run 'git merge main' and resolve conflict

Author: mingmingl-llvm

.ci/generate-buildkite-pipeline-premerge

@@ -108,7 +108,7 @@ function add-dependencies() {
     compiler-rt|libc|openmp)
       echo clang lld
     ;;
-    flang|lldb)
+    flang|lldb|libclc)
       for p in llvm clang; do
         echo $p
       done

.github/CODEOWNERS

@@ -113,7 +113,15 @@ clang/test/AST/Interp/ @tbaederr
 
 # MLIR NVVM Dialect in MLIR
 /mlir/**/LLVMIR/**/BasicPtxBuilderInterface* @grypp
-/mlir/**/NVVM*/ @grypp
+/mlir/**/NVVM* @grypp
+
+# MLIR Python Bindings
+/mlir/test/python/ @ftynse @makslevental @stellaraccident
+/mlir/python/ @ftynse @makslevental @stellaraccident
+
+# MLIR Mem2Reg/SROA
+/mlir/**/Transforms/Mem2Reg.* @moxinilian
+/mlir/**/Transforms/SROA.* @moxinilian
 
 # BOLT
 /bolt/ @aaupov @maksfb @rafaelauler @ayermolo @dcci

.github/new-prs-labeler.yml

@@ -1,3 +1,9 @@
+ClangIR:
+  - clang/include/clang/CIR/**/*
+  - clang/lib/CIR/**/*
+  - clang/tools/cir-*/**/*
+  - clang/test/CIR/**/*
+
 clang:dataflow:
   - clang/include/clang/Analysis/FlowSensitive/**/*
   - clang/lib/Analysis/FlowSensitive/**/*
@@ -461,6 +467,7 @@ backend:m68k:
 
 libc++:
   - libcxx/**
+  - .github/workflows/libcxx-*
 
 libc++abi:
   - libcxxabi/**
@@ -938,3 +945,6 @@ openmp:libomptarget:
 
 bazel:
   - utils/bazel/**
+
+offload:
+  - offload/**

.github/workflows/libcxx-build-and-test.yaml

@@ -61,20 +61,17 @@ jobs:
         ]
         cc: [  'clang-19' ]
         cxx: [ 'clang++-19' ]
-        clang_tidy: [ 'ON' ]
         include:
           - config: 'generic-gcc'
             cc: 'gcc-13'
             cxx: 'g++-13'
-            clang_tidy: 'OFF'
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}.${{ matrix.cxx }}
         run: libcxx/utils/ci/run-buildbot ${{ matrix.config }}
         env:
           CC: ${{ matrix.cc }}
           CXX: ${{ matrix.cxx }}
-          ENABLE_CLANG_TIDY: ${{ matrix.clang_tidy }}
       - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()
         with:
@@ -102,28 +99,23 @@ jobs:
         ]
         cc: [ 'clang-19' ]
         cxx: [ 'clang++-19' ]
-        clang_tidy: [ 'ON' ]
         include:
           - config: 'generic-gcc-cxx11'
             cc: 'gcc-13'
             cxx: 'g++-13'
-            clang_tidy: 'OFF'
           - config: 'generic-cxx23'
             cc: 'clang-17'
             cxx: 'clang++-17'
-            clang_tidy: 'OFF'
           - config: 'generic-cxx26'
             cc: 'clang-18'
             cxx: 'clang++-18'
-            clang_tidy: 'ON'
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}
         run: libcxx/utils/ci/run-buildbot ${{ matrix.config }}
         env:
           CC: ${{ matrix.cc }}
           CXX: ${{ matrix.cxx }}
-          ENABLE_CLANG_TIDY: ${{ matrix.clang_tidy }}
       - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()  # Upload artifacts even if the build or test suite fails
         with:
@@ -188,7 +180,6 @@ jobs:
         env:
           CC: clang-19
           CXX: clang++-19
-          ENABLE_CLANG_TIDY: "OFF"
       - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()
         with:

.github/workflows/pr-code-format.yml

@@ -1,4 +1,8 @@
 name: "Check code formatting"
+
+permissions:
+  contents: read
+
 on:
   pull_request:
     branches:

bolt/docs/BAT.md

@@ -81,9 +81,10 @@ Hot indices are delta encoded, implicitly starting at zero.
 | `FuncHash` | 8b | Function hash for input function | Hot |
 | `NumBlocks` | ULEB128 | Number of basic blocks in the original function | Hot |
 | `NumSecEntryPoints` | ULEB128 | Number of secondary entry points in the original function | Hot |
+| `ColdInputSkew` | ULEB128 | Skew to apply to all input offsets | Cold |
 | `NumEntries` | ULEB128 | Number of address translation entries for a function | Both |
-| `EqualElems` | ULEB128 | Number of equal offsets in the beginning of a function | Hot |
-| `BranchEntries` | Bitmask, `alignTo(EqualElems, 8)` bits | If `EqualElems` is non-zero, bitmask denoting entries with `BRANCHENTRY` bit | Hot |
+| `EqualElems` | ULEB128 | Number of equal offsets in the beginning of a function | Both |
+| `BranchEntries` | Bitmask, `alignTo(EqualElems, 8)` bits | If `EqualElems` is non-zero, bitmask denoting entries with `BRANCHENTRY` bit | Both |
 
 Function header is followed by *Address Translation Table* with `NumEntries`
 total entries, and *Secondary Entry Points* table with `NumSecEntryPoints`
@@ -99,8 +100,8 @@ entry is encoded. Input offsets implicitly start at zero.
 | `BBHash` | Optional, 8b | Basic block hash in input binary | BB |
 | `BBIdx`  | Optional, Delta, ULEB128 | Basic block index in input binary | BB |
 
-For hot fragments, the table omits the first `EqualElems` input offsets
-where the input offset equals output offset.
+The table omits the first `EqualElems` input offsets where the input offset
+equals output offset.
 
 `BRANCHENTRY` bit denotes whether a given offset pair is a control flow source
 (branch or call instruction). If not set, it signifies a control flow target

bolt/include/bolt/Core/BinaryData.h

@@ -107,7 +107,6 @@ class BinaryData {
   std::vector<MCSymbol *> &getSymbols() { return Symbols; }
 
   bool hasName(StringRef Name) const;
-  bool hasNameRegex(StringRef Name) const;
   bool nameStartsWith(StringRef Prefix) const;
 
   bool hasSymbol(const MCSymbol *Symbol) const {

bolt/include/bolt/Core/BinaryFunction.h

@@ -1402,7 +1402,8 @@ class BinaryFunction {
 
   /// Return true if the function has CFI instructions
   bool hasCFI() const {
-    return !FrameInstructions.empty() || !CIEFrameInstructions.empty();
+    return !FrameInstructions.empty() || !CIEFrameInstructions.empty() ||
+           IsInjected;
   }
 
   /// Return unique number associated with the function.

bolt/include/bolt/Passes/BinaryPasses.h

@@ -400,8 +400,7 @@ class PrintProfileStats : public BinaryFunctionPass {
 /// dyno stats categories.
 class PrintProgramStats : public BinaryFunctionPass {
 public:
-  explicit PrintProgramStats(const cl::opt<bool> &PrintPass)
-      : BinaryFunctionPass(PrintPass) {}
+  explicit PrintProgramStats() : BinaryFunctionPass(false) {}
 
   const char *getName() const override { return "print-stats"; }
   bool shouldPrint(const BinaryFunction &) const override { return false; }

bolt/include/bolt/Profile/BoltAddressTranslation.h

@@ -119,11 +119,6 @@ class BoltAddressTranslation {
   /// True if a given \p Address is a function with translation table entry.
   bool isBATFunction(uint64_t Address) const { return Maps.count(Address); }
 
-  /// Returns branch offsets grouped by containing basic block in a given
-  /// function.
-  std::unordered_map<uint32_t, std::vector<uint32_t>>
-  getBFBranches(uint64_t FuncOutputAddress) const;
-
   /// For a given \p Symbol in the output binary and known \p InputOffset
   /// return a corresponding pair of parent BinaryFunction and secondary entry
   /// point in it.
@@ -154,9 +149,9 @@ class BoltAddressTranslation {
   /// entries in function address translation map.
   APInt calculateBranchEntriesBitMask(MapTy &Map, size_t EqualElems);
 
-  /// Calculate the number of equal offsets (output = input) in the beginning
-  /// of the function.
-  size_t getNumEqualOffsets(const MapTy &Map) const;
+  /// Calculate the number of equal offsets (output = input - skew) in the
+  /// beginning of the function.
+  size_t getNumEqualOffsets(const MapTy &Map, uint32_t Skew) const;
 
   std::map<uint64_t, MapTy> Maps;
 
@@ -193,7 +188,7 @@ class BoltAddressTranslation {
       EntryTy(unsigned Index, size_t Hash) : Index(Index), Hash(Hash) {}
     };
 
-    std::unordered_map<uint32_t, EntryTy> Map;
+    std::map<uint32_t, EntryTy> Map;
     const EntryTy &getEntry(uint32_t BBInputOffset) const {
       auto It = Map.find(BBInputOffset);
       assert(It != Map.end());
@@ -218,6 +213,10 @@ class BoltAddressTranslation {
     }
 
     size_t getNumBasicBlocks() const { return Map.size(); }
+
+    auto begin() const { return Map.begin(); }
+    auto end() const { return Map.end(); }
+    auto upper_bound(uint32_t Offset) const { return Map.upper_bound(Offset); }
   };
 
   /// Map function output address to its hash and basic blocks hash map.

bolt/include/bolt/Profile/DataAggregator.h

@@ -225,6 +225,10 @@ class DataAggregator : public DataReader {
   /// Aggregation statistics
   uint64_t NumInvalidTraces{0};
   uint64_t NumLongRangeTraces{0};
+  /// Specifies how many samples were recorded in cold areas if we are dealing
+  /// with profiling data collected in a bolted binary. For LBRs, incremented
+  /// for the source of the branch to avoid counting cold activity twice (one
+  /// for source and another for destination).
   uint64_t NumColdSamples{0};
 
   /// Looks into system PATH for Linux Perf and set up the aggregator to use it
@@ -245,14 +249,12 @@ class DataAggregator : public DataReader {
   /// disassembled BinaryFunctions
   BinaryFunction *getBinaryFunctionContainingAddress(uint64_t Address) const;
 
+  /// Perform BAT translation for a given \p Func and return the parent
+  /// BinaryFunction or nullptr.
+  BinaryFunction *getBATParentFunction(const BinaryFunction &Func) const;
+
   /// Retrieve the location name to be used for samples recorded in \p Func.
-  /// If doing BAT translation, link cold parts to the hot part  names (used by
-  /// the original binary).  \p Count specifies how many samples were recorded
-  /// at that location, so we can tally total activity in cold areas if we are
-  /// dealing with profiling data collected in a bolted binary. For LBRs,
-  /// \p Count should only be used for the source of the branch to avoid
-  /// counting cold activity twice (one for source and another for destination).
-  StringRef getLocationName(BinaryFunction &Func, uint64_t Count);
+  StringRef getLocationName(const BinaryFunction &Func) const;
 
   /// Semantic actions - parser hooks to interpret parsed perf samples
   /// Register a sample (non-LBR mode), i.e. a new hit at \p Address
@@ -467,9 +469,6 @@ class DataAggregator : public DataReader {
   std::error_code writeBATYAML(BinaryContext &BC,
                                StringRef OutputFilename) const;
 
-  /// Fixup profile collected on BOLTed binary, namely handle split functions.
-  void fixupBATProfile(BinaryContext &BC);
-
   /// Filter out binaries based on PID
   void filterBinaryMMapInfo();
 

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -368,13 +368,6 @@ class RewriteInstance {
   /// rewritten binary.
   void patchBuildID();
 
-  /// Return file offset corresponding to a given virtual address.
-  uint64_t getFileOffsetFor(uint64_t Address) {
-    assert(Address >= NewTextSegmentAddress &&
-           "address in not in the new text segment");
-    return Address - NewTextSegmentAddress + NewTextSegmentOffset;
-  }
-
   /// Return file offset corresponding to a virtual \p Address.
   /// Return 0 if the address has no mapping in the file, including being
   /// part of .bss section.
@@ -398,9 +391,6 @@ class RewriteInstance {
   /// Return true if the section holds debug information.
   static bool isDebugSection(StringRef SectionName);
 
-  /// Return true if the section holds linux kernel symbol information.
-  static bool isKSymtabSection(StringRef SectionName);
-
   /// Adds Debug section to overwrite.
   static void addToDebugSectionsToOverwrite(const char *Section) {
     DebugSectionsToOverwrite.emplace_back(Section);
@@ -436,6 +426,9 @@ class RewriteInstance {
   static StringRef getEHFrameSectionName() { return ".eh_frame"; }
   static StringRef getRelaDynSectionName() { return ".rela.dyn"; }
 
+  /// FILE symbol name used for local fragments of global functions.
+  static StringRef getBOLTFileSymbolName() { return "bolt-pseudo.o"; }
+
   /// An instance of the input binary we are processing, externally owned.
   llvm::object::ELFObjectFileBase *InputFile;
 

bolt/lib/Core/BinaryContext.cpp

@@ -555,6 +555,9 @@ bool BinaryContext::analyzeJumpTable(const uint64_t Address,
                                      const uint64_t NextJTAddress,
                                      JumpTable::AddressesType *EntriesAsAddress,
                                      bool *HasEntryInFragment) const {
+  // Target address of __builtin_unreachable.
+  const uint64_t UnreachableAddress = BF.getAddress() + BF.getSize();
+
   // Is one of the targets __builtin_unreachable?
   bool HasUnreachable = false;
 
@@ -564,9 +567,15 @@ bool BinaryContext::analyzeJumpTable(const uint64_t Address,
   // Number of targets other than __builtin_unreachable.
   uint64_t NumRealEntries = 0;
 
-  auto addEntryAddress = [&](uint64_t EntryAddress) {
-    if (EntriesAsAddress)
-      EntriesAsAddress->emplace_back(EntryAddress);
+  // Size of the jump table without trailing __builtin_unreachable entries.
+  size_t TrimmedSize = 0;
+
+  auto addEntryAddress = [&](uint64_t EntryAddress, bool Unreachable = false) {
+    if (!EntriesAsAddress)
+      return;
+    EntriesAsAddress->emplace_back(EntryAddress);
+    if (!Unreachable)
+      TrimmedSize = EntriesAsAddress->size();
   };
 
   ErrorOr<const BinarySection &> Section = getSectionForAddress(Address);
@@ -618,8 +627,8 @@ bool BinaryContext::analyzeJumpTable(const uint64_t Address,
             : *getPointerAtAddress(EntryAddress);
 
     // __builtin_unreachable() case.
-    if (Value == BF.getAddress() + BF.getSize()) {
-      addEntryAddress(Value);
+    if (Value == UnreachableAddress) {
+      addEntryAddress(Value, /*Unreachable*/ true);
       HasUnreachable = true;
       LLVM_DEBUG(dbgs() << formatv("OK: {0:x} __builtin_unreachable\n", Value));
       continue;
@@ -673,6 +682,13 @@ bool BinaryContext::analyzeJumpTable(const uint64_t Address,
     addEntryAddress(Value);
   }
 
+  // Trim direct/normal jump table to exclude trailing unreachable entries that
+  // can collide with a function address.
+  if (Type == JumpTable::JTT_NORMAL && EntriesAsAddress &&
+      TrimmedSize != EntriesAsAddress->size() &&
+      getBinaryFunctionAtAddress(UnreachableAddress))
+    EntriesAsAddress->resize(TrimmedSize);
+
   // It's a jump table if the number of real entries is more than 1, or there's
   // one real entry and one or more special targets. If there are only multiple
   // special targets, then it's not a jump table.
@@ -1864,7 +1880,7 @@ MarkerSymType BinaryContext::getMarkerType(const SymbolRef &Symbol) const {
   // For aarch64 and riscv, the ABI defines mapping symbols so we identify data
   // in the code section (see IHI0056B). $x identifies a symbol starting code or
   // the end of a data chunk inside code, $d identifies start of data.
-  if ((!isAArch64() && !isRISCV()) || ELFSymbolRef(Symbol).getSize())
+  if (isX86() || ELFSymbolRef(Symbol).getSize())
     return MarkerSymType::NONE;
 
   Expected<StringRef> NameOrError = Symbol.getName();

bolt/lib/Core/BinaryData.cpp

@@ -55,14 +55,6 @@ bool BinaryData::hasName(StringRef Name) const {
   return false;
 }
 
-bool BinaryData::hasNameRegex(StringRef NameRegex) const {
-  Regex MatchName(NameRegex);
-  for (const MCSymbol *Symbol : Symbols)
-    if (MatchName.match(Symbol->getName()))
-      return true;
-  return false;
-}
-
 bool BinaryData::nameStartsWith(StringRef Prefix) const {
   for (const MCSymbol *Symbol : Symbols)
     if (Symbol->getName().starts_with(Prefix))

bolt/lib/Core/BinaryEmitter.cpp

@@ -512,7 +512,7 @@ void BinaryEmitter::emitFunctionBody(BinaryFunction &BF, FunctionFragment &FF,
 
       // Emit sized NOPs via MCAsmBackend::writeNopData() interface on x86.
       // This is a workaround for invalid NOPs handling by asm/disasm layer.
-      if (BC.MIB->isNoop(Instr) && BC.isX86()) {
+      if (BC.isX86() && BC.MIB->isNoop(Instr)) {
         if (std::optional<uint32_t> Size = BC.MIB->getSize(Instr)) {
           SmallString<15> Code;
           raw_svector_ostream VecOS(Code);