Merge branch 'main' into minnum_ieee_ppc

Author: wzssyqa

.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"

.clang-format-ignore

@@ -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/**/*

.github/new-prs-labeler.yml

@@ -19,13 +19,13 @@ jobs:
         include:
           - os: ubuntu-24.04
             ccache-variant: sccache
-            c_compiler: clang
-            cpp_compiler: clang++
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
           # TODO: remove ccache logic when https://github.com/hendrikmuhs/ccache-action/issues/279 is resolved.
           - os: ubuntu-24.04-arm
             ccache-variant: ccache
-            c_compiler: clang
-            cpp_compiler: clang++
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
           # TODO: add back gcc build when it is fixed
           # - c_compiler: gcc
           #   cpp_compiler: g++
@@ -51,6 +51,9 @@ jobs:
     #   For more information, see https://wiki.debian.org/Multiarch/LibraryPathOverview
     - name: Prepare dependencies (Ubuntu)
       run: |
+        wget https://apt.llvm.org/llvm.sh
+        chmod +x llvm.sh
+        sudo ./llvm.sh 20
         sudo apt-get update
         sudo apt-get install -y libmpfr-dev libgmp-dev libmpc-dev ninja-build linux-libc-dev
         sudo ln -sf /usr/include/$(uname -p)-linux-gnu/asm /usr/include/asm

.github/workflows/libc-fullbuild-tests.yml

@@ -69,7 +69,7 @@ jobs:
       - name: Upload Artifacts
         uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
         with:
-          name: Premerge Artifacts
+          name: Premerge Artifacts (Linux)
           path: artifacts/
           retention-days: 5
           include-hidden-files: 'true'
@@ -124,7 +124,7 @@ jobs:
       - name: Upload Artifacts
         uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
         with:
-          name: Premerge Artifacts
+          name: Premerge Artifacts (Windows)
           path: artifacts/
           retention-days: 5
           include-hidden-files: 'true'

.github/workflows/premerge.yaml

@@ -82,7 +82,8 @@ endforeach()
 
 set(BOLT_ENABLE_RUNTIME_default OFF)
 if ((CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64"
-    OR CMAKE_SYSTEM_PROCESSOR MATCHES "^(arm64|aarch64)$")
+    OR CMAKE_SYSTEM_PROCESSOR MATCHES "^(arm64|aarch64)$"
+    OR CMAKE_SYSTEM_PROCESSOR STREQUAL "riscv64")
     AND (CMAKE_SYSTEM_NAME STREQUAL "Linux"
       OR CMAKE_SYSTEM_NAME STREQUAL "Darwin")
     AND (NOT CMAKE_CROSSCOMPILING))
@@ -136,7 +137,7 @@ if (LLVM_INCLUDE_TESTS)
 endif()
 
 if (BOLT_ENABLE_RUNTIME)
-  message(STATUS "Building BOLT runtime libraries for X86")
+  message(STATUS "Building BOLT runtime libraries for ${CMAKE_SYSTEM_PROCESSOR}")
   set(extra_args "")
   if(CMAKE_SYSROOT)
     list(APPEND extra_args -DCMAKE_SYSROOT=${CMAKE_SYSROOT})

bolt/CMakeLists.txt

@@ -1174,6 +1174,11 @@ class BinaryFunction {
     return getSecondaryEntryPointSymbol(BB.getLabel());
   }
 
+  /// Remove a label from the secondary entry point map.
+  void removeSymbolFromSecondaryEntryPointMap(const MCSymbol *Label) {
+    SecondaryEntryPoints.erase(Label);
+  }
+
   /// Return true if the basic block is an entry point into the function
   /// (either primary or secondary).
   bool isEntryPoint(const BinaryBasicBlock &BB) const {
@@ -2126,6 +2131,10 @@ class BinaryFunction {
     return Islands && !Islands->DataOffsets.empty();
   }
 
+  bool isStartOfConstantIsland(uint64_t Offset) const {
+    return hasConstantIsland() && Islands->DataOffsets.count(Offset);
+  }
+
   /// Return true iff the symbol could be seen inside this function otherwise
   /// it is probably another function.
   bool isSymbolValidInScope(const SymbolRef &Symbol, uint64_t SymbolSize) const;

bolt/include/bolt/Core/BinaryFunction.h

@@ -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/BinaryBasicBlock.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/BinaryEmitter.cpp

@@ -1896,6 +1896,15 @@ void BinaryFunction::postProcessEntryPoints() {
     if (BC.isAArch64() && Offset == getSize())
       continue;
 
+    // If we have grabbed a wrong code label which actually points to some
+    // constant island inside the function, ignore this label and remove it
+    // from the secondary entry point map.
+    if (isStartOfConstantIsland(Offset)) {
+      BC.SymbolToFunctionMap.erase(Label);
+      removeSymbolFromSecondaryEntryPointMap(Label);
+      continue;
+    }
+
     BC.errs() << "BOLT-WARNING: reference in the middle of instruction "
                  "detected in function "
               << *this << " at offset 0x" << Twine::utohexstr(Offset) << '\n';
@@ -2367,7 +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/BinaryFunction.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);
 

bolt/lib/Core/DebugNames.cpp

@@ -123,6 +123,7 @@ static bool isSupportedRISCV(uint32_t Type) {
   case ELF::R_RISCV_LO12_S:
   case ELF::R_RISCV_64:
   case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TLS_GD_HI20:
   case ELF::R_RISCV_TPREL_HI20:
   case ELF::R_RISCV_TPREL_ADD:
   case ELF::R_RISCV_TPREL_LO12_I:
@@ -236,6 +237,7 @@ static size_t getSizeForTypeRISCV(uint32_t Type) {
   case ELF::R_RISCV_64:
   case ELF::R_RISCV_GOT_HI20:
   case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TLS_GD_HI20:
     // See extractValueRISCV for why this is necessary.
     return 8;
   }
@@ -491,6 +493,7 @@ static uint64_t extractValueRISCV(uint32_t Type, uint64_t Contents,
     return extractBImmRISCV(Contents);
   case ELF::R_RISCV_GOT_HI20:
   case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TLS_GD_HI20:
     // We need to know the exact address of the GOT entry so we extract the
     // value from both the AUIPC and L[D|W]. We cannot rely on the symbol in the
     // relocation for this since it simply refers to the object that is stored
@@ -707,6 +710,7 @@ static bool isPCRelativeRISCV(uint32_t Type) {
   case ELF::R_RISCV_RVC_BRANCH:
   case ELF::R_RISCV_32_PCREL:
   case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TLS_GD_HI20:
     return true;
   }
 }

bolt/lib/Core/Relocation.cpp

@@ -133,12 +133,9 @@ std::vector<yaml::bolt::PseudoProbeInfo>
 YAMLProfileWriter::convertNodeProbes(NodeIdToProbes &NodeProbes) {
   struct BlockProbeInfoHasher {
     size_t operator()(const yaml::bolt::PseudoProbeInfo &BPI) const {
-      auto HashCombine = [](auto &Range) {
-        return llvm::hash_combine_range(Range.begin(), Range.end());
-      };
-      return llvm::hash_combine(HashCombine(BPI.BlockProbes),
-                                HashCombine(BPI.CallProbes),
-                                HashCombine(BPI.IndCallProbes));
+      return llvm::hash_combine(llvm::hash_combine_range(BPI.BlockProbes),
+                                llvm::hash_combine_range(BPI.CallProbes),
+                                llvm::hash_combine_range(BPI.IndCallProbes));
     }
   };