Merge branch 'main' into fix-up-for-vop3p-gisel

Author: Shoreshen

.github/copilot-instructions.md

@@ -0,0 +1,4 @@
+When performing a code review, pay close attention to code modifying a function's
+control flow. Could the change result in the corruption of performance profile
+data? Could the change result in invalid debug information, in particular for
+branches and calls?

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -202,6 +202,9 @@ class RewriteInstance {
   /// Map code sections generated by BOLT.
   void mapCodeSections(BOLTLinker::SectionMapper MapSection);
 
+  /// Map code without relocating sections.
+  void mapCodeSectionsInPlace(BOLTLinker::SectionMapper MapSection);
+
   /// Map the rest of allocatable sections.
   void mapAllocatableSections(BOLTLinker::SectionMapper MapSection);
 

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -3856,136 +3856,138 @@ std::vector<BinarySection *> RewriteInstance::getCodeSections() {
 }
 
 void RewriteInstance::mapCodeSections(BOLTLinker::SectionMapper MapSection) {
-  if (BC->HasRelocations) {
-    // Map sections for functions with pre-assigned addresses.
-    for (BinaryFunction *InjectedFunction : BC->getInjectedBinaryFunctions()) {
-      const uint64_t OutputAddress = InjectedFunction->getOutputAddress();
-      if (!OutputAddress)
-        continue;
-
-      ErrorOr<BinarySection &> FunctionSection =
-          InjectedFunction->getCodeSection();
-      assert(FunctionSection && "function should have section");
-      FunctionSection->setOutputAddress(OutputAddress);
-      MapSection(*FunctionSection, OutputAddress);
-      InjectedFunction->setImageAddress(FunctionSection->getAllocAddress());
-      InjectedFunction->setImageSize(FunctionSection->getOutputSize());
-    }
-
-    // Populate the list of sections to be allocated.
-    std::vector<BinarySection *> CodeSections = getCodeSections();
+  if (!BC->HasRelocations) {
+    mapCodeSectionsInPlace(MapSection);
+    return;
+  }
 
-    // Remove sections that were pre-allocated (patch sections).
-    llvm::erase_if(CodeSections, [](BinarySection *Section) {
-      return Section->getOutputAddress();
-    });
-    LLVM_DEBUG(dbgs() << "Code sections in the order of output:\n";
-      for (const BinarySection *Section : CodeSections)
-        dbgs() << Section->getName() << '\n';
-    );
+  // Map sections for functions with pre-assigned addresses.
+  for (BinaryFunction *InjectedFunction : BC->getInjectedBinaryFunctions()) {
+    const uint64_t OutputAddress = InjectedFunction->getOutputAddress();
+    if (!OutputAddress)
+      continue;
 
-    uint64_t PaddingSize = 0; // size of padding required at the end
+    ErrorOr<BinarySection &> FunctionSection =
+        InjectedFunction->getCodeSection();
+    assert(FunctionSection && "function should have section");
+    FunctionSection->setOutputAddress(OutputAddress);
+    MapSection(*FunctionSection, OutputAddress);
+    InjectedFunction->setImageAddress(FunctionSection->getAllocAddress());
+    InjectedFunction->setImageSize(FunctionSection->getOutputSize());
+  }
 
-    // Allocate sections starting at a given Address.
-    auto allocateAt = [&](uint64_t Address) {
-      const char *LastNonColdSectionName = BC->HasWarmSection
-                                               ? BC->getWarmCodeSectionName()
-                                               : BC->getMainCodeSectionName();
-      for (BinarySection *Section : CodeSections) {
-        Address = alignTo(Address, Section->getAlignment());
-        Section->setOutputAddress(Address);
-        Address += Section->getOutputSize();
-
-        // Hugify: Additional huge page from right side due to
-        // weird ASLR mapping addresses (4KB aligned)
-        if (opts::Hugify && !BC->HasFixedLoadAddress &&
-            Section->getName() == LastNonColdSectionName)
-          Address = alignTo(Address, Section->getAlignment());
-      }
+  // Populate the list of sections to be allocated.
+  std::vector<BinarySection *> CodeSections = getCodeSections();
 
-      // Make sure we allocate enough space for huge pages.
-      ErrorOr<BinarySection &> TextSection =
-          BC->getUniqueSectionByName(LastNonColdSectionName);
-      if (opts::HotText && TextSection && TextSection->hasValidSectionID()) {
-        uint64_t HotTextEnd =
-            TextSection->getOutputAddress() + TextSection->getOutputSize();
-        HotTextEnd = alignTo(HotTextEnd, BC->PageAlign);
-        if (HotTextEnd > Address) {
-          PaddingSize = HotTextEnd - Address;
-          Address = HotTextEnd;
-        }
-      }
-      return Address;
-    };
+  // Remove sections that were pre-allocated (patch sections).
+  llvm::erase_if(CodeSections, [](BinarySection *Section) {
+    return Section->getOutputAddress();
+  });
+  LLVM_DEBUG(dbgs() << "Code sections in the order of output:\n";
+             for (const BinarySection *Section : CodeSections) dbgs()
+             << Section->getName() << '\n';);
 
-    // Try to allocate sections before the \p Address and return an address for
-    // the allocation of the first section, or 0 if [0, Address) range is not
-    // big enough to fit all sections.
-    auto allocateBefore = [&](uint64_t Address) -> uint64_t {
-      for (BinarySection *Section : llvm::reverse(CodeSections)) {
-        if (Section->getOutputSize() > Address)
-          return 0;
-        Address -= Section->getOutputSize();
-        Address = alignDown(Address, Section->getAlignment());
-        Section->setOutputAddress(Address);
-      }
-      return Address;
-    };
+  uint64_t PaddingSize = 0; // size of padding required at the end
 
-    // Check if we can fit code in the original .text
-    bool AllocationDone = false;
-    if (opts::UseOldText) {
-      uint64_t StartAddress;
-      uint64_t EndAddress;
-      if (opts::HotFunctionsAtEnd) {
-        EndAddress = BC->OldTextSectionAddress + BC->OldTextSectionSize;
-        StartAddress = allocateBefore(EndAddress);
-      } else {
-        StartAddress = BC->OldTextSectionAddress;
-        EndAddress = allocateAt(BC->OldTextSectionAddress);
-      }
+  // Allocate sections starting at a given Address.
+  auto allocateAt = [&](uint64_t Address) {
+    const char *LastNonColdSectionName = BC->HasWarmSection
+                                             ? BC->getWarmCodeSectionName()
+                                             : BC->getMainCodeSectionName();
+    for (BinarySection *Section : CodeSections) {
+      Address = alignTo(Address, Section->getAlignment());
+      Section->setOutputAddress(Address);
+      Address += Section->getOutputSize();
+
+      // Hugify: Additional huge page from right side due to
+      // weird ASLR mapping addresses (4KB aligned)
+      if (opts::Hugify && !BC->HasFixedLoadAddress &&
+          Section->getName() == LastNonColdSectionName)
+        Address = alignTo(Address, Section->getAlignment());
+    }
 
-      const uint64_t CodeSize = EndAddress - StartAddress;
-      if (CodeSize <= BC->OldTextSectionSize) {
-        BC->outs() << "BOLT-INFO: using original .text for new code with 0x"
-                   << Twine::utohexstr(opts::AlignText) << " alignment";
-        if (StartAddress != BC->OldTextSectionAddress)
-          BC->outs() << " at 0x" << Twine::utohexstr(StartAddress);
-        BC->outs() << '\n';
-        AllocationDone = true;
-      } else {
-        BC->errs()
-            << "BOLT-WARNING: original .text too small to fit the new code"
-            << " using 0x" << Twine::utohexstr(opts::AlignText)
-            << " alignment. " << CodeSize << " bytes needed, have "
-            << BC->OldTextSectionSize << " bytes available.\n";
-        opts::UseOldText = false;
+    // Make sure we allocate enough space for huge pages.
+    ErrorOr<BinarySection &> TextSection =
+        BC->getUniqueSectionByName(LastNonColdSectionName);
+    if (opts::HotText && TextSection && TextSection->hasValidSectionID()) {
+      uint64_t HotTextEnd =
+          TextSection->getOutputAddress() + TextSection->getOutputSize();
+      HotTextEnd = alignTo(HotTextEnd, BC->PageAlign);
+      if (HotTextEnd > Address) {
+        PaddingSize = HotTextEnd - Address;
+        Address = HotTextEnd;
       }
     }
+    return Address;
+  };
 
-    if (!AllocationDone)
-      NextAvailableAddress = allocateAt(NextAvailableAddress);
+  // Try to allocate sections before the \p Address and return an address for
+  // the allocation of the first section, or 0 if [0, Address) range is not
+  // big enough to fit all sections.
+  auto allocateBefore = [&](uint64_t Address) -> uint64_t {
+    for (BinarySection *Section : llvm::reverse(CodeSections)) {
+      if (Section->getOutputSize() > Address)
+        return 0;
+      Address -= Section->getOutputSize();
+      Address = alignDown(Address, Section->getAlignment());
+      Section->setOutputAddress(Address);
+    }
+    return Address;
+  };
 
-    // Do the mapping for ORC layer based on the allocation.
-    for (BinarySection *Section : CodeSections) {
-      LLVM_DEBUG(
-          dbgs() << "BOLT: mapping " << Section->getName() << " at 0x"
-                 << Twine::utohexstr(Section->getAllocAddress()) << " to 0x"
-                 << Twine::utohexstr(Section->getOutputAddress()) << '\n');
-      MapSection(*Section, Section->getOutputAddress());
-      Section->setOutputFileOffset(
-          getFileOffsetForAddress(Section->getOutputAddress()));
+  // Check if we can fit code in the original .text
+  bool AllocationDone = false;
+  if (opts::UseOldText) {
+    uint64_t StartAddress;
+    uint64_t EndAddress;
+    if (opts::HotFunctionsAtEnd) {
+      EndAddress = BC->OldTextSectionAddress + BC->OldTextSectionSize;
+      StartAddress = allocateBefore(EndAddress);
+    } else {
+      StartAddress = BC->OldTextSectionAddress;
+      EndAddress = allocateAt(BC->OldTextSectionAddress);
+    }
+
+    const uint64_t CodeSize = EndAddress - StartAddress;
+    if (CodeSize <= BC->OldTextSectionSize) {
+      BC->outs() << "BOLT-INFO: using original .text for new code with 0x"
+                 << Twine::utohexstr(opts::AlignText) << " alignment";
+      if (StartAddress != BC->OldTextSectionAddress)
+        BC->outs() << " at 0x" << Twine::utohexstr(StartAddress);
+      BC->outs() << '\n';
+      AllocationDone = true;
+    } else {
+      BC->errs() << "BOLT-WARNING: original .text too small to fit the new code"
+                 << " using 0x" << Twine::utohexstr(opts::AlignText)
+                 << " alignment. " << CodeSize << " bytes needed, have "
+                 << BC->OldTextSectionSize << " bytes available.\n";
+      opts::UseOldText = false;
     }
+  }
 
-    // Check if we need to insert a padding section for hot text.
-    if (PaddingSize && !opts::UseOldText)
-      BC->outs() << "BOLT-INFO: padding code to 0x"
-                 << Twine::utohexstr(NextAvailableAddress)
-                 << " to accommodate hot text\n";
+  if (!AllocationDone)
+    NextAvailableAddress = allocateAt(NextAvailableAddress);
 
-    return;
+  // Do the mapping for ORC layer based on the allocation.
+  for (BinarySection *Section : CodeSections) {
+    LLVM_DEBUG(dbgs() << "BOLT: mapping " << Section->getName() << " at 0x"
+                      << Twine::utohexstr(Section->getAllocAddress())
+                      << " to 0x"
+                      << Twine::utohexstr(Section->getOutputAddress()) << '\n');
+    MapSection(*Section, Section->getOutputAddress());
+    Section->setOutputFileOffset(
+        getFileOffsetForAddress(Section->getOutputAddress()));
   }
 
+  // Check if we need to insert a padding section for hot text.
+  if (PaddingSize && !opts::UseOldText)
+    BC->outs() << "BOLT-INFO: padding code to 0x"
+               << Twine::utohexstr(NextAvailableAddress)
+               << " to accommodate hot text\n";
+}
+
+void RewriteInstance::mapCodeSectionsInPlace(
+    BOLTLinker::SectionMapper MapSection) {
   // Processing in non-relocation mode.
   uint64_t NewTextSectionStartAddress = NextAvailableAddress;
 

clang-tools-extra/clang-doc/BitcodeReader.cpp

@@ -94,6 +94,7 @@ static llvm::Error decodeRecord(const Record &R, InfoType &Field,
   case InfoType::IT_typedef:
   case InfoType::IT_concept:
   case InfoType::IT_variable:
+  case InfoType::IT_friend:
     Field = IT;
     return llvm::Error::success();
   }
@@ -111,6 +112,7 @@ static llvm::Error decodeRecord(const Record &R, FieldId &Field,
   case FieldId::F_child_namespace:
   case FieldId::F_child_record:
   case FieldId::F_concept:
+  case FieldId::F_friend:
   case FieldId::F_default:
     Field = F;
     return llvm::Error::success();
@@ -450,6 +452,15 @@ static llvm::Error parseRecord(const Record &R, unsigned ID,
   }
 }
 
+static llvm::Error parseRecord(const Record &R, unsigned ID, StringRef Blob,
+                               FriendInfo *F) {
+  if (ID == FRIEND_IS_CLASS) {
+    return decodeRecord(R, F->IsClass, Blob);
+  }
+  return llvm::createStringError(llvm::inconvertibleErrorCode(),
+                                 "invalid field for Friend");
+}
+
 template <typename T> static llvm::Expected<CommentInfo *> getCommentInfo(T I) {
   return llvm::createStringError(llvm::inconvertibleErrorCode(),
                                  "invalid type cannot contain CommentInfo");
@@ -525,6 +536,18 @@ template <> llvm::Error addTypeInfo(FunctionInfo *I, FieldTypeInfo &&T) {
   return llvm::Error::success();
 }
 
+template <> llvm::Error addTypeInfo(FriendInfo *I, FieldTypeInfo &&T) {
+  if (!I->Params)
+    I->Params.emplace();
+  I->Params->emplace_back(std::move(T));
+  return llvm::Error::success();
+}
+
+template <> llvm::Error addTypeInfo(FriendInfo *I, TypeInfo &&T) {
+  I->ReturnType.emplace(std::move(T));
+  return llvm::Error::success();
+}
+
 template <> llvm::Error addTypeInfo(EnumInfo *I, TypeInfo &&T) {
   I->BaseType = std::move(T);
   return llvm::Error::success();
@@ -667,6 +690,16 @@ llvm::Error addReference(ConstraintInfo *I, Reference &&R, FieldId F) {
       "ConstraintInfo cannot contain this Reference");
 }
 
+template <>
+llvm::Error addReference(FriendInfo *Friend, Reference &&R, FieldId F) {
+  if (F == FieldId::F_friend) {
+    Friend->Ref = std::move(R);
+    return llvm::Error::success();
+  }
+  return llvm::createStringError(llvm::inconvertibleErrorCode(),
+                                 "Friend cannot contain this Reference");
+}
+
 template <typename T, typename ChildInfoType>
 static void addChild(T I, ChildInfoType &&R) {
   llvm::errs() << "invalid child type for info";
@@ -700,6 +733,9 @@ template <> void addChild(RecordInfo *I, EnumInfo &&R) {
 template <> void addChild(RecordInfo *I, TypedefInfo &&R) {
   I->Children.Typedefs.emplace_back(std::move(R));
 }
+template <> void addChild(RecordInfo *I, FriendInfo &&R) {
+  I->Friends.emplace_back(std::move(R));
+}
 
 // Other types of children:
 template <> void addChild(EnumInfo *I, EnumValueInfo &&R) {
@@ -741,6 +777,9 @@ template <> void addTemplate(FunctionInfo *I, TemplateInfo &&P) {
 template <> void addTemplate(ConceptInfo *I, TemplateInfo &&P) {
   I->Template = std::move(P);
 }
+template <> void addTemplate(FriendInfo *I, TemplateInfo &&P) {
+  I->Template.emplace(std::move(P));
+}
 
 // Template specializations go only into template records.
 template <typename T>
@@ -921,6 +960,10 @@ llvm::Error ClangDocBitcodeReader::readSubBlock(unsigned ID, T I) {
   case BI_VAR_BLOCK_ID: {
     return handleSubBlock<VarInfo>(ID, I, CreateAddFunc(addChild<T, VarInfo>));
   }
+  case BI_FRIEND_BLOCK_ID: {
+    return handleSubBlock<FriendInfo>(ID, I,
+                                      CreateAddFunc(addChild<T, FriendInfo>));
+  }
   default:
     return llvm::createStringError(llvm::inconvertibleErrorCode(),
                                    "invalid subblock type");
@@ -1032,6 +1075,8 @@ ClangDocBitcodeReader::readBlockToInfo(unsigned ID) {
     return createInfo<FunctionInfo>(ID);
   case BI_VAR_BLOCK_ID:
     return createInfo<VarInfo>(ID);
+  case BI_FRIEND_BLOCK_ID:
+    return createInfo<FriendInfo>(ID);
   default:
     return llvm::createStringError(llvm::inconvertibleErrorCode(),
                                    "cannot create info");
@@ -1072,6 +1117,7 @@ ClangDocBitcodeReader::readBitcode() {
     case BI_TYPEDEF_BLOCK_ID:
     case BI_CONCEPT_BLOCK_ID:
     case BI_VAR_BLOCK_ID:
+    case BI_FRIEND_BLOCK_ID:
     case BI_FUNCTION_BLOCK_ID: {
       auto InfoOrErr = readBlockToInfo(ID);
       if (!InfoOrErr)