[BOLT] Detect .warm split functions as cold fragments (#93759)

CDSplit splits functions up to three ways: main fragment with no suffix,
and fragments with .cold and .warm suffixes.

Add .warm suffix to the regex used to recognize split fragments.

Test Plan: updated register-fragments-bolt-symbols.s

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -21,6 +21,7 @@
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Support/Error.h"
+#include "llvm/Support/Regex.h"
 #include <map>
 #include <set>
 #include <unordered_map>
@@ -596,6 +597,9 @@ private:
 
   NameResolver NR;
 
+  // Regex object matching split function names.
+  const Regex FunctionFragmentTemplate{"(.*)\\.(cold|warm)(\\.[0-9]+)?"};
+
   friend class RewriteInstanceDiff;
 };
 

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -55,7 +55,6 @@
 #include "llvm/Support/Error.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/ManagedStatic.h"
-#include "llvm/Support/Regex.h"
 #include "llvm/Support/Timer.h"
 #include "llvm/Support/ToolOutputFile.h"
 #include "llvm/Support/raw_ostream.h"
@@ -945,9 +944,6 @@ void RewriteInstance::discoverFileObjects() {
   BinaryFunction *PreviousFunction = nullptr;
   unsigned AnonymousId = 0;
 
-  // Regex object for matching cold fragments.
-  const Regex ColdFragment(".*\\.cold(\\.[0-9]+)?");
-
   const auto SortedSymbolsEnd =
       LastSymbol == SortedSymbols.end() ? LastSymbol : std::next(LastSymbol);
   for (auto Iter = SortedSymbols.begin(); Iter != SortedSymbolsEnd; ++Iter) {
@@ -1229,7 +1225,7 @@ void RewriteInstance::discoverFileObjects() {
     }
 
     // Check if it's a cold function fragment.
-    if (ColdFragment.match(SymName)) {
+    if (FunctionFragmentTemplate.match(SymName)) {
       static bool PrintedWarning = false;
       if (!PrintedWarning) {
         PrintedWarning = true;
@@ -1460,10 +1456,10 @@ void RewriteInstance::registerFragments() {
     for (StringRef Name : Function.getNames()) {
       StringRef BaseName = NR.restore(Name);
       const bool IsGlobal = BaseName == Name;
-      const size_t ColdSuffixPos = BaseName.find(".cold");
-      if (ColdSuffixPos == StringRef::npos)
+      SmallVector<StringRef> Matches;
+      if (!FunctionFragmentTemplate.match(BaseName, &Matches))
         continue;
-      StringRef ParentName = BaseName.substr(0, ColdSuffixPos);
+      StringRef ParentName = Matches[1];
       const BinaryData *BD = BC->getBinaryDataByName(ParentName);
       const uint64_t NumPossibleLocalParents =
           NR.getUniquifiedNameCount(ParentName);

bolt/test/X86/register-fragments-bolt-symbols.s

@@ -3,8 +3,20 @@
 # RUN: llvm-mc --filetype=obj --triple x86_64-unknown-unknown %S/cdsplit-symbol-names.s -o %t.main.o
 # RUN: llvm-mc --filetype=obj --triple x86_64-unknown-unknown %s -o %t.chain.o
 # RUN: link_fdata %S/cdsplit-symbol-names.s %t.main.o %t.fdata
-# RUN: sed -i 's|chain|chain/2|g' %t.fdata
 # RUN: llvm-strip --strip-unneeded %t.main.o
+
+## Check warm fragment name matching (produced by cdsplit)
+# RUN: %clang %cflags %t.main.o -o %t.warm.exe -Wl,-q
+# RUN: llvm-bolt %t.warm.exe -o %t.warm.bolt --split-functions --split-strategy=cdsplit \
+# RUN:   --call-scale=2 --data=%t.fdata --reorder-blocks=ext-tsp --enable-bat
+# RUN: link_fdata %s %t.warm.bolt %t.preagg.warm PREAGGWARM
+# PREAGGWARM: B X:0 #chain.warm# 1 0
+# RUN: perf2bolt %t.warm.bolt -p %t.preagg.warm --pa -o %t.warm.fdata -w %t.warm.yaml \
+# RUN:   -v=1 | FileCheck %s --check-prefix=CHECK-BOLT-WARM
+
+# CHECK-BOLT-WARM: marking chain.warm/1(*2) as a fragment of chain
+
+# RUN: sed -i 's|chain|chain/2|g' %t.fdata
 # RUN: llvm-objcopy --localize-symbol=chain %t.main.o
 # RUN: %clang %cflags %t.chain.o %t.main.o -o %t.exe -Wl,-q
 # RUN: llvm-bolt %t.exe -o %t.bolt --split-functions --split-strategy=randomN \