Merge branch 'libbpf:master' into master

Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit:   227a0713b319e7a8605312dee1c97c97a719a9fc
Checkpoint bpf-next commit: dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca
Baseline bpf commit:        77b1b8b43ec3c060ecf7e926a92b0f8772171046
Checkpoint bpf commit:      fe68195daf34d5dddacd3f93dd3eafc4beca3a0e

Andrii Nakryiko (1):
  libbpf: Fix compilation warning due to mismatched printf format

Dan Carpenter (1):
  libbpf: Fix signedness bug in btf_dump_array_data()

Hengqi Chen (1):
  libbpf: Add BPF_KPROBE_SYSCALL macro

Ilya Leoshkevich (7):
  libbpf: Add PT_REGS_SYSCALL_REGS macro
  libbpf: Fix accessing syscall arguments on powerpc
  libbpf: Fix riscv register names
  libbpf: Fix accessing syscall arguments on riscv
  libbpf: Allow overriding PT_REGS_PARM1{_CORE}_SYSCALL
  libbpf: Fix accessing the first syscall argument on arm64
  libbpf: Fix accessing the first syscall argument on s390

Mauricio Vásquez (1):
  libbpf: Remove mode check in libbpf_set_strict_mode()

 src/bpf_tracing.h | 85 +++++++++++++++++++++++++++++++++++++++++------
 src/btf_dump.c    |  6 ++--
 src/libbpf.c      |  8 -----
 3 files changed, 79 insertions(+), 20 deletions(-)

--
2.30.2

.github/actions/build-selftests/action.yml

@@ -0,0 +1,30 @@
+name: 'build-selftests'
+description: 'Build BPF selftests'
+inputs:
+  repo-path:
+    description: 'where is the source code'
+    required: true
+  kernel:
+    description: 'kernel version or LATEST'
+    required: true
+    default: 'LATEST'
+  vmlinux:
+    description: 'where is vmlinux file'
+    required: true
+    default: '${{ github.workspace }}/vmlinux'
+
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        echo "::group::Setup Env"
+        sudo apt-get install -y qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev python3-docutils
+        echo "::endgroup::"
+    - shell: bash
+      run: |
+        export KERNEL=${{ inputs.kernel }}
+        export REPO_ROOT="${{ github.workspace }}"
+        export REPO_PATH="${{ inputs.repo-path }}"
+        export VMLINUX_BTF="${{ inputs.vmlinux }}"
+        ${{ github.action_path }}/build_selftests.sh

.github/actions/build-selftests/build_selftests.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+
+set -euo pipefail
+
+THISDIR="$(cd $(dirname $0) && pwd)"
+
+source ${THISDIR}/helpers.sh
+
+travis_fold start prepare_selftests "Building selftests"
+
+LLVM_VER=15
+LIBBPF_PATH="${REPO_ROOT}"
+
+PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh
+if [ -f "${PREPARE_SELFTESTS_SCRIPT}" ]; then
+	(cd "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" && ${PREPARE_SELFTESTS_SCRIPT})
+fi
+
+if [[ "${KERNEL}" = 'LATEST' ]]; then
+	VMLINUX_H=
+else
+	VMLINUX_H=${THISDIR}/vmlinux.h
+fi
+
+cd ${REPO_ROOT}/${REPO_PATH}
+make \
+	CLANG=clang-${LLVM_VER} \
+	LLC=llc-${LLVM_VER} \
+	LLVM_STRIP=llvm-strip-${LLVM_VER} \
+	VMLINUX_BTF="${VMLINUX_BTF}" \
+	VMLINUX_H=${VMLINUX_H} \
+	-C "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
+	-j $((4*$(nproc))) > /dev/null
+cd -
+mkdir ${LIBBPF_PATH}/selftests
+cp -R "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
+	${LIBBPF_PATH}/selftests
+cd ${LIBBPF_PATH}
+rm selftests/bpf/.gitignore
+git add selftests
+
+travis_fold end prepare_selftests

.github/actions/build-selftests/helpers.sh

@@ -0,0 +1,44 @@
+# $1 - start or end
+# $2 - fold identifier, no spaces
+# $3 - fold section description
+travis_fold() {
+  local YELLOW='\033[1;33m'
+  local NOCOLOR='\033[0m'
+  if [ -z ${GITHUB_WORKFLOW+x} ]; then
+    echo travis_fold:$1:$2
+    if [ ! -z "${3:-}" ]; then
+      echo -e "${YELLOW}$3${NOCOLOR}"
+    fi
+    echo
+  else
+    if [ $1 = "start" ]; then
+      line="::group::$2"
+      if [ ! -z "${3:-}" ]; then
+        line="$line - ${YELLOW}$3${NOCOLOR}"
+      fi
+    else
+      line="::endgroup::"
+    fi
+    echo -e "$line"
+  fi
+}
+
+__print() {
+  local TITLE=""
+  if [[ -n $2 ]]; then
+      TITLE=" title=$2"
+  fi
+  echo "::$1${TITLE}::$3"
+}
+
+# $1 - title
+# $2 - message
+print_error() {
+  __print error $1 $2
+}
+
+# $1 - title
+# $2 - message
+print_notice() {
+  __print notice $1 $2
+}

.github/actions/build-selftests/prepare_selftests-4.9.0.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile

.github/actions/build-selftests/prepare_selftests-5.5.0.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile

.github/actions/debian/action.yml

@@ -0,0 +1,16 @@
+name: 'debian'
+description: 'Build'
+inputs:
+  target:
+    description: 'Run target'
+    required: true
+runs:
+  using: "composite"
+  steps:
+    - run: |
+        source /tmp/ci_setup
+        bash -x $CI_ROOT/managers/debian.sh SETUP
+        bash -x $CI_ROOT/managers/debian.sh ${{ inputs.target }}
+        bash -x $CI_ROOT/managers/debian.sh CLEANUP
+      shell: bash
+

.github/actions/setup/action.yml

@@ -0,0 +1,23 @@
+name: 'setup'
+description: 'setup env, create /tmp/ci_setup'
+runs:
+  using: "composite"
+  steps:
+    - id: variables
+      run: |
+        export REPO_ROOT=$GITHUB_WORKSPACE
+        export CI_ROOT=$REPO_ROOT/travis-ci
+        # this is somewhat ugly, but that is the easiest way to share this code with
+        # arch specific docker
+        echo 'echo ::group::Env setup' > /tmp/ci_setup
+        echo export DEBIAN_FRONTEND=noninteractive >> /tmp/ci_setup
+        echo sudo apt-get update >> /tmp/ci_setup
+        echo sudo apt-get install -y aptitude qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev libguestfs-tools >> /tmp/ci_setup
+        echo export PROJECT_NAME='libbpf' >> /tmp/ci_setup
+        echo export AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")" >> /tmp/ci_setup
+        echo export REPO_ROOT=$GITHUB_WORKSPACE >> /tmp/ci_setup
+        echo export CI_ROOT=$REPO_ROOT/travis-ci >> /tmp/ci_setup
+        echo export VMTEST_ROOT=$CI_ROOT/vmtest >> /tmp/ci_setup
+        echo 'echo ::endgroup::' >> /tmp/ci_setup
+      shell: bash
+

.github/actions/vmtest/action.yml

@@ -0,0 +1,87 @@
+name: 'vmtest'
+description: 'Build + run vmtest'
+inputs:
+  kernel:
+    description: 'kernel version or LATEST'
+    required: true
+    default: 'LATEST'
+  arch:
+    description: 'what arch to test'
+    required: true
+    default: 'x86_64'
+  pahole:
+    description: 'pahole rev or master'
+    required: true
+    default: 'master'
+runs:
+  using: "composite"
+  steps:
+    # setup envinronment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@master
+      with:
+        pahole: ${{ inputs.pahole }}
+    # 1. download CHECKPOINT kernel source
+    - name: Get checkpoint commit
+      shell: bash
+      run: |
+        cat CHECKPOINT-COMMIT
+        echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
+    - name: Get kernel source at checkpoint
+      uses: libbpf/ci/get-linux-source@master
+      with:
+        repo: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        rev: ${{ env.CHECKPOINT }}
+        dest: '${{ github.workspace }}/.kernel'
+    - name: Patch kernel source
+      uses: libbpf/ci/patch-kernel@master
+      with:
+        patches-root: '${{ github.workspace }}/travis-ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        echo "::group::Prepare buidling selftest"
+        cd .kernel
+        cp ${{ github.workspace }}/travis-ci/vmtest/configs/config-latest.${{ inputs.arch }} .config
+        make olddefconfig && make prepare
+        cd -
+        echo "::endgroup::"
+    # 2. if kernel == LATEST, build kernel image from tree
+    - name: Build kernel image
+      if: ${{ inputs.kernel == 'LATEST' }}
+      shell: bash
+      run: |
+        echo "::group::Build Kernel Image"
+        cd .kernel
+        make -j $((4*$(nproc))) all > /dev/null
+        cp vmlinux ${{ github.workspace }}
+        cd -
+        echo "::endgroup::"
+    # else, just download prebuilt kernel image
+    - name: Download prebuilt kernel
+      if: ${{ inputs.kernel != 'LATEST' }}
+      uses: libbpf/ci/download-vmlinux@master
+      with:
+        kernel: ${{ inputs.kernel }}
+        arch: ${{ inputs.arch }}
+    # 3. build selftests
+    - name: Build BPF selftests
+      uses: ./.github/actions/build-selftests
+      with:
+        repo-path: '.kernel'
+        kernel: ${{ inputs.kernel }}
+    # 4. prepare rootfs
+    - name: prepare rootfs
+      uses: libbpf/ci/prepare-rootfs@master
+      with:
+        kernel: ${{ inputs.kernel }}
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+    # 5. run selftest in QEMU
+    - name: Run selftests
+      uses: libbpf/ci/run-qemu@master
+      with:
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        arch: ${{ inputs.arch }}

.github/workflows/build.yml

@@ -0,0 +1,81 @@
+name: libbpf-build
+
+on:
+  pull_request:
+  push:
+  schedule:
+    - cron:  '0 18 * * *'
+
+concurrency:
+  group: ci-build-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+
+  debian:
+    runs-on: ubuntu-latest
+    name: Debian Build (${{ matrix.name }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: default
+            target: RUN
+          - name: ASan+UBSan
+            target: RUN_ASAN
+          - name: clang
+            target: RUN_CLANG
+          - name: clang ASan+UBSan
+            target: RUN_CLANG_ASAN
+          - name: gcc-10
+            target: RUN_GCC10
+          - name: gcc-10 ASan+UBSan
+            target: RUN_GCC10_ASAN
+    steps:
+      - uses: actions/checkout@v2
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Setup
+      - uses: ./.github/actions/debian
+        name: Build
+        with:
+          target: ${{ matrix.target }}
+
+  ubuntu:
+    runs-on: ubuntu-latest
+    name: Ubuntu Focal Build (${{ matrix.arch }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - arch: aarch64
+          - arch: ppc64le
+          - arch: s390x
+          - arch: x86
+    steps:
+      - uses: actions/checkout@v2
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Pre-Setup
+      - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
+        if: matrix.arch == 'x86'
+        name: Setup
+      - uses: uraimo/run-on-arch-action@v2.0.5
+        name: Build in docker
+        if: matrix.arch != 'x86'
+        with:
+          distro:
+            ubuntu20.04
+          arch:
+            ${{ matrix.arch }}
+          setup:
+            cp /tmp/ci_setup $GITHUB_WORKSPACE
+          dockerRunArgs: |
+            --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
+          shell: /bin/bash
+          install: |
+            export DEBIAN_FRONTEND=noninteractive
+            export TZ="America/Los_Angeles"
+            apt-get update -y
+            apt-get install -y tzdata build-essential sudo
+          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh

.github/workflows/cifuzz.yml

@@ -0,0 +1,40 @@
+---
+# https://google.github.io/oss-fuzz/getting-started/continuous-integration/
+name: CIFuzz
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+jobs:
+  Fuzzing:
+    runs-on: ubuntu-latest
+    if: github.repository == 'libbpf/libbpf'
+    strategy:
+      fail-fast: false
+      matrix:
+        sanitizer: [address, undefined, memory]
+    steps:
+      - name: Build Fuzzers (${{ matrix.sanitizer }})
+        id: build
+        uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master
+        with:
+          oss-fuzz-project-name: 'libbpf'
+          dry-run: false
+          allowed-broken-targets-percentage: 0
+          sanitizer: ${{ matrix.sanitizer }}
+      - name: Run Fuzzers (${{ matrix.sanitizer }})
+        uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master
+        with:
+          oss-fuzz-project-name: 'libbpf'
+          fuzz-seconds: 300
+          dry-run: false
+          sanitizer: ${{ matrix.sanitizer }}
+      - name: Upload Crash
+        uses: actions/upload-artifact@v1
+        if: failure() && steps.build.outcome == 'success'
+        with:
+          name: ${{ matrix.sanitizer }}-artifacts
+          path: ./out/artifacts

.github/workflows/coverity.yml

@@ -0,0 +1,31 @@
+name: libbpf-ci-coverity
+
+on:
+  schedule:
+    - cron:  '0 18 * * *'
+
+
+jobs:
+  coverity:
+    runs-on: ubuntu-latest
+    if: github.repository == 'libbpf/libbpf'
+    name: Coverity
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/setup
+      - name: Run coverity
+        run: |
+          echo ::group::Setup CI env
+          source /tmp/ci_setup
+          export COVERITY_SCAN_NOTIFICATION_EMAIL="${AUTHOR_EMAIL}"
+          export COVERITY_SCAN_BRANCH_PATTERN=${GITHUB_REF##refs/*/}
+          export TRAVIS_BRANCH=${COVERITY_SCAN_BRANCH_PATTERN}
+          echo ::endgroup::
+          scripts/coverity.sh
+        env:
+          COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}
+          COVERITY_SCAN_PROJECT_NAME: libbpf
+          COVERITY_SCAN_BUILD_COMMAND_PREPEND: 'cd src/'
+          COVERITY_SCAN_BUILD_COMMAND: 'make'
+      - name: SCM log
+        run: cat /home/runner/work/libbpf/libbpf/src/cov-int/scm_log.txt

.github/workflows/ondemand.yml

@@ -0,0 +1,36 @@
+name: ondemand
+
+on:
+  workflow_dispatch:
+    inputs:
+      kernel-origin:
+        description: 'git repo for linux kernel'
+        default: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        required: true
+      kernel-rev:
+        description: 'rev/tag/branch for linux kernel'
+        default: "master"
+        required: true
+      pahole-origin:
+        description: 'git repo for pahole'
+        default: 'https://git.kernel.org/pub/scm/devel/pahole/pahole.git'
+        required: true
+      pahole-rev:
+        description: 'ref/tag/branch for pahole'
+        default: "master"
+        required: true
+
+jobs:
+  vmtest:
+    runs-on: ubuntu-latest
+    name: vmtest with customized pahole/Kernel
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/setup
+      - uses: ./.github/actions/vmtest
+        with:
+          kernel: 'LATEST'
+          kernel-rev: ${{ github.event.inputs.kernel-rev }}
+          kernel-origin: ${{ github.event.inputs.kernel-origin }}
+          pahole: ${{ github.event.inputs.pahole-rev }}
+          pahole-origin: ${{ github.event.inputs.pahole-origin }}

.github/workflows/pahole.yml

@@ -0,0 +1,20 @@
+name: pahole-staging
+
+on:
+  schedule:
+    - cron:  '0 18 * * *'
+
+
+jobs:
+  vmtest:
+    runs-on: ubuntu-latest
+    name: Kernel LATEST + staging pahole
+    env:
+      STAGING: tmp.master
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/setup
+      - uses: ./.github/actions/vmtest
+        with:
+          kernel: LATEST
+          pahole: $STAGING

.github/workflows/test.yml

@@ -0,0 +1,42 @@
+name: libbpf-ci
+
+on: 
+  pull_request:
+  push:
+  schedule:
+    - cron:  '0 18 * * *'
+
+concurrency: 
+  group: ci-test-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  vmtest:
+    runs-on: ${{ matrix.runs_on }}
+    name: Kernel ${{ matrix.kernel }} on ${{ matrix.runs_on }} + selftests
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - kernel: 'LATEST'
+            runs_on: ubuntu-latest
+            arch: 'x86_64'
+          - kernel: '5.5.0'
+            runs_on: ubuntu-latest
+            arch: 'x86_64'
+          - kernel: '4.9.0'
+            runs_on: ubuntu-latest
+            arch: 'x86_64'
+          - kernel: 'LATEST'
+            runs_on: z15
+            arch: 's390x'
+    steps:
+      - uses: actions/checkout@v2
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Setup
+      - uses: ./.github/actions/vmtest
+        name: vmtest
+        with:
+          kernel: ${{ matrix.kernel }}
+          arch: ${{ matrix.arch }}

.lgtm.yml

@@ -0,0 +1,14 @@
+# vi: set ts=2 sw=2:
+extraction:
+  cpp:
+    prepare:
+      packages:
+        - libelf-dev
+        - pkg-config
+    after_prepare:
+      # As the buildsystem detection by LGTM is performed _only_ during the
+      # 'configure' phase, we need to trick LGTM we use a supported build
+      # system (configure, meson, cmake, etc.). This way LGTM correctly detects
+      # that our sources are in the src/ subfolder.
+      - touch src/configure
+      - chmod +x src/configure

.readthedocs.yaml

@@ -0,0 +1,17 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  builder: html
+  configuration: docs/conf.py
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+   version: 3.7
+   install:
+   - requirements: docs/sphinx/requirements.txt

.travis.yml

@@ -1,122 +1,130 @@
 sudo: required
-dist: xenial
+language: bash
+dist: focal
 services:
     - docker
 
 env:
     global:
-        - AUTHOR_EMAIL="$(git log -1 $TRAVIS_COMMIT --pretty=\"%aE\")"
-        - CI_MANAGERS="$TRAVIS_BUILD_DIR/travis-ci/managers"
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
         - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+
+stages:
+    # Run Coverity periodically instead of for each PR for following reasons:
+    # 1) Coverity jobs are heavily rate-limited
+    # 2) Due to security restrictions of encrypted environment variables
+    #    in Travis CI, pull requests made from forks can't access encrypted
+    #    env variables, making Coverity unusable
+    #    See: https://docs.travis-ci.com/user/pull-requests#pull-requests-and-security-restrictions
+    - name: Coverity
+      if: type = cron
 
 jobs:
     include:
-        - stage: Build & test
-          name: Debian Testing
+        - stage: Builds & Tests
+          name: Kernel 5.5.0 + selftests
+          language: bash
+          env: KERNEL=5.5.0
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1
+
+        - name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1
+
+        - name: Kernel 4.9.0 + selftests
+          language: bash
+          env: KERNEL=4.9.0
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1
+
+        - name: Debian Build
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Debian Build (ASan+UBSan)
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN_ASAN || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Debian Build (clang)
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Debian Build (clang ASan+UBSan)
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG_ASAN || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Debian Build (gcc-10)
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC10 || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Debian Build (gcc-10 ASan+UBSan)
+          language: bash
+          install:        $CI_ROOT/managers/debian.sh SETUP
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC10_ASAN || travis_terminate 1
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
+
+        - name: Ubuntu Focal Build
+          language: bash
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
+
+        - name: Ubuntu Focal Build (arm)
+          arch: arm64
+          language: bash
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
+
+        - name: Ubuntu Focal Build (s390x)
+          arch: s390x
+          language: bash
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
+
+        - name: Ubuntu Focal Build (ppc64le)
+          arch: ppc64le
+          language: bash
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
+
+        - stage: Coverity
           language: bash
           env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
+              # Coverity configuration
+              # COVERITY_SCAN_TOKEN=xxx
+              # Encrypted using `travis encrypt --repo libbpf/libbpf COVERITY_SCAN_TOKEN=xxx`
+              - secure: "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"
+              - COVERITY_SCAN_PROJECT_NAME="libbpf"
+              - COVERITY_SCAN_NOTIFICATION_EMAIL="${AUTHOR_EMAIL}"
+              - COVERITY_SCAN_BRANCH_PATTERN="$TRAVIS_BRANCH"
+              # Note: `make -C src/` as a BUILD_COMMAND will not work here
+              - COVERITY_SCAN_BUILD_COMMAND_PREPEND="cd src/"
+              - COVERITY_SCAN_BUILD_COMMAND="make"
           install:
-              - $CI_MANAGERS/debian.sh SETUP
+              - sudo echo 'deb-src http://archive.ubuntu.com/ubuntu/ focal main restricted universe multiverse' >>/etc/apt/sources.list
+              - sudo apt-get update
+              - sudo apt-get -y build-dep libelf-dev
+              - sudo apt-get install -y libelf-dev pkg-config
           script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Debian Testing (ASan+UBSan)
-          language: bash
-          env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN_ASAN
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Debian Testing (clang)
-          language: bash
-          env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN_CLANG
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Debian Testing (clang ASan+UBSan)
-          language: bash
-          env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN_CLANG_ASAN
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Debian Testing (gcc-8)
-          language: bash
-          env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN_GCC8
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Debian Testing (gcc-8 ASan+UBSan)
-          language: bash
-          env:
-              - DEBIAN_RELEASE="testing"
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          script:
-              - set -e
-              - $CI_MANAGERS/debian.sh RUN_GCC8_ASAN
-              - set +e
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
-
-        - name: Ubuntu Xenial
-          language: bash
-          script:
-              - set -e
-              - sudo $CI_MANAGERS/xenial.sh
-              - set +e
+              - scripts/coverity.sh || travis_terminate 1
+    allow_failures:
+        - env: KERNEL=x.x.x

BPF-CHECKPOINT-COMMIT

@@ -0,0 +1 @@
+fe68195daf34d5dddacd3f93dd3eafc4beca3a0e

CHECKPOINT-COMMIT

@@ -1 +1 @@
-f49aa1de98363b6c5fba4637678d6b0ba3d18065
+dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca

LICENSE

@@ -0,0 +1 @@
+LGPL-2.1 OR BSD-2-Clause

LICENSE.BSD-2-Clause

@@ -0,0 +1,32 @@
+Valid-License-Identifier: BSD-2-Clause
+SPDX-URL: https://spdx.org/licenses/BSD-2-Clause.html
+Usage-Guide:
+  To use the BSD 2-clause "Simplified" License put the following SPDX
+  tag/value pair into a comment according to the placement guidelines in
+  the licensing rules documentation:
+    SPDX-License-Identifier: BSD-2-Clause
+License-Text:
+
+Copyright (c) <year> <owner> . All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

LICENSE.LGPL-2.1

@@ -0,0 +1,503 @@
+Valid-License-Identifier: LGPL-2.1
+Valid-License-Identifier: LGPL-2.1+
+SPDX-URL: https://spdx.org/licenses/LGPL-2.1.html
+Usage-Guide:
+  To use this license in source code, put one of the following SPDX
+  tag/value pairs into a comment according to the placement
+  guidelines in the licensing rules documentation.
+  For 'GNU Lesser General Public License (LGPL) version 2.1 only' use:
+    SPDX-License-Identifier: LGPL-2.1
+  For 'GNU Lesser General Public License (LGPL) version 2.1 or any later
+  version' use:
+    SPDX-License-Identifier: LGPL-2.1+
+License-Text:
+
+GNU LESSER GENERAL PUBLIC LICENSE
+Version 2.1, February 1999
+
+Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+Everyone is permitted to copy and distribute verbatim copies of this
+license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL. It also counts as
+the successor of the GNU Library Public License, version 2, hence the
+version number 2.1.]
+
+Preamble
+
+The licenses for most software are designed to take away your freedom to
+share and change it. By contrast, the GNU General Public Licenses are
+intended to guarantee your freedom to share and change free software--to
+make sure the software is free for all its users.
+
+This license, the Lesser General Public License, applies to some specially
+designated software packages--typically libraries--of the Free Software
+Foundation and other authors who decide to use it. You can use it too, but
+we suggest you first think carefully about whether this license or the
+ordinary General Public License is the better strategy to use in any
+particular case, based on the explanations below.
+
+When we speak of free software, we are referring to freedom of use, not
+price. Our General Public Licenses are designed to make sure that you have
+the freedom to distribute copies of free software (and charge for this
+service if you wish); that you receive source code or can get it if you
+want it; that you can change the software and use pieces of it in new free
+programs; and that you are informed that you can do these things.
+
+To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights. These restrictions translate to certain responsibilities for you if
+you distribute copies of the library or if you modify it.
+
+For example, if you distribute copies of the library, whether gratis or for
+a fee, you must give the recipients all the rights that we gave you. You
+must make sure that they, too, receive or can get the source code. If you
+link other code with the library, you must provide complete object files to
+the recipients, so that they can relink them with the library after making
+changes to the library and recompiling it. And you must show them these
+terms so they know their rights.
+
+We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+To protect each distributor, we want to make it very clear that there is no
+warranty for the free library. Also, if the library is modified by someone
+else and passed on, the recipients should know that what they have is not
+the original version, so that the original author's reputation will not be
+affected by problems that might be introduced by others.
+
+Finally, software patents pose a constant threat to the existence of any
+free program. We wish to make sure that a company cannot effectively
+restrict the users of a free program by obtaining a restrictive license
+from a patent holder. Therefore, we insist that any patent license obtained
+for a version of the library must be consistent with the full freedom of
+use specified in this license.
+
+Most GNU software, including some libraries, is covered by the ordinary GNU
+General Public License. This license, the GNU Lesser General Public
+License, applies to certain designated libraries, and is quite different
+from the ordinary General Public License. We use this license for certain
+libraries in order to permit linking those libraries into non-free
+programs.
+
+When a program is linked with a library, whether statically or using a
+shared library, the combination of the two is legally speaking a combined
+work, a derivative of the original library. The ordinary General Public
+License therefore permits such linking only if the entire combination fits
+its criteria of freedom. The Lesser General Public License permits more lax
+criteria for linking other code with the library.
+
+We call this license the "Lesser" General Public License because it does
+Less to protect the user's freedom than the ordinary General Public
+License. It also provides other free software developers Less of an
+advantage over competing non-free programs. These disadvantages are the
+reason we use the ordinary General Public License for many
+libraries. However, the Lesser license provides advantages in certain
+special circumstances.
+
+For example, on rare occasions, there may be a special need to encourage
+the widest possible use of a certain library, so that it becomes a de-facto
+standard. To achieve this, non-free programs must be allowed to use the
+library. A more frequent case is that a free library does the same job as
+widely used non-free libraries. In this case, there is little to gain by
+limiting the free library to free software only, so we use the Lesser
+General Public License.
+
+In other cases, permission to use a particular library in non-free programs
+enables a greater number of people to use a large body of free
+software. For example, permission to use the GNU C Library in non-free
+programs enables many more people to use the whole GNU operating system, as
+well as its variant, the GNU/Linux operating system.
+
+Although the Lesser General Public License is Less protective of the users'
+freedom, it does ensure that the user of a program that is linked with the
+Library has the freedom and the wherewithal to run that program using a
+modified version of the Library.
+
+The precise terms and conditions for copying, distribution and modification
+follow. Pay close attention to the difference between a "work based on the
+library" and a "work that uses the library". The former contains code
+derived from the library, whereas the latter must be combined with the
+library in order to run.
+
+TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+0. This License Agreement applies to any software library or other program
+   which contains a notice placed by the copyright holder or other
+   authorized party saying it may be distributed under the terms of this
+   Lesser General Public License (also called "this License"). Each
+   licensee is addressed as "you".
+
+   A "library" means a collection of software functions and/or data
+   prepared so as to be conveniently linked with application programs
+   (which use some of those functions and data) to form executables.
+
+   The "Library", below, refers to any such software library or work which
+   has been distributed under these terms. A "work based on the Library"
+   means either the Library or any derivative work under copyright law:
+   that is to say, a work containing the Library or a portion of it, either
+   verbatim or with modifications and/or translated straightforwardly into
+   another language. (Hereinafter, translation is included without
+   limitation in the term "modification".)
+
+   "Source code" for a work means the preferred form of the work for making
+   modifications to it. For a library, complete source code means all the
+   source code for all modules it contains, plus any associated interface
+   definition files, plus the scripts used to control compilation and
+   installation of the library.
+
+    Activities other than copying, distribution and modification are not
+    covered by this License; they are outside its scope. The act of running
+    a program using the Library is not restricted, and output from such a
+    program is covered only if its contents constitute a work based on the
+    Library (independent of the use of the Library in a tool for writing
+    it). Whether that is true depends on what the Library does and what the
+    program that uses the Library does.
+
+1. You may copy and distribute verbatim copies of the Library's complete
+   source code as you receive it, in any medium, provided that you
+   conspicuously and appropriately publish on each copy an appropriate
+   copyright notice and disclaimer of warranty; keep intact all the notices
+   that refer to this License and to the absence of any warranty; and
+   distribute a copy of this License along with the Library.
+
+   You may charge a fee for the physical act of transferring a copy, and
+   you may at your option offer warranty protection in exchange for a fee.
+
+2. You may modify your copy or copies of the Library or any portion of it,
+   thus forming a work based on the Library, and copy and distribute such
+   modifications or work under the terms of Section 1 above, provided that
+   you also meet all of these conditions:
+
+   a) The modified work must itself be a software library.
+
+   b) You must cause the files modified to carry prominent notices stating
+      that you changed the files and the date of any change.
+
+   c) You must cause the whole of the work to be licensed at no charge to
+      all third parties under the terms of this License.
+
+   d) If a facility in the modified Library refers to a function or a table
+      of data to be supplied by an application program that uses the
+      facility, other than as an argument passed when the facility is
+      invoked, then you must make a good faith effort to ensure that, in
+      the event an application does not supply such function or table, the
+      facility still operates, and performs whatever part of its purpose
+      remains meaningful.
+
+   (For example, a function in a library to compute square roots has a
+    purpose that is entirely well-defined independent of the
+    application. Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must be
+    optional: if the application does not supply it, the square root
+    function must still compute square roots.)
+
+   These requirements apply to the modified work as a whole. If
+   identifiable sections of that work are not derived from the Library, and
+   can be reasonably considered independent and separate works in
+   themselves, then this License, and its terms, do not apply to those
+   sections when you distribute them as separate works. But when you
+   distribute the same sections as part of a whole which is a work based on
+   the Library, the distribution of the whole must be on the terms of this
+   License, whose permissions for other licensees extend to the entire
+   whole, and thus to each and every part regardless of who wrote it.
+
+   Thus, it is not the intent of this section to claim rights or contest
+   your rights to work written entirely by you; rather, the intent is to
+   exercise the right to control the distribution of derivative or
+   collective works based on the Library.
+
+   In addition, mere aggregation of another work not based on the Library
+   with the Library (or with a work based on the Library) on a volume of a
+   storage or distribution medium does not bring the other work under the
+   scope of this License.
+
+3. You may opt to apply the terms of the ordinary GNU General Public
+   License instead of this License to a given copy of the Library. To do
+   this, you must alter all the notices that refer to this License, so that
+   they refer to the ordinary GNU General Public License, version 2,
+   instead of to this License. (If a newer version than version 2 of the
+   ordinary GNU General Public License has appeared, then you can specify
+   that version instead if you wish.) Do not make any other change in these
+   notices.
+
+   Once this change is made in a given copy, it is irreversible for that
+   copy, so the ordinary GNU General Public License applies to all
+   subsequent copies and derivative works made from that copy.
+
+   This option is useful when you wish to copy part of the code of the
+   Library into a program that is not a library.
+
+4. You may copy and distribute the Library (or a portion or derivative of
+   it, under Section 2) in object code or executable form under the terms
+   of Sections 1 and 2 above provided that you accompany it with the
+   complete corresponding machine-readable source code, which must be
+   distributed under the terms of Sections 1 and 2 above on a medium
+   customarily used for software interchange.
+
+   If distribution of object code is made by offering access to copy from a
+   designated place, then offering equivalent access to copy the source
+   code from the same place satisfies the requirement to distribute the
+   source code, even though third parties are not compelled to copy the
+   source along with the object code.
+
+5. A program that contains no derivative of any portion of the Library, but
+   is designed to work with the Library by being compiled or linked with
+   it, is called a "work that uses the Library". Such a work, in isolation,
+   is not a derivative work of the Library, and therefore falls outside the
+   scope of this License.
+
+   However, linking a "work that uses the Library" with the Library creates
+   an executable that is a derivative of the Library (because it contains
+   portions of the Library), rather than a "work that uses the
+   library". The executable is therefore covered by this License. Section 6
+   states terms for distribution of such executables.
+
+   When a "work that uses the Library" uses material from a header file
+   that is part of the Library, the object code for the work may be a
+   derivative work of the Library even though the source code is
+   not. Whether this is true is especially significant if the work can be
+   linked without the Library, or if the work is itself a library. The
+   threshold for this to be true is not precisely defined by law.
+
+   If such an object file uses only numerical parameters, data structure
+   layouts and accessors, and small macros and small inline functions (ten
+   lines or less in length), then the use of the object file is
+   unrestricted, regardless of whether it is legally a derivative
+   work. (Executables containing this object code plus portions of the
+   Library will still fall under Section 6.)
+
+   Otherwise, if the work is a derivative of the Library, you may
+   distribute the object code for the work under the terms of Section
+   6. Any executables containing that work also fall under Section 6,
+   whether or not they are linked directly with the Library itself.
+
+6. As an exception to the Sections above, you may also combine or link a
+   "work that uses the Library" with the Library to produce a work
+   containing portions of the Library, and distribute that work under terms
+   of your choice, provided that the terms permit modification of the work
+   for the customer's own use and reverse engineering for debugging such
+   modifications.
+
+   You must give prominent notice with each copy of the work that the
+   Library is used in it and that the Library and its use are covered by
+   this License. You must supply a copy of this License. If the work during
+   execution displays copyright notices, you must include the copyright
+   notice for the Library among them, as well as a reference directing the
+   user to the copy of this License. Also, you must do one of these things:
+
+   a) Accompany the work with the complete corresponding machine-readable
+      source code for the Library including whatever changes were used in
+      the work (which must be distributed under Sections 1 and 2 above);
+      and, if the work is an executable linked with the Library, with the
+      complete machine-readable "work that uses the Library", as object
+      code and/or source code, so that the user can modify the Library and
+      then relink to produce a modified executable containing the modified
+      Library. (It is understood that the user who changes the contents of
+      definitions files in the Library will not necessarily be able to
+      recompile the application to use the modified definitions.)
+
+   b) Use a suitable shared library mechanism for linking with the
+      Library. A suitable mechanism is one that (1) uses at run time a copy
+      of the library already present on the user's computer system, rather
+      than copying library functions into the executable, and (2) will
+      operate properly with a modified version of the library, if the user
+      installs one, as long as the modified version is interface-compatible
+      with the version that the work was made with.
+
+   c) Accompany the work with a written offer, valid for at least three
+      years, to give the same user the materials specified in Subsection
+      6a, above, for a charge no more than the cost of performing this
+      distribution.
+
+   d) If distribution of the work is made by offering access to copy from a
+      designated place, offer equivalent access to copy the above specified
+      materials from the same place.
+
+   e) Verify that the user has already received a copy of these materials
+      or that you have already sent this user a copy.
+
+   For an executable, the required form of the "work that uses the Library"
+   must include any data and utility programs needed for reproducing the
+   executable from it. However, as a special exception, the materials to be
+   distributed need not include anything that is normally distributed (in
+   either source or binary form) with the major components (compiler,
+   kernel, and so on) of the operating system on which the executable runs,
+   unless that component itself accompanies the executable.
+
+   It may happen that this requirement contradicts the license restrictions
+   of other proprietary libraries that do not normally accompany the
+   operating system. Such a contradiction means you cannot use both them
+   and the Library together in an executable that you distribute.
+
+7. You may place library facilities that are a work based on the Library
+   side-by-side in a single library together with other library facilities
+   not covered by this License, and distribute such a combined library,
+   provided that the separate distribution of the work based on the Library
+   and of the other library facilities is otherwise permitted, and provided
+   that you do these two things:
+
+   a) Accompany the combined library with a copy of the same work based on
+      the Library, uncombined with any other library facilities. This must
+      be distributed under the terms of the Sections above.
+
+   b) Give prominent notice with the combined library of the fact that part
+      of it is a work based on the Library, and explaining where to find
+      the accompanying uncombined form of the same work.
+
+8. You may not copy, modify, sublicense, link with, or distribute the
+   Library except as expressly provided under this License. Any attempt
+   otherwise to copy, modify, sublicense, link with, or distribute the
+   Library is void, and will automatically terminate your rights under this
+   License. However, parties who have received copies, or rights, from you
+   under this License will not have their licenses terminated so long as
+   such parties remain in full compliance.
+
+9. You are not required to accept this License, since you have not signed
+   it. However, nothing else grants you permission to modify or distribute
+   the Library or its derivative works. These actions are prohibited by law
+   if you do not accept this License. Therefore, by modifying or
+   distributing the Library (or any work based on the Library), you
+   indicate your acceptance of this License to do so, and all its terms and
+   conditions for copying, distributing or modifying the Library or works
+   based on it.
+
+10. Each time you redistribute the Library (or any work based on the
+    Library), the recipient automatically receives a license from the
+    original licensor to copy, distribute, link with or modify the Library
+    subject to these terms and conditions. You may not impose any further
+    restrictions on the recipients' exercise of the rights granted
+    herein. You are not responsible for enforcing compliance by third
+    parties with this License.
+
+11. If, as a consequence of a court judgment or allegation of patent
+    infringement or for any other reason (not limited to patent issues),
+    conditions are imposed on you (whether by court order, agreement or
+    otherwise) that contradict the conditions of this License, they do not
+    excuse you from the conditions of this License. If you cannot
+    distribute so as to satisfy simultaneously your obligations under this
+    License and any other pertinent obligations, then as a consequence you
+    may not distribute the Library at all. For example, if a patent license
+    would not permit royalty-free redistribution of the Library by all
+    those who receive copies directly or indirectly through you, then the
+    only way you could satisfy both it and this License would be to refrain
+    entirely from distribution of the Library.
+
+    If any portion of this section is held invalid or unenforceable under
+    any particular circumstance, the balance of the section is intended to
+    apply, and the section as a whole is intended to apply in other
+    circumstances.
+
+    It is not the purpose of this section to induce you to infringe any
+    patents or other property right claims or to contest validity of any
+    such claims; this section has the sole purpose of protecting the
+    integrity of the free software distribution system which is implemented
+    by public license practices. Many people have made generous
+    contributions to the wide range of software distributed through that
+    system in reliance on consistent application of that system; it is up
+    to the author/donor to decide if he or she is willing to distribute
+    software through any other system and a licensee cannot impose that
+    choice.
+
+    This section is intended to make thoroughly clear what is believed to
+    be a consequence of the rest of this License.
+
+12. If the distribution and/or use of the Library is restricted in certain
+    countries either by patents or by copyrighted interfaces, the original
+    copyright holder who places the Library under this License may add an
+    explicit geographical distribution limitation excluding those
+    countries, so that distribution is permitted only in or among countries
+    not thus excluded. In such case, this License incorporates the
+    limitation as if written in the body of this License.
+
+13. The Free Software Foundation may publish revised and/or new versions of
+    the Lesser General Public License from time to time. Such new versions
+    will be similar in spirit to the present version, but may differ in
+    detail to address new problems or concerns.
+
+    Each version is given a distinguishing version number. If the Library
+    specifies a version number of this License which applies to it and "any
+    later version", you have the option of following the terms and
+    conditions either of that version or of any later version published by
+    the Free Software Foundation. If the Library does not specify a license
+    version number, you may choose any version ever published by the Free
+    Software Foundation.
+
+14. If you wish to incorporate parts of the Library into other free
+    programs whose distribution conditions are incompatible with these,
+    write to the author to ask for permission. For software which is
+    copyrighted by the Free Software Foundation, write to the Free Software
+    Foundation; we sometimes make exceptions for this. Our decision will be
+    guided by the two goals of preserving the free status of all
+    derivatives of our free software and of promoting the sharing and reuse
+    of software generally.
+
+NO WARRANTY
+
+15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+    FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+    OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+    PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER
+    EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
+    ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE LIBRARY IS WITH
+    YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL
+    NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+    WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+    REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU FOR
+    DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL
+    DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE LIBRARY
+    (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED
+    INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF
+    THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF SUCH HOLDER OR
+    OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+END OF TERMS AND CONDITIONS
+
+How to Apply These Terms to Your New Libraries
+
+If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change. You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+To apply these terms, attach the following notices to the library. It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+one line to give the library's name and an idea of what it does.
+Copyright (C) year name of author
+
+This library is free software; you can redistribute it and/or modify it
+under the terms of the GNU Lesser General Public License as published by
+the Free Software Foundation; either version 2.1 of the License, or (at
+your option) any later version.
+
+This library is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License
+for more details.
+
+You should have received a copy of the GNU Lesser General Public License
+along with this library; if not, write to the Free Software Foundation,
+Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA Also add
+information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary. Here is a sample; alter the names:
+
+Yoyodyne, Inc., hereby disclaims all copyright interest in
+the library `Frob' (a library for tweaking knobs) written
+by James Random Hacker.
+
+signature of Ty Coon, 1 April 1990
+Ty Coon, President of Vice
+That's all there is to it!

README.md

@@ -1,29 +1,54 @@
-
-This is a mirror of [bpf-next linux tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next)'s
+This is a mirror of [bpf-next Linux source
+tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next)'s
 `tools/lib/bpf` directory plus its supporting header files.
 
-The following files will by sync'ed with bpf-next repo:
-  - `src/` <-> `bpf-next/tools/lib/bpf/`
-  - `include/uapi/linux/bpf_common.h` <-> `bpf-next/tools/include/uapi/linux/bpf_common.h`
-  - `include/uapi/linux/bpf.h` <-> `bpf-next/tools/include/uapi/linux/bpf.h`
-  - `include/uapi/linux/btf.h` <-> `bpf-next/tools/include/uapi/linux/btf.h`
-  - `include/uapi/linux/if_link.h` <-> `bpf-next/tools/include/uapi/linux/if_link.h`
-  - `include/uapi/linux/if_xdp.h` <-> `bpf-next/tools/include/uapi/linux/if_xdp.h`
-  - `include/uapi/linux/netlink.h` <-> `bpf-next/tools/include/uapi/linux/netlink.h`
-  - `include/tools/libc_compat.h` <-> `bpf-next/tools/include/tools/libc_compat.h`
+All the gory details of syncing can be found in `scripts/sync-kernel.sh`
+script.
 
-Other header files at this repo (`include/linux/*.h`) are reduced versions of
-their counterpart files at bpf-next's `tools/include/linux/*.h` to make compilation
-successful.
+Some header files in this repo (`include/linux/*.h`) are reduced versions of
+their counterpart files at
+[bpf-next](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/)'s
+`tools/include/linux/*.h` to make compilation successful.
 
-Build [![Build Status](https://travis-ci.org/libbpf/libbpf.svg?branch=master)](https://travis-ci.org/libbpf/libbpf)
+BPF/libbpf usage and questions
+==============================
+
+Please check out [libbpf-bootstrap](https://github.com/libbpf/libbpf-bootstrap)
+and [the companion blog post](https://nakryiko.com/posts/libbpf-bootstrap/) for
+the examples of building BPF applications with libbpf.
+[libbpf-tools](https://github.com/iovisor/bcc/tree/master/libbpf-tools) are also
+a good source of the real-world libbpf-based tracing tools.
+
+See also ["BPF CO-RE reference guide"](https://nakryiko.com/posts/bpf-core-reference-guide/)
+for the coverage of practical aspects of building BPF CO-RE applications and
+["BPF CO-RE"](https://nakryiko.com/posts/bpf-portability-and-co-re/) for
+general introduction into BPF portability issues and BPF CO-RE origins.
+
+All general BPF questions, including kernel functionality, libbpf APIs and
+their application, should be sent to bpf@vger.kernel.org mailing list. You can
+subscribe to it [here](http://vger.kernel.org/vger-lists.html#bpf) and search
+its archive [here](https://lore.kernel.org/bpf/). Please search the archive
+before asking new questions. It very well might be that this was already
+addressed or answered before.
+
+bpf@vger.kernel.org is monitored by many more people and they will happily try
+to help you with whatever issue you have. This repository's PRs and issues
+should be opened only for dealing with issues pertaining to specific way this
+libbpf mirror repo is set up and organized.
+
+Build
+[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
+[![Total alerts](https://img.shields.io/lgtm/alerts/g/libbpf/libbpf.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/libbpf/libbpf/alerts/)
+[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
+[![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
 =====
 libelf is an internal dependency of libbpf and thus it is required to link
 against and must be installed on the system for applications to work.
 pkg-config is used by default to find libelf, and the program called can be
 overridden with `PKG_CONFIG`.
-If using `pkg-config` at build time is not desired, it can be disabled by setting
-`NO_PKG_CONFIG=1` when calling make.
+
+If using `pkg-config` at build time is not desired, it can be disabled by
+setting `NO_PKG_CONFIG=1` when calling make.
 
 To build both static libbpf.a and shared libbpf.so:
 ```bash
@@ -48,23 +73,91 @@ $ cd src
 $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make install
 ```
 
-To integrate libbpf into a project which uses Meson building system define
-`[wrap-git]` file in `subprojects` folder.
-To add libbpf dependency to the parent parent project, e.g. for
-libbpf_static_dep:
-```
-libbpf_obj = subproject('libbpf', required : true)
-libbpf_static_dep = libbpf_proj.get_variable('libbpf_static_dep')
-```
+Distributions
+=============
 
-To validate changes to meson.build
-```bash
-$ python3 meson.py build
-$ ninja -C build/
-```
+Distributions packaging libbpf from this mirror:
+  - [Fedora](https://src.fedoraproject.org/rpms/libbpf)
+  - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
+  - [Debian](https://packages.debian.org/source/sid/libbpf)
+  - [Arch](https://www.archlinux.org/packages/extra/x86_64/libbpf/)
+  - [Ubuntu](https://packages.ubuntu.com/source/impish/libbpf)
+  - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
 
-To install headers, libs and pkgconfig
-```bash
-$ cd build
-$ ninja install
+Benefits of packaging from the mirror over packaging from kernel sources:
+  - Consistent versioning across distributions.
+  - No ties to any specific kernel, transparent handling of older kernels.
+    Libbpf is designed to be kernel-agnostic and work across multitude of
+    kernel versions. It has built-in mechanisms to gracefully handle older
+    kernels, that are missing some of the features, by working around or
+    gracefully degrading functionality. Thus libbpf is not tied to a specific
+    kernel version and can/should be packaged and versioned independently.
+  - Continuous integration testing via
+    [TravisCI](https://travis-ci.org/libbpf/libbpf).
+  - Static code analysis via [LGTM](https://lgtm.com/projects/g/libbpf/libbpf)
+    and [Coverity](https://scan.coverity.com/projects/libbpf).
+
+Package dependencies of libbpf, package names may vary across distros:
+  - zlib
+  - libelf
+
+BPF CO-RE (Compile Once – Run Everywhere)
+=========================================
+
+Libbpf supports building BPF CO-RE-enabled applications, which, in contrast to
+[BCC](https://github.com/iovisor/bcc/), do not require Clang/LLVM runtime
+being deployed to target servers and doesn't rely on kernel-devel headers
+being available.
+
+It does rely on kernel to be built with [BTF type
+information](https://www.kernel.org/doc/html/latest/bpf/btf.html), though.
+Some major Linux distributions come with kernel BTF already built in:
+  - Fedora 31+
+  - RHEL 8.2+
+  - OpenSUSE Tumbleweed (in the next release, as of 2020-06-04)
+  - Arch Linux (from kernel 5.7.1.arch1-1)
+  - Manjaro (from kernel 5.4 if compiled after 2021-06-18)
+  - Ubuntu 20.10
+  - Debian 11 (amd64/arm64)
+
+If your kernel doesn't come with BTF built-in, you'll need to build custom
+kernel. You'll need:
+  - `pahole` 1.16+ tool (part of `dwarves` package), which performs DWARF to
+    BTF conversion;
+  - kernel built with `CONFIG_DEBUG_INFO_BTF=y` option;
+  - you can check if your kernel has BTF built-in by looking for
+    `/sys/kernel/btf/vmlinux` file:
+  
+```shell
+$ ls -la /sys/kernel/btf/vmlinux
+-r--r--r--. 1 root root 3541561 Jun  2 18:16 /sys/kernel/btf/vmlinux
 ```
+  
+To develop and build BPF programs, you'll need Clang/LLVM 10+. The following
+distributions have Clang/LLVM 10+ packaged by default:
+  - Fedora 32+
+  - Ubuntu 20.04+
+  - Arch Linux
+  - Ubuntu 20.10 (LLVM 11)
+  - Debian 11 (LLVM 11)
+  - Alpine 3.13+
+
+Otherwise, please make sure to update it on your system.
+
+The following resources are useful to understand what BPF CO-RE is and how to
+use it:
+- [BPF CO-RE reference guide](https://nakryiko.com/posts/bpf-core-reference-guide/)
+- [BPF Portability and CO-RE](https://nakryiko.com/posts/bpf-portability-and-co-re/)
+- [HOWTO: BCC to libbpf conversion](https://nakryiko.com/posts/bcc-to-libbpf-howto-guide/)
+- [libbpf-tools in BCC repo](https://github.com/iovisor/bcc/tree/master/libbpf-tools)
+  contain lots of real-world tools converted from BCC to BPF CO-RE. Consider
+  converting some more to both contribute to the BPF community and gain some
+  more experience with it.
+
+License
+=======
+
+This work is dual-licensed under BSD 2-clause license and GNU LGPL v2.1 license.
+You can choose between one of them if you use this work.
+
+`SPDX-License-Identifier: BSD-2-Clause OR LGPL-2.1`

docs/.gitignore

@@ -0,0 +1,2 @@
+sphinx/build
+sphinx/doxygen/build

docs/api.rst

@@ -0,0 +1,93 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+.. _api:
+
+.. toctree:: Table of Contents
+
+
+LIBBPF API
+==========
+
+Error Handling
+--------------
+
+When libbpf is used in "libbpf 1.0 mode", API functions can return errors in one of two ways.
+
+You can set "libbpf 1.0" mode with the following line:
+
+.. code-block::
+
+    libbpf_set_strict_mode(LIBBPF_STRICT_DIRECT_ERRS | LIBBPF_STRICT_CLEAN_PTRS);
+
+If the function returns an error code directly, it uses 0 to indicate success
+and a negative error code to indicate what caused the error. In this case the
+error code should be checked directly from the return, you do not need to check
+errno.
+
+For example:
+
+.. code-block::
+
+    err = some_libbpf_api_with_error_return(...);
+    if (err < 0) {
+        /* Handle error accordingly */
+    }
+
+If the function returns a pointer, it will return NULL to indicate there was
+an error. In this case errno should be checked for the error code.
+
+For example:
+
+.. code-block::
+
+    ptr = some_libbpf_api_returning_ptr();
+    if (!ptr) {
+        /* note no minus sign for EINVAL and E2BIG below */
+        if (errno == EINVAL) {
+           /* handle EINVAL error */
+        } else if (errno == E2BIG) {
+           /* handle E2BIG error */
+        }
+    }
+
+libbpf.h
+--------
+.. doxygenfile:: libbpf.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+bpf.h
+-----
+.. doxygenfile:: bpf.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+btf.h
+-----
+.. doxygenfile:: btf.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+xsk.h
+-----
+.. doxygenfile:: xsk.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+bpf_tracing.h
+-------------
+.. doxygenfile:: bpf_tracing.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+bpf_core_read.h
+---------------
+.. doxygenfile:: bpf_core_read.h
+   :project: libbpf
+   :sections: func define public-type enum
+
+bpf_endian.h
+------------
+.. doxygenfile:: bpf_endian.h
+   :project: libbpf
+   :sections: func define public-type enum

docs/conf.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+import os
+import subprocess
+
+project = "libbpf"
+
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.doctest',
+    'sphinx.ext.mathjax',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.imgmath',
+    'sphinx.ext.todo',
+    'breathe',
+]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = []
+
+read_the_docs_build = os.environ.get('READTHEDOCS', None) == 'True'
+
+if read_the_docs_build:
+    subprocess.call('cd sphinx ; make clean', shell=True)
+    subprocess.call('cd sphinx/doxygen ; doxygen', shell=True)
+
+html_theme = 'sphinx_rtd_theme'
+
+breathe_projects = { "libbpf": "./sphinx/doxygen/build/xml/" }
+breathe_default_project = "libbpf"
+breathe_show_define_initializer = True
+breathe_show_enumvalue_initializer = True

docs/index.rst

@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+libbpf
+======
+
+.. toctree::
+   :maxdepth: 1
+
+   libbpf_naming_convention
+   libbpf_build
+
+This is documentation for libbpf, a userspace library for loading and
+interacting with bpf programs.
+
+For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_.
+
+All general BPF questions, including kernel functionality, libbpf APIs and
+their application, should be sent to bpf@vger.kernel.org mailing list.
+You can `subscribe <http://vger.kernel.org/vger-lists.html#bpf>`_ to the
+mailing list search its `archive <https://lore.kernel.org/bpf/>`_.
+Please search the archive before asking new questions. It very well might
+be that this was already addressed or answered before.

docs/libbpf_build.rst

@@ -0,0 +1,37 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+Building libbpf
+===============
+
+libelf and zlib are internal dependencies of libbpf and thus are required to link
+against and must be installed on the system for applications to work.
+pkg-config is used by default to find libelf, and the program called
+can be overridden with PKG_CONFIG.
+
+If using pkg-config at build time is not desired, it can be disabled by
+setting NO_PKG_CONFIG=1 when calling make.
+
+To build both static libbpf.a and shared libbpf.so:
+
+.. code-block:: bash
+
+    $ cd src
+    $ make
+
+To build only static libbpf.a library in directory build/ and install them
+together with libbpf headers in a staging directory root/:
+
+.. code-block:: bash
+
+    $ cd src
+    $ mkdir build root
+    $ BUILD_STATIC_ONLY=y OBJDIR=build DESTDIR=root make install
+
+To build both static libbpf.a and shared libbpf.so against a custom libelf
+dependency installed in /build/root/ and install them together with libbpf
+headers in a build directory /build/root/:
+
+.. code-block:: bash
+
+    $ cd src
+    $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make

docs/libbpf_naming_convention.rst

@@ -1,7 +1,7 @@
 .. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
-libbpf API naming convention
-============================
+API naming convention
+=====================
 
 libbpf API provides access to a few logically separated groups of
 functions and types. Every group has its own naming convention
@@ -9,14 +9,15 @@ described here. It's recommended to follow these conventions whenever a
 new function or type is added to keep libbpf API clean and consistent.
 
 All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
+``btf_dump_``, ``ring_buffer_``, ``perf_buffer_``.
 
 System call wrappers
 --------------------
 
 System call wrappers are simple wrappers for commands supported by
 sys_bpf system call. These wrappers should go to ``bpf.h`` header file
-and map one-on-one to corresponding commands.
+and map one to one to corresponding commands.
 
 For example ``bpf_map_lookup_elem`` wraps ``BPF_MAP_LOOKUP_ELEM``
 command of sys_bpf, ``bpf_prog_attach`` wraps ``BPF_PROG_ATTACH``, etc.
@@ -48,10 +49,6 @@ object, ``bpf_object``, double underscore and ``open`` that defines the
 purpose of the function to open ELF file and create ``bpf_object`` from
 it.
 
-Another example: ``bpf_program__load`` is named for corresponding
-object, ``bpf_program``, that is separated from other part of the name
-by double underscore.
-
 All objects and corresponding functions other than BTF related should go
 to ``libbpf.h``. BTF types and functions should go to ``btf.h``.
 
@@ -71,12 +68,8 @@ of both low-level ring access functions and high-level configuration
 functions. These can be mixed and matched. Note that these functions
 are not reentrant for performance reasons.
 
-Please take a look at Documentation/networking/af_xdp.rst in the Linux
-kernel source tree on how to use XDP sockets and for some common
-mistakes in case you do not get any traffic up to user space.
-
-libbpf ABI
-==========
+ABI
+---
 
 libbpf can be both linked statically or used as DSO. To avoid possible
 conflicts with other libraries an application is linked with, all
@@ -115,7 +108,8 @@ This bump in ABI version is at most once per kernel development cycle.
 
 For example, if current state of ``libbpf.map`` is:
 
-.. code-block::
+.. code-block:: none
+
         LIBBPF_0.0.1 {
         	global:
                         bpf_func_a;
@@ -127,7 +121,8 @@ For example, if current state of ``libbpf.map`` is:
 , and a new symbol ``bpf_func_c`` is being introduced, then
 ``libbpf.map`` should be changed like this:
 
-.. code-block::
+.. code-block:: none
+
         LIBBPF_0.0.1 {
         	global:
                         bpf_func_a;
@@ -147,7 +142,7 @@ Format of version script and ways to handle ABI changes, including
 incompatible ones, described in details in [1].
 
 Stand-alone build
-=================
+-------------------
 
 Under https://github.com/libbpf/libbpf there is a (semi-)automated
 mirror of the mainline's version of libbpf for a stand-alone build.
@@ -155,13 +150,53 @@ mirror of the mainline's version of libbpf for a stand-alone build.
 However, all changes to libbpf's code base must be upstreamed through
 the mainline kernel tree.
 
+
+API documentation convention
+============================
+
+The libbpf API is documented via comments above definitions in
+header files. These comments can be rendered by doxygen and sphinx
+for well organized html output. This section describes the
+convention in which these comments should be formated.
+
+Here is an example from btf.h:
+
+.. code-block:: c
+
+        /**
+         * @brief **btf__new()** creates a new instance of a BTF object from the raw
+         * bytes of an ELF's BTF section
+         * @param data raw bytes
+         * @param size number of bytes passed in `data`
+         * @return new BTF object instance which has to be eventually freed with
+         * **btf__free()**
+         *
+         * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+         * error code from such a pointer `libbpf_get_error()` should be used. If
+         * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+         * returned on error instead. In both cases thread-local `errno` variable is
+         * always set to error code as well.
+         */
+
+The comment must start with a block comment of the form '/\*\*'.
+
+The documentation always starts with a @brief directive. This line is a short
+description about this API. It starts with the name of the API, denoted in bold
+like so: **api_name**. Please include an open and close parenthesis if this is a
+function. Follow with the short description of the API. A longer form description
+can be added below the last directive, at the bottom of the comment.
+
+Parameters are denoted with the @param directive, there should be one for each
+parameter. If this is a function with a non-void return, use the @return directive
+to document it.
+
 License
-=======
+-------------------
 
 libbpf is dual-licensed under LGPL 2.1 and BSD 2-Clause.
 
 Links
-=====
+-------------------
 
 [1] https://www.akkadia.org/drepper/dsohowto.pdf
     (Chapter 3. Maintaining APIs and ABIs).

docs/sphinx/Makefile

@@ -0,0 +1,9 @@
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = ../src
+BUILDDIR      = build
+
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)"
+
+%:
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)"

docs/sphinx/doxygen/Doxyfile

@@ -0,0 +1,277 @@
+DOXYFILE_ENCODING      = UTF-8
+PROJECT_NAME           = "libbpf"
+PROJECT_NUMBER         =
+PROJECT_BRIEF          =
+PROJECT_LOGO           =
+OUTPUT_DIRECTORY       = ./build
+CREATE_SUBDIRS         = NO
+ALLOW_UNICODE_NAMES    = NO
+OUTPUT_LANGUAGE        = English
+OUTPUT_TEXT_DIRECTION  = None
+BRIEF_MEMBER_DESC      = YES
+REPEAT_BRIEF           = YES
+ALWAYS_DETAILED_SEC    = NO
+INLINE_INHERITED_MEMB  = NO
+FULL_PATH_NAMES        = YES
+STRIP_FROM_PATH        =
+STRIP_FROM_INC_PATH    =
+SHORT_NAMES            = NO
+JAVADOC_AUTOBRIEF      = NO
+JAVADOC_BANNER         = NO
+QT_AUTOBRIEF           = NO
+MULTILINE_CPP_IS_BRIEF = NO
+PYTHON_DOCSTRING       = NO
+INHERIT_DOCS           = YES
+SEPARATE_MEMBER_PAGES  = NO
+TAB_SIZE               = 4
+ALIASES                =
+OPTIMIZE_OUTPUT_FOR_C  = YES
+OPTIMIZE_OUTPUT_JAVA   = NO
+OPTIMIZE_FOR_FORTRAN   = NO
+OPTIMIZE_OUTPUT_VHDL   = NO
+OPTIMIZE_OUTPUT_SLICE  = NO
+EXTENSION_MAPPING      =
+MARKDOWN_SUPPORT       = YES
+TOC_INCLUDE_HEADINGS   = 5
+AUTOLINK_SUPPORT       = YES
+BUILTIN_STL_SUPPORT    = NO
+CPP_CLI_SUPPORT        = NO
+SIP_SUPPORT            = NO
+IDL_PROPERTY_SUPPORT   = YES
+DISTRIBUTE_GROUP_DOC   = NO
+GROUP_NESTED_COMPOUNDS = NO
+SUBGROUPING            = YES
+INLINE_GROUPED_CLASSES = NO
+INLINE_SIMPLE_STRUCTS  = NO
+TYPEDEF_HIDES_STRUCT   = NO
+LOOKUP_CACHE_SIZE      = 0
+NUM_PROC_THREADS       = 1
+EXTRACT_ALL            = NO
+EXTRACT_PRIVATE        = NO
+EXTRACT_PRIV_VIRTUAL   = NO
+EXTRACT_PACKAGE        = NO
+EXTRACT_STATIC         = NO
+EXTRACT_LOCAL_CLASSES  = YES
+EXTRACT_LOCAL_METHODS  = NO
+EXTRACT_ANON_NSPACES   = NO
+RESOLVE_UNNAMED_PARAMS = YES
+HIDE_UNDOC_MEMBERS     = NO
+HIDE_UNDOC_CLASSES     = NO
+HIDE_FRIEND_COMPOUNDS  = NO
+HIDE_IN_BODY_DOCS      = NO
+INTERNAL_DOCS          = NO
+CASE_SENSE_NAMES       = YES
+HIDE_SCOPE_NAMES       = NO
+HIDE_COMPOUND_REFERENCE= NO
+SHOW_INCLUDE_FILES     = YES
+SHOW_GROUPED_MEMB_INC  = NO
+FORCE_LOCAL_INCLUDES   = NO
+INLINE_INFO            = YES
+SORT_MEMBER_DOCS       = YES
+SORT_BRIEF_DOCS        = NO
+SORT_MEMBERS_CTORS_1ST = NO
+SORT_GROUP_NAMES       = NO
+SORT_BY_SCOPE_NAME     = NO
+STRICT_PROTO_MATCHING  = NO
+GENERATE_TODOLIST      = YES
+GENERATE_TESTLIST      = YES
+GENERATE_BUGLIST       = YES
+GENERATE_DEPRECATEDLIST= YES
+ENABLED_SECTIONS       =
+MAX_INITIALIZER_LINES  = 30
+SHOW_USED_FILES        = YES
+SHOW_FILES             = YES
+SHOW_NAMESPACES        = YES
+FILE_VERSION_FILTER    =
+LAYOUT_FILE            =
+CITE_BIB_FILES         =
+QUIET                  = NO
+WARNINGS               = YES
+WARN_IF_UNDOCUMENTED   = YES
+WARN_IF_DOC_ERROR      = YES
+WARN_NO_PARAMDOC       = NO
+WARN_AS_ERROR          = NO
+WARN_FORMAT            = "$file:$line: $text"
+WARN_LOGFILE           =
+INPUT                  = ../../../src
+INPUT_ENCODING         = UTF-8
+FILE_PATTERNS          = *.c \
+                         *.h
+RECURSIVE              = NO
+EXCLUDE                =
+EXCLUDE_SYMLINKS       = NO
+EXCLUDE_PATTERNS       =
+EXCLUDE_SYMBOLS        = ___*
+EXAMPLE_PATH           =
+EXAMPLE_PATTERNS       = *
+EXAMPLE_RECURSIVE      = NO
+IMAGE_PATH             =
+INPUT_FILTER           =
+FILTER_PATTERNS        =
+FILTER_SOURCE_FILES    = NO
+FILTER_SOURCE_PATTERNS =
+USE_MDFILE_AS_MAINPAGE = YES
+SOURCE_BROWSER         = NO
+INLINE_SOURCES         = NO
+STRIP_CODE_COMMENTS    = YES
+REFERENCED_BY_RELATION = NO
+REFERENCES_RELATION    = NO
+REFERENCES_LINK_SOURCE = YES
+SOURCE_TOOLTIPS        = YES
+USE_HTAGS              = NO
+VERBATIM_HEADERS       = YES
+ALPHABETICAL_INDEX     = YES
+IGNORE_PREFIX          =
+GENERATE_HTML          = NO
+HTML_OUTPUT            = html
+HTML_FILE_EXTENSION    = .html
+HTML_HEADER            =
+HTML_FOOTER            =
+HTML_STYLESHEET        =
+HTML_EXTRA_STYLESHEET  =
+HTML_EXTRA_FILES       =
+HTML_COLORSTYLE_HUE    = 220
+HTML_COLORSTYLE_SAT    = 100
+HTML_COLORSTYLE_GAMMA  = 80
+HTML_TIMESTAMP         = NO
+HTML_DYNAMIC_MENUS     = YES
+HTML_DYNAMIC_SECTIONS  = NO
+HTML_INDEX_NUM_ENTRIES = 100
+GENERATE_DOCSET        = NO
+DOCSET_FEEDNAME        = "Doxygen generated docs"
+DOCSET_BUNDLE_ID       = org.doxygen.Project
+DOCSET_PUBLISHER_ID    = org.doxygen.Publisher
+DOCSET_PUBLISHER_NAME  = Publisher
+GENERATE_HTMLHELP      = NO
+CHM_FILE               =
+HHC_LOCATION           =
+GENERATE_CHI           = NO
+CHM_INDEX_ENCODING     =
+BINARY_TOC             = NO
+TOC_EXPAND             = NO
+GENERATE_QHP           = NO
+QCH_FILE               =
+QHP_NAMESPACE          = org.doxygen.Project
+QHP_VIRTUAL_FOLDER     = doc
+QHP_CUST_FILTER_NAME   =
+QHP_CUST_FILTER_ATTRS  =
+QHP_SECT_FILTER_ATTRS  =
+QHG_LOCATION           =
+GENERATE_ECLIPSEHELP   = NO
+ECLIPSE_DOC_ID         = org.doxygen.Project
+DISABLE_INDEX          = NO
+GENERATE_TREEVIEW      = NO
+ENUM_VALUES_PER_LINE   = 4
+TREEVIEW_WIDTH         = 250
+EXT_LINKS_IN_WINDOW    = NO
+HTML_FORMULA_FORMAT    = png
+FORMULA_FONTSIZE       = 10
+FORMULA_TRANSPARENT    = YES
+FORMULA_MACROFILE      =
+USE_MATHJAX            = NO
+MATHJAX_FORMAT         = HTML-CSS
+MATHJAX_RELPATH        = https://cdn.jsdelivr.net/npm/mathjax@2
+MATHJAX_EXTENSIONS     =
+MATHJAX_CODEFILE       =
+SEARCHENGINE           = YES
+SERVER_BASED_SEARCH    = NO
+EXTERNAL_SEARCH        = NO
+SEARCHENGINE_URL       =
+SEARCHDATA_FILE        = searchdata.xml
+EXTERNAL_SEARCH_ID     =
+EXTRA_SEARCH_MAPPINGS  =
+GENERATE_LATEX         = NO
+LATEX_OUTPUT           = latex
+LATEX_CMD_NAME         =
+MAKEINDEX_CMD_NAME     = makeindex
+LATEX_MAKEINDEX_CMD    = makeindex
+COMPACT_LATEX          = NO
+PAPER_TYPE             = a4
+EXTRA_PACKAGES         =
+LATEX_HEADER           =
+LATEX_FOOTER           =
+LATEX_EXTRA_STYLESHEET =
+LATEX_EXTRA_FILES      =
+PDF_HYPERLINKS         = YES
+USE_PDFLATEX           = YES
+LATEX_BATCHMODE        = NO
+LATEX_HIDE_INDICES     = NO
+LATEX_SOURCE_CODE      = NO
+LATEX_BIB_STYLE        = plain
+LATEX_TIMESTAMP        = NO
+LATEX_EMOJI_DIRECTORY  =
+GENERATE_RTF           = NO
+RTF_OUTPUT             = rtf
+COMPACT_RTF            = NO
+RTF_HYPERLINKS         = NO
+RTF_STYLESHEET_FILE    =
+RTF_EXTENSIONS_FILE    =
+RTF_SOURCE_CODE        = NO
+GENERATE_MAN           = NO
+MAN_OUTPUT             = man
+MAN_EXTENSION          = .3
+MAN_SUBDIR             =
+MAN_LINKS              = NO
+GENERATE_XML           = YES
+XML_OUTPUT             = xml
+XML_PROGRAMLISTING     = YES
+XML_NS_MEMB_FILE_SCOPE = NO
+GENERATE_DOCBOOK       = NO
+DOCBOOK_OUTPUT         = docbook
+DOCBOOK_PROGRAMLISTING = NO
+GENERATE_AUTOGEN_DEF   = NO
+GENERATE_PERLMOD       = NO
+PERLMOD_LATEX          = NO
+PERLMOD_PRETTY         = YES
+PERLMOD_MAKEVAR_PREFIX =
+ENABLE_PREPROCESSING   = YES
+MACRO_EXPANSION        = NO
+EXPAND_ONLY_PREDEF     = YES
+SEARCH_INCLUDES        = YES
+INCLUDE_PATH           =
+INCLUDE_FILE_PATTERNS  =
+PREDEFINED             =
+EXPAND_AS_DEFINED      =
+SKIP_FUNCTION_MACROS   = NO
+TAGFILES               =
+GENERATE_TAGFILE       =
+ALLEXTERNALS           = NO
+EXTERNAL_GROUPS        = YES
+EXTERNAL_PAGES         = YES
+CLASS_DIAGRAMS         = YES
+DIA_PATH               =
+HIDE_UNDOC_RELATIONS   = YES
+HAVE_DOT               = NO
+DOT_NUM_THREADS        = 0
+DOT_FONTNAME           = Helvetica
+DOT_FONTSIZE           = 10
+DOT_FONTPATH           =
+CLASS_GRAPH            = YES
+COLLABORATION_GRAPH    = YES
+GROUP_GRAPHS           = YES
+UML_LOOK               = NO
+UML_LIMIT_NUM_FIELDS   = 10
+DOT_UML_DETAILS        = NO
+DOT_WRAP_THRESHOLD     = 17
+TEMPLATE_RELATIONS     = NO
+INCLUDE_GRAPH          = YES
+INCLUDED_BY_GRAPH      = YES
+CALL_GRAPH             = NO
+CALLER_GRAPH           = NO
+GRAPHICAL_HIERARCHY    = YES
+DIRECTORY_GRAPH        = YES
+DOT_IMAGE_FORMAT       = png
+INTERACTIVE_SVG        = NO
+DOT_PATH               =
+DOTFILE_DIRS           =
+MSCFILE_DIRS           =
+DIAFILE_DIRS           =
+PLANTUML_JAR_PATH      =
+PLANTUML_CFG_FILE      =
+PLANTUML_INCLUDE_PATH  =
+DOT_GRAPH_MAX_NODES    = 50
+MAX_DOT_GRAPH_DEPTH    = 0
+DOT_TRANSPARENT        = NO
+DOT_MULTI_TARGETS      = NO
+GENERATE_LEGEND        = YES
+DOT_CLEANUP            = YES

docs/sphinx/requirements.txt

@@ -0,0 +1 @@
+breathe

fuzz/bpf-object-fuzzer.c

@@ -0,0 +1,23 @@
+#include "libbpf.h"
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
+	struct bpf_object *obj = NULL;
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+	int err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	opts.object_name = "fuzz-object";
+	obj = bpf_object__open_mem(data, size, &opts);
+	err = libbpf_get_error(obj);
+	if (err)
+		return 0;
+
+	bpf_object__close(obj);
+	return 0;
+}

include/linux/err.h

@@ -30,4 +30,9 @@ static inline bool IS_ERR_OR_NULL(const void *ptr)
 	return (!ptr) || IS_ERR_VALUE((unsigned long)ptr);
 }
 
+static inline long PTR_ERR_OR_ZERO(const void *ptr)
+{
+	return IS_ERR(ptr) ? PTR_ERR(ptr) : 0;
+}
+
 #endif

include/linux/filter.h

@@ -5,6 +5,22 @@
 
 #include <linux/bpf.h>
 
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
+	((struct bpf_insn) {					\
+		.code = CODE,					\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off = OFF,					\
+		.imm = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
 #define BPF_ALU64_IMM(OP, DST, IMM)				\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
@@ -96,7 +112,7 @@
 			      MAP_FD, 0)
 
 #define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF)		\
-	BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0,	\
+	BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0,	\
 			      MAP_FD, VALUE_OFF)
 
 #define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
@@ -107,5 +123,12 @@
 		.off  = OFF,					\
 		.imm  = IMM })
 
+#define BPF_JMP32_IMM(OP, DST, IMM, OFF)			\
+	((struct bpf_insn) {					\
+		.code = BPF_JMP32 | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off  = OFF,					\
+		.imm  = IMM })
 
 #endif

include/linux/list.h

@@ -72,11 +72,20 @@ static inline void list_del(struct list_head *entry)
         entry->prev = LIST_POISON2;
 }
 
+static inline int list_empty(const struct list_head *head)
+{
+	return head->next == head;
+}
+
 #define list_entry(ptr, type, member) \
         container_of(ptr, type, member)
 #define list_first_entry(ptr, type, member) \
         list_entry((ptr)->next, type, member)
 #define list_next_entry(pos, member) \
         list_entry((pos)->member.next, typeof(*(pos)), member)
+#define list_for_each_entry(pos, head, member) \
+	for (pos = list_first_entry(head, typeof(*pos), member); \
+	     &pos->member != (head); \
+	     pos = list_next_entry(pos, member))
 
 #endif

include/linux/types.h

@@ -7,6 +7,8 @@
 #include <stddef.h>
 #include <stdint.h>
 
+#include <linux/stddef.h>
+
 #include <asm/types.h>
 #include <asm/posix_types.h>
 

include/tools/libc_compat.h

@@ -1,20 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause)
-/* Copyright (C) 2018 Netronome Systems, Inc. */
-
-#ifndef __TOOLS_LIBC_COMPAT_H
-#define __TOOLS_LIBC_COMPAT_H
-
-#include <stdlib.h>
-#include <linux/overflow.h>
-
-#ifdef COMPAT_NEED_REALLOCARRAY
-static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
-{
-	size_t bytes;
-
-	if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
-		return NULL;
-	return realloc(ptr, bytes);
-}
-#endif
-#endif

include/uapi/linux/btf.h

@@ -22,9 +22,9 @@ struct btf_header {
 };
 
 /* Max # of type identifier */
-#define BTF_MAX_TYPE	0x0000ffff
+#define BTF_MAX_TYPE	0x000fffff
 /* Max offset into the string section */
-#define BTF_MAX_NAME_OFFSET	0x0000ffff
+#define BTF_MAX_NAME_OFFSET	0x00ffffff
 /* Max # of struct/union/enum members or func args */
 #define BTF_MAX_VLEN	0xffff
 
@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO and VAR.
+	 * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -52,28 +52,34 @@ struct btf_type {
 	};
 };
 
-#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
+#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x1f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
 #define BTF_INFO_KFLAG(info)	((info) >> 31)
 
-#define BTF_KIND_UNKN		0	/* Unknown	*/
-#define BTF_KIND_INT		1	/* Integer	*/
-#define BTF_KIND_PTR		2	/* Pointer	*/
-#define BTF_KIND_ARRAY		3	/* Array	*/
-#define BTF_KIND_STRUCT		4	/* Struct	*/
-#define BTF_KIND_UNION		5	/* Union	*/
-#define BTF_KIND_ENUM		6	/* Enumeration	*/
-#define BTF_KIND_FWD		7	/* Forward	*/
-#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
-#define BTF_KIND_VOLATILE	9	/* Volatile	*/
-#define BTF_KIND_CONST		10	/* Const	*/
-#define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_FUNC		12	/* Function	*/
-#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_VAR		14	/* Variable	*/
-#define BTF_KIND_DATASEC	15	/* Section	*/
-#define BTF_KIND_MAX		BTF_KIND_DATASEC
-#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
+enum {
+	BTF_KIND_UNKN		= 0,	/* Unknown	*/
+	BTF_KIND_INT		= 1,	/* Integer	*/
+	BTF_KIND_PTR		= 2,	/* Pointer	*/
+	BTF_KIND_ARRAY		= 3,	/* Array	*/
+	BTF_KIND_STRUCT		= 4,	/* Struct	*/
+	BTF_KIND_UNION		= 5,	/* Union	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_FWD		= 7,	/* Forward	*/
+	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
+	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
+	BTF_KIND_CONST		= 10,	/* Const	*/
+	BTF_KIND_RESTRICT	= 11,	/* Restrict	*/
+	BTF_KIND_FUNC		= 12,	/* Function	*/
+	BTF_KIND_FUNC_PROTO	= 13,	/* Function Proto	*/
+	BTF_KIND_VAR		= 14,	/* Variable	*/
+	BTF_KIND_DATASEC	= 15,	/* Section	*/
+	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
+	BTF_KIND_TYPE_TAG	= 18,	/* Type Tag */
+
+	NR_BTF_KINDS,
+	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
+};
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -142,7 +148,14 @@ struct btf_param {
 
 enum {
 	BTF_VAR_STATIC = 0,
-	BTF_VAR_GLOBAL_ALLOCATED,
+	BTF_VAR_GLOBAL_ALLOCATED = 1,
+	BTF_VAR_GLOBAL_EXTERN = 2,
+};
+
+enum btf_func_linkage {
+	BTF_FUNC_STATIC = 0,
+	BTF_FUNC_GLOBAL = 1,
+	BTF_FUNC_EXTERN = 2,
 };
 
 /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
@@ -162,4 +175,15 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+       __s32   component_idx;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

include/uapi/linux/if_link.h

@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -167,12 +337,33 @@ enum {
 	IFLA_NEW_IFINDEX,
 	IFLA_MIN_MTU,
 	IFLA_MAX_MTU,
+	IFLA_PROP_LIST,
+	IFLA_ALT_IFNAME, /* Alternative ifname */
+	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+	IFLA_GRO_MAX_SIZE,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -227,6 +418,7 @@ enum {
 	IFLA_INET6_ICMP6STATS,	/* statistics (icmpv6)		*/
 	IFLA_INET6_TOKEN,	/* device token			*/
 	IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+	IFLA_INET6_RA_MTU,	/* mtu carried in the RA message */
 	__IFLA_INET6_MAX
 };
 
@@ -289,6 +481,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -340,6 +533,10 @@ enum {
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
 	IFLA_BRPORT_BACKUP_PORT,
+	IFLA_BRPORT_MRP_RING_OPEN,
+	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -404,6 +601,8 @@ enum {
 	IFLA_MACVLAN_MACADDR,
 	IFLA_MACVLAN_MACADDR_DATA,
 	IFLA_MACVLAN_MACADDR_COUNT,
+	IFLA_MACVLAN_BC_QUEUE_LEN,
+	IFLA_MACVLAN_BC_QUEUE_LEN_USED,
 	__IFLA_MACVLAN_MAX,
 };
 
@@ -425,6 +624,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -460,6 +660,7 @@ enum {
 	IFLA_MACSEC_REPLAY_PROTECT,
 	IFLA_MACSEC_VALIDATION,
 	IFLA_MACSEC_PAD,
+	IFLA_MACSEC_OFFLOAD,
 	__IFLA_MACSEC_MAX,
 };
 
@@ -483,6 +684,14 @@ enum macsec_validation_type {
 	MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
 };
 
+enum macsec_offload {
+	MACSEC_OFFLOAD_OFF = 0,
+	MACSEC_OFFLOAD_PHY = 1,
+	MACSEC_OFFLOAD_MAC = 2,
+	__MACSEC_OFFLOAD_END,
+	MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
+};
+
 /* IPVLAN section */
 enum {
 	IFLA_IPVLAN_UNSPEC,
@@ -580,6 +789,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
@@ -636,6 +857,9 @@ enum {
 	IFLA_BOND_AD_USER_PORT_KEY,
 	IFLA_BOND_AD_ACTOR_SYSTEM,
 	IFLA_BOND_TLB_DYNAMIC_LB,
+	IFLA_BOND_PEER_NOTIF_DELAY,
+	IFLA_BOND_AD_LACP_ACTIVE,
+	IFLA_BOND_MISSED_MAX,
 	__IFLA_BOND_MAX,
 };
 
@@ -694,6 +918,7 @@ enum {
 	IFLA_VF_IB_NODE_GUID,	/* VF Infiniband node GUID */
 	IFLA_VF_IB_PORT_GUID,	/* VF Infiniband port GUID */
 	IFLA_VF_VLAN_LIST,	/* nested list of vlans, option for QinQ */
+	IFLA_VF_BROADCAST,	/* VF broadcast */
 	__IFLA_VF_MAX,
 };
 
@@ -704,6 +929,10 @@ struct ifla_vf_mac {
 	__u8 mac[32]; /* MAX_ADDR_LEN */
 };
 
+struct ifla_vf_broadcast {
+	__u8 broadcast[32];
+};
+
 struct ifla_vf_vlan {
 	__u32 vf;
 	__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
@@ -875,7 +1104,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -885,6 +1121,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -944,11 +1183,12 @@ enum {
 #define XDP_FLAGS_SKB_MODE		(1U << 1)
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
+#define XDP_FLAGS_REPLACE		(1U << 4)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {
@@ -968,6 +1208,7 @@ enum {
 	IFLA_XDP_DRV_PROG_ID,
 	IFLA_XDP_SKB_PROG_ID,
 	IFLA_XDP_HW_PROG_ID,
+	IFLA_XDP_EXPECTED_FD,
 	__IFLA_XDP_MAX,
 };
 
@@ -1007,6 +1248,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1022,4 +1265,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

include/uapi/linux/if_xdp.h

@@ -16,6 +16,18 @@
 #define XDP_SHARED_UMEM	(1 << 0)
 #define XDP_COPY	(1 << 1) /* Force copy-mode */
 #define XDP_ZEROCOPY	(1 << 2) /* Force zero-copy mode */
+/* If this option is set, the driver might go sleep and in that case
+ * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be
+ * set. If it is set, the application need to explicitly wake up the
+ * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are
+ * running the driver and the application on the same core, you should
+ * use this option so that the kernel will yield to the user space
+ * application.
+ */
+#define XDP_USE_NEED_WAKEUP (1 << 3)
+
+/* Flags for xsk_umem_config flags */
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -25,10 +37,14 @@ struct sockaddr_xdp {
 	__u32 sxdp_shared_umem_fd;
 };
 
+/* XDP_RING flags */
+#define XDP_RING_NEED_WAKEUP (1 << 0)
+
 struct xdp_ring_offset {
 	__u64 producer;
 	__u64 consumer;
 	__u64 desc;
+	__u64 flags;
 };
 
 struct xdp_mmap_offsets {
@@ -46,26 +62,43 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_FILL_RING		5
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
+#define XDP_OPTIONS			8
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */
 	__u64 len; /* Length of packet data area */
 	__u32 chunk_size;
 	__u32 headroom;
+	__u32 flags;
 };
 
 struct xdp_statistics {
-	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_dropped; /* Dropped for other reasons */
 	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 rx_ring_full; /* Dropped due to rx ring being full */
+	__u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+	__u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
 };
 
+struct xdp_options {
+	__u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
 /* Pgoff for mmaping the rings */
 #define XDP_PGOFF_RX_RING			  0
 #define XDP_PGOFF_TX_RING		 0x80000000
 #define XDP_UMEM_PGOFF_FILL_RING	0x100000000ULL
 #define XDP_UMEM_PGOFF_COMPLETION_RING	0x180000000ULL
 
+/* Masks for unaligned chunks mode */
+#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48
+#define XSK_UNALIGNED_BUF_ADDR_MASK \
+	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;

include/uapi/linux/pkt_cls.h

@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV,
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif

meson.build

@@ -1,95 +0,0 @@
-# SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
-project('libbpf', 'c',
-        version : '0.0.3',
-        license : 'LGPL-2.1 OR BSD-2-Clause',
-        default_options : [
-                'prefix=/usr',
-        ],
-        meson_version : '>= 0.46',
-        )
-
-patchlevel = meson.project_version().split('.')[1]
-
-libbpf_source_dir = './'
-
-libbpf_sources = files(run_command('find',
-        [
-        '@0@/src'.format(libbpf_source_dir),
-        '-type',
-        'f',
-        '-name',
-        '*.[h|c]']).stdout().split())
-
-libbpf_headers = files(
-        join_paths(libbpf_source_dir, 'src/bpf.h'),
-        join_paths(libbpf_source_dir, 'src/btf.h'),
-        join_paths(libbpf_source_dir, 'src/libbpf.h'))
-
-feature_rellocarray = run_command(join_paths(libbpf_source_dir, 'scripts/check-reallocarray.sh'))
-
-libbpf_c_args = ['-g',
-                '-O2',
-                '-Werror',
-                '-Wall',
-]
-
-if feature_rellocarray.stdout().strip() != ''
-        libbpf_c_args += '-DCOMPAT_NEED_REALLOCARRAY'
-endif
-
-# bpf_includes are required to include bpf.h, btf.h, libbpf.h
-bpf_includes = include_directories(
-        join_paths(libbpf_source_dir, 'src'))
-
-libbpf_includes = include_directories(
-        join_paths(libbpf_source_dir, 'include'),
-        join_paths(libbpf_source_dir, 'include/uapi'))
-
-libelf = dependency('libelf')
-libelf = dependency('libelf', required: false)
-if not libelf.found()
-        libelf = cc.find_library('elf', required: true)
-endif
-
-deps = [libelf]
-
-libbpf_static = static_library(
-        'bpf',
-        libbpf_sources,
-        c_args : libbpf_c_args,
-        dependencies : deps,
-        include_directories : libbpf_includes,
-        install : true)
-
-libbpf_static_dep = declare_dependency(link_with : libbpf_static)
-
-libbpf_map_source_path = join_paths(libbpf_source_dir, 'src/libbpf.map')
-libbpf_map_abs_path = join_paths(meson.current_source_dir(), libbpf_map_source_path)
-
-libbpf_c_args += ['-fPIC', '-fvisibility=hidden']
-
-libbpf_link_args = ['-Wl,--version-script=@0@'.format(libbpf_map_abs_path)]
-
-libbpf_shared = shared_library(
-        'bpf',
-        libbpf_sources,
-        c_args : libbpf_c_args,
-        dependencies : deps,
-        include_directories : libbpf_includes,
-        install : true,
-        link_args : libbpf_link_args,
-        link_depends : libbpf_map_source_path,
-        soversion : patchlevel,
-        version : meson.project_version())
-
-libbpf_shared_dep = declare_dependency(link_with : libbpf_shared)
-
-install_headers(libbpf_headers, subdir : 'bpf')
-
-pkg = import('pkgconfig')
-pkg.generate(
-        name: meson.project_name(),
-        version: meson.project_version(),
-        libraries: libbpf_shared,
-        requires_private: ['libelf'],
-        description: '''BPF library''')

scripts/build-fuzzers.sh

@@ -0,0 +1,58 @@
+#!/bin/bash
+set -eux
+
+SANITIZER=${SANITIZER:-address}
+flags="-O1 -fno-omit-frame-pointer -g -DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION -fsanitize=$SANITIZER -fsanitize=fuzzer-no-link"
+
+export CC=${CC:-clang}
+export CFLAGS=${CFLAGS:-$flags}
+
+export CXX=${CXX:-clang++}
+export CXXFLAGS=${CXXFLAGS:-$flags}
+
+cd "$(dirname -- "$0")/.."
+
+export OUT=${OUT:-"$(pwd)/out"}
+mkdir -p "$OUT"
+
+export LIB_FUZZING_ENGINE=${LIB_FUZZING_ENGINE:--fsanitize=fuzzer}
+
+# Ideally libbelf should be built using release tarballs available
+# at https://sourceware.org/elfutils/ftp/. Unfortunately sometimes they
+# fail to compile (for example, elfutils-0.185 fails to compile with LDFLAGS enabled
+# due to https://bugs.gentoo.org/794601) so let's just point the script to
+# commits referring to versions of libelf that actually can be built
+rm -rf elfutils
+git clone git://sourceware.org/git/elfutils.git
+(
+cd elfutils
+git checkout 983e86fd89e8bf02f2d27ba5dce5bf078af4ceda
+git log --oneline -1
+
+# ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
+find -name Makefile.am | xargs sed -i 's/,--no-undefined//'
+
+# ASan isn't compatible with -Wl,-z,defs either:
+# https://clang.llvm.org/docs/AddressSanitizer.html#usage
+sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
+
+
+autoreconf -i -f
+if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
+	    CC="$CC" CFLAGS="-Wno-error $CFLAGS" CXX="$CXX" CXXFLAGS="-Wno-error $CXXFLAGS" LDFLAGS="$CFLAGS"; then
+    cat config.log
+    exit 1
+fi
+
+make -C config -j$(nproc) V=1
+make -C lib -j$(nproc) V=1
+make -C libelf -j$(nproc) V=1
+)
+
+make -C src BUILD_STATIC_ONLY=y V=1 clean
+make -C src -j$(nproc) CFLAGS="-I$(pwd)/elfutils/libelf $CFLAGS" BUILD_STATIC_ONLY=y V=1
+
+$CC $CFLAGS -Isrc -Iinclude -Iinclude/uapi -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64  -c fuzz/bpf-object-fuzzer.c -o bpf-object-fuzzer.o
+$CXX $CXXFLAGS $LIB_FUZZING_ENGINE bpf-object-fuzzer.o src/libbpf.a "$(pwd)/elfutils/libelf/libelf.a" -l:libz.a -o "$OUT/bpf-object-fuzzer"
+
+cp fuzz/bpf-object-fuzzer_seed_corpus.zip "$OUT"

scripts/check-reallocarray.sh

@@ -1,18 +0,0 @@
-#!/bin/sh
-
-tfile=$(mktemp /tmp/test_reallocarray_XXXXXXXX.c)
-ofile=${tfile%.c}.o
-
-cat > $tfile <<EOL
-#define _GNU_SOURCE
-#include <stdlib.h>
-
-int main(void)
-{
-	return !!reallocarray(NULL, 1, 1);
-}
-EOL
-
-gcc $tfile -o $ofile >/dev/null 2>&1
-if [ $? -ne 0 ]; then echo "FAIL"; fi
-/bin/rm -f $tfile $ofile

scripts/coverity.sh

@@ -0,0 +1,105 @@
+#!/bin/bash
+# Taken from: https://scan.coverity.com/scripts/travisci_build_coverity_scan.sh
+# Local changes are annotated with "#[local]"
+
+set -e
+
+# Environment check
+echo -e "\033[33;1mNote: COVERITY_SCAN_PROJECT_NAME and COVERITY_SCAN_TOKEN are available on Project Settings page on scan.coverity.com\033[0m"
+[ -z "$COVERITY_SCAN_PROJECT_NAME" ] && echo "ERROR: COVERITY_SCAN_PROJECT_NAME must be set" && exit 1
+[ -z "$COVERITY_SCAN_NOTIFICATION_EMAIL" ] && echo "ERROR: COVERITY_SCAN_NOTIFICATION_EMAIL must be set" && exit 1
+[ -z "$COVERITY_SCAN_BRANCH_PATTERN" ] && echo "ERROR: COVERITY_SCAN_BRANCH_PATTERN must be set" && exit 1
+[ -z "$COVERITY_SCAN_BUILD_COMMAND" ] && echo "ERROR: COVERITY_SCAN_BUILD_COMMAND must be set" && exit 1
+[ -z "$COVERITY_SCAN_TOKEN" ] && echo "ERROR: COVERITY_SCAN_TOKEN must be set" && exit 1
+
+PLATFORM=`uname`
+#[local] Use /var/tmp for TOOL_ARCHIVE and TOOL_BASE, as on certain systems
+# /tmp is tmpfs and is sometimes too small to handle all necessary tooling
+TOOL_ARCHIVE=/var//tmp/cov-analysis-${PLATFORM}.tgz
+TOOL_URL=https://scan.coverity.com/download/${PLATFORM}
+TOOL_BASE=/var/tmp/coverity-scan-analysis
+UPLOAD_URL="https://scan.coverity.com/builds"
+SCAN_URL="https://scan.coverity.com"
+
+# Do not run on pull requests
+if [ "${TRAVIS_PULL_REQUEST}" = "true" ]; then
+  echo -e "\033[33;1mINFO: Skipping Coverity Analysis: branch is a pull request.\033[0m"
+  exit 0
+fi
+
+# Verify this branch should run
+IS_COVERITY_SCAN_BRANCH=`ruby -e "puts '${TRAVIS_BRANCH}' =~ /\\A$COVERITY_SCAN_BRANCH_PATTERN\\z/ ? 1 : 0"`
+if [ "$IS_COVERITY_SCAN_BRANCH" = "1" ]; then
+  echo -e "\033[33;1mCoverity Scan configured to run on branch ${TRAVIS_BRANCH}\033[0m"
+else
+  echo -e "\033[33;1mCoverity Scan NOT configured to run on branch ${TRAVIS_BRANCH}\033[0m"
+  exit 1
+fi
+
+# Verify upload is permitted
+AUTH_RES=`curl -s --form project="$COVERITY_SCAN_PROJECT_NAME" --form token="$COVERITY_SCAN_TOKEN" $SCAN_URL/api/upload_permitted`
+if [ "$AUTH_RES" = "Access denied" ]; then
+  echo -e "\033[33;1mCoverity Scan API access denied. Check COVERITY_SCAN_PROJECT_NAME and COVERITY_SCAN_TOKEN.\033[0m"
+  exit 1
+else
+  AUTH=`echo $AUTH_RES | ruby -e "require 'rubygems'; require 'json'; puts JSON[STDIN.read]['upload_permitted']"`
+  if [ "$AUTH" = "true" ]; then
+    echo -e "\033[33;1mCoverity Scan analysis authorized per quota.\033[0m"
+  else
+    WHEN=`echo $AUTH_RES | ruby -e "require 'rubygems'; require 'json'; puts JSON[STDIN.read]['next_upload_permitted_at']"`
+    echo -e "\033[33;1mCoverity Scan analysis NOT authorized until $WHEN.\033[0m"
+    exit 0
+  fi
+fi
+
+if [ ! -d $TOOL_BASE ]; then
+  # Download Coverity Scan Analysis Tool
+  if [ ! -e $TOOL_ARCHIVE ]; then
+    echo -e "\033[33;1mDownloading Coverity Scan Analysis Tool...\033[0m"
+    wget -nv -O $TOOL_ARCHIVE $TOOL_URL --post-data "project=$COVERITY_SCAN_PROJECT_NAME&token=$COVERITY_SCAN_TOKEN"
+  fi
+
+  # Extract Coverity Scan Analysis Tool
+  echo -e "\033[33;1mExtracting Coverity Scan Analysis Tool...\033[0m"
+  mkdir -p $TOOL_BASE
+  pushd $TOOL_BASE
+  tar xzf $TOOL_ARCHIVE
+  popd
+fi
+
+TOOL_DIR=`find $TOOL_BASE -type d -name 'cov-analysis*'`
+export PATH=$TOOL_DIR/bin:$PATH
+
+# Build
+echo -e "\033[33;1mRunning Coverity Scan Analysis Tool...\033[0m"
+COV_BUILD_OPTIONS=""
+#COV_BUILD_OPTIONS="--return-emit-failures 8 --parse-error-threshold 85"
+RESULTS_DIR="cov-int"
+eval "${COVERITY_SCAN_BUILD_COMMAND_PREPEND}"
+COVERITY_UNSUPPORTED=1 cov-build --dir $RESULTS_DIR $COV_BUILD_OPTIONS $COVERITY_SCAN_BUILD_COMMAND
+cov-import-scm --dir $RESULTS_DIR --scm git --log $RESULTS_DIR/scm_log.txt 2>&1
+
+# Upload results
+echo -e "\033[33;1mTarring Coverity Scan Analysis results...\033[0m"
+RESULTS_ARCHIVE=analysis-results.tgz
+tar czf $RESULTS_ARCHIVE $RESULTS_DIR
+SHA=`git rev-parse --short HEAD`
+
+echo -e "\033[33;1mUploading Coverity Scan Analysis results...\033[0m"
+response=$(curl \
+  --silent --write-out "\n%{http_code}\n" \
+  --form project=$COVERITY_SCAN_PROJECT_NAME \
+  --form token=$COVERITY_SCAN_TOKEN \
+  --form email=$COVERITY_SCAN_NOTIFICATION_EMAIL \
+  --form file=@$RESULTS_ARCHIVE \
+  --form version=$SHA \
+  --form description="Travis CI build" \
+  $UPLOAD_URL)
+status_code=$(echo "$response" | sed -n '$p')
+#[local] Coverity used to return 201 on success, but it's 200 now
+# See https://github.com/systemd/systemd/blob/master/tools/coverity.sh#L145
+if [ "$status_code" != "200" ]; then
+  TEXT=$(echo "$response" | sed '$d')
+  echo -e "\033[33;1mCoverity Scan upload failed: $TEXT.\033[0m"
+  exit 1
+fi

scripts/sync-kernel.sh

@@ -1,40 +1,209 @@
 #!/bin/bash
 
 usage () {
-    echo "USAGE: ./sync-kernel.sh <kernel-repo> <libbpf-repo> [<baseline-commit>]"
-    echo ""
-    echo "If <baseline-commit> is not specified, it's read from <libbpf-repo>/CHECKPOINT-COMMIT"
-    exit 1
+	echo "USAGE: ./sync-kernel.sh <libbpf-repo> <kernel-repo> <bpf-branch>"
+	echo ""
+	echo "Set BPF_NEXT_BASELINE to override bpf-next tree commit, otherwise read from <libbpf-repo>/CHECKPOINT-COMMIT."
+	echo "Set BPF_BASELINE to override bpf tree commit, otherwise read from <libbpf-repo>/BPF-CHECKPOINT-COMMIT."
+	echo "Set MANUAL_MODE to 1 to manually control every cherry-picked commits."
+	exit 1
 }
 
-LINUX_REPO=${1-""}
-LIBBPF_REPO=${2-""}
-
-if [ -z "${LINUX_REPO}" ]; then
-    usage
-fi
-if [ -z "${LIBBPF_REPO}" ]; then
-    usage
-fi
-
 set -eu
 
-WORKDIR=$(pwd)
-trap "cd ${WORKDIR}; exit" INT TERM EXIT
+LIBBPF_REPO=${1-""}
+LINUX_REPO=${2-""}
+BPF_BRANCH=${3-""}
+BASELINE_COMMIT=${BPF_NEXT_BASELINE:-$(cat ${LIBBPF_REPO}/CHECKPOINT-COMMIT)}
+BPF_BASELINE_COMMIT=${BPF_BASELINE:-$(cat ${LIBBPF_REPO}/BPF-CHECKPOINT-COMMIT)}
 
-echo "WORKDIR:         ${WORKDIR}"
-echo "LINUX REPO:      ${LINUX_REPO}"
-echo "LIBBPF REPO:     ${LIBBPF_REPO}"
+if [ -z "${LIBBPF_REPO}" ] || [ -z "${LINUX_REPO}" ]; then
+	echo "Error: libbpf or linux repos are not specified"
+	usage
+fi
+if [ -z "${BPF_BRANCH}" ]; then
+	echo "Error: linux's bpf tree branch is not specified"
+	usage
+fi
+if [ -z "${BASELINE_COMMIT}" ] || [ -z "${BPF_BASELINE_COMMIT}" ]; then
+	echo "Error: bpf or bpf-next baseline commits are not provided"
+	usage
+fi
 
 SUFFIX=$(date --utc +%Y-%m-%dT%H-%M-%S.%3NZ)
-BASELINE_COMMIT=${3-$(cat ${LIBBPF_REPO}/CHECKPOINT-COMMIT)}
+WORKDIR=$(pwd)
+TMP_DIR=$(mktemp -d)
+
+trap "cd ${WORKDIR}; exit" INT TERM EXIT
+
+declare -A PATH_MAP
+PATH_MAP=(									\
+	[tools/lib/bpf]=src							\
+	[tools/include/uapi/linux/bpf_common.h]=include/uapi/linux/bpf_common.h	\
+	[tools/include/uapi/linux/bpf.h]=include/uapi/linux/bpf.h		\
+	[tools/include/uapi/linux/btf.h]=include/uapi/linux/btf.h		\
+	[tools/include/uapi/linux/if_link.h]=include/uapi/linux/if_link.h	\
+	[tools/include/uapi/linux/if_xdp.h]=include/uapi/linux/if_xdp.h		\
+	[tools/include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h	\
+	[tools/include/uapi/linux/pkt_cls.h]=include/uapi/linux/pkt_cls.h	\
+	[tools/include/uapi/linux/pkt_sched.h]=include/uapi/linux/pkt_sched.h	\
+	[include/uapi/linux/perf_event.h]=include/uapi/linux/perf_event.h	\
+	[Documentation/bpf/libbpf]=docs						\
+)
+
+LIBBPF_PATHS="${!PATH_MAP[@]} :^tools/lib/bpf/Makefile :^tools/lib/bpf/Build :^tools/lib/bpf/.gitignore :^tools/include/tools/libc_compat.h"
+LIBBPF_VIEW_PATHS="${PATH_MAP[@]}"
+LIBBPF_VIEW_EXCLUDE_REGEX='^src/(Makefile|Build|test_libbpf\.c|bpf_helper_defs\.h|\.gitignore)$|^docs/(\.gitignore|api\.rst|conf\.py)$|^docs/sphinx/.*'
+LINUX_VIEW_EXCLUDE_REGEX='^include/tools/libc_compat.h$'
+
+LIBBPF_TREE_FILTER="mkdir -p __libbpf/include/uapi/linux __libbpf/include/tools && "$'\\\n'
+for p in "${!PATH_MAP[@]}"; do
+	LIBBPF_TREE_FILTER+="git mv -kf ${p} __libbpf/${PATH_MAP[${p}]} && "$'\\\n'
+done
+LIBBPF_TREE_FILTER+="git rm --ignore-unmatch -f __libbpf/src/{Makefile,Build,test_libbpf.c,.gitignore} >/dev/null"
+
+cd_to()
+{
+	cd ${WORKDIR} && cd "$1"
+}
+
+# Output brief single-line commit description
+# $1 - commit ref
+commit_desc()
+{
+	git log -n1 --pretty='%h ("%s")' $1
+}
+
+# Create commit single-line signature, which consists of:
+# - full commit subject
+# - author date in ISO8601 format
+# - full commit body with newlines replaced with vertical bars (|)
+# - shortstat appended at the end
+# The idea is that this single-line signature is good enough to make final
+# decision about whether two commits are the same, across different repos.
+# $1 - commit ref
+# $2 - paths filter
+commit_signature()
+{
+	git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|'
+}
+
+# Cherry-pick commits touching libbpf-related files
+# $1 - baseline_tag
+# $2 - tip_tag
+cherry_pick_commits()
+{
+	local manual_mode=${MANUAL_MODE:-0}
+	local baseline_tag=$1
+	local tip_tag=$2
+	local new_commits
+	local signature
+	local should_skip
+	local synced_cnt
+	local manual_check
+	local libbpf_conflict_cnt
+	local desc
+
+	new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${LIBBPF_PATHS[@]})
+	for new_commit in ${new_commits}; do
+		desc="$(commit_desc ${new_commit})"
+		signature="$(commit_signature ${new_commit} "${LIBBPF_PATHS[@]}")"
+		synced_cnt=$(grep -F "${signature}" ${TMP_DIR}/libbpf_commits.txt | wc -l)
+		manual_check=0
+		if ((${synced_cnt} > 0)); then
+			# commit with the same subject is already in libbpf, but it's
+			# not 100% the same commit, so check with user
+			echo "Commit '${desc}' is synced into libbpf as:"
+			grep -F "${signature}" ${TMP_DIR}/libbpf_commits.txt | \
+				cut -d'|' -f1 | sed -e 's/^/- /'
+			if ((${manual_mode} != 1 && ${synced_cnt} == 1)); then
+				echo "Skipping '${desc}' due to unique match..."
+				continue
+			fi
+			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
+			case "${should_skip}" in
+				"y" | "Y")
+					echo "Skipping '${desc}'..."
+					continue
+					;;
+			esac
+		fi
+		# commit hasn't been synced into libbpf yet
+		echo "Picking '${desc}'..."
+		if ! git cherry-pick ${new_commit} &>/dev/null; then
+			echo "Warning! Cherry-picking '${desc} failed, checking if it's non-libbpf files causing problems..."
+			libbpf_conflict_cnt=$(git diff --name-only --diff-filter=U -- ${LIBBPF_PATHS[@]} | wc -l)
+			conflict_cnt=$(git diff --name-only | wc -l)
+			prompt_resolution=1
+
+			if ((${libbpf_conflict_cnt} == 0)); then
+				echo "Looks like only non-libbpf files have conflicts, ignoring..."
+				if ((${conflict_cnt} == 0)); then
+					echo "Empty cherry-pick, skipping it..."
+					git cherry-pick --abort
+					continue
+				fi
+
+				git add .
+				# GIT_EDITOR=true to avoid editor popping up to edit commit message
+				if ! GIT_EDITOR=true git cherry-pick --continue &>/dev/null; then
+					echo "Error! That still failed! Please resolve manually."
+				else
+					echo "Success! All cherry-pick conflicts were resolved for '${desc}'!"
+					prompt_resolution=0
+				fi
+			fi
+
+			if ((${prompt_resolution} == 1)); then
+				read -p "Error! Cherry-picking '${desc}' failed, please fix manually and press <return> to proceed..."
+			fi
+		fi
+		# Append signature of just cherry-picked commit to avoid
+		# potentially cherry-picking the same commit twice later when
+		# processing bpf tree commits. At this point we don't know yet
+		# the final commit sha in libbpf repo, so we record Linux SHA
+		# instead as LINUX_<sha>.
+		echo LINUX_$(git log --pretty='%h' -n1) "${signature}" >> ${TMP_DIR}/libbpf_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
+
+	cd_to .
+	echo "DONE."
+}
+
+
+cd_to ${LIBBPF_REPO}
+GITHUB_ABS_DIR=$(pwd)
+echo "Dumping existing libbpf commit signatures..."
+for h in $(git log --pretty='%h' -n500); do
+	echo $h "$(commit_signature $h)" >> ${TMP_DIR}/libbpf_commits.txt
+done
 
 # Use current kernel repo HEAD as a source of patches
-cd ${LINUX_REPO}
+cd_to ${LINUX_REPO}
+LINUX_ABS_DIR=$(pwd)
 TIP_SYM_REF=$(git symbolic-ref -q --short HEAD || git rev-parse HEAD)
 TIP_COMMIT=$(git rev-parse HEAD)
+BPF_TIP_COMMIT=$(git rev-parse ${BPF_BRANCH})
 BASELINE_TAG=libbpf-baseline-${SUFFIX}
 TIP_TAG=libbpf-tip-${SUFFIX}
+BPF_BASELINE_TAG=libbpf-bpf-baseline-${SUFFIX}
+BPF_TIP_TAG=libbpf-bpf-tip-${SUFFIX}
 VIEW_TAG=libbpf-view-${SUFFIX}
 LIBBPF_SYNC_TAG=libbpf-sync-${SUFFIX}
 
@@ -43,142 +212,139 @@ SQUASH_BASE_TAG=libbpf-squash-base-${SUFFIX}
 SQUASH_TIP_TAG=libbpf-squash-tip-${SUFFIX}
 SQUASH_COMMIT=$(git commit-tree ${BASELINE_COMMIT}^{tree} -m "BASELINE SQUASH ${BASELINE_COMMIT}")
 
-echo "SUFFIX:          ${SUFFIX}"
-echo "BASELINE COMMIT: $(git log --pretty=oneline --no-walk ${BASELINE_COMMIT})"
-echo "TIP COMMIT:      $(git log --pretty=oneline --no-walk ${TIP_COMMIT})"
-echo "SQUASH COMMIT:   ${SQUASH_COMMIT}"
-echo "BASELINE TAG:    ${BASELINE_TAG}"
-echo "TIP TAG:         ${TIP_TAG}"
-echo "SQUASH BASE TAG: ${SQUASH_BASE_TAG}"
-echo "SQUASH TIP TAG:  ${SQUASH_TIP_TAG}"
-echo "VIEW TAG:        ${VIEW_TAG}"
-echo "LIBBPF SYNC TAG: ${LIBBPF_SYNC_TAG}"
-
-TMP_DIR=$(mktemp -d)
-echo "TEMP DIR:        ${TMP_DIR}"
-echo "PATCHES+COVER:   ${TMP_DIR}/patches"
-echo "PATCHSET:        ${TMP_DIR}/patchset.patch"
+echo "WORKDIR:          ${WORKDIR}"
+echo "LINUX REPO:       ${LINUX_REPO}"
+echo "LIBBPF REPO:      ${LIBBPF_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 "SQUASH COMMIT:    ${SQUASH_COMMIT}"
+echo "BASELINE TAG:     ${BASELINE_TAG}"
+echo "TIP TAG:          ${TIP_TAG}"
+echo "BPF BASELINE TAG: ${BPF_BASELINE_TAG}"
+echo "BPF TIP TAG:      ${BPF_TIP_TAG}"
+echo "SQUASH BASE TAG:  ${SQUASH_BASE_TAG}"
+echo "SQUASH TIP TAG:   ${SQUASH_TIP_TAG}"
+echo "VIEW TAG:         ${VIEW_TAG}"
+echo "LIBBPF SYNC TAG:  ${LIBBPF_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}
 
 # Cherry-pick new commits onto squashed baseline commit
-LIBBPF_PATHS=(tools/lib/bpf tools/include/uapi/linux/{bpf_common.h,bpf.h,btf.h,if_link.h,netlink.h} tools/include/tools/libc_compat.h)
+cherry_pick_commits ${BASELINE_TAG} ${TIP_TAG}
+cherry_pick_commits ${BPF_BASELINE_TAG} ${BPF_TIP_TAG}
 
-LIBBPF_NEW_MERGES=$(git rev-list --merges --topo-order --reverse ${BASELINE_TAG}..${TIP_TAG} ${LIBBPF_PATHS[@]})
-for LIBBPF_NEW_MERGE in ${LIBBPF_NEW_MERGES}; do
-	printf "MERGE:\t" && git log --oneline -n1 ${LIBBPF_NEW_MERGE}
-	MERGE_CHANGES=$(git log --format='' -n1 ${LIBBPF_NEW_MERGE} | wc -l)
-	if ((${MERGE_CHANGES} > 0)); then
-		echo "Merge is non empty, aborting!.."
-		exit 3
-	fi
-done
-
-cd ${WORKDIR} && cd ${LIBBPF_REPO}
-git log --oneline -n500 > ${TMP_DIR}/libbpf_commits.txt
-cd ${WORKDIR} && cd ${LINUX_REPO}
-
-LIBBPF_NEW_COMMITS=$(git rev-list --no-merges --topo-order --reverse ${BASELINE_TAG}..${TIP_TAG} ${LIBBPF_PATHS[@]})
-for LIBBPF_NEW_COMMIT in ${LIBBPF_NEW_COMMITS}; do
-	echo "Checking commit '${LIBBPF_NEW_COMMIT}'"
-	SYNCED_COMMITS=$(grep -F "$(git log -n1 --pretty=format:%s ${LIBBPF_NEW_COMMIT})" ${TMP_DIR}/libbpf_commits.txt || echo "")
-	if [ -n "${SYNCED_COMMITS}" ]; then
-		# commit with the same subject is already in libbpf, but it's not 100% the same commit, so check with user
-		echo "Commit '$(git log -n1 --oneline ${LIBBPF_NEW_COMMIT})' appears to be already synced into libbpf..."
-		echo "Corresponding libbpf commit(s):"
-		echo "${SYNCED_COMMITS}"
-		read -p "Do you want to skip it? [y/N]: " SHOULD_SKIP
-		case "${SHOULD_SKIP}" in 
-			"y" | "Y")
-				echo "Skipping '$(git log -n1 --oneline ${LIBBPF_NEW_COMMIT})'..."
-				continue
-				;;
-		esac
-	fi
-	# commit hasn't been synced into libbpf yet
-	if ! git cherry-pick ${LIBBPF_NEW_COMMIT}; then 
-		read -p "Cherry-picking '$(git log --oneline -n1 ${LIBBPF_NEW_COMMIT})' failed, please fix manually and press <return> to proceed..."
-	fi
-done
-
-LIBBPF_TREE_FILTER='												\
-    mkdir -p __libbpf/include/uapi/linux __libbpf/include/tools &&						\
-    git mv -kf tools/lib/bpf __libbpf/src &&									\
-    git mv -kf tools/include/uapi/linux/{bpf_common.h,bpf.h,btf.h,if_link.h,if_xdp.h,netlink.h}			\
-	       __libbpf/include/uapi/linux &&									\
-    git mv -kf tools/include/tools/libc_compat.h __libbpf/include/tools &&					\
-    git rm --ignore-unmatch -f __libbpf/src/{Makefile,Build,test_libbpf.cpp,.gitignore}				\
-'
 # Move all libbpf files into __libbpf directory.
-git filter-branch --prune-empty -f --tree-filter "${LIBBPF_TREE_FILTER}" ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --tree-filter "${LIBBPF_TREE_FILTER}" ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
 # Make __libbpf a new root directory
-git filter-branch --prune-empty -f --subdirectory-filter __libbpf ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --subdirectory-filter __libbpf ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
 
 # If there are no new commits with  libbpf-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
 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
-# Now generate single-file patchset w/o cover to apply on top of libbpf repo
-git format-patch ${SQUASH_BASE_TAG}..${SQUASH_TIP_TAG} --stdout > ${TMP_DIR}/patchset.patch
 
-# Now is time to re-apply libbpf-related linux  patches to libbpf repo
-cd ${WORKDIR} && cd ${LIBBPF_REPO}
+# Now is time to re-apply libbpf-related linux patches to libbpf repo
+cd_to ${LIBBPF_REPO}
 git checkout -b ${LIBBPF_SYNC_TAG}
-git am --committer-date-is-author-date ${TMP_DIR}/patchset.patch
+
+for patch in $(ls -1 ${TMP_DIR}/patches | tail -n +2); do
+	if ! git am -3 --committer-date-is-author-date "${TMP_DIR}/patches/${patch}"; then
+		if ! patch -p1 --merge < "${TMP_DIR}/patches/${patch}"; then
+			read -p "Applying ${TMP_DIR}/patches/${patch} failed, please resolve manually and press <return> to proceed..."
+		fi
+		git am --continue
+	fi
+done
+
+# Generate bpf_helper_defs.h and commit, if anything changed
+# restore Linux tip to use bpf_doc.py
+cd_to ${LINUX_REPO}
+git checkout ${TIP_TAG}
+# re-generate bpf_helper_defs.h
+cd_to ${LIBBPF_REPO}
+"${LINUX_ABS_DIR}/scripts/bpf_doc.py" --header					      \
+	--file include/uapi/linux/bpf.h > src/bpf_helper_defs.h
+# if anything changed, commit it
+helpers_changes=$(git status --porcelain src/bpf_helper_defs.h | wc -l)
+if ((${helpers_changes} == 1)); then
+	git add src/bpf_helper_defs.h
+	git commit -m "sync: auto-generate latest BPF helpers
+
+Latest changes to BPF helper definitions.
+" -- src/bpf_helper_defs.h
+fi
 
 # 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 &&				      \
 git add CHECKPOINT-COMMIT &&							      \
+git add BPF-CHECKPOINT-COMMIT &&						      \
 awk '/\*\*\* BLURB HERE \*\*\*/ {p=1} p' ${TMP_DIR}/patches/0000-cover-letter.patch | \
 sed "s/\*\*\* BLURB HERE \*\*\*/\
 sync: latest libbpf changes from kernel\n\
 \n\
 Syncing latest libbpf commits from kernel repository.\n\
-Baseline commit:   ${BASELINE_COMMIT}\n\
-Checkpoint commit: ${TIP_COMMIT}/" |						      \
+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}/" |				      \
 git commit --file=-
 
 echo "SUCCESS! ${COMMIT_CNT} commits synced."
 
 echo "Verifying Linux's and Github's libbpf state"
-LIBBPF_VIEW_PATHS=(src include/uapi/linux/{bpf_common.h,bpf.h,btf.h,if_link.h,if_xdp.h,netlink.h} include/tools/libc_compat.h)
-LIBBPF_VIEW_EXCLUDE_REGEX='^src/(Makefile|Build|test_libbpf.cpp|\.gitignore)$'
 
-cd ${WORKDIR} && cd ${LINUX_REPO}
-LINUX_ABS_DIR=$(pwd)
+cd_to ${LINUX_REPO}
 git checkout -b ${VIEW_TAG} ${TIP_COMMIT}
-git filter-branch -f --tree-filter "${LIBBPF_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG}
-git filter-branch -f --subdirectory-filter __libbpf ${VIEW_TAG}^..${VIEW_TAG}
-git ls-files -- ${LIBBPF_VIEW_PATHS[@]} > ${TMP_DIR}/linux-view.ls
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${LIBBPF_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --subdirectory-filter __libbpf ${VIEW_TAG}^..${VIEW_TAG}
+git ls-files -- ${LIBBPF_VIEW_PATHS[@]} | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/linux-view.ls
 
-cd ${WORKDIR} && cd ${LIBBPF_REPO}
-GITHUB_ABS_DIR=$(pwd)
+cd_to ${LIBBPF_REPO}
 git ls-files -- ${LIBBPF_VIEW_PATHS[@]} | grep -v -E "${LIBBPF_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls
 
 echo "Comparing list of files..."
-diff ${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 ${TMP_DIR}/linux-view.ls); do
-	diff "${LINUX_ABS_DIR}/${F}" "${GITHUB_ABS_DIR}/${F}"
+	if ! diff -u "${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
-echo "Contents appear identical!"
-
-echo "Cleaning up..."
-rm -r ${TMP_DIR}
-cd ${WORKDIR} && cd ${LINUX_REPO}
-git checkout ${TIP_SYM_REF}
-git branch -D ${BASELINE_TAG} ${TIP_TAG} ${SQUASH_BASE_TAG} ${SQUASH_TIP_TAG} ${VIEW_TAG}
-
-cd ${WORKDIR}
-echo "DONE."
+if ((${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
+	case "${ignore_inconsistency}" in
+		"y" | "Y")
+			echo "Ok, proceeding..."
+			;;
+		*)
+			echo "Oops, exiting with error..."
+			exit 4
+	esac
+fi
 
+cleanup

src/.gitignore

@@ -1,2 +1,6 @@
 *.o
 *.a
+/libbpf.pc
+/libbpf.so*
+/staticobjs
+/sharedobjs

src/Makefile

@@ -1,52 +1,59 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
-VERSION = 0
-PATCHLEVEL = 0
-EXTRAVERSION = 3
+ifeq ($(V),1)
+	Q =
+	msg =
+else
+	Q = @
+	msg = @printf '  %-8s %s%s\n' "$(1)" "$(2)" "$(if $(3), $(3))";
+endif
 
-LIBBPF_VERSION	= $(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)
+LIBBPF_VERSION := $(shell \
+	grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
+	sort -rV | head -n1 | cut -d'_' -f2)
+LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
 
 TOPDIR = ..
 
 INCLUDES := -I. -I$(TOPDIR)/include -I$(TOPDIR)/include/uapi
 ALL_CFLAGS := $(INCLUDES)
 
-FEATURE_REALLOCARRAY := $(shell $(TOPDIR)/scripts/check-reallocarray.sh)
-ifneq ($(FEATURE_REALLOCARRAY),)
-	ALL_CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
-endif
+SHARED_CFLAGS += -fPIC -fvisibility=hidden -DSHARED
 
-ifndef BUILD_STATIC_ONLY
-	ALL_CFLAGS += -fPIC -fvisibility=hidden
-endif
-
-CFLAGS ?= -g -O2 -Werror -Wall
-ALL_CFLAGS += $(CFLAGS)
+CFLAGS ?= -g -O2 -Werror -Wall -std=gnu89
+ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS += $(LDFLAGS)
 ifdef NO_PKG_CONFIG
-	ALL_LDFLAGS += -lelf
+	ALL_LDFLAGS += -lelf -lz
 else
 	PKG_CONFIG ?= pkg-config
-	ALL_CFLAGS += $(shell $(PKG_CONFIG) --cflags libelf)
-	ALL_LDFLAGS += $(shell $(PKG_CONFIG) --libs libelf)
+	ALL_CFLAGS += $(shell $(PKG_CONFIG) --cflags libelf zlib)
+	ALL_LDFLAGS += $(shell $(PKG_CONFIG) --libs libelf zlib)
 endif
 
 OBJDIR ?= .
+SHARED_OBJDIR := $(OBJDIR)/sharedobjs
+STATIC_OBJDIR := $(OBJDIR)/staticobjs
+OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
+	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o \
+	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
+	relo_core.o
+SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
+STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
-OBJS := $(addprefix $(OBJDIR)/,bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
-	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o)
-
-LIBS := $(OBJDIR)/libbpf.a
+STATIC_LIBS := $(OBJDIR)/libbpf.a
 ifndef BUILD_STATIC_ONLY
-	LIBS += $(OBJDIR)/libbpf.so \
-		$(OBJDIR)/libbpf.so.$(VERSION) \
-		$(OBJDIR)/libbpf.so.$(LIBBPF_VERSION)
+	SHARED_LIBS := $(OBJDIR)/libbpf.so \
+		       $(OBJDIR)/libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+		       $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION)
 	VERSION_SCRIPT := libbpf.map
 endif
 
-HEADERS := bpf.h libbpf.h btf.h xsk.h libbpf_util.h
-UAPI_HEADERS := $(addprefix $(TOPDIR)/include/uapi/linux/,bpf.h bpf_common.h \
-	btf.h)
+HEADERS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
+	   bpf_helpers.h bpf_helper_defs.h bpf_tracing.h \
+	   bpf_endian.h bpf_core_read.h skel_internal.h libbpf_version.h
+UAPI_HEADERS := $(addprefix $(TOPDIR)/include/uapi/linux/,\
+			    bpf.h bpf_common.h btf.h)
 
 PC_FILE := $(OBJDIR)/libbpf.pc
 
@@ -54,59 +61,81 @@ INSTALL = install
 
 DESTDIR ?=
 
-ifeq ($(shell uname -m),x86_64)
+ifeq ($(filter-out %64 %64be %64eb %64le %64el s390x, $(shell uname -m)),)
 	LIBSUBDIR := lib64
 else
 	LIBSUBDIR := lib
 endif
 
+# By default let the pc file itself use ${prefix} in includedir/libdir so that
+# the prefix can be overridden at runtime (eg: --define-prefix)
+ifndef LIBDIR
+	LIBDIR_PC := $$\{prefix\}/$(LIBSUBDIR)
+else
+	LIBDIR_PC := $(LIBDIR)
+endif
 PREFIX ?= /usr
 LIBDIR ?= $(PREFIX)/$(LIBSUBDIR)
 INCLUDEDIR ?= $(PREFIX)/include
 UAPIDIR ?= $(PREFIX)/include
 
-all: $(LIBS) $(PC_FILE)
+TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags)
 
-$(OBJDIR)/libbpf.a: $(OBJS)
-	$(AR) rcs $@ $^
+all: $(STATIC_LIBS) $(SHARED_LIBS) $(PC_FILE)
 
-$(OBJDIR)/libbpf.so: $(OBJDIR)/libbpf.so.$(VERSION)
-	ln -sf $(^F) $@
+$(OBJDIR)/libbpf.a: $(STATIC_OBJS)
+	$(call msg,AR,$@)
+	$(Q)$(AR) rcs $@ $^
 
-$(OBJDIR)/libbpf.so.$(VERSION): $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION)
-	ln -sf $(^F) $@
+$(OBJDIR)/libbpf.so: $(OBJDIR)/libbpf.so.$(LIBBPF_MAJOR_VERSION)
+	$(Q)ln -sf $(^F) $@
 
-$(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(OBJS)
-	$(CC) -shared $(ALL_LDFLAGS) -Wl,--version-script=$(VERSION_SCRIPT) \
-				     -Wl,-soname,libbpf.so.$(VERSION) \
-				     $^ -o $@
+$(OBJDIR)/libbpf.so.$(LIBBPF_MAJOR_VERSION): $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION)
+	$(Q)ln -sf $(^F) $@
+
+$(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(SHARED_OBJS)
+	$(call msg,CC,$@)
+	$(Q)$(CC) -shared -Wl,--version-script=$(VERSION_SCRIPT) \
+		  -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+		  $^ $(ALL_LDFLAGS) -o $@
 
 $(OBJDIR)/libbpf.pc:
-	sed -e "s|@PREFIX@|$(PREFIX)|" \
-		-e "s|@LIBDIR@|$(LIBDIR)|" \
+	$(Q)sed -e "s|@PREFIX@|$(PREFIX)|" \
+		-e "s|@LIBDIR@|$(LIBDIR_PC)|" \
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-$(OBJDIR)/%.o: %.c
-	$(CC) $(ALL_CFLAGS) $(CPPFLAGS) -c $< -o $@
+$(STATIC_OBJDIR) $(SHARED_OBJDIR):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $@
+
+$(STATIC_OBJDIR)/%.o: %.c | $(STATIC_OBJDIR)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(ALL_CFLAGS) $(CPPFLAGS) -c $< -o $@
+
+$(SHARED_OBJDIR)/%.o: %.c | $(SHARED_OBJDIR)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(ALL_CFLAGS) $(SHARED_CFLAGS) $(CPPFLAGS) -c $< -o $@
 
 define do_install
-	if [ ! -d '$(DESTDIR)$2' ]; then		\
+	$(call msg,INSTALL,$1)
+	$(Q)if [ ! -d '$(DESTDIR)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR)$2';	\
-	fi;						\
-	$(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR)$2'
+	fi;
+	$(Q)$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR)$2'
 endef
 
 # Preserve symlinks at installation.
 define do_s_install
-	if [ ! -d '$(DESTDIR)$2' ]; then		\
+	$(call msg,INSTALL,$1)
+	$(Q)if [ ! -d '$(DESTDIR)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR)$2';	\
-	fi;						\
-	cp -fpR $1 '$(DESTDIR)$2'
+	fi;
+	$(Q)cp -fR $1 '$(DESTDIR)$2'
 endef
 
 install: all install_headers install_pkgconfig
-	$(call do_s_install,$(LIBS),$(LIBDIR))
+	$(call do_s_install,$(STATIC_LIBS) $(SHARED_LIBS),$(LIBDIR))
 
 install_headers:
 	$(call do_install,$(HEADERS),$(INCLUDEDIR)/bpf,644)
@@ -120,4 +149,16 @@ install_pkgconfig: $(PC_FILE)
 	$(call do_install,$(PC_FILE),$(LIBDIR)/pkgconfig,644)
 
 clean:
-	rm -f *.o *.a *.so *.so.* *.pc
+	$(call msg,CLEAN)
+	$(Q)rm -rf *.o *.a *.so *.so.* *.pc $(SHARED_OBJDIR) $(STATIC_OBJDIR)
+
+.PHONY: cscope tags
+cscope:
+	$(call msg,CSCOPE)
+	$(Q)ls *.c *.h > cscope.files
+	$(Q)cscope -b -q -f cscope.out
+
+tags:
+	$(call msg,CTAGS)
+	$(Q)rm -f TAGS tags
+	$(Q)ls *.c *.h | xargs $(TAGS_PROG) -a

src/bpf.h

@@ -28,13 +28,38 @@
 #include <stddef.h>
 #include <stdint.h>
 
+#include "libbpf_common.h"
+#include "libbpf_legacy.h"
+
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-#ifndef LIBBPF_API
-#define LIBBPF_API __attribute__((visibility("default")))
-#endif
+int libbpf_set_memlock_rlim(size_t memlock_bytes);
+
+struct bpf_map_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	__u32 btf_fd;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
+	__u32 btf_vmlinux_value_type_id;
+
+	__u32 inner_map_fd;
+	__u32 map_flags;
+	__u64 map_extra;
+
+	__u32 numa_node;
+	__u32 map_ifindex;
+};
+#define bpf_map_create_opts__last_field map_ifindex
+
+LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
+			      const char *map_name,
+			      __u32 key_size,
+			      __u32 value_size,
+			      __u32 max_entries,
+			      const struct bpf_map_create_opts *opts);
 
 struct bpf_create_map_attr {
 	const char *name;
@@ -48,28 +73,101 @@ struct bpf_create_map_attr {
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
 	__u32 map_ifindex;
-	__u32 inner_map_fd;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
 };
 
-LIBBPF_API int
-bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
+LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 				   int key_size, int value_size,
 				   int max_entries, __u32 map_flags, int node);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
 				   int key_size, int value_size,
 				   int max_entries, __u32 map_flags);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
 			      int value_size, int max_entries, __u32 map_flags);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
 					  const char *name, int key_size,
 					  int inner_map_fd, int max_entries,
 					  __u32 map_flags, int node);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
 				     const char *name, int key_size,
 				     int inner_map_fd, int max_entries,
 				     __u32 map_flags);
 
+struct bpf_prog_load_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	/* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns
+	 * -EAGAIN. This field determines how many attempts libbpf has to
+	 *  make. If not specified, libbpf will use default value of 5.
+	 */
+	int attempts;
+
+	enum bpf_attach_type expected_attach_type;
+	__u32 prog_btf_fd;
+	__u32 prog_flags;
+	__u32 prog_ifindex;
+	__u32 kern_version;
+
+	__u32 attach_btf_id;
+	__u32 attach_prog_fd;
+	__u32 attach_btf_obj_fd;
+
+	const int *fd_array;
+
+	/* .BTF.ext func info data */
+	const void *func_info;
+	__u32 func_info_cnt;
+	__u32 func_info_rec_size;
+
+	/* .BTF.ext line info data */
+	const void *line_info;
+	__u32 line_info_cnt;
+	__u32 line_info_rec_size;
+
+	/* verifier log options */
+	__u32 log_level;
+	__u32 log_size;
+	char *log_buf;
+};
+#define bpf_prog_load_opts__last_field log_buf
+
+LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
+			     const char *prog_name, const char *license,
+			     const struct bpf_insn *insns, size_t insn_cnt,
+			     const struct bpf_prog_load_opts *opts);
+/* this "specialization" should go away in libbpf 1.0 */
+LIBBPF_API int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
+				    const char *prog_name, const char *license,
+				    const struct bpf_insn *insns, size_t insn_cnt,
+				    const struct bpf_prog_load_opts *opts);
+
+/* This is an elaborate way to not conflict with deprecated bpf_prog_load()
+ * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone.
+ * With this approach, if someone is calling bpf_prog_load() with
+ * 4 arguments, they will use the deprecated API, which keeps backwards
+ * compatibility (both source code and binary). If bpf_prog_load() is called
+ * with 6 arguments, though, it gets redirected to __bpf_prog_load.
+ * So looking forward to libbpf 1.0 when this hack will be gone and
+ * __bpf_prog_load() will be called just bpf_prog_load().
+ */
+#ifndef bpf_prog_load
+#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__)
+#define ___bpf_prog_load4(file, type, pobj, prog_fd) \
+	bpf_prog_load_deprecated(file, type, pobj, prog_fd)
+#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \
+	bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts)
+#endif /* bpf_prog_load */
+
 struct bpf_load_program_attr {
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
@@ -77,8 +175,14 @@ struct bpf_load_program_attr {
 	const struct bpf_insn *insns;
 	size_t insns_cnt;
 	const char *license;
-	__u32 kern_version;
-	__u32 prog_ifindex;
+	union {
+		__u32 kern_version;
+		__u32 attach_prog_fd;
+	};
+	union {
+		__u32 prog_ifindex;
+		__u32 attach_btf_id;
+	};
 	__u32 prog_btf_fd;
 	__u32 func_info_rec_size;
 	const void *func_info;
@@ -87,20 +191,24 @@ struct bpf_load_program_attr {
 	const void *line_info;
 	__u32 line_info_cnt;
 	__u32 log_level;
+	__u32 prog_flags;
 };
 
 /* Flags to direct loading requirements */
 #define MAPS_RELAX_COMPAT	0x01
 
-/* Recommend log buffer size */
+/* Recommended log buffer size */
 #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
-LIBBPF_API int
-bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-		       char *log_buf, size_t log_buf_sz);
+
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
+LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+				      char *log_buf, size_t log_buf_sz);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
 LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
 				const struct bpf_insn *insns, size_t insns_cnt,
 				const char *license, __u32 kern_version,
 				char *log_buf, size_t log_buf_sz);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
 LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  const struct bpf_insn *insns,
 				  size_t insns_cnt, __u32 prog_flags,
@@ -108,6 +216,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  char *log_buf, size_t log_buf_sz,
 				  int log_level);
 
+struct bpf_btf_load_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	/* kernel log options */
+	char *log_buf;
+	__u32 log_level;
+	__u32 log_size;
+};
+#define bpf_btf_load_opts__last_field log_size
+
+LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
+			    const struct bpf_btf_load_opts *opts);
+
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead")
+LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
+			    __u32 log_buf_size, bool do_log);
+
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
@@ -116,17 +241,201 @@ LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
 					 __u64 flags);
 LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 					      void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
+						    void *value, __u64 flags);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
+
+struct bpf_map_batch_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u64 elem_flags;
+	__u64 flags;
+};
+#define bpf_map_batch_opts__last_field flags
+
+
+/**
+ * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple
+ * elements in a BPF map.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param count input and output parameter; on input **count** represents the
+ * number of  elements in the map to delete in batch;
+ * on output if a non-EFAULT error is returned, **count** represents the number of deleted
+ * elements if the output **count** value is not equal to the input **count** value
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch deletion works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys,
+				    __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements.
+ *
+ * The parameter *in_batch* is the address of the first element in the batch to read.
+ * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent
+ * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate
+ * that the batched lookup starts from the beginning of the map.
+ *
+ * The *keys* and *values* are output parameters which must point to memory large enough to
+ * hold *count* items based on the key and value size of the map *map_fd*. The *keys*
+ * buffer must be of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * indicate that the batched lookup starts from the beginning of the map.
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array large enough for *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read in batch; on output it's the number of elements that were
+ * successfully read.
+ * If a non-EFAULT error is returned, count will be set as the number of elements
+ * that were read before the error occurred.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch lookup works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
+				    void *keys, void *values, __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion
+ * of BPF map elements where each element is deleted after being retrieved.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * get address of the first element in *out_batch*
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read and delete in batch; on output it represents the number of
+ * elements that were successfully read and deleted
+ * If a non-**EFAULT** error code is returned and if the output **count** value
+ * is not equal to the input **count** value, up to **count** elements may
+ * have been deleted.
+ * if **EFAULT** is returned up to *count* elements may have been deleted without
+ * being returned via the *keys* and *values* output parameters.
+ * @param opts options for configuring the way the batch lookup and delete works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
+					void *out_batch, void *keys,
+					void *values, __u32 *count,
+					const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_update_batch()** updates multiple elements in a map
+ * by specifying keys and their corresponding values.
+ *
+ * The *keys* and *values* parameters must point to memory large enough
+ * to hold *count* items based on the key and value size of the map.
+ *
+ * The *opts* parameter can be used to control how *bpf_map_update_batch()*
+ * should handle keys that either do or do not already exist in the map.
+ * In particular the *flags* parameter of *bpf_map_batch_opts* can be
+ * one of the following:
+ *
+ * Note that *count* is an input and output parameter, where on output it
+ * represents how many elements were successfully updated. Also note that if
+ * **EFAULT** then *count* should not be trusted to be correct.
+ *
+ * **BPF_ANY**
+ *    Create new elements or update existing.
+ *
+ * **BPF_NOEXIST**
+ *    Create new elements only if they do not exist.
+ *
+ * **BPF_EXIST**
+ *    Update existing elements.
+ *
+ * **BPF_F_LOCK**
+ *    Update spin_lock-ed map elements. This must be
+ *    specified if the map value contains a spinlock.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array of *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to update in batch; on output if a non-EFAULT error is returned,
+ * **count** represents the number of updated elements if the output **count**
+ * value is not equal to the input **count** value.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch update works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values,
+				    __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
+
+struct bpf_prog_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	unsigned int flags;
+	int replace_prog_fd;
+};
+#define bpf_prog_attach_opts__last_field replace_prog_fd
+
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead")
+LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
+union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */
+struct bpf_link_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	union bpf_iter_link_info *iter_info;
+	__u32 iter_info_len;
+	__u32 target_btf_id;
+	union {
+		struct {
+			__u64 bpf_cookie;
+		} perf_event;
+	};
+	size_t :0;
+};
+#define bpf_link_create_opts__last_field perf_event
+
+LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
+			       enum bpf_attach_type attach_type,
+			       const struct bpf_link_create_opts *opts);
+
+LIBBPF_API int bpf_link_detach(int link_fd);
+
+struct bpf_link_update_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;	   /* extra flags */
+	__u32 old_prog_fd; /* expected old program FD */
+};
+#define bpf_link_update_opts__last_field old_prog_fd
+
+LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
+			       const struct bpf_link_update_opts *opts);
+
+LIBBPF_API int bpf_iter_create(int link_fd);
+
 struct bpf_prog_test_run_attr {
 	int prog_fd;
 	int repeat;
@@ -144,31 +453,71 @@ struct bpf_prog_test_run_attr {
 			     * out: length of cxt_out */
 };
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
 LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
 
 /*
  * bpf_prog_test_run does not check that data_out is large enough. Consider
- * using bpf_prog_test_run_xattr instead.
+ * using bpf_prog_test_run_opts instead.
  */
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
 LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
 				 __u32 size, void *data_out, __u32 *size_out,
 				 __u32 *retval, __u32 *duration);
 LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
-LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
-			    __u32 log_buf_size, bool do_log);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
 
+enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
+LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
+
+struct bpf_prog_bind_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+};
+#define bpf_prog_bind_opts__last_field flags
+
+LIBBPF_API int bpf_prog_bind_map(int prog_fd, int map_fd,
+				 const struct bpf_prog_bind_opts *opts);
+
+struct bpf_test_run_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const void *data_in; /* optional */
+	void *data_out;      /* optional */
+	__u32 data_size_in;
+	__u32 data_size_out; /* in: max length of data_out
+			      * out: length of data_out
+			      */
+	const void *ctx_in; /* optional */
+	void *ctx_out;      /* optional */
+	__u32 ctx_size_in;
+	__u32 ctx_size_out; /* in: max length of ctx_out
+			     * out: length of cxt_out
+			     */
+	__u32 retval;        /* out: return code of the BPF program */
+	int repeat;
+	__u32 duration;      /* out: average per repetition in ns */
+	__u32 flags;
+	__u32 cpu;
+};
+#define bpf_test_run_opts__last_field cpu
+
+LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
+				      struct bpf_test_run_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/bpf_core_read.h

@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_CORE_READ_H__
+#define __BPF_CORE_READ_H__
+
+/*
+ * enum bpf_field_info_kind is passed as a second argument into
+ * __builtin_preserve_field_info() built-in to get a specific aspect of
+ * a field, captured as a first argument. __builtin_preserve_field_info(field,
+ * info_kind) returns __u32 integer and produces BTF field relocation, which
+ * is understood and processed by libbpf during BPF object loading. See
+ * selftests/bpf for examples.
+ */
+enum bpf_field_info_kind {
+	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
+	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
+};
+
+/* second argument to __builtin_btf_type_id() built-in */
+enum bpf_type_id_kind {
+	BPF_TYPE_ID_LOCAL = 0,		/* BTF type ID in local program */
+	BPF_TYPE_ID_TARGET = 1,		/* BTF type ID in target kernel */
+};
+
+/* second argument to __builtin_preserve_type_info() built-in */
+enum bpf_type_info_kind {
+	BPF_TYPE_EXISTS = 0,		/* type existence in target kernel */
+	BPF_TYPE_SIZE = 1,		/* type size in target kernel */
+};
+
+/* second argument to __builtin_preserve_enum_value() built-in */
+enum bpf_enum_value_kind {
+	BPF_ENUMVAL_EXISTS = 0,		/* enum value existence in kernel */
+	BPF_ENUMVAL_VALUE = 1,		/* enum value value relocation */
+};
+
+#define __CORE_RELO(src, field, info)					      \
+	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read_kernel(						      \
+			(void *)dst,				      \
+			__CORE_RELO(src, fld, BYTE_SIZE),		      \
+			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#else
+/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so
+ * for big-endian we need to adjust destination pointer accordingly, based on
+ * field byte size
+ */
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read_kernel(						      \
+			(void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \
+			__CORE_RELO(src, fld, BYTE_SIZE),		      \
+			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#endif
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * All this is done in relocatable manner, so bitfield changes such as
+ * signedness, bit size, offset changes, this will be handled automatically.
+ * This version of macro is using bpf_probe_read_kernel() to read underlying
+ * integer storage. Macro functions as an expression and its return type is
+ * bpf_probe_read_kernel()'s return value: 0, on success, <0 on error.
+ */
+#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({			      \
+	unsigned long long val = 0;					      \
+									      \
+	__CORE_BITFIELD_PROBE_READ(&val, s, field);			      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * This version of macro is using direct memory reads and should be used from
+ * BPF program types that support such functionality (e.g., typed raw
+ * tracepoints).
+ */
+#define BPF_CORE_READ_BITFIELD(s, field) ({				      \
+	const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \
+	unsigned long long val;						      \
+									      \
+	/* This is a so-called barrier_var() operation that makes specified   \
+	 * variable "a black box" for optimizing compiler.		      \
+	 * It forces compiler to perform BYTE_OFFSET relocation on p and use  \
+	 * its calculated value in the switch below, instead of applying      \
+	 * the same relocation 4 times for each individual memory load.       \
+	 */								      \
+	asm volatile("" : "=r"(p) : "0"(p));				      \
+									      \
+	switch (__CORE_RELO(s, field, BYTE_SIZE)) {			      \
+	case 1: val = *(const unsigned char *)p; break;			      \
+	case 2: val = *(const unsigned short *)p; break;		      \
+	case 4: val = *(const unsigned int *)p; break;			      \
+	case 8: val = *(const unsigned long long *)p; break;		      \
+	}								      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
+/*
+ * Convenience macro to check that field actually exists in target kernel's.
+ * Returns:
+ *    1, if matching field is present in target kernel;
+ *    0, if no matching field found.
+ */
+#define bpf_core_field_exists(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
+
+/*
+ * Convenience macro to get the byte size of a field. Works for integers,
+ * struct/unions, pointers, arrays, and enums.
+ */
+#define bpf_core_field_size(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+
+/*
+ * Convenience macro to get BTF type ID of a specified type, using a local BTF
+ * information. Return 32-bit unsigned integer with type ID from program's own
+ * BTF. Always succeeds.
+ */
+#define bpf_core_type_id_local(type)					    \
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL)
+
+/*
+ * Convenience macro to get BTF type ID of a target kernel's type that matches
+ * specified local type.
+ * Returns:
+ *    - valid 32-bit unsigned type ID in kernel BTF;
+ *    - 0, if no matching type was found in a target kernel BTF.
+ */
+#define bpf_core_type_id_kernel(type)					    \
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET)
+
+/*
+ * Convenience macro to check that provided named type
+ * (struct/union/enum/typedef) exists in a target kernel.
+ * Returns:
+ *    1, if such type is present in target kernel's BTF;
+ *    0, if no matching type is found.
+ */
+#define bpf_core_type_exists(type)					    \
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS)
+
+/*
+ * Convenience macro to get the byte size of a provided named type
+ * (struct/union/enum/typedef) in a target kernel.
+ * Returns:
+ *    >= 0 size (in bytes), if type is present in target kernel's BTF;
+ *    0, if no matching type is found.
+ */
+#define bpf_core_type_size(type)					    \
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE)
+
+/*
+ * Convenience macro to check that provided enumerator value is defined in
+ * a target kernel.
+ * Returns:
+ *    1, if specified enum type and its enumerator value are present in target
+ *    kernel's BTF;
+ *    0, if no matching enum and/or enum value within that enum is found.
+ */
+#define bpf_core_enum_value_exists(enum_type, enum_value)		    \
+	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS)
+
+/*
+ * Convenience macro to get the integer value of an enumerator value in
+ * a target kernel.
+ * Returns:
+ *    64-bit value, if specified enum type and its enumerator value are
+ *    present in target kernel's BTF;
+ *    0, if no matching enum and/or enum value within that enum is found.
+ */
+#define bpf_core_enum_value(enum_type, enum_value)			    \
+	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE)
+
+/*
+ * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures
+ * offset relocation for source address using __builtin_preserve_access_index()
+ * built-in, provided by Clang.
+ *
+ * __builtin_preserve_access_index() takes as an argument an expression of
+ * taking an address of a field within struct/union. It makes compiler emit
+ * a relocation, which records BTF type ID describing root struct/union and an
+ * accessor string which describes exact embedded field that was used to take
+ * an address. See detailed description of this relocation format and
+ * semantics in comments to struct bpf_field_reloc in libbpf_internal.h.
+ *
+ * This relocation allows libbpf to adjust BPF instruction to use correct
+ * actual field offset, based on target kernel BTF type that matches original
+ * (local) BTF, used to record relocation.
+ */
+#define bpf_core_read(dst, sz, src)					    \
+	bpf_probe_read_kernel(dst, sz, (const void *)__builtin_preserve_access_index(src))
+
+/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */
+#define bpf_core_read_user(dst, sz, src)				    \
+	bpf_probe_read_user(dst, sz, (const void *)__builtin_preserve_access_index(src))
+/*
+ * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str()
+ * additionally emitting BPF CO-RE field relocation for specified source
+ * argument.
+ */
+#define bpf_core_read_str(dst, sz, src)					    \
+	bpf_probe_read_kernel_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
+
+/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */
+#define bpf_core_read_user_str(dst, sz, src)				    \
+	bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
+
+#define ___concat(a, b) a ## b
+#define ___apply(fn, n) ___concat(fn, n)
+#define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N
+
+/*
+ * return number of provided arguments; used for switch-based variadic macro
+ * definitions (see ___last, ___arrow, etc below)
+ */
+#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+/*
+ * return 0 if no arguments are passed, N - otherwise; used for
+ * recursively-defined macros to specify termination (0) case, and generic
+ * (N) case (e.g., ___read_ptrs, ___core_read)
+ */
+#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___last1(x) x
+#define ___last2(a, x) x
+#define ___last3(a, b, x) x
+#define ___last4(a, b, c, x) x
+#define ___last5(a, b, c, d, x) x
+#define ___last6(a, b, c, d, e, x) x
+#define ___last7(a, b, c, d, e, f, x) x
+#define ___last8(a, b, c, d, e, f, g, x) x
+#define ___last9(a, b, c, d, e, f, g, h, x) x
+#define ___last10(a, b, c, d, e, f, g, h, i, x) x
+#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___nolast2(a, _) a
+#define ___nolast3(a, b, _) a, b
+#define ___nolast4(a, b, c, _) a, b, c
+#define ___nolast5(a, b, c, d, _) a, b, c, d
+#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e
+#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f
+#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g
+#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h
+#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i
+#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___arrow1(a) a
+#define ___arrow2(a, b) a->b
+#define ___arrow3(a, b, c) a->b->c
+#define ___arrow4(a, b, c, d) a->b->c->d
+#define ___arrow5(a, b, c, d, e) a->b->c->d->e
+#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f
+#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g
+#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h
+#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i
+#define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j
+#define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___type(...) typeof(___arrow(__VA_ARGS__))
+
+#define ___read(read_fn, dst, src_type, src, accessor)			    \
+	read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor)
+
+/* "recursively" read a sequence of inner pointers using local __t var */
+#define ___rd_first(fn, src, a) ___read(fn, &__t, ___type(src), src, a);
+#define ___rd_last(fn, ...)						    \
+	___read(fn, &__t, ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__));
+#define ___rd_p1(fn, ...) const void *__t; ___rd_first(fn, __VA_ARGS__)
+#define ___rd_p2(fn, ...) ___rd_p1(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p3(fn, ...) ___rd_p2(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p4(fn, ...) ___rd_p3(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p5(fn, ...) ___rd_p4(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p6(fn, ...) ___rd_p5(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p7(fn, ...) ___rd_p6(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p8(fn, ...) ___rd_p7(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p9(fn, ...) ___rd_p8(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___read_ptrs(fn, src, ...)					    \
+	___apply(___rd_p, ___narg(__VA_ARGS__))(fn, src, __VA_ARGS__)
+
+#define ___core_read0(fn, fn_ptr, dst, src, a)				    \
+	___read(fn, dst, ___type(src), src, a);
+#define ___core_readN(fn, fn_ptr, dst, src, ...)			    \
+	___read_ptrs(fn_ptr, src, ___nolast(__VA_ARGS__))		    \
+	___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t,	    \
+		___last(__VA_ARGS__));
+#define ___core_read(fn, fn_ptr, dst, src, a, ...)			    \
+	___apply(___core_read, ___empty(__VA_ARGS__))(fn, fn_ptr, dst,	    \
+						      src, a, ##__VA_ARGS__)
+
+/*
+ * BPF_CORE_READ_INTO() is a more performance-conscious variant of
+ * BPF_CORE_READ(), in which final field is read into user-provided storage.
+ * See BPF_CORE_READ() below for more details on general usage.
+ */
+#define BPF_CORE_READ_INTO(dst, src, a, ...) ({				    \
+	___core_read(bpf_core_read, bpf_core_read,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Variant of BPF_CORE_READ_INTO() for reading from user-space memory.
+ *
+ * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use.
+ */
+#define BPF_CORE_READ_USER_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_core_read_user, bpf_core_read_user,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ_INTO() */
+#define BPF_PROBE_READ_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_probe_read, bpf_probe_read,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ_USER_INTO().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_probe_read_user, bpf_probe_read_user,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as
+ * BPF_CORE_READ() for intermediate pointers, but then executes (and returns
+ * corresponding error code) bpf_core_read_str() for final string read.
+ */
+#define BPF_CORE_READ_STR_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_core_read_str, bpf_core_read,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Variant of BPF_CORE_READ_STR_INTO() for reading from user-space memory.
+ *
+ * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use.
+ */
+#define BPF_CORE_READ_USER_STR_INTO(dst, src, a, ...) ({		    \
+	___core_read(bpf_core_read_user_str, bpf_core_read_user,	    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */
+#define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_probe_read_str, bpf_probe_read,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Non-CO-RE variant of BPF_CORE_READ_USER_STR_INTO().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER_STR_INTO(dst, src, a, ...) ({		    \
+	___core_read(bpf_probe_read_user_str, bpf_probe_read_user,	    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially
+ * when there are few pointer chasing steps.
+ * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like:
+ *	int x = s->a.b.c->d.e->f->g;
+ * can be succinctly achieved using BPF_CORE_READ as:
+ *	int x = BPF_CORE_READ(s, a.b.c, d.e, f, g);
+ *
+ * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF
+ * CO-RE relocatable bpf_probe_read_kernel() wrapper) calls, logically
+ * equivalent to:
+ * 1. const void *__t = s->a.b.c;
+ * 2. __t = __t->d.e;
+ * 3. __t = __t->f;
+ * 4. return __t->g;
+ *
+ * Equivalence is logical, because there is a heavy type casting/preservation
+ * involved, as well as all the reads are happening through
+ * bpf_probe_read_kernel() calls using __builtin_preserve_access_index() to
+ * emit CO-RE relocations.
+ *
+ * N.B. Only up to 9 "field accessors" are supported, which should be more
+ * than enough for any practical purpose.
+ */
+#define BPF_CORE_READ(src, a, ...) ({					    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_CORE_READ_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/*
+ * Variant of BPF_CORE_READ() for reading from user-space memory.
+ *
+ * NOTE: all the source types involved are still *kernel types* and need to
+ * exist in kernel (or kernel module) BTF, otherwise CO-RE relocation will
+ * fail. Custom user types are not relocatable with CO-RE.
+ * The typical situation in which BPF_CORE_READ_USER() might be used is to
+ * read kernel UAPI types from the user-space memory passed in as a syscall
+ * input argument.
+ */
+#define BPF_CORE_READ_USER(src, a, ...) ({				    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_CORE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ() */
+#define BPF_PROBE_READ(src, a, ...) ({					    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_PROBE_READ_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/*
+ * Non-CO-RE variant of BPF_CORE_READ_USER().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER(src, a, ...) ({				    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_PROBE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__);	    \
+	__r;								    \
+})
+
+#endif
+

src/bpf_endian.h

@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_ENDIAN__
+#define __BPF_ENDIAN__
+
+/*
+ * Isolate byte #n and put it into byte #m, for __u##b type.
+ * E.g., moving byte #6 (nnnnnnnn) into byte #1 (mmmmmmmm) for __u64:
+ * 1) xxxxxxxx nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx
+ * 2) nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx 00000000
+ * 3) 00000000 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn
+ * 4) 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn 00000000
+ */
+#define ___bpf_mvb(x, b, n, m) ((__u##b)(x) << (b-(n+1)*8) >> (b-8) << (m*8))
+
+#define ___bpf_swab16(x) ((__u16)(			\
+			  ___bpf_mvb(x, 16, 0, 1) |	\
+			  ___bpf_mvb(x, 16, 1, 0)))
+
+#define ___bpf_swab32(x) ((__u32)(			\
+			  ___bpf_mvb(x, 32, 0, 3) |	\
+			  ___bpf_mvb(x, 32, 1, 2) |	\
+			  ___bpf_mvb(x, 32, 2, 1) |	\
+			  ___bpf_mvb(x, 32, 3, 0)))
+
+#define ___bpf_swab64(x) ((__u64)(			\
+			  ___bpf_mvb(x, 64, 0, 7) |	\
+			  ___bpf_mvb(x, 64, 1, 6) |	\
+			  ___bpf_mvb(x, 64, 2, 5) |	\
+			  ___bpf_mvb(x, 64, 3, 4) |	\
+			  ___bpf_mvb(x, 64, 4, 3) |	\
+			  ___bpf_mvb(x, 64, 5, 2) |	\
+			  ___bpf_mvb(x, 64, 6, 1) |	\
+			  ___bpf_mvb(x, 64, 7, 0)))
+
+/* LLVM's BPF target selects the endianness of the CPU
+ * it compiles on, or the user specifies (bpfel/bpfeb),
+ * respectively. The used __BYTE_ORDER__ is defined by
+ * the compiler, we cannot rely on __BYTE_ORDER from
+ * libc headers, since it doesn't reflect the actual
+ * requested byte order.
+ *
+ * Note, LLVM's BPF target has different __builtin_bswapX()
+ * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE
+ * in bpfel and bpfeb case, which means below, that we map
+ * to cpu_to_be16(). We could use it unconditionally in BPF
+ * case, but better not rely on it, so that this header here
+ * can be used from application and BPF program side, which
+ * use different targets.
+ */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+# define __bpf_ntohs(x)			__builtin_bswap16(x)
+# define __bpf_htons(x)			__builtin_bswap16(x)
+# define __bpf_constant_ntohs(x)	___bpf_swab16(x)
+# define __bpf_constant_htons(x)	___bpf_swab16(x)
+# define __bpf_ntohl(x)			__builtin_bswap32(x)
+# define __bpf_htonl(x)			__builtin_bswap32(x)
+# define __bpf_constant_ntohl(x)	___bpf_swab32(x)
+# define __bpf_constant_htonl(x)	___bpf_swab32(x)
+# define __bpf_be64_to_cpu(x)		__builtin_bswap64(x)
+# define __bpf_cpu_to_be64(x)		__builtin_bswap64(x)
+# define __bpf_constant_be64_to_cpu(x)	___bpf_swab64(x)
+# define __bpf_constant_cpu_to_be64(x)	___bpf_swab64(x)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+# define __bpf_ntohs(x)			(x)
+# define __bpf_htons(x)			(x)
+# define __bpf_constant_ntohs(x)	(x)
+# define __bpf_constant_htons(x)	(x)
+# define __bpf_ntohl(x)			(x)
+# define __bpf_htonl(x)			(x)
+# define __bpf_constant_ntohl(x)	(x)
+# define __bpf_constant_htonl(x)	(x)
+# define __bpf_be64_to_cpu(x)		(x)
+# define __bpf_cpu_to_be64(x)		(x)
+# define __bpf_constant_be64_to_cpu(x)  (x)
+# define __bpf_constant_cpu_to_be64(x)  (x)
+#else
+# error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+
+#define bpf_htons(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_htons(x) : __bpf_htons(x))
+#define bpf_ntohs(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_ntohs(x) : __bpf_ntohs(x))
+#define bpf_htonl(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_htonl(x) : __bpf_htonl(x))
+#define bpf_ntohl(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_ntohl(x) : __bpf_ntohl(x))
+#define bpf_cpu_to_be64(x)			\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x))
+#define bpf_be64_to_cpu(x)			\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x))
+
+#endif /* __BPF_ENDIAN__ */

src/bpf_gen_internal.h

@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __BPF_GEN_INTERNAL_H
+#define __BPF_GEN_INTERNAL_H
+
+#include "bpf.h"
+
+struct ksym_relo_desc {
+	const char *name;
+	int kind;
+	int insn_idx;
+	bool is_weak;
+	bool is_typeless;
+};
+
+struct ksym_desc {
+	const char *name;
+	int ref;
+	int kind;
+	union {
+		/* used for kfunc */
+		int off;
+		/* used for typeless ksym */
+		bool typeless;
+	};
+	int insn;
+};
+
+struct bpf_gen {
+	struct gen_loader_opts *opts;
+	void *data_start;
+	void *data_cur;
+	void *insn_start;
+	void *insn_cur;
+	ssize_t cleanup_label;
+	__u32 nr_progs;
+	__u32 nr_maps;
+	int log_level;
+	int error;
+	struct ksym_relo_desc *relos;
+	int relo_cnt;
+	struct bpf_core_relo *core_relos;
+	int core_relo_cnt;
+	char attach_target[128];
+	int attach_kind;
+	struct ksym_desc *ksyms;
+	__u32 nr_ksyms;
+	int fd_array;
+	int nr_fd_array;
+};
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
+void bpf_gen__free(struct bpf_gen *gen);
+void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
+void bpf_gen__map_create(struct bpf_gen *gen,
+			 enum bpf_map_type map_type, const char *map_name,
+			 __u32 key_size, __u32 value_size, __u32 max_entries,
+			 struct bpf_map_create_opts *map_attr, int map_idx);
+void bpf_gen__prog_load(struct bpf_gen *gen,
+			enum bpf_prog_type prog_type, const char *prog_name,
+			const char *license, struct bpf_insn *insns, size_t insn_cnt,
+			struct bpf_prog_load_opts *load_attr, int prog_idx);
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
+void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
+void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx);
+void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo);
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx);
+
+#endif

src/bpf_helpers.h

@@ -0,0 +1,262 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_HELPERS__
+#define __BPF_HELPERS__
+
+/*
+ * Note that bpf programs need to include either
+ * vmlinux.h (auto-generated from BTF) or linux/types.h
+ * in advance since bpf_helper_defs.h uses such types
+ * as __u64.
+ */
+#include "bpf_helper_defs.h"
+
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) typeof(val) *name
+#define __array(name, val) typeof(val) *name[]
+
+/*
+ * Helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by libbpf depending on the context (BPF programs, BPF maps,
+ * extern variables, etc).
+ * To allow use of SEC() with externs (e.g., for extern .maps declarations),
+ * make sure __attribute__((unused)) doesn't trigger compilation warning.
+ */
+#define SEC(name) \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
+	__attribute__((section(name), used))				    \
+	_Pragma("GCC diagnostic pop")					    \
+
+/* Avoid 'linux/stddef.h' definition of '__always_inline'. */
+#undef __always_inline
+#define __always_inline inline __attribute__((always_inline))
+
+#ifndef __noinline
+#define __noinline __attribute__((noinline))
+#endif
+#ifndef __weak
+#define __weak __attribute__((weak))
+#endif
+
+/*
+ * Use __hidden attribute to mark a non-static BPF subprogram effectively
+ * static for BPF verifier's verification algorithm purposes, allowing more
+ * extensive and permissive BPF verification process, taking into account
+ * subprogram's caller context.
+ */
+#define __hidden __attribute__((visibility("hidden")))
+
+/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include
+ * any system-level headers (such as stddef.h, linux/version.h, etc), and
+ * commonly-used macros like NULL and KERNEL_VERSION aren't available through
+ * vmlinux.h. This just adds unnecessary hurdles and forces users to re-define
+ * them on their own. So as a convenience, provide such definitions here.
+ */
+#ifndef NULL
+#define NULL ((void *)0)
+#endif
+
+#ifndef KERNEL_VERSION
+#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c)))
+#endif
+
+/*
+ * Helper macros to manipulate data structures
+ */
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER)	((unsigned long)&((TYPE *)0)->MEMBER)
+#endif
+#ifndef container_of
+#define container_of(ptr, type, member)				\
+	({							\
+		void *__mptr = (void *)(ptr);			\
+		((type *)(__mptr - offsetof(type, member)));	\
+	})
+#endif
+
+/*
+ * Helper macro to throw a compilation error if __bpf_unreachable() gets
+ * built into the resulting code. This works given BPF back end does not
+ * implement __builtin_trap(). This is useful to assert that certain paths
+ * of the program code are never used and hence eliminated by the compiler.
+ *
+ * For example, consider a switch statement that covers known cases used by
+ * the program. __bpf_unreachable() can then reside in the default case. If
+ * the program gets extended such that a case is not covered in the switch
+ * statement, then it will throw a build error due to the default case not
+ * being compiled out.
+ */
+#ifndef __bpf_unreachable
+# define __bpf_unreachable()	__builtin_trap()
+#endif
+
+/*
+ * Helper function to perform a tail call with a constant/immediate map slot.
+ */
+#if __clang_major__ >= 8 && defined(__bpf__)
+static __always_inline void
+bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
+{
+	if (!__builtin_constant_p(slot))
+		__bpf_unreachable();
+
+	/*
+	 * Provide a hard guarantee that LLVM won't optimize setting r2 (map
+	 * pointer) and r3 (constant map index) from _different paths_ ending
+	 * up at the _same_ call insn as otherwise we won't be able to use the
+	 * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel
+	 * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key
+	 * tracking for prog array pokes") for details on verifier tracking.
+	 *
+	 * Note on clobber list: we need to stay in-line with BPF calling
+	 * convention, so even if we don't end up using r0, r4, r5, we need
+	 * to mark them as clobber so that LLVM doesn't end up using them
+	 * before / after the call.
+	 */
+	asm volatile("r1 = %[ctx]\n\t"
+		     "r2 = %[map]\n\t"
+		     "r3 = %[slot]\n\t"
+		     "call 12"
+		     :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
+		     : "r0", "r1", "r2", "r3", "r4", "r5");
+}
+#endif
+
+/*
+ * Helper structure used by eBPF C program
+ * to describe BPF map attributes to libbpf loader
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+} __attribute__((deprecated("use BTF-defined maps in .maps section")));
+
+enum libbpf_pin_type {
+	LIBBPF_PIN_NONE,
+	/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+	LIBBPF_PIN_BY_NAME,
+};
+
+enum libbpf_tristate {
+	TRI_NO = 0,
+	TRI_YES = 1,
+	TRI_MODULE = 2,
+};
+
+#define __kconfig __attribute__((section(".kconfig")))
+#define __ksym __attribute__((section(".ksyms")))
+
+#ifndef ___bpf_concat
+#define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+
+#define ___bpf_fill0(arr, p, x) do {} while (0)
+#define ___bpf_fill1(arr, p, x) arr[p] = x
+#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
+#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
+#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
+#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
+#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
+#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
+#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
+#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
+#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
+#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
+#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
+#define ___bpf_fill(arr, args...) \
+	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
+
+/*
+ * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
+ * in a structure.
+ */
+#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
+		       ___param, sizeof(___param));		\
+})
+
+/*
+ * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
+ * an array of u64.
+ */
+#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_snprintf(out, out_size, ___fmt,			\
+		     ___param, sizeof(___param));		\
+})
+
+#ifdef BPF_NO_GLOBAL_DATA
+#define BPF_PRINTK_FMT_MOD
+#else
+#define BPF_PRINTK_FMT_MOD static const
+#endif
+
+#define __bpf_printk(fmt, ...)				\
+({							\
+	BPF_PRINTK_FMT_MOD char ____fmt[] = fmt;	\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments
+ * instead of an array of u64.
+ */
+#define __bpf_vprintk(fmt, args...)				\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_trace_vprintk(___fmt, sizeof(___fmt),		\
+			  ___param, sizeof(___param));		\
+})
+
+/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
+ * Otherwise use __bpf_vprintk
+ */
+#define ___bpf_pick_printk(...) \
+	___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,	\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,		\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\
+		   __bpf_printk /*1*/, __bpf_printk /*0*/)
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args)
+
+#endif

src/bpf_prog_linfo.c

@@ -6,10 +6,7 @@
 #include <linux/err.h>
 #include <linux/bpf.h>
 #include "libbpf.h"
-
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
+#include "libbpf_internal.h"
 
 struct bpf_prog_linfo {
 	void *raw_linfo;
@@ -104,11 +101,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 {
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
+	__u64 data_sz;
 
 	nr_linfo = info->nr_line_info;
 
 	if (!nr_linfo)
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	/*
 	 * The min size that bpf_prog_linfo has to access for
@@ -116,20 +114,20 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	 */
 	if (info->line_info_rec_size <
 	    offsetof(struct bpf_line_info, file_name_off))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	prog_linfo = calloc(1, sizeof(*prog_linfo));
 	if (!prog_linfo)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
 	prog_linfo->rec_size = info->line_info_rec_size;
-	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->rec_size;
+	prog_linfo->raw_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_linfo)
 		goto err_free;
-	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
-	       nr_linfo * prog_linfo->rec_size);
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz);
 
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
@@ -145,13 +143,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy jited_line_info */
 	prog_linfo->nr_jited_func = nr_jited_func;
 	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
-	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
-					     prog_linfo->jited_rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_jited_linfo)
 		goto err_free;
 	memcpy(prog_linfo->raw_jited_linfo,
-	       (void *)(long)info->jited_line_info,
-	       nr_linfo * prog_linfo->jited_rec_size);
+	       (void *)(long)info->jited_line_info, data_sz);
 
 	/* Number of jited_line_info per jited func */
 	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
@@ -177,7 +174,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 
 err_free:
 	bpf_prog_linfo__free(prog_linfo);
-	return NULL;
+	return errno = EINVAL, NULL;
 }
 
 const struct bpf_line_info *
@@ -189,11 +186,11 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 	const __u64 *jited_linfo;
 
 	if (func_idx >= prog_linfo->nr_jited_func)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx];
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip;
 	jited_rec_size = prog_linfo->jited_rec_size;
@@ -201,7 +198,7 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 		(start * jited_rec_size);
 	jited_linfo = raw_jited_linfo;
 	if (addr < *jited_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	rec_size = prog_linfo->rec_size;
@@ -228,13 +225,13 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
 
 	nr_linfo = prog_linfo->nr_linfo;
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	rec_size = prog_linfo->rec_size;
 	raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size);
 	linfo = raw_linfo;
 	if (insn_off < linfo->insn_off)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	for (i = 0; i < nr_linfo; i++) {

src/bpf_tracing.h

@@ -0,0 +1,508 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_TRACING_H__
+#define __BPF_TRACING_H__
+
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_s390)
+	#define bpf_target_s390
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm)
+	#define bpf_target_arm
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+	#define bpf_target_sparc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_riscv)
+	#define bpf_target_riscv
+	#define bpf_target_defined
+#else
+
+/* Fall back to what the compiler says */
+#if defined(__x86_64__)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__s390__)
+	#define bpf_target_s390
+	#define bpf_target_defined
+#elif defined(__arm__)
+	#define bpf_target_arm
+	#define bpf_target_defined
+#elif defined(__aarch64__)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__mips__)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__powerpc__)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__sparc__)
+	#define bpf_target_sparc
+	#define bpf_target_defined
+#elif defined(__riscv) && __riscv_xlen == 64
+	#define bpf_target_riscv
+	#define bpf_target_defined
+#endif /* no compiler target */
+
+#endif
+
+#ifndef __BPF_TARGET_MISSING
+#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\""
+#endif
+
+#if defined(bpf_target_x86)
+
+#if defined(__KERNEL__) || defined(__VMLINUX_H__)
+
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
+
+#else
+
+#ifdef __i386__
+
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
+/* i386 kernel is built with -mregparm=3 */
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip
+
+#else /* __i386__ */
+
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
+
+#endif /* __i386__ */
+
+#endif /* __KERNEL__ || __VMLINUX_H__ */
+
+#elif defined(bpf_target_s390)
+
+struct pt_regs___s390 {
+	unsigned long orig_gpr2;
+};
+
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG gprs[2]
+#define __PT_SP_REG gprs[15]
+#define __PT_IP_REG psw.addr
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
+
+#elif defined(bpf_target_arm)
+
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]
+
+#elif defined(bpf_target_arm64)
+
+struct pt_regs___arm64 {
+	unsigned long orig_x0;
+};
+
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[0]
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
+
+#elif defined(bpf_target_mips)
+
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc
+
+#elif defined(bpf_target_powerpc)
+
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+
+#elif defined(bpf_target_sparc)
+
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
+/* Should this also be a bpf_target check for the sparc case? */
+#if defined(__arch64__)
+#define __PT_IP_REG tpc
+#else
+#define __PT_IP_REG pc
+#endif
+
+#elif defined(bpf_target_riscv)
+
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG s0
+#define __PT_RC_REG a5
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+
+#endif
+
+#if defined(bpf_target_defined)
+
+struct pt_regs;
+
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
+#endif
+
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
+#if defined(bpf_target_powerpc)
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
+#elif defined(bpf_target_sparc)
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
+#else
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
+#endif
+
+#ifndef PT_REGS_PARM1_SYSCALL
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#endif
+#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
+#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
+#ifndef PT_REGS_PARM4_SYSCALL
+#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#endif
+#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
+
+#ifndef PT_REGS_PARM1_CORE_SYSCALL
+#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#endif
+#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
+#ifndef PT_REGS_PARM4_CORE_SYSCALL
+#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#endif
+#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
+
+#else /* defined(bpf_target_defined) */
+
+#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#endif /* defined(bpf_target_defined) */
+
+/*
+ * When invoked from a syscall handler kprobe, returns a pointer to a
+ * struct pt_regs containing syscall arguments and suitable for passing to
+ * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL().
+ */
+#ifndef PT_REGS_SYSCALL_REGS
+/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx))
+#endif
+
+#ifndef ___bpf_concat
+#define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
+#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+
+#define ___bpf_ctx_cast0()            ctx
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
+#define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
+ */
+#define BPF_PROG(name, args...)						    \
+name(unsigned long long *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(unsigned long long *ctx, ##args);				    \
+typeof(name(0)) name(unsigned long long *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_ctx_cast(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(unsigned long long *ctx, ##args)
+
+struct pt_regs;
+
+#define ___bpf_kprobe_args0()           ctx
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0()       ctx
+#define ___bpf_kretprobe_args1(x)      ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
+ * return value (in addition to `struct pt_regs *ctx`), but no input
+ * arguments, because they will be clobbered by the time probed function
+ * returns.
+ */
+#define BPF_KRETPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kretprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_syscall_args0()           ctx
+#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for
+ * tracing syscall functions, like __x64_sys_close. It hides the underlying
+ * platform-specific low-level way of getting syscall input arguments from
+ * struct pt_regs, and provides a familiar typed and named function arguments
+ * syntax and semantics of accessing syscall input parameters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ *
+ * This macro relies on BPF CO-RE support.
+ */
+#define BPF_KPROBE_SYSCALL(name, args...)				    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx);		    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_syscall_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args)
+
+#endif

src/btf.h

@@ -1,21 +1,24 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
+/*! \file */
 
 #ifndef __LIBBPF_BTF_H
 #define __LIBBPF_BTF_H
 
+#include <stdarg.h>
+#include <stdbool.h>
+#include <linux/btf.h>
 #include <linux/types.h>
 
+#include "libbpf_common.h"
+
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-#ifndef LIBBPF_API
-#define LIBBPF_API __attribute__((visibility("default")))
-#endif
-
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
 
 struct btf;
 struct btf_ext;
@@ -23,82 +26,577 @@ struct btf_type;
 
 struct bpf_object;
 
-/*
- * The .BTF.ext ELF section layout defined as
- *   struct btf_ext_header
- *   func_info subsection
- *
- * The func_info subsection layout:
- *   record size for struct bpf_func_info in the func_info subsection
- *   struct btf_sec_func_info for section #1
- *   a list of bpf_func_info records for section #1
- *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
- *     but may not be identical
- *   struct btf_sec_func_info for section #2
- *   a list of bpf_func_info records for section #2
- *   ......
- *
- * Note that the bpf_func_info record size in .BTF.ext may not
- * be the same as the one defined in include/uapi/linux/bpf.h.
- * The loader should ensure that record_size meets minimum
- * requirement and pass the record as is to the kernel. The
- * kernel will handle the func_info properly based on its contents.
- */
-struct btf_ext_header {
-	__u16	magic;
-	__u8	version;
-	__u8	flags;
-	__u32	hdr_len;
-
-	/* All offsets are in bytes relative to the end of this header */
-	__u32	func_info_off;
-	__u32	func_info_len;
-	__u32	line_info_off;
-	__u32	line_info_len;
+enum btf_endianness {
+	BTF_LITTLE_ENDIAN = 0,
+	BTF_BIG_ENDIAN = 1,
 };
 
+/**
+ * @brief **btf__free()** frees all data of a BTF object
+ * @param btf BTF object to free
+ */
 LIBBPF_API void btf__free(struct btf *btf);
-LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+
+/**
+ * @brief **btf__new()** creates a new instance of a BTF object from the raw
+ * bytes of an ELF's BTF section
+ * @param data raw bytes
+ * @param size number of bytes passed in `data`
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
+LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+
+/**
+ * @brief **btf__new_split()** create a new instance of a BTF object from the
+ * provided raw data bytes. It takes another BTF instance, **base_btf**, which
+ * serves as a base BTF, which is extended by types in a newly created BTF
+ * instance
+ * @param data raw bytes
+ * @param size length of raw bytes
+ * @param base_btf the base BTF object
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and
+ * creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
+LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
+
+/**
+ * @brief **btf__new_empty()** creates an empty BTF object.  Use
+ * `btf__add_*()` to populate such BTF object.
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
+LIBBPF_API struct btf *btf__new_empty(void);
+
+/**
+ * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an
+ * ELF BTF section except with a base BTF on top of which split BTF should be
+ * based
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to
+ * `btf__new_empty()` and creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
+LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
+
+LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
+LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf);
+LIBBPF_API struct btf *btf__parse_raw(const char *path);
+LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf);
+
+LIBBPF_API struct btf *btf__load_vmlinux_btf(void);
+LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf);
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
+LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
+LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
+LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
+
+LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only")
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
 LIBBPF_API int btf__load(struct btf *btf);
+LIBBPF_API int btf__load_into_kernel(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
+LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
+					const char *type_name, __u32 kind);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1")
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API __u32 btf__type_cnt(const struct btf *btf);
+LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
+LIBBPF_API size_t btf__pointer_size(const struct btf *btf);
+LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz);
+LIBBPF_API enum btf_endianness btf__endianness(const struct btf *btf);
+LIBBPF_API int btf__set_endianness(struct btf *btf, enum btf_endianness endian);
 LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
 LIBBPF_API int btf__fd(const struct btf *btf);
-LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
+LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
-LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
+LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used")
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 				    __u32 expected_key_size,
 				    __u32 expected_value_size,
 				    __u32 *key_type_id, __u32 *value_type_id);
 
-LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size);
+LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size);
 LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
-LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext,
-					     __u32 *size);
-LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf,
-					const struct btf_ext *btf_ext,
-					const char *sec_name, __u32 insns_cnt,
-					void **func_info, __u32 *cnt);
-LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
-					const struct btf_ext *btf_ext,
-					const char *sec_name, __u32 insns_cnt,
-					void **line_info, __u32 *cnt);
-LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
-LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
+int btf_ext__reloc_func_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **func_info, __u32 *cnt);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
+int btf_ext__reloc_line_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **line_info, __u32 *cnt);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size")
+__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size")
+__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
-struct btf_dedup_opts {
-	unsigned int dedup_table_size;
-	bool dont_resolve_fwds;
+LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
+LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
+LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf,
+			     const struct btf_type *src_type);
+/**
+ * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf*
+ * @param btf BTF object which all the BTF types and strings are added to
+ * @param src_btf BTF object which all BTF types and referenced strings are copied from
+ * @return BTF type ID of the first appended BTF type, or negative error code
+ *
+ * **btf__add_btf()** can be used to simply and efficiently append the entire
+ * contents of one BTF object to another one. All the BTF type data is copied
+ * over, all referenced type IDs are adjusted by adding a necessary ID offset.
+ * Only strings referenced from BTF types are copied over and deduplicated, so
+ * if there were some unused strings in *src_btf*, those won't be copied over,
+ * which is consistent with the general string deduplication semantics of BTF
+ * writing APIs.
+ *
+ * If any error is encountered during this process, the contents of *btf* is
+ * left intact, which means that **btf__add_btf()** follows the transactional
+ * semantics and the operation as a whole is all-or-nothing.
+ *
+ * *src_btf* has to be non-split BTF, as of now copying types from split BTF
+ * is not supported and will result in -ENOTSUP error code returned.
+ */
+LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf);
+
+LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
+LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
+LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_array(struct btf *btf,
+			      int index_type_id, int elem_type_id, __u32 nr_elems);
+/* struct/union construction APIs */
+LIBBPF_API int btf__add_struct(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_union(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_id,
+			      __u32 bit_offset, __u32 bit_size);
+
+/* enum construction APIs */
+LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz);
+LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value);
+
+enum btf_fwd_kind {
+	BTF_FWD_STRUCT = 0,
+	BTF_FWD_UNION = 1,
+	BTF_FWD_ENUM = 2,
 };
 
-LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
-			  const struct btf_dedup_opts *opts);
+LIBBPF_API int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind);
+LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id);
+LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id);
+
+/* func and func_proto construction APIs */
+LIBBPF_API int btf__add_func(struct btf *btf, const char *name,
+			     enum btf_func_linkage linkage, int proto_type_id);
+LIBBPF_API int btf__add_func_proto(struct btf *btf, int ret_type_id);
+LIBBPF_API int btf__add_func_param(struct btf *btf, const char *name, int type_id);
+
+/* var & datasec construction APIs */
+LIBBPF_API int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id);
+LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz);
+LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
+					 __u32 offset, __u32 byte_sz);
+
+/* tag construction API */
+LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+			    int component_idx);
+
+struct btf_dedup_opts {
+	size_t sz;
+	/* optional .BTF.ext info to dedup along the main BTF info */
+	struct btf_ext *btf_ext;
+	/* force hash collisions (used for testing) */
+	bool force_collisions;
+	size_t :0;
+};
+#define btf_dedup_opts__last_field force_collisions
+
+LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
+
+LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts);
+
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead")
+LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts);
+#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__)
+#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts)
+#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts)
+
+struct btf_dump;
+
+struct btf_dump_opts {
+	union {
+		size_t sz;
+		void *ctx; /* DEPRECATED: will be gone in v1.0 */
+	};
+};
+
+typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
+
+LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
+					  btf_dump_printf_fn_t printf_fn,
+					  void *ctx,
+					  const struct btf_dump_opts *opts);
+
+LIBBPF_API struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
+						 btf_dump_printf_fn_t printf_fn,
+						 void *ctx,
+						 const struct btf_dump_opts *opts);
+
+LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
+						     const struct btf_ext *btf_ext,
+						     const struct btf_dump_opts *opts,
+						     btf_dump_printf_fn_t printf_fn);
+
+/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the
+ * type of 4th argument. If it's btf_dump's print callback, use deprecated
+ * API; otherwise, choose the new btf_dump__new(). ___libbpf_override()
+ * doesn't work here because both variants have 4 input arguments.
+ *
+ * (void *) casts are necessary to avoid compilation warnings about type
+ * mismatches, because even though __builtin_choose_expr() only ever evaluates
+ * one side the other side still has to satisfy type constraints (this is
+ * compiler implementation limitation which might be lifted eventually,
+ * according to the documentation). So passing struct btf_ext in place of
+ * btf_dump_printf_fn_t would be generating compilation warning.  Casting to
+ * void * avoids this issue.
+ *
+ * Also, two type compatibility checks for a function and function pointer are
+ * required because passing function reference into btf_dump__new() as
+ * btf_dump__new(..., my_callback, ...) and as btf_dump__new(...,
+ * &my_callback, ...) (not explicit ampersand in the latter case) actually
+ * differs as far as __builtin_types_compatible_p() is concerned. Thus two
+ * checks are combined to detect callback argument.
+ *
+ * The rest works just like in case of ___libbpf_override() usage with symbol
+ * versioning.
+ *
+ * C++ compilers don't support __builtin_types_compatible_p(), so at least
+ * don't screw up compilation for them and let C++ users pick btf_dump__new
+ * vs btf_dump__new_deprecated explicitly.
+ */
+#ifndef __cplusplus
+#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr(				\
+	__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) ||		\
+	__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)),	\
+	btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4),	\
+	btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
+#endif
+
+LIBBPF_API void btf_dump__free(struct btf_dump *d);
+
+LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
+
+struct btf_dump_emit_type_decl_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* optional field name for type declaration, e.g.:
+	 * - struct my_struct <FNAME>
+	 * - void (*<FNAME>)(int)
+	 * - char (*<FNAME>)[123]
+	 */
+	const char *field_name;
+	/* extra indentation level (in number of tabs) to emit for multi-line
+	 * type declarations (e.g., anonymous struct); applies for lines
+	 * starting from the second one (first line is assumed to have
+	 * necessary indentation already
+	 */
+	int indent_level;
+	/* strip all the const/volatile/restrict mods */
+	bool strip_mods;
+	size_t :0;
+};
+#define btf_dump_emit_type_decl_opts__last_field strip_mods
+
+LIBBPF_API int
+btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
+			 const struct btf_dump_emit_type_decl_opts *opts);
+
+
+struct btf_dump_type_data_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+	const char *indent_str;
+	int indent_level;
+	/* below match "show" flags for bpf_show_snprintf() */
+	bool compact;		/* no newlines/indentation */
+	bool skip_names;	/* skip member/type names */
+	bool emit_zeroes;	/* show 0-valued fields */
+	size_t :0;
+};
+#define btf_dump_type_data_opts__last_field emit_zeroes
+
+LIBBPF_API int
+btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
+			 const void *data, size_t data_sz,
+			 const struct btf_dump_type_data_opts *opts);
+
+/*
+ * A set of helpers for easier BTF types handling.
+ *
+ * The inline functions below rely on constants from the kernel headers which
+ * may not be available for applications including this header file. To avoid
+ * compilation errors, we define all the constants here that were added after
+ * the initial introduction of the BTF_KIND* constants.
+ */
+#ifndef BTF_KIND_FUNC
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#endif
+#ifndef BTF_KIND_VAR
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#endif
+#ifndef BTF_KIND_FLOAT
+#define BTF_KIND_FLOAT		16	/* Floating point	*/
+#endif
+/* The kernel header switched to enums, so these two were never #defined */
+#define BTF_KIND_DECL_TAG	17	/* Decl Tag */
+#define BTF_KIND_TYPE_TAG	18	/* Type Tag */
+
+static inline __u16 btf_kind(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info);
+}
+
+static inline __u16 btf_vlen(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static inline bool btf_is_void(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_UNKN;
+}
+
+static inline bool btf_is_int(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_INT;
+}
+
+static inline bool btf_is_ptr(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_PTR;
+}
+
+static inline bool btf_is_array(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_is_struct(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_STRUCT;
+}
+
+static inline bool btf_is_union(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_composite(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_enum(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_is_fwd(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FWD;
+}
+
+static inline bool btf_is_typedef(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TYPEDEF;
+}
+
+static inline bool btf_is_volatile(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VOLATILE;
+}
+
+static inline bool btf_is_const(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_CONST;
+}
+
+static inline bool btf_is_restrict(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_mod(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_VOLATILE ||
+	       kind == BTF_KIND_CONST ||
+	       kind == BTF_KIND_RESTRICT ||
+	       kind == BTF_KIND_TYPE_TAG;
+}
+
+static inline bool btf_is_func(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC;
+}
+
+static inline bool btf_is_func_proto(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC_PROTO;
+}
+
+static inline bool btf_is_var(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VAR;
+}
+
+static inline bool btf_is_datasec(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DATASEC;
+}
+
+static inline bool btf_is_float(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FLOAT;
+}
+
+static inline bool btf_is_decl_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DECL_TAG;
+}
+
+static inline bool btf_is_type_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TYPE_TAG;
+}
+
+static inline __u8 btf_int_encoding(const struct btf_type *t)
+{
+	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_offset(const struct btf_type *t)
+{
+	return BTF_INT_OFFSET(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
+static inline struct btf_array *btf_array(const struct btf_type *t)
+{
+	return (struct btf_array *)(t + 1);
+}
+
+static inline struct btf_enum *btf_enum(const struct btf_type *t)
+{
+	return (struct btf_enum *)(t + 1);
+}
+
+static inline struct btf_member *btf_members(const struct btf_type *t)
+{
+	return (struct btf_member *)(t + 1);
+}
+
+/* Get bit offset of a member with specified index. */
+static inline __u32 btf_member_bit_offset(const struct btf_type *t,
+					  __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+}
+/*
+ * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or
+ * BTF_KIND_UNION. If member is not a bitfield, zero is returned.
+ */
+static inline __u32 btf_member_bitfield_size(const struct btf_type *t,
+					     __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+}
+
+static inline struct btf_param *btf_params(const struct btf_type *t)
+{
+	return (struct btf_param *)(t + 1);
+}
+
+static inline struct btf_var *btf_var(const struct btf_type *t)
+{
+	return (struct btf_var *)(t + 1);
+}
+
+static inline struct btf_var_secinfo *
+btf_var_secinfos(const struct btf_type *t)
+{
+	return (struct btf_var_secinfo *)(t + 1);
+}
+
+struct btf_decl_tag;
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
 
 #ifdef __cplusplus
 } /* extern "C" */

src/hashmap.c

@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
+/* start with 4 buckets */
+#define HASHMAP_MIN_CAP_BITS 2
+
+static void hashmap_add_entry(struct hashmap_entry **pprev,
+			      struct hashmap_entry *entry)
+{
+	entry->next = *pprev;
+	*pprev = entry;
+}
+
+static void hashmap_del_entry(struct hashmap_entry **pprev,
+			      struct hashmap_entry *entry)
+{
+	*pprev = entry->next;
+	entry->next = NULL;
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+		   hashmap_equal_fn equal_fn, void *ctx)
+{
+	map->hash_fn = hash_fn;
+	map->equal_fn = equal_fn;
+	map->ctx = ctx;
+
+	map->buckets = NULL;
+	map->cap = 0;
+	map->cap_bits = 0;
+	map->sz = 0;
+}
+
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+			     hashmap_equal_fn equal_fn,
+			     void *ctx)
+{
+	struct hashmap *map = malloc(sizeof(struct hashmap));
+
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+	hashmap__init(map, hash_fn, equal_fn, ctx);
+	return map;
+}
+
+void hashmap__clear(struct hashmap *map)
+{
+	struct hashmap_entry *cur, *tmp;
+	size_t bkt;
+
+	hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+		free(cur);
+	}
+	free(map->buckets);
+	map->buckets = NULL;
+	map->cap = map->cap_bits = map->sz = 0;
+}
+
+void hashmap__free(struct hashmap *map)
+{
+	if (IS_ERR_OR_NULL(map))
+		return;
+
+	hashmap__clear(map);
+	free(map);
+}
+
+size_t hashmap__size(const struct hashmap *map)
+{
+	return map->sz;
+}
+
+size_t hashmap__capacity(const struct hashmap *map)
+{
+	return map->cap;
+}
+
+static bool hashmap_needs_to_grow(struct hashmap *map)
+{
+	/* grow if empty or more than 75% filled */
+	return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap);
+}
+
+static int hashmap_grow(struct hashmap *map)
+{
+	struct hashmap_entry **new_buckets;
+	struct hashmap_entry *cur, *tmp;
+	size_t new_cap_bits, new_cap;
+	size_t h, bkt;
+
+	new_cap_bits = map->cap_bits + 1;
+	if (new_cap_bits < HASHMAP_MIN_CAP_BITS)
+		new_cap_bits = HASHMAP_MIN_CAP_BITS;
+
+	new_cap = 1UL << new_cap_bits;
+	new_buckets = calloc(new_cap, sizeof(new_buckets[0]));
+	if (!new_buckets)
+		return -ENOMEM;
+
+	hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+		h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits);
+		hashmap_add_entry(&new_buckets[h], cur);
+	}
+
+	map->cap = new_cap;
+	map->cap_bits = new_cap_bits;
+	free(map->buckets);
+	map->buckets = new_buckets;
+
+	return 0;
+}
+
+static bool hashmap_find_entry(const struct hashmap *map,
+			       const void *key, size_t hash,
+			       struct hashmap_entry ***pprev,
+			       struct hashmap_entry **entry)
+{
+	struct hashmap_entry *cur, **prev_ptr;
+
+	if (!map->buckets)
+		return false;
+
+	for (prev_ptr = &map->buckets[hash], cur = *prev_ptr;
+	     cur;
+	     prev_ptr = &cur->next, cur = cur->next) {
+		if (map->equal_fn(cur->key, key, map->ctx)) {
+			if (pprev)
+				*pprev = prev_ptr;
+			*entry = cur;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+		    enum hashmap_insert_strategy strategy,
+		    const void **old_key, void **old_value)
+{
+	struct hashmap_entry *entry;
+	size_t h;
+	int err;
+
+	if (old_key)
+		*old_key = NULL;
+	if (old_value)
+		*old_value = NULL;
+
+	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+	if (strategy != HASHMAP_APPEND &&
+	    hashmap_find_entry(map, key, h, NULL, &entry)) {
+		if (old_key)
+			*old_key = entry->key;
+		if (old_value)
+			*old_value = entry->value;
+
+		if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) {
+			entry->key = key;
+			entry->value = value;
+			return 0;
+		} else if (strategy == HASHMAP_ADD) {
+			return -EEXIST;
+		}
+	}
+
+	if (strategy == HASHMAP_UPDATE)
+		return -ENOENT;
+
+	if (hashmap_needs_to_grow(map)) {
+		err = hashmap_grow(map);
+		if (err)
+			return err;
+		h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+	}
+
+	entry = malloc(sizeof(struct hashmap_entry));
+	if (!entry)
+		return -ENOMEM;
+
+	entry->key = key;
+	entry->value = value;
+	hashmap_add_entry(&map->buckets[h], entry);
+	map->sz++;
+
+	return 0;
+}
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+{
+	struct hashmap_entry *entry;
+	size_t h;
+
+	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+	if (!hashmap_find_entry(map, key, h, NULL, &entry))
+		return false;
+
+	if (value)
+		*value = entry->value;
+	return true;
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+		     const void **old_key, void **old_value)
+{
+	struct hashmap_entry **pprev, *entry;
+	size_t h;
+
+	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+	if (!hashmap_find_entry(map, key, h, &pprev, &entry))
+		return false;
+
+	if (old_key)
+		*old_key = entry->key;
+	if (old_value)
+		*old_value = entry->value;
+
+	hashmap_del_entry(pprev, entry);
+	free(entry);
+	map->sz--;
+
+	return true;
+}

src/hashmap.h

@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#ifndef __LIBBPF_HASHMAP_H
+#define __LIBBPF_HASHMAP_H
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <limits.h>
+
+static inline size_t hash_bits(size_t h, int bits)
+{
+	/* shuffle bits and return requested number of upper bits */
+	if (bits == 0)
+		return 0;
+
+#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
+	/* LP64 case */
+	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
+#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__)
+	return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits);
+#else
+#	error "Unsupported size_t size"
+#endif
+}
+
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
+typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
+typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+
+struct hashmap_entry {
+	const void *key;
+	void *value;
+	struct hashmap_entry *next;
+};
+
+struct hashmap {
+	hashmap_hash_fn hash_fn;
+	hashmap_equal_fn equal_fn;
+	void *ctx;
+
+	struct hashmap_entry **buckets;
+	size_t cap;
+	size_t cap_bits;
+	size_t sz;
+};
+
+#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
+	.hash_fn = (hash_fn),			\
+	.equal_fn = (equal_fn),			\
+	.ctx = (ctx),				\
+	.buckets = NULL,			\
+	.cap = 0,				\
+	.cap_bits = 0,				\
+	.sz = 0,				\
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+		   hashmap_equal_fn equal_fn, void *ctx);
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+			     hashmap_equal_fn equal_fn,
+			     void *ctx);
+void hashmap__clear(struct hashmap *map);
+void hashmap__free(struct hashmap *map);
+
+size_t hashmap__size(const struct hashmap *map);
+size_t hashmap__capacity(const struct hashmap *map);
+
+/*
+ * Hashmap insertion strategy:
+ * - HASHMAP_ADD - only add key/value if key doesn't exist yet;
+ * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise,
+ *   update value;
+ * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do
+ *   nothing and return -ENOENT;
+ * - HASHMAP_APPEND - always add key/value pair, even if key already exists.
+ *   This turns hashmap into a multimap by allowing multiple values to be
+ *   associated with the same key. Most useful read API for such hashmap is
+ *   hashmap__for_each_key_entry() iteration. If hashmap__find() is still
+ *   used, it will return last inserted key/value entry (first in a bucket
+ *   chain).
+ */
+enum hashmap_insert_strategy {
+	HASHMAP_ADD,
+	HASHMAP_SET,
+	HASHMAP_UPDATE,
+	HASHMAP_APPEND,
+};
+
+/*
+ * hashmap__insert() adds key/value entry w/ various semantics, depending on
+ * provided strategy value. If a given key/value pair replaced already
+ * existing key/value pair, both old key and old value will be returned
+ * through old_key and old_value to allow calling code do proper memory
+ * management.
+ */
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+		    enum hashmap_insert_strategy strategy,
+		    const void **old_key, void **old_value);
+
+static inline int hashmap__add(struct hashmap *map,
+			       const void *key, void *value)
+{
+	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
+}
+
+static inline int hashmap__set(struct hashmap *map,
+			       const void *key, void *value,
+			       const void **old_key, void **old_value)
+{
+	return hashmap__insert(map, key, value, HASHMAP_SET,
+			       old_key, old_value);
+}
+
+static inline int hashmap__update(struct hashmap *map,
+				  const void *key, void *value,
+				  const void **old_key, void **old_value)
+{
+	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
+			       old_key, old_value);
+}
+
+static inline int hashmap__append(struct hashmap *map,
+				  const void *key, void *value)
+{
+	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+		     const void **old_key, void **old_value);
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+
+/*
+ * hashmap__for_each_entry - iterate over all entries in hashmap
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry(map, cur, bkt)				    \
+	for (bkt = 0; bkt < map->cap; bkt++)				    \
+		for (cur = map->buckets[bkt]; cur; cur = cur->next)
+
+/*
+ * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
+ * against removals
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @tmp: struct hashmap_entry * used as a temporary next cursor storage
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry_safe(map, cur, tmp, bkt)		    \
+	for (bkt = 0; bkt < map->cap; bkt++)				    \
+		for (cur = map->buckets[bkt];				    \
+		     cur && ({tmp = cur->next; true; });		    \
+		     cur = tmp)
+
+/*
+ * hashmap__for_each_key_entry - iterate over entries associated with given key
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @key: key to iterate entries for
+ */
+#define hashmap__for_each_key_entry(map, cur, _key)			    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
+	     cur;							    \
+	     cur = cur->next)						    \
+		if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
+	     cur && ({ tmp = cur->next; true; });			    \
+	     cur = tmp)							    \
+		if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#endif /* __LIBBPF_HASHMAP_H */

src/libbpf.map

@@ -164,3 +164,278 @@ LIBBPF_0.0.3 {
 		bpf_map_freeze;
 		btf__finalize_data;
 } LIBBPF_0.0.2;
+
+LIBBPF_0.0.4 {
+	global:
+		bpf_link__destroy;
+		bpf_object__load_xattr;
+		bpf_program__attach_kprobe;
+		bpf_program__attach_perf_event;
+		bpf_program__attach_raw_tracepoint;
+		bpf_program__attach_tracepoint;
+		bpf_program__attach_uprobe;
+		btf_dump__dump_type;
+		btf_dump__free;
+		btf_dump__new;
+		btf__parse_elf;
+		libbpf_num_possible_cpus;
+		perf_buffer__free;
+		perf_buffer__new;
+		perf_buffer__new_raw;
+		perf_buffer__poll;
+		xsk_umem__create;
+} LIBBPF_0.0.3;
+
+LIBBPF_0.0.5 {
+	global:
+		bpf_btf_get_next_id;
+} LIBBPF_0.0.4;
+
+LIBBPF_0.0.6 {
+	global:
+		bpf_get_link_xdp_info;
+		bpf_map__get_pin_path;
+		bpf_map__is_pinned;
+		bpf_map__set_pin_path;
+		bpf_object__open_file;
+		bpf_object__open_mem;
+		bpf_program__attach_trace;
+		bpf_program__get_expected_attach_type;
+		bpf_program__get_type;
+		bpf_program__is_tracing;
+		bpf_program__set_tracing;
+		bpf_program__size;
+		btf__find_by_name_kind;
+		libbpf_find_vmlinux_btf_id;
+} LIBBPF_0.0.5;
+
+LIBBPF_0.0.7 {
+	global:
+		btf_dump__emit_type_decl;
+		bpf_link__disconnect;
+		bpf_map__attach_struct_ops;
+		bpf_map_delete_batch;
+		bpf_map_lookup_and_delete_batch;
+		bpf_map_lookup_batch;
+		bpf_map_update_batch;
+		bpf_object__find_program_by_name;
+		bpf_object__attach_skeleton;
+		bpf_object__destroy_skeleton;
+		bpf_object__detach_skeleton;
+		bpf_object__load_skeleton;
+		bpf_object__open_skeleton;
+		bpf_probe_large_insn_limit;
+		bpf_prog_attach_xattr;
+		bpf_program__attach;
+		bpf_program__name;
+		bpf_program__is_extension;
+		bpf_program__is_struct_ops;
+		bpf_program__set_extension;
+		bpf_program__set_struct_ops;
+		btf__align_of;
+		libbpf_find_kernel_btf;
+} LIBBPF_0.0.6;
+
+LIBBPF_0.0.8 {
+	global:
+		bpf_link__fd;
+		bpf_link__open;
+		bpf_link__pin;
+		bpf_link__pin_path;
+		bpf_link__unpin;
+		bpf_link__update_program;
+		bpf_link_create;
+		bpf_link_update;
+		bpf_map__set_initial_value;
+		bpf_prog_attach_opts;
+		bpf_program__attach_cgroup;
+		bpf_program__attach_lsm;
+		bpf_program__is_lsm;
+		bpf_program__set_attach_target;
+		bpf_program__set_lsm;
+		bpf_set_link_xdp_fd_opts;
+} LIBBPF_0.0.7;
+
+LIBBPF_0.0.9 {
+	global:
+		bpf_enable_stats;
+		bpf_iter_create;
+		bpf_link_get_fd_by_id;
+		bpf_link_get_next_id;
+		bpf_program__attach_iter;
+		bpf_program__attach_netns;
+		perf_buffer__consume;
+		ring_buffer__add;
+		ring_buffer__consume;
+		ring_buffer__free;
+		ring_buffer__new;
+		ring_buffer__poll;
+} LIBBPF_0.0.8;
+
+LIBBPF_0.1.0 {
+	global:
+		bpf_link__detach;
+		bpf_link_detach;
+		bpf_map__ifindex;
+		bpf_map__key_size;
+		bpf_map__map_flags;
+		bpf_map__max_entries;
+		bpf_map__numa_node;
+		bpf_map__set_key_size;
+		bpf_map__set_map_flags;
+		bpf_map__set_max_entries;
+		bpf_map__set_numa_node;
+		bpf_map__set_type;
+		bpf_map__set_value_size;
+		bpf_map__type;
+		bpf_map__value_size;
+		bpf_program__attach_xdp;
+		bpf_program__autoload;
+		bpf_program__is_sk_lookup;
+		bpf_program__set_autoload;
+		bpf_program__set_sk_lookup;
+		btf__parse;
+		btf__parse_raw;
+		btf__pointer_size;
+		btf__set_fd;
+		btf__set_pointer_size;
+} LIBBPF_0.0.9;
+
+LIBBPF_0.2.0 {
+	global:
+		bpf_prog_bind_map;
+		bpf_prog_test_run_opts;
+		bpf_program__attach_freplace;
+		bpf_program__section_name;
+		btf__add_array;
+		btf__add_const;
+		btf__add_enum;
+		btf__add_enum_value;
+		btf__add_datasec;
+		btf__add_datasec_var_info;
+		btf__add_field;
+		btf__add_func;
+		btf__add_func_param;
+		btf__add_func_proto;
+		btf__add_fwd;
+		btf__add_int;
+		btf__add_ptr;
+		btf__add_restrict;
+		btf__add_str;
+		btf__add_struct;
+		btf__add_typedef;
+		btf__add_union;
+		btf__add_var;
+		btf__add_volatile;
+		btf__endianness;
+		btf__find_str;
+		btf__new_empty;
+		btf__set_endianness;
+		btf__str_by_offset;
+		perf_buffer__buffer_cnt;
+		perf_buffer__buffer_fd;
+		perf_buffer__epoll_fd;
+		perf_buffer__consume_buffer;
+		xsk_socket__create_shared;
+} LIBBPF_0.1.0;
+
+LIBBPF_0.3.0 {
+	global:
+		btf__base_btf;
+		btf__parse_elf_split;
+		btf__parse_raw_split;
+		btf__parse_split;
+		btf__new_empty_split;
+		btf__new_split;
+		ring_buffer__epoll_fd;
+		xsk_setup_xdp_prog;
+		xsk_socket__update_xskmap;
+} LIBBPF_0.2.0;
+
+LIBBPF_0.4.0 {
+	global:
+		btf__add_float;
+		btf__add_type;
+		bpf_linker__add_file;
+		bpf_linker__finalize;
+		bpf_linker__free;
+		bpf_linker__new;
+		bpf_map__inner_map;
+		bpf_object__set_kversion;
+		bpf_tc_attach;
+		bpf_tc_detach;
+		bpf_tc_hook_create;
+		bpf_tc_hook_destroy;
+		bpf_tc_query;
+} LIBBPF_0.3.0;
+
+LIBBPF_0.5.0 {
+	global:
+		bpf_map__initial_value;
+		bpf_map__pin_path;
+		bpf_map_lookup_and_delete_elem_flags;
+		bpf_program__attach_kprobe_opts;
+		bpf_program__attach_perf_event_opts;
+		bpf_program__attach_tracepoint_opts;
+		bpf_program__attach_uprobe_opts;
+		bpf_object__gen_loader;
+		btf__load_from_kernel_by_id;
+		btf__load_from_kernel_by_id_split;
+		btf__load_into_kernel;
+		btf__load_module_btf;
+		btf__load_vmlinux_btf;
+		btf_dump__dump_type_data;
+		libbpf_set_strict_mode;
+} LIBBPF_0.4.0;
+
+LIBBPF_0.6.0 {
+	global:
+		bpf_map__map_extra;
+		bpf_map__set_map_extra;
+		bpf_map_create;
+		bpf_object__next_map;
+		bpf_object__next_program;
+		bpf_object__prev_map;
+		bpf_object__prev_program;
+		bpf_prog_load_deprecated;
+		bpf_prog_load;
+		bpf_program__flags;
+		bpf_program__insn_cnt;
+		bpf_program__insns;
+		bpf_program__set_flags;
+		btf__add_btf;
+		btf__add_decl_tag;
+		btf__add_type_tag;
+		btf__dedup;
+		btf__dedup_deprecated;
+		btf__raw_data;
+		btf__type_cnt;
+		btf_dump__new;
+		btf_dump__new_deprecated;
+		libbpf_major_version;
+		libbpf_minor_version;
+		libbpf_version_string;
+		perf_buffer__new;
+		perf_buffer__new_deprecated;
+		perf_buffer__new_raw;
+		perf_buffer__new_raw_deprecated;
+} LIBBPF_0.5.0;
+
+LIBBPF_0.7.0 {
+	global:
+		bpf_btf_load;
+		bpf_program__expected_attach_type;
+		bpf_program__log_buf;
+		bpf_program__log_level;
+		bpf_program__set_log_buf;
+		bpf_program__set_log_level;
+		bpf_program__type;
+		bpf_xdp_attach;
+		bpf_xdp_detach;
+		bpf_xdp_query;
+		bpf_xdp_query_id;
+		libbpf_probe_bpf_helper;
+		libbpf_probe_bpf_map_type;
+		libbpf_probe_bpf_prog_type;
+		libbpf_set_memlock_rlim_max;
+};

src/libbpf.pc.template

@@ -8,5 +8,5 @@ Name: libbpf
 Description: BPF library
 Version: @VERSION@
 Libs: -L${libdir} -lbpf
-Requires.private: libelf
+Requires.private: libelf zlib
 Cflags: -I${includedir}

src/libbpf_common.h

@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Common user-facing libbpf helpers.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+
+#ifndef __LIBBPF_LIBBPF_COMMON_H
+#define __LIBBPF_LIBBPF_COMMON_H
+
+#include <string.h>
+#include "libbpf_version.h"
+
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
+#define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg)))
+
+/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */
+#define LIBBPF_DEPRECATED_SINCE(major, minor, msg)			    \
+	__LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor		    \
+		(LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg))
+
+#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor)			    \
+	(LIBBPF_MAJOR_VERSION > (major) ||				    \
+	 (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor)))
+
+/* Add checks for other versions below when planning deprecation of API symbols
+ * with the LIBBPF_DEPRECATED_SINCE macro.
+ */
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6)
+#define __LIBBPF_MARK_DEPRECATED_0_6(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_6(X)
+#endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7)
+#define __LIBBPF_MARK_DEPRECATED_0_7(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_7(X)
+#endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8)
+#define __LIBBPF_MARK_DEPRECATED_0_8(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_8(X)
+#endif
+
+/* This set of internal macros allows to do "function overloading" based on
+ * number of arguments provided by used in backwards-compatible way during the
+ * transition to libbpf 1.0
+ * It's ugly but necessary evil that will be cleaned up when we get to 1.0.
+ * See bpf_prog_load() overload for example.
+ */
+#define ___libbpf_cat(A, B) A ## B
+#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM)
+#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N
+#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1)
+#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__)
+
+/* Helper macro to declare and initialize libbpf options struct
+ *
+ * This dance with uninitialized declaration, followed by memset to zero,
+ * followed by assignment using compound literal syntax is done to preserve
+ * ability to use a nice struct field initialization syntax and **hopefully**
+ * have all the padding bytes initialized to zero. It's not guaranteed though,
+ * when copying literal, that compiler won't copy garbage in literal's padding
+ * bytes, but that's the best way I've found and it seems to work in practice.
+ *
+ * Macro declares opts struct of given type and name, zero-initializes,
+ * including any extra padding, it with memset() and then assigns initial
+ * values provided by users in struct initializer-syntax as varargs.
+ */
+#define LIBBPF_OPTS(TYPE, NAME, ...)					    \
+	struct TYPE NAME = ({ 						    \
+		memset(&NAME, 0, sizeof(struct TYPE));			    \
+		(struct TYPE) {						    \
+			.sz = sizeof(struct TYPE),			    \
+			__VA_ARGS__					    \
+		};							    \
+	})
+
+#endif /* __LIBBPF_LIBBPF_COMMON_H */

src/libbpf_errno.c

@@ -12,6 +12,10 @@
 #include <string.h>
 
 #include "libbpf.h"
+#include "libbpf_internal.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
 #define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
@@ -36,7 +40,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 int libbpf_strerror(int err, char *buf, size_t size)
 {
 	if (!buf || !size)
-		return -1;
+		return libbpf_err(-EINVAL);
 
 	err = err > 0 ? err : -err;
 
@@ -45,7 +49,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 		ret = strerror_r(err, buf, size);
 		buf[size - 1] = '\0';
-		return ret;
+		return libbpf_err_errno(ret);
 	}
 
 	if (err < __LIBBPF_ERRNO__END) {
@@ -59,5 +63,5 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 	snprintf(buf, size, "Unknown libbpf error %d", err);
 	buf[size - 1] = '\0';
-	return -1;
+	return libbpf_err(-ENOENT);
 }

src/libbpf_internal.h

@@ -9,6 +9,55 @@
 #ifndef __LIBBPF_LIBBPF_INTERNAL_H
 #define __LIBBPF_LIBBPF_INTERNAL_H
 
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include "libbpf_legacy.h"
+#include "relo_core.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
+#include "libbpf.h"
+#include "btf.h"
+
+#ifndef EM_BPF
+#define EM_BPF 247
+#endif
+
+#ifndef R_BPF_64_64
+#define R_BPF_64_64 1
+#endif
+#ifndef R_BPF_64_ABS64
+#define R_BPF_64_ABS64 2
+#endif
+#ifndef R_BPF_64_ABS32
+#define R_BPF_64_ABS32 3
+#endif
+#ifndef R_BPF_64_32
+#define R_BPF_64_32 10
+#endif
+
+#ifndef SHT_LLVM_ADDRSIG
+#define SHT_LLVM_ADDRSIG 0x6FFF4C03
+#endif
+
+/* if libelf is old and doesn't support mmap(), fall back to read() */
+#ifndef ELF_C_READ_MMAP
+#define ELF_C_READ_MMAP ELF_C_READ
+#endif
+
+/* Older libelf all end up in this expression, for both 32 and 64 bit */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o) ((o) & 0x03)
+#endif
+
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
 	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
@@ -20,6 +69,68 @@
 #define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset)
 #define BTF_PARAM_ENC(name, type) (name), (type)
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
+#define BTF_TYPE_FLOAT_ENC(name, sz) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
+#define BTF_TYPE_TYPE_TAG_ENC(value, type) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type)
+
+#ifndef likely
+#define likely(x) __builtin_expect(!!(x), 1)
+#endif
+#ifndef unlikely
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#endif
+#ifndef min
+# define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#ifndef max
+# define max(x, y) ((x) < (y) ? (y) : (x))
+#endif
+#ifndef offsetofend
+# define offsetofend(TYPE, FIELD) \
+	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
+#endif
+#ifndef __alias
+#define __alias(symbol) __attribute__((alias(#symbol)))
+#endif
+
+/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is
+ * a string literal known at compilation time or char * pointer known only at
+ * runtime.
+ */
+#define str_has_pfx(str, pfx) \
+	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
+
+/* Symbol versioning is different between static and shared library.
+ * Properly versioned symbols are needed for shared library, but
+ * only the symbol of the new version is needed for static library.
+ * Starting with GNU C 10, use symver attribute instead of .symver assembler
+ * directive, which works better with GCC LTO builds.
+ */
+#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10
+
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@@" #version)))
+#define COMPAT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@" #version)))
+
+#elif defined(SHARED)
+
+#define COMPAT_VERSION(internal_name, api_name, version) \
+	asm(".symver " #internal_name "," #api_name "@" #version);
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	asm(".symver " #internal_name "," #api_name "@@" #version);
+
+#else /* !SHARED */
+
+#define COMPAT_VERSION(internal_name, api_name, version)
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	extern typeof(internal_name) api_name \
+	__attribute__((alias(#internal_name)));
+
+#endif
 
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
@@ -30,11 +141,392 @@ do {				\
 	libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__);	\
 } while (0)
 
-#define pr_warning(fmt, ...)	__pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
+#define pr_warn(fmt, ...)	__pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
-int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
-			  const char *str_sec, size_t str_len);
+#ifndef __has_builtin
+#define __has_builtin(x) 0
+#endif
+/*
+ * Re-implement glibc's reallocarray() for libbpf internal-only use.
+ * reallocarray(), unfortunately, is not available in all versions of glibc,
+ * so requires extra feature detection and using reallocarray() stub from
+ * <tools/libc_compat.h> and COMPAT_NEED_REALLOCARRAY. All this complicates
+ * build of libbpf unnecessarily and is just a maintenance burden. Instead,
+ * it's trivial to implement libbpf-specific internal version and use it
+ * throughout libbpf.
+ */
+static inline void *libbpf_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);
+}
+
+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+	size_t i;
+
+	if (sz == 0)
+		return;
+
+	sz--;
+	for (i = 0; i < sz && src[i]; i++)
+		dst[i] = src[i];
+	dst[i] = '\0';
+}
+
+__u32 get_kernel_version(void);
+
+struct btf;
+struct btf_type;
+
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
+const char *btf_kind_str(const struct btf_type *t);
+const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
+static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
+{
+	return (enum btf_func_linkage)(int)btf_vlen(t);
+}
+
+static inline __u32 btf_type_info(int kind, int vlen, int kflag)
+{
+	return (kflag << 31) | (kind << 24) | vlen;
+}
+
+enum map_def_parts {
+	MAP_DEF_MAP_TYPE	= 0x001,
+	MAP_DEF_KEY_TYPE	= 0x002,
+	MAP_DEF_KEY_SIZE	= 0x004,
+	MAP_DEF_VALUE_TYPE	= 0x008,
+	MAP_DEF_VALUE_SIZE	= 0x010,
+	MAP_DEF_MAX_ENTRIES	= 0x020,
+	MAP_DEF_MAP_FLAGS	= 0x040,
+	MAP_DEF_NUMA_NODE	= 0x080,
+	MAP_DEF_PINNING		= 0x100,
+	MAP_DEF_INNER_MAP	= 0x200,
+	MAP_DEF_MAP_EXTRA	= 0x400,
+
+	MAP_DEF_ALL		= 0x7ff, /* combination of all above */
+};
+
+struct btf_map_def {
+	enum map_def_parts parts;
+	__u32 map_type;
+	__u32 key_type_id;
+	__u32 key_size;
+	__u32 value_type_id;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 map_flags;
+	__u32 numa_node;
+	__u32 pinning;
+	__u64 map_extra;
+};
+
+int parse_btf_map_def(const char *map_name, struct btf *btf,
+		      const struct btf_type *def_t, bool strict,
+		      struct btf_map_def *map_def, struct btf_map_def *inner_def);
+
+void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+		     size_t cur_cnt, size_t max_cnt, size_t add_cnt);
+int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
+
+static inline bool libbpf_is_mem_zeroed(const char *p, ssize_t len)
+{
+	while (len > 0) {
+		if (*p)
+			return false;
+		p++;
+		len--;
+	}
+	return true;
+}
+
+static inline bool libbpf_validate_opts(const char *opts,
+					size_t opts_sz, size_t user_sz,
+					const char *type_name)
+{
+	if (user_sz < sizeof(size_t)) {
+		pr_warn("%s size (%zu) is too small\n", type_name, user_sz);
+		return false;
+	}
+	if (!libbpf_is_mem_zeroed(opts + opts_sz, (ssize_t)user_sz - opts_sz)) {
+		pr_warn("%s has non-zero extra bytes\n", type_name);
+		return false;
+	}
+	return true;
+}
+
+#define OPTS_VALID(opts, type)						      \
+	(!(opts) || libbpf_validate_opts((const char *)opts,		      \
+					 offsetofend(struct type,	      \
+						     type##__last_field),     \
+					 (opts)->sz, #type))
+#define OPTS_HAS(opts, field) \
+	((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
+#define OPTS_GET(opts, field, fallback_value) \
+	(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
+#define OPTS_SET(opts, field, value)		\
+	do {					\
+		if (OPTS_HAS(opts, field))	\
+			(opts)->field = value;	\
+	} while (0)
+
+#define OPTS_ZEROED(opts, last_nonzero_field)				      \
+({									      \
+	ssize_t __off = offsetofend(typeof(*(opts)), last_nonzero_field);     \
+	!(opts) || libbpf_is_mem_zeroed((const void *)opts + __off,	      \
+					(opts)->sz - __off);		      \
+})
+
+enum kern_feature_id {
+	/* v4.14: kernel support for program & map names. */
+	FEAT_PROG_NAME,
+	/* v5.2: kernel support for global data sections. */
+	FEAT_GLOBAL_DATA,
+	/* BTF support */
+	FEAT_BTF,
+	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+	FEAT_BTF_FUNC,
+	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+	FEAT_BTF_DATASEC,
+	/* BTF_FUNC_GLOBAL is supported */
+	FEAT_BTF_GLOBAL_FUNC,
+	/* BPF_F_MMAPABLE is supported for arrays */
+	FEAT_ARRAY_MMAP,
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	FEAT_EXP_ATTACH_TYPE,
+	/* bpf_probe_read_{kernel,user}[_str] helpers */
+	FEAT_PROBE_READ_KERN,
+	/* BPF_PROG_BIND_MAP is supported */
+	FEAT_PROG_BIND_MAP,
+	/* Kernel support for module BTFs */
+	FEAT_MODULE_BTF,
+	/* BTF_KIND_FLOAT support */
+	FEAT_BTF_FLOAT,
+	/* BPF perf link support */
+	FEAT_PERF_LINK,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
+	/* BTF_KIND_TYPE_TAG support */
+	FEAT_BTF_TYPE_TAG,
+	/* memcg-based accounting for BPF maps and progs */
+	FEAT_MEMCG_ACCOUNT,
+	__FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);
+
+int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
+int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+			 const char *str_sec, size_t str_len);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
+
+struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
+void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
+				const char **prefix, int *kind);
+
+struct btf_ext_info {
+	/*
+	 * info points to the individual info section (e.g. func_info and
+	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
+	 */
+	void *info;
+	__u32 rec_size;
+	__u32 len;
+};
+
+#define for_each_btf_ext_sec(seg, sec)					\
+	for (sec = (seg)->info;						\
+	     (void *)sec < (seg)->info + (seg)->len;			\
+	     sec = (void *)sec + sizeof(struct btf_ext_info_sec) +	\
+		   (seg)->rec_size * sec->num_info)
+
+#define for_each_btf_ext_rec(seg, sec, i, rec)				\
+	for (i = 0, rec = (void *)&(sec)->data;				\
+	     i < (sec)->num_info;					\
+	     i++, rec = (void *)rec + (seg)->rec_size)
+
+/*
+ * The .BTF.ext ELF section layout defined as
+ *   struct btf_ext_header
+ *   func_info subsection
+ *
+ * The func_info subsection layout:
+ *   record size for struct bpf_func_info in the func_info subsection
+ *   struct btf_sec_func_info for section #1
+ *   a list of bpf_func_info records for section #1
+ *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ *     but may not be identical
+ *   struct btf_sec_func_info for section #2
+ *   a list of bpf_func_info records for section #2
+ *   ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+	__u32	hdr_len;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	func_info_off;
+	__u32	func_info_len;
+	__u32	line_info_off;
+	__u32	line_info_len;
+
+	/* optional part of .BTF.ext header */
+	__u32	core_relo_off;
+	__u32	core_relo_len;
+};
+
+struct btf_ext {
+	union {
+		struct btf_ext_header *hdr;
+		void *data;
+	};
+	struct btf_ext_info func_info;
+	struct btf_ext_info line_info;
+	struct btf_ext_info core_relo_info;
+	__u32 data_size;
+};
+
+struct btf_ext_info_sec {
+	__u32	sec_name_off;
+	__u32	num_info;
+	/* Followed by num_info * record_size number of bytes */
+	__u8	data[];
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_off;
+	__u32   type_id;
+};
+
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
+
+typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
+typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
+int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
+int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
+int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
+int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind);
+
+extern enum libbpf_strict_mode libbpf_mode;
+
+/* handle direct returned errors */
+static inline int libbpf_err(int ret)
+{
+	if (ret < 0)
+		errno = -ret;
+	return ret;
+}
+
+/* handle errno-based (e.g., syscall or libc) errors according to libbpf's
+ * strict mode settings
+ */
+static inline int libbpf_err_errno(int ret)
+{
+	if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS)
+		/* errno is already assumed to be set on error */
+		return ret < 0 ? -errno : ret;
+
+	/* legacy: on error return -1 directly and don't touch errno */
+	return ret;
+}
+
+/* handle error for pointer-returning APIs, err is assumed to be < 0 always */
+static inline void *libbpf_err_ptr(int err)
+{
+	/* set errno on error, this doesn't break anything */
+	errno = -err;
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return NULL;
+
+	/* legacy: encode err as ptr */
+	return ERR_PTR(err);
+}
+
+/* handle pointer-returning APIs' error handling */
+static inline void *libbpf_ptr(void *ret)
+{
+	/* set errno on error, this doesn't break anything */
+	if (IS_ERR(ret))
+		errno = -PTR_ERR(ret);
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return IS_ERR(ret) ? NULL : ret;
+
+	/* legacy: pass-through original pointer */
+	return ret;
+}
+
+static inline bool str_is_empty(const char *s)
+{
+	return !s || !s[0];
+}
+
+static inline bool is_ldimm64_insn(struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
+ * Takes ownership of the fd passed in, and closes it if calling
+ * fcntl(fd, F_DUPFD_CLOEXEC, 3).
+ */
+static inline int ensure_good_fd(int fd)
+{
+	int old_fd = fd, saved_errno;
+
+	if (fd < 0)
+		return fd;
+	if (fd < 3) {
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
+		saved_errno = errno;
+		close(old_fd);
+		if (fd < 0) {
+			pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
+			errno = saved_errno;
+		}
+	}
+	return fd;
+}
 
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_legacy.h

@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0])
+ *
+ *   [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY
+ *
+ * Copyright (C) 2021 Facebook
+ */
+#ifndef __LIBBPF_LEGACY_BPF_H
+#define __LIBBPF_LEGACY_BPF_H
+
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include "libbpf_common.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+enum libbpf_strict_mode {
+	/* Turn on all supported strict features of libbpf to simulate libbpf
+	 * v1.0 behavior.
+	 * This will be the default behavior in libbpf v1.0.
+	 */
+	LIBBPF_STRICT_ALL = 0xffffffff,
+
+	/*
+	 * Disable any libbpf 1.0 behaviors. This is the default before libbpf
+	 * v1.0. It won't be supported anymore in v1.0, please update your
+	 * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0.
+	 */
+	LIBBPF_STRICT_NONE = 0x00,
+	/*
+	 * Return NULL pointers on error, not ERR_PTR(err).
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_CLEAN_PTRS = 0x01,
+	/*
+	 * Return actual error codes from low-level APIs directly, not just -1.
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
+	/*
+	 * Enforce strict BPF program section (SEC()) names.
+	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
+	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
+	 * unrecognized by libbpf and would have to be just SEC("xdp") and
+	 * SEC("xdp") and SEC("perf_event").
+	 *
+	 * Note, in this mode the program pin path will be based on the
+	 * function name instead of section name.
+	 */
+	LIBBPF_STRICT_SEC_NAME = 0x04,
+	/*
+	 * Disable the global 'bpf_objects_list'. Maintaining this list adds
+	 * a race condition to bpf_object__open() and bpf_object__close().
+	 * Clients can maintain it on their own if it is valuable for them.
+	 */
+	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+	/*
+	 * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the
+	 * first BPF program or map creation operation. This is done only if
+	 * kernel is too old to support memcg-based memory accounting for BPF
+	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
+	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
+	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
+	 * operation.
+	 */
+	LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,
+	/*
+	 * Error out on any SEC("maps") map definition, which are deprecated
+	 * in favor of BTF-defined map definitions in SEC(".maps").
+	 */
+	LIBBPF_STRICT_MAP_DEFINITIONS = 0x20,
+
+	__LIBBPF_STRICT_LAST,
+};
+
+LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
+
+#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS
+
+/* "Discouraged" APIs which don't follow consistent libbpf naming patterns.
+ * They are normally a trivial aliases or wrappers for proper APIs and are
+ * left to minimize unnecessary disruption for users of libbpf. But they
+ * shouldn't be used going forward.
+ */
+
+struct bpf_program;
+struct bpf_map;
+struct btf;
+struct btf_ext;
+
+LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog);
+LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog);
+LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
+LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __LIBBPF_LEGACY_BPF_H */

src/libbpf_probes.c

@@ -33,7 +33,7 @@ static int get_vendor_id(int ifindex)
 
 	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return -1;
 
@@ -48,35 +48,65 @@ static int get_vendor_id(int ifindex)
 	return strtol(buf, NULL, 0);
 }
 
-static int get_kernel_version(void)
+static int probe_prog_load(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)
 {
-	int version, subversion, patchlevel;
-	struct utsname utsn;
-
-	/* Return 0 on failure, and attempt to probe with empty kversion */
-	if (uname(&utsn))
-		return 0;
-
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
-		return 0;
-
-	return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
-	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
-	struct bpf_load_program_attr xattr = {};
-	int fd;
+	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, err, exp_err = 0;
+	const char *exp_msg = NULL;
+	char buf[4096];
 
 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-		xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+		opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+		break;
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+		opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
+		break;
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		opts.expected_attach_type = BPF_SK_LOOKUP;
 		break;
 	case BPF_PROG_TYPE_KPROBE:
-		xattr.kern_version = get_kernel_version();
+		opts.kern_version = get_kernel_version();
+		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		opts.expected_attach_type = BPF_LIRC_MODE2;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		if (prog_type == BPF_PROG_TYPE_TRACING)
+			opts.expected_attach_type = BPF_TRACE_FENTRY;
+		else
+			opts.expected_attach_type = BPF_MODIFY_RETURN;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "attach_btf_id 1 is not a function";
+		break;
+	case BPF_PROG_TYPE_EXT:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "Cannot replace kernel functions";
+		break;
+	case BPF_PROG_TYPE_SYSCALL:
+		opts.prog_flags = BPF_F_SLEEPABLE;
+		break;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		exp_err = -524; /* -ENOTSUPP */
 		break;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_SOCKET_FILTER:
@@ -97,23 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	default:
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
-	xattr.prog_type = prog_type;
-	xattr.insns = insns;
-	xattr.insns_cnt = insns_cnt;
-	xattr.license = "GPL";
-	xattr.prog_ifindex = ifindex;
-
-	fd = bpf_load_program_xattr(&xattr, buf, buf_len);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	err = -errno;
 	if (fd >= 0)
 		close(fd);
+	if (exp_err) {
+		if (fd >= 0 || err != exp_err)
+			return 0;
+		if (exp_msg && !strstr(buf, exp_msg))
+			return 0;
+		return 1;
+	}
+	return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN()
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+	return libbpf_err(ret);
 }
 
 bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
@@ -123,18 +172,22 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 		BPF_EXIT_INSN()
 	};
 
+	/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
+	if (ifindex == 0)
+		return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
+
 	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
 		/* nfp returns -EINVAL on exit(0) with TC offload */
 		insns[0].imm = 2;
 
 	errno = 0;
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
 
 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
 
-int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
-			  const char *str_sec, size_t str_len)
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+			 const char *str_sec, size_t str_len)
 {
 	struct btf_header hdr = {
 		.magic = BTF_MAGIC,
@@ -156,18 +209,13 @@ int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
 	memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
 	memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
 
-	btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false);
-	if (btf_fd < 0) {
-		free(raw_btf);
-		return 0;
-	}
+	btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
 
-	close(btf_fd);
 	free(raw_btf);
-	return 1;
+	return btf_fd;
 }
 
-static int load_sk_storage_btf(void)
+static int load_local_storage_btf(void)
 {
 	const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l";
 	/* struct bpf_spin_lock {
@@ -190,21 +238,22 @@ static int load_sk_storage_btf(void)
 		BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
 	};
 
-	return libbpf__probe_raw_btf((char *)types, sizeof(types),
+	return libbpf__load_raw_btf((char *)types, sizeof(types),
 				     strs, sizeof(strs));
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 {
-	int key_size, value_size, max_entries, map_flags;
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int key_size, value_size, max_entries;
 	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
-	struct bpf_create_map_attr attr = {};
-	int fd = -1, btf_fd = -1, fd_inner;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+
+	opts.map_ifindex = ifindex;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
 	max_entries	= 1;
-	map_flags	= 0;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -213,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_LPM_TRIE:
 		key_size	= sizeof(__u64);
 		value_size	= sizeof(__u64);
-		map_flags	= BPF_F_NO_PREALLOC;
+		opts.map_flags	= BPF_F_NO_PREALLOC;
 		break;
 	case BPF_MAP_TYPE_CGROUP_STORAGE:
 	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
@@ -226,16 +275,31 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		key_size	= 0;
 		break;
 	case BPF_MAP_TYPE_SK_STORAGE:
+	case BPF_MAP_TYPE_INODE_STORAGE:
+	case BPF_MAP_TYPE_TASK_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
-		map_flags = BPF_F_NO_PREALLOC;
-		btf_fd = load_sk_storage_btf();
+		opts.map_flags = BPF_F_NO_PREALLOC;
+		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
-			return false;
+			return btf_fd;
+		break;
+	case BPF_MAP_TYPE_RINGBUF:
+		key_size = 0;
+		value_size = 0;
+		max_entries = 4096;
+		break;
+	case BPF_MAP_TYPE_STRUCT_OPS:
+		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+		opts.btf_vmlinux_value_type_id = 1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -248,13 +312,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_CPUMAP:
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
-	default:
 		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
@@ -263,37 +330,102 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		 * map-in-map for offload
 		 */
 		if (ifindex)
-			return false;
+			goto cleanup;
 
-		fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH,
-					  sizeof(__u32), sizeof(__u32), 1, 0);
+		fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
+					  sizeof(__u32), sizeof(__u32), 1, NULL);
 		if (fd_inner < 0)
-			return false;
-		fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32),
-					   fd_inner, 1, 0);
-		close(fd_inner);
-	} else {
-		/* Note: No other restriction on map type probes for offload */
-		attr.map_type = map_type;
-		attr.key_size = key_size;
-		attr.value_size = value_size;
-		attr.max_entries = max_entries;
-		attr.map_flags = map_flags;
-		attr.map_ifindex = ifindex;
-		if (btf_fd >= 0) {
-			attr.btf_fd = btf_fd;
-			attr.btf_key_type_id = btf_key_type_id;
-			attr.btf_value_type_id = btf_value_type_id;
-		}
+			goto cleanup;
 
-		fd = bpf_create_map_xattr(&attr);
+		opts.inner_map_fd = fd_inner;
 	}
+
+	if (btf_fd >= 0) {
+		opts.btf_fd = btf_fd;
+		opts.btf_key_type_id = btf_key_type_id;
+		opts.btf_value_type_id = btf_value_type_id;
+	}
+
+	fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+	err = -errno;
+
+cleanup:
 	if (fd >= 0)
 		close(fd);
+	if (fd_inner >= 0)
+		close(fd_inner);
 	if (btf_fd >= 0)
 		close(btf_fd);
 
-	return fd >= 0;
+	if (exp_err)
+		return fd < 0 && err == exp_err ? 1 : 0;
+	else
+		return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
+{
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_map_create(map_type, 0);
+	return libbpf_err(ret);
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+	return probe_map_create(map_type, ifindex) == 1;
+}
+
+int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
+			    const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL((__u32)helper_id),
+		BPF_EXIT_INSN(),
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	char buf[4096];
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	/* we can't successfully load all prog types to check for BPF helper
+	 * support, so bail out with -EOPNOTSUPP error
+	 */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return -EOPNOTSUPP;
+	default:
+		break;
+	}
+
+	buf[0] = '\0';
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	/* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
+	 * at all, it will emit something like "invalid func unknown#181".
+	 * If BPF verifier recognizes BPF helper but it's not supported for
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
+	 * In both cases, provided combination of BPF program type and BPF
+	 * helper is not supported by the kernel.
+	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
+	 * because BPF helper happens to accept no input arguments or it
+	 * accepts one input argument and initial PTR_TO_CTX is fine for
+	 * that), or we'll get some more specific BPF verifier error about
+	 * some unsatisfied conditions.
+	 */
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+		return 0;
+	return 1; /* assume supported */
 }
 
 bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
@@ -306,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 	char buf[4096] = {};
 	bool res;
 
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
-		   ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
 	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
 
 	if (ifindex) {
@@ -323,3 +454,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 
 	return res;
 }
+
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+bool bpf_probe_large_insn_limit(__u32 ifindex)
+{
+	struct bpf_insn insns[BPF_MAXINSNS + 1];
+	int i;
+
+	for (i = 0; i < BPF_MAXINSNS; i++)
+		insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+	errno = 0;
+	probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+			ifindex);
+
+	return errno != E2BIG && errno != EINVAL;
+}

src/libbpf_util.h

@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-/* Copyright (c) 2019 Facebook */
-
-#ifndef __LIBBPF_LIBBPF_UTIL_H
-#define __LIBBPF_LIBBPF_UTIL_H
-
-#include <stdbool.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* Use these barrier functions instead of smp_[rw]mb() when they are
- * used in a libbpf header file. That way they can be built into the
- * application that uses libbpf.
- */
-#if defined(__i386__) || defined(__x86_64__)
-# define libbpf_smp_rmb() asm volatile("" : : : "memory")
-# define libbpf_smp_wmb() asm volatile("" : : : "memory")
-# define libbpf_smp_mb() \
-	asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
-/* Hinders stores to be observed before older loads. */
-# define libbpf_smp_rwmb() asm volatile("" : : : "memory")
-#elif defined(__aarch64__)
-# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
-# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
-# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
-# define libbpf_smp_rwmb() libbpf_smp_mb()
-#elif defined(__arm__)
-/* These are only valid for armv7 and above */
-# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
-# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
-# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
-# define libbpf_smp_rwmb() libbpf_smp_mb()
-#else
-/* Architecture missing native barrier functions. */
-# define libbpf_smp_rmb() __sync_synchronize()
-# define libbpf_smp_wmb() __sync_synchronize()
-# define libbpf_smp_mb() __sync_synchronize()
-# define libbpf_smp_rwmb() __sync_synchronize()
-#endif
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif

src/libbpf_version.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (C) 2021 Facebook */
+#ifndef __LIBBPF_VERSION_H
+#define __LIBBPF_VERSION_H
+
+#define LIBBPF_MAJOR_VERSION 0
+#define LIBBPF_MINOR_VERSION 7
+
+#endif /* __LIBBPF_VERSION_H */

src/netlink.c

@@ -4,7 +4,10 @@
 #include <stdlib.h>
 #include <memory.h>
 #include <unistd.h>
+#include <arpa/inet.h>
 #include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -12,22 +15,25 @@
 
 #include "bpf.h"
 #include "libbpf.h"
+#include "libbpf_internal.h"
 #include "nlattr.h"
 
 #ifndef SOL_NETLINK
 #define SOL_NETLINK 270
 #endif
 
+typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+
 typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 			      void *cookie);
 
 struct xdp_id_md {
 	int ifindex;
 	__u32 flags;
-	__u32 id;
+	struct xdp_link_info info;
 };
 
-int libbpf_netlink_open(__u32 *nl_pid)
+static int libbpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -37,13 +43,13 @@ int libbpf_netlink_open(__u32 *nl_pid)
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
 
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
 	if (sock < 0)
 		return -errno;
 
 	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
 		       &one, sizeof(one)) < 0) {
-		fprintf(stderr, "Netlink error reporting not supported\n");
+		pr_warn("Netlink error reporting not supported\n");
 	}
 
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
@@ -70,9 +76,20 @@ cleanup:
 	return ret;
 }
 
-static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
-			    void *cookie)
+static void libbpf_netlink_close(int sock)
+{
+	close(sock);
+}
+
+enum {
+	NL_CONT,
+	NL_NEXT,
+	NL_DONE,
+};
+
+static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
+			       void *cookie)
 {
 	bool multipart = true;
 	struct nlmsgerr *err;
@@ -81,6 +98,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 	int len, ret;
 
 	while (multipart) {
+start:
 		multipart = false;
 		len = recv(sock, buf, sizeof(buf), 0);
 		if (len < 0) {
@@ -118,8 +136,16 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			}
 			if (_fn) {
 				ret = _fn(nh, fn, cookie);
-				if (ret)
+				switch (ret) {
+				case NL_CONT:
+					break;
+				case NL_NEXT:
+					goto start;
+				case NL_DONE:
+					return 0;
+				default:
 					return ret;
+				}
 			}
 		}
 	}
@@ -128,65 +154,116 @@ done:
 	return ret;
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
+				    __dump_nlmsg_t parse_msg,
+				    libbpf_dump_nlmsg_t parse_attr,
+				    void *cookie)
 {
-	int sock, seq = 0, ret;
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
+	int sock, ret;
 
 	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
 		return sock;
 
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
+	req->nh.nlmsg_pid = 0;
+	req->nh.nlmsg_seq = time(NULL);
 
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = IFLA_XDP_FD;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_FLAGS;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
-	}
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+	if (send(sock, req, req->nh.nlmsg_len, 0) < 0) {
 		ret = -errno;
-		goto cleanup;
+		goto out;
 	}
-	ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
 
-cleanup:
-	close(sock);
+	ret = libbpf_netlink_recv(sock, nl_pid, req->nh.nlmsg_seq,
+				  parse_msg, parse_attr, cookie);
+out:
+	libbpf_netlink_close(sock);
 	return ret;
 }
 
+static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
+					 __u32 flags)
+{
+	struct nlattr *nla;
+	int ret;
+	struct libbpf_nla_req req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags    = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type     = RTM_SETLINK;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index  = ifindex;
+
+	nla = nlattr_begin_nested(&req, IFLA_XDP);
+	if (!nla)
+		return -EMSGSIZE;
+	ret = nlattr_add(&req, IFLA_XDP_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
+	if (flags) {
+		ret = nlattr_add(&req, IFLA_XDP_FLAGS, &flags, sizeof(flags));
+		if (ret < 0)
+			return ret;
+	}
+	if (flags & XDP_FLAGS_REPLACE) {
+		ret = nlattr_add(&req, IFLA_XDP_EXPECTED_FD, &old_fd,
+				 sizeof(old_fd));
+		if (ret < 0)
+			return ret;
+	}
+	nlattr_end_nested(&req, nla);
+
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+}
+
+int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+	int old_prog_fd, err;
+
+	if (!OPTS_VALID(opts, bpf_xdp_attach_opts))
+		return libbpf_err(-EINVAL);
+
+	old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+	if (old_prog_fd)
+		flags |= XDP_FLAGS_REPLACE;
+	else
+		old_prog_fd = -1;
+
+	err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags);
+	return libbpf_err(err);
+}
+
+int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+	return bpf_xdp_attach(ifindex, -1, flags, opts);
+}
+
+int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+			     const struct bpf_xdp_set_link_opts *opts)
+{
+	int old_fd = -1, ret;
+
+	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
+		return libbpf_err(-EINVAL);
+
+	if (OPTS_HAS(opts, old_fd)) {
+		old_fd = OPTS_GET(opts, old_fd, -1);
+		flags |= XDP_FLAGS_REPLACE;
+	}
+
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags);
+	return libbpf_err(ret);
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	int ret;
+
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+	return libbpf_err(ret);
+}
+
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
@@ -196,32 +273,18 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+
 	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags)
-{
-	if (mode != XDP_ATTACHED_MULTI)
-		return IFLA_XDP_PROG_ID;
-	if (flags & XDP_FLAGS_DRV_MODE)
-		return IFLA_XDP_DRV_PROG_ID;
-	if (flags & XDP_FLAGS_HW_MODE)
-		return IFLA_XDP_HW_PROG_ID;
-	if (flags & XDP_FLAGS_SKB_MODE)
-		return IFLA_XDP_SKB_PROG_ID;
-
-	return IFLA_XDP_UNSPEC;
-}
-
-static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
+static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct nlattr *xdp_tb[IFLA_XDP_MAX + 1];
 	struct xdp_id_md *xdp_id = cookie;
 	struct ifinfomsg *ifinfo = msg;
-	unsigned char mode, xdp_attr;
 	int ret;
 
 	if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index)
@@ -237,186 +300,510 @@ static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
 	if (!xdp_tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]);
-	if (mode == XDP_ATTACHED_NONE)
+	xdp_id->info.attach_mode = libbpf_nla_getattr_u8(
+		xdp_tb[IFLA_XDP_ATTACHED]);
+
+	if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE)
 		return 0;
 
-	xdp_attr = get_xdp_id_attr(mode, xdp_id->flags);
-	if (!xdp_attr || !xdp_tb[xdp_attr])
-		return 0;
+	if (xdp_tb[IFLA_XDP_PROG_ID])
+		xdp_id->info.prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_PROG_ID]);
 
-	xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]);
+	if (xdp_tb[IFLA_XDP_SKB_PROG_ID])
+		xdp_id->info.skb_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_SKB_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_DRV_PROG_ID])
+		xdp_id->info.drv_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_DRV_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_HW_PROG_ID])
+		xdp_id->info.hw_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_HW_PROG_ID]);
 
 	return 0;
 }
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 {
+	struct libbpf_nla_req req = {
+		.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.nh.nlmsg_type     = RTM_GETLINK,
+		.nh.nlmsg_flags    = NLM_F_DUMP | NLM_F_REQUEST,
+		.ifinfo.ifi_family = AF_PACKET,
+	};
 	struct xdp_id_md xdp_id = {};
-	int sock, ret;
-	__u32 nl_pid;
-	__u32 mask;
+	int err;
 
-	if (flags & ~XDP_FLAGS_MASK)
-		return -EINVAL;
+	if (!OPTS_VALID(opts, bpf_xdp_query_opts))
+		return libbpf_err(-EINVAL);
+
+	if (xdp_flags & ~XDP_FLAGS_MASK)
+		return libbpf_err(-EINVAL);
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
-	flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
-	mask = flags - 1;
-	if (flags && flags & mask)
-		return -EINVAL;
-
-	sock = libbpf_netlink_open(&nl_pid);
-	if (sock < 0)
-		return sock;
+	xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE;
+	if (xdp_flags & (xdp_flags - 1))
+		return libbpf_err(-EINVAL);
 
 	xdp_id.ifindex = ifindex;
-	xdp_id.flags = flags;
+	xdp_id.flags = xdp_flags;
 
-	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id);
-	if (!ret)
-		*prog_id = xdp_id.id;
+	err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+				       get_xdp_info, &xdp_id);
+	if (err)
+		return libbpf_err(err);
 
-	close(sock);
+	OPTS_SET(opts, prog_id, xdp_id.info.prog_id);
+	OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id);
+	OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id);
+	OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
+	OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
+
+	return 0;
+}
+
+int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+			  size_t info_size, __u32 flags)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	size_t sz;
+	int err;
+
+	if (!info_size)
+		return libbpf_err(-EINVAL);
+
+	err = bpf_xdp_query(ifindex, flags, &opts);
+	if (err)
+		return libbpf_err(err);
+
+	/* struct xdp_link_info field layout matches struct bpf_xdp_query_opts
+	 * layout after sz field
+	 */
+	sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode));
+	memcpy(info, &opts.prog_id, sz);
+	memset((void *)info + sz, 0, info_size - sz);
+
+	return 0;
+}
+
+int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	int ret;
+
+	ret = bpf_xdp_query(ifindex, flags, &opts);
+	if (ret)
+		return libbpf_err(ret);
+
+	flags &= XDP_FLAGS_MODES;
+
+	if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags)
+		*prog_id = opts.prog_id;
+	else if (flags & XDP_FLAGS_DRV_MODE)
+		*prog_id = opts.drv_prog_id;
+	else if (flags & XDP_FLAGS_HW_MODE)
+		*prog_id = opts.hw_prog_id;
+	else if (flags & XDP_FLAGS_SKB_MODE)
+		*prog_id = opts.skb_prog_id;
+	else
+		*prog_id = 0;
+
+	return 0;
+}
+
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+	return bpf_xdp_query_id(ifindex, flags, prog_id);
+}
+
+typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
+
+static int clsact_config(struct libbpf_nla_req *req)
+{
+	req->tc.tcm_parent = TC_H_CLSACT;
+	req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
+
+	return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact"));
+}
+
+static int attach_point_to_config(struct bpf_tc_hook *hook,
+				  qdisc_config_t *config)
+{
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		if (OPTS_GET(hook, parent, 0))
+			return -EINVAL;
+		*config = &clsact_config;
+		return 0;
+	case BPF_TC_CUSTOM:
+		return -EOPNOTSUPP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point,
+			     __u32 *parent)
+{
+	switch (attach_point) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		if (*parent)
+			return -EINVAL;
+		*parent = TC_H_MAKE(TC_H_CLSACT,
+				    attach_point == BPF_TC_INGRESS ?
+				    TC_H_MIN_INGRESS : TC_H_MIN_EGRESS);
+		break;
+	case BPF_TC_CUSTOM:
+		if (!*parent)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
+{
+	qdisc_config_t config;
+	int ret;
+	struct libbpf_nla_req req;
+
+	ret = attach_point_to_config(hook, &config);
+	if (ret < 0)
+		return ret;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
+	req.nh.nlmsg_type  = cmd;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
+
+	ret = config(&req);
+	if (ret < 0)
+		return ret;
+
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+}
+
+static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE | NLM_F_EXCL);
+}
+
+static int tc_qdisc_delete(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_DELQDISC, 0);
+}
+
+int bpf_tc_hook_create(struct bpf_tc_hook *hook)
+{
+	int ret;
+
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	ret = tc_qdisc_create_excl(hook);
+	return libbpf_err(ret);
+}
+
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush);
+
+int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
+{
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		return libbpf_err(tc_qdisc_delete(hook));
+	case BPF_TC_CUSTOM:
+		return libbpf_err(-EOPNOTSUPP);
+	default:
+		return libbpf_err(-EINVAL);
+	}
+}
+
+struct bpf_cb_ctx {
+	struct bpf_tc_opts *opts;
+	bool processed;
+};
+
+static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb,
+			 bool unicast)
+{
+	struct nlattr *tbb[TCA_BPF_MAX + 1];
+	struct bpf_cb_ctx *info = cookie;
+
+	if (!info || !info->opts)
+		return -EINVAL;
+	if (unicast && info->processed)
+		return -EINVAL;
+	if (!tb[TCA_OPTIONS])
+		return NL_CONT;
+
+	libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL);
+	if (!tbb[TCA_BPF_ID])
+		return -EINVAL;
+
+	OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID]));
+	OPTS_SET(info->opts, handle, tc->tcm_handle);
+	OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16);
+
+	info->processed = true;
+	return unicast ? NL_NEXT : NL_DONE;
+}
+
+static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+		       void *cookie)
+{
+	struct tcmsg *tc = NLMSG_DATA(nh);
+	struct nlattr *tb[TCA_MAX + 1];
+
+	libbpf_nla_parse(tb, TCA_MAX,
+			 (struct nlattr *)((void *)tc + NLMSG_ALIGN(sizeof(*tc))),
+			 NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL);
+	if (!tb[TCA_KIND])
+		return NL_CONT;
+	return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO);
+}
+
+static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	char name[256];
+	int len, ret;
+
+	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (ret < 0)
+		return ret;
+
+	ret = nlattr_add(req, TCA_BPF_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
+	len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id);
+	if (len < 0)
+		return -errno;
+	if (len >= sizeof(name))
+		return -ENAMETOOLONG;
+	return nlattr_add(req, TCA_BPF_NAME, name, len + 1);
+}
+
+int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
+{
+	__u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct libbpf_nla_req req;
+	struct nlattr *nla;
+
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || !prog_fd || prog_id)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+	if (flags & ~BPF_TC_F_REPLACE)
+		return libbpf_err(-EINVAL);
+
+	flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL;
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE |
+			     NLM_F_ECHO | flags;
+	req.nh.nlmsg_type  = RTM_NEWTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nla = nlattr_begin_nested(&req, TCA_OPTIONS);
+	if (!nla)
+		return libbpf_err(-EMSGSIZE);
+	ret = tc_add_fd_and_name(&req, prog_fd);
+	if (ret < 0)
+		return libbpf_err(ret);
+	bpf_flags = TCA_BPF_FLAG_ACT_DIRECT;
+	ret = nlattr_add(&req, TCA_BPF_FLAGS, &bpf_flags, sizeof(bpf_flags));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nlattr_end_nested(&req, nla);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
 	return ret;
 }
 
-int libbpf_nl_get_link(int sock, unsigned int nl_pid,
-		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush)
 {
-	struct {
-		struct nlmsghdr nlh;
-		struct ifinfomsg ifm;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
-		.nlh.nlmsg_type = RTM_GETLINK,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.ifm.ifi_family = AF_PACKET,
-	};
-	int seq = time(NULL);
+	__u32 protocol = 0, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct libbpf_nla_req req;
 
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
-		return -errno;
+	if (!hook ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return -EINVAL;
 
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
-				dump_link_nlmsg, cookie);
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id)
+		return -EINVAL;
+	if (priority > UINT16_MAX)
+		return -EINVAL;
+	if (!flush) {
+		if (!handle || !priority)
+			return -EINVAL;
+		protocol = ETH_P_ALL;
+	} else {
+		if (handle || priority)
+			return -EINVAL;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type  = RTM_DELTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	if (!flush) {
+		req.tc.tcm_handle = handle;
+		req.tc.tcm_info   = TC_H_MAKE(priority << 16, htons(protocol));
+	}
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return ret;
+	req.tc.tcm_parent = parent;
+
+	if (!flush) {
+		ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+		if (ret < 0)
+			return ret;
+	}
+
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
 }
 
-static int __dump_class_nlmsg(struct nlmsghdr *nlh,
-			      libbpf_dump_nlmsg_t dump_class_nlmsg,
-			      void *cookie)
+int bpf_tc_detach(const struct bpf_tc_hook *hook,
+		  const struct bpf_tc_opts *opts)
 {
-	struct nlattr *tb[TCA_MAX + 1], *attr;
-	struct tcmsg *t = NLMSG_DATA(nlh);
-	int len;
+	int ret;
 
-	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
-	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
-		return -LIBBPF_ERRNO__NLPARSE;
+	if (!opts)
+		return libbpf_err(-EINVAL);
 
-	return dump_class_nlmsg(cookie, t, tb);
+	ret = __bpf_tc_detach(hook, opts, false);
+	return libbpf_err(ret);
 }
 
-int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie)
+int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
 {
-	struct {
-		struct nlmsghdr nlh;
-		struct tcmsg t;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
-		.nlh.nlmsg_type = RTM_GETTCLASS,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.t.tcm_family = AF_UNSPEC,
-		.t.tcm_ifindex = ifindex,
-	};
-	int seq = time(NULL);
+	__u32 protocol, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct libbpf_nla_req req;
 
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
-		return -errno;
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
 
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg,
-				dump_class_nlmsg, cookie);
-}
-
-static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
-			      libbpf_dump_nlmsg_t dump_qdisc_nlmsg,
-			      void *cookie)
-{
-	struct nlattr *tb[TCA_MAX + 1], *attr;
-	struct tcmsg *t = NLMSG_DATA(nlh);
-	int len;
-
-	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
-	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
-		return -LIBBPF_ERRNO__NLPARSE;
-
-	return dump_qdisc_nlmsg(cookie, t, tb);
-}
-
-int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
-{
-	struct {
-		struct nlmsghdr nlh;
-		struct tcmsg t;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
-		.nlh.nlmsg_type = RTM_GETQDISC,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.t.tcm_family = AF_UNSPEC,
-		.t.tcm_ifindex = ifindex,
-	};
-	int seq = time(NULL);
-
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
-		return -errno;
-
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg,
-				dump_qdisc_nlmsg, cookie);
-}
-
-static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
-			       libbpf_dump_nlmsg_t dump_filter_nlmsg,
-			       void *cookie)
-{
-	struct nlattr *tb[TCA_MAX + 1], *attr;
-	struct tcmsg *t = NLMSG_DATA(nlh);
-	int len;
-
-	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
-	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
-		return -LIBBPF_ERRNO__NLPARSE;
-
-	return dump_filter_nlmsg(cookie, t, tb);
-}
-
-int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie)
-{
-	struct {
-		struct nlmsghdr nlh;
-		struct tcmsg t;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
-		.nlh.nlmsg_type = RTM_GETTFILTER,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.t.tcm_family = AF_UNSPEC,
-		.t.tcm_ifindex = ifindex,
-		.t.tcm_parent = handle,
-	};
-	int seq = time(NULL);
-
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
-		return -errno;
-
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg,
-				dump_filter_nlmsg, cookie);
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id ||
+	    !handle || !priority)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST;
+	req.nh.nlmsg_type  = RTM_GETTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
+	return ret;
 }

src/nlattr.c

@@ -7,10 +7,11 @@
  */
 
 #include <errno.h>
-#include "nlattr.h"
-#include <linux/rtnetlink.h>
 #include <string.h>
 #include <stdio.h>
+#include <linux/rtnetlink.h>
+#include "nlattr.h"
+#include "libbpf_internal.h"
 
 static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
 	[LIBBPF_NLA_U8]		= sizeof(uint8_t),
@@ -26,7 +27,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
 	int totlen = NLA_ALIGN(nla->nla_len);
 
 	*remaining -= totlen;
-	return (struct nlattr *) ((char *) nla + totlen);
+	return (struct nlattr *)((void *)nla + totlen);
 }
 
 static int nla_ok(const struct nlattr *nla, int remaining)
@@ -121,8 +122,8 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
 		}
 
 		if (tb[type])
-			fprintf(stderr, "Attribute of type %#x found multiple times in message, "
-				  "previous attribute is being ignored.\n", type);
+			pr_warn("Attribute of type %#x found multiple times in message, "
+				"previous attribute is being ignored.\n", type);
 
 		tb[type] = nla;
 	}
@@ -181,15 +182,14 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 
 	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
 			     extack_policy) != 0) {
-		fprintf(stderr,
-			"Failed to parse extended error attributes\n");
+		pr_warn("Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
 		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
-	fprintf(stderr, "Kernel error message: %s\n", errmsg);
+	pr_warn("Kernel error message: %s\n", errmsg);
 
 	return 0;
 }

src/nlattr.h

@@ -10,7 +10,11 @@
 #define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
+#include <string.h>
+#include <errno.h>
 #include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
 /* avoid multiple definition of netlink features */
 #define __LINUX_NETLINK_H
 
@@ -49,6 +53,15 @@ struct libbpf_nla_policy {
 	uint16_t	maxlen;
 };
 
+struct libbpf_nla_req {
+	struct nlmsghdr nh;
+	union {
+		struct ifinfomsg ifinfo;
+		struct tcmsg tc;
+	};
+	char buf[128];
+};
+
 /**
  * @ingroup attr
  * Iterate over a stream of attributes
@@ -68,7 +81,7 @@ struct libbpf_nla_policy {
  */
 static inline void *libbpf_nla_data(const struct nlattr *nla)
 {
-	return (char *) nla + NLA_HDRLEN;
+	return (void *)nla + NLA_HDRLEN;
 }
 
 static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
@@ -103,4 +116,49 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
 
 int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
+static inline struct nlattr *nla_data(struct nlattr *nla)
+{
+	return (struct nlattr *)((void *)nla + NLA_HDRLEN);
+}
+
+static inline struct nlattr *req_tail(struct libbpf_nla_req *req)
+{
+	return (struct nlattr *)((void *)req + NLMSG_ALIGN(req->nh.nlmsg_len));
+}
+
+static inline int nlattr_add(struct libbpf_nla_req *req, int type,
+			     const void *data, int len)
+{
+	struct nlattr *nla;
+
+	if (NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > sizeof(*req))
+		return -EMSGSIZE;
+	if (!!data != !!len)
+		return -EINVAL;
+
+	nla = req_tail(req);
+	nla->nla_type = type;
+	nla->nla_len = NLA_HDRLEN + len;
+	if (data)
+		memcpy(nla_data(nla), data, len);
+	req->nh.nlmsg_len = NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(nla->nla_len);
+	return 0;
+}
+
+static inline struct nlattr *nlattr_begin_nested(struct libbpf_nla_req *req, int type)
+{
+	struct nlattr *tail;
+
+	tail = req_tail(req);
+	if (nlattr_add(req, type | NLA_F_NESTED, NULL, 0))
+		return NULL;
+	return tail;
+}
+
+static inline void nlattr_end_nested(struct libbpf_nla_req *req,
+				     struct nlattr *tail)
+{
+	tail->nla_len = (void *)req_tail(req) - (void *)tail;
+}
+
 #endif /* __LIBBPF_NLATTR_H */

src/relo_core.h

@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2019 Facebook */
+
+#ifndef __RELO_CORE_H
+#define __RELO_CORE_H
+
+#include <linux/bpf.h>
+
+struct bpf_core_cand {
+	const struct btf *btf;
+	__u32 id;
+};
+
+/* dynamically sized list of type IDs and its associated struct btf */
+struct bpf_core_cand_list {
+	struct bpf_core_cand *cands;
+	int len;
+};
+
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+	__u32 type_id;		/* struct/union type or array element type */
+	__u32 idx;		/* field index or array index */
+	const char *name;	/* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+	const struct btf *btf;
+	/* high-level spec: named fields and array indices only */
+	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+	/* original unresolved (no skip_mods_or_typedefs) root type ID */
+	__u32 root_type_id;
+	/* CO-RE relocation kind */
+	enum bpf_core_relo_kind relo_kind;
+	/* high-level spec length */
+	int len;
+	/* raw, low-level spec: 1-to-1 with accessor spec string */
+	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+	/* raw spec length */
+	int raw_len;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
+};
+
+int bpf_core_apply_relo_insn(const char *prog_name,
+			     struct bpf_insn *insn, int insn_idx,
+			     const struct bpf_core_relo *relo, int relo_idx,
+			     const struct btf *local_btf,
+			     struct bpf_core_cand_list *cands,
+			     struct bpf_core_spec *specs_scratch);
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+			      const struct btf *targ_btf, __u32 targ_id);
+
+size_t bpf_core_essential_name_len(const char *name);
+#endif

src/ringbuf.c

@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * Ring buffer operations.
+ *
+ * Copyright (C) 2020 Facebook, Inc.
+ */
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include <asm/barrier.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "bpf.h"
+
+struct ring {
+	ring_buffer_sample_fn sample_cb;
+	void *ctx;
+	void *data;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	unsigned long mask;
+	int map_fd;
+};
+
+struct ring_buffer {
+	struct epoll_event *events;
+	struct ring *rings;
+	size_t page_size;
+	int epoll_fd;
+	int ring_cnt;
+};
+
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
+{
+	if (r->consumer_pos) {
+		munmap(r->consumer_pos, rb->page_size);
+		r->consumer_pos = NULL;
+	}
+	if (r->producer_pos) {
+		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
+		r->producer_pos = NULL;
+	}
+}
+
+/* Add extra RINGBUF maps to this ring buffer manager */
+int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+		     ring_buffer_sample_fn sample_cb, void *ctx)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	struct epoll_event *e;
+	struct ring *r;
+	void *tmp;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
+			map_fd, err);
+		return libbpf_err(err);
+	}
+
+	if (info.type != BPF_MAP_TYPE_RINGBUF) {
+		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
+			map_fd);
+		return libbpf_err(-EINVAL);
+	}
+
+	tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
+	if (!tmp)
+		return libbpf_err(-ENOMEM);
+	rb->rings = tmp;
+
+	tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
+	if (!tmp)
+		return libbpf_err(-ENOMEM);
+	rb->events = tmp;
+
+	r = &rb->rings[rb->ring_cnt];
+	memset(r, 0, sizeof(*r));
+
+	r->map_fd = map_fd;
+	r->sample_cb = sample_cb;
+	r->ctx = ctx;
+	r->mask = info.max_entries - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return libbpf_err(err);
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. We map twice as big
+	 * data size to allow simple reading of samples that wrap around the
+	 * end of a ring buffer. See kernel implementation for details.
+	 * */
+	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
+		   MAP_SHARED, map_fd, rb->page_size);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
+		return libbpf_err(err);
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + rb->page_size;
+
+	e = &rb->events[rb->ring_cnt];
+	memset(e, 0, sizeof(*e));
+
+	e->events = EPOLLIN;
+	e->data.fd = rb->ring_cnt;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
+			map_fd, err);
+		return libbpf_err(err);
+	}
+
+	rb->ring_cnt++;
+	return 0;
+}
+
+void ring_buffer__free(struct ring_buffer *rb)
+{
+	int i;
+
+	if (!rb)
+		return;
+
+	for (i = 0; i < rb->ring_cnt; ++i)
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb->events);
+	free(rb->rings);
+	free(rb);
+}
+
+struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts)
+{
+	struct ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, ring_buffer_opts))
+		return errno = EINVAL, NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return errno = ENOMEM, NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = ring_buffer__add(rb, map_fd, sample_cb, ctx);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	ring_buffer__free(rb);
+	return errno = -err, NULL;
+}
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits (discard and busy, if set) */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += BPF_RINGBUF_HDR_SZ;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;
+}
+
+static int64_t ringbuf_process_ring(struct ring* r)
+{
+	int *len_ptr, len, err;
+	/* 64-bit to avoid overflow in case of extreme application behavior */
+	int64_t cnt = 0;
+	unsigned long cons_pos, prod_pos;
+	bool got_new_data;
+	void *sample;
+
+	cons_pos = smp_load_acquire(r->consumer_pos);
+	do {
+		got_new_data = false;
+		prod_pos = smp_load_acquire(r->producer_pos);
+		while (cons_pos < prod_pos) {
+			len_ptr = r->data + (cons_pos & r->mask);
+			len = smp_load_acquire(len_ptr);
+
+			/* sample not committed yet, bail out for now */
+			if (len & BPF_RINGBUF_BUSY_BIT)
+				goto done;
+
+			got_new_data = true;
+			cons_pos += roundup_len(len);
+
+			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
+				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
+				err = r->sample_cb(r->ctx, sample, len);
+				if (err < 0) {
+					/* update consumer pos and bail out */
+					smp_store_release(r->consumer_pos,
+							  cons_pos);
+					return err;
+				}
+				cnt++;
+			}
+
+			smp_store_release(r->consumer_pos, cons_pos);
+		}
+	} while (got_new_data);
+done:
+	return cnt;
+}
+
+/* Consume available ring buffer(s) data without event polling.
+ * Returns number of records consumed across all registered ring buffers (or
+ * INT_MAX, whichever is less), or negative number if any of the callbacks
+ * return error.
+ */
+int ring_buffer__consume(struct ring_buffer *rb)
+{
+	int64_t err, res = 0;
+	int i;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = &rb->rings[i];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return libbpf_err(err);
+		res += err;
+	}
+	if (res > INT_MAX)
+		return INT_MAX;
+	return res;
+}
+
+/* Poll for available data and consume records, if any are available.
+ * Returns number of records consumed (or INT_MAX, whichever is less), or
+ * negative number, if any of the registered callbacks returned error.
+ */
+int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
+{
+	int i, cnt;
+	int64_t err, res = 0;
+
+	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
+	if (cnt < 0)
+		return libbpf_err(-errno);
+
+	for (i = 0; i < cnt; i++) {
+		__u32 ring_id = rb->events[i].data.fd;
+		struct ring *ring = &rb->rings[ring_id];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return libbpf_err(err);
+		res += err;
+	}
+	if (res > INT_MAX)
+		return INT_MAX;
+	return res;
+}
+
+/* Get an fd that can be used to sleep until data is available in the ring(s) */
+int ring_buffer__epoll_fd(const struct ring_buffer *rb)
+{
+	return rb->epoll_fd;
+}

src/skel_internal.h

@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __SKEL_INTERNAL_H
+#define __SKEL_INTERNAL_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+
+#ifndef __NR_bpf
+# if defined(__mips__) && defined(_ABIO32)
+#  define __NR_bpf 4355
+# elif defined(__mips__) && defined(_ABIN32)
+#  define __NR_bpf 6319
+# elif defined(__mips__) && defined(_ABI64)
+#  define __NR_bpf 5315
+# endif
+#endif
+
+/* This file is a base header for auto-generated *.lskel.h files.
+ * Its contents will change and may become part of auto-generation in the future.
+ *
+ * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent
+ * and will change from one version of libbpf to another and features
+ * requested during loader program generation.
+ */
+struct bpf_map_desc {
+	union {
+		/* input for the loader prog */
+		struct {
+			__aligned_u64 initial_value;
+			__u32 max_entries;
+		};
+		/* output of the loader prog */
+		struct {
+			int map_fd;
+		};
+	};
+};
+struct bpf_prog_desc {
+	int prog_fd;
+};
+
+struct bpf_loader_ctx {
+	size_t sz;
+	__u32 log_level;
+	__u32 log_size;
+	__u64 log_buf;
+};
+
+struct bpf_load_and_run_opts {
+	struct bpf_loader_ctx *ctx;
+	const void *data;
+	const void *insns;
+	__u32 data_sz;
+	__u32 insns_sz;
+	const char *errstr;
+};
+
+static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+			  unsigned int size)
+{
+	return syscall(__NR_bpf, cmd, attr, size);
+}
+
+static inline int skel_closenz(int fd)
+{
+	if (fd > 0)
+		return close(fd);
+	return -EINVAL;
+}
+
+#ifndef offsetofend
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER)	+ sizeof((((TYPE *)0)->MEMBER)))
+#endif
+
+static inline int skel_map_create(enum bpf_map_type map_type,
+				  const char *map_name,
+				  __u32 key_size,
+				  __u32 value_size,
+				  __u32 max_entries)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+
+	attr.map_type = map_type;
+	strncpy(attr.map_name, map_name, sizeof(attr.map_name));
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+
+	return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz);
+}
+
+static inline int skel_map_update_elem(int fd, const void *key,
+				       const void *value, __u64 flags)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long) key;
+	attr.value = (long) value;
+	attr.flags = flags;
+
+	return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
+}
+
+static inline int skel_raw_tracepoint_open(const char *name, int prog_fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.raw_tracepoint.name = (long) name;
+	attr.raw_tracepoint.prog_fd = prog_fd;
+
+	return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
+}
+
+static inline int skel_link_create(int prog_fd, int target_fd,
+				   enum bpf_attach_type attach_type)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.link_create.prog_fd = prog_fd;
+	attr.link_create.target_fd = target_fd;
+	attr.link_create.attach_type = attach_type;
+
+	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
+}
+
+static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
+{
+	int map_fd = -1, prog_fd = -1, key = 0, err;
+	union bpf_attr attr;
+
+	map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
+	if (map_fd < 0) {
+		opts->errstr = "failed to create loader map";
+		err = -errno;
+		goto out;
+	}
+
+	err = skel_map_update_elem(map_fd, &key, opts->data, 0);
+	if (err < 0) {
+		opts->errstr = "failed to update loader map";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
+	attr.insns = (long) opts->insns;
+	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
+	attr.license = (long) "Dual BSD/GPL";
+	memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
+	attr.fd_array = (long) &map_fd;
+	attr.log_level = opts->ctx->log_level;
+	attr.log_size = opts->ctx->log_size;
+	attr.log_buf = opts->ctx->log_buf;
+	attr.prog_flags = BPF_F_SLEEPABLE;
+	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	if (prog_fd < 0) {
+		opts->errstr = "failed to load loader prog";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.ctx_in = (long) opts->ctx;
+	attr.test.ctx_size_in = opts->ctx->sz;
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	if (err < 0 || (int)attr.test.retval < 0) {
+		opts->errstr = "failed to execute loader prog";
+		if (err < 0) {
+			err = -errno;
+		} else {
+			err = (int)attr.test.retval;
+			errno = -err;
+		}
+		goto out;
+	}
+	err = 0;
+out:
+	if (map_fd >= 0)
+		close(map_fd);
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return err;
+}
+
+#endif

src/str_error.c

@@ -4,6 +4,9 @@
 #include <stdio.h>
 #include "str_error.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 /*
  * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
  * libc, while checking strerror_r() return to avoid having to check this in
@@ -11,7 +14,7 @@
  */
 char *libbpf_strerror_r(int err, char *dst, int len)
 {
-	int ret = strerror_r(err, dst, len);
+	int ret = strerror_r(err < 0 ? -err : err, dst, len);
 	if (ret)
 		snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
 	return dst;

src/strset.c

@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+#include "libbpf_internal.h"
+#include "strset.h"
+
+struct strset {
+	void *strs_data;
+	size_t strs_data_len;
+	size_t strs_data_cap;
+	size_t strs_data_max_len;
+
+	/* lookup index for each unique string in strings set */
+	struct hashmap *strs_hash;
+};
+
+static size_t strset_hash_fn(const void *key, void *ctx)
+{
+	const struct strset *s = ctx;
+	const char *str = s->strs_data + (long)key;
+
+	return str_hash(str);
+}
+
+static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
+{
+	const struct strset *s = ctx;
+	const char *str1 = s->strs_data + (long)key1;
+	const char *str2 = s->strs_data + (long)key2;
+
+	return strcmp(str1, str2) == 0;
+}
+
+struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz)
+{
+	struct strset *set = calloc(1, sizeof(*set));
+	struct hashmap *hash;
+	int err = -ENOMEM;
+
+	if (!set)
+		return ERR_PTR(-ENOMEM);
+
+	hash = hashmap__new(strset_hash_fn, strset_equal_fn, set);
+	if (IS_ERR(hash))
+		goto err_out;
+
+	set->strs_data_max_len = max_data_sz;
+	set->strs_hash = hash;
+
+	if (init_data) {
+		long off;
+
+		set->strs_data = malloc(init_data_sz);
+		if (!set->strs_data)
+			goto err_out;
+
+		memcpy(set->strs_data, init_data, init_data_sz);
+		set->strs_data_len = init_data_sz;
+		set->strs_data_cap = init_data_sz;
+
+		for (off = 0; off < set->strs_data_len; off += strlen(set->strs_data + off) + 1) {
+			/* hashmap__add() returns EEXIST if string with the same
+			 * content already is in the hash map
+			 */
+			err = hashmap__add(hash, (void *)off, (void *)off);
+			if (err == -EEXIST)
+				continue; /* duplicate */
+			if (err)
+				goto err_out;
+		}
+	}
+
+	return set;
+err_out:
+	strset__free(set);
+	return ERR_PTR(err);
+}
+
+void strset__free(struct strset *set)
+{
+	if (IS_ERR_OR_NULL(set))
+		return;
+
+	hashmap__free(set->strs_hash);
+	free(set->strs_data);
+	free(set);
+}
+
+size_t strset__data_size(const struct strset *set)
+{
+	return set->strs_data_len;
+}
+
+const char *strset__data(const struct strset *set)
+{
+	return set->strs_data;
+}
+
+static void *strset_add_str_mem(struct strset *set, size_t add_sz)
+{
+	return libbpf_add_mem(&set->strs_data, &set->strs_data_cap, 1,
+			      set->strs_data_len, set->strs_data_max_len, add_sz);
+}
+
+/* Find string offset that corresponds to a given string *s*.
+ * Returns:
+ *   - >0 offset into string data, if string is found;
+ *   - -ENOENT, if string is not in the string data;
+ *   - <0, on any other error.
+ */
+int strset__find_str(struct strset *set, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+
+	/* see strset__add_str() for why we do this */
+	len = strlen(s) + 1;
+	p = strset_add_str_mem(set, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = set->strs_data_len;
+	memcpy(p, s, len);
+
+	if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
+		return old_off;
+
+	return -ENOENT;
+}
+
+/* Add a string s to the string data. If the string already exists, return its
+ * offset within string data.
+ * Returns:
+ *   - > 0 offset into string data, on success;
+ *   - < 0, on error.
+ */
+int strset__add_str(struct strset *set, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+	int err;
+
+	/* Hashmap keys are always offsets within set->strs_data, so to even
+	 * look up some string from the "outside", we need to first append it
+	 * at the end, so that it can be addressed with an offset. Luckily,
+	 * until set->strs_data_len is incremented, that string is just a piece
+	 * of garbage for the rest of the code, so no harm, no foul. On the
+	 * other hand, if the string is unique, it's already appended and
+	 * ready to be used, only a simple set->strs_data_len increment away.
+	 */
+	len = strlen(s) + 1;
+	p = strset_add_str_mem(set, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = set->strs_data_len;
+	memcpy(p, s, len);
+
+	/* Now attempt to add the string, but only if the string with the same
+	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
+	 * string exists, we'll get its offset in old_off (that's old_key).
+	 */
+	err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
+			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	if (err == -EEXIST)
+		return old_off; /* duplicated string, return existing offset */
+	if (err)
+		return err;
+
+	set->strs_data_len += len; /* new unique string, adjust data length */
+	return new_off;
+}

src/strset.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/* Copyright (c) 2021 Facebook */
+#ifndef __LIBBPF_STRSET_H
+#define __LIBBPF_STRSET_H
+
+#include <stdbool.h>
+#include <stddef.h>
+
+struct strset;
+
+struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz);
+void strset__free(struct strset *set);
+
+const char *strset__data(const struct strset *set);
+size_t strset__data_size(const struct strset *set);
+
+int strset__find_str(struct strset *set, const char *s);
+int strset__add_str(struct strset *set, const char *s);
+
+#endif /* __LIBBPF_STRSET_H */

src/xsk.h

@@ -3,7 +3,8 @@
 /*
  * AF_XDP user-space access library.
  *
- * Copyright(c) 2018 - 2019 Intel Corporation.
+ * Copyright (c) 2018 - 2019 Intel Corporation.
+ * Copyright (c) 2019 Facebook
  *
  * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
  */
@@ -13,15 +14,86 @@
 
 #include <stdio.h>
 #include <stdint.h>
+#include <stdbool.h>
 #include <linux/if_xdp.h>
 
 #include "libbpf.h"
-#include "libbpf_util.h"
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+/* This whole API has been deprecated and moved to libxdp that can be found at
+ * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
+ * it should just be linking with libxdp instead of libbpf for this set of
+ * functionality. If not, please submit a bug report on the aforementioned page.
+ */
+
+/* Load-Acquire Store-Release barriers used by the XDP socket
+ * library. The following macros should *NOT* be considered part of
+ * the xsk.h API, and is subject to change anytime.
+ *
+ * LIBRARY INTERNAL
+ */
+
+#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x)
+#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v)
+
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_store_release(p, v)					\
+	do {								\
+		asm volatile("" : : : "memory");			\
+		__XSK_WRITE_ONCE(*p, v);				\
+	} while (0)
+# define libbpf_smp_load_acquire(p)					\
+	({								\
+		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
+		asm volatile("" : : : "memory");			\
+		___p1;							\
+	})
+#elif defined(__aarch64__)
+# define libbpf_smp_store_release(p, v)					\
+		asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
+# define libbpf_smp_load_acquire(p)					\
+	({								\
+		typeof(*p) ___p1;					\
+		asm volatile ("ldar %w0, %1"				\
+			      : "=r" (___p1) : "Q" (*p) : "memory");	\
+		___p1;							\
+	})
+#elif defined(__riscv)
+# define libbpf_smp_store_release(p, v)					\
+	do {								\
+		asm volatile ("fence rw,w" : : : "memory");		\
+		__XSK_WRITE_ONCE(*p, v);				\
+	} while (0)
+# define libbpf_smp_load_acquire(p)					\
+	({								\
+		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
+		asm volatile ("fence r,rw" : : : "memory");		\
+		___p1;							\
+	})
+#endif
+
+#ifndef libbpf_smp_store_release
+#define libbpf_smp_store_release(p, v)					\
+	do {								\
+		__sync_synchronize();					\
+		__XSK_WRITE_ONCE(*p, v);				\
+	} while (0)
+#endif
+
+#ifndef libbpf_smp_load_acquire
+#define libbpf_smp_load_acquire(p)					\
+	({								\
+		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
+		__sync_synchronize();					\
+		___p1;							\
+	})
+#endif
+
+/* LIBRARY INTERNAL -- END */
+
 /* Do not access these members directly. Use the functions below. */
 #define DEFINE_XSK_RING(name) \
 struct name { \
@@ -32,6 +104,7 @@ struct name { \
 	__u32 *producer; \
 	__u32 *consumer; \
 	void *ring; \
+	__u32 *flags; \
 }
 
 DEFINE_XSK_RING(xsk_ring_prod);
@@ -76,6 +149,11 @@ xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx)
 	return &descs[idx & rx->mask];
 }
 
+static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r)
+{
+	return *r->flags & XDP_RING_NEED_WAKEUP;
+}
+
 static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
 {
 	__u32 free_entries = r->cached_cons - r->cached_prod;
@@ -90,7 +168,8 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
 	 * this function. Without this optimization it whould have been
 	 * free_entries = r->cached_prod - r->cached_cons + r->size.
 	 */
-	r->cached_cons = *r->consumer + r->size;
+	r->cached_cons = libbpf_smp_load_acquire(r->consumer);
+	r->cached_cons += r->size;
 
 	return r->cached_cons - r->cached_prod;
 }
@@ -100,15 +179,14 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
 	__u32 entries = r->cached_prod - r->cached_cons;
 
 	if (entries == 0) {
-		r->cached_prod = *r->producer;
+		r->cached_prod = libbpf_smp_load_acquire(r->producer);
 		entries = r->cached_prod - r->cached_cons;
 	}
 
 	return (entries > nb) ? nb : entries;
 }
 
-static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
-					    size_t nb, __u32 *idx)
+static inline __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx)
 {
 	if (xsk_prod_nb_free(prod, nb) < nb)
 		return 0;
@@ -119,27 +197,19 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
 	return nb;
 }
 
-static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
+static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
 {
 	/* Make sure everything has been written to the ring before indicating
 	 * this to the kernel by writing the producer pointer.
 	 */
-	libbpf_smp_wmb();
-
-	*prod->producer += nb;
+	libbpf_smp_store_release(prod->producer, *prod->producer + nb);
 }
 
-static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
-					 size_t nb, __u32 *idx)
+static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
 {
-	size_t entries = xsk_cons_nb_avail(cons, nb);
+	__u32 entries = xsk_cons_nb_avail(cons, nb);
 
 	if (entries > 0) {
-		/* Make sure we do not speculatively read the data before
-		 * we have received the packet buffers from the ring.
-		 */
-		libbpf_smp_rmb();
-
 		*idx = cons->cached_cons;
 		cons->cached_cons += entries;
 	}
@@ -147,14 +217,18 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
 	return entries;
 }
 
-static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
+static inline void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb)
+{
+	cons->cached_cons -= nb;
+}
+
+static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
 {
 	/* Make sure data has been read before indicating we are done
 	 * with the entries by updating the consumer pointer.
 	 */
-	libbpf_smp_rwmb();
+	libbpf_smp_store_release(cons->consumer, *cons->consumer + nb);
 
-	*cons->consumer += nb;
 }
 
 static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
@@ -162,22 +236,46 @@ static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
 	return &((char *)umem_area)[addr];
 }
 
-LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
-LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+static inline __u64 xsk_umem__extract_addr(__u64 addr)
+{
+	return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+}
+
+static inline __u64 xsk_umem__extract_offset(__u64 addr)
+{
+	return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
+}
+
+static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
+{
+	return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
+}
+
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
-#define XSK_UMEM__DEFAULT_FRAME_SHIFT    11 /* 2048 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT    12 /* 4096 bytes */
 #define XSK_UMEM__DEFAULT_FRAME_SIZE     (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
 #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
+#define XSK_UMEM__DEFAULT_FLAGS 0
 
 struct xsk_umem_config {
 	__u32 fill_size;
 	__u32 comp_size;
 	__u32 frame_size;
 	__u32 frame_headroom;
+	__u32 flags;
 };
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
+
 /* Flags for the libbpf_flags field. */
 #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
 
@@ -190,21 +288,46 @@ struct xsk_socket_config {
 };
 
 /* Set config to NULL to get the default configuration. */
-LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
-				void *umem_area, __u64 size,
-				struct xsk_ring_prod *fill,
-				struct xsk_ring_cons *comp,
-				const struct xsk_umem_config *config);
-LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
-				  const char *ifname, __u32 queue_id,
-				  struct xsk_umem *umem,
-				  struct xsk_ring_cons *rx,
-				  struct xsk_ring_prod *tx,
-				  const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create(struct xsk_umem **umem,
+		     void *umem_area, __u64 size,
+		     struct xsk_ring_prod *fill,
+		     struct xsk_ring_cons *comp,
+		     const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create(struct xsk_socket **xsk,
+		       const char *ifname, __u32 queue_id,
+		       struct xsk_umem *umem,
+		       struct xsk_ring_cons *rx,
+		       struct xsk_ring_prod *tx,
+		       const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
+			      const char *ifname,
+			      __u32 queue_id, struct xsk_umem *umem,
+			      struct xsk_ring_cons *rx,
+			      struct xsk_ring_prod *tx,
+			      struct xsk_ring_prod *fill,
+			      struct xsk_ring_cons *comp,
+			      const struct xsk_socket_config *config);
 
 /* Returns 0 for success and -EBUSY if the umem is still in use. */
-LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
-LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+void xsk_socket__delete(struct xsk_socket *xsk);
 
 #ifdef __cplusplus
 } /* extern "C" */

travis-ci/diffs/001-fix-oob-write-in-test_verifier.diff

@@ -0,0 +1,35 @@
+From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
+To: bpf@vger.kernel.org
+Cc: Alexei Starovoitov <ast@kernel.org>,
+	Daniel Borkmann <daniel@iogearbox.net>,
+	Andrii Nakryiko <andrii@kernel.org>
+Subject: [PATCH bpf-next] selftests/bpf: Fix OOB write in test_verifier
+Date: Tue, 14 Dec 2021 07:18:00 +0530	[thread overview]
+Message-ID: <20211214014800.78762-1-memxor@gmail.com> (raw)
+
+The commit referenced below added fixup_map_timer support (to create a
+BPF map containing timers), but failed to increase the size of the
+map_fds array, leading to out of bounds write. Fix this by changing
+MAX_NR_MAPS to 22.
+
+Fixes: e60e6962c503 ("selftests/bpf: Add tests for restricted helpers")
+Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
+---
+ tools/testing/selftests/bpf/test_verifier.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
+index ad5d30bafd93..33e2ecb3bef9 100644
+--- a/tools/testing/selftests/bpf/test_verifier.c
++++ b/tools/testing/selftests/bpf/test_verifier.c
+@@ -54,7 +54,7 @@
+ #define MAX_INSNS	BPF_MAXINSNS
+ #define MAX_TEST_INSNS	1000000
+ #define MAX_FIXUPS	8
+-#define MAX_NR_MAPS	21
++#define MAX_NR_MAPS	22
+ #define MAX_TEST_RUNS	8
+ #define POINTER_VALUE	0xcafe4all
+ #define TEST_DATA_LEN	64
+--
+2.34.1

travis-ci/managers/debian.sh

@@ -2,22 +2,26 @@
 
 PHASES=(${@:-SETUP RUN RUN_ASAN CLEANUP})
 DEBIAN_RELEASE="${DEBIAN_RELEASE:-testing}"
-CONT_NAME="${CONT_NAME:-debian-$DEBIAN_RELEASE-$RANDOM}"
+CONT_NAME="${CONT_NAME:-libbpf-debian-$DEBIAN_RELEASE}"
 ENV_VARS="${ENV_VARS:-}"
 DOCKER_RUN="${DOCKER_RUN:-docker run}"
 REPO_ROOT="${REPO_ROOT:-$PWD}"
-ADDITIONAL_DEPS=(clang pkg-config gcc-8)
+ADDITIONAL_DEPS=(clang pkg-config gcc-10)
 CFLAGS="-g -O2 -Werror -Wall"
 
 function info() {
     echo -e "\033[33;1m$1\033[0m"
 }
 
-function docker_exec() {
-    docker exec $ENV_VARS -it $CONT_NAME "$@"
+function error() {
+    echo -e "\033[31;1m$1\033[0m"
 }
 
-set -e
+function docker_exec() {
+    docker exec $ENV_VARS $CONT_NAME "$@"
+}
+
+set -eu
 
 source "$(dirname $0)/travis_wait.bash"
 
@@ -26,43 +30,52 @@ for phase in "${PHASES[@]}"; do
         SETUP)
             info "Setup phase"
             info "Using Debian $DEBIAN_RELEASE"
-	    docker pull debian:$DEBIAN_RELEASE
+
+            docker --version
+
+            docker pull debian:$DEBIAN_RELEASE
             info "Starting container $CONT_NAME"
             $DOCKER_RUN -v $REPO_ROOT:/build:rw \
                         -w /build --privileged=true --name $CONT_NAME \
-			-dit --net=host debian:$DEBIAN_RELEASE /bin/bash
+                        -dit --net=host debian:$DEBIAN_RELEASE /bin/bash
+            echo -e "::group::Build Env Setup"
             docker_exec bash -c "echo deb-src http://deb.debian.org/debian $DEBIAN_RELEASE main >>/etc/apt/sources.list"
             docker_exec apt-get -y update
-            docker_exec apt-get -y build-dep libelf-dev
-            docker_exec apt-get -y install libelf-dev
-            docker_exec apt-get -y install "${ADDITIONAL_DEPS[@]}"
+            docker_exec apt-get -y install aptitude
+            docker_exec aptitude -y build-dep libelf-dev
+            docker_exec aptitude -y install libelf-dev
+            docker_exec aptitude -y install "${ADDITIONAL_DEPS[@]}"
+            echo -e "::endgroup::"
             ;;
-        RUN|RUN_CLANG|RUN_GCC8)
-            if [[ "$phase" = "RUN_CLANG" ]]; then
+        RUN|RUN_CLANG|RUN_GCC10|RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC10_ASAN)
+            CC="cc"
+            if [[ "$phase" = *"CLANG"* ]]; then
                 ENV_VARS="-e CC=clang -e CXX=clang++"
                 CC="clang"
-            elif [[ "$phase" = "RUN_GCC8" ]]; then
-                ENV_VARS="-e CC=gcc-8 -e CXX=g++-8"
-                CC="gcc-8"
+            elif [[ "$phase" = *"GCC10"* ]]; then
+                ENV_VARS="-e CC=gcc-10 -e CXX=g++-10"
+                CC="gcc-10"
+                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
+            else
+                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
             fi
-            docker_exec mkdir build
-            docker_exec ${CC:-cc} --version
-            docker_exec make CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
-            docker_exec rm -rf build
-            ;;
-        RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC8_ASAN)
-            if [[ "$phase" = "RUN_CLANG_ASAN" ]]; then
-                ENV_VARS="-e CC=clang -e CXX=clang++"
-                CC="clang"
-            elif [[ "$phase" = "RUN_GCC8_ASAN" ]]; then
-                ENV_VARS="-e CC=gcc-8 -e CXX=g++-8"
-                CC="gcc-8"
+            if [[ "$phase" = *"ASAN"* ]]; then
+                CFLAGS="${CFLAGS} -fsanitize=address,undefined"
             fi
-            CFLAGS="${CFLAGS} -fsanitize=address,undefined"
-            docker_exec mkdir build
-            docker_exec ${CC:-cc} --version
-            docker_exec make CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
-            docker_exec rm -rf build
+            docker_exec mkdir build install
+            docker_exec ${CC} --version
+            info "build"
+            docker_exec make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+            info "ldd build/libbpf.so:"
+            docker_exec ldd build/libbpf.so
+            if ! docker_exec ldd build/libbpf.so | grep -q libelf; then
+                error "No reference to libelf.so in libbpf.so!"
+                exit 1
+            fi
+            info "install"
+            docker_exec make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
+            info "link binary"
+            docker_exec bash -c "CFLAGS=\"${CFLAGS}\" ./travis-ci/managers/test_compile.sh"
             ;;
         CLEANUP)
             info "Cleanup phase"

travis-ci/managers/test_compile.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+set -euox pipefail
+
+CFLAGS=${CFLAGS:-}
+
+cat << EOF > main.c
+#include <bpf/libbpf.h>
+int main() {
+  return bpf_object__open(0) < 0;
+}
+EOF
+
+# static linking
+${CC:-cc} ${CFLAGS} -o main -I./install/usr/include main.c ./build/libbpf.a -lelf -lz

travis-ci/managers/ubuntu.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+set -eux
+
+RELEASE="focal"
+
+apt-get update
+apt-get install -y pkg-config
+
+source "$(dirname $0)/travis_wait.bash"
+
+cd $REPO_ROOT
+
+CFLAGS="-g -O2 -Werror -Wall -fsanitize=address,undefined -Wno-stringop-truncation"
+mkdir build install
+cc --version
+make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+ldd build/libbpf.so
+if ! ldd build/libbpf.so | grep -q libelf; then
+    echo "FAIL: No reference to libelf.so in libbpf.so!"
+    exit 1
+fi
+make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
+CFLAGS=${CFLAGS} $(dirname $0)/test_compile.sh

travis-ci/managers/xenial.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-set -e
-set -x
-
-apt-get update
-apt-get -y build-dep libelf-dev
-apt-get install -y libelf-dev
-
-source "$(dirname $0)/travis_wait.bash"
-
-cd $REPO_ROOT
-
-CFLAGS="-g -O2 -Werror -Wall -fsanitize=address,undefined"
-mkdir build
-cc --version
-make CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
-rm -rf build

travis-ci/rootfs/mkrootfs_arch.sh

@@ -0,0 +1,106 @@
+#!/bin/bash
+
+# This script is based on drgn script for generating Arch Linux bootstrap
+# images.
+# https://github.com/osandov/drgn/blob/master/scripts/vmtest/mkrootfs.sh
+
+set -euo pipefail
+
+usage () {
+	USAGE_STRING="usage: $0 [NAME]
+       $0 -h
+
+Build an Arch Linux root filesystem image for testing libbpf in a virtual
+machine.
+
+The image is generated as a zstd-compressed tarball.
+
+This must be run as root, as most of the installation is done in a chroot.
+
+Arguments:
+  NAME   name of generated image file (default:
+         libbpf-vmtest-rootfs-\$DATE.tar.zst)
+
+Options:
+  -h     display this help message and exit"
+
+	case "$1" in
+		out)
+			echo "$USAGE_STRING"
+			exit 0
+			;;
+		err)
+			echo "$USAGE_STRING" >&2
+			exit 1
+			;;
+	esac
+}
+
+while getopts "h" OPT; do
+	case "$OPT" in
+		h)
+			usage out
+			;;
+		*)
+			usage err
+			;;
+	esac
+done
+if [[ $OPTIND -eq $# ]]; then
+	NAME="${!OPTIND}"
+elif [[ $OPTIND -gt $# ]]; then
+	NAME="libbpf-vmtest-rootfs-$(date +%Y.%m.%d).tar.zst"
+else
+	usage err
+fi
+
+pacman_conf=
+root=
+trap 'rm -rf "$pacman_conf" "$root"' EXIT
+pacman_conf="$(mktemp -p "$PWD")"
+cat > "$pacman_conf" << "EOF"
+[options]
+Architecture = x86_64
+CheckSpace
+SigLevel = Required DatabaseOptional
+[core]
+Include = /etc/pacman.d/mirrorlist
+[extra]
+Include = /etc/pacman.d/mirrorlist
+[community]
+Include = /etc/pacman.d/mirrorlist
+EOF
+root="$(mktemp -d -p "$PWD")"
+
+packages=(
+	busybox
+	# libbpf dependencies.
+	libelf
+	zlib
+	# selftests test_progs dependencies.
+	binutils
+	elfutils
+	glibc
+	iproute2
+	# selftests test_verifier dependencies.
+	libcap
+)
+
+pacstrap -C "$pacman_conf" -cGM "$root" "${packages[@]}"
+
+# Remove unnecessary files from the chroot.
+
+# We don't need the pacman databases anymore.
+rm -rf "$root/var/lib/pacman/sync/"
+# We don't need D, Fortran, or Go.
+ rm -f "$root/usr/lib/libgdruntime."* \
+	"$root/usr/lib/libgphobos."* \
+	"$root/usr/lib/libgfortran."* \
+	"$root/usr/lib/libgo."*
+# We don't need any documentation.
+rm -rf "$root/usr/share/{doc,help,man,texinfo}"
+
+"$(dirname "$0")"/mkrootfs_tweak.sh "$root"
+
+tar -C "$root" -c . | zstd -T0 -19 -o "$NAME"
+chmod 644 "$NAME"