Merge remote-tracking branch 'llvm/main' into onesided_lower_bound

* llvm/main: (500 commits)
  [docs] Add beginner-focused office hours (llvm#80308)
  [mlir][sparse] external entry method wrapper for sparse tensors (llvm#80326)
  [StackSlotColoring] Ignore non-spill objects in RemoveDeadStores. (llvm#80242)
  [libc][stdbit] fix return types (llvm#80337)
  Revert "[RISCV] Refine cost on Min/Max reduction" (llvm#80340)
  [TTI]Add support for strided loads/stores.
  [analyzer][HTMLRewriter] Cache partial rewrite results. (llvm#80220)
  [flang][openacc][openmp] Use #0 from hlfir.declare value when generating bound ops (llvm#80317)
  [AArch64][PAC] Expand blend(reg, imm) operation in aarch64-pauth pass (llvm#74729)
  [SHT_LLVM_BB_ADDR_MAP][llvm-readobj] Implements llvm-readobj handling for PGOAnalysisMap. (llvm#79520)
  [libc] add bazel support for most of unistd (llvm#80078)
  [clang-tidy] Remove enforcement of rule C.48 from cppcoreguidelines-prefer-member-init (llvm#80330)
  [OpenMP] Fix typo (NFC) (llvm#80332)
  [BOLT] Enable re-writing of Linux kernel binary (llvm#80228)
  [BOLT] Adjust section sizes based on file offsets (llvm#80226)
  [libc] fix stdbit include test when not all entrypoints are available (llvm#80323)
  [RISCV][GISel] RegBank select and instruction select for vector G_ADD, G_SUB (llvm#74114)
  [RISCV] Add srmcfg CSR from Ssqosid extension. (llvm#79914)
  [mlir][sparse] add sparsification options to pretty print and debug s… (llvm#80205)
  [RISCV][MC] MC layer support for the experimental zalasr extension (llvm#79911)
  ...

.git-blame-ignore-revs

@@ -73,3 +73,8 @@ f6d557ee34b6bbdb1dc32f29e34b4a4a8ad35e81
 
 # [libc++] Format the code base (#74334)
 9783f28cbb155e4a8d49c12e1c60ce14dcfaf0c7
+
+# [RFC] compiler-rt builtins cleanup and refactoring
+082b89b25faae3e45a023caf51b65ca0f02f377f
+0ba22f51d128bee9d69756c56c4678097270e10b
+84da0e1bb75f8666cf222d2f600f37bebb9ea389

.github/new-prs-labeler.yml

@@ -75,12 +75,49 @@ mc:
 clang:driver:
   - clang/*/Driver/**
 
+compiler-rt:asan:
+  - compiler-rt/lib/asan/**
+  - compiler-rt/include/sanitizer/asan_interface.h
+  - compiler-rt/test/asan/**
+  - compiler-rt/lib/asan_abi/**
+  - compiler-rt/test/asan_abi/**
+
+compiler-rt:builtins:
+  - compiler-rt/lib/builtins/**
+  - compiler-rt/test/builtins/**
+
+compiler-rt:cfi:
+  - compiler-rt/lib/cfi/**
+  - compiler-rt/test/cfi/**
+
+compiler-rt:fuzzer:
+  - compiler-rt/lib/fuzzer/**
+  - compiler-rt/include/fuzzer/**
+  - compiler-rt/test/fuzzer/**
+
+compiler-rt:hwasan:
+  - compiler-rt/lib/hwasan/**
+  - compiler-rt/include/sanitizer/hwasan_interface.h
+  - compiler-rt/test/hwasan/**
+
+compiler-rt:lsan:
+  - compiler-rt/lib/lsan/**
+  - compiler-rt/include/sanitizer/lsan_interface.h
+  - compiler-rt/test/lsan/**
+
+compiler-rt:msan:
+  - compiler-rt/lib/msan/**
+  - compiler-rt/include/sanitizer/msan_interface.h
+  - compiler-rt/test/msan/**
+
 compiler-rt:sanitizer:
   - llvm/lib/Transforms/Instrumentation/*Sanitizer*
   - compiler-rt/lib/interception/**
   - compiler-rt/lib/*san*/**
+  - compiler-rt/include/sanitizer/**
   - compiler-rt/test/*san*/**
   - compiler-rt/lib/fuzzer/**
+  - compiler-rt/include/fuzzer/**
   - compiler-rt/test/fuzzer/**
   - compiler-rt/lib/scudo/**
   - compiler-rt/test/scudo/**
@@ -89,6 +126,19 @@ compiler-rt:scudo:
   - compiler-rt/lib/scudo/**
   - compiler-rt/test/scudo/**
 
+compiler-rt:tsan:
+  - compiler-rt/lib/tsan/**
+  - compiler-rt/include/sanitizer/tsan_interface.h
+  - compiler-rt/include/sanitizer/tsan_interface_atomic.h
+  - compiler-rt/test/tsan/**
+
+compiler-rt:ubsan:
+  - compiler-rt/lib/ubsan/**
+  - compiler-rt/include/sanitizer/ubsan_interface.h
+  - compiler-rt/test/ubsan/**
+  - compiler-rt/lib/ubsan_minimal/**
+  - compiler-rt/test/ubsan_minimal/**
+
 xray:
   - llvm/tools/llvm-xray/**
   - compiler-rt/*/xray/**

.github/workflows/containers/github-action-ci/Dockerfile

@@ -2,29 +2,35 @@ FROM docker.io/library/ubuntu:22.04 as base
 ENV LLVM_SYSROOT=/opt/llvm/
 
 FROM base as toolchain
-ENV LLVM_MAJOR=17
-ENV LLVM_VERSION=${LLVM_MAJOR}.0.6
-ENV LLVM_DIRNAME=clang+llvm-${LLVM_VERSION}-x86_64-linux-gnu-ubuntu-22.04
-ENV LLVM_FILENAME=${LLVM_DIRNAME}.tar.xz
+ENV LLVM_VERSION=17.0.6
 
 RUN apt-get update && \
     apt-get install -y \
-    curl \
-    xz-utils
+    wget \
+    gcc \
+    g++ \
+    cmake \
+    ninja-build \
+    python3
+
+RUN wget https://github.com/llvm/llvm-project/archive/refs/tags/llvmorg-$LLVM_VERSION.tar.gz && tar -xf llvmorg-$LLVM_VERSION.tar.gz
 
-RUN mkdir -p $LLVM_SYSROOT/bin/ $LLVM_SYSROOT/lib/
+WORKDIR /llvm-project-llvmorg-$LLVM_VERSION
 
-RUN curl -O -L https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/$LLVM_FILENAME
+RUN mkdir build
 
-RUN tar -C $LLVM_SYSROOT --strip-components=1 -xJf $LLVM_FILENAME \
-    $LLVM_DIRNAME/bin/clang \
-    $LLVM_DIRNAME/bin/clang++ \
-    $LLVM_DIRNAME/bin/clang-cl \
-    $LLVM_DIRNAME/bin/clang-$LLVM_MAJOR \
-    $LLVM_DIRNAME/bin/lld \
-    $LLVM_DIRNAME/bin/ld.lld \
-    $LLVM_DIRNAME/lib/clang/
+RUN cmake -B ./build -G Ninja ./llvm \
+  -C ./clang/cmake/caches/BOLT-PGO.cmake \
+  -DBOOTSTRAP_LLVM_ENABLE_LLD=ON \
+  -DBOOTSTRAP_BOOTSTRAP_LLVM_ENABLE_LLD=ON \
+  -DPGO_INSTRUMENT_LTO=Thin \
+  -DLLVM_ENABLE_RUNTIMES="compiler-rt" \
+  -DCMAKE_INSTALL_PREFIX="$LLVM_SYSROOT" \
+  -DLLVM_ENABLE_PROJECTS="bolt;clang;lld;clang-tools-extra" \
+  -DLLVM_DISTRIBUTION_COMPONENTS="lld;compiler-rt;clang-format" \
+  -DCLANG_DEFAULT_LINKER="lld"
 
+RUN ninja -C ./build stage2-clang-bolt stage2-install-distribution && ninja -C ./build install-distribution && rm -rf ./build
 
 FROM base
 

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

@@ -75,7 +75,7 @@ jobs:
           CC: ${{ matrix.cc }}
           CXX: ${{ matrix.cxx }}
           ENABLE_CLANG_TIDY: ${{ matrix.clang_tidy }}
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()
         with:
           name: ${{ matrix.config }}-${{ matrix.cxx }}-results
@@ -124,10 +124,10 @@ jobs:
           CC: ${{ matrix.cc }}
           CXX: ${{ matrix.cxx }}
           ENABLE_CLANG_TIDY: ${{ matrix.clang_tidy }}
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()  # Upload artifacts even if the build or test suite fails
         with:
-          name: ${{ matrix.config }}-results
+          name: ${{ matrix.config }}-${{ matrix.cxx }}-results
           path: |
             **/test-results.xml
             **/*.abilist
@@ -189,7 +189,7 @@ jobs:
           CC: clang-18
           CXX: clang++-18
           ENABLE_CLANG_TIDY: "OFF"
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()
         with:
           name: ${{ matrix.config }}-results

.github/workflows/merged-prs.yml

@@ -0,0 +1,41 @@
+name: "Add buildbot information to first PRs from new contributors"
+
+permissions:
+  contents: read
+
+on:
+  # It's safe to use pull_request_target here, because we aren't checking out
+  # code from the pull request branch.
+  # See https://securitylab.github.com/research/github-actions-preventing-pwn-requests/
+  pull_request_target:
+    types:
+      - closed
+
+jobs:
+  buildbot_comment:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    if: >-
+      (github.repository == 'llvm/llvm-project') &&
+      (github.event.pull_request.merged == true)
+    steps:
+      - name: Checkout Automation Script
+        uses: actions/checkout@v4
+        with:
+          sparse-checkout: llvm/utils/git/
+          ref: main
+
+      - name: Setup Automation Script
+        working-directory: ./llvm/utils/git/
+        run: |
+          pip install -r requirements.txt
+
+      - name: Add Buildbot information comment
+        working-directory: ./llvm/utils/git/
+        run: |
+          python3 ./github-automation.py \
+            --token '${{ secrets.GITHUB_TOKEN }}' \
+            pr-buildbot-information \
+            --issue-number "${{ github.event.pull_request.number }}" \
+            --author "${{ github.event.pull_request.user.login }}"

bolt/include/bolt/Core/BinaryContext.h

@@ -554,6 +554,9 @@ class BinaryContext {
   /// Huge page size to use.
   static constexpr unsigned HugePageSize = 0x200000;
 
+  /// Addresses reserved for kernel on x86_64 start at this location.
+  static constexpr uint64_t KernelStartX86_64 = 0xFFFF'FFFF'8000'0000;
+
   /// Map address to a constant island owner (constant data in code section)
   std::map<uint64_t, BinaryFunction *> AddressToConstantIslandMap;
 
@@ -602,6 +605,9 @@ class BinaryContext {
 
   std::unique_ptr<MCAsmBackend> MAB;
 
+  /// Indicates if the binary is Linux kernel.
+  bool IsLinuxKernel{false};
+
   /// Indicates if relocations are available for usage.
   bool HasRelocations{false};
 
@@ -665,6 +671,11 @@ class BinaryContext {
     uint64_t StaleSampleCount{0};
     ///   the count of matched samples
     uint64_t MatchedSampleCount{0};
+    ///   the number of stale functions that have matching number of blocks in
+    ///   the profile
+    uint64_t NumStaleFuncsWithEqualBlockCount{0};
+    ///   the number of blocks that have matching size but a differing hash
+    uint64_t NumStaleBlocksWithEqualIcount{0};
   } Stats;
 
   // Address of the first allocated segment.

bolt/include/bolt/Rewrite/MetadataManager.h

@@ -36,6 +36,9 @@ class MetadataManager {
   /// Execute metadata initializers after CFG was constructed for functions.
   void runInitializersPostCFG();
 
+  /// Run finalization step of rewriters before the binary is emitted.
+  void runFinalizersPreEmit();
+
   /// Run finalization step of rewriters after code has been emitted.
   void runFinalizersAfterEmit();
 };

bolt/include/bolt/Rewrite/MetadataRewriter.h

@@ -52,6 +52,9 @@ class MetadataRewriter {
   /// Run the rewriter once the functions are in CFG state.
   virtual Error postCFGInitializer() { return Error::success(); }
 
+  /// Run the pass before the binary is emitted.
+  virtual Error preEmitFinalizer() { return Error::success(); }
+
   /// Finalize section contents based on the new context after the new code is
   /// emitted.
   virtual Error postEmitFinalizer() { return Error::success(); }

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -183,6 +183,9 @@ class RewriteInstance {
   /// Process metadata in special sections after CFG is built for functions.
   void processMetadataPostCFG();
 
+  /// Make changes to metadata before the binary is emitted.
+  void finalizeMetadataPreEmit();
+
   /// Update debug and other auxiliary information in the file.
   void updateMetadata();
 
@@ -261,6 +264,11 @@ class RewriteInstance {
   void createPLTBinaryFunction(uint64_t TargetAddress, uint64_t EntryAddress,
                                uint64_t EntrySize);
 
+  /// Disassemble PLT instruction.
+  void disassemblePLTInstruction(const BinarySection &Section,
+                                 uint64_t InstrOffset, MCInst &Instruction,
+                                 uint64_t &InstrSize);
+
   /// Disassemble aarch64-specific .plt \p Section auxiliary function
   void disassemblePLTSectionAArch64(BinarySection &Section);
 

bolt/include/bolt/Utils/CommandLineOpts.h

@@ -18,7 +18,6 @@
 namespace opts {
 
 extern bool HeatmapMode;
-extern bool LinuxKernelMode;
 
 extern llvm::cl::OptionCategory BoltCategory;
 extern llvm::cl::OptionCategory BoltDiffCategory;

bolt/lib/Passes/BinaryPasses.cpp

@@ -1420,6 +1420,12 @@ void PrintProgramStats::runOnFunctions(BinaryContext &BC) {
   if (NumAllStaleFunctions) {
     const float PctStale =
         NumAllStaleFunctions / (float)NumAllProfiledFunctions * 100.0f;
+    const float PctStaleFuncsWithEqualBlockCount =
+        (float)BC.Stats.NumStaleFuncsWithEqualBlockCount /
+        NumAllStaleFunctions * 100.0f;
+    const float PctStaleBlocksWithEqualIcount =
+        (float)BC.Stats.NumStaleBlocksWithEqualIcount /
+        BC.Stats.NumStaleBlocks * 100.0f;
     auto printErrorOrWarning = [&]() {
       if (PctStale > opts::StaleThreshold)
         errs() << "BOLT-ERROR: ";
@@ -1442,6 +1448,16 @@ void PrintProgramStats::runOnFunctions(BinaryContext &BC) {
              << "%) belong to functions with invalid"
                 " (possibly stale) profile.\n";
     }
+    outs() << "BOLT-INFO: " << BC.Stats.NumStaleFuncsWithEqualBlockCount
+           << " stale function"
+           << (BC.Stats.NumStaleFuncsWithEqualBlockCount == 1 ? "" : "s")
+           << format(" (%.1f%% of all stale)", PctStaleFuncsWithEqualBlockCount)
+           << " have matching block count.\n";
+    outs() << "BOLT-INFO: " << BC.Stats.NumStaleBlocksWithEqualIcount
+           << " stale block"
+           << (BC.Stats.NumStaleBlocksWithEqualIcount == 1 ? "" : "s")
+           << format(" (%.1f%% of all stale)", PctStaleBlocksWithEqualIcount)
+           << " have matching icount.\n";
     if (PctStale > opts::StaleThreshold) {
       errs() << "BOLT-ERROR: stale functions exceed specified threshold of "
              << opts::StaleThreshold << "%. Exiting.\n";

bolt/lib/Profile/DataAggregator.cpp

@@ -524,7 +524,7 @@ Error DataAggregator::preprocessProfile(BinaryContext &BC) {
       ErrorCallback(ReturnCode, ErrBuf);
   };
 
-  if (opts::LinuxKernelMode) {
+  if (BC.IsLinuxKernel) {
     // Current MMap parsing logic does not work with linux kernel.
     // MMap entries for linux kernel uses PERF_RECORD_MMAP
     // format instead of typical PERF_RECORD_MMAP2 format.
@@ -1056,7 +1056,7 @@ ErrorOr<DataAggregator::PerfBranchSample> DataAggregator::parseBranchSample() {
   if (std::error_code EC = PIDRes.getError())
     return EC;
   auto MMapInfoIter = BinaryMMapInfo.find(*PIDRes);
-  if (!opts::LinuxKernelMode && MMapInfoIter == BinaryMMapInfo.end()) {
+  if (!BC->IsLinuxKernel && MMapInfoIter == BinaryMMapInfo.end()) {
     consumeRestOfLine();
     return make_error_code(errc::no_such_process);
   }
@@ -1277,7 +1277,7 @@ std::error_code DataAggregator::printLBRHeatMap() {
   NamedRegionTimer T("parseBranch", "Parsing branch events", TimerGroupName,
                      TimerGroupDesc, opts::TimeAggregator);
 
-  if (opts::LinuxKernelMode) {
+  if (BC->IsLinuxKernel) {
     opts::HeatmapMaxAddress = 0xffffffffffffffff;
     opts::HeatmapMinAddress = KernelBaseAddr;
   }

bolt/lib/Profile/StaleProfileMatching.cpp

@@ -418,6 +418,7 @@ void matchWeightsByHashes(BinaryContext &BC,
     if (MatchedBlock == nullptr && YamlBB.Index == 0)
       MatchedBlock = Blocks[0];
     if (MatchedBlock != nullptr) {
+      const BinaryBasicBlock *BB = BlockOrder[MatchedBlock->Index - 1];
       MatchedBlocks[YamlBB.Index] = MatchedBlock;
       BlendedBlockHash BinHash = BlendedHashes[MatchedBlock->Index - 1];
       LLVM_DEBUG(dbgs() << "Matched yaml block (bid = " << YamlBB.Index << ")"
@@ -433,6 +434,8 @@ void matchWeightsByHashes(BinaryContext &BC,
       } else {
         LLVM_DEBUG(dbgs() << "  loose match\n");
       }
+      if (YamlBB.NumInstructions == BB->size())
+        ++BC.Stats.NumStaleBlocksWithEqualIcount;
     } else {
       LLVM_DEBUG(
           dbgs() << "Couldn't match yaml block (bid = " << YamlBB.Index << ")"

bolt/lib/Profile/YAMLProfileReader.cpp

@@ -246,20 +246,20 @@ bool YAMLProfileReader::parseFunctionProfile(
 
   ProfileMatched &= !MismatchedBlocks && !MismatchedCalls && !MismatchedEdges;
 
-  if (ProfileMatched)
-    BF.markProfiled(YamlBP.Header.Flags);
+  if (!ProfileMatched) {
+    if (opts::Verbosity >= 1)
+      errs() << "BOLT-WARNING: " << MismatchedBlocks << " blocks, "
+             << MismatchedCalls << " calls, and " << MismatchedEdges
+             << " edges in profile did not match function " << BF << '\n';
 
-  if (!ProfileMatched && opts::Verbosity >= 1)
-    errs() << "BOLT-WARNING: " << MismatchedBlocks << " blocks, "
-           << MismatchedCalls << " calls, and " << MismatchedEdges
-           << " edges in profile did not match function " << BF << '\n';
+    if (YamlBF.NumBasicBlocks != BF.size())
+      ++BC.Stats.NumStaleFuncsWithEqualBlockCount;
 
-  if (!ProfileMatched && opts::InferStaleProfile) {
-    if (inferStaleProfile(BF, YamlBF)) {
+    if (opts::InferStaleProfile && inferStaleProfile(BF, YamlBF))
       ProfileMatched = true;
-      BF.markProfiled(YamlBP.Header.Flags);
-    }
   }
+  if (ProfileMatched)
+    BF.markProfiled(YamlBP.Header.Flags);
 
   return ProfileMatched;
 }