Merge commit '82383d5f3fa8' into bump_to_82383d5f3fa8

.ci/generate-buildkite-pipeline-premerge

@@ -91,7 +91,7 @@ function add-dependencies() {
     echo "${project}"
     case ${project} in
     bolt)
-      for p in lld llvm; do
+      for p in clang lld llvm; do
         echo $p
       done
     ;;

.ci/monolithic-linux.sh

@@ -48,7 +48,6 @@ cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_LIT_ARGS="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --timeout=1200 --time-tests" \
       -D LLVM_ENABLE_LLD=ON \
       -D CMAKE_CXX_FLAGS=-gmlt \
-      -D BOLT_CLANG_EXE=/usr/bin/clang \
       -D LLVM_CCACHE_BUILD=ON \
       -D MLIR_ENABLE_BINDINGS_PYTHON=ON
 

.github/CODEOWNERS

@@ -35,6 +35,10 @@
 clang/lib/AST/Interp/ @tbaederr
 clang/test/AST/Interp/ @tbaederr
 
+/clang/include/clang/CIR @lanza @bcardosolopes
+/clang/lib/CIR @lanza @bcardosolopes
+/clang/tools/cir-* @lanza @bcardosolopes
+
 /lldb/ @JDevlieghere
 
 # MLIR Interfaces.
@@ -119,6 +123,10 @@ clang/test/AST/Interp/ @tbaederr
 /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 +1,6 @@
+BOLT:
+  - bolt/**/*
+
 ClangIR:
   - clang/include/clang/CIR/**/*
   - clang/lib/CIR/**/*
@@ -467,6 +470,7 @@ backend:m68k:
 
 libc++:
   - libcxx/**
+  - .github/workflows/libcxx-*
 
 libc++abi:
   - libcxxabi/**

.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:

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/DataAggregator.h

@@ -198,14 +198,8 @@ class DataAggregator : public DataReader {
   /// A trace is region of code executed between two LBR entries supplied in
   /// execution order.
   ///
-  /// Return true if the trace is valid, false otherwise.
-  bool
-  recordTrace(BinaryFunction &BF, const LBREntry &First, const LBREntry &Second,
-              uint64_t Count,
-              SmallVector<std::pair<uint64_t, uint64_t>, 16> &Branches) const;
-
   /// Return a vector of offsets corresponding to a trace in a function
-  /// (see recordTrace() above).
+  /// if the trace is valid, std::nullopt otherwise.
   std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
   getFallthroughsInTrace(BinaryFunction &BF, const LBREntry &First,
                          const LBREntry &Second, uint64_t Count = 1) const;

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -422,10 +422,18 @@ class RewriteInstance {
   /// Section name used for extra BOLT code in addition to .text.
   static StringRef getBOLTTextSectionName() { return ".bolt.text"; }
 
+  /// Symbol markers for BOLT reserved area.
+  static StringRef getBOLTReservedStart() { return "__bolt_reserved_start"; }
+  static StringRef getBOLTReservedEnd() { return "__bolt_reserved_end"; }
+
   /// Common section names.
   static StringRef getEHFrameSectionName() { return ".eh_frame"; }
+  static StringRef getEHFrameHdrSectionName() { return ".eh_frame_hdr"; }
   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;
 
@@ -490,6 +498,9 @@ class RewriteInstance {
   /// Store all non-zero symbols in this map for a quick address lookup.
   std::map<uint64_t, llvm::object::SymbolRef> FileSymRefs;
 
+  /// FILE symbols used for disambiguating split function parents.
+  std::vector<ELFSymbolRef> FileSymbols;
+
   std::unique_ptr<DWARFRewriter> DebugInfoRewriter;
 
   std::unique_ptr<BoltAddressTranslation> BAT;

bolt/include/bolt/Utils/NameResolver.h

@@ -28,10 +28,23 @@ class NameResolver {
   static constexpr char Sep = '/';
 
 public:
-  /// Return unique version of the \p Name in the form "Name<Sep><Number>".
+  /// Return the number of uniquified versions of a given \p Name.
+  uint64_t getUniquifiedNameCount(StringRef Name) const {
+    if (Counters.contains(Name))
+      return Counters.at(Name);
+    return 0;
+  }
+
+  /// Return unique version of the \p Name in the form "Name<Sep><ID>".
+  std::string getUniqueName(StringRef Name, const uint64_t ID) const {
+    return (Name + Twine(Sep) + Twine(ID)).str();
+  }
+
+  /// Register new version of \p Name and return unique version in the form
+  /// "Name<Sep><Number>".
   std::string uniquify(StringRef Name) {
     const uint64_t ID = ++Counters[Name];
-    return (Name + Twine(Sep) + Twine(ID)).str();
+    return getUniqueName(Name, ID);
   }
 
   /// For uniquified \p Name, return the original form (that may no longer be

bolt/lib/Profile/DataAggregator.cpp

@@ -14,6 +14,7 @@
 #include "bolt/Profile/DataAggregator.h"
 #include "bolt/Core/BinaryContext.h"
 #include "bolt/Core/BinaryFunction.h"
+#include "bolt/Passes/BinaryPasses.h"
 #include "bolt/Profile/BoltAddressTranslation.h"
 #include "bolt/Profile/Heatmap.h"
 #include "bolt/Profile/YAMLProfileWriter.h"
@@ -611,6 +612,7 @@ Error DataAggregator::readProfile(BinaryContext &BC) {
         if (std::error_code EC = writeBATYAML(BC, opts::SaveProfile))
           report_error("cannot create output data file", EC);
     }
+    BC.logBOLTErrorsAndQuitOnFatal(PrintProgramStats().runOnFunctions(BC));
   }
 
   return Error::success();
@@ -859,14 +861,17 @@ bool DataAggregator::doTrace(const LBREntry &First, const LBREntry &Second,
   return true;
 }
 
-bool DataAggregator::recordTrace(
-    BinaryFunction &BF, const LBREntry &FirstLBR, const LBREntry &SecondLBR,
-    uint64_t Count,
-    SmallVector<std::pair<uint64_t, uint64_t>, 16> &Branches) const {
+std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
+DataAggregator::getFallthroughsInTrace(BinaryFunction &BF,
+                                       const LBREntry &FirstLBR,
+                                       const LBREntry &SecondLBR,
+                                       uint64_t Count) const {
+  SmallVector<std::pair<uint64_t, uint64_t>, 16> Branches;
+
   BinaryContext &BC = BF.getBinaryContext();
 
   if (!BF.isSimple())
-    return false;
+    return std::nullopt;
 
   assert(BF.hasCFG() && "can only record traces in CFG state");
 
@@ -875,13 +880,13 @@ bool DataAggregator::recordTrace(
   const uint64_t To = SecondLBR.From - BF.getAddress();
 
   if (From > To)
-    return false;
+    return std::nullopt;
 
   const BinaryBasicBlock *FromBB = BF.getBasicBlockContainingOffset(From);
   const BinaryBasicBlock *ToBB = BF.getBasicBlockContainingOffset(To);
 
   if (!FromBB || !ToBB)
-    return false;
+    return std::nullopt;
 
   // Adjust FromBB if the first LBR is a return from the last instruction in
   // the previous block (that instruction should be a call).
@@ -905,7 +910,7 @@ bool DataAggregator::recordTrace(
   // within the same basic block, e.g. when two call instructions are in the
   // same block. In this case we skip the processing.
   if (FromBB == ToBB)
-    return true;
+    return Branches;
 
   // Process blocks in the original layout order.
   BinaryBasicBlock *BB = BF.getLayout().getBlock(FromBB->getIndex());
@@ -919,7 +924,7 @@ bool DataAggregator::recordTrace(
       LLVM_DEBUG(dbgs() << "no fall-through for the trace:\n"
                         << "  " << FirstLBR << '\n'
                         << "  " << SecondLBR << '\n');
-      return false;
+      return std::nullopt;
     }
 
     const MCInst *Instr = BB->getLastNonPseudoInstr();
@@ -943,20 +948,7 @@ bool DataAggregator::recordTrace(
     BI.Count += Count;
   }
 
-  return true;
-}
-
-std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
-DataAggregator::getFallthroughsInTrace(BinaryFunction &BF,
-                                       const LBREntry &FirstLBR,
-                                       const LBREntry &SecondLBR,
-                                       uint64_t Count) const {
-  SmallVector<std::pair<uint64_t, uint64_t>, 16> Res;
-
-  if (!recordTrace(BF, FirstLBR, SecondLBR, Count, Res))
-    return std::nullopt;
-
-  return Res;
+  return Branches;
 }
 
 bool DataAggregator::recordEntry(BinaryFunction &BF, uint64_t To, bool Mispred,

bolt/lib/Rewrite/BinaryPassManager.cpp

@@ -356,7 +356,7 @@ Error BinaryFunctionPassManager::runAllPasses(BinaryContext &BC) {
   // order they're registered.
 
   // Run this pass first to use stats for the original functions.
-  Manager.registerPass(std::make_unique<PrintProgramStats>(NeverPrint));
+  Manager.registerPass(std::make_unique<PrintProgramStats>());
 
   if (opts::PrintProfileStats)
     Manager.registerPass(std::make_unique<PrintProfileStats>(NeverPrint));

bolt/lib/Rewrite/BoltDiff.cpp

@@ -292,7 +292,7 @@ class RewriteInstanceDiff {
         }
       }
     }
-    PrintProgramStats PPS(opts::NeverPrint);
+    PrintProgramStats PPS;
     outs() << "* BOLT-DIFF: Starting print program stats pass for binary 1\n";
     RI1.BC->logBOLTErrorsAndQuitOnFatal(PPS.runOnFunctions(*RI1.BC));
     outs() << "* BOLT-DIFF: Starting print program stats pass for binary 2\n";

bolt/lib/Rewrite/LinuxKernelRewriter.cpp

@@ -248,6 +248,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
   /// Update ORC data in the binary.
   Error rewriteORCTables();
 
+  /// Validate written ORC tables after binary emission.
+  Error validateORCTables();
+
   /// Static call table handling.
   Error readStaticCalls();
   Error rewriteStaticCalls();
@@ -358,6 +361,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
     if (Error E = updateStaticKeysJumpTablePostEmit())
       return E;
 
+    if (Error E = validateORCTables())
+      return E;
+
     return Error::success();
   }
 };
@@ -837,6 +843,32 @@ Error LinuxKernelRewriter::rewriteORCTables() {
   return Error::success();
 }
 
+Error LinuxKernelRewriter::validateORCTables() {
+  if (!ORCUnwindIPSection)
+    return Error::success();
+
+  const uint64_t IPSectionAddress = ORCUnwindIPSection->getAddress();
+  DataExtractor IPDE = DataExtractor(ORCUnwindIPSection->getOutputContents(),
+                                     BC.AsmInfo->isLittleEndian(),
+                                     BC.AsmInfo->getCodePointerSize());
+  DataExtractor::Cursor IPCursor(0);
+  uint64_t PrevIP = 0;
+  for (uint32_t Index = 0; Index < NumORCEntries; ++Index) {
+    const uint64_t IP =
+        IPSectionAddress + IPCursor.tell() + (int32_t)IPDE.getU32(IPCursor);
+    if (!IPCursor)
+      return createStringError(errc::executable_format_error,
+                               "out of bounds while reading ORC IP table: %s",
+                               toString(IPCursor.takeError()).c_str());
+
+    assert(IP >= PrevIP && "Unsorted ORC table detected");
+    (void)PrevIP;
+    PrevIP = IP;
+  }
+
+  return Error::success();
+}
+
 /// The static call site table is created by objtool and contains entries in the
 /// following format:
 ///