ci: add MemorySanitizer CI job

Add build_msan_toolchain.sh to produce a tarball containing an
MSan-instrumented libc++/libc++abi/libunwind toolchain, and add an msan
CI job that downloads the tarball and runs the test suite under MSan.

Also add USE_MSAN CMake option that disables conflicting sanitizers,
switches to lld, and propagates -fsanitize=memory to the shared library
and fuzz_driver targets.

.gitea/workflows/ci.yml

@@ -218,6 +218,87 @@ jobs:
             --link "https://minio.weaselab.dev/jenkins/conflict-set/${{ gitea.run_number }}/release-${{ matrix.arch }}/Test.xml.zst" \
             | tee -a "$GITHUB_STEP_SUMMARY"
 
+  msan:
+    runs-on: ubuntu-latest-amd64
+    env:
+      MSAN_VERSION: "21.1.8"
+      MSAN_URL: "https://minio.weaselab.dev/public/x86_64/msan-toolchain-21.1.8.tar.zst"
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/cache@v4
+        with:
+          path: /var/cache/apt/archives
+          key: apt-amd64-${{ hashFiles('.gitea/workflows/ci.yml') }}
+
+      - name: Install dependencies
+        run: |
+          . /etc/os-release
+          wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc
+          echo "deb http://apt.llvm.org/${VERSION_CODENAME}/ llvm-toolchain-${VERSION_CODENAME}-21 main" | sudo tee /etc/apt/sources.list.d/llvm.list
+          sudo apt-get update -qq
+          sudo apt-get install -y \
+            build-essential ccache clang-21 cmake libc6-dbg \
+            llvm-21 lld-21 mold ninja-build python3 zstd
+          for tool in clang clang++ llvm-ar llvm-nm llvm-ranlib llvm-objcopy llvm-cov llvm-symbolizer lld ld.lld; do
+            sudo update-alternatives --install /usr/bin/${tool} ${tool} /usr/bin/${tool}-21 100
+          done
+
+      - name: Download MSan toolchain
+        run: |
+          curl -Ls "${MSAN_URL}" -o /tmp/msan-toolchain.tar.zst
+          sudo mkdir -p /opt/msan
+          sudo tar --zstd -xf /tmp/msan-toolchain.tar.zst -C /opt/msan
+
+      - uses: actions/cache@v4
+        with:
+          path: .ccache
+          key: ccache-msan-${{ gitea.sha }}
+          restore-keys: |
+            ccache-msan-
+
+      - name: Build
+        run: |
+          export CCACHE_DIR="$GITHUB_WORKSPACE/.ccache"
+          rm -rf build
+          cmake -S . -B build -G Ninja \
+            -DCMAKE_C_COMPILER=clang \
+            -DCMAKE_CXX_COMPILER=clang++ \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_BUILD_TYPE=Debug \
+            -DDISABLE_TSAN=ON \
+            -DUSE_MSAN=ON \
+            -DCMAKE_CXX_FLAGS="-fsanitize=memory -stdlib=libc++ -I/opt/msan/include/c++/v1 -L/opt/msan/lib -UNDEBUG" \
+            -DCMAKE_EXE_LINKER_FLAGS="-stdlib=libc++ -Wl,-rpath,/opt/msan/lib" \
+            -DCMAKE_SHARED_LINKER_FLAGS="-stdlib=libc++ -Wl,-rpath,/opt/msan/lib"
+          ninja -C build
+          ccache -s
+
+      - name: Test
+        run: |
+          cd build
+          ctest --no-compress-output --test-output-size-passed 100000 --test-output-size-failed 100000 -T Test -j "$(nproc)" --timeout 300 > /dev/null
+
+      - name: Upload test results to MinIO
+        if: always()
+        env:
+          MINIO_ACCESS_KEY: ${{ secrets.MINIO_ACCESS_KEY }}
+          MC_HOST_minio: https://${{ secrets.MINIO_ACCESS_KEY }}:${{ secrets.MINIO_SECRET_KEY }}@minio.weaselab.dev
+        run: |
+          if [ -z "$MINIO_ACCESS_KEY" ]; then
+            echo "MinIO credentials not configured; skipping upload"
+            exit 0
+          fi
+          zstd build/Testing/*/Test.xml
+          mc cp build/Testing/*/Test.xml.zst "minio/jenkins/conflict-set/${{ gitea.run_number }}/msan/"
+
+      - name: Test summary
+        if: always()
+        run: |
+          python3 ctest_summary.py build/Testing/*/Test.xml \
+            --link "https://minio.weaselab.dev/jenkins/conflict-set/${{ gitea.run_number }}/msan/Test.xml.zst" \
+            | tee -a "$GITHUB_STEP_SUMMARY"
+
   coverage:
     runs-on: ubuntu-latest-amd64
     steps:

CMakeLists.txt

@@ -49,6 +49,18 @@ if(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
         ${LLVM_OBJCOPY}
         CACHE FILEPATH "path to objcopy binary" FORCE)
   endif()
+  if(USE_MSAN)
+    find_program(LLD_LINKER lld)
+    if(LLD_LINKER)
+      set(CMAKE_LINKER_TYPE
+          "LLD"
+          CACHE STRING "Use LLD linker" FORCE)
+      set(CMAKE_LINKER
+          ${LLD_LINKER}
+          CACHE FILEPATH "path to linker binary" FORCE)
+      add_link_options("-fuse-ld=lld")
+    endif()
+  endif()
 endif()
 
 if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
@@ -103,6 +115,8 @@ option(USE_SIMD_FALLBACK
 
 option(DISABLE_TSAN "Disable TSAN" OFF)
 
+option(USE_MSAN "Build with MemorySanitizer (disables ASan/UBSan)" OFF)
+
 # This is encouraged according to
 # https://valgrind.org/docs/manual/manual-core-adv.html#manual-core-adv.clientreq
 include_directories(SYSTEM ${CMAKE_CURRENT_SOURCE_DIR}/third_party/valgrind)
@@ -232,8 +246,10 @@ if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR AND BUILD_TESTING)
   target_compile_definitions(conflict_set_main PRIVATE ENABLE_MAIN)
   target_link_libraries(conflict_set_main PRIVATE nanobench)
 
-  if(NOT APPLE)
+  if(NOT APPLE AND NOT USE_MSAN)
-    # libfuzzer target, to generate/manage corpus
+    # libfuzzer target, to generate/manage corpus. MSan requires an instrumented
+    # libfuzzer runtime, which is not shipped with the compiler, so skip this
+    # target when building with MSan.
     set(FUZZ_FLAGS "-fsanitize=fuzzer-no-link,address,undefined")
     include(CheckCXXCompilerFlag)
     cmake_push_check_state()
@@ -257,9 +273,14 @@ if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR AND BUILD_TESTING)
   add_executable(fuzz_driver ConflictSet.cpp FuzzTestDriver.cpp)
   target_compile_options(fuzz_driver PRIVATE ${TEST_FLAGS})
   if(NOT CMAKE_CROSSCOMPILING)
+    if(USE_MSAN)
+      target_compile_options(fuzz_driver PRIVATE -fsanitize=memory)
+      target_link_options(fuzz_driver PRIVATE -fsanitize=memory)
+    else()
       target_compile_options(fuzz_driver PRIVATE -fsanitize=address,undefined)
       target_link_options(fuzz_driver PRIVATE -fsanitize=address,undefined)
     endif()
+  endif()
   target_compile_definitions(fuzz_driver PRIVATE ENABLE_FUZZ)
   target_include_directories(fuzz_driver
                              PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include)
@@ -269,7 +290,9 @@ if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR AND BUILD_TESTING)
   endforeach()
 
   # tsan tests
-  if(NOT CMAKE_CROSSCOMPILING AND NOT DISABLE_TSAN)
+  if(NOT CMAKE_CROSSCOMPILING
+     AND NOT DISABLE_TSAN
+     AND NOT USE_MSAN)
     add_executable(tsan_driver ConflictSet.cpp FuzzTestDriver.cpp)
     target_compile_options(tsan_driver PRIVATE ${TEST_FLAGS} -fsanitize=thread)
     target_link_options(tsan_driver PRIVATE -fsanitize=thread)
@@ -491,6 +514,11 @@ target_include_directories(
   PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
          $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${PROJECT_NAME}>)
 
+if(USE_MSAN)
+  target_compile_options(${PROJECT_NAME} PUBLIC -fsanitize=memory)
+  target_link_options(${PROJECT_NAME} PUBLIC -fsanitize=memory)
+endif()
+
 set_target_properties(
   ${PROJECT_NAME} PROPERTIES VERSION ${PROJECT_VERSION}
                              SOVERSION ${PROJECT_VERSION_MAJOR})

build_msan_toolchain.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+LLVM_VERSION="${LLVM_VERSION:-21}"
+MSAN_PREFIX="${MSAN_PREFIX:-$PWD/msan}"
+JOBS="${JOBS:-$(nproc)}"
+
+cd /tmp
+rm -rf libcxx-msan
+mkdir libcxx-msan
+cd libcxx-msan
+
+git clone --depth=1 "https://github.com/llvm/llvm-project.git" -b "release/${LLVM_VERSION}.x"
+
+cmake -S llvm-project/runtimes -B build \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DCMAKE_C_COMPILER="clang-${LLVM_VERSION}" \
+  -DCMAKE_CXX_COMPILER="clang++-${LLVM_VERSION}" \
+  -DLLVM_USE_SANITIZER=MemoryWithOrigins \
+  -DLLVM_ENABLE_RUNTIMES="libcxx;libcxxabi;libunwind" \
+  -DLLVM_TARGETS_TO_BUILD=Native \
+  -DCMAKE_INSTALL_PREFIX="${MSAN_PREFIX}" \
+  -DLIBCXXABI_USE_LLVM_UNWINDER=ON \
+  -DLIBCXXABI_ENABLE_STATIC_UNWINDER=ON \
+  -DLIBCXX_USE_COMPILER_RT=ON \
+  -DLIBCXXABI_USE_COMPILER_RT=ON \
+  -DLIBUNWIND_USE_COMPILER_RT=ON \
+  -DLIBCXX_INCLUDE_TESTS=OFF \
+  -DLIBCXXABI_INCLUDE_TESTS=OFF \
+  -DLIBUNWIND_INCLUDE_TESTS=OFF \
+  -DLIBCXX_ENABLE_CLANG_TIDY=OFF
+
+cmake --build build -j"${JOBS}"
+cmake --install build
+
+VERSION="$(clang-"${LLVM_VERSION}" --version | head -n1 | sed -E 's/.*clang version ([0-9.]+).*/\1/')"
+TARBALL="msan-toolchain-${VERSION}.tar.zst"
+
+tar --zstd -cf "${TARBALL}" -C "${MSAN_PREFIX}" .
+
+TARBALL_PATH="$(pwd)/${TARBALL}"
+echo "Created: ${TARBALL_PATH}"