diff options
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | 2023-11-08 00:03:27 +0000 |
---|---|---|
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | 2023-11-08 00:03:27 +0000 |
commit | 757e1068624ce6e86a08458bfc0da959b50df521 (patch) | |
tree | 1c240a98c2896c94781ea4ff487379b18a894e09 | |
parent | 02d04222256d8977954746eb334d91efb16fca9f (diff) | |
parent | f2c1cc94de204b9459eb4f108a27fb9e04c2fb08 (diff) | |
download | bpftool-757e1068624ce6e86a08458bfc0da959b50df521.tar.gz |
Snap for 11066218 from f2c1cc94de204b9459eb4f108a27fb9e04c2fb08 to sdk-release
Change-Id: I48e984c1dbf1f05a269c9049715112fa0e495acc
72 files changed, 7117 insertions, 1599 deletions
diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..05e03be --- /dev/null +++ b/.gitattributes @@ -0,0 +1 @@ +src/Makefile.* linguist-language=Makefile diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml index 333f65a..6d24cf6 100644 --- a/.github/workflows/build.yaml +++ b/.github/workflows/build.yaml @@ -1,44 +1,96 @@ name: build on: - pull_request: {} + pull_request: + paths: + - '.github/workflows/build.yaml' + - 'docs/**' + - 'include/**' + - 'libbpf/**' + - 'src/**' push: branches: - master +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.after }} + cancel-in-progress: true + jobs: build: - runs-on: ubuntu-latest + strategy: + fail-fast: false + matrix: + os: [ubuntu-20.04, ubuntu-22.04] + runs-on: ${{ matrix.os }} + env: + FEATURES: .llvm and .skeletons + steps: - name: Checkout repository - uses: actions/checkout@ec3a7ce113134d7a93b817d10a8272cb61118579 + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 with: submodules: true + - name: Use clang-12 and not clang-11 for older Ubuntu + if: matrix.os == 'ubuntu-20.04' + run: | + sudo apt-get remove -y clang-11 llvm-11 + sudo update-alternatives --install /usr/bin/clang clang /usr/bin/clang-12 50 + - name: Install dependencies run: | sudo apt-get update sudo apt-get install -y \ - clang libbfd-dev libcap-dev libelf-dev python3-docutils + libbfd-dev libcap-dev libelf-dev libiberty-dev python3-docutils + # clang/LLVM are already installed, but we're missing some aliases. + CLANG_VERSION="$(echo '__clang_major__' | clang -E - | tail -n 1)" + sudo update-alternatives \ + --install /usr/bin/llvm-config llvm-config /usr/bin/llvm-config-"${CLANG_VERSION}" 50 \ + --slave /usr/bin/llvm-ar llvm-ar /usr/bin/llvm-ar-"${CLANG_VERSION}" \ + --slave /usr/bin/llvm-strip llvm-strip /usr/bin/llvm-strip-"${CLANG_VERSION}" + echo "CLANG_VERSION=${CLANG_VERSION}" >> "${GITHUB_ENV}" - - name: Build bpftool + - name: Build bpftool (default LLVM disassembler) run: | - make -j -C src + make -j -C src V=1 ./src/bpftool 2>&1 | grep -q Usage ./src/bpftool -p version | \ tee /dev/stderr | \ - jq --exit-status '.features | .libbfd and .libbpf_strict' + jq --exit-status ".features | ${FEATURES}" - name: Build bpftool, with clang run: | make -C src clean - LLVM=1 make -j -C src + LLVM=1 make -j -C src V=1 ./src/bpftool 2>&1 | grep -q Usage ./src/bpftool -p version | \ tee /dev/stderr | \ - jq --exit-status '.features | .libbfd and .libbpf_strict' + jq --exit-status ".features | ${FEATURES}" + + - name: Build bpftool, with fallback to libbfd disassembler + run: | + sudo apt-get remove -y llvm-"${CLANG_VERSION}"-dev + make -C src clean + make -j -C src V=1 + ./src/bpftool 2>&1 | grep -q Usage + ./src/bpftool -p version | \ + tee /dev/stderr | \ + jq --exit-status ".features | .libbfd and (.llvm | not)" + + - name: Build bpftool, with libbfd, static build + run: | + make -C src clean + EXTRA_CFLAGS=--static make -j -C src V=1 + ./src/bpftool 2>&1 | grep -q Usage + ./src/bpftool -p version | \ + tee /dev/stderr | \ + jq --exit-status ".features | .libbfd and (.llvm | not)" + ldd ./src/bpftool 2>&1 | \ + tee /dev/stderr | \ + grep -q 'not a dynamic executable' - name: Build bpftool's documentation run: | make -j -C docs - grep -q ".TH BPFTOOL 8" ./docs/bpftool.8 + grep -q '.TH "\?BPFTOOL"\? 8' ./docs/bpftool.8 diff --git a/.github/workflows/docker.yaml b/.github/workflows/docker.yaml new file mode 100644 index 0000000..9e62830 --- /dev/null +++ b/.github/workflows/docker.yaml @@ -0,0 +1,44 @@ +name: docker + +on: + pull_request: + paths: + - '.github/workflows/docker.yaml' + - 'Dockerfile' + - 'include/**' + - 'libbpf/**' + - 'src/**' + push: + branches: + - master + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.after }} + cancel-in-progress: true + +jobs: + dockerimage: + name: Docker image + runs-on: ubuntu-latest + steps: + - name: Checkout repository + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + with: + submodules: recursive + + - name: Build bpftool container image + uses: docker/build-push-action@3b5e8027fcad23fda98b2e3ac259d8d67585f671 # v4.0.0 + with: + push: false + tags: bpftool:latest + + - name: Test bpftool container image + run: | + docker run --rm --privileged --pid=host bpftool version + docker run --rm --privileged --pid=host bpftool prog + docker run --rm --privileged --pid=host bpftool map + + - name: Lint Docker image + uses: hadolint/hadolint-action@54c9adbab1582c2ef04b2016b760714a4bfde3cf # v3.1.0 + with: + dockerfile: Dockerfile diff --git a/.github/workflows/lint-commits.yaml b/.github/workflows/lint-commits.yaml new file mode 100644 index 0000000..8220313 --- /dev/null +++ b/.github/workflows/lint-commits.yaml @@ -0,0 +1,86 @@ +name: lint-commits + +on: + pull_request: + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number }} + cancel-in-progress: true + +jobs: + checkCommits: + name: check commits + runs-on: ubuntu-latest + steps: + - name: Checkout repository + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + with: + fetch-depth: 0 + + - name: Get list of commits + run: | + read PR_BASE PR_TIP < <(curl -L \ + -H "Accept: application/vnd.github.v3+json" \ + -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" \ + -H "X-GitHub-Api-Version: 2022-11-28" \ + ${{ github.event.pull_request.url }} | \ + tee /dev/stderr | \ + jq -r '"\(.base.sha) \(.head.sha)"' | \ + tee /dev/stderr) + echo "PR_TIP=${PR_TIP}" >> "${GITHUB_ENV}" + echo "PR_BASE=${PR_BASE}" >> "${GITHUB_ENV}" + + - name: Check commit prefixes + run: | + if [[ -z "${PR_TIP}" || -z "${PR_BASE}" ]]; then + echo "::error title=invalid base and head:: Failed to retrieve base and head for Pull Request" + # Fail workflow + false + fi + START_MARKER='sync: Update libbpf submodule' + END_MARKER='sync: Pull latest bpftool changes from kernel' + declare -a PREFIXES=( + "ci" + "mirror" + ) + + misformed=0 + syncing=0 + while read commit ; do + valid=1 + sha="${commit%% *}" + object="${commit#* }" + case "${object}" in + "${START_MARKER}") + syncing=1 + ;; + "${END_MARKER}") + syncing=0 + ;; + *) + if [[ "${syncing}" == 0 ]]; then + valid=0 + for prefix in "${PREFIXES[@]}"; do + if [[ "${object}" =~ ^"${prefix}: " ]]; then + valid=1 + break + fi + done + fi + ;; + esac + if [[ "${valid}" = 1 ]]; then + echo "::notice title=valid prefix::${sha} (\"${object}\") has a valid prefix" + else + echo "::error title=invalid prefix::${sha} (\"${object}\") does not have a valid prefix" + misformed=$((misformed+1)) + fi + done < <(git log --format='%h %s' --reverse ${{ env.PR_BASE }}..${{ env.PR_TIP }}) + + echo "::notice ::Found ${misformed} invalid commit object(s)" + if [[ "${misformed}" != 0 ]]; then + echo "Please ensure all commits not part of kernel sync are prefixed with one of:" + echo " ${PREFIXES[@]/%/:}" + # Fail workflow + false + fi diff --git a/.github/workflows/lint-shell.yaml b/.github/workflows/lint-shell.yaml new file mode 100644 index 0000000..68d1c0c --- /dev/null +++ b/.github/workflows/lint-shell.yaml @@ -0,0 +1,27 @@ +name: lint-shell + +on: + pull_request: + paths: + - '.github/workflows/lint-shell.yaml' + - 'scripts/**' + push: + branches: + - master + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.after }} + cancel-in-progress: true + +jobs: + shellcheck: + name: ShellCheck + runs-on: ubuntu-latest + steps: + - name: Checkout repository + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + + - name: Run ShellCheck + uses: ludeeus/action-shellcheck@00cae500b08a931fb5698e11e79bfbd38e612a38 # v2.0.0 + with: + scandir: './scripts' diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml new file mode 100644 index 0000000..69c00a4 --- /dev/null +++ b/.github/workflows/release.yaml @@ -0,0 +1,147 @@ +name: build and release + +on: + push: + tags: + - 'v[0-9]+.[0-9]+.[0-9]*' + +concurrency: + group: ${{ github.workflow }}-${{ github.event.after }} + cancel-in-progress: true + +env: + # https://github.com/llvm/llvm-project/releases/tag/llvmorg-15.0.0 + LLVM_URL_PREFIX: https://github.com/llvm/llvm-project/releases/download/llvmorg-15.0.0 + LLVM_arm64: clang+llvm-15.0.0-aarch64-linux-gnu + LLVM_amd64: clang+llvm-15.0.0-x86_64-linux-gnu-rhel-8.4 + +jobs: + build: + name: Build static bpftool binary + runs-on: ubuntu-22.04 + env: + TARGETARCH: ${{ matrix.arch }} + FILE_STRING_ARCH_amd64: x86-64 + FILE_STRING_ARCH_arm64: aarch64 + strategy: + matrix: + arch: [arm64, amd64] + + steps: + # amd64 needs the dependencies to build bpftool + - name: Install dependencies (amd64) + if: matrix.arch == 'amd64' + run: | + sudo apt-get update + sudo apt-get install -y libelf-dev libcap-dev + + - name: Download and extract compiled LLVM release + env: + LLVM: ${{ env[format('LLVM_{0}', matrix.arch)] }} + run: | + curl -L -O "${{ env.LLVM_URL_PREFIX}}/${{ env.LLVM }}.tar.xz" + tar -xvf "${{ env.LLVM }}.tar.xz" + + - name: Checkout bpftool code + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + with: + submodules: recursive + # Create a new directory to avoid wiping out LLVM on bpftool checkout + path: 'bpftool' + + - name: Build static bpftool natively for amd64 + if: matrix.arch == 'amd64' + working-directory: 'bpftool' + env: + LLVM_PATH: ${{ env[format('LLVM_{0}', matrix.arch)] }} + run: | + EXTRA_CFLAGS=--static \ + LLVM_CONFIG="${GITHUB_WORKSPACE}/${{ env.LLVM_PATH }}/bin/llvm-config" \ + LLVM_STRIP="${GITHUB_WORKSPACE}/${{ env.LLVM_PATH }}/bin/llvm-strip" \ + HOSTAR="${GITHUB_WORKSPACE}/${{ env.LLVM_PATH }}/bin/llvm-ar" \ + make -j -C src V=1 + strip src/bpftool + + - name: Set up QEMU + uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v2.1.0 + if: matrix.arch == 'arm64' + with: + platforms: arm64 + + # The emulated build leverages Docker and Ubuntu 22.04 container image + # distribution to have all the needed arm64 packages. + - name: Build static bpftool for arm64 with emulation + if: matrix.arch == 'arm64' + env: + LLVM_PATH: ${{ env[format('LLVM_{0}', matrix.arch)] }} + run: | + docker run --platform linux/arm64 --rm -v $(pwd):/build ubuntu:22.04 \ + bash -c "apt-get update && \ + apt-get install -y make pkg-config gcc \ + libelf-dev libcap-dev libstdc++-11-dev zlib1g-dev && \ + cd /build/bpftool && \ + EXTRA_CFLAGS=--static \ + LLVM_CONFIG='/build/${{ env.LLVM_PATH }}/bin/llvm-config' \ + LLVM_STRIP='/build/${{ env.LLVM_PATH }}/bin/llvm-strip' \ + CLANG='/build/${{ env.LLVM_PATH }}/bin/clang' \ + make -j -C src V=1 && \ + strip src/bpftool" + + - name: Test bpftool binary + working-directory: 'bpftool/src' + env: + ARCH: ${{ env[format('FILE_STRING_ARCH_{0}', matrix.arch)] }} + run: | + file ./bpftool | \ + tee /dev/stderr | \ + grep -q "${{ env.ARCH }}" + ./bpftool 2>&1 | grep -q Usage + ./bpftool -p version | \ + tee /dev/stderr | \ + jq --exit-status ".features | .llvm and .skeletons" + ldd ./bpftool 2>&1 | \ + tee /dev/stderr | \ + grep -q 'not a dynamic executable' + + - name: Upload Artifact + uses: actions/upload-artifact@0b7f8abb1508181956e8e162db84b466c27e18ce # v3.1.2 + with: + name: ${{ format('bpftool_{0}', matrix.arch) }} + path: bpftool/src/bpftool + + draft-release: + name: Create a draft release + runs-on: ubuntu-22.04 + needs: build + permissions: + contents: write + steps: + - name: Download artifacts from build + uses: actions/download-artifact@9bc31d5ccc31df68ecc42ccf4149144866c47d8a # v3.0.2 + + - name: Rename binaries and compress + run: | + archive_amd64="bpftool-${{ github.ref_name }}-amd64.tar.gz" + archive_arm64="bpftool-${{ github.ref_name }}-arm64.tar.gz" + tar -C bpftool_amd64 -I 'gzip -9' -cvf "${archive_amd64}" bpftool + tar -C bpftool_arm64 -I 'gzip -9' -cvf "${archive_arm64}" bpftool + sha256sum "${archive_amd64}" > "${archive_amd64}.sha256sum" + sha256sum "${archive_arm64}" > "${archive_arm64}.sha256sum" + + - name: Checkout bpftool and libbpf code + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + with: + submodules: recursive + path: 'bpftool' + + - name: Package source code including submodules + uses: qmonnet/git-archive-all-action@791fb850881cf58b1d1fcc9b06c01940080bba0a # v1.0.1 + with: + output-files: bpftool-libbpf-${{ github.ref_name }}-sources.tar.gz + base-repo: bpftool + + - name: Create draft release and add artifacts + uses: softprops/action-gh-release@de2c0eb89ae2a093876385947365aca7b0e5f844 # v0.1.15 + with: + draft: true + files: bpftool* diff --git a/.github/workflows/static-build.yaml b/.github/workflows/static-build.yaml new file mode 100644 index 0000000..5190295 --- /dev/null +++ b/.github/workflows/static-build.yaml @@ -0,0 +1,60 @@ +name: static LLVM build + +on: + pull_request: + paths: + - '.github/workflows/static-build.yaml' + - 'include/**' + - 'libbpf/**' + - 'src/**' + push: + branches: + - master + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.after }} + cancel-in-progress: true + +jobs: + build: + runs-on: ubuntu-22.04 + env: + LLVM_URL_PREFIX: https://github.com/llvm/llvm-project/releases/download/llvmorg-15.0.0 + LLVM_PATH: clang+llvm-15.0.0-x86_64-linux-gnu-rhel-8.4 + + steps: + - name: Install dependencies + run: | + sudo apt-get update + sudo apt-get install -y libelf-dev + + - name: Download and extract compiled LLVM release + run: | + curl -L -O "${{ env.LLVM_URL_PREFIX }}/${{ env.LLVM_PATH }}.tar.xz" + tar -xvf "${{ env.LLVM_PATH }}.tar.xz" + + - name: Checkout bpftool + uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 + with: + submodules: recursive + # Create a new directory to avoid wiping out LLVM on bpftool checkout + path: 'bpftool' + + - name: Build bpftool (static build, default LLVM disassembler) + working-directory: 'bpftool' + run: | + EXTRA_CFLAGS=--static \ + LLVM_CONFIG="${GITHUB_WORKSPACE}/${LLVM_PATH}/bin/llvm-config" \ + LLVM_STRIP="${GITHUB_WORKSPACE}/${LLVM_PATH}/bin/llvm-strip" \ + make -j -C src V=1 + + - name: Test bpftool binary + working-directory: 'bpftool' + run: | + ./src/bpftool 2>&1 | grep -q Usage + ./src/bpftool -p version | \ + tee /dev/stderr | \ + jq --exit-status ".features | .llvm" + ldd ./src/bpftool 2>&1 | \ + tee /dev/stderr | \ + grep -q 'not a dynamic executable' diff --git a/BPF-CHECKPOINT-COMMIT b/BPF-CHECKPOINT-COMMIT index 24171b2..70bb5d7 100644 --- a/BPF-CHECKPOINT-COMMIT +++ b/BPF-CHECKPOINT-COMMIT @@ -1 +1 @@ -fe68195daf34d5dddacd3f93dd3eafc4beca3a0e +9077fc228f09c9f975c498c55f5d2e882cd0da59 diff --git a/CHECKPOINT-COMMIT b/CHECKPOINT-COMMIT index af1a0c8..a196913 100644 --- a/CHECKPOINT-COMMIT +++ b/CHECKPOINT-COMMIT @@ -1 +1 @@ -dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca +2147c8d07e1abc8dfc3433ca18eed5295e230ede diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..730319c --- /dev/null +++ b/Dockerfile @@ -0,0 +1,39 @@ +# With this Dockerfile, you can create a container image: +# $ docker build -f Dockerfile -t bpftool . +# And then use it: +# $ docker run --rm -ti --privileged --pid=host bpftool prog + +# hadolint global ignore=DL3008 + +FROM ubuntu:22.04 as builder + +RUN \ + export DEBIAN_FRONTEND=noninteractive && \ + apt-get update && \ + apt-get -y install --no-install-recommends \ + build-essential \ + libelf-dev \ + libz-dev \ + libcap-dev \ + clang llvm llvm-dev lld \ + binutils-dev \ + pkg-config && \ + rm -rf /var/lib/apt/lists/* + +COPY . /src +RUN \ + make -C /src/src clean && \ + make -C /src/src -j "$(nproc)" + +FROM ubuntu:22.04 +RUN \ + export DEBIAN_FRONTEND=noninteractive && \ + apt-get update && \ + apt-get -y install --no-install-recommends \ + libelf1 \ + llvm && \ + rm -rf /var/lib/apt/lists/* + +COPY --from=builder /src/src/bpftool /bin/bpftool + +ENTRYPOINT ["/bin/bpftool"] @@ -9,11 +9,11 @@ third_party { type: GIT value: "https://github.com/libbpf/bpftool.git" } - version: "51d4a12c69c7339f60813b04fc9d0fd6154792a6" + version: "66c1c8b51826fc4cd0641e5b99d54f469a11f726" license_type: RESTRICTED last_upgrade_date { - year: 2022 - month: 2 - day: 10 + year: 2023 + month: 10 + day: 16 } } @@ -19,7 +19,7 @@ BPF/bpftool usage and questions Please check out [the manual pages](docs) for documentation about bpftool. A number of example invocations are also displayed in [this blog -post](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/bpf/bpftool). +post](https://qmonnet.github.io/whirl-offload/2021/09/23/bpftool-features-thread/). All general BPF questions, including kernel functionality, bpftool features and usage, should be sent to bpf@vger.kernel.org mailing list. You can subscribe to @@ -101,6 +101,46 @@ $ cd src $ make V=1 ``` +Additional compilation flags can be passed to the command line if required. For +example, we can create a static build with the following commands: + +```console +$ cd src +$ EXTRA_CFLAGS=--static make +``` + +Note that to use the LLVM disassembler with static builds, we need a static +version of the LLVM library installed on the system: + +1. Download a precompiled LLVM release or build it locally. + + - Download the appropriate + [release of LLVM](https://releases.llvm.org/download.html) for your + platform, for example on x86_64 with LLVM 15.0.0: + + ```console + $ curl -LO https://github.com/llvm/llvm-project/releases/download/llvmorg-15.0.0/clang+llvm-15.0.0-x86_64-linux-gnu-rhel-8.4.tar.xz + $ tar xvf clang+llvm-15.0.0-x86_64-linux-gnu-rhel-8.4.tar.xz + $ mv clang+llvm-15.0.0-x86_64-linux-gnu-rhel-8.4 llvm_build + ``` + + - Alternatively, clone and build the LLVM libraries locally. + + ```console + $ git clone https://github.com/llvm/llvm-project.git + $ mkdir llvm_build + $ cmake -S llvm-project/llvm -B llvm_build -DCMAKE_BUILD_TYPE=Release + $ make -j -C llvm_build llvm-config llvm-libraries + ``` + +2. Build bpftool with `EXTRA_CFLAGS` set to `--static`, and by passing the + path to the relevant `llvm-config`. + + ```console + $ cd bpftool + $ LLVM_CONFIG=../../llvm_build/bin/llvm-config EXTRA_CFLAGS=--static make -j -C src + ``` + ### Build bpftool's man pages The man pages for bpftool can be built with: diff --git a/bash-completion/bpftool b/bash-completion/bpftool index 493753a..085bf18 100644 --- a/bash-completion/bpftool +++ b/bash-completion/bpftool @@ -255,27 +255,30 @@ _bpftool_map_update_get_name() _bpftool() { - local cur prev words objword + local cur prev words objword json=0 _init_completion || return # Deal with options if [[ ${words[cword]} == -* ]]; then local c='--version --json --pretty --bpffs --mapcompat --debug \ - --use-loader --base-btf --legacy' + --use-loader --base-btf' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi + if _bpftool_search_list -j --json -p --pretty; then + json=1 + fi # Deal with simplest keywords case $prev in - help|hex|opcodes|visual|linum) + help|hex) return 0 ;; tag) _bpftool_get_prog_tags return 0 ;; - dev) + dev|offload_dev|xdpmeta_dev) _sysfs_get_netdevs return 0 ;; @@ -366,13 +369,16 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) + # "file" is not compatible with other keywords here + if _bpftool_search_list 'file'; then + return 0 + fi + if ! _bpftool_search_list 'linum opcodes visual'; then + _bpftool_once_attr 'file' + fi + _bpftool_once_attr 'linum opcodes' + if _bpftool_search_list 'xlated' && [[ "$json" == 0 ]]; then + _bpftool_once_attr 'visual' fi return 0 ;; @@ -407,8 +413,8 @@ _bpftool() return 0 ;; 5) - local BPFTOOL_PROG_ATTACH_TYPES='msg_verdict \ - skb_verdict stream_verdict stream_parser \ + local BPFTOOL_PROG_ATTACH_TYPES='sk_msg_verdict \ + sk_skb_verdict sk_skb_stream_verdict sk_skb_stream_parser \ flow_dissector' COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_ATTACH_TYPES" -- "$cur" ) ) return 0 @@ -502,9 +508,8 @@ _bpftool() ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) - _bpftool_once_attr 'type' - _bpftool_once_attr 'dev' - _bpftool_once_attr 'pinmaps' + _bpftool_once_attr 'type pinmaps autoattach' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' return 0 ;; esac @@ -703,15 +708,8 @@ _bpftool() return 0 ;; type) - local BPFTOOL_MAP_CREATE_TYPES='hash array \ - prog_array perf_event_array percpu_hash \ - percpu_array stack_trace cgroup_array lru_hash \ - lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap devmap_hash sockmap cpumap \ - xskmap sockhash cgroup_storage reuseport_sockarray \ - percpu_cgroup_storage queue stack sk_storage \ - struct_ops ringbuf inode_storage task_storage \ - bloom_filter' + local BPFTOOL_MAP_CREATE_TYPES="$(bpftool feature list_builtins map_types 2>/dev/null | \ + grep -v '^unspec$')" COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) return 0 ;; @@ -736,16 +734,10 @@ _bpftool() esac ;; *) - _bpftool_once_attr 'type' - _bpftool_once_attr 'key' - _bpftool_once_attr 'value' - _bpftool_once_attr 'entries' - _bpftool_once_attr 'name' - _bpftool_once_attr 'flags' + _bpftool_once_attr 'type key value entries name flags offload_dev' if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then _bpftool_once_attr 'inner_map' fi - _bpftool_once_attr 'dev' return 0 ;; esac @@ -886,8 +878,7 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'cpu' - _bpftool_once_attr 'index' + _bpftool_once_attr 'cpu index' return 0 ;; esac @@ -1003,9 +994,25 @@ _bpftool() ;; esac ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) + _filedir + return 0 + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'object skeleton help' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) ;; esac ;; @@ -1023,12 +1030,8 @@ _bpftool() return 0 ;; attach|detach) - local BPFTOOL_CGROUP_ATTACH_TYPES='ingress egress \ - sock_create sock_ops device \ - bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ - getpeername4 getpeername6 getsockname4 getsockname6 \ - sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt sock_release' + local BPFTOOL_CGROUP_ATTACH_TYPES="$(bpftool feature list_builtins attach_types 2>/dev/null | \ + grep '^cgroup_')" local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' # Check for $prev = $command first @@ -1157,9 +1160,14 @@ _bpftool() _bpftool_once_attr 'full unprivileged' return 0 ;; + list_builtins) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'prog_types map_types \ + attach_types link_types helpers' -- "$cur" ) ) + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'help probe' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'help list_builtins probe' -- "$cur" ) ) ;; esac ;; diff --git a/docs/bpftool-cgroup.rst b/docs/bpftool-cgroup.rst index a17e9aa..bd015ec 100644 --- a/docs/bpftool-cgroup.rst +++ b/docs/bpftool-cgroup.rst @@ -31,11 +31,17 @@ CGROUP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | -| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | -| **sock_release** } +| *ATTACH_TYPE* := { **cgroup_inet_ingress** | **cgroup_inet_egress** | +| **cgroup_inet_sock_create** | **cgroup_sock_ops** | +| **cgroup_device** | **cgroup_inet4_bind** | **cgroup_inet6_bind** | +| **cgroup_inet4_post_bind** | **cgroup_inet6_post_bind** | +| **cgroup_inet4_connect** | **cgroup_inet6_connect** | +| **cgroup_inet4_getpeername** | **cgroup_inet6_getpeername** | +| **cgroup_inet4_getsockname** | **cgroup_inet6_getsockname** | +| **cgroup_udp4_sendmsg** | **cgroup_udp6_sendmsg** | +| **cgroup_udp4_recvmsg** | **cgroup_udp6_recvmsg** | +| **cgroup_sysctl** | **cgroup_getsockopt** | **cgroup_setsockopt** | +| **cgroup_inet_sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION diff --git a/docs/bpftool-feature.rst b/docs/bpftool-feature.rst index 4ce9a77..e44039f 100644 --- a/docs/bpftool-feature.rst +++ b/docs/bpftool-feature.rst @@ -24,9 +24,11 @@ FEATURE COMMANDS ================ | **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature list_builtins** *GROUP* | **bpftool** **feature help** | | *COMPONENT* := { **kernel** | **dev** *NAME* } +| *GROUP* := { **prog_types** | **map_types** | **attach_types** | **link_types** | **helpers** } DESCRIPTION =========== @@ -70,6 +72,16 @@ DESCRIPTION The keywords **full**, **macros** and **prefix** have the same role as when probing the kernel. + **bpftool feature list_builtins** *GROUP* + List items known to bpftool. These can be BPF program types + (**prog_types**), BPF map types (**map_types**), attach types + (**attach_types**), link types (**link_types**), or BPF helper + functions (**helpers**). The command does not probe the system, but + simply lists the elements that bpftool knows from compilation time, + as provided from libbpf (for all object types) or from the BPF UAPI + header (list of helpers). This can be used in scripts to iterate over + BPF types or helpers. + **bpftool feature help** Print short help message. diff --git a/docs/bpftool-gen.rst b/docs/bpftool-gen.rst index bc27638..5006e72 100644 --- a/docs/bpftool-gen.rst +++ b/docs/bpftool-gen.rst @@ -25,6 +25,8 @@ GEN COMMANDS | **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] | **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] | **bpftool** **gen help** DESCRIPTION @@ -149,6 +151,50 @@ DESCRIPTION (non-read-only) data from userspace, with same simplicity as for BPF side. + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given + *INPUT* BTF file, containing all needed BTF types so one, or + more, given eBPF objects CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, + libbpf, when loading an eBPF object, has to rely on external + BTF files to be able to calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel + DWARF data using pahole. It contains all the types used by + its respective kernel image and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized + to one or multiple eBPF objects, so they can be distributed + together with an eBPF CO-RE based application, turning the + application portable to different kernel versions. + + Check examples bellow for more information how to use it. + **bpftool gen help** Print short help message. @@ -214,8 +260,10 @@ EXAMPLES This is example BPF application with two BPF programs and a mix of BPF maps and global variables. Source code is split across two source code files. -**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o** -**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o** +**$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o** + +**$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o** + **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** This set of commands compiles *example1.bpf.c* and *example2.bpf.c* @@ -329,3 +377,70 @@ BPF ELF object file *example.bpf.o*. my_static_var: 7 This is a stripped-out version of skeleton generated for above example code. + +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/docs/bpftool-map.rst b/docs/bpftool-map.rst index 7c188a5..3b7ba03 100644 --- a/docs/bpftool-map.rst +++ b/docs/bpftool-map.rst @@ -28,7 +28,7 @@ MAP COMMANDS | **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ | **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ -| [**dev** *NAME*] +| [**offload_dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* [**key** *DATA*] @@ -55,7 +55,7 @@ MAP COMMANDS | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** -| | **task_storage** | **bloom_filter** } +| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** } DESCRIPTION =========== @@ -73,7 +73,7 @@ DESCRIPTION maps. On such kernels bpftool will automatically emit this information as well. - **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**offload_dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -86,8 +86,8 @@ DESCRIPTION kernel needs it to collect metadata related to the inner maps that the new map will work with. - Keyword **dev** expects a network interface name, and is used - to request hardware offload for the map. + Keyword **offload_dev** expects a network interface name, + and is used to request hardware offload for the map. **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, diff --git a/docs/bpftool-net.rst b/docs/bpftool-net.rst index f4e0a51..5e2abd3 100644 --- a/docs/bpftool-net.rst +++ b/docs/bpftool-net.rst @@ -4,7 +4,7 @@ bpftool-net ================ ------------------------------------------------------------------------------- -tool for inspection of netdev/tc related bpf prog attachments +tool for inspection of networking related bpf prog attachments ------------------------------------------------------------------------------- :Manual section: 8 @@ -37,10 +37,13 @@ DESCRIPTION **bpftool net { show | list }** [ **dev** *NAME* ] List bpf program attachments in the kernel networking subsystem. - Currently, only device driver xdp attachments and tc filter - classification/action attachments are implemented, i.e., for - program types **BPF_PROG_TYPE_SCHED_CLS**, - **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. + Currently, device driver xdp attachments, tcx and old-style tc + classifier/action attachments, flow_dissector as well as netfilter + attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT**, **BPF_PROG_TYPE_FLOW_DISSECTOR**, + **BPF_PROG_TYPE_NETFILTER**. + For programs attached to a particular cgroup, e.g., **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, @@ -49,12 +52,13 @@ DESCRIPTION bpf programs, users should consult other tools, e.g., iproute2. The current output will start with all xdp program attachments, followed by - all tc class/qdisc bpf program attachments. Both xdp programs and - tc programs are ordered based on ifindex number. If multiple bpf - programs attached to the same networking device through **tc filter**, - the order will be first all bpf programs attached to tc classes, then - all bpf programs attached to non clsact qdiscs, and finally all - bpf programs attached to root and clsact qdisc. + all tcx, then tc class/qdisc bpf program attachments, then flow_dissector + and finally netfilter programs. Both xdp programs and tcx/tc programs are + ordered based on ifindex number. If multiple bpf programs attached + to the same networking device through **tc**, the order will be first + all bpf programs attached to tcx, then tc classes, then all bpf programs + attached to non clsact qdiscs, and finally all bpf programs attached + to root and clsact qdisc. **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] Attach bpf program *PROG* to network interface *NAME* with diff --git a/docs/bpftool-prog.rst b/docs/bpftool-prog.rst index a2e9359..dcae81b 100644 --- a/docs/bpftool-prog.rst +++ b/docs/bpftool-prog.rst @@ -28,10 +28,10 @@ PROG COMMANDS ============= | **bpftool** **prog** { **show** | **list** } [*PROG*] -| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] -| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] +| **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] +| **bpftool** **prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -53,8 +53,9 @@ PROG COMMANDS | **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } -| *ATTACH_TYPE* := { -| **msg_verdict** | **skb_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** +| *ATTACH_TYPE* := { +| **sk_msg_verdict** | **sk_skb_verdict** | **sk_skb_stream_verdict** | +| **sk_skb_stream_parser** | **flow_dissector** | } | *METRICs* := { | **cycles** | **instructions** | **l1d_loads** | **llc_misses** | @@ -87,7 +88,7 @@ DESCRIPTION programs. On such kernels bpftool will automatically emit this information as well. - **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] Dump eBPF instructions of the programs from the kernel. By default, eBPF will be disassembled and printed to standard output in human-readable format. In this case, **opcodes** @@ -105,11 +106,10 @@ DESCRIPTION CFG in DOT format, on standard output. If the programs have line_info available, the source line will - be displayed by default. If **linum** is specified, - the filename, line number and line column will also be - displayed on top of the source line. + be displayed. If **linum** is specified, the filename, line + number and line column will also be displayed. - **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] + **bpftool prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] Dump jited image (host machine code) of the program. If *FILE* is specified image will be written to a file, @@ -119,9 +119,8 @@ DESCRIPTION **opcodes** controls if raw opcodes will be printed. If the prog has line_info available, the source line will - be displayed by default. If **linum** is specified, - the filename, line number and line column will also be - displayed on top of the source line. + be displayed. If **linum** is specified, the filename, line + number and line column will also be displayed. **bpftool prog pin** *PROG* *FILE* Pin program *PROG* as *FILE*. @@ -130,7 +129,7 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog loadall** pins all programs @@ -144,11 +143,25 @@ DESCRIPTION to be replaced in the ELF file counting from 0, while *NAME* allows to replace a map by name. *MAP* specifies the map to use, referring to it by **id** or through a **pinned** file. - If **dev** *NAME* is specified program will be loaded onto - given networking device (offload). + If **offload_dev** *NAME* is specified program will be loaded + onto given networking device (offload). + If **xdpmeta_dev** *NAME* is specified program will become + device-bound without offloading, this facilitates access + to XDP metadata. Optional **pinmaps** argument can be provided to pin all maps under *MAP_DIR* directory. + If **autoattach** is specified program will be attached + before pin. In that case, only the link (representing the + program attached to its hook) is pinned, not the program as + such, so the path won't show in **bpftool prog show -f**, + only show in **bpftool link show -f**. Also, this only works + when bpftool (libbpf) is able to infer all necessary + information from the object file, in particular, it's not + supported for all program types. If a program does not + support autoattach, bpftool falls back to regular pinning + for that program instead. + Note: *PATH* must be located in *bpffs* mount. It must not contain a dot character ('.'), which is reserved for future extensions of *bpffs*. diff --git a/docs/bpftool-struct_ops.rst b/docs/bpftool-struct_ops.rst index ee53a12..8022b53 100644 --- a/docs/bpftool-struct_ops.rst +++ b/docs/bpftool-struct_ops.rst @@ -26,7 +26,7 @@ STRUCT_OPS COMMANDS | **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*] | **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*] -| **bpftool** **struct_ops register** *OBJ* +| **bpftool** **struct_ops register** *OBJ* [*LINK_DIR*] | **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP* | **bpftool** **struct_ops help** | @@ -51,10 +51,14 @@ DESCRIPTION for the given struct_ops. Otherwise, it dumps all struct_ops currently existing in the system. - **bpftool struct_ops register** *OBJ* + **bpftool struct_ops register** *OBJ* [*LINK_DIR*] Register bpf struct_ops from *OBJ*. All struct_ops under - the ELF section ".struct_ops" will be registered to - its kernel subsystem. + the ELF section ".struct_ops" and ".struct_ops.link" will + be registered to its kernel subsystem. For each + struct_ops in the ".struct_ops.link" section, a link + will be created. You can give *LINK_DIR* to provide a + directory path where these links will be pinned with the + same name as their corresponding map name. **bpftool struct_ops unregister** *STRUCT_OPS_MAP* Unregister the *STRUCT_OPS_MAP* from the kernel subsystem. diff --git a/docs/bpftool.rst b/docs/bpftool.rst index 7084dd9..6965c94 100644 --- a/docs/bpftool.rst +++ b/docs/bpftool.rst @@ -20,7 +20,8 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } + *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } @@ -31,6 +32,8 @@ SYNOPSIS *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **attach** | **detach** | **help** } + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } *PERF-COMMANDS* := { **show** | **list** | **help** } @@ -39,6 +42,14 @@ SYNOPSIS *FEATURE-COMMANDS* := { **probe** | **help** } + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects diff --git a/docs/common_options.rst b/docs/common_options.rst index 908487b..30df7a7 100644 --- a/docs/common_options.rst +++ b/docs/common_options.rst @@ -4,12 +4,13 @@ Print short help message (similar to **bpftool help**). -V, --version - Print version number (similar to **bpftool version**), and optional - features that were included when bpftool was compiled. Optional - features include linking against libbfd to provide the disassembler - for JIT-ted programs (**bpftool prog dump jited**) and usage of BPF - skeletons (some features like **bpftool prog profile** or showing - pids associated to BPF objects may rely on it). + Print bpftool's version number (similar to **bpftool version**), the + number of the libbpf version in use, and optional features that were + included when bpftool was compiled. Optional features include linking + against LLVM or libbfd to provide the disassembler for JIT-ted + programs (**bpftool prog dump jited**) and usage of BPF skeletons + (some features like **bpftool prog profile** or showing pids + associated to BPF objects may rely on it). -j, --json Generate JSON output. For commands that cannot produce JSON, this @@ -22,12 +23,3 @@ Print all logs available, even debug-level information. This includes logs from libbpf as well as from the verifier, when attempting to load programs. - --l, --legacy - Use legacy libbpf mode which has more relaxed BPF program - requirements. By default, bpftool has more strict requirements - about section names, changes pinning logic and doesn't support - some of the older non-BTF map declarations. - - See https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0 - for details. diff --git a/docs/substitutions.rst b/docs/substitutions.rst index ccf1ffa..827e3ff 100644 --- a/docs/substitutions.rst +++ b/docs/substitutions.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -.. |COMMON_OPTIONS| replace:: { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | { **-l** | **--legacy** } +.. |COMMON_OPTIONS| replace:: { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e7f6808..8d22d29 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -13,6 +13,12 @@ + __GNUC_PATCHLEVEL__) #endif +#if __has_attribute(__fallthrough__) +# define fallthrough __attribute__((__fallthrough__)) +#else +# define fallthrough do {} while (0) /* fallthrough */ +#endif + #if __has_attribute(__error__) # define __compiletime_error(message) __attribute__((error(message))) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 138edc4..f256caf 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -45,4 +45,12 @@ .off = OFF, \ .imm = IMM }) +#define BPF_EMIT_CALL(FUNC) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = ((FUNC) - BPF_FUNC_unspec) }) + #endif diff --git a/include/tools/dis-asm-compat.h b/include/tools/dis-asm-compat.h new file mode 100644 index 0000000..70f331e --- /dev/null +++ b/include/tools/dis-asm-compat.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +#ifndef _TOOLS_DIS_ASM_COMPAT_H +#define _TOOLS_DIS_ASM_COMPAT_H + +#include <stdio.h> +#include <dis-asm.h> + +/* define types for older binutils version, to centralize ifdef'ery a bit */ +#ifndef DISASM_INIT_STYLED +enum disassembler_style {DISASSEMBLER_STYLE_NOT_EMPTY}; +typedef int (*fprintf_styled_ftype) (void *, enum disassembler_style, const char*, ...); +#endif + +/* + * Trivial fprintf wrapper to be used as the fprintf_styled_func argument to + * init_disassemble_info_compat() when normal fprintf suffices. + */ +static inline int fprintf_styled(void *out, + enum disassembler_style style, + const char *fmt, ...) +{ + va_list args; + int r; + + (void)style; + + va_start(args, fmt); + r = vfprintf(out, fmt, args); + va_end(args); + + return r; +} + +/* + * Wrapper for init_disassemble_info() that hides version + * differences. Depending on binutils version and architecture either + * fprintf_func or fprintf_styled_func will be called. + */ +static inline void init_disassemble_info_compat(struct disassemble_info *info, + void *stream, + fprintf_ftype unstyled_func, + fprintf_styled_ftype styled_func) +{ +#ifdef DISASM_INIT_STYLED + init_disassemble_info(info, stream, + unstyled_func, + styled_func); +#else + (void)styled_func; + init_disassemble_info(info, stream, + unstyled_func); +#endif +} + +#endif /* _TOOLS_DIS_ASM_COMPAT_H */ diff --git a/include/tools/libc_compat.h b/include/tools/libc_compat.h deleted file mode 100644 index 327961d..0000000 --- a/include/tools/libc_compat.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ - -#ifndef __TOOLS_LIBC_COMPAT_H -#define __TOOLS_LIBC_COMPAT_H - -#include <limits.h> -#include <stdlib.h> - -#ifndef unlikely -#define unlikely(x) __builtin_expect(!!(x), 0) -#endif - -#ifndef __has_builtin -#define __has_builtin(x) 0 -#endif - -/* - * Re-implement glibc's reallocarray(). This function is not available in all - * versions of glibc. The version of bpftool shipped with the kernel deals with - * this by doing an extra feature detection, and by using a stub in - * <tools/libc_compat.h> (this file) when COMPAT_NEED_REALLOCARRAY is set. - * Let's keep things simple here: it is trivial to re-implement the function. - * Libbpf does the same in libbpf_internal.h: we can copy its version. - */ -static inline void *bpftool_reallocarray(void *ptr, size_t nmemb, size_t size) -{ - size_t total; - -#if __has_builtin(__builtin_mul_overflow) - if (unlikely(__builtin_mul_overflow(nmemb, size, &total))) - return NULL; -#else - if (size == 0 || nmemb > ULONG_MAX / size) - return NULL; - total = nmemb * size; -#endif - return realloc(ptr, total); -} - -/* - * Overwrite default reallocarray(). It would probably be cleaner to use - * "bpftool_reallocarray()" in the source code to make the distinction - * explicit, but we want to avoid touching the code to remain in sync with the - * kernel and ease maintenance. - */ -#define reallocarray(ptr, nmemb, size) bpftool_reallocarray(ptr, nmemb, size) - -#endif diff --git a/include/uapi/asm-generic/bitsperlong.h b/include/uapi/asm-generic/bitsperlong.h index 23e6c41..352cb81 100644 --- a/include/uapi/asm-generic/bitsperlong.h +++ b/include/uapi/asm-generic/bitsperlong.h @@ -1,6 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG #define _UAPI__ASM_GENERIC_BITS_PER_LONG +#ifndef __BITS_PER_LONG +/* + * In order to keep safe and avoid regression, only unify uapi + * bitsperlong.h for some archs which are using newer toolchains + * that have the definitions of __CHAR_BIT__ and __SIZEOF_LONG__. + * See the following link for more info: + * https://lore.kernel.org/linux-arch/b9624545-2c80-49a1-ac3c-39264a591f7b@app.fastmail.com/ + */ +#if defined(__CHAR_BIT__) && defined(__SIZEOF_LONG__) +#define __BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__) +#else /* * There seems to be no way of detecting this automatically from user * space, so 64 bit architectures should override this in their @@ -8,8 +20,8 @@ * both 32 and 64 bit user space must not rely on CONFIG_64BIT * to decide it, but rather check a compiler provided macro. */ -#ifndef __BITS_PER_LONG #define __BITS_PER_LONG 32 #endif +#endif #endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7f0dde..70bfa99 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -19,6 +19,7 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_MEMSX 0x80 /* load with sign extension */ #define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ #define BPF_XADD 0xc0 /* exclusive add - legacy name */ @@ -87,10 +88,35 @@ struct bpf_cgroup_storage_key { __u32 attach_type; /* program attach type (enum bpf_attach_type) */ }; +enum bpf_cgroup_iter_order { + BPF_CGROUP_ITER_ORDER_UNSPEC = 0, + BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */ + BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */ + BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */ + BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */ +}; + union bpf_iter_link_info { struct { __u32 map_fd; } map; + struct { + enum bpf_cgroup_iter_order order; + + /* At most one of cgroup_fd and cgroup_id can be non-zero. If + * both are zero, the walk starts from the default cgroup v2 + * root. For walking v1 hierarchy, one should always explicitly + * specify cgroup_fd. + */ + __u32 cgroup_fd; + __u64 cgroup_id; + } cgroup; + /* Parameters of task iterators. */ + struct { + __u32 tid; + __u32 pid; + __u32 pid_fd; + } task; }; /* BPF syscall commands, see bpf(2) man-page for more details. */ @@ -897,9 +923,23 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs + * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE + + * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * deprecated. + */ + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, @@ -909,6 +949,8 @@ enum bpf_map_type { BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, + BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -952,6 +994,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ + BPF_PROG_TYPE_NETFILTER, }; enum bpf_attach_type { @@ -997,6 +1040,13 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, + BPF_STRUCT_OPS, + BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,10 +1061,24 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, - + BPF_LINK_TYPE_KPROBE_MULTI = 8, + BPF_LINK_TYPE_STRUCT_OPS = 9, + BPF_LINK_TYPE_NETFILTER = 10, + BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, MAX_BPF_LINK_TYPE, }; +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -1061,7 +1125,12 @@ enum bpf_link_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ #define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -1070,7 +1139,7 @@ enum bpf_link_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) -/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will allow any alignment whatsoever. On platforms * with strict alignment requirements for loads ands stores (such * as sparc and mips) the verifier validates that all loads and @@ -1118,6 +1187,30 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_UPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1218,13 +1311,19 @@ enum { /* Create a map that is suitable to be an inner map with dynamic max entries */ BPF_F_INNER_MAP = (1U << 12), + +/* Create a map that will be registered/unregesitered by the backed bpf_link */ + BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ /* Query effective (directly attached + inherited from ancestor cgroups) * programs that will be executed for events within a cgroup. - * attach_flags with this flag are returned only for directly attached programs. + * attach_flags with this flag are always returned 0. */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -1232,6 +1331,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1353,23 +1454,40 @@ union bpf_attr { __aligned_u64 fd_array; /* array of FDs */ __aligned_u64 core_relos; __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 log_true_size; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; __u32 attach_type; __u32 attach_flags; - __u32 replace_bpf_fd; /* previously attached eBPF - * program to replace if - * BPF_F_REPLACE is used - */ + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -1393,6 +1511,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1414,12 +1533,26 @@ union bpf_attr { } info; struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __u32 target_fd; /* container object to query */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; __u32 query_flags; __u32 attach_flags; __aligned_u64 prog_ids; - __u32 prog_cnt; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; + /* output: per-program attach_flags. + * not allowed to be set during effective query. + */ + __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -1433,6 +1566,11 @@ union bpf_attr { __u32 btf_size; __u32 btf_log_size; __u32 btf_log_level; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 btf_log_true_size; }; struct { @@ -1452,15 +1590,18 @@ union bpf_attr { } task_fd_query; struct { /* struct used by BPF_LINK_CREATE command */ - __u32 prog_fd; /* eBPF program to attach */ union { - __u32 target_fd; /* object to attach to */ - __u32 target_ifindex; /* target ifindex */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 map_fd; /* struct_ops to attach */ + }; + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ union { - __u32 target_btf_id; /* btf_id of target to attach to */ + __u32 target_btf_id; /* btf_id of target to attach to */ struct { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ @@ -1472,17 +1613,66 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; + struct { + /* this is overlaid with the target_btf_id above. */ + __u32 target_btf_id; + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 cookie; + } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 cnt; + __u32 flags; + __u32 pid; + } uprobe_multi; }; } link_create; struct { /* struct used by BPF_LINK_UPDATE command */ __u32 link_fd; /* link fd */ - /* new program fd to update link with */ - __u32 new_prog_fd; + union { + /* new program fd to update link with */ + __u32 new_prog_fd; + /* new struct_ops map fd to update link with */ + __u32 new_map_fd; + }; __u32 flags; /* extra flags */ - /* expected link's program fd; is specified only if - * BPF_F_REPLACE flag is set in flags */ - __u32 old_prog_fd; + union { + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags. + */ + __u32 old_prog_fd; + /* expected link's map fd; is specified only + * if BPF_F_REPLACE flag is set. + */ + __u32 old_map_fd; + }; } link_update; struct { @@ -1576,17 +1766,17 @@ union bpf_attr { * Description * This helper is a "printk()-like" facility for debugging. It * prints a message defined by format *fmt* (of size *fmt_size*) - * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * to file *\/sys/kernel/tracing/trace* from TraceFS, if * available. It can take up to three additional **u64** * arguments (as an eBPF helpers, the total number of arguments is * limited to five). * * Each time the helper is called, it appends a line to the trace. - * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is - * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. + * Lines are discarded while *\/sys/kernel/tracing/trace* is + * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this. * The format of the trace is customizable, and the exact output * one will get depends on the options set in - * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *\/sys/kernel/tracing/trace_options* (see also the * *README* file under the same directory). However, it usually * defaults to something like: * @@ -1779,7 +1969,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description @@ -1935,6 +2127,9 @@ union bpf_attr { * sending the packet. This flag was added for GRE * encapsulation, but might be used with other protocols * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. * * Here is a typical usage on the transmit path: * @@ -2299,8 +2494,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -2332,7 +2527,8 @@ union bpf_attr { * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes * from *skb* readable and writable. If a zero value is passed for - * *len*, then the whole length of the *skb* is pulled. + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. * * This helper is only needed for reading and writing with direct * packet access. @@ -2517,14 +2713,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -2543,10 +2744,12 @@ union bpf_attr { * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). + * (room space is added or removed between the layer 2 and + * layer 3 headers). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). + * (room space is added or removed between the layer 3 and + * layer 4 headers). * * The following flags are supported at this time: * @@ -2570,6 +2773,11 @@ union bpf_attr { * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the * L2 type as Ethernet. * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -2578,7 +2786,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -2714,7 +2922,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see @@ -2739,12 +2947,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * @@ -2978,8 +3184,18 @@ union bpf_attr { * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. * **BPF_F_USER_BUILD_ID** - * Collect buildid+offset instead of ips for user stack, - * only valid if **BPF_F_USER_STACK** is also specified. + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. * * **bpf_get_stack**\ () can collect up to * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject @@ -2992,8 +3208,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack=<new value> * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -3036,9 +3252,18 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -3570,10 +3795,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3756,10 +3982,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -4006,9 +4233,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This @@ -4299,8 +4523,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack=<new value> * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description @@ -4393,7 +4617,7 @@ union bpf_attr { * * **-EEXIST** if the option already exists. * - * **-EFAULT** on failrue to parse the existing header options. + * **-EFAULT** on failure to parse the existing header options. * * **-EPERM** if the helper cannot be used under the current * *skops*\ **->op**. @@ -4602,7 +4826,7 @@ union bpf_attr { * a *map* with *task* as the **key**. From this * perspective, the usage is not much different from * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this - * helper enforces the key must be an task_struct and the map must also + * helper enforces the key must be a task_struct and the map must also * be a **BPF_MAP_TYPE_TASK_STORAGE**. * * Underneath, the value is stored locally at *task* instead of @@ -4660,7 +4884,7 @@ union bpf_attr { * * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) * Description - * Returns the stored IMA hash of the *inode* (if it's avaialable). + * Returns the stored IMA hash of the *inode* (if it's available). * If the hash is larger than *size*, then only *size* * bytes will be copied to *dst* * Return @@ -4684,12 +4908,12 @@ union bpf_attr { * * The argument *len_diff* can be used for querying with a planned * size change. This allows to check MTU prior to changing packet - * ctx. Providing an *len_diff* adjustment that is larger than the + * ctx. Providing a *len_diff* adjustment that is larger than the * actual packet size (resulting in negative packet size) will in - * principle not exceed the MTU, why it is not considered a - * failure. Other BPF-helpers are needed for performing the - * planned size change, why the responsability for catch a negative - * packet size belong in those helpers. + * principle not exceed the MTU, which is why it is not considered + * a failure. Other BPF helpers are needed for performing the + * planned size change; therefore the responsibility for catching + * a negative packet size belongs in those helpers. * * Specifying *ifindex* zero means the MTU check is performed * against the current net device. This is practical if this isn't @@ -4867,6 +5091,12 @@ union bpf_attr { * different maps if key/value layout matches across maps. * Every bpf_timer_set_callback() can have different callback_fn. * + * *flags* can be one of: + * + * **BPF_F_TIMER_ABS** + * Start the timer in absolute expire value instead of the + * default relative one. + * * Return * 0 on success. * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier @@ -4885,8 +5115,14 @@ union bpf_attr { * u64 bpf_get_func_ip(void *ctx) * Description * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * * Return - * Address of the traced function. + * Address of the traced function for kprobe. + * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. * * u64 bpf_get_attach_cookie(void *ctx) * Description @@ -5016,12 +5252,12 @@ union bpf_attr { * * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) * Description - * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * Get **n**-th argument register (zero based) of the traced function (for tracing programs) * returned in **value**. * * Return * 0 on success. - * **-EINVAL** if n >= arguments count of traced function. + * **-EINVAL** if n >= argument register count of traced function. * * long bpf_get_func_ret(void *ctx, u64 *value) * Description @@ -5034,24 +5270,37 @@ union bpf_attr { * * long bpf_get_func_arg_cnt(void *ctx) * Description - * Get number of arguments of the traced function (for tracing programs). + * Get number of registers of the traced function (for tracing programs) where + * function arguments are stored in these registers. * * Return - * The number of arguments of the traced function. + * The number of argument registers of the traced function. * * int bpf_get_retval(void) * Description - * Get the syscall's return value that will be returned to userspace. + * Get the BPF program's return value that will be returned to the upper layers. * - * This helper is currently supported by cgroup programs only. + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. * Return - * The syscall's return value. + * The BPF program's return value. * * int bpf_set_retval(int retval) * Description - * Set the syscall's return value that will be returned to userspace. + * Set the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Note that there is the following corner case where the program exports an error + * via bpf_set_retval but signals success via 'return 1': + * + * bpf_set_retval(-EPERM); + * return 1; + * + * In this case, the BPF program's return value will use helper's -EPERM. This + * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case. * - * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. * @@ -5086,208 +5335,548 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. + * + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) + * Description + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. + * + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp + * instead. + * + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. + * + * void *bpf_kptr_xchg(void *map_value, void *ptr) + * Description + * Exchange kptr at pointer *map_value* with *ptr*, and return the + * old value. *ptr* can be NULL, otherwise it must be a referenced + * pointer which will be released when this helper is called. + * Return + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. + * + * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu) + * Description + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * Return + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. + * + * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. + * + * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * Return + * 0 on success, or a negative error in case of failure. + * + * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * Return + * Nothing. Always succeeds. + * + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) + * Description + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. + * + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * Description + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * + * *flags* must be 0 except for skb-type dynptrs. + * + * For skb-type dynptrs: + * * All data slices of the dynptr are automatically + * invalidated after **bpf_dynptr_write**\ (). This is + * because writing may pull the skb and change the + * underlying packet buffer. + * + * * For *flags*, please see the flags accepted by + * **bpf_skb_store_bytes**\ (). + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, + * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). + * + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) + * Description + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * + * skb and xdp type dynptrs may not use bpf_dynptr_data. They should + * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr. + * Return + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * + * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags) + * Description + * Drain samples from the specified user ring buffer, and invoke + * the provided callback for each such sample: + * + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); + * + * If **callback_fn** returns 0, the helper will continue to try + * and drain the next sample, up to a maximum of + * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, + * the helper will skip the rest of the samples and return. Other + * return values are not used now, and will be rejected by the + * verifier. + * Return + * The number of drained samples if no error was encountered while + * draining samples, or 0 if no samples were present in the ring + * buffer. If a user-space producer was epoll-waiting on this map, + * and at least one sample was drained, they will receive an event + * notification notifying them of available space in the ring + * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this + * function, no wakeup notification will be sent. If the + * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will + * be sent even if no sample was drained. + * + * On failure, the returned value is one of the following: + * + * **-EBUSY** if the ring buffer is contended, and another calling + * context was concurrently draining the ring buffer. + * + * **-EINVAL** if user-space is not properly tracking the ring + * buffer due to the producer position not being aligned to 8 + * bytes, a sample not being aligned to 8 bytes, or the producer + * position not matching the advertised length of a sample. + * + * **-E2BIG** if user-space has tried to publish a sample which is + * larger than the size of the ring buffer, or which cannot fit + * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ -#define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - FN(redirect_map), \ - FN(sk_redirect_map), \ - FN(sock_map_update), \ - FN(xdp_adjust_meta), \ - FN(perf_event_read_value), \ - FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), \ - FN(sock_ops_cb_flags_set), \ - FN(msg_redirect_map), \ - FN(msg_apply_bytes), \ - FN(msg_cork_bytes), \ - FN(msg_pull_data), \ - FN(bind), \ - FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), \ - FN(get_stack), \ - FN(skb_load_bytes_relative), \ - FN(fib_lookup), \ - FN(sock_hash_update), \ - FN(msg_redirect_hash), \ - FN(sk_redirect_hash), \ - FN(lwt_push_encap), \ - FN(lwt_seg6_store_bytes), \ - FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), \ - FN(rc_repeat), \ - FN(rc_keydown), \ - FN(skb_cgroup_id), \ - FN(get_current_cgroup_id), \ - FN(get_local_storage), \ - FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), \ - FN(sk_lookup_tcp), \ - FN(sk_lookup_udp), \ - FN(sk_release), \ - FN(map_push_elem), \ - FN(map_pop_elem), \ - FN(map_peek_elem), \ - FN(msg_push_data), \ - FN(msg_pop_data), \ - FN(rc_pointer_rel), \ - FN(spin_lock), \ - FN(spin_unlock), \ - FN(sk_fullsock), \ - FN(tcp_sock), \ - FN(skb_ecn_set_ce), \ - FN(get_listener_sock), \ - FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), \ - FN(sysctl_get_name), \ - FN(sysctl_get_current_value), \ - FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), \ - FN(strtol), \ - FN(strtoul), \ - FN(sk_storage_get), \ - FN(sk_storage_delete), \ - FN(send_signal), \ - FN(tcp_gen_syncookie), \ - FN(skb_output), \ - FN(probe_read_user), \ - FN(probe_read_kernel), \ - FN(probe_read_user_str), \ - FN(probe_read_kernel_str), \ - FN(tcp_send_ack), \ - FN(send_signal_thread), \ - FN(jiffies64), \ - FN(read_branch_records), \ - FN(get_ns_current_pid_tgid), \ - FN(xdp_output), \ - FN(get_netns_cookie), \ - FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), \ - FN(ktime_get_boot_ns), \ - FN(seq_printf), \ - FN(seq_write), \ - FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), \ - FN(ringbuf_output), \ - FN(ringbuf_reserve), \ - FN(ringbuf_submit), \ - FN(ringbuf_discard), \ - FN(ringbuf_query), \ - FN(csum_level), \ - FN(skc_to_tcp6_sock), \ - FN(skc_to_tcp_sock), \ - FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), \ - FN(get_task_stack), \ - FN(load_hdr_opt), \ - FN(store_hdr_opt), \ - FN(reserve_hdr_opt), \ - FN(inode_storage_get), \ - FN(inode_storage_delete), \ - FN(d_path), \ - FN(copy_from_user), \ - FN(snprintf_btf), \ - FN(seq_printf_btf), \ - FN(skb_cgroup_classid), \ - FN(redirect_neigh), \ - FN(per_cpu_ptr), \ - FN(this_cpu_ptr), \ - FN(redirect_peer), \ - FN(task_storage_get), \ - FN(task_storage_delete), \ - FN(get_current_task_btf), \ - FN(bprm_opts_set), \ - FN(ktime_get_coarse_ns), \ - FN(ima_inode_hash), \ - FN(sock_from_file), \ - FN(check_mtu), \ - FN(for_each_map_elem), \ - FN(snprintf), \ - FN(sys_bpf), \ - FN(btf_find_by_name_kind), \ - FN(sys_close), \ - FN(timer_init), \ - FN(timer_set_callback), \ - FN(timer_start), \ - FN(timer_cancel), \ - FN(get_func_ip), \ - FN(get_attach_cookie), \ - FN(task_pt_regs), \ - FN(get_branch_snapshot), \ - FN(trace_vprintk), \ - FN(skc_to_unix_sock), \ - FN(kallsyms_lookup_name), \ - FN(find_vma), \ - FN(loop), \ - FN(strncmp), \ - FN(get_func_arg), \ - FN(get_func_ret), \ - FN(get_func_arg_cnt), \ - FN(get_retval), \ - FN(set_retval), \ - FN(xdp_get_buff_len), \ - FN(xdp_load_bytes), \ - FN(xdp_store_bytes), \ - FN(copy_from_user_task), \ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ -#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN @@ -5340,6 +5929,12 @@ enum { BPF_F_ZERO_CSUM_TX = (1ULL << 1), BPF_F_DONT_FRAGMENT = (1ULL << 2), BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), +}; + +/* BPF_FUNC_skb_get_tunnel_key flags. */ +enum { + BPF_F_TUNINFO_FLAGS = (1ULL << 4), }; /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and @@ -5374,6 +5969,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { @@ -5469,6 +6066,15 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -5509,7 +6115,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u32 :32; /* Padding, future use. */ + __u8 tstamp_type; + __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; @@ -5521,8 +6128,15 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; /* Padding, future use. */ + union { + __u16 tunnel_ext; /* compat */ + __be16 tunnel_flags; + }; __u32 tunnel_label; + union { + __u32 local_ipv4; + __u32 local_ipv6[4]; + }; }; /* user accessible mirror of in-kernel xfrm_state. @@ -5561,6 +6175,11 @@ enum bpf_ret_code { * represented by BPF_REDIRECT above). */ BPF_LWT_REROUTE = 128, + /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR + * to indicate that no custom dissection was performed, and + * fallback to standard dissector is requested. + */ + BPF_FLOW_DISSECTOR_CONTINUE = 129, }; struct bpf_sock { @@ -5644,6 +6263,19 @@ struct bpf_sock_tuple { }; }; +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + struct bpf_xdp_sock { __u32 queue_id; }; @@ -5806,6 +6438,8 @@ struct bpf_prog_info { __u64 run_cnt; __u64 recursion_misses; __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; } __attribute__((aligned(8))); struct bpf_map_info { @@ -5857,11 +6491,26 @@ struct bpf_link_info { struct { __aligned_u64 target_name; /* in/out: target_name buffer ptr */ __u32 target_name_len; /* in/out: target_name buffer len */ + + /* If the iter specific field is 32 bits, it can be put + * in the first or second union. Otherwise it should be + * put in the second union. + */ union { struct { __u32 map_id; } map; }; + union { + struct { + __u64 cgroup_id; + __u32 order; + } cgroup; + struct { + __u32 tid; + __u32 pid; + } task; + }; } iter; struct { __u32 netns_ino; @@ -5870,6 +6519,51 @@ struct bpf_link_info { struct { __u32 ifindex; } xdp; + struct { + __u32 map_id; + } struct_ops; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + __u64 missed; + } kprobe_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + __u64 missed; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; }; } __attribute__((aligned(8))); @@ -5980,6 +6674,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -6265,6 +6960,8 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), }; enum { @@ -6325,9 +7022,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; @@ -6417,6 +7124,38 @@ struct bpf_timer { __u64 :64; } __attribute__((aligned(8))); +struct bpf_dynptr { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_root { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 :64; + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_refcount { + __u32 :32; +} __attribute__((aligned(4))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. @@ -6453,7 +7192,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ @@ -6507,6 +7247,7 @@ enum bpf_core_relo_kind { BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ }; /* @@ -6564,4 +7305,21 @@ struct bpf_core_relo { enum bpf_core_relo_kind kind; }; +/* + * Flags to control bpf_timer_start() behaviour. + * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is + * relative to current time. + */ +enum { + BPF_F_TIMER_ABS = (1ULL << 0), +}; + +/* BPF numbers iterator state */ +struct bpf_iter_num { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index b0d8fea..ec1798b 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -33,13 +33,13 @@ struct btf_type { /* "info" bits arrangement * bits 0-15: vlen (e.g. # of struct's members) * bits 16-23: unused - * bits 24-27: kind (e.g. int, ptr, array...etc) - * bits 28-30: unused + * bits 24-28: kind (e.g. int, ptr, array...etc) + * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ BTF_KIND_TYPEDEF = 8, /* Typedef */ BTF_KIND_VOLATILE = 9, /* Volatile */ @@ -76,6 +76,7 @@ enum { BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -186,4 +187,14 @@ struct btf_decl_tag { __s32 component_idx; }; +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index af2a44c..a429381 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6218f93..39e659c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -348,6 +348,8 @@ enum { IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, IFLA_GRO_MAX_SIZE, + IFLA_TSO_MAX_SIZE, + IFLA_TSO_MAX_SEGS, __IFLA_MAX }; @@ -603,6 +605,7 @@ enum { IFLA_MACVLAN_MACADDR_COUNT, IFLA_MACVLAN_BC_QUEUE_LEN, IFLA_MACVLAN_BC_QUEUE_LEN_USED, + IFLA_MACVLAN_BC_CUTOFF, __IFLA_MACVLAN_MAX, }; @@ -671,6 +674,7 @@ enum { IFLA_XFRM_UNSPEC, IFLA_XFRM_LINK, IFLA_XFRM_IF_ID, + IFLA_XFRM_COLLECT_METADATA, __IFLA_XFRM_MAX }; @@ -860,6 +864,7 @@ enum { IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, __IFLA_BOND_MAX, }; @@ -887,6 +892,7 @@ enum { IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + IFLA_BOND_SLAVE_PRIO, __IFLA_BOND_SLAVE_MAX, }; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h new file mode 100644 index 0000000..0a4d733 --- /dev/null +++ b/include/uapi/linux/netlink.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include <linux/kernel.h> +#include <linux/socket.h> /* for __kernel_sa_family_t */ +#include <linux/types.h> + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 +#define NETLINK_GET_STRICT_CHK 12 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 4cd39aa..39c6a25 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -164,8 +164,6 @@ enum perf_event_sample_format { PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ - - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) @@ -204,6 +202,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */ + PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -233,6 +233,8 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; @@ -251,9 +253,50 @@ enum { PERF_BR_SYSRET = 8, /* syscall return */ PERF_BR_COND_CALL = 9, /* conditional function call */ PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_ERET = 11, /* exception return */ + PERF_BR_IRQ = 12, /* irq */ + PERF_BR_SERROR = 13, /* system error */ + PERF_BR_NO_TX = 14, /* not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* extend ABI */ PERF_BR_MAX, }; +/* + * Common branch speculation outcome classification + */ +enum { + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_MAX, +}; + +enum { + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_MAX, +}; + +enum { + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, +}; + +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -299,6 +342,7 @@ enum { * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST * } && !PERF_FORMAT_GROUP * * { u64 nr; @@ -306,6 +350,7 @@ enum { * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 value; * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST * } cntr[nr]; * } && PERF_FORMAT_GROUP * }; @@ -315,8 +360,9 @@ enum perf_event_read_format { PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, PERF_FORMAT_GROUP = 1U << 3, + PERF_FORMAT_LOST = 1U << 4, - PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ @@ -328,6 +374,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -465,8 +512,12 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via * siginfo_t::si_perf_data, e.g. to permit user to identify the event. + * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be + * truncated accordingly on 32 bit architectures. */ __u64 sig_data; + + __u64 config3; /* extension of config2 */ }; /* @@ -487,7 +538,7 @@ struct perf_event_query_bpf { /* * User provided buffer to store program ids */ - __u32 ids[0]; + __u32 ids[]; }; /* @@ -1288,7 +1339,10 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0xa available */ +/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ #define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ @@ -1306,7 +1360,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOP_SHIFT 19 #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -/* 1 free */ +#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ #define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ @@ -1332,9 +1386,9 @@ union perf_mem_data_src { /* hop level */ #define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ +#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ +#define PERF_MEM_HOPS_3 0x04 /* remote board */ /* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 @@ -1356,6 +1410,7 @@ union perf_mem_data_src { * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) * type: branch type + * spec: branch speculation info (or 0 if not supported) */ struct perf_branch_entry { __u64 from; @@ -1366,7 +1421,10 @@ struct perf_branch_entry { abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ type:4, /* branch type */ - reserved:40; + spec:2, /* branch speculation info */ + new_type:4, /* additional branch type */ + priv:3, /* privilege level */ + reserved:31; }; union perf_sample_weight { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 1215377..3faee01 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -180,7 +180,7 @@ struct tc_u32_sel { short hoff; __be32 hmask; - struct tc_u32_key keys[0]; + struct tc_u32_key keys[]; }; struct tc_u32_mark { @@ -192,7 +192,7 @@ struct tc_u32_mark { struct tc_u32_pcnt { __u64 rcnt; __u64 rhit; - __u64 kcnts[0]; + __u64 kcnts[]; }; /* Flags */ diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 653c4f9..fe6c8f8 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_TC_BPF_H diff --git a/scripts/README.md b/scripts/README.md new file mode 100644 index 0000000..a5f765c --- /dev/null +++ b/scripts/README.md @@ -0,0 +1,164 @@ +# Scripts + +This directory contains scripts for maintaining bpftool's GitHub mirror. + +## gh-label-release-assets.sh + +This script can **add labels to GitHub release assets**. Labels are used in the +GitHub interface instead of the file name in the list of assets, but they do +not alter the download URL. + +The script takes the tag reference for the release as single parameter. The +repository to use, and the names and labels to set for assets are currently +defined in the script itself. + +It requires the [GitHub command line][gh] (`gh`). + +Note that only users with push access to the repository can update release +assets and set labels. + +[gh]: https://cli.github.com/ + +## sync-kernel.sh + +### Synchronize Linux and bpftool mirror + +This script synchronizes the bpftool mirror with the bpftool sources (and +related files) from the Linux kernel repository. + +Synchronization is usually performed against the `bpf-next` and `bpf` trees, +because this is where most bpftool updates are merged. + +By default, the script does not pick the very latest commits in these trees, +but instead it uses the commits referenced in the libbpf submodule. This is +because bpftool strongly relies on libbpf, and the libbpf GitHub mirror is used +here as a submodule dependency. This libbpf mirror is also periodically updated +to the latest `bpf-next` and `bpf` tree, and records to what kernel commits it +was brought up-to-date. To ensure optimal compatibility between the bpftool +sources and the libbpf dependency, we want to update them to the same point of +reference. + +### Prerequisites + +There is no particular tool required for running the script, except `git` of +course. + +However, you need a local copy of the Linux Git repository on your system +in order to successfully run the script. You can set it up as follows: + +```console +$ git clone 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git' linux +$ cd linux +$ git remote rename origin bpf-next +$ git branch --move master bpf-next +$ git remote add bpf 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git' +$ git fetch bpf +$ git checkout bpf/master +$ git switch --create bpf +$ git branch --set-upstream-to bpf/master +$ git switch bpf-next +``` + +At the end of the process, the repository should contain two branches +`bpf-next` and `bpf`, pointing to the `master` branches of the `bpf-next` and +`bpf` remote repositories, respectively. These two branches are required to +synchronize the mirror correctly. + +You can later update this repository with the following commands: + +```console +$ git switch bpf +$ git pull --set-upstream bpf master +$ git switch bpf-next +$ git pull --set-upstream bpf-next master +``` + +Also make sure you have cloned the bpftool mirror recursively, to check out the +libbpf submodule. If you have not, run the following: + +```console +$ git submodule update --init +``` + +### Usage + +As preliminary steps: + +- Make sure that you have a Linux Git repository installed (see above), with + two branches `bpf-next` and `bpf` up-to-date. +- Make sure your mirror repository is clean. + +Then run the script: + +```console +$ ./sync-kernel.sh <bpftool-repo> <kernel-repo> +``` + +If working from within the bpftool repository, the path to the `<bpftool-repo>` +is typically the current working directory (`.`). The second argument, +`<kernel-repo>`, is the path to the Linux Git repository mentioned earlier. + +Several environment variables can modify some internal parameters of the +script: + +- Set `BPF_NEXT_BASELINE `to override the `bpf-next` tree commit to use (the + commit from the `bpf-next` branch with which the bpftool repository is + currently synchronized, prior to running the script). If unset, use the hash + from `<bpftool-repo>/CHECKPOINT-COMMIT` is used. +- Set `BPF_BASELINE `to override the `bpf` tree commit to use (the commit from + the `bpf` branch with which the bpftool repository is currently synchronized, + prior to running the script). If unset, use the hash from + `<bpftool-repo>/BPF-CHECKPOINT-COMMIT` is used. +- Set `BPF_NEXT_TIP_COMMIT` to override the `bpf-next` tree target commit (the + commit in `bpf-next` up to which the bpftool mirror should be synchronized). + If unset, use the hash from `<bpftool-repo>/libbpf/CHECKPOINT-COMMIT`, after + the libbpf repository update that takes place at the beginning of the update + process. +- Set `BPF_TIP_COMMIT` to override the `bpf` tree target commit (the commit in + `bpf` up to which the bpftool mirror should be synchronized). If unset, use + the hash from `<bpftool-repo>/libbpf/BPF-CHECKPOINT-COMMIT`, after the libbpf + repository update that takes place at the beginning of the update process. +- Set `SKIP_LIBBPF_UPDATE` to `1` to avoid updating libbpf automatically. +- Set `MANUAL_MODE` to `1` to manually control every cherry-picked commit. + +### How it works + +This script synchronizes the bpftool mirror with upstream bpftool sources from +the Linux kernel repository. + +It performs the following steps: + +- First, the script updates the libbpf submodule, commits the change, and (by + default) picks up libbpf's latest checkpoints to use them as target commits + for the bpftool mirror. + +- In the Linux repository, from the `bpf-next` branch, it creates new branches, + filters out all non-bpftool-related files, and reworks the layout to + replicate the layout from the bpftool mirror. + +- It generates patches for each commit touching `bpftool` or the required UAPI + files, up to the target commit, and exports these patches to a temporary + repository. + +- In a new branch in the bpftool mirror, the script applies (`git am`) each of + these patches to the mirror. + +- Then the script checks out the `bpf` branch in the Linux repository, and + repeats the same operations. + +- On top of the new patches applied to the mirror, the script creates a last + commit with the updated checkpoints, using a cover letter summarizing the + changes as the commit description. + +- The next step is verification. The script applies to the Linux repository + (`bpf-next` branch) a patch containing known differences between the Linux + repository and the bpftool mirror. Then it looks for remaining differences + between the two repositories, and warn the user if it finds any. Patches + picked up from the `bpf` tree are usually a source of differences at this + step. If the patch containing the known differences is to be updated after + the synchronization in progress, the user should do it at this time, before + the temporary files from the script are deleted. + +- At last, the script cleans up the temporary files and branches in the Linux + repository. Note that these temporary files and branches are not cleaned up + if the script fails during execution. diff --git a/scripts/gh-label-release-assets.sh b/scripts/gh-label-release-assets.sh new file mode 100755 index 0000000..4143a1e --- /dev/null +++ b/scripts/gh-label-release-assets.sh @@ -0,0 +1,91 @@ +#!/usr/bin/env bash + +set -o errexit +set -o nounset +set -o pipefail + +# Use this script to add labels to GitHub release assets for a given release. +# +# Based on the following console workflow: +# +# gh api \ +# '/repos/qmonnet/bpftool/releases/tags/v7.2.0-snapshot.0' \ +# --jq '.id' +# gh api \ +# '/repos/qmonnet/bpftool/releases/96330927/assets' \ +# --jq '.[] | select(.name == "bpftool-amd64.tar.gz").id' +# gh api \ +# --method PATCH \ +# -H "Accept: application/vnd.github+json" \ +# -H "X-GitHub-Api-Version: 2022-11-28" \ +# '/repos/qmonnet/bpftool/releases/assets/100280866' \ +# -f name='bpftool-arm64.tar.gz' \ +# -f label='Compressed binary (arm64)' + +REPO="libbpf/bpftool" + +usage() { + echo "Update asset labels for bpftool releases" + echo "Usage:" + echo " $0 [options] <release_tag>" + echo "" + echo "OPTIONS" + echo " -h display this help" + exit "$1" +} + +OPTIND=1 +while getopts "h" opt; do + case "$opt" in + h) + usage 0 + ;; + *) + usage 1 + ;; + esac +done +shift $((OPTIND-1)) +[[ "${1:-}" = "--" ]] && shift + +# Get release tag from command line +if [[ "$#" -lt 1 ]]; then + echo "error: missing release tag" + usage 1 +fi +release_tag="$1" +echo "repo: ${REPO}, release tag: ${release_tag}" + +# Add labels to set for given asset names here: +declare -A assets_labels=( + ["bpftool-libbpf-${release_tag}-sources.tar.gz"]="Source code, including libbpf submodule (tar.gz)" +) + +# Get release ID +release_id="$(gh api "/repos/${REPO}/releases/tags/${release_tag}" --jq '.id')" +echo " found release ID ${release_id}" + +# For each label to set, get asset ID, prompt user for confirmation, set label +for asset_name in "${!assets_labels[@]}"; do + asset_id="$(gh api "/repos/${REPO}/releases/${release_id}/assets" \ + --jq ".[] | select(.name == \"${asset_name}\").id")" + echo " found asset ID ${asset_id}" + + echo "asset '${asset_name}': add label '${assets_labels[${asset_name}]}'" + answer="" + read -rp 'proceed? [y/N]: ' answer + + case "${answer}" in + y|yes|Y|Yes|YES) + gh api \ + --method PATCH \ + -H 'Accept: application/vnd.github+json' \ + -H 'X-GitHub-Api-Version: 2022-11-28' \ + "/repos/${REPO}/releases/assets/${asset_id}" \ + -f label="${assets_labels[${asset_name}]}" + ;; + *) + echo "cancelled" + ;; + esac +done diff --git a/scripts/sync-kernel-expected-diff.patch b/scripts/sync-kernel-expected-diff.patch new file mode 100644 index 0000000..769801a --- /dev/null +++ b/scripts/sync-kernel-expected-diff.patch @@ -0,0 +1,152 @@ +--- docs/Makefile ++++ docs/Makefile +@@ -1,5 +1,5 @@ + # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +-include ../../../scripts/Makefile.include ++include ../src/Makefile.include + + INSTALL ?= install + RM ?= rm -f +--- src/.gitignore ++++ src/.gitignore +@@ -1,8 +1,8 @@ + # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) ++*.o + *.d + /bootstrap/ + /bpftool +-bpftool*.8 + FEATURE-DUMP.bpftool + feature + libbpf +--- src/Makefile ++++ src/Makefile +@@ -1,10 +1,8 @@ + # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +-include ../../scripts/Makefile.include ++include Makefile.include + + ifeq ($(srctree),) + srctree := $(patsubst %/,%,$(dir $(CURDIR))) +-srctree := $(patsubst %/,%,$(dir $(srctree))) +-srctree := $(patsubst %/,%,$(dir $(srctree))) + endif + + ifeq ($(V),1) +@@ -13,7 +11,7 @@ + Q = @ + endif + +-BPF_DIR = $(srctree)/tools/lib/bpf ++BPF_DIR = $(srctree)/libbpf/src + + ifneq ($(OUTPUT),) + _OUTPUT := $(OUTPUT) +@@ -43,16 +41,16 @@ + $(QUIET_MKDIR)mkdir -p $@ + + $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) +- $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ +- DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers ++ $(Q)$(MAKE) -C $(BPF_DIR) OBJDIR=$(patsubst %/,%,$(LIBBPF_OUTPUT)) \ ++ PREFIX=$(LIBBPF_DESTDIR:/=) $(LIBBPF) install_headers + + $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $< + + $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) +- $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ +- DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ ++ $(Q)$(MAKE) -C $(BPF_DIR) OBJDIR=$(patsubst %/,%,$(LIBBPF_BOOTSTRAP_OUTPUT)) \ ++ PREFIX=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" $@ install_headers + + $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) +@@ -76,9 +74,9 @@ + CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(or $(OUTPUT),.) \ + -I$(LIBBPF_INCLUDE) \ +- -I$(srctree)/kernel/bpf/ \ +- -I$(srctree)/tools/include \ +- -I$(srctree)/tools/include/uapi ++ -I$(srctree)/src/kernel/bpf/ \ ++ -I$(srctree)/include \ ++ -I$(srctree)/include/uapi + ifneq ($(BPFTOOL_VERSION),) + CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' + endif +@@ -119,11 +117,7 @@ + endif + + ifeq ($(check_feat),1) +-ifeq ($(FEATURES_DUMP),) +-include $(srctree)/tools/build/Makefile.feature +-else +-include $(FEATURES_DUMP) +-endif ++include Makefile.feature + endif + + LIBS = $(LIBBPF) -lelf -lz +@@ -213,7 +207,7 @@ + $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) + $(QUIET_CLANG)$(CLANG) \ + -I$(or $(OUTPUT),.) \ +- -I$(srctree)/tools/include/uapi/ \ ++ -I$(srctree)/include/uapi/ \ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ + -g -O2 -Wall -fno-stack-protector \ + -target bpf -c $< -o $@ +@@ -231,10 +225,10 @@ + + CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) + +-$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c ++$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/src/kernel/bpf/disasm.c + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ + +-$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c ++$(OUTPUT)disasm.o: $(srctree)/src/kernel/bpf/disasm.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + + $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) +@@ -253,7 +247,7 @@ + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + +-clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean ++clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean + $(call QUIET_CLEAN, bpftool) + $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h +@@ -269,7 +263,7 @@ + + install: install-bin + $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir) +- $(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir) ++ $(Q)$(INSTALL) -m 0644 $(srctree)/bash-completion/bpftool $(DESTDIR)$(bash_compdir) + + uninstall: + $(call QUIET_UNINST, bpftool) +@@ -277,16 +271,16 @@ + $(Q)$(RM) -- $(DESTDIR)$(bash_compdir)/bpftool + + doc: +- $(call descend,Documentation) ++ $(call descend,$(srctree)/docs) + + doc-clean: +- $(call descend,Documentation,clean) ++ $(call descend,$(srctree)/docs,clean) + + doc-install: +- $(call descend,Documentation,install) ++ $(call descend,$(srctree)/docs,install) + + doc-uninstall: +- $(call descend,Documentation,uninstall) ++ $(call descend,$(srctree)/docs,uninstall) + + FORCE: + diff --git a/scripts/sync-kernel.sh b/scripts/sync-kernel.sh index 24e1762..086b60b 100755 --- a/scripts/sync-kernel.sh +++ b/scripts/sync-kernel.sh @@ -8,7 +8,6 @@ usage () { echo " - Update the libbpf submodule, commit, and use its new checkpoints as target commits for bpftool." echo " - Cherry-pick commits from the bpf-next branch, up to the bpf-next target commit." echo " - Cherry-pick commits from the bpf branch, up to the bpf target commit." - echo " - Update bpftool's version number based on bpf-next's kernel version and target commit." echo " - Create a new commit with the updated version and checkpoints." echo " - Check consistency." echo "" @@ -31,8 +30,8 @@ if [ -z "${BPFTOOL_REPO}" ] || [ -z "${LINUX_REPO}" ]; then usage fi -BASELINE_COMMIT=${BPF_NEXT_BASELINE:-$(cat ${BPFTOOL_REPO}/CHECKPOINT-COMMIT)} -BPF_BASELINE_COMMIT=${BPF_BASELINE:-$(cat ${BPFTOOL_REPO}/BPF-CHECKPOINT-COMMIT)} +BASELINE_COMMIT=${BPF_NEXT_BASELINE:-$(cat "${BPFTOOL_REPO}"/CHECKPOINT-COMMIT)} +BPF_BASELINE_COMMIT=${BPF_BASELINE:-$(cat "${BPFTOOL_REPO}"/BPF-CHECKPOINT-COMMIT)} if [ -z "${BASELINE_COMMIT}" ] || [ -z "${BPF_BASELINE_COMMIT}" ]; then echo "Error: bpf or bpf-next baseline commits are not provided" @@ -43,6 +42,7 @@ SUFFIX=$(date --utc +%Y-%m-%dT%H-%M-%S.%3NZ) WORKDIR=$(pwd) TMP_DIR=$(mktemp -d) +# shellcheck disable=SC2064 trap "cd ${WORKDIR}; exit" INT TERM EXIT BPFTOOL_SRC_DIR="tools/bpf/bpftool" @@ -54,20 +54,22 @@ PATH_MAP=( \ [${BPFTOOL_SRC_DIR}/Documentation]=docs \ [kernel/bpf/disasm.c]=src/kernel/bpf/disasm.c \ [kernel/bpf/disasm.h]=src/kernel/bpf/disasm.h \ + [tools/include/tools/dis-asm-compat.h]=include/tools/dis-asm-compat.h \ [tools/include/uapi/asm-generic/bitsperlong.h]=include/uapi/asm-generic/bitsperlong.h \ [tools/include/uapi/linux/bpf_common.h]=include/uapi/linux/bpf_common.h \ [tools/include/uapi/linux/bpf.h]=include/uapi/linux/bpf.h \ [tools/include/uapi/linux/btf.h]=include/uapi/linux/btf.h \ [tools/include/uapi/linux/const.h]=include/uapi/linux/const.h \ [tools/include/uapi/linux/if_link.h]=include/uapi/linux/if_link.h \ + [tools/include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h \ [tools/include/uapi/linux/perf_event.h]=include/uapi/linux/perf_event.h \ [tools/include/uapi/linux/pkt_cls.h]=include/uapi/linux/pkt_cls.h \ [tools/include/uapi/linux/pkt_sched.h]=include/uapi/linux/pkt_sched.h \ [tools/include/uapi/linux/tc_act/tc_bpf.h]=include/uapi/linux/tc_act/tc_bpf.h \ ) -BPFTOOL_PATHS="${!PATH_MAP[@]}" -BPFTOOL_VIEW_PATHS="${PATH_MAP[@]}" +BPFTOOL_PATHS=( "${!PATH_MAP[@]}" ) +BPFTOOL_VIEW_PATHS=( "${PATH_MAP[@]}" ) BPFTOOL_VIEW_EXCLUDE_REGEX='^(docs/\.gitignore|src/Makefile\.(feature|include))$' LINUX_VIEW_EXCLUDE_REGEX='^$' @@ -80,7 +82,7 @@ BPFTOOL_TREE_FILTER+="git mv -kf ${BPFTOOL_SRC_DIR} __bpftool/${PATH_MAP[${BPFTO BPFTOOL_TREE_FILTER+="git mv -kf __bpftool/src/bash-completion __bpftool/bash-completion && "$'\\\n' BPFTOOL_TREE_FILTER+="git mv -kf __bpftool/src/Documentation __bpftool/docs && "$'\\\n' -BPFTOOL_TREE_FILTER+="mkdir -p __bpftool/include/uapi/asm-generic __bpftool/include/uapi/linux/tc_act __bpftool/src/kernel/bpf && "$'\\\n' +BPFTOOL_TREE_FILTER+="mkdir -p __bpftool/include/tools __bpftool/include/uapi/asm-generic __bpftool/include/uapi/linux/tc_act __bpftool/src/kernel/bpf && "$'\\\n' for p in "${!PATH_MAP[@]}"; do case ${p} in ${BPFTOOL_SRC_DIR}*) @@ -92,14 +94,14 @@ BPFTOOL_TREE_FILTER+="true >/dev/null" cd_to() { - cd ${WORKDIR} && cd "$1" + cd "${WORKDIR}" && cd "$1" } # Output brief single-line commit description # $1 - commit ref commit_desc() { - git log -n1 --pretty='%h ("%s")' $1 + git log -n1 --pretty='%h ("%s")' "$1" } # Create commit single-line signature, which consists of: @@ -113,7 +115,8 @@ commit_desc() # $2 - paths filter commit_signature() { - git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|' + # shellcheck disable=SC2086 + git show --pretty='("%s")|%aI|%b' --shortstat "$1" -- ${2-.} | tr '\n' '|' } # Cherry-pick commits touching bpftool-related files @@ -132,7 +135,8 @@ cherry_pick_commits() local bpftool_conflict_cnt local desc - new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${BPFTOOL_PATHS[@]}) + # shellcheck disable=SC2068 + new_commits=$(git rev-list --no-merges --topo-order --reverse "${baseline_tag}".."${tip_tag}" ${BPFTOOL_PATHS[@]}) for new_commit in ${new_commits}; do if [[ "${baseline_tag}" == "${BPF_BASELINE_TAG}" ]]; then if git merge-base --is-ancestor "${new_commit}" "${BASELINE_COMMIT}"; then @@ -140,27 +144,28 @@ cherry_pick_commits() continue fi fi - desc="$(commit_desc ${new_commit})" - signature="$(commit_signature ${new_commit} "${BPFTOOL_PATHS[@]}")" - synced_cnt=$(grep -F "${signature}" ${TMP_DIR}/bpftool_commits.txt | wc -l) + desc="$(commit_desc "${new_commit}")" + signature="$(commit_signature "${new_commit}" "${BPFTOOL_PATHS[*]}")" + # shellcheck disable=SC2126 + synced_cnt=$(grep -F "${signature}" "${TMP_DIR}"/bpftool_commits.txt | wc -l) manual_check=0 - if ((${synced_cnt} > 0)); then + if (("${synced_cnt}" > 0)); then # commit with the same subject is already in bpftool, but it's # not 100% the same commit, so check with user echo "Commit '${desc}' is synced into bpftool as:" - grep -F "${signature}" ${TMP_DIR}/bpftool_commits.txt | \ + grep -F "${signature}" "${TMP_DIR}"/bpftool_commits.txt | \ cut -d'|' -f1 | sed -e 's/^/- /' - if ((${manual_mode} != 1 && ${synced_cnt} == 1)); then + if (("${manual_mode}" != 1 && "${synced_cnt}" == 1)); then echo "Skipping '${desc}' due to unique match..." continue fi - if ((${synced_cnt} > 1)); then + if (("${synced_cnt}" > 1)); then echo "'${desc} matches multiple commits, please, double-check!" manual_check=1 fi fi - if ((${manual_mode} == 1 || ${manual_check} == 1)); then - read -p "Do you want to skip '${desc}'? [y/N]: " should_skip + if (("${manual_mode}" == 1 || "${manual_check}" == 1)); then + read -rp "Do you want to skip '${desc}'? [y/N]: " should_skip case "${should_skip}" in "y" | "Y") echo "Skipping '${desc}'..." @@ -170,15 +175,16 @@ cherry_pick_commits() fi # commit hasn't been synced into bpftool yet echo "Picking '${desc}'..." - if ! git cherry-pick ${new_commit} &>/dev/null; then + if ! git cherry-pick "${new_commit}" &>/dev/null; then echo "Warning! Cherry-picking '${desc} failed, checking if it's non-bpftool files causing problems..." + # shellcheck disable=SC2068 bpftool_conflict_cnt=$(git diff --name-only --diff-filter=U -- ${BPFTOOL_PATHS[@]} | wc -l) conflict_cnt=$(git diff --name-only | wc -l) prompt_resolution=1 - if ((${bpftool_conflict_cnt} == 0)); then + if (("${bpftool_conflict_cnt}" == 0)); then echo "Looks like only non-bpftool files have conflicts, ignoring..." - if ((${conflict_cnt} == 0)); then + if (("${conflict_cnt}" == 0)); then echo "Empty cherry-pick, skipping it..." git cherry-pick --abort continue @@ -194,8 +200,8 @@ cherry_pick_commits() fi fi - if ((${prompt_resolution} == 1)); then - read -p "Error! Cherry-picking '${desc}' failed, please fix manually and press <return> to proceed..." + if (("${prompt_resolution}" == 1)); then + read -rp "Error! Cherry-picking '${desc}' failed, please fix manually and press <return> to proceed..." fi fi # Append signature of just cherry-picked commit to avoid @@ -203,37 +209,40 @@ cherry_pick_commits() # processing bpf tree commits. At this point we don't know yet # the final commit sha in bpftool repo, so we record Linux SHA # instead as LINUX_<sha>. - echo LINUX_$(git log --pretty='%h' -n1) "${signature}" >> ${TMP_DIR}/bpftool_commits.txt + echo "LINUX_$(git log --pretty='%h' -n1) ${signature}" >> "${TMP_DIR}"/bpftool_commits.txt done } cleanup() { echo "Cleaning up..." - rm -r ${TMP_DIR} - cd_to ${LINUX_REPO} - git checkout ${TIP_SYM_REF} - git branch -D ${BASELINE_TAG} ${TIP_TAG} ${BPF_BASELINE_TAG} ${BPF_TIP_TAG} \ - ${SQUASH_BASE_TAG} ${SQUASH_TIP_TAG} ${VIEW_TAG} || true + rm -r -- "${TMP_DIR}" + cd_to "${LINUX_REPO}" + git checkout "${TIP_SYM_REF}" + git branch -D "${BASELINE_TAG}" "${TIP_TAG}" "${BPF_BASELINE_TAG}" "${BPF_TIP_TAG}" \ + "${SQUASH_BASE_TAG}" "${SQUASH_TIP_TAG}" || true + # shellcheck disable=SC2015 + git show-ref --verify --quiet refs/heads/"${VIEW_TAG}" && \ + git branch -D "${VIEW_TAG}" || true cd_to . echo "DONE." } -cd_to ${BPFTOOL_REPO} -BPFTOOL_SYNC_TAG=bpftool-sync-${SUFFIX} -git checkout -b ${BPFTOOL_SYNC_TAG} +cd_to "${BPFTOOL_REPO}" +BPFTOOL_SYNC_TAG="bpftool-sync-${SUFFIX}" +git checkout -b "${BPFTOOL_SYNC_TAG}" # Update libbpf if [[ "${SKIP_LIBBPF_UPDATE:-0}" -ne 1 ]]; then - cd_to ${BPFTOOL_REPO}/libbpf + cd_to "${BPFTOOL_REPO}"/libbpf git pull origin master LIBBPF_VERSION=$(grep -oE '^LIBBPF_([0-9.]+)' src/libbpf.map | sort -rV | head -n1 | cut -d'_' -f2) LIBBPF_COMMIT=$(git rev-parse HEAD) - cd_to ${BPFTOOL_REPO} + cd_to "${BPFTOOL_REPO}" if [[ -n "$(git status --porcelain --untracked-files=no)" ]]; then git add libbpf - git commit -m 'sync: Update libbpf submodule' \ + git commit --signoff -m 'sync: Update libbpf submodule' \ -m "\ Pull latest libbpf from mirror. Libbpf version: ${LIBBPF_VERSION} @@ -243,44 +252,44 @@ Libbpf commit: ${LIBBPF_COMMIT}" \ fi # Use libbpf's new checkpoints as tips -TIP_COMMIT=${BPF_NEXT_TIP_COMMIT:-$(cat ${BPFTOOL_REPO}/libbpf/CHECKPOINT-COMMIT)} -BPF_TIP_COMMIT=${BPF_TIP_COMMIT:-$(cat ${BPFTOOL_REPO}/libbpf/BPF-CHECKPOINT-COMMIT)} +TIP_COMMIT=${BPF_NEXT_TIP_COMMIT:-$(cat "${BPFTOOL_REPO}"/libbpf/CHECKPOINT-COMMIT)} +BPF_TIP_COMMIT=${BPF_TIP_COMMIT:-$(cat "${BPFTOOL_REPO}"/libbpf/BPF-CHECKPOINT-COMMIT)} if [ -z "${TIP_COMMIT}" ] || [ -z "${BPF_TIP_COMMIT}" ]; then echo "Error: bpf or bpf-next tip commits are not provided" usage fi -cd_to ${BPFTOOL_REPO} +cd_to "${BPFTOOL_REPO}" GITHUB_ABS_DIR=$(pwd) echo "Dumping existing bpftool commit signatures..." for h in $(git log --pretty='%h' -n500); do - echo $h "$(commit_signature $h)" >> ${TMP_DIR}/bpftool_commits.txt + echo "$h" "$(commit_signature "$h")" >> "${TMP_DIR}"/bpftool_commits.txt done # Use current kernel repo HEAD as a source of patches -cd_to ${LINUX_REPO} +cd_to "${LINUX_REPO}" LINUX_ABS_DIR=$(pwd) TIP_SYM_REF=$(git symbolic-ref -q --short HEAD || git rev-parse HEAD) -BASELINE_TAG=bpftool-baseline-${SUFFIX} -TIP_TAG=bpftool-tip-${SUFFIX} -BPF_BASELINE_TAG=bpftool-bpf-baseline-${SUFFIX} -BPF_TIP_TAG=bpftool-bpf-tip-${SUFFIX} -VIEW_TAG=bpftool-view-${SUFFIX} +BASELINE_TAG="bpftool-baseline-${SUFFIX}" +TIP_TAG="bpftool-tip-${SUFFIX}" +BPF_BASELINE_TAG="bpftool-bpf-baseline-${SUFFIX}" +BPF_TIP_TAG="bpftool-bpf-tip-${SUFFIX}" +VIEW_TAG="bpftool-view-${SUFFIX}" # Squash state of kernel repo at baseline into single commit -SQUASH_BASE_TAG=bpftool-squash-base-${SUFFIX} -SQUASH_TIP_TAG=bpftool-squash-tip-${SUFFIX} -SQUASH_COMMIT=$(git commit-tree ${BASELINE_COMMIT}^{tree} -m "BASELINE SQUASH ${BASELINE_COMMIT}") +SQUASH_BASE_TAG="bpftool-squash-base-${SUFFIX}" +SQUASH_TIP_TAG="bpftool-squash-tip-${SUFFIX}" +SQUASH_COMMIT=$(git commit-tree "${BASELINE_COMMIT}^{tree}" -m "BASELINE SQUASH ${BASELINE_COMMIT}") echo "WORKDIR: ${WORKDIR}" echo "LINUX REPO: ${LINUX_REPO}" echo "BPFTOOL REPO: ${BPFTOOL_REPO}" echo "TEMP DIR: ${TMP_DIR}" echo "SUFFIX: ${SUFFIX}" -echo "BASE COMMIT: '$(commit_desc ${BASELINE_COMMIT})'" -echo "TIP COMMIT: '$(commit_desc ${TIP_COMMIT})'" -echo "BPF BASE COMMIT: '$(commit_desc ${BPF_BASELINE_COMMIT})'" -echo "BPF TIP COMMIT: '$(commit_desc ${BPF_TIP_COMMIT})'" +echo "BASE COMMIT: '$(commit_desc "${BASELINE_COMMIT}")'" +echo "TIP COMMIT: '$(commit_desc "${TIP_COMMIT}")'" +echo "BPF BASE COMMIT: '$(commit_desc "${BPF_BASELINE_COMMIT}")'" +echo "BPF TIP COMMIT: '$(commit_desc "${BPF_TIP_COMMIT}")'" echo "SQUASH COMMIT: ${SQUASH_COMMIT}" echo "BASELINE TAG: ${BASELINE_TAG}" echo "TIP TAG: ${TIP_TAG}" @@ -292,60 +301,53 @@ echo "VIEW TAG: ${VIEW_TAG}" echo "BPFTOOL SYNC TAG: ${BPFTOOL_SYNC_TAG}" echo "PATCHES: ${TMP_DIR}/patches" -git branch ${BASELINE_TAG} ${BASELINE_COMMIT} -git branch ${TIP_TAG} ${TIP_COMMIT} -git branch ${BPF_BASELINE_TAG} ${BPF_BASELINE_COMMIT} -git branch ${BPF_TIP_TAG} ${BPF_TIP_COMMIT} -git branch ${SQUASH_BASE_TAG} ${SQUASH_COMMIT} -git checkout -b ${SQUASH_TIP_TAG} ${SQUASH_COMMIT} +git branch "${BASELINE_TAG}" "${BASELINE_COMMIT}" +git branch "${TIP_TAG}" "${TIP_COMMIT}" +git branch "${BPF_BASELINE_TAG}" "${BPF_BASELINE_COMMIT}" +git branch "${BPF_TIP_TAG}" "${BPF_TIP_COMMIT}" +git branch "${SQUASH_BASE_TAG}" "${SQUASH_COMMIT}" +git checkout -b "${SQUASH_TIP_TAG}" "${SQUASH_COMMIT}" # Cherry-pick new commits onto squashed baseline commit echo "Cherry-pick for bpf-next..." -cherry_pick_commits ${BASELINE_TAG} ${TIP_TAG} +cherry_pick_commits "${BASELINE_TAG}" "${TIP_TAG}" echo "Cherry-pick for bpf..." -cherry_pick_commits ${BPF_BASELINE_TAG} ${BPF_TIP_TAG} +cherry_pick_commits "${BPF_BASELINE_TAG}" "${BPF_TIP_TAG}" # Move all bpftool files into __bpftool directory. -FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --tree-filter "${BPFTOOL_TREE_FILTER}" ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG} +FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --tree-filter "${BPFTOOL_TREE_FILTER}" "${SQUASH_TIP_TAG}" "${SQUASH_BASE_TAG}" # Make __bpftool a new root directory -FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --subdirectory-filter __bpftool ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG} +FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --subdirectory-filter __bpftool "${SQUASH_TIP_TAG}" "${SQUASH_BASE_TAG}" # If there are no new commits with bpftool-related changes, bail out -COMMIT_CNT=$(git rev-list --count ${SQUASH_BASE_TAG}..${SQUASH_TIP_TAG}) -if ((${COMMIT_CNT} <= 0)); then - echo "No new changes to apply, we are done!" - cleanup - exit 2 +COMMIT_CNT=$(git rev-list --count "${SQUASH_BASE_TAG}".."${SQUASH_TIP_TAG}") +if (("${COMMIT_CNT}" <= 0)); then + echo "No new changes to apply, we are done!" + cleanup + exit 2 fi # Exclude baseline commit and generate nice cover letter with summary -git format-patch ${SQUASH_BASE_TAG}..${SQUASH_TIP_TAG} --cover-letter -o ${TMP_DIR}/patches - -# Compute version by concatenating kernel tip's version and hash -git -c advice.detachedHead=false checkout ${TIP_COMMIT} -BPFTOOL_VERSION="$(make kernelversion)+${TIP_COMMIT::12}" +git format-patch --no-signature "${SQUASH_BASE_TAG}".."${SQUASH_TIP_TAG}" --cover-letter -o "${TMP_DIR}"/patches # Now is time to re-apply bpftool-related linux patches to bpftool repo -cd_to ${BPFTOOL_REPO} +cd_to "${BPFTOOL_REPO}" -for patch in $(ls -1 ${TMP_DIR}/patches | tail -n +2); do +# shellcheck disable=SC2012 +for patch in $(ls -1 "${TMP_DIR}"/patches | tail -n +2); do if ! git am --3way --committer-date-is-author-date "${TMP_DIR}/patches/${patch}"; then - read -p "Applying ${TMP_DIR}/patches/${patch} failed, please resolve manually and press <return> to proceed..." + read -rp "Applying ${TMP_DIR}/patches/${patch} failed, please resolve manually and press <return> to proceed..." fi done -# Bump bpftool version number if necessary -sed -i "s/^\(BPFTOOL_VERSION := \).*/\1${BPFTOOL_VERSION}/" src/Makefile -git add src/Makefile - # Use generated cover-letter as a template for "sync commit" with # baseline and checkpoint commits from kernel repo (and leave summary # from cover letter intact, of course) -echo ${TIP_COMMIT} > CHECKPOINT-COMMIT && \ -echo ${BPF_TIP_COMMIT} > BPF-CHECKPOINT-COMMIT && \ +echo "${TIP_COMMIT}" > CHECKPOINT-COMMIT && \ +echo "${BPF_TIP_COMMIT}" > BPF-CHECKPOINT-COMMIT && \ git add CHECKPOINT-COMMIT && \ git add BPF-CHECKPOINT-COMMIT && \ -awk '/\*\*\* BLURB HERE \*\*\*/ {p=1} p' ${TMP_DIR}/patches/0000-cover-letter.patch | \ +awk '/\*\*\* BLURB HERE \*\*\*/ {p=1} p' "${TMP_DIR}"/patches/0000-cover-letter.patch | \ sed "s/\*\*\* BLURB HERE \*\*\*/\ sync: Pull latest bpftool changes from kernel\n\ \n\ @@ -353,39 +355,61 @@ Syncing latest bpftool commits from kernel repository.\n\ Baseline bpf-next commit: ${BASELINE_COMMIT}\n\ Checkpoint bpf-next commit: ${TIP_COMMIT}\n\ Baseline bpf commit: ${BPF_BASELINE_COMMIT}\n\ -Checkpoint bpf commit: ${BPF_TIP_COMMIT}\n\ -Latest bpftool version: ${BPFTOOL_VERSION}/" | \ -git commit --file=- +Checkpoint bpf commit: ${BPF_TIP_COMMIT}/" | \ +git commit --signoff --file=- echo "SUCCESS! ${COMMIT_CNT} commits synced." echo "Verifying Linux's and Github's bpftool state" -cd_to ${LINUX_REPO} -git checkout -b ${VIEW_TAG} ${TIP_COMMIT} -FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${BPFTOOL_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG} -FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --subdirectory-filter __bpftool ${VIEW_TAG}^..${VIEW_TAG} -git ls-files -- ${BPFTOOL_VIEW_PATHS[@]} | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/linux-view.ls - -cd_to ${BPFTOOL_REPO} -git ls-files -- ${BPFTOOL_VIEW_PATHS[@]} | grep -v -E "${BPFTOOL_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls +cd_to "${LINUX_REPO}" +git checkout -b "${VIEW_TAG}" "${TIP_COMMIT}" +FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${BPFTOOL_TREE_FILTER}" "${VIEW_TAG}"^.."${VIEW_TAG}" +FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --subdirectory-filter __bpftool "${VIEW_TAG}"^.."${VIEW_TAG}" +# shellcheck disable=SC2068 +git ls-files -- ${BPFTOOL_VIEW_PATHS[@]} | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > "${TMP_DIR}"/linux-view.ls +# Before we compare each file, try to apply to the mirror a patch containing the +# expected differences between the two repositories; this is to avoid checking +# "known" differences visually and taking the risk of missing a new, relevant +# differences. +echo "Patching to account for expected differences..." +patch -d "${LINUX_ABS_DIR}" -p0 -f --reject-file=- --no-backup-if-mismatch < "${GITHUB_ABS_DIR}/scripts/sync-kernel-expected-diff.patch" || true +git add -u +git commit -m 'tmp: apply expected differences to compare github/kernel repos' || true + +cd_to "${BPFTOOL_REPO}" +# shellcheck disable=SC2068 +git ls-files -- ${BPFTOOL_VIEW_PATHS[@]} | grep -v -E "${BPFTOOL_VIEW_EXCLUDE_REGEX}" > "${TMP_DIR}"/github-view.ls echo "Comparing list of files..." -diff -u ${TMP_DIR}/linux-view.ls ${TMP_DIR}/github-view.ls +diff -u "${TMP_DIR}"/linux-view.ls "${TMP_DIR}"/github-view.ls echo "Comparing file contents..." CONSISTENT=1 -for F in $(cat ${TMP_DIR}/linux-view.ls); do +while IFS= read -r F; do if ! diff -u --color "${LINUX_ABS_DIR}/${F}" "${GITHUB_ABS_DIR}/${F}"; then echo "${LINUX_ABS_DIR}/${F} and ${GITHUB_ABS_DIR}/${F} are different!" CONSISTENT=0 fi -done -if ((${CONSISTENT} == 1)); then +done < "${TMP_DIR}"/linux-view.ls +echo "" +if (("${CONSISTENT}" == 1)); then echo "Great! Content is identical!" else ignore_inconsistency=n echo "Unfortunately, there are some inconsistencies, please double check." - read -p "Does everything look good? [y/N]: " ignore_inconsistency + echo "Some of them may come from patches in bpf tree but absent from bpf-next." + echo "Note: I applied scripts/sync-kernel-expected-diff.patch before checking," + echo "to account for expected changes. If this patch needs an update," + echo "you can do it now with:" + echo "------" + echo " (cd \"${LINUX_ABS_DIR}\" && git -c advice.detachedHead=false checkout HEAD~)" + echo " for f in \$(cat \"${TMP_DIR}/linux-view.ls\"); do" + echo " diff -u --label \"\${f}\" --label \"\${f}\" \\" + echo " \"${LINUX_ABS_DIR}/\${f}\" \\" + echo " \"${GITHUB_ABS_DIR}/\${f}\"" + echo " done > \"${GITHUB_ABS_DIR}/scripts/sync-kernel-expected-diff.patch\"" + echo "------" + read -rp "Does everything look good? [y/N]: " ignore_inconsistency case "${ignore_inconsistency}" in "y" | "Y") echo "Ok, proceeding..." diff --git a/src/Makefile b/src/Makefile index b447f5c..048d221 100644 --- a/src/Makefile +++ b/src/Makefile @@ -16,37 +16,33 @@ BPF_DIR = $(srctree)/libbpf/src ifneq ($(OUTPUT),) _OUTPUT := $(OUTPUT) else - _OUTPUT := $(CURDIR) + _OUTPUT := $(CURDIR)/ endif -BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/ +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ -LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/ +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) -LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf LIBBPF := $(LIBBPF_OUTPUT)libbpf.a LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) -LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a -# We need to copy hashmap.h and nlattr.h which is not otherwise exported by -# libbpf, but still required by bpftool. -LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h) -LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h) - -ifeq ($(BPFTOOL_VERSION),) -BPFTOOL_VERSION := 5.16.0+dc37dc617fab -endif +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): $(QUIET_MKDIR)mkdir -p $@ $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OBJDIR=$(patsubst %/,%,$(LIBBPF_OUTPUT)) \ - PREFIX=$(LIBBPF_DESTDIR) $(LIBBPF) install_headers + PREFIX=$(LIBBPF_DESTDIR:/=) $(LIBBPF) install_headers $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -54,8 +50,8 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OBJDIR=$(patsubst %/,%,$(LIBBPF_BOOTSTRAP_OUTPUT)) \ - PREFIX=$(LIBBPF_BOOTSTRAP_DESTDIR) \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers + PREFIX=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" $@ install_headers $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -76,12 +72,14 @@ CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(LIBBPF_INCLUDE) \ -I$(srctree)/src/kernel/bpf/ \ -I$(srctree)/include \ -I$(srctree)/include/uapi +ifneq ($(BPFTOOL_VERSION),) CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) endif @@ -93,10 +91,22 @@ INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ - clang-bpf-co-re -FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ - clang-bpf-co-re + +FEATURE_TESTS := clang-bpf-co-re +FEATURE_TESTS += llvm +FEATURE_TESTS += libcap +FEATURE_TESTS += libbfd +FEATURE_TESTS += libbfd-liberty +FEATURE_TESTS += libbfd-liberty-z +FEATURE_TESTS += disassembler-four-args +FEATURE_TESTS += disassembler-init-styled + +FEATURE_DISPLAY := clang-bpf-co-re +FEATURE_DISPLAY += llvm +FEATURE_DISPLAY += libcap +FEATURE_DISPLAY += libbfd +FEATURE_DISPLAY += libbfd-liberty +FEATURE_DISPLAY += libbfd-liberty-z check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -110,14 +120,6 @@ ifeq ($(check_feat),1) include Makefile.feature endif -ifeq ($(feature-disassembler-four-args), 1) -CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE -endif - -ifeq ($(feature-reallocarray), 0) -CFLAGS += -DCOMPAT_NEED_REALLOCARRAY -endif - LIBS = $(LIBBPF) -lelf -lz LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz ifeq ($(feature-libcap), 1) @@ -129,21 +131,45 @@ include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool -BFD_SRCS = jit_disasm.c - -SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c)) - -ifeq ($(feature-libbfd),1) - LIBS += -lbfd -ldl -lopcodes -else ifeq ($(feature-libbfd-liberty),1) - LIBS += -lbfd -ldl -lopcodes -liberty -else ifeq ($(feature-libbfd-liberty-z),1) - LIBS += -lbfd -ldl -lopcodes -liberty -lz +SRCS := $(wildcard *.c) + +ifeq ($(feature-llvm),1) + # If LLVM is available, use it for JIT disassembly + CFLAGS += -DHAVE_LLVM_SUPPORT + LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets + CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static) + LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LIBS += -lstdc++ + endif + LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags) +else + # Fall back on libbfd + ifeq ($(feature-libbfd),1) + LIBS += -lbfd -ldl -lopcodes + else ifeq ($(feature-libbfd-liberty),1) + LIBS += -lbfd -ldl -lopcodes -liberty + else ifeq ($(feature-libbfd-liberty-z),1) + LIBS += -lbfd -ldl -lopcodes -liberty -lz + endif + + # If one of the above feature combinations is set, we support libbfd + ifneq ($(filter -lbfd,$(LIBS)),) + CFLAGS += -DHAVE_LIBBFD_SUPPORT + + # Libbfd interface changed over time, figure out what we need + ifeq ($(feature-disassembler-four-args), 1) + CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE + endif + ifeq ($(feature-disassembler-init-styled), 1) + CFLAGS += -DDISASM_INIT_STYLED + endif + endif endif - -ifneq ($(filter -lbfd,$(LIBS)),) -CFLAGS += -DHAVE_LIBBFD_SUPPORT -SRCS += $(BFD_SRCS) +ifeq ($(filter -DHAVE_LLVM_SUPPORT -DHAVE_LIBBFD_SUPPORT,$(CFLAGS)),) + # No support for JIT disassembly + SRCS := $(filter-out jit_disasm.c,$(SRCS)) endif HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ @@ -180,10 +206,11 @@ endif $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(srctree)/include/uapi/ \ -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ - -g -O2 -Wall -target bpf -c $< -o $@ + -g -O2 -Wall -fno-stack-protector \ + --target=bpf -c $< -o $@ $(Q)$(LLVM_STRIP) -g $@ $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) @@ -204,11 +231,6 @@ $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/src/kernel/bpf/disasm.c $(OUTPUT)disasm.o: $(srctree)/src/kernel/bpf/disasm.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ -$(OUTPUT)feature.o: -ifneq ($(feature-zlib), 1) - $(error "No zlib found") -endif - $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ @@ -266,3 +288,6 @@ FORCE: .PHONY: all FORCE bootstrap clean install-bin install uninstall .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all + +# Delete partially updated (corrupted) files on error +.DELETE_ON_ERROR: diff --git a/src/Makefile.feature b/src/Makefile.feature index a7b7077..d091cda 100644 --- a/src/Makefile.feature +++ b/src/Makefile.feature @@ -3,95 +3,161 @@ pound := \# CFLAGS_BACKUP := $(CFLAGS) +CFLAGS := $(EXTRA_CFLAGS) ifneq ($(LLVM),) CFLAGS += -Wno-unused-command-line-argument endif -### feature-clang-bpf-co-re +ifeq ($(V),1) + LOG=$(warning $(1)) + LOG_RES = (echo $(1) && >&2 echo result: $(1)) + define detect + $(warning $(1) && $(call LOG_RES,1) || $(call LOG_RES,0)) + $(shell $(1) && $(call LOG_RES,1) || $(call LOG_RES,0)) + endef +else + LOG= + LOG_RES = (echo $(1)) + define detect + $(shell $(1) 2>&1 && $(call LOG_RES,1) || $(call LOG_RES,0)) + endef + QUIET_STDERR := 2>/dev/null +endif -feature-clang-bpf-co-re := \ - $(shell printf '%s\n' 'struct s { int i; } __attribute__((preserve_access_index)); struct s foo;' | \ - $(CLANG) -g -target bpf -S -o - -x c - 2>/dev/null | grep -q BTF_KIND_VAR && echo 1) +### feature-clang-bpf-co-re -### feature-reallocarray +CLANG_BPF_CO_RE_PROBE_CMD = \ + printf '%s\n' 'struct s { int i; } __attribute__((preserve_access_index)); struct s foo;' | \ + $(CLANG) -g -target bpf -S -o - -x c - $(QUIET_STDERR) | grep -q BTF_KIND_VAR -# This mirror re-implements reallocarray(), so the function is always available. -feature-reallocarray := 1 +ifneq ($(findstring clang-bpf-co-re,$(FEATURE_TESTS)),) +$(call LOG,Probing: feature-clang-bpf-co-re) +feature-clang-bpf-co-re := \ + $(findstring 1,$(call detect,$(CLANG_BPF_CO_RE_PROBE_CMD))) +endif # clang-bpf-co-re ### feature-libbfd +ifneq ($(findstring libbfd,$(FEATURE_TESTS)),) LIBBFD_PROBE := '$(pound)include <bfd.h>\n' LIBBFD_PROBE += 'int main(void) {' LIBBFD_PROBE += ' bfd_demangle(0, 0, 0);' LIBBFD_PROBE += ' return 0;' LIBBFD_PROBE += '}' +LIBBFD_PROBE_CMD = printf '%b\n' $(LIBBFD_PROBE) | \ + $(CC) $(CFLAGS) -Wall -Werror -x c - $(1) -o /dev/null >/dev/null define libbfd_build - $(shell printf '%b\n' $(LIBBFD_PROBE) | \ - $(CC) $(CFLAGS) -Wall -Werror $(LDFLAGS) -x c - $(1) -S -o - >/dev/null 2>&1 \ - && echo 1) + $(call detect,$(LIBBFD_PROBE_CMD)) endef +$(call LOG,Probing: feature-libbfd) feature-libbfd := \ $(findstring 1,$(call libbfd_build,-lbfd -ldl)) ifneq ($(feature-libbfd),1) + $(call LOG,Probing: feature-libbfd-liberty) feature-libbfd-liberty := \ $(findstring 1,$(call libbfd_build,-lbfd -ldl -liberty)) ifneq ($(feature-libbfd-liberty),1) - $(findstring 1,feature-libbfd-liberty-z := \ - $(call libbfd_build,-lbfd -ldl -liberty -lz)) + $(call LOG,Probing: feature-libbfd-liberty-z) + feature-libbfd-liberty-z := \ + $(findstring 1,$(call libbfd_build,-lbfd -ldl -liberty -lz)) endif endif HAS_LIBBFD := $(findstring 1, \ $(feature-libbfd)$(feature-libbfd-liberty)$(feature-libbfd-liberty-z)) +endif # libbfd ### feature-disassembler-four-args +ifneq ($(findstring disassembler-four-args,$(FEATURE_TESTS)),) DISASSEMBLER_PROBE := '$(pound)include <dis-asm.h>\n' DISASSEMBLER_PROBE += 'int main(void) {' DISASSEMBLER_PROBE += ' disassembler((enum bfd_architecture)0, 0, 0, NULL);' DISASSEMBLER_PROBE += ' return 0;' DISASSEMBLER_PROBE += '}' +DISASSEMBLER_PROBE_CMD = printf '%b\n' $(1) | \ + $(CC) $(CFLAGS) -Wall -Werror -x c - -lbfd -lopcodes -S -o - >/dev/null define disassembler_build - $(shell printf '%b\n' $(DISASSEMBLER_PROBE) | \ - $(CC) $(CFLAGS) -Wall -Werror $(LDFLAGS) -x c - -lbfd -lopcodes -S -o - >/dev/null 2>&1 \ - && echo 1) + $(call detect,$(DISASSEMBLER_PROBE_CMD)) endef -feature-disassembler-four-args := $(findstring 1, $(call disassembler_build)) - -### feature-zlib +$(call LOG,Probing: feature-disassembler-four-args) +feature-disassembler-four-args := \ + $(findstring 1, $(call disassembler_build,$(DISASSEMBLER_PROBE))) +endif # disassembler-four-args -ZLIB_PROBE := '$(pound)include <zlib.h>\n' -ZLIB_PROBE += 'int main(void) {' -ZLIB_PROBE += ' gzopen(NULL, "r");' -ZLIB_PROBE += ' return 0;' -ZLIB_PROBE += '}' +### feature-disassembler-init-styled -define zlib_build - $(shell printf '%b\n' $(ZLIB_PROBE) | \ - $(CC) $(CFLAGS) -Wall -Werror $(LDFLAGS) -x c - -lz -S -o - >/dev/null 2>&1 \ - && echo 1) -endef +ifneq ($(findstring disassembler-init-styled,$(FEATURE_TESTS)),) +DISASSEMBLER_STYLED_PROBE := '$(pound)include <dis-asm.h>\n' +DISASSEMBLER_STYLED_PROBE += 'int main(void) {' +DISASSEMBLER_STYLED_PROBE += ' init_disassemble_info(NULL, 0, NULL, NULL);' +DISASSEMBLER_STYLED_PROBE += ' return 0;' +DISASSEMBLER_STYLED_PROBE += '}' -feature-zlib := $(findstring 1, $(call zlib_build)) +$(call LOG,Probing: feature-disassembler-styled) +feature-disassembler-init-styled := \ + $(findstring 1, $(call disassembler_build,$(DISASSEMBLER_STYLED_PROBE))) +endif # disassembler-init-styled ### feature-libcap +ifneq ($(findstring libcap,$(FEATURE_TESTS)),) LIBCAP_PROBE := '$(pound)include <sys/capability.h>\n' LIBCAP_PROBE += 'int main(void) {' LIBCAP_PROBE += ' cap_free(0);' LIBCAP_PROBE += ' return 0;' LIBCAP_PROBE += '}' +LIBCAP_PROBE_CMD = printf '%b\n' $(LIBCAP_PROBE) | \ + $(CC) $(CFLAGS) -Wall -Werror -x c - -lcap -S -o - >/dev/null define libcap_build - $(shell printf '%b\n' $(LIBCAP_PROBE) | \ - $(CC) $(CFLAGS) -Wall -Werror $(LDFLAGS) -x c - -lcap -S -o - >/dev/null 2>&1 \ - && echo 1) + $(call detect,$(LIBCAP_PROBE_CMD)) endef +$(call LOG,Probing: feature-libcap) feature-libcap := $(findstring 1, $(call libcap_build)) +endif # libcap + +### feature-llvm + +ifneq ($(findstring llvm,$(FEATURE_TESTS)),) +LLVM_PROBE := '$(pound)include <llvm-c/Core.h>\n' +LLVM_PROBE += '$(pound)include <llvm-c/TargetMachine.h>\n' +LLVM_PROBE += 'int main(void) {' +LLVM_PROBE += ' char *triple = LLVMNormalizeTargetTriple("");' +LLVM_PROBE += ' LLVMDisposeMessage(triple);' +LLVM_PROBE += ' return 0;' +LLVM_PROBE += '}' + +# We need some adjustments for the flags. +# - $(CFLAGS) was set to parent $(EXTRA_CFLAGS) at the beginning of this file. +# - $(EXTRA_LDFLAGS) from parent Makefile should be kept as well. +# - Libraries to use depend on whether we have a static or shared version of +# LLVM, pass the llvm-config flag and adjust the list of libraries +# accordingly. +FEATURE_LLVM_CFLAGS := $(CFLAGS) $(shell $(LLVM_CONFIG) --cflags 2>/dev/null) +FEATURE_LLVM_LIBS := $(shell $(LLVM_CONFIG) --libs target 2>/dev/null) +ifeq ($(shell $(LLVM_CONFIG) --shared-mode 2>/dev/null),static) + FEATURE_LLVM_LIBS += $(shell $(LLVM_CONFIG) --system-libs target 2>/dev/null) + FEATURE_LLVM_LIBS += -lstdc++ +endif +FEATURE_LDFLAGS := $(EXTRA_LDFLAGS) $(shell $(LLVM_CONFIG) --ldflags 2>/dev/null) + +LLVM_PROBE_CMD = printf '%b\n' $(LLVM_PROBE) | \ + $(CC) $(FEATURE_LLVM_CFLAGS) $(FEATURE_LDFLAGS) \ + -Wall -Werror -x c - $(FEATURE_LLVM_LIBS) \ + -o /dev/null >/dev/null + +define llvm_build + $(call detect,$(LLVM_PROBE_CMD)) +endef + +$(call LOG,Probing: feature-llvm) +feature-llvm := $(findstring 1, $(call llvm_build)) +endif # llvm ### Print detection results @@ -106,7 +172,8 @@ feature_print_status = $(eval $(print_status)) $(info $(MSG)) $(call feature_print_status,$(HAS_LIBBFD),libbfd) -$(foreach feature,$(filter-out libbfd,$(FEATURE_DISPLAY)), \ +$(foreach feature,$(filter-out libbfd%,$(FEATURE_DISPLAY)), \ $(call feature_print_status,$(feature-$(feature)),$(feature))) CFLAGS := $(CFLAGS_BACKUP) +undefine LOG LOG_RES diff --git a/src/Makefile.include b/src/Makefile.include index ec3df48..d01b7d1 100644 --- a/src/Makefile.include +++ b/src/Makefile.include @@ -7,16 +7,21 @@ endif LLVM_VERSION ?= CLANG ?= clang$(LLVM_VERSION) +LLVM_CONFIG ?= llvm-config$(LLVM_VERSION) LLVM_STRIP ?= llvm-strip$(LLVM_VERSION) ifneq ($(LLVM),) + $(if $(findstring default,$(origin AR)),$(eval AR := llvm-ar$(LLVM_VERSION))) $(if $(findstring default,$(origin CC)),$(eval CC := clang$(LLVM_VERSION))) $(if $(findstring default,$(origin LD)),$(eval LD := ld.lld$(LLVM_VERSION))) + HOSTAR ?= llvm-ar HOSTCC ?= clang HOSTLD ?= ld.lld else + $(if $(findstring default,$(origin AR)),$(eval AR = $(CROSS_COMPILE)$(AR))) $(if $(findstring default,$(origin CC)),$(eval CC = $(CROSS_COMPILE)$(CC))) $(if $(findstring default,$(origin LD)),$(eval LD = $(CROSS_COMPILE)$(LD))) + HOSTAR ?= ar HOSTCC ?= gcc HOSTLD ?= ld endif @@ -40,11 +40,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", [BTF_KIND_TYPE_TAG] = "TYPE_TAG", -}; - -struct btf_attach_point { - __u32 obj_id; - __u32 btf_id; + [BTF_KIND_ENUM64] = "ENUM64", }; static const char *btf_int_enc_str(__u8 encoding) @@ -212,15 +208,18 @@ static int dump_btf_type(const struct btf *btf, __u32 id, case BTF_KIND_ENUM: { const struct btf_enum *v = (const void *)(t + 1); __u16 vlen = BTF_INFO_VLEN(t->info); + const char *encoding; int i; + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; if (json_output) { + jsonw_string_field(w, "encoding", encoding); jsonw_uint_field(w, "size", t->size); jsonw_uint_field(w, "vlen", vlen); jsonw_name(w, "values"); jsonw_start_array(w); } else { - printf(" size=%u vlen=%u", t->size, vlen); + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); } for (i = 0; i < vlen; i++, v++) { const char *name = btf_str(btf, v->name_off); @@ -228,10 +227,57 @@ static int dump_btf_type(const struct btf *btf, __u32 id, if (json_output) { jsonw_start_object(w); jsonw_string_field(w, "name", name); - jsonw_uint_field(w, "val", v->val); + if (btf_kflag(t)) + jsonw_int_field(w, "val", v->val); + else + jsonw_uint_field(w, "val", v->val); jsonw_end_object(w); } else { - printf("\n\t'%s' val=%u", name, v->val); + if (btf_kflag(t)) + printf("\n\t'%s' val=%d", name, v->val); + else + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *v = btf_enum64(t); + __u16 vlen = btf_vlen(t); + const char *encoding; + int i; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + __u64 val = ((__u64)v->val_hi32 << 32) | v->val_lo32; + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + if (btf_kflag(t)) + jsonw_int_field(w, "val", val); + else + jsonw_uint_field(w, "val", val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%lldLL", name, + (unsigned long long)val); + else + printf("\n\t'%s' val=%lluULL", name, + (unsigned long long)val); } } if (json_output) @@ -421,9 +467,8 @@ static int dump_btf_c(const struct btf *btf, int err = 0, i; d = btf_dump__new(btf, btf_dump_printf, NULL, NULL); - err = libbpf_get_error(d); - if (err) - return err; + if (!d) + return -errno; printf("#ifndef __VMLINUX_H__\n"); printf("#define __VMLINUX_H__\n"); @@ -459,6 +504,49 @@ done: return err; } +static const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; + +static struct btf *get_vmlinux_btf_from_sysfs(void) +{ + struct btf *base; + + base = btf__parse(sysfs_vmlinux, NULL); + if (!base) + p_err("failed to parse vmlinux BTF at '%s': %d\n", + sysfs_vmlinux, -errno); + + return base; +} + +#define BTF_NAME_BUFF_LEN 64 + +static bool btf_is_kernel_module(__u32 btf_id) +{ + struct bpf_btf_info btf_info = {}; + char btf_name[BTF_NAME_BUFF_LEN]; + int btf_fd; + __u32 len; + int err; + + btf_fd = bpf_btf_get_fd_by_id(btf_id); + if (btf_fd < 0) { + p_err("can't get BTF object by id (%u): %s", btf_id, strerror(errno)); + return false; + } + + len = sizeof(btf_info); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); + close(btf_fd); + if (err) { + p_err("can't get BTF (ID %u) object info: %s", btf_id, strerror(errno)); + return false; + } + + return btf_info.kernel_btf && strncmp(btf_name, "vmlinux", sizeof(btf_name)) != 0; +} + static int do_dump(int argc, char **argv) { struct btf *btf = NULL, *base = NULL; @@ -468,7 +556,7 @@ static int do_dump(int argc, char **argv) __u32 btf_id = -1; const char *src; int fd = -1; - int err; + int err = 0; if (!REQ_ARGS(2)) { usage(); @@ -518,7 +606,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) return -1; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info: %s", strerror(errno)); goto done; @@ -536,25 +624,17 @@ static int do_dump(int argc, char **argv) NEXT_ARG(); } else if (is_prefix(src, "file")) { const char sysfs_prefix[] = "/sys/kernel/btf/"; - const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; if (!base_btf && strncmp(*argv, sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0 && - strcmp(*argv, sysfs_vmlinux) != 0) { - base = btf__parse(sysfs_vmlinux, NULL); - if (libbpf_get_error(base)) { - p_err("failed to parse vmlinux BTF at '%s': %ld\n", - sysfs_vmlinux, libbpf_get_error(base)); - base = NULL; - } - } + strcmp(*argv, sysfs_vmlinux) != 0) + base = get_vmlinux_btf_from_sysfs(); btf = btf__parse_split(*argv, base ?: base_btf); - err = libbpf_get_error(btf); - if (err) { - btf = NULL; + if (!btf) { + err = -errno; p_err("failed to load BTF from %s: %s", - *argv, strerror(err)); + *argv, strerror(errno)); goto done; } NEXT_ARG(); @@ -591,10 +671,16 @@ static int do_dump(int argc, char **argv) } if (!btf) { + if (!base_btf && btf_is_kernel_module(btf_id)) { + p_info("Warning: valid base BTF was not specified with -B option, falling back to standard base BTF (%s)", + sysfs_vmlinux); + base_btf = get_vmlinux_btf_from_sysfs(); + } + btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); - err = libbpf_get_error(btf); - if (err) { - p_err("get btf by id (%u): %s", btf_id, strerror(err)); + if (!btf) { + err = -errno; + p_err("get btf by id (%u): %s", btf_id, strerror(errno)); goto done; } } @@ -703,7 +789,10 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, } memset(info, 0, *len); - err = bpf_obj_get_info_by_fd(fd, info, len); + if (type == BPF_OBJ_PROG) + err = bpf_prog_get_info_by_fd(fd, info, len); + else + err = bpf_map_get_info_by_fd(fd, info, len); close(fd); if (err) { p_err("can't get %s info: %s", names[type], @@ -726,11 +815,10 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, if (!btf_id) continue; - err = hashmap__append(tab, u32_as_hash_field(btf_id), - u32_as_hash_field(id)); + err = hashmap__append(tab, btf_id, id); if (err) { p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s", - btf_id, id, strerror(errno)); + btf_id, id, strerror(-err)); goto err_free; } } @@ -786,17 +874,13 @@ show_btf_plain(struct bpf_btf_info *info, int fd, printf("size %uB", info->btf_size); n = 0; - hashmap__for_each_key_entry(btf_prog_table, entry, - u32_as_hash_field(info->id)) { - printf("%s%u", n++ == 0 ? " prog_ids " : ",", - hash_field_as_u32(entry->value)); + hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " prog_ids " : ",", entry->value); } n = 0; - hashmap__for_each_key_entry(btf_map_table, entry, - u32_as_hash_field(info->id)) { - printf("%s%u", n++ == 0 ? " map_ids " : ",", - hash_field_as_u32(entry->value)); + hashmap__for_each_key_entry(btf_map_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " map_ids " : ",", entry->value); } emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); @@ -818,17 +902,15 @@ show_btf_json(struct bpf_btf_info *info, int fd, jsonw_name(json_wtr, "prog_ids"); jsonw_start_array(json_wtr); /* prog_ids */ - hashmap__for_each_key_entry(btf_prog_table, entry, - u32_as_hash_field(info->id)) { - jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); + hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { + jsonw_uint(json_wtr, entry->value); } jsonw_end_array(json_wtr); /* prog_ids */ jsonw_name(json_wtr, "map_ids"); jsonw_start_array(json_wtr); /* map_ids */ - hashmap__for_each_key_entry(btf_map_table, entry, - u32_as_hash_field(info->id)) { - jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); + hashmap__for_each_key_entry(btf_map_table, entry, info->id) { + jsonw_uint(json_wtr, entry->value); } jsonw_end_array(json_wtr); /* map_ids */ @@ -852,7 +934,7 @@ show_btf(int fd, struct hashmap *btf_prog_table, int err; memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get BTF object info: %s", strerror(errno)); return -1; @@ -864,7 +946,7 @@ show_btf(int fd, struct hashmap *btf_prog_table, info.name = ptr_to_u64(name); len = sizeof(info); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get BTF object info: %s", strerror(errno)); return -1; diff --git a/src/btf_dumper.c b/src/btf_dumper.c index f5dddf8..1b7f697 100644 --- a/src/btf_dumper.c +++ b/src/btf_dumper.c @@ -57,7 +57,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, if (prog_fd < 0) goto print; - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (err) goto print; @@ -70,12 +70,12 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, info.func_info_rec_size = finfo_rec_size; info.func_info = ptr_to_u64(&finfo); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (err) goto print; prog_btf = btf__load_from_kernel_by_id(info.btf_id); - if (libbpf_get_error(prog_btf)) + if (!prog_btf) goto print; func_type = btf__type_by_id(prog_btf, finfo.type_id); if (!func_type || !btf_is_func(func_type)) @@ -182,6 +182,32 @@ static int btf_dumper_enum(const struct btf_dumper *d, return 0; } +static int btf_dumper_enum64(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum64 *enums = btf_enum64(t); + __u32 val_lo32, val_hi32; + __u64 value; + __u16 i; + + value = *(__u64 *)data; + val_lo32 = (__u32)value; + val_hi32 = value >> 32; + + for (i = 0; i < btf_vlen(t); i++) { + if (val_lo32 == enums[i].val_lo32 && val_hi32 == enums[i].val_hi32) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + static bool is_str_array(const struct btf *btf, const struct btf_array *arr, const char *s) { @@ -426,7 +452,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, *(char *)data); break; case BTF_INT_BOOL: - jsonw_bool(jw, *(int *)data); + jsonw_bool(jw, *(bool *)data); break; default: /* shouldn't happen */ @@ -542,6 +568,8 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, return btf_dumper_array(d, type_id, data); case BTF_KIND_ENUM: return btf_dumper_enum(d, t, data); + case BTF_KIND_ENUM64: + return btf_dumper_enum64(d, t, data); case BTF_KIND_PTR: btf_dumper_ptr(d, t, data); return 0; @@ -618,6 +646,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, btf__name_by_offset(btf, t->name_off)); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: BTF_PRINT_ARG("enum %s ", btf__name_by_offset(btf, t->name_off)); break; @@ -792,3 +821,86 @@ void btf_dump_linfo_json(const struct btf *btf, BPF_LINE_INFO_LINE_COL(linfo->line_col)); } } + +static void dotlabel_puts(const char *s) +{ + for (; *s; ++s) { + switch (*s) { + case '\\': + case '"': + case '{': + case '}': + case '<': + case '>': + case '|': + case ' ': + putchar('\\'); + fallthrough; + default: + putchar(*s); + } + } +} + +static const char *shorten_path(const char *path) +{ + const unsigned int MAX_PATH_LEN = 32; + size_t len = strlen(path); + const char *shortpath; + + if (len <= MAX_PATH_LEN) + return path; + + /* Search for last '/' under the MAX_PATH_LEN limit */ + shortpath = strchr(path + len - MAX_PATH_LEN, '/'); + if (shortpath) { + if (shortpath < path + strlen("...")) + /* We removed a very short prefix, e.g. "/w", and we'll + * make the path longer by prefixing with the ellipsis. + * Not worth it, keep initial path. + */ + return path; + return shortpath; + } + + /* File base name length is > MAX_PATH_LEN, search for last '/' */ + shortpath = strrchr(path, '/'); + if (shortpath) + return shortpath; + + return path; +} + +void btf_dump_linfo_dotlabel(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (!line || !strlen(line)) + return; + line = ltrim(line); + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + const char *shortfile; + + /* More forgiving on file because linum option is + * expected to provide more info than the already + * available src line. + */ + if (!file) + shortfile = ""; + else + shortfile = shorten_path(file); + + printf("; [%s", shortfile > file ? "..." : ""); + dotlabel_puts(shortfile); + printf(" line:%u col:%u]\\l\\\n", + BPF_LINE_INFO_LINE_NUM(linfo->line_col), + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } + + printf("; "); + dotlabel_puts(line); + printf("\\l\\\n"); +} @@ -380,7 +380,9 @@ static void cfg_destroy(struct cfg *cfg) } } -static void draw_bb_node(struct func_node *func, struct bb_node *bb) +static void +draw_bb_node(struct func_node *func, struct bb_node *bb, struct dump_data *dd, + bool opcodes, bool linum) { const char *shape; @@ -398,13 +400,10 @@ static void draw_bb_node(struct func_node *func, struct bb_node *bb) printf("EXIT"); } else { unsigned int start_idx; - struct dump_data dd = {}; - - printf("{"); - kernel_syms_load(&dd); + printf("{\\\n"); start_idx = bb->head - func->start; - dump_xlated_for_graph(&dd, bb->head, bb->tail, start_idx); - kernel_syms_destroy(&dd); + dump_xlated_for_graph(dd, bb->head, bb->tail, start_idx, + opcodes, linum); printf("}"); } @@ -430,12 +429,14 @@ static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb) } } -static void func_output_bb_def(struct func_node *func) +static void +func_output_bb_def(struct func_node *func, struct dump_data *dd, + bool opcodes, bool linum) { struct bb_node *bb; list_for_each_entry(bb, &func->bbs, l) { - draw_bb_node(func, bb); + draw_bb_node(func, bb, dd, opcodes, linum); } } @@ -455,7 +456,8 @@ static void func_output_edges(struct func_node *func) func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX); } -static void cfg_dump(struct cfg *cfg) +static void +cfg_dump(struct cfg *cfg, struct dump_data *dd, bool opcodes, bool linum) { struct func_node *func; @@ -463,14 +465,15 @@ static void cfg_dump(struct cfg *cfg) list_for_each_entry(func, &cfg->funcs, l) { printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n", func->idx, func->idx); - func_output_bb_def(func); + func_output_bb_def(func, dd, opcodes, linum); func_output_edges(func); printf("}\n"); } printf("}\n"); } -void dump_xlated_cfg(void *buf, unsigned int len) +void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) { struct bpf_insn *insn = buf; struct cfg cfg; @@ -479,7 +482,7 @@ void dump_xlated_cfg(void *buf, unsigned int len) if (cfg_build(&cfg, insn, len)) return; - cfg_dump(&cfg); + cfg_dump(&cfg, dd, opcodes, linum); cfg_destroy(&cfg); } @@ -4,6 +4,9 @@ #ifndef __BPF_TOOL_CFG_H #define __BPF_TOOL_CFG_H -void dump_xlated_cfg(void *buf, unsigned int len); +#include "xlated_dumper.h" + +void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); #endif /* __BPF_TOOL_CFG_H */ diff --git a/src/cgroup.c b/src/cgroup.c index effe136..ac846b0 100644 --- a/src/cgroup.c +++ b/src/cgroup.c @@ -15,43 +15,92 @@ #include <unistd.h> #include <bpf/bpf.h> +#include <bpf/btf.h> #include "main.h" #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ - " sock_ops | device | bind4 | bind6 |\n" \ - " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | getpeername4 | getpeername6 |\n" \ - " getsockname4 | getsockname6 | sendmsg4 |\n" \ - " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt |\n" \ - " sock_release }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { cgroup_inet_ingress | cgroup_inet_egress |\n" \ + " cgroup_inet_sock_create | cgroup_sock_ops |\n" \ + " cgroup_device | cgroup_inet4_bind |\n" \ + " cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \ + " cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \ + " cgroup_inet6_connect | cgroup_inet4_getpeername |\n" \ + " cgroup_inet6_getpeername | cgroup_inet4_getsockname |\n" \ + " cgroup_inet6_getsockname | cgroup_udp4_sendmsg |\n" \ + " cgroup_udp6_sendmsg | cgroup_udp4_recvmsg |\n" \ + " cgroup_udp6_recvmsg | cgroup_sysctl |\n" \ + " cgroup_getsockopt | cgroup_setsockopt |\n" \ + " cgroup_inet_sock_release }" static unsigned int query_flags; +static struct btf *btf_vmlinux; +static __u32 btf_vmlinux_id; static enum bpf_attach_type parse_attach_type(const char *str) { + const char *attach_type_str; enum bpf_attach_type type; - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - if (attach_type_name[type] && - is_prefix(str, attach_type_name[type])) + for (type = 0; ; type++) { + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!attach_type_str) + break; + if (!strcmp(str, attach_type_str)) + return type; + } + + /* Also check traditionally used attach type strings. For these we keep + * allowing prefixed usage. + */ + for (type = 0; ; type++) { + attach_type_str = bpf_attach_type_input_str(type); + if (!attach_type_str) + break; + if (is_prefix(str, attach_type_str)) return type; } return __MAX_BPF_ATTACH_TYPE; } +static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) +{ + struct bpf_btf_info btf_info = {}; + __u32 btf_len = sizeof(btf_info); + char name[16] = {}; + int err; + int fd; + + btf_info.name = ptr_to_u64(name); + btf_info.name_len = sizeof(name); + + fd = bpf_btf_get_fd_by_id(attach_btf_obj_id); + if (fd < 0) + return; + + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_len); + if (err) + goto out; + + if (btf_info.kernel_btf && strncmp(name, "vmlinux", sizeof(name)) == 0) + btf_vmlinux_id = btf_info.id; + +out: + close(fd); +} + static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { char prog_name[MAX_PROG_FULL_NAME]; + const char *attach_btf_name = NULL; struct bpf_prog_info info = {}; + const char *attach_type_str; __u32 info_len = sizeof(info); int prog_fd; @@ -59,31 +108,58 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, if (prog_fd < 0) return -1; - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { close(prog_fd); return -1; } + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + + if (btf_vmlinux) { + if (!btf_vmlinux_id) + guess_vmlinux_btf_id(info.attach_btf_obj_id); + + if (btf_vmlinux_id == info.attach_btf_obj_id && + info.attach_btf_id < btf__type_cnt(btf_vmlinux)) { + const struct btf_type *t = + btf__type_by_id(btf_vmlinux, info.attach_btf_id); + attach_btf_name = + btf__name_by_offset(btf_vmlinux, t->name_off); + } + } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(json_wtr, "attach_type", - attach_type_name[attach_type]); + if (attach_type_str) + jsonw_string_field(json_wtr, "attach_type", attach_type_str); else jsonw_uint_field(json_wtr, "attach_type", attach_type); - jsonw_string_field(json_wtr, "attach_flags", - attach_flags_str); + if (!(query_flags & BPF_F_QUERY_EFFECTIVE)) + jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); jsonw_string_field(json_wtr, "name", prog_name); + if (attach_btf_name) + jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name); + jsonw_uint_field(json_wtr, "attach_btf_obj_id", info.attach_btf_obj_id); + jsonw_uint_field(json_wtr, "attach_btf_id", info.attach_btf_id); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("%-15s", attach_type_name[attach_type]); + if (attach_type_str) + printf("%-15s", attach_type_str); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, prog_name); + if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf(" %-15s", prog_name); + else + printf(" %-15s %-15s", attach_flags_str, prog_name); + if (attach_btf_name) + printf(" %-15s", attach_btf_name); + else if (info.attach_btf_id) + printf(" attach_btf_obj_id=%d attach_btf_id=%d", + info.attach_btf_obj_id, info.attach_btf_id); + printf("\n"); } close(prog_fd); @@ -122,47 +198,90 @@ static int cgroup_has_attached_progs(int cgroup_fd) return no_prog ? 0 : 1; } + +static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_ids[1024] = {0}; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) + show_bpf_prog(prog_ids[iter], type, NULL, level); + + return 0; +} + static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_attach_flags[1024] = {0}; const char *attach_flags_str; __u32 prog_ids[1024] = {0}; - __u32 prog_cnt, iter; - __u32 attach_flags; char buf[32]; + __u32 iter; int ret; - prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, - prog_ids, &prog_cnt); + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + p.prog_attach_flags = prog_attach_flags; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); if (ret) return ret; - if (prog_cnt == 0) + if (p.prog_cnt == 0) return 0; - switch (attach_flags) { - case BPF_F_ALLOW_MULTI: - attach_flags_str = "multi"; - break; - case BPF_F_ALLOW_OVERRIDE: - attach_flags_str = "override"; - break; - case 0: - attach_flags_str = ""; - break; - default: - snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); - attach_flags_str = buf; - } + for (iter = 0; iter < p.prog_cnt; iter++) { + __u32 attach_flags; + + attach_flags = prog_attach_flags[iter] ?: p.attach_flags; + + switch (attach_flags) { + case BPF_F_ALLOW_MULTI: + attach_flags_str = "multi"; + break; + case BPF_F_ALLOW_OVERRIDE: + attach_flags_str = "override"; + break; + case 0: + attach_flags_str = ""; + break; + default: + snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); + attach_flags_str = buf; + } - for (iter = 0; iter < prog_cnt; iter++) show_bpf_prog(prog_ids[iter], type, attach_flags_str, level); + } return 0; } +static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + return query_flags & BPF_F_QUERY_EFFECTIVE ? + show_effective_bpf_progs(cgroup_fd, type, level) : + show_attached_bpf_progs(cgroup_fd, type, level); +} + static int do_show(int argc, char **argv) { enum bpf_attach_type type; @@ -210,10 +329,13 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name"); else printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType", "AttachFlags", "Name"); + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { /* * Not all attach types may be supported, so it's expected, @@ -221,7 +343,7 @@ static int do_show(int argc, char **argv) * If we were able to get the show for at least one * attach type, let's return 0. */ - if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0) + if (show_bpf_progs(cgroup_fd, type, 0) == 0) ret = 0; } @@ -277,8 +399,9 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, printf("%s\n", fpath); } + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) - show_attached_bpf_progs(cgroup_fd, type, ftw->level); + show_bpf_progs(cgroup_fd, type, ftw->level); if (errno == EINVAL) /* Last attach type does not support query. @@ -352,6 +475,11 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%s\n" + "%-8s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "Name"); else printf("%s\n" "%-8s %-15s %-15s %-15s\n", diff --git a/src/common.c b/src/common.c index 606743c..cc6e6aa 100644 --- a/src/common.c +++ b/src/common.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <ctype.h> #include <errno.h> #include <fcntl.h> @@ -13,14 +15,17 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <linux/limits.h> -#include <linux/magic.h> #include <net/if.h> #include <sys/mount.h> #include <sys/resource.h> #include <sys/stat.h> #include <sys/vfs.h> +#include <linux/filter.h> +#include <linux/limits.h> +#include <linux/magic.h> +#include <linux/unistd.h> + #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ @@ -32,52 +37,6 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif -const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", - [BPF_CGROUP_INET_SOCK_RELEASE] = "sock_release", - [BPF_CGROUP_SOCK_OPS] = "sock_ops", - [BPF_CGROUP_DEVICE] = "device", - [BPF_CGROUP_INET4_BIND] = "bind4", - [BPF_CGROUP_INET6_BIND] = "bind6", - [BPF_CGROUP_INET4_CONNECT] = "connect4", - [BPF_CGROUP_INET6_CONNECT] = "connect6", - [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", - [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", - [BPF_CGROUP_INET4_GETPEERNAME] = "getpeername4", - [BPF_CGROUP_INET6_GETPEERNAME] = "getpeername6", - [BPF_CGROUP_INET4_GETSOCKNAME] = "getsockname4", - [BPF_CGROUP_INET6_GETSOCKNAME] = "getsockname6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", - [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", - [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", - [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", - [BPF_LIRC_MODE2] = "lirc_mode2", - [BPF_FLOW_DISSECTOR] = "flow_dissector", - [BPF_TRACE_RAW_TP] = "raw_tp", - [BPF_TRACE_FENTRY] = "fentry", - [BPF_TRACE_FEXIT] = "fexit", - [BPF_MODIFY_RETURN] = "mod_ret", - [BPF_LSM_MAC] = "lsm_mac", - [BPF_SK_LOOKUP] = "sk_lookup", - [BPF_TRACE_ITER] = "trace_iter", - [BPF_XDP_DEVMAP] = "xdp_devmap", - [BPF_XDP_CPUMAP] = "xdp_cpumap", - [BPF_XDP] = "xdp", - [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", - [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", - [BPF_PERF_EVENT] = "perf_event", -}; - void p_err(const char *fmt, ...) { va_list ap; @@ -109,7 +68,7 @@ void p_info(const char *fmt, ...) va_end(ap); } -static bool is_bpffs(char *path) +static bool is_bpffs(const char *path) { struct statfs st_fs; @@ -119,11 +78,73 @@ static bool is_bpffs(char *path) return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; } +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and programs. This was done in + * commit 97306be45fbe ("Merge branch 'switch to memcg-based memory + * accounting'"), in Linux 5.11. + * + * Libbpf also offers to probe for memcg-based accounting vs rlimit, but does + * so by checking for the availability of a given BPF helper and this has + * failed on some kernels with backports in the past, see commit 6b4384ff1088 + * ("Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK""). + * Instead, we can probe by lowering the process-based rlimit to 0, trying to + * load a BPF object, and resetting the rlimit. If the load succeeds then + * memcg-based accounting is supported. + * + * This would be too dangerous to do in the library, because multithreaded + * applications might attempt to load items while the rlimit is at 0. Given + * that bpftool is single-threaded, this is fine to do here. + */ +static bool known_to_need_rlimit(void) +{ + struct rlimit rlim_init, rlim_cur_zero = {}; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd, err; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim_init)) + return false; + + /* Drop the soft limit to zero. We maintain the hard limit to its + * current value, because lowering it would be a permanent operation + * for unprivileged users. + */ + rlim_cur_zero.rlim_max = rlim_init.rlim_max; + if (setrlimit(RLIMIT_MEMLOCK, &rlim_cur_zero)) + return false; + + /* Do not use bpf_prog_load() from libbpf here, because it calls + * bump_rlimit_memlock(), interfering with the current probe. + */ + prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + err = errno; + + /* reset soft rlimit to its initial value */ + setrlimit(RLIMIT_MEMLOCK, &rlim_init); + + if (prog_fd < 0) + return err == EPERM; + + close(prog_fd); + return false; +} + void set_max_rlimit(void) { struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - setrlimit(RLIMIT_MEMLOCK, &rinf); + if (known_to_need_rlimit()) + setrlimit(RLIMIT_MEMLOCK, &rinf); } static int @@ -223,13 +244,16 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name) +int mount_bpffs_for_pin(const char *name, bool is_dir) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; + if (is_dir && is_bpffs(name)) + return err; + file = malloc(strlen(name) + 1); if (!file) { p_err("mem alloc failed"); @@ -265,7 +289,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name); + err = mount_bpffs_for_pin(name, false); if (err) return err; @@ -281,6 +305,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; @@ -297,6 +324,7 @@ const char *get_fd_type_name(enum bpf_obj_type type) [BPF_OBJ_UNKNOWN] = "unknown", [BPF_OBJ_PROG] = "prog", [BPF_OBJ_MAP] = "map", + [BPF_OBJ_LINK] = "link", }; if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) @@ -328,7 +356,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, info.func_info_rec_size = sizeof(finfo); info.func_info = ptr_to_u64(&finfo); - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) goto copy_name; prog_btf = btf__load_from_kernel_by_id(info.btf_id); @@ -463,7 +491,7 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, goto out_close; memset(&pinned_info, 0, sizeof(pinned_info)); - if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len)) + if (bpf_prog_get_info_by_fd(fd, &pinned_info, &len)) goto out_close; path = strdup(fpath); @@ -472,10 +500,11 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, goto out_close; } - err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path); + err = hashmap__append(build_fn_table, pinned_info.id, path); if (err) { p_err("failed to append entry to hashmap for ID %u, path '%s': %s", pinned_info.id, path, strerror(errno)); + free(path); goto out_close; } @@ -523,7 +552,7 @@ void delete_pinned_obj_table(struct hashmap *map) return; hashmap__for_each_entry(map, entry, bkt) - free(entry->value); + free(entry->pvalue); hashmap__free(map); } @@ -605,12 +634,11 @@ static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name) } const char * -ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, - const char **opt) +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt) { + __maybe_unused int device_id; char devname[IF_NAMESIZE]; int vendor_id; - int device_id; if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) { p_err("Can't get net device name for ifindex %d: %s", ifindex, @@ -625,6 +653,7 @@ ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, } switch (vendor_id) { +#ifdef HAVE_LIBBFD_SUPPORT case 0x19ee: device_id = read_sysfs_netdev_hex_int(devname, "device"); if (device_id != 0x4000 && @@ -633,8 +662,10 @@ ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch"); *opt = "ctx4"; return "NFP-6xxx"; +#endif /* HAVE_LIBBFD_SUPPORT */ + /* No NFP support in LLVM, we have no valid triple to return. */ default: - p_err("Can't get bfd arch name for device vendor id 0x%04x", + p_err("Can't get arch name for device vendor id 0x%04x", vendor_id); return NULL; } @@ -702,6 +733,7 @@ print_all_levels(__maybe_unused enum libbpf_print_level level, static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) { + char prog_name[MAX_PROG_FULL_NAME]; unsigned int id = 0; int fd, nb_fds = 0; void *tmp; @@ -727,19 +759,27 @@ static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) goto err_close_fds; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info (%u): %s", id, strerror(errno)); goto err_close_fd; } - if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || - (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + if (tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) { close(fd); continue; } + if (!tag) { + get_prog_full_name(&info, fd, prog_name, + sizeof(prog_name)); + if (strncmp(nametag, prog_name, sizeof(prog_name))) { + close(fd); + continue; + } + } + if (nb_fds > 0) { tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); if (!tmp) { @@ -800,7 +840,7 @@ int prog_parse_fds(int *argc, char ***argv, int **fds) NEXT_ARGP(); name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + if (strlen(name) > MAX_PROG_FULL_NAME - 1) { p_err("can't parse name"); return -1; } @@ -879,7 +919,7 @@ static int map_fd_by_name(char *name, int **fds) goto err_close_fds; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info (%u): %s", id, strerror(errno)); @@ -989,7 +1029,8 @@ exit_free: return fd; } -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len) { int err; int fd; @@ -998,7 +1039,7 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) if (fd < 0) return -1; - err = bpf_obj_get_info_by_fd(fd, info, info_len); + err = bpf_map_get_info_by_fd(fd, info, info_len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -1008,12 +1049,62 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) return fd; } -size_t hash_fn_for_key_as_id(const void *key, void *ctx) +size_t hash_fn_for_key_as_id(long key, void *ctx) { - return (size_t)key; + return key; } -bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx) +bool equal_fn_for_key_as_id(long k1, long k2, void *ctx) { return k1 == k2; } + +const char *bpf_attach_type_input_str(enum bpf_attach_type t) +{ + switch (t) { + case BPF_CGROUP_INET_INGRESS: return "ingress"; + case BPF_CGROUP_INET_EGRESS: return "egress"; + case BPF_CGROUP_INET_SOCK_CREATE: return "sock_create"; + case BPF_CGROUP_INET_SOCK_RELEASE: return "sock_release"; + case BPF_CGROUP_SOCK_OPS: return "sock_ops"; + case BPF_CGROUP_DEVICE: return "device"; + case BPF_CGROUP_INET4_BIND: return "bind4"; + case BPF_CGROUP_INET6_BIND: return "bind6"; + case BPF_CGROUP_INET4_CONNECT: return "connect4"; + case BPF_CGROUP_INET6_CONNECT: return "connect6"; + case BPF_CGROUP_INET4_POST_BIND: return "post_bind4"; + case BPF_CGROUP_INET6_POST_BIND: return "post_bind6"; + case BPF_CGROUP_INET4_GETPEERNAME: return "getpeername4"; + case BPF_CGROUP_INET6_GETPEERNAME: return "getpeername6"; + case BPF_CGROUP_INET4_GETSOCKNAME: return "getsockname4"; + case BPF_CGROUP_INET6_GETSOCKNAME: return "getsockname6"; + case BPF_CGROUP_UDP4_SENDMSG: return "sendmsg4"; + case BPF_CGROUP_UDP6_SENDMSG: return "sendmsg6"; + case BPF_CGROUP_SYSCTL: return "sysctl"; + case BPF_CGROUP_UDP4_RECVMSG: return "recvmsg4"; + case BPF_CGROUP_UDP6_RECVMSG: return "recvmsg6"; + case BPF_CGROUP_GETSOCKOPT: return "getsockopt"; + case BPF_CGROUP_SETSOCKOPT: return "setsockopt"; + case BPF_TRACE_RAW_TP: return "raw_tp"; + case BPF_TRACE_FENTRY: return "fentry"; + case BPF_TRACE_FEXIT: return "fexit"; + case BPF_MODIFY_RETURN: return "mod_ret"; + case BPF_SK_REUSEPORT_SELECT: return "sk_skb_reuseport_select"; + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return "sk_skb_reuseport_select_or_migrate"; + default: return libbpf_bpf_attach_type_str(t); + } +} + +int pathname_concat(char *buf, int buf_sz, const char *path, + const char *name) +{ + int len; + + len = snprintf(buf, buf_sz, "%s/%s", path, name); + if (len < 0) + return -EINVAL; + if (len >= buf_sz) + return -ENAMETOOLONG; + + return 0; +} diff --git a/src/feature.c b/src/feature.c index 9c894b1..edda4fc 100644 --- a/src/feature.c +++ b/src/feature.c @@ -3,6 +3,7 @@ #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> #include <net/if.h> @@ -45,6 +46,11 @@ static bool run_as_unprivileged; /* Miscellaneous utility functions */ +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + static bool check_procfs(void) { struct statfs st_fs; @@ -135,12 +141,38 @@ static void print_end_section(void) /* Probing functions */ -static int read_procfs(const char *path) +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -162,7 +194,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -175,20 +207,23 @@ static void probe_unprivileged_disabled(void) printf("bpf() syscall for unprivileged users is enabled\n"); break; case 1: - printf("bpf() syscall restricted to privileged users\n"); + printf("bpf() syscall restricted to privileged users (without recovery)\n"); + break; + case 2: + printf("bpf() syscall restricted to privileged users (admin can change)\n"); break; case -1: printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -210,7 +245,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -218,7 +253,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -240,7 +275,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -248,7 +283,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -267,14 +302,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -287,7 +322,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } @@ -451,16 +486,16 @@ static void probe_kernel_image_config(const char *define_prefix) } } -end_parse: - if (file) - gzclose(file); - for (i = 0; i < ARRAY_SIZE(options); i++) { if (define_prefix && !options[i].macro_dump) continue; print_kernel_option(options[i].name, values[i], define_prefix); free(values[i]); } + +end_parse: + if (file) + gzclose(file); } static bool probe_bpf_syscall(const char *define_prefix) @@ -478,9 +513,43 @@ static bool probe_bpf_syscall(const char *define_prefix) return res; } +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + static void -probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, - const char *define_prefix, __u32 ifindex) +probe_prog_type(enum bpf_prog_type prog_type, const char *prog_type_str, + bool *supported_types, const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF program_type "; @@ -488,11 +557,19 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, bool res; if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL) > 0; } - res = libbpf_probe_bpf_prog_type(prog_type, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -503,27 +580,43 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, supported_types[prog_type] |= res; - if (!prog_type_name[prog_type]) { - p_info("program type name not found (type %d)", prog_type); - return; - } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(prog_type_name[prog_type]) > maxlen) { + if (strlen(prog_type_str) > maxlen) { p_info("program type name too long"); return; } - sprintf(feat_name, "have_%s_prog_type", prog_type_name[prog_type]); - sprintf(define_name, "%s_prog_type", prog_type_name[prog_type]); + sprintf(feat_name, "have_%s_prog_type", prog_type_str); + sprintf(define_name, "%s_prog_type", prog_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, prog_type_name[prog_type]); + sprintf(plain_desc, "%s%s", plain_comment, prog_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + static void -probe_map_type(enum bpf_map_type map_type, const char *define_prefix, - __u32 ifindex) +probe_map_type(enum bpf_map_type map_type, char const *map_type_str, + const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF map_type "; @@ -531,35 +624,65 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, bool res; if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; - } + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } - res = libbpf_probe_bpf_map_type(map_type, NULL); + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL) > 0; + } /* Probe result depends on the success of map creation, no additional * check required for unprivileged users */ - if (!map_type_name[map_type]) { - p_info("map type name not found (type %d)", map_type); - return; - } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(map_type_name[map_type]) > maxlen) { + if (strlen(map_type_str) > maxlen) { p_info("map type name too long"); return; } - sprintf(feat_name, "have_%s_map_type", map_type_name[map_type]); - sprintf(define_name, "%s_map_type", map_type_name[map_type]); + sprintf(feat_name, "have_%s_map_type", map_type_str); + sprintf(define_name, "%s_map_type", map_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, map_type_name[map_type]); + sprintf(plain_desc, "%s%s", plain_comment, map_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } -static void +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + +static bool probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, const char *ptype_name, __u32 ifindex) @@ -567,12 +690,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, bool res = false; if (supported_type) { - if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; - } - - res = libbpf_probe_bpf_helper(prog_type, id, NULL); + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL) > 0; #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for * unprivileged users check that we did not fail because of @@ -594,15 +715,18 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, if (res) printf("\n\t- %s", helper_name[id]); } + + return res; } static void -probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, +probe_helpers_for_progtype(enum bpf_prog_type prog_type, + const char *prog_type_str, bool supported_type, const char *define_prefix, __u32 ifindex) { - const char *ptype_name = prog_type_name[prog_type]; char feat_name[128]; unsigned int id; + bool probe_res = false; if (ifindex) /* Only test helpers for offload-able program types */ @@ -615,12 +739,12 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, } if (json_output) { - sprintf(feat_name, "%s_available_helpers", ptype_name); + sprintf(feat_name, "%s_available_helpers", prog_type_str); jsonw_name(json_wtr, feat_name); jsonw_start_array(json_wtr); } else if (!define_prefix) { printf("eBPF helpers supported for program type %s:", - ptype_name); + prog_type_str); } for (id = 1; id < ARRAY_SIZE(helper_name); id++) { @@ -633,18 +757,27 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, case BPF_FUNC_probe_write_user: if (!full_mode) continue; - /* fallthrough */ + fallthrough; default: - probe_helper_for_progtype(prog_type, supported_type, - define_prefix, id, ptype_name, + probe_res |= probe_helper_for_progtype(prog_type, supported_type, + define_prefix, id, prog_type_str, ifindex); } } if (json_output) jsonw_end_array(json_wtr); - else if (!define_prefix) + else if (!define_prefix) { printf("\n"); + if (!probe_res) { + if (!supported_type) + printf("\tProgram type not supported\n"); + else + printf("\tCould not determine which helpers are available\n"); + } + } + + } static void @@ -802,30 +935,47 @@ static void section_program_types(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("program_types", "Scanning eBPF program types...", "/*** eBPF program types ***/", define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) - probe_prog_type(i, supported_types, define_prefix, ifindex); + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_prog_type(prog_type, prog_type_str, supported_types, define_prefix, + ifindex); + } print_end_section(); } static void section_map_types(const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int map_type = BPF_MAP_TYPE_UNSPEC; + const char *map_type_str; print_start_section("map_types", "Scanning eBPF map types...", "/*** eBPF map types ***/", define_prefix); - for (i = BPF_MAP_TYPE_UNSPEC + 1; i < map_type_name_size; i++) - probe_map_type(i, define_prefix, ifindex); + while (true) { + map_type++; + map_type_str = libbpf_bpf_map_type_str(map_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!map_type_str) + break; + + probe_map_type(map_type, map_type_str, define_prefix, ifindex); + } print_end_section(); } @@ -833,7 +983,8 @@ static void section_map_types(const char *define_prefix, __u32 ifindex) static void section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("helpers", "Scanning eBPF helper functions...", @@ -855,9 +1006,18 @@ section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", define_prefix, define_prefix, define_prefix, define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) - probe_helpers_for_progtype(i, supported_types[i], define_prefix, + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_helpers_for_progtype(prog_type, prog_type_str, + supported_types[prog_type], + define_prefix, ifindex); + } print_end_section(); } @@ -987,7 +1147,7 @@ exit_free: return res; #else /* Detection assumes user has specific privileges. - * We do not use libpcap so let's approximate, and restrict usage to + * We do not use libcap so let's approximate, and restrict usage to * root user only. */ if (geteuid()) { @@ -1098,6 +1258,58 @@ exit_close_json: return 0; } +static const char *get_helper_name(unsigned int id) +{ + if (id >= ARRAY_SIZE(helper_name)) + return NULL; + + return helper_name[id]; +} + +static int do_list_builtins(int argc, char **argv) +{ + const char *(*get_name)(unsigned int id); + unsigned int id = 0; + + if (argc < 1) + usage(); + + if (is_prefix(*argv, "prog_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_prog_type_str; + } else if (is_prefix(*argv, "map_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_map_type_str; + } else if (is_prefix(*argv, "attach_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_attach_type_str; + } else if (is_prefix(*argv, "link_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_link_type_str; + } else if (is_prefix(*argv, "helpers")) { + get_name = get_helper_name; + } else { + p_err("expected 'prog_types', 'map_types', 'attach_types', 'link_types' or 'helpers', got: %s", *argv); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + const char *name; + + name = get_name(id++); + if (!name) + break; + if (json_output) + jsonw_string(json_wtr, name); + else + printf("%s\n", name); + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1107,9 +1319,11 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s list_builtins GROUP\n" " %1$s %2$s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" + " GROUP := { prog_types | map_types | attach_types | link_types | helpers }\n" " " HELP_SPEC_OPTIONS " }\n" "", bin_name, argv[-2]); @@ -1118,8 +1332,9 @@ static int do_help(int argc, char **argv) } static const struct cmd cmds[] = { - { "probe", do_probe }, - { "help", do_help }, + { "probe", do_probe }, + { "list_builtins", do_list_builtins }, + { "help", do_help }, { 0 } }; @@ -14,6 +14,7 @@ #include <unistd.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> @@ -63,11 +64,11 @@ static void get_obj_name(char *name, const char *file) sanitize_identifier(name); } -static void get_header_guard(char *guard, const char *obj_name) +static void get_header_guard(char *guard, const char *obj_name, const char *suffix) { int i; - sprintf(guard, "__%s_SKEL_H__", obj_name); + sprintf(guard, "__%s_%s__", obj_name, suffix); for (i = 0; guard[i]; i++) guard[i] = toupper(guard[i]); } @@ -208,48 +209,58 @@ static int codegen_datasec_def(struct bpf_object *obj, return 0; } +static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident) +{ + int n = btf__type_cnt(btf), i; + char sec_ident[256]; + + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) + return t; + } + return NULL; +} + +static bool is_internal_mmapable_map(const struct bpf_map *map, char *buf, size_t sz) +{ + if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + return false; + + if (!get_map_ident(map, buf, sz)) + return false; + + return true; +} + static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) { struct btf *btf = bpf_object__btf(obj); - int n = btf__type_cnt(btf); struct btf_dump *d; struct bpf_map *map; const struct btf_type *sec; - char sec_ident[256], map_ident[256]; - int i, err = 0; + char map_ident[256]; + int err = 0; d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); - err = libbpf_get_error(d); - if (err) - return err; + if (!d) + return -errno; bpf_object__for_each_map(map, obj) { /* only generate definitions for memory-mapped internal maps */ - if (!bpf_map__is_internal(map)) - continue; - if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) continue; - if (!get_map_ident(map, map_ident, sizeof(map_ident))) - continue; - - sec = NULL; - for (i = 1; i < n; i++) { - const struct btf_type *t = btf__type_by_id(btf, i); - const char *name; - - if (!btf_is_datasec(t)) - continue; - - name = btf__str_by_offset(btf, t->name_off); - if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) - continue; - - if (strcmp(sec_ident, map_ident) == 0) { - sec = t; - break; - } - } + sec = find_type_for_map(btf, map_ident); /* In some cases (e.g., sections like .rodata.cst16 containing * compiler allocated string constants only) there will be @@ -274,6 +285,96 @@ out: return err; } +static bool btf_is_ptr_to_func_proto(const struct btf *btf, + const struct btf_type *v) +{ + return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type)); +} + +static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec, *var; + const struct btf_var_secinfo *sec_var; + int i, err = 0, vlen; + char map_ident[256], sec_ident[256]; + bool strip_mods = false, needs_typeof = false; + const char *sec_name, *var_name; + __u32 var_type_id; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("typeof("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); + } + +out: + btf_dump__free(d); + return err; +} + static void codegen(const char *template, ...) { const char *src, *end; @@ -362,6 +463,72 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) return map_sz; } +/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ +static void codegen_asserts(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct bpf_map *map; + struct btf_var_secinfo *sec_var; + int i, vlen; + const struct btf_type *sec; + char map_ident[256], var_ident[256]; + + if (!btf) + return; + + codegen("\ + \n\ + __attribute__((unused)) static void \n\ + %1$s__assert(struct %1$s *s __attribute__((unused))) \n\ + { \n\ + #ifdef __cplusplus \n\ + #define _Static_assert static_assert \n\ + #endif \n\ + ", obj_name); + + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) { + /* best effort, couldn't find the type for this map */ + continue; + } + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + long var_size; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + var_size = btf__resolve_size(btf, var->type); + if (var_size < 0) + continue; + + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t_Static_assert(sizeof(s->%s->%s) == %ld, \"unexpected size of '%s'\");\n", + map_ident, var_ident, var_size, var_ident); + } + } + codegen("\ + \n\ + #ifdef __cplusplus \n\ + #undef _Static_assert \n\ + #endif \n\ + } \n\ + "); +} + static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) { struct bpf_program *prog; @@ -384,6 +551,7 @@ static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); break; case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER) printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n"); else @@ -472,7 +640,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) continue; if (bpf_map__is_internal(map) && (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) - printf("\tmunmap(skel->%1$s, %2$zd);\n", + printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n", ident, bpf_map_mmap_sz(map)); codegen("\ \n\ @@ -481,7 +649,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) } codegen("\ \n\ - free(skel); \n\ + skel_free(skel); \n\ } \n\ ", obj_name); @@ -525,7 +693,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h { \n\ struct %1$s *skel; \n\ \n\ - skel = calloc(sizeof(*skel), 1); \n\ + skel = skel_alloc(sizeof(*skel)); \n\ if (!skel) \n\ goto cleanup; \n\ skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ @@ -535,27 +703,22 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h const void *mmap_data = NULL; size_t mmap_size = 0; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; codegen("\ - \n\ - skel->%1$s = \n\ - mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\ - MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\ - if (skel->%1$s == (void *) -1) \n\ - goto cleanup; \n\ - memcpy(skel->%1$s, (void *)\"\\ \n\ - ", ident, bpf_map_mmap_sz(map)); + \n\ + skel->%1$s = skel_prep_map_data((void *)\"\\ \n\ + ", ident); mmap_data = bpf_map__initial_value(map, &mmap_size); print_hex(mmap_data, mmap_size); - printf("\", %2$zd);\n" - "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n", - ident, mmap_size); + codegen("\ + \n\ + \", %1$zd, %2$zd); \n\ + if (!skel->%3$s) \n\ + goto cleanup; \n\ + skel->maps.%3$s.initial_value = (__u64) (long) skel->%3$s;\n\ + ", bpf_map_mmap_sz(map), mmap_size, ident); } codegen("\ \n\ @@ -599,11 +762,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h bpf_object__for_each_map(map, obj) { const char *mmap_flags; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) @@ -611,9 +770,13 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h else mmap_flags = "PROT_READ | PROT_WRITE"; - printf("\tskel->%1$s =\n" - "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n" - "\t\t\tskel->maps.%1$s.map_fd, 0);\n", + codegen("\ + \n\ + skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value, \n\ + %2$zd, %3$s, skel->maps.%1$s.map_fd);\n\ + if (!skel->%1$s) \n\ + return -ENOMEM; \n\ + ", ident, bpf_map_mmap_sz(map), mmap_flags); } codegen("\ @@ -635,8 +798,11 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h } \n\ return skel; \n\ } \n\ + \n\ ", obj_name); + codegen_asserts(obj, obj_name); + codegen("\ \n\ \n\ @@ -648,10 +814,99 @@ out: return err; } +static void +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +{ + struct bpf_map *map; + char ident[256]; + size_t i; + + if (!map_cnt) + return; + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (mmaped && is_internal_mmapable_map(map, ident, sizeof(ident))) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } +} + +static void +codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links) +{ + struct bpf_program *prog; + int i; + + if (!prog_cnt) + return; + + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + ", + i, bpf_program__name(prog)); + + if (populate_links) { + codegen("\ + \n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + } + i++; + } +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; - size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; @@ -720,13 +975,12 @@ static int do_skeleton(int argc, char **argv) /* log_level1 + log_level2 + stats, but not stable UAPI */ opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_mem(obj_data, file_sz, &opts); - err = libbpf_get_error(obj); - if (err) { + if (!obj) { char err_buf[256]; + err = -errno; libbpf_strerror(err, err_buf, sizeof(err_buf)); p_err("failed to open BPF object file: %s", err_buf); - obj = NULL; goto out; } @@ -742,17 +996,15 @@ static int do_skeleton(int argc, char **argv) prog_cnt++; } - get_header_guard(header_guard, obj_name); + get_header_guard(header_guard, obj_name, "SKEL_H"); if (use_loader) { codegen("\ \n\ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ - /* THIS FILE IS AUTOGENERATED! */ \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ #ifndef %2$s \n\ #define %2$s \n\ \n\ - #include <stdlib.h> \n\ - #include <bpf/bpf.h> \n\ #include <bpf/skel_internal.h> \n\ \n\ struct %1$s { \n\ @@ -765,7 +1017,7 @@ static int do_skeleton(int argc, char **argv) \n\ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ \n\ - /* THIS FILE IS AUTOGENERATED! */ \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ #ifndef %2$s \n\ #define %2$s \n\ \n\ @@ -830,6 +1082,16 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\ + static inline struct %1$s *open_and_load(); \n\ + static inline int load(struct %1$s *skel); \n\ + static inline int attach(struct %1$s *skel); \n\ + static inline void detach(struct %1$s *skel); \n\ + static inline void destroy(struct %1$s *skel); \n\ + static inline const void *elf_bytes(size_t *sz); \n\ + #endif /* __cplusplus */ \n\ }; \n\ \n\ static void \n\ @@ -911,7 +1173,7 @@ static int do_skeleton(int argc, char **argv) static inline void \n\ %1$s__detach(struct %1$s *obj) \n\ { \n\ - return bpf_object__detach_skeleton(obj->skeleton); \n\ + bpf_object__detach_skeleton(obj->skeleton); \n\ } \n\ ", obj_name @@ -926,10 +1188,13 @@ static int do_skeleton(int argc, char **argv) %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ - if (!s) \n\ + if (!s) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -937,76 +1202,20 @@ static int do_skeleton(int argc, char **argv) ", obj_name ); - if (map_cnt) { - codegen("\ - \n\ - \n\ - /* maps */ \n\ - s->map_cnt = %zu; \n\ - s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ - goto err; \n\ - ", - map_cnt - ); - i = 0; - bpf_object__for_each_map(map, obj) { - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - codegen("\ - \n\ - \n\ - s->maps[%zu].name = \"%s\"; \n\ - s->maps[%zu].map = &obj->maps.%s; \n\ - ", - i, bpf_map__name(map), i, ident); - /* memory-mapped internal maps */ - if (bpf_map__is_internal(map) && - (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) { - printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", - i, ident); - } - i++; - } - } - if (prog_cnt) { - codegen("\ - \n\ - \n\ - /* programs */ \n\ - s->prog_cnt = %zu; \n\ - s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ - goto err; \n\ - ", - prog_cnt - ); - i = 0; - bpf_object__for_each_program(prog, obj) { - codegen("\ - \n\ - \n\ - s->progs[%1$zu].name = \"%2$s\"; \n\ - s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ - s->progs[%1$zu].link = &obj->links.%2$s;\n\ - ", - i, bpf_program__name(prog)); - i++; - } - } + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + codegen("\ \n\ \n\ - s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ + s->data = %2$s__elf_bytes(&s->data_sz); \n\ \n\ obj->skeleton = s; \n\ return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ + return err; \n\ } \n\ \n\ static inline const void *%2$s__elf_bytes(size_t *sz) \n\ @@ -1024,7 +1233,25 @@ static int do_skeleton(int argc, char **argv) \"; \n\ } \n\ \n\ - #endif /* %s */ \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object_open_opts *opts) { return %1$s__open_opts(opts); }\n\ + struct %1$s *%1$s::open_and_load() { return %1$s__open_and_load(); } \n\ + int %1$s::load(struct %1$s *skel) { return %1$s__load(skel); } \n\ + int %1$s::attach(struct %1$s *skel) { return %1$s__attach(skel); } \n\ + void %1$s::detach(struct %1$s *skel) { %1$s__detach(skel); } \n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); } \n\ + const void *%1$s::elf_bytes(size_t *sz) { return %1$s__elf_bytes(sz); } \n\ + #endif /* __cplusplus */ \n\ + \n\ + ", + obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %1$s */ \n\ ", header_guard); err = 0; @@ -1036,6 +1263,311 @@ out: return err; } +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + err = codegen_subskel_datasecs(obj, obj_name); + if (err) + goto out; + + /* emit code that will allocate enough storage for all symbols */ + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object *src);\n\ + static inline void destroy(struct %1$s *skel); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static inline void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + if (skel->subskel) \n\ + bpf_object__destroy_subskeleton(skel->subskel);\n\ + free(skel); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(const struct bpf_object *src) \n\ + { \n\ + struct %1$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + obj_name, var_cnt + ); + + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; + } + } + + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + + codegen("\ + \n\ + \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ + ", + obj_name, header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + static int do_object(int argc, char **argv) { struct bpf_linker *linker; @@ -1060,14 +1592,14 @@ static int do_object(int argc, char **argv) err = bpf_linker__add_file(linker, file, NULL); if (err) { - p_err("failed to link '%s': %s (%d)", file, strerror(err), err); + p_err("failed to link '%s': %s (%d)", file, strerror(errno), errno); goto out; } } err = bpf_linker__finalize(linker); if (err) { - p_err("failed to finalize ELF file: %s (%d)", strerror(err), err); + p_err("failed to finalize ELF file: %s (%d)", strerror(errno), errno); goto out; } @@ -1087,6 +1619,8 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" " %1$s %2$s help\n" "\n" " " HELP_SPEC_OPTIONS " |\n" @@ -1097,10 +1631,699 @@ static int do_help(int argc, char **argv) return 0; } +static int btf_save_raw(const struct btf *btf, const char *path) +{ + const void *data; + FILE *f = NULL; + __u32 data_sz; + int err = 0; + + data = btf__raw_data(btf, &data_sz); + if (!data) + return -ENOMEM; + + f = fopen(path, "wb"); + if (!f) + return -errno; + + if (fwrite(data, 1, data_sz, f) != data_sz) + err = -errno; + + fclose(f); + return err; +} + +struct btfgen_info { + struct btf *src_btf; + struct btf *marked_btf; /* btf structure used to mark used types */ +}; + +static size_t btfgen_hash_fn(long key, void *ctx) +{ + return key; +} + +static bool btfgen_equal_fn(long k1, long k2, void *ctx) +{ + return k1 == k2; +} + +static void btfgen_free_info(struct btfgen_info *info) +{ + if (!info) + return; + + btf__free(info->src_btf); + btf__free(info->marked_btf); + + free(info); +} + +static struct btfgen_info * +btfgen_new_info(const char *targ_btf_path) +{ + struct btfgen_info *info; + int err; + + info = calloc(1, sizeof(*info)); + if (!info) + return NULL; + + info->src_btf = btf__parse(targ_btf_path, NULL); + if (!info->src_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + info->marked_btf = btf__parse(targ_btf_path, NULL); + if (!info->marked_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + return info; + +err_out: + btfgen_free_info(info); + errno = -err; + return NULL; +} + +#define MARKED UINT32_MAX + +static void btfgen_mark_member(struct btfgen_info *info, int type_id, int idx) +{ + const struct btf_type *t = btf__type_by_id(info->marked_btf, type_id); + struct btf_member *m = btf_members(t) + idx; + + m->name_off = MARKED; +} + +static int +btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_pointers) +{ + const struct btf_type *btf_type = btf__type_by_id(info->src_btf, type_id); + struct btf_type *cloned_type; + struct btf_param *param; + struct btf_array *array; + int err, i; + + if (type_id == 0) + return 0; + + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *) btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + /* recursively mark other types needed by it */ + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + break; + case BTF_KIND_PTR: + if (follow_pointers) { + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + } + break; + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + + /* mark array type */ + err = btfgen_mark_type(info, array->type, follow_pointers); + /* mark array's index type */ + err = err ? : btfgen_mark_type(info, array->index_type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_FUNC_PROTO: + /* mark ret type */ + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < btf_vlen(btf_type); i++) { + err = btfgen_mark_type(info, param->type, follow_pointers); + if (err) + return err; + param++; + } + break; + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + struct btf *btf = info->src_btf; + const struct btf_type *btf_type; + struct btf_member *btf_member; + struct btf_array *array; + unsigned int type_id = targ_spec->root_type_id; + int idx, err; + + /* mark root type */ + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + + /* mark types for complex types (arrays, unions, structures) */ + for (int i = 1; i < targ_spec->raw_len; i++) { + /* skip typedefs and mods */ + while (btf_is_mod(btf_type) || btf_is_typedef(btf_type)) { + type_id = btf_type->type; + btf_type = btf__type_by_id(btf, type_id); + } + + switch (btf_kind(btf_type)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + idx = targ_spec->raw_spec[i]; + btf_member = btf_members(btf_type) + idx; + + /* mark member */ + btfgen_mark_member(info, type_id, idx); + + /* mark member's type */ + type_id = btf_member->type; + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + type_id = array->type; + btf_type = btf__type_by_id(btf, type_id); + break; + default: + p_err("unsupported kind: %s (%d)", + btf_kind_str(btf_type), btf_type->type); + return -EINVAL; + } + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + * + * The `behind_ptr` argument is used to stop marking of composite types reached + * through a pointer. This way, we can keep BTF size in check while providing + * reasonable match semantics. + */ +static int btfgen_mark_type_match(struct btfgen_info *info, __u32 type_id, bool behind_ptr) +{ + const struct btf_type *btf_type; + struct btf *btf = info->src_btf; + struct btf_type *cloned_type; + int i, err; + + if (type_id == 0) + return 0; + + btf_type = btf__type_by_id(btf, type_id); + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *)btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(btf_type); + __u16 vlen = btf_vlen(btf_type); + + if (behind_ptr) + break; + + for (i = 0; i < vlen; i++, m++) { + /* mark member */ + btfgen_mark_member(info, type_id, i); + + /* mark member's type */ + err = btfgen_mark_type_match(info, m->type, false); + if (err) + return err; + } + break; + } + case BTF_KIND_CONST: + case BTF_KIND_FWD: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + return btfgen_mark_type_match(info, btf_type->type, behind_ptr); + case BTF_KIND_PTR: + return btfgen_mark_type_match(info, btf_type->type, true); + case BTF_KIND_ARRAY: { + struct btf_array *array; + + array = btf_array(btf_type); + /* mark array type */ + err = btfgen_mark_type_match(info, array->type, false); + /* mark array's index type */ + err = err ? : btfgen_mark_type_match(info, array->index_type, false); + if (err) + return err; + break; + } + case BTF_KIND_FUNC_PROTO: { + __u16 vlen = btf_vlen(btf_type); + struct btf_param *param; + + /* mark ret type */ + err = btfgen_mark_type_match(info, btf_type->type, false); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < vlen; i++) { + err = btfgen_mark_type_match(info, param->type, false); + if (err) + return err; + param++; + } + break; + } + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + */ +static int btfgen_record_type_match_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type_match(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, true); +} + +static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res) +{ + switch (res->relo_kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: + return btfgen_record_field_relo(info, res); + case BPF_CORE_TYPE_ID_LOCAL: /* BPF_CORE_TYPE_ID_LOCAL doesn't require kernel BTF */ + return 0; + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: + return btfgen_record_type_relo(info, res); + case BPF_CORE_TYPE_MATCHES: + return btfgen_record_type_match_relo(info, res); + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: + return btfgen_record_enumval_relo(info, res); + default: + return -EINVAL; + } +} + +static struct bpf_core_cand_list * +btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id) +{ + const struct btf_type *local_type; + struct bpf_core_cand_list *cands = NULL; + struct bpf_core_cand local_cand = {}; + size_t local_essent_len; + const char *local_name; + int err; + + local_cand.btf = local_btf; + local_cand.id = local_id; + + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) { + err = -EINVAL; + goto err_out; + } + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (!local_name) { + err = -EINVAL; + goto err_out; + } + local_essent_len = bpf_core_essential_name_len(local_name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return NULL; + + err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + return cands; + +err_out: + bpf_core_free_cands(cands); + errno = -err; + return NULL; +} + +/* Record relocation information for a single BPF object */ +static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_core_relo *relo; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct btf_ext *btf_ext = NULL; + unsigned int relo_idx; + struct btf *btf = NULL; + size_t i; + int err; + + btf = btf__parse(obj_path, &btf_ext); + if (!btf) { + err = -errno; + p_err("failed to parse BPF object '%s': %s", obj_path, strerror(errno)); + return err; + } + + if (!btf_ext) { + p_err("failed to parse BPF object '%s': section %s not found", + obj_path, BTF_EXT_ELF_SEC); + err = -EINVAL; + goto out; + } + + if (btf_ext->core_relo_info.len == 0) { + err = 0; + goto out; + } + + cand_cache = hashmap__new(btfgen_hash_fn, btfgen_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + for_each_btf_ext_rec(seg, sec, relo_idx, relo) { + struct bpf_core_spec specs_scratch[3] = {}; + struct bpf_core_relo_res targ_res = {}; + struct bpf_core_cand_list *cands = NULL; + const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off); + + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && + !hashmap__find(cand_cache, relo->type_id, &cands)) { + cands = btfgen_find_cands(btf, info->src_btf, relo->type_id); + if (!cands) { + err = -errno; + goto out; + } + + err = hashmap__set(cand_cache, relo->type_id, cands, + NULL, NULL); + if (err) + goto out; + } + + err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands, + specs_scratch, &targ_res); + if (err) + goto out; + + /* specs_scratch[2] is the target spec */ + err = btfgen_record_reloc(info, &specs_scratch[2]); + if (err) + goto out; + } + } + +out: + btf__free(btf); + btf_ext__free(btf_ext); + + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->pvalue); + } + hashmap__free(cand_cache); + } + + return err; +} + +static int btfgen_remap_id(__u32 *type_id, void *ctx) +{ + unsigned int *ids = ctx; + + *type_id = ids[*type_id]; + + return 0; +} + +/* Generate BTF from relocation information previously recorded */ +static struct btf *btfgen_get_btf(struct btfgen_info *info) +{ + struct btf *btf_new = NULL; + unsigned int *ids = NULL; + unsigned int i, n = btf__type_cnt(info->marked_btf); + int err = 0; + + btf_new = btf__new_empty(); + if (!btf_new) { + err = -errno; + goto err_out; + } + + ids = calloc(n, sizeof(*ids)); + if (!ids) { + err = -errno; + goto err_out; + } + + /* first pass: add all marked types to btf_new and add their new ids to the ids map */ + for (i = 1; i < n; i++) { + const struct btf_type *cloned_type, *type; + const char *name; + int new_id; + + cloned_type = btf__type_by_id(info->marked_btf, i); + + if (cloned_type->name_off != MARKED) + continue; + + type = btf__type_by_id(info->src_btf, i); + + /* add members for struct and union */ + if (btf_is_composite(type)) { + struct btf_member *cloned_m, *m; + unsigned short vlen; + int idx_src; + + name = btf__str_by_offset(info->src_btf, type->name_off); + + if (btf_is_struct(type)) + err = btf__add_struct(btf_new, name, type->size); + else + err = btf__add_union(btf_new, name, type->size); + + if (err < 0) + goto err_out; + new_id = err; + + cloned_m = btf_members(cloned_type); + m = btf_members(type); + vlen = btf_vlen(cloned_type); + for (idx_src = 0; idx_src < vlen; idx_src++, cloned_m++, m++) { + /* add only members that are marked as used */ + if (cloned_m->name_off != MARKED) + continue; + + name = btf__str_by_offset(info->src_btf, m->name_off); + err = btf__add_field(btf_new, name, m->type, + btf_member_bit_offset(cloned_type, idx_src), + btf_member_bitfield_size(cloned_type, idx_src)); + if (err < 0) + goto err_out; + } + } else { + err = btf__add_type(btf_new, info->src_btf, type); + if (err < 0) + goto err_out; + new_id = err; + } + + /* add ID mapping */ + ids[i] = new_id; + } + + /* second pass: fix up type ids */ + for (i = 1; i < btf__type_cnt(btf_new); i++) { + struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i); + + err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids); + if (err) + goto err_out; + } + + free(ids); + return btf_new; + +err_out: + btf__free(btf_new); + free(ids); + errno = -err; + return NULL; +} + +/* Create minimized BTF file for a set of BPF objects. + * + * The BTFGen algorithm is divided in two main parts: (1) collect the + * BTF types that are involved in relocations and (2) generate the BTF + * object using the collected types. + * + * In order to collect the types involved in the relocations, we parse + * the BTF and BTF.ext sections of the BPF objects and use + * bpf_core_calc_relo_insn() to get the target specification, this + * indicates how the types and fields are used in a relocation. + * + * Types are recorded in different ways according to the kind of the + * relocation. For field-based relocations only the members that are + * actually used are saved in order to reduce the size of the generated + * BTF file. For type-based relocations empty struct / unions are + * generated and for enum-based relocations the whole type is saved. + * + * The second part of the algorithm generates the BTF object. It creates + * an empty BTF object and fills it with the types recorded in the + * previous step. This function takes care of only adding the structure + * and union members that were marked as used and it also fixes up the + * type IDs on the generated BTF object. + */ +static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[]) +{ + struct btfgen_info *info; + struct btf *btf_new = NULL; + int err, i; + + info = btfgen_new_info(src_btf); + if (!info) { + err = -errno; + p_err("failed to allocate info structure: %s", strerror(errno)); + goto out; + } + + for (i = 0; objspaths[i] != NULL; i++) { + err = btfgen_record_obj(info, objspaths[i]); + if (err) { + p_err("error recording relocations for %s: %s", objspaths[i], + strerror(errno)); + goto out; + } + } + + btf_new = btfgen_get_btf(info); + if (!btf_new) { + err = -errno; + p_err("error generating BTF: %s", strerror(errno)); + goto out; + } + + err = btf_save_raw(btf_new, dst_btf); + if (err) { + p_err("error saving btf file: %s", strerror(errno)); + goto out; + } + +out: + btf__free(btf_new); + btfgen_free_info(info); + + return err; +} + +static int do_min_core_btf(int argc, char **argv) +{ + const char *input, *output, **objs; + int i, err; + + if (!REQ_ARGS(3)) { + usage(); + return -1; + } + + input = GET_ARG(); + output = GET_ARG(); + + objs = (const char **) calloc(argc + 1, sizeof(*objs)); + if (!objs) { + p_err("failed to allocate array for object names"); + return -ENOMEM; + } + + i = 0; + while (argc) + objs[i++] = GET_ARG(); + + err = minimize_btf(input, output, objs); + free(objs); + return err; +} + static const struct cmd cmds[] = { - { "object", do_object }, - { "skeleton", do_skeleton }, - { "help", do_help }, + { "object", do_object }, + { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, + { "min_core_btf", do_min_core_btf}, + { "help", do_help }, { 0 } }; @@ -1,7 +1,10 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (C) 2020 Facebook +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif +#include <errno.h> #include <unistd.h> #include <linux/err.h> #include <bpf/libbpf.h> @@ -46,8 +49,8 @@ static int do_pin(int argc, char **argv) } obj = bpf_object__open(objfile); - err = libbpf_get_error(obj); - if (err) { + if (!obj) { + err = -errno; p_err("can't open objfile %s", objfile); goto close_map_fd; } @@ -60,19 +63,20 @@ static int do_pin(int argc, char **argv) prog = bpf_object__next_program(obj, NULL); if (!prog) { + err = -errno; p_err("can't find bpf program in objfile %s", objfile); goto close_obj; } link = bpf_program__attach_iter(prog, &iter_opts); - err = libbpf_get_error(link); - if (err) { + if (!link) { + err = -errno; p_err("attach_iter failed for program %s", bpf_program__name(prog)); goto close_obj; } - err = mount_bpffs_for_pin(path); + err = mount_bpffs_for_pin(path, false); if (err) goto close_link; diff --git a/src/jit_disasm.c b/src/jit_disasm.c index 24734f2..7b8d9ec 100644 --- a/src/jit_disasm.c +++ b/src/jit_disasm.c @@ -11,43 +11,157 @@ * Licensed under the GNU General Public License, version 2.0 (GPLv2) */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <stdio.h> #include <stdarg.h> #include <stdint.h> #include <stdlib.h> -#include <assert.h> #include <unistd.h> #include <string.h> -#include <bfd.h> -#include <dis-asm.h> #include <sys/stat.h> #include <limits.h> #include <bpf/libbpf.h> +#ifdef HAVE_LLVM_SUPPORT +#include <llvm-c/Core.h> +#include <llvm-c/Disassembler.h> +#include <llvm-c/Target.h> +#include <llvm-c/TargetMachine.h> +#endif + +#ifdef HAVE_LIBBFD_SUPPORT +#include <bfd.h> +#include <dis-asm.h> +#include <tools/dis-asm-compat.h> +#endif + #include "json_writer.h" #include "main.h" -static void get_exec_path(char *tpath, size_t size) +static int oper_count; + +#ifdef HAVE_LLVM_SUPPORT +#define DISASM_SPACER + +typedef LLVMDisasmContextRef disasm_ctx_t; + +static int printf_json(char *s) +{ + s = strtok(s, " \t"); + jsonw_string_field(json_wtr, "operation", s); + + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count = 1; + + while ((s = strtok(NULL, " \t,()")) != 0) { + jsonw_string(json_wtr, s); + oper_count++; + } + return 0; +} + +/* This callback to set the ref_type is necessary to have the LLVM disassembler + * print PC-relative addresses instead of byte offsets for branch instruction + * targets. + */ +static const char * +symbol_lookup_callback(__maybe_unused void *disasm_info, + __maybe_unused uint64_t ref_value, + uint64_t *ref_type, __maybe_unused uint64_t ref_PC, + __maybe_unused const char **ref_name) +{ + *ref_type = LLVMDisassembler_ReferenceType_InOut_None; + return NULL; +} + +static int +init_context(disasm_ctx_t *ctx, const char *arch, + __maybe_unused const char *disassembler_options, + __maybe_unused unsigned char *image, __maybe_unused ssize_t len) +{ + char *triple; + + if (arch) + triple = LLVMNormalizeTargetTriple(arch); + else + triple = LLVMGetDefaultTargetTriple(); + if (!triple) { + p_err("Failed to retrieve triple"); + return -1; + } + *ctx = LLVMCreateDisasm(triple, NULL, 0, NULL, symbol_lookup_callback); + LLVMDisposeMessage(triple); + + if (!*ctx) { + p_err("Failed to create disassembler"); + return -1; + } + + return 0; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + LLVMDisposeMessage(*ctx); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, unsigned char *image, ssize_t len, int pc) +{ + char buf[256]; + int count; + + count = LLVMDisasmInstruction(*ctx, image + pc, len - pc, pc, + buf, sizeof(buf)); + if (json_output) + printf_json(buf); + else + printf("%s", buf); + + return count; +} + +int disasm_init(void) +{ + LLVMInitializeAllTargetInfos(); + LLVMInitializeAllTargetMCs(); + LLVMInitializeAllDisassemblers(); + return 0; +} +#endif /* HAVE_LLVM_SUPPORT */ + +#ifdef HAVE_LIBBFD_SUPPORT +#define DISASM_SPACER "\t" + +typedef struct { + struct disassemble_info *info; + disassembler_ftype disassemble; + bfd *bfdf; +} disasm_ctx_t; + +static int get_exec_path(char *tpath, size_t size) { const char *path = "/proc/self/exe"; ssize_t len; len = readlink(path, tpath, size - 1); - assert(len > 0); + if (len <= 0) + return -1; + tpath[len] = 0; + + return 0; } -static int oper_count; -static int fprintf_json(void *out, const char *fmt, ...) +static int printf_json(void *out, const char *fmt, va_list ap) { - va_list ap; char *s; int err; - va_start(ap, fmt); err = vasprintf(&s, fmt, ap); - va_end(ap); if (err < 0) return -1; @@ -73,37 +187,72 @@ static int fprintf_json(void *out, const char *fmt, ...) return 0; } -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum) +static int fprintf_json(void *out, const char *fmt, ...) { - const struct bpf_line_info *linfo = NULL; - disassembler_ftype disassemble; - struct disassemble_info info; - unsigned int nr_skip = 0; - int count, i, pc = 0; + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int init_context(disasm_ctx_t *ctx, const char *arch, + const char *disassembler_options, + unsigned char *image, ssize_t len) +{ + struct disassemble_info *info; char tpath[PATH_MAX]; bfd *bfdf; - if (!len) - return; - memset(tpath, 0, sizeof(tpath)); - get_exec_path(tpath, sizeof(tpath)); + if (get_exec_path(tpath, sizeof(tpath))) { + p_err("failed to create disassembler (get_exec_path)"); + return -1; + } + + ctx->bfdf = bfd_openr(tpath, NULL); + if (!ctx->bfdf) { + p_err("failed to create disassembler (bfd_openr)"); + return -1; + } + if (!bfd_check_format(ctx->bfdf, bfd_object)) { + p_err("failed to create disassembler (bfd_check_format)"); + goto err_close; + } + bfdf = ctx->bfdf; - bfdf = bfd_openr(tpath, NULL); - assert(bfdf); - assert(bfd_check_format(bfdf, bfd_object)); + ctx->info = malloc(sizeof(struct disassemble_info)); + if (!ctx->info) { + p_err("mem alloc failed"); + goto err_close; + } + info = ctx->info; if (json_output) - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf_json); + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); else - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf); + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); /* Update architecture info for offload. */ if (arch) { @@ -113,28 +262,77 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, bfdf->arch_info = inf; } else { p_err("No libbfd support for %s", arch); - return; + goto err_free; } } - info.arch = bfd_get_arch(bfdf); - info.mach = bfd_get_mach(bfdf); + info->arch = bfd_get_arch(bfdf); + info->mach = bfd_get_mach(bfdf); if (disassembler_options) - info.disassembler_options = disassembler_options; - info.buffer = image; - info.buffer_length = len; + info->disassembler_options = disassembler_options; + info->buffer = image; + info->buffer_length = len; - disassemble_init_for_target(&info); + disassemble_init_for_target(info); #ifdef DISASM_FOUR_ARGS_SIGNATURE - disassemble = disassembler(info.arch, - bfd_big_endian(bfdf), - info.mach, - bfdf); + ctx->disassemble = disassembler(info->arch, + bfd_big_endian(bfdf), + info->mach, + bfdf); #else - disassemble = disassembler(bfdf); + ctx->disassemble = disassembler(bfdf); #endif - assert(disassemble); + if (!ctx->disassemble) { + p_err("failed to create disassembler"); + goto err_free; + } + return 0; + +err_free: + free(info); +err_close: + bfd_close(ctx->bfdf); + return -1; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + free(ctx->info); + bfd_close(ctx->bfdf); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, __maybe_unused unsigned char *image, + __maybe_unused ssize_t len, int pc) +{ + return ctx->disassemble(pc, ctx->info); +} + +int disasm_init(void) +{ + bfd_init(); + return 0; +} +#endif /* HAVE_LIBBPFD_SUPPORT */ + +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) +{ + const struct bpf_line_info *linfo = NULL; + unsigned int nr_skip = 0; + int count, i, pc = 0; + disasm_ctx_t ctx; + + if (!len) + return -1; + + if (init_context(&ctx, arch, disassembler_options, image, len)) + return -1; if (json_output) jsonw_start_array(json_wtr); @@ -159,10 +357,11 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, if (linfo) btf_dump_linfo_plain(btf, linfo, "; ", linum); - printf("%4x:\t", pc); + printf("%4x:" DISASM_SPACER, pc); } - count = disassemble(pc, &info); + count = disassemble_insn(&ctx, image, len, pc); + if (json_output) { /* Operand array, was started in fprintf_json. Before * that, make sure we have a _null_ value if no operand @@ -198,11 +397,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, if (json_output) jsonw_end_array(json_wtr); - bfd_close(bfdf); -} + destroy_context(&ctx); -int disasm_init(void) -{ - bfd_init(); return 0; } diff --git a/src/json_writer.c b/src/json_writer.c index 7fea83b..be37961 100644 --- a/src/json_writer.c +++ b/src/json_writer.c @@ -75,14 +75,11 @@ static void jsonw_puts(json_writer_t *self, const char *str) fputs("\\b", self->out); break; case '\\': - fputs("\\n", self->out); + fputs("\\\\", self->out); break; case '"': fputs("\\\"", self->out); break; - case '\'': - fputs("\\\'", self->out); - break; default: putc(*str, self->out); } diff --git a/src/json_writer.h b/src/json_writer.h index 8ace65c..5aaffd3 100644 --- a/src/json_writer.h +++ b/src/json_writer.h @@ -14,6 +14,7 @@ #include <stdbool.h> #include <stdint.h> #include <stdarg.h> +#include <stdio.h> #include <linux/compiler.h> /* Opaque class structure */ diff --git a/src/kernel/bpf/disasm.c b/src/kernel/bpf/disasm.c index 7b4afb7..49940c2 100644 --- a/src/kernel/bpf/disasm.c +++ b/src/kernel/bpf/disasm.c @@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = { [BPF_END >> 4] = "endian", }; +static const char *const bpf_alu_sign_string[16] = { + [BPF_DIV >> 4] = "s/=", + [BPF_MOD >> 4] = "s%=", +}; + +static const char *const bpf_movsx_string[4] = { + [0] = "(s8)", + [1] = "(s16)", + [3] = "(s32)", +}; + static const char *const bpf_atomic_alu_string[16] = { [BPF_ADD >> 4] = "add", [BPF_AND >> 4] = "and", @@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = { [BPF_DW >> 3] = "u64", }; +static const char *const bpf_ldsx_string[] = { + [BPF_W >> 3] = "s32", + [BPF_H >> 3] = "s16", + [BPF_B >> 3] = "s8", +}; + static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", @@ -128,6 +145,27 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose, insn->imm, insn->dst_reg); } +static void print_bpf_bswap_insn(bpf_insn_print_t verbose, + void *private_data, + const struct bpf_insn *insn) +{ + verbose(private_data, "(%02x) r%d = bswap%d r%d\n", + insn->code, insn->dst_reg, + insn->imm, insn->dst_reg); +} + +static bool is_sdiv_smod(const struct bpf_insn *insn) +{ + return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) && + insn->off == 1; +} + +static bool is_movsx(const struct bpf_insn *insn) +{ + return BPF_OP(insn->code) == BPF_MOV && + (insn->off == 8 || insn->off == 16 || insn->off == 32); +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -138,7 +176,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) - verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code); + print_bpf_bswap_insn(verbose, cbs->private_data, insn); else print_bpf_end_insn(verbose, cbs->private_data, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { @@ -147,17 +185,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { - verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n", + verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], + is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "", class == BPF_ALU ? 'w' : 'r', insn->src_reg); } else { verbose(cbs->private_data, "(%02x) %c%d %s %d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], insn->imm); } } else if (class == BPF_STX) { @@ -218,13 +259,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); } } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); return; } verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + BPF_MODE(insn->code) == BPF_MEM ? + bpf_ldst_string[BPF_SIZE(insn->code) >> 3] : + bpf_ldsx_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (class == BPF_LD) { if (BPF_MODE(insn->code) == BPF_ABS) { @@ -279,6 +322,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP32 | BPF_JA)) { + verbose(cbs->private_data, "(%02x) gotol pc%+d\n", + insn->code, insn->imm); } else if (insn->code == (BPF_JMP | BPF_EXIT)) { verbose(cbs->private_data, "(%02x) exit\n", insn->code); } else if (BPF_SRC(insn->code) == BPF_X) { @@ -3,6 +3,10 @@ #include <errno.h> #include <linux/err.h> +#include <netinet/in.h> +#include <linux/netfilter.h> +#include <linux/netfilter_arp.h> +#include <linux/perf_event.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -12,17 +16,78 @@ #include "json_writer.h" #include "main.h" +#include "xlated_dumper.h" -static const char * const link_type_name[] = { - [BPF_LINK_TYPE_UNSPEC] = "unspec", - [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_LINK_TYPE_TRACING] = "tracing", - [BPF_LINK_TYPE_CGROUP] = "cgroup", - [BPF_LINK_TYPE_ITER] = "iter", - [BPF_LINK_TYPE_NETNS] = "netns", -}; +#define PERF_HW_CACHE_LEN 128 static struct hashmap *link_table; +static struct dump_data dd; + +static const char *perf_type_name[PERF_TYPE_MAX] = { + [PERF_TYPE_HARDWARE] = "hardware", + [PERF_TYPE_SOFTWARE] = "software", + [PERF_TYPE_TRACEPOINT] = "tracepoint", + [PERF_TYPE_HW_CACHE] = "hw-cache", + [PERF_TYPE_RAW] = "raw", + [PERF_TYPE_BREAKPOINT] = "breakpoint", +}; + +const char *event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = "cpu-cycles", + [PERF_COUNT_HW_INSTRUCTIONS] = "instructions", + [PERF_COUNT_HW_CACHE_REFERENCES] = "cache-references", + [PERF_COUNT_HW_CACHE_MISSES] = "cache-misses", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "branch-instructions", + [PERF_COUNT_HW_BRANCH_MISSES] = "branch-misses", + [PERF_COUNT_HW_BUS_CYCLES] = "bus-cycles", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "stalled-cycles-frontend", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "stalled-cycles-backend", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "ref-cycles", +}; + +const char *event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = "cpu-clock", + [PERF_COUNT_SW_TASK_CLOCK] = "task-clock", + [PERF_COUNT_SW_PAGE_FAULTS] = "page-faults", + [PERF_COUNT_SW_CONTEXT_SWITCHES] = "context-switches", + [PERF_COUNT_SW_CPU_MIGRATIONS] = "cpu-migrations", + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = "minor-faults", + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = "major-faults", + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = "alignment-faults", + [PERF_COUNT_SW_EMULATION_FAULTS] = "emulation-faults", + [PERF_COUNT_SW_DUMMY] = "dummy", + [PERF_COUNT_SW_BPF_OUTPUT] = "bpf-output", + [PERF_COUNT_SW_CGROUP_SWITCHES] = "cgroup-switches", +}; + +const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] = { + [PERF_COUNT_HW_CACHE_L1D] = "L1-dcache", + [PERF_COUNT_HW_CACHE_L1I] = "L1-icache", + [PERF_COUNT_HW_CACHE_LL] = "LLC", + [PERF_COUNT_HW_CACHE_DTLB] = "dTLB", + [PERF_COUNT_HW_CACHE_ITLB] = "iTLB", + [PERF_COUNT_HW_CACHE_BPU] = "branch", + [PERF_COUNT_HW_CACHE_NODE] = "node", +}; + +const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] = { + [PERF_COUNT_HW_CACHE_OP_READ] = "load", + [PERF_COUNT_HW_CACHE_OP_WRITE] = "store", + [PERF_COUNT_HW_CACHE_OP_PREFETCH] = "prefetch", +}; + +const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [PERF_COUNT_HW_CACHE_RESULT_ACCESS] = "refs", + [PERF_COUNT_HW_CACHE_RESULT_MISS] = "misses", +}; + +#define perf_event_name(array, id) ({ \ + const char *event_str = NULL; \ + \ + if ((id) < ARRAY_SIZE(array)) \ + event_str = array[id]; \ + event_str; \ +}) static int link_parse_fd(int *argc, char ***argv) { @@ -63,9 +128,12 @@ static int link_parse_fd(int *argc, char ***argv) static void show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) { + const char *link_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - jsonw_string_field(wtr, "type", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + jsonw_string_field(wtr, "type", link_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -74,19 +142,63 @@ show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(wtr, "attach_type", - attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + jsonw_string_field(wtr, "attach_type", attach_type_str); else jsonw_uint_field(wtr, "attach_type", attach_type); } +static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr) +{ + char devname[IF_NAMESIZE] = "(unknown)"; + + if (ifindex) + if_indextoname(ifindex, devname); + else + snprintf(devname, sizeof(devname), "(detached)"); + jsonw_string_field(wtr, "devname", devname); + jsonw_uint_field(wtr, "ifindex", ifindex); +} + static bool is_iter_map_target(const char *target_name) { return strcmp(target_name, "bpf_map_elem") == 0 || strcmp(target_name, "bpf_sk_storage_map") == 0; } +static bool is_iter_cgroup_target(const char *target_name) +{ + return strcmp(target_name, "cgroup") == 0; +} + +static const char *cgroup_order_string(__u32 order) +{ + switch (order) { + case BPF_CGROUP_ITER_ORDER_UNSPEC: + return "order_unspec"; + case BPF_CGROUP_ITER_SELF_ONLY: + return "self_only"; + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + return "descendants_pre"; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + return "descendants_post"; + case BPF_CGROUP_ITER_ANCESTORS_UP: + return "ancestors_up"; + default: /* won't happen */ + return "unknown"; + } +} + +static bool is_iter_task_target(const char *target_name) +{ + return strcmp(target_name, "task") == 0 || + strcmp(target_name, "task_file") == 0 || + strcmp(target_name, "task_vma") == 0; +} + static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) { const char *target_name = u64_to_ptr(info->iter.target_name); @@ -95,6 +207,30 @@ static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) if (is_iter_map_target(target_name)) jsonw_uint_field(wtr, "map_id", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + jsonw_uint_field(wtr, "tid", info->iter.task.tid); + else if (info->iter.task.pid) + jsonw_uint_field(wtr, "pid", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + jsonw_lluint_field(wtr, "cgroup_id", info->iter.cgroup.cgroup_id); + jsonw_string_field(wtr, "order", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(json_wtr, "pf", + info->netfilter.pf); + jsonw_uint_field(json_wtr, "hook", + info->netfilter.hooknum); + jsonw_int_field(json_wtr, "prio", + info->netfilter.priority); + jsonw_uint_field(json_wtr, "flags", + info->netfilter.flags); } static int get_prog_info(int prog_id, struct bpf_prog_info *info) @@ -107,16 +243,167 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info) return prog_fd; memset(info, 0, sizeof(*info)); - err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + err = bpf_prog_get_info_by_fd(prog_fd, info, &len); if (err) p_err("can't get prog info: %s", strerror(errno)); close(prog_fd); return err; } +static int cmp_u64(const void *A, const void *B) +{ + const __u64 *a = A, *b = B; + + return *a - *b; +} + +static void +show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u32 i, j = 0; + __u64 *addrs; + + jsonw_bool_field(json_wtr, "retprobe", + info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN); + jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count); + jsonw_uint_field(json_wtr, "missed", info->kprobe_multi.missed); + jsonw_name(json_wtr, "funcs"); + jsonw_start_array(json_wtr); + addrs = u64_to_ptr(info->kprobe_multi.addrs); + qsort(addrs, info->kprobe_multi.count, sizeof(addrs[0]), cmp_u64); + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != addrs[j]) + continue; + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address); + jsonw_string_field(json_wtr, "func", dd.sym_mapping[i].name); + /* Print null if it is vmlinux */ + if (dd.sym_mapping[i].module[0] == '\0') { + jsonw_name(json_wtr, "module"); + jsonw_null(json_wtr); + } else { + jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module); + } + jsonw_end_object(json_wtr); + if (j++ == info->kprobe_multi.count) + break; + } + jsonw_end_array(json_wtr); +} + +static void +show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_KRETPROBE); + jsonw_uint_field(wtr, "addr", info->perf_event.kprobe.addr); + jsonw_string_field(wtr, "func", + u64_to_ptr(info->perf_event.kprobe.func_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset); + jsonw_uint_field(wtr, "missed", info->perf_event.kprobe.missed); +} + +static void +show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_URETPROBE); + jsonw_string_field(wtr, "file", + u64_to_ptr(info->perf_event.uprobe.file_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset); +} + +static void +show_perf_event_tracepoint_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_string_field(wtr, "tracepoint", + u64_to_ptr(info->perf_event.tracepoint.tp_name)); +} + +static char *perf_config_hw_cache_str(__u64 config) +{ + const char *hw_cache, *result, *op; + char *str = malloc(PERF_HW_CACHE_LEN); + + if (!str) { + p_err("mem alloc failed"); + return NULL; + } + + hw_cache = perf_event_name(evsel__hw_cache, config & 0xff); + if (hw_cache) + snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache); + else + snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff); + + op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff); + if (op) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s-", op); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld-", (config >> 8) & 0xff); + + result = perf_event_name(evsel__hw_cache_result, config >> 16); + if (result) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s", result); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld", config >> 16); + return str; +} + +static const char *perf_config_str(__u32 type, __u64 config) +{ + const char *perf_config; + + switch (type) { + case PERF_TYPE_HARDWARE: + perf_config = perf_event_name(event_symbols_hw, config); + break; + case PERF_TYPE_SOFTWARE: + perf_config = perf_event_name(event_symbols_sw, config); + break; + case PERF_TYPE_HW_CACHE: + perf_config = perf_config_hw_cache_str(config); + break; + default: + perf_config = NULL; + break; + } + return perf_config; +} + +static void +show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + jsonw_string_field(wtr, "event_type", perf_type); + else + jsonw_uint_field(wtr, "event_type", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + jsonw_string_field(wtr, "event_config", perf_config); + else + jsonw_uint_field(wtr, "event_config", config); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); +} + static int show_link_close_json(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; jsonw_start_object(json_wtr); @@ -133,15 +420,17 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < prog_type_name_size) - jsonw_string_field(json_wtr, "prog_type", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + jsonw_string_field(json_wtr, "prog_type", prog_type_str); else - jsonw_uint_field(json_wtr, "prog_type", - prog_info.type); + jsonw_uint_field(json_wtr, "prog_type", prog_info.type); show_link_attach_type_json(info->tracing.attach_type, json_wtr); + jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id); + jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: jsonw_lluint_field(json_wtr, "cgroup_id", @@ -156,6 +445,43 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) info->netns.netns_ino); show_link_attach_type_json(info->netns.attach_type, json_wtr); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_json(info, json_wtr); + break; + case BPF_LINK_TYPE_TCX: + show_link_ifindex_json(info->tcx.ifindex, json_wtr); + show_link_attach_type_json(info->tcx.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_XDP: + show_link_ifindex_json(info->xdp.ifindex, json_wtr); + break; + case BPF_LINK_TYPE_STRUCT_OPS: + jsonw_uint_field(json_wtr, "map_id", + info->struct_ops.map_id); + break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_json(info, json_wtr); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_json(info, json_wtr); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_json(info, json_wtr); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_json(info, json_wtr); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_json(info, json_wtr); + break; + default: + break; + } + break; default: break; } @@ -165,9 +491,8 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hashmap__for_each_key_entry(link_table, entry, - u32_as_hash_field(info->id)) - jsonw_string(json_wtr, entry->value); + hashmap__for_each_key_entry(link_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } @@ -180,23 +505,48 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) static void show_link_header_plain(struct bpf_link_info *info) { + const char *link_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - printf("%s ", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + printf("%s ", link_type_str); else printf("type %u ", info->type); - printf("prog %u ", info->prog_id); + if (info->type == BPF_LINK_TYPE_STRUCT_OPS) + printf("map %u ", info->struct_ops.map_id); + else + printf("prog %u ", info->prog_id); } static void show_link_attach_type_plain(__u32 attach_type) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("attach_type %s ", attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + printf("attach_type %s ", attach_type_str); else printf("attach_type %u ", attach_type); } +static void show_link_ifindex_plain(__u32 ifindex) +{ + char devname[IF_NAMESIZE * 2] = "(unknown)"; + char tmpname[IF_NAMESIZE]; + char *ret = NULL; + + if (ifindex) + ret = if_indextoname(ifindex, tmpname); + else + snprintf(devname, sizeof(devname), "(detached)"); + if (ret) + snprintf(devname, sizeof(devname), "%s(%d)", + tmpname, ifindex); + printf("ifindex %s ", devname); +} + static void show_iter_plain(struct bpf_link_info *info) { const char *target_name = u64_to_ptr(info->iter.target_name); @@ -205,11 +555,197 @@ static void show_iter_plain(struct bpf_link_info *info) if (is_iter_map_target(target_name)) printf("map_id %u ", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + printf("tid %u ", info->iter.task.tid); + else if (info->iter.task.pid) + printf("pid %u ", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + printf("cgroup_id %llu ", info->iter.cgroup.cgroup_id); + printf("order %s ", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +static const char * const pf2name[] = { + [NFPROTO_INET] = "inet", + [NFPROTO_IPV4] = "ip", + [NFPROTO_ARP] = "arp", + [NFPROTO_NETDEV] = "netdev", + [NFPROTO_BRIDGE] = "bridge", + [NFPROTO_IPV6] = "ip6", +}; + +static const char * const inethook2name[] = { + [NF_INET_PRE_ROUTING] = "prerouting", + [NF_INET_LOCAL_IN] = "input", + [NF_INET_FORWARD] = "forward", + [NF_INET_LOCAL_OUT] = "output", + [NF_INET_POST_ROUTING] = "postrouting", +}; + +static const char * const arphook2name[] = { + [NF_ARP_IN] = "input", + [NF_ARP_OUT] = "output", +}; + +void netfilter_dump_plain(const struct bpf_link_info *info) +{ + const char *hookname = NULL, *pfname = NULL; + unsigned int hook = info->netfilter.hooknum; + unsigned int pf = info->netfilter.pf; + + if (pf < ARRAY_SIZE(pf2name)) + pfname = pf2name[pf]; + + switch (pf) { + case NFPROTO_BRIDGE: /* bridge shares numbers with enum nf_inet_hooks */ + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + if (hook < ARRAY_SIZE(inethook2name)) + hookname = inethook2name[hook]; + break; + case NFPROTO_ARP: + if (hook < ARRAY_SIZE(arphook2name)) + hookname = arphook2name[hook]; + default: + break; + } + + if (pfname) + printf("\n\t%s", pfname); + else + printf("\n\tpf: %d", pf); + + if (hookname) + printf(" %s", hookname); + else + printf(", hook %u,", hook); + + printf(" prio %d", info->netfilter.priority); + + if (info->netfilter.flags) + printf(" flags 0x%x", info->netfilter.flags); +} + +static void show_kprobe_multi_plain(struct bpf_link_info *info) +{ + __u32 i, j = 0; + __u64 *addrs; + + if (!info->kprobe_multi.count) + return; + + if (info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN) + printf("\n\tkretprobe.multi "); + else + printf("\n\tkprobe.multi "); + printf("func_cnt %u ", info->kprobe_multi.count); + if (info->kprobe_multi.missed) + printf("missed %llu ", info->kprobe_multi.missed); + addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs); + qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64); + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + if (!dd.sym_count) + return; + + printf("\n\t%-16s %s", "addr", "func [module]"); + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != addrs[j]) + continue; + printf("\n\t%016lx %s", + dd.sym_mapping[i].address, dd.sym_mapping[i].name); + if (dd.sym_mapping[i].module[0] != '\0') + printf(" [%s] ", dd.sym_mapping[i].module); + else + printf(" "); + + if (j++ == info->kprobe_multi.count) + break; + } +} + +static void show_perf_event_kprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.kprobe.func_name); + if (buf[0] == '\0' && !info->perf_event.kprobe.addr) + return; + + if (info->perf_event.type == BPF_PERF_EVENT_KRETPROBE) + printf("\n\tkretprobe "); + else + printf("\n\tkprobe "); + if (info->perf_event.kprobe.addr) + printf("%llx ", info->perf_event.kprobe.addr); + printf("%s", buf); + if (info->perf_event.kprobe.offset) + printf("+%#x", info->perf_event.kprobe.offset); + if (info->perf_event.kprobe.missed) + printf(" missed %llu", info->perf_event.kprobe.missed); + printf(" "); +} + +static void show_perf_event_uprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.uprobe.file_name); + if (buf[0] == '\0') + return; + + if (info->perf_event.type == BPF_PERF_EVENT_URETPROBE) + printf("\n\turetprobe "); + else + printf("\n\tuprobe "); + printf("%s+%#x ", buf, info->perf_event.uprobe.offset); +} + +static void show_perf_event_tracepoint_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.tracepoint.tp_name); + if (buf[0] == '\0') + return; + + printf("\n\ttracepoint %s ", buf); +} + +static void show_perf_event_event_plain(struct bpf_link_info *info) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + printf("\n\tevent "); + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + printf("%s:", perf_type); + else + printf("%u :", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + printf("%s ", perf_config); + else + printf("%llu ", config); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); } static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; show_link_header_plain(info); @@ -224,13 +760,18 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < prog_type_name_size) - printf("\n\tprog_type %s ", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + printf("\n\tprog_type %s ", prog_type_str); else printf("\n\tprog_type %u ", prog_info.type); show_link_attach_type_plain(info->tracing.attach_type); + if (info->tracing.target_obj_id || info->tracing.target_btf_id) + printf("\n\ttarget_obj_id %u target_btf_id %u ", + info->tracing.target_obj_id, + info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); @@ -243,6 +784,41 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tnetns_ino %u ", info->netns.netns_ino); show_link_attach_type_plain(info->netns.attach_type); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_plain(info); + break; + case BPF_LINK_TYPE_TCX: + printf("\n\t"); + show_link_ifindex_plain(info->tcx.ifindex); + show_link_attach_type_plain(info->tcx.attach_type); + break; + case BPF_LINK_TYPE_XDP: + printf("\n\t"); + show_link_ifindex_plain(info->xdp.ifindex); + break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_plain(info); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_plain(info); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_plain(info); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_plain(info); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_plain(info); + break; + default: + break; + } + break; default: break; } @@ -250,9 +826,8 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) if (!hashmap__empty(link_table)) { struct hashmap_entry *entry; - hashmap__for_each_key_entry(link_table, entry, - u32_as_hash_field(info->id)) - printf("\n\tpinned %s", (char *)entry->value); + hashmap__for_each_key_entry(link_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); @@ -265,12 +840,15 @@ static int do_show_link(int fd) { struct bpf_link_info info; __u32 len = sizeof(info); - char buf[256]; + __u64 *addrs = NULL; + char buf[PATH_MAX]; + int count; int err; memset(&info, 0, sizeof(info)); + buf[0] = '\0'; again: - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_link_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get link info: %s", strerror(errno)); @@ -279,22 +857,67 @@ again: } if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && !info.raw_tracepoint.tp_name) { - info.raw_tracepoint.tp_name = (unsigned long)&buf; + info.raw_tracepoint.tp_name = ptr_to_u64(&buf); info.raw_tracepoint.tp_name_len = sizeof(buf); goto again; } if (info.type == BPF_LINK_TYPE_ITER && !info.iter.target_name) { - info.iter.target_name = (unsigned long)&buf; + info.iter.target_name = ptr_to_u64(&buf); info.iter.target_name_len = sizeof(buf); goto again; } + if (info.type == BPF_LINK_TYPE_KPROBE_MULTI && + !info.kprobe_multi.addrs) { + count = info.kprobe_multi.count; + if (count) { + addrs = calloc(count, sizeof(__u64)); + if (!addrs) { + p_err("mem alloc failed"); + close(fd); + return -ENOMEM; + } + info.kprobe_multi.addrs = ptr_to_u64(addrs); + goto again; + } + } + if (info.type == BPF_LINK_TYPE_PERF_EVENT) { + switch (info.perf_event.type) { + case BPF_PERF_EVENT_TRACEPOINT: + if (!info.perf_event.tracepoint.tp_name) { + info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); + info.perf_event.tracepoint.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + if (!info.perf_event.kprobe.func_name) { + info.perf_event.kprobe.func_name = ptr_to_u64(&buf); + info.perf_event.kprobe.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + if (!info.perf_event.uprobe.file_name) { + info.perf_event.uprobe.file_name = ptr_to_u64(&buf); + info.perf_event.uprobe.name_len = sizeof(buf); + goto again; + } + break; + default: + break; + } + } if (json_output) show_link_close_json(fd, &info); else show_link_close_plain(fd, &info); + if (addrs) + free(addrs); close(fd); return 0; } @@ -319,7 +942,8 @@ static int do_show(int argc, char **argv) fd = link_parse_fd(&argc, &argv); if (fd < 0) return fd; - return do_show_link(fd); + do_show_link(fd); + goto out; } if (argc) @@ -358,6 +982,9 @@ static int do_show(int argc, char **argv) if (show_pinned) delete_pinned_obj_table(link_table); +out: + if (dd.sym_count) + kernel_syms_destroy(&dd); return errno == ENOENT ? 0 : -1; } @@ -31,7 +31,6 @@ bool block_mount; bool verifier_logs; bool relaxed_maps; bool use_loader; -bool legacy_libbpf; struct btf *base_btf; struct hashmap *refs_table; @@ -71,6 +70,47 @@ static int do_help(int argc, char **argv) return 0; } +static int do_batch(int argc, char **argv); +static int do_version(int argc, char **argv); + +static const struct cmd commands[] = { + { "help", do_help }, + { "batch", do_batch }, + { "prog", do_prog }, + { "map", do_map }, + { "link", do_link }, + { "cgroup", do_cgroup }, + { "perf", do_perf }, + { "net", do_net }, + { "feature", do_feature }, + { "btf", do_btf }, + { "gen", do_gen }, + { "struct_ops", do_struct_ops }, + { "iter", do_iter }, + { "version", do_version }, + { 0 } +}; + +#ifndef BPFTOOL_VERSION +/* bpftool's major and minor version numbers are aligned on libbpf's. There is + * an offset of 6 for the version number, because bpftool's version was higher + * than libbpf's when we adopted this scheme. The patch number remains at 0 + * for now. Set BPFTOOL_VERSION to override. + */ +#define BPFTOOL_MAJOR_VERSION (LIBBPF_MAJOR_VERSION + 6) +#define BPFTOOL_MINOR_VERSION LIBBPF_MINOR_VERSION +#define BPFTOOL_PATCH_VERSION 0 +#endif + +static void +print_feature(const char *feature, bool state, unsigned int *nb_features) +{ + if (state) { + printf("%s %s", *nb_features ? "," : "", feature); + *nb_features = *nb_features + 1; + } +} + static int do_version(int argc, char **argv) { #ifdef HAVE_LIBBFD_SUPPORT @@ -78,41 +118,67 @@ static int do_version(int argc, char **argv) #else const bool has_libbfd = false; #endif +#ifdef HAVE_LLVM_SUPPORT + const bool has_llvm = true; +#else + const bool has_llvm = false; +#endif #ifdef BPFTOOL_WITHOUT_SKELETONS const bool has_skeletons = false; #else const bool has_skeletons = true; #endif + bool bootstrap = false; + int i; + + for (i = 0; commands[i].cmd; i++) { + if (!strcmp(commands[i].cmd, "prog")) { + /* Assume we run a bootstrap version if "bpftool prog" + * is not available. + */ + bootstrap = !commands[i].func; + break; + } + } if (json_output) { jsonw_start_object(json_wtr); /* root object */ jsonw_name(json_wtr, "version"); +#ifdef BPFTOOL_VERSION jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION); +#else + jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + jsonw_name(json_wtr, "libbpf_version"); + jsonw_printf(json_wtr, "\"%d.%d\"", + libbpf_major_version(), libbpf_minor_version()); jsonw_name(json_wtr, "features"); jsonw_start_object(json_wtr); /* features */ jsonw_bool_field(json_wtr, "libbfd", has_libbfd); - jsonw_bool_field(json_wtr, "libbpf_strict", !legacy_libbpf); + jsonw_bool_field(json_wtr, "llvm", has_llvm); jsonw_bool_field(json_wtr, "skeletons", has_skeletons); + jsonw_bool_field(json_wtr, "bootstrap", bootstrap); jsonw_end_object(json_wtr); /* features */ jsonw_end_object(json_wtr); /* root object */ } else { unsigned int nb_features = 0; +#ifdef BPFTOOL_VERSION printf("%s v%s\n", bin_name, BPFTOOL_VERSION); +#else + printf("%s v%d.%d.%d\n", bin_name, BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + printf("using libbpf %s\n", libbpf_version_string()); printf("features:"); - if (has_libbfd) { - printf(" libbfd"); - nb_features++; - } - if (!legacy_libbpf) { - printf("%s libbpf_strict", nb_features++ ? "," : ""); - nb_features++; - } - if (has_skeletons) - printf("%s skeletons", nb_features++ ? "," : ""); + print_feature("libbfd", has_libbfd, &nb_features); + print_feature("llvm", has_llvm, &nb_features); + print_feature("skeletons", has_skeletons, &nb_features); + print_feature("bootstrap", bootstrap, &nb_features); printf("\n"); } return 0; @@ -254,26 +320,6 @@ static int make_args(char *line, char *n_argv[], int maxargs, int cmd_nb) return n_argc; } -static int do_batch(int argc, char **argv); - -static const struct cmd cmds[] = { - { "help", do_help }, - { "batch", do_batch }, - { "prog", do_prog }, - { "map", do_map }, - { "link", do_link }, - { "cgroup", do_cgroup }, - { "perf", do_perf }, - { "net", do_net }, - { "feature", do_feature }, - { "btf", do_btf }, - { "gen", do_gen }, - { "struct_ops", do_struct_ops }, - { "iter", do_iter }, - { "version", do_version }, - { 0 } -}; - static int do_batch(int argc, char **argv) { char buf[BATCH_LINE_LEN_MAX], contline[BATCH_LINE_LEN_MAX]; @@ -288,12 +334,12 @@ static int do_batch(int argc, char **argv) if (argc < 2) { p_err("too few parameters for batch"); return -1; - } else if (!is_prefix(*argv, "file")) { - p_err("expected 'file', got: %s", *argv); - return -1; } else if (argc > 2) { p_err("too many parameters for batch"); return -1; + } else if (!is_prefix(*argv, "file")) { + p_err("expected 'file', got: %s", *argv); + return -1; } NEXT_ARG(); @@ -361,7 +407,7 @@ static int do_batch(int argc, char **argv) jsonw_name(json_wtr, "output"); } - err = cmd_select(cmds, n_argc, n_argv, do_help); + err = cmd_select(commands, n_argc, n_argv, do_help); if (json_output) jsonw_end_object(json_wtr); @@ -402,7 +448,6 @@ int main(int argc, char **argv) { "debug", no_argument, NULL, 'd' }, { "use-loader", no_argument, NULL, 'L' }, { "base-btf", required_argument, NULL, 'B' }, - { "legacy", no_argument, NULL, 'l' }, { 0 } }; bool version_requested = false; @@ -410,12 +455,22 @@ int main(int argc, char **argv) setlinebuf(stdout); +#ifdef USE_LIBCAP + /* Libcap < 2.63 hooks before main() to compute the number of + * capabilities of the running kernel, and doing so it calls prctl() + * which may fail and set errno to non-zero. + * Let's reset errno to make sure this does not interfere with the + * batch mode. + */ + errno = 0; +#endif + last_do_help = do_help; pretty_output = false; json_output = false; show_pinned = false; block_mount = false; - bin_name = argv[0]; + bin_name = "bpftool"; opterr = 0; while ((opt = getopt_long(argc, argv, "VhpjfLmndB:l", @@ -455,19 +510,15 @@ int main(int argc, char **argv) break; case 'B': base_btf = btf__parse(optarg, NULL); - if (libbpf_get_error(base_btf)) { - p_err("failed to parse base BTF at '%s': %ld\n", - optarg, libbpf_get_error(base_btf)); - base_btf = NULL; + if (!base_btf) { + p_err("failed to parse base BTF at '%s': %d\n", + optarg, -errno); return -1; } break; case 'L': use_loader = true; break; - case 'l': - legacy_libbpf = true; - break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) @@ -477,16 +528,6 @@ int main(int argc, char **argv) } } - if (!legacy_libbpf) { - /* Allow legacy map definitions for skeleton generation. - * It will still be rejected if users use LIBBPF_STRICT_ALL - * mode for loading generated skeleton. - */ - ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); - if (ret) - p_err("failed to enable libbpf strict mode: %d", ret); - } - argc -= optind; argv += optind; if (argc < 0) @@ -495,7 +536,7 @@ int main(int argc, char **argv) if (version_requested) return do_version(argc, argv); - ret = cmd_select(cmds, argc, argv, do_help); + ret = cmd_select(commands, argc, argv, do_help); if (json_output) jsonw_destroy(&json_wtr); @@ -8,10 +8,10 @@ #undef GCC_VERSION #include <stdbool.h> #include <stdio.h> +#include <stdlib.h> #include <linux/bpf.h> #include <linux/compiler.h> #include <linux/kernel.h> -#include <tools/libc_compat.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> @@ -57,20 +57,12 @@ static inline void *u64_to_ptr(__u64 ptr) #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ - "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}" + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug}" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" #define HELP_SPEC_LINK \ "LINK := { id LINK_ID | pinned FILE }" -extern const char * const prog_type_name[]; -extern const size_t prog_type_name_size; - -extern const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE]; - -extern const char * const map_type_name[]; -extern const size_t map_type_name_size; - /* keep in sync with the definition in skeleton/pid_iter.bpf.c */ enum bpf_obj_type { BPF_OBJ_UNKNOWN, @@ -90,7 +82,6 @@ extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; extern bool use_loader; -extern bool legacy_libbpf; extern struct btf *base_btf; extern struct hashmap *refs_table; @@ -113,7 +104,9 @@ struct obj_ref { struct obj_refs { int ref_cnt; + bool has_bpf_cookie; struct obj_ref *refs; + __u64 bpf_cookie; }; struct btf; @@ -149,7 +142,7 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(const char *path, bool quiet); int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name); +int mount_bpffs_for_pin(const char *name, bool is_dir); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); @@ -175,30 +168,32 @@ int prog_parse_fd(int *argc, char ***argv); int prog_parse_fds(int *argc, char ***argv, int **fds); int map_parse_fd(int *argc, char ***argv); int map_parse_fds(int *argc, char ***argv, int **fds); -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len); struct bpf_prog_linfo; -#ifdef HAVE_LIBBFD_SUPPORT -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum); +#if defined(HAVE_LLVM_SUPPORT) || defined(HAVE_LIBBFD_SUPPORT) +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum); int disasm_init(void); #else static inline -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum) +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) { + return 0; } static inline int disasm_init(void) { - p_err("No libbfd support"); + p_err("No JIT disassembly support"); return -1; } #endif @@ -208,8 +203,7 @@ void print_hex_data_json(uint8_t *data, size_t len); unsigned int get_page_size(void); unsigned int get_possible_cpus(void); const char * -ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, - const char **opt); +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt); struct btf_dumper { const struct btf *btf; @@ -235,6 +229,8 @@ void btf_dump_linfo_plain(const struct btf *btf, const char *prefix, bool linum); void btf_dump_linfo_json(const struct btf *btf, const struct bpf_line_info *linfo, bool linum); +void btf_dump_linfo_dotlabel(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum); struct nlattr; struct ifinfomsg; @@ -246,22 +242,32 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, int print_all_levels(__maybe_unused enum libbpf_print_level level, const char *format, va_list args); -size_t hash_fn_for_key_as_id(const void *key, void *ctx); -bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx); - -static inline void *u32_as_hash_field(__u32 x) -{ - return (void *)(uintptr_t)x; -} +size_t hash_fn_for_key_as_id(long key, void *ctx); +bool equal_fn_for_key_as_id(long k1, long k2, void *ctx); -static inline __u32 hash_field_as_u32(const void *x) -{ - return (__u32)(uintptr_t)x; -} +/* bpf_attach_type_input_str - convert the provided attach type value into a + * textual representation that we accept for input purposes. + * + * This function is similar in nature to libbpf_bpf_attach_type_str, but + * recognizes some attach type names that have been used by the program in the + * past and which do not follow the string inference scheme that libbpf uses. + * These textual representations should only be used for user input. + * + * @t: The attach type + * Returns a pointer to a static string identifying the attach type. NULL is + * returned for unknown bpf_attach_type values. + */ +const char *bpf_attach_type_input_str(enum bpf_attach_type t); static inline bool hashmap__empty(struct hashmap *map) { return map ? hashmap__size(map) == 0 : true; } +int pathname_concat(char *buf, int buf_sz, const char *path, + const char *name); + +/* print netfilter bpf_link info */ +void netfilter_dump_plain(const struct bpf_link_info *info); +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr); #endif @@ -1,7 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ -#include <assert.h> #include <errno.h> #include <fcntl.h> #include <linux/err.h> @@ -22,42 +21,6 @@ #include "json_writer.h" #include "main.h" -const char * const map_type_name[] = { - [BPF_MAP_TYPE_UNSPEC] = "unspec", - [BPF_MAP_TYPE_HASH] = "hash", - [BPF_MAP_TYPE_ARRAY] = "array", - [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", - [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", - [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", - [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", - [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", - [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", - [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", - [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", - [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", - [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", - [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", - [BPF_MAP_TYPE_DEVMAP] = "devmap", - [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", - [BPF_MAP_TYPE_SOCKMAP] = "sockmap", - [BPF_MAP_TYPE_CPUMAP] = "cpumap", - [BPF_MAP_TYPE_XSKMAP] = "xskmap", - [BPF_MAP_TYPE_SOCKHASH] = "sockhash", - [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", - [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", - [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", - [BPF_MAP_TYPE_QUEUE] = "queue", - [BPF_MAP_TYPE_STACK] = "stack", - [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", - [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_MAP_TYPE_RINGBUF] = "ringbuf", - [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", - [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", - [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", -}; - -const size_t map_type_name_size = ARRAY_SIZE(map_type_name); - static struct hashmap *map_table; static bool map_is_per_cpu(__u32 type) @@ -81,12 +44,18 @@ static bool map_is_map_of_progs(__u32 type) static int map_type_from_str(const char *type) { + const char *map_type_str; unsigned int i; - for (i = 0; i < ARRAY_SIZE(map_type_name); i++) + for (i = 0; ; i++) { + map_type_str = libbpf_bpf_map_type_str(i); + if (!map_type_str) + break; + /* Don't allow prefixing in case of possible future shadowing */ - if (map_type_name[i] && !strcmp(map_type_name[i], type)) + if (!strcmp(map_type_str, type)) return i; + } return -1; } @@ -170,6 +139,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, print_hex_data_json(key, info->key_size); jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); + if (map_is_map_of_maps(info->type)) + jsonw_uint_field(json_wtr, "inner_map_id", + *(unsigned int *)value); if (btf) { struct btf_dumper d = { .btf = btf, @@ -290,8 +262,13 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { - printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (map_is_map_of_maps(info->type)) { + printf("inner_map_id:%c", break_names ? '\n' : ' '); + printf("%u ", *(unsigned int *)value); + } else { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } } printf("\n"); @@ -472,9 +449,12 @@ static int parse_elem(char **argv, struct bpf_map_info *info, static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) { + const char *map_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(wtr, "type", map_type_name[info->type]); + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + jsonw_string_field(wtr, "type", map_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -504,7 +484,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "max_entries", info->max_entries); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { @@ -513,10 +493,12 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < prog_type_name_size) + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) jsonw_string_field(json_wtr, "owner_prog_type", - prog_type_name[prog_type]); + prog_type_str); else jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); @@ -544,9 +526,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hashmap__for_each_key_entry(map_table, entry, - u32_as_hash_field(info->id)) - jsonw_string(json_wtr, entry->value); + hashmap__for_each_key_entry(map_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } @@ -559,9 +540,13 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) static void show_map_header_plain(struct bpf_map_info *info) { + const char *map_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - printf("%s ", map_type_name[info->type]); + + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + printf("%s ", map_type_str); else printf("type %u ", info->type); @@ -597,10 +582,11 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < prog_type_name_size) - printf("owner_prog_type %s ", - prog_type_name[prog_type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + printf("owner_prog_type %s ", prog_type_str); else printf("owner_prog_type %d ", prog_type); } @@ -616,21 +602,17 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (!hashmap__empty(map_table)) { struct hashmap_entry *entry; - hashmap__for_each_key_entry(map_table, entry, - u32_as_hash_field(info->id)) - printf("\n\tpinned %s", (char *)entry->value); + hashmap__for_each_key_entry(map_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } - printf("\n"); if (frozen_str) { frozen = atoi(frozen_str); free(frozen_str); } - if (!info->btf_id && !frozen) - return 0; - - printf("\t"); + if (info->btf_id || frozen) + printf("\n\t"); if (info->btf_id) printf("btf_id %d", info->btf_id); @@ -664,7 +646,7 @@ static int do_show_subset(int argc, char **argv) if (json_output && nb_fds > 1) jsonw_start_array(json_wtr); /* root array */ for (i = 0; i < nb_fds; i++) { - err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); @@ -734,7 +716,7 @@ static int do_show(int argc, char **argv) break; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -790,7 +772,7 @@ static int maps_have_btf(int *fds, int nb_fds) int err, i; for (i = 0; i < nb_fds; i++) { - err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); return -1; @@ -805,43 +787,38 @@ static int maps_have_btf(int *fds, int nb_fds) static struct btf *btf_vmlinux; -static struct btf *get_map_kv_btf(const struct bpf_map_info *info) +static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf) { - struct btf *btf = NULL; + int err = 0; if (info->btf_vmlinux_value_type_id) { if (!btf_vmlinux) { btf_vmlinux = libbpf_find_kernel_btf(); - if (libbpf_get_error(btf_vmlinux)) + if (!btf_vmlinux) { p_err("failed to get kernel btf"); + return -errno; + } } - return btf_vmlinux; + *btf = btf_vmlinux; } else if (info->btf_value_type_id) { - int err; - - btf = btf__load_from_kernel_by_id(info->btf_id); - err = libbpf_get_error(btf); - if (err) { + *btf = btf__load_from_kernel_by_id(info->btf_id); + if (!*btf) { + err = -errno; p_err("failed to get btf"); - btf = ERR_PTR(err); } + } else { + *btf = NULL; } - return btf; + return err; } static void free_map_kv_btf(struct btf *btf) { - if (!libbpf_get_error(btf) && btf != btf_vmlinux) + if (btf != btf_vmlinux) btf__free(btf); } -static void free_btf_vmlinux(void) -{ - if (!libbpf_get_error(btf_vmlinux)) - btf__free(btf_vmlinux); -} - static int map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, bool show_header) @@ -862,8 +839,7 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, prev_key = NULL; if (wtr) { - btf = get_map_kv_btf(info); - err = libbpf_get_error(btf); + err = get_map_kv_btf(info, &btf); if (err) { goto exit_free; } @@ -879,9 +855,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, } if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info->value_size != 8) + info->value_size != 8) { + const char *map_type_str; + + map_type_str = libbpf_bpf_map_type_str(info->type); p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info->type]); + map_type_str); + } while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -953,7 +933,7 @@ static int do_dump(int argc, char **argv) if (wtr && nb_fds > 1) jsonw_start_array(wtr); /* root array */ for (i = 0; i < nb_fds; i++) { - if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + if (bpf_map_get_info_by_fd(fds[i], &info, &len)) { p_err("can't get map info: %s", strerror(errno)); break; } @@ -975,7 +955,7 @@ exit_close: close(fds[i]); exit_free: free(fds); - free_btf_vmlinux(); + btf__free(btf_vmlinux); return err; } @@ -1054,11 +1034,8 @@ static void print_key_value(struct bpf_map_info *info, void *key, json_writer_t *btf_wtr; struct btf *btf; - btf = btf__load_from_kernel_by_id(info->btf_id); - if (libbpf_get_error(btf)) { - p_err("failed to get btf"); + if (get_map_kv_btf(info, &btf)) return; - } if (json_output) { print_entry_json(info, key, value, btf); @@ -1310,6 +1287,11 @@ static int do_create(int argc, char **argv) "flags")) goto exit; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool map create [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to request hardware offload for the map."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); if (attr.map_ifindex) { @@ -1454,7 +1436,7 @@ static int do_help(int argc, char **argv) "Usage: %1$s %2$s { show | list } [MAP]\n" " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [inner_map MAP] [dev NAME]\n" + " [inner_map MAP] [offload_dev NAME]\n" " %1$s %2$s dump MAP\n" " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" " %1$s %2$s lookup MAP [key DATA]\n" @@ -1481,7 +1463,7 @@ static int do_help(int argc, char **argv) " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" - " task_storage | bloom_filter }\n" + " task_storage | bloom_filter | user_ringbuf | cgrp_storage }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-n|--nomount} }\n" "", diff --git a/src/map_perf_ring.c b/src/map_perf_ring.c index 6b0c410..21d7d44 100644 --- a/src/map_perf_ring.c +++ b/src/map_perf_ring.c @@ -29,13 +29,6 @@ static volatile bool stop; -struct event_ring_info { - int fd; - int key; - unsigned int cpu; - void *mem; -}; - struct perf_event_sample { struct perf_event_header header; __u64 time; @@ -195,10 +188,9 @@ int do_event_pipe(int argc, char **argv) opts.map_keys = &ctx.idx; pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, print_bpf_output, &ctx, &opts); - err = libbpf_get_error(pb); - if (err) { + if (!pb) { p_err("failed to create perf buffer: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_map; } @@ -213,7 +205,7 @@ int do_event_pipe(int argc, char **argv) err = perf_buffer__poll(pb, 200); if (err < 0 && err != -EINTR) { p_err("perf buffer polling failed: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_pb; } } @@ -1,7 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (C) 2018 Facebook +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <errno.h> #include <fcntl.h> #include <stdlib.h> @@ -74,6 +76,11 @@ static const char * const attach_type_strings[] = { [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", }; +static const char * const attach_loc_strings[] = { + [BPF_TCX_INGRESS] = "tcx/ingress", + [BPF_TCX_EGRESS] = "tcx/egress", +}; + const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); static enum net_attach_type parse_attach_type(const char *str) @@ -420,8 +427,89 @@ static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) filter_info->devname, filter_info->ifindex); } -static int show_dev_tc_bpf(int sock, unsigned int nl_pid, - struct ip_devname_ifindex *dev) +static int __show_dev_tc_bpf_name(__u32 id, char *name, size_t len) +{ + struct bpf_prog_info info = {}; + __u32 ilen = sizeof(info); + int fd, ret; + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) + return fd; + ret = bpf_obj_get_info_by_fd(fd, &info, &ilen); + if (ret < 0) + goto out; + ret = -ENOENT; + if (info.name[0]) { + get_prog_full_name(&info, fd, name, len); + ret = 0; + } +out: + close(fd); + return ret; +} + +static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev, + const enum bpf_attach_type loc) +{ + __u32 prog_flags[64] = {}, link_flags[64] = {}, i, j; + __u32 prog_ids[64] = {}, link_ids[64] = {}; + LIBBPF_OPTS(bpf_prog_query_opts, optq); + char prog_name[MAX_PROG_FULL_NAME]; + int ret; + + optq.prog_ids = prog_ids; + optq.prog_attach_flags = prog_flags; + optq.link_ids = link_ids; + optq.link_attach_flags = link_flags; + optq.count = ARRAY_SIZE(prog_ids); + + ret = bpf_prog_query_opts(dev->ifindex, loc, &optq); + if (ret) + return; + for (i = 0; i < optq.count; i++) { + NET_START_OBJECT; + NET_DUMP_STR("devname", "%s", dev->devname); + NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex); + NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]); + ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name, + sizeof(prog_name)); + if (!ret) + NET_DUMP_STR("name", " %s", prog_name); + NET_DUMP_UINT("prog_id", " prog_id %u ", prog_ids[i]); + if (prog_flags[i] || json_output) { + NET_START_ARRAY("prog_flags", "%s "); + for (j = 0; prog_flags[i] && j < 32; j++) { + if (!(prog_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + if (link_ids[i] || json_output) { + NET_DUMP_UINT("link_id", "link_id %u ", link_ids[i]); + if (link_flags[i] || json_output) { + NET_START_ARRAY("link_flags", "%s "); + for (j = 0; link_flags[i] && j < 32; j++) { + if (!(link_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + } + NET_END_OBJECT_FINAL; + } +} + +static void show_dev_tc_bpf(struct ip_devname_ifindex *dev) +{ + __show_dev_tc_bpf(dev, BPF_TCX_INGRESS); + __show_dev_tc_bpf(dev, BPF_TCX_EGRESS); +} + +static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid, + struct ip_devname_ifindex *dev) { struct bpf_filter_t filter_info; struct bpf_tcinfo_t tcinfo; @@ -645,6 +733,108 @@ static int do_detach(int argc, char **argv) return 0; } +static int netfilter_link_compar(const void *a, const void *b) +{ + const struct bpf_link_info *nfa = a; + const struct bpf_link_info *nfb = b; + int delta; + + delta = nfa->netfilter.pf - nfb->netfilter.pf; + if (delta) + return delta; + + delta = nfa->netfilter.hooknum - nfb->netfilter.hooknum; + if (delta) + return delta; + + if (nfa->netfilter.priority < nfb->netfilter.priority) + return -1; + if (nfa->netfilter.priority > nfb->netfilter.priority) + return 1; + + return nfa->netfilter.flags - nfb->netfilter.flags; +} + +static void show_link_netfilter(void) +{ + unsigned int nf_link_len = 0, nf_link_count = 0; + struct bpf_link_info *nf_link_info = NULL; + __u32 id = 0; + + while (true) { + struct bpf_link_info info; + int fd, err; + __u32 len; + + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s (id %d)", strerror(errno), id); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get link by id (%u): %s", id, strerror(errno)); + continue; + } + + memset(&info, 0, sizeof(info)); + len = sizeof(info); + + err = bpf_link_get_info_by_fd(fd, &info, &len); + + close(fd); + + if (err) { + p_err("can't get link info for fd %d: %s", fd, strerror(errno)); + continue; + } + + if (info.type != BPF_LINK_TYPE_NETFILTER) + continue; + + if (nf_link_count >= nf_link_len) { + static const unsigned int max_link_count = INT_MAX / sizeof(info); + struct bpf_link_info *expand; + + if (nf_link_count > max_link_count) { + p_err("cannot handle more than %u links\n", max_link_count); + break; + } + + nf_link_len += 16; + + expand = realloc(nf_link_info, nf_link_len * sizeof(info)); + if (!expand) { + p_err("realloc: %s", strerror(errno)); + break; + } + + nf_link_info = expand; + } + + nf_link_info[nf_link_count] = info; + nf_link_count++; + } + + qsort(nf_link_info, nf_link_count, sizeof(*nf_link_info), netfilter_link_compar); + + for (id = 0; id < nf_link_count; id++) { + NET_START_OBJECT; + if (json_output) + netfilter_dump_json(&nf_link_info[id], json_wtr); + else + netfilter_dump_plain(&nf_link_info[id]); + + NET_DUMP_UINT("id", " prog_id %u", nf_link_info[id].prog_id); + NET_END_OBJECT; + } + + free(nf_link_info); +} + static int do_show(int argc, char **argv) { struct bpf_attach_info attach_info = {}; @@ -686,8 +876,9 @@ static int do_show(int argc, char **argv) if (!ret) { NET_START_ARRAY("tc", "%s:\n"); for (i = 0; i < dev_array.used_len; i++) { - ret = show_dev_tc_bpf(sock, nl_pid, - &dev_array.devices[i]); + show_dev_tc_bpf(&dev_array.devices[i]); + ret = show_dev_tc_bpf_classic(sock, nl_pid, + &dev_array.devices[i]); if (ret) break; } @@ -699,6 +890,10 @@ static int do_show(int argc, char **argv) NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); NET_END_ARRAY("\n"); + NET_START_ARRAY("netfilter", "%s:\n"); + show_link_netfilter(); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); @@ -731,7 +926,8 @@ static int do_help(int argc, char **argv) " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" " " HELP_SPEC_OPTIONS " }\n" "\n" - "Note: Only xdp and tc attachments are supported now.\n" + "Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n" + " are currently supported.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" diff --git a/src/netlink_dumper.h b/src/netlink_dumper.h index 774af6c..9631810 100644 --- a/src/netlink_dumper.h +++ b/src/netlink_dumper.h @@ -76,6 +76,14 @@ fprintf(stdout, fmt_str, val); \ } +#define NET_DUMP_UINT_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_uint(json_wtr, str); \ + else \ + fprintf(stdout, "%u ", str); \ +} + #define NET_DUMP_STR(name, fmt_str, str) \ { \ if (json_output) \ @@ -2,7 +2,9 @@ // Copyright (C) 2018 Facebook // Author: Yonghong Song <yhs@fb.com> +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <ctype.h> #include <errno.h> #include <fcntl.h> @@ -11,7 +13,7 @@ #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> -#include <ftw.h> +#include <dirent.h> #include <bpf/bpf.h> @@ -160,81 +162,83 @@ static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, } } -static int show_proc(const char *fpath, const struct stat *sb, - int tflag, struct FTW *ftwbuf) +static int show_proc(void) { + struct dirent *proc_de, *pid_fd_de; __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; - int err, pid = 0, fd = 0; + DIR *proc, *pid_fd; + int err, pid, fd; const char *pch; char buf[4096]; - /* prefix always /proc */ - pch = fpath + 5; - if (*pch == '\0') - return 0; + proc = opendir("/proc"); + if (!proc) + return -1; - /* pid should be all numbers */ - pch++; - while (isdigit(*pch)) { - pid = pid * 10 + *pch - '0'; - pch++; - } - if (*pch == '\0') - return 0; - if (*pch != '/') - return FTW_SKIP_SUBTREE; - - /* check /proc/<pid>/fd directory */ - pch++; - if (strncmp(pch, "fd", 2)) - return FTW_SKIP_SUBTREE; - pch += 2; - if (*pch == '\0') - return 0; - if (*pch != '/') - return FTW_SKIP_SUBTREE; - - /* check /proc/<pid>/fd/<fd_num> */ - pch++; - while (isdigit(*pch)) { - fd = fd * 10 + *pch - '0'; - pch++; - } - if (*pch != '\0') - return FTW_SKIP_SUBTREE; + while ((proc_de = readdir(proc))) { + pid = 0; + pch = proc_de->d_name; - /* query (pid, fd) for potential perf events */ - len = sizeof(buf); - err = bpf_task_fd_query(pid, fd, 0, buf, &len, &prog_id, &fd_type, - &probe_offset, &probe_addr); - if (err < 0) - return 0; + /* pid should be all numbers */ + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; - if (json_output) - print_perf_json(pid, fd, prog_id, fd_type, buf, probe_offset, - probe_addr); - else - print_perf_plain(pid, fd, prog_id, fd_type, buf, probe_offset, - probe_addr); + err = snprintf(buf, sizeof(buf), "/proc/%s/fd", proc_de->d_name); + if (err < 0 || err >= (int)sizeof(buf)) + continue; + pid_fd = opendir(buf); + if (!pid_fd) + continue; + + while ((pid_fd_de = readdir(pid_fd))) { + fd = 0; + pch = pid_fd_de->d_name; + + /* fd should be all numbers */ + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, + &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + continue; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + } + closedir(pid_fd); + } + closedir(proc); return 0; } static int do_show(int argc, char **argv) { - int flags = FTW_ACTIONRETVAL | FTW_PHYS; - int err = 0, nopenfd = 16; + int err; if (!has_perf_query_support()) return -1; if (json_output) jsonw_start_array(json_wtr); - if (nftw("/proc", show_proc, nopenfd, flags) == -1) { - p_err("%s", strerror(errno)); - err = -1; - } + err = show_proc(); if (json_output) jsonw_end_array(json_wtr); @@ -245,7 +249,7 @@ static int do_help(int argc, char **argv) { fprintf(stderr, "Usage: %1$s %2$s { show | list }\n" - " %1$s %2$s help }\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_OPTIONS " }\n" "", @@ -36,8 +36,8 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e) int err, i; void *tmp; - hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) { - refs = entry->value; + hashmap__for_each_key_entry(map, entry, e->id) { + refs = entry->pvalue; for (i = 0; i < refs->ref_cnt; i++) { if (refs->refs[i].pid == e->pid) @@ -78,8 +78,10 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e) ref->pid = e->pid; memcpy(ref->comm, e->comm, sizeof(ref->comm)); refs->ref_cnt = 1; + refs->has_bpf_cookie = e->has_bpf_cookie; + refs->bpf_cookie = e->bpf_cookie; - err = hashmap__append(map, u32_as_hash_field(e->id), refs); + err = hashmap__append(map, e->id, refs); if (err) p_err("failed to append entry to hashmap for ID %u: %s", e->id, strerror(errno)); @@ -181,7 +183,7 @@ void delete_obj_refs_table(struct hashmap *map) return; hashmap__for_each_entry(map, entry, bkt) { - struct obj_refs *refs = entry->value; + struct obj_refs *refs = entry->pvalue; free(refs->refs); free(refs); @@ -198,13 +200,16 @@ void emit_obj_refs_json(struct hashmap *map, __u32 id, if (hashmap__empty(map)) return; - hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { - struct obj_refs *refs = entry->value; + hashmap__for_each_key_entry(map, entry, id) { + struct obj_refs *refs = entry->pvalue; int i; if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie); + jsonw_name(json_writer, "pids"); jsonw_start_array(json_writer); for (i = 0; i < refs->ref_cnt; i++) { @@ -227,13 +232,16 @@ void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) if (hashmap__empty(map)) return; - hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { - struct obj_refs *refs = entry->value; + hashmap__for_each_key_entry(map, entry, id) { + struct obj_refs *refs = entry->pvalue; int i; if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie); + printf("%s", prefix); for (i = 0; i < refs->ref_cnt; i++) { struct obj_ref *ref = &refs->refs[i]; @@ -1,7 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -26,6 +28,7 @@ #include <bpf/btf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include <bpf/skel_internal.h> #include "cfg.h" @@ -35,53 +38,28 @@ #define BPF_METADATA_PREFIX "bpf_metadata_" #define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) -const char * const prog_type_name[] = { - [BPF_PROG_TYPE_UNSPEC] = "unspec", - [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", - [BPF_PROG_TYPE_KPROBE] = "kprobe", - [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", - [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", - [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", - [BPF_PROG_TYPE_XDP] = "xdp", - [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", - [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", - [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", - [BPF_PROG_TYPE_LWT_IN] = "lwt_in", - [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", - [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", - [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", - [BPF_PROG_TYPE_SK_SKB] = "sk_skb", - [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", - [BPF_PROG_TYPE_SK_MSG] = "sk_msg", - [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", - [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", - [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", - [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", - [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", - [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", - [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", - [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", - [BPF_PROG_TYPE_TRACING] = "tracing", - [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_PROG_TYPE_EXT] = "ext", - [BPF_PROG_TYPE_LSM] = "lsm", - [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", -}; - -const size_t prog_type_name_size = ARRAY_SIZE(prog_type_name); - enum dump_mode { DUMP_JITED, DUMP_XLATED, }; +static const bool attach_types[] = { + [BPF_SK_SKB_STREAM_PARSER] = true, + [BPF_SK_SKB_STREAM_VERDICT] = true, + [BPF_SK_SKB_VERDICT] = true, + [BPF_SK_MSG_VERDICT] = true, + [BPF_FLOW_DISSECTOR] = true, + [__MAX_BPF_ATTACH_TYPE] = false, +}; + +/* Textual representations traditionally used by the program and kept around + * for the sake of backwards compatibility. + */ static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", [BPF_SK_SKB_VERDICT] = "skb_verdict", [BPF_SK_MSG_VERDICT] = "msg_verdict", - [BPF_FLOW_DISSECTOR] = "flow_dissector", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -92,6 +70,14 @@ static enum bpf_attach_type parse_attach_type(const char *str) enum bpf_attach_type type; for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_types[type]) { + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!strcmp(str, attach_type_str)) + return type; + } + if (attach_type_strings[type] && is_prefix(str, attach_type_strings[type])) return type; @@ -212,7 +198,7 @@ static void show_prog_maps(int fd, __u32 num_maps) info.nr_map_ids = num_maps; info.map_ids = ptr_to_u64(map_ids); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err || !info.nr_map_ids) return; @@ -245,7 +231,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) memset(&prog_info, 0, sizeof(prog_info)); prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) return NULL; @@ -262,7 +248,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) prog_info.map_ids = ptr_to_u64(map_ids); prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) goto free_map_ids; @@ -273,7 +259,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) memset(map_info, 0, sizeof(*map_info)); map_info_len = sizeof(*map_info); - ret = bpf_obj_get_info_by_fd(map_fd, map_info, &map_info_len); + ret = bpf_map_get_info_by_fd(map_fd, map_info, &map_info_len); if (ret < 0) { close(map_fd); goto free_map_ids; @@ -336,7 +322,7 @@ static void show_prog_metadata(int fd, __u32 num_maps) return; btf = btf__load_from_kernel_by_id(map_info.btf_id); - if (libbpf_get_error(btf)) + if (!btf) goto out_free; t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id); @@ -426,12 +412,14 @@ out_free: static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; char prog_name[MAX_PROG_FULL_NAME]; jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - jsonw_string_field(json_wtr, "type", - prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + + if (prog_type_str) + jsonw_string_field(json_wtr, "type", prog_type_str); else jsonw_uint_field(json_wtr, "type", info->type); @@ -484,7 +472,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) memlock = get_fdinfo(fd, "memlock"); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->nr_map_ids) @@ -498,9 +486,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hashmap__for_each_key_entry(prog_table, entry, - u32_as_hash_field(info->id)) - jsonw_string(json_wtr, entry->value); + hashmap__for_each_key_entry(prog_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } @@ -513,11 +500,13 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; char prog_name[MAX_PROG_FULL_NAME]; printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - printf("%s ", prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + if (prog_type_str) + printf("%s ", prog_type_str); else printf("type %u ", info->type); @@ -571,9 +560,8 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) if (!hashmap__empty(prog_table)) { struct hashmap_entry *entry; - hashmap__for_each_key_entry(prog_table, entry, - u32_as_hash_field(info->id)) - printf("\n\tpinned %s", (char *)entry->value); + hashmap__for_each_key_entry(prog_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } if (info->btf_id) @@ -592,7 +580,7 @@ static int show_prog(int fd) __u32 len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info: %s", strerror(errno)); return -1; @@ -738,7 +726,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, if (info->btf_id) { btf = btf__load_from_kernel_by_id(info->btf_id); - if (libbpf_get_error(btf)) { + if (!btf) { p_err("failed to get btf"); return -1; } @@ -774,10 +762,8 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, const char *name = NULL; if (info->ifindex) { - name = ifindex_to_bfd_params(info->ifindex, - info->netns_dev, - info->netns_ino, - &disasm_opt); + name = ifindex_to_arch(info->ifindex, info->netns_dev, + info->netns_ino, &disasm_opt); if (!name) goto exit_free; } @@ -832,10 +818,11 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, printf("%s:\n", sym_name); } - disasm_print_insn(img, lens[i], opcodes, - name, disasm_opt, btf, - prog_linfo, ksyms[i], i, - linum); + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + prog_linfo, ksyms[i], i, + linum)) + goto exit_free; img += lens[i]; @@ -848,14 +835,11 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, if (json_output) jsonw_end_array(json_wtr); } else { - disasm_print_insn(buf, member_len, opcodes, name, - disasm_opt, btf, NULL, 0, 0, false); + if (disasm_print_insn(buf, member_len, opcodes, name, + disasm_opt, btf, NULL, 0, 0, + false)) + goto exit_free; } - } else if (visual) { - if (json_output) - jsonw_null(json_wtr); - else - dump_xlated_cfg(buf, member_len); } else { kernel_syms_load(&dd); dd.nr_jited_ksyms = info->nr_jited_ksyms; @@ -866,11 +850,11 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, dd.prog_linfo = prog_linfo; if (json_output) - dump_xlated_json(&dd, buf, member_len, opcodes, - linum); + dump_xlated_json(&dd, buf, member_len, opcodes, linum); + else if (visual) + dump_xlated_cfg(&dd, buf, member_len, opcodes, linum); else - dump_xlated_plain(&dd, buf, member_len, opcodes, - linum); + dump_xlated_plain(&dd, buf, member_len, opcodes, linum); kernel_syms_destroy(&dd); } @@ -921,37 +905,46 @@ static int do_dump(int argc, char **argv) if (nb_fds < 1) goto exit_free; - if (is_prefix(*argv, "file")) { - NEXT_ARG(); - if (!argc) { - p_err("expected file path"); - goto exit_close; - } - if (nb_fds > 1) { - p_err("several programs matched"); - goto exit_close; - } + while (argc) { + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + p_err("expected file path"); + goto exit_close; + } + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } - filepath = *argv; - NEXT_ARG(); - } else if (is_prefix(*argv, "opcodes")) { - opcodes = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "visual")) { - if (nb_fds > 1) { - p_err("several programs matched"); + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } else { + usage(); goto exit_close; } - - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); } - if (argc) { - usage(); + if (filepath && (opcodes || visual || linum)) { + p_err("'file' is not compatible with 'opcodes', 'visual', or 'linum'"); + goto exit_close; + } + if (json_output && visual) { + p_err("'visual' is not compatible with JSON output"); goto exit_close; } @@ -960,7 +953,7 @@ static int do_dump(int argc, char **argv) for (i = 0; i < nb_fds; i++) { memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); if (err) { p_err("can't get prog info: %s", strerror(errno)); break; @@ -972,7 +965,7 @@ static int do_dump(int argc, char **argv) break; } - err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); if (err) { p_err("can't get prog info: %s", strerror(errno)); break; @@ -1465,6 +1458,54 @@ get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, return ret; } +static int +auto_attach_program(struct bpf_program *prog, const char *path) +{ + struct bpf_link *link; + int err; + + link = bpf_program__attach(prog); + if (!link) { + p_info("Program %s does not support autoattach, falling back to pinning", + bpf_program__name(prog)); + return bpf_obj_pin(bpf_program__fd(prog), path); + } + + err = bpf_link__pin(link, path); + bpf_link__destroy(link); + return err; +} + +static int +auto_attach_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + char buf[PATH_MAX]; + int err; + + bpf_object__for_each_program(prog, obj) { + err = pathname_concat(buf, sizeof(buf), path, bpf_program__name(prog)); + if (err) + goto err_unpin_programs; + + err = auto_attach_program(prog, buf); + if (err) + goto err_unpin_programs; + } + + return 0; + +err_unpin_programs: + while ((prog = bpf_object__prev_program(obj, prog))) { + if (pathname_concat(buf, sizeof(buf), path, bpf_program__name(prog))) + continue; + + bpf_program__unpin(prog, buf); + } + + return err; +} + static int load_with_options(int argc, char **argv, bool first_prog_only) { enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC; @@ -1476,11 +1517,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; const char *pinmaps = NULL; + __u32 xdpmeta_ifindex = 0; + __u32 offload_ifindex = 0; + bool auto_attach = false; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; unsigned int i, j; - __u32 ifindex = 0; const char *file; int idx, err; @@ -1558,9 +1601,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) if (fd < 0) goto err_free_reuse_maps; - new_map_replace = reallocarray(map_replace, - old_map_fds + 1, - sizeof(*map_replace)); + new_map_replace = libbpf_reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); if (!new_map_replace) { p_err("mem alloc failed"); goto err_free_reuse_maps; @@ -1572,17 +1615,46 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) map_replace[old_map_fds].fd = fd; old_map_fds++; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool prog load [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to offload program to device.\n" + "For applications using XDP hints only, use 'xdpmeta_dev <ifname>'."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); - if (ifindex) { - p_err("offload device already specified"); + if (offload_ifindex) { + p_err("offload_dev already specified"); + goto err_free_reuse_maps; + } else if (xdpmeta_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); goto err_free_reuse_maps; } if (!REQ_ARGS(1)) goto err_free_reuse_maps; - ifindex = if_nametoindex(*argv); - if (!ifindex) { + offload_ifindex = if_nametoindex(*argv); + if (!offload_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "xdpmeta_dev")) { + NEXT_ARG(); + + if (xdpmeta_ifindex) { + p_err("xdpmeta_dev already specified"); + goto err_free_reuse_maps; + } else if (offload_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); goto err_free_reuse_maps; @@ -1595,6 +1667,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_free_reuse_maps; pinmaps = GET_ARG(); + } else if (is_prefix(*argv, "autoattach")) { + auto_attach = true; + NEXT_ARG(); } else { p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?", *argv); @@ -1609,7 +1684,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) open_opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_file(file, &open_opts); - if (libbpf_get_error(obj)) { + if (!obj) { p_err("failed to open object file"); goto err_free_reuse_maps; } @@ -1626,8 +1701,14 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - bpf_program__set_ifindex(pos, ifindex); - bpf_program__set_type(pos, prog_type); + if (prog_type == BPF_PROG_TYPE_XDP && xdpmeta_ifindex) { + bpf_program__set_flags(pos, BPF_F_XDP_DEV_BOUND_ONLY); + bpf_program__set_ifindex(pos, xdpmeta_ifindex); + } else { + bpf_program__set_ifindex(pos, offload_ifindex); + } + if (bpf_program__type(pos) != prog_type) + bpf_program__set_type(pos, prog_type); bpf_program__set_expected_attach_type(pos, expected_attach_type); } @@ -1663,7 +1744,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) idx = 0; bpf_object__for_each_map(map, obj) { if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) - bpf_map__set_ifindex(map, ifindex); + bpf_map__set_ifindex(map, offload_ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { err = bpf_map__reuse_fd(map, map_replace[j++].fd); @@ -1693,7 +1774,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile); + err = mount_bpffs_for_pin(pinfile, !first_prog_only); if (err) goto err_close_obj; @@ -1704,14 +1785,20 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = bpf_obj_pin(bpf_program__fd(prog), pinfile); + if (auto_attach) + err = auto_attach_program(prog, pinfile); + else + err = bpf_obj_pin(bpf_program__fd(prog), pinfile); if (err) { p_err("failed to pin program %s", bpf_program__section_name(prog)); goto err_close_obj; } } else { - err = bpf_object__pin_programs(obj, pinfile); + if (auto_attach) + err = auto_attach_programs(obj, pinfile); + else + err = bpf_object__pin_programs(obj, pinfile); if (err) { p_err("failed to pin all programs"); goto err_close_obj; @@ -1742,11 +1829,6 @@ err_unpin: else bpf_object__unpin_programs(obj, pinfile); err_close_obj: - if (!legacy_libbpf) { - p_info("Warning: bpftool is now running in libbpf strict mode and has more stringent requirements about BPF programs.\n" - "If it used to work for this object file but now doesn't, see --legacy option for more details.\n"); - } - bpf_object__close(obj); err_free_reuse_maps: for (i = 0; i < old_map_fds; i++) @@ -1827,7 +1909,7 @@ static int do_loader(int argc, char **argv) open_opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_file(file, &open_opts); - if (libbpf_get_error(obj)) { + if (!obj) { p_err("failed to open object file"); goto err_close_obj; } @@ -1974,7 +2056,7 @@ static int profile_parse_metrics(int argc, char **argv) int selected_cnt = 0; unsigned int i; - metric_cnt = sizeof(metrics) / sizeof(struct profile_metric); + metric_cnt = ARRAY_SIZE(metrics); while (argc > 0) { for (i = 0; i < metric_cnt; i++) { @@ -2115,9 +2197,9 @@ static char *profile_target_name(int tgt_fd) char *name = NULL; int err; - err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); if (err) { - p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd); + p_err("failed to get info for prog FD %d", tgt_fd); goto out; } @@ -2128,7 +2210,7 @@ static char *profile_target_name(int tgt_fd) func_info_rec_size = info.func_info_rec_size; if (info.nr_func_info == 0) { - p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd); + p_err("found 0 func_info for prog FD %d", tgt_fd); goto out; } @@ -2137,14 +2219,14 @@ static char *profile_target_name(int tgt_fd) info.func_info_rec_size = func_info_rec_size; info.func_info = ptr_to_u64(&func_info); - err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); if (err) { p_err("failed to get func_info for prog FD %d", tgt_fd); goto out; } btf = btf__load_from_kernel_by_id(info.btf_id); - if (libbpf_get_error(btf)) { + if (!btf) { p_err("failed to load btf for prog FD %d", tgt_fd); goto out; } @@ -2178,10 +2260,38 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); @@ -2200,17 +2310,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; @@ -2343,13 +2447,14 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [PROG]\n" - " %1$s %2$s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n" - " %1$s %2$s dump jited PROG [{ file FILE | opcodes | linum }]\n" + " %1$s %2$s dump xlated PROG [{ file FILE | [opcodes] [linum] [visual] }]\n" + " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" " %1$s %2$s pin PROG FILE\n" " %1$s %2$s { load | loadall } OBJ PATH \\\n" - " [type TYPE] [dev NAME] \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" + " [autoattach]\n" " %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n" " %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n" " %1$s %2$s run PROG \\\n" @@ -2375,8 +2480,8 @@ static int do_help(int argc, char **argv) " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" - " ATTACH_TYPE := { msg_verdict | skb_verdict | stream_verdict |\n" - " stream_parser | flow_dissector }\n" + " ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n" + " sk_skb_stream_parser | flow_dissector }\n" " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n" diff --git a/src/skeleton/pid_iter.bpf.c b/src/skeleton/pid_iter.bpf.c index f70702f..26004f0 100644 --- a/src/skeleton/pid_iter.bpf.c +++ b/src/skeleton/pid_iter.bpf.c @@ -15,6 +15,19 @@ enum bpf_obj_type { BPF_OBJ_BTF, }; +struct bpf_perf_link___local { + struct bpf_link link; + struct file *perf_file; +} __attribute__((preserve_access_index)); + +struct perf_event___local { + u64 bpf_cookie; +} __attribute__((preserve_access_index)); + +enum bpf_link_type___local { + BPF_LINK_TYPE_PERF_EVENT___local = 7, +}; + extern const void bpf_link_fops __ksym; extern const void bpf_map_fops __ksym; extern const void bpf_prog_fops __ksym; @@ -38,6 +51,17 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) } } +/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ +static __u64 get_bpf_cookie(struct bpf_link *link) +{ + struct bpf_perf_link___local *perf_link; + struct perf_event___local *event; + + perf_link = container_of(link, struct bpf_perf_link___local, link); + event = BPF_CORE_READ(perf_link, perf_file, private_data); + return BPF_CORE_READ(event, bpf_cookie); +} + SEC("iter/task_file") int iter(struct bpf_iter__task_file *ctx) { @@ -69,8 +93,22 @@ int iter(struct bpf_iter__task_file *ctx) if (file->f_op != fops) return 0; + __builtin_memset(&e, 0, sizeof(e)); e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); + + if (obj_type == BPF_OBJ_LINK && + bpf_core_enum_value_exists(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + struct bpf_link *link = (struct bpf_link *) file->private_data; + + if (link->type == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), task->group_leader->comm); bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); diff --git a/src/skeleton/pid_iter.h b/src/skeleton/pid_iter.h index 5692cf2..bbb570d 100644 --- a/src/skeleton/pid_iter.h +++ b/src/skeleton/pid_iter.h @@ -6,6 +6,8 @@ struct pid_iter_entry { __u32 id; int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; char comm[16]; }; diff --git a/src/skeleton/profiler.bpf.c b/src/skeleton/profiler.bpf.c index ce5b65e..2f80edc 100644 --- a/src/skeleton/profiler.bpf.c +++ b/src/skeleton/profiler.bpf.c @@ -4,6 +4,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + /* map of perf event fds, num_cpu * num_metric entries */ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -15,14 +21,14 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } fentry_readings SEC(".maps"); /* accumulated readings */ struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } accum_readings SEC(".maps"); /* sample counts, one per cpu */ @@ -39,7 +45,7 @@ const volatile __u32 num_metric = 1; SEC("fentry/XXX") int BPF_PROG(fentry_XXX) { - struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; u32 key = bpf_get_smp_processor_id(); u32 i; @@ -53,10 +59,10 @@ int BPF_PROG(fentry_XXX) } for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { - struct bpf_perf_event_value reading; + struct bpf_perf_event_value___local reading; int err; - err = bpf_perf_event_read_value(&events, key, &reading, + err = bpf_perf_event_read_value(&events, key, (void *)&reading, sizeof(reading)); if (err) return 0; @@ -68,14 +74,14 @@ int BPF_PROG(fentry_XXX) } static inline void -fexit_update_maps(u32 id, struct bpf_perf_event_value *after) +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) { - struct bpf_perf_event_value *before, diff; + struct bpf_perf_event_value___local *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ if (before && before->counter) { - struct bpf_perf_event_value *accum; + struct bpf_perf_event_value___local *accum; diff.counter = after->counter - before->counter; diff.enabled = after->enabled - before->enabled; @@ -93,7 +99,7 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after) SEC("fexit/XXX") int BPF_PROG(fexit_XXX) { - struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); u32 i, zero = 0; int err; @@ -102,7 +108,8 @@ int BPF_PROG(fexit_XXX) /* read all events before updating the maps, to reduce error */ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, - readings + i, sizeof(*readings)); + (void *)(readings + i), + sizeof(*readings)); if (err) return 0; } diff --git a/src/struct_ops.c b/src/struct_ops.c index e08a6ff..3ebc9fe 100644 --- a/src/struct_ops.c +++ b/src/struct_ops.c @@ -32,7 +32,7 @@ static const struct btf *get_btf_vmlinux(void) return btf_vmlinux; btf_vmlinux = libbpf_find_kernel_btf(); - if (libbpf_get_error(btf_vmlinux)) + if (!btf_vmlinux) p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); return btf_vmlinux; @@ -45,7 +45,7 @@ static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) const char *st_ops_name; kern_btf = get_btf_vmlinux(); - if (libbpf_get_error(kern_btf)) + if (!kern_btf) return "<btf_vmlinux_not_found>"; t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); @@ -63,10 +63,8 @@ static __s32 get_map_info_type_id(void) return map_info_type_id; kern_btf = get_btf_vmlinux(); - if (libbpf_get_error(kern_btf)) { - map_info_type_id = PTR_ERR(kern_btf); - return map_info_type_id; - } + if (!kern_btf) + return 0; map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info", BTF_KIND_STRUCT); @@ -153,7 +151,7 @@ static int get_next_struct_ops_map(const char *name, int *res_fd, return -1; } - err = bpf_obj_get_info_by_fd(fd, info, &info_len); + err = bpf_map_get_info_by_fd(fd, info, &info_len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -264,7 +262,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, goto done; } - if (bpf_obj_get_info_by_fd(fd, info, &info_len)) { + if (bpf_map_get_info_by_fd(fd, info, &info_len)) { p_err("can't get map info: %s", strerror(errno)); res.nr_errs++; goto done; @@ -415,7 +413,7 @@ static int do_dump(int argc, char **argv) } kern_btf = get_btf_vmlinux(); - if (libbpf_get_error(kern_btf)) + if (!kern_btf) return -1; if (!json_output) { @@ -477,28 +475,51 @@ static int do_unregister(int argc, char **argv) return cmd_retval(&res, true); } +static int pin_link(struct bpf_link *link, const char *pindir, + const char *name) +{ + char pinfile[PATH_MAX]; + int err; + + err = pathname_concat(pinfile, sizeof(pinfile), pindir, name); + if (err) + return -1; + + return bpf_link__pin(link, pinfile); +} + static int do_register(int argc, char **argv) { LIBBPF_OPTS(bpf_object_open_opts, open_opts); + __u32 link_info_len = sizeof(struct bpf_link_info); + struct bpf_link_info link_info = {}; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); int nr_errs = 0, nr_maps = 0; + const char *linkdir = NULL; struct bpf_object *obj; struct bpf_link *link; struct bpf_map *map; const char *file; - if (argc != 1) + if (argc != 1 && argc != 2) usage(); file = GET_ARG(); + if (argc == 1) + linkdir = GET_ARG(); + + if (linkdir && mount_bpffs_for_pin(linkdir, true)) { + p_err("can't mount bpffs for pinning"); + return -1; + } if (verifier_logs) /* log_level1 + log_level2 + stats, but not stable UAPI */ open_opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_file(file, &open_opts); - if (libbpf_get_error(obj)) + if (!obj) return -1; set_max_rlimit(); @@ -513,30 +534,52 @@ static int do_register(int argc, char **argv) continue; link = bpf_map__attach_struct_ops(map); - if (libbpf_get_error(link)) { + if (!link) { p_err("can't register struct_ops %s: %s", - bpf_map__name(map), - strerror(-PTR_ERR(link))); + bpf_map__name(map), strerror(errno)); nr_errs++; continue; } nr_maps++; - bpf_link__disconnect(link); - bpf_link__destroy(link); - - if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, - &info_len)) - p_info("Registered %s %s id %u", - get_kern_struct_ops_name(&info), - bpf_map__name(map), - info.id); - else + if (bpf_map_get_info_by_fd(bpf_map__fd(map), &info, + &info_len)) { /* Not p_err. The struct_ops was attached * successfully. */ p_info("Registered %s but can't find id: %s", bpf_map__name(map), strerror(errno)); + goto clean_link; + } + if (!(bpf_map__map_flags(map) & BPF_F_LINK)) { + p_info("Registered %s %s id %u", + get_kern_struct_ops_name(&info), + info.name, + info.id); + goto clean_link; + } + if (bpf_link_get_info_by_fd(bpf_link__fd(link), + &link_info, + &link_info_len)) { + p_err("Registered %s but can't find link id: %s", + bpf_map__name(map), strerror(errno)); + nr_errs++; + goto clean_link; + } + if (linkdir && pin_link(link, linkdir, info.name)) { + p_err("can't pin link %u for %s: %s", + link_info.id, info.name, + strerror(errno)); + nr_errs++; + goto clean_link; + } + p_info("Registered %s %s map id %u link id %u", + get_kern_struct_ops_name(&info), + info.name, info.id, link_info.id); + +clean_link: + bpf_link__disconnect(link); + bpf_link__destroy(link); } bpf_object__close(obj); @@ -565,7 +608,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [STRUCT_OPS_MAP]\n" " %1$s %2$s dump [STRUCT_OPS_MAP]\n" - " %1$s %2$s register OBJ\n" + " %1$s %2$s register OBJ [LINK_DIR]\n" " %1$s %2$s unregister STRUCT_OPS_MAP\n" " %1$s %2$s help\n" "\n" @@ -593,8 +636,7 @@ int do_struct_ops(int argc, char **argv) err = cmd_select(cmds, argc, argv, do_help); - if (!libbpf_get_error(btf_vmlinux)) - btf__free(btf_vmlinux); + btf__free(btf_vmlinux); return err; } diff --git a/src/xlated_dumper.c b/src/xlated_dumper.c index f1f32e2..567f56d 100644 --- a/src/xlated_dumper.c +++ b/src/xlated_dumper.c @@ -1,13 +1,16 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <stdarg.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/types.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include "disasm.h" #include "json_writer.h" @@ -32,8 +35,8 @@ void kernel_syms_load(struct dump_data *dd) return; while (fgets(buff, sizeof(buff), fp)) { - tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1, - sizeof(*dd->sym_mapping)); + tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); if (!tmp) { out: free(dd->sym_mapping); @@ -43,7 +46,11 @@ out: } dd->sym_mapping = tmp; sym = &dd->sym_mapping[dd->sym_count]; - if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + + /* module is optional */ + sym->module[0] = '\0'; + /* trim the square brackets around the module name */ + if (sscanf(buff, "%p %*c %s [%[^]]s", &address, sym->name, sym->module) < 2) continue; sym->address = (unsigned long)address; if (!strcmp(sym->name, "__bpf_call_base")) { @@ -358,7 +365,8 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, } void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, - unsigned int start_idx) + unsigned int start_idx, + bool opcodes, bool linum) { const struct bpf_insn_cbs cbs = { .cb_print = print_insn_for_graph, @@ -366,14 +374,61 @@ void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, .cb_imm = print_imm, .private_data = dd, }; + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_line_info *last_linfo = NULL; + struct bpf_func_info *record = dd->func_info; struct bpf_insn *insn_start = buf_start; struct bpf_insn *insn_end = buf_end; struct bpf_insn *cur = insn_start; + struct btf *btf = dd->btf; + bool double_insn = false; + char func_sig[1024]; for (; cur <= insn_end; cur++) { - printf("% 4d: ", (int)(cur - insn_start + start_idx)); + unsigned int insn_off; + + if (double_insn) { + double_insn = false; + continue; + } + double_insn = cur->code == (BPF_LD | BPF_IMM | BPF_DW); + + insn_off = (unsigned int)(cur - insn_start + start_idx); + if (btf && record) { + if (record->insn_off == insn_off) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') + printf("; %s:\\l\\\n", func_sig); + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, insn_off, 0); + if (linfo && linfo != last_linfo) { + btf_dump_linfo_dotlabel(btf, linfo, linum); + last_linfo = linfo; + } + } + + printf("%d: ", insn_off); print_bpf_insn(&cbs, cur, true); + + if (opcodes) { + printf("\\ \\ \\ \\ "); + fprint_hex(stdout, cur, 8, " "); + if (double_insn && cur <= insn_end - 1) { + printf(" "); + fprint_hex(stdout, cur + 1, 8, " "); + } + printf("\\l\\\n"); + } + if (cur != insn_end) - printf(" | "); + printf("| "); } } diff --git a/src/xlated_dumper.h b/src/xlated_dumper.h index 54847e1..db3ba06 100644 --- a/src/xlated_dumper.h +++ b/src/xlated_dumper.h @@ -5,12 +5,14 @@ #define __BPF_TOOL_XLATED_DUMPER_H #define SYM_MAX_NAME 256 +#define MODULE_MAX_NAME 64 struct bpf_prog_linfo; struct kernel_sym { unsigned long address; char name[SYM_MAX_NAME]; + char module[MODULE_MAX_NAME]; }; struct dump_data { @@ -34,6 +36,7 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, bool opcodes, bool linum); void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end, - unsigned int start_index); + unsigned int start_index, + bool opcodes, bool linum); #endif |