[COFF] Add cg_profile directive and .llvm.call-graph-profile section

[MaskRay]

Hi, your git commit contains extra Phabricator tags. You can drop Reviewers: Subscribers: Tags: and the text Summary: from the git commit with the following script:

arcfilter () {
        arc amend
        git log -1 --pretty=%B | awk '/Reviewers:|Subscribers:/{p=1} /Reviewed By:|Differential Revision:/{p=0} !p && !/^Summary:$/ {sub(/^Summary: /,"");print}' | git commit --amend --date=now -F -
}

Reviewed By: is considered important by some people. Please keep the tag. (--date=now is my personal preference (author dates are usually not useful. Using committer dates can make log almost monotonic in time))

llvm/utils/git/pre-push.py can validate the message does not include unneeded tags.

[zequanwu]

This is the same as D81775, but I put the wrong diff ID in the commit message. Sorry about the confusion.

llvm/include/llvm/MC/MCParser/MCAsmParserExtension.h

public:
   bool parseMany(function_ref<bool()> parseOne, bool hasComma = true) {
     return getParser().parseMany(parseOne, hasComma);
   }
 
   bool parseOptionalToken(AsmToken::TokenKind T) {
     return getParser().parseOptionalToken(T);
   }
 
+  bool ParseDirectiveCGProfile(StringRef, SMLoc);
+
   bool check(bool P, const Twine &Msg) {
     return getParser().check(P, Msg);
   }
 
   bool check(bool P, SMLoc Loc, const Twine &Msg) {
     return getParser().check(P, Loc, Msg);
   }
 

llvm/include/llvm/MC/MCWinCOFFStreamer.h

public:
   void emitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size,
                              unsigned ByteAlignment) override;
   void emitZerofill(MCSection *Section, MCSymbol *Symbol, uint64_t Size,
                     unsigned ByteAlignment, SMLoc Loc = SMLoc()) override;
   void emitTBSSSymbol(MCSection *Section, MCSymbol *Symbol, uint64_t Size,
                       unsigned ByteAlignment) override;
   void emitIdent(StringRef IdentString) override;
   void EmitWinEHHandlerData(SMLoc Loc) override;
+  void emitCGProfileEntry(const MCSymbolRefExpr *From,
+                          const MCSymbolRefExpr *To, uint64_t Count) override;
   void finishImpl() override;
 
   /// \}
 
 protected:
   const MCSymbol *CurSymbol;
 
   void emitInstToData(const MCInst &Inst, const MCSubtargetInfo &STI) override;
 
+  void finalizeCGProfileEntry(const MCSymbolRefExpr *&S);
+  void finalizeCGProfile();
+
 private:
   void Error(const Twine &Msg) const;
 };
 
 } // end namespace llvm
 
 #endif // LLVM_MC_MCWINCOFFSTREAMER_H

llvm/lib/MC/MCParser/COFFAsmParser.cpp

void Initialize(MCAsmParser &Parser) override {
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveEndef>(".endef");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveSecRel32>(".secrel32");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveSymIdx>(".symidx");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveSafeSEH>(".safeseh");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveSecIdx>(".secidx");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveLinkOnce>(".linkonce");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveRVA>(".rva");
     addDirectiveHandler<&COFFAsmParser::ParseDirectiveSymbolAttribute>(".weak");
+    addDirectiveHandler<&COFFAsmParser::ParseDirectiveCGProfile>(".cg_profile");
 
     // Win64 EH directives.
     addDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveStartProc>(
                                                                    ".seh_proc");
     addDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveEndProc>(
                                                                 ".seh_endproc");
     addDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveStartChained>(
                                                            ".seh_startchained");
class COFFAsmParser : public MCAsmParserExtension {
   bool ParseDirectiveEndef(StringRef, SMLoc);
   bool ParseDirectiveSecRel32(StringRef, SMLoc);
   bool ParseDirectiveSecIdx(StringRef, SMLoc);
   bool ParseDirectiveSafeSEH(StringRef, SMLoc);
   bool ParseDirectiveSymIdx(StringRef, SMLoc);
   bool parseCOMDATType(COFF::COMDATType &Type);
   bool ParseDirectiveLinkOnce(StringRef, SMLoc);
   bool ParseDirectiveRVA(StringRef, SMLoc);
+  bool ParseDirectiveCGProfile(StringRef, SMLoc);
 
   // Win64 EH directives.
   bool ParseSEHDirectiveStartProc(StringRef, SMLoc);
   bool ParseSEHDirectiveEndProc(StringRef, SMLoc);
   bool ParseSEHDirectiveStartChained(StringRef, SMLoc);
   bool ParseSEHDirectiveEndChained(StringRef, SMLoc);
   bool ParseSEHDirectiveHandler(StringRef, SMLoc);
   bool ParseSEHDirectiveHandlerData(StringRef, SMLoc);
while (true) {
       Lex();
     }
   }
 
   Lex();
   return false;
 }
 
+bool COFFAsmParser::ParseDirectiveCGProfile(StringRef S, SMLoc Loc) {
+  return MCAsmParserExtension::ParseDirectiveCGProfile(S, Loc);
+}
+
 bool COFFAsmParser::ParseSectionSwitch(StringRef Section,
                                        unsigned Characteristics,
                                        SectionKind Kind) {
   return ParseSectionSwitch(Section, Characteristics, Kind, "", (COFF::COMDATType)0);
 }
 
 bool COFFAsmParser::ParseSectionSwitch(StringRef Section,
                                        unsigned Characteristics,

llvm/lib/MC/MCParser/ELFAsmParser.cpp

if (getLexer().isNot(AsmToken::EndOfStatement))
     return TokError("unexpected token in directive");
 
   Lex();
 
   getStreamer().SubSection(Subsection);
   return false;
 }
 
-/// ParseDirectiveCGProfile
-///  ::= .cg_profile identifier, identifier, <number>
-bool ELFAsmParser::ParseDirectiveCGProfile(StringRef, SMLoc) {
-  StringRef From;
-  SMLoc FromLoc = getLexer().getLoc();
-  if (getParser().parseIdentifier(From))
-    return TokError("expected identifier in directive");
-
-  if (getLexer().isNot(AsmToken::Comma))
-    return TokError("expected a comma");
-  Lex();
-
-  StringRef To;
-  SMLoc ToLoc = getLexer().getLoc();
-  if (getParser().parseIdentifier(To))
-    return TokError("expected identifier in directive");
-
-  if (getLexer().isNot(AsmToken::Comma))
-    return TokError("expected a comma");
-  Lex();
-
-  int64_t Count;
-  if (getParser().parseIntToken(
-          Count, "expected integer count in '.cg_profile' directive"))
-    return true;
-
-  if (getLexer().isNot(AsmToken::EndOfStatement))
-    return TokError("unexpected token in directive");
-
-  MCSymbol *FromSym = getContext().getOrCreateSymbol(From);
-  MCSymbol *ToSym = getContext().getOrCreateSymbol(To);
-
-  getStreamer().emitCGProfileEntry(
-      MCSymbolRefExpr::create(FromSym, MCSymbolRefExpr::VK_None, getContext(),
-                              FromLoc),
-      MCSymbolRefExpr::create(ToSym, MCSymbolRefExpr::VK_None, getContext(),
-                              ToLoc),
-      Count);
-  return false;
+bool ELFAsmParser::ParseDirectiveCGProfile(StringRef S, SMLoc Loc) {
+  return MCAsmParserExtension::ParseDirectiveCGProfile(S, Loc);
 }
 
 namespace llvm {
 
 MCAsmParserExtension *createELFAsmParser() {
   return new ELFAsmParser;
 }
 
 } // end namespace llvm

llvm/lib/MC/MCParser/MCAsmParserExtension.cpp

 //===- MCAsmParserExtension.cpp - Asm Parser Hooks ------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCParser/MCAsmParserExtension.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCStreamer.h"
 
 using namespace llvm;
 
 MCAsmParserExtension::MCAsmParserExtension() = default;
 
 MCAsmParserExtension::~MCAsmParserExtension() = default;
 
 void MCAsmParserExtension::Initialize(MCAsmParser &Parser) {
   this->Parser = &Parser;
 }
+
+/// ParseDirectiveCGProfile
+///  ::= .cg_profile identifier, identifier, <number>
+bool MCAsmParserExtension::ParseDirectiveCGProfile(StringRef, SMLoc) {
+  StringRef From;
+  SMLoc FromLoc = getLexer().getLoc();
+  if (getParser().parseIdentifier(From))
+    return TokError("expected identifier in directive");
+
+  if (getLexer().isNot(AsmToken::Comma))
+    return TokError("expected a comma");
+  Lex();
+
+  StringRef To;
+  SMLoc ToLoc = getLexer().getLoc();
+  if (getParser().parseIdentifier(To))
+    return TokError("expected identifier in directive");
+
+  if (getLexer().isNot(AsmToken::Comma))
+    return TokError("expected a comma");
+  Lex();
+
+  int64_t Count;
+  if (getParser().parseIntToken(
+          Count, "expected integer count in '.cg_profile' directive"))
+    return true;
+
+  if (getLexer().isNot(AsmToken::EndOfStatement))
+    return TokError("unexpected token in directive");
+
+  MCSymbol *FromSym = getContext().getOrCreateSymbol(From);
+  MCSymbol *ToSym = getContext().getOrCreateSymbol(To);
+
+  getStreamer().emitCGProfileEntry(
+      MCSymbolRefExpr::create(FromSym, MCSymbolRefExpr::VK_None, getContext(),
+                              FromLoc),
+      MCSymbolRefExpr::create(ToSym, MCSymbolRefExpr::VK_None, getContext(),
+                              ToLoc),
+      Count);
+  return false;
+}

llvm/lib/MC/MCWinCOFFStreamer.cpp

 void MCWinCOFFStreamer::emitIdent(StringRef IdentString) {
   llvm_unreachable("not implemented");
 }
 
 void MCWinCOFFStreamer::EmitWinEHHandlerData(SMLoc Loc) {
   llvm_unreachable("not implemented");
 }
 
+void MCWinCOFFStreamer::emitCGProfileEntry(const MCSymbolRefExpr *From,
+                                           const MCSymbolRefExpr *To,
+                                           uint64_t Count) {
+  // Ignore temporary symbols for now.
+  if (!From->getSymbol().isTemporary() && !To->getSymbol().isTemporary())
+    getAssembler().CGProfile.push_back({From, To, Count});
+}
+
+void MCWinCOFFStreamer::finalizeCGProfileEntry(const MCSymbolRefExpr *&SRE) {
+  const MCSymbol *S = &SRE->getSymbol();
+  bool Created;
+  getAssembler().registerSymbol(*S, &Created);
+  if (Created) {
+    cast<MCSymbolCOFF>(S)->setIsWeakExternal();
+    cast<MCSymbolCOFF>(S)->setExternal(true);
+  }
+}
+
+void MCWinCOFFStreamer::finalizeCGProfile() {
+  for (MCAssembler::CGProfileEntry &E : getAssembler().CGProfile) {
+    finalizeCGProfileEntry(E.From);
+    finalizeCGProfileEntry(E.To);
+  }
+}
+
 void MCWinCOFFStreamer::finishImpl() {
+  finalizeCGProfile();
+
   MCObjectStreamer::finishImpl();
 }
 
 void MCWinCOFFStreamer::Error(const Twine &Msg) const {
   getContext().reportError(SMLoc(), Msg);
 }

llvm/lib/MC/WinCOFFObjectWriter.cpp

public:
   symbol_list WeakDefaults;
 
   bool UseBigObj;
 
   bool EmitAddrsigSection = false;
   MCSectionCOFF *AddrsigSection;
   std::vector<const MCSymbol *> AddrsigSyms;
 
+  MCSectionCOFF *CGProfileSection = nullptr;
+
   WinCOFFObjectWriter(std::unique_ptr<MCWinCOFFObjectTargetWriter> MOTW,
                       raw_pwrite_stream &OS);
 
   void reset() override {
     memset(&Header, 0, sizeof(Header));
     Header.Machine = TargetObjectWriter->getMachine();
     Sections.clear();
     Symbols.clear();
void WinCOFFObjectWriter::executePostLayoutBinding(MCAssembler &Asm,
                                                    const MCAsmLayout &Layout) {
   if (EmitAddrsigSection) {
     AddrsigSection = Asm.getContext().getCOFFSection(
         ".llvm_addrsig", COFF::IMAGE_SCN_LNK_REMOVE,
         SectionKind::getMetadata());
     Asm.registerSection(*AddrsigSection);
   }
 
+  if (!Asm.CGProfile.empty()) {
+    CGProfileSection = Asm.getContext().getCOFFSection(
+        ".llvm.call-graph-profile", COFF::IMAGE_SCN_LNK_REMOVE,
+        SectionKind::getMetadata());
+    Asm.registerSection(*CGProfileSection);
+  }
+
   // "Define" each section & symbol. This creates section & symbol
   // entries in the staging area.
   for (const auto &Section : Asm)
     defineSection(static_cast<const MCSectionCOFF &>(Section));
 
   for (const MCSymbol &Symbol : Asm.symbols())
     if (!Symbol.isTemporary())
       DefineSymbol(Symbol, Asm, Layout);
for (const MCSymbol *S : AddrsigSyms) {
       MCSection *TargetSection = &S->getSection();
       assert(SectionMap.find(TargetSection) != SectionMap.end() &&
              "Section must already have been defined in "
              "executePostLayoutBinding!");
       encodeULEB128(SectionMap[TargetSection]->Symbol->getIndex(), OS);
     }
   }
 
+  // Create the contents of the .llvm.call-graph-profile section.
+  if (CGProfileSection) {
+    auto *Frag = new MCDataFragment(CGProfileSection);
+    Frag->setLayoutOrder(0);
+    raw_svector_ostream OS(Frag->getContents());
+    for (const MCAssembler::CGProfileEntry &CGPE : Asm.CGProfile) {
+      uint32_t FromIndex = CGPE.From->getSymbol().getIndex();
+      uint32_t ToIndex = CGPE.To->getSymbol().getIndex();
+      OS.write((const char *)&FromIndex, sizeof(uint32_t));
+      OS.write((const char *)&ToIndex, sizeof(uint32_t));
+      OS.write((const char *)&CGPE.Count, sizeof(uint64_t));
+    }
+  }
+
   assignFileOffsets(Asm, Layout);
 
   // MS LINK expects to be able to use this timestamp to implement their
   // /INCREMENTAL feature.
   if (Asm.isIncrementalLinkerCompatible()) {
     Header.TimeDateStamp = getTime();
   } else {
     // Have deterministic output if /INCREMENTAL isn't needed. Also matches GNU.

llvm/test/MC/AsmParser/directive_cgprofile.s

 # RUN: llvm-mc -triple i386-unknown-unknown %s | FileCheck %s
-
+# RUN: llvm-mc -triple x86_64-pc-win32 %s | FileCheck %s
   .cg_profile a, b, 32
   .cg_profile freq, a, 11
   .cg_profile freq, b, 20
 
 # CHECK: .cg_profile a, b, 32
 # CHECK: .cg_profile freq, a, 11
 # CHECK: .cg_profile freq, b, 20

llvm/test/MC/COFF/cgprofile.s

+# RUN: llvm-mc -filetype=obj -triple x86_64-pc-win32 %s -o %t
+# RUN: llvm-readobj -S --symbols --sd --cg-profile %t | FileCheck %s
+
+  .section .test,"w"
+a:
+
+  .cg_profile a, b, 32
+  .cg_profile freq, a, 11
+  .cg_profile late, late2, 20
+  .cg_profile .L.local, b, 42
+
+  .globl late
+late:
+late2: .word 0
+late3:
+.L.local:
+
+# CHECK:      Name: .llvm.call-graph-profile
+# CHECK-NEXT: VirtualSize:
+# CHECK-NEXT: VirtualAddress:
+# CHECK-NEXT: RawDataSize: 48
+# CHECK-NEXT: PointerToRawData:
+# CHECK-NEXT: PointerToRelocations:
+# CHECK-NEXT: PointerToLineNumbers:
+# CHECK-NEXT: RelocationCount:
+# CHECK-NEXT: LineNumberCount:
+# CHECK-NEXT: Characteristics [ (0x100800)
+# CHECK-NEXT:   IMAGE_SCN_ALIGN_1BYTES (0x100000)
+# CHECK-NEXT:   IMAGE_SCN_LNK_REMOVE (0x800)
+# CHECK-NEXT: ]
+# CHECK-NEXT: SectionData (
+# CHECK-NEXT:   0000: 0A000000 0E000000 20000000 00000000
+# CHECK-NEXT:   0010: 11000000 0A000000 0B000000 00000000
+# CHECK-NEXT:   0020: 0B000000 0C000000 14000000 00000000
+# CHECK-NEXT: )
+
+# CHECK: Symbols [
+# CHECK:      Name: a
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: .test
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: Static
+# CHECK-NEXT: AuxSymbolCount:
+# CHECK:      Name: late
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: .test
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: External
+# CHECK-NEXT: AuxSymbolCount:
+# CHECK:      Name: late2
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: .test
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: Static
+# CHECK-NEXT: AuxSymbolCount:
+# CHECK:      Name: late3
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: .test
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: Static
+# CHECK-NEXT: AuxSymbolCount:
+# CHECK:      Name: b
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: IMAGE_SYM_UNDEFINED
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: WeakExternal
+# CHECK-NEXT: AuxSymbolCount: 1
+# CHECK-NEXT: AuxWeakExternal {
+# CHECK-NEXT:   Linked: .weak.b.default.late
+# CHECK-NEXT:   Search: Alias
+# CHECK-NEXT: }
+# CHECK:      Name: .weak.b.default.late
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: IMAGE_SYM_ABSOLUTE
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: External
+# CHECK-NEXT: AuxSymbolCount: 0
+# CHECK:      Name: freq
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: IMAGE_SYM_UNDEFINED
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: WeakExternal
+# CHECK-NEXT: AuxSymbolCount: 1
+# CHECK-NEXT: AuxWeakExternal {
+# CHECK-NEXT:   Linked: .weak.freq.default.late
+# CHECK-NEXT:   Search: Alias
+# CHECK-NEXT: }
+# CHECK:      Name: .weak.freq.default.late
+# CHECK-NEXT: Value:
+# CHECK-NEXT: Section: IMAGE_SYM_ABSOLUTE
+# CHECK-NEXT: BaseType:
+# CHECK-NEXT: ComplexType:
+# CHECK-NEXT: StorageClass: External
+# CHECK-NEXT: AuxSymbolCount: 0
+
+# CHECK:      CGProfile [
+# CHECK-NEXT:   CGProfileEntry {
+# CHECK-NEXT:     From: a
+# CHECK-NEXT:     To: b
+# CHECK-NEXT:     Weight: 32
+# CHECK-NEXT:   }
+# CHECK-NEXT:   CGProfileEntry {
+# CHECK-NEXT:     From: freq
+# CHECK-NEXT:     To: a
+# CHECK-NEXT:     Weight: 11
+# CHECK-NEXT:   }
+# CHECK-NEXT:   CGProfileEntry {
+# CHECK-NEXT:     From: late
+# CHECK-NEXT:     To: late2
+# CHECK-NEXT:     Weight: 20
+# CHECK-NEXT:   }
+# CHECK-NEXT: ]