=0
 ; RUN: llvm-profgen --format=text --unsymbolized-profile=%t.prof --binary=%S/Inputs/missing-dwarf.exe --output=%t1 --fill-zero-for-all-funcs --show-detailed-warning --use-offset=0 --load-function-from-symbol=0 2>&1 | FileCheck %s --check-prefix=CHECK-NO-LOAD-SYMTAB
 
-; CHECK-NO-LOAD-SYMTAB:      warning: 100.00%(1/1) of function range samples do not belong to any function
-; CHECK-NO-LOAD-SYMTAB-NEXT: warning: 100.00%(1/1) of LBR source samples do not belong to any function
-; CHECK-NO-LOAD-SYMTAB-NEXT: warning: 100.00%(1/1) of LBR target samples do not belong to any function
+; CHECK-NO-LOAD-SYMTAB:      warning: Loading of DWARF info completed, but no binary functions have been retrieved.
 
 ; Test --load-function-from-symbol=1
 ; RUN: llvm-profgen --format=text --unsymbolized-profile=%t.prof --binary=%S/Inputs/missing-dwarf.exe --output=%t2 --fill-zero-for-all-funcs --show-detailed-warning --use-offset=0 --load-function-from-symbol=1

llvm/tools/llvm-profgen/PerfReader.cpp

@@ -1274,13 +1274,17 @@ void PerfScriptReader::warnInvalidRange() {
 
   const char *EndNotBoundaryMsg = "Range is not on instruction boundary, "
                                   "likely due to profile and binary mismatch.";
+  const char *DanglingRangeMsg = "Range does not belong to any functions, "
+                                 "likely from PLT, .init or .fini section.";
   const char *RangeCrossFuncMsg =
       "Fall through range should not cross function boundaries, likely due to "
       "profile and binary mismatch.";
   const char *BogusRangeMsg = "Range start is after or too far from range end.";
 
   uint64_t TotalRangeNum = 0;
   uint64_t InstNotBoundary = 0;
+  uint64_t UnmatchedRange = 0;
+  uint64_t RecoveredRange = 0;
   uint64_t RangeCrossFunc = 0;
   uint64_t BogusRange = 0;
 
@@ -1300,8 +1304,14 @@ void PerfScriptReader::warnInvalidRange() {
     }
 
     auto *FRange = Binary->findFuncRange(StartAddress);
-    if (!FRange)
+    if (!FRange) {
+      UnmatchedRange += I.second;
+      WarnInvalidRange(StartAddress, EndAddress, DanglingRangeMsg);
       continue;
+    }
+
+    if (FRange->Func->FromSymtab)
+      RecoveredRange += I.second;
 
     if (EndAddress >= FRange->EndAddress) {
       RangeCrossFunc += I.second;
@@ -1319,6 +1329,12 @@ void PerfScriptReader::warnInvalidRange() {
   emitWarningSummary(
       InstNotBoundary, TotalRangeNum,
       "of samples are from ranges that are not on instruction boundary.");
+  emitWarningSummary(
+      UnmatchedRange, TotalRangeNum,
+      "of samples are from ranges that do not belong to any functions.");
+  emitWarningSummary(
+      RecoveredRange, TotalRangeNum,
+      "of samples are from ranges that belong to functions recovered from symbol table.");
   emitWarningSummary(
       RangeCrossFunc, TotalRangeNum,
       "of samples are from ranges that do cross function boundaries.");

llvm/tools/llvm-profgen/ProfileGenerator.cpp

@@ -449,62 +449,29 @@ bool ProfileGeneratorBase::collectFunctionsFromRawProfile(
   // Go through all the stacks, ranges and branches in sample counters, use
   // the start of the range to look up the function it belongs and record the
   // function.
-  uint64_t ErrStkAddr = 0, ErrFuncRange = 0, ErrSrc = 0, ErrTgt = 0;
-  uint64_t TotalStkAddr = 0, TotalFuncRange = 0, TotalSrc = 0, TotalTgt = 0;
   for (const auto &CI : *SampleCounters) {
     if (const auto *CtxKey = dyn_cast<AddrBasedCtxKey>(CI.first.getPtr())) {
       for (auto StackAddr : CtxKey->Context) {
-        uint64_t Inc = Binary->addressIsCode(StackAddr) ? 1 : 0;
-        TotalStkAddr += Inc;
         if (FuncRange *FRange = Binary->findFuncRange(StackAddr))
           ProfiledFunctions.insert(FRange->Func);
-        else
-          ErrStkAddr += Inc;
       }
     }
 
     for (auto Item : CI.second.RangeCounter) {
       uint64_t StartAddress = Item.first.first;
-      uint64_t Inc = Binary->addressIsCode(StartAddress) ? Item.second : 0;
-      TotalFuncRange += Inc;
       if (FuncRange *FRange = Binary->findFuncRange(StartAddress))
         ProfiledFunctions.insert(FRange->Func);
-      else
-        ErrFuncRange += Inc;
     }
 
     for (auto Item : CI.second.BranchCounter) {
       uint64_t SourceAddress = Item.first.first;
       uint64_t TargetAddress = Item.first.second;
-      uint64_t SrcInc = Binary->addressIsCode(SourceAddress) ? Item.second : 0;
-      uint64_t TgtInc = Binary->addressIsCode(TargetAddress) ? Item.second : 0;
-      TotalSrc += SrcInc;
       if (FuncRange *FRange = Binary->findFuncRange(SourceAddress))
         ProfiledFunctions.insert(FRange->Func);
-      else
-        ErrSrc += SrcInc;
-      TotalTgt += TgtInc;
       if (FuncRange *FRange = Binary->findFuncRange(TargetAddress))
         ProfiledFunctions.insert(FRange->Func);
-      else
-        ErrTgt += TgtInc;
     }
   }
-
-  if (ErrStkAddr)
-    emitWarningSummary(
-        ErrStkAddr, TotalStkAddr,
-        "of stack address samples do not belong to any function");
-  if (ErrFuncRange)
-    emitWarningSummary(
-        ErrFuncRange, TotalFuncRange,
-        "of function range samples do not belong to any function");
-  if (ErrSrc)
-    emitWarningSummary(ErrSrc, TotalSrc,
-                       "of LBR source samples do not belong to any function");
-  if (ErrTgt)
-    emitWarningSummary(ErrTgt, TotalTgt,
-                       "of LBR target samples do not belong to any function");
   return true;
 }
 

llvm/tools/llvm-profgen/ProfiledBinary.cpp

@@ -831,13 +831,21 @@ void ProfiledBinary::populateSymbolAddressList(const ObjectFile *Obj) {
 }
 
 void ProfiledBinary::populateSymbolsFromBinary(const ObjectFile *Obj) {
-  // Load binary functions from symbol table when Debug info is incomplete
-  const SmallVector<StringRef> Suffixes(
-      {".destroy", ".resume", ".llvm.", ".cold", ".warm"});
+  // Load binary functions from symbol table when Debug info is incomplete.
+  // Strip the internal suffixes which are not reflected in the DWARF info.
+  const SmallVector<StringRef, 6> Suffixes(
+      {
+        // Internal suffixes from CoroSplit pass
+        ".cleanup", ".destroy", ".resume",
+        // Internal suffixes from Bolt
+        ".cold", ".warm",
+        // Compiler internal
+        ".llvm.",
+      });
   StringRef FileName = Obj->getFileName();
   for (const SymbolRef &Symbol : Obj->symbols()) {
     const SymbolRef::Type Type = unwrapOrError(Symbol.getType(), FileName);
-    const uint64_t Addr = unwrapOrError(Symbol.getAddress(), FileName);
+    const uint64_t StartAddr = unwrapOrError(Symbol.getAddress(), FileName);
     const StringRef Name = unwrapOrError(Symbol.getName(), FileName);
     uint64_t Size = 0;
     if (isa<ELFObjectFileBase>(Symbol.getObject())) {
@@ -855,25 +863,26 @@ void ProfiledBinary::populateSymbolsFromBinary(const ObjectFile *Obj) {
     auto &Func = Ret.first->second;
     if (Ret.second) {
       Func.FuncName = Ret.first->first;
+      Func.FromSymtab = true;
       HashBinaryFunctions[MD5Hash(StringRef(SymName))] = &Func;
     }
 
-    if (auto Range = findFuncRange(Addr)) {
-      if (Ret.second && ShowDetailedWarning)
+    if (auto Range = findFuncRange(StartAddr)) {
+      if (Ret.second && Range->getFuncName() != SymName && ShowDetailedWarning)
         WithColor::warning()
-            << "Symbol " << Name << " start address "
-            << format("%8" PRIx64, Addr) << " already exists in DWARF at "
-            << format("%8" PRIx64, Range->StartAddress) << " in function "
-            << Range->getFuncName() << "\n";
+            << "Conflicting symbol " << Name << " already exists in DWARF as "
+            << Range->getFuncName() << " at address " << format("%8" PRIx64, StartAddr)
+            << ". The DWARF indicates a range from " << format("%8" PRIx64, Range->StartAddress) << " to "
+            << format("%8" PRIx64, Range->EndAddress) << "\n";
     } else {
       // Store/Update Function Range from SymTab
-      Func.Ranges.emplace_back(Addr, Addr + Size);
+      Func.Ranges.emplace_back(StartAddr, StartAddr + Size);
 
-      auto R = StartAddrToFuncRangeMap.emplace(Addr, FuncRange());
+      auto R = StartAddrToFuncRangeMap.emplace(StartAddr, FuncRange());
       FuncRange &FRange = R.first->second;
       FRange.Func = &Func;
-      FRange.StartAddress = Addr;
-      FRange.EndAddress = Addr + Size;
+      FRange.StartAddress = StartAddr;
+      FRange.EndAddress = StartAddr + Size;
     }
   }
 }
@@ -902,8 +911,10 @@ void ProfiledBinary::loadSymbolsFromDWARFUnit(DWARFUnit &CompilationUnit) {
     // BinaryFunction indexed by the name.
     auto Ret = BinaryFunctions.emplace(Name, BinaryFunction());
     auto &Func = Ret.first->second;
-    if (Ret.second)
+    if (Ret.second) {
       Func.FuncName = Ret.first->first;
+      Func.FromSymtab = false;
+    }
 
     for (const auto &Range : Ranges) {
       uint64_t StartAddress = Range.LowPC;

llvm/tools/llvm-profgen/ProfiledBinary.h

@@ -76,6 +76,7 @@ struct BinaryFunction {
   StringRef FuncName;
   // End of range is an exclusive bound.
   RangesTy Ranges;
+  bool FromSymtab;
 
   uint64_t getFuncSize() {
     uint64_t Sum = 0;