Merge branch 'main' into obj2yaml/root-descriptors

Author: joaosaffran

.ci/compute_projects.py

@@ -52,6 +52,9 @@
     "clang": {"clang-tools-extra", "compiler-rt", "cross-project-tests"},
     "clang-tools-extra": {"libc"},
     "mlir": {"flang"},
+    # Test everything if ci scripts are changed.
+    # FIXME: Figure out what is missing and add here.
+    ".ci": {"llvm", "clang", "lld", "lldb"},
 }
 
 DEPENDENT_RUNTIMES_TO_TEST = {"clang": {"libcxx", "libcxxabi", "libunwind"}}
@@ -130,12 +133,11 @@ def _add_dependencies(projects: Set[str]) -> Set[str]:
 def _compute_projects_to_test(modified_projects: Set[str], platform: str) -> Set[str]:
     projects_to_test = set()
     for modified_project in modified_projects:
-        # Skip all projects where we cannot run tests.
-        if modified_project not in PROJECT_CHECK_TARGETS:
-            continue
         if modified_project in RUNTIMES:
             continue
-        projects_to_test.add(modified_project)
+        # Skip all projects where we cannot run tests.
+        if modified_project in PROJECT_CHECK_TARGETS:
+            projects_to_test.add(modified_project)
         if modified_project not in DEPENDENTS_TO_TEST:
             continue
         for dependent_project in DEPENDENTS_TO_TEST[modified_project]:

.ci/compute_projects_test.py

@@ -188,6 +188,23 @@ def test_exclude_gn(self):
         self.assertEqual(env_variables["runtimes_to_build"], "")
         self.assertEqual(env_variables["runtimes_check_targets"], "")
 
+    def test_ci(self):
+        env_variables = compute_projects.get_env_variables(
+            [".ci/compute_projects.py"], "Linux"
+        )
+        self.assertEqual(env_variables["projects_to_build"], "clang;lld;llvm;lldb")
+        self.assertEqual(
+            env_variables["project_check_targets"],
+            "check-clang check-lld check-llvm check-lldb",
+        )
+        self.assertEqual(
+            env_variables["runtimes_to_build"], "libcxx;libcxxabi;libunwind"
+        )
+        self.assertEqual(
+            env_variables["runtimes_check_targets"],
+            "check-cxx check-cxxabi check-unwind",
+        )
+
 
 if __name__ == "__main__":
     unittest.main()

.ci/monolithic-linux.sh

@@ -28,10 +28,14 @@ if [[ -n "${CLEAR_CACHE:-}" ]]; then
   ccache --clear
 fi
 
+mkdir -p artifacts/reproducers
+
+# Make sure any clang reproducers will end up as artifacts.
+export CLANG_CRASH_DIAGNOSTICS_DIR=`realpath artifacts/reproducers`
+
 function at-exit {
   retcode=$?
 
-  mkdir -p artifacts
   ccache --print-stats > artifacts/ccache_stats.txt
   cp "${BUILD_DIR}"/.ninja_log artifacts/.ninja_log
 
@@ -58,9 +62,18 @@ export PIP_BREAK_SYSTEM_PACKAGES=1
 pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
 pip install -q -r "${MONOREPO_ROOT}"/lldb/test/requirements.txt
 pip install -q -r "${MONOREPO_ROOT}"/.ci/requirements.txt
+
+# Set the system llvm-symbolizer as preferred.
+export LLVM_SYMBOLIZER_PATH=`which llvm-symbolizer`
+[[ ! -f "${LLVM_SYMBOLIZER_PATH}" ]] && echo "llvm-symbolizer not found!"
+
+# Set up all runtimes either way. libcxx is a dependency of LLDB.
+# It will not be built unless it is used.
 cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_PROJECTS="${projects}" \
+      -D LLVM_ENABLE_RUNTIMES="libcxx;libcxxabi;libunwind" \
       -G Ninja \
+      -D CMAKE_PREFIX_PATH="${HOME}/.local" \
       -D CMAKE_BUILD_TYPE=Release \
       -D LLVM_ENABLE_ASSERTIONS=ON \
       -D LLVM_BUILD_EXAMPLES=ON \
@@ -69,7 +82,10 @@ cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_LLD=ON \
       -D CMAKE_CXX_FLAGS=-gmlt \
       -D LLVM_CCACHE_BUILD=ON \
+      -D LIBCXX_CXX_ABI=libcxxabi \
       -D MLIR_ENABLE_BINDINGS_PYTHON=ON \
+      -D LLDB_ENABLE_PYTHON=ON \
+      -D LLDB_ENFORCE_STRICT_TEST_REQUIREMENTS=ON \
       -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}"
 
 echo "--- ninja"

.github/CODEOWNERS

@@ -128,7 +128,7 @@
 /mlir/**/Transforms/SROA.* @moxinilian
 
 # BOLT
-/bolt/ @aaupov @maksfb @rafaelauler @ayermolo @dcci @yota9
+/bolt/ @aaupov @maksfb @rafaelauler @ayermolo @yota9
 
 # Bazel build system.
 /utils/bazel/ @rupprecht @keith @aaronmondal

.github/new-prs-labeler.yml

@@ -7,6 +7,12 @@ ClangIR:
   - clang/tools/cir-*/**/*
   - clang/test/CIR/**/*
 
+clang:bytecode:
+  - clang/docs/ConstantInterpreter.rst
+  - clang/lib/AST/ByteCode/**/*
+  - clang/test/AST/ByteCode/**/*
+  - clang/unittests/AST/ByteCode/**/*
+
 clang:dataflow:
   - clang/include/clang/Analysis/FlowSensitive/**/*
   - clang/lib/Analysis/FlowSensitive/**/*

bolt/include/bolt/Profile/DataAggregator.h

@@ -223,14 +223,16 @@ class DataAggregator : public DataReader {
   bool recordExit(BinaryFunction &BF, uint64_t From, bool Mispred,
                   uint64_t Count = 1) const;
 
-  /// Aggregation statistics
+  /// Branch stacks aggregation statistics
+  uint64_t NumTraces{0};
   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};
+  uint64_t NumTotalSamples{0};
 
   /// Looks into system PATH for Linux Perf and set up the aggregator to use it
   void findPerfExecutable();
@@ -327,8 +329,8 @@ class DataAggregator : public DataReader {
   /// Parse a single LBR entry as output by perf script -Fbrstack
   ErrorOr<LBREntry> parseLBREntry();
 
-  /// Parse LBR sample, returns the number of traces.
-  uint64_t parseLBRSample(const PerfBranchSample &Sample, bool NeedsSkylakeFix);
+  /// Parse LBR sample.
+  void parseLBRSample(const PerfBranchSample &Sample, bool NeedsSkylakeFix);
 
   /// Parse and pre-aggregate branch events.
   std::error_code parseBranchEvents();
@@ -487,6 +489,13 @@ class DataAggregator : public DataReader {
   void dump(const PerfBranchSample &Sample) const;
   void dump(const PerfMemSample &Sample) const;
 
+  /// Profile diagnostics print methods
+  void printColdSamplesDiagnostic() const;
+  void printLongRangeTracesDiagnostic() const;
+  void printBranchSamplesDiagnostics() const;
+  void printBasicSamplesDiagnostics(uint64_t OutOfRangeSamples) const;
+  void printBranchStacksDiagnostics(uint64_t IgnoredSamples) const;
+
 public:
   /// If perf.data was collected without build ids, the buildid-list may contain
   /// incomplete entries. Return true if the buffer containing

bolt/lib/Core/BinaryBasicBlock.cpp

@@ -372,8 +372,7 @@ void BinaryBasicBlock::updateJumpTableSuccessors() {
              [](const BinaryBasicBlock *BB1, const BinaryBasicBlock *BB2) {
                return BB1->getInputOffset() < BB2->getInputOffset();
              });
-  SuccessorBBs.erase(std::unique(SuccessorBBs.begin(), SuccessorBBs.end()),
-                     SuccessorBBs.end());
+  SuccessorBBs.erase(llvm::unique(SuccessorBBs), SuccessorBBs.end());
 
   for (BinaryBasicBlock *BB : SuccessorBBs)
     addSuccessor(BB);

bolt/lib/Core/BinaryEmitter.cpp

@@ -373,8 +373,10 @@ bool BinaryEmitter::emitFunction(BinaryFunction &Function,
     Streamer.emitLabel(StartSymbol);
   }
 
+  const bool NeedsFDE =
+      Function.hasCFI() && !(Function.isPatch() && Function.isAnonymous());
   // Emit CFI start
-  if (Function.hasCFI()) {
+  if (NeedsFDE) {
     Streamer.emitCFIStartProc(/*IsSimple=*/false);
     if (Function.getPersonalityFunction() != nullptr)
       Streamer.emitCFIPersonality(Function.getPersonalityFunction(),
@@ -421,7 +423,7 @@ bool BinaryEmitter::emitFunction(BinaryFunction &Function,
     Streamer.emitBytes(BC.MIB->getTrapFillValue());
 
   // Emit CFI end
-  if (Function.hasCFI())
+  if (NeedsFDE)
     Streamer.emitCFIEndProc();
 
   MCSymbol *EndSymbol = Function.getFunctionEndLabel(FF.getFragmentNum());

bolt/lib/Core/BinaryFunction.cpp

@@ -2376,7 +2376,7 @@ Error BinaryFunction::buildCFG(MCPlusBuilder::AllocatorIdTy AllocatorId) {
   // Without doing jump table value profiling we don't have a use for extra
   // (duplicate) branches.
   llvm::sort(TakenBranches);
-  auto NewEnd = std::unique(TakenBranches.begin(), TakenBranches.end());
+  auto NewEnd = llvm::unique(TakenBranches);
   TakenBranches.erase(NewEnd, TakenBranches.end());
 
   for (std::pair<uint32_t, uint32_t> &Branch : TakenBranches) {

bolt/lib/Core/DebugNames.cpp

@@ -440,8 +440,7 @@ void DWARF5AcceleratorTable::computeBucketCount() {
   for (const auto &E : Entries)
     Uniques.push_back(E.second.HashValue);
   array_pod_sort(Uniques.begin(), Uniques.end());
-  std::vector<uint32_t>::iterator P =
-      std::unique(Uniques.begin(), Uniques.end());
+  std::vector<uint32_t>::iterator P = llvm::unique(Uniques);
 
   UniqueHashCount = std::distance(Uniques.begin(), P);